mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Merge
This commit is contained in:
Sengian
commit
16a9c42edc
@ -2,6 +2,7 @@
|
||||
.check-cache.pickle
|
||||
src/calibre/plugins
|
||||
resources/images.qrc
|
||||
resources/compiled_coffeescript.zip
|
||||
src/calibre/ebooks/oeb/display/test/*.js
|
||||
src/calibre/manual/.build/
|
||||
src/calibre/manual/cli/
|
||||
@ -16,7 +17,6 @@ resources/ebook-convert-complete.pickle
|
||||
resources/builtin_recipes.xml
|
||||
resources/builtin_recipes.zip
|
||||
resources/template-functions.json
|
||||
resources/display/*.js
|
||||
setup/installer/windows/calibre/build.log
|
||||
src/calibre/translations/.errors
|
||||
src/cssutils/.svn/
|
||||
|
||||
@ -19,6 +19,67 @@
|
||||
# new recipes:
|
||||
# - title:
|
||||
|
||||
- version: 0.8.51
|
||||
date: 2012-05-11
|
||||
|
||||
new features:
|
||||
- title: "When switching libraries preserve the position and selected books if you switch back to a previously opened library."
|
||||
tickets: [994514]
|
||||
|
||||
- title: "Conversion pipeline: Filter out the useless font-face rules inserted by Microsoft Word for every font on the system"
|
||||
|
||||
- title: "Driver for Motorola XT875 and Pandigital SuperNova"
|
||||
tickets: [996890]
|
||||
|
||||
- title: "Add a colour swatch the the dialog for creating column coloring rules, to ease selection of colors"
|
||||
tickets: [994811]
|
||||
|
||||
- title: "EPUB Output: Consolidate internal CSS generated by calibre into external stylesheets for ease of editing the EPUB"
|
||||
|
||||
- title: "List EPUB and MOBI at the top of the dropdown list fo formats to convert to, as they are the most common choices"
|
||||
tickets: [994838]
|
||||
|
||||
bug fixes:
|
||||
- title: "E-book viewer: Improve performance when switching between normal and fullscreen views."
|
||||
tickets: [996102]
|
||||
|
||||
- title: "Edit metadata dialog: When running download metadata do not insert duplicate tags into the list of tags"
|
||||
|
||||
- title: "KF8 Input: Do not error out if the file has a few invalidly encoded bytes."
|
||||
tickets: [997034]
|
||||
|
||||
- title: "Fix download of news in AZW3 format not working"
|
||||
tickets: [996439]
|
||||
|
||||
- title: "Pocketbook driver: Update for new PB 611 firmware."
|
||||
tickets: [903079]
|
||||
|
||||
- title: "ebook-convert: Error out if the user prvides extra command line args instead of silently ignoring them"
|
||||
tickets: [994939]
|
||||
|
||||
- title: "EPUB Output: Do not self close any container tags to prevent artifacts when EPUBs are viewed using buggy browser based viewers."
|
||||
tickets: [994861]
|
||||
|
||||
- title: "Fix regression in 0.8.50 that broke the conversion of HTML files that contained non-ascii font-face declarations, typically produced by Microsoft Word"
|
||||
|
||||
improved recipes:
|
||||
- Mainichi news
|
||||
- derStandard
|
||||
- Endgadget Japan
|
||||
|
||||
new recipes:
|
||||
- title: Mainichi English
|
||||
author: Hiroshi Miura
|
||||
|
||||
- title: The Grid TO
|
||||
author: Yusuf W
|
||||
|
||||
- title: National Geographic (Italy)
|
||||
author: faber1971
|
||||
|
||||
- title: Rebelion
|
||||
author: Marc Busque
|
||||
|
||||
- version: 0.8.50
|
||||
date: 2012-05-04
|
||||
|
||||
|
||||
@ -7,10 +7,11 @@ __copyright__ = '2009, Gerhard Aigner <gerhard.aigner at gmail.com>'
|
||||
''' http://www.derstandard.at - Austrian Newspaper '''
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from time import strftime
|
||||
|
||||
class DerStandardRecipe(BasicNewsRecipe):
|
||||
title = u'derStandard'
|
||||
__author__ = 'Gerhard Aigner and Sujata Raman and Marcel Jira'
|
||||
__author__ = 'Gerhard Aigner and Sujata Raman and Marcel Jira and Peter Reschenhofer'
|
||||
description = u'Nachrichten aus Österreich'
|
||||
publisher ='derStandard.at'
|
||||
category = 'news, politics, nachrichten, Austria'
|
||||
@ -88,3 +89,41 @@ class DerStandardRecipe(BasicNewsRecipe):
|
||||
for t in soup.findAll(['ul', 'li']):
|
||||
t.name = 'div'
|
||||
return soup
|
||||
|
||||
def get_cover_url(self):
|
||||
highResolution = True
|
||||
|
||||
date = strftime("%Y/%Y%m%d")
|
||||
# it is also possible for the past
|
||||
#date = '2012/20120503'
|
||||
|
||||
urlP1 = 'http://epaper.derstandarddigital.at/'
|
||||
urlP2 = 'data_ep/STAN/' + date
|
||||
urlP3 = '/V.B1/'
|
||||
urlP4 = 'paper.htm'
|
||||
urlHTML = urlP1 + urlP2 + urlP3 + urlP4
|
||||
|
||||
br = self.clone_browser(self.browser)
|
||||
htmlF = br.open_novisit(urlHTML)
|
||||
htmlC = htmlF.read()
|
||||
|
||||
|
||||
# URL EXAMPLE: data_ep/STAN/2012/20120504/V.B1/pages/A3B6798F-2751-4D8D-A103-C5EF22F7ACBE.htm
|
||||
# consists of part2 + part3 + 'pages/' + code
|
||||
# 'pages/' has length 6, code has lenght 36
|
||||
|
||||
index = htmlC.find(urlP2) + len(urlP2 + urlP3) + 6
|
||||
code = htmlC[index:index + 36]
|
||||
|
||||
|
||||
# URL EXAMPLE HIGH RESOLUTION: http://epaper.derstandarddigital.at/data_ep/STAN/2012/20120504/pagejpg/A3B6798F-2751-4D8D-A103-C5EF22F7ACBE_b.png
|
||||
# URL EXAMPLE LOW RESOLUTION: http://epaper.derstandarddigital.at/data_ep/STAN/2012/20120504/pagejpg/2AB52F71-11C1-4859-9114-CDCD79BEFDCB.png
|
||||
|
||||
urlPic = urlP1 + urlP2 + '/pagejpg/' + code
|
||||
|
||||
if highResolution:
|
||||
urlPic = urlPic + '_b'
|
||||
|
||||
urlPic = urlPic + '.png'
|
||||
|
||||
return urlPic
|
||||
|
||||
@ -17,7 +17,25 @@ class EndgadgetJapan(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
language = 'ja'
|
||||
encoding = 'utf-8'
|
||||
feeds = [(u'engadget', u'http://japanese.engadget.com/rss.xml')]
|
||||
index = 'http://japanese.engadget.com/'
|
||||
remove_javascript = True
|
||||
|
||||
remove_tags_before = dict(name="h1", attrs={'class':"post_title"})
|
||||
remove_tags_after = dict(name='div', attrs={'class':'post_body'})
|
||||
|
||||
def parse_index(self):
|
||||
feeds = []
|
||||
newsarticles = []
|
||||
soup = self.index_to_soup(self.index)
|
||||
for topstories in soup.findAll('div',attrs={'class':'post_content'}):
|
||||
itt = topstories.find('h4')
|
||||
itema = itt.find('a',href=True)
|
||||
newsarticles.append({
|
||||
'title' :itema.string
|
||||
,'date' :''
|
||||
,'url' :itema['href']
|
||||
,'description':''
|
||||
})
|
||||
feeds.append(('Latest Posts', newsarticles))
|
||||
return feeds
|
||||
|
||||
remove_tags_before = dict(name="div", attrs={'id':"content_wrap"})
|
||||
remove_tags_after = dict(name='h3', attrs={'id':'addcomments'})
|
||||
|
||||
82
recipes/folha.recipe
Normal file
82
recipes/folha.recipe
Normal file
@ -0,0 +1,82 @@
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
www.folha.uol.com.br
|
||||
'''
|
||||
import urllib
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Folha_de_s_paulo(BasicNewsRecipe):
|
||||
title = u'Folha de São Paulo - portal'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'Um Jornala a servicao do Brasil'
|
||||
publisher = 'Folhapress'
|
||||
category = 'news, politics, Brasil'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 200
|
||||
no_stylesheets = True
|
||||
encoding = 'cp1252'
|
||||
use_embedded_content = False
|
||||
language = 'pt_BR'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
masthead_url = 'http://f.i.uol.com.br/fsp/furniture/images/lgo-fsp-430x50-ffffff.gif'
|
||||
extra_css = """
|
||||
body{font-family: Arial,Helvetica,sans-serif }
|
||||
img{margin-bottom: 0.4em; display:block}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
remove_tags = [dict(name=['meta','link','base','iframe','embed','object'])]
|
||||
keep_only_tags = [dict(attrs={'id':'articleNew'})]
|
||||
|
||||
|
||||
feeds = [
|
||||
(u'Poder' , u'http://feeds.folha.uol.com.br/poder/rss091.xml' )
|
||||
,(u'Mundo' , u'http://feeds.folha.uol.com.br/mundo/rss091.xml' )
|
||||
,(u'Mercado' , u'http://feeds.folha.uol.com.br/mercado/rss091.xml' )
|
||||
,(u'Cotidiano' , u'http://feeds.folha.uol.com.br/cotidiano/rss091.xml' )
|
||||
,(u'Esporte' , u'http://feeds.folha.uol.com.br/esporte/rss091.xml' )
|
||||
,(u'Ilustrada' , u'http://feeds.folha.uol.com.br/ilustrada/rss091.xml' )
|
||||
,(u'F5' , u'http://feeds.folha.uol.com.br/f5/rss091.xml' )
|
||||
,(u'Ciência' , u'http://feeds.folha.uol.com.br/ciencia/rss091.xml' )
|
||||
,(u'Tec' , u'http://feeds.folha.uol.com.br/tec/rss091.xml' )
|
||||
,(u'Ambiente' , u'http://feeds.folha.uol.com.br/ambiente/rss091.xml' )
|
||||
,(u'Bichos' , u'http://feeds.folha.uol.com.br/bichos/rss091.xml' )
|
||||
,(u'Celebridades' , u'http://feeds.folha.uol.com.br/celebridades/rss091.xml' )
|
||||
,(u'Comida' , u'http://feeds.folha.uol.com.br/comida/rss091.xml' )
|
||||
,(u'Equilibrio' , u'http://feeds.folha.uol.com.br/equilibrioesaude/rss091.xml' )
|
||||
,(u'Folhateen' , u'http://feeds.folha.uol.com.br/folhateen/rss091.xml' )
|
||||
,(u'Folhinha' , u'http://feeds.folha.uol.com.br/folhinha/rss091.xml' )
|
||||
,(u'Ilustrissima' , u'http://feeds.folha.uol.com.br/ilustrissima/rss091.xml' )
|
||||
,(u'Saber' , u'http://feeds.folha.uol.com.br/saber/rss091.xml' )
|
||||
,(u'Turismo' , u'http://feeds.folha.uol.com.br/turismo/rss091.xml' )
|
||||
,(u'Panel do Leitor', u'http://feeds.folha.uol.com.br/folha/paineldoleitor/rss091.xml')
|
||||
,(u'Publifolha' , u'http://feeds.folha.uol.com.br/folha/publifolha/rss091.xml' )
|
||||
,(u'Em cima da hora', u'http://feeds.folha.uol.com.br/emcimadahora/rss091.xml' )
|
||||
]
|
||||
|
||||
def get_article_url(self, article):
|
||||
url = BasicNewsRecipe.get_article_url(self, article)
|
||||
curl = url.partition('/*')[2]
|
||||
return curl
|
||||
|
||||
def print_version(self, url):
|
||||
return 'http://tools.folha.com.br/print?site=emcimadahora&url=' + urllib.quote_plus(url)
|
||||
|
||||
def get_cover_url(self):
|
||||
soup = self.index_to_soup('http://www.folha.uol.com.br/')
|
||||
cont = soup.find('div', attrs={'id':'newspaper'})
|
||||
if cont:
|
||||
ai = cont.find('a', href='http://www1.folha.uol.com.br/fsp/')
|
||||
if ai:
|
||||
return ai.img['src']
|
||||
return None
|
||||
@ -8,7 +8,7 @@ from urllib2 import Request, urlopen, URLError
|
||||
class FolhaOnline(BasicNewsRecipe):
|
||||
THUMBALIZR_API = '' # ---->Get your at http://www.thumbalizr.com/ and put here
|
||||
LANGUAGE = 'pt_br'
|
||||
language = 'pt'
|
||||
language = 'pt_BR'
|
||||
LANGHTM = 'pt-br'
|
||||
ENCODING = 'cp1252'
|
||||
ENCHTM = 'iso-8859-1'
|
||||
|
||||
@ -14,7 +14,7 @@ class FSP(BasicNewsRecipe):
|
||||
HOMEPAGE = 'http://www1.folha.uol.com.br/fsp/'
|
||||
masthead_url = 'http://f.i.uol.com.br/fsp/furniture/images/lgo-fsp-430x50-ffffff.gif'
|
||||
|
||||
language = 'pt'
|
||||
language = 'pt_BR'
|
||||
no_stylesheets = True
|
||||
max_articles_per_feed = 40
|
||||
remove_javascript = True
|
||||
|
||||
79
recipes/grid_to.recipe
Normal file
79
recipes/grid_to.recipe
Normal file
@ -0,0 +1,79 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class TheGridTO(BasicNewsRecipe):
|
||||
#: The title to use for the ebook
|
||||
title = u'The Grid TO'
|
||||
|
||||
#: A couple of lines that describe the content this recipe downloads.
|
||||
#: This will be used primarily in a GUI that presents a list of recipes.
|
||||
description = (u'The Grid is a weekly city magazine and daily website providing a fresh, '
|
||||
'accessible voice for Toronto.')
|
||||
|
||||
#: The author of this recipe
|
||||
__author__ = u'Yusuf W'
|
||||
|
||||
#: The language that the news is in. Must be an ISO-639 code either
|
||||
#: two or three characters long
|
||||
language = 'en_CA'
|
||||
|
||||
#: Publication type
|
||||
#: Set to newspaper, magazine or blog
|
||||
publication_type = 'newspaper'
|
||||
|
||||
#: Convenient flag to disable loading of stylesheets for websites
|
||||
#: that have overly complex stylesheets unsuitable for conversion
|
||||
#: to ebooks formats
|
||||
#: If True stylesheets are not downloaded and processed
|
||||
no_stylesheets = True
|
||||
|
||||
#: List of tags to be removed. Specified tags are removed from downloaded HTML.
|
||||
remove_tags_before = dict(name='div', id='content')
|
||||
remove_tags_after = dict(name='div', id='content')
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':'right-content pull-right'}),
|
||||
dict(name='div', attrs={'class':'right-content'}),
|
||||
dict(name='div', attrs={'class':'ftr-line'}),
|
||||
dict(name='div', attrs={'class':'pull-right'}),
|
||||
dict(name='div', id='comments'),
|
||||
dict(name='div', id='tags')
|
||||
]
|
||||
|
||||
#: Keep only the specified tags and their children.
|
||||
#keep_only_tags = [dict(name='div', id='content')]
|
||||
|
||||
cover_margins = (0, 0, '#ffffff')
|
||||
|
||||
INDEX = 'http://www.thegridto.com'
|
||||
|
||||
def get_cover_url(self):
|
||||
soup = self.index_to_soup(self.INDEX)
|
||||
cover_url = soup.find(attrs={'class':'article-block latest-issue'}).find('img')['src']
|
||||
|
||||
return cover_url
|
||||
|
||||
def parse_index(self):
|
||||
|
||||
# Get the latest issue
|
||||
soup = self.index_to_soup(self.INDEX)
|
||||
a = soup.find('div', attrs={'class': 'full-content stuff-ftr'}).findAll('a')[2]
|
||||
|
||||
# Parse the index of the latest issue
|
||||
self.INDEX = self.INDEX + a['href']
|
||||
soup = self.index_to_soup(self.INDEX)
|
||||
|
||||
feeds = []
|
||||
for section in ['city', 'life', 'culture']:
|
||||
section_class = 'left-content article-listing ' + section + ' pull-left'
|
||||
div = soup.find(attrs={'class': section_class})
|
||||
|
||||
articles = []
|
||||
for tag in div.findAllNext(attrs={'class':'search-block'}):
|
||||
a = tag.findAll('a', href=True)[1]
|
||||
|
||||
title = self.tag_to_string(a)
|
||||
url = a['href']
|
||||
|
||||
articles.append({'title': title, 'url': url, 'description':'', 'date':''})
|
||||
|
||||
feeds.append((section, articles))
|
||||
return feeds
|
||||
BIN
recipes/icons/folha.png
Normal file
BIN
recipes/icons/folha.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.6 KiB |
@ -20,6 +20,8 @@ class JijiDotCom(BasicNewsRecipe):
|
||||
top_url = 'http://www.jiji.com/'
|
||||
|
||||
feeds = [(u'\u30cb\u30e5\u30fc\u30b9', u'http://www.jiji.com/rss/ranking.rdf')]
|
||||
|
||||
remove_tags_before = dict(id="article-area")
|
||||
remove_tags_after = dict(id="ad_google")
|
||||
|
||||
def get_cover_url(self):
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'Lorenzo Vigentini, based on Darko Miletic, Gabriele Marini'
|
||||
__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>'
|
||||
description = 'Italian daily newspaper - v1.01 (04, January 2010); 16.05.2010 new version; 17.10.2011 new version; 14.12.2011 new version'
|
||||
__author__ = 'Lorenzo Vigentini, based on Darko Miletic, Gabriele Marini; minor fixes by faber1971'
|
||||
__copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>, faber1971'
|
||||
description = 'Italian daily newspaper - v1.02 (04, January 2010); 16.05.2010 new version; 17.10.2011 new version; 14.12.2011 new version; 11.05.2012 new version'
|
||||
|
||||
'''
|
||||
http://www.repubblica.it/
|
||||
@ -12,14 +12,14 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class LaRepubblica(BasicNewsRecipe):
|
||||
title = 'La Repubblica'
|
||||
__author__ = 'Lorenzo Vigentini, Gabriele Marini, Darko Miletic'
|
||||
__author__ = 'Lorenzo Vigentini, Gabriele Marini, Darko Miletic, faber1971'
|
||||
description = 'il quotidiano online con tutte le notizie in tempo reale. News e ultime notizie. Tutti i settori: politica, cronaca, economia, sport, esteri, scienza, tecnologia, internet, spettacoli, musica, cultura, arte, mostre, libri, dvd, vhs, concerti, cinema, attori, attrici, recensioni, chat, cucina, mappe. Le citta di Repubblica: Roma, Milano, Bologna, Firenze, Palermo, Napoli, Bari, Torino.'
|
||||
masthead_url = 'http://www.repubblica.it/static/images/homepage/2010/la-repubblica-logo-home-payoff.png'
|
||||
publisher = 'Gruppo editoriale L\'Espresso'
|
||||
category = 'News, politics, culture, economy, general interest'
|
||||
language = 'it'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
oldest_article = 5
|
||||
oldest_article = 1
|
||||
encoding = 'utf8'
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
@ -59,6 +59,7 @@ class LaRepubblica(BasicNewsRecipe):
|
||||
dict(attrs={'class':'articolo'}),
|
||||
dict(attrs={'class':'body-text'}),
|
||||
dict(name='p', attrs={'class':'disclaimer clearfix'}),
|
||||
dict(name='div', attrs={'id':'main'}),
|
||||
dict(attrs={'id':'contA'})
|
||||
]
|
||||
|
||||
@ -67,7 +68,7 @@ class LaRepubblica(BasicNewsRecipe):
|
||||
dict(name=['object','link','meta','iframe','embed']),
|
||||
dict(name='span',attrs={'class':'linkindice'}),
|
||||
dict(name='div', attrs={'class':['bottom-mobile','adv adv-middle-inline']}),
|
||||
dict(name='div', attrs={'id':['rssdiv','blocco','fb-like-head']}),
|
||||
dict(name='div', attrs={'id':['rssdiv','blocco','fb-like-head', 'sidebar']}),
|
||||
dict(name='div', attrs={'class':['utility','fb-like-button','archive-button']}),
|
||||
dict(name='div', attrs={'class':'generalbox'}),
|
||||
dict(name='ul', attrs={'id':'hystory'})
|
||||
@ -88,11 +89,12 @@ class LaRepubblica(BasicNewsRecipe):
|
||||
(u'Sport', u'http://www.repubblica.it/rss/sport/rss2.0.xml'),
|
||||
(u'Calcio', u'http://www.repubblica.it/rss/sport/calcio/rss2.0.xml'),
|
||||
(u'Motori', u'http://www.repubblica.it/rss/motori/rss2.0.xml'),
|
||||
(u'Edizione Roma', u'http://roma.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Edizione Torino', u'http://torino.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Edizione Milano', u'feed://milano.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Edizione Napoli', u'feed://napoli.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Edizione Palermo', u'feed://palermo.repubblica.it/rss/rss2.0.xml')
|
||||
(u'Roma', u'http://roma.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Torino', u'http://torino.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Milano', u'feed://milano.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Napoli', u'feed://napoli.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Bari', u'http://bari.repubblica.it/rss/rss2.0.xml'),
|
||||
(u'Palermo', u'feed://palermo.repubblica.it/rss/rss2.0.xml')
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
|
||||
@ -16,12 +16,12 @@ class MainichiDailyNews(BasicNewsRecipe):
|
||||
publisher = 'Mainichi Daily News'
|
||||
category = 'news, japan'
|
||||
language = 'ja'
|
||||
|
||||
feeds = [(u'daily news', u'http://mainichi.jp/rss/etc/flash.rss')]
|
||||
index = 'http://mainichi.jp/select/'
|
||||
remove_javascript = True
|
||||
masthead_title = u'MAINICHI DAILY NEWS'
|
||||
|
||||
remove_tags_before = {'class':"NewsTitle"}
|
||||
remove_tags = [{'class':"RelatedArticle"}]
|
||||
remove_tags_after = {'class':"Credit"}
|
||||
remove_tags_after = {'class':"NewsBody clr"}
|
||||
|
||||
def parse_feeds(self):
|
||||
|
||||
@ -32,9 +32,30 @@ class MainichiDailyNews(BasicNewsRecipe):
|
||||
for a,curarticle in enumerate(curfeed.articles):
|
||||
if re.search(r'pheedo.jp', curarticle.url):
|
||||
delList.append(curarticle)
|
||||
if re.search(r'rssad.jp', curarticle.url):
|
||||
delList.append(curarticle)
|
||||
if len(delList)>0:
|
||||
for d in delList:
|
||||
index = curfeed.articles.index(d)
|
||||
curfeed.articles[index:index+1] = []
|
||||
|
||||
return feeds
|
||||
|
||||
def parse_index(self):
|
||||
feeds = []
|
||||
soup = self.index_to_soup(self.index)
|
||||
topstories = soup.find('ul',attrs={'class':'MaiLink'})
|
||||
if topstories:
|
||||
newsarticles = []
|
||||
for itt in topstories.findAll('li'):
|
||||
itema = itt.find('a',href=True)
|
||||
if itema:
|
||||
newsarticles.append({
|
||||
'title' :itema.string
|
||||
,'date' :''
|
||||
,'url' :itema['href']
|
||||
,'description':''
|
||||
})
|
||||
feeds.append(('latest', newsarticles))
|
||||
return feeds
|
||||
|
||||
|
||||
67
recipes/mainichi_en.recipe
Normal file
67
recipes/mainichi_en.recipe
Normal file
@ -0,0 +1,67 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
|
||||
'''
|
||||
www.mainichi.jp
|
||||
'''
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class MainichiEnglishNews(BasicNewsRecipe):
|
||||
title = u'The Mainichi'
|
||||
__author__ = 'Hiroshi Miura'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 40
|
||||
description = 'Japanese traditional newspaper Mainichi news in English'
|
||||
publisher = 'Mainichi News'
|
||||
category = 'news, japan'
|
||||
language = 'en_JP'
|
||||
index = 'http://mainichi.jp/english/english/index.html'
|
||||
remove_javascript = True
|
||||
masthead_url = 'http://mainichi.jp/english/images/themainichi.png'
|
||||
|
||||
remove_tags_before = {'class':"NewsTitle"}
|
||||
remove_tags_after = {'class':"NewsBody clr"}
|
||||
|
||||
def parse_feeds(self):
|
||||
|
||||
feeds = BasicNewsRecipe.parse_feeds(self)
|
||||
|
||||
for curfeed in feeds:
|
||||
delList = []
|
||||
for a,curarticle in enumerate(curfeed.articles):
|
||||
if re.search(r'pheedo.jp', curarticle.url):
|
||||
delList.append(curarticle)
|
||||
if re.search(r'rssad.jp', curarticle.url):
|
||||
delList.append(curarticle)
|
||||
if len(delList)>0:
|
||||
for d in delList:
|
||||
index = curfeed.articles.index(d)
|
||||
curfeed.articles[index:index+1] = []
|
||||
|
||||
return feeds
|
||||
|
||||
def parse_index(self):
|
||||
feeds = []
|
||||
soup = self.index_to_soup(self.index)
|
||||
for section in soup.findAll('section'):
|
||||
newsarticles = []
|
||||
section_name = 'news'
|
||||
hds = section.find('div', attrs={'class':'CategoryHead clr'})
|
||||
if hds:
|
||||
section_item = hds.find('h1')
|
||||
if section_item:
|
||||
section_name = section_item.find('a').string
|
||||
items = section.find('ul', attrs={'class':'MaiLink'})
|
||||
for item in items.findAll('li'):
|
||||
if item:
|
||||
itema = item.find('a')
|
||||
newsarticles.append({
|
||||
'title' :itema.string
|
||||
,'date' :''
|
||||
,'url' :itema['href']
|
||||
,'description':''
|
||||
})
|
||||
feeds.append((section_name, newsarticles))
|
||||
return feeds
|
||||
|
||||
@ -1,34 +0,0 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
class MainichiDailyITNews(BasicNewsRecipe):
|
||||
title = u'\u6bce\u65e5\u65b0\u805e(IT&\u5bb6\u96fb)'
|
||||
__author__ = 'Hiroshi Miura'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
description = 'Japanese traditional newspaper Mainichi Daily News - IT and electronics'
|
||||
publisher = 'Mainichi Daily News'
|
||||
category = 'news, Japan, IT, Electronics'
|
||||
language = 'ja'
|
||||
|
||||
feeds = [(u'IT News', u'http://mainichi.pheedo.jp/f/mainichijp_electronics')]
|
||||
|
||||
remove_tags_before = {'class':"NewsTitle"}
|
||||
remove_tags = [{'class':"RelatedArticle"}]
|
||||
remove_tags_after = {'class':"Credit"}
|
||||
|
||||
def parse_feeds(self):
|
||||
|
||||
feeds = BasicNewsRecipe.parse_feeds(self)
|
||||
|
||||
for curfeed in feeds:
|
||||
delList = []
|
||||
for a,curarticle in enumerate(curfeed.articles):
|
||||
if re.search(r'pheedo.jp', curarticle.url):
|
||||
delList.append(curarticle)
|
||||
if len(delList)>0:
|
||||
for d in delList:
|
||||
index = curfeed.articles.index(d)
|
||||
curfeed.articles[index:index+1] = []
|
||||
|
||||
return feeds
|
||||
59
recipes/mainichi_science_news.recipe
Normal file
59
recipes/mainichi_science_news.recipe
Normal file
@ -0,0 +1,59 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
|
||||
'''
|
||||
www.mainichi.jp
|
||||
'''
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class MainichiDailyScienceNews(BasicNewsRecipe):
|
||||
title = u'\u6bce\u65e5\u65b0\u805e(Science)'
|
||||
__author__ = 'Hiroshi Miura'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 20
|
||||
description = 'Japanese traditional newspaper Mainichi Daily News - science'
|
||||
publisher = 'Mainichi Daily News'
|
||||
category = 'news, japan'
|
||||
language = 'ja'
|
||||
index = 'http://mainichi.jp/select/science'
|
||||
remove_javascript = True
|
||||
masthead_title = u'MAINICHI DAILY NEWS'
|
||||
|
||||
remove_tags_before = {'class':"NewsTitle"}
|
||||
remove_tags_after = {'class':"NewsBody clr"}
|
||||
|
||||
def parse_feeds(self):
|
||||
|
||||
feeds = BasicNewsRecipe.parse_feeds(self)
|
||||
|
||||
for curfeed in feeds:
|
||||
delList = []
|
||||
for a,curarticle in enumerate(curfeed.articles):
|
||||
if re.search(r'rssad.jp', curarticle.url):
|
||||
delList.append(curarticle)
|
||||
if len(delList)>0:
|
||||
for d in delList:
|
||||
index = curfeed.articles.index(d)
|
||||
curfeed.articles[index:index+1] = []
|
||||
|
||||
return feeds
|
||||
|
||||
def parse_index(self):
|
||||
feeds = []
|
||||
soup = self.index_to_soup(self.index)
|
||||
topstories = soup.find('ul',attrs={'class':'MaiLink'})
|
||||
if topstories:
|
||||
newsarticles = []
|
||||
for itt in topstories.findAll('li'):
|
||||
itema = itt.find('a',href=True)
|
||||
if itema:
|
||||
newsarticles.append({
|
||||
'title' :itema.string
|
||||
,'date' :''
|
||||
,'url' :itema['href']
|
||||
,'description':''
|
||||
})
|
||||
feeds.append(('Science', newsarticles))
|
||||
return feeds
|
||||
|
||||
16
recipes/national_geographic_it.recipe
Normal file
16
recipes/national_geographic_it.recipe
Normal file
@ -0,0 +1,16 @@
|
||||
__version__ = 'v1.0'
|
||||
__date__ = '5, May 2012'
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1336226255(BasicNewsRecipe):
|
||||
title = u'National Geographic'
|
||||
__author__ = 'faber1971'
|
||||
description = 'Science magazine'
|
||||
language = 'it'
|
||||
|
||||
oldest_article = 15
|
||||
max_articles_per_feed = 100
|
||||
auto_cleanup = True
|
||||
remove_tags = [dict(name='div',attrs={'class':'banner-abbonamenti'})]
|
||||
feeds = [(u'National Geographic', u'http://www.nationalgeographic.it/rss/all/rss2.0.xml')]
|
||||
@ -1,5 +1,5 @@
|
||||
"""
|
||||
Pocket Calibre Recipe v1.0
|
||||
Pocket Calibre Recipe v1.1
|
||||
"""
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '''
|
||||
@ -73,6 +73,9 @@ class Pocket(BasicNewsRecipe):
|
||||
articles = []
|
||||
soup = self.index_to_soup(feedurl)
|
||||
ritem = soup.find('ul', attrs={'id':'list'})
|
||||
if ritem is None:
|
||||
self.log.exception("Page %s skipped: invalid HTML" % (feedtitle if feedtitle else feedurl))
|
||||
continue
|
||||
for item in reversed(ritem.findAll('li')):
|
||||
if articlesToGrab < 1:
|
||||
break
|
||||
@ -94,7 +97,7 @@ class Pocket(BasicNewsRecipe):
|
||||
self.readList.append(readLink)
|
||||
totalfeeds.append((feedtitle, articles))
|
||||
if len(self.readList) < self.minimum_articles:
|
||||
raise Exception("Not enough articles in RIL! Change minimum_articles or add more.")
|
||||
raise Exception("Not enough articles in Pocket! Change minimum_articles or add more articles.")
|
||||
return totalfeeds
|
||||
|
||||
def mark_as_read(self, markList):
|
||||
|
||||
@ -12,14 +12,14 @@ msgstr ""
|
||||
"Report-Msgid-Bugs-To: Debian iso-codes team <pkg-isocodes-"
|
||||
"devel@lists.alioth.debian.org>\n"
|
||||
"POT-Creation-Date: 2011-11-25 14:01+0000\n"
|
||||
"PO-Revision-Date: 2012-04-28 10:42+0000\n"
|
||||
"Last-Translator: Ferran Rius <frius64@hotmail.com>\n"
|
||||
"PO-Revision-Date: 2012-05-03 16:09+0000\n"
|
||||
"Last-Translator: Dídac Rios <didac@niorcs.com>\n"
|
||||
"Language-Team: Catalan <linux@softcatala.org>\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=UTF-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"X-Launchpad-Export-Date: 2012-04-29 04:45+0000\n"
|
||||
"X-Generator: Launchpad (build 15149)\n"
|
||||
"X-Launchpad-Export-Date: 2012-05-04 04:47+0000\n"
|
||||
"X-Generator: Launchpad (build 15195)\n"
|
||||
"Language: ca\n"
|
||||
|
||||
#. name for aaa
|
||||
@ -9936,11 +9936,11 @@ msgstr "Ibani"
|
||||
|
||||
#. name for ica
|
||||
msgid "Ede Ica"
|
||||
msgstr ""
|
||||
msgstr "Ede Ica"
|
||||
|
||||
#. name for ich
|
||||
msgid "Etkywan"
|
||||
msgstr ""
|
||||
msgstr "Etkywan"
|
||||
|
||||
#. name for icl
|
||||
msgid "Icelandic Sign Language"
|
||||
@ -9952,7 +9952,7 @@ msgstr "Anglès crioll; Islander"
|
||||
|
||||
#. name for ida
|
||||
msgid "Idakho-Isukha-Tiriki"
|
||||
msgstr ""
|
||||
msgstr "Idakho-Isukha-Tiriki"
|
||||
|
||||
#. name for idb
|
||||
msgid "Indo-Portuguese"
|
||||
@ -9960,15 +9960,15 @@ msgstr "Indo-portuguès"
|
||||
|
||||
#. name for idc
|
||||
msgid "Idon"
|
||||
msgstr ""
|
||||
msgstr "Idon"
|
||||
|
||||
#. name for idd
|
||||
msgid "Ede Idaca"
|
||||
msgstr ""
|
||||
msgstr "Ede Idaca"
|
||||
|
||||
#. name for ide
|
||||
msgid "Idere"
|
||||
msgstr ""
|
||||
msgstr "Idere"
|
||||
|
||||
#. name for idi
|
||||
msgid "Idi"
|
||||
@ -9976,43 +9976,43 @@ msgstr ""
|
||||
|
||||
#. name for ido
|
||||
msgid "Ido"
|
||||
msgstr ""
|
||||
msgstr "ido"
|
||||
|
||||
#. name for idr
|
||||
msgid "Indri"
|
||||
msgstr ""
|
||||
msgstr "Indri"
|
||||
|
||||
#. name for ids
|
||||
msgid "Idesa"
|
||||
msgstr ""
|
||||
msgstr "Idesa"
|
||||
|
||||
#. name for idt
|
||||
msgid "Idaté"
|
||||
msgstr ""
|
||||
msgstr "Idaté"
|
||||
|
||||
#. name for idu
|
||||
msgid "Idoma"
|
||||
msgstr ""
|
||||
msgstr "Idoma"
|
||||
|
||||
#. name for ifa
|
||||
msgid "Ifugao; Amganad"
|
||||
msgstr ""
|
||||
msgstr "Ifugao; Amganad"
|
||||
|
||||
#. name for ifb
|
||||
msgid "Ifugao; Batad"
|
||||
msgstr ""
|
||||
msgstr "Ifugao; Batad"
|
||||
|
||||
#. name for ife
|
||||
msgid "Ifè"
|
||||
msgstr ""
|
||||
msgstr "Ifè"
|
||||
|
||||
#. name for iff
|
||||
msgid "Ifo"
|
||||
msgstr ""
|
||||
msgstr "Ifo"
|
||||
|
||||
#. name for ifk
|
||||
msgid "Ifugao; Tuwali"
|
||||
msgstr ""
|
||||
msgstr "Ifugao; Tuwali"
|
||||
|
||||
#. name for ifm
|
||||
msgid "Teke-Fuumu"
|
||||
@ -10020,15 +10020,15 @@ msgstr "Teke; Fuumu"
|
||||
|
||||
#. name for ifu
|
||||
msgid "Ifugao; Mayoyao"
|
||||
msgstr ""
|
||||
msgstr "Ifugao; Mayoyao"
|
||||
|
||||
#. name for ify
|
||||
msgid "Kallahan; Keley-I"
|
||||
msgstr ""
|
||||
msgstr "Kallahan; Keley-I"
|
||||
|
||||
#. name for igb
|
||||
msgid "Ebira"
|
||||
msgstr ""
|
||||
msgstr "Ebira"
|
||||
|
||||
#. name for ige
|
||||
msgid "Igede"
|
||||
|
||||
@ -8,14 +8,14 @@ msgstr ""
|
||||
"Report-Msgid-Bugs-To: Debian iso-codes team <pkg-isocodes-"
|
||||
"devel@lists.alioth.debian.org>\n"
|
||||
"POT-Creation-Date: 2011-11-25 14:01+0000\n"
|
||||
"PO-Revision-Date: 2012-03-25 12:19+0000\n"
|
||||
"Last-Translator: Radan Putnik <srastral@gmail.com>\n"
|
||||
"PO-Revision-Date: 2012-05-03 14:49+0000\n"
|
||||
"Last-Translator: Иван Старчевић <ivanstar61@gmail.com>\n"
|
||||
"Language-Team: Serbian <gnu@prevod.org>\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=UTF-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"X-Launchpad-Export-Date: 2012-03-26 04:37+0000\n"
|
||||
"X-Generator: Launchpad (build 15008)\n"
|
||||
"X-Launchpad-Export-Date: 2012-05-04 04:47+0000\n"
|
||||
"X-Generator: Launchpad (build 15195)\n"
|
||||
"Language: sr\n"
|
||||
|
||||
#. name for aaa
|
||||
@ -6152,7 +6152,7 @@ msgstr ""
|
||||
|
||||
#. name for deu
|
||||
msgid "German"
|
||||
msgstr "немачки"
|
||||
msgstr "Немачки"
|
||||
|
||||
#. name for dev
|
||||
msgid "Domung"
|
||||
@ -8416,7 +8416,7 @@ msgstr "ирски"
|
||||
|
||||
#. name for glg
|
||||
msgid "Galician"
|
||||
msgstr ""
|
||||
msgstr "Галицијски"
|
||||
|
||||
#. name for glh
|
||||
msgid "Pashayi; Northwest"
|
||||
@ -8472,11 +8472,11 @@ msgstr ""
|
||||
|
||||
#. name for gmh
|
||||
msgid "German; Middle High (ca. 1050-1500)"
|
||||
msgstr ""
|
||||
msgstr "Немачки; средње високи (ca. 1050-1500)"
|
||||
|
||||
#. name for gml
|
||||
msgid "German; Middle Low"
|
||||
msgstr ""
|
||||
msgstr "Немачки; средње низак"
|
||||
|
||||
#. name for gmm
|
||||
msgid "Gbaya-Mbodomo"
|
||||
@ -8792,7 +8792,7 @@ msgstr ""
|
||||
|
||||
#. name for gsg
|
||||
msgid "German Sign Language"
|
||||
msgstr ""
|
||||
msgstr "Немачки језик"
|
||||
|
||||
#. name for gsl
|
||||
msgid "Gusilay"
|
||||
@ -8820,7 +8820,7 @@ msgstr ""
|
||||
|
||||
#. name for gsw
|
||||
msgid "German; Swiss"
|
||||
msgstr ""
|
||||
msgstr "Немачки ; Швајцарска"
|
||||
|
||||
#. name for gta
|
||||
msgid "Guató"
|
||||
@ -17954,7 +17954,7 @@ msgstr ""
|
||||
|
||||
#. name for nds
|
||||
msgid "German; Low"
|
||||
msgstr ""
|
||||
msgstr "Немачки; низак"
|
||||
|
||||
#. name for ndt
|
||||
msgid "Ndunga"
|
||||
@ -18778,7 +18778,7 @@ msgstr ""
|
||||
|
||||
#. name for nno
|
||||
msgid "Norwegian Nynorsk"
|
||||
msgstr "норвешки модерни"
|
||||
msgstr "Норвешки модерни"
|
||||
|
||||
#. name for nnp
|
||||
msgid "Naga; Wancho"
|
||||
@ -18830,7 +18830,7 @@ msgstr ""
|
||||
|
||||
#. name for nob
|
||||
msgid "Norwegian Bokmål"
|
||||
msgstr ""
|
||||
msgstr "Норвешки (књижевни)"
|
||||
|
||||
#. name for noc
|
||||
msgid "Nuk"
|
||||
@ -18886,7 +18886,7 @@ msgstr ""
|
||||
|
||||
#. name for nor
|
||||
msgid "Norwegian"
|
||||
msgstr "норвешки"
|
||||
msgstr "Норвешки"
|
||||
|
||||
#. name for nos
|
||||
msgid "Nisu; Eastern"
|
||||
@ -19066,7 +19066,7 @@ msgstr ""
|
||||
|
||||
#. name for nsl
|
||||
msgid "Norwegian Sign Language"
|
||||
msgstr ""
|
||||
msgstr "Норвешки језик"
|
||||
|
||||
#. name for nsm
|
||||
msgid "Naga; Sumi"
|
||||
@ -20406,7 +20406,7 @@ msgstr ""
|
||||
|
||||
#. name for pdc
|
||||
msgid "German; Pennsylvania"
|
||||
msgstr ""
|
||||
msgstr "Немачки ; Пенсилванија"
|
||||
|
||||
#. name for pdi
|
||||
msgid "Pa Di"
|
||||
@ -22086,7 +22086,7 @@ msgstr ""
|
||||
|
||||
#. name for rmg
|
||||
msgid "Norwegian; Traveller"
|
||||
msgstr ""
|
||||
msgstr "Норвешки; путнички"
|
||||
|
||||
#. name for rmh
|
||||
msgid "Murkim"
|
||||
@ -22871,7 +22871,7 @@ msgstr ""
|
||||
|
||||
#. name for sgg
|
||||
msgid "Swiss-German Sign Language"
|
||||
msgstr ""
|
||||
msgstr "Швајцарско-Немачки језик"
|
||||
|
||||
#. name for sgh
|
||||
msgid "Shughni"
|
||||
|
||||
@ -26,7 +26,7 @@ def get_opts_from_parser(parser):
|
||||
class Coffee(Command): # {{{
|
||||
|
||||
description = 'Compile coffeescript files into javascript'
|
||||
COFFEE_DIRS = {'ebooks/oeb/display': 'display'}
|
||||
COFFEE_DIRS = ('ebooks/oeb/display',)
|
||||
|
||||
def add_options(self, parser):
|
||||
parser.add_option('--watch', '-w', action='store_true', default=False,
|
||||
@ -47,47 +47,67 @@ class Coffee(Command): # {{{
|
||||
except KeyboardInterrupt:
|
||||
pass
|
||||
|
||||
def show_js(self, jsfile):
|
||||
def show_js(self, raw):
|
||||
from pygments.lexers import JavascriptLexer
|
||||
from pygments.formatters import TerminalFormatter
|
||||
from pygments import highlight
|
||||
with open(jsfile, 'rb') as f:
|
||||
raw = f.read()
|
||||
print highlight(raw, JavascriptLexer(), TerminalFormatter())
|
||||
|
||||
def do_coffee_compile(self, opts, timestamp=False, ignore_errors=False):
|
||||
for toplevel, dest in self.COFFEE_DIRS.iteritems():
|
||||
dest = self.j(self.RESOURCES, dest)
|
||||
for x in glob.glob(self.j(self.SRC, __appname__, toplevel, '*.coffee')):
|
||||
js = self.j(dest, os.path.basename(x.rpartition('.')[0]+'.js'))
|
||||
if self.newer(js, x):
|
||||
src_files = {}
|
||||
for src in self.COFFEE_DIRS:
|
||||
for f in glob.glob(self.j(self.SRC, __appname__, src,
|
||||
'*.coffee')):
|
||||
bn = os.path.basename(f).rpartition('.')[0]
|
||||
arcname = src.replace('/', '.') + '.' + bn + '.js'
|
||||
src_files[arcname] = (f, os.stat(f).st_mtime)
|
||||
|
||||
existing = {}
|
||||
dest = self.j(self.RESOURCES, 'compiled_coffeescript.zip')
|
||||
if os.path.exists(dest):
|
||||
with zipfile.ZipFile(dest, 'r') as zf:
|
||||
for info in zf.infolist():
|
||||
mtime = time.mktime(info.date_time + (0, 0, -1))
|
||||
arcname = info.filename
|
||||
if (arcname in src_files and src_files[arcname][1] <
|
||||
mtime):
|
||||
existing[arcname] = (zf.read(info), info)
|
||||
|
||||
todo = set(src_files) - set(existing)
|
||||
updated = {}
|
||||
for arcname in todo:
|
||||
name = arcname.rpartition('.')[0]
|
||||
print ('\t%sCompiling %s'%(time.strftime('[%H:%M:%S] ') if
|
||||
timestamp else '', os.path.basename(x)))
|
||||
timestamp else '', name))
|
||||
src = src_files[arcname][0]
|
||||
try:
|
||||
cs = subprocess.check_output(self.compiler +
|
||||
[x]).decode('utf-8')
|
||||
js = subprocess.check_output(self.compiler +
|
||||
[src]).decode('utf-8')
|
||||
except Exception as e:
|
||||
print ('\n\tCompilation of %s failed'%os.path.basename(x))
|
||||
print ('\n\tCompilation of %s failed'%name)
|
||||
print (e)
|
||||
if ignore_errors:
|
||||
with open(js, 'wb') as f:
|
||||
f.write('# Compilation from coffeescript failed')
|
||||
js = u'# Compilation from coffeescript failed'
|
||||
else:
|
||||
raise SystemExit(1)
|
||||
else:
|
||||
with open(js, 'wb') as f:
|
||||
f.write(cs.encode('utf-8'))
|
||||
if opts.show_js:
|
||||
self.show_js(js)
|
||||
print ('#'*80)
|
||||
print ('#'*80)
|
||||
zi = zipfile.ZipInfo()
|
||||
zi.filename = arcname
|
||||
zi.date_time = time.localtime()[:6]
|
||||
updated[arcname] = (js.encode('utf-8'), zi)
|
||||
if updated:
|
||||
with zipfile.ZipFile(dest, 'w', zipfile.ZIP_STORED) as zf:
|
||||
for raw, zi in updated.itervalues():
|
||||
zf.writestr(zi, raw)
|
||||
for raw, zi in existing.itervalues():
|
||||
zf.writestr(zi, raw)
|
||||
|
||||
def clean(self):
|
||||
for toplevel, dest in self.COFFEE_DIRS.iteritems():
|
||||
dest = self.j(self.RESOURCES, dest)
|
||||
for x in glob.glob(self.j(self.SRC, __appname__, toplevel, '*.coffee')):
|
||||
x = x.rpartition('.')[0] + '.js'
|
||||
x = self.j(dest, os.path.basename(x))
|
||||
x = self.j(self.RESOURCES, 'compiled_coffeescript.zip')
|
||||
if os.path.exists(x):
|
||||
os.remove(x)
|
||||
# }}}
|
||||
|
||||
@ -4,7 +4,7 @@ __license__ = 'GPL v3'
|
||||
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
__appname__ = u'calibre'
|
||||
numeric_version = (0, 8, 50)
|
||||
numeric_version = (0, 8, 51)
|
||||
__version__ = u'.'.join(map(unicode, numeric_version))
|
||||
__author__ = u"Kovid Goyal <kovid@kovidgoyal.net>"
|
||||
|
||||
|
||||
@ -57,6 +57,7 @@ class ANDROID(USBMS):
|
||||
0x4316 : [0x216],
|
||||
0x42d6 : [0x216],
|
||||
0x42d7 : [0x216],
|
||||
0x42f7 : [0x216],
|
||||
},
|
||||
# Freescale
|
||||
0x15a2 : {
|
||||
@ -193,7 +194,7 @@ class ANDROID(USBMS):
|
||||
'GT-I9003_CARD', 'XT912', 'FILE-CD_GADGET', 'RK29_SDK', 'MB855',
|
||||
'XT910', 'BOOK_A10', 'USB_2.0_DRIVER', 'I9100T', 'P999DW',
|
||||
'KTABLET_PC', 'INGENIC', 'GT-I9001_CARD', 'USB_2.0_DRIVER',
|
||||
'GT-S5830L_CARD', 'UNIVERSE']
|
||||
'GT-S5830L_CARD', 'UNIVERSE', 'XT875']
|
||||
WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897',
|
||||
'FILE-STOR_GADGET', 'SGH-T959_CARD', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD',
|
||||
'A70S', 'A101IT', '7', 'INCREDIBLE', 'A7EB', 'SGH-T849_CARD',
|
||||
@ -201,7 +202,7 @@ class ANDROID(USBMS):
|
||||
'ANDROID_MID', 'P990_SD_CARD', '.K080', 'LTE_CARD', 'MB853',
|
||||
'A1-07___C0541A4F', 'XT912', 'MB855', 'XT910', 'BOOK_A10_CARD',
|
||||
'USB_2.0_DRIVER', 'I9100T', 'P999DW_SD_CARD', 'KTABLET_PC',
|
||||
'FILE-CD_GADGET', 'GT-I9001_CARD', 'USB_2.0_DRIVER']
|
||||
'FILE-CD_GADGET', 'GT-I9001_CARD', 'USB_2.0_DRIVER', 'XT875']
|
||||
|
||||
OSX_MAIN_MEM = 'Android Device Main Memory'
|
||||
|
||||
|
||||
@ -92,6 +92,10 @@ class POCKETBOOK360(EB600):
|
||||
name = 'PocketBook 360 Device Interface'
|
||||
|
||||
gui_name = 'PocketBook 360'
|
||||
VENDOR_ID = [0x1f85, 0x525]
|
||||
PRODUCT_ID = [0x1688, 0xa4a5]
|
||||
BCD = [0x110]
|
||||
|
||||
|
||||
FORMATS = ['epub', 'fb2', 'prc', 'mobi', 'pdf', 'djvu', 'rtf', 'chm', 'txt']
|
||||
|
||||
|
||||
@ -12,7 +12,7 @@ class MOBIInput(InputFormatPlugin):
|
||||
name = 'MOBI Input'
|
||||
author = 'Kovid Goyal'
|
||||
description = 'Convert MOBI files (.mobi, .prc, .azw) to HTML'
|
||||
file_types = set(['mobi', 'prc', 'azw', 'azw3'])
|
||||
file_types = set(['mobi', 'prc', 'azw', 'azw3', 'pobi'])
|
||||
|
||||
def convert(self, stream, options, file_ext, log,
|
||||
accelerators):
|
||||
|
||||
@ -306,6 +306,11 @@ class MOBIHeader(object): # {{{
|
||||
self.extra_data_flags = 0
|
||||
if self.has_extra_data_flags:
|
||||
self.unknown4 = self.raw[184:192]
|
||||
if self.file_version < 8:
|
||||
self.first_text_record, self.last_text_record = \
|
||||
struct.unpack_from(b'>HH', self.raw, 192)
|
||||
self.fdst_count = struct.unpack_from(b'>L', self.raw, 196)
|
||||
else:
|
||||
self.fdst_idx, self.fdst_count = struct.unpack_from(b'>LL',
|
||||
self.raw, 192)
|
||||
if self.fdst_count <= 1:
|
||||
@ -409,6 +414,10 @@ class MOBIHeader(object): # {{{
|
||||
a('DRM Flags: %r'%self.drm_flags)
|
||||
if self.has_extra_data_flags:
|
||||
a('Unknown4: %r'%self.unknown4)
|
||||
if hasattr(self, 'first_text_record'):
|
||||
a('First content record: %d'%self.first_text_record)
|
||||
a('Last content record: %d'%self.last_text_record)
|
||||
else:
|
||||
r('FDST Index', 'fdst_idx')
|
||||
a('FDST Count: %d'% self.fdst_count)
|
||||
r('FCIS number', 'fcis_number')
|
||||
|
||||
@ -111,7 +111,11 @@ def update_flow_links(mobi8_reader, resource_map, log):
|
||||
continue
|
||||
|
||||
if not isinstance(flow, unicode):
|
||||
try:
|
||||
flow = flow.decode(mr.header.codec)
|
||||
except UnicodeDecodeError:
|
||||
log.error('Flow part has invalid %s encoded bytes'%mr.header.codec)
|
||||
flow = flow.decode(mr.header.codec, 'replace')
|
||||
|
||||
# links to raster image files from image tags
|
||||
# image_pattern
|
||||
|
||||
@ -207,9 +207,9 @@ class Mobi8Reader(object):
|
||||
fname = 'svgimg' + nstr + '.svg'
|
||||
else:
|
||||
# search for CDATA and if exists inline it
|
||||
if flowpart.find('[CDATA[') >= 0:
|
||||
if flowpart.find(b'[CDATA[') >= 0:
|
||||
typ = 'css'
|
||||
flowpart = '<style type="text/css">\n' + flowpart + '\n</style>\n'
|
||||
flowpart = b'<style type="text/css">\n' + flowpart + b'\n</style>\n'
|
||||
format = 'inline'
|
||||
dir = None
|
||||
fname = None
|
||||
|
||||
@ -382,6 +382,7 @@ class MobiWriter(object):
|
||||
first_image_record = len(self.records)
|
||||
self.resources.serialize(self.records, used_images)
|
||||
resource_record_count = len(self.records) - old
|
||||
last_content_record = len(self.records) - 1
|
||||
|
||||
# FCIS/FLIS (Seems to serve no purpose)
|
||||
flis_number = len(self.records)
|
||||
@ -406,7 +407,7 @@ class MobiWriter(object):
|
||||
# header
|
||||
header_fields['first_resource_record'] = first_image_record
|
||||
header_fields['exth_flags'] = 0b100001010000 # Kinglegen uses this
|
||||
header_fields['fdst_record'] = NULL_INDEX
|
||||
header_fields['fdst_record'] = pack(b'>HH', 1, last_content_record)
|
||||
header_fields['fdst_count'] = 1 # Why not 0? Kindlegen uses 1
|
||||
header_fields['flis_record'] = flis_number
|
||||
header_fields['fcis_record'] = fcis_number
|
||||
|
||||
@ -314,9 +314,9 @@ class KF8Writer(object):
|
||||
return
|
||||
|
||||
# Flatten the ToC into a depth first list
|
||||
fl = toc.iter() if is_periodical else toc.iterdescendants()
|
||||
fl = toc.iterdescendants()
|
||||
for i, item in enumerate(fl):
|
||||
entry = {'id': id(item), 'index': i, 'href':item.href,
|
||||
entry = {'id': id(item), 'index': i, 'href':item.href or '',
|
||||
'label':(item.title or _('Unknown')),
|
||||
'children':[]}
|
||||
entry['depth'] = getattr(item, 'ncx_hlvl', 0)
|
||||
|
||||
@ -138,6 +138,8 @@ class MOBIHeader(Header): # {{{
|
||||
unknown2 = zeroes(8)
|
||||
|
||||
# 192: FDST
|
||||
# In MOBI 6 the fdst record is instead two two byte fields storing the
|
||||
# index of the first and last content records
|
||||
fdst_record = DYN
|
||||
fdst_count = DYN
|
||||
|
||||
|
||||
@ -389,8 +389,17 @@ class CanonicalFragmentIdentifier
|
||||
# Drill down into iframes, etc.
|
||||
while true
|
||||
target = cdoc.elementFromPoint x, y
|
||||
if not target or target.localName == 'html'
|
||||
log("No element at (#{ x }, #{ y })")
|
||||
if not target or target.localName in ['html', 'body']
|
||||
# We ignore both html and body even though body could
|
||||
# have text nodes under it as performance is very poor if body
|
||||
# has large margins/padding (for e.g. in fullscreen mode)
|
||||
# A possible solution for this is to wrap all text node
|
||||
# children of body in <span> but that is seriously ugly and
|
||||
# might have side effects. Lets do this only if there are lots of
|
||||
# books in the wild that actually have text children of body,
|
||||
# and even in this case it might be better to change the input
|
||||
# plugin to prevent this from happening.
|
||||
# log("No element at (#{ x }, #{ y })")
|
||||
return null
|
||||
|
||||
name = target.localName
|
||||
|
||||
76
src/calibre/ebooks/oeb/display/indexing.coffee
Normal file
76
src/calibre/ebooks/oeb/display/indexing.coffee
Normal file
@ -0,0 +1,76 @@
|
||||
#!/usr/bin/env coffee
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
|
||||
|
||||
###
|
||||
Copyright 2012, Kovid Goyal <kovid@kovidgoyal.net>
|
||||
Released under the GPLv3 License
|
||||
###
|
||||
|
||||
body_height = () ->
|
||||
db = document.body
|
||||
dde = document.documentElement
|
||||
if db? and dde?
|
||||
return Math.max(db.scrollHeight, dde.scrollHeight, db.offsetHeight,
|
||||
dde.offsetHeight, db.clientHeight, dde.clientHeight)
|
||||
return 0
|
||||
|
||||
abstop = (elem) ->
|
||||
ans = elem.offsetTop
|
||||
while elem.offsetParent
|
||||
elem = elem.offsetParent
|
||||
ans += elem.offsetTop
|
||||
return ans
|
||||
|
||||
class BookIndexing
|
||||
###
|
||||
This class is a namespace to expose indexing functions via the
|
||||
window.book_indexing object. The most important functions are:
|
||||
|
||||
anchor_positions(): Get the absolute (document co-ordinate system) position
|
||||
for elements with the specified id/name attributes.
|
||||
|
||||
###
|
||||
|
||||
constructor: () ->
|
||||
this.cache = {}
|
||||
this.body_height_at_last_check = null
|
||||
|
||||
cache_valid: (anchors) ->
|
||||
for a in anchors
|
||||
if not Object.prototype.hasOwnProperty.call(this.cache, a)
|
||||
return false
|
||||
for p of this.cache
|
||||
if Object.prototype.hasOwnProperty.call(this.cache, p) and p not in anchors
|
||||
return false
|
||||
return true
|
||||
|
||||
anchor_positions: (anchors, use_cache=false) ->
|
||||
if use_cache and body_height() == this.body_height_at_last_check and this.cache_valid(anchors)
|
||||
return this.cache
|
||||
|
||||
ans = {}
|
||||
for anchor in anchors
|
||||
elem = document.getElementById(anchor)
|
||||
if elem == null
|
||||
# Look for an <a name="anchor"> element
|
||||
try
|
||||
result = document.evaluate(
|
||||
".//*[local-name() = 'a' and @name='#{ anchor }']",
|
||||
document.body, null,
|
||||
XPathResult.FIRST_ORDERED_NODE_TYPE, null)
|
||||
elem = result.singleNodeValue
|
||||
catch error
|
||||
# The anchor had a ' or other invalid char
|
||||
elem = null
|
||||
if elem == null
|
||||
pos = body_height() + 10000
|
||||
else
|
||||
pos = abstop(elem)
|
||||
ans[anchor] = pos
|
||||
this.cache = ans
|
||||
this.body_height_at_last_check = body_height()
|
||||
return ans
|
||||
|
||||
if window?
|
||||
window.book_indexing = new BookIndexing()
|
||||
|
||||
@ -1,383 +0,0 @@
|
||||
from __future__ import with_statement
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2008 Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
|
||||
'''
|
||||
Iterate over the HTML files in an ebook. Useful for writing viewers.
|
||||
'''
|
||||
|
||||
import re, os, math
|
||||
from cStringIO import StringIO
|
||||
|
||||
from PyQt4.Qt import QFontDatabase
|
||||
|
||||
from calibre.customize.ui import available_input_formats
|
||||
from calibre.ebooks.metadata.opf2 import OPF
|
||||
from calibre.ptempfile import TemporaryDirectory
|
||||
from calibre.ebooks.chardet import xml_to_unicode
|
||||
from calibre.utils.zipfile import safe_replace
|
||||
from calibre.utils.config import DynamicConfig
|
||||
from calibre.utils.logging import Log
|
||||
from calibre import (guess_type, prints, prepare_string_for_xml,
|
||||
xml_replace_entities)
|
||||
from calibre.ebooks.oeb.transforms.cover import CoverManager
|
||||
from calibre.constants import filesystem_encoding
|
||||
|
||||
TITLEPAGE = CoverManager.SVG_TEMPLATE.decode('utf-8').replace(\
|
||||
'__ar__', 'none').replace('__viewbox__', '0 0 600 800'
|
||||
).replace('__width__', '600').replace('__height__', '800')
|
||||
BM_FIELD_SEP = u'*|!|?|*'
|
||||
BM_LEGACY_ESC = u'esc-text-%&*#%(){}ads19-end-esc'
|
||||
|
||||
def character_count(html):
|
||||
'''
|
||||
Return the number of "significant" text characters in a HTML string.
|
||||
'''
|
||||
count = 0
|
||||
strip_space = re.compile(r'\s+')
|
||||
for match in re.finditer(r'>[^<]+<', html):
|
||||
count += len(strip_space.sub(' ', match.group()))-2
|
||||
return count
|
||||
|
||||
class UnsupportedFormatError(Exception):
|
||||
|
||||
def __init__(self, fmt):
|
||||
Exception.__init__(self, _('%s format books are not supported')%fmt.upper())
|
||||
|
||||
class SpineItem(unicode):
|
||||
|
||||
def __new__(cls, path, mime_type=None):
|
||||
ppath = path.partition('#')[0]
|
||||
if not os.path.exists(path) and os.path.exists(ppath):
|
||||
path = ppath
|
||||
obj = super(SpineItem, cls).__new__(cls, path)
|
||||
raw = open(path, 'rb').read()
|
||||
raw, obj.encoding = xml_to_unicode(raw)
|
||||
obj.character_count = character_count(raw)
|
||||
obj.start_page = -1
|
||||
obj.pages = -1
|
||||
obj.max_page = -1
|
||||
if mime_type is None:
|
||||
mime_type = guess_type(obj)[0]
|
||||
obj.mime_type = mime_type
|
||||
return obj
|
||||
|
||||
class FakeOpts(object):
|
||||
verbose = 0
|
||||
breadth_first = False
|
||||
max_levels = 5
|
||||
input_encoding = None
|
||||
|
||||
def is_supported(path):
|
||||
ext = os.path.splitext(path)[1].replace('.', '').lower()
|
||||
ext = re.sub(r'(x{0,1})htm(l{0,1})', 'html', ext)
|
||||
return ext in available_input_formats()
|
||||
|
||||
|
||||
def write_oebbook(oeb, path):
|
||||
from calibre.ebooks.oeb.writer import OEBWriter
|
||||
from calibre import walk
|
||||
w = OEBWriter()
|
||||
w(oeb, path)
|
||||
for f in walk(path):
|
||||
if f.endswith('.opf'):
|
||||
return f
|
||||
|
||||
class EbookIterator(object):
|
||||
|
||||
CHARACTERS_PER_PAGE = 1000
|
||||
|
||||
def __init__(self, pathtoebook, log=None):
|
||||
self.log = log
|
||||
if log is None:
|
||||
self.log = Log()
|
||||
pathtoebook = pathtoebook.strip()
|
||||
self.pathtoebook = os.path.abspath(pathtoebook)
|
||||
self.config = DynamicConfig(name='iterator')
|
||||
ext = os.path.splitext(pathtoebook)[1].replace('.', '').lower()
|
||||
ext = re.sub(r'(x{0,1})htm(l{0,1})', 'html', ext)
|
||||
self.ebook_ext = ext.replace('original_', '')
|
||||
|
||||
def search(self, text, index, backwards=False):
|
||||
text = prepare_string_for_xml(text.lower())
|
||||
pmap = [(i, path) for i, path in enumerate(self.spine)]
|
||||
if backwards:
|
||||
pmap.reverse()
|
||||
for i, path in pmap:
|
||||
if (backwards and i < index) or (not backwards and i > index):
|
||||
with open(path, 'rb') as f:
|
||||
raw = f.read().decode(path.encoding)
|
||||
try:
|
||||
raw = xml_replace_entities(raw)
|
||||
except:
|
||||
pass
|
||||
if text in raw.lower():
|
||||
return i
|
||||
|
||||
def find_missing_css_files(self):
|
||||
for x in os.walk(os.path.dirname(self.pathtoopf)):
|
||||
for f in x[-1]:
|
||||
if f.endswith('.css'):
|
||||
yield os.path.join(x[0], f)
|
||||
|
||||
def find_declared_css_files(self):
|
||||
for item in self.opf.manifest:
|
||||
if item.mime_type and 'css' in item.mime_type.lower():
|
||||
yield item.path
|
||||
|
||||
def find_embedded_fonts(self):
|
||||
'''
|
||||
This will become unnecessary once Qt WebKit supports the @font-face rule.
|
||||
'''
|
||||
css_files = set(self.find_declared_css_files())
|
||||
if not css_files:
|
||||
css_files = set(self.find_missing_css_files())
|
||||
bad_map = {}
|
||||
font_family_pat = re.compile(r'font-family\s*:\s*([^;]+)')
|
||||
for csspath in css_files:
|
||||
try:
|
||||
css = open(csspath, 'rb').read().decode('utf-8', 'replace')
|
||||
except:
|
||||
continue
|
||||
for match in re.compile(r'@font-face\s*{([^}]+)}').finditer(css):
|
||||
block = match.group(1)
|
||||
family = font_family_pat.search(block)
|
||||
url = re.compile(r'url\s*\([\'"]*(.+?)[\'"]*\)', re.DOTALL).search(block)
|
||||
if url:
|
||||
path = url.group(1).split('/')
|
||||
path = os.path.join(os.path.dirname(csspath), *path)
|
||||
if not os.access(path, os.R_OK):
|
||||
continue
|
||||
id = QFontDatabase.addApplicationFont(path)
|
||||
if id != -1:
|
||||
families = [unicode(f) for f in QFontDatabase.applicationFontFamilies(id)]
|
||||
if family:
|
||||
family = family.group(1)
|
||||
specified_families = [x.strip().replace('"',
|
||||
'').replace("'", '') for x in family.split(',')]
|
||||
aliasing_ok = False
|
||||
for f in specified_families:
|
||||
bad_map[f] = families[0]
|
||||
if not aliasing_ok and f in families:
|
||||
aliasing_ok = True
|
||||
|
||||
if not aliasing_ok:
|
||||
prints('WARNING: Family aliasing not fully supported.')
|
||||
prints('\tDeclared family: %r not in actual families: %r'
|
||||
% (family, families))
|
||||
else:
|
||||
prints('Loaded embedded font:', repr(family))
|
||||
if bad_map:
|
||||
def prepend_embedded_font(match):
|
||||
for bad, good in bad_map.items():
|
||||
if bad in match.group(1):
|
||||
prints('Substituting font family: %s -> %s'%(bad, good))
|
||||
return match.group().replace(bad, '"%s"'%good)
|
||||
|
||||
from calibre.ebooks.chardet import force_encoding
|
||||
for csspath in css_files:
|
||||
with open(csspath, 'r+b') as f:
|
||||
css = f.read()
|
||||
enc = force_encoding(css, False)
|
||||
css = css.decode(enc, 'replace')
|
||||
ncss = font_family_pat.sub(prepend_embedded_font, css)
|
||||
if ncss != css:
|
||||
f.seek(0)
|
||||
f.truncate()
|
||||
f.write(ncss.encode(enc))
|
||||
|
||||
def __enter__(self, processed=False, only_input_plugin=False):
|
||||
self.delete_on_exit = []
|
||||
self._tdir = TemporaryDirectory('_ebook_iter')
|
||||
self.base = self._tdir.__enter__()
|
||||
if not isinstance(self.base, unicode):
|
||||
self.base = self.base.decode(filesystem_encoding)
|
||||
from calibre.ebooks.conversion.plumber import Plumber, create_oebbook
|
||||
plumber = Plumber(self.pathtoebook, self.base, self.log)
|
||||
plumber.setup_options()
|
||||
if self.pathtoebook.lower().endswith('.opf'):
|
||||
plumber.opts.dont_package = True
|
||||
if hasattr(plumber.opts, 'no_process'):
|
||||
plumber.opts.no_process = True
|
||||
|
||||
plumber.input_plugin.for_viewer = True
|
||||
with plumber.input_plugin:
|
||||
self.pathtoopf = plumber.input_plugin(open(plumber.input, 'rb'),
|
||||
plumber.opts, plumber.input_fmt, self.log,
|
||||
{}, self.base)
|
||||
|
||||
if not only_input_plugin:
|
||||
if processed or plumber.input_fmt.lower() in ('pdb', 'pdf', 'rb') and \
|
||||
not hasattr(self.pathtoopf, 'manifest'):
|
||||
if hasattr(self.pathtoopf, 'manifest'):
|
||||
self.pathtoopf = write_oebbook(self.pathtoopf, self.base)
|
||||
self.pathtoopf = create_oebbook(self.log, self.pathtoopf,
|
||||
plumber.opts)
|
||||
|
||||
if hasattr(self.pathtoopf, 'manifest'):
|
||||
self.pathtoopf = write_oebbook(self.pathtoopf, self.base)
|
||||
|
||||
self.book_format = os.path.splitext(self.pathtoebook)[1][1:].upper()
|
||||
if getattr(plumber.input_plugin, 'is_kf8', False):
|
||||
self.book_format = 'KF8'
|
||||
|
||||
self.opf = getattr(plumber.input_plugin, 'optimize_opf_parsing', None)
|
||||
if self.opf is None:
|
||||
self.opf = OPF(self.pathtoopf, os.path.dirname(self.pathtoopf))
|
||||
self.language = self.opf.language
|
||||
if self.language:
|
||||
self.language = self.language.lower()
|
||||
ordered = [i for i in self.opf.spine if i.is_linear] + \
|
||||
[i for i in self.opf.spine if not i.is_linear]
|
||||
self.spine = []
|
||||
for i in ordered:
|
||||
spath = i.path
|
||||
mt = None
|
||||
if i.idref is not None:
|
||||
mt = self.opf.manifest.type_for_id(i.idref)
|
||||
if mt is None:
|
||||
mt = guess_type(spath)[0]
|
||||
try:
|
||||
self.spine.append(SpineItem(spath, mime_type=mt))
|
||||
except:
|
||||
self.log.warn('Missing spine item:', repr(spath))
|
||||
|
||||
cover = self.opf.cover
|
||||
if self.ebook_ext in ('lit', 'mobi', 'prc', 'opf', 'fb2') and cover:
|
||||
cfile = os.path.join(self.base, 'calibre_iterator_cover.html')
|
||||
rcpath = os.path.relpath(cover, self.base).replace(os.sep, '/')
|
||||
chtml = (TITLEPAGE%prepare_string_for_xml(rcpath, True)).encode('utf-8')
|
||||
open(cfile, 'wb').write(chtml)
|
||||
self.spine[0:0] = [SpineItem(cfile,
|
||||
mime_type='application/xhtml+xml')]
|
||||
self.delete_on_exit.append(cfile)
|
||||
|
||||
if self.opf.path_to_html_toc is not None and \
|
||||
self.opf.path_to_html_toc not in self.spine:
|
||||
try:
|
||||
self.spine.append(SpineItem(self.opf.path_to_html_toc))
|
||||
except:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
|
||||
|
||||
sizes = [i.character_count for i in self.spine]
|
||||
self.pages = [math.ceil(i/float(self.CHARACTERS_PER_PAGE)) for i in sizes]
|
||||
for p, s in zip(self.pages, self.spine):
|
||||
s.pages = p
|
||||
start = 1
|
||||
|
||||
for s in self.spine:
|
||||
s.start_page = start
|
||||
start += s.pages
|
||||
s.max_page = s.start_page + s.pages - 1
|
||||
self.toc = self.opf.toc
|
||||
|
||||
self.read_bookmarks()
|
||||
|
||||
return self
|
||||
|
||||
def parse_bookmarks(self, raw):
|
||||
for line in raw.splitlines():
|
||||
bm = None
|
||||
if line.count('^') > 0:
|
||||
tokens = line.rpartition('^')
|
||||
title, ref = tokens[0], tokens[2]
|
||||
try:
|
||||
spine, _, pos = ref.partition('#')
|
||||
spine = int(spine.strip())
|
||||
except:
|
||||
continue
|
||||
bm = {'type':'legacy', 'title':title, 'spine':spine, 'pos':pos}
|
||||
elif BM_FIELD_SEP in line:
|
||||
try:
|
||||
title, spine, pos = line.strip().split(BM_FIELD_SEP)
|
||||
spine = int(spine)
|
||||
except:
|
||||
continue
|
||||
# Unescape from serialization
|
||||
pos = pos.replace(BM_LEGACY_ESC, u'^')
|
||||
# Check for pos being a scroll fraction
|
||||
try:
|
||||
pos = float(pos)
|
||||
except:
|
||||
pass
|
||||
bm = {'type':'cfi', 'title':title, 'pos':pos, 'spine':spine}
|
||||
|
||||
if bm:
|
||||
self.bookmarks.append(bm)
|
||||
|
||||
def serialize_bookmarks(self, bookmarks):
|
||||
dat = []
|
||||
for bm in bookmarks:
|
||||
if bm['type'] == 'legacy':
|
||||
rec = u'%s^%d#%s'%(bm['title'], bm['spine'], bm['pos'])
|
||||
else:
|
||||
pos = bm['pos']
|
||||
if isinstance(pos, (int, float)):
|
||||
pos = unicode(pos)
|
||||
else:
|
||||
pos = pos.replace(u'^', BM_LEGACY_ESC)
|
||||
rec = BM_FIELD_SEP.join([bm['title'], unicode(bm['spine']), pos])
|
||||
dat.append(rec)
|
||||
return (u'\n'.join(dat) +u'\n')
|
||||
|
||||
def read_bookmarks(self):
|
||||
self.bookmarks = []
|
||||
bmfile = os.path.join(self.base, 'META-INF', 'calibre_bookmarks.txt')
|
||||
raw = ''
|
||||
if os.path.exists(bmfile):
|
||||
with open(bmfile, 'rb') as f:
|
||||
raw = f.read()
|
||||
else:
|
||||
saved = self.config['bookmarks_'+self.pathtoebook]
|
||||
if saved:
|
||||
raw = saved
|
||||
if not isinstance(raw, unicode):
|
||||
raw = raw.decode('utf-8')
|
||||
self.parse_bookmarks(raw)
|
||||
|
||||
def save_bookmarks(self, bookmarks=None):
|
||||
if bookmarks is None:
|
||||
bookmarks = self.bookmarks
|
||||
dat = self.serialize_bookmarks(bookmarks)
|
||||
if os.path.splitext(self.pathtoebook)[1].lower() == '.epub' and \
|
||||
os.access(self.pathtoebook, os.R_OK):
|
||||
try:
|
||||
zf = open(self.pathtoebook, 'r+b')
|
||||
except IOError:
|
||||
return
|
||||
safe_replace(zf, 'META-INF/calibre_bookmarks.txt',
|
||||
StringIO(dat.encode('utf-8')),
|
||||
add_missing=True)
|
||||
else:
|
||||
self.config['bookmarks_'+self.pathtoebook] = dat
|
||||
|
||||
def add_bookmark(self, bm):
|
||||
self.bookmarks = [x for x in self.bookmarks if x['title'] !=
|
||||
bm['title']]
|
||||
self.bookmarks.append(bm)
|
||||
self.save_bookmarks()
|
||||
|
||||
def set_bookmarks(self, bookmarks):
|
||||
self.bookmarks = bookmarks
|
||||
|
||||
def __exit__(self, *args):
|
||||
self._tdir.__exit__(*args)
|
||||
for x in self.delete_on_exit:
|
||||
if os.path.exists(x):
|
||||
os.remove(x)
|
||||
|
||||
def get_preprocess_html(path_to_ebook, output):
|
||||
from calibre.ebooks.conversion.preprocess import HTMLPreProcessor
|
||||
iterator = EbookIterator(path_to_ebook)
|
||||
iterator.__enter__(only_input_plugin=True)
|
||||
preprocessor = HTMLPreProcessor(None, False)
|
||||
with open(output, 'wb') as out:
|
||||
for path in iterator.spine:
|
||||
with open(path, 'rb') as f:
|
||||
html = f.read().decode('utf-8', 'replace')
|
||||
html = preprocessor(html, get_preprocess_html=True)
|
||||
out.write(html.encode('utf-8'))
|
||||
out.write(b'\n\n' + b'-'*80 + b'\n\n')
|
||||
|
||||
42
src/calibre/ebooks/oeb/iterator/__init__.py
Normal file
42
src/calibre/ebooks/oeb/iterator/__init__.py
Normal file
@ -0,0 +1,42 @@
|
||||
#!/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__ = '2012, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import os, re
|
||||
|
||||
from calibre.customize.ui import available_input_formats
|
||||
|
||||
def is_supported(path):
|
||||
ext = os.path.splitext(path)[1].replace('.', '').lower()
|
||||
ext = re.sub(r'(x{0,1})htm(l{0,1})', 'html', ext)
|
||||
return ext in available_input_formats()
|
||||
|
||||
class UnsupportedFormatError(Exception):
|
||||
|
||||
def __init__(self, fmt):
|
||||
Exception.__init__(self, _('%s format books are not supported')%fmt.upper())
|
||||
|
||||
def EbookIterator(*args, **kwargs):
|
||||
'For backwards compatibility'
|
||||
from calibre.ebooks.oeb.iterator.book import EbookIterator
|
||||
return EbookIterator(*args, **kwargs)
|
||||
|
||||
def get_preprocess_html(path_to_ebook, output):
|
||||
from calibre.ebooks.conversion.preprocess import HTMLPreProcessor
|
||||
iterator = EbookIterator(path_to_ebook)
|
||||
iterator.__enter__(only_input_plugin=True, run_char_count=False,
|
||||
read_anchor_map=False)
|
||||
preprocessor = HTMLPreProcessor(None, False)
|
||||
with open(output, 'wb') as out:
|
||||
for path in iterator.spine:
|
||||
with open(path, 'rb') as f:
|
||||
html = f.read().decode('utf-8', 'replace')
|
||||
html = preprocessor(html, get_preprocess_html=True)
|
||||
out.write(html.encode('utf-8'))
|
||||
out.write(b'\n\n' + b'-'*80 + b'\n\n')
|
||||
|
||||
187
src/calibre/ebooks/oeb/iterator/book.py
Normal file
187
src/calibre/ebooks/oeb/iterator/book.py
Normal file
@ -0,0 +1,187 @@
|
||||
#!/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__ = '2012, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
|
||||
'''
|
||||
Iterate over the HTML files in an ebook. Useful for writing viewers.
|
||||
'''
|
||||
|
||||
import re, os, math
|
||||
from functools import partial
|
||||
|
||||
from calibre.ebooks.metadata.opf2 import OPF
|
||||
from calibre.ptempfile import TemporaryDirectory
|
||||
from calibre.utils.config import DynamicConfig
|
||||
from calibre.utils.logging import default_log
|
||||
from calibre import (guess_type, prepare_string_for_xml,
|
||||
xml_replace_entities)
|
||||
from calibre.ebooks.oeb.transforms.cover import CoverManager
|
||||
|
||||
from calibre.ebooks.oeb.iterator.spine import (SpineItem, create_indexing_data)
|
||||
from calibre.ebooks.oeb.iterator.bookmarks import BookmarksMixin
|
||||
|
||||
TITLEPAGE = CoverManager.SVG_TEMPLATE.decode('utf-8').replace(\
|
||||
'__ar__', 'none').replace('__viewbox__', '0 0 600 800'
|
||||
).replace('__width__', '600').replace('__height__', '800')
|
||||
|
||||
class FakeOpts(object):
|
||||
verbose = 0
|
||||
breadth_first = False
|
||||
max_levels = 5
|
||||
input_encoding = None
|
||||
|
||||
|
||||
def write_oebbook(oeb, path):
|
||||
from calibre.ebooks.oeb.writer import OEBWriter
|
||||
from calibre import walk
|
||||
w = OEBWriter()
|
||||
w(oeb, path)
|
||||
for f in walk(path):
|
||||
if f.endswith('.opf'):
|
||||
return f
|
||||
|
||||
class EbookIterator(BookmarksMixin):
|
||||
|
||||
CHARACTERS_PER_PAGE = 1000
|
||||
|
||||
def __init__(self, pathtoebook, log=None):
|
||||
self.log = log or default_log
|
||||
pathtoebook = pathtoebook.strip()
|
||||
self.pathtoebook = os.path.abspath(pathtoebook)
|
||||
self.config = DynamicConfig(name='iterator')
|
||||
ext = os.path.splitext(pathtoebook)[1].replace('.', '').lower()
|
||||
ext = re.sub(r'(x{0,1})htm(l{0,1})', 'html', ext)
|
||||
self.ebook_ext = ext.replace('original_', '')
|
||||
|
||||
def search(self, text, index, backwards=False):
|
||||
text = prepare_string_for_xml(text.lower())
|
||||
pmap = [(i, path) for i, path in enumerate(self.spine)]
|
||||
if backwards:
|
||||
pmap.reverse()
|
||||
for i, path in pmap:
|
||||
if (backwards and i < index) or (not backwards and i > index):
|
||||
with open(path, 'rb') as f:
|
||||
raw = f.read().decode(path.encoding)
|
||||
try:
|
||||
raw = xml_replace_entities(raw)
|
||||
except:
|
||||
pass
|
||||
if text in raw.lower():
|
||||
return i
|
||||
|
||||
def __enter__(self, processed=False, only_input_plugin=False,
|
||||
run_char_count=True, read_anchor_map=True):
|
||||
''' Convert an ebook file into an exploded OEB book suitable for
|
||||
display in viewers/preprocessing etc. '''
|
||||
|
||||
from calibre.ebooks.conversion.plumber import Plumber, create_oebbook
|
||||
|
||||
self.delete_on_exit = []
|
||||
self._tdir = TemporaryDirectory('_ebook_iter')
|
||||
self.base = self._tdir.__enter__()
|
||||
plumber = Plumber(self.pathtoebook, self.base, self.log)
|
||||
plumber.setup_options()
|
||||
if self.pathtoebook.lower().endswith('.opf'):
|
||||
plumber.opts.dont_package = True
|
||||
if hasattr(plumber.opts, 'no_process'):
|
||||
plumber.opts.no_process = True
|
||||
|
||||
plumber.input_plugin.for_viewer = True
|
||||
with plumber.input_plugin, open(plumber.input, 'rb') as inf:
|
||||
self.pathtoopf = plumber.input_plugin(inf,
|
||||
plumber.opts, plumber.input_fmt, self.log,
|
||||
{}, self.base)
|
||||
|
||||
if not only_input_plugin:
|
||||
# Run the HTML preprocess/parsing from the conversion pipeline as
|
||||
# well
|
||||
if (processed or plumber.input_fmt.lower() in {'pdb', 'pdf', 'rb'}
|
||||
and not hasattr(self.pathtoopf, 'manifest')):
|
||||
if hasattr(self.pathtoopf, 'manifest'):
|
||||
self.pathtoopf = write_oebbook(self.pathtoopf, self.base)
|
||||
self.pathtoopf = create_oebbook(self.log, self.pathtoopf,
|
||||
plumber.opts)
|
||||
|
||||
if hasattr(self.pathtoopf, 'manifest'):
|
||||
self.pathtoopf = write_oebbook(self.pathtoopf, self.base)
|
||||
|
||||
self.book_format = os.path.splitext(self.pathtoebook)[1][1:].upper()
|
||||
if getattr(plumber.input_plugin, 'is_kf8', False):
|
||||
self.book_format = 'KF8'
|
||||
|
||||
self.opf = getattr(plumber.input_plugin, 'optimize_opf_parsing', None)
|
||||
if self.opf is None:
|
||||
self.opf = OPF(self.pathtoopf, os.path.dirname(self.pathtoopf))
|
||||
self.language = self.opf.language
|
||||
if self.language:
|
||||
self.language = self.language.lower()
|
||||
ordered = [i for i in self.opf.spine if i.is_linear] + \
|
||||
[i for i in self.opf.spine if not i.is_linear]
|
||||
self.spine = []
|
||||
Spiny = partial(SpineItem, read_anchor_map=read_anchor_map,
|
||||
run_char_count=run_char_count)
|
||||
for i in ordered:
|
||||
spath = i.path
|
||||
mt = None
|
||||
if i.idref is not None:
|
||||
mt = self.opf.manifest.type_for_id(i.idref)
|
||||
if mt is None:
|
||||
mt = guess_type(spath)[0]
|
||||
try:
|
||||
self.spine.append(Spiny(spath, mime_type=mt))
|
||||
except:
|
||||
self.log.warn('Missing spine item:', repr(spath))
|
||||
|
||||
cover = self.opf.cover
|
||||
if cover and self.ebook_ext in {'lit', 'mobi', 'prc', 'opf', 'fb2',
|
||||
'azw', 'azw3'}:
|
||||
cfile = os.path.join(self.base, 'calibre_iterator_cover.html')
|
||||
rcpath = os.path.relpath(cover, self.base).replace(os.sep, '/')
|
||||
chtml = (TITLEPAGE%prepare_string_for_xml(rcpath, True)).encode('utf-8')
|
||||
with open(cfile, 'wb') as f:
|
||||
f.write(chtml)
|
||||
self.spine[0:0] = [Spiny(cfile,
|
||||
mime_type='application/xhtml+xml')]
|
||||
self.delete_on_exit.append(cfile)
|
||||
|
||||
if self.opf.path_to_html_toc is not None and \
|
||||
self.opf.path_to_html_toc not in self.spine:
|
||||
try:
|
||||
self.spine.append(Spiny(self.opf.path_to_html_toc))
|
||||
except:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
|
||||
sizes = [i.character_count for i in self.spine]
|
||||
self.pages = [math.ceil(i/float(self.CHARACTERS_PER_PAGE)) for i in sizes]
|
||||
for p, s in zip(self.pages, self.spine):
|
||||
s.pages = p
|
||||
start = 1
|
||||
|
||||
for s in self.spine:
|
||||
s.start_page = start
|
||||
start += s.pages
|
||||
s.max_page = s.start_page + s.pages - 1
|
||||
self.toc = self.opf.toc
|
||||
if read_anchor_map:
|
||||
create_indexing_data(self.spine, self.toc)
|
||||
|
||||
self.read_bookmarks()
|
||||
|
||||
return self
|
||||
|
||||
def __exit__(self, *args):
|
||||
self._tdir.__exit__(*args)
|
||||
for x in self.delete_on_exit:
|
||||
try:
|
||||
os.remove(x)
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
105
src/calibre/ebooks/oeb/iterator/bookmarks.py
Normal file
105
src/calibre/ebooks/oeb/iterator/bookmarks.py
Normal file
@ -0,0 +1,105 @@
|
||||
#!/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__ = '2012, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import os
|
||||
from io import BytesIO
|
||||
|
||||
from calibre.utils.zipfile import safe_replace
|
||||
|
||||
BM_FIELD_SEP = u'*|!|?|*'
|
||||
BM_LEGACY_ESC = u'esc-text-%&*#%(){}ads19-end-esc'
|
||||
|
||||
class BookmarksMixin(object):
|
||||
|
||||
def parse_bookmarks(self, raw):
|
||||
for line in raw.splitlines():
|
||||
bm = None
|
||||
if line.count('^') > 0:
|
||||
tokens = line.rpartition('^')
|
||||
title, ref = tokens[0], tokens[2]
|
||||
try:
|
||||
spine, _, pos = ref.partition('#')
|
||||
spine = int(spine.strip())
|
||||
except:
|
||||
continue
|
||||
bm = {'type':'legacy', 'title':title, 'spine':spine, 'pos':pos}
|
||||
elif BM_FIELD_SEP in line:
|
||||
try:
|
||||
title, spine, pos = line.strip().split(BM_FIELD_SEP)
|
||||
spine = int(spine)
|
||||
except:
|
||||
continue
|
||||
# Unescape from serialization
|
||||
pos = pos.replace(BM_LEGACY_ESC, u'^')
|
||||
# Check for pos being a scroll fraction
|
||||
try:
|
||||
pos = float(pos)
|
||||
except:
|
||||
pass
|
||||
bm = {'type':'cfi', 'title':title, 'pos':pos, 'spine':spine}
|
||||
|
||||
if bm:
|
||||
self.bookmarks.append(bm)
|
||||
|
||||
def serialize_bookmarks(self, bookmarks):
|
||||
dat = []
|
||||
for bm in bookmarks:
|
||||
if bm['type'] == 'legacy':
|
||||
rec = u'%s^%d#%s'%(bm['title'], bm['spine'], bm['pos'])
|
||||
else:
|
||||
pos = bm['pos']
|
||||
if isinstance(pos, (int, float)):
|
||||
pos = unicode(pos)
|
||||
else:
|
||||
pos = pos.replace(u'^', BM_LEGACY_ESC)
|
||||
rec = BM_FIELD_SEP.join([bm['title'], unicode(bm['spine']), pos])
|
||||
dat.append(rec)
|
||||
return (u'\n'.join(dat) +u'\n')
|
||||
|
||||
def read_bookmarks(self):
|
||||
self.bookmarks = []
|
||||
bmfile = os.path.join(self.base, 'META-INF', 'calibre_bookmarks.txt')
|
||||
raw = ''
|
||||
if os.path.exists(bmfile):
|
||||
with open(bmfile, 'rb') as f:
|
||||
raw = f.read()
|
||||
else:
|
||||
saved = self.config['bookmarks_'+self.pathtoebook]
|
||||
if saved:
|
||||
raw = saved
|
||||
if not isinstance(raw, unicode):
|
||||
raw = raw.decode('utf-8')
|
||||
self.parse_bookmarks(raw)
|
||||
|
||||
def save_bookmarks(self, bookmarks=None):
|
||||
if bookmarks is None:
|
||||
bookmarks = self.bookmarks
|
||||
dat = self.serialize_bookmarks(bookmarks)
|
||||
if os.path.splitext(self.pathtoebook)[1].lower() == '.epub' and \
|
||||
os.access(self.pathtoebook, os.R_OK):
|
||||
try:
|
||||
zf = open(self.pathtoebook, 'r+b')
|
||||
except IOError:
|
||||
return
|
||||
safe_replace(zf, 'META-INF/calibre_bookmarks.txt',
|
||||
BytesIO(dat.encode('utf-8')),
|
||||
add_missing=True)
|
||||
else:
|
||||
self.config['bookmarks_'+self.pathtoebook] = dat
|
||||
|
||||
def add_bookmark(self, bm):
|
||||
self.bookmarks = [x for x in self.bookmarks if x['title'] !=
|
||||
bm['title']]
|
||||
self.bookmarks.append(bm)
|
||||
self.save_bookmarks()
|
||||
|
||||
def set_bookmarks(self, bookmarks):
|
||||
self.bookmarks = bookmarks
|
||||
|
||||
|
||||
120
src/calibre/ebooks/oeb/iterator/spine.py
Normal file
120
src/calibre/ebooks/oeb/iterator/spine.py
Normal file
@ -0,0 +1,120 @@
|
||||
#!/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__ = '2012, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import re, os
|
||||
from functools import partial
|
||||
from operator import attrgetter
|
||||
from collections import namedtuple
|
||||
|
||||
from calibre import guess_type
|
||||
from calibre.ebooks.chardet import xml_to_unicode
|
||||
|
||||
def character_count(html):
|
||||
''' Return the number of "significant" text characters in a HTML string. '''
|
||||
count = 0
|
||||
strip_space = re.compile(r'\s+')
|
||||
for match in re.finditer(r'>[^<]+<', html):
|
||||
count += len(strip_space.sub(' ', match.group()))-2
|
||||
return count
|
||||
|
||||
def anchor_map(html):
|
||||
''' Return map of all anchor names to their offsets in the html '''
|
||||
ans = {}
|
||||
for match in re.finditer(
|
||||
r'''(?:id|name)\s*=\s*['"]([^'"]+)['"]''', html):
|
||||
anchor = match.group(0)
|
||||
ans[anchor] = ans.get(anchor, match.start())
|
||||
return ans
|
||||
|
||||
class SpineItem(unicode):
|
||||
|
||||
def __new__(cls, path, mime_type=None, read_anchor_map=True,
|
||||
run_char_count=True):
|
||||
ppath = path.partition('#')[0]
|
||||
if not os.path.exists(path) and os.path.exists(ppath):
|
||||
path = ppath
|
||||
obj = super(SpineItem, cls).__new__(cls, path)
|
||||
with open(path, 'rb') as f:
|
||||
raw = f.read()
|
||||
raw, obj.encoding = xml_to_unicode(raw)
|
||||
obj.character_count = character_count(raw) if run_char_count else 10000
|
||||
obj.anchor_map = anchor_map(raw) if read_anchor_map else {}
|
||||
obj.start_page = -1
|
||||
obj.pages = -1
|
||||
obj.max_page = -1
|
||||
obj.index_entries = []
|
||||
if mime_type is None:
|
||||
mime_type = guess_type(obj)[0]
|
||||
obj.mime_type = mime_type
|
||||
return obj
|
||||
|
||||
class IndexEntry(object):
|
||||
|
||||
def __init__(self, spine, toc_entry, num):
|
||||
self.num = num
|
||||
self.text = toc_entry.text or _('Unknown')
|
||||
self.key = toc_entry.abspath
|
||||
self.anchor = self.start_anchor = toc_entry.fragment or None
|
||||
try:
|
||||
self.spine_pos = spine.index(self.key)
|
||||
except ValueError:
|
||||
self.spine_pos = -1
|
||||
self.anchor_pos = 0
|
||||
if self.spine_pos > -1:
|
||||
self.anchor_pos = spine[self.spine_pos].anchor_map.get(self.anchor,
|
||||
0)
|
||||
|
||||
self.depth = 0
|
||||
p = toc_entry.parent
|
||||
while p is not None:
|
||||
self.depth += 1
|
||||
p = p.parent
|
||||
|
||||
self.sort_key = (self.spine_pos, self.anchor_pos)
|
||||
self.spine_count = len(spine)
|
||||
|
||||
def find_end(self, all_entries):
|
||||
potential_enders = [i for i in all_entries if
|
||||
i.depth <= self.depth and
|
||||
(
|
||||
(i.spine_pos == self.spine_pos and i.anchor_pos >
|
||||
self.anchor_pos)
|
||||
or
|
||||
i.spine_pos > self.spine_pos
|
||||
)]
|
||||
if potential_enders:
|
||||
# potential_enders is sorted by (spine_pos, anchor_pos)
|
||||
end = potential_enders[0]
|
||||
self.end_spine_pos = end.spine_pos
|
||||
self.end_anchor = end.anchor
|
||||
else:
|
||||
self.end_spine_pos = self.spine_count - 1
|
||||
self.end_anchor = None
|
||||
|
||||
def create_indexing_data(spine, toc):
|
||||
if not toc: return
|
||||
f = partial(IndexEntry, spine)
|
||||
index_entries = list(map(f,
|
||||
(t for t in toc.flat() if t is not toc),
|
||||
(i-1 for i, t in enumerate(toc.flat()) if t is not toc)
|
||||
))
|
||||
index_entries.sort(key=attrgetter('sort_key'))
|
||||
[ i.find_end(index_entries) for i in index_entries ]
|
||||
|
||||
ie = namedtuple('IndexEntry', 'entry start_anchor end_anchor')
|
||||
|
||||
for spine_pos, spine_item in enumerate(spine):
|
||||
for i in index_entries:
|
||||
if i.end_spine_pos < spine_pos or i.spine_pos > spine_pos:
|
||||
continue # Does not touch this file
|
||||
start = i.anchor if i.spine_pos == spine_pos else None
|
||||
end = i.end_anchor if i.spine_pos == spine_pos else None
|
||||
spine_item.index_entries.append(ie(i, start, end))
|
||||
|
||||
@ -361,9 +361,11 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
|
||||
# Remove any encoding-specifying <meta/> elements
|
||||
for meta in META_XP(data):
|
||||
meta.getparent().remove(meta)
|
||||
etree.SubElement(head, XHTML('meta'),
|
||||
attrib={'http-equiv': 'Content-Type',
|
||||
'content': '%s; charset=utf-8' % XHTML_NS})
|
||||
meta = etree.SubElement(head, XHTML('meta'),
|
||||
attrib={'http-equiv': 'Content-Type'})
|
||||
meta.set('content', 'text/html; charset=utf-8') # Ensure content is second
|
||||
# attribute
|
||||
|
||||
# Ensure has a <body/>
|
||||
if not xpath(data, '/h:html/h:body'):
|
||||
body = xpath(data, '//h:body')
|
||||
|
||||
@ -347,6 +347,10 @@ class Stylizer(object):
|
||||
style = self.flatten_style(rule.style)
|
||||
self.page_rule.update(style)
|
||||
elif isinstance(rule, CSSFontFaceRule):
|
||||
if rule.style.length > 1:
|
||||
# Ignore the meaningless font face rules generated by the
|
||||
# benighted MS Word that contain only a font-family declaration
|
||||
# and nothing else
|
||||
self.font_face_rules.append(rule)
|
||||
return results
|
||||
|
||||
|
||||
@ -137,8 +137,9 @@ def _config(): # {{{
|
||||
c.add_opt('LRF_ebook_viewer_options', default=None,
|
||||
help=_('Options for the LRF ebook viewer'))
|
||||
c.add_opt('internally_viewed_formats', default=['LRF', 'EPUB', 'LIT',
|
||||
'MOBI', 'PRC', 'AZW', 'HTML', 'FB2', 'PDB', 'RB', 'SNB', 'HTMLZ'],
|
||||
help=_('Formats that are viewed using the internal viewer'))
|
||||
'MOBI', 'PRC', 'POBI', 'AZW', 'AZW3', 'HTML', 'FB2', 'PDB', 'RB',
|
||||
'SNB', 'HTMLZ'], help=_(
|
||||
'Formats that are viewed using the internal viewer'))
|
||||
c.add_opt('column_map', default=ALL_COLUMNS,
|
||||
help=_('Columns to be displayed in the book list'))
|
||||
c.add_opt('autolaunch_server', default=False, help=_('Automatically launch content server on application startup'))
|
||||
|
||||
@ -357,7 +357,9 @@ class MetadataSingleDialogBase(ResizableDialog):
|
||||
old_tags = self.tags.current_val
|
||||
tags = mi.tags if mi.tags else []
|
||||
if old_tags and merge_tags:
|
||||
tags += old_tags
|
||||
ltags, lotags = {t.lower() for t in tags}, {t.lower() for t in
|
||||
old_tags}
|
||||
tags = [t for t in tags if t.lower() in ltags-lotags] + old_tags
|
||||
self.tags.current_val = tags
|
||||
if not mi.is_null('identifiers'):
|
||||
current = self.identifiers.current_val
|
||||
@ -463,7 +465,12 @@ class MetadataSingleDialogBase(ResizableDialog):
|
||||
ResizableDialog.reject(self)
|
||||
|
||||
def save_state(self):
|
||||
try:
|
||||
gprefs['metasingle_window_geometry3'] = bytearray(self.saveGeometry())
|
||||
except:
|
||||
# Weird failure, see https://bugs.launchpad.net/bugs/995271
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
|
||||
# Dialog use methods {{{
|
||||
def start(self, row_list, current_row, view_slot=None,
|
||||
|
||||
@ -955,7 +955,7 @@ class FullFetch(QDialog): # {{{
|
||||
# QWebView. Seems to only happen on windows, but keep it for all
|
||||
# platforms just in case.
|
||||
self.identify_widget.comments_view.setMaximumHeight(500)
|
||||
self.resize(850, 550)
|
||||
self.resize(850, 600)
|
||||
|
||||
self.finished.connect(self.cleanup)
|
||||
|
||||
@ -1034,7 +1034,7 @@ class CoverFetch(QDialog): # {{{
|
||||
self.covers_widget.chosen.connect(self.accept)
|
||||
l.addWidget(self.covers_widget)
|
||||
|
||||
self.resize(850, 550)
|
||||
self.resize(850, 600)
|
||||
|
||||
self.finished.connect(self.cleanup)
|
||||
|
||||
|
||||
@ -11,6 +11,7 @@ import os, zipfile
|
||||
|
||||
import calibre
|
||||
from calibre.utils.localization import lang_as_iso639_1
|
||||
from calibre.utils.resources import compiled_coffeescript
|
||||
|
||||
class JavaScriptLoader(object):
|
||||
|
||||
@ -27,7 +28,7 @@ class JavaScriptLoader(object):
|
||||
}.iteritems()}
|
||||
|
||||
CS = {
|
||||
'cfi':('ebooks/oeb/display/cfi.coffee', 'display/cfi.js'),
|
||||
'cfi':'ebooks.oeb.display.cfi',
|
||||
}
|
||||
|
||||
ORDER = ('jquery', 'jquery_scrollTo', 'bookmarks', 'referencing', 'images',
|
||||
@ -59,21 +60,9 @@ class JavaScriptLoader(object):
|
||||
ans = P(src, data=True,
|
||||
allow_user_override=False).decode('utf-8')
|
||||
else:
|
||||
f = getattr(calibre, '__file__', None)
|
||||
if self._dynamic_coffeescript and f and os.path.exists(f):
|
||||
src = src[0]
|
||||
src = os.path.join(os.path.dirname(f), *(src.split('/')))
|
||||
from calibre.utils.serve_coffee import compile_coffeescript
|
||||
with open(src, 'rb') as f:
|
||||
cs, errors = compile_coffeescript(f.read(), src)
|
||||
if errors:
|
||||
for line in errors:
|
||||
print (line)
|
||||
raise Exception('Failed to compile coffeescript'
|
||||
': %s'%src)
|
||||
ans = cs
|
||||
else:
|
||||
ans = P(src[1], data=True, allow_user_override=False)
|
||||
dynamic = (self._dynamic_coffeescript and
|
||||
os.path.exists(calibre.__file__))
|
||||
ans = compiled_coffeescript(src, dynamic=dynamic).decode('utf-8')
|
||||
self._cache[name] = ans
|
||||
return ans
|
||||
|
||||
|
||||
@ -1,24 +1,24 @@
|
||||
from __future__ import with_statement
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
import traceback, os, sys, functools, collections, re
|
||||
|
||||
import traceback, os, sys, functools, collections, textwrap
|
||||
from functools import partial
|
||||
from threading import Thread
|
||||
|
||||
from PyQt4.Qt import (QApplication, Qt, QIcon, QTimer, SIGNAL, QByteArray,
|
||||
QSize, QDoubleSpinBox, QLabel, QTextBrowser, QPropertyAnimation,
|
||||
QPainter, QBrush, QColor, QStandardItemModel, QPalette, QStandardItem,
|
||||
QUrl, QRegExpValidator, QRegExp, QLineEdit, QToolButton, QMenu,
|
||||
QInputDialog, QAction, QKeySequence)
|
||||
from PyQt4.Qt import (QApplication, Qt, QIcon, QTimer, QByteArray, QSize,
|
||||
QDoubleSpinBox, QLabel, QTextBrowser, QPropertyAnimation, QPainter,
|
||||
QBrush, QColor, pyqtSignal, QUrl, QRegExpValidator, QRegExp, QLineEdit,
|
||||
QToolButton, QMenu, QInputDialog, QAction, QKeySequence, QModelIndex)
|
||||
|
||||
from calibre.gui2.viewer.main_ui import Ui_EbookViewer
|
||||
from calibre.gui2.viewer.printing import Printing
|
||||
from calibre.gui2.viewer.bookmarkmanager import BookmarkManager
|
||||
from calibre.gui2.viewer.toc import TOC
|
||||
from calibre.gui2.widgets import ProgressIndicator
|
||||
from calibre.gui2.main_window import MainWindow
|
||||
from calibre.gui2 import Application, ORG_NAME, APP_UID, choose_files, \
|
||||
info_dialog, error_dialog, open_url, available_height
|
||||
from calibre.ebooks.oeb.iterator import EbookIterator
|
||||
from calibre.gui2 import (Application, ORG_NAME, APP_UID, choose_files,
|
||||
info_dialog, error_dialog, open_url, available_height)
|
||||
from calibre.ebooks.oeb.iterator.book import EbookIterator
|
||||
from calibre.ebooks import DRMError
|
||||
from calibre.constants import islinux, isbsd, isosx, filesystem_encoding
|
||||
from calibre.utils.config import Config, StringConfig, JSONConfig
|
||||
@ -31,31 +31,6 @@ from calibre.ptempfile import reset_base_dir
|
||||
|
||||
vprefs = JSONConfig('viewer')
|
||||
|
||||
class TOCItem(QStandardItem):
|
||||
|
||||
def __init__(self, toc):
|
||||
text = toc.text
|
||||
if text:
|
||||
text = re.sub(r'\s', ' ', text)
|
||||
QStandardItem.__init__(self, text if text else '')
|
||||
self.abspath = toc.abspath
|
||||
self.fragment = toc.fragment
|
||||
for t in toc:
|
||||
self.appendRow(TOCItem(t))
|
||||
self.setFlags(Qt.ItemIsEnabled|Qt.ItemIsSelectable)
|
||||
|
||||
@classmethod
|
||||
def type(cls):
|
||||
return QStandardItem.UserType+10
|
||||
|
||||
class TOC(QStandardItemModel):
|
||||
|
||||
def __init__(self, toc):
|
||||
QStandardItemModel.__init__(self)
|
||||
for t in toc:
|
||||
self.appendRow(TOCItem(t))
|
||||
self.setHorizontalHeaderItem(0, QStandardItem(_('Table of Contents')))
|
||||
|
||||
class Worker(Thread):
|
||||
|
||||
def run(self):
|
||||
@ -142,31 +117,22 @@ class DoubleSpinBox(QDoubleSpinBox):
|
||||
' [{0:.0%}]'.format(float(val)/self.maximum()))
|
||||
self.blockSignals(False)
|
||||
|
||||
class HelpfulLineEdit(QLineEdit):
|
||||
class Reference(QLineEdit):
|
||||
|
||||
HELP_TEXT = _('Go to...')
|
||||
goto = pyqtSignal(object)
|
||||
|
||||
def __init__(self, *args):
|
||||
QLineEdit.__init__(self, *args)
|
||||
self.default_palette = QApplication.palette(self)
|
||||
self.gray = QPalette(self.default_palette)
|
||||
self.gray.setBrush(QPalette.Text, QBrush(QColor('gray')))
|
||||
self.connect(self, SIGNAL('editingFinished()'),
|
||||
lambda : self.emit(SIGNAL('goto(PyQt_PyObject)'), unicode(self.text())))
|
||||
self.clear_to_help_mode()
|
||||
self.setValidator(QRegExpValidator(QRegExp(r'\d+\.\d+'), self))
|
||||
self.setToolTip(textwrap.fill('<p>'+_(
|
||||
'Go to a reference. To get reference numbers, use the <i>reference '
|
||||
'mode</i>, by clicking the reference mode button in the toolbar.')))
|
||||
if hasattr(self, 'setPlaceholderText'):
|
||||
self.setPlaceholderText(_('Go to...'))
|
||||
self.editingFinished.connect(self.editing_finished)
|
||||
|
||||
def focusInEvent(self, ev):
|
||||
self.setPalette(QApplication.palette(self))
|
||||
if self.in_help_mode():
|
||||
self.setText('')
|
||||
return QLineEdit.focusInEvent(self, ev)
|
||||
|
||||
def in_help_mode(self):
|
||||
return unicode(self.text()) == self.HELP_TEXT
|
||||
|
||||
def clear_to_help_mode(self):
|
||||
self.setPalette(self.gray)
|
||||
self.setText(self.HELP_TEXT)
|
||||
def editing_finished(self):
|
||||
self.goto.emit(unicode(self.text()))
|
||||
|
||||
class RecentAction(QAction):
|
||||
|
||||
@ -207,9 +173,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
|
||||
self.pos.setMinimum(1.)
|
||||
self.pos.setMinimumWidth(150)
|
||||
self.tool_bar2.insertWidget(self.action_find_next, self.pos)
|
||||
self.reference = HelpfulLineEdit()
|
||||
self.reference.setValidator(QRegExpValidator(QRegExp(r'\d+\.\d+'), self.reference))
|
||||
self.reference.setToolTip(_('Go to a reference. To get reference numbers, use the reference mode.'))
|
||||
self.reference = Reference()
|
||||
self.tool_bar2.insertSeparator(self.action_find_next)
|
||||
self.tool_bar2.insertWidget(self.action_find_next, self.reference)
|
||||
self.tool_bar2.insertSeparator(self.action_find_next)
|
||||
@ -233,8 +197,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
|
||||
if isosx:
|
||||
qs += [Qt.CTRL+Qt.Key_W]
|
||||
self.action_quit.setShortcuts(qs)
|
||||
self.connect(self.action_quit, SIGNAL('triggered(bool)'),
|
||||
lambda x:QApplication.instance().quit())
|
||||
self.action_quit.triggered.connect(self.quit)
|
||||
self.action_focus_search = QAction(self)
|
||||
self.addAction(self.action_focus_search)
|
||||
self.action_focus_search.setShortcuts([Qt.Key_Slash,
|
||||
@ -247,42 +210,34 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
|
||||
self.action_table_of_contents.setCheckable(True)
|
||||
self.toc.setMinimumWidth(80)
|
||||
self.action_reference_mode.setCheckable(True)
|
||||
self.connect(self.action_reference_mode, SIGNAL('triggered(bool)'),
|
||||
lambda x: self.view.reference_mode(x))
|
||||
self.connect(self.action_metadata, SIGNAL('triggered(bool)'), lambda x:self.metadata.setVisible(x))
|
||||
self.action_reference_mode.triggered[bool].connect(self.view.reference_mode)
|
||||
self.action_metadata.triggered[bool].connect(self.metadata.setVisible)
|
||||
self.action_table_of_contents.toggled[bool].connect(self.set_toc_visible)
|
||||
self.connect(self.action_copy, SIGNAL('triggered(bool)'), self.copy)
|
||||
self.action_copy.triggered[bool].connect(self.copy)
|
||||
self.action_font_size_larger.triggered.connect(self.font_size_larger)
|
||||
self.action_font_size_smaller.triggered.connect(self.font_size_smaller)
|
||||
self.connect(self.action_open_ebook, SIGNAL('triggered(bool)'),
|
||||
self.open_ebook)
|
||||
self.connect(self.action_next_page, SIGNAL('triggered(bool)'),
|
||||
lambda x:self.view.next_page())
|
||||
self.connect(self.action_previous_page, SIGNAL('triggered(bool)'),
|
||||
lambda x:self.view.previous_page())
|
||||
self.connect(self.action_find_next, SIGNAL('triggered(bool)'),
|
||||
lambda x:self.find(unicode(self.search.text()), repeat=True))
|
||||
self.connect(self.action_find_previous, SIGNAL('triggered(bool)'),
|
||||
lambda x:self.find(unicode(self.search.text()),
|
||||
repeat=True, backwards=True))
|
||||
|
||||
self.connect(self.action_full_screen, SIGNAL('triggered(bool)'),
|
||||
self.toggle_fullscreen)
|
||||
self.action_open_ebook.triggered[bool].connect(self.open_ebook)
|
||||
self.action_next_page.triggered.connect(self.view.next_page)
|
||||
self.action_previous_page.triggered.connect(self.view.previous_page)
|
||||
self.action_find_next.triggered.connect(self.find_next)
|
||||
self.action_find_previous.triggered.connect(self.find_previous)
|
||||
self.action_full_screen.triggered[bool].connect(self.toggle_fullscreen)
|
||||
self.action_full_screen.setShortcuts([Qt.Key_F11, Qt.CTRL+Qt.SHIFT+Qt.Key_F])
|
||||
self.action_full_screen.setToolTip(_('Toggle full screen (%s)') %
|
||||
_(' or ').join([unicode(x.toString(x.NativeText)) for x in
|
||||
self.action_full_screen.shortcuts()]))
|
||||
self.connect(self.action_back, SIGNAL('triggered(bool)'), self.back)
|
||||
self.connect(self.action_bookmark, SIGNAL('triggered(bool)'), self.bookmark)
|
||||
self.connect(self.action_forward, SIGNAL('triggered(bool)'), self.forward)
|
||||
self.connect(self.action_preferences, SIGNAL('triggered(bool)'), lambda x: self.view.config(self))
|
||||
self.action_back.triggered[bool].connect(self.back)
|
||||
self.action_forward.triggered[bool].connect(self.forward)
|
||||
self.action_bookmark.triggered[bool].connect(self.bookmark)
|
||||
self.action_preferences.triggered.connect(lambda :
|
||||
self.view.config(self))
|
||||
self.pos.editingFinished.connect(self.goto_page_num)
|
||||
self.connect(self.vertical_scrollbar, SIGNAL('valueChanged(int)'),
|
||||
lambda x: self.goto_page(x/100.))
|
||||
self.vertical_scrollbar.valueChanged[int].connect(lambda
|
||||
x:self.goto_page(x/100.))
|
||||
self.search.search.connect(self.find)
|
||||
self.search.focus_to_library.connect(lambda: self.view.setFocus(Qt.OtherFocusReason))
|
||||
self.connect(self.toc, SIGNAL('clicked(QModelIndex)'), self.toc_clicked)
|
||||
self.connect(self.reference, SIGNAL('goto(PyQt_PyObject)'), self.goto)
|
||||
self.toc.clicked[QModelIndex].connect(self.toc_clicked)
|
||||
self.reference.goto.connect(self.goto)
|
||||
|
||||
self.bookmarks_menu = QMenu()
|
||||
self.action_bookmark.setMenu(self.bookmarks_menu)
|
||||
@ -335,8 +290,8 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
|
||||
self.print_menu.addAction(QIcon(I('print-preview.png')), _('Print Preview'))
|
||||
self.action_print.setMenu(self.print_menu)
|
||||
self.tool_bar.widgetForAction(self.action_print).setPopupMode(QToolButton.MenuButtonPopup)
|
||||
self.connect(self.action_print, SIGNAL("triggered(bool)"), partial(self.print_book, preview=False))
|
||||
self.connect(self.print_menu.actions()[0], SIGNAL("triggered(bool)"), partial(self.print_book, preview=True))
|
||||
self.action_print.triggered.connect(self.print_book)
|
||||
self.print_menu.actions()[0].triggered.connect(self.print_preview)
|
||||
ca = self.view.copy_action
|
||||
ca.setShortcut(QKeySequence.Copy)
|
||||
self.addAction(ca)
|
||||
@ -381,13 +336,22 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
|
||||
m.addAction(RecentAction(path, m))
|
||||
count += 1
|
||||
|
||||
def closeEvent(self, e):
|
||||
def shutdown(self):
|
||||
if self.isFullScreen():
|
||||
self.action_full_screen.trigger()
|
||||
e.ignore()
|
||||
return
|
||||
return False
|
||||
self.save_state()
|
||||
return True
|
||||
|
||||
def quit(self):
|
||||
if self.shutdown():
|
||||
QApplication.instance().quit()
|
||||
|
||||
def closeEvent(self, e):
|
||||
if self.shutdown():
|
||||
return MainWindow.closeEvent(self, e)
|
||||
else:
|
||||
e.ignore()
|
||||
|
||||
def toggle_toolbars(self):
|
||||
for x in ('tool_bar', 'tool_bar2'):
|
||||
@ -440,8 +404,11 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
|
||||
c = config().parse()
|
||||
return c.remember_current_page
|
||||
|
||||
def print_book(self, preview):
|
||||
Printing(self.iterator.spine, preview)
|
||||
def print_book(self):
|
||||
Printing(self.iterator.spine, False)
|
||||
|
||||
def print_preview(self):
|
||||
Printing(self.iterator.spine, True)
|
||||
|
||||
def toggle_fullscreen(self, x):
|
||||
if self.isFullScreen():
|
||||
@ -629,6 +596,12 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
|
||||
self.pending_search_dir = 'backwards' if backwards else 'forwards'
|
||||
self.load_path(self.iterator.spine[index])
|
||||
|
||||
def find_next(self):
|
||||
self.find(unicode(self.search.text()), repeat=True)
|
||||
|
||||
def find_previous(self):
|
||||
self.find(unicode(self.search.text()), repeat=True, backwards=True)
|
||||
|
||||
def do_search(self, text, backwards):
|
||||
self.pending_search = None
|
||||
self.pending_search_dir = None
|
||||
@ -829,11 +802,13 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
|
||||
if not title:
|
||||
title = os.path.splitext(os.path.basename(pathtoebook))[0]
|
||||
if self.iterator.toc:
|
||||
self.toc_model = TOC(self.iterator.toc)
|
||||
self.toc_model = TOC(self.iterator.spine, self.iterator.toc)
|
||||
self.toc.setModel(self.toc_model)
|
||||
if self.show_toc_on_open:
|
||||
self.action_table_of_contents.setChecked(True)
|
||||
else:
|
||||
self.toc_model = TOC(self.iterator.spine)
|
||||
self.toc.setModel(self.toc_model)
|
||||
self.action_table_of_contents.setChecked(False)
|
||||
if isbytestring(pathtoebook):
|
||||
pathtoebook = force_unicode(pathtoebook, filesystem_encoding)
|
||||
|
||||
42
src/calibre/gui2/viewer/toc.py
Normal file
42
src/calibre/gui2/viewer/toc.py
Normal file
@ -0,0 +1,42 @@
|
||||
#!/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__ = '2012, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import re
|
||||
from PyQt4.Qt import QStandardItem, QStandardItemModel, Qt
|
||||
|
||||
from calibre.ebooks.metadata.toc import TOC as MTOC
|
||||
|
||||
class TOCItem(QStandardItem):
|
||||
|
||||
def __init__(self, toc):
|
||||
text = toc.text
|
||||
if text:
|
||||
text = re.sub(r'\s', ' ', text)
|
||||
QStandardItem.__init__(self, text if text else '')
|
||||
self.abspath = toc.abspath
|
||||
self.fragment = toc.fragment
|
||||
for t in toc:
|
||||
self.appendRow(TOCItem(t))
|
||||
self.setFlags(Qt.ItemIsEnabled|Qt.ItemIsSelectable)
|
||||
|
||||
@classmethod
|
||||
def type(cls):
|
||||
return QStandardItem.UserType+10
|
||||
|
||||
class TOC(QStandardItemModel):
|
||||
|
||||
def __init__(self, spine, toc=None):
|
||||
QStandardItemModel.__init__(self)
|
||||
if toc is None:
|
||||
toc = MTOC()
|
||||
for t in toc:
|
||||
self.appendRow(TOCItem(t))
|
||||
self.setHorizontalHeaderItem(0, QStandardItem(_('Table of Contents')))
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff Show More
Loading…
x
Reference in New Issue
Block a user