diff --git a/Changelog.yaml b/Changelog.yaml index 6ba9bdd5e4..652333d897 100644 --- a/Changelog.yaml +++ b/Changelog.yaml @@ -19,6 +19,66 @@ # new recipes: # - title: +- version: 0.8.7 + date: 2011-06-24 + + new features: + - title: "Connect to iTunes: You now need to tell iTunes to keep its own copy of every ebook. Do this in iTunes by going to Preferences->Advanced and setting the 'Copy files to iTunes Media folder when adding to library' option. To learn about why this is necessary, see: http://www.mobileread.com/forums/showthread.php?t=140260" + type: major + + - title: "Add a couple of date related functions to the calibre template langauge to get 'todays' date and create text based on the value of a date type field" + + - title: "Improved reading of metadata from FB2 files, with support for reading isbns, tags, published date, etc." + + - title: "Driver for the Imagine IMEB5" + tickets: [800642] + + - title: "Show the currently used network proxies in Preferences->Miscellaneous" + + - title: "Kobo Touch driver: Show Favorites as a device collection. Various other minor fixes." + + - title: "Content server now sends the Content-Disposition header when sending ebook files." + + - title: "Allow search and replace on comments custom columns." + + - title: "Add a new action 'Quick View' to show the books in your library by the author/tags/series/etc. of the currently selected book, in a separate window. You can add it to your toolbar or right click menu by going to Preferences->Toolbars." + + - title: "Get Books: Add libri.de as a book source. Fix a bug that caused some books downloads to fail. Fixes to the Legimi and beam-ebooks.de stores" + tickets: [799367] + + bug fixes: + - title: "Fix a memory leak that could result in the leaking of several MB of memory with large libraries" + tickets: [800952] + + - title: "Fix the read metadata from format button in the edit metadata dialog using the wrong timezone when setting published date" + tickets: [799777] + + - title: "Generating catalog: Fix occassional file in use errors when generating catalogs on windows" + + - title: "Fix clicking on News in Tag Browser not working in non English locales." + tickets: [799471] + + - title: "HTML Input: Fix a regression in 0.8.6 that caused CSS stylesheets to be ignored" + tickets: [799171] + + - title: "Fix a regression that caused restore database to stop working on some windows sytems" + + - title: "EPUB Output: Convert
tags with text in them into as ADE cannot handle them." + tickets: [794427] + + improved recipes: + - Le Temps + - Perfil + - Financial Times UK + + new recipes: + - title: "Daytona Beach Journal" + author: BRGriff + + - title: "El club del ebook and Frontline" + author: Darko Miletic + + - version: 0.8.6 date: 2011-06-17 diff --git a/recipes/financial_times.recipe b/recipes/financial_times.recipe index e750b6f113..0079b2be3a 100644 --- a/recipes/financial_times.recipe +++ b/recipes/financial_times.recipe @@ -1,32 +1,41 @@ -#!/usr/bin/env python - __license__ = 'GPL v3' -__copyright__ = '2008, Darko Miletic ' +__copyright__ = '2010-2011, Darko Miletic ' ''' -ft.com +www.ft.com ''' +import datetime from calibre.web.feeds.news import BasicNewsRecipe -class FinancialTimes(BasicNewsRecipe): - title = u'Financial Times' - __author__ = 'Darko Miletic and Sujata Raman' - description = ('Financial world news. Available after 5AM ' - 'GMT, daily.') +class FinancialTimes_rss(BasicNewsRecipe): + title = 'Financial Times' + __author__ = 'Darko Miletic' + description = "The Financial Times (FT) is one of the world's leading business news and information organisations, recognised internationally for its authority, integrity and accuracy." + publisher = 'The Financial Times Ltd.' + category = 'news, finances, politics, World' oldest_article = 2 - language = 'en' - - max_articles_per_feed = 100 + language = 'en' + max_articles_per_feed = 250 no_stylesheets = True use_embedded_content = False needs_subscription = True - simultaneous_downloads= 1 - delay = 1 + encoding = 'utf8' + publication_type = 'newspaper' + masthead_url = 'http://im.media.ft.com/m/img/masthead_main.jpg' + LOGIN = 'https://registration.ft.com/registration/barrier/login' + INDEX = 'http://www.ft.com' - LOGIN = 'https://registration.ft.com/registration/barrier/login' + conversion_options = { + 'comment' : description + , 'tags' : category + , 'publisher' : publisher + , 'language' : language + , 'linearize_tables' : True + } def get_browser(self): br = BasicNewsRecipe.get_browser() + br.open(self.INDEX) if self.username is not None and self.password is not None: br.open(self.LOGIN) br.select_form(name='loginForm') @@ -35,31 +44,63 @@ class FinancialTimes(BasicNewsRecipe): br.submit() return br - keep_only_tags = [ dict(name='div', attrs={'id':'cont'}) ] - remove_tags_after = dict(name='p', attrs={'class':'copyright'}) + keep_only_tags = [dict(name='div', attrs={'class':['fullstory fullstoryHeader','fullstory fullstoryBody','ft-story-header','ft-story-body','index-detail']})] remove_tags = [ - dict(name='div', attrs={'id':'floating-con'}) + dict(name='div', attrs={'id':'floating-con'}) + ,dict(name=['meta','iframe','base','object','embed','link']) + ,dict(attrs={'class':['storyTools','story-package','screen-copy','story-package separator','expandable-image']}) ] + remove_attributes = ['width','height','lang'] - extra_css = ''' - body{font-family:Arial,Helvetica,sans-serif;} - h2(font-size:large;} - .ft-story-header(font-size:xx-small;} - .ft-story-body(font-size:small;} - a{color:#003399;} + extra_css = """ + body{font-family: Georgia,Times,"Times New Roman",serif} + h2{font-size:large} + .ft-story-header{font-size: x-small} .container{font-size:x-small;} h3{font-size:x-small;color:#003399;} - ''' + .copyright{font-size: x-small} + img{margin-top: 0.8em; display: block} + .lastUpdated{font-family: Arial,Helvetica,sans-serif; font-size: x-small} + .byline,.ft-story-body,.ft-story-header{font-family: Arial,Helvetica,sans-serif} + """ + feeds = [ (u'UK' , u'http://www.ft.com/rss/home/uk' ) ,(u'US' , u'http://www.ft.com/rss/home/us' ) - ,(u'Europe' , u'http://www.ft.com/rss/home/europe' ) ,(u'Asia' , u'http://www.ft.com/rss/home/asia' ) ,(u'Middle East', u'http://www.ft.com/rss/home/middleeast') ] def preprocess_html(self, soup): - content_type = soup.find('meta', {'http-equiv':'Content-Type'}) - if content_type: - content_type['content'] = 'text/html; charset=utf-8' + items = ['promo-box','promo-title', + 'promo-headline','promo-image', + 'promo-intro','promo-link','subhead'] + for item in items: + for it in soup.findAll(item): + it.name = 'div' + it.attrs = [] + for item in soup.findAll(style=True): + del item['style'] + for item in soup.findAll('a'): + limg = item.find('img') + if item.string is not None: + str = item.string + item.replaceWith(str) + else: + if limg: + item.name = 'div' + item.attrs = [] + else: + str = self.tag_to_string(item) + item.replaceWith(str) + for item in soup.findAll('img'): + if not item.has_key('alt'): + item['alt'] = 'image' return soup + + def get_cover_url(self): + cdate = datetime.date.today() + if cdate.isoweekday() == 7: + cdate -= datetime.timedelta(days=1) + return cdate.strftime('http://specials.ft.com/vtf_pdf/%d%m%y_FRONT1_USA.pdf') + diff --git a/recipes/financial_times_uk.recipe b/recipes/financial_times_uk.recipe index cf219cfda1..e06eb0dc77 100644 --- a/recipes/financial_times_uk.recipe +++ b/recipes/financial_times_uk.recipe @@ -1,15 +1,19 @@ __license__ = 'GPL v3' __copyright__ = '2010-2011, Darko Miletic ' ''' -ft.com +www.ft.com/uk-edition ''' + +import datetime from calibre import strftime from calibre.web.feeds.news import BasicNewsRecipe class FinancialTimes(BasicNewsRecipe): - title = u'Financial Times - UK printed edition' + title = 'Financial Times - UK printed edition' __author__ = 'Darko Miletic' - description = 'Financial world news' + description = "The Financial Times (FT) is one of the world's leading business news and information organisations, recognised internationally for its authority, integrity and accuracy." + publisher = 'The Financial Times Ltd.' + category = 'news, finances, politics, UK, World' oldest_article = 2 language = 'en_GB' max_articles_per_feed = 250 @@ -17,14 +21,23 @@ class FinancialTimes(BasicNewsRecipe): use_embedded_content = False needs_subscription = True encoding = 'utf8' - simultaneous_downloads= 1 - delay = 1 + publication_type = 'newspaper' + masthead_url = 'http://im.media.ft.com/m/img/masthead_main.jpg' LOGIN = 'https://registration.ft.com/registration/barrier/login' INDEX = 'http://www.ft.com/uk-edition' PREFIX = 'http://www.ft.com' + conversion_options = { + 'comment' : description + , 'tags' : category + , 'publisher' : publisher + , 'language' : language + , 'linearize_tables' : True + } + def get_browser(self): br = BasicNewsRecipe.get_browser() + br.open(self.INDEX) if self.username is not None and self.password is not None: br.open(self.LOGIN) br.select_form(name='loginForm') @@ -33,29 +46,34 @@ class FinancialTimes(BasicNewsRecipe): br.submit() return br - keep_only_tags = [ dict(name='div', attrs={'id':'cont'}) ] - remove_tags_after = dict(name='p', attrs={'class':'copyright'}) + keep_only_tags = [dict(name='div', attrs={'class':['fullstory fullstoryHeader','fullstory fullstoryBody','ft-story-header','ft-story-body','index-detail']})] remove_tags = [ dict(name='div', attrs={'id':'floating-con'}) ,dict(name=['meta','iframe','base','object','embed','link']) + ,dict(attrs={'class':['storyTools','story-package','screen-copy','story-package separator','expandable-image']}) ] remove_attributes = ['width','height','lang'] extra_css = """ - body{font-family:Arial,Helvetica,sans-serif;} - h2{font-size:large;} - .ft-story-header{font-size:xx-small;} - .ft-story-body{font-size:small;} - a{color:#003399;} + body{font-family: Georgia,Times,"Times New Roman",serif} + h2{font-size:large} + .ft-story-header{font-size: x-small} .container{font-size:x-small;} h3{font-size:x-small;color:#003399;} .copyright{font-size: x-small} + img{margin-top: 0.8em; display: block} + .lastUpdated{font-family: Arial,Helvetica,sans-serif; font-size: x-small} + .byline,.ft-story-body,.ft-story-header{font-family: Arial,Helvetica,sans-serif} """ def get_artlinks(self, elem): articles = [] for item in elem.findAll('a',href=True): - url = self.PREFIX + item['href'] + rawlink = item['href'] + if rawlink.startswith('http://'): + url = rawlink + else: + url = self.PREFIX + rawlink title = self.tag_to_string(item) date = strftime(self.timefmt) articles.append({ @@ -65,7 +83,7 @@ class FinancialTimes(BasicNewsRecipe): ,'description':'' }) return articles - + def parse_index(self): feeds = [] soup = self.index_to_soup(self.INDEX) @@ -80,11 +98,41 @@ class FinancialTimes(BasicNewsRecipe): strest.insert(0,st) for item in strest: ftitle = self.tag_to_string(item) - self.report_progress(0, _('Fetching feed')+' %s...'%(ftitle)) + self.report_progress(0, _('Fetching feed')+' %s...'%(ftitle)) feedarts = self.get_artlinks(item.parent.ul) feeds.append((ftitle,feedarts)) return feeds def preprocess_html(self, soup): - return self.adeify_images(soup) + items = ['promo-box','promo-title', + 'promo-headline','promo-image', + 'promo-intro','promo-link','subhead'] + for item in items: + for it in soup.findAll(item): + it.name = 'div' + it.attrs = [] + for item in soup.findAll(style=True): + del item['style'] + for item in soup.findAll('a'): + limg = item.find('img') + if item.string is not None: + str = item.string + item.replaceWith(str) + else: + if limg: + item.name = 'div' + item.attrs = [] + else: + str = self.tag_to_string(item) + item.replaceWith(str) + for item in soup.findAll('img'): + if not item.has_key('alt'): + item['alt'] = 'image' + return soup + def get_cover_url(self): + cdate = datetime.date.today() + if cdate.isoweekday() == 7: + cdate -= datetime.timedelta(days=1) + return cdate.strftime('http://specials.ft.com/vtf_pdf/%d%m%y_FRONT1_LON.pdf') + \ No newline at end of file diff --git a/recipes/icons/financial_times.png b/recipes/icons/financial_times.png new file mode 100644 index 0000000000..2a769d9dbb Binary files /dev/null and b/recipes/icons/financial_times.png differ diff --git a/recipes/icons/financial_times_uk.png b/recipes/icons/financial_times_uk.png new file mode 100644 index 0000000000..2a769d9dbb Binary files /dev/null and b/recipes/icons/financial_times_uk.png differ diff --git a/recipes/ming_pao.recipe b/recipes/ming_pao.recipe index 08ee20cb15..3566fca667 100644 --- a/recipes/ming_pao.recipe +++ b/recipes/ming_pao.recipe @@ -1,17 +1,23 @@ -# -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = '2010-2011, Eddie Lau' +# Region - Hong Kong, Vancouver, Toronto +__Region__ = 'Hong Kong' # Users of Kindle 3 with limited system-level CJK support # please replace the following "True" with "False". __MakePeriodical__ = True # Turn below to true if your device supports display of CJK titles __UseChineseTitle__ = False -# Trun below to true if you wish to use life.mingpao.com as the main article source +# Set it to False if you want to skip images +__KeepImages__ = True +# (HK only) Turn below to true if you wish to use life.mingpao.com as the main article source __UseLife__ = True + ''' Change Log: +2011/06/26: add fetching Vancouver and Toronto versions of the paper, also provide captions for images using life.mingpao fetch source + provide options to remove all images in the file 2011/05/12: switch the main parse source to life.mingpao.com, which has more photos on the article pages 2011/03/06: add new articles for finance section, also a new section "Columns" 2011/02/28: rearrange the sections @@ -34,21 +40,96 @@ Change Log: import os, datetime, re from calibre.web.feeds.recipes import BasicNewsRecipe from contextlib import nested - - from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.ebooks.metadata.opf2 import OPFCreator from calibre.ebooks.metadata.toc import TOC from calibre.ebooks.metadata import MetaInformation -class MPHKRecipe(BasicNewsRecipe): - title = 'Ming Pao - Hong Kong' +# MAIN CLASS +class MPRecipe(BasicNewsRecipe): + if __Region__ == 'Hong Kong': + title = 'Ming Pao - Hong Kong' + description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)' + category = 'Chinese, News, Hong Kong' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}' + masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif' + keep_only_tags = [dict(name='h1'), + dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page title + dict(name='font', attrs={'color':['AA0000']}), # for column articles title + dict(attrs={'id':['newscontent']}), # entertainment and column page content + dict(attrs={'id':['newscontent01','newscontent02']}), + dict(attrs={'class':['photo']}), + dict(name='table', attrs={'width':['100%'], 'border':['0'], 'cellspacing':['5'], 'cellpadding':['0']}), # content in printed version of life.mingpao.com + dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com + ] + if __KeepImages__: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + #dict(name='table') # for content fetched from life.mingpao.com + ] + else: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + dict(name='img'), + #dict(name='table') # for content fetched from life.mingpao.com + ] + remove_attributes = ['width'] + preprocess_regexps = [ + (re.compile(r'
', re.DOTALL|re.IGNORECASE), + lambda match: '

'), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), + lambda match: ''), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), # for entertainment page + lambda match: ''), + # skip
after title in life.mingpao.com fetched article + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "
"), + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "") + ] + elif __Region__ == 'Vancouver': + title = 'Ming Pao - Vancouver' + description = 'Vancouver Chinese Newspaper (http://www.mingpaovan.com)' + category = 'Chinese, News, Vancouver' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaovan.com/image/mainlogo2_VAN2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + elif __Region__ == 'Toronto': + title = 'Ming Pao - Toronto' + description = 'Toronto Chinese Newspaper (http://www.mingpaotor.com)' + category = 'Chinese, News, Toronto' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaotor.com/image/mainlogo2_TOR2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + oldest_article = 1 max_articles_per_feed = 100 __author__ = 'Eddie Lau' - description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)' publisher = 'MingPao' - category = 'Chinese, News, Hong Kong' remove_javascript = True use_embedded_content = False no_stylesheets = True @@ -57,33 +138,6 @@ class MPHKRecipe(BasicNewsRecipe): recursions = 0 conversion_options = {'linearize_tables':True} timefmt = '' - extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}' - masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif' - keep_only_tags = [dict(name='h1'), - dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page title - dict(name='font', attrs={'color':['AA0000']}), # for column articles title - dict(attrs={'id':['newscontent']}), # entertainment and column page content - dict(attrs={'id':['newscontent01','newscontent02']}), - dict(attrs={'class':['photo']}), - dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com - ] - remove_tags = [dict(name='style'), - dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com - dict(name='table')] # for content fetched from life.mingpao.com - remove_attributes = ['width'] - preprocess_regexps = [ - (re.compile(r'
', re.DOTALL|re.IGNORECASE), - lambda match: '

'), - (re.compile(r'

', re.DOTALL|re.IGNORECASE), - lambda match: ''), - (re.compile(r'

', re.DOTALL|re.IGNORECASE), # for entertainment page - lambda match: ''), - # skip
after title in life.mingpao.com fetched article - (re.compile(r"

", re.DOTALL|re.IGNORECASE), - lambda match: "
"), - (re.compile(r"

", re.DOTALL|re.IGNORECASE), - lambda match: "") - ] def image_url_processor(cls, baseurl, url): # trick: break the url at the first occurance of digit, add an additional @@ -124,8 +178,18 @@ class MPHKRecipe(BasicNewsRecipe): def get_dtlocal(self): dt_utc = datetime.datetime.utcnow() - # convert UTC to local hk time - at around HKT 6.00am, all news are available - dt_local = dt_utc - datetime.timedelta(-2.0/24) + if __Region__ == 'Hong Kong': + # convert UTC to local hk time - at HKT 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(4.5/24) + # dt_local = dt_utc.astimezone(pytz.timezone('Asia/Hong_Kong')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Vancouver': + # convert UTC to local Vancouver time - at PST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-8.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Vancouver')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Toronto': + # convert UTC to local Toronto time - at EST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-5.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Toronto')) - datetime.timedelta(4.5/24) return dt_local def get_fetchdate(self): @@ -135,13 +199,15 @@ class MPHKRecipe(BasicNewsRecipe): return self.get_dtlocal().strftime("%Y-%m-%d") def get_fetchday(self): - # dt_utc = datetime.datetime.utcnow() - # convert UTC to local hk time - at around HKT 6.00am, all news are available - # dt_local = dt_utc - datetime.timedelta(-2.0/24) return self.get_dtlocal().strftime("%d") def get_cover_url(self): - cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg' + if __Region__ == 'Hong Kong': + cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg' + elif __Region__ == 'Vancouver': + cover = 'http://www.mingpaovan.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgva1s.jpg' + elif __Region__ == 'Toronto': + cover = 'http://www.mingpaotor.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgtas.jpg' br = BasicNewsRecipe.get_browser() try: br.open(cover) @@ -153,76 +219,104 @@ class MPHKRecipe(BasicNewsRecipe): feeds = [] dateStr = self.get_fetchdate() - if __UseLife__: - for title, url, keystr in [(u'\u8981\u805e Headline', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalga', 'nal'), - (u'\u6e2f\u805e Local', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgb', 'nal'), - (u'\u6559\u80b2 Education', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgf', 'nal'), - (u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr', 'nal'), - (u'\u8ad6\u58c7 Forum', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalfa', 'nal'), - (u'\u4e2d\u570b China', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalca', 'nal'), - (u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'), - (u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'), - (u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'), - (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'), - (u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]: - articles = self.parse_section2(url, keystr) + if __Region__ == 'Hong Kong': + if __UseLife__: + for title, url, keystr in [(u'\u8981\u805e Headline', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalga', 'nal'), + (u'\u6e2f\u805e Local', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgb', 'nal'), + (u'\u6559\u80b2 Education', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgf', 'nal'), + (u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr', 'nal'), + (u'\u8ad6\u58c7 Forum', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalfa', 'nal'), + (u'\u4e2d\u570b China', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalca', 'nal'), + (u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'), + (u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'), + (u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'), + (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'), + (u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]: + articles = self.parse_section2(url, keystr) + if articles: + feeds.append((title, articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + else: + for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'), + (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'), + (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special- editorial + ed_articles = self.parse_ed_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr') + if ed_articles: + feeds.append((u'\u793e\u8a55/\u7b46\u9663 Editorial', ed_articles)) + + for title, url in [(u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'), + (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'), + (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - finance + #fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm') + fin_articles = self.parse_fin_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea') + if fin_articles: + feeds.append((u'\u7d93\u6fdf Finance', fin_articles)) + + for title, url in [('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'), + (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - entertainment + ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm') + if ent_articles: + feeds.append((u'\u5f71\u8996 Film/TV', ent_articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + + # special- columns + col_articles = self.parse_col_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn') + if col_articles: + feeds.append((u'\u5c08\u6b04 Columns', col_articles)) + elif __Region__ == 'Vancouver': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VBindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VDindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-VGindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VTindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VCindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VEindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaovan.com/') if articles: feeds.append((title, articles)) - - for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), - (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: - articles = self.parse_section(url) + elif __Region__ == 'Toronto': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TDindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TFindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TCAindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TTAindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-GAindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/THindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaotor.com/') if articles: feeds.append((title, articles)) - else: - for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'), - (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'), - (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]: - articles = self.parse_section(url) - if articles: - feeds.append((title, articles)) - - # special- editorial - ed_articles = self.parse_ed_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr') - if ed_articles: - feeds.append((u'\u793e\u8a55/\u7b46\u9663 Editorial', ed_articles)) - - for title, url in [(u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'), - (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'), - (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm')]: - articles = self.parse_section(url) - if articles: - feeds.append((title, articles)) - - # special - finance - #fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm') - fin_articles = self.parse_fin_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea') - if fin_articles: - feeds.append((u'\u7d93\u6fdf Finance', fin_articles)) - - for title, url in [('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'), - (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm')]: - articles = self.parse_section(url) - if articles: - feeds.append((title, articles)) - - # special - entertainment - ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm') - if ent_articles: - feeds.append((u'\u5f71\u8996 Film/TV', ent_articles)) - - for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), - (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: - articles = self.parse_section(url) - if articles: - feeds.append((title, articles)) - - - # special- columns - col_articles = self.parse_col_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn') - if col_articles: - feeds.append((u'\u5c08\u6b04 Columns', col_articles)) - return feeds # parse from news.mingpao.com @@ -256,11 +350,30 @@ class MPHKRecipe(BasicNewsRecipe): title = self.tag_to_string(i) url = 'http://life.mingpao.com/cfm/' + i.get('href', False) if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind(keystr) == -1): + url = url.replace('dailynews3.cfm', 'dailynews3a.cfm') # use printed version of the article current_articles.append({'title': title, 'url': url, 'description': ''}) included_urls.append(url) current_articles.reverse() return current_articles + # parse from www.mingpaovan.com + def parse_section3(self, url, baseUrl): + self.get_fetchdate() + soup = self.index_to_soup(url) + divs = soup.findAll(attrs={'class': ['ListContentLargeLink']}) + current_articles = [] + included_urls = [] + divs.reverse() + for i in divs: + title = self.tag_to_string(i) + urlstr = i.get('href', False) + urlstr = baseUrl + '/' + urlstr.replace('../../../', '') + if urlstr not in included_urls: + current_articles.append({'title': title, 'url': urlstr, 'description': '', 'date': ''}) + included_urls.append(urlstr) + current_articles.reverse() + return current_articles + def parse_ed_section(self, url): self.get_fetchdate() soup = self.index_to_soup(url) @@ -338,7 +451,12 @@ class MPHKRecipe(BasicNewsRecipe): if dir is None: dir = self.output_dir if __UseChineseTitle__ == True: - title = u'\u660e\u5831 (\u9999\u6e2f)' + if __Region__ == 'Hong Kong': + title = u'\u660e\u5831 (\u9999\u6e2f)' + elif __Region__ == 'Vancouver': + title = u'\u660e\u5831 (\u6eab\u54e5\u83ef)' + elif __Region__ == 'Toronto': + title = u'\u660e\u5831 (\u591a\u502b\u591a)' else: title = self.short_title() # if not generating a periodical, force date to apply in title diff --git a/recipes/ming_pao_toronto.recipe b/recipes/ming_pao_toronto.recipe new file mode 100644 index 0000000000..677a8272b0 --- /dev/null +++ b/recipes/ming_pao_toronto.recipe @@ -0,0 +1,594 @@ +__license__ = 'GPL v3' +__copyright__ = '2010-2011, Eddie Lau' + +# Region - Hong Kong, Vancouver, Toronto +__Region__ = 'Toronto' +# Users of Kindle 3 with limited system-level CJK support +# please replace the following "True" with "False". +__MakePeriodical__ = True +# Turn below to true if your device supports display of CJK titles +__UseChineseTitle__ = False +# Set it to False if you want to skip images +__KeepImages__ = True +# (HK only) Turn below to true if you wish to use life.mingpao.com as the main article source +__UseLife__ = True + + +''' +Change Log: +2011/06/26: add fetching Vancouver and Toronto versions of the paper, also provide captions for images using life.mingpao fetch source + provide options to remove all images in the file +2011/05/12: switch the main parse source to life.mingpao.com, which has more photos on the article pages +2011/03/06: add new articles for finance section, also a new section "Columns" +2011/02/28: rearrange the sections + [Disabled until Kindle has better CJK support and can remember last (section,article) read in Sections & Articles + View] make it the same title if generating a periodical, so past issue will be automatically put into "Past Issues" + folder in Kindle 3 +2011/02/20: skip duplicated links in finance section, put photos which may extend a whole page to the back of the articles + clean up the indentation +2010/12/07: add entertainment section, use newspaper front page as ebook cover, suppress date display in section list + (to avoid wrong date display in case the user generates the ebook in a time zone different from HKT) +2010/11/22: add English section, remove eco-news section which is not updated daily, correct + ordering of articles +2010/11/12: add news image and eco-news section +2010/11/08: add parsing of finance section +2010/11/06: temporary work-around for Kindle device having no capability to display unicode + in section/article list. +2010/10/31: skip repeated articles in section pages +''' + +import os, datetime, re +from calibre.web.feeds.recipes import BasicNewsRecipe +from contextlib import nested +from calibre.ebooks.BeautifulSoup import BeautifulSoup +from calibre.ebooks.metadata.opf2 import OPFCreator +from calibre.ebooks.metadata.toc import TOC +from calibre.ebooks.metadata import MetaInformation + +# MAIN CLASS +class MPRecipe(BasicNewsRecipe): + if __Region__ == 'Hong Kong': + title = 'Ming Pao - Hong Kong' + description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)' + category = 'Chinese, News, Hong Kong' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}' + masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif' + keep_only_tags = [dict(name='h1'), + dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page title + dict(name='font', attrs={'color':['AA0000']}), # for column articles title + dict(attrs={'id':['newscontent']}), # entertainment and column page content + dict(attrs={'id':['newscontent01','newscontent02']}), + dict(attrs={'class':['photo']}), + dict(name='table', attrs={'width':['100%'], 'border':['0'], 'cellspacing':['5'], 'cellpadding':['0']}), # content in printed version of life.mingpao.com + dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com + ] + if __KeepImages__: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + #dict(name='table') # for content fetched from life.mingpao.com + ] + else: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + dict(name='img'), + #dict(name='table') # for content fetched from life.mingpao.com + ] + remove_attributes = ['width'] + preprocess_regexps = [ + (re.compile(r'
', re.DOTALL|re.IGNORECASE), + lambda match: '

'), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), + lambda match: ''), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), # for entertainment page + lambda match: ''), + # skip
after title in life.mingpao.com fetched article + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "
"), + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "") + ] + elif __Region__ == 'Vancouver': + title = 'Ming Pao - Vancouver' + description = 'Vancouver Chinese Newspaper (http://www.mingpaovan.com)' + category = 'Chinese, News, Vancouver' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaovan.com/image/mainlogo2_VAN2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + elif __Region__ == 'Toronto': + title = 'Ming Pao - Toronto' + description = 'Toronto Chinese Newspaper (http://www.mingpaotor.com)' + category = 'Chinese, News, Toronto' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaotor.com/image/mainlogo2_TOR2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + + oldest_article = 1 + max_articles_per_feed = 100 + __author__ = 'Eddie Lau' + publisher = 'MingPao' + remove_javascript = True + use_embedded_content = False + no_stylesheets = True + language = 'zh' + encoding = 'Big5-HKSCS' + recursions = 0 + conversion_options = {'linearize_tables':True} + timefmt = '' + + def image_url_processor(cls, baseurl, url): + # trick: break the url at the first occurance of digit, add an additional + # '_' at the front + # not working, may need to move this to preprocess_html() method +# minIdx = 10000 +# i0 = url.find('0') +# if i0 >= 0 and i0 < minIdx: +# minIdx = i0 +# i1 = url.find('1') +# if i1 >= 0 and i1 < minIdx: +# minIdx = i1 +# i2 = url.find('2') +# if i2 >= 0 and i2 < minIdx: +# minIdx = i2 +# i3 = url.find('3') +# if i3 >= 0 and i0 < minIdx: +# minIdx = i3 +# i4 = url.find('4') +# if i4 >= 0 and i4 < minIdx: +# minIdx = i4 +# i5 = url.find('5') +# if i5 >= 0 and i5 < minIdx: +# minIdx = i5 +# i6 = url.find('6') +# if i6 >= 0 and i6 < minIdx: +# minIdx = i6 +# i7 = url.find('7') +# if i7 >= 0 and i7 < minIdx: +# minIdx = i7 +# i8 = url.find('8') +# if i8 >= 0 and i8 < minIdx: +# minIdx = i8 +# i9 = url.find('9') +# if i9 >= 0 and i9 < minIdx: +# minIdx = i9 + return url + + def get_dtlocal(self): + dt_utc = datetime.datetime.utcnow() + if __Region__ == 'Hong Kong': + # convert UTC to local hk time - at HKT 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(4.5/24) + # dt_local = dt_utc.astimezone(pytz.timezone('Asia/Hong_Kong')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Vancouver': + # convert UTC to local Vancouver time - at PST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-8.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Vancouver')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Toronto': + # convert UTC to local Toronto time - at EST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-5.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Toronto')) - datetime.timedelta(4.5/24) + return dt_local + + def get_fetchdate(self): + return self.get_dtlocal().strftime("%Y%m%d") + + def get_fetchformatteddate(self): + return self.get_dtlocal().strftime("%Y-%m-%d") + + def get_fetchday(self): + return self.get_dtlocal().strftime("%d") + + def get_cover_url(self): + if __Region__ == 'Hong Kong': + cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg' + elif __Region__ == 'Vancouver': + cover = 'http://www.mingpaovan.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgva1s.jpg' + elif __Region__ == 'Toronto': + cover = 'http://www.mingpaotor.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgtas.jpg' + br = BasicNewsRecipe.get_browser() + try: + br.open(cover) + except: + cover = None + return cover + + def parse_index(self): + feeds = [] + dateStr = self.get_fetchdate() + + if __Region__ == 'Hong Kong': + if __UseLife__: + for title, url, keystr in [(u'\u8981\u805e Headline', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalga', 'nal'), + (u'\u6e2f\u805e Local', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgb', 'nal'), + (u'\u6559\u80b2 Education', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgf', 'nal'), + (u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr', 'nal'), + (u'\u8ad6\u58c7 Forum', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalfa', 'nal'), + (u'\u4e2d\u570b China', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalca', 'nal'), + (u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'), + (u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'), + (u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'), + (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'), + (u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]: + articles = self.parse_section2(url, keystr) + if articles: + feeds.append((title, articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + else: + for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'), + (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'), + (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special- editorial + ed_articles = self.parse_ed_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr') + if ed_articles: + feeds.append((u'\u793e\u8a55/\u7b46\u9663 Editorial', ed_articles)) + + for title, url in [(u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'), + (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'), + (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - finance + #fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm') + fin_articles = self.parse_fin_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea') + if fin_articles: + feeds.append((u'\u7d93\u6fdf Finance', fin_articles)) + + for title, url in [('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'), + (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - entertainment + ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm') + if ent_articles: + feeds.append((u'\u5f71\u8996 Film/TV', ent_articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + + # special- columns + col_articles = self.parse_col_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn') + if col_articles: + feeds.append((u'\u5c08\u6b04 Columns', col_articles)) + elif __Region__ == 'Vancouver': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VBindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VDindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-VGindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VTindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VCindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VEindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaovan.com/') + if articles: + feeds.append((title, articles)) + elif __Region__ == 'Toronto': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TDindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TFindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TCAindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TTAindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-GAindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/THindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaotor.com/') + if articles: + feeds.append((title, articles)) + return feeds + + # parse from news.mingpao.com + def parse_section(self, url): + dateStr = self.get_fetchdate() + soup = self.index_to_soup(url) + divs = soup.findAll(attrs={'class': ['bullet','bullet_grey']}) + current_articles = [] + included_urls = [] + divs.reverse() + for i in divs: + a = i.find('a', href = True) + title = self.tag_to_string(a) + url = a.get('href', False) + url = 'http://news.mingpao.com/' + dateStr + '/' +url + if url not in included_urls and url.rfind('Redirect') == -1: + current_articles.append({'title': title, 'url': url, 'description':'', 'date':''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + # parse from life.mingpao.com + def parse_section2(self, url, keystr): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind(keystr) == -1): + url = url.replace('dailynews3.cfm', 'dailynews3a.cfm') # use printed version of the article + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + # parse from www.mingpaovan.com + def parse_section3(self, url, baseUrl): + self.get_fetchdate() + soup = self.index_to_soup(url) + divs = soup.findAll(attrs={'class': ['ListContentLargeLink']}) + current_articles = [] + included_urls = [] + divs.reverse() + for i in divs: + title = self.tag_to_string(i) + urlstr = i.get('href', False) + urlstr = baseUrl + '/' + urlstr.replace('../../../', '') + if urlstr not in included_urls: + current_articles.append({'title': title, 'url': urlstr, 'description': '', 'date': ''}) + included_urls.append(urlstr) + current_articles.reverse() + return current_articles + + def parse_ed_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('nal') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def parse_fin_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href= True) + current_articles = [] + included_urls = [] + for i in a: + #url = 'http://www.mpfinance.com/cfm/' + i.get('href', False) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + #if url not in included_urls and not url.rfind(dateStr) == -1 and url.rfind('index') == -1: + if url not in included_urls and (not url.rfind('txt') == -1) and (not url.rfind('nal') == -1): + title = self.tag_to_string(i) + current_articles.append({'title': title, 'url': url, 'description':''}) + included_urls.append(url) + return current_articles + + def parse_ent_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://ol.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('star') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def parse_col_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('ncl') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + for item in soup.findAll(style=True): + del item['width'] + for item in soup.findAll(stype=True): + del item['absmiddle'] + return soup + + def create_opf(self, feeds, dir=None): + if dir is None: + dir = self.output_dir + if __UseChineseTitle__ == True: + if __Region__ == 'Hong Kong': + title = u'\u660e\u5831 (\u9999\u6e2f)' + elif __Region__ == 'Vancouver': + title = u'\u660e\u5831 (\u6eab\u54e5\u83ef)' + elif __Region__ == 'Toronto': + title = u'\u660e\u5831 (\u591a\u502b\u591a)' + else: + title = self.short_title() + # if not generating a periodical, force date to apply in title + if __MakePeriodical__ == False: + title = title + ' ' + self.get_fetchformatteddate() + if True: + mi = MetaInformation(title, [self.publisher]) + mi.publisher = self.publisher + mi.author_sort = self.publisher + if __MakePeriodical__ == True: + mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title() + else: + mi.publication_type = self.publication_type+':'+self.short_title() + #mi.timestamp = nowf() + mi.timestamp = self.get_dtlocal() + mi.comments = self.description + if not isinstance(mi.comments, unicode): + mi.comments = mi.comments.decode('utf-8', 'replace') + #mi.pubdate = nowf() + mi.pubdate = self.get_dtlocal() + opf_path = os.path.join(dir, 'index.opf') + ncx_path = os.path.join(dir, 'index.ncx') + opf = OPFCreator(dir, mi) + # Add mastheadImage entry to section + mp = getattr(self, 'masthead_path', None) + if mp is not None and os.access(mp, os.R_OK): + from calibre.ebooks.metadata.opf2 import Guide + ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu()) + ref.type = 'masthead' + ref.title = 'Masthead Image' + opf.guide.append(ref) + + manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))] + manifest.append(os.path.join(dir, 'index.html')) + manifest.append(os.path.join(dir, 'index.ncx')) + + # Get cover + cpath = getattr(self, 'cover_path', None) + if cpath is None: + pf = open(os.path.join(dir, 'cover.jpg'), 'wb') + if self.default_cover(pf): + cpath = pf.name + if cpath is not None and os.access(cpath, os.R_OK): + opf.cover = cpath + manifest.append(cpath) + + # Get masthead + mpath = getattr(self, 'masthead_path', None) + if mpath is not None and os.access(mpath, os.R_OK): + manifest.append(mpath) + + opf.create_manifest_from_files_in(manifest) + for mani in opf.manifest: + if mani.path.endswith('.ncx'): + mani.id = 'ncx' + if mani.path.endswith('mastheadImage.jpg'): + mani.id = 'masthead-image' + entries = ['index.html'] + toc = TOC(base_path=dir) + self.play_order_counter = 0 + self.play_order_map = {} + + def feed_index(num, parent): + f = feeds[num] + for j, a in enumerate(f): + if getattr(a, 'downloaded', False): + adir = 'feed_%d/article_%d/'%(num, j) + auth = a.author + if not auth: + auth = None + desc = a.text_summary + if not desc: + desc = None + else: + desc = self.description_limiter(desc) + entries.append('%sindex.html'%adir) + po = self.play_order_map.get(entries[-1], None) + if po is None: + self.play_order_counter += 1 + po = self.play_order_counter + parent.add_item('%sindex.html'%adir, None, a.title if a.title else _('Untitled Article'), + play_order=po, author=auth, description=desc) + last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep)) + for sp in a.sub_pages: + prefix = os.path.commonprefix([opf_path, sp]) + relp = sp[len(prefix):] + entries.append(relp.replace(os.sep, '/')) + last = sp + + if os.path.exists(last): + with open(last, 'rb') as fi: + src = fi.read().decode('utf-8') + soup = BeautifulSoup(src) + body = soup.find('body') + if body is not None: + prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last)))) + templ = self.navbar.generate(True, num, j, len(f), + not self.has_single_feed, + a.orig_url, self.publisher, prefix=prefix, + center=self.center_navbar) + elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div') + body.insert(len(body.contents), elem) + with open(last, 'wb') as fi: + fi.write(unicode(soup).encode('utf-8')) + if len(feeds) == 0: + raise Exception('All feeds are empty, aborting.') + + if len(feeds) > 1: + for i, f in enumerate(feeds): + entries.append('feed_%d/index.html'%i) + po = self.play_order_map.get(entries[-1], None) + if po is None: + self.play_order_counter += 1 + po = self.play_order_counter + auth = getattr(f, 'author', None) + if not auth: + auth = None + desc = getattr(f, 'description', None) + if not desc: + desc = None + feed_index(i, toc.add_item('feed_%d/index.html'%i, None, + f.title, play_order=po, description=desc, author=auth)) + + else: + entries.append('feed_%d/index.html'%0) + feed_index(0, toc) + + for i, p in enumerate(entries): + entries[i] = os.path.join(dir, p.replace('/', os.sep)) + opf.create_spine(entries) + opf.set_toc(toc) + + with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file): + opf.render(opf_file, ncx_file) + diff --git a/recipes/ming_pao_vancouver.recipe b/recipes/ming_pao_vancouver.recipe new file mode 100644 index 0000000000..3312c8f7b8 --- /dev/null +++ b/recipes/ming_pao_vancouver.recipe @@ -0,0 +1,594 @@ +__license__ = 'GPL v3' +__copyright__ = '2010-2011, Eddie Lau' + +# Region - Hong Kong, Vancouver, Toronto +__Region__ = 'Vancouver' +# Users of Kindle 3 with limited system-level CJK support +# please replace the following "True" with "False". +__MakePeriodical__ = True +# Turn below to true if your device supports display of CJK titles +__UseChineseTitle__ = False +# Set it to False if you want to skip images +__KeepImages__ = True +# (HK only) Turn below to true if you wish to use life.mingpao.com as the main article source +__UseLife__ = True + + +''' +Change Log: +2011/06/26: add fetching Vancouver and Toronto versions of the paper, also provide captions for images using life.mingpao fetch source + provide options to remove all images in the file +2011/05/12: switch the main parse source to life.mingpao.com, which has more photos on the article pages +2011/03/06: add new articles for finance section, also a new section "Columns" +2011/02/28: rearrange the sections + [Disabled until Kindle has better CJK support and can remember last (section,article) read in Sections & Articles + View] make it the same title if generating a periodical, so past issue will be automatically put into "Past Issues" + folder in Kindle 3 +2011/02/20: skip duplicated links in finance section, put photos which may extend a whole page to the back of the articles + clean up the indentation +2010/12/07: add entertainment section, use newspaper front page as ebook cover, suppress date display in section list + (to avoid wrong date display in case the user generates the ebook in a time zone different from HKT) +2010/11/22: add English section, remove eco-news section which is not updated daily, correct + ordering of articles +2010/11/12: add news image and eco-news section +2010/11/08: add parsing of finance section +2010/11/06: temporary work-around for Kindle device having no capability to display unicode + in section/article list. +2010/10/31: skip repeated articles in section pages +''' + +import os, datetime, re +from calibre.web.feeds.recipes import BasicNewsRecipe +from contextlib import nested +from calibre.ebooks.BeautifulSoup import BeautifulSoup +from calibre.ebooks.metadata.opf2 import OPFCreator +from calibre.ebooks.metadata.toc import TOC +from calibre.ebooks.metadata import MetaInformation + +# MAIN CLASS +class MPRecipe(BasicNewsRecipe): + if __Region__ == 'Hong Kong': + title = 'Ming Pao - Hong Kong' + description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)' + category = 'Chinese, News, Hong Kong' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}' + masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif' + keep_only_tags = [dict(name='h1'), + dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page title + dict(name='font', attrs={'color':['AA0000']}), # for column articles title + dict(attrs={'id':['newscontent']}), # entertainment and column page content + dict(attrs={'id':['newscontent01','newscontent02']}), + dict(attrs={'class':['photo']}), + dict(name='table', attrs={'width':['100%'], 'border':['0'], 'cellspacing':['5'], 'cellpadding':['0']}), # content in printed version of life.mingpao.com + dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com + ] + if __KeepImages__: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + #dict(name='table') # for content fetched from life.mingpao.com + ] + else: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + dict(name='img'), + #dict(name='table') # for content fetched from life.mingpao.com + ] + remove_attributes = ['width'] + preprocess_regexps = [ + (re.compile(r'
', re.DOTALL|re.IGNORECASE), + lambda match: '

'), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), + lambda match: ''), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), # for entertainment page + lambda match: ''), + # skip
after title in life.mingpao.com fetched article + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "
"), + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "") + ] + elif __Region__ == 'Vancouver': + title = 'Ming Pao - Vancouver' + description = 'Vancouver Chinese Newspaper (http://www.mingpaovan.com)' + category = 'Chinese, News, Vancouver' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaovan.com/image/mainlogo2_VAN2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + elif __Region__ == 'Toronto': + title = 'Ming Pao - Toronto' + description = 'Toronto Chinese Newspaper (http://www.mingpaotor.com)' + category = 'Chinese, News, Toronto' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaotor.com/image/mainlogo2_TOR2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + + oldest_article = 1 + max_articles_per_feed = 100 + __author__ = 'Eddie Lau' + publisher = 'MingPao' + remove_javascript = True + use_embedded_content = False + no_stylesheets = True + language = 'zh' + encoding = 'Big5-HKSCS' + recursions = 0 + conversion_options = {'linearize_tables':True} + timefmt = '' + + def image_url_processor(cls, baseurl, url): + # trick: break the url at the first occurance of digit, add an additional + # '_' at the front + # not working, may need to move this to preprocess_html() method +# minIdx = 10000 +# i0 = url.find('0') +# if i0 >= 0 and i0 < minIdx: +# minIdx = i0 +# i1 = url.find('1') +# if i1 >= 0 and i1 < minIdx: +# minIdx = i1 +# i2 = url.find('2') +# if i2 >= 0 and i2 < minIdx: +# minIdx = i2 +# i3 = url.find('3') +# if i3 >= 0 and i0 < minIdx: +# minIdx = i3 +# i4 = url.find('4') +# if i4 >= 0 and i4 < minIdx: +# minIdx = i4 +# i5 = url.find('5') +# if i5 >= 0 and i5 < minIdx: +# minIdx = i5 +# i6 = url.find('6') +# if i6 >= 0 and i6 < minIdx: +# minIdx = i6 +# i7 = url.find('7') +# if i7 >= 0 and i7 < minIdx: +# minIdx = i7 +# i8 = url.find('8') +# if i8 >= 0 and i8 < minIdx: +# minIdx = i8 +# i9 = url.find('9') +# if i9 >= 0 and i9 < minIdx: +# minIdx = i9 + return url + + def get_dtlocal(self): + dt_utc = datetime.datetime.utcnow() + if __Region__ == 'Hong Kong': + # convert UTC to local hk time - at HKT 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(4.5/24) + # dt_local = dt_utc.astimezone(pytz.timezone('Asia/Hong_Kong')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Vancouver': + # convert UTC to local Vancouver time - at PST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-8.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Vancouver')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Toronto': + # convert UTC to local Toronto time - at EST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-5.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Toronto')) - datetime.timedelta(4.5/24) + return dt_local + + def get_fetchdate(self): + return self.get_dtlocal().strftime("%Y%m%d") + + def get_fetchformatteddate(self): + return self.get_dtlocal().strftime("%Y-%m-%d") + + def get_fetchday(self): + return self.get_dtlocal().strftime("%d") + + def get_cover_url(self): + if __Region__ == 'Hong Kong': + cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg' + elif __Region__ == 'Vancouver': + cover = 'http://www.mingpaovan.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgva1s.jpg' + elif __Region__ == 'Toronto': + cover = 'http://www.mingpaotor.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgtas.jpg' + br = BasicNewsRecipe.get_browser() + try: + br.open(cover) + except: + cover = None + return cover + + def parse_index(self): + feeds = [] + dateStr = self.get_fetchdate() + + if __Region__ == 'Hong Kong': + if __UseLife__: + for title, url, keystr in [(u'\u8981\u805e Headline', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalga', 'nal'), + (u'\u6e2f\u805e Local', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgb', 'nal'), + (u'\u6559\u80b2 Education', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgf', 'nal'), + (u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr', 'nal'), + (u'\u8ad6\u58c7 Forum', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalfa', 'nal'), + (u'\u4e2d\u570b China', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalca', 'nal'), + (u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'), + (u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'), + (u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'), + (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'), + (u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]: + articles = self.parse_section2(url, keystr) + if articles: + feeds.append((title, articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + else: + for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'), + (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'), + (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special- editorial + ed_articles = self.parse_ed_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr') + if ed_articles: + feeds.append((u'\u793e\u8a55/\u7b46\u9663 Editorial', ed_articles)) + + for title, url in [(u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'), + (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'), + (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - finance + #fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm') + fin_articles = self.parse_fin_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea') + if fin_articles: + feeds.append((u'\u7d93\u6fdf Finance', fin_articles)) + + for title, url in [('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'), + (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - entertainment + ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm') + if ent_articles: + feeds.append((u'\u5f71\u8996 Film/TV', ent_articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + + # special- columns + col_articles = self.parse_col_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn') + if col_articles: + feeds.append((u'\u5c08\u6b04 Columns', col_articles)) + elif __Region__ == 'Vancouver': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VBindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VDindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-VGindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VTindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VCindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VEindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaovan.com/') + if articles: + feeds.append((title, articles)) + elif __Region__ == 'Toronto': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TDindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TFindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TCAindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TTAindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-GAindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/THindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaotor.com/') + if articles: + feeds.append((title, articles)) + return feeds + + # parse from news.mingpao.com + def parse_section(self, url): + dateStr = self.get_fetchdate() + soup = self.index_to_soup(url) + divs = soup.findAll(attrs={'class': ['bullet','bullet_grey']}) + current_articles = [] + included_urls = [] + divs.reverse() + for i in divs: + a = i.find('a', href = True) + title = self.tag_to_string(a) + url = a.get('href', False) + url = 'http://news.mingpao.com/' + dateStr + '/' +url + if url not in included_urls and url.rfind('Redirect') == -1: + current_articles.append({'title': title, 'url': url, 'description':'', 'date':''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + # parse from life.mingpao.com + def parse_section2(self, url, keystr): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind(keystr) == -1): + url = url.replace('dailynews3.cfm', 'dailynews3a.cfm') # use printed version of the article + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + # parse from www.mingpaovan.com + def parse_section3(self, url, baseUrl): + self.get_fetchdate() + soup = self.index_to_soup(url) + divs = soup.findAll(attrs={'class': ['ListContentLargeLink']}) + current_articles = [] + included_urls = [] + divs.reverse() + for i in divs: + title = self.tag_to_string(i) + urlstr = i.get('href', False) + urlstr = baseUrl + '/' + urlstr.replace('../../../', '') + if urlstr not in included_urls: + current_articles.append({'title': title, 'url': urlstr, 'description': '', 'date': ''}) + included_urls.append(urlstr) + current_articles.reverse() + return current_articles + + def parse_ed_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('nal') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def parse_fin_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href= True) + current_articles = [] + included_urls = [] + for i in a: + #url = 'http://www.mpfinance.com/cfm/' + i.get('href', False) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + #if url not in included_urls and not url.rfind(dateStr) == -1 and url.rfind('index') == -1: + if url not in included_urls and (not url.rfind('txt') == -1) and (not url.rfind('nal') == -1): + title = self.tag_to_string(i) + current_articles.append({'title': title, 'url': url, 'description':''}) + included_urls.append(url) + return current_articles + + def parse_ent_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://ol.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('star') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def parse_col_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('ncl') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + for item in soup.findAll(style=True): + del item['width'] + for item in soup.findAll(stype=True): + del item['absmiddle'] + return soup + + def create_opf(self, feeds, dir=None): + if dir is None: + dir = self.output_dir + if __UseChineseTitle__ == True: + if __Region__ == 'Hong Kong': + title = u'\u660e\u5831 (\u9999\u6e2f)' + elif __Region__ == 'Vancouver': + title = u'\u660e\u5831 (\u6eab\u54e5\u83ef)' + elif __Region__ == 'Toronto': + title = u'\u660e\u5831 (\u591a\u502b\u591a)' + else: + title = self.short_title() + # if not generating a periodical, force date to apply in title + if __MakePeriodical__ == False: + title = title + ' ' + self.get_fetchformatteddate() + if True: + mi = MetaInformation(title, [self.publisher]) + mi.publisher = self.publisher + mi.author_sort = self.publisher + if __MakePeriodical__ == True: + mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title() + else: + mi.publication_type = self.publication_type+':'+self.short_title() + #mi.timestamp = nowf() + mi.timestamp = self.get_dtlocal() + mi.comments = self.description + if not isinstance(mi.comments, unicode): + mi.comments = mi.comments.decode('utf-8', 'replace') + #mi.pubdate = nowf() + mi.pubdate = self.get_dtlocal() + opf_path = os.path.join(dir, 'index.opf') + ncx_path = os.path.join(dir, 'index.ncx') + opf = OPFCreator(dir, mi) + # Add mastheadImage entry to section + mp = getattr(self, 'masthead_path', None) + if mp is not None and os.access(mp, os.R_OK): + from calibre.ebooks.metadata.opf2 import Guide + ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu()) + ref.type = 'masthead' + ref.title = 'Masthead Image' + opf.guide.append(ref) + + manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))] + manifest.append(os.path.join(dir, 'index.html')) + manifest.append(os.path.join(dir, 'index.ncx')) + + # Get cover + cpath = getattr(self, 'cover_path', None) + if cpath is None: + pf = open(os.path.join(dir, 'cover.jpg'), 'wb') + if self.default_cover(pf): + cpath = pf.name + if cpath is not None and os.access(cpath, os.R_OK): + opf.cover = cpath + manifest.append(cpath) + + # Get masthead + mpath = getattr(self, 'masthead_path', None) + if mpath is not None and os.access(mpath, os.R_OK): + manifest.append(mpath) + + opf.create_manifest_from_files_in(manifest) + for mani in opf.manifest: + if mani.path.endswith('.ncx'): + mani.id = 'ncx' + if mani.path.endswith('mastheadImage.jpg'): + mani.id = 'masthead-image' + entries = ['index.html'] + toc = TOC(base_path=dir) + self.play_order_counter = 0 + self.play_order_map = {} + + def feed_index(num, parent): + f = feeds[num] + for j, a in enumerate(f): + if getattr(a, 'downloaded', False): + adir = 'feed_%d/article_%d/'%(num, j) + auth = a.author + if not auth: + auth = None + desc = a.text_summary + if not desc: + desc = None + else: + desc = self.description_limiter(desc) + entries.append('%sindex.html'%adir) + po = self.play_order_map.get(entries[-1], None) + if po is None: + self.play_order_counter += 1 + po = self.play_order_counter + parent.add_item('%sindex.html'%adir, None, a.title if a.title else _('Untitled Article'), + play_order=po, author=auth, description=desc) + last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep)) + for sp in a.sub_pages: + prefix = os.path.commonprefix([opf_path, sp]) + relp = sp[len(prefix):] + entries.append(relp.replace(os.sep, '/')) + last = sp + + if os.path.exists(last): + with open(last, 'rb') as fi: + src = fi.read().decode('utf-8') + soup = BeautifulSoup(src) + body = soup.find('body') + if body is not None: + prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last)))) + templ = self.navbar.generate(True, num, j, len(f), + not self.has_single_feed, + a.orig_url, self.publisher, prefix=prefix, + center=self.center_navbar) + elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div') + body.insert(len(body.contents), elem) + with open(last, 'wb') as fi: + fi.write(unicode(soup).encode('utf-8')) + if len(feeds) == 0: + raise Exception('All feeds are empty, aborting.') + + if len(feeds) > 1: + for i, f in enumerate(feeds): + entries.append('feed_%d/index.html'%i) + po = self.play_order_map.get(entries[-1], None) + if po is None: + self.play_order_counter += 1 + po = self.play_order_counter + auth = getattr(f, 'author', None) + if not auth: + auth = None + desc = getattr(f, 'description', None) + if not desc: + desc = None + feed_index(i, toc.add_item('feed_%d/index.html'%i, None, + f.title, play_order=po, description=desc, author=auth)) + + else: + entries.append('feed_%d/index.html'%0) + feed_index(0, toc) + + for i, p in enumerate(entries): + entries[i] = os.path.join(dir, p.replace('/', os.sep)) + opf.create_spine(entries) + opf.set_toc(toc) + + with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file): + opf.render(opf_file, ncx_file) + diff --git a/src/calibre/constants.py b/src/calibre/constants.py index ec0134e4cb..d347b2d524 100644 --- a/src/calibre/constants.py +++ b/src/calibre/constants.py @@ -4,7 +4,7 @@ __license__ = 'GPL v3' __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' __docformat__ = 'restructuredtext en' __appname__ = u'calibre' -numeric_version = (0, 8, 6) +numeric_version = (0, 8, 7) __version__ = u'.'.join(map(unicode, numeric_version)) __author__ = u"Kovid Goyal " diff --git a/src/calibre/customize/builtins.py b/src/calibre/customize/builtins.py index e3b7bef5d8..333a5baaa4 100644 --- a/src/calibre/customize/builtins.py +++ b/src/calibre/customize/builtins.py @@ -1148,7 +1148,7 @@ plugins += [LookAndFeel, Behavior, Columns, Toolbar, Search, InputOptions, class StoreAmazonKindleStore(StoreBase): name = 'Amazon Kindle' description = u'Kindle books from Amazon.' - actual_plugin = 'calibre.gui2.store.amazon_plugin:AmazonKindleStore' + actual_plugin = 'calibre.gui2.store.stores.amazon_plugin:AmazonKindleStore' headquarters = 'US' formats = ['KINDLE'] @@ -1158,7 +1158,7 @@ class StoreAmazonDEKindleStore(StoreBase): name = 'Amazon DE Kindle' author = 'Charles Haley' description = u'Kindle Bücher von Amazon.' - actual_plugin = 'calibre.gui2.store.amazon_de_plugin:AmazonDEKindleStore' + actual_plugin = 'calibre.gui2.store.stores.amazon_de_plugin:AmazonDEKindleStore' headquarters = 'DE' formats = ['KINDLE'] @@ -1168,7 +1168,7 @@ class StoreAmazonUKKindleStore(StoreBase): name = 'Amazon UK Kindle' author = 'Charles Haley' description = u'Kindle books from Amazon\'s UK web site. Also, includes French language ebooks.' - actual_plugin = 'calibre.gui2.store.amazon_uk_plugin:AmazonUKKindleStore' + actual_plugin = 'calibre.gui2.store.stores.amazon_uk_plugin:AmazonUKKindleStore' headquarters = 'UK' formats = ['KINDLE'] @@ -1177,7 +1177,7 @@ class StoreAmazonUKKindleStore(StoreBase): class StoreArchiveOrgStore(StoreBase): name = 'Archive.org' description = u'An Internet library offering permanent access for researchers, historians, scholars, people with disabilities, and the general public to historical collections that exist in digital format.' - actual_plugin = 'calibre.gui2.store.archive_org_plugin:ArchiveOrgStore' + actual_plugin = 'calibre.gui2.store.stores.archive_org_plugin:ArchiveOrgStore' drm_free_only = True headquarters = 'US' @@ -1186,7 +1186,7 @@ class StoreArchiveOrgStore(StoreBase): class StoreBaenWebScriptionStore(StoreBase): name = 'Baen WebScription' description = u'Sci-Fi & Fantasy brought to you by Jim Baen.' - actual_plugin = 'calibre.gui2.store.baen_webscription_plugin:BaenWebScriptionStore' + actual_plugin = 'calibre.gui2.store.stores.baen_webscription_plugin:BaenWebScriptionStore' drm_free_only = True headquarters = 'US' @@ -1195,7 +1195,7 @@ class StoreBaenWebScriptionStore(StoreBase): class StoreBNStore(StoreBase): name = 'Barnes and Noble' description = u'The world\'s largest book seller. As the ultimate destination for book lovers, Barnes & Noble.com offers an incredible array of content.' - actual_plugin = 'calibre.gui2.store.bn_plugin:BNStore' + actual_plugin = 'calibre.gui2.store.stores.bn_plugin:BNStore' headquarters = 'US' formats = ['NOOK'] @@ -1205,7 +1205,7 @@ class StoreBeamEBooksDEStore(StoreBase): name = 'Beam EBooks DE' author = 'Charles Haley' description = u'Bei uns finden Sie: Tausende deutschsprachige eBooks; Alle eBooks ohne hartes DRM; PDF, ePub und Mobipocket Format; Sofortige Verfügbarkeit - 24 Stunden am Tag; Günstige Preise; eBooks für viele Lesegeräte, PC,Mac und Smartphones; Viele Gratis eBooks' - actual_plugin = 'calibre.gui2.store.beam_ebooks_de_plugin:BeamEBooksDEStore' + actual_plugin = 'calibre.gui2.store.stores.beam_ebooks_de_plugin:BeamEBooksDEStore' drm_free_only = True headquarters = 'DE' @@ -1215,7 +1215,7 @@ class StoreBeamEBooksDEStore(StoreBase): class StoreBeWriteStore(StoreBase): name = 'BeWrite Books' description = u'Publishers of fine books. Highly selective and editorially driven. Does not offer: books for children or exclusively YA, erotica, swords-and-sorcery fantasy and space-opera-style science fiction. All other genres are represented.' - actual_plugin = 'calibre.gui2.store.bewrite_plugin:BeWriteStore' + actual_plugin = 'calibre.gui2.store.stores.bewrite_plugin:BeWriteStore' drm_free_only = True headquarters = 'US' @@ -1224,7 +1224,7 @@ class StoreBeWriteStore(StoreBase): class StoreDieselEbooksStore(StoreBase): name = 'Diesel eBooks' description = u'Instant access to over 2.4 million titles from hundreds of publishers including Harlequin, HarperCollins, John Wiley & Sons, McGraw-Hill, Simon & Schuster and Random House.' - actual_plugin = 'calibre.gui2.store.diesel_ebooks_plugin:DieselEbooksStore' + actual_plugin = 'calibre.gui2.store.stores.diesel_ebooks_plugin:DieselEbooksStore' headquarters = 'US' formats = ['EPUB', 'PDF'] @@ -1233,7 +1233,7 @@ class StoreDieselEbooksStore(StoreBase): class StoreEbookscomStore(StoreBase): name = 'eBooks.com' description = u'Sells books in multiple electronic formats in all categories. Technical infrastructure is cutting edge, robust and scalable, with servers in the US and Europe.' - actual_plugin = 'calibre.gui2.store.ebooks_com_plugin:EbookscomStore' + actual_plugin = 'calibre.gui2.store.stores.ebooks_com_plugin:EbookscomStore' headquarters = 'US' formats = ['EPUB', 'LIT', 'MOBI', 'PDF'] @@ -1243,7 +1243,7 @@ class StoreEPubBuyDEStore(StoreBase): name = 'EPUBBuy DE' author = 'Charles Haley' description = u'Bei EPUBBuy.com finden Sie ausschliesslich eBooks im weitverbreiteten EPUB-Format und ohne DRM. So haben Sie die freie Wahl, wo Sie Ihr eBook lesen: Tablet, eBook-Reader, Smartphone oder einfach auf Ihrem PC. So macht eBook-Lesen Spaß!' - actual_plugin = 'calibre.gui2.store.epubbuy_de_plugin:EPubBuyDEStore' + actual_plugin = 'calibre.gui2.store.stores.epubbuy_de_plugin:EPubBuyDEStore' drm_free_only = True headquarters = 'DE' @@ -1254,7 +1254,7 @@ class StoreEBookShoppeUKStore(StoreBase): name = 'ebookShoppe UK' author = u'Charles Haley' description = u'We made this website in an attempt to offer the widest range of UK eBooks possible across and as many formats as we could manage.' - actual_plugin = 'calibre.gui2.store.ebookshoppe_uk_plugin:EBookShoppeUKStore' + actual_plugin = 'calibre.gui2.store.stores.ebookshoppe_uk_plugin:EBookShoppeUKStore' headquarters = 'UK' formats = ['EPUB', 'PDF'] @@ -1263,7 +1263,7 @@ class StoreEBookShoppeUKStore(StoreBase): class StoreEHarlequinStore(StoreBase): name = 'eHarlequin' description = u'A global leader in series romance and one of the world\'s leading publishers of books for women. Offers women a broad range of reading from romance to bestseller fiction, from young adult novels to erotic literature, from nonfiction to fantasy, from African-American novels to inspirational romance, and more.' - actual_plugin = 'calibre.gui2.store.eharlequin_plugin:EHarlequinStore' + actual_plugin = 'calibre.gui2.store.stores.eharlequin_plugin:EHarlequinStore' headquarters = 'CA' formats = ['EPUB', 'PDF'] @@ -1272,7 +1272,7 @@ class StoreEHarlequinStore(StoreBase): class StoreEpubBudStore(StoreBase): name = 'ePub Bud' description = 'Well, it\'s pretty much just "YouTube for Children\'s eBooks. A not-for-profit organization devoted to brining self published childrens books to the world.' - actual_plugin = 'calibre.gui2.store.epubbud_plugin:EpubBudStore' + actual_plugin = 'calibre.gui2.store.stores.epubbud_plugin:EpubBudStore' drm_free_only = True headquarters = 'US' @@ -1281,7 +1281,7 @@ class StoreEpubBudStore(StoreBase): class StoreFeedbooksStore(StoreBase): name = 'Feedbooks' description = u'Feedbooks is a cloud publishing and distribution service, connected to a large ecosystem of reading systems and social networks. Provides a variety of genres from independent and classic books.' - actual_plugin = 'calibre.gui2.store.feedbooks_plugin:FeedbooksStore' + actual_plugin = 'calibre.gui2.store.stores.feedbooks_plugin:FeedbooksStore' headquarters = 'FR' formats = ['EPUB', 'MOBI', 'PDF'] @@ -1290,7 +1290,7 @@ class StoreFoylesUKStore(StoreBase): name = 'Foyles UK' author = 'Charles Haley' description = u'Foyles of London\'s ebook store. Provides extensive range covering all subjects.' - actual_plugin = 'calibre.gui2.store.foyles_uk_plugin:FoylesUKStore' + actual_plugin = 'calibre.gui2.store.stores.foyles_uk_plugin:FoylesUKStore' headquarters = 'UK' formats = ['EPUB', 'PDF'] @@ -1300,7 +1300,7 @@ class StoreGandalfStore(StoreBase): name = 'Gandalf' author = u'Tomasz Długosz' description = u'Księgarnia internetowa Gandalf.' - actual_plugin = 'calibre.gui2.store.gandalf_plugin:GandalfStore' + actual_plugin = 'calibre.gui2.store.stores.gandalf_plugin:GandalfStore' headquarters = 'PL' formats = ['EPUB', 'PDF'] @@ -1308,7 +1308,7 @@ class StoreGandalfStore(StoreBase): class StoreGoogleBooksStore(StoreBase): name = 'Google Books' description = u'Google Books' - actual_plugin = 'calibre.gui2.store.google_books_plugin:GoogleBooksStore' + actual_plugin = 'calibre.gui2.store.stores.google_books_plugin:GoogleBooksStore' headquarters = 'US' formats = ['EPUB', 'PDF', 'TXT'] @@ -1316,7 +1316,7 @@ class StoreGoogleBooksStore(StoreBase): class StoreGutenbergStore(StoreBase): name = 'Project Gutenberg' description = u'The first producer of free ebooks. Free in the United States because their copyright has expired. They may not be free of copyright in other countries. Readers outside of the United States must check the copyright laws of their countries before downloading or redistributing our ebooks.' - actual_plugin = 'calibre.gui2.store.gutenberg_plugin:GutenbergStore' + actual_plugin = 'calibre.gui2.store.stores.gutenberg_plugin:GutenbergStore' drm_free_only = True headquarters = 'US' @@ -1325,7 +1325,7 @@ class StoreGutenbergStore(StoreBase): class StoreKoboStore(StoreBase): name = 'Kobo' description = u'With over 2.3 million eBooks to browse we have engaged readers in over 200 countries in Kobo eReading. Our eBook listings include New York Times Bestsellers, award winners, classics and more!' - actual_plugin = 'calibre.gui2.store.kobo_plugin:KoboStore' + actual_plugin = 'calibre.gui2.store.stores.kobo_plugin:KoboStore' headquarters = 'CA' formats = ['EPUB'] @@ -1335,7 +1335,7 @@ class StoreLegimiStore(StoreBase): name = 'Legimi' author = u'Tomasz Długosz' description = u'Tanie oraz darmowe ebooki, egazety i blogi w formacie EPUB, wprost na Twój e-czytnik, iPhone, iPad, Android i komputer' - actual_plugin = 'calibre.gui2.store.legimi_plugin:LegimiStore' + actual_plugin = 'calibre.gui2.store.stores.legimi_plugin:LegimiStore' headquarters = 'PL' formats = ['EPUB'] @@ -1344,7 +1344,7 @@ class StoreLibreDEStore(StoreBase): name = 'Libri DE' author = 'Charles Haley' description = u'Sicher Bücher, Hörbücher und Downloads online bestellen.' - actual_plugin = 'calibre.gui2.store.libri_de_plugin:LibreDEStore' + actual_plugin = 'calibre.gui2.store.stores.libri_de_plugin:LibreDEStore' headquarters = 'DE' formats = ['EPUB', 'PDF'] @@ -1353,7 +1353,7 @@ class StoreLibreDEStore(StoreBase): class StoreManyBooksStore(StoreBase): name = 'ManyBooks' description = u'Public domain and creative commons works from many sources.' - actual_plugin = 'calibre.gui2.store.manybooks_plugin:ManyBooksStore' + actual_plugin = 'calibre.gui2.store.stores.manybooks_plugin:ManyBooksStore' drm_free_only = True headquarters = 'US' @@ -1362,7 +1362,7 @@ class StoreManyBooksStore(StoreBase): class StoreMobileReadStore(StoreBase): name = 'MobileRead' description = u'Ebooks handcrafted with the utmost care.' - actual_plugin = 'calibre.gui2.store.mobileread.mobileread_plugin:MobileReadStore' + actual_plugin = 'calibre.gui2.store.stores.mobileread.mobileread_plugin:MobileReadStore' drm_free_only = True headquarters = 'CH' @@ -1372,16 +1372,24 @@ class StoreNextoStore(StoreBase): name = 'Nexto' author = u'Tomasz Długosz' description = u'Największy w Polsce sklep internetowy z audiobookami mp3, ebookami pdf oraz prasą do pobrania on-line.' - actual_plugin = 'calibre.gui2.store.nexto_plugin:NextoStore' + actual_plugin = 'calibre.gui2.store.stores.nexto_plugin:NextoStore' headquarters = 'PL' formats = ['EPUB', 'PDF'] affiliate = True +class StoreOpenBooksStore(StoreBase): + name = 'Open Books' + description = u'Comprehensive listing of DRM free ebooks from a variety of sources provided by users of calibre.' + actual_plugin = 'calibre.gui2.store.stores.open_books_plugin:OpenBooksStore' + + drm_free_only = True + headquarters = 'US' + class StoreOpenLibraryStore(StoreBase): name = 'Open Library' description = u'One web page for every book ever published. The goal is to be a true online library. Over 20 million records from a variety of large catalogs as well as single contributions, with more on the way.' - actual_plugin = 'calibre.gui2.store.open_library_plugin:OpenLibraryStore' + actual_plugin = 'calibre.gui2.store.stores.open_library_plugin:OpenLibraryStore' drm_free_only = True headquarters = 'US' @@ -1390,7 +1398,7 @@ class StoreOpenLibraryStore(StoreBase): class StoreOReillyStore(StoreBase): name = 'OReilly' description = u'Programming and tech ebooks from OReilly.' - actual_plugin = 'calibre.gui2.store.oreilly_plugin:OReillyStore' + actual_plugin = 'calibre.gui2.store.stores.oreilly_plugin:OReillyStore' drm_free_only = True headquarters = 'US' @@ -1399,7 +1407,7 @@ class StoreOReillyStore(StoreBase): class StorePragmaticBookshelfStore(StoreBase): name = 'Pragmatic Bookshelf' description = u'The Pragmatic Bookshelf\'s collection of programming and tech books avaliable as ebooks.' - actual_plugin = 'calibre.gui2.store.pragmatic_bookshelf_plugin:PragmaticBookshelfStore' + actual_plugin = 'calibre.gui2.store.stores.pragmatic_bookshelf_plugin:PragmaticBookshelfStore' drm_free_only = True headquarters = 'US' @@ -1408,7 +1416,7 @@ class StorePragmaticBookshelfStore(StoreBase): class StoreSmashwordsStore(StoreBase): name = 'Smashwords' description = u'An ebook publishing and distribution platform for ebook authors, publishers and readers. Covers many genres and formats.' - actual_plugin = 'calibre.gui2.store.smashwords_plugin:SmashwordsStore' + actual_plugin = 'calibre.gui2.store.stores.smashwords_plugin:SmashwordsStore' drm_free_only = True headquarters = 'US' @@ -1419,7 +1427,7 @@ class StoreVirtualoStore(StoreBase): name = 'Virtualo' author = u'Tomasz Długosz' description = u'Księgarnia internetowa, która oferuje bezpieczny i szeroki dostęp do książek w formie cyfrowej.' - actual_plugin = 'calibre.gui2.store.virtualo_plugin:VirtualoStore' + actual_plugin = 'calibre.gui2.store.stores.virtualo_plugin:VirtualoStore' headquarters = 'PL' formats = ['EPUB', 'PDF'] @@ -1428,7 +1436,7 @@ class StoreWaterstonesUKStore(StoreBase): name = 'Waterstones UK' author = 'Charles Haley' description = u'Waterstone\'s mission is to be the leading Bookseller on the High Street and online providing customers the widest choice, great value and expert advice from a team passionate about Bookselling.' - actual_plugin = 'calibre.gui2.store.waterstones_uk_plugin:WaterstonesUKStore' + actual_plugin = 'calibre.gui2.store.stores.waterstones_uk_plugin:WaterstonesUKStore' headquarters = 'UK' formats = ['EPUB', 'PDF'] @@ -1436,7 +1444,7 @@ class StoreWaterstonesUKStore(StoreBase): class StoreWeightlessBooksStore(StoreBase): name = 'Weightless Books' description = u'An independent DRM-free ebooksite devoted to ebooks of all sorts.' - actual_plugin = 'calibre.gui2.store.weightless_books_plugin:WeightlessBooksStore' + actual_plugin = 'calibre.gui2.store.stores.weightless_books_plugin:WeightlessBooksStore' drm_free_only = True headquarters = 'US' @@ -1446,7 +1454,7 @@ class StoreWHSmithUKStore(StoreBase): name = 'WH Smith UK' author = 'Charles Haley' description = u"Shop for savings on Books, discounted Magazine subscriptions and great prices on Stationery, Toys & Games" - actual_plugin = 'calibre.gui2.store.whsmith_uk_plugin:WHSmithUKStore' + actual_plugin = 'calibre.gui2.store.stores.whsmith_uk_plugin:WHSmithUKStore' headquarters = 'UK' formats = ['EPUB', 'PDF'] @@ -1454,7 +1462,7 @@ class StoreWHSmithUKStore(StoreBase): class StoreWizardsTowerBooksStore(StoreBase): name = 'Wizards Tower Books' description = u'A science fiction and fantasy publisher. Concentrates mainly on making out-of-print works available once more as e-books, and helping other small presses exploit the e-book market. Also publishes a small number of limited-print-run anthologies with a view to encouraging diversity in the science fiction and fantasy field.' - actual_plugin = 'calibre.gui2.store.wizards_tower_books_plugin:WizardsTowerBooksStore' + actual_plugin = 'calibre.gui2.store.stores.wizards_tower_books_plugin:WizardsTowerBooksStore' drm_free_only = True headquarters = 'UK' @@ -1464,7 +1472,7 @@ class StoreWoblinkStore(StoreBase): name = 'Woblink' author = u'Tomasz Długosz' description = u'Czytanie zdarza się wszędzie!' - actual_plugin = 'calibre.gui2.store.woblink_plugin:WoblinkStore' + actual_plugin = 'calibre.gui2.store.stores.woblink_plugin:WoblinkStore' headquarters = 'PL' formats = ['EPUB'] @@ -1473,7 +1481,7 @@ class StoreZixoStore(StoreBase): name = 'Zixo' author = u'Tomasz Długosz' description = u'Księgarnia z ebookami oraz książkami audio. Aby otwierać książki w formacie Zixo należy zainstalować program dostępny na stronie księgarni. Umożliwia on m.in. dodawanie zakładek i dostosowywanie rozmiaru czcionki.' - actual_plugin = 'calibre.gui2.store.zixo_plugin:ZixoStore' + actual_plugin = 'calibre.gui2.store.stores.zixo_plugin:ZixoStore' headquarters = 'PL' formats = ['PDF, ZIXO'] @@ -1504,6 +1512,7 @@ plugins += [ StoreManyBooksStore, StoreMobileReadStore, StoreNextoStore, + StoreOpenBooksStore, StoreOpenLibraryStore, StoreOReillyStore, StorePragmaticBookshelfStore, diff --git a/src/calibre/devices/android/driver.py b/src/calibre/devices/android/driver.py index 40cc3a34dc..2c840c644a 100644 --- a/src/calibre/devices/android/driver.py +++ b/src/calibre/devices/android/driver.py @@ -45,8 +45,11 @@ class ANDROID(USBMS): 0xfce : { 0xd12e : [0x0100]}, # Google - 0x18d1 : { 0x4e11 : [0x0100, 0x226, 0x227], 0x4e12: [0x0100, 0x226, - 0x227], 0x4e21: [0x0100, 0x226, 0x227], 0xb058: [0x0222]}, + 0x18d1 : { + 0x4e11 : [0x0100, 0x226, 0x227], + 0x4e12: [0x0100, 0x226, 0x227], + 0x4e21: [0x0100, 0x226, 0x227], + 0xb058: [0x0222, 0x226, 0x227]}, # Samsung 0x04e8 : { 0x681d : [0x0222, 0x0223, 0x0224, 0x0400], @@ -107,7 +110,7 @@ class ANDROID(USBMS): VENDOR_NAME = ['HTC', 'MOTOROLA', 'GOOGLE_', 'ANDROID', 'ACER', 'GT-I5700', 'SAMSUNG', 'DELL', 'LINUX', 'GOOGLE', 'ARCHOS', 'TELECHIP', 'HUAWEI', 'T-MOBILE', 'SEMC', 'LGE', 'NVIDIA', - 'GENERIC-', 'ZTE'] + 'GENERIC-', 'ZTE', 'MID'] WINDOWS_MAIN_MEM = ['ANDROID_PHONE', 'A855', 'A853', 'INC.NEXUS_ONE', '__UMS_COMPOSITE', '_MB200', 'MASS_STORAGE', '_-_CARD', 'SGH-I897', 'GT-I9000', 'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID', @@ -116,7 +119,7 @@ class ANDROID(USBMS): 'IDEOS_TABLET', 'MYTOUCH_4G', 'UMS_COMPOSITE', 'SCH-I800_CARD', '7', 'A956', 'A955', 'A43', 'ANDROID_PLATFORM', 'TEGRA_2', 'MB860', 'MULTI-CARD', 'MID7015A', 'INCREDIBLE', 'A7EB', 'STREAK', - 'MB525'] + 'MB525', 'ANDROID2.3'] WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897', 'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD', 'A70S', 'A101IT', '7', 'INCREDIBLE', 'A7EB', 'SGH-T849_CARD', diff --git a/src/calibre/devices/iriver/driver.py b/src/calibre/devices/iriver/driver.py index 0ad540f8a3..21b188e031 100644 --- a/src/calibre/devices/iriver/driver.py +++ b/src/calibre/devices/iriver/driver.py @@ -20,11 +20,11 @@ class IRIVER_STORY(USBMS): FORMATS = ['epub', 'fb2', 'pdf', 'djvu', 'txt'] VENDOR_ID = [0x1006] - PRODUCT_ID = [0x4023, 0x4024, 0x4025] - BCD = [0x0323] + PRODUCT_ID = [0x4023, 0x4024, 0x4025, 0x4034] + BCD = [0x0323, 0x0326] VENDOR_NAME = 'IRIVER' - WINDOWS_MAIN_MEM = ['STORY', 'STORY_EB05', 'STORY_WI-FI'] + WINDOWS_MAIN_MEM = ['STORY', 'STORY_EB05', 'STORY_WI-FI', 'STORY_EB07'] WINDOWS_CARD_A_MEM = ['STORY', 'STORY_SD'] #OSX_MAIN_MEM = 'Kindle Internal Storage Media' diff --git a/src/calibre/devices/usbms/books.py b/src/calibre/devices/usbms/books.py index 731d3e2b49..4d726e5bde 100644 --- a/src/calibre/devices/usbms/books.py +++ b/src/calibre/devices/usbms/books.py @@ -14,7 +14,7 @@ from calibre.constants import preferred_encoding from calibre import isbytestring, force_unicode from calibre.utils.config import prefs, tweaks from calibre.utils.icu import strcmp -from calibre.utils.formatter import eval_formatter +from calibre.utils.formatter import EvalFormatter class Book(Metadata): def __init__(self, prefix, lpath, size=None, other=None): @@ -116,7 +116,7 @@ class CollectionsBookList(BookList): field_name = field_meta['name'] else: field_name = '' - cat_name = eval_formatter.safe_format( + cat_name = EvalFormatter().safe_format( fmt=tweaks['sony_collection_name_template'], kwargs={'category':field_name, 'value':field_value}, error_value='GET_CATEGORY', book=None) diff --git a/src/calibre/ebooks/comic/input.py b/src/calibre/ebooks/comic/input.py index 5203e3698d..f6833ca197 100755 --- a/src/calibre/ebooks/comic/input.py +++ b/src/calibre/ebooks/comic/input.py @@ -351,7 +351,9 @@ class ComicInput(InputFormatPlugin): comics = [] with CurrentDir(tdir): if not os.path.exists('comics.txt'): - raise ValueError('%s is not a valid comic collection' + raise ValueError(( + '%s is not a valid comic collection' + ' no comics.txt was found in the file') %stream.name) raw = open('comics.txt', 'rb').read() if raw.startswith(codecs.BOM_UTF16_BE): diff --git a/src/calibre/ebooks/compression/palmdoc.py b/src/calibre/ebooks/compression/palmdoc.py index 90dabcb5a8..6069777fab 100644 --- a/src/calibre/ebooks/compression/palmdoc.py +++ b/src/calibre/ebooks/compression/palmdoc.py @@ -17,6 +17,8 @@ def decompress_doc(data): return cPalmdoc.decompress(data) def compress_doc(data): + if not data: + return u'' return cPalmdoc.compress(data) def test(): diff --git a/src/calibre/ebooks/conversion/plumber.py b/src/calibre/ebooks/conversion/plumber.py index 3eb59a21b9..9ec474e60f 100644 --- a/src/calibre/ebooks/conversion/plumber.py +++ b/src/calibre/ebooks/conversion/plumber.py @@ -59,6 +59,8 @@ class CompositeProgressReporter(object): (self.global_max - self.global_min) self.global_reporter(global_frac, msg) +ARCHIVE_FMTS = ('zip', 'rar', 'oebzip') + class Plumber(object): ''' The `Plumber` manages the conversion pipeline. An UI should call the methods @@ -594,7 +596,7 @@ OptionRecommendation(name='sr3_replace', raise ValueError('Input file must have an extension') input_fmt = input_fmt[1:].lower() self.archive_input_tdir = None - if input_fmt in ('zip', 'rar', 'oebzip'): + if input_fmt in ARCHIVE_FMTS: self.log('Processing archive...') tdir = PersistentTemporaryDirectory('_plumber_archive') self.input, input_fmt = self.unarchive(self.input, tdir) diff --git a/src/calibre/ebooks/metadata/book/base.py b/src/calibre/ebooks/metadata/book/base.py index c28c65f7c9..3be37d922e 100644 --- a/src/calibre/ebooks/metadata/book/base.py +++ b/src/calibre/ebooks/metadata/book/base.py @@ -71,6 +71,7 @@ class SafeFormat(TemplateFormatter): return '' return v +# DEPRECATED. This is not thread safe. Do not use. composite_formatter = SafeFormat() class Metadata(object): @@ -111,6 +112,7 @@ class Metadata(object): # List of strings or [] self.author = list(authors) if authors else []# Needed for backward compatibility self.authors = list(authors) if authors else [] + self.formatter = SafeFormat() def is_null(self, field): ''' @@ -147,7 +149,7 @@ class Metadata(object): return val if val is None: d['#value#'] = 'RECURSIVE_COMPOSITE FIELD (Metadata) ' + field - val = d['#value#'] = composite_formatter.safe_format( + val = d['#value#'] = self.formatter.safe_format( d['display']['composite_template'], self, _('TEMPLATE ERROR'), @@ -424,11 +426,12 @@ class Metadata(object): ''' if not ops: return + formatter = SafeFormat() for op in ops: try: src = op[0] dest = op[1] - val = composite_formatter.safe_format\ + val = formatter.safe_format\ (src, other, 'PLUGBOARD TEMPLATE ERROR', other) if dest == 'tags': self.set(dest, [f.strip() for f in val.split(',') if f.strip()]) diff --git a/src/calibre/gui2/__init__.py b/src/calibre/gui2/__init__.py index 0b21502327..8dbc72ab98 100644 --- a/src/calibre/gui2/__init__.py +++ b/src/calibre/gui2/__init__.py @@ -7,12 +7,13 @@ from urllib import unquote from PyQt4.Qt import (QVariant, QFileInfo, QObject, SIGNAL, QBuffer, Qt, QByteArray, QTranslator, QCoreApplication, QThread, QEvent, QTimer, pyqtSignal, QDate, QDesktopServices, - QFileDialog, QFileIconProvider, + QFileDialog, QFileIconProvider, QSettings, QIcon, QApplication, QDialog, QUrl, QFont) ORG_NAME = 'KovidsBrain' APP_UID = 'libprs500' -from calibre.constants import islinux, iswindows, isbsd, isfrozen, isosx +from calibre.constants import (islinux, iswindows, isbsd, isfrozen, isosx, + config_dir) from calibre.utils.config import Config, ConfigProxy, dynamic, JSONConfig from calibre.utils.localization import set_qt_translator from calibre.ebooks.metadata import MetaInformation @@ -192,6 +193,11 @@ def _config(): # {{{ config = _config() # }}} +QSettings.setPath(QSettings.IniFormat, QSettings.UserScope, config_dir) +QSettings.setPath(QSettings.IniFormat, QSettings.SystemScope, + config_dir) +QSettings.setDefaultFormat(QSettings.IniFormat) + # Turn off DeprecationWarnings in windows GUI if iswindows: import warnings diff --git a/src/calibre/gui2/actions/choose_library.py b/src/calibre/gui2/actions/choose_library.py index 32460b6bec..f96a261790 100644 --- a/src/calibre/gui2/actions/choose_library.py +++ b/src/calibre/gui2/actions/choose_library.py @@ -5,7 +5,7 @@ __license__ = 'GPL v3' __copyright__ = '2010, Kovid Goyal ' __docformat__ = 'restructuredtext en' -import os, shutil +import os from functools import partial from PyQt4.Qt import QMenu, Qt, QInputDialog, QToolButton @@ -14,7 +14,7 @@ from calibre import isbytestring from calibre.constants import filesystem_encoding, iswindows from calibre.utils.config import prefs from calibre.gui2 import (gprefs, warning_dialog, Dispatcher, error_dialog, - question_dialog, info_dialog) + question_dialog, info_dialog, open_local_file) from calibre.library.database2 import LibraryDatabase2 from calibre.gui2.actions import InterfaceAction @@ -107,7 +107,7 @@ class ChooseLibraryAction(InterfaceAction): self.quick_menu_action = self.choose_menu.addMenu(self.quick_menu) self.rename_menu = QMenu(_('Rename library')) self.rename_menu_action = self.choose_menu.addMenu(self.rename_menu) - self.delete_menu = QMenu(_('Delete library')) + self.delete_menu = QMenu(_('Remove library')) self.delete_menu_action = self.choose_menu.addMenu(self.delete_menu) ac = self.create_action(spec=(_('Pick a random book'), 'catalog.png', @@ -252,22 +252,15 @@ class ChooseLibraryAction(InterfaceAction): def delete_requested(self, name, location): loc = location.replace('/', os.sep) - if not question_dialog(self.gui, _('Are you sure?'), - _('

WARNING

')+ - _('All files (not just ebooks) ' - 'from

%s

will be ' - 'permanently deleted. Are you sure?') % loc, - show_copy_button=False, default_yes=False): - return - exists = self.gui.library_view.model().db.exists_at(loc) - if exists: - try: - shutil.rmtree(loc, ignore_errors=True) - except: - pass self.stats.remove(location) self.build_menus() self.gui.iactions['Copy To Library'].build_menus() + info_dialog(self.gui, _('Library removed'), + _('The library %s has been removed from calibre. ' + 'The files remain on your computer, if you want ' + 'to delete them, you will have to do so manually.') % loc, + show=True) + open_local_file(loc) def backup_status(self, location): dirty_text = 'no' diff --git a/src/calibre/gui2/convert/regex_builder.py b/src/calibre/gui2/convert/regex_builder.py index f79e6df3fe..c7b03c9bb4 100644 --- a/src/calibre/gui2/convert/regex_builder.py +++ b/src/calibre/gui2/convert/regex_builder.py @@ -139,7 +139,12 @@ class RegexBuilder(QDialog, Ui_RegexBuilder): try: self.open_book(fpath) finally: - os.remove(fpath) + try: + os.remove(fpath) + except: + # Fails on windows if the input plugin for this format keeps the file open + # Happens for LIT files + pass return True def open_book(self, pathtoebook): @@ -148,7 +153,8 @@ class RegexBuilder(QDialog, Ui_RegexBuilder): text = [u''] preprocessor = HTMLPreProcessor(None, False) for path in self.iterator.spine: - html = open(path, 'rb').read().decode('utf-8', 'replace') + with open(path, 'rb') as f: + html = f.read().decode('utf-8', 'replace') html = preprocessor(html, get_preprocess_html=True) text.append(html) self.preview.setPlainText('\n---\n'.join(text)) diff --git a/src/calibre/gui2/convert/single.py b/src/calibre/gui2/convert/single.py index 15e670ee32..9a9f55be3b 100644 --- a/src/calibre/gui2/convert/single.py +++ b/src/calibre/gui2/convert/single.py @@ -11,8 +11,8 @@ import sys, cPickle, shutil, importlib from PyQt4.Qt import QString, SIGNAL, QAbstractListModel, Qt, QVariant, QFont from calibre.gui2 import ResizableDialog, NONE -from calibre.ebooks.conversion.config import GuiRecommendations, save_specifics, \ - load_specifics +from calibre.ebooks.conversion.config import (GuiRecommendations, save_specifics, + load_specifics) from calibre.gui2.convert.single_ui import Ui_Dialog from calibre.gui2.convert.metadata import MetadataWidget from calibre.gui2.convert.look_and_feel import LookAndFeelWidget @@ -24,7 +24,8 @@ from calibre.gui2.convert.toc import TOCWidget from calibre.gui2.convert.debug import DebugWidget -from calibre.ebooks.conversion.plumber import Plumber, supported_input_formats +from calibre.ebooks.conversion.plumber import (Plumber, + supported_input_formats, ARCHIVE_FMTS) from calibre.ebooks.conversion.config import delete_specifics from calibre.customize.ui import available_output_formats from calibre.customize.conversion import OptionRecommendation @@ -158,7 +159,10 @@ class Config(ResizableDialog, Ui_Dialog): output_path = 'dummy.'+output_format log = Log() log.outputs = [] - self.plumber = Plumber('dummy.'+input_format, output_path, log) + input_file = 'dummy.'+input_format + if input_format in ARCHIVE_FMTS: + input_file = 'dummy.html' + self.plumber = Plumber(input_file, output_path, log) def widget_factory(cls): return cls(self.stack, self.plumber.get_option_by_name, diff --git a/src/calibre/gui2/dialogs/metadata_bulk.py b/src/calibre/gui2/dialogs/metadata_bulk.py index 7c7c78629c..22dfb98956 100644 --- a/src/calibre/gui2/dialogs/metadata_bulk.py +++ b/src/calibre/gui2/dialogs/metadata_bulk.py @@ -12,7 +12,7 @@ from PyQt4.Qt import Qt, QDialog, QGridLayout, QVBoxLayout, QFont, QLabel, \ from calibre.gui2.dialogs.metadata_bulk_ui import Ui_MetadataBulkDialog from calibre.gui2.dialogs.tag_editor import TagEditor from calibre.ebooks.metadata import string_to_authors, authors_to_string, title_sort -from calibre.ebooks.metadata.book.base import composite_formatter +from calibre.ebooks.metadata.book.base import SafeFormat from calibre.gui2.custom_column_widgets import populate_metadata_page from calibre.gui2 import error_dialog, ResizableDialog, UNDEFINED_QDATE, \ gprefs, question_dialog @@ -499,7 +499,7 @@ class MetadataBulkDialog(ResizableDialog, Ui_MetadataBulkDialog): def s_r_get_field(self, mi, field): if field: if field == '{template}': - v = composite_formatter.safe_format\ + v = SafeFormat().safe_format\ (unicode(self.s_r_template.text()), mi, _('S/R TEMPLATE ERROR'), mi) return [v] fm = self.db.metadata_for_field(field) diff --git a/src/calibre/gui2/dialogs/template_dialog.py b/src/calibre/gui2/dialogs/template_dialog.py index f78e7a7383..7d30f37bc1 100644 --- a/src/calibre/gui2/dialogs/template_dialog.py +++ b/src/calibre/gui2/dialogs/template_dialog.py @@ -11,7 +11,7 @@ from PyQt4.Qt import (Qt, QDialog, QDialogButtonBox, QSyntaxHighlighter, QFont, from calibre.gui2 import error_dialog from calibre.gui2.dialogs.template_dialog_ui import Ui_TemplateDialog from calibre.utils.formatter_functions import formatter_functions -from calibre.ebooks.metadata.book.base import composite_formatter, Metadata +from calibre.ebooks.metadata.book.base import SafeFormat, Metadata from calibre.library.coloring import (displayable_columns) @@ -270,7 +270,7 @@ class TemplateDialog(QDialog, Ui_TemplateDialog): self.highlighter.regenerate_paren_positions() self.text_cursor_changed() self.template_value.setText( - composite_formatter.safe_format(cur_text, self.mi, + SafeFormat().safe_format(cur_text, self.mi, _('EXCEPTION: '), self.mi)) def text_cursor_changed(self): diff --git a/src/calibre/gui2/init.py b/src/calibre/gui2/init.py index 874be6832f..67b4d5edd6 100644 --- a/src/calibre/gui2/init.py +++ b/src/calibre/gui2/init.py @@ -16,7 +16,7 @@ from calibre.constants import isosx, __appname__, preferred_encoding, \ from calibre.gui2 import config, is_widescreen, gprefs from calibre.gui2.library.views import BooksView, DeviceBooksView from calibre.gui2.widgets import Splitter -from calibre.gui2.tag_view import TagBrowserWidget +from calibre.gui2.tag_browser.ui import TagBrowserWidget from calibre.gui2.book_details import BookDetails from calibre.gui2.notify import get_notifier diff --git a/src/calibre/gui2/library/models.py b/src/calibre/gui2/library/models.py index d4aeada313..b3cba27bc9 100644 --- a/src/calibre/gui2/library/models.py +++ b/src/calibre/gui2/library/models.py @@ -14,7 +14,7 @@ from PyQt4.Qt import (QAbstractTableModel, Qt, pyqtSignal, QIcon, QImage, from calibre.gui2 import NONE, UNDEFINED_QDATE from calibre.utils.pyparsing import ParseException from calibre.ebooks.metadata import fmt_sidx, authors_to_string, string_to_authors -from calibre.ebooks.metadata.book.base import composite_formatter +from calibre.ebooks.metadata.book.base import SafeFormat from calibre.ptempfile import PersistentTemporaryFile from calibre.utils.config import tweaks, prefs from calibre.utils.date import dt_factory, qt_to_dt @@ -92,6 +92,7 @@ class BooksModel(QAbstractTableModel): # {{{ self.highlight_only = False self.current_row = -1 self.colors = frozenset([unicode(c) for c in QColor.colorNames()]) + self.formatter = SafeFormat() self.read_config() def change_alignment(self, colname, alignment): @@ -717,7 +718,7 @@ class BooksModel(QAbstractTableModel): # {{{ try: if mi is None: mi = self.db.get_metadata(id_, index_is_id=True) - color = composite_formatter.safe_format(fmt, mi, '', mi) + color = self.formatter.safe_format(fmt, mi, '', mi) if color in self.colors: color = QColor(color) if color.isValid(): diff --git a/src/calibre/gui2/metadata/basic_widgets.py b/src/calibre/gui2/metadata/basic_widgets.py index e00af37d33..2d6c79d0e3 100644 --- a/src/calibre/gui2/metadata/basic_widgets.py +++ b/src/calibre/gui2/metadata/basic_widgets.py @@ -173,9 +173,20 @@ class TitleSortEdit(TitleEdit): def auto_generate(self, *args): self.current_val = title_sort(self.title_edit.current_val) - self.title_edit.textChanged.disconnect() - self.textChanged.disconnect() - self.autogen_button.clicked.disconnect() + + def break_cycles(self): + try: + self.title_edit.textChanged.disconnect() + except: + pass + try: + self.textChanged.disconnect() + except: + pass + try: + self.autogen_button.clicked.disconnect() + except: + pass # }}} @@ -280,7 +291,10 @@ class AuthorsEdit(MultiCompleteComboBox): def break_cycles(self): self.db = self.dialog = None - self.manage_authors_signal.triggered.disconnect() + try: + self.manage_authors_signal.triggered.disconnect() + except: + pass class AuthorSortEdit(EnLineEdit): @@ -387,11 +401,26 @@ class AuthorSortEdit(EnLineEdit): def break_cycles(self): self.db = None - self.authors_edit.editTextChanged.disconnect() - self.textChanged.disconnect() - self.autogen_button.clicked.disconnect() - self.copy_a_to_as_action.triggered.disconnect() - self.copy_as_to_a_action.triggered.disconnect() + try: + self.authors_edit.editTextChanged.disconnect() + except: + pass + try: + self.textChanged.disconnect() + except: + pass + try: + self.autogen_button.clicked.disconnect() + except: + pass + try: + self.copy_a_to_as_action.triggered.disconnect() + except: + pass + try: + self.copy_as_to_a_action.triggered.disconnect() + except: + pass self.authors_edit = None # }}} @@ -519,9 +548,18 @@ class SeriesIndexEdit(QDoubleSpinBox): traceback.print_exc() def break_cycles(self): - self.series_edit.currentIndexChanged.disconnect() - self.series_edit.editTextChanged.disconnect() - self.series_edit.lineEdit().editingFinished.disconnect() + try: + self.series_edit.currentIndexChanged.disconnect() + except: + pass + try: + self.series_edit.editTextChanged.disconnect() + except: + pass + try: + self.series_edit.lineEdit().editingFinished.disconnect() + except: + pass self.db = self.series_edit = self.dialog = None # }}} @@ -898,7 +936,10 @@ class Cover(ImageView): # {{{ return True def break_cycles(self): - self.cover_changed.disconnect() + try: + self.cover_changed.disconnect() + except: + pass self.dialog = self._cdata = self.current_val = self.original_val = None # }}} diff --git a/src/calibre/gui2/store/archive_org_plugin.py b/src/calibre/gui2/store/archive_org_plugin.py deleted file mode 100644 index e8e96b3839..0000000000 --- a/src/calibre/gui2/store/archive_org_plugin.py +++ /dev/null @@ -1,89 +0,0 @@ -# -*- coding: utf-8 -*- - -from __future__ import (unicode_literals, division, absolute_import, print_function) - -__license__ = 'GPL 3' -__copyright__ = '2011, John Schember ' -__docformat__ = 'restructuredtext en' - -import urllib -from contextlib import closing - -from lxml import html - -from PyQt4.Qt import QUrl - -from calibre import browser, url_slash_cleaner -from calibre.gui2 import open_url -from calibre.gui2.store import StorePlugin -from calibre.gui2.store.basic_config import BasicStoreConfig -from calibre.gui2.store.search_result import SearchResult -from calibre.gui2.store.web_store_dialog import WebStoreDialog - -class ArchiveOrgStore(BasicStoreConfig, StorePlugin): - - def open(self, parent=None, detail_item=None, external=False): - url = 'http://www.archive.org/details/texts' - - if detail_item: - detail_item = url_slash_cleaner('http://www.archive.org' + detail_item) - - if external or self.config.get('open_external', False): - open_url(QUrl(url_slash_cleaner(detail_item if detail_item else url))) - else: - d = WebStoreDialog(self.gui, url, parent, detail_item) - d.setWindowTitle(self.name) - d.set_tags(self.config.get('tags', '')) - d.exec_() - - def search(self, query, max_results=10, timeout=60): - query = query + ' AND mediatype:texts' - url = 'http://www.archive.org/search.php?query=' + urllib.quote(query) - - br = browser() - - counter = max_results - with closing(br.open(url, timeout=timeout)) as f: - doc = html.fromstring(f.read()) - for data in doc.xpath('//td[@class="hitCell"]'): - if counter <= 0: - break - - id = ''.join(data.xpath('.//a[@class="titleLink"]/@href')) - if not id: - continue - - title = ''.join(data.xpath('.//a[@class="titleLink"]//text()')) - authors = data.xpath('.//text()') - if not authors: - continue - author = None - for a in authors: - if '-' in a: - author = a.replace('-', ' ').strip() - if author: - break - if not author: - continue - - counter -= 1 - - s = SearchResult() - s.title = title.strip() - s.author = author.strip() - s.price = '$0.00' - s.detail_item = id.strip() - s.drm = SearchResult.DRM_UNLOCKED - - yield s - - def get_details(self, search_result, timeout): - url = url_slash_cleaner('http://www.archive.org' + search_result.detail_item) - - br = browser() - with closing(br.open(url, timeout=timeout)) as nf: - idata = html.fromstring(nf.read()) - formats = ', '.join(idata.xpath('//p[@id="dl" and @class="content"]//a/text()')) - search_result.formats = formats.upper() - - return True diff --git a/src/calibre/gui2/store/config/chooser/models.py b/src/calibre/gui2/store/config/chooser/models.py index dbda367fae..d2c6bcd8d3 100644 --- a/src/calibre/gui2/store/config/chooser/models.py +++ b/src/calibre/gui2/store/config/chooser/models.py @@ -133,7 +133,7 @@ class Matches(QAbstractItemModel): return QVariant('

%s

' % result.description) elif col == 2: if result.drm_free_only: - return QVariant('

' + _('This store only distributes ebooks with DRM.') + '

') + return QVariant('

' + _('This store only distributes ebooks without DRM.') + '

') else: return QVariant('

' + _('This store distributes ebooks with DRM. It may have some titles without DRM, but you will need to check on a per title basis.') + '

') elif col == 3: diff --git a/src/calibre/gui2/store/declined.txt b/src/calibre/gui2/store/declined.txt index ada839662d..3e553f2dc8 100644 --- a/src/calibre/gui2/store/declined.txt +++ b/src/calibre/gui2/store/declined.txt @@ -1,9 +1,6 @@ This is a list of stores that objected, declined or asked not to be included in the store integration. -* Borders (http://www.borders.com/) -* Indigo (http://www.chapters.indigo.ca/) +* Borders (http://www.borders.com/). +* Indigo (http://www.chapters.indigo.ca/). * Libraria Rizzoli (http://libreriarizzoli.corriere.it/). - No reply with two attempts over 2 weeks -* WH Smith (http://www.whsmith.co.uk/) - Refused to permit signing up for the affiliate program \ No newline at end of file diff --git a/src/calibre/gui2/store/feedbooks_plugin.py b/src/calibre/gui2/store/feedbooks_plugin.py deleted file mode 100644 index 9b1f7f6574..0000000000 --- a/src/calibre/gui2/store/feedbooks_plugin.py +++ /dev/null @@ -1,106 +0,0 @@ -# -*- coding: utf-8 -*- - -from __future__ import (unicode_literals, division, absolute_import, print_function) - -__license__ = 'GPL 3' -__copyright__ = '2011, John Schember ' -__docformat__ = 'restructuredtext en' - -import urllib2 -from contextlib import closing - -from lxml import html - -from PyQt4.Qt import QUrl - -from calibre import browser, url_slash_cleaner -from calibre.gui2 import open_url -from calibre.gui2.store import StorePlugin -from calibre.gui2.store.basic_config import BasicStoreConfig -from calibre.gui2.store.search_result import SearchResult -from calibre.gui2.store.web_store_dialog import WebStoreDialog - -class FeedbooksStore(BasicStoreConfig, StorePlugin): - - def open(self, parent=None, detail_item=None, external=False): - url = 'http://m.feedbooks.com/' - ext_url = 'http://feedbooks.com/' - - if external or self.config.get('open_external', False): - if detail_item: - ext_url = ext_url + detail_item - open_url(QUrl(url_slash_cleaner(ext_url))) - else: - detail_url = None - if detail_item: - detail_url = url + detail_item - d = WebStoreDialog(self.gui, url, parent, detail_url) - d.setWindowTitle(self.name) - d.set_tags(self.config.get('tags', '')) - d.exec_() - - def search(self, query, max_results=10, timeout=60): - url = 'http://m.feedbooks.com/search?query=' + urllib2.quote(query) - - br = browser() - - counter = max_results - with closing(br.open(url, timeout=timeout)) as f: - doc = html.fromstring(f.read()) - for data in doc.xpath('//ul[@class="m-list"]//li'): - if counter <= 0: - break - data = html.fromstring(html.tostring(data)) - - id = '' - id_a = data.xpath('//a[@class="buy"]') - if id_a: - id = id_a[0].get('href', None) - id = id.split('/')[-2] - id = '/item/' + id - else: - id_a = data.xpath('//a[@class="download"]') - if id_a: - id = id_a[0].get('href', None) - id = id.split('/')[-1] - id = id.split('.')[0] - id = '/book/' + id - if not id: - continue - - title = ''.join(data.xpath('//h5//a/text()')) - author = ''.join(data.xpath('//h6//a/text()')) - price = ''.join(data.xpath('//a[@class="buy"]/text()')) - formats = 'EPUB' - if not price: - price = '$0.00' - formats = 'EPUB, MOBI, PDF' - cover_url = '' - cover_url_img = data.xpath('//img') - if cover_url_img: - cover_url = cover_url_img[0].get('src') - cover_url.split('?')[0] - - counter -= 1 - - s = SearchResult() - s.cover_url = cover_url - s.title = title.strip() - s.author = author.strip() - s.price = price.replace(' ', '').strip() - s.detail_item = id.strip() - s.formats = formats - - yield s - - def get_details(self, search_result, timeout): - url = 'http://m.feedbooks.com/' - - br = browser() - with closing(br.open(url_slash_cleaner(url + search_result.detail_item), timeout=timeout)) as nf: - idata = html.fromstring(nf.read()) - if idata.xpath('boolean(//div[contains(@class, "m-description-long")]//p[contains(., "DRM") or contains(b, "Protection")])'): - search_result.drm = SearchResult.DRM_LOCKED - else: - search_result.drm = SearchResult.DRM_UNLOCKED - return True diff --git a/src/calibre/gui2/store/opensearch_store.py b/src/calibre/gui2/store/opensearch_store.py new file mode 100644 index 0000000000..8a25a80132 --- /dev/null +++ b/src/calibre/gui2/store/opensearch_store.py @@ -0,0 +1,75 @@ +# -*- coding: utf-8 -*- + +from __future__ import (unicode_literals, division, absolute_import, print_function) + +__license__ = 'GPL 3' +__copyright__ = '2011, John Schember ' +__docformat__ = 'restructuredtext en' + +import mimetypes +import urllib + +from PyQt4.Qt import QUrl + +from calibre.gui2 import open_url +from calibre.gui2.store import StorePlugin +from calibre.gui2.store.search_result import SearchResult +from calibre.gui2.store.web_store_dialog import WebStoreDialog +from calibre.utils.opensearch import Client + +class OpenSearchStore(StorePlugin): + + open_search_url = '' + web_url = '' + + def open(self, parent=None, detail_item=None, external=False): + if not hasattr(self, 'web_url'): + return + + if external or self.config.get('open_external', False): + open_url(QUrl(detail_item if detail_item else self.web_url)) + else: + d = WebStoreDialog(self.gui, self.web_url, parent, detail_item) + d.setWindowTitle(self.name) + d.set_tags(self.config.get('tags', '')) + d.exec_() + + def search(self, query, max_results=10, timeout=60): + if not hasattr(self, 'open_search_url'): + return + + client = Client(self.open_search_url) + results = client.search(urllib.quote_plus(query), max_results) + + counter = max_results + for r in results: + if counter <= 0: + break + counter -= 1 + + s = SearchResult() + + s.detail_item = r.get('id', '') + + links = r.get('links', None) + for l in links: + if l.get('rel', None): + if l['rel'] in ('http://opds-spec.org/thumbnail', 'http://opds-spec.org/image/thumbnail'): + s.cover_url = l.get('href', '') + elif l['rel'] == u'http://opds-spec.org/acquisition/buy': + s.detail_item = l.get('href', s.detail_item) + elif l['rel'] == u'http://opds-spec.org/acquisition': + mime = l.get('type', '') + if mime: + ext = mimetypes.guess_extension(mime) + if ext: + ext = ext[1:].upper() + s.downloads[ext] = l.get('href', '') + + s.formats = ', '.join(s.downloads.keys()) + + s.title = r.get('title', '') + s.author = r.get('author', '') + s.price = r.get('price', '') + + yield s diff --git a/src/calibre/gui2/store/pragmatic_bookshelf_plugin.py b/src/calibre/gui2/store/pragmatic_bookshelf_plugin.py deleted file mode 100644 index f3803bbcea..0000000000 --- a/src/calibre/gui2/store/pragmatic_bookshelf_plugin.py +++ /dev/null @@ -1,84 +0,0 @@ -# -*- coding: utf-8 -*- - -from __future__ import (unicode_literals, division, absolute_import, print_function) - -__license__ = 'GPL 3' -__copyright__ = '2011, John Schember ' -__docformat__ = 'restructuredtext en' - -import urllib -from contextlib import closing - -from lxml import html - -from PyQt4.Qt import QUrl - -from calibre import browser, url_slash_cleaner -from calibre.gui2 import open_url -from calibre.gui2.store import StorePlugin -from calibre.gui2.store.basic_config import BasicStoreConfig -from calibre.gui2.store.search_result import SearchResult -from calibre.gui2.store.web_store_dialog import WebStoreDialog - -class PragmaticBookshelfStore(BasicStoreConfig, StorePlugin): - - def open(self, parent=None, detail_item=None, external=False): - url = 'http://pragprog.com/' - - if external or self.config.get('open_external', False): - open_url(QUrl(url_slash_cleaner(detail_item if detail_item else url))) - else: - d = WebStoreDialog(self.gui, url, parent, detail_item) - d.setWindowTitle(self.name) - d.set_tags(self.config.get('tags', '')) - d.exec_() - - def search(self, query, max_results=10, timeout=60): - ''' - OPDS based search. - - We really should get the catelog from http://pragprog.com/catalog.opds - and look for the application/opensearchdescription+xml entry. - Then get the opensearch description to get the search url and - format. However, we are going to be lazy and hard code it. - ''' - url = 'http://pragprog.com/catalog/search?q=' + urllib.quote_plus(query) - - br = browser() - - counter = max_results - with closing(br.open(url, timeout=timeout)) as f: - # Use html instead of etree as html allows us - # to ignore the namespace easily. - doc = html.fromstring(f.read()) - for data in doc.xpath('//entry'): - if counter <= 0: - break - - id = ''.join(data.xpath('.//link[@rel="http://opds-spec.org/acquisition/buy"]/@href')) - if not id: - continue - - price = ''.join(data.xpath('.//price/@currencycode')).strip() - price += ' ' - price += ''.join(data.xpath('.//price/text()')).strip() - if not price.strip(): - continue - - cover_url = ''.join(data.xpath('.//link[@rel="http://opds-spec.org/cover"]/@href')) - - title = ''.join(data.xpath('.//title/text()')) - author = ''.join(data.xpath('.//author//text()')) - - counter -= 1 - - s = SearchResult() - s.cover_url = cover_url - s.title = title.strip() - s.author = author.strip() - s.price = price.strip() - s.detail_item = id.strip() - s.drm = SearchResult.DRM_UNLOCKED - s.formats = 'EPUB, PDF, MOBI' - - yield s diff --git a/src/calibre/gui2/store/search/adv_search_builder.py b/src/calibre/gui2/store/search/adv_search_builder.py index cc89ca4eb7..127ac27acb 100644 --- a/src/calibre/gui2/store/search/adv_search_builder.py +++ b/src/calibre/gui2/store/search/adv_search_builder.py @@ -45,6 +45,7 @@ class AdvSearchBuilderDialog(QDialog, Ui_Dialog): self.author_box.setText('') self.price_box.setText('') self.format_box.setText('') + self.download_combo.setCurrentIndex(0) self.affiliate_combo.setCurrentIndex(0) def tokens(self, raw): @@ -119,6 +120,9 @@ class AdvSearchBuilderDialog(QDialog, Ui_Dialog): format = unicode(self.format_box.text()).strip() if format: ans.append('format:"' + self.mc + format + '"') + download = unicode(self.download_combo.currentText()).strip() + if download: + ans.append('download:' + download) affiliate = unicode(self.affiliate_combo.currentText()).strip() if affiliate: ans.append('affiliate:' + affiliate) diff --git a/src/calibre/gui2/store/search/adv_search_builder.ui b/src/calibre/gui2/store/search/adv_search_builder.ui index ab12dbbc00..02eb8f6aa1 100644 --- a/src/calibre/gui2/store/search/adv_search_builder.ui +++ b/src/calibre/gui2/store/search/adv_search_builder.ui @@ -226,7 +226,7 @@ - + @@ -244,7 +244,7 @@ - + Qt::Vertical @@ -283,14 +283,14 @@ - + Affiliate: - + @@ -309,6 +309,32 @@ + + + + Download: + + + + + + + + + + + + + true + + + + + false + + + + diff --git a/src/calibre/gui2/store/search/models.py b/src/calibre/gui2/store/search/models.py index e2c1a03e90..1fb0e5327b 100644 --- a/src/calibre/gui2/store/search/models.py +++ b/src/calibre/gui2/store/search/models.py @@ -33,7 +33,7 @@ class Matches(QAbstractItemModel): total_changed = pyqtSignal(int) - HEADERS = [_('Cover'), _('Title'), _('Price'), _('DRM'), _('Store'), ''] + HEADERS = [_('Cover'), _('Title'), _('Price'), _('DRM'), _('Store'), _('Download'), _('Affiliate')] HTML_COLS = (1, 4) def __init__(self, cover_thread_count=2, detail_thread_count=4): @@ -47,6 +47,8 @@ class Matches(QAbstractItemModel): Qt.SmoothTransformation) self.DONATE_ICON = QPixmap(I('donate.png')).scaledToHeight(16, Qt.SmoothTransformation) + self.DOWNLOAD_ICON = QPixmap(I('arrow-down.png')).scaledToHeight(16, + Qt.SmoothTransformation) # All matches. Used to determine the order to display # self.matches because the SearchFilter returns @@ -181,9 +183,11 @@ class Matches(QAbstractItemModel): elif result.drm == SearchResult.DRM_UNKNOWN: return QVariant(self.DRM_UNKNOWN_ICON) if col == 5: + if result.downloads: + return QVariant(self.DOWNLOAD_ICON) + if col == 6: if result.affiliate: return QVariant(self.DONATE_ICON) - return NONE elif role == Qt.ToolTipRole: if col == 1: return QVariant('

%s

' % result.title) @@ -199,6 +203,9 @@ class Matches(QAbstractItemModel): elif col == 4: return QVariant('

%s

' % result.formats) elif col == 5: + if result.downloads: + return QVariant('

' + _('The following formats can be downloaded directly: %s.') % ', '.join(result.downloads.keys()) + '

') + elif col == 6: if result.affiliate: return QVariant('

' + _('Buying from this store supports the calibre developer: %s.') % result.plugin_author + '

') elif role == Qt.SizeHintRole: @@ -221,6 +228,11 @@ class Matches(QAbstractItemModel): elif col == 4: text = result.store_name elif col == 5: + if result.downloads: + text = 'a' + else: + text = 'b' + elif col == 6: if result.affiliate: text = 'a' else: @@ -257,6 +269,8 @@ class SearchFilter(SearchQueryParser): 'author', 'authors', 'cover', + 'download', + 'downloads', 'drm', 'format', 'formats', @@ -282,6 +296,8 @@ class SearchFilter(SearchQueryParser): location = location.lower().strip() if location == 'authors': location = 'author' + elif location == 'downloads': + location = 'download' elif location == 'formats': location = 'format' @@ -308,12 +324,13 @@ class SearchFilter(SearchQueryParser): 'author': lambda x: x.author.lower(), 'cover': attrgetter('cover_url'), 'drm': attrgetter('drm'), + 'download': attrgetter('downloads'), 'format': attrgetter('formats'), 'price': lambda x: comparable_price(x.price), 'store': lambda x: x.store_name.lower(), 'title': lambda x: x.title.lower(), } - for x in ('author', 'format'): + for x in ('author', 'download', 'format'): q[x+'s'] = q[x] for sr in self.srs: for locvalue in locations: @@ -347,7 +364,7 @@ class SearchFilter(SearchQueryParser): matches.add(sr) continue # this is bool or treated as bool, so can't match below. - if locvalue in ('affiliate', 'drm'): + if locvalue in ('affiliate', 'drm', 'download', 'downloads'): continue try: ### Can't separate authors because comma is used for name sep and author sep diff --git a/src/calibre/gui2/store/search/results_view.py b/src/calibre/gui2/store/search/results_view.py index 91c067006e..3957e18ef6 100644 --- a/src/calibre/gui2/store/search/results_view.py +++ b/src/calibre/gui2/store/search/results_view.py @@ -6,13 +6,18 @@ __license__ = 'GPL 3' __copyright__ = '2011, John Schember ' __docformat__ = 'restructuredtext en' -from PyQt4.Qt import (QTreeView) +from functools import partial + +from PyQt4.Qt import (pyqtSignal, QMenu, QTreeView) from calibre.gui2.metadata.single_download import RichTextDelegate from calibre.gui2.store.search.models import Matches class ResultsView(QTreeView): + download_requested = pyqtSignal(object) + open_requested = pyqtSignal(object) + def __init__(self, *args): QTreeView.__init__(self,*args) @@ -24,3 +29,18 @@ class ResultsView(QTreeView): for i in self._model.HTML_COLS: self.setItemDelegateForColumn(i, self.rt_delegate) + def contextMenuEvent(self, event): + index = self.indexAt(event.pos()) + + if not index.isValid(): + return + + result = self.model().get_result(index) + + menu = QMenu() + da = menu.addAction(_('Download...'), partial(self.download_requested.emit, result)) + if not result.downloads: + da.setEnabled(False) + menu.addSeparator() + menu.addAction(_('Goto in store...'), partial(self.open_requested.emit, result)) + menu.exec_(event.globalPos()) diff --git a/src/calibre/gui2/store/search/search.py b/src/calibre/gui2/store/search/search.py index 7db4d1bbaf..fd20669f09 100644 --- a/src/calibre/gui2/store/search/search.py +++ b/src/calibre/gui2/store/search/search.py @@ -14,6 +14,7 @@ from PyQt4.Qt import (Qt, QDialog, QDialogButtonBox, QTimer, QCheckBox, QLabel, QComboBox) from calibre.gui2 import JSONConfig, info_dialog +from calibre.gui2.dialogs.choose_format import ChooseFormatDialog from calibre.gui2.progress_indicator import ProgressIndicator from calibre.gui2.store.config.chooser.chooser_widget import StoreChooserWidget from calibre.gui2.store.config.search.search_widget import StoreConfigWidget @@ -72,7 +73,9 @@ class SearchDialog(QDialog, Ui_Dialog): self.search.clicked.connect(self.do_search) self.checker.timeout.connect(self.get_results) self.progress_checker.timeout.connect(self.check_progress) - self.results_view.activated.connect(self.open_store) + self.results_view.activated.connect(self.result_item_activated) + self.results_view.download_requested.connect(self.download_book) + self.results_view.open_requested.connect(self.open_store) self.results_view.model().total_changed.connect(self.update_book_total) self.select_all_stores.clicked.connect(self.stores_select_all) self.select_invert_stores.clicked.connect(self.stores_select_invert) @@ -129,11 +132,15 @@ class SearchDialog(QDialog, Ui_Dialog): # Title / Author self.results_view.setColumnWidth(1,int(total*.40)) # Price - self.results_view.setColumnWidth(2,int(total*.20)) + self.results_view.setColumnWidth(2,int(total*.12)) # DRM self.results_view.setColumnWidth(3, int(total*.15)) # Store / Formats self.results_view.setColumnWidth(4, int(total*.25)) + # Download + self.results_view.setColumnWidth(5, 20) + # Affiliate + self.results_view.setColumnWidth(6, 20) def do_search(self): # Stop all running threads. @@ -183,7 +190,7 @@ class SearchDialog(QDialog, Ui_Dialog): query = re.sub(r'%s:"(?P
[^\s"]+)"' % loc, '\g', query) query = query.replace('%s:' % loc, '') # Remove the prefix and search text. - for loc in ('cover', 'drm', 'format', 'formats', 'price', 'store'): + for loc in ('cover', 'download', 'downloads', 'drm', 'format', 'formats', 'price', 'store'): query = re.sub(r'%s:"[^"]"' % loc, '', query) query = re.sub(r'%s:[^\s]*' % loc, '', query) # Remove logic. @@ -330,8 +337,21 @@ class SearchDialog(QDialog, Ui_Dialog): def update_book_total(self, total): self.total.setText('%s' % total) - def open_store(self, index): + def result_item_activated(self, index): result = self.results_view.model().get_result(index) + + if result.downloads: + self.download_book(result) + else: + self.open_store(result) + + def download_book(self, result): + d = ChooseFormatDialog(self, _('Choose format to download to your library.'), result.downloads.keys()) + if d.exec_() == d.Accepted: + ext = d.format() + self.gui.download_ebook(result.downloads[ext]) + + def open_store(self, result): self.gui.istores[result.store_name].open(self, result.detail_item, self.open_external.isChecked()) def check_progress(self): diff --git a/src/calibre/gui2/store/search_result.py b/src/calibre/gui2/store/search_result.py index 7d6ac5acad..5cf71f011e 100644 --- a/src/calibre/gui2/store/search_result.py +++ b/src/calibre/gui2/store/search_result.py @@ -22,6 +22,9 @@ class SearchResult(object): self.detail_item = '' self.drm = None self.formats = '' + # key = format in upper case. + # value = url to download the file. + self.downloads = {} self.affiliate = False self.plugin_author = '' diff --git a/src/calibre/gui2/store/stores/__init__.py b/src/calibre/gui2/store/stores/__init__.py new file mode 100644 index 0000000000..db25b54b67 --- /dev/null +++ b/src/calibre/gui2/store/stores/__init__.py @@ -0,0 +1,3 @@ +''' +All store plugins are placed here. +''' \ No newline at end of file diff --git a/src/calibre/gui2/store/amazon_de_plugin.py b/src/calibre/gui2/store/stores/amazon_de_plugin.py similarity index 100% rename from src/calibre/gui2/store/amazon_de_plugin.py rename to src/calibre/gui2/store/stores/amazon_de_plugin.py diff --git a/src/calibre/gui2/store/amazon_plugin.py b/src/calibre/gui2/store/stores/amazon_plugin.py similarity index 100% rename from src/calibre/gui2/store/amazon_plugin.py rename to src/calibre/gui2/store/stores/amazon_plugin.py diff --git a/src/calibre/gui2/store/amazon_uk_plugin.py b/src/calibre/gui2/store/stores/amazon_uk_plugin.py similarity index 100% rename from src/calibre/gui2/store/amazon_uk_plugin.py rename to src/calibre/gui2/store/stores/amazon_uk_plugin.py diff --git a/src/calibre/gui2/store/stores/archive_org_plugin.py b/src/calibre/gui2/store/stores/archive_org_plugin.py new file mode 100644 index 0000000000..bafc6e096e --- /dev/null +++ b/src/calibre/gui2/store/stores/archive_org_plugin.py @@ -0,0 +1,36 @@ +# -*- coding: utf-8 -*- + +from __future__ import (unicode_literals, division, absolute_import, print_function) + +__license__ = 'GPL 3' +__copyright__ = '2011, John Schember ' +__docformat__ = 'restructuredtext en' + + +from calibre.gui2.store.basic_config import BasicStoreConfig +from calibre.gui2.store.opensearch_store import OpenSearchStore +from calibre.gui2.store.search_result import SearchResult + +class ArchiveOrgStore(BasicStoreConfig, OpenSearchStore): + + open_search_url = 'http://bookserver.archive.org/catalog/opensearch.xml' + web_url = 'http://www.archive.org/details/texts' + + # http://bookserver.archive.org/catalog/ + + def search(self, query, max_results=10, timeout=60): + for s in OpenSearchStore.search(self, query, max_results, timeout): + s.detail_item = 'http://www.archive.org/details/' + s.detail_item.split(':')[-1] + s.price = '$0.00' + s.drm = SearchResult.DRM_UNLOCKED + yield s +''' + def get_details(self, search_result, timeout): + br = browser() + with closing(br.open(search_result.detail_item, timeout=timeout)) as nf: + idata = html.fromstring(nf.read()) + formats = ', '.join(idata.xpath('//p[@id="dl" and @class="content"]//a/text()')) + search_result.formats = formats.upper() + + return True +''' diff --git a/src/calibre/gui2/store/baen_webscription_plugin.py b/src/calibre/gui2/store/stores/baen_webscription_plugin.py similarity index 100% rename from src/calibre/gui2/store/baen_webscription_plugin.py rename to src/calibre/gui2/store/stores/baen_webscription_plugin.py diff --git a/src/calibre/gui2/store/beam_ebooks_de_plugin.py b/src/calibre/gui2/store/stores/beam_ebooks_de_plugin.py similarity index 100% rename from src/calibre/gui2/store/beam_ebooks_de_plugin.py rename to src/calibre/gui2/store/stores/beam_ebooks_de_plugin.py diff --git a/src/calibre/gui2/store/bewrite_plugin.py b/src/calibre/gui2/store/stores/bewrite_plugin.py similarity index 100% rename from src/calibre/gui2/store/bewrite_plugin.py rename to src/calibre/gui2/store/stores/bewrite_plugin.py diff --git a/src/calibre/gui2/store/bn_plugin.py b/src/calibre/gui2/store/stores/bn_plugin.py similarity index 100% rename from src/calibre/gui2/store/bn_plugin.py rename to src/calibre/gui2/store/stores/bn_plugin.py diff --git a/src/calibre/gui2/store/diesel_ebooks_plugin.py b/src/calibre/gui2/store/stores/diesel_ebooks_plugin.py similarity index 100% rename from src/calibre/gui2/store/diesel_ebooks_plugin.py rename to src/calibre/gui2/store/stores/diesel_ebooks_plugin.py diff --git a/src/calibre/gui2/store/ebooks_com_plugin.py b/src/calibre/gui2/store/stores/ebooks_com_plugin.py similarity index 100% rename from src/calibre/gui2/store/ebooks_com_plugin.py rename to src/calibre/gui2/store/stores/ebooks_com_plugin.py diff --git a/src/calibre/gui2/store/ebookshoppe_uk_plugin.py b/src/calibre/gui2/store/stores/ebookshoppe_uk_plugin.py similarity index 100% rename from src/calibre/gui2/store/ebookshoppe_uk_plugin.py rename to src/calibre/gui2/store/stores/ebookshoppe_uk_plugin.py diff --git a/src/calibre/gui2/store/eharlequin_plugin.py b/src/calibre/gui2/store/stores/eharlequin_plugin.py similarity index 100% rename from src/calibre/gui2/store/eharlequin_plugin.py rename to src/calibre/gui2/store/stores/eharlequin_plugin.py diff --git a/src/calibre/gui2/store/stores/epubbud_plugin.py b/src/calibre/gui2/store/stores/epubbud_plugin.py new file mode 100644 index 0000000000..b4d642f62b --- /dev/null +++ b/src/calibre/gui2/store/stores/epubbud_plugin.py @@ -0,0 +1,27 @@ +# -*- coding: utf-8 -*- + +from __future__ import (unicode_literals, division, absolute_import, print_function) + +__license__ = 'GPL 3' +__copyright__ = '2011, John Schember ' +__docformat__ = 'restructuredtext en' + +from calibre.gui2.store.basic_config import BasicStoreConfig +from calibre.gui2.store.opensearch_store import OpenSearchStore +from calibre.gui2.store.search_result import SearchResult + +class EpubBudStore(BasicStoreConfig, OpenSearchStore): + + open_search_url = 'http://www.epubbud.com/feeds/opensearch.xml' + web_url = 'http://www.epubbud.com/' + + # http://www.epubbud.com/feeds/catalog.atom + + def search(self, query, max_results=10, timeout=60): + for s in OpenSearchStore.search(self, query, max_results, timeout): + s.price = '$0.00' + s.drm = SearchResult.DRM_UNLOCKED + s.formats = 'EPUB' + # Download links are broken for this store. + s.downloads = {} + yield s diff --git a/src/calibre/gui2/store/epubbuy_de_plugin.py b/src/calibre/gui2/store/stores/epubbuy_de_plugin.py similarity index 100% rename from src/calibre/gui2/store/epubbuy_de_plugin.py rename to src/calibre/gui2/store/stores/epubbuy_de_plugin.py diff --git a/src/calibre/gui2/store/stores/feedbooks_plugin.py b/src/calibre/gui2/store/stores/feedbooks_plugin.py new file mode 100644 index 0000000000..96d0a10dc7 --- /dev/null +++ b/src/calibre/gui2/store/stores/feedbooks_plugin.py @@ -0,0 +1,28 @@ +# -*- coding: utf-8 -*- + +from __future__ import (unicode_literals, division, absolute_import, print_function) + +__license__ = 'GPL 3' +__copyright__ = '2011, John Schember ' +__docformat__ = 'restructuredtext en' + +from calibre.gui2.store.basic_config import BasicStoreConfig +from calibre.gui2.store.opensearch_store import OpenSearchStore +from calibre.gui2.store.search_result import SearchResult + +class FeedbooksStore(BasicStoreConfig, OpenSearchStore): + + open_search_url = 'http://assets0.feedbooks.net/opensearch.xml?t=1253087147' + web_url = 'http://feedbooks.com/' + + # http://www.feedbooks.com/catalog + + def search(self, query, max_results=10, timeout=60): + for s in OpenSearchStore.search(self, query, max_results, timeout): + if s.downloads: + s.drm = SearchResult.DRM_UNLOCKED + s.price = '$0.00' + else: + s.drm = SearchResult.DRM_LOCKED + s.formats = 'EPUB' + yield s diff --git a/src/calibre/gui2/store/foyles_uk_plugin.py b/src/calibre/gui2/store/stores/foyles_uk_plugin.py similarity index 100% rename from src/calibre/gui2/store/foyles_uk_plugin.py rename to src/calibre/gui2/store/stores/foyles_uk_plugin.py diff --git a/src/calibre/gui2/store/gandalf_plugin.py b/src/calibre/gui2/store/stores/gandalf_plugin.py similarity index 100% rename from src/calibre/gui2/store/gandalf_plugin.py rename to src/calibre/gui2/store/stores/gandalf_plugin.py diff --git a/src/calibre/gui2/store/google_books_plugin.py b/src/calibre/gui2/store/stores/google_books_plugin.py similarity index 100% rename from src/calibre/gui2/store/google_books_plugin.py rename to src/calibre/gui2/store/stores/google_books_plugin.py diff --git a/src/calibre/gui2/store/gutenberg_plugin.py b/src/calibre/gui2/store/stores/gutenberg_plugin.py similarity index 100% rename from src/calibre/gui2/store/gutenberg_plugin.py rename to src/calibre/gui2/store/stores/gutenberg_plugin.py diff --git a/src/calibre/gui2/store/kobo_plugin.py b/src/calibre/gui2/store/stores/kobo_plugin.py similarity index 100% rename from src/calibre/gui2/store/kobo_plugin.py rename to src/calibre/gui2/store/stores/kobo_plugin.py diff --git a/src/calibre/gui2/store/legimi_plugin.py b/src/calibre/gui2/store/stores/legimi_plugin.py similarity index 100% rename from src/calibre/gui2/store/legimi_plugin.py rename to src/calibre/gui2/store/stores/legimi_plugin.py diff --git a/src/calibre/gui2/store/libri_de_plugin.py b/src/calibre/gui2/store/stores/libri_de_plugin.py similarity index 100% rename from src/calibre/gui2/store/libri_de_plugin.py rename to src/calibre/gui2/store/stores/libri_de_plugin.py diff --git a/src/calibre/gui2/store/manybooks_plugin.py b/src/calibre/gui2/store/stores/manybooks_plugin.py similarity index 95% rename from src/calibre/gui2/store/manybooks_plugin.py rename to src/calibre/gui2/store/stores/manybooks_plugin.py index efd8d21e68..829a97012f 100644 --- a/src/calibre/gui2/store/manybooks_plugin.py +++ b/src/calibre/gui2/store/stores/manybooks_plugin.py @@ -20,7 +20,7 @@ from calibre.gui2.store import StorePlugin from calibre.gui2.store.basic_config import BasicStoreConfig from calibre.gui2.store.search_result import SearchResult from calibre.gui2.store.web_store_dialog import WebStoreDialog - + class ManyBooksStore(BasicStoreConfig, StorePlugin): def open(self, parent=None, detail_item=None, external=False): @@ -29,7 +29,7 @@ class ManyBooksStore(BasicStoreConfig, StorePlugin): detail_url = None if detail_item: detail_url = url + detail_item - + if external or self.config.get('open_external', False): open_url(QUrl(url_slash_cleaner(detail_url if detail_url else url))) else: @@ -44,16 +44,16 @@ class ManyBooksStore(BasicStoreConfig, StorePlugin): # secondary titles. Google is also faster. # Using a google search so we can search on both fields at once. url = 'http://www.google.com/xhtml?q=site:manybooks.net+' + urllib.quote_plus(query) - + br = browser() - + counter = max_results with closing(br.open(url, timeout=timeout)) as f: doc = html.fromstring(f.read()) for data in doc.xpath('//div[@class="edewpi"]//div[@class="r ld"]'): if counter <= 0: break - + url = '' url_a = data.xpath('div[@class="jd"]/a') if url_a: @@ -65,13 +65,13 @@ class ManyBooksStore(BasicStoreConfig, StorePlugin): continue id = url.split('/')[-1] id = id.strip() - + url_a = html.fromstring(html.tostring(url_a)) heading = ''.join(url_a.xpath('//text()')) title, _, author = heading.rpartition('by ') author = author.split('-')[0] price = '$0.00' - + cover_url = '' mo = re.match('^\D+', id) if mo: @@ -79,10 +79,9 @@ class ManyBooksStore(BasicStoreConfig, StorePlugin): cover_name = cover_name.replace('etext', '') cover_id = id.split('.')[0] cover_url = 'http://www.manybooks.net/images/' + id[0] + '/' + cover_name + '/' + cover_id + '-thumb.jpg' - print(cover_url) counter -= 1 - + s = SearchResult() s.cover_url = cover_url s.title = title.strip() @@ -91,5 +90,5 @@ class ManyBooksStore(BasicStoreConfig, StorePlugin): s.detail_item = '/titles/' + id s.drm = SearchResult.DRM_UNLOCKED s.formts = 'EPUB, PDB (eReader, PalmDoc, zTXT, Plucker, iSilo), FB2, ZIP, AZW, MOBI, PRC, LIT, PKG, PDF, TXT, RB, RTF, LRF, TCR, JAR' - + yield s diff --git a/src/calibre/gui2/store/mobileread/__init__.py b/src/calibre/gui2/store/stores/mobileread/__init__.py similarity index 100% rename from src/calibre/gui2/store/mobileread/__init__.py rename to src/calibre/gui2/store/stores/mobileread/__init__.py diff --git a/src/calibre/gui2/store/mobileread/adv_search_builder.py b/src/calibre/gui2/store/stores/mobileread/adv_search_builder.py similarity index 97% rename from src/calibre/gui2/store/mobileread/adv_search_builder.py rename to src/calibre/gui2/store/stores/mobileread/adv_search_builder.py index 8c41f1924b..8bc7850b0f 100644 --- a/src/calibre/gui2/store/mobileread/adv_search_builder.py +++ b/src/calibre/gui2/store/stores/mobileread/adv_search_builder.py @@ -10,7 +10,7 @@ import re from PyQt4.Qt import (QDialog, QDialogButtonBox) -from calibre.gui2.store.mobileread.adv_search_builder_ui import Ui_Dialog +from calibre.gui2.store.stores.mobileread.adv_search_builder_ui import Ui_Dialog from calibre.library.caches import CONTAINS_MATCH, EQUALS_MATCH class AdvSearchBuilderDialog(QDialog, Ui_Dialog): diff --git a/src/calibre/gui2/store/mobileread/adv_search_builder.ui b/src/calibre/gui2/store/stores/mobileread/adv_search_builder.ui similarity index 100% rename from src/calibre/gui2/store/mobileread/adv_search_builder.ui rename to src/calibre/gui2/store/stores/mobileread/adv_search_builder.ui diff --git a/src/calibre/gui2/store/mobileread/cache_progress_dialog.py b/src/calibre/gui2/store/stores/mobileread/cache_progress_dialog.py similarity index 94% rename from src/calibre/gui2/store/mobileread/cache_progress_dialog.py rename to src/calibre/gui2/store/stores/mobileread/cache_progress_dialog.py index 71416d8680..de2cf50f84 100644 --- a/src/calibre/gui2/store/mobileread/cache_progress_dialog.py +++ b/src/calibre/gui2/store/stores/mobileread/cache_progress_dialog.py @@ -8,7 +8,7 @@ __docformat__ = 'restructuredtext en' from PyQt4.Qt import QDialog -from calibre.gui2.store.mobileread.cache_progress_dialog_ui import Ui_Dialog +from calibre.gui2.store.stores.mobileread.cache_progress_dialog_ui import Ui_Dialog class CacheProgressDialog(QDialog, Ui_Dialog): diff --git a/src/calibre/gui2/store/mobileread/cache_progress_dialog.ui b/src/calibre/gui2/store/stores/mobileread/cache_progress_dialog.ui similarity index 100% rename from src/calibre/gui2/store/mobileread/cache_progress_dialog.ui rename to src/calibre/gui2/store/stores/mobileread/cache_progress_dialog.ui diff --git a/src/calibre/gui2/store/mobileread/cache_update_thread.py b/src/calibre/gui2/store/stores/mobileread/cache_update_thread.py similarity index 100% rename from src/calibre/gui2/store/mobileread/cache_update_thread.py rename to src/calibre/gui2/store/stores/mobileread/cache_update_thread.py diff --git a/src/calibre/gui2/store/mobileread/mobileread_plugin.py b/src/calibre/gui2/store/stores/mobileread/mobileread_plugin.py similarity index 91% rename from src/calibre/gui2/store/mobileread/mobileread_plugin.py rename to src/calibre/gui2/store/stores/mobileread/mobileread_plugin.py index 4e11d62bbd..3ffb5c36a1 100644 --- a/src/calibre/gui2/store/mobileread/mobileread_plugin.py +++ b/src/calibre/gui2/store/stores/mobileread/mobileread_plugin.py @@ -15,10 +15,10 @@ from calibre.gui2.store import StorePlugin from calibre.gui2.store.basic_config import BasicStoreConfig from calibre.gui2.store.search_result import SearchResult from calibre.gui2.store.web_store_dialog import WebStoreDialog -from calibre.gui2.store.mobileread.models import SearchFilter -from calibre.gui2.store.mobileread.cache_progress_dialog import CacheProgressDialog -from calibre.gui2.store.mobileread.cache_update_thread import CacheUpdateThread -from calibre.gui2.store.mobileread.store_dialog import MobileReadStoreDialog +from calibre.gui2.store.stores.mobileread.models import SearchFilter +from calibre.gui2.store.stores.mobileread.cache_progress_dialog import CacheProgressDialog +from calibre.gui2.store.stores.mobileread.cache_update_thread import CacheUpdateThread +from calibre.gui2.store.stores.mobileread.store_dialog import MobileReadStoreDialog class MobileReadStore(BasicStoreConfig, StorePlugin): diff --git a/src/calibre/gui2/store/mobileread/models.py b/src/calibre/gui2/store/stores/mobileread/models.py similarity index 100% rename from src/calibre/gui2/store/mobileread/models.py rename to src/calibre/gui2/store/stores/mobileread/models.py diff --git a/src/calibre/gui2/store/mobileread/store_dialog.py b/src/calibre/gui2/store/stores/mobileread/store_dialog.py similarity index 93% rename from src/calibre/gui2/store/mobileread/store_dialog.py rename to src/calibre/gui2/store/stores/mobileread/store_dialog.py index 749f96a614..ff7fea090f 100644 --- a/src/calibre/gui2/store/mobileread/store_dialog.py +++ b/src/calibre/gui2/store/stores/mobileread/store_dialog.py @@ -9,9 +9,9 @@ __docformat__ = 'restructuredtext en' from PyQt4.Qt import (Qt, QDialog, QIcon, QComboBox) -from calibre.gui2.store.mobileread.adv_search_builder import AdvSearchBuilderDialog -from calibre.gui2.store.mobileread.models import BooksModel -from calibre.gui2.store.mobileread.store_dialog_ui import Ui_Dialog +from calibre.gui2.store.stores.mobileread.adv_search_builder import AdvSearchBuilderDialog +from calibre.gui2.store.stores.mobileread.models import BooksModel +from calibre.gui2.store.stores.mobileread.store_dialog_ui import Ui_Dialog class MobileReadStoreDialog(QDialog, Ui_Dialog): diff --git a/src/calibre/gui2/store/mobileread/store_dialog.ui b/src/calibre/gui2/store/stores/mobileread/store_dialog.ui similarity index 100% rename from src/calibre/gui2/store/mobileread/store_dialog.ui rename to src/calibre/gui2/store/stores/mobileread/store_dialog.ui diff --git a/src/calibre/gui2/store/nexto_plugin.py b/src/calibre/gui2/store/stores/nexto_plugin.py similarity index 100% rename from src/calibre/gui2/store/nexto_plugin.py rename to src/calibre/gui2/store/stores/nexto_plugin.py diff --git a/src/calibre/gui2/store/epubbud_plugin.py b/src/calibre/gui2/store/stores/open_books_plugin.py similarity index 58% rename from src/calibre/gui2/store/epubbud_plugin.py rename to src/calibre/gui2/store/stores/open_books_plugin.py index d6193f6ae0..2e6c438d9d 100644 --- a/src/calibre/gui2/store/epubbud_plugin.py +++ b/src/calibre/gui2/store/stores/open_books_plugin.py @@ -20,59 +20,56 @@ from calibre.gui2.store.basic_config import BasicStoreConfig from calibre.gui2.store.search_result import SearchResult from calibre.gui2.store.web_store_dialog import WebStoreDialog -class EpubBudStore(BasicStoreConfig, StorePlugin): +class OpenBooksStore(BasicStoreConfig, StorePlugin): def open(self, parent=None, detail_item=None, external=False): - url = 'http://epubbud.com/' + url = 'http://drmfree.calibre-ebook.com/' if external or self.config.get('open_external', False): open_url(QUrl(url_slash_cleaner(detail_item if detail_item else url))) else: - d = WebStoreDialog(self.gui, url, parent, detail_item) + d = WebStoreDialog(self.gui, self.url, parent, detail_item) d.setWindowTitle(self.name) d.set_tags(self.config.get('tags', '')) d.exec_() def search(self, query, max_results=10, timeout=60): - ''' - OPDS based search. - - We really should get the catelog from http://pragprog.com/catalog.opds - and look for the application/opensearchdescription+xml entry. - Then get the opensearch description to get the search url and - format. However, we are going to be lazy and hard code it. - ''' - url = 'http://www.epubbud.com/search.php?format=atom&q=' + urllib.quote_plus(query) - + url = 'http://drmfree.calibre-ebook.com/search/?q=' + urllib.quote_plus(query) + br = browser() - + counter = max_results with closing(br.open(url, timeout=timeout)) as f: - # Use html instead of etree as html allows us - # to ignore the namespace easily. doc = html.fromstring(f.read()) - for data in doc.xpath('//entry'): + for data in doc.xpath('//ul[@id="object_list"]//li'): if counter <= 0: break - - id = ''.join(data.xpath('.//id/text()')) + + id = ''.join(data.xpath('.//div[@class="links"]/a[1]/@href')) + id = id.strip() if not id: continue - cover_url = ''.join(data.xpath('.//link[@rel="http://opds-spec.org/thumbnail"]/@href')) - - title = u''.join(data.xpath('.//title/text()')) - author = u''.join(data.xpath('.//author/name/text()')) + cover_url = ''.join(data.xpath('.//div[@class="cover"]/img/@src')) + + price = ''.join(data.xpath('.//div[@class="price"]/text()')) + a, b, price = price.partition('Price:') + price = price.strip() + if not price: + continue + + title = ''.join(data.xpath('.//div/strong/text()')) + author = ''.join(data.xpath('.//div[@class="author"]//text()')) + author = author.partition('by')[-1] counter -= 1 - + s = SearchResult() s.cover_url = cover_url s.title = title.strip() s.author = author.strip() - s.price = '$0.00' + s.price = price.strip() s.detail_item = id.strip() s.drm = SearchResult.DRM_UNLOCKED - s.formats = 'EPUB' - + yield s diff --git a/src/calibre/gui2/store/open_library_plugin.py b/src/calibre/gui2/store/stores/open_library_plugin.py similarity index 100% rename from src/calibre/gui2/store/open_library_plugin.py rename to src/calibre/gui2/store/stores/open_library_plugin.py diff --git a/src/calibre/gui2/store/oreilly_plugin.py b/src/calibre/gui2/store/stores/oreilly_plugin.py similarity index 100% rename from src/calibre/gui2/store/oreilly_plugin.py rename to src/calibre/gui2/store/stores/oreilly_plugin.py diff --git a/src/calibre/gui2/store/stores/pragmatic_bookshelf_plugin.py b/src/calibre/gui2/store/stores/pragmatic_bookshelf_plugin.py new file mode 100644 index 0000000000..671186ba87 --- /dev/null +++ b/src/calibre/gui2/store/stores/pragmatic_bookshelf_plugin.py @@ -0,0 +1,24 @@ +# -*- coding: utf-8 -*- + +from __future__ import (unicode_literals, division, absolute_import, print_function) + +__license__ = 'GPL 3' +__copyright__ = '2011, John Schember ' +__docformat__ = 'restructuredtext en' + +from calibre.gui2.store.basic_config import BasicStoreConfig +from calibre.gui2.store.opensearch_store import OpenSearchStore +from calibre.gui2.store.search_result import SearchResult + +class PragmaticBookshelfStore(BasicStoreConfig, OpenSearchStore): + + open_search_url = 'http://pragprog.com/catalog/search-description' + web_url = 'http://pragprog.com/' + + # http://pragprog.com/catalog.opds + + def search(self, query, max_results=10, timeout=60): + for s in OpenSearchStore.search(self, query, max_results, timeout): + s.drm = SearchResult.DRM_UNLOCKED + s.formats = 'EPUB, PDF, MOBI' + yield s diff --git a/src/calibre/gui2/store/smashwords_plugin.py b/src/calibre/gui2/store/stores/smashwords_plugin.py similarity index 100% rename from src/calibre/gui2/store/smashwords_plugin.py rename to src/calibre/gui2/store/stores/smashwords_plugin.py diff --git a/src/calibre/gui2/store/virtualo_plugin.py b/src/calibre/gui2/store/stores/virtualo_plugin.py similarity index 100% rename from src/calibre/gui2/store/virtualo_plugin.py rename to src/calibre/gui2/store/stores/virtualo_plugin.py diff --git a/src/calibre/gui2/store/waterstones_uk_plugin.py b/src/calibre/gui2/store/stores/waterstones_uk_plugin.py similarity index 100% rename from src/calibre/gui2/store/waterstones_uk_plugin.py rename to src/calibre/gui2/store/stores/waterstones_uk_plugin.py diff --git a/src/calibre/gui2/store/weightless_books_plugin.py b/src/calibre/gui2/store/stores/weightless_books_plugin.py similarity index 100% rename from src/calibre/gui2/store/weightless_books_plugin.py rename to src/calibre/gui2/store/stores/weightless_books_plugin.py diff --git a/src/calibre/gui2/store/whsmith_uk_plugin.py b/src/calibre/gui2/store/stores/whsmith_uk_plugin.py similarity index 100% rename from src/calibre/gui2/store/whsmith_uk_plugin.py rename to src/calibre/gui2/store/stores/whsmith_uk_plugin.py diff --git a/src/calibre/gui2/store/wizards_tower_books_plugin.py b/src/calibre/gui2/store/stores/wizards_tower_books_plugin.py similarity index 100% rename from src/calibre/gui2/store/wizards_tower_books_plugin.py rename to src/calibre/gui2/store/stores/wizards_tower_books_plugin.py diff --git a/src/calibre/gui2/store/woblink_plugin.py b/src/calibre/gui2/store/stores/woblink_plugin.py similarity index 100% rename from src/calibre/gui2/store/woblink_plugin.py rename to src/calibre/gui2/store/stores/woblink_plugin.py diff --git a/src/calibre/gui2/store/zixo_plugin.py b/src/calibre/gui2/store/stores/zixo_plugin.py similarity index 100% rename from src/calibre/gui2/store/zixo_plugin.py rename to src/calibre/gui2/store/stores/zixo_plugin.py diff --git a/src/calibre/gui2/tag_browser/__init__.py b/src/calibre/gui2/tag_browser/__init__.py new file mode 100644 index 0000000000..cc6da1e995 --- /dev/null +++ b/src/calibre/gui2/tag_browser/__init__.py @@ -0,0 +1,11 @@ +#!/usr/bin/env python +# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai +from __future__ import (unicode_literals, division, absolute_import, + print_function) + +__license__ = 'GPL v3' +__copyright__ = '2011, Kovid Goyal ' +__docformat__ = 'restructuredtext en' + + + diff --git a/src/calibre/gui2/tag_browser/model.py b/src/calibre/gui2/tag_browser/model.py new file mode 100644 index 0000000000..0e599ed431 --- /dev/null +++ b/src/calibre/gui2/tag_browser/model.py @@ -0,0 +1,1294 @@ +#!/usr/bin/env python +# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai +from __future__ import (unicode_literals, division, absolute_import, + print_function) +from future_builtins import map + +__license__ = 'GPL v3' +__copyright__ = '2011, Kovid Goyal ' +__docformat__ = 'restructuredtext en' + +import traceback, cPickle, copy +from itertools import repeat + +from PyQt4.Qt import (QAbstractItemModel, QIcon, QVariant, QFont, Qt, + QMimeData, QModelIndex, pyqtSignal) + +from calibre.gui2 import NONE, gprefs, config, error_dialog +from calibre.library.database2 import Tag +from calibre.utils.config import tweaks +from calibre.utils.icu import sort_key, lower, strcmp +from calibre.library.field_metadata import TagsIcons, category_icon_map +from calibre.gui2.dialogs.confirm_delete import confirm +from calibre.utils.formatter import EvalFormatter +from calibre.utils.search_query_parser import saved_searches + +TAG_SEARCH_STATES = {'clear': 0, 'mark_plus': 1, 'mark_plusplus': 2, + 'mark_minus': 3, 'mark_minusminus': 4} + +_bf = None +def bf(): + global _bf + if _bf is None: + _bf = QFont() + _bf.setBold(True) + _bf = QVariant(_bf) + return _bf + +class TagTreeItem(object): # {{{ + + CATEGORY = 0 + TAG = 1 + ROOT = 2 + + def __init__(self, data=None, category_icon=None, icon_map=None, + parent=None, tooltip=None, category_key=None, temporary=False): + self.parent = parent + self.children = [] + self.id_set = set() + self.is_gst = False + self.boxed = False + self.icon_state_map = list(map(QVariant, icon_map)) + if self.parent is not None: + self.parent.append(self) + + if data is None: + self.type = self.ROOT + else: + self.type = self.TAG if category_icon is None else self.CATEGORY + + if self.type == self.CATEGORY: + self.name, self.icon = map(QVariant, (data, category_icon)) + self.py_name = data + self.category_key = category_key + self.temporary = temporary + self.tag = Tag(data, category=category_key, + is_editable=category_key not in ['news', 'search', 'identifiers'], + is_searchable=category_key not in ['search']) + + elif self.type == self.TAG: + self.icon_state_map[0] = QVariant(data.icon) + self.tag = data + + self.tooltip = (tooltip + ' ') if tooltip else '' + + def break_cycles(self): + del self.parent + del self.children + + def __str__(self): + if self.type == self.ROOT: + return 'ROOT' + if self.type == self.CATEGORY: + return 'CATEGORY:'+str(QVariant.toString( + self.name))+':%d'%len(getattr(self, + 'children', [])) + return 'TAG: %s'%self.tag.name + + def row(self): + if self.parent is not None: + return self.parent.children.index(self) + return 0 + + def append(self, child): + child.parent = self + self.children.append(child) + + def data(self, role): + if role == Qt.UserRole: + return self + if self.type == self.TAG: + return self.tag_data(role) + if self.type == self.CATEGORY: + return self.category_data(role) + return NONE + + def category_data(self, role): + if role == Qt.DisplayRole: + return QVariant(self.py_name + ' [%d]'%len(self.child_tags())) + if role == Qt.EditRole: + return QVariant(self.py_name) + if role == Qt.DecorationRole: + if self.tag.state: + return self.icon_state_map[self.tag.state] + return self.icon + if role == Qt.FontRole: + return bf() + if role == Qt.ToolTipRole and self.tooltip is not None: + return QVariant(self.tooltip) + return NONE + + def tag_data(self, role): + tag = self.tag + if tag.use_sort_as_name: + name = tag.sort + tt_author = True + else: + p = self + while p.parent.type != self.ROOT: + p = p.parent + if not tag.is_hierarchical: + name = tag.original_name + else: + name = tag.name + tt_author = False + if role == Qt.DisplayRole: + count = len(self.id_set) + count = count if count > 0 else tag.count + if count == 0: + return QVariant('%s'%(name)) + else: + return QVariant('[%d] %s'%(count, name)) + if role == Qt.EditRole: + return QVariant(tag.original_name) + if role == Qt.DecorationRole: + return self.icon_state_map[tag.state] + if role == Qt.ToolTipRole: + if tt_author: + if tag.tooltip is not None: + return QVariant('(%s) %s'%(tag.name, tag.tooltip)) + else: + return QVariant(tag.name) + if tag.tooltip: + return QVariant(self.tooltip + tag.tooltip) + else: + return QVariant(self.tooltip) + return NONE + + def toggle(self, set_to=None): + ''' + set_to: None => advance the state, otherwise a value from TAG_SEARCH_STATES + ''' + if set_to is None: + while True: + self.tag.state = (self.tag.state + 1)%5 + if self.tag.state == TAG_SEARCH_STATES['mark_plus'] or \ + self.tag.state == TAG_SEARCH_STATES['mark_minus']: + if self.tag.is_searchable: + break + elif self.tag.state == TAG_SEARCH_STATES['mark_plusplus'] or\ + self.tag.state == TAG_SEARCH_STATES['mark_minusminus']: + if self.tag.is_searchable and len(self.children) and \ + self.tag.is_hierarchical == '5state': + break + else: + break + else: + self.tag.state = set_to + + def all_children(self): + res = [] + def recurse(nodes, res): + for t in nodes: + res.append(t) + recurse(t.children, res) + recurse(self.children, res) + return res + + def child_tags(self): + res = [] + def recurse(nodes, res): + for t in nodes: + if t.type != TagTreeItem.CATEGORY: + res.append(t) + recurse(t.children, res) + recurse(self.children, res) + return res + # }}} + +class TagsModel(QAbstractItemModel): # {{{ + + search_item_renamed = pyqtSignal() + tag_item_renamed = pyqtSignal() + refresh_required = pyqtSignal() + restriction_error = pyqtSignal() + drag_drop_finished = pyqtSignal(object) + user_categories_edited = pyqtSignal(object, object) + + def __init__(self, parent): + QAbstractItemModel.__init__(self, parent) + self.node_map = {} + self.category_nodes = [] + iconmap = {} + for key in category_icon_map: + iconmap[key] = QIcon(I(category_icon_map[key])) + self.category_icon_map = TagsIcons(iconmap) + self.categories_with_ratings = ['authors', 'series', 'publisher', 'tags'] + self.icon_state_map = [None, QIcon(I('plus.png')), QIcon(I('plusplus.png')), + QIcon(I('minus.png')), QIcon(I('minusminus.png'))] + + self.hidden_categories = set() + self.search_restriction = None + self.filter_categories_by = None + self.collapse_model = 'disable' + self.row_map = [] + self.root_item = self.create_node(icon_map=self.icon_state_map) + self.db = None + self.reread_collapse_model({}, rebuild=False) + + def reread_collapse_model(self, state_map, rebuild=True): + if gprefs['tags_browser_collapse_at'] == 0: + self.collapse_model = 'disable' + else: + self.collapse_model = gprefs['tags_browser_partition_method'] + if rebuild: + self.rebuild_node_tree(state_map) + + def set_search_restriction(self, s): + self.search_restriction = s + self.rebuild_node_tree() + + def set_database(self, db): + self.beginResetModel() + self.search_restriction = None + hidden_cats = db.prefs.get('tag_browser_hidden_categories', None) + # migrate from config to db prefs + if hidden_cats is None: + hidden_cats = config['tag_browser_hidden_categories'] + self.hidden_categories = set() + # strip out any non-existence field keys + for cat in hidden_cats: + if cat in db.field_metadata: + self.hidden_categories.add(cat) + db.prefs.set('tag_browser_hidden_categories', list(self.hidden_categories)) + + self.db = db + self._run_rebuild() + self.endResetModel() + + def rebuild_node_tree(self, state_map={}): + self.beginResetModel() + self._run_rebuild(state_map=state_map) + self.endResetModel() + + def _run_rebuild(self, state_map={}): + for node in self.node_map.itervalues(): + node.break_cycles() + del node #Clear reference to node in the current frame + self.node_map.clear() + self.category_nodes = [] + self.root_item = self.create_node(icon_map=self.icon_state_map) + self._rebuild_node_tree(state_map=state_map) + + def _rebuild_node_tree(self, state_map): + # Note that _get_category_nodes can indirectly change the + # user_categories dict. + data = self._get_category_nodes(config['sort_tags_by']) + gst = self.db.prefs.get('grouped_search_terms', {}) + + last_category_node = None + category_node_map = {} + self.category_node_tree = {} + for i, key in enumerate(self.row_map): + if self.hidden_categories: + if key in self.hidden_categories: + continue + found = False + for cat in self.hidden_categories: + if cat.startswith('@') and key.startswith(cat + '.'): + found = True + if found: + continue + is_gst = False + if key.startswith('@') and key[1:] in gst: + tt = _(u'The grouped search term name is "{0}"').format(key[1:]) + is_gst = True + elif key == 'news': + tt = '' + else: + tt = _(u'The lookup/search name is "{0}"').format(key) + + if key.startswith('@'): + path_parts = [p for p in key.split('.')] + path = '' + last_category_node = self.root_item + tree_root = self.category_node_tree + for i,p in enumerate(path_parts): + path += p + if path not in category_node_map: + node = self.create_node(parent=last_category_node, + data=p[1:] if i == 0 else p, + category_icon=self.category_icon_map[key], + tooltip=tt if path == key else path, + category_key=path, + icon_map=self.icon_state_map) + last_category_node = node + category_node_map[path] = node + self.category_nodes.append(node) + node.can_be_edited = (not is_gst) and (i == (len(path_parts)-1)) + node.is_gst = is_gst + if not is_gst: + node.tag.is_hierarchical = '5state' + if not is_gst: + tree_root[p] = {} + tree_root = tree_root[p] + else: + last_category_node = category_node_map[path] + tree_root = tree_root[p] + path += '.' + else: + node = self.create_node(parent=self.root_item, + data=self.categories[key], + category_icon=self.category_icon_map[key], + tooltip=tt, category_key=key, + icon_map=self.icon_state_map) + node.is_gst = False + category_node_map[key] = node + last_category_node = node + self.category_nodes.append(node) + self._create_node_tree(data, state_map) + + def _create_node_tree(self, data, state_map): + sort_by = config['sort_tags_by'] + + eval_formatter = EvalFormatter() + + if data is None: + print ('_create_node_tree: no data!') + traceback.print_stack() + return + + collapse = gprefs['tags_browser_collapse_at'] + collapse_model = self.collapse_model + if collapse == 0: + collapse_model = 'disable' + elif collapse_model != 'disable': + if sort_by == 'name': + collapse_template = tweaks['categories_collapsed_name_template'] + elif sort_by == 'rating': + collapse_model = 'partition' + collapse_template = tweaks['categories_collapsed_rating_template'] + else: + collapse_model = 'partition' + collapse_template = tweaks['categories_collapsed_popularity_template'] + + def process_one_node(category, state_map): # {{{ + collapse_letter = None + category_node = category + key = category_node.category_key + if key not in data: + return + cat_len = len(data[key]) + if cat_len <= 0: + return + + category_child_map = {} + fm = self.db.field_metadata[key] + clear_rating = True if key not in self.categories_with_ratings and \ + not fm['is_custom'] and \ + not fm['kind'] == 'user' \ + else False + in_uc = fm['kind'] == 'user' + tt = key if in_uc else None + + if collapse_model == 'first letter': + # Build a list of 'equal' first letters by looking for + # overlapping ranges. If a range overlaps another, then the + # letters are assumed to be equivalent. ICU collating is complex + # beyond belief. This mechanism lets us determine the logical + # first character from ICU's standpoint. + chardict = {} + for idx,tag in enumerate(data[key]): + if not tag.sort: + c = ' ' + else: + c = icu_upper(tag.sort[0]) + if c not in chardict: + chardict[c] = [idx, idx] + else: + chardict[c][1] = idx + + # sort the ranges to facilitate detecting overlap + ranges = sorted([(v[0], v[1], c) for c,v in chardict.items()]) + + # Create a list of 'first letters' to use for each item in + # the category. The list is generated using the ranges. Overlaps + # are filled with the character that first occurs. + cl_list = list(repeat(None, len(data[key]))) + for t in ranges: + start = t[0] + c = t[2] + if cl_list[start] is None: + nc = c + else: + nc = cl_list[start] + for i in range(start, t[1]+1): + cl_list[i] = nc + + for idx,tag in enumerate(data[key]): + if clear_rating: + tag.avg_rating = None + tag.state = state_map.get((tag.name, tag.category), 0) + + if collapse_model != 'disable' and cat_len > collapse: + if collapse_model == 'partition': + if (idx % collapse) == 0: + d = {'first': tag} + if cat_len > idx + collapse: + d['last'] = data[key][idx+collapse-1] + else: + d['last'] = data[key][cat_len-1] + name = eval_formatter.safe_format(collapse_template, + d, 'TAG_VIEW', None) + sub_cat = self.create_node(parent=category, data = name, + tooltip = None, temporary=True, + category_icon = category_node.icon, + category_key=category_node.category_key, + icon_map=self.icon_state_map) + sub_cat.tag.is_searchable = False + else: # by 'first letter' + cl = cl_list[idx] + if cl != collapse_letter: + collapse_letter = cl + sub_cat = self.create_node(parent=category, + data = collapse_letter, + category_icon = category_node.icon, + tooltip = None, temporary=True, + category_key=category_node.category_key, + icon_map=self.icon_state_map) + node_parent = sub_cat + else: + node_parent = category + + # category display order is important here. The following works + # only of all the non-user categories are displayed before the + # user categories + components = [t.strip() for t in tag.original_name.split('.') + if t.strip()] + if len(components) == 0 or '.'.join(components) != tag.original_name: + components = [tag.original_name] + if (not tag.is_hierarchical) and (in_uc or + (fm['is_custom'] and fm['display'].get('is_names', False)) or + key in ['authors', 'publisher', 'news', 'formats', 'rating'] or + key not in self.db.prefs.get('categories_using_hierarchy', []) or + len(components) == 1): + n = self.create_node(parent=node_parent, data=tag, tooltip=tt, + icon_map=self.icon_state_map) + if tag.id_set is not None: + n.id_set |= tag.id_set + category_child_map[tag.name, tag.category] = n + else: + for i,comp in enumerate(components): + if i == 0: + child_map = category_child_map + else: + child_map = dict([((t.tag.name, t.tag.category), t) + for t in node_parent.children + if t.type != TagTreeItem.CATEGORY]) + if (comp,tag.category) in child_map: + node_parent = child_map[(comp,tag.category)] + node_parent.tag.is_hierarchical = \ + '5state' if tag.category != 'search' else '3state' + else: + if i < len(components)-1: + t = copy.copy(tag) + t.original_name = '.'.join(components[:i+1]) + if key != 'search': + # This 'manufactured' intermediate node can + # be searched, but cannot be edited. + t.is_editable = False + else: + t.is_searchable = t.is_editable = False + else: + t = tag + if not in_uc: + t.original_name = t.name + t.is_hierarchical = \ + '5state' if t.category != 'search' else '3state' + t.name = comp + node_parent = self.create_node(parent=node_parent, data=t, + tooltip=tt, icon_map=self.icon_state_map) + child_map[(comp,tag.category)] = node_parent + # This id_set must not be None + node_parent.id_set |= tag.id_set + return + # }}} + + for category in self.category_nodes: + process_one_node(category, state_map.get(category.py_name, {})) + + # Drag'n Drop {{{ + def mimeTypes(self): + return ["application/calibre+from_library", + 'application/calibre+from_tag_browser'] + + def mimeData(self, indexes): + data = [] + for idx in indexes: + if idx.isValid(): + # get some useful serializable data + node = self.get_node(idx) + path = self.path_for_index(idx) + if node.type == TagTreeItem.CATEGORY: + d = (node.type, node.py_name, node.category_key) + else: + t = node.tag + p = node + while p.type != TagTreeItem.CATEGORY: + p = p.parent + d = (node.type, p.category_key, p.is_gst, t.original_name, + t.category, path) + data.append(d) + else: + data.append(None) + raw = bytearray(cPickle.dumps(data, -1)) + ans = QMimeData() + ans.setData('application/calibre+from_tag_browser', raw) + return ans + + def dropMimeData(self, md, action, row, column, parent): + fmts = set([unicode(x) for x in md.formats()]) + if not fmts.intersection(set(self.mimeTypes())): + return False + if "application/calibre+from_library" in fmts: + if action != Qt.CopyAction: + return False + return self.do_drop_from_library(md, action, row, column, parent) + elif 'application/calibre+from_tag_browser' in fmts: + return self.do_drop_from_tag_browser(md, action, row, column, parent) + + def do_drop_from_tag_browser(self, md, action, row, column, parent): + if not parent.isValid(): + return False + dest = self.get_node(parent) + if dest.type != TagTreeItem.CATEGORY: + return False + if not md.hasFormat('application/calibre+from_tag_browser'): + return False + data = str(md.data('application/calibre+from_tag_browser')) + src = cPickle.loads(data) + for s in src: + if s[0] != TagTreeItem.TAG: + return False + return self.move_or_copy_item_to_user_category(src, dest, action) + + def move_or_copy_item_to_user_category(self, src, dest, action): + ''' + src is a list of tuples representing items to copy. The tuple is + (type, containing category key, category key is global search term, + full name, category key, path to node) + The type must be TagTreeItem.TAG + dest is the TagTreeItem node to receive the items + action is Qt.CopyAction or Qt.MoveAction + ''' + def process_source_node(user_cats, src_parent, src_parent_is_gst, + is_uc, dest_key, node): + ''' + Copy/move an item and all its children to the destination + ''' + copied = False + src_name = node.tag.original_name + src_cat = node.tag.category + # delete the item if the source is a user category and action is move + if is_uc and not src_parent_is_gst and src_parent in user_cats and \ + action == Qt.MoveAction: + new_cat = [] + for tup in user_cats[src_parent]: + if src_name == tup[0] and src_cat == tup[1]: + continue + new_cat.append(list(tup)) + user_cats[src_parent] = new_cat + else: + copied = True + + # Now add the item to the destination user category + add_it = True + if not is_uc and src_cat == 'news': + src_cat = 'tags' + for tup in user_cats[dest_key]: + if src_name == tup[0] and src_cat == tup[1]: + add_it = False + if add_it: + user_cats[dest_key].append([src_name, src_cat, 0]) + + for c in node.children: + copied = process_source_node(user_cats, src_parent, src_parent_is_gst, + is_uc, dest_key, c) + return copied + + user_cats = self.db.prefs.get('user_categories', {}) + path = None + for s in src: + src_parent, src_parent_is_gst = s[1:3] + path = s[5] + + if src_parent.startswith('@'): + is_uc = True + src_parent = src_parent[1:] + else: + is_uc = False + dest_key = dest.category_key[1:] + + if dest_key not in user_cats: + continue + + node = self.index_for_path(path) + if node: + process_source_node(user_cats, src_parent, src_parent_is_gst, + is_uc, dest_key, + self.get_node(node)) + + self.db.prefs.set('user_categories', user_cats) + self.refresh_required.emit() + + return True + + def do_drop_from_library(self, md, action, row, column, parent): + idx = parent + if idx.isValid(): + node = self.data(idx, Qt.UserRole) + if node.type == TagTreeItem.TAG: + fm = self.db.metadata_for_field(node.tag.category) + if node.tag.category in \ + ('tags', 'series', 'authors', 'rating', 'publisher') or \ + (fm['is_custom'] and ( + fm['datatype'] in ['text', 'rating', 'series', + 'enumeration'] or + (fm['datatype'] == 'composite' and + fm['display'].get('make_category', False)))): + mime = 'application/calibre+from_library' + ids = list(map(int, str(md.data(mime)).split())) + self.handle_drop(node, ids) + return True + elif node.type == TagTreeItem.CATEGORY: + fm_dest = self.db.metadata_for_field(node.category_key) + if fm_dest['kind'] == 'user': + fm_src = self.db.metadata_for_field(md.column_name) + if md.column_name in ['authors', 'publisher', 'series'] or \ + (fm_src['is_custom'] and ( + (fm_src['datatype'] in ['series', 'text', 'enumeration'] and + not fm_src['is_multiple']))or + (fm_src['datatype'] == 'composite' and + fm_src['display'].get('make_category', False))): + mime = 'application/calibre+from_library' + ids = list(map(int, str(md.data(mime)).split())) + self.handle_user_category_drop(node, ids, md.column_name) + return True + return False + + def handle_user_category_drop(self, on_node, ids, column): + categories = self.db.prefs.get('user_categories', {}) + category = categories.get(on_node.category_key[1:], None) + if category is None: + return + fm_src = self.db.metadata_for_field(column) + for id in ids: + label = fm_src['label'] + if not fm_src['is_custom']: + if label == 'authors': + items = self.db.get_authors_with_ids() + items = [(i[0], i[1].replace('|', ',')) for i in items] + value = self.db.authors(id, index_is_id=True) + value = [v.replace('|', ',') for v in value.split(',')] + elif label == 'publisher': + items = self.db.get_publishers_with_ids() + value = self.db.publisher(id, index_is_id=True) + elif label == 'series': + items = self.db.get_series_with_ids() + value = self.db.series(id, index_is_id=True) + else: + items = self.db.get_custom_items_with_ids(label=label) + if fm_src['datatype'] != 'composite': + value = self.db.get_custom(id, label=label, index_is_id=True) + else: + value = self.db.get_property(id, loc=fm_src['rec_index'], + index_is_id=True) + if value is None: + return + if not isinstance(value, list): + value = [value] + for val in value: + for (v, c, id) in category: + if v == val and c == column: + break + else: + category.append([val, column, 0]) + categories[on_node.category_key[1:]] = category + self.db.prefs.set('user_categories', categories) + self.refresh_required.emit() + + def handle_drop(self, on_node, ids): + #print 'Dropped ids:', ids, on_node.tag + key = on_node.tag.category + if (key == 'authors' and len(ids) >= 5): + if not confirm('

'+_('Changing the authors for several books can ' + 'take a while. Are you sure?') + +'

', 'tag_browser_drop_authors', self.parent()): + return + elif len(ids) > 15: + if not confirm('

'+_('Changing the metadata for that many books ' + 'can take a while. Are you sure?') + +'

', 'tag_browser_many_changes', self.parent()): + return + + fm = self.db.metadata_for_field(key) + is_multiple = fm['is_multiple'] + val = on_node.tag.original_name + for id in ids: + mi = self.db.get_metadata(id, index_is_id=True) + + # Prepare to ignore the author, unless it is changed. Title is + # always ignored -- see the call to set_metadata + set_authors = False + + # Author_sort cannot change explicitly. Changing the author might + # change it. + mi.author_sort = None # Never will change by itself. + + if key == 'authors': + mi.authors = [val] + set_authors=True + elif fm['datatype'] == 'rating': + mi.set(key, len(val) * 2) + elif fm['is_custom'] and fm['datatype'] == 'series': + mi.set(key, val, extra=1.0) + elif is_multiple: + new_val = mi.get(key, []) + if val in new_val: + # Fortunately, only one field can change, so the continue + # won't break anything + continue + new_val.append(val) + mi.set(key, new_val) + else: + mi.set(key, val) + self.db.set_metadata(id, mi, set_title=False, + set_authors=set_authors, commit=False) + self.db.commit() + self.drag_drop_finished.emit(ids) + # }}} + + def _get_category_nodes(self, sort): + ''' + Called by __init__. Do not directly call this method. + ''' + self.row_map = [] + self.categories = {} + + # Get the categories + if self.search_restriction: + try: + data = self.db.get_categories(sort=sort, + icon_map=self.category_icon_map, + ids=self.db.search('', return_matches=True)) + except: + data = self.db.get_categories(sort=sort, icon_map=self.category_icon_map) + self.restriction_error.emit() + else: + data = self.db.get_categories(sort=sort, icon_map=self.category_icon_map) + + # Reconstruct the user categories, putting them into metadata + self.db.field_metadata.remove_dynamic_categories() + tb_cats = self.db.field_metadata + for user_cat in sorted(self.db.prefs.get('user_categories', {}).keys(), + key=sort_key): + cat_name = '@' + user_cat # add the '@' to avoid name collision + while True: + try: + tb_cats.add_user_category(label=cat_name, name=user_cat) + dot = cat_name.rfind('.') + if dot < 0: + break + cat_name = cat_name[:dot] + except ValueError: + break + + for cat in sorted(self.db.prefs.get('grouped_search_terms', {}).keys(), + key=sort_key): + if (u'@' + cat) in data: + try: + tb_cats.add_user_category(label=u'@' + cat, name=cat) + except ValueError: + traceback.print_exc() + self.db.data.change_search_locations(self.db.field_metadata.get_search_terms()) + + if len(saved_searches().names()): + tb_cats.add_search_category(label='search', name=_('Searches')) + + if self.filter_categories_by: + for category in data.keys(): + data[category] = [t for t in data[category] + if lower(t.name).find(self.filter_categories_by) >= 0] + + tb_categories = self.db.field_metadata + for category in tb_categories: + if category in data: # The search category can come and go + self.row_map.append(category) + self.categories[category] = tb_categories[category]['name'] + return data + + def refresh(self, data=None): + ''' + Here to trap usages of refresh in the old architecture. Can eventually + be removed. + ''' + print ('TagsModel: refresh called!') + traceback.print_stack() + return False + + def create_node(self, *args, **kwargs): + node = TagTreeItem(*args, **kwargs) + self.node_map[id(node)] = node + return node + + def get_node(self, idx): + ans = self.node_map.get(idx.internalId(), self.root_item) + return ans + + def createIndex(self, row, column, internal_pointer=None): + idx = QAbstractItemModel.createIndex(self, row, column, + id(internal_pointer)) + return idx + + def index_for_category(self, name): + for row, category in enumerate(self.category_nodes): + if category.py_name == name: + return self.index(row, 0, QModelIndex()) + + def columnCount(self, parent): + return 1 + + def data(self, index, role): + if not index.isValid(): + return NONE + item = self.get_node(index) + return item.data(role) + + def setData(self, index, value, role=Qt.EditRole): + if not index.isValid(): + return False + # set up to reposition at the same item. We can do this except if + # working with the last item and that item is deleted, in which case + # we position at the parent label + val = unicode(value.toString()).strip() + if not val: + error_dialog(self.parent(), _('Item is blank'), + _('An item cannot be set to nothing. Delete it instead.')).exec_() + return False + item = self.get_node(index) + if item.type == TagTreeItem.CATEGORY and item.category_key.startswith('@'): + if val.find('.') >= 0: + error_dialog(self.parent(), _('Rename user category'), + _('You cannot use periods in the name when ' + 'renaming user categories'), show=True) + return False + + user_cats = self.db.prefs.get('user_categories', {}) + user_cat_keys_lower = [icu_lower(k) for k in user_cats] + ckey = item.category_key[1:] + ckey_lower = icu_lower(ckey) + dotpos = ckey.rfind('.') + if dotpos < 0: + nkey = val + else: + nkey = ckey[:dotpos+1] + val + nkey_lower = icu_lower(nkey) + for c in sorted(user_cats.keys(), key=sort_key): + if icu_lower(c).startswith(ckey_lower): + if len(c) == len(ckey): + if strcmp(ckey, nkey) != 0 and \ + nkey_lower in user_cat_keys_lower: + error_dialog(self.parent(), _('Rename user category'), + _('The name %s is already used')%nkey, show=True) + return False + user_cats[nkey] = user_cats[ckey] + del user_cats[ckey] + elif c[len(ckey)] == '.': + rest = c[len(ckey):] + if strcmp(ckey, nkey) != 0 and \ + icu_lower(nkey + rest) in user_cat_keys_lower: + error_dialog(self.parent(), _('Rename user category'), + _('The name %s is already used')%(nkey+rest), show=True) + return False + user_cats[nkey + rest] = user_cats[ckey + rest] + del user_cats[ckey + rest] + self.user_categories_edited.emit(user_cats, nkey) # Does a refresh + return True + + key = item.tag.category + name = item.tag.original_name + # make certain we know about the item's category + if key not in self.db.field_metadata: + return False + if key == 'authors': + if val.find('&') >= 0: + error_dialog(self.parent(), _('Invalid author name'), + _('Author names cannot contain & characters.')).exec_() + return False + if key == 'search': + if val in saved_searches().names(): + error_dialog(self.parent(), _('Duplicate search name'), + _('The saved search name %s is already used.')%val).exec_() + return False + saved_searches().rename(unicode(item.data(role).toString()), val) + item.tag.name = val + self.search_item_renamed.emit() # Does a refresh + else: + if key == 'series': + self.db.rename_series(item.tag.id, val) + elif key == 'publisher': + self.db.rename_publisher(item.tag.id, val) + elif key == 'tags': + self.db.rename_tag(item.tag.id, val) + elif key == 'authors': + self.db.rename_author(item.tag.id, val) + elif self.db.field_metadata[key]['is_custom']: + self.db.rename_custom_item(item.tag.id, val, + label=self.db.field_metadata[key]['label']) + self.tag_item_renamed.emit() + item.tag.name = val + self.rename_item_in_all_user_categories(name, key, val) + self.refresh_required.emit() + return True + + def rename_item_in_all_user_categories(self, item_name, item_category, new_name): + ''' + Search all user categories for items named item_name with category + item_category and rename them to new_name. The caller must arrange to + redisplay the tree as appropriate. + ''' + user_cats = self.db.prefs.get('user_categories', {}) + for k in user_cats.keys(): + new_contents = [] + for tup in user_cats[k]: + if tup[0] == item_name and tup[1] == item_category: + new_contents.append([new_name, item_category, 0]) + else: + new_contents.append(tup) + user_cats[k] = new_contents + self.db.prefs.set('user_categories', user_cats) + + def delete_item_from_all_user_categories(self, item_name, item_category): + ''' + Search all user categories for items named item_name with category + item_category and delete them. The caller must arrange to redisplay the + tree as appropriate. + ''' + user_cats = self.db.prefs.get('user_categories', {}) + for cat in user_cats.keys(): + self.delete_item_from_user_category(cat, item_name, item_category, + user_categories=user_cats) + self.db.prefs.set('user_categories', user_cats) + + def delete_item_from_user_category(self, category, item_name, item_category, + user_categories=None): + if user_categories is not None: + user_cats = user_categories + else: + user_cats = self.db.prefs.get('user_categories', {}) + new_contents = [] + for tup in user_cats[category]: + if tup[0] != item_name or tup[1] != item_category: + new_contents.append(tup) + user_cats[category] = new_contents + if user_categories is None: + self.db.prefs.set('user_categories', user_cats) + + def headerData(self, *args): + return NONE + + def flags(self, index, *args): + ans = Qt.ItemIsEnabled|Qt.ItemIsSelectable|Qt.ItemIsEditable + if index.isValid(): + node = self.data(index, Qt.UserRole) + if node.type == TagTreeItem.TAG: + if node.tag.is_editable: + ans |= Qt.ItemIsDragEnabled + fm = self.db.metadata_for_field(node.tag.category) + if node.tag.category in \ + ('tags', 'series', 'authors', 'rating', 'publisher') or \ + (fm['is_custom'] and \ + fm['datatype'] in ['text', 'rating', 'series', 'enumeration']): + ans |= Qt.ItemIsDropEnabled + else: + ans |= Qt.ItemIsDropEnabled + return ans + + def supportedDropActions(self): + return Qt.CopyAction|Qt.MoveAction + + def path_for_index(self, index): + ans = [] + while index.isValid(): + ans.append(index.row()) + index = self.parent(index) + ans.reverse() + return ans + + def index_for_path(self, path): + parent = QModelIndex() + for i in path: + parent = self.index(i, 0, parent) + if not parent.isValid(): + return QModelIndex() + return parent + + def index(self, row, column, parent): + if not self.hasIndex(row, column, parent): + return QModelIndex() + + if not parent.isValid(): + parent_item = self.root_item + else: + parent_item = self.get_node(parent) + + try: + child_item = parent_item.children[row] + except IndexError: + return QModelIndex() + + ans = self.createIndex(row, column, child_item) + return ans + + def parent(self, index): + if not index.isValid(): + return QModelIndex() + + child_item = self.get_node(index) + parent_item = getattr(child_item, 'parent', None) + + if parent_item is self.root_item or parent_item is None: + return QModelIndex() + + ans = self.createIndex(parent_item.row(), 0, parent_item) + return ans + + def rowCount(self, parent): + if parent.column() > 0: + return 0 + + if not parent.isValid(): + parent_item = self.root_item + else: + parent_item = self.get_node(parent) + + return len(parent_item.children) + + def reset_all_states(self, except_=None): + update_list = [] + def process_tag(tag_item): + tag = tag_item.tag + if tag is except_: + tag_index = self.createIndex(tag_item.row(), 0, tag_item) + self.dataChanged.emit(tag_index, tag_index) + elif tag.state != 0 or tag in update_list: + tag_index = self.createIndex(tag_item.row(), 0, tag_item) + tag.state = 0 + update_list.append(tag) + self.dataChanged.emit(tag_index, tag_index) + for t in tag_item.children: + process_tag(t) + + for t in self.root_item.children: + process_tag(t) + + def clear_state(self): + self.reset_all_states() + + def toggle(self, index, exclusive, set_to=None): + ''' + exclusive: clear all states before applying this one + set_to: None => advance the state, otherwise a value from TAG_SEARCH_STATES + ''' + if not index.isValid(): return False + item = self.get_node(index) + item.toggle(set_to=set_to) + if exclusive: + self.reset_all_states(except_=item.tag) + self.dataChanged.emit(index, index) + return True + + def tokens(self): + ans = [] + # Tags can be in the news and the tags categories. However, because of + # the desire to use two different icons (tags and news), the nodes are + # not shared, which can lead to the possibility of searching twice for + # the same tag. The tags_seen set helps us prevent that + tags_seen = set() + # Tag nodes are in their own category and possibly in user categories. + # They will be 'checked' in both places, but we want to put the node + # into the search string only once. The nodes_seen set helps us do that + nodes_seen = set() + + node_searches = {TAG_SEARCH_STATES['mark_plus'] : 'true', + TAG_SEARCH_STATES['mark_plusplus'] : '.true', + TAG_SEARCH_STATES['mark_minus'] : 'false', + TAG_SEARCH_STATES['mark_minusminus'] : '.false'} + + for node in self.category_nodes: + if node.tag.state: + if node.category_key == "news": + if node_searches[node.tag.state] == 'true': + ans.append('tags:"=' + _('News') + '"') + else: + ans.append('( not tags:"=' + _('News') + '")') + else: + ans.append('%s:%s'%(node.category_key, node_searches[node.tag.state])) + + key = node.category_key + for tag_item in node.all_children(): + if tag_item.type == TagTreeItem.CATEGORY: + if self.collapse_model == 'first letter' and \ + tag_item.temporary and not key.startswith('@') \ + and tag_item.tag.state: + k = 'author_sort' if key == 'authors' else key + letters_seen = {} + for subnode in tag_item.children: + letters_seen[subnode.tag.sort[0]] = True + charclass = ''.join(letters_seen) + if k == 'author_sort': + expr = r'%s:"~(^[%s])|(&\\s*[%s])"'%(k, charclass, charclass) + else: + expr = r'%s:"~^[%s]"'%(k, charclass) + if node_searches[tag_item.tag.state] == 'true': + ans.append(expr) + else: + ans.append('(not ' + expr + ')') + continue + tag = tag_item.tag + if tag.state != TAG_SEARCH_STATES['clear']: + if tag.state == TAG_SEARCH_STATES['mark_minus'] or \ + tag.state == TAG_SEARCH_STATES['mark_minusminus']: + prefix = ' not ' + else: + prefix = '' + category = tag.category if key != 'news' else 'tag' + add_colon = False + if self.db.field_metadata[tag.category]['is_csp']: + add_colon = True + + if tag.name and tag.name[0] == u'\u2605': # char is a star. Assume rating + ans.append('%s%s:%s'%(prefix, category, len(tag.name))) + else: + name = tag.original_name + use_prefix = tag.state in [TAG_SEARCH_STATES['mark_plusplus'], + TAG_SEARCH_STATES['mark_minusminus']] + if category == 'tags': + if name in tags_seen: + continue + tags_seen.add(name) + if tag in nodes_seen: + continue + nodes_seen.add(tag) + n = name.replace(r'"', r'\"') + if name.startswith('.'): + n = '.' + n + ans.append('%s%s:"=%s%s%s"'%(prefix, category, + '.' if use_prefix else '', n, + ':' if add_colon else '')) + return ans + + def find_item_node(self, key, txt, start_path, equals_match=False): + ''' + Search for an item (a node) in the tags browser list that matches both + the key (exact case-insensitive match) and txt (not equals_match => + case-insensitive contains match; equals_match => case_insensitive + equal match). Returns the path to the node. Note that paths are to a + location (second item, fourth item, 25 item), not to a node. If + start_path is None, the search starts with the topmost node. If the tree + is changed subsequent to calling this method, the path can easily refer + to a different node or no node at all. + ''' + if not txt: + return None + txt = lower(txt) if not equals_match else txt + self.path_found = None + if start_path is None: + start_path = [] + + def process_tag(depth, tag_index, tag_item, start_path): + path = self.path_for_index(tag_index) + if depth < len(start_path) and path[depth] <= start_path[depth]: + return False + tag = tag_item.tag + if tag is None: + return False + name = tag.original_name + if (equals_match and strcmp(name, txt) == 0) or \ + (not equals_match and lower(name).find(txt) >= 0): + self.path_found = path + return True + for i,c in enumerate(tag_item.children): + if process_tag(depth+1, self.createIndex(i, 0, c), c, start_path): + return True + return False + + def process_level(depth, category_index, start_path): + path = self.path_for_index(category_index) + if depth < len(start_path): + if path[depth] < start_path[depth]: + return False + if path[depth] > start_path[depth]: + start_path = path + my_key = self.get_node(category_index).category_key + for j in xrange(self.rowCount(category_index)): + tag_index = self.index(j, 0, category_index) + tag_item = self.get_node(tag_index) + if tag_item.type == TagTreeItem.CATEGORY: + if process_level(depth+1, tag_index, start_path): + return True + elif not key or strcmp(key, my_key) == 0: + if process_tag(depth+1, tag_index, tag_item, start_path): + return True + return False + + for i in xrange(self.rowCount(QModelIndex())): + if process_level(0, self.index(i, 0, QModelIndex()), start_path): + break + return self.path_found + + def find_category_node(self, key, parent=QModelIndex()): + ''' + Search for an category node (a top-level node) in the tags browser list + that matches the key (exact case-insensitive match). Returns the path to + the node. Paths are as in find_item_node. + ''' + if not key: + return None + + for i in xrange(self.rowCount(parent)): + idx = self.index(i, 0, parent) + node = self.get_node(idx) + if node.type == TagTreeItem.CATEGORY: + ckey = node.category_key + if strcmp(ckey, key) == 0: + return self.path_for_index(idx) + if len(node.children): + v = self.find_category_node(key, idx) + if v is not None: + return v + return None + + def set_boxed(self, idx): + tag_item = self.get_node(idx) + tag_item.boxed = True + self.dataChanged.emit(idx, idx) + + def clear_boxed(self): + ''' + Clear all boxes around items. + ''' + def process_tag(tag_index, tag_item): + if tag_item.boxed: + tag_item.boxed = False + self.dataChanged.emit(tag_index, tag_index) + for i,c in enumerate(tag_item.children): + process_tag(self.index(i, 0, tag_index), c) + + def process_level(category_index): + for j in xrange(self.rowCount(category_index)): + tag_index = self.index(j, 0, category_index) + tag_item = self.get_node(tag_index) + if tag_item.boxed: + tag_item.boxed = False + self.dataChanged.emit(tag_index, tag_index) + if tag_item.type == TagTreeItem.CATEGORY: + process_level(tag_index) + else: + process_tag(tag_index, tag_item) + + for i in xrange(self.rowCount(QModelIndex())): + process_level(self.index(i, 0, QModelIndex())) + + # }}} + diff --git a/src/calibre/gui2/tag_browser/ui.py b/src/calibre/gui2/tag_browser/ui.py new file mode 100644 index 0000000000..f7f724b118 --- /dev/null +++ b/src/calibre/gui2/tag_browser/ui.py @@ -0,0 +1,458 @@ +#!/usr/bin/env python +# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai +from __future__ import (unicode_literals, division, absolute_import, + print_function) + +__license__ = 'GPL v3' +__copyright__ = '2011, Kovid Goyal ' +__docformat__ = 'restructuredtext en' + +from functools import partial + +from PyQt4.Qt import (Qt, QIcon, QWidget, QHBoxLayout, QVBoxLayout, QShortcut, + QKeySequence, QToolButton, QString, QLabel, QFrame, QTimer, QComboBox, + QMenu, QPushButton) + +from calibre.gui2 import error_dialog, question_dialog +from calibre.gui2.widgets import HistoryLineEdit +from calibre.library.field_metadata import category_icon_map +from calibre.utils.icu import sort_key +from calibre.gui2.tag_browser.view import TagsView +from calibre.ebooks.metadata import title_sort +from calibre.gui2.dialogs.tag_categories import TagCategories +from calibre.gui2.dialogs.tag_list_editor import TagListEditor +from calibre.gui2.dialogs.edit_authors_dialog import EditAuthorsDialog + +class TagBrowserMixin(object): # {{{ + + def __init__(self, db): + self.library_view.model().count_changed_signal.connect(self.tags_view.recount) + self.tags_view.set_database(db, self.tag_match, self.sort_by) + self.tags_view.tags_marked.connect(self.search.set_search_string) + self.tags_view.tag_list_edit.connect(self.do_tags_list_edit) + self.tags_view.edit_user_category.connect(self.do_edit_user_categories) + self.tags_view.delete_user_category.connect(self.do_delete_user_category) + self.tags_view.del_item_from_user_cat.connect(self.do_del_item_from_user_cat) + self.tags_view.add_subcategory.connect(self.do_add_subcategory) + self.tags_view.add_item_to_user_cat.connect(self.do_add_item_to_user_cat) + self.tags_view.saved_search_edit.connect(self.do_saved_search_edit) + self.tags_view.rebuild_saved_searches.connect(self.do_rebuild_saved_searches) + self.tags_view.author_sort_edit.connect(self.do_author_sort_edit) + self.tags_view.tag_item_renamed.connect(self.do_tag_item_renamed) + self.tags_view.search_item_renamed.connect(self.saved_searches_changed) + self.tags_view.drag_drop_finished.connect(self.drag_drop_finished) + self.tags_view.restriction_error.connect(self.do_restriction_error, + type=Qt.QueuedConnection) + + for text, func, args, cat_name in ( + (_('Manage Authors'), + self.do_author_sort_edit, (self, None), 'authors'), + (_('Manage Series'), + self.do_tags_list_edit, (None, 'series'), 'series'), + (_('Manage Publishers'), + self.do_tags_list_edit, (None, 'publisher'), 'publisher'), + (_('Manage Tags'), + self.do_tags_list_edit, (None, 'tags'), 'tags'), + (_('Manage User Categories'), + self.do_edit_user_categories, (None,), 'user:'), + (_('Manage Saved Searches'), + self.do_saved_search_edit, (None,), 'search') + ): + self.manage_items_button.menu().addAction( + QIcon(I(category_icon_map[cat_name])), + text, partial(func, *args)) + + def do_restriction_error(self): + error_dialog(self.tags_view, _('Invalid search restriction'), + _('The current search restriction is invalid'), show=True) + + def do_add_subcategory(self, on_category_key, new_category_name=None): + ''' + Add a subcategory to the category 'on_category'. If new_category_name is + None, then a default name is shown and the user is offered the + opportunity to edit the name. + ''' + db = self.library_view.model().db + user_cats = db.prefs.get('user_categories', {}) + + # Ensure that the temporary name we will use is not already there + i = 0 + if new_category_name is not None: + new_name = new_category_name.replace('.', '') + else: + new_name = _('New Category').replace('.', '') + n = new_name + while True: + new_cat = on_category_key[1:] + '.' + n + if new_cat not in user_cats: + break + i += 1 + n = new_name + unicode(i) + # Add the new category + user_cats[new_cat] = [] + db.prefs.set('user_categories', user_cats) + self.tags_view.set_new_model() + m = self.tags_view.model() + idx = m.index_for_path(m.find_category_node('@' + new_cat)) + m.show_item_at_index(idx) + # Open the editor on the new item to rename it + if new_category_name is None: + self.tags_view.edit(idx) + + def do_edit_user_categories(self, on_category=None): + ''' + Open the user categories editor. + ''' + db = self.library_view.model().db + d = TagCategories(self, db, on_category) + if d.exec_() == d.Accepted: + db.prefs.set('user_categories', d.categories) + db.field_metadata.remove_user_categories() + for k in d.categories: + db.field_metadata.add_user_category('@' + k, k) + db.data.change_search_locations(db.field_metadata.get_search_terms()) + self.tags_view.set_new_model() + + def do_delete_user_category(self, category_name): + ''' + Delete the user category named category_name. Any leading '@' is removed + ''' + if category_name.startswith('@'): + category_name = category_name[1:] + db = self.library_view.model().db + user_cats = db.prefs.get('user_categories', {}) + cat_keys = sorted(user_cats.keys(), key=sort_key) + has_children = False + found = False + for k in cat_keys: + if k == category_name: + found = True + has_children = len(user_cats[k]) + elif k.startswith(category_name + '.'): + has_children = True + if not found: + return error_dialog(self.tags_view, _('Delete user category'), + _('%s is not a user category')%category_name, show=True) + if has_children: + if not question_dialog(self.tags_view, _('Delete user category'), + _('%s contains items. Do you really ' + 'want to delete it?')%category_name): + return + for k in cat_keys: + if k == category_name: + del user_cats[k] + elif k.startswith(category_name + '.'): + del user_cats[k] + db.prefs.set('user_categories', user_cats) + self.tags_view.set_new_model() + + def do_del_item_from_user_cat(self, user_cat, item_name, item_category): + ''' + Delete the item (item_name, item_category) from the user category with + key user_cat. Any leading '@' characters are removed + ''' + if user_cat.startswith('@'): + user_cat = user_cat[1:] + db = self.library_view.model().db + user_cats = db.prefs.get('user_categories', {}) + if user_cat not in user_cats: + error_dialog(self.tags_view, _('Remove category'), + _('User category %s does not exist')%user_cat, + show=True) + return + self.tags_view.model().delete_item_from_user_category(user_cat, + item_name, item_category) + self.tags_view.recount() + + def do_add_item_to_user_cat(self, dest_category, src_name, src_category): + ''' + Add the item src_name in src_category to the user category + dest_category. Any leading '@' is removed + ''' + db = self.library_view.model().db + user_cats = db.prefs.get('user_categories', {}) + + if dest_category and dest_category.startswith('@'): + dest_category = dest_category[1:] + + if dest_category not in user_cats: + return error_dialog(self.tags_view, _('Add to user category'), + _('A user category %s does not exist')%dest_category, show=True) + + # Now add the item to the destination user category + add_it = True + if src_category == 'news': + src_category = 'tags' + for tup in user_cats[dest_category]: + if src_name == tup[0] and src_category == tup[1]: + add_it = False + if add_it: + user_cats[dest_category].append([src_name, src_category, 0]) + db.prefs.set('user_categories', user_cats) + self.tags_view.recount() + + def do_tags_list_edit(self, tag, category): + ''' + Open the 'manage_X' dialog where X == category. If tag is not None, the + dialog will position the editor on that item. + ''' + db=self.library_view.model().db + if category == 'tags': + result = db.get_tags_with_ids() + key = sort_key + elif category == 'series': + result = db.get_series_with_ids() + key = lambda x:sort_key(title_sort(x)) + elif category == 'publisher': + result = db.get_publishers_with_ids() + key = sort_key + else: # should be a custom field + cc_label = None + if category in db.field_metadata: + cc_label = db.field_metadata[category]['label'] + result = db.get_custom_items_with_ids(label=cc_label) + else: + result = [] + key = sort_key + + d = TagListEditor(self, tag_to_match=tag, data=result, key=key) + d.exec_() + if d.result() == d.Accepted: + to_rename = d.to_rename # dict of new text to old id + to_delete = d.to_delete # list of ids + orig_name = d.original_names # dict of id: name + + rename_func = None + if category == 'tags': + rename_func = db.rename_tag + delete_func = db.delete_tag_using_id + elif category == 'series': + rename_func = db.rename_series + delete_func = db.delete_series_using_id + elif category == 'publisher': + rename_func = db.rename_publisher + delete_func = db.delete_publisher_using_id + else: + rename_func = partial(db.rename_custom_item, label=cc_label) + delete_func = partial(db.delete_custom_item_using_id, label=cc_label) + m = self.tags_view.model() + if rename_func: + for item in to_delete: + delete_func(item) + m.delete_item_from_all_user_categories(orig_name[item], category) + for old_id in to_rename: + rename_func(old_id, new_name=unicode(to_rename[old_id])) + m.rename_item_in_all_user_categories(orig_name[old_id], + category, unicode(to_rename[old_id])) + + # Clean up the library view + self.do_tag_item_renamed() + self.tags_view.recount() + + def do_tag_item_renamed(self): + # Clean up library view and search + # get information to redo the selection + rows = [r.row() for r in \ + self.library_view.selectionModel().selectedRows()] + m = self.library_view.model() + ids = [m.id(r) for r in rows] + + m.refresh(reset=False) + m.research() + self.library_view.select_rows(ids) + # refreshing the tags view happens at the emit()/call() site + + def do_author_sort_edit(self, parent, id, select_sort=True): + ''' + Open the manage authors dialog + ''' + db = self.library_view.model().db + editor = EditAuthorsDialog(parent, db, id, select_sort) + d = editor.exec_() + if d: + for (id, old_author, new_author, new_sort) in editor.result: + if old_author != new_author: + # The id might change if the new author already exists + id = db.rename_author(id, new_author) + db.set_sort_field_for_author(id, unicode(new_sort), + commit=False, notify=False) + db.commit() + self.library_view.model().refresh() + self.tags_view.recount() + + def drag_drop_finished(self, ids): + self.library_view.model().refresh_ids(ids) + +# }}} + +class TagBrowserWidget(QWidget): # {{{ + + def __init__(self, parent): + QWidget.__init__(self, parent) + self.parent = parent + self._layout = QVBoxLayout() + self.setLayout(self._layout) + self._layout.setContentsMargins(0,0,0,0) + + # Set up the find box & button + search_layout = QHBoxLayout() + self._layout.addLayout(search_layout) + self.item_search = HistoryLineEdit(parent) + try: + self.item_search.lineEdit().setPlaceholderText( + _('Find item in tag browser')) + except: + pass # Using Qt < 4.7 + self.item_search.setToolTip(_( + 'Search for items. This is a "contains" search; items containing the\n' + 'text anywhere in the name will be found. You can limit the search\n' + 'to particular categories using syntax similar to search. For example,\n' + 'tags:foo will find foo in any tag, but not in authors etc. Entering\n' + '*foo will filter all categories at once, showing only those items\n' + 'containing the text "foo"')) + search_layout.addWidget(self.item_search) + # Not sure if the shortcut should be translatable ... + sc = QShortcut(QKeySequence(_('ALT+f')), parent) + sc.activated.connect(self.set_focus_to_find_box) + + self.search_button = QToolButton() + self.search_button.setText(_('F&ind')) + self.search_button.setToolTip(_('Find the first/next matching item')) + search_layout.addWidget(self.search_button) + + self.expand_button = QToolButton() + self.expand_button.setText('-') + self.expand_button.setToolTip(_('Collapse all categories')) + search_layout.addWidget(self.expand_button) + search_layout.setStretch(0, 10) + search_layout.setStretch(1, 1) + search_layout.setStretch(2, 1) + + self.current_find_position = None + self.search_button.clicked.connect(self.find) + self.item_search.initialize('tag_browser_search') + self.item_search.lineEdit().returnPressed.connect(self.do_find) + self.item_search.lineEdit().textEdited.connect(self.find_text_changed) + self.item_search.activated[QString].connect(self.do_find) + self.item_search.completer().setCaseSensitivity(Qt.CaseSensitive) + + parent.tags_view = TagsView(parent) + self.tags_view = parent.tags_view + self.expand_button.clicked.connect(self.tags_view.collapseAll) + self._layout.addWidget(parent.tags_view) + + # Now the floating 'not found' box + l = QLabel(self.tags_view) + self.not_found_label = l + l.setFrameStyle(QFrame.StyledPanel) + l.setAutoFillBackground(True) + l.setText('

'+_('No More Matches.

Click Find again to go to first match')) + l.setAlignment(Qt.AlignVCenter) + l.setWordWrap(True) + l.resize(l.sizeHint()) + l.move(10,20) + l.setVisible(False) + self.not_found_label_timer = QTimer() + self.not_found_label_timer.setSingleShot(True) + self.not_found_label_timer.timeout.connect(self.not_found_label_timer_event, + type=Qt.QueuedConnection) + + parent.sort_by = QComboBox(parent) + # Must be in the same order as db2.CATEGORY_SORTS + for x in (_('Sort by name'), _('Sort by popularity'), + _('Sort by average rating')): + parent.sort_by.addItem(x) + parent.sort_by.setToolTip( + _('Set the sort order for entries in the Tag Browser')) + parent.sort_by.setStatusTip(parent.sort_by.toolTip()) + parent.sort_by.setCurrentIndex(0) + self._layout.addWidget(parent.sort_by) + + # Must be in the same order as db2.MATCH_TYPE + parent.tag_match = QComboBox(parent) + for x in (_('Match any'), _('Match all')): + parent.tag_match.addItem(x) + parent.tag_match.setCurrentIndex(0) + self._layout.addWidget(parent.tag_match) + parent.tag_match.setToolTip( + _('When selecting multiple entries in the Tag Browser ' + 'match any or all of them')) + parent.tag_match.setStatusTip(parent.tag_match.toolTip()) + + + l = parent.manage_items_button = QPushButton(self) + l.setStyleSheet('QPushButton {text-align: left; }') + l.setText(_('Manage authors, tags, etc')) + l.setToolTip(_('All of these category_managers are available by right-clicking ' + 'on items in the tag browser above')) + l.m = QMenu() + l.setMenu(l.m) + self._layout.addWidget(l) + + # self.leak_test_timer = QTimer(self) + # self.leak_test_timer.timeout.connect(self.test_for_leak) + # self.leak_test_timer.start(5000) + + def set_pane_is_visible(self, to_what): + self.tags_view.set_pane_is_visible(to_what) + + def find_text_changed(self, str): + self.current_find_position = None + + def set_focus_to_find_box(self): + self.item_search.setFocus() + self.item_search.lineEdit().selectAll() + + def do_find(self, str=None): + self.current_find_position = None + self.find() + + def find(self): + model = self.tags_view.model() + model.clear_boxed() + txt = unicode(self.item_search.currentText()).strip() + + if txt.startswith('*'): + self.tags_view.set_new_model(filter_categories_by=txt[1:]) + self.current_find_position = None + return + if model.get_filter_categories_by(): + self.tags_view.set_new_model(filter_categories_by=None) + self.current_find_position = None + model = self.tags_view.model() + + if not txt: + return + + self.item_search.lineEdit().blockSignals(True) + self.search_button.setFocus(True) + self.item_search.lineEdit().blockSignals(False) + + key = None + colon = txt.rfind(':') if len(txt) > 2 else 0 + if colon > 0: + key = self.parent.library_view.model().db.\ + field_metadata.search_term_to_field_key(txt[:colon]) + txt = txt[colon+1:] + + self.current_find_position = \ + model.find_item_node(key, txt, self.current_find_position) + if self.current_find_position: + model.show_item_at_path(self.current_find_position, box=True) + elif self.item_search.text(): + self.not_found_label.setVisible(True) + if self.tags_view.verticalScrollBar().isVisible(): + sbw = self.tags_view.verticalScrollBar().width() + else: + sbw = 0 + width = self.width() - 8 - sbw + height = self.not_found_label.heightForWidth(width) + 20 + self.not_found_label.resize(width, height) + self.not_found_label.move(4, 10) + self.not_found_label_timer.start(2000) + + def not_found_label_timer_event(self): + self.not_found_label.setVisible(False) + +# }}} + diff --git a/src/calibre/gui2/tag_browser/view.py b/src/calibre/gui2/tag_browser/view.py new file mode 100644 index 0000000000..4ff1227a6a --- /dev/null +++ b/src/calibre/gui2/tag_browser/view.py @@ -0,0 +1,588 @@ +#!/usr/bin/env python +# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai +from __future__ import (unicode_literals, division, absolute_import, + print_function) + +__license__ = 'GPL v3' +__copyright__ = '2011, Kovid Goyal ' +__docformat__ = 'restructuredtext en' + +import cPickle +from functools import partial +from itertools import izip + +from PyQt4.Qt import (QItemDelegate, Qt, QTreeView, pyqtSignal, QSize, QIcon, + QApplication, QMenu, QPoint, QModelIndex) + +from calibre.gui2.tag_browser.model import (TagTreeItem, TAG_SEARCH_STATES, + TagsModel) +from calibre.gui2 import config, gprefs +from calibre.utils.search_query_parser import saved_searches +from calibre.utils.icu import sort_key + +class TagDelegate(QItemDelegate): # {{{ + + def paint(self, painter, option, index): + item = index.data(Qt.UserRole).toPyObject() + if item.type != TagTreeItem.TAG: + QItemDelegate.paint(self, painter, option, index) + return + r = option.rect + model = self.parent().model() + icon = model.data(index, Qt.DecorationRole).toPyObject() + painter.save() + if item.tag.state != 0 or not config['show_avg_rating'] or \ + item.tag.avg_rating is None: + icon.paint(painter, r, Qt.AlignLeft) + else: + painter.setOpacity(0.3) + icon.paint(painter, r, Qt.AlignLeft) + painter.setOpacity(1) + rating = item.tag.avg_rating + painter.setClipRect(r.left(), r.bottom()-int(r.height()*(rating/5.0)), + r.width(), r.height()) + icon.paint(painter, r, Qt.AlignLeft) + painter.setClipRect(r) + + # Paint the text + if item.boxed: + painter.drawRoundedRect(r.adjusted(1,1,-1,-1), 5, 5) + r.setLeft(r.left()+r.height()+3) + painter.drawText(r, Qt.AlignLeft|Qt.AlignVCenter, + model.data(index, Qt.DisplayRole).toString()) + painter.restore() + + # }}} + +class TagsView(QTreeView): # {{{ + + refresh_required = pyqtSignal() + tags_marked = pyqtSignal(object) + edit_user_category = pyqtSignal(object) + delete_user_category = pyqtSignal(object) + del_item_from_user_cat = pyqtSignal(object, object, object) + add_item_to_user_cat = pyqtSignal(object, object, object) + add_subcategory = pyqtSignal(object) + tag_list_edit = pyqtSignal(object, object) + saved_search_edit = pyqtSignal(object) + rebuild_saved_searches = pyqtSignal() + author_sort_edit = pyqtSignal(object, object) + tag_item_renamed = pyqtSignal() + search_item_renamed = pyqtSignal() + drag_drop_finished = pyqtSignal(object) + restriction_error = pyqtSignal() + show_at_path = pyqtSignal() + + def __init__(self, parent=None): + QTreeView.__init__(self, parent=None) + self.tag_match = None + self.disable_recounting = False + self.setUniformRowHeights(True) + self.setCursor(Qt.PointingHandCursor) + self.setIconSize(QSize(30, 30)) + self.setTabKeyNavigation(True) + self.setAlternatingRowColors(True) + self.setAnimated(True) + self.setHeaderHidden(True) + self.setItemDelegate(TagDelegate(self)) + self.made_connections = False + self.setAcceptDrops(True) + self.setDragEnabled(True) + self.setDragDropMode(self.DragDrop) + self.setDropIndicatorShown(True) + self.setAutoExpandDelay(500) + self.pane_is_visible = False + self.search_icon = QIcon(I('search.png')) + self.user_category_icon = QIcon(I('tb_folder.png')) + self.delete_icon = QIcon(I('list_remove.png')) + self.rename_icon = QIcon(I('edit-undo.png')) + self.show_at_path.connect(self.show_item_at_path, + type=Qt.QueuedConnection) + + self._model = TagsModel(self) + self._model.search_item_renamed.connect(self.search_item_renamed) + self._model.refresh_required.connect(self.refresh_required, + type=Qt.QueuedConnection) + self._model.tag_item_renamed.connect(self.tag_item_renamed) + self._model.restriction_error.connect(self.restriction_error) + self._model.user_categories_edited.connect(self.user_categories_edited, + type=Qt.QueuedConnection) + self._model.drag_drop_finished.connect(self.drag_drop_finished) + + @property + def hidden_categories(self): + return self._model.hidden_categories + + @property + def db(self): + return self._model.db + + @property + def collapse_model(self): + return self._model.collapse_model + + def set_pane_is_visible(self, to_what): + pv = self.pane_is_visible + self.pane_is_visible = to_what + if to_what and not pv: + self.recount() + + def get_state(self): + state_map = {} + expanded_categories = [] + for row, category in enumerate(self._model.category_nodes): + if self.isExpanded(self._model.index(row, 0, QModelIndex())): + expanded_categories.append(category.py_name) + states = [c.tag.state for c in category.child_tags()] + names = [(c.tag.name, c.tag.category) for c in category.child_tags()] + state_map[category.py_name] = dict(izip(names, states)) + return expanded_categories, state_map + + def reread_collapse_parameters(self): + self._model.reread_collapse_parameters(self.get_state()[1]) + + def set_database(self, db, tag_match, sort_by): + self._model.set_database(db) + + self.pane_is_visible = True # because TagsModel.set_database did a recount + self.sort_by = sort_by + self.tag_match = tag_match + self.setModel(self._model) + self.setContextMenuPolicy(Qt.CustomContextMenu) + pop = config['sort_tags_by'] + self.sort_by.setCurrentIndex(self.db.CATEGORY_SORTS.index(pop)) + try: + match_pop = self.db.MATCH_TYPE.index(config['match_tags_type']) + except ValueError: + match_pop = 0 + self.tag_match.setCurrentIndex(match_pop) + if not self.made_connections: + self.clicked.connect(self.toggle) + self.customContextMenuRequested.connect(self.show_context_menu) + self.refresh_required.connect(self.recount, type=Qt.QueuedConnection) + self.sort_by.currentIndexChanged.connect(self.sort_changed) + self.tag_match.currentIndexChanged.connect(self.match_changed) + self.made_connections = True + self.refresh_signal_processed = True + db.add_listener(self.database_changed) + self.expanded.connect(self.item_expanded) + + def database_changed(self, event, ids): + if self.refresh_signal_processed: + self.refresh_signal_processed = False + self.refresh_required.emit() + + def user_categories_edited(self, user_cats, nkey): + state_map = self.get_state()[1] + self.db.prefs.set('user_categories', user_cats) + self._model.rebuild_node_tree(state_map=state_map) + self.show_at_path.emit('@'+nkey) + + @property + def match_all(self): + return self.tag_match and self.tag_match.currentIndex() > 0 + + def sort_changed(self, pop): + config.set('sort_tags_by', self.db.CATEGORY_SORTS[pop]) + self.recount() + + def match_changed(self, pop): + try: + config.set('match_tags_type', self.db.MATCH_TYPE[pop]) + except: + pass + + def set_search_restriction(self, s): + s = s if s else None + self._model.set_search_restriction(s) + + def mouseReleaseEvent(self, event): + # Swallow everything except leftButton so context menus work correctly + if event.button() == Qt.LeftButton: + QTreeView.mouseReleaseEvent(self, event) + + def mouseDoubleClickEvent(self, event): + # swallow these to avoid toggling and editing at the same time + pass + + @property + def search_string(self): + tokens = self._model.tokens() + joiner = ' and ' if self.match_all else ' or ' + return joiner.join(tokens) + + def toggle(self, index): + self._toggle(index, None) + + def _toggle(self, index, set_to): + ''' + set_to: if None, advance the state. Otherwise must be one of the values + in TAG_SEARCH_STATES + ''' + modifiers = int(QApplication.keyboardModifiers()) + exclusive = modifiers not in (Qt.CTRL, Qt.SHIFT) + if self._model.toggle(index, exclusive, set_to=set_to): + self.tags_marked.emit(self.search_string) + + def conditional_clear(self, search_string): + if search_string != self.search_string: + self.clear() + + def context_menu_handler(self, action=None, category=None, + key=None, index=None, search_state=None): + if not action: + return + try: + if action == 'edit_item': + self.edit(index) + return + if action == 'open_editor': + self.tag_list_edit.emit(category, key) + return + if action == 'manage_categories': + self.edit_user_category.emit(category) + return + if action == 'search': + self._toggle(index, set_to=search_state) + return + if action == 'add_to_category': + tag = index.tag + if len(index.children) > 0: + for c in index.children: + self.add_item_to_user_cat.emit(category, c.tag.original_name, + c.tag.category) + self.add_item_to_user_cat.emit(category, tag.original_name, + tag.category) + return + if action == 'add_subcategory': + self.add_subcategory.emit(key) + return + if action == 'search_category': + self._toggle(index, set_to=search_state) + return + if action == 'delete_user_category': + self.delete_user_category.emit(key) + return + if action == 'delete_search': + saved_searches().delete(key) + self.rebuild_saved_searches.emit() + return + if action == 'delete_item_from_user_category': + tag = index.tag + if len(index.children) > 0: + for c in index.children: + self.del_item_from_user_cat.emit(key, c.tag.original_name, + c.tag.category) + self.del_item_from_user_cat.emit(key, tag.original_name, tag.category) + return + if action == 'manage_searches': + self.saved_search_edit.emit(category) + return + if action == 'edit_author_sort': + self.author_sort_edit.emit(self, index) + return + + reset_filter_categories = True + if action == 'hide': + self.hidden_categories.add(category) + elif action == 'show': + self.hidden_categories.discard(category) + elif action == 'categorization': + changed = self.collapse_model != category + self._model.collapse_model = category + if changed: + reset_filter_categories = False + gprefs['tags_browser_partition_method'] = category + elif action == 'defaults': + self.hidden_categories.clear() + self.db.prefs.set('tag_browser_hidden_categories', list(self.hidden_categories)) + if reset_filter_categories: + self._model.filter_categories_by = None + self._model.rebuild_node_tree() + except: + return + + def show_context_menu(self, point): + def display_name( tag): + if tag.category == 'search': + n = tag.name + if len(n) > 45: + n = n[:45] + '...' + return "'" + n + "'" + return tag.name + + index = self.indexAt(point) + self.context_menu = QMenu(self) + + if index.isValid(): + item = index.data(Qt.UserRole).toPyObject() + tag = None + + if item.type == TagTreeItem.TAG: + tag_item = item + tag = item.tag + while item.type != TagTreeItem.CATEGORY: + item = item.parent + + if item.type == TagTreeItem.CATEGORY: + if not item.category_key.startswith('@'): + while item.parent != self._model.root_item: + item = item.parent + category = unicode(item.name.toString()) + key = item.category_key + # Verify that we are working with a field that we know something about + if key not in self.db.field_metadata: + return True + + # Did the user click on a leaf node? + if tag: + # If the user right-clicked on an editable item, then offer + # the possibility of renaming that item. + if tag.is_editable: + # Add the 'rename' items + self.context_menu.addAction(self.rename_icon, + _('Rename %s')%display_name(tag), + partial(self.context_menu_handler, action='edit_item', + index=index)) + if key == 'authors': + self.context_menu.addAction(_('Edit sort for %s')%display_name(tag), + partial(self.context_menu_handler, + action='edit_author_sort', index=tag.id)) + + # is_editable is also overloaded to mean 'can be added + # to a user category' + m = self.context_menu.addMenu(self.user_category_icon, + _('Add %s to user category')%display_name(tag)) + nt = self.model().category_node_tree + def add_node_tree(tree_dict, m, path): + p = path[:] + for k in sorted(tree_dict.keys(), key=sort_key): + p.append(k) + n = k[1:] if k.startswith('@') else k + m.addAction(self.user_category_icon, n, + partial(self.context_menu_handler, + 'add_to_category', + category='.'.join(p), index=tag_item)) + if len(tree_dict[k]): + tm = m.addMenu(self.user_category_icon, + _('Children of %s')%n) + add_node_tree(tree_dict[k], tm, p) + p.pop() + add_node_tree(nt, m, []) + elif key == 'search': + self.context_menu.addAction(self.rename_icon, + _('Rename %s')%display_name(tag), + partial(self.context_menu_handler, action='edit_item', + index=index)) + self.context_menu.addAction(self.delete_icon, + _('Delete search %s')%display_name(tag), + partial(self.context_menu_handler, + action='delete_search', key=tag.name)) + if key.startswith('@') and not item.is_gst: + self.context_menu.addAction(self.user_category_icon, + _('Remove %s from category %s')% + (display_name(tag), item.py_name), + partial(self.context_menu_handler, + action='delete_item_from_user_category', + key = key, index = tag_item)) + # Add the search for value items. All leaf nodes are searchable + self.context_menu.addAction(self.search_icon, + _('Search for %s')%display_name(tag), + partial(self.context_menu_handler, action='search', + search_state=TAG_SEARCH_STATES['mark_plus'], + index=index)) + self.context_menu.addAction(self.search_icon, + _('Search for everything but %s')%display_name(tag), + partial(self.context_menu_handler, action='search', + search_state=TAG_SEARCH_STATES['mark_minus'], + index=index)) + self.context_menu.addSeparator() + elif key.startswith('@') and not item.is_gst: + if item.can_be_edited: + self.context_menu.addAction(self.rename_icon, + _('Rename %s')%item.py_name, + partial(self.context_menu_handler, action='edit_item', + index=index)) + self.context_menu.addAction(self.user_category_icon, + _('Add sub-category to %s')%item.py_name, + partial(self.context_menu_handler, + action='add_subcategory', key=key)) + self.context_menu.addAction(self.delete_icon, + _('Delete user category %s')%item.py_name, + partial(self.context_menu_handler, + action='delete_user_category', key=key)) + self.context_menu.addSeparator() + # Hide/Show/Restore categories + self.context_menu.addAction(_('Hide category %s') % category, + partial(self.context_menu_handler, action='hide', + category=key)) + if self.hidden_categories: + m = self.context_menu.addMenu(_('Show category')) + for col in sorted(self.hidden_categories, + key=lambda x: sort_key(self.db.field_metadata[x]['name'])): + m.addAction(self.db.field_metadata[col]['name'], + partial(self.context_menu_handler, action='show', category=col)) + + # search by category. Some categories are not searchable, such + # as search and news + if item.tag.is_searchable: + self.context_menu.addAction(self.search_icon, + _('Search for books in category %s')%category, + partial(self.context_menu_handler, + action='search_category', + index=self._model.createIndex(item.row(), 0, item), + search_state=TAG_SEARCH_STATES['mark_plus'])) + self.context_menu.addAction(self.search_icon, + _('Search for books not in category %s')%category, + partial(self.context_menu_handler, + action='search_category', + index=self._model.createIndex(item.row(), 0, item), + search_state=TAG_SEARCH_STATES['mark_minus'])) + # Offer specific editors for tags/series/publishers/saved searches + self.context_menu.addSeparator() + if key in ['tags', 'publisher', 'series'] or \ + self.db.field_metadata[key]['is_custom']: + self.context_menu.addAction(_('Manage %s')%category, + partial(self.context_menu_handler, action='open_editor', + category=tag.original_name if tag else None, + key=key)) + elif key == 'authors': + self.context_menu.addAction(_('Manage %s')%category, + partial(self.context_menu_handler, action='edit_author_sort')) + elif key == 'search': + self.context_menu.addAction(_('Manage Saved Searches'), + partial(self.context_menu_handler, action='manage_searches', + category=tag.name if tag else None)) + + # Always show the user categories editor + self.context_menu.addSeparator() + if key.startswith('@') and \ + key[1:] in self.db.prefs.get('user_categories', {}).keys(): + self.context_menu.addAction(_('Manage User Categories'), + partial(self.context_menu_handler, action='manage_categories', + category=key[1:])) + else: + self.context_menu.addAction(_('Manage User Categories'), + partial(self.context_menu_handler, action='manage_categories', + category=None)) + + if self.hidden_categories: + if not self.context_menu.isEmpty(): + self.context_menu.addSeparator() + self.context_menu.addAction(_('Show all categories'), + partial(self.context_menu_handler, action='defaults')) + + m = self.context_menu.addMenu(_('Change sub-categorization scheme')) + da = m.addAction('Disable', + partial(self.context_menu_handler, action='categorization', category='disable')) + fla = m.addAction('By first letter', + partial(self.context_menu_handler, action='categorization', category='first letter')) + pa = m.addAction('Partition', + partial(self.context_menu_handler, action='categorization', category='partition')) + if self.collapse_model == 'disable': + da.setCheckable(True) + da.setChecked(True) + elif self.collapse_model == 'first letter': + fla.setCheckable(True) + fla.setChecked(True) + else: + pa.setCheckable(True) + pa.setChecked(True) + + if not self.context_menu.isEmpty(): + self.context_menu.popup(self.mapToGlobal(point)) + return True + + def dragMoveEvent(self, event): + QTreeView.dragMoveEvent(self, event) + self.setDropIndicatorShown(False) + index = self.indexAt(event.pos()) + if not index.isValid(): + return + src_is_tb = event.mimeData().hasFormat('application/calibre+from_tag_browser') + item = index.data(Qt.UserRole).toPyObject() + flags = self._model.flags(index) + if item.type == TagTreeItem.TAG and flags & Qt.ItemIsDropEnabled: + self.setDropIndicatorShown(not src_is_tb) + return + if item.type == TagTreeItem.CATEGORY and not item.is_gst: + fm_dest = self.db.metadata_for_field(item.category_key) + if fm_dest['kind'] == 'user': + if src_is_tb: + if event.dropAction() == Qt.MoveAction: + data = str(event.mimeData().data('application/calibre+from_tag_browser')) + src = cPickle.loads(data) + for s in src: + if s[0] == TagTreeItem.TAG and \ + (not s[1].startswith('@') or s[2]): + return + self.setDropIndicatorShown(True) + return + md = event.mimeData() + if hasattr(md, 'column_name'): + fm_src = self.db.metadata_for_field(md.column_name) + if md.column_name in ['authors', 'publisher', 'series'] or \ + (fm_src['is_custom'] and ( + (fm_src['datatype'] in ['series', 'text', 'enumeration'] and + not fm_src['is_multiple']) or + (fm_src['datatype'] == 'composite' and + fm_src['display'].get('make_category', False)))): + self.setDropIndicatorShown(True) + + def clear(self): + if self.model(): + self.model().clear_state() + + def is_visible(self, idx): + item = idx.data(Qt.UserRole).toPyObject() + if getattr(item, 'type', None) == TagTreeItem.TAG: + idx = idx.parent() + return self.isExpanded(idx) + + def recount(self, *args): + ''' + Rebuild the category tree, expand any categories that were expanded, + reset the search states, and reselect the current node. + ''' + if self.disable_recounting or not self.pane_is_visible: + return + self.refresh_signal_processed = True + ci = self.currentIndex() + if not ci.isValid(): + ci = self.indexAt(QPoint(10, 10)) + path = self.model().path_for_index(ci) if self.is_visible(ci) else None + expanded_categories, state_map = self.get_state() + self._model.rebuild_node_tree(state_map=state_map) + for category in expanded_categories: + self.expand(self._model.index_for_category(category)) + self.show_item_at_path(path) + + def show_item_at_path(self, path, box=False, + position=QTreeView.PositionAtCenter): + ''' + Scroll the browser and open categories to show the item referenced by + path. If possible, the item is placed in the center. If box=True, a + box is drawn around the item. + ''' + if path: + self.show_item_at_index(self._model.index_for_path(path), box=box, + position=position) + + def show_item_at_index(self, idx, box=False, + position=QTreeView.PositionAtCenter): + if idx.isValid(): + self.setCurrentIndex(idx) + self.scrollTo(idx, position) + self.setCurrentIndex(idx) + if box: + self._model.set_boxed(idx) + + def item_expanded(self, idx): + ''' + Called by the expanded signal + ''' + self.setCurrentIndex(idx) + + # }}} + + diff --git a/src/calibre/gui2/tag_view.py b/src/calibre/gui2/tag_view.py deleted file mode 100644 index 22319891d5..0000000000 --- a/src/calibre/gui2/tag_view.py +++ /dev/null @@ -1,2303 +0,0 @@ -#!/usr/bin/env python -__license__ = 'GPL v3' -__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' -__docformat__ = 'restructuredtext en' - -''' -Browsing book collection by tags. -''' - -import traceback, copy, cPickle - -from itertools import izip, repeat -from functools import partial - -from PyQt4.Qt import (Qt, QTreeView, QApplication, pyqtSignal, QFont, QSize, - QIcon, QPoint, QVBoxLayout, QHBoxLayout, QComboBox, QTimer, - QAbstractItemModel, QVariant, QModelIndex, QMenu, QFrame, - QWidget, QItemDelegate, QString, QLabel, QPushButton, - QShortcut, QKeySequence, SIGNAL, QMimeData, QToolButton) - -from calibre.ebooks.metadata import title_sort -from calibre.gui2 import config, NONE, gprefs -from calibre.library.field_metadata import TagsIcons, category_icon_map -from calibre.library.database2 import Tag -from calibre.utils.config import tweaks -from calibre.utils.icu import sort_key, lower, strcmp -from calibre.utils.search_query_parser import saved_searches -from calibre.utils.formatter import eval_formatter -from calibre.gui2 import error_dialog, question_dialog -from calibre.gui2.dialogs.confirm_delete import confirm -from calibre.gui2.dialogs.tag_categories import TagCategories -from calibre.gui2.dialogs.tag_list_editor import TagListEditor -from calibre.gui2.dialogs.edit_authors_dialog import EditAuthorsDialog -from calibre.gui2.widgets import HistoryLineEdit - -class TagDelegate(QItemDelegate): # {{{ - - def paint(self, painter, option, index): - item = index.internalPointer() - if item.type != TagTreeItem.TAG: - QItemDelegate.paint(self, painter, option, index) - return - r = option.rect - model = self.parent().model() - icon = model.data(index, Qt.DecorationRole).toPyObject() - painter.save() - if item.tag.state != 0 or not config['show_avg_rating'] or \ - item.tag.avg_rating is None: - icon.paint(painter, r, Qt.AlignLeft) - else: - painter.setOpacity(0.3) - icon.paint(painter, r, Qt.AlignLeft) - painter.setOpacity(1) - rating = item.tag.avg_rating - painter.setClipRect(r.left(), r.bottom()-int(r.height()*(rating/5.0)), - r.width(), r.height()) - icon.paint(painter, r, Qt.AlignLeft) - painter.setClipRect(r) - - # Paint the text - if item.boxed: - painter.drawRoundedRect(r.adjusted(1,1,-1,-1), 5, 5) - r.setLeft(r.left()+r.height()+3) - painter.drawText(r, Qt.AlignLeft|Qt.AlignVCenter, - model.data(index, Qt.DisplayRole).toString()) - painter.restore() - - # }}} - -TAG_SEARCH_STATES = {'clear': 0, 'mark_plus': 1, 'mark_plusplus': 2, - 'mark_minus': 3, 'mark_minusminus': 4} - -class TagsView(QTreeView): # {{{ - - refresh_required = pyqtSignal() - tags_marked = pyqtSignal(object) - edit_user_category = pyqtSignal(object) - delete_user_category = pyqtSignal(object) - del_item_from_user_cat = pyqtSignal(object, object, object) - add_item_to_user_cat = pyqtSignal(object, object, object) - add_subcategory = pyqtSignal(object) - tag_list_edit = pyqtSignal(object, object) - saved_search_edit = pyqtSignal(object) - rebuild_saved_searches = pyqtSignal() - author_sort_edit = pyqtSignal(object, object) - tag_item_renamed = pyqtSignal() - search_item_renamed = pyqtSignal() - drag_drop_finished = pyqtSignal(object) - restriction_error = pyqtSignal() - - def __init__(self, parent=None): - QTreeView.__init__(self, parent=None) - self.tag_match = None - self.disable_recounting = False - self.setUniformRowHeights(True) - self.setCursor(Qt.PointingHandCursor) - self.setIconSize(QSize(30, 30)) - self.setTabKeyNavigation(True) - self.setAlternatingRowColors(True) - self.setAnimated(True) - self.setHeaderHidden(True) - self.setItemDelegate(TagDelegate(self)) - self.made_connections = False - self.setAcceptDrops(True) - self.setDragEnabled(True) - self.setDragDropMode(self.DragDrop) - self.setDropIndicatorShown(True) - self.setAutoExpandDelay(500) - self.pane_is_visible = False - if gprefs['tags_browser_collapse_at'] == 0: - self.collapse_model = 'disable' - else: - self.collapse_model = gprefs['tags_browser_partition_method'] - self.search_icon = QIcon(I('search.png')) - self.user_category_icon = QIcon(I('tb_folder.png')) - self.delete_icon = QIcon(I('list_remove.png')) - self.rename_icon = QIcon(I('edit-undo.png')) - - def set_pane_is_visible(self, to_what): - pv = self.pane_is_visible - self.pane_is_visible = to_what - if to_what and not pv: - self.recount() - - def reread_collapse_parameters(self): - if gprefs['tags_browser_collapse_at'] == 0: - self.collapse_model = 'disable' - else: - self.collapse_model = gprefs['tags_browser_partition_method'] - self.set_new_model(self._model.get_filter_categories_by()) - - def set_database(self, db, tag_match, sort_by): - hidden_cats = db.prefs.get('tag_browser_hidden_categories', None) - self.hidden_categories = [] - # migrate from config to db prefs - if hidden_cats is None: - hidden_cats = config['tag_browser_hidden_categories'] - # strip out any non-existence field keys - for cat in hidden_cats: - if cat in db.field_metadata: - self.hidden_categories.append(cat) - db.prefs.set('tag_browser_hidden_categories', list(self.hidden_categories)) - self.hidden_categories = set(self.hidden_categories) - - old = getattr(self, '_model', None) - if old is not None: - old.break_cycles() - self._model = TagsModel(db, parent=self, - hidden_categories=self.hidden_categories, - search_restriction=None, - drag_drop_finished=self.drag_drop_finished, - collapse_model=self.collapse_model, - state_map={}) - self.pane_is_visible = True # because TagsModel.init did a recount - self.sort_by = sort_by - self.tag_match = tag_match - self.db = db - self.search_restriction = None - self.setModel(self._model) - self.setContextMenuPolicy(Qt.CustomContextMenu) - pop = config['sort_tags_by'] - self.sort_by.setCurrentIndex(self.db.CATEGORY_SORTS.index(pop)) - try: - match_pop = self.db.MATCH_TYPE.index(config['match_tags_type']) - except ValueError: - match_pop = 0 - self.tag_match.setCurrentIndex(match_pop) - if not self.made_connections: - self.clicked.connect(self.toggle) - self.customContextMenuRequested.connect(self.show_context_menu) - self.refresh_required.connect(self.recount, type=Qt.QueuedConnection) - self.sort_by.currentIndexChanged.connect(self.sort_changed) - self.tag_match.currentIndexChanged.connect(self.match_changed) - self.made_connections = True - self.refresh_signal_processed = True - db.add_listener(self.database_changed) - self.expanded.connect(self.item_expanded) - - def database_changed(self, event, ids): - if self.refresh_signal_processed: - self.refresh_signal_processed = False - self.refresh_required.emit() - - @property - def match_all(self): - return self.tag_match and self.tag_match.currentIndex() > 0 - - def sort_changed(self, pop): - config.set('sort_tags_by', self.db.CATEGORY_SORTS[pop]) - self.recount() - - def match_changed(self, pop): - try: - config.set('match_tags_type', self.db.MATCH_TYPE[pop]) - except: - pass - - def set_search_restriction(self, s): - if s: - self.search_restriction = s - else: - self.search_restriction = None - self.set_new_model() - - def mouseReleaseEvent(self, event): - # Swallow everything except leftButton so context menus work correctly - if event.button() == Qt.LeftButton: - QTreeView.mouseReleaseEvent(self, event) - - def mouseDoubleClickEvent(self, event): - # swallow these to avoid toggling and editing at the same time - pass - - @property - def search_string(self): - tokens = self._model.tokens() - joiner = ' and ' if self.match_all else ' or ' - return joiner.join(tokens) - - def toggle(self, index): - self._toggle(index, None) - - def _toggle(self, index, set_to): - ''' - set_to: if None, advance the state. Otherwise must be one of the values - in TAG_SEARCH_STATES - ''' - modifiers = int(QApplication.keyboardModifiers()) - exclusive = modifiers not in (Qt.CTRL, Qt.SHIFT) - if self._model.toggle(index, exclusive, set_to=set_to): - self.tags_marked.emit(self.search_string) - - def conditional_clear(self, search_string): - if search_string != self.search_string: - self.clear() - - def context_menu_handler(self, action=None, category=None, - key=None, index=None, search_state=None): - if not action: - return - try: - if action == 'edit_item': - self.edit(index) - return - if action == 'open_editor': - self.tag_list_edit.emit(category, key) - return - if action == 'manage_categories': - self.edit_user_category.emit(category) - return - if action == 'search': - self._toggle(index, set_to=search_state) - return - if action == 'add_to_category': - tag = index.tag - if len(index.children) > 0: - for c in index.children: - self.add_item_to_user_cat.emit(category, c.tag.original_name, - c.tag.category) - self.add_item_to_user_cat.emit(category, tag.original_name, - tag.category) - return - if action == 'add_subcategory': - self.add_subcategory.emit(key) - return - if action == 'search_category': - self._toggle(index, set_to=search_state) - return - if action == 'delete_user_category': - self.delete_user_category.emit(key) - return - if action == 'delete_search': - saved_searches().delete(key) - self.rebuild_saved_searches.emit() - return - if action == 'delete_item_from_user_category': - tag = index.tag - if len(index.children) > 0: - for c in index.children: - self.del_item_from_user_cat.emit(key, c.tag.original_name, - c.tag.category) - self.del_item_from_user_cat.emit(key, tag.original_name, tag.category) - return - if action == 'manage_searches': - self.saved_search_edit.emit(category) - return - if action == 'edit_author_sort': - self.author_sort_edit.emit(self, index) - return - - if action == 'hide': - self.hidden_categories.add(category) - elif action == 'show': - self.hidden_categories.discard(category) - elif action == 'categorization': - changed = self.collapse_model != category - self.collapse_model = category - if changed: - self.set_new_model(self._model.get_filter_categories_by()) - gprefs['tags_browser_partition_method'] = category - elif action == 'defaults': - self.hidden_categories.clear() - self.db.prefs.set('tag_browser_hidden_categories', list(self.hidden_categories)) - self.set_new_model() - except: - return - - def show_context_menu(self, point): - def display_name( tag): - if tag.category == 'search': - n = tag.name - if len(n) > 45: - n = n[:45] + '...' - return "'" + n + "'" - return tag.name - - index = self.indexAt(point) - self.context_menu = QMenu(self) - - if index.isValid(): - item = index.internalPointer() - tag = None - - if item.type == TagTreeItem.TAG: - tag_item = item - tag = item.tag - while item.type != TagTreeItem.CATEGORY: - item = item.parent - - if item.type == TagTreeItem.CATEGORY: - if not item.category_key.startswith('@'): - while item.parent != self._model.root_item: - item = item.parent - category = unicode(item.name.toString()) - key = item.category_key - # Verify that we are working with a field that we know something about - if key not in self.db.field_metadata: - return True - - # Did the user click on a leaf node? - if tag: - # If the user right-clicked on an editable item, then offer - # the possibility of renaming that item. - if tag.is_editable: - # Add the 'rename' items - self.context_menu.addAction(self.rename_icon, - _('Rename %s')%display_name(tag), - partial(self.context_menu_handler, action='edit_item', - index=index)) - if key == 'authors': - self.context_menu.addAction(_('Edit sort for %s')%display_name(tag), - partial(self.context_menu_handler, - action='edit_author_sort', index=tag.id)) - - # is_editable is also overloaded to mean 'can be added - # to a user category' - m = self.context_menu.addMenu(self.user_category_icon, - _('Add %s to user category')%display_name(tag)) - nt = self.model().category_node_tree - def add_node_tree(tree_dict, m, path): - p = path[:] - for k in sorted(tree_dict.keys(), key=sort_key): - p.append(k) - n = k[1:] if k.startswith('@') else k - m.addAction(self.user_category_icon, n, - partial(self.context_menu_handler, - 'add_to_category', - category='.'.join(p), index=tag_item)) - if len(tree_dict[k]): - tm = m.addMenu(self.user_category_icon, - _('Children of %s')%n) - add_node_tree(tree_dict[k], tm, p) - p.pop() - add_node_tree(nt, m, []) - elif key == 'search': - self.context_menu.addAction(self.rename_icon, - _('Rename %s')%display_name(tag), - partial(self.context_menu_handler, action='edit_item', - index=index)) - self.context_menu.addAction(self.delete_icon, - _('Delete search %s')%display_name(tag), - partial(self.context_menu_handler, - action='delete_search', key=tag.name)) - if key.startswith('@') and not item.is_gst: - self.context_menu.addAction(self.user_category_icon, - _('Remove %s from category %s')% - (display_name(tag), item.py_name), - partial(self.context_menu_handler, - action='delete_item_from_user_category', - key = key, index = tag_item)) - # Add the search for value items. All leaf nodes are searchable - self.context_menu.addAction(self.search_icon, - _('Search for %s')%display_name(tag), - partial(self.context_menu_handler, action='search', - search_state=TAG_SEARCH_STATES['mark_plus'], - index=index)) - self.context_menu.addAction(self.search_icon, - _('Search for everything but %s')%display_name(tag), - partial(self.context_menu_handler, action='search', - search_state=TAG_SEARCH_STATES['mark_minus'], - index=index)) - self.context_menu.addSeparator() - elif key.startswith('@') and not item.is_gst: - if item.can_be_edited: - self.context_menu.addAction(self.rename_icon, - _('Rename %s')%item.py_name, - partial(self.context_menu_handler, action='edit_item', - index=index)) - self.context_menu.addAction(self.user_category_icon, - _('Add sub-category to %s')%item.py_name, - partial(self.context_menu_handler, - action='add_subcategory', key=key)) - self.context_menu.addAction(self.delete_icon, - _('Delete user category %s')%item.py_name, - partial(self.context_menu_handler, - action='delete_user_category', key=key)) - self.context_menu.addSeparator() - # Hide/Show/Restore categories - self.context_menu.addAction(_('Hide category %s') % category, - partial(self.context_menu_handler, action='hide', - category=key)) - if self.hidden_categories: - m = self.context_menu.addMenu(_('Show category')) - for col in sorted(self.hidden_categories, - key=lambda x: sort_key(self.db.field_metadata[x]['name'])): - m.addAction(self.db.field_metadata[col]['name'], - partial(self.context_menu_handler, action='show', category=col)) - - # search by category. Some categories are not searchable, such - # as search and news - if item.tag.is_searchable: - self.context_menu.addAction(self.search_icon, - _('Search for books in category %s')%category, - partial(self.context_menu_handler, - action='search_category', - index=self._model.createIndex(item.row(), 0, item), - search_state=TAG_SEARCH_STATES['mark_plus'])) - self.context_menu.addAction(self.search_icon, - _('Search for books not in category %s')%category, - partial(self.context_menu_handler, - action='search_category', - index=self._model.createIndex(item.row(), 0, item), - search_state=TAG_SEARCH_STATES['mark_minus'])) - # Offer specific editors for tags/series/publishers/saved searches - self.context_menu.addSeparator() - if key in ['tags', 'publisher', 'series'] or \ - self.db.field_metadata[key]['is_custom']: - self.context_menu.addAction(_('Manage %s')%category, - partial(self.context_menu_handler, action='open_editor', - category=tag.original_name if tag else None, - key=key)) - elif key == 'authors': - self.context_menu.addAction(_('Manage %s')%category, - partial(self.context_menu_handler, action='edit_author_sort')) - elif key == 'search': - self.context_menu.addAction(_('Manage Saved Searches'), - partial(self.context_menu_handler, action='manage_searches', - category=tag.name if tag else None)) - - # Always show the user categories editor - self.context_menu.addSeparator() - if key.startswith('@') and \ - key[1:] in self.db.prefs.get('user_categories', {}).keys(): - self.context_menu.addAction(_('Manage User Categories'), - partial(self.context_menu_handler, action='manage_categories', - category=key[1:])) - else: - self.context_menu.addAction(_('Manage User Categories'), - partial(self.context_menu_handler, action='manage_categories', - category=None)) - - if self.hidden_categories: - if not self.context_menu.isEmpty(): - self.context_menu.addSeparator() - self.context_menu.addAction(_('Show all categories'), - partial(self.context_menu_handler, action='defaults')) - - m = self.context_menu.addMenu(_('Change sub-categorization scheme')) - da = m.addAction('Disable', - partial(self.context_menu_handler, action='categorization', category='disable')) - fla = m.addAction('By first letter', - partial(self.context_menu_handler, action='categorization', category='first letter')) - pa = m.addAction('Partition', - partial(self.context_menu_handler, action='categorization', category='partition')) - if self.collapse_model == 'disable': - da.setCheckable(True) - da.setChecked(True) - elif self.collapse_model == 'first letter': - fla.setCheckable(True) - fla.setChecked(True) - else: - pa.setCheckable(True) - pa.setChecked(True) - - if not self.context_menu.isEmpty(): - self.context_menu.popup(self.mapToGlobal(point)) - return True - - def dragMoveEvent(self, event): - QTreeView.dragMoveEvent(self, event) - self.setDropIndicatorShown(False) - index = self.indexAt(event.pos()) - if not index.isValid(): - return - src_is_tb = event.mimeData().hasFormat('application/calibre+from_tag_browser') - item = index.internalPointer() - flags = self._model.flags(index) - if item.type == TagTreeItem.TAG and flags & Qt.ItemIsDropEnabled: - self.setDropIndicatorShown(not src_is_tb) - return - if item.type == TagTreeItem.CATEGORY and not item.is_gst: - fm_dest = self.db.metadata_for_field(item.category_key) - if fm_dest['kind'] == 'user': - if src_is_tb: - if event.dropAction() == Qt.MoveAction: - data = str(event.mimeData().data('application/calibre+from_tag_browser')) - src = cPickle.loads(data) - for s in src: - if s[0] == TagTreeItem.TAG and \ - (not s[1].startswith('@') or s[2]): - return - self.setDropIndicatorShown(True) - return - md = event.mimeData() - if hasattr(md, 'column_name'): - fm_src = self.db.metadata_for_field(md.column_name) - if md.column_name in ['authors', 'publisher', 'series'] or \ - (fm_src['is_custom'] and ( - (fm_src['datatype'] in ['series', 'text', 'enumeration'] and - not fm_src['is_multiple']) or - (fm_src['datatype'] == 'composite' and - fm_src['display'].get('make_category', False)))): - self.setDropIndicatorShown(True) - - def clear(self): - if self.model(): - self.model().clear_state() - - def is_visible(self, idx): - item = idx.internalPointer() - if getattr(item, 'type', None) == TagTreeItem.TAG: - idx = idx.parent() - return self.isExpanded(idx) - - def recount(self, *args): - ''' - Rebuild the category tree, expand any categories that were expanded, - reset the search states, and reselect the current node. - ''' - if self.disable_recounting or not self.pane_is_visible: - return - self.refresh_signal_processed = True - ci = self.currentIndex() - if not ci.isValid(): - ci = self.indexAt(QPoint(10, 10)) - path = self.model().path_for_index(ci) if self.is_visible(ci) else None - expanded_categories, state_map = self.model().get_state() - self.set_new_model(state_map=state_map) - for category in expanded_categories: - self.expand(self.model().index_for_category(category)) - self._model.show_item_at_path(path) - - def item_expanded(self, idx): - ''' - Called by the expanded signal - ''' - self.setCurrentIndex(idx) - - def set_new_model(self, filter_categories_by=None, state_map={}): - ''' - There are cases where we need to rebuild the category tree without - attempting to reposition the current node. - ''' - try: - old = getattr(self, '_model', None) - if old is not None: - old.break_cycles() - self._model = TagsModel(self.db, parent=self, - hidden_categories=self.hidden_categories, - search_restriction=self.search_restriction, - drag_drop_finished=self.drag_drop_finished, - filter_categories_by=filter_categories_by, - collapse_model=self.collapse_model, - state_map=state_map) - self.setModel(self._model) - except: - # The DB must be gone. Set the model to None and hope that someone - # will call set_database later. I don't know if this in fact works. - # But perhaps a Bad Thing Happened, so print the exception - traceback.print_exc() - self._model = None - self.setModel(None) - # }}} - -class TagTreeItem(object): # {{{ - - CATEGORY = 0 - TAG = 1 - ROOT = 2 - - def __init__(self, data=None, category_icon=None, icon_map=None, - parent=None, tooltip=None, category_key=None, temporary=False): - self.parent = parent - self.children = [] - self.id_set = set() - self.is_gst = False - self.boxed = False - self.icon_state_map = list(map(QVariant, icon_map)) - if self.parent is not None: - self.parent.append(self) - if data is None: - self.type = self.ROOT - else: - self.type = self.TAG if category_icon is None else self.CATEGORY - if self.type == self.CATEGORY: - self.name, self.icon = map(QVariant, (data, category_icon)) - self.py_name = data - self.bold_font = QFont() - self.bold_font.setBold(True) - self.bold_font = QVariant(self.bold_font) - self.category_key = category_key - self.temporary = temporary - self.tag = Tag(data, category=category_key, - is_editable=category_key not in ['news', 'search', 'identifiers'], - is_searchable=category_key not in ['search']) - - elif self.type == self.TAG: - self.icon_state_map[0] = QVariant(data.icon) - self.tag = data - if tooltip: - self.tooltip = tooltip + ' ' - else: - self.tooltip = '' - - def break_cycles(self): - for x in self.children: - try: - x.break_cycles() - except: - pass - self.parent = self.icon_state_map = self.bold_font = self.tag = \ - self.icon = self.children = self.tooltip = \ - self.py_name = self.id_set = self.category_key = None - - def __str__(self): - if self.type == self.ROOT: - return 'ROOT' - if self.type == self.CATEGORY: - return 'CATEGORY:'+str(QVariant.toString(self.name))+':%d'%len(self.children) - return 'TAG:'+self.tag.name - - def row(self): - if self.parent is not None: - return self.parent.children.index(self) - return 0 - - def append(self, child): - child.parent = self - self.children.append(child) - - def data(self, role): - if role == Qt.UserRole: - return self - if self.type == self.TAG: - return self.tag_data(role) - if self.type == self.CATEGORY: - return self.category_data(role) - return NONE - - def category_data(self, role): - if role == Qt.DisplayRole: - return QVariant(self.py_name + ' [%d]'%len(self.child_tags())) - if role == Qt.EditRole: - return QVariant(self.py_name) - if role == Qt.DecorationRole: - if self.tag.state: - return self.icon_state_map[self.tag.state] - return self.icon - if role == Qt.FontRole: - return self.bold_font - if role == Qt.ToolTipRole and self.tooltip is not None: - return QVariant(self.tooltip) - return NONE - - def tag_data(self, role): - tag = self.tag - if tag.use_sort_as_name: - name = tag.sort - tt_author = True - else: - p = self - while p.parent.type != self.ROOT: - p = p.parent - if not tag.is_hierarchical: - name = tag.original_name - else: - name = tag.name - tt_author = False - if role == Qt.DisplayRole: - count = len(self.id_set) - count = count if count > 0 else tag.count - if count == 0: - return QVariant('%s'%(name)) - else: - return QVariant('[%d] %s'%(count, name)) - if role == Qt.EditRole: - return QVariant(tag.original_name) - if role == Qt.DecorationRole: - return self.icon_state_map[tag.state] - if role == Qt.ToolTipRole: - if tt_author: - if tag.tooltip is not None: - return QVariant('(%s) %s'%(tag.name, tag.tooltip)) - else: - return QVariant(tag.name) - if tag.tooltip: - return QVariant(self.tooltip + tag.tooltip) - else: - return QVariant(self.tooltip) - return NONE - - def toggle(self, set_to=None): - ''' - set_to: None => advance the state, otherwise a value from TAG_SEARCH_STATES - ''' - if set_to is None: - while True: - self.tag.state = (self.tag.state + 1)%5 - if self.tag.state == TAG_SEARCH_STATES['mark_plus'] or \ - self.tag.state == TAG_SEARCH_STATES['mark_minus']: - if self.tag.is_searchable: - break - elif self.tag.state == TAG_SEARCH_STATES['mark_plusplus'] or\ - self.tag.state == TAG_SEARCH_STATES['mark_minusminus']: - if self.tag.is_searchable and len(self.children) and \ - self.tag.is_hierarchical == '5state': - break - else: - break - else: - self.tag.state = set_to - - def all_children(self): - res = [] - def recurse(nodes, res): - for t in nodes: - res.append(t) - recurse(t.children, res) - recurse(self.children, res) - return res - - def child_tags(self): - res = [] - def recurse(nodes, res): - for t in nodes: - if t.type != TagTreeItem.CATEGORY: - res.append(t) - recurse(t.children, res) - recurse(self.children, res) - return res - # }}} - -class TagsModel(QAbstractItemModel): # {{{ - - def __init__(self, db, parent, hidden_categories=None, - search_restriction=None, drag_drop_finished=None, - filter_categories_by=None, collapse_model='disable', - state_map={}): - QAbstractItemModel.__init__(self, parent) - - # must do this here because 'QPixmap: Must construct a QApplication - # before a QPaintDevice'. The ':' at the end avoids polluting either of - # the other namespaces (alpha, '#', or '@') - iconmap = {} - for key in category_icon_map: - iconmap[key] = QIcon(I(category_icon_map[key])) - self.category_icon_map = TagsIcons(iconmap) - - self.categories_with_ratings = ['authors', 'series', 'publisher', 'tags'] - self.drag_drop_finished = drag_drop_finished - - self.icon_state_map = [None, QIcon(I('plus.png')), QIcon(I('plusplus.png')), - QIcon(I('minus.png')), QIcon(I('minusminus.png'))] - self.db = db - self.tags_view = parent - self.hidden_categories = hidden_categories - self.search_restriction = search_restriction - self.row_map = [] - self.filter_categories_by = filter_categories_by - self.collapse_model = collapse_model - - # Note that _get_category_nodes can indirectly change the - # user_categories dict. - - data = self._get_category_nodes(config['sort_tags_by']) - gst = db.prefs.get('grouped_search_terms', {}) - self.root_item = TagTreeItem(icon_map=self.icon_state_map) - self.category_nodes = [] - - last_category_node = None - category_node_map = {} - self.category_node_tree = {} - for i, key in enumerate(self.row_map): - if self.hidden_categories: - if key in self.hidden_categories: - continue - found = False - for cat in self.hidden_categories: - if cat.startswith('@') and key.startswith(cat + '.'): - found = True - if found: - continue - is_gst = False - if key.startswith('@') and key[1:] in gst: - tt = _(u'The grouped search term name is "{0}"').format(key[1:]) - is_gst = True - elif key == 'news': - tt = '' - else: - tt = _(u'The lookup/search name is "{0}"').format(key) - - if key.startswith('@'): - path_parts = [p for p in key.split('.')] - path = '' - last_category_node = self.root_item - tree_root = self.category_node_tree - for i,p in enumerate(path_parts): - path += p - if path not in category_node_map: - node = TagTreeItem(parent=last_category_node, - data=p[1:] if i == 0 else p, - category_icon=self.category_icon_map[key], - tooltip=tt if path == key else path, - category_key=path, - icon_map=self.icon_state_map) - last_category_node = node - category_node_map[path] = node - self.category_nodes.append(node) - node.can_be_edited = (not is_gst) and (i == (len(path_parts)-1)) - node.is_gst = is_gst - if not is_gst: - node.tag.is_hierarchical = '5state' - if not is_gst: - tree_root[p] = {} - tree_root = tree_root[p] - else: - last_category_node = category_node_map[path] - tree_root = tree_root[p] - path += '.' - else: - node = TagTreeItem(parent=self.root_item, - data=self.categories[key], - category_icon=self.category_icon_map[key], - tooltip=tt, category_key=key, - icon_map=self.icon_state_map) - node.is_gst = False - category_node_map[key] = node - last_category_node = node - self.category_nodes.append(node) - self._create_node_tree(data, state_map) - - def break_cycles(self): - self.root_item.break_cycles() - self.db = self.root_item = None - - def mimeTypes(self): - return ["application/calibre+from_library", - 'application/calibre+from_tag_browser'] - - def mimeData(self, indexes): - data = [] - for idx in indexes: - if idx.isValid(): - # get some useful serializable data - node = idx.internalPointer() - path = self.path_for_index(idx) - if node.type == TagTreeItem.CATEGORY: - d = (node.type, node.py_name, node.category_key) - else: - t = node.tag - p = node - while p.type != TagTreeItem.CATEGORY: - p = p.parent - d = (node.type, p.category_key, p.is_gst, t.original_name, - t.category, path) - data.append(d) - else: - data.append(None) - raw = bytearray(cPickle.dumps(data, -1)) - ans = QMimeData() - ans.setData('application/calibre+from_tag_browser', raw) - return ans - - def dropMimeData(self, md, action, row, column, parent): - fmts = set([unicode(x) for x in md.formats()]) - if not fmts.intersection(set(self.mimeTypes())): - return False - if "application/calibre+from_library" in fmts: - if action != Qt.CopyAction: - return False - return self.do_drop_from_library(md, action, row, column, parent) - elif 'application/calibre+from_tag_browser' in fmts: - return self.do_drop_from_tag_browser(md, action, row, column, parent) - - def do_drop_from_tag_browser(self, md, action, row, column, parent): - if not parent.isValid(): - return False - dest = parent.internalPointer() - if dest.type != TagTreeItem.CATEGORY: - return False - if not md.hasFormat('application/calibre+from_tag_browser'): - return False - data = str(md.data('application/calibre+from_tag_browser')) - src = cPickle.loads(data) - for s in src: - if s[0] != TagTreeItem.TAG: - return False - return self.move_or_copy_item_to_user_category(src, dest, action) - - def move_or_copy_item_to_user_category(self, src, dest, action): - ''' - src is a list of tuples representing items to copy. The tuple is - (type, containing category key, category key is global search term, - full name, category key, path to node) - The type must be TagTreeItem.TAG - dest is the TagTreeItem node to receive the items - action is Qt.CopyAction or Qt.MoveAction - ''' - def process_source_node(user_cats, src_parent, src_parent_is_gst, - is_uc, dest_key, node): - ''' - Copy/move an item and all its children to the destination - ''' - copied = False - src_name = node.tag.original_name - src_cat = node.tag.category - # delete the item if the source is a user category and action is move - if is_uc and not src_parent_is_gst and src_parent in user_cats and \ - action == Qt.MoveAction: - new_cat = [] - for tup in user_cats[src_parent]: - if src_name == tup[0] and src_cat == tup[1]: - continue - new_cat.append(list(tup)) - user_cats[src_parent] = new_cat - else: - copied = True - - # Now add the item to the destination user category - add_it = True - if not is_uc and src_cat == 'news': - src_cat = 'tags' - for tup in user_cats[dest_key]: - if src_name == tup[0] and src_cat == tup[1]: - add_it = False - if add_it: - user_cats[dest_key].append([src_name, src_cat, 0]) - - for c in node.children: - copied = process_source_node(user_cats, src_parent, src_parent_is_gst, - is_uc, dest_key, c) - return copied - - user_cats = self.db.prefs.get('user_categories', {}) - parent_node = None - copied = False - path = None - for s in src: - src_parent, src_parent_is_gst = s[1:3] - path = s[5] - parent_node = src_parent - - if src_parent.startswith('@'): - is_uc = True - src_parent = src_parent[1:] - else: - is_uc = False - dest_key = dest.category_key[1:] - - if dest_key not in user_cats: - continue - - node = self.index_for_path(path) - if node: - copied = process_source_node(user_cats, src_parent, src_parent_is_gst, - is_uc, dest_key, node.internalPointer()) - - self.db.prefs.set('user_categories', user_cats) - self.tags_view.recount() - - # Scroll to the item copied. If it was moved, scroll to the parent - if parent_node is not None: - self.clear_boxed() - m = self.tags_view.model() - if not copied: - p = path[-1] - if p == 0: - path = m.find_category_node(parent_node) - else: - path[-1] = p - 1 - idx = m.index_for_path(path) - self.tags_view.setExpanded(idx, True) - if idx.internalPointer().type == TagTreeItem.TAG: - m.show_item_at_index(idx, box=True) - else: - m.show_item_at_index(idx) - return True - - def do_drop_from_library(self, md, action, row, column, parent): - idx = parent - if idx.isValid(): - self.tags_view.setCurrentIndex(idx) - node = self.data(idx, Qt.UserRole) - if node.type == TagTreeItem.TAG: - fm = self.db.metadata_for_field(node.tag.category) - if node.tag.category in \ - ('tags', 'series', 'authors', 'rating', 'publisher') or \ - (fm['is_custom'] and ( - fm['datatype'] in ['text', 'rating', 'series', - 'enumeration'] or - (fm['datatype'] == 'composite' and - fm['display'].get('make_category', False)))): - mime = 'application/calibre+from_library' - ids = list(map(int, str(md.data(mime)).split())) - self.handle_drop(node, ids) - return True - elif node.type == TagTreeItem.CATEGORY: - fm_dest = self.db.metadata_for_field(node.category_key) - if fm_dest['kind'] == 'user': - fm_src = self.db.metadata_for_field(md.column_name) - if md.column_name in ['authors', 'publisher', 'series'] or \ - (fm_src['is_custom'] and ( - (fm_src['datatype'] in ['series', 'text', 'enumeration'] and - not fm_src['is_multiple']))or - (fm_src['datatype'] == 'composite' and - fm_src['display'].get('make_category', False))): - mime = 'application/calibre+from_library' - ids = list(map(int, str(md.data(mime)).split())) - self.handle_user_category_drop(node, ids, md.column_name) - return True - return False - - def handle_user_category_drop(self, on_node, ids, column): - categories = self.db.prefs.get('user_categories', {}) - category = categories.get(on_node.category_key[1:], None) - if category is None: - return - fm_src = self.db.metadata_for_field(column) - for id in ids: - label = fm_src['label'] - if not fm_src['is_custom']: - if label == 'authors': - items = self.db.get_authors_with_ids() - items = [(i[0], i[1].replace('|', ',')) for i in items] - value = self.db.authors(id, index_is_id=True) - value = [v.replace('|', ',') for v in value.split(',')] - elif label == 'publisher': - items = self.db.get_publishers_with_ids() - value = self.db.publisher(id, index_is_id=True) - elif label == 'series': - items = self.db.get_series_with_ids() - value = self.db.series(id, index_is_id=True) - else: - items = self.db.get_custom_items_with_ids(label=label) - if fm_src['datatype'] != 'composite': - value = self.db.get_custom(id, label=label, index_is_id=True) - else: - value = self.db.get_property(id, loc=fm_src['rec_index'], - index_is_id=True) - if value is None: - return - if not isinstance(value, list): - value = [value] - for val in value: - for (v, c, id) in category: - if v == val and c == column: - break - else: - category.append([val, column, 0]) - categories[on_node.category_key[1:]] = category - self.db.prefs.set('user_categories', categories) - self.tags_view.recount() - - def handle_drop(self, on_node, ids): - #print 'Dropped ids:', ids, on_node.tag - key = on_node.tag.category - if (key == 'authors' and len(ids) >= 5): - if not confirm('

'+_('Changing the authors for several books can ' - 'take a while. Are you sure?') - +'

', 'tag_browser_drop_authors', self.tags_view): - return - elif len(ids) > 15: - if not confirm('

'+_('Changing the metadata for that many books ' - 'can take a while. Are you sure?') - +'

', 'tag_browser_many_changes', self.tags_view): - return - - fm = self.db.metadata_for_field(key) - is_multiple = fm['is_multiple'] - val = on_node.tag.original_name - for id in ids: - mi = self.db.get_metadata(id, index_is_id=True) - - # Prepare to ignore the author, unless it is changed. Title is - # always ignored -- see the call to set_metadata - set_authors = False - - # Author_sort cannot change explicitly. Changing the author might - # change it. - mi.author_sort = None # Never will change by itself. - - if key == 'authors': - mi.authors = [val] - set_authors=True - elif fm['datatype'] == 'rating': - mi.set(key, len(val) * 2) - elif fm['is_custom'] and fm['datatype'] == 'series': - mi.set(key, val, extra=1.0) - elif is_multiple: - new_val = mi.get(key, []) - if val in new_val: - # Fortunately, only one field can change, so the continue - # won't break anything - continue - new_val.append(val) - mi.set(key, new_val) - else: - mi.set(key, val) - self.db.set_metadata(id, mi, set_title=False, - set_authors=set_authors, commit=False) - self.db.commit() - self.drag_drop_finished.emit(ids) - - def set_search_restriction(self, s): - self.search_restriction = s - - def _get_category_nodes(self, sort): - ''' - Called by __init__. Do not directly call this method. - ''' - self.row_map = [] - self.categories = {} - - # Get the categories - if self.search_restriction: - try: - data = self.db.get_categories(sort=sort, - icon_map=self.category_icon_map, - ids=self.db.search('', return_matches=True)) - except: - data = self.db.get_categories(sort=sort, icon_map=self.category_icon_map) - self.tags_view.restriction_error.emit() - else: - data = self.db.get_categories(sort=sort, icon_map=self.category_icon_map) - - # Reconstruct the user categories, putting them into metadata - self.db.field_metadata.remove_dynamic_categories() - tb_cats = self.db.field_metadata - for user_cat in sorted(self.db.prefs.get('user_categories', {}).keys(), - key=sort_key): - cat_name = '@' + user_cat # add the '@' to avoid name collision - while True: - try: - tb_cats.add_user_category(label=cat_name, name=user_cat) - dot = cat_name.rfind('.') - if dot < 0: - break - cat_name = cat_name[:dot] - except ValueError: - break - - for cat in sorted(self.db.prefs.get('grouped_search_terms', {}).keys(), - key=sort_key): - if (u'@' + cat) in data: - try: - tb_cats.add_user_category(label=u'@' + cat, name=cat) - except ValueError: - traceback.print_exc() - self.db.data.change_search_locations(self.db.field_metadata.get_search_terms()) - - if len(saved_searches().names()): - tb_cats.add_search_category(label='search', name=_('Searches')) - - if self.filter_categories_by: - for category in data.keys(): - data[category] = [t for t in data[category] - if lower(t.name).find(self.filter_categories_by) >= 0] - - tb_categories = self.db.field_metadata - for category in tb_categories: - if category in data: # The search category can come and go - self.row_map.append(category) - self.categories[category] = tb_categories[category]['name'] - return data - - def refresh(self, data=None): - ''' - Here to trap usages of refresh in the old architecture. Can eventually - be removed. - ''' - print 'TagsModel: refresh called!' - traceback.print_stack() - return False - - def _create_node_tree(self, data, state_map): - ''' - Called by __init__. Do not directly call this method. - ''' - sort_by = config['sort_tags_by'] - - if data is None: - print '_create_node_tree: no data!' - traceback.print_stack() - return - - collapse = gprefs['tags_browser_collapse_at'] - collapse_model = self.collapse_model - if collapse == 0: - collapse_model = 'disable' - elif collapse_model != 'disable': - if sort_by == 'name': - collapse_template = tweaks['categories_collapsed_name_template'] - elif sort_by == 'rating': - collapse_model = 'partition' - collapse_template = tweaks['categories_collapsed_rating_template'] - else: - collapse_model = 'partition' - collapse_template = tweaks['categories_collapsed_popularity_template'] - - def process_one_node(category, state_map): # {{{ - collapse_letter = None - category_index = self.createIndex(category.row(), 0, category) - category_node = category_index.internalPointer() - key = category_node.category_key - if key not in data: - return - cat_len = len(data[key]) - if cat_len <= 0: - return - - category_child_map = {} - fm = self.db.field_metadata[key] - clear_rating = True if key not in self.categories_with_ratings and \ - not fm['is_custom'] and \ - not fm['kind'] == 'user' \ - else False - in_uc = fm['kind'] == 'user' - tt = key if in_uc else None - - if collapse_model == 'first letter': - # Build a list of 'equal' first letters by looking for - # overlapping ranges. If a range overlaps another, then the - # letters are assumed to be equivalent. ICU collating is complex - # beyond belief. This mechanism lets us determine the logical - # first character from ICU's standpoint. - chardict = {} - for idx,tag in enumerate(data[key]): - if not tag.sort: - c = ' ' - else: - c = icu_upper(tag.sort[0]) - if c not in chardict: - chardict[c] = [idx, idx] - else: - chardict[c][1] = idx - - # sort the ranges to facilitate detecting overlap - ranges = sorted([(v[0], v[1], c) for c,v in chardict.items()]) - - # Create a list of 'first letters' to use for each item in - # the category. The list is generated using the ranges. Overlaps - # are filled with the character that first occurs. - cl_list = list(repeat(None, len(data[key]))) - for t in ranges: - start = t[0] - c = t[2] - if cl_list[start] is None: - nc = c - else: - nc = cl_list[start] - for i in range(start, t[1]+1): - cl_list[i] = nc - - for idx,tag in enumerate(data[key]): - if clear_rating: - tag.avg_rating = None - tag.state = state_map.get((tag.name, tag.category), 0) - - if collapse_model != 'disable' and cat_len > collapse: - if collapse_model == 'partition': - if (idx % collapse) == 0: - d = {'first': tag} - if cat_len > idx + collapse: - d['last'] = data[key][idx+collapse-1] - else: - d['last'] = data[key][cat_len-1] - name = eval_formatter.safe_format(collapse_template, - d, 'TAG_VIEW', None) - self.beginInsertRows(category_index, 999998, 999999) #len(data[key])-1) - sub_cat = TagTreeItem(parent=category, data = name, - tooltip = None, temporary=True, - category_icon = category_node.icon, - category_key=category_node.category_key, - icon_map=self.icon_state_map) - sub_cat.tag.is_searchable = False - self.endInsertRows() - else: # by 'first letter' - cl = cl_list[idx] - if cl != collapse_letter: - collapse_letter = cl - sub_cat = TagTreeItem(parent=category, - data = collapse_letter, - category_icon = category_node.icon, - tooltip = None, temporary=True, - category_key=category_node.category_key, - icon_map=self.icon_state_map) - node_parent = sub_cat - else: - node_parent = category - - # category display order is important here. The following works - # only of all the non-user categories are displayed before the - # user categories - components = [t.strip() for t in tag.original_name.split('.') - if t.strip()] - if len(components) == 0 or '.'.join(components) != tag.original_name: - components = [tag.original_name] - if (not tag.is_hierarchical) and (in_uc or - (fm['is_custom'] and fm['display'].get('is_names', False)) or - key in ['authors', 'publisher', 'news', 'formats', 'rating'] or - key not in self.db.prefs.get('categories_using_hierarchy', []) or - len(components) == 1): - self.beginInsertRows(category_index, 999998, 999999) - n = TagTreeItem(parent=node_parent, data=tag, tooltip=tt, - icon_map=self.icon_state_map) - if tag.id_set is not None: - n.id_set |= tag.id_set - category_child_map[tag.name, tag.category] = n - self.endInsertRows() - else: - for i,comp in enumerate(components): - if i == 0: - child_map = category_child_map - else: - child_map = dict([((t.tag.name, t.tag.category), t) - for t in node_parent.children - if t.type != TagTreeItem.CATEGORY]) - if (comp,tag.category) in child_map: - node_parent = child_map[(comp,tag.category)] - node_parent.tag.is_hierarchical = \ - '5state' if tag.category != 'search' else '3state' - else: - if i < len(components)-1: - t = copy.copy(tag) - t.original_name = '.'.join(components[:i+1]) - if key != 'search': - # This 'manufactured' intermediate node can - # be searched, but cannot be edited. - t.is_editable = False - else: - t.is_searchable = t.is_editable = False - else: - t = tag - if not in_uc: - t.original_name = t.name - t.is_hierarchical = \ - '5state' if t.category != 'search' else '3state' - t.name = comp - self.beginInsertRows(category_index, 999998, 999999) - node_parent = TagTreeItem(parent=node_parent, data=t, - tooltip=tt, icon_map=self.icon_state_map) - child_map[(comp,tag.category)] = node_parent - self.endInsertRows() - # This id_set must not be None - node_parent.id_set |= tag.id_set - return - # }}} - - for category in self.category_nodes: - process_one_node(category, state_map.get(category.py_name, {})) - - def get_state(self): - state_map = {} - expanded_categories = [] - for row, category in enumerate(self.category_nodes): - if self.tags_view.isExpanded(self.index(row, 0, QModelIndex())): - expanded_categories.append(category.py_name) - states = [c.tag.state for c in category.child_tags()] - names = [(c.tag.name, c.tag.category) for c in category.child_tags()] - state_map[category.py_name] = dict(izip(names, states)) - return expanded_categories, state_map - - def index_for_category(self, name): - for row, category in enumerate(self.category_nodes): - if category.py_name == name: - return self.index(row, 0, QModelIndex()) - - def columnCount(self, parent): - return 1 - - def data(self, index, role): - if not index.isValid(): - return NONE - item = index.internalPointer() - return item.data(role) - - def setData(self, index, value, role=Qt.EditRole): - if not index.isValid(): - return NONE - # set up to reposition at the same item. We can do this except if - # working with the last item and that item is deleted, in which case - # we position at the parent label - path = index.model().path_for_index(index) - val = unicode(value.toString()).strip() - if not val: - error_dialog(self.tags_view, _('Item is blank'), - _('An item cannot be set to nothing. Delete it instead.')).exec_() - return False - item = index.internalPointer() - if item.type == TagTreeItem.CATEGORY and item.category_key.startswith('@'): - if val.find('.') >= 0: - error_dialog(self.tags_view, _('Rename user category'), - _('You cannot use periods in the name when ' - 'renaming user categories'), show=True) - return False - - user_cats = self.db.prefs.get('user_categories', {}) - user_cat_keys_lower = [icu_lower(k) for k in user_cats] - ckey = item.category_key[1:] - ckey_lower = icu_lower(ckey) - dotpos = ckey.rfind('.') - if dotpos < 0: - nkey = val - else: - nkey = ckey[:dotpos+1] + val - nkey_lower = icu_lower(nkey) - for c in sorted(user_cats.keys(), key=sort_key): - if icu_lower(c).startswith(ckey_lower): - if len(c) == len(ckey): - if strcmp(ckey, nkey) != 0 and \ - nkey_lower in user_cat_keys_lower: - error_dialog(self.tags_view, _('Rename user category'), - _('The name %s is already used')%nkey, show=True) - return False - user_cats[nkey] = user_cats[ckey] - del user_cats[ckey] - elif c[len(ckey)] == '.': - rest = c[len(ckey):] - if strcmp(ckey, nkey) != 0 and \ - icu_lower(nkey + rest) in user_cat_keys_lower: - error_dialog(self.tags_view, _('Rename user category'), - _('The name %s is already used')%(nkey+rest), show=True) - return False - user_cats[nkey + rest] = user_cats[ckey + rest] - del user_cats[ckey + rest] - self.db.prefs.set('user_categories', user_cats) - self.tags_view.set_new_model() - # must not use 'self' below because the model has changed! - p = self.tags_view.model().find_category_node('@' + nkey) - self.tags_view.model().show_item_at_path(p) - return True - - key = item.tag.category - name = item.tag.original_name - # make certain we know about the item's category - if key not in self.db.field_metadata: - return False - if key == 'authors': - if val.find('&') >= 0: - error_dialog(self.tags_view, _('Invalid author name'), - _('Author names cannot contain & characters.')).exec_() - return False - if key == 'search': - if val in saved_searches().names(): - error_dialog(self.tags_view, _('Duplicate search name'), - _('The saved search name %s is already used.')%val).exec_() - return False - saved_searches().rename(unicode(item.data(role).toString()), val) - item.tag.name = val - self.tags_view.search_item_renamed.emit() # Does a refresh - else: - if key == 'series': - self.db.rename_series(item.tag.id, val) - elif key == 'publisher': - self.db.rename_publisher(item.tag.id, val) - elif key == 'tags': - self.db.rename_tag(item.tag.id, val) - elif key == 'authors': - self.db.rename_author(item.tag.id, val) - elif self.db.field_metadata[key]['is_custom']: - self.db.rename_custom_item(item.tag.id, val, - label=self.db.field_metadata[key]['label']) - self.tags_view.tag_item_renamed.emit() - item.tag.name = val - self.rename_item_in_all_user_categories(name, key, val) - self.refresh_required.emit() - self.show_item_at_path(path) - return True - - def rename_item_in_all_user_categories(self, item_name, item_category, new_name): - ''' - Search all user categories for items named item_name with category - item_category and rename them to new_name. The caller must arrange to - redisplay the tree as appropriate (recount or set_new_model) - ''' - user_cats = self.db.prefs.get('user_categories', {}) - for k in user_cats.keys(): - new_contents = [] - for tup in user_cats[k]: - if tup[0] == item_name and tup[1] == item_category: - new_contents.append([new_name, item_category, 0]) - else: - new_contents.append(tup) - user_cats[k] = new_contents - self.db.prefs.set('user_categories', user_cats) - - def delete_item_from_all_user_categories(self, item_name, item_category): - ''' - Search all user categories for items named item_name with category - item_category and delete them. The caller must arrange to redisplay the - tree as appropriate (recount or set_new_model) - ''' - user_cats = self.db.prefs.get('user_categories', {}) - for cat in user_cats.keys(): - self.delete_item_from_user_category(cat, item_name, item_category, - user_categories=user_cats) - self.db.prefs.set('user_categories', user_cats) - - def delete_item_from_user_category(self, category, item_name, item_category, - user_categories=None): - if user_categories is not None: - user_cats = user_categories - else: - user_cats = self.db.prefs.get('user_categories', {}) - new_contents = [] - for tup in user_cats[category]: - if tup[0] != item_name or tup[1] != item_category: - new_contents.append(tup) - user_cats[category] = new_contents - if user_categories is None: - self.db.prefs.set('user_categories', user_cats) - - def headerData(self, *args): - return NONE - - def flags(self, index, *args): - ans = Qt.ItemIsEnabled|Qt.ItemIsSelectable|Qt.ItemIsEditable - if index.isValid(): - node = self.data(index, Qt.UserRole) - if node.type == TagTreeItem.TAG: - if node.tag.is_editable: - ans |= Qt.ItemIsDragEnabled - fm = self.db.metadata_for_field(node.tag.category) - if node.tag.category in \ - ('tags', 'series', 'authors', 'rating', 'publisher') or \ - (fm['is_custom'] and \ - fm['datatype'] in ['text', 'rating', 'series', 'enumeration']): - ans |= Qt.ItemIsDropEnabled - else: - ans |= Qt.ItemIsDropEnabled - return ans - - def supportedDropActions(self): - return Qt.CopyAction|Qt.MoveAction - - def path_for_index(self, index): - ans = [] - while index.isValid(): - ans.append(index.row()) - index = self.parent(index) - ans.reverse() - return ans - - def index_for_path(self, path): - parent = QModelIndex() - for i in path: - parent = self.index(i, 0, parent) - if not parent.isValid(): - return QModelIndex() - return parent - - def index(self, row, column, parent): - if not self.hasIndex(row, column, parent): - return QModelIndex() - - if not parent.isValid(): - parent_item = self.root_item - else: - parent_item = parent.internalPointer() - - try: - child_item = parent_item.children[row] - except IndexError: - return QModelIndex() - - ans = self.createIndex(row, column, child_item) - return ans - - def parent(self, index): - if not index.isValid(): - return QModelIndex() - - child_item = index.internalPointer() - parent_item = getattr(child_item, 'parent', None) - - if parent_item is self.root_item or parent_item is None: - return QModelIndex() - - ans = self.createIndex(parent_item.row(), 0, parent_item) - return ans - - def rowCount(self, parent): - if parent.column() > 0: - return 0 - - if not parent.isValid(): - parent_item = self.root_item - else: - parent_item = parent.internalPointer() - - return len(parent_item.children) - - def reset_all_states(self, except_=None): - update_list = [] - def process_tag(tag_item): - tag = tag_item.tag - if tag is except_: - tag_index = self.createIndex(tag_item.row(), 0, tag_item) - self.dataChanged.emit(tag_index, tag_index) - elif tag.state != 0 or tag in update_list: - tag_index = self.createIndex(tag_item.row(), 0, tag_item) - tag.state = 0 - update_list.append(tag) - self.dataChanged.emit(tag_index, tag_index) - for t in tag_item.children: - process_tag(t) - - for t in self.root_item.children: - process_tag(t) - - def clear_state(self): - self.reset_all_states() - - def toggle(self, index, exclusive, set_to=None): - ''' - exclusive: clear all states before applying this one - set_to: None => advance the state, otherwise a value from TAG_SEARCH_STATES - ''' - if not index.isValid(): return False - item = index.internalPointer() - item.toggle(set_to=set_to) - if exclusive: - self.reset_all_states(except_=item.tag) - self.dataChanged.emit(index, index) - return True - - def tokens(self): - ans = [] - # Tags can be in the news and the tags categories. However, because of - # the desire to use two different icons (tags and news), the nodes are - # not shared, which can lead to the possibility of searching twice for - # the same tag. The tags_seen set helps us prevent that - tags_seen = set() - # Tag nodes are in their own category and possibly in user categories. - # They will be 'checked' in both places, but we want to put the node - # into the search string only once. The nodes_seen set helps us do that - nodes_seen = set() - - node_searches = {TAG_SEARCH_STATES['mark_plus'] : 'true', - TAG_SEARCH_STATES['mark_plusplus'] : '.true', - TAG_SEARCH_STATES['mark_minus'] : 'false', - TAG_SEARCH_STATES['mark_minusminus'] : '.false'} - - for node in self.category_nodes: - if node.tag.state: - if node.category_key == "news": - if node_searches[node.tag.state] == 'true': - ans.append('tags:"=' + _('News') + '"') - else: - ans.append('( not tags:"=' + _('News') + '")') - else: - ans.append('%s:%s'%(node.category_key, node_searches[node.tag.state])) - - key = node.category_key - for tag_item in node.all_children(): - if tag_item.type == TagTreeItem.CATEGORY: - if self.collapse_model == 'first letter' and \ - tag_item.temporary and not key.startswith('@') \ - and tag_item.tag.state: - if node_searches[tag_item.tag.state] == 'true': - ans.append('%s:~^%s'%(key, tag_item.py_name)) - else: - ans.append('(not %s:~^%s )'%(key, tag_item.py_name)) - continue - tag = tag_item.tag - if tag.state != TAG_SEARCH_STATES['clear']: - if tag.state == TAG_SEARCH_STATES['mark_minus'] or \ - tag.state == TAG_SEARCH_STATES['mark_minusminus']: - prefix = ' not ' - else: - prefix = '' - category = tag.category if key != 'news' else 'tag' - add_colon = False - if self.db.field_metadata[tag.category]['is_csp']: - add_colon = True - - if tag.name and tag.name[0] == u'\u2605': # char is a star. Assume rating - ans.append('%s%s:%s'%(prefix, category, len(tag.name))) - else: - name = tag.original_name - use_prefix = tag.state in [TAG_SEARCH_STATES['mark_plusplus'], - TAG_SEARCH_STATES['mark_minusminus']] - if category == 'tags': - if name in tags_seen: - continue - tags_seen.add(name) - if tag in nodes_seen: - continue - nodes_seen.add(tag) - n = name.replace(r'"', r'\"') - if name.startswith('.'): - n = '.' + n - ans.append('%s%s:"=%s%s%s"'%(prefix, category, - '.' if use_prefix else '', n, - ':' if add_colon else '')) - return ans - - def find_item_node(self, key, txt, start_path, equals_match=False): - ''' - Search for an item (a node) in the tags browser list that matches both - the key (exact case-insensitive match) and txt (not equals_match => - case-insensitive contains match; equals_match => case_insensitive - equal match). Returns the path to the node. Note that paths are to a - location (second item, fourth item, 25 item), not to a node. If - start_path is None, the search starts with the topmost node. If the tree - is changed subsequent to calling this method, the path can easily refer - to a different node or no node at all. - ''' - if not txt: - return None - txt = lower(txt) if not equals_match else txt - self.path_found = None - if start_path is None: - start_path = [] - - def process_tag(depth, tag_index, tag_item, start_path): - path = self.path_for_index(tag_index) - if depth < len(start_path) and path[depth] <= start_path[depth]: - return False - tag = tag_item.tag - if tag is None: - return False - name = tag.original_name - if (equals_match and strcmp(name, txt) == 0) or \ - (not equals_match and lower(name).find(txt) >= 0): - self.path_found = path - return True - for i,c in enumerate(tag_item.children): - if process_tag(depth+1, self.createIndex(i, 0, c), c, start_path): - return True - return False - - def process_level(depth, category_index, start_path): - path = self.path_for_index(category_index) - if depth < len(start_path): - if path[depth] < start_path[depth]: - return False - if path[depth] > start_path[depth]: - start_path = path - my_key = category_index.internalPointer().category_key - for j in xrange(self.rowCount(category_index)): - tag_index = self.index(j, 0, category_index) - tag_item = tag_index.internalPointer() - if tag_item.type == TagTreeItem.CATEGORY: - if process_level(depth+1, tag_index, start_path): - return True - elif not key or strcmp(key, my_key) == 0: - if process_tag(depth+1, tag_index, tag_item, start_path): - return True - return False - - for i in xrange(self.rowCount(QModelIndex())): - if process_level(0, self.index(i, 0, QModelIndex()), start_path): - break - return self.path_found - - def find_category_node(self, key, parent=QModelIndex()): - ''' - Search for an category node (a top-level node) in the tags browser list - that matches the key (exact case-insensitive match). Returns the path to - the node. Paths are as in find_item_node. - ''' - if not key: - return None - - for i in xrange(self.rowCount(parent)): - idx = self.index(i, 0, parent) - node = idx.internalPointer() - if node.type == TagTreeItem.CATEGORY: - ckey = node.category_key - if strcmp(ckey, key) == 0: - return self.path_for_index(idx) - if len(node.children): - v = self.find_category_node(key, idx) - if v is not None: - return v - return None - - def show_item_at_path(self, path, box=False, - position=QTreeView.PositionAtCenter): - ''' - Scroll the browser and open categories to show the item referenced by - path. If possible, the item is placed in the center. If box=True, a - box is drawn around the item. - ''' - if path: - self.show_item_at_index(self.index_for_path(path), box=box, - position=position) - - def show_item_at_index(self, idx, box=False, - position=QTreeView.PositionAtCenter): - if idx.isValid(): - self.tags_view.setCurrentIndex(idx) - self.tags_view.scrollTo(idx, position) - if box: - tag_item = idx.internalPointer() - tag_item.boxed = True - self.dataChanged.emit(idx, idx) - - def clear_boxed(self): - ''' - Clear all boxes around items. - ''' - def process_tag(tag_index, tag_item): - if tag_item.boxed: - tag_item.boxed = False - self.dataChanged.emit(tag_index, tag_index) - for i,c in enumerate(tag_item.children): - process_tag(self.index(i, 0, tag_index), c) - - def process_level(category_index): - for j in xrange(self.rowCount(category_index)): - tag_index = self.index(j, 0, category_index) - tag_item = tag_index.internalPointer() - if tag_item.boxed: - tag_item.boxed = False - self.dataChanged.emit(tag_index, tag_index) - if tag_item.type == TagTreeItem.CATEGORY: - process_level(tag_index) - else: - process_tag(tag_index, tag_item) - - for i in xrange(self.rowCount(QModelIndex())): - process_level(self.index(i, 0, QModelIndex())) - - def get_filter_categories_by(self): - return self.filter_categories_by - - # }}} - -class TagBrowserMixin(object): # {{{ - - def __init__(self, db): - self.library_view.model().count_changed_signal.connect(self.tags_view.recount) - self.tags_view.set_database(db, self.tag_match, self.sort_by) - self.tags_view.tags_marked.connect(self.search.set_search_string) - self.tags_view.tag_list_edit.connect(self.do_tags_list_edit) - self.tags_view.edit_user_category.connect(self.do_edit_user_categories) - self.tags_view.delete_user_category.connect(self.do_delete_user_category) - self.tags_view.del_item_from_user_cat.connect(self.do_del_item_from_user_cat) - self.tags_view.add_subcategory.connect(self.do_add_subcategory) - self.tags_view.add_item_to_user_cat.connect(self.do_add_item_to_user_cat) - self.tags_view.saved_search_edit.connect(self.do_saved_search_edit) - self.tags_view.rebuild_saved_searches.connect(self.do_rebuild_saved_searches) - self.tags_view.author_sort_edit.connect(self.do_author_sort_edit) - self.tags_view.tag_item_renamed.connect(self.do_tag_item_renamed) - self.tags_view.search_item_renamed.connect(self.saved_searches_changed) - self.tags_view.drag_drop_finished.connect(self.drag_drop_finished) - self.tags_view.restriction_error.connect(self.do_restriction_error, - type=Qt.QueuedConnection) - - for text, func, args, cat_name in ( - (_('Manage Authors'), - self.do_author_sort_edit, (self, None), 'authors'), - (_('Manage Series'), - self.do_tags_list_edit, (None, 'series'), 'series'), - (_('Manage Publishers'), - self.do_tags_list_edit, (None, 'publisher'), 'publisher'), - (_('Manage Tags'), - self.do_tags_list_edit, (None, 'tags'), 'tags'), - (_('Manage User Categories'), - self.do_edit_user_categories, (None,), 'user:'), - (_('Manage Saved Searches'), - self.do_saved_search_edit, (None,), 'search') - ): - self.manage_items_button.menu().addAction( - QIcon(I(category_icon_map[cat_name])), - text, partial(func, *args)) - - def do_restriction_error(self): - error_dialog(self.tags_view, _('Invalid search restriction'), - _('The current search restriction is invalid'), show=True) - - def do_add_subcategory(self, on_category_key, new_category_name=None): - ''' - Add a subcategory to the category 'on_category'. If new_category_name is - None, then a default name is shown and the user is offered the - opportunity to edit the name. - ''' - db = self.library_view.model().db - user_cats = db.prefs.get('user_categories', {}) - - # Ensure that the temporary name we will use is not already there - i = 0 - if new_category_name is not None: - new_name = new_category_name.replace('.', '') - else: - new_name = _('New Category').replace('.', '') - n = new_name - while True: - new_cat = on_category_key[1:] + '.' + n - if new_cat not in user_cats: - break - i += 1 - n = new_name + unicode(i) - # Add the new category - user_cats[new_cat] = [] - db.prefs.set('user_categories', user_cats) - self.tags_view.set_new_model() - m = self.tags_view.model() - idx = m.index_for_path(m.find_category_node('@' + new_cat)) - m.show_item_at_index(idx) - # Open the editor on the new item to rename it - if new_category_name is None: - self.tags_view.edit(idx) - - def do_edit_user_categories(self, on_category=None): - ''' - Open the user categories editor. - ''' - db = self.library_view.model().db - d = TagCategories(self, db, on_category) - if d.exec_() == d.Accepted: - db.prefs.set('user_categories', d.categories) - db.field_metadata.remove_user_categories() - for k in d.categories: - db.field_metadata.add_user_category('@' + k, k) - db.data.change_search_locations(db.field_metadata.get_search_terms()) - self.tags_view.set_new_model() - - def do_delete_user_category(self, category_name): - ''' - Delete the user category named category_name. Any leading '@' is removed - ''' - if category_name.startswith('@'): - category_name = category_name[1:] - db = self.library_view.model().db - user_cats = db.prefs.get('user_categories', {}) - cat_keys = sorted(user_cats.keys(), key=sort_key) - has_children = False - found = False - for k in cat_keys: - if k == category_name: - found = True - has_children = len(user_cats[k]) - elif k.startswith(category_name + '.'): - has_children = True - if not found: - return error_dialog(self.tags_view, _('Delete user category'), - _('%s is not a user category')%category_name, show=True) - if has_children: - if not question_dialog(self.tags_view, _('Delete user category'), - _('%s contains items. Do you really ' - 'want to delete it?')%category_name): - return - for k in cat_keys: - if k == category_name: - del user_cats[k] - elif k.startswith(category_name + '.'): - del user_cats[k] - db.prefs.set('user_categories', user_cats) - self.tags_view.set_new_model() - - def do_del_item_from_user_cat(self, user_cat, item_name, item_category): - ''' - Delete the item (item_name, item_category) from the user category with - key user_cat. Any leading '@' characters are removed - ''' - if user_cat.startswith('@'): - user_cat = user_cat[1:] - db = self.library_view.model().db - user_cats = db.prefs.get('user_categories', {}) - if user_cat not in user_cats: - error_dialog(self.tags_view, _('Remove category'), - _('User category %s does not exist')%user_cat, - show=True) - return - self.tags_view.model().delete_item_from_user_category(user_cat, - item_name, item_category) - self.tags_view.recount() - - def do_add_item_to_user_cat(self, dest_category, src_name, src_category): - ''' - Add the item src_name in src_category to the user category - dest_category. Any leading '@' is removed - ''' - db = self.library_view.model().db - user_cats = db.prefs.get('user_categories', {}) - - if dest_category and dest_category.startswith('@'): - dest_category = dest_category[1:] - - if dest_category not in user_cats: - return error_dialog(self.tags_view, _('Add to user category'), - _('A user category %s does not exist')%dest_category, show=True) - - # Now add the item to the destination user category - add_it = True - if src_category == 'news': - src_category = 'tags' - for tup in user_cats[dest_category]: - if src_name == tup[0] and src_category == tup[1]: - add_it = False - if add_it: - user_cats[dest_category].append([src_name, src_category, 0]) - db.prefs.set('user_categories', user_cats) - self.tags_view.recount() - - def do_tags_list_edit(self, tag, category): - ''' - Open the 'manage_X' dialog where X == category. If tag is not None, the - dialog will position the editor on that item. - ''' - db=self.library_view.model().db - if category == 'tags': - result = db.get_tags_with_ids() - key = sort_key - elif category == 'series': - result = db.get_series_with_ids() - key = lambda x:sort_key(title_sort(x)) - elif category == 'publisher': - result = db.get_publishers_with_ids() - key = sort_key - else: # should be a custom field - cc_label = None - if category in db.field_metadata: - cc_label = db.field_metadata[category]['label'] - result = db.get_custom_items_with_ids(label=cc_label) - else: - result = [] - key = sort_key - - d = TagListEditor(self, tag_to_match=tag, data=result, key=key) - d.exec_() - if d.result() == d.Accepted: - to_rename = d.to_rename # dict of new text to old id - to_delete = d.to_delete # list of ids - orig_name = d.original_names # dict of id: name - - rename_func = None - if category == 'tags': - rename_func = db.rename_tag - delete_func = db.delete_tag_using_id - elif category == 'series': - rename_func = db.rename_series - delete_func = db.delete_series_using_id - elif category == 'publisher': - rename_func = db.rename_publisher - delete_func = db.delete_publisher_using_id - else: - rename_func = partial(db.rename_custom_item, label=cc_label) - delete_func = partial(db.delete_custom_item_using_id, label=cc_label) - m = self.tags_view.model() - if rename_func: - for item in to_delete: - delete_func(item) - m.delete_item_from_all_user_categories(orig_name[item], category) - for old_id in to_rename: - rename_func(old_id, new_name=unicode(to_rename[old_id])) - m.rename_item_in_all_user_categories(orig_name[old_id], - category, unicode(to_rename[old_id])) - - # Clean up the library view - self.do_tag_item_renamed() - self.tags_view.recount() - - def do_tag_item_renamed(self): - # Clean up library view and search - # get information to redo the selection - rows = [r.row() for r in \ - self.library_view.selectionModel().selectedRows()] - m = self.library_view.model() - ids = [m.id(r) for r in rows] - - m.refresh(reset=False) - m.research() - self.library_view.select_rows(ids) - # refreshing the tags view happens at the emit()/call() site - - def do_author_sort_edit(self, parent, id, select_sort=True): - ''' - Open the manage authors dialog - ''' - db = self.library_view.model().db - editor = EditAuthorsDialog(parent, db, id, select_sort) - d = editor.exec_() - if d: - for (id, old_author, new_author, new_sort, new_link) in editor.result: - if old_author != new_author: - # The id might change if the new author already exists - id = db.rename_author(id, new_author) - db.set_sort_field_for_author(id, unicode(new_sort), - commit=False, notify=False) - db.set_link_field_for_author(id, unicode(new_link), - commit=False, notify=False) - db.commit() - self.library_view.model().refresh() - self.tags_view.recount() - - def drag_drop_finished(self, ids): - self.library_view.model().refresh_ids(ids) - -# }}} - -class TagBrowserWidget(QWidget): # {{{ - - def __init__(self, parent): - QWidget.__init__(self, parent) - self.parent = parent - self._layout = QVBoxLayout() - self.setLayout(self._layout) - self._layout.setContentsMargins(0,0,0,0) - - # Set up the find box & button - search_layout = QHBoxLayout() - self._layout.addLayout(search_layout) - self.item_search = HistoryLineEdit(parent) - try: - self.item_search.lineEdit().setPlaceholderText( - _('Find item in tag browser')) - except: - pass # Using Qt < 4.7 - self.item_search.setToolTip(_( - 'Search for items. This is a "contains" search; items containing the\n' - 'text anywhere in the name will be found. You can limit the search\n' - 'to particular categories using syntax similar to search. For example,\n' - 'tags:foo will find foo in any tag, but not in authors etc. Entering\n' - '*foo will filter all categories at once, showing only those items\n' - 'containing the text "foo"')) - search_layout.addWidget(self.item_search) - # Not sure if the shortcut should be translatable ... - sc = QShortcut(QKeySequence(_('ALT+f')), parent) - sc.connect(sc, SIGNAL('activated()'), self.set_focus_to_find_box) - - self.search_button = QToolButton() - self.search_button.setText(_('F&ind')) - self.search_button.setToolTip(_('Find the first/next matching item')) - search_layout.addWidget(self.search_button) - - self.expand_button = QToolButton() - self.expand_button.setText('-') - self.expand_button.setToolTip(_('Collapse all categories')) - search_layout.addWidget(self.expand_button) - search_layout.setStretch(0, 10) - search_layout.setStretch(1, 1) - search_layout.setStretch(2, 1) - - self.current_find_position = None - self.search_button.clicked.connect(self.find) - self.item_search.initialize('tag_browser_search') - self.item_search.lineEdit().returnPressed.connect(self.do_find) - self.item_search.lineEdit().textEdited.connect(self.find_text_changed) - self.item_search.activated[QString].connect(self.do_find) - self.item_search.completer().setCaseSensitivity(Qt.CaseSensitive) - - parent.tags_view = TagsView(parent) - self.tags_view = parent.tags_view - self.expand_button.clicked.connect(self.tags_view.collapseAll) - self._layout.addWidget(parent.tags_view) - - # Now the floating 'not found' box - l = QLabel(self.tags_view) - self.not_found_label = l - l.setFrameStyle(QFrame.StyledPanel) - l.setAutoFillBackground(True) - l.setText('

'+_('No More Matches.

Click Find again to go to first match')) - l.setAlignment(Qt.AlignVCenter) - l.setWordWrap(True) - l.resize(l.sizeHint()) - l.move(10,20) - l.setVisible(False) - self.not_found_label_timer = QTimer() - self.not_found_label_timer.setSingleShot(True) - self.not_found_label_timer.timeout.connect(self.not_found_label_timer_event, - type=Qt.QueuedConnection) - - parent.sort_by = QComboBox(parent) - # Must be in the same order as db2.CATEGORY_SORTS - for x in (_('Sort by name'), _('Sort by popularity'), - _('Sort by average rating')): - parent.sort_by.addItem(x) - parent.sort_by.setToolTip( - _('Set the sort order for entries in the Tag Browser')) - parent.sort_by.setStatusTip(parent.sort_by.toolTip()) - parent.sort_by.setCurrentIndex(0) - self._layout.addWidget(parent.sort_by) - - # Must be in the same order as db2.MATCH_TYPE - parent.tag_match = QComboBox(parent) - for x in (_('Match any'), _('Match all')): - parent.tag_match.addItem(x) - parent.tag_match.setCurrentIndex(0) - self._layout.addWidget(parent.tag_match) - parent.tag_match.setToolTip( - _('When selecting multiple entries in the Tag Browser ' - 'match any or all of them')) - parent.tag_match.setStatusTip(parent.tag_match.toolTip()) - - - l = parent.manage_items_button = QPushButton(self) - l.setStyleSheet('QPushButton {text-align: left; }') - l.setText(_('Manage authors, tags, etc')) - l.setToolTip(_('All of these category_managers are available by right-clicking ' - 'on items in the tag browser above')) - l.m = QMenu() - l.setMenu(l.m) - self._layout.addWidget(l) - - # self.leak_test_timer = QTimer(self) - # self.leak_test_timer.timeout.connect(self.test_for_leak) - # self.leak_test_timer.start(5000) - - def set_pane_is_visible(self, to_what): - self.tags_view.set_pane_is_visible(to_what) - - def find_text_changed(self, str): - self.current_find_position = None - - def set_focus_to_find_box(self): - self.item_search.setFocus() - self.item_search.lineEdit().selectAll() - - def do_find(self, str=None): - self.current_find_position = None - self.find() - - def find(self): - model = self.tags_view.model() - model.clear_boxed() - txt = unicode(self.item_search.currentText()).strip() - - if txt.startswith('*'): - self.tags_view.set_new_model(filter_categories_by=txt[1:]) - self.current_find_position = None - return - if model.get_filter_categories_by(): - self.tags_view.set_new_model(filter_categories_by=None) - self.current_find_position = None - model = self.tags_view.model() - - if not txt: - return - - self.item_search.lineEdit().blockSignals(True) - self.search_button.setFocus(True) - self.item_search.lineEdit().blockSignals(False) - - key = None - colon = txt.rfind(':') if len(txt) > 2 else 0 - if colon > 0: - key = self.parent.library_view.model().db.\ - field_metadata.search_term_to_field_key(txt[:colon]) - txt = txt[colon+1:] - - self.current_find_position = \ - model.find_item_node(key, txt, self.current_find_position) - if self.current_find_position: - model.show_item_at_path(self.current_find_position, box=True) - elif self.item_search.text(): - self.not_found_label.setVisible(True) - if self.tags_view.verticalScrollBar().isVisible(): - sbw = self.tags_view.verticalScrollBar().width() - else: - sbw = 0 - width = self.width() - 8 - sbw - height = self.not_found_label.heightForWidth(width) + 20 - self.not_found_label.resize(width, height) - self.not_found_label.move(4, 10) - self.not_found_label_timer.start(2000) - - def not_found_label_timer_event(self): - self.not_found_label.setVisible(False) - - def test_for_leak(self): - from calibre.utils.mem import memory - import gc - before = memory() - self.tags_view.recount() - for i in xrange(3): gc.collect() - print 'Used memory:', memory(before)/(1024.), 'KB' - -# }}} - diff --git a/src/calibre/gui2/ui.py b/src/calibre/gui2/ui.py index cf9f6ee610..5007d343ce 100644 --- a/src/calibre/gui2/ui.py +++ b/src/calibre/gui2/ui.py @@ -39,7 +39,7 @@ from calibre.gui2.jobs import JobManager, JobsDialog, JobsButton from calibre.gui2.init import LibraryViewMixin, LayoutMixin from calibre.gui2.search_box import SearchBoxMixin, SavedSearchBoxMixin from calibre.gui2.search_restriction_mixin import SearchRestrictionMixin -from calibre.gui2.tag_view import TagBrowserMixin +from calibre.gui2.tag_browser.ui import TagBrowserMixin class Listener(Thread): # {{{ diff --git a/src/calibre/gui2/update.py b/src/calibre/gui2/update.py index c9a908bdf6..9d4d4def75 100644 --- a/src/calibre/gui2/update.py +++ b/src/calibre/gui2/update.py @@ -72,9 +72,7 @@ class UpdateNotification(QDialog): self.label = QLabel(('

'+ _('%s has been updated to version %s. ' 'See the new features.') + '

'+_('Update only if one of the ' - 'new features or bug fixes is important to you. ' - 'If the current version works well for you, do not update.'))%( + '">new features.'))%( __appname__, calibre_version)) self.label.setOpenExternalLinks(True) self.label.setWordWrap(True) diff --git a/src/calibre/library/database2.py b/src/calibre/library/database2.py index 13f65c3b2b..9d8f28e8e6 100644 --- a/src/calibre/library/database2.py +++ b/src/calibre/library/database2.py @@ -2016,7 +2016,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns): val = mi.get(key, None) if force_changes or val is not None: doit(self.set_custom, id, val=val, extra=mi.get_extra(key), - label=user_mi[key]['label'], commit=False) + label=user_mi[key]['label'], commit=False, notify=False) if commit: self.conn.commit() if notify: diff --git a/src/calibre/translations/calibre.pot b/src/calibre/translations/calibre.pot index 5f080cf28d..a1a9de158a 100644 --- a/src/calibre/translations/calibre.pot +++ b/src/calibre/translations/calibre.pot @@ -4,9 +4,9 @@ # msgid "" msgstr "" -"Project-Id-Version: calibre 0.8.6\n" -"POT-Creation-Date: 2011-06-23 12:00+MDT\n" -"PO-Revision-Date: 2011-06-23 12:00+MDT\n" +"Project-Id-Version: calibre 0.8.7\n" +"POT-Creation-Date: 2011-06-24 11:37+MDT\n" +"PO-Revision-Date: 2011-06-24 11:37+MDT\n" "Last-Translator: Automatically generated\n" "Language-Team: LANGUAGE\n" "MIME-Version: 1.0\n" @@ -53,7 +53,8 @@ msgstr "" #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/ereader.py:36 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/ereader.py:61 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/extz.py:23 -#: /home/kovid/work/calibre/src/calibre/ebooks/metadata/fb2.py:55 +#: /home/kovid/work/calibre/src/calibre/ebooks/metadata/fb2.py:40 +#: /home/kovid/work/calibre/src/calibre/ebooks/metadata/fb2.py:100 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/meta.py:36 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/meta.py:64 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/meta.py:66 @@ -123,8 +124,8 @@ msgstr "" #: /home/kovid/work/calibre/src/calibre/ebooks/pdf/writer.py:102 #: /home/kovid/work/calibre/src/calibre/ebooks/rtf/input.py:313 #: /home/kovid/work/calibre/src/calibre/ebooks/rtf/input.py:315 -#: /home/kovid/work/calibre/src/calibre/gui2/__init__.py:362 -#: /home/kovid/work/calibre/src/calibre/gui2/__init__.py:370 +#: /home/kovid/work/calibre/src/calibre/gui2/__init__.py:363 +#: /home/kovid/work/calibre/src/calibre/gui2/__init__.py:371 #: /home/kovid/work/calibre/src/calibre/gui2/actions/add.py:156 #: /home/kovid/work/calibre/src/calibre/gui2/actions/edit_metadata.py:376 #: /home/kovid/work/calibre/src/calibre/gui2/actions/edit_metadata.py:379 @@ -165,11 +166,11 @@ msgstr "" #: /home/kovid/work/calibre/src/calibre/library/database2.py:532 #: /home/kovid/work/calibre/src/calibre/library/database2.py:540 #: /home/kovid/work/calibre/src/calibre/library/database2.py:551 -#: /home/kovid/work/calibre/src/calibre/library/database2.py:1932 -#: /home/kovid/work/calibre/src/calibre/library/database2.py:2078 -#: /home/kovid/work/calibre/src/calibre/library/database2.py:3085 -#: /home/kovid/work/calibre/src/calibre/library/database2.py:3087 -#: /home/kovid/work/calibre/src/calibre/library/database2.py:3220 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:1946 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:2092 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:3099 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:3101 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:3234 #: /home/kovid/work/calibre/src/calibre/library/server/content.py:212 #: /home/kovid/work/calibre/src/calibre/library/server/content.py:213 #: /home/kovid/work/calibre/src/calibre/library/server/mobile.py:233 @@ -886,14 +887,14 @@ msgstr "" #: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:479 #: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:1058 #: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:1101 -#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:3098 -#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:3138 +#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:3103 +#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:3143 msgid "%d of %d" msgstr "" #: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:486 #: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:1106 -#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:3144 +#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:3149 #: /home/kovid/work/calibre/src/calibre/gui2/ebook_download.py:106 msgid "finished" msgstr "" @@ -911,7 +912,7 @@ msgid "" "Click 'Show Details' for a list." msgstr "" -#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:2669 +#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:2673 #: /home/kovid/work/calibre/src/calibre/devices/nook/driver.py:102 #: /home/kovid/work/calibre/src/calibre/devices/prs505/sony_cache.py:447 #: /home/kovid/work/calibre/src/calibre/devices/prs505/sony_cache.py:470 @@ -920,24 +921,24 @@ msgstr "" #: /home/kovid/work/calibre/src/calibre/devices/usbms/device.py:951 #: /home/kovid/work/calibre/src/calibre/gui2/actions/fetch_news.py:73 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/scheduler.py:445 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1661 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1663 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1678 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1680 #: /home/kovid/work/calibre/src/calibre/library/database2.py:328 #: /home/kovid/work/calibre/src/calibre/library/database2.py:341 -#: /home/kovid/work/calibre/src/calibre/library/database2.py:2949 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:2963 #: /home/kovid/work/calibre/src/calibre/library/field_metadata.py:170 msgid "News" msgstr "" -#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:2670 +#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:2674 #: /home/kovid/work/calibre/src/calibre/gui2/catalog/catalog_epub_mobi.py:65 #: /home/kovid/work/calibre/src/calibre/library/catalog.py:652 -#: /home/kovid/work/calibre/src/calibre/library/database2.py:2909 -#: /home/kovid/work/calibre/src/calibre/library/database2.py:2927 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:2923 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:2941 msgid "Catalog" msgstr "" -#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:3000 +#: /home/kovid/work/calibre/src/calibre/devices/apple/driver.py:3005 msgid "Communicate with iTunes." msgstr "" @@ -1718,321 +1719,321 @@ msgstr "" msgid "Output saved to" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:103 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:105 msgid "Level of verbosity. Specify multiple times for greater verbosity." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:110 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:112 msgid "Save the output from different stages of the conversion pipeline to the specified directory. Useful if you are unsure at which stage of the conversion process a bug is occurring." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:119 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:121 msgid "Specify the input profile. The input profile gives the conversion system information on how to interpret various information in the input document. For example resolution dependent lengths (i.e. lengths in pixels). Choices are:" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:130 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:132 msgid "Specify the output profile. The output profile tells the conversion system how to optimize the created document for the specified device. In some cases, an output profile is required to produce documents that will work on a device. For example EPUB on the SONY reader. Choices are:" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:141 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:143 msgid "The base font size in pts. All font sizes in the produced book will be rescaled based on this size. By choosing a larger size you can make the fonts in the output bigger and vice versa. By default, the base font size is chosen based on the output profile you chose." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:151 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:153 msgid "Mapping from CSS font names to font sizes in pts. An example setting is 12,12,14,16,18,20,22,24. These are the mappings for the sizes xx-small to xx-large, with the final size being for huge fonts. The font rescaling algorithm uses these sizes to intelligently rescale fonts. The default is to use a mapping based on the output profile you chose." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:163 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:165 msgid "Disable all rescaling of font sizes." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:169 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:171 msgid "The minimum line height, as a percentage of the element's calculated font size. calibre will ensure that every element has a line height of at least this setting, irrespective of what the input document specifies. Set to zero to disable. Default is 120%. Use this setting in preference to the direct line height specification, unless you know what you are doing. For example, you can achieve \"double spaced\" text by setting this to 240." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:184 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:186 msgid "The line height in pts. Controls spacing between consecutive lines of text. Only applies to elements that do not define their own line height. In most cases, the minimum line height option is more useful. By default no line height manipulation is performed." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:195 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:197 msgid "Some badly designed documents use tables to control the layout of text on the page. When converted these documents often have text that runs off the page and other artifacts. This option will extract the content from the tables and present it in a linear fashion." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:205 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:207 msgid "XPath expression that specifies all tags that should be added to the Table of Contents at level one. If this is specified, it takes precedence over other forms of auto-detection." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:214 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:216 msgid "XPath expression that specifies all tags that should be added to the Table of Contents at level two. Each entry is added under the previous level one entry." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:222 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:224 msgid "XPath expression that specifies all tags that should be added to the Table of Contents at level three. Each entry is added under the previous level two entry." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:230 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:232 msgid "Normally, if the source file already has a Table of Contents, it is used in preference to the auto-generated one. With this option, the auto-generated one is always used." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:238 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:240 msgid "Don't add auto-detected chapters to the Table of Contents." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:245 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:247 msgid "If fewer than this number of chapters is detected, then links are added to the Table of Contents. Default: %default" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:252 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:254 msgid "Maximum number of links to insert into the TOC. Set to 0 to disable. Default is: %default. Links are only added to the TOC if less than the threshold number of chapters were detected." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:260 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:262 msgid "Remove entries from the Table of Contents whose titles match the specified regular expression. Matching entries and all their children are removed." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:271 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:273 msgid "An XPath expression to detect chapter titles. The default is to consider

or

tags that contain the words \"chapter\",\"book\",\"section\" or \"part\" as chapter titles as well as any tags that have class=\"chapter\". The expression used must evaluate to a list of elements. To disable chapter detection, use the expression \"/\". See the XPath Tutorial in the calibre User Manual for further help on using this feature." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:285 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:287 msgid "Specify how to mark detected chapters. A value of \"pagebreak\" will insert page breaks before chapters. A value of \"rule\" will insert a line before chapters. A value of \"none\" will disable chapter marking and a value of \"both\" will use both page breaks and lines to mark chapters." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:295 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:297 msgid "Either the path to a CSS stylesheet or raw CSS. This CSS will be appended to the style rules from the source file, so it can be used to override those rules." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:304 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:306 msgid "An XPath expression. Page breaks are inserted before the specified elements." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:310 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:312 msgid "Some documents specify page margins by specifying a left and right margin on each individual paragraph. calibre will try to detect and remove these margins. Sometimes, this can cause the removal of margins that should not have been removed. In this case you can disable the removal." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:321 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:323 msgid "Set the top margin in pts. Default is %default. Note: 72 pts equals 1 inch" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:326 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:328 msgid "Set the bottom margin in pts. Default is %default. Note: 72 pts equals 1 inch" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:331 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:333 msgid "Set the left margin in pts. Default is %default. Note: 72 pts equals 1 inch" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:336 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:338 msgid "Set the right margin in pts. Default is %default. Note: 72 pts equals 1 inch" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:342 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:344 msgid "Change text justification. A value of \"left\" converts all justified text in the source to left aligned (i.e. unjustified) text. A value of \"justify\" converts all unjustified text to justified. A value of \"original\" (the default) does not change justification in the source file. Note that only some output formats support justification." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:352 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:354 msgid "Remove spacing between paragraphs. Also sets an indent on paragraphs of 1.5em. Spacing removal will not work if the source file does not use paragraphs (

or

tags)." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:359 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:361 msgid "When calibre removes inter paragraph spacing, it automatically sets a paragraph indent, to ensure that paragraphs can be easily distinguished. This option controls the width of that indent." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:366 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:368 msgid "Use the cover detected from the source file in preference to the specified cover." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:372 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:374 msgid "Insert a blank line between paragraphs. Will not work if the source file does not use paragraphs (

or

tags)." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:379 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:381 msgid "Remove the first image from the input ebook. Useful if the first image in the source file is a cover and you are specifying an external cover." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:387 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:389 msgid "Insert the book metadata at the start of the book. This is useful if your ebook reader does not support displaying/searching metadata directly." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:395 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:397 msgid "Convert plain quotes, dashes and ellipsis to their typographically correct equivalents. For details, see http://daringfireball.net/projects/smartypants" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:404 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:406 msgid "Read metadata from the specified OPF file. Metadata read from this file will override any metadata in the source file." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:411 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:413 msgid "Transliterate unicode characters to an ASCII representation. Use with care because this will replace unicode characters with ASCII. For instance it will replace \"%s\" with \"Mikhail Gorbachiov\". Also, note that in cases where there are multiple representations of a character (characters shared by Chinese and Japanese for instance) the representation based on the current calibre interface language will be used." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:426 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:428 msgid "Preserve ligatures present in the input document. A ligature is a special rendering of a pair of characters like ff, fi, fl et cetera. Most readers do not have support for ligatures in their default fonts, so they are unlikely to render correctly. By default, calibre will turn a ligature into the corresponding pair of normal characters. This option will preserve them instead." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:438 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:440 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/cli.py:38 msgid "Set the title." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:442 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:444 msgid "Set the authors. Multiple authors should be separated by ampersands." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:447 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:449 msgid "The version of the title to be used for sorting. " msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:451 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:453 msgid "String to be used when sorting by author. " msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:455 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:457 msgid "Set the cover to the specified file or URL" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:459 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:461 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/cli.py:54 msgid "Set the ebook description." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:463 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:465 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/cli.py:56 msgid "Set the ebook publisher." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:467 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:469 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/cli.py:60 msgid "Set the series this ebook belongs to." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:471 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:473 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/cli.py:62 msgid "Set the index of the book in this series." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:475 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:477 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/cli.py:64 msgid "Set the rating. Should be a number between 1 and 5." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:479 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:481 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/cli.py:66 msgid "Set the ISBN of the book." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:483 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:485 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/cli.py:68 msgid "Set the tags for the book. Should be a comma separated list." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:487 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:489 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/cli.py:70 msgid "Set the book producer." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:491 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:493 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/cli.py:72 msgid "Set the language." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:495 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:497 msgid "Set the publication date." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:499 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:501 msgid "Set the book timestamp (used by the date column in calibre)." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:503 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:505 msgid "Enable heuristic processing. This option must be set for any heuristic processing to take place." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:508 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:510 msgid "Detect unformatted chapter headings and sub headings. Change them to h2 and h3 tags. This setting will not create a TOC, but can be used in conjunction with structure detection to create one." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:515 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:517 msgid "Look for common words and patterns that denote italics and italicize them." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:520 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:522 msgid "Turn indentation created from multiple non-breaking space entities into CSS indents." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:525 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:527 msgid "Scale used to determine the length at which a line should be unwrapped. Valid values are a decimal between 0 and 1. The default is 0.4, just below the median line length. If only a few lines in the document require unwrapping this value should be reduced" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:533 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:535 msgid "Unwrap lines using punctuation and other formatting clues." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:537 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:539 msgid "Remove empty paragraphs from the document when they exist between every other paragraph" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:542 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:544 msgid "Left aligned scene break markers are center aligned. Replace soft scene breaks that use multiple blank lines withhorizontal rules." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:548 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:550 msgid "Replace scene breaks with the specified text. By default, the text from the input document is used." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:553 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:555 msgid "Analyze hyphenated words throughout the document. The document itself is used as a dictionary to determine whether hyphens should be retained or removed." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:559 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:561 msgid "Looks for occurrences of sequential

or

tags. The tags are renumbered to prevent splitting in the middle of chapter headings." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:565 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:567 msgid "Search pattern (regular expression) to be replaced with sr1-replace." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:570 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:572 msgid "Replacement to replace the text found with sr1-search." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:574 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:576 msgid "Search pattern (regular expression) to be replaced with sr2-replace." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:579 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:581 msgid "Replacement to replace the text found with sr2-search." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:583 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:585 msgid "Search pattern (regular expression) to be replaced with sr3-replace." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:588 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:590 msgid "Replacement to replace the text found with sr3-search." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:690 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:692 msgid "Could not find an ebook inside the archive" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:748 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:750 msgid "Values of series index and rating must be numbers. Ignoring" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:755 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:757 msgid "Failed to parse date/time" msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:914 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:916 msgid "Converting input to HTML..." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:941 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:943 msgid "Running transforms on ebook..." msgstr "" -#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:1037 +#: /home/kovid/work/calibre/src/calibre/ebooks/conversion/plumber.py:1039 msgid "Creating" msgstr "" @@ -2451,7 +2452,7 @@ msgstr "" #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/book/base.py:733 #: /home/kovid/work/calibre/src/calibre/ebooks/pdf/manipulate/info.py:45 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/delete_matching_from_device.py:75 -#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/quickview.py:68 +#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/quickview.py:71 #: /home/kovid/work/calibre/src/calibre/gui2/library/models.py:56 #: /home/kovid/work/calibre/src/calibre/gui2/library/models.py:1015 #: /home/kovid/work/calibre/src/calibre/gui2/metadata/single_download.py:133 @@ -2501,7 +2502,7 @@ msgstr "" #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/book/base.py:741 #: /home/kovid/work/calibre/src/calibre/ebooks/oeb/transforms/jacket.py:168 -#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/quickview.py:72 +#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/quickview.py:75 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/tag_categories.py:60 #: /home/kovid/work/calibre/src/calibre/gui2/library/models.py:65 #: /home/kovid/work/calibre/src/calibre/gui2/preferences/create_custom_column.py:70 @@ -3341,7 +3342,7 @@ msgstr "" msgid "tag browser categories not to display" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/__init__.py:476 +#: /home/kovid/work/calibre/src/calibre/gui2/__init__.py:477 msgid "Choose Files" msgstr "" @@ -3686,7 +3687,7 @@ msgid "The folder %s already exists. Delete it first." msgstr "" #: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:235 -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:294 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:295 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/choose_library.py:70 #: /home/kovid/work/calibre/src/calibre/gui2/wizard/__init__.py:661 msgid "Too long" @@ -3715,34 +3716,38 @@ msgid "Are you sure?" msgstr "" #: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:256 +msgid "

WARNING

" +msgstr "" + +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:257 msgid "All files (not just ebooks) from

%s

will be permanently deleted. Are you sure?" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:277 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:278 msgid "none" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:278 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:279 msgid "Backup status" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:279 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:280 msgid "Book metadata files remaining to be written: %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:285 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:286 msgid "Backup metadata" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:286 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:287 msgid "Metadata will be backed up while calibre is running, at the rate of approximately 1 book every three seconds." msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:295 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:296 msgid "Path to library too long. Must be less than %d characters. Move your library to a location with a shorter path using Windows Explorer, then point calibre to the new location and try again." msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:330 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:331 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/plugin_updater.py:731 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/restore_library.py:106 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/restore_library.py:111 @@ -3751,11 +3756,11 @@ msgstr "" msgid "Success" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:331 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:332 msgid "Found no errors in your calibre library database. Do you want calibre to check if the files in your library match the information in the database?" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:336 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:337 #: /home/kovid/work/calibre/src/calibre/gui2/actions/copy_to_library.py:160 #: /home/kovid/work/calibre/src/calibre/gui2/device.py:741 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/metadata_bulk.py:966 @@ -3765,39 +3770,39 @@ msgstr "" msgid "Failed" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:337 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:338 msgid "Database integrity check failed, click Show details for details." msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:342 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:343 msgid "No problems found" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:343 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:344 msgid "The files in your library match the information in the database." msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:352 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:353 msgid "No library found" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:353 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:354 msgid "No existing calibre library was found at %s. It will be removed from the list of known libraries." msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:419 -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:424 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:420 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:425 #: /home/kovid/work/calibre/src/calibre/gui2/actions/copy_to_library.py:177 #: /home/kovid/work/calibre/src/calibre/gui2/actions/save_to_disk.py:100 -#: /home/kovid/work/calibre/src/calibre/gui2/library/views.py:862 +#: /home/kovid/work/calibre/src/calibre/gui2/library/views.py:866 msgid "Not allowed" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:420 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:421 msgid "You cannot change libraries while using the environment variable CALIBRE_OVERRIDE_DATABASE_PATH." msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:425 +#: /home/kovid/work/calibre/src/calibre/gui2/actions/choose_library.py:426 msgid "You cannot change libraries while jobs are running." msgstr "" @@ -5336,7 +5341,7 @@ msgid "Bulk Convert" msgstr "" #: /home/kovid/work/calibre/src/calibre/gui2/convert/bulk.py:89 -#: /home/kovid/work/calibre/src/calibre/gui2/convert/single.py:185 +#: /home/kovid/work/calibre/src/calibre/gui2/convert/single.py:189 msgid "Options specific to the output format." msgstr "" @@ -6152,11 +6157,11 @@ msgstr "" msgid "

Search and replace uses regular expressions. See the regular expressions tutorial to get started with regular expressions. Also clicking the wizard buttons below will allow you to test your regular expression against the current input document." msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/convert/single.py:169 +#: /home/kovid/work/calibre/src/calibre/gui2/convert/single.py:173 msgid "Convert" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/convert/single.py:196 +#: /home/kovid/work/calibre/src/calibre/gui2/convert/single.py:200 msgid "Options specific to the input format." msgstr "" @@ -7069,7 +7074,7 @@ msgid "New &Location:" msgstr "" #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/choose_library_ui.py:80 -msgid "Use &existing library at the new location" +msgid "Use the previously &existing library at the new location" msgstr "" #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/choose_library_ui.py:81 @@ -7279,13 +7284,13 @@ msgstr "" #: #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/edit_authors_dialog.py:271 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1453 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1470 msgid "Invalid author name" msgstr "" #: #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/edit_authors_dialog.py:272 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1454 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1471 msgid "Author names cannot contain & characters." msgstr "" @@ -7303,7 +7308,7 @@ msgstr "" #: #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/edit_authors_dialog_ui.py:90 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2134 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2154 msgid "F&ind" msgstr "" @@ -7378,19 +7383,19 @@ msgstr "" msgid "Show detailed information about this error" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/message_box.py:98 +#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/message_box.py:100 #: /home/kovid/work/calibre/src/calibre/gui2/wizard/__init__.py:525 msgid "Copied" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/message_box.py:135 +#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/message_box.py:138 #: /home/kovid/work/calibre/src/calibre/gui2/metadata/single_download.py:770 #: /home/kovid/work/calibre/src/calibre/gui2/viewer/main_ui.py:205 msgid "Copy to clipboard" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/message_box.py:181 -#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/message_box.py:229 +#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/message_box.py:184 +#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/message_box.py:232 #: /home/kovid/work/calibre/src/calibre/gui2/metadata/single_download.py:831 #: /home/kovid/work/calibre/src/calibre/gui2/metadata/single_download.py:922 msgid "View log" @@ -8167,17 +8172,21 @@ msgstr "" msgid "Aborting..." msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/quickview.py:70 +#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/quickview.py:73 #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/tag_categories.py:60 #: /home/kovid/work/calibre/src/calibre/gui2/preferences/metadata_sources.py:146 #: /home/kovid/work/calibre/src/calibre/library/field_metadata.py:111 msgid "Authors" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/quickview.py:161 +#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/quickview.py:166 msgid "Books with selected item: {0}" msgstr "" +#: /home/kovid/work/calibre/src/calibre/gui2/dialogs/quickview.py:171 +msgid "Double-click on a book to change the selection in the library view. Shift- or control-double-click to edit the metadata of a book" +msgstr "" + #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/quickview_ui.py:75 msgid "Quickview" msgstr "" @@ -8807,12 +8816,12 @@ msgid "%s (was %s)" msgstr "" #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/tag_list_editor.py:85 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1399 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1416 msgid "Item is blank" msgstr "" #: /home/kovid/work/calibre/src/calibre/gui2/dialogs/tag_list_editor.py:86 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1400 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1417 msgid "An item cannot be set to nothing. Delete it instead." msgstr "" @@ -9525,7 +9534,7 @@ msgstr "" #: /home/kovid/work/calibre/src/calibre/gui2/library/models.py:758 #: /home/kovid/work/calibre/src/calibre/gui2/library/models.py:1317 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:807 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:820 msgid "The lookup/search name is \"{0}\"" msgstr "" @@ -9591,7 +9600,7 @@ msgstr "" msgid "Restore default layout" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/library/views.py:863 +#: /home/kovid/work/calibre/src/calibre/gui2/library/views.py:867 msgid "Dropping onto a device is not supported. First add the book to the calibre library." msgstr "" @@ -12775,190 +12784,190 @@ msgstr "" msgid "%p%" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:345 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:375 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:404 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:347 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:377 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:406 msgid "Rename %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:349 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:351 msgid "Edit sort for %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:356 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:358 msgid "Add %s to user category" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:369 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:371 msgid "Children of %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:379 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:381 msgid "Delete search %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:384 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:386 msgid "Remove %s from category %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:391 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:393 msgid "Search for %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:396 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:398 msgid "Search for everything but %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:408 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:410 msgid "Add sub-category to %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:412 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:414 msgid "Delete user category %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:417 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:419 msgid "Hide category %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:421 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:423 msgid "Show category" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:431 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:433 msgid "Search for books in category %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:437 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:439 msgid "Search for books not in category %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:446 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:451 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:448 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:453 msgid "Manage %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:454 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1873 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:456 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1893 msgid "Manage Saved Searches" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:462 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:466 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1871 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:464 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:468 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1891 msgid "Manage User Categories" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:473 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:475 msgid "Show all categories" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:476 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:478 msgid "Change sub-categorization scheme" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:802 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:815 msgid "The grouped search term name is \"{0}\"" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1075 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1088 msgid "Changing the authors for several books can take a while. Are you sure?" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1080 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1093 msgid "Changing the metadata for that many books can take a while. Are you sure?" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1167 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1182 #: /home/kovid/work/calibre/src/calibre/library/database2.py:447 msgid "Searches" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1405 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1425 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1434 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1422 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1442 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1451 msgid "Rename user category" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1406 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1423 msgid "You cannot use periods in the name when renaming user categories" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1426 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1435 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1443 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1452 msgid "The name %s is already used" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1458 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1475 msgid "Duplicate search name" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1459 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1476 msgid "The saved search name %s is already used." msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1863 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1883 msgid "Manage Authors" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1865 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1885 msgid "Manage Series" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1867 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1887 msgid "Manage Publishers" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1869 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1889 msgid "Manage Tags" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1881 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1901 msgid "Invalid search restriction" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1882 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1902 msgid "The current search restriction is invalid" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1898 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1918 msgid "New Category" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1949 -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1952 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1969 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1972 msgid "Delete user category" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1950 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1970 msgid "%s is not a user category" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1953 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1973 msgid "%s contains items. Do you really want to delete it?" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1974 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1994 msgid "Remove category" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1975 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1995 msgid "User category %s does not exist" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1994 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2014 msgid "Add to user category" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1995 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2015 msgid "A user category %s does not exist" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2118 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2138 msgid "Find item in tag browser" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2121 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2141 msgid "" "Search for items. This is a \"contains\" search; items containing the\n" "text anywhere in the name will be found. You can limit the search\n" @@ -12968,55 +12977,55 @@ msgid "" "containing the text \"foo\"" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2130 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2150 msgid "ALT+f" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2135 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2155 msgid "Find the first/next matching item" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2140 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2160 msgid "Collapse all categories" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2164 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2184 msgid "No More Matches.

Click Find again to go to first match" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2177 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2197 msgid "Sort by name" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2177 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2197 msgid "Sort by popularity" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2178 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2198 msgid "Sort by average rating" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2181 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2201 msgid "Set the sort order for entries in the Tag Browser" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2188 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2208 msgid "Match all" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2188 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2208 msgid "Match any" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2193 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2213 msgid "When selecting multiple entries in the Tag Browser match any or all of them" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2200 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2220 msgid "Manage authors, tags, etc" msgstr "" -#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2201 +#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:2221 msgid "All of these category_managers are available by right-clicking on items in the tag browser above" msgstr "" @@ -14763,15 +14772,15 @@ msgstr "" msgid "Main" msgstr "" -#: /home/kovid/work/calibre/src/calibre/library/database2.py:3246 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:3260 msgid "

Migrating old database to ebook library in %s

" msgstr "" -#: /home/kovid/work/calibre/src/calibre/library/database2.py:3275 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:3289 msgid "Copying %s" msgstr "" -#: /home/kovid/work/calibre/src/calibre/library/database2.py:3292 +#: /home/kovid/work/calibre/src/calibre/library/database2.py:3306 msgid "Compacting database" msgstr "" @@ -15434,6 +15443,14 @@ msgstr "" msgid "merge_lists(list1, list2, separator) -- return a list made by merging the items in list1 and list2, removing duplicate items using a case-insensitive compare. If items differ in case, the one in list1 is used. The items in list1 and list2 are separated by separator, as are the items in the returned list." msgstr "" +#: /home/kovid/work/calibre/src/calibre/utils/formatter_functions.py:761 +msgid "today() -- return a date string for today. This value is designed for use in format_date or days_between, but can be manipulated like any other string. The date is in ISO format." +msgstr "" + +#: /home/kovid/work/calibre/src/calibre/utils/formatter_functions.py:772 +msgid "days_between(date1, date2) -- return the number of days between date1 and date2. The number is positive if date1 is greater than date2, otherwise negative. If either date1 or date2 are not dates, the function returns the empty string." +msgstr "" + #: /home/kovid/work/calibre/src/calibre/utils/ipc/job.py:43 msgid "Waiting..." msgstr "" diff --git a/src/calibre/utils/formatter.py b/src/calibre/utils/formatter.py index ebf47db854..3a93c2b650 100644 --- a/src/calibre/utils/formatter.py +++ b/src/calibre/utils/formatter.py @@ -347,5 +347,6 @@ class EvalFormatter(TemplateFormatter): key = key.lower() return kwargs.get(key, _('No such variable ') + key) +# DEPRECATED. This is not thread safe. Do not use. eval_formatter = EvalFormatter() diff --git a/src/calibre/utils/formatter_functions.py b/src/calibre/utils/formatter_functions.py index 63264e6379..c6f4bd1b0e 100644 --- a/src/calibre/utils/formatter_functions.py +++ b/src/calibre/utils/formatter_functions.py @@ -202,9 +202,9 @@ class BuiltinEval(BuiltinFormatterFunction): 'results from local variables.') def evaluate(self, formatter, kwargs, mi, locals, template): - from formatter import eval_formatter + from formatter import EvalFormatter template = template.replace('[[', '{').replace(']]', '}') - return eval_formatter.safe_format(template, locals, 'EVAL', None) + return EvalFormatter().safe_format(template, locals, 'EVAL', None) class BuiltinAssign(BuiltinFormatterFunction): name = 'assign' @@ -785,7 +785,7 @@ class BuiltinDaysBetween(BuiltinFormatterFunction): except: return '' i = d1 - d2 - return str(i.days) + return str('%d.%d'%(i.days, i.seconds/8640)) builtin_add = BuiltinAdd() diff --git a/src/calibre/utils/ipc/proxy.py b/src/calibre/utils/ipc/proxy.py index b60f9eb755..3b037a42a6 100644 --- a/src/calibre/utils/ipc/proxy.py +++ b/src/calibre/utils/ipc/proxy.py @@ -7,15 +7,82 @@ __license__ = 'GPL v3' __copyright__ = '2011, Kovid Goyal ' __docformat__ = 'restructuredtext en' -import os +import os, cPickle, struct from threading import Thread +from Queue import Queue, Empty from multiprocessing.connection import arbitrary_address, Listener +from functools import partial -from calibre.constants import iswindows +from calibre import as_unicode, prints +from calibre.constants import iswindows, DEBUG + +def _encode(msg): + raw = cPickle.dumps(msg, -1) + size = len(raw) + header = struct.pack('!Q', size) + return header + raw + +def _decode(raw): + sz = struct.calcsize('!Q') + if len(raw) < sz: + return 'invalid', None + header, = struct.unpack('!Q', raw[:sz]) + if len(raw) != sz + header or header == 0: + return 'invalid', None + return cPickle.loads(raw[sz:]) + + +class Writer(Thread): + + TIMEOUT = 60 #seconds + + def __init__(self, conn): + Thread.__init__(self) + self.daemon = True + self.dataq, self.resultq = Queue(), Queue() + self.conn = conn + self.start() + self.data_written = False + + def close(self): + self.dataq.put(None) + + def flush(self): + pass + + def write(self, raw_data): + self.dataq.put(raw_data) + + try: + ex = self.resultq.get(True, self.TIMEOUT) + except Empty: + raise IOError('Writing to socket timed out') + else: + if ex is not None: + raise IOError('Writing to socket failed with error: %s' % ex) + + def run(self): + while True: + x = self.dataq.get() + if x is None: + break + try: + self.data_written = True + self.conn.send_bytes(x) + except Exception as e: + self.resultq.put(as_unicode(e)) + else: + self.resultq.put(None) + + def __enter__(self): + return self + + def __exit__(self, exc_type, exc_val, exc_tb): + self.close() class Server(Thread): - def __init__(self): + def __init__(self, dispatcher): Thread.__init__(self) self.daemon = True @@ -27,6 +94,13 @@ class Server(Thread): authkey=self.auth_key, backlog=4) self.keep_going = True + self.dispatcher = dispatcher + + @property + def connection_information(self): + if not self.is_alive(): + self.start() + return (self.address, self.auth_key) def stop(self): self.keep_going = False @@ -43,4 +117,49 @@ class Server(Thread): except: pass + def handle_client(self, conn): + t = Thread(target=partial(self._handle_client, conn)) + t.daemon = True + t.start() + + def _handle_client(self, conn): + while True: + try: + func_name, args, kwargs = conn.recv() + except EOFError: + try: + conn.close() + except: + pass + return + else: + try: + self.call_func(func_name, args, kwargs, conn) + except: + try: + conn.close() + except: + pass + prints('Proxy function: %s with args: %r and' + ' kwargs: %r failed') + if DEBUG: + import traceback + traceback.print_exc() + break + + def call_func(self, func_name, args, kwargs, conn): + with Writer(conn) as f: + try: + self.dispatcher(f, func_name, args, kwargs) + except Exception as e: + if not f.data_written: + import traceback + # Try to tell the client process what error happened + try: + conn.send_bytes(_encode(('failed', (unicode(e), + as_unicode(traceback.format_exc()))))) + except: + pass + raise + diff --git a/src/calibre/utils/opensearch/__init__.py b/src/calibre/utils/opensearch/__init__.py new file mode 100644 index 0000000000..ec3f1704b0 --- /dev/null +++ b/src/calibre/utils/opensearch/__init__.py @@ -0,0 +1,6 @@ +from description import Description +from query import Query +from client import Client +from results import Results + +Description, Query, Client, Results diff --git a/src/calibre/utils/opensearch/client.py b/src/calibre/utils/opensearch/client.py new file mode 100644 index 0000000000..434e921568 --- /dev/null +++ b/src/calibre/utils/opensearch/client.py @@ -0,0 +1,39 @@ +from description import Description +from query import Query +from results import Results + +class Client: + + """This is the class you'll probably want to be using. You simply + pass the constructor the url for the service description file and + issue a search and get back results as an iterable Results object. + + The neat thing about a Results object is that it will seamlessly + handle fetching more results from the opensearch server when it can... + so you just need to iterate and can let the paging be taken care of + for you. + + from opensearch import Client + client = Client(description_url) + results = client.search("computer") + for result in results: + print result.title + """ + + def __init__(self, url, agent="python-opensearch "): + self.agent = agent + self.description = Description(url, self.agent) + + def search(self, search_terms, page_size=25): + """Perform a search and get back a results object + """ + url = self.description.get_best_template() + query = Query(url) + + # set up initial values + query.searchTerms = search_terms + query.count = page_size + + # run the results + return Results(query, agent=self.agent) + diff --git a/src/calibre/utils/opensearch/description.py b/src/calibre/utils/opensearch/description.py new file mode 100644 index 0000000000..2909dbceb3 --- /dev/null +++ b/src/calibre/utils/opensearch/description.py @@ -0,0 +1,127 @@ +from urllib2 import urlopen, Request +from xml.dom.minidom import parse +from url import URL + +class Description: + """A class for representing OpenSearch Description files. + """ + + def __init__(self, url="", agent=""): + """The constructor which may pass an optional url to load from. + + d = Description("http://www.example.com/description") + """ + self.agent = agent + if url: + self.load(url) + + + def load(self, url): + """For loading up a description object from a url. Normally + you'll probably just want to pass a URL into the constructor. + """ + req = Request(url, headers={'User-Agent':self.agent}) + self.dom = parse(urlopen(req)) + + # version 1.1 has repeating Url elements + self.urls = self._get_urls() + + # this is version 1.0 specific + self.url = self._get_element_text('Url') + self.format = self._get_element_text('Format') + + self.shortname = self._get_element_text('ShortName') + self.longname = self._get_element_text('LongName') + self.description = self._get_element_text('Description') + self.image = self._get_element_text('Image') + self.samplesearch = self._get_element_text('SampleSearch') + self.developer = self._get_element_text('Developer') + self.contact = self._get_element_text('Contact') + self.attribution = self._get_element_text('Attribution') + self.syndicationright = self._get_element_text('SyndicationRight') + + tag_text = self._get_element_text('Tags') + if tag_text != None: + self.tags = tag_text.split(" ") + + if self._get_element_text('AdultContent') == 'true': + self.adultcontent = True + else: + self.adultcontent = False + + def get_url_by_type(self, type): + """Walks available urls and returns them by type. Only + appropriate in opensearch v1.1 where there can be multiple + query targets. Returns none if no such type is found. + + url = description.get_url_by_type('application/rss+xml') + """ + for url in self.urls: + if url.type == type: + return url + return None + + def get_best_template(self): + """OK, best is a value judgement, but so be it. You'll get + back either the atom, rss or first template available. This + method handles the main difference between opensearch v1.0 and v1.1 + """ + # version 1.0 + if self.url: + return self.url + + # atom + if self.get_url_by_type('application/atom+xml'): + return self.get_url_by_type('application/atom+xml').template + + # rss + if self.get_url_by_type('application/rss+xml'): + return self.get_url_by_type('application/rss+xml').template + + # other possible rss type + if self.get_url_by_type('text/xml'): + return self.get_url_by_Type('text/xml').template + + # otherwise just the first one + if len(self.urls) > 0: + return self.urls[0].template + + # out of luck + return None + + + # these are internal methods for querying xml + + def _get_element_text(self, tag): + elements = self._get_elements(tag) + if not elements: + return None + return self._get_text(elements[0].childNodes) + + def _get_attribute_text(self, tag, attribute): + elements = self._get_elements(tag) + if not elements: + return '' + return elements[0].getAttribute('template') + + def _get_elements(self, tag): + return self.dom.getElementsByTagName(tag) + + def _get_text(self, nodes): + text = '' + for node in nodes: + if node.nodeType == node.TEXT_NODE: + text += node.data + return text.strip() + + def _get_urls(self): + urls = [] + for element in self._get_elements('Url'): + template = element.getAttribute('template') + type = element.getAttribute('type') + if template and type: + url = URL() + url.template = template + url.type = type + urls.append(url) + return urls diff --git a/src/calibre/utils/opensearch/osfeedparser.py b/src/calibre/utils/opensearch/osfeedparser.py new file mode 100644 index 0000000000..41ef018b61 --- /dev/null +++ b/src/calibre/utils/opensearch/osfeedparser.py @@ -0,0 +1,2799 @@ +#!/usr/bin/env python +"""Universal feed parser + +Handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom 0.3, and Atom 1.0 feeds + +Visit http://feedparser.org/ for the latest version +Visit http://feedparser.org/docs/ for the latest documentation + +Required: Python 2.1 or later +Recommended: Python 2.3 or later +Recommended: CJKCodecs and iconv_codec +""" + +__version__ = "4.0.2"# + "$Revision: 1.88 $"[11:15] + "-cvs" +__license__ = """Copyright (c) 2002-2005, Mark Pilgrim, All rights reserved. + +Redistribution and use in source and binary forms, with or without modification, +are permitted provided that the following conditions are met: + +* Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. +* Redistributions in binary form must reproduce the above copyright notice, + this list of conditions and the following disclaimer in the documentation + and/or other materials provided with the distribution. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS' +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE.""" +__author__ = "Mark Pilgrim " +__contributors__ = ["Jason Diamond ", + "John Beimler ", + "Fazal Majid ", + "Aaron Swartz ", + "Kevin Marks "] +_debug = 0 + +# HTTP "User-Agent" header to send to servers when downloading feeds. +# If you are embedding feedparser in a larger application, you should +# change this to your application name and URL. +# Changed by John Schember +from calibre import USER_AGENT +USER_AGENT = USER_AGENT + +# HTTP "Accept" header to send to servers when downloading feeds. If you don't +# want to send an Accept header, set this to None. +ACCEPT_HEADER = "application/atom+xml,application/rdf+xml,application/rss+xml,application/x-netcdf,application/xml;q=0.9,text/xml;q=0.2,*/*;q=0.1" + +# List of preferred XML parsers, by SAX driver name. These will be tried first, +# but if they're not installed, Python will keep searching through its own list +# of pre-installed parsers until it finds one that supports everything we need. +PREFERRED_XML_PARSERS = ["drv_libxml2"] + +# If you want feedparser to automatically run HTML markup through HTML Tidy, set +# this to 1. Requires mxTidy +# or utidylib . +TIDY_MARKUP = 0 + +# List of Python interfaces for HTML Tidy, in order of preference. Only useful +# if TIDY_MARKUP = 1 +PREFERRED_TIDY_INTERFACES = ["uTidy", "mxTidy"] + +# ---------- required modules (should come with any Python distribution) ---------- +import sgmllib, re, sys, copy, urlparse, time, rfc822, types, cgi +from cStringIO import StringIO as _StringIO + +# ---------- optional modules (feedparser will work without these, but with reduced functionality) ---------- + +# gzip is included with most Python distributions, but may not be available if you compiled your own +import gzip +import zlib + +# timeoutsocket allows feedparser to time out rather than hang forever on ultra-slow servers. +# Python 2.3 now has this functionality available in the standard socket library, so under +# 2.3 or later you don't need to install anything. In fact, under Python 2.4, timeoutsocket +# write all sorts of crazy errors to stderr while running my unit tests, so it's probably +# outlived its usefulness. +import socket +if hasattr(socket, 'setdefaulttimeout'): + socket.setdefaulttimeout(20) +else: + try: + import timeoutsocket # http://www.timo-tasi.org/python/timeoutsocket.py + timeoutsocket.setDefaultSocketTimeout(20) + except ImportError: + pass +import urllib, urllib2 + +# If a real XML parser is available, feedparser will attempt to use it. feedparser has +# been tested with the built-in SAX parser, PyXML, and libxml2. On platforms where the +# Python distribution does not come with an XML parser (such as Mac OS X 10.2 and some +# versions of FreeBSD), feedparser will quietly fall back on regex-based parsing. +import xml.sax +xml.sax.make_parser(PREFERRED_XML_PARSERS) # test for valid parsers +from xml.sax.saxutils import escape as _xmlescape +_XML_AVAILABLE = 1 + +# base64 support for Atom feeds that contain embedded binary data +import base64, binascii + +# cjkcodecs and iconv_codec provide support for more character encodings. +# Both are available from http://cjkpython.i18n.org/ +try: + import cjkcodecs.aliases + cjkcodecs +except: + pass +try: + import iconv_codec + iconv_codec +except: + pass + +# ---------- don't touch these ---------- +class ThingsNobodyCaresAboutButMe(Exception): pass +class CharacterEncodingOverride(ThingsNobodyCaresAboutButMe): pass +class CharacterEncodingUnknown(ThingsNobodyCaresAboutButMe): pass +class NonXMLContentType(ThingsNobodyCaresAboutButMe): pass +class UndeclaredNamespace(Exception): pass + +sgmllib.tagfind = re.compile('[a-zA-Z][-_.:a-zA-Z0-9]*') +sgmllib.special = re.compile('' % (tag, ''.join([' %s="%s"' % t for t in attrs])), escape=0) + + # match namespaces + if tag.find(':') <> -1: + prefix, suffix = tag.split(':', 1) + else: + prefix, suffix = '', tag + prefix = self.namespacemap.get(prefix, prefix) + if prefix: + prefix = prefix + '_' + + # special hack for better tracking of empty textinput/image elements in illformed feeds + if (not prefix) and tag not in ('title', 'link', 'description', 'name'): + self.intextinput = 0 + if (not prefix) and tag not in ('title', 'link', 'description', 'url', 'href', 'width', 'height'): + self.inimage = 0 + + # call special handler (if defined) or default handler + methodname = '_start_' + prefix + suffix + try: + method = getattr(self, methodname) + return method(attrsD) + except AttributeError: + return self.push(prefix + suffix, 1) + + def unknown_endtag(self, tag): + if _debug: sys.stderr.write('end %s\n' % tag) + # match namespaces + if tag.find(':') <> -1: + prefix, suffix = tag.split(':', 1) + else: + prefix, suffix = '', tag + prefix = self.namespacemap.get(prefix, prefix) + if prefix: + prefix = prefix + '_' + + # call special handler (if defined) or default handler + methodname = '_end_' + prefix + suffix + try: + method = getattr(self, methodname) + method() + except AttributeError: + self.pop(prefix + suffix) + + # track inline content + if self.incontent and self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): + # element declared itself as escaped markup, but it isn't really + self.contentparams['type'] = 'application/xhtml+xml' + if self.incontent and self.contentparams.get('type') == 'application/xhtml+xml': + tag = tag.split(':')[-1] + self.handle_data('' % tag, escape=0) + + # track xml:base and xml:lang going out of scope + if self.basestack: + self.basestack.pop() + if self.basestack and self.basestack[-1]: + self.baseuri = self.basestack[-1] + if self.langstack: + self.langstack.pop() + if self.langstack: # and (self.langstack[-1] is not None): + self.lang = self.langstack[-1] + + def handle_charref(self, ref): + # called for each character reference, e.g. for ' ', ref will be '160' + if not self.elementstack: return + ref = ref.lower() + if ref in ('34', '38', '39', '60', '62', 'x22', 'x26', 'x27', 'x3c', 'x3e'): + text = '&#%s;' % ref + else: + if ref[0] == 'x': + c = int(ref[1:], 16) + else: + c = int(ref) + text = unichr(c).encode('utf-8') + self.elementstack[-1][2].append(text) + + def handle_entityref(self, ref): + # called for each entity reference, e.g. for '©', ref will be 'copy' + if not self.elementstack: return + if _debug: sys.stderr.write('entering handle_entityref with %s\n' % ref) + if ref in ('lt', 'gt', 'quot', 'amp', 'apos'): + text = '&%s;' % ref + else: + # entity resolution graciously donated by Aaron Swartz + def name2cp(k): + import htmlentitydefs + if hasattr(htmlentitydefs, 'name2codepoint'): # requires Python 2.3 + return htmlentitydefs.name2codepoint[k] + k = htmlentitydefs.entitydefs[k] + if k.startswith('&#') and k.endswith(';'): + return int(k[2:-1]) # not in latin-1 + return ord(k) + try: name2cp(ref) + except KeyError: text = '&%s;' % ref + else: text = unichr(name2cp(ref)).encode('utf-8') + self.elementstack[-1][2].append(text) + + def handle_data(self, text, escape=1): + # called for each block of plain text, i.e. outside of any tag and + # not containing any character or entity references + if not self.elementstack: return + if escape and self.contentparams.get('type') == 'application/xhtml+xml': + text = _xmlescape(text) + self.elementstack[-1][2].append(text) + + def handle_comment(self, text): + # called for each comment, e.g. + pass + + def handle_pi(self, text): + # called for each processing instruction, e.g. + pass + + def handle_decl(self, text): + pass + + def parse_declaration(self, i): + # override internal declaration handler to handle CDATA blocks + if _debug: sys.stderr.write('entering parse_declaration\n') + if self.rawdata[i:i+9] == '', i) + if k == -1: k = len(self.rawdata) + self.handle_data(_xmlescape(self.rawdata[i+9:k]), 0) + return k+3 + else: + k = self.rawdata.find('>', i) + return k+1 + + def mapContentType(self, contentType): + contentType = contentType.lower() + if contentType == 'text': + contentType = 'text/plain' + elif contentType == 'html': + contentType = 'text/html' + elif contentType == 'xhtml': + contentType = 'application/xhtml+xml' + return contentType + + def trackNamespace(self, prefix, uri): + loweruri = uri.lower() + if (prefix, loweruri) == (None, 'http://my.netscape.com/rdf/simple/0.9/') and not self.version: + self.version = 'rss090' + if loweruri == 'http://purl.org/rss/1.0/' and not self.version: + self.version = 'rss10' + if loweruri == 'http://www.w3.org/2005/atom' and not self.version: + self.version = 'atom10' + if loweruri.find('backend.userland.com/rss') <> -1: + # match any backend.userland.com namespace + uri = 'http://backend.userland.com/rss' + loweruri = uri + if self._matchnamespaces.has_key(loweruri): + self.namespacemap[prefix] = self._matchnamespaces[loweruri] + self.namespacesInUse[self._matchnamespaces[loweruri]] = uri + else: + self.namespacesInUse[prefix or ''] = uri + + def resolveURI(self, uri): + return _urljoin(self.baseuri or '', uri) + + def decodeEntities(self, element, data): + return data + + def push(self, element, expectingText): + self.elementstack.append([element, expectingText, []]) + + def pop(self, element, stripWhitespace=1): + if not self.elementstack: return + if self.elementstack[-1][0] != element: return + + element, expectingText, pieces = self.elementstack.pop() + output = ''.join(pieces) + if stripWhitespace: + output = output.strip() + if not expectingText: return output + + # decode base64 content + if base64 and self.contentparams.get('base64', 0): + try: + output = base64.decodestring(output) + except binascii.Error: + pass + except binascii.Incomplete: + pass + + # resolve relative URIs + if (element in self.can_be_relative_uri) and output: + output = self.resolveURI(output) + + # decode entities within embedded markup + if not self.contentparams.get('base64', 0): + output = self.decodeEntities(element, output) + + # remove temporary cruft from contentparams + try: + del self.contentparams['mode'] + except KeyError: + pass + try: + del self.contentparams['base64'] + except KeyError: + pass + + # resolve relative URIs within embedded markup + if self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types: + if element in self.can_contain_relative_uris: + output = _resolveRelativeURIs(output, self.baseuri, self.encoding) + + # sanitize embedded markup + if self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types: + if element in self.can_contain_dangerous_markup: + output = _sanitizeHTML(output, self.encoding) + + if self.encoding and type(output) != type(u''): + try: + output = unicode(output, self.encoding) + except: + pass + + # categories/tags/keywords/whatever are handled in _end_category + if element == 'category': + return output + + # store output in appropriate place(s) + if self.inentry and not self.insource: + if element == 'content': + self.entries[-1].setdefault(element, []) + contentparams = copy.deepcopy(self.contentparams) + contentparams['value'] = output + self.entries[-1][element].append(contentparams) + elif element == 'link': + self.entries[-1][element] = output + if output: + self.entries[-1]['links'][-1]['href'] = output + else: + if element == 'description': + element = 'summary' + self.entries[-1][element] = output + if self.incontent: + contentparams = copy.deepcopy(self.contentparams) + contentparams['value'] = output + self.entries[-1][element + '_detail'] = contentparams + elif (self.infeed or self.insource) and (not self.intextinput) and (not self.inimage): + context = self._getContext() + if element == 'description': + element = 'subtitle' + context[element] = output + if element == 'link': + context['links'][-1]['href'] = output + elif self.incontent: + contentparams = copy.deepcopy(self.contentparams) + contentparams['value'] = output + context[element + '_detail'] = contentparams + return output + + def pushContent(self, tag, attrsD, defaultContentType, expectingText): + self.incontent += 1 + self.contentparams = FeedParserDict({ + 'type': self.mapContentType(attrsD.get('type', defaultContentType)), + 'language': self.lang, + 'base': self.baseuri}) + self.contentparams['base64'] = self._isBase64(attrsD, self.contentparams) + self.push(tag, expectingText) + + def popContent(self, tag): + value = self.pop(tag) + self.incontent -= 1 + self.contentparams.clear() + return value + + def _mapToStandardPrefix(self, name): + colonpos = name.find(':') + if colonpos <> -1: + prefix = name[:colonpos] + suffix = name[colonpos+1:] + prefix = self.namespacemap.get(prefix, prefix) + name = prefix + ':' + suffix + return name + + def _getAttribute(self, attrsD, name): + return attrsD.get(self._mapToStandardPrefix(name)) + + def _isBase64(self, attrsD, contentparams): + if attrsD.get('mode', '') == 'base64': + return 1 + if self.contentparams['type'].startswith('text/'): + return 0 + if self.contentparams['type'].endswith('+xml'): + return 0 + if self.contentparams['type'].endswith('/xml'): + return 0 + return 1 + + def _itsAnHrefDamnIt(self, attrsD): + href = attrsD.get('url', attrsD.get('uri', attrsD.get('href', None))) + if href: + try: + del attrsD['url'] + except KeyError: + pass + try: + del attrsD['uri'] + except KeyError: + pass + attrsD['href'] = href + return attrsD + + def _save(self, key, value): + context = self._getContext() + context.setdefault(key, value) + + def _start_rss(self, attrsD): + versionmap = {'0.91': 'rss091u', + '0.92': 'rss092', + '0.93': 'rss093', + '0.94': 'rss094'} + if not self.version: + attr_version = attrsD.get('version', '') + version = versionmap.get(attr_version) + if version: + self.version = version + elif attr_version.startswith('2.'): + self.version = 'rss20' + else: + self.version = 'rss' + + def _start_dlhottitles(self, attrsD): + self.version = 'hotrss' + + def _start_channel(self, attrsD): + self.infeed = 1 + self._cdf_common(attrsD) + _start_feedinfo = _start_channel + + def _cdf_common(self, attrsD): + if attrsD.has_key('lastmod'): + self._start_modified({}) + self.elementstack[-1][-1] = attrsD['lastmod'] + self._end_modified() + if attrsD.has_key('href'): + self._start_link({}) + self.elementstack[-1][-1] = attrsD['href'] + self._end_link() + + def _start_feed(self, attrsD): + self.infeed = 1 + versionmap = {'0.1': 'atom01', + '0.2': 'atom02', + '0.3': 'atom03'} + if not self.version: + attr_version = attrsD.get('version') + version = versionmap.get(attr_version) + if version: + self.version = version + else: + self.version = 'atom' + + def _end_channel(self): + self.infeed = 0 + _end_feed = _end_channel + + def _start_image(self, attrsD): + self.inimage = 1 + self.push('image', 0) + context = self._getContext() + context.setdefault('image', FeedParserDict()) + + def _end_image(self): + self.pop('image') + self.inimage = 0 + + def _start_textinput(self, attrsD): + self.intextinput = 1 + self.push('textinput', 0) + context = self._getContext() + context.setdefault('textinput', FeedParserDict()) + _start_textInput = _start_textinput + + def _end_textinput(self): + self.pop('textinput') + self.intextinput = 0 + _end_textInput = _end_textinput + + def _start_author(self, attrsD): + self.inauthor = 1 + self.push('author', 1) + _start_managingeditor = _start_author + _start_dc_author = _start_author + _start_dc_creator = _start_author + _start_itunes_author = _start_author + + def _end_author(self): + self.pop('author') + self.inauthor = 0 + self._sync_author_detail() + _end_managingeditor = _end_author + _end_dc_author = _end_author + _end_dc_creator = _end_author + _end_itunes_author = _end_author + + def _start_itunes_owner(self, attrsD): + self.inpublisher = 1 + self.push('publisher', 0) + + def _end_itunes_owner(self): + self.pop('publisher') + self.inpublisher = 0 + self._sync_author_detail('publisher') + + def _start_contributor(self, attrsD): + self.incontributor = 1 + context = self._getContext() + context.setdefault('contributors', []) + context['contributors'].append(FeedParserDict()) + self.push('contributor', 0) + + def _end_contributor(self): + self.pop('contributor') + self.incontributor = 0 + + def _start_dc_contributor(self, attrsD): + self.incontributor = 1 + context = self._getContext() + context.setdefault('contributors', []) + context['contributors'].append(FeedParserDict()) + self.push('name', 0) + + def _end_dc_contributor(self): + self._end_name() + self.incontributor = 0 + + def _start_name(self, attrsD): + self.push('name', 0) + _start_itunes_name = _start_name + + def _end_name(self): + value = self.pop('name') + if self.inpublisher: + self._save_author('name', value, 'publisher') + elif self.inauthor: + self._save_author('name', value) + elif self.incontributor: + self._save_contributor('name', value) + elif self.intextinput: + context = self._getContext() + context['textinput']['name'] = value + _end_itunes_name = _end_name + + def _start_width(self, attrsD): + self.push('width', 0) + + def _end_width(self): + value = self.pop('width') + try: + value = int(value) + except: + value = 0 + if self.inimage: + context = self._getContext() + context['image']['width'] = value + + def _start_height(self, attrsD): + self.push('height', 0) + + def _end_height(self): + value = self.pop('height') + try: + value = int(value) + except: + value = 0 + if self.inimage: + context = self._getContext() + context['image']['height'] = value + + def _start_url(self, attrsD): + self.push('href', 1) + _start_homepage = _start_url + _start_uri = _start_url + + def _end_url(self): + value = self.pop('href') + if self.inauthor: + self._save_author('href', value) + elif self.incontributor: + self._save_contributor('href', value) + elif self.inimage: + context = self._getContext() + context['image']['href'] = value + elif self.intextinput: + context = self._getContext() + context['textinput']['link'] = value + _end_homepage = _end_url + _end_uri = _end_url + + def _start_email(self, attrsD): + self.push('email', 0) + _start_itunes_email = _start_email + + def _end_email(self): + value = self.pop('email') + if self.inpublisher: + self._save_author('email', value, 'publisher') + elif self.inauthor: + self._save_author('email', value) + elif self.incontributor: + self._save_contributor('email', value) + _end_itunes_email = _end_email + + def _getContext(self): + if self.insource: + context = self.sourcedata + elif self.inentry: + context = self.entries[-1] + else: + context = self.feeddata + return context + + def _save_author(self, key, value, prefix='author'): + context = self._getContext() + context.setdefault(prefix + '_detail', FeedParserDict()) + context[prefix + '_detail'][key] = value + self._sync_author_detail() + + def _save_contributor(self, key, value): + context = self._getContext() + context.setdefault('contributors', [FeedParserDict()]) + context['contributors'][-1][key] = value + + def _sync_author_detail(self, key='author'): + context = self._getContext() + detail = context.get('%s_detail' % key) + if detail: + name = detail.get('name') + email = detail.get('email') + if name and email: + context[key] = '%s (%s)' % (name, email) + elif name: + context[key] = name + elif email: + context[key] = email + else: + author = context.get(key) + if not author: return + emailmatch = re.search(r'''(([a-zA-Z0-9\_\-\.\+]+)@((\[[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?))''', author) + if not emailmatch: return + email = emailmatch.group(0) + # probably a better way to do the following, but it passes all the tests + author = author.replace(email, '') + author = author.replace('()', '') + author = author.strip() + if author and (author[0] == '('): + author = author[1:] + if author and (author[-1] == ')'): + author = author[:-1] + author = author.strip() + context.setdefault('%s_detail' % key, FeedParserDict()) + context['%s_detail' % key]['name'] = author + context['%s_detail' % key]['email'] = email + + def _start_subtitle(self, attrsD): + self.pushContent('subtitle', attrsD, 'text/plain', 1) + _start_tagline = _start_subtitle + _start_itunes_subtitle = _start_subtitle + + def _end_subtitle(self): + self.popContent('subtitle') + _end_tagline = _end_subtitle + _end_itunes_subtitle = _end_subtitle + + def _start_rights(self, attrsD): + self.pushContent('rights', attrsD, 'text/plain', 1) + _start_dc_rights = _start_rights + _start_copyright = _start_rights + + def _end_rights(self): + self.popContent('rights') + _end_dc_rights = _end_rights + _end_copyright = _end_rights + + def _start_item(self, attrsD): + self.entries.append(FeedParserDict()) + self.push('item', 0) + self.inentry = 1 + self.guidislink = 0 + id = self._getAttribute(attrsD, 'rdf:about') + if id: + context = self._getContext() + context['id'] = id + self._cdf_common(attrsD) + _start_entry = _start_item + _start_product = _start_item + + def _end_item(self): + self.pop('item') + self.inentry = 0 + _end_entry = _end_item + + def _start_dc_language(self, attrsD): + self.push('language', 1) + _start_language = _start_dc_language + + def _end_dc_language(self): + self.lang = self.pop('language') + _end_language = _end_dc_language + + def _start_dc_publisher(self, attrsD): + self.push('publisher', 1) + _start_webmaster = _start_dc_publisher + + def _end_dc_publisher(self): + self.pop('publisher') + self._sync_author_detail('publisher') + _end_webmaster = _end_dc_publisher + + def _start_published(self, attrsD): + self.push('published', 1) + _start_dcterms_issued = _start_published + _start_issued = _start_published + + def _end_published(self): + value = self.pop('published') + self._save('published_parsed', _parse_date(value)) + _end_dcterms_issued = _end_published + _end_issued = _end_published + + def _start_updated(self, attrsD): + self.push('updated', 1) + _start_modified = _start_updated + _start_dcterms_modified = _start_updated + _start_pubdate = _start_updated + _start_dc_date = _start_updated + + def _end_updated(self): + value = self.pop('updated') + parsed_value = _parse_date(value) + self._save('updated_parsed', parsed_value) + _end_modified = _end_updated + _end_dcterms_modified = _end_updated + _end_pubdate = _end_updated + _end_dc_date = _end_updated + + def _start_created(self, attrsD): + self.push('created', 1) + _start_dcterms_created = _start_created + + def _end_created(self): + value = self.pop('created') + self._save('created_parsed', _parse_date(value)) + _end_dcterms_created = _end_created + + def _start_expirationdate(self, attrsD): + self.push('expired', 1) + + def _end_expirationdate(self): + self._save('expired_parsed', _parse_date(self.pop('expired'))) + + def _start_cc_license(self, attrsD): + self.push('license', 1) + value = self._getAttribute(attrsD, 'rdf:resource') + if value: + self.elementstack[-1][2].append(value) + self.pop('license') + + def _start_creativecommons_license(self, attrsD): + self.push('license', 1) + + def _end_creativecommons_license(self): + self.pop('license') + + def _addTag(self, term, scheme, label): + context = self._getContext() + tags = context.setdefault('tags', []) + if (not term) and (not scheme) and (not label): return + value = FeedParserDict({'term': term, 'scheme': scheme, 'label': label}) + if value not in tags: + tags.append(FeedParserDict({'term': term, 'scheme': scheme, 'label': label})) + + def _start_category(self, attrsD): + if _debug: sys.stderr.write('entering _start_category with %s\n' % repr(attrsD)) + term = attrsD.get('term') + scheme = attrsD.get('scheme', attrsD.get('domain')) + label = attrsD.get('label') + self._addTag(term, scheme, label) + self.push('category', 1) + _start_dc_subject = _start_category + _start_keywords = _start_category + + def _end_itunes_keywords(self): + for term in self.pop('itunes_keywords').split(): + self._addTag(term, 'http://www.itunes.com/', None) + + def _start_itunes_category(self, attrsD): + self._addTag(attrsD.get('text'), 'http://www.itunes.com/', None) + self.push('category', 1) + + def _end_category(self): + value = self.pop('category') + if not value: return + context = self._getContext() + tags = context['tags'] + if value and len(tags) and not tags[-1]['term']: + tags[-1]['term'] = value + else: + self._addTag(value, None, None) + _end_dc_subject = _end_category + _end_keywords = _end_category + _end_itunes_category = _end_category + + def _start_cloud(self, attrsD): + self._getContext()['cloud'] = FeedParserDict(attrsD) + + def _start_link(self, attrsD): + attrsD.setdefault('rel', 'alternate') + attrsD.setdefault('type', 'text/html') + attrsD = self._itsAnHrefDamnIt(attrsD) + if attrsD.has_key('href'): + attrsD['href'] = self.resolveURI(attrsD['href']) + expectingText = self.infeed or self.inentry or self.insource + context = self._getContext() + context.setdefault('links', []) + context['links'].append(FeedParserDict(attrsD)) + if attrsD['rel'] == 'enclosure': + self._start_enclosure(attrsD) + if attrsD.has_key('href'): + expectingText = 0 + if (attrsD.get('rel') == 'alternate') and (self.mapContentType(attrsD.get('type')) in self.html_types): + context['link'] = attrsD['href'] + else: + self.push('link', expectingText) + _start_producturl = _start_link + + def _end_link(self): + value = self.pop('link') + context = self._getContext() + if self.intextinput: + context['textinput']['link'] = value + if self.inimage: + context['image']['link'] = value + _end_producturl = _end_link + + def _start_guid(self, attrsD): + self.guidislink = (attrsD.get('ispermalink', 'true') == 'true') + self.push('id', 1) + + def _end_guid(self): + value = self.pop('id') + self._save('guidislink', self.guidislink and not self._getContext().has_key('link')) + if self.guidislink: + # guid acts as link, but only if 'ispermalink' is not present or is 'true', + # and only if the item doesn't already have a link element + self._save('link', value) + + def _start_title(self, attrsD): + self.pushContent('title', attrsD, 'text/plain', self.infeed or self.inentry or self.insource) + _start_dc_title = _start_title + _start_media_title = _start_title + + def _end_title(self): + value = self.popContent('title') + context = self._getContext() + if self.intextinput: + context['textinput']['title'] = value + elif self.inimage: + context['image']['title'] = value + _end_dc_title = _end_title + _end_media_title = _end_title + + def _start_description(self, attrsD): + context = self._getContext() + if context.has_key('summary'): + self._summaryKey = 'content' + self._start_content(attrsD) + else: + self.pushContent('description', attrsD, 'text/html', self.infeed or self.inentry or self.insource) + + def _start_abstract(self, attrsD): + self.pushContent('description', attrsD, 'text/plain', self.infeed or self.inentry or self.insource) + + def _end_description(self): + if self._summaryKey == 'content': + self._end_content() + else: + value = self.popContent('description') + context = self._getContext() + if self.intextinput: + context['textinput']['description'] = value + elif self.inimage: + context['image']['description'] = value + self._summaryKey = None + _end_abstract = _end_description + + def _start_info(self, attrsD): + self.pushContent('info', attrsD, 'text/plain', 1) + _start_feedburner_browserfriendly = _start_info + + def _end_info(self): + self.popContent('info') + _end_feedburner_browserfriendly = _end_info + + def _start_generator(self, attrsD): + if attrsD: + attrsD = self._itsAnHrefDamnIt(attrsD) + if attrsD.has_key('href'): + attrsD['href'] = self.resolveURI(attrsD['href']) + self._getContext()['generator_detail'] = FeedParserDict(attrsD) + self.push('generator', 1) + + def _end_generator(self): + value = self.pop('generator') + context = self._getContext() + if context.has_key('generator_detail'): + context['generator_detail']['name'] = value + + def _start_admin_generatoragent(self, attrsD): + self.push('generator', 1) + value = self._getAttribute(attrsD, 'rdf:resource') + if value: + self.elementstack[-1][2].append(value) + self.pop('generator') + self._getContext()['generator_detail'] = FeedParserDict({'href': value}) + + def _start_admin_errorreportsto(self, attrsD): + self.push('errorreportsto', 1) + value = self._getAttribute(attrsD, 'rdf:resource') + if value: + self.elementstack[-1][2].append(value) + self.pop('errorreportsto') + + def _start_summary(self, attrsD): + context = self._getContext() + if context.has_key('summary'): + self._summaryKey = 'content' + self._start_content(attrsD) + else: + self._summaryKey = 'summary' + self.pushContent(self._summaryKey, attrsD, 'text/plain', 1) + _start_itunes_summary = _start_summary + + def _end_summary(self): + if self._summaryKey == 'content': + self._end_content() + else: + self.popContent(self._summaryKey or 'summary') + self._summaryKey = None + _end_itunes_summary = _end_summary + + def _start_enclosure(self, attrsD): + attrsD = self._itsAnHrefDamnIt(attrsD) + self._getContext().setdefault('enclosures', []).append(FeedParserDict(attrsD)) + href = attrsD.get('href') + if href: + context = self._getContext() + if not context.get('id'): + context['id'] = href + + def _start_source(self, attrsD): + self.insource = 1 + + def _end_source(self): + self.insource = 0 + self._getContext()['source'] = copy.deepcopy(self.sourcedata) + self.sourcedata.clear() + + def _start_content(self, attrsD): + self.pushContent('content', attrsD, 'text/plain', 1) + src = attrsD.get('src') + if src: + self.contentparams['src'] = src + self.push('content', 1) + + def _start_prodlink(self, attrsD): + self.pushContent('content', attrsD, 'text/html', 1) + + def _start_body(self, attrsD): + self.pushContent('content', attrsD, 'application/xhtml+xml', 1) + _start_xhtml_body = _start_body + + def _start_content_encoded(self, attrsD): + self.pushContent('content', attrsD, 'text/html', 1) + _start_fullitem = _start_content_encoded + + def _end_content(self): + copyToDescription = self.mapContentType(self.contentparams.get('type')) in (['text/plain'] + self.html_types) + value = self.popContent('content') + if copyToDescription: + self._save('description', value) + _end_body = _end_content + _end_xhtml_body = _end_content + _end_content_encoded = _end_content + _end_fullitem = _end_content + _end_prodlink = _end_content + + def _start_itunes_image(self, attrsD): + self.push('itunes_image', 0) + self._getContext()['image'] = FeedParserDict({'href': attrsD.get('href')}) + _start_itunes_link = _start_itunes_image + + def _end_itunes_block(self): + value = self.pop('itunes_block', 0) + self._getContext()['itunes_block'] = (value == 'yes') and 1 or 0 + + def _end_itunes_explicit(self): + value = self.pop('itunes_explicit', 0) + self._getContext()['itunes_explicit'] = (value == 'yes') and 1 or 0 + +if _XML_AVAILABLE: + class _StrictFeedParser(_FeedParserMixin, xml.sax.handler.ContentHandler): + def __init__(self, baseuri, baselang, encoding): + if _debug: sys.stderr.write('trying StrictFeedParser\n') + xml.sax.handler.ContentHandler.__init__(self) + _FeedParserMixin.__init__(self, baseuri, baselang, encoding) + self.bozo = 0 + self.exc = None + + def startPrefixMapping(self, prefix, uri): + self.trackNamespace(prefix, uri) + + def startElementNS(self, name, qname, attrs): + namespace, localname = name + lowernamespace = str(namespace or '').lower() + if lowernamespace.find('backend.userland.com/rss') <> -1: + # match any backend.userland.com namespace + namespace = 'http://backend.userland.com/rss' + lowernamespace = namespace + if qname and qname.find(':') > 0: + givenprefix = qname.split(':')[0] + else: + givenprefix = None + prefix = self._matchnamespaces.get(lowernamespace, givenprefix) + if givenprefix and (prefix == None or (prefix == '' and lowernamespace == '')) and not self.namespacesInUse.has_key(givenprefix): + raise UndeclaredNamespace, "'%s' is not associated with a namespace" % givenprefix + if prefix: + localname = prefix + ':' + localname + localname = str(localname).lower() + if _debug: sys.stderr.write('startElementNS: qname = %s, namespace = %s, givenprefix = %s, prefix = %s, attrs = %s, localname = %s\n' % (qname, namespace, givenprefix, prefix, attrs.items(), localname)) + + # qname implementation is horribly broken in Python 2.1 (it + # doesn't report any), and slightly broken in Python 2.2 (it + # doesn't report the xml: namespace). So we match up namespaces + # with a known list first, and then possibly override them with + # the qnames the SAX parser gives us (if indeed it gives us any + # at all). Thanks to MatejC for helping me test this and + # tirelessly telling me that it didn't work yet. + attrsD = {} + for (namespace, attrlocalname), attrvalue in attrs._attrs.items(): + lowernamespace = (namespace or '').lower() + prefix = self._matchnamespaces.get(lowernamespace, '') + if prefix: + attrlocalname = prefix + ':' + attrlocalname + attrsD[str(attrlocalname).lower()] = attrvalue + for qname in attrs.getQNames(): + attrsD[str(qname).lower()] = attrs.getValueByQName(qname) + self.unknown_starttag(localname, attrsD.items()) + + def characters(self, text): + self.handle_data(text) + + def endElementNS(self, name, qname): + namespace, localname = name + lowernamespace = str(namespace or '').lower() + if qname and qname.find(':') > 0: + givenprefix = qname.split(':')[0] + else: + givenprefix = '' + prefix = self._matchnamespaces.get(lowernamespace, givenprefix) + if prefix: + localname = prefix + ':' + localname + localname = str(localname).lower() + self.unknown_endtag(localname) + + def error(self, exc): + self.bozo = 1 + self.exc = exc + + def fatalError(self, exc): + self.error(exc) + raise exc + +class _BaseHTMLProcessor(sgmllib.SGMLParser): + elements_no_end_tag = ['area', 'base', 'basefont', 'br', 'col', 'frame', 'hr', + 'img', 'input', 'isindex', 'link', 'meta', 'param'] + + def __init__(self, encoding): + self.encoding = encoding + if _debug: sys.stderr.write('entering BaseHTMLProcessor, encoding=%s\n' % self.encoding) + sgmllib.SGMLParser.__init__(self) + + def reset(self): + self.pieces = [] + sgmllib.SGMLParser.reset(self) + + def _shorttag_replace(self, match): + tag = match.group(1) + if tag in self.elements_no_end_tag: + return '<' + tag + ' />' + else: + return '<' + tag + '>' + + def feed(self, data): + data = re.compile(r'', self._shorttag_replace, data) + data = data.replace(''', "'") + data = data.replace('"', '"') + if self.encoding and type(data) == type(u''): + data = data.encode(self.encoding) + sgmllib.SGMLParser.feed(self, data) + + def normalize_attrs(self, attrs): + # utility method to be called by descendants + attrs = [(k.lower(), v) for k, v in attrs] + attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs] + return attrs + + def unknown_starttag(self, tag, attrs): + # called for each start tag + # attrs is a list of (attr, value) tuples + # e.g. for
, tag='pre', attrs=[('class', 'screen')]
+        if _debug: sys.stderr.write('_BaseHTMLProcessor, unknown_starttag, tag=%s\n' % tag)
+        uattrs = []
+        # thanks to Kevin Marks for this breathtaking hack to deal with (valid) high-bit attribute values in UTF-8 feeds
+        for key, value in attrs:
+            if type(value) != type(u''):
+                value = unicode(value, self.encoding)
+            uattrs.append((unicode(key, self.encoding), value))
+        strattrs = u''.join([u' %s="%s"' % (key, value) for key, value in uattrs]).encode(self.encoding)
+        strattrs
+        if tag in self.elements_no_end_tag:
+            self.pieces.append('<%(tag)s%(strattrs)s />' % locals())
+        else:
+            self.pieces.append('<%(tag)s%(strattrs)s>' % locals())
+
+    def unknown_endtag(self, tag):
+        # called for each end tag, e.g. for 
, tag will be 'pre' + # Reconstruct the original end tag. + if tag not in self.elements_no_end_tag: + self.pieces.append("" % locals()) + + def handle_charref(self, ref): + # called for each character reference, e.g. for ' ', ref will be '160' + # Reconstruct the original character reference. + self.pieces.append('&#%(ref)s;' % locals()) + + def handle_entityref(self, ref): + # called for each entity reference, e.g. for '©', ref will be 'copy' + # Reconstruct the original entity reference. + self.pieces.append('&%(ref)s;' % locals()) + + def handle_data(self, text): + # called for each block of plain text, i.e. outside of any tag and + # not containing any character or entity references + # Store the original text verbatim. + if _debug: sys.stderr.write('_BaseHTMLProcessor, handle_text, text=%s\n' % text) + self.pieces.append(text) + + def handle_comment(self, text): + # called for each HTML comment, e.g. + # Reconstruct the original comment. + self.pieces.append('' % locals()) + + def handle_pi(self, text): + # called for each processing instruction, e.g. + # Reconstruct original processing instruction. + self.pieces.append('' % locals()) + + def handle_decl(self, text): + # called for the DOCTYPE, if present, e.g. + # + # Reconstruct original DOCTYPE + self.pieces.append('' % locals()) + + _new_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9:]*\s*').match + def _scan_name(self, i, declstartpos): + rawdata = self.rawdata + n = len(rawdata) + if i == n: + return None, -1 + m = self._new_declname_match(rawdata, i) + if m: + s = m.group() + name = s.strip() + if (i + len(s)) == n: + return None, -1 # end of buffer + return name.lower(), m.end() + else: + self.handle_data(rawdata) +# self.updatepos(declstartpos, i) + return None, -1 + + def output(self): + '''Return processed HTML as a single string''' + return ''.join([str(p) for p in self.pieces]) + +class _LooseFeedParser(_FeedParserMixin, _BaseHTMLProcessor): + def __init__(self, baseuri, baselang, encoding): + sgmllib.SGMLParser.__init__(self) + _FeedParserMixin.__init__(self, baseuri, baselang, encoding) + + def decodeEntities(self, element, data): + data = data.replace('<', '<') + data = data.replace('<', '<') + data = data.replace('>', '>') + data = data.replace('>', '>') + data = data.replace('&', '&') + data = data.replace('&', '&') + data = data.replace('"', '"') + data = data.replace('"', '"') + data = data.replace(''', ''') + data = data.replace(''', ''') + if self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): + data = data.replace('<', '<') + data = data.replace('>', '>') + data = data.replace('&', '&') + data = data.replace('"', '"') + data = data.replace(''', "'") + return data + +class _RelativeURIResolver(_BaseHTMLProcessor): + relative_uris = [('a', 'href'), + ('applet', 'codebase'), + ('area', 'href'), + ('blockquote', 'cite'), + ('body', 'background'), + ('del', 'cite'), + ('form', 'action'), + ('frame', 'longdesc'), + ('frame', 'src'), + ('iframe', 'longdesc'), + ('iframe', 'src'), + ('head', 'profile'), + ('img', 'longdesc'), + ('img', 'src'), + ('img', 'usemap'), + ('input', 'src'), + ('input', 'usemap'), + ('ins', 'cite'), + ('link', 'href'), + ('object', 'classid'), + ('object', 'codebase'), + ('object', 'data'), + ('object', 'usemap'), + ('q', 'cite'), + ('script', 'src')] + + def __init__(self, baseuri, encoding): + _BaseHTMLProcessor.__init__(self, encoding) + self.baseuri = baseuri + + def resolveURI(self, uri): + return _urljoin(self.baseuri, uri) + + def unknown_starttag(self, tag, attrs): + attrs = self.normalize_attrs(attrs) + attrs = [(key, ((tag, key) in self.relative_uris) and self.resolveURI(value) or value) for key, value in attrs] + _BaseHTMLProcessor.unknown_starttag(self, tag, attrs) + +def _resolveRelativeURIs(htmlSource, baseURI, encoding): + if _debug: sys.stderr.write('entering _resolveRelativeURIs\n') + p = _RelativeURIResolver(baseURI, encoding) + p.feed(htmlSource) + return p.output() + +class _HTMLSanitizer(_BaseHTMLProcessor): + acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area', 'b', 'big', + 'blockquote', 'br', 'button', 'caption', 'center', 'cite', 'code', 'col', + 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'fieldset', + 'font', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', + 'ins', 'kbd', 'label', 'legend', 'li', 'map', 'menu', 'ol', 'optgroup', + 'option', 'p', 'pre', 'q', 's', 'samp', 'select', 'small', 'span', 'strike', + 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'tfoot', 'th', + 'thead', 'tr', 'tt', 'u', 'ul', 'var'] + + acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey', + 'action', 'align', 'alt', 'axis', 'border', 'cellpadding', 'cellspacing', + 'char', 'charoff', 'charset', 'checked', 'cite', 'class', 'clear', 'cols', + 'colspan', 'color', 'compact', 'coords', 'datetime', 'dir', 'disabled', + 'enctype', 'for', 'frame', 'headers', 'height', 'href', 'hreflang', 'hspace', + 'id', 'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'media', 'method', + 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly', + 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape', 'size', + 'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title', 'type', + 'usemap', 'valign', 'value', 'vspace', 'width'] + + unacceptable_elements_with_end_tag = ['script', 'applet'] + + def reset(self): + _BaseHTMLProcessor.reset(self) + self.unacceptablestack = 0 + + def unknown_starttag(self, tag, attrs): + if not tag in self.acceptable_elements: + if tag in self.unacceptable_elements_with_end_tag: + self.unacceptablestack += 1 + return + attrs = self.normalize_attrs(attrs) + attrs = [(key, value) for key, value in attrs if key in self.acceptable_attributes] + _BaseHTMLProcessor.unknown_starttag(self, tag, attrs) + + def unknown_endtag(self, tag): + if not tag in self.acceptable_elements: + if tag in self.unacceptable_elements_with_end_tag: + self.unacceptablestack -= 1 + return + _BaseHTMLProcessor.unknown_endtag(self, tag) + + def handle_pi(self, text): + pass + + def handle_decl(self, text): + pass + + def handle_data(self, text): + if not self.unacceptablestack: + _BaseHTMLProcessor.handle_data(self, text) + +def _sanitizeHTML(htmlSource, encoding): + p = _HTMLSanitizer(encoding) + p.feed(htmlSource) + data = p.output() + if TIDY_MARKUP: + # loop through list of preferred Tidy interfaces looking for one that's installed, + # then set up a common _tidy function to wrap the interface-specific API. + _tidy = None + for tidy_interface in PREFERRED_TIDY_INTERFACES: + try: + if tidy_interface == "uTidy": + from tidy import parseString as _utidy + def _tidy(data, **kwargs): + return str(_utidy(data, **kwargs)) + break + except: + pass + if _tidy: + utf8 = type(data) == type(u'') + if utf8: + data = data.encode('utf-8') + data = _tidy(data, output_xhtml=1, numeric_entities=1, wrap=0, char_encoding="utf8") + if utf8: + data = unicode(data, 'utf-8') + if data.count(''): + data = data.split('>', 1)[1] + if data.count('= '2.3.3' + assert base64 != None + user, passw = base64.decodestring(req.headers['Authorization'].split(' ')[1]).split(':') + realm = re.findall('realm="([^"]*)"', headers['WWW-Authenticate'])[0] + self.add_password(realm, host, user, passw) + retry = self.http_error_auth_reqed('www-authenticate', host, req, headers) + self.reset_retry_count() + return retry + except: + return self.http_error_default(req, fp, code, msg, headers) + +def _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers): + """URL, filename, or string --> stream + + This function lets you define parsers that take any input source + (URL, pathname to local or network file, or actual data as a string) + and deal with it in a uniform manner. Returned object is guaranteed + to have all the basic stdio read methods (read, readline, readlines). + Just .close() the object when you're done with it. + + If the etag argument is supplied, it will be used as the value of an + If-None-Match request header. + + If the modified argument is supplied, it must be a tuple of 9 integers + as returned by gmtime() in the standard Python time module. This MUST + be in GMT (Greenwich Mean Time). The formatted date/time will be used + as the value of an If-Modified-Since request header. + + If the agent argument is supplied, it will be used as the value of a + User-Agent request header. + + If the referrer argument is supplied, it will be used as the value of a + Referer[sic] request header. + + If handlers is supplied, it is a list of handlers used to build a + urllib2 opener. + """ + + if hasattr(url_file_stream_or_string, 'read'): + return url_file_stream_or_string + + if url_file_stream_or_string == '-': + return sys.stdin + + if urlparse.urlparse(url_file_stream_or_string)[0] in ('http', 'https', 'ftp'): + if not agent: + agent = USER_AGENT + # test for inline user:password for basic auth + auth = None + if base64: + urltype, rest = urllib.splittype(url_file_stream_or_string) + realhost, rest = urllib.splithost(rest) + if realhost: + user_passwd, realhost = urllib.splituser(realhost) + if user_passwd: + url_file_stream_or_string = '%s://%s%s' % (urltype, realhost, rest) + auth = base64.encodestring(user_passwd).strip() + # try to open with urllib2 (to use optional headers) + request = urllib2.Request(url_file_stream_or_string) + request.add_header('User-Agent', agent) + if etag: + request.add_header('If-None-Match', etag) + if modified: + # format into an RFC 1123-compliant timestamp. We can't use + # time.strftime() since the %a and %b directives can be affected + # by the current locale, but RFC 2616 states that dates must be + # in English. + short_weekdays = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] + months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] + request.add_header('If-Modified-Since', '%s, %02d %s %04d %02d:%02d:%02d GMT' % (short_weekdays[modified[6]], modified[2], months[modified[1] - 1], modified[0], modified[3], modified[4], modified[5])) + if referrer: + request.add_header('Referer', referrer) + if gzip and zlib: + request.add_header('Accept-encoding', 'gzip, deflate') + elif gzip: + request.add_header('Accept-encoding', 'gzip') + elif zlib: + request.add_header('Accept-encoding', 'deflate') + else: + request.add_header('Accept-encoding', '') + if auth: + request.add_header('Authorization', 'Basic %s' % auth) + if ACCEPT_HEADER: + request.add_header('Accept', ACCEPT_HEADER) + request.add_header('A-IM', 'feed') # RFC 3229 support + opener = apply(urllib2.build_opener, tuple([_FeedURLHandler()] + handlers)) + opener.addheaders = [] # RMK - must clear so we only send our custom User-Agent + try: + return opener.open(request) + finally: + opener.close() # JohnD + + # try to open with native open function (if url_file_stream_or_string is a filename) + try: + return open(url_file_stream_or_string) + except: + pass + + # treat url_file_stream_or_string as string + return _StringIO(str(url_file_stream_or_string)) + +_date_handlers = [] +def registerDateHandler(func): + '''Register a date handler function (takes string, returns 9-tuple date in GMT)''' + _date_handlers.insert(0, func) + +# ISO-8601 date parsing routines written by Fazal Majid. +# The ISO 8601 standard is very convoluted and irregular - a full ISO 8601 +# parser is beyond the scope of feedparser and would be a worthwhile addition +# to the Python library. +# A single regular expression cannot parse ISO 8601 date formats into groups +# as the standard is highly irregular (for instance is 030104 2003-01-04 or +# 0301-04-01), so we use templates instead. +# Please note the order in templates is significant because we need a +# greedy match. +_iso8601_tmpl = ['YYYY-?MM-?DD', 'YYYY-MM', 'YYYY-?OOO', + 'YY-?MM-?DD', 'YY-?OOO', 'YYYY', + '-YY-?MM', '-OOO', '-YY', + '--MM-?DD', '--MM', + '---DD', + 'CC', ''] +_iso8601_re = [ + tmpl.replace( + 'YYYY', r'(?P\d{4})').replace( + 'YY', r'(?P\d\d)').replace( + 'MM', r'(?P[01]\d)').replace( + 'DD', r'(?P[0123]\d)').replace( + 'OOO', r'(?P[0123]\d\d)').replace( + 'CC', r'(?P\d\d$)') + + r'(T?(?P\d{2}):(?P\d{2})' + + r'(:(?P\d{2}))?' + + r'(?P[+-](?P\d{2})(:(?P\d{2}))?|Z)?)?' + for tmpl in _iso8601_tmpl] +del tmpl +_iso8601_matches = [re.compile(regex).match for regex in _iso8601_re] +del regex +def _parse_date_iso8601(dateString): + '''Parse a variety of ISO-8601-compatible formats like 20040105''' + m = None + for _iso8601_match in _iso8601_matches: + m = _iso8601_match(dateString) + if m: break + if not m: return + if m.span() == (0, 0): return + params = m.groupdict() + ordinal = params.get('ordinal', 0) + if ordinal: + ordinal = int(ordinal) + else: + ordinal = 0 + year = params.get('year', '--') + if not year or year == '--': + year = time.gmtime()[0] + elif len(year) == 2: + # ISO 8601 assumes current century, i.e. 93 -> 2093, NOT 1993 + year = 100 * int(time.gmtime()[0] / 100) + int(year) + else: + year = int(year) + month = params.get('month', '-') + if not month or month == '-': + # ordinals are NOT normalized by mktime, we simulate them + # by setting month=1, day=ordinal + if ordinal: + month = 1 + else: + month = time.gmtime()[1] + month = int(month) + day = params.get('day', 0) + if not day: + # see above + if ordinal: + day = ordinal + elif params.get('century', 0) or \ + params.get('year', 0) or params.get('month', 0): + day = 1 + else: + day = time.gmtime()[2] + else: + day = int(day) + # special case of the century - is the first year of the 21st century + # 2000 or 2001 ? The debate goes on... + if 'century' in params.keys(): + year = (int(params['century']) - 1) * 100 + 1 + # in ISO 8601 most fields are optional + for field in ['hour', 'minute', 'second', 'tzhour', 'tzmin']: + if not params.get(field, None): + params[field] = 0 + hour = int(params.get('hour', 0)) + minute = int(params.get('minute', 0)) + second = int(params.get('second', 0)) + # weekday is normalized by mktime(), we can ignore it + weekday = 0 + # daylight savings is complex, but not needed for feedparser's purposes + # as time zones, if specified, include mention of whether it is active + # (e.g. PST vs. PDT, CET). Using -1 is implementation-dependent and + # and most implementations have DST bugs + daylight_savings_flag = 0 + tm = [year, month, day, hour, minute, second, weekday, + ordinal, daylight_savings_flag] + # ISO 8601 time zone adjustments + tz = params.get('tz') + if tz and tz != 'Z': + if tz[0] == '-': + tm[3] += int(params.get('tzhour', 0)) + tm[4] += int(params.get('tzmin', 0)) + elif tz[0] == '+': + tm[3] -= int(params.get('tzhour', 0)) + tm[4] -= int(params.get('tzmin', 0)) + else: + return None + # Python's time.mktime() is a wrapper around the ANSI C mktime(3c) + # which is guaranteed to normalize d/m/y/h/m/s. + # Many implementations have bugs, but we'll pretend they don't. + return time.localtime(time.mktime(tm)) +registerDateHandler(_parse_date_iso8601) + +# 8-bit date handling routines written by ytrewq1. +_korean_year = u'\ub144' # b3e2 in euc-kr +_korean_month = u'\uc6d4' # bff9 in euc-kr +_korean_day = u'\uc77c' # c0cf in euc-kr +_korean_am = u'\uc624\uc804' # bfc0 c0fc in euc-kr +_korean_pm = u'\uc624\ud6c4' # bfc0 c8c4 in euc-kr + +_korean_onblog_date_re = \ + re.compile('(\d{4})%s\s+(\d{2})%s\s+(\d{2})%s\s+(\d{2}):(\d{2}):(\d{2})' % \ + (_korean_year, _korean_month, _korean_day)) +_korean_nate_date_re = \ + re.compile(u'(\d{4})-(\d{2})-(\d{2})\s+(%s|%s)\s+(\d{,2}):(\d{,2}):(\d{,2})' % \ + (_korean_am, _korean_pm)) +def _parse_date_onblog(dateString): + '''Parse a string according to the OnBlog 8-bit date format''' + m = _korean_onblog_date_re.match(dateString) + if not m: return + w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ + {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ + 'hour': m.group(4), 'minute': m.group(5), 'second': m.group(6),\ + 'zonediff': '+09:00'} + if _debug: sys.stderr.write('OnBlog date parsed as: %s\n' % w3dtfdate) + return _parse_date_w3dtf(w3dtfdate) +registerDateHandler(_parse_date_onblog) + +def _parse_date_nate(dateString): + '''Parse a string according to the Nate 8-bit date format''' + m = _korean_nate_date_re.match(dateString) + if not m: return + hour = int(m.group(5)) + ampm = m.group(4) + if (ampm == _korean_pm): + hour += 12 + hour = str(hour) + if len(hour) == 1: + hour = '0' + hour + w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ + {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ + 'hour': hour, 'minute': m.group(6), 'second': m.group(7),\ + 'zonediff': '+09:00'} + if _debug: sys.stderr.write('Nate date parsed as: %s\n' % w3dtfdate) + return _parse_date_w3dtf(w3dtfdate) +registerDateHandler(_parse_date_nate) + +_mssql_date_re = \ + re.compile('(\d{4})-(\d{2})-(\d{2})\s+(\d{2}):(\d{2}):(\d{2})(\.\d+)?') +def _parse_date_mssql(dateString): + '''Parse a string according to the MS SQL date format''' + m = _mssql_date_re.match(dateString) + if not m: return + w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ + {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ + 'hour': m.group(4), 'minute': m.group(5), 'second': m.group(6),\ + 'zonediff': '+09:00'} + if _debug: sys.stderr.write('MS SQL date parsed as: %s\n' % w3dtfdate) + return _parse_date_w3dtf(w3dtfdate) +registerDateHandler(_parse_date_mssql) + +# Unicode strings for Greek date strings +_greek_months = \ + { \ + u'\u0399\u03b1\u03bd': u'Jan', # c9e1ed in iso-8859-7 + u'\u03a6\u03b5\u03b2': u'Feb', # d6e5e2 in iso-8859-7 + u'\u039c\u03ac\u03ce': u'Mar', # ccdcfe in iso-8859-7 + u'\u039c\u03b1\u03ce': u'Mar', # cce1fe in iso-8859-7 + u'\u0391\u03c0\u03c1': u'Apr', # c1f0f1 in iso-8859-7 + u'\u039c\u03ac\u03b9': u'May', # ccdce9 in iso-8859-7 + u'\u039c\u03b1\u03ca': u'May', # cce1fa in iso-8859-7 + u'\u039c\u03b1\u03b9': u'May', # cce1e9 in iso-8859-7 + u'\u0399\u03bf\u03cd\u03bd': u'Jun', # c9effded in iso-8859-7 + u'\u0399\u03bf\u03bd': u'Jun', # c9efed in iso-8859-7 + u'\u0399\u03bf\u03cd\u03bb': u'Jul', # c9effdeb in iso-8859-7 + u'\u0399\u03bf\u03bb': u'Jul', # c9f9eb in iso-8859-7 + u'\u0391\u03cd\u03b3': u'Aug', # c1fde3 in iso-8859-7 + u'\u0391\u03c5\u03b3': u'Aug', # c1f5e3 in iso-8859-7 + u'\u03a3\u03b5\u03c0': u'Sep', # d3e5f0 in iso-8859-7 + u'\u039f\u03ba\u03c4': u'Oct', # cfeaf4 in iso-8859-7 + u'\u039d\u03bf\u03ad': u'Nov', # cdefdd in iso-8859-7 + u'\u039d\u03bf\u03b5': u'Nov', # cdefe5 in iso-8859-7 + u'\u0394\u03b5\u03ba': u'Dec', # c4e5ea in iso-8859-7 + } + +_greek_wdays = \ + { \ + u'\u039a\u03c5\u03c1': u'Sun', # caf5f1 in iso-8859-7 + u'\u0394\u03b5\u03c5': u'Mon', # c4e5f5 in iso-8859-7 + u'\u03a4\u03c1\u03b9': u'Tue', # d4f1e9 in iso-8859-7 + u'\u03a4\u03b5\u03c4': u'Wed', # d4e5f4 in iso-8859-7 + u'\u03a0\u03b5\u03bc': u'Thu', # d0e5ec in iso-8859-7 + u'\u03a0\u03b1\u03c1': u'Fri', # d0e1f1 in iso-8859-7 + u'\u03a3\u03b1\u03b2': u'Sat', # d3e1e2 in iso-8859-7 + } + +_greek_date_format_re = \ + re.compile(u'([^,]+),\s+(\d{2})\s+([^\s]+)\s+(\d{4})\s+(\d{2}):(\d{2}):(\d{2})\s+([^\s]+)') + +def _parse_date_greek(dateString): + '''Parse a string according to a Greek 8-bit date format.''' + m = _greek_date_format_re.match(dateString) + if not m: return + try: + wday = _greek_wdays[m.group(1)] + month = _greek_months[m.group(3)] + except: + return + rfc822date = '%(wday)s, %(day)s %(month)s %(year)s %(hour)s:%(minute)s:%(second)s %(zonediff)s' % \ + {'wday': wday, 'day': m.group(2), 'month': month, 'year': m.group(4),\ + 'hour': m.group(5), 'minute': m.group(6), 'second': m.group(7),\ + 'zonediff': m.group(8)} + if _debug: sys.stderr.write('Greek date parsed as: %s\n' % rfc822date) + return _parse_date_rfc822(rfc822date) +registerDateHandler(_parse_date_greek) + +# Unicode strings for Hungarian date strings +_hungarian_months = \ + { \ + u'janu\u00e1r': u'01', # e1 in iso-8859-2 + u'febru\u00e1ri': u'02', # e1 in iso-8859-2 + u'm\u00e1rcius': u'03', # e1 in iso-8859-2 + u'\u00e1prilis': u'04', # e1 in iso-8859-2 + u'm\u00e1ujus': u'05', # e1 in iso-8859-2 + u'j\u00fanius': u'06', # fa in iso-8859-2 + u'j\u00falius': u'07', # fa in iso-8859-2 + u'augusztus': u'08', + u'szeptember': u'09', + u'okt\u00f3ber': u'10', # f3 in iso-8859-2 + u'november': u'11', + u'december': u'12', + } + +_hungarian_date_format_re = \ + re.compile(u'(\d{4})-([^-]+)-(\d{,2})T(\d{,2}):(\d{2})((\+|-)(\d{,2}:\d{2}))') + +def _parse_date_hungarian(dateString): + '''Parse a string according to a Hungarian 8-bit date format.''' + m = _hungarian_date_format_re.match(dateString) + if not m: return + try: + month = _hungarian_months[m.group(2)] + day = m.group(3) + if len(day) == 1: + day = '0' + day + hour = m.group(4) + if len(hour) == 1: + hour = '0' + hour + except: + return + w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s%(zonediff)s' % \ + {'year': m.group(1), 'month': month, 'day': day,\ + 'hour': hour, 'minute': m.group(5),\ + 'zonediff': m.group(6)} + if _debug: sys.stderr.write('Hungarian date parsed as: %s\n' % w3dtfdate) + return _parse_date_w3dtf(w3dtfdate) +registerDateHandler(_parse_date_hungarian) + +# W3DTF-style date parsing adapted from PyXML xml.utils.iso8601, written by +# Drake and licensed under the Python license. Removed all range checking +# for month, day, hour, minute, and second, since mktime will normalize +# these later +def _parse_date_w3dtf(dateString): + def __extract_date(m): + year = int(m.group('year')) + if year < 100: + year = 100 * int(time.gmtime()[0] / 100) + int(year) + if year < 1000: + return 0, 0, 0 + julian = m.group('julian') + if julian: + julian = int(julian) + month = julian / 30 + 1 + day = julian % 30 + 1 + jday = None + while jday != julian: + t = time.mktime((year, month, day, 0, 0, 0, 0, 0, 0)) + jday = time.gmtime(t)[-2] + diff = abs(jday - julian) + if jday > julian: + if diff < day: + day = day - diff + else: + month = month - 1 + day = 31 + elif jday < julian: + if day + diff < 28: + day = day + diff + else: + month = month + 1 + return year, month, day + month = m.group('month') + day = 1 + if month is None: + month = 1 + else: + month = int(month) + day = m.group('day') + if day: + day = int(day) + else: + day = 1 + return year, month, day + + def __extract_time(m): + if not m: + return 0, 0, 0 + hours = m.group('hours') + if not hours: + return 0, 0, 0 + hours = int(hours) + minutes = int(m.group('minutes')) + seconds = m.group('seconds') + if seconds: + seconds = int(seconds) + else: + seconds = 0 + return hours, minutes, seconds + + def __extract_tzd(m): + '''Return the Time Zone Designator as an offset in seconds from UTC.''' + if not m: + return 0 + tzd = m.group('tzd') + if not tzd: + return 0 + if tzd == 'Z': + return 0 + hours = int(m.group('tzdhours')) + minutes = m.group('tzdminutes') + if minutes: + minutes = int(minutes) + else: + minutes = 0 + offset = (hours*60 + minutes) * 60 + if tzd[0] == '+': + return -offset + return offset + + __date_re = ('(?P\d\d\d\d)' + '(?:(?P-|)' + '(?:(?P\d\d\d)' + '|(?P\d\d)(?:(?P=dsep)(?P\d\d))?))?') + __tzd_re = '(?P[-+](?P\d\d)(?::?(?P\d\d))|Z)' + __time_re = ('(?P\d\d)(?P:|)(?P\d\d)' + '(?:(?P=tsep)(?P\d\d(?:[.,]\d+)?))?' + + __tzd_re) + __datetime_re = '%s(?:T%s)?' % (__date_re, __time_re) + __datetime_rx = re.compile(__datetime_re) + m = __datetime_rx.match(dateString) + if (m is None) or (m.group() != dateString): return + gmt = __extract_date(m) + __extract_time(m) + (0, 0, 0) + if gmt[0] == 0: return + return time.gmtime(time.mktime(gmt) + __extract_tzd(m) - time.timezone) +registerDateHandler(_parse_date_w3dtf) + +def _parse_date_rfc822(dateString): + '''Parse an RFC822, RFC1123, RFC2822, or asctime-style date''' + data = dateString.split() + if data[0][-1] in (',', '.') or data[0].lower() in rfc822._daynames: + del data[0] + if len(data) == 4: + s = data[3] + i = s.find('+') + if i > 0: + data[3:] = [s[:i], s[i+1:]] + else: + data.append('') + dateString = " ".join(data) + if len(data) < 5: + dateString += ' 00:00:00 GMT' + tm = rfc822.parsedate_tz(dateString) + if tm: + return time.gmtime(rfc822.mktime_tz(tm)) +# rfc822.py defines several time zones, but we define some extra ones. +# 'ET' is equivalent to 'EST', etc. +_additional_timezones = {'AT': -400, 'ET': -500, 'CT': -600, 'MT': -700, 'PT': -800} +rfc822._timezones.update(_additional_timezones) +registerDateHandler(_parse_date_rfc822) + +def _parse_date(dateString): + '''Parses a variety of date formats into a 9-tuple in GMT''' + for handler in _date_handlers: + try: + date9tuple = handler(dateString) + if not date9tuple: continue + if len(date9tuple) != 9: + if _debug: sys.stderr.write('date handler function must return 9-tuple\n') + raise ValueError + map(int, date9tuple) + return date9tuple + except Exception, e: + if _debug: sys.stderr.write('%s raised %s\n' % (handler.__name__, repr(e))) + pass + return None + +def _getCharacterEncoding(http_headers, xml_data): + '''Get the character encoding of the XML document + + http_headers is a dictionary + xml_data is a raw string (not Unicode) + + This is so much trickier than it sounds, it's not even funny. + According to RFC 3023 ('XML Media Types'), if the HTTP Content-Type + is application/xml, application/*+xml, + application/xml-external-parsed-entity, or application/xml-dtd, + the encoding given in the charset parameter of the HTTP Content-Type + takes precedence over the encoding given in the XML prefix within the + document, and defaults to 'utf-8' if neither are specified. But, if + the HTTP Content-Type is text/xml, text/*+xml, or + text/xml-external-parsed-entity, the encoding given in the XML prefix + within the document is ALWAYS IGNORED and only the encoding given in + the charset parameter of the HTTP Content-Type header should be + respected, and it defaults to 'us-ascii' if not specified. + + Furthermore, discussion on the atom-syntax mailing list with the + author of RFC 3023 leads me to the conclusion that any document + served with a Content-Type of text/* and no charset parameter + must be treated as us-ascii. (We now do this.) And also that it + must always be flagged as non-well-formed. (We now do this too.) + + If Content-Type is unspecified (input was local file or non-HTTP source) + or unrecognized (server just got it totally wrong), then go by the + encoding given in the XML prefix of the document and default to + 'iso-8859-1' as per the HTTP specification (RFC 2616). + + Then, assuming we didn't find a character encoding in the HTTP headers + (and the HTTP Content-type allowed us to look in the body), we need + to sniff the first few bytes of the XML data and try to determine + whether the encoding is ASCII-compatible. Section F of the XML + specification shows the way here: + http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info + + If the sniffed encoding is not ASCII-compatible, we need to make it + ASCII compatible so that we can sniff further into the XML declaration + to find the encoding attribute, which will tell us the true encoding. + + Of course, none of this guarantees that we will be able to parse the + feed in the declared character encoding (assuming it was declared + correctly, which many are not). CJKCodecs and iconv_codec help a lot; + you should definitely install them if you can. + http://cjkpython.i18n.org/ + ''' + + def _parseHTTPContentType(content_type): + '''takes HTTP Content-Type header and returns (content type, charset) + + If no charset is specified, returns (content type, '') + If no content type is specified, returns ('', '') + Both return parameters are guaranteed to be lowercase strings + ''' + content_type = content_type or '' + content_type, params = cgi.parse_header(content_type) + return content_type, params.get('charset', '').replace("'", '') + + sniffed_xml_encoding = '' + xml_encoding = '' + true_encoding = '' + http_content_type, http_encoding = _parseHTTPContentType(http_headers.get('content-type')) + # Must sniff for non-ASCII-compatible character encodings before + # searching for XML declaration. This heuristic is defined in + # section F of the XML specification: + # http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info + try: + if xml_data[:4] == '\x4c\x6f\xa7\x94': + # EBCDIC + xml_data = _ebcdic_to_ascii(xml_data) + elif xml_data[:4] == '\x00\x3c\x00\x3f': + # UTF-16BE + sniffed_xml_encoding = 'utf-16be' + xml_data = unicode(xml_data, 'utf-16be').encode('utf-8') + elif (len(xml_data) >= 4) and (xml_data[:2] == '\xfe\xff') and (xml_data[2:4] != '\x00\x00'): + # UTF-16BE with BOM + sniffed_xml_encoding = 'utf-16be' + xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8') + elif xml_data[:4] == '\x3c\x00\x3f\x00': + # UTF-16LE + sniffed_xml_encoding = 'utf-16le' + xml_data = unicode(xml_data, 'utf-16le').encode('utf-8') + elif (len(xml_data) >= 4) and (xml_data[:2] == '\xff\xfe') and (xml_data[2:4] != '\x00\x00'): + # UTF-16LE with BOM + sniffed_xml_encoding = 'utf-16le' + xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8') + elif xml_data[:4] == '\x00\x00\x00\x3c': + # UTF-32BE + sniffed_xml_encoding = 'utf-32be' + xml_data = unicode(xml_data, 'utf-32be').encode('utf-8') + elif xml_data[:4] == '\x3c\x00\x00\x00': + # UTF-32LE + sniffed_xml_encoding = 'utf-32le' + xml_data = unicode(xml_data, 'utf-32le').encode('utf-8') + elif xml_data[:4] == '\x00\x00\xfe\xff': + # UTF-32BE with BOM + sniffed_xml_encoding = 'utf-32be' + xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8') + elif xml_data[:4] == '\xff\xfe\x00\x00': + # UTF-32LE with BOM + sniffed_xml_encoding = 'utf-32le' + xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8') + elif xml_data[:3] == '\xef\xbb\xbf': + # UTF-8 with BOM + sniffed_xml_encoding = 'utf-8' + xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8') + else: + # ASCII-compatible + pass + xml_encoding_match = re.compile('^<\?.*encoding=[\'"](.*?)[\'"].*\?>').match(xml_data) + except: + xml_encoding_match = None + if xml_encoding_match: + xml_encoding = xml_encoding_match.groups()[0].lower() + if sniffed_xml_encoding and (xml_encoding in ('iso-10646-ucs-2', 'ucs-2', 'csunicode', 'iso-10646-ucs-4', 'ucs-4', 'csucs4', 'utf-16', 'utf-32', 'utf_16', 'utf_32', 'utf16', 'u16')): + xml_encoding = sniffed_xml_encoding + acceptable_content_type = 0 + application_content_types = ('application/xml', 'application/xml-dtd', 'application/xml-external-parsed-entity') + text_content_types = ('text/xml', 'text/xml-external-parsed-entity') + if (http_content_type in application_content_types) or \ + (http_content_type.startswith('application/') and http_content_type.endswith('+xml')): + acceptable_content_type = 1 + true_encoding = http_encoding or xml_encoding or 'utf-8' + elif (http_content_type in text_content_types) or \ + (http_content_type.startswith('text/')) and http_content_type.endswith('+xml'): + acceptable_content_type = 1 + true_encoding = http_encoding or 'us-ascii' + elif http_content_type.startswith('text/'): + true_encoding = http_encoding or 'us-ascii' + elif http_headers and (not http_headers.has_key('content-type')): + true_encoding = xml_encoding or 'iso-8859-1' + else: + true_encoding = xml_encoding or 'utf-8' + return true_encoding, http_encoding, xml_encoding, sniffed_xml_encoding, acceptable_content_type + +def _toUTF8(data, encoding): + '''Changes an XML data stream on the fly to specify a new encoding + + data is a raw sequence of bytes (not Unicode) that is presumed to be in %encoding already + encoding is a string recognized by encodings.aliases + ''' + if _debug: sys.stderr.write('entering _toUTF8, trying encoding %s\n' % encoding) + # strip Byte Order Mark (if present) + if (len(data) >= 4) and (data[:2] == '\xfe\xff') and (data[2:4] != '\x00\x00'): + if _debug: + sys.stderr.write('stripping BOM\n') + if encoding != 'utf-16be': + sys.stderr.write('trying utf-16be instead\n') + encoding = 'utf-16be' + data = data[2:] + elif (len(data) >= 4) and (data[:2] == '\xff\xfe') and (data[2:4] != '\x00\x00'): + if _debug: + sys.stderr.write('stripping BOM\n') + if encoding != 'utf-16le': + sys.stderr.write('trying utf-16le instead\n') + encoding = 'utf-16le' + data = data[2:] + elif data[:3] == '\xef\xbb\xbf': + if _debug: + sys.stderr.write('stripping BOM\n') + if encoding != 'utf-8': + sys.stderr.write('trying utf-8 instead\n') + encoding = 'utf-8' + data = data[3:] + elif data[:4] == '\x00\x00\xfe\xff': + if _debug: + sys.stderr.write('stripping BOM\n') + if encoding != 'utf-32be': + sys.stderr.write('trying utf-32be instead\n') + encoding = 'utf-32be' + data = data[4:] + elif data[:4] == '\xff\xfe\x00\x00': + if _debug: + sys.stderr.write('stripping BOM\n') + if encoding != 'utf-32le': + sys.stderr.write('trying utf-32le instead\n') + encoding = 'utf-32le' + data = data[4:] + newdata = unicode(data, encoding) + if _debug: sys.stderr.write('successfully converted %s data to unicode\n' % encoding) + declmatch = re.compile('^<\?xml[^>]*?>') + newdecl = '''''' + if declmatch.search(newdata): + newdata = declmatch.sub(newdecl, newdata) + else: + newdata = newdecl + u'\n' + newdata + return newdata.encode('utf-8') + +def _stripDoctype(data): + '''Strips DOCTYPE from XML document, returns (rss_version, stripped_data) + + rss_version may be 'rss091n' or None + stripped_data is the same XML document, minus the DOCTYPE + ''' + entity_pattern = re.compile(r']*?)>', re.MULTILINE) + data = entity_pattern.sub('', data) + doctype_pattern = re.compile(r']*?)>', re.MULTILINE) + doctype_results = doctype_pattern.findall(data) + doctype = doctype_results and doctype_results[0] or '' + if doctype.lower().count('netscape'): + version = 'rss091n' + else: + version = None + data = doctype_pattern.sub('', data) + return version, data + +def opensearch_parse(url_file_stream_or_string, etag=None, modified=None, agent=None, referrer=None, handlers=[]): + '''Parse a feed from a URL, file, stream, or string''' + result = FeedParserDict() + result['feed'] = FeedParserDict() + result['entries'] = [] + if _XML_AVAILABLE: + result['bozo'] = 0 + if type(handlers) == types.InstanceType: + handlers = [handlers] + try: + f = _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers) + data = f.read() + except Exception, e: + result['bozo'] = 1 + result['bozo_exception'] = e + data = '' + f = None + + # if feed is gzip-compressed, decompress it + if f and data and hasattr(f, 'headers'): + if gzip and f.headers.get('content-encoding', '') == 'gzip': + try: + data = gzip.GzipFile(fileobj=_StringIO(data)).read() + except Exception, e: + # Some feeds claim to be gzipped but they're not, so + # we get garbage. Ideally, we should re-request the + # feed without the 'Accept-encoding: gzip' header, + # but we don't. + result['bozo'] = 1 + result['bozo_exception'] = e + data = '' + elif zlib and f.headers.get('content-encoding', '') == 'deflate': + try: + data = zlib.decompress(data, -zlib.MAX_WBITS) + except Exception, e: + result['bozo'] = 1 + result['bozo_exception'] = e + data = '' + + # save HTTP headers + if hasattr(f, 'info'): + info = f.info() + result['etag'] = info.getheader('ETag') + last_modified = info.getheader('Last-Modified') + if last_modified: + result['modified'] = _parse_date(last_modified) + if hasattr(f, 'url'): + result['href'] = f.url + result['status'] = 200 + if hasattr(f, 'status'): + result['status'] = f.status + if hasattr(f, 'headers'): + result['headers'] = f.headers.dict + if hasattr(f, 'close'): + f.close() + + # there are four encodings to keep track of: + # - http_encoding is the encoding declared in the Content-Type HTTP header + # - xml_encoding is the encoding declared in the ; changed +# project name +#2.5 - 7/25/2003 - MAP - changed to Python license (all contributors agree); +# removed unnecessary urllib code -- urllib2 should always be available anyway; +# return actual url, status, and full HTTP headers (as result['url'], +# result['status'], and result['headers']) if parsing a remote feed over HTTP -- +# this should pass all the HTTP tests at ; +# added the latest namespace-of-the-week for RSS 2.0 +#2.5.1 - 7/26/2003 - RMK - clear opener.addheaders so we only send our custom +# User-Agent (otherwise urllib2 sends two, which confuses some servers) +#2.5.2 - 7/28/2003 - MAP - entity-decode inline xml properly; added support for +# inline and as used in some RSS 2.0 feeds +#2.5.3 - 8/6/2003 - TvdV - patch to track whether we're inside an image or +# textInput, and also to return the character encoding (if specified) +#2.6 - 1/1/2004 - MAP - dc:author support (MarekK); fixed bug tracking +# nested divs within content (JohnD); fixed missing sys import (JohanS); +# fixed regular expression to capture XML character encoding (Andrei); +# added support for Atom 0.3-style links; fixed bug with textInput tracking; +# added support for cloud (MartijnP); added support for multiple +# category/dc:subject (MartijnP); normalize content model: 'description' gets +# description (which can come from description, summary, or full content if no +# description), 'content' gets dict of base/language/type/value (which can come +# from content:encoded, xhtml:body, content, or fullitem); +# fixed bug matching arbitrary Userland namespaces; added xml:base and xml:lang +# tracking; fixed bug tracking unknown tags; fixed bug tracking content when +# element is not in default namespace (like Pocketsoap feed); +# resolve relative URLs in link, guid, docs, url, comments, wfw:comment, +# wfw:commentRSS; resolve relative URLs within embedded HTML markup in +# description, xhtml:body, content, content:encoded, title, subtitle, +# summary, info, tagline, and copyright; added support for pingback and +# trackback namespaces +#2.7 - 1/5/2004 - MAP - really added support for trackback and pingback +# namespaces, as opposed to 2.6 when I said I did but didn't really; +# sanitize HTML markup within some elements; added mxTidy support (if +# installed) to tidy HTML markup within some elements; fixed indentation +# bug in _parse_date (FazalM); use socket.setdefaulttimeout if available +# (FazalM); universal date parsing and normalization (FazalM): 'created', modified', +# 'issued' are parsed into 9-tuple date format and stored in 'created_parsed', +# 'modified_parsed', and 'issued_parsed'; 'date' is duplicated in 'modified' +# and vice-versa; 'date_parsed' is duplicated in 'modified_parsed' and vice-versa +#2.7.1 - 1/9/2004 - MAP - fixed bug handling " and '. fixed memory +# leak not closing url opener (JohnD); added dc:publisher support (MarekK); +# added admin:errorReportsTo support (MarekK); Python 2.1 dict support (MarekK) +#2.7.4 - 1/14/2004 - MAP - added workaround for improperly formed
tags in +# encoded HTML (skadz); fixed unicode handling in normalize_attrs (ChrisL); +# fixed relative URI processing for guid (skadz); added ICBM support; added +# base64 support +#2.7.5 - 1/15/2004 - MAP - added workaround for malformed DOCTYPE (seen on many +# blogspot.com sites); added _debug variable +#2.7.6 - 1/16/2004 - MAP - fixed bug with StringIO importing +#3.0b3 - 1/23/2004 - MAP - parse entire feed with real XML parser (if available); +# added several new supported namespaces; fixed bug tracking naked markup in +# description; added support for enclosure; added support for source; re-added +# support for cloud which got dropped somehow; added support for expirationDate +#3.0b4 - 1/26/2004 - MAP - fixed xml:lang inheritance; fixed multiple bugs tracking +# xml:base URI, one for documents that don't define one explicitly and one for +# documents that define an outer and an inner xml:base that goes out of scope +# before the end of the document +#3.0b5 - 1/26/2004 - MAP - fixed bug parsing multiple links at feed level +#3.0b6 - 1/27/2004 - MAP - added feed type and version detection, result['version'] +# will be one of SUPPORTED_VERSIONS.keys() or empty string if unrecognized; +# added support for creativeCommons:license and cc:license; added support for +# full Atom content model in title, tagline, info, copyright, summary; fixed bug +# with gzip encoding (not always telling server we support it when we do) +#3.0b7 - 1/28/2004 - MAP - support Atom-style author element in author_detail +# (dictionary of 'name', 'url', 'email'); map author to author_detail if author +# contains name + email address +#3.0b8 - 1/28/2004 - MAP - added support for contributor +#3.0b9 - 1/29/2004 - MAP - fixed check for presence of dict function; added +# support for summary +#3.0b10 - 1/31/2004 - MAP - incorporated ISO-8601 date parsing routines from +# xml.util.iso8601 +#3.0b11 - 2/2/2004 - MAP - added 'rights' to list of elements that can contain +# dangerous markup; fiddled with decodeEntities (not right); liberalized +# date parsing even further +#3.0b12 - 2/6/2004 - MAP - fiddled with decodeEntities (still not right); +# added support to Atom 0.2 subtitle; added support for Atom content model +# in copyright; better sanitizing of dangerous HTML elements with end tags +# (script, frameset) +#3.0b13 - 2/8/2004 - MAP - better handling of empty HTML tags (br, hr, img, +# etc.) in embedded markup, in either HTML or XHTML form (
,
,
) +#3.0b14 - 2/8/2004 - MAP - fixed CDATA handling in non-wellformed feeds under +# Python 2.1 +#3.0b15 - 2/11/2004 - MAP - fixed bug resolving relative links in wfw:commentRSS; +# fixed bug capturing author and contributor URL; fixed bug resolving relative +# links in author and contributor URL; fixed bug resolvin relative links in +# generator URL; added support for recognizing RSS 1.0; passed Simon Fell's +# namespace tests, and included them permanently in the test suite with his +# permission; fixed namespace handling under Python 2.1 +#3.0b16 - 2/12/2004 - MAP - fixed support for RSS 0.90 (broken in b15) +#3.0b17 - 2/13/2004 - MAP - determine character encoding as per RFC 3023 +#3.0b18 - 2/17/2004 - MAP - always map description to summary_detail (Andrei); +# use libxml2 (if available) +#3.0b19 - 3/15/2004 - MAP - fixed bug exploding author information when author +# name was in parentheses; removed ultra-problematic mxTidy support; patch to +# workaround crash in PyXML/expat when encountering invalid entities +# (MarkMoraes); support for textinput/textInput +#3.0b20 - 4/7/2004 - MAP - added CDF support +#3.0b21 - 4/14/2004 - MAP - added Hot RSS support +#3.0b22 - 4/19/2004 - MAP - changed 'channel' to 'feed', 'item' to 'entries' in +# results dict; changed results dict to allow getting values with results.key +# as well as results[key]; work around embedded illformed HTML with half +# a DOCTYPE; work around malformed Content-Type header; if character encoding +# is wrong, try several common ones before falling back to regexes (if this +# works, bozo_exception is set to CharacterEncodingOverride); fixed character +# encoding issues in BaseHTMLProcessor by tracking encoding and converting +# from Unicode to raw strings before feeding data to sgmllib.SGMLParser; +# convert each value in results to Unicode (if possible), even if using +# regex-based parsing +#3.0b23 - 4/21/2004 - MAP - fixed UnicodeDecodeError for feeds that contain +# high-bit characters in attributes in embedded HTML in description (thanks +# Thijs van de Vossen); moved guid, date, and date_parsed to mapped keys in +# FeedParserDict; tweaked FeedParserDict.has_key to return True if asking +# about a mapped key +#3.0fc1 - 4/23/2004 - MAP - made results.entries[0].links[0] and +# results.entries[0].enclosures[0] into FeedParserDict; fixed typo that could +# cause the same encoding to be tried twice (even if it failed the first time); +# fixed DOCTYPE stripping when DOCTYPE contained entity declarations; +# better textinput and image tracking in illformed RSS 1.0 feeds +#3.0fc2 - 5/10/2004 - MAP - added and passed Sam's amp tests; added and passed +# my blink tag tests +#3.0fc3 - 6/18/2004 - MAP - fixed bug in _changeEncodingDeclaration that +# failed to parse utf-16 encoded feeds; made source into a FeedParserDict; +# duplicate admin:generatorAgent/@rdf:resource in generator_detail.url; +# added support for image; refactored parse() fallback logic to try other +# encodings if SAX parsing fails (previously it would only try other encodings +# if re-encoding failed); remove unichr madness in normalize_attrs now that +# we're properly tracking encoding in and out of BaseHTMLProcessor; set +# feed.language from root-level xml:lang; set entry.id from rdf:about; +# send Accept header +#3.0 - 6/21/2004 - MAP - don't try iso-8859-1 (can't distinguish between +# iso-8859-1 and windows-1252 anyway, and most incorrectly marked feeds are +# windows-1252); fixed regression that could cause the same encoding to be +# tried twice (even if it failed the first time) +#3.0.1 - 6/22/2004 - MAP - default to us-ascii for all text/* content types; +# recover from malformed content-type header parameter with no equals sign +# ('text/xml; charset:iso-8859-1') +#3.1 - 6/28/2004 - MAP - added and passed tests for converting HTML entities +# to Unicode equivalents in illformed feeds (aaronsw); added and +# passed tests for converting character entities to Unicode equivalents +# in illformed feeds (aaronsw); test for valid parsers when setting +# XML_AVAILABLE; make version and encoding available when server returns +# a 304; add handlers parameter to pass arbitrary urllib2 handlers (like +# digest auth or proxy support); add code to parse username/password +# out of url and send as basic authentication; expose downloading-related +# exceptions in bozo_exception (aaronsw); added __contains__ method to +# FeedParserDict (aaronsw); added publisher_detail (aaronsw) +#3.2 - 7/3/2004 - MAP - use cjkcodecs and iconv_codec if available; always +# convert feed to UTF-8 before passing to XML parser; completely revamped +# logic for determining character encoding and attempting XML parsing +# (much faster); increased default timeout to 20 seconds; test for presence +# of Location header on redirects; added tests for many alternate character +# encodings; support various EBCDIC encodings; support UTF-16BE and +# UTF16-LE with or without a BOM; support UTF-8 with a BOM; support +# UTF-32BE and UTF-32LE with or without a BOM; fixed crashing bug if no +# XML parsers are available; added support for 'Content-encoding: deflate'; +# send blank 'Accept-encoding: ' header if neither gzip nor zlib modules +# are available +#3.3 - 7/15/2004 - MAP - optimize EBCDIC to ASCII conversion; fix obscure +# problem tracking xml:base and xml:lang if element declares it, child +# doesn't, first grandchild redeclares it, and second grandchild doesn't; +# refactored date parsing; defined public registerDateHandler so callers +# can add support for additional date formats at runtime; added support +# for OnBlog, Nate, MSSQL, Greek, and Hungarian dates (ytrewq1); added +# zopeCompatibilityHack() which turns FeedParserDict into a regular +# dictionary, required for Zope compatibility, and also makes command- +# line debugging easier because pprint module formats real dictionaries +# better than dictionary-like objects; added NonXMLContentType exception, +# which is stored in bozo_exception when a feed is served with a non-XML +# media type such as 'text/plain'; respect Content-Language as default +# language if not xml:lang is present; cloud dict is now FeedParserDict; +# generator dict is now FeedParserDict; better tracking of xml:lang, +# including support for xml:lang='' to unset the current language; +# recognize RSS 1.0 feeds even when RSS 1.0 namespace is not the default +# namespace; don't overwrite final status on redirects (scenarios: +# redirecting to a URL that returns 304, redirecting to a URL that +# redirects to another URL with a different type of redirect); add +# support for HTTP 303 redirects +#4.0 - MAP - support for relative URIs in xml:base attribute; fixed +# encoding issue with mxTidy (phopkins); preliminary support for RFC 3229; +# support for Atom 1.0; support for iTunes extensions; new 'tags' for +# categories/keywords/etc. as array of dict +# {'term': term, 'scheme': scheme, 'label': label} to match Atom 1.0 +# terminology; parse RFC 822-style dates with no time; lots of other +# bug fixes diff --git a/src/calibre/utils/opensearch/query.py b/src/calibre/utils/opensearch/query.py new file mode 100644 index 0000000000..31c37ca923 --- /dev/null +++ b/src/calibre/utils/opensearch/query.py @@ -0,0 +1,66 @@ +from urlparse import urlparse, urlunparse +from urllib import urlencode +from cgi import parse_qs + +class Query: + """Represents an opensearch query. Used internally by the Client to + construct an opensearch url to request. Really this class is just a + helper for substituting values into the macros in a format. + + format = 'http://beta.indeed.com/opensearch?q={searchTerms}&start={startIndex}&limit={count}' + q = Query(format) + q.searchTerms('zx81') + q.startIndex = 1 + q.count = 25 + print q.to_url() + """ + + standard_macros = ['searchTerms','count','startIndex','startPage', + 'language', 'outputEncoding', 'inputEncoding'] + + def __init__(self, format): + """Create a query object by passing it the url format obtained + from the opensearch Description. + """ + self.format = format + + # unpack the url to a tuple + self.url_parts = urlparse(format) + + # unpack the query string to a dictionary + self.query_string = parse_qs(self.url_parts[4]) + + # look for standard macros and create a mapping of the + # opensearch names to the service specific ones + # so q={searchTerms} will result in a mapping between searchTerms and q + self.macro_map = {} + for key,values in self.query_string.items(): + # TODO eventually optional/required params should be + # distinguished somehow (the ones with/without trailing ? + macro = values[0].replace('{','').replace('}','').replace('?','') + if macro in Query.standard_macros: + self.macro_map[macro] = key + + def url(self): + # copy the original query string + query_string = dict(self.query_string) + + # iterate through macros and set the position in the querystring + for macro, name in self.macro_map.items(): + if hasattr(self, macro): + # set the name/value pair + query_string[name] = [getattr(self, macro)] + else: + # remove the name/value pair + del(query_string[name]) + + # copy the url parts and substitute in our new query string + url_parts = list(self.url_parts) + url_parts[4] = urlencode(query_string, 1) + + # recompose and return url + return urlunparse(tuple(url_parts)) + + def has_macro(self, macro): + return self.macro_map.has_key(macro) + diff --git a/src/calibre/utils/opensearch/results.py b/src/calibre/utils/opensearch/results.py new file mode 100644 index 0000000000..0472b512e1 --- /dev/null +++ b/src/calibre/utils/opensearch/results.py @@ -0,0 +1,131 @@ + +class Results(object): + + def __init__(self, query, agent=None): + self.agent = agent + self._fetch(query) + self._iter = 0 + + def __iter__(self): + self._iter = 0 + return self + + def __len__(self): + return self.totalResults + + def next(self): + + # just keep going like the energizer bunny + while True: + + # return any item we haven't returned + if self._iter < len(self.items): + self._iter += 1 + return self.items[self._iter-1] + + # if there appears to be more to fetch + if \ + self.totalResults != 0 \ + and self.totalResults > self.startIndex + self.itemsPerPage - 1: + + # get the next query + next_query = self._get_next_query() + + # if we got one executed it and go back to the beginning + if next_query: + self._fetch(next_query) + # very important to reset this counter + # or else the return will fail + self._iter = 0 + + else: + raise StopIteration + + + def _fetch(self, query): + import osfeedparser + feed = osfeedparser.opensearch_parse(query.url(), agent=self.agent) + self.feed = feed + + # general channel stuff + channel = feed['feed'] + self.title = _pick(channel,'title') + self.link = _pick(channel,'link') + self.description = _pick(channel,'description') + self.language = _pick(channel,'language') + self.copyright = _pick(channel,'copyright') + + # get back opensearch specific values + self.totalResults = _pick(channel,'opensearch_totalresults',0) + self.startIndex = _pick(channel,'opensearch_startindex',1) + self.itemsPerPage = _pick(channel,'opensearch_itemsperpage',0) + + # alias items from the feed to our results object + self.items = feed['items'] + + # set default values if necessary + if self.startIndex == 0: + self.startIndex = 1 + if self.itemsPerPage == 0 and len(self.items) > 0: + self.itemsPerPage = len(self.items) + + # store away query for calculating next results + # if necessary + self.last_query = query + + + def _get_next_query(self): + # update our query to get the next set of records + query = self.last_query + + # use start page if the query supports it + if query.has_macro('startPage'): + # if the query already defined the startPage + # we just need to increment it + if hasattr(query, 'startPage'): + query.startPage += 1 + # to issue the first query startPage might not have + # been specified, so set it to 2 + else: + query.startPage = 2 + return query + + # otherwise the query should support startIndex + elif query.has_macro('startIndex'): + # if startIndex was used before we just add the + # items per page to it to get the next set + if hasattr(query, 'startIndex'): + query.startIndex += self.itemsPerPage + # to issue the first query the startIndex may have + # been left blank in that case we assume it to be + # the item just after the last one on this page + else: + query.startIndex = self.itemsPerPage + 1 + return query + + # doesn't look like there is another stage to this query + return None + + +# helper for pulling values out of a dictionary if they're there +# and returning a default value if they're not +def _pick(d,key,default=None): + + # get the value out + value = d.get(key) + + # if it wasn't there return the default + if value == None: + return default + + # if they want an int try to convert to an int + # and return default if it fails + if type(default) == int: + try: + return int(d[key]) + except: + return default + + # otherwise we're good to return the value + return value + diff --git a/src/calibre/utils/opensearch/url.py b/src/calibre/utils/opensearch/url.py new file mode 100644 index 0000000000..665c024ef3 --- /dev/null +++ b/src/calibre/utils/opensearch/url.py @@ -0,0 +1,8 @@ +class URL: + """Class for representing a URL in an opensearch v1.1 query""" + + def __init__(self, type='', template='', method='GET'): + self.type = type + self.template = template + self.method = 'GET' + self.params = [] diff --git a/src/calibre/web/feeds/recipes/collection.py b/src/calibre/web/feeds/recipes/collection.py index 87a65dd9e6..13bae3a554 100644 --- a/src/calibre/web/feeds/recipes/collection.py +++ b/src/calibre/web/feeds/recipes/collection.py @@ -85,7 +85,7 @@ def serialize_builtin_recipes(): return serialize_collection(recipe_mapping) def get_builtin_recipe_collection(): - return etree.parse(P('builtin_recipes.xml')).getroot() + return etree.parse(P('builtin_recipes.xml', allow_user_override=False)).getroot() def get_custom_recipe_collection(*args): from calibre.web.feeds.recipes import compile_recipe, \ @@ -179,7 +179,7 @@ def download_builtin_recipe(urn): return br.open_novisit('http://status.calibre-ebook.com/recipe/'+urn).read() def get_builtin_recipe(urn): - with zipfile.ZipFile(P('builtin_recipes.zip'), 'r') as zf: + with zipfile.ZipFile(P('builtin_recipes.zip', allow_user_override=False), 'r') as zf: return zf.read(urn+'.recipe') def get_builtin_recipe_by_title(title, log=None, download_recipe=False): diff --git a/src/calibre/web/feeds/recipes/model.py b/src/calibre/web/feeds/recipes/model.py index 2c52c85f83..5f8d906e61 100644 --- a/src/calibre/web/feeds/recipes/model.py +++ b/src/calibre/web/feeds/recipes/model.py @@ -140,7 +140,8 @@ class RecipeModel(QAbstractItemModel, SearchQueryParser): self.builtin_recipe_collection = get_builtin_recipe_collection() self.scheduler_config = SchedulerConfig() try: - with zipfile.ZipFile(P('builtin_recipes.zip'), 'r') as zf: + with zipfile.ZipFile(P('builtin_recipes.zip', + allow_user_override=False), 'r') as zf: self.favicons = dict([(x.filename, x) for x in zf.infolist() if x.filename.endswith('.png')]) except: @@ -181,7 +182,7 @@ class RecipeModel(QAbstractItemModel, SearchQueryParser): def do_refresh(self, restrict_to_urns=set([])): self.custom_recipe_collection = get_custom_recipe_collection() - zf = P('builtin_recipes.zip') + zf = P('builtin_recipes.zip', allow_user_override=False) def factory(cls, parent, *args): args = list(args)