Merge from trunk

This commit is contained in:
Charles Haley 2011-02-07 09:04:24 +00:00
commit 56f4ab8e68
101 changed files with 74630 additions and 52234 deletions

View File

@ -19,6 +19,124 @@
# new recipes:
# - title:
- version: 0.7.44
date: 2011-02-04
new features:
- title: "Nook Color driver: Send downloaded news to the My Files/Magazines folder on the Nook Color. Also when getting the list of books on the device look at all folders in My Files, not just My Files/Books."
- title: "MOBI Output: Use the book uuid as the ASIN field and set cdetype to EBOK to allow Amazon furthest read tracking to work with calibre generated MOBI files."
tickets: [8721]
- title: "Comic input: Add an option to override the image size in the generated comic. Useful if you have a device whose screen size is not coverred by one of the available output profiles."
tickets: [7837]
- title: "Add a restore database option to the Library maintenance menu in the GUI"
- title: "TXT Output: Allow output in the textile markup language"
- title: "PML Output: Create multi-level Table of Contents"
- title: "Driver for the Archos 7O"
- title: "Search and Replace in the Bulk metadata dialog can now operate on the title_sort field as well"
tickets: [8732]
- title: "Allow changing the case of authors/tags/series etc. via the edit metadata dialog"
- title: "Connect/share menu: Re-organize to make it a little less easy to select email and delete instead of just email by mistake"
- title: "Heuristics: Improved Scene break detection and add option to control what scene breaks are replaced by."
- title: "SONY driver: Add option to not preserve aspect ratio of cover thumbnails."
- title: "BiBTeX catalog: Add on device column when available"
- title: "Add search to the plugin preferences dialog"
bug fixes:
- title: "Fix a bug that could cause files to be lost when changing metadata on east asian windows installs if the title and/or author is very long."
tickets: [8620]
- title: "Tag browser: Fix searching with items in a user category not owrking if the main category is hidden"
tickets: [8741]
- title: "Make completion for author/series/tags/etc. fields less disruptive"
- title: "Fix regression that broke the content server when user categories/custom columns are present"
- title: "Catalog generation: Handle user supplied templates more robustly"
- title: "Move the Tags to apply to newly added books option into Preferences->Adding books"
tickets: [8730]
- title: "Workaround for bug in Qt on OS X that caused crashes when reading metedata from two or more EPUB files with HTML covers that used embedded fonts. Now the embedded fonts are ignored on OS X."
tickets: [8643]
- title: "Fix regression that broke the use of the group searched terms tweak"
tickets: [8739]
- title: "Fix template program regression triggered by recursively calling the processor"
- title: "Fix mimetype sent by content server for PDB files"
- title: "OPF: Write title_sort as a calibre custom metadata field rather than as a file-as attribute on the title. This conforms to the OPF spec"
tickets: [7883]
- title: "SONY driver: Fix thumbnails being sent to SD card are sent to the wrong location. Also use correct thumbnail size so that the SONY does not regenerate the thumbnail on disconnect"
- title: "Do not discard the result of a conversion if the user opens the edit metadata dialog while the conversion is running"
tickets: [8672]
- title: "CHM Input: When the chm file lacks a hhc, look for index.html instead"
tickets: [8688]
- title: "EPUB Input: Filter some invalid media types from the spine"
- title: "RTF Input: More encoding handlig fixes."
tickets: [8678]
- title: "Linux binary build: Restore functioning of CALIBRE_DEVELOP_FROM, which was accidentally removed a few versions ago"
- title: "RTF Output: Retain html headings as rtf headings when converting to rtf. Also fix output of italics."
tickets: [8641, 8640]
- title: "LIT Input: Fix regression that broke handling of LIT files that contain txt data instead of html"
- title: "MOBI Input: Handle more non printing ASCII codes"
tickets: [8646]
- title: "Handle empty cover files more gracefully"
tickets: [8656]
- title: "Catalog geenration: Fix error when Pocketbook is connected and trying to geenrate catalog"
tickets: [8651]
- title: "Heuristics: Italicize common cases, reduce false positives."
- title: "Fix regression that caused reporting of device connection errors to break"
improved recipes:
- MSN Japan
- The Onion
- La Tribuna de
- Wall Street Journal
- "20 Minutos"
- LA Times
- Endgadget Japan
- Ledevoir
- Vijesti
new recipes:
- title: "Cinco Dias and BBC Mundo"
author: Luis Hernandez
- title: "Explosm"
author: Andromeda Rabbit
- title: "Cinco Dias"
author: Luis Hernandez
- version: 0.7.43
date: 2011-01-28

View File

@ -1,57 +1,10 @@
body { background-color: white; }
p.title {
margin-top:0em;
margin-bottom:0em;
text-align:center;
font-style:italic;
font-size:xx-large;
}
p.series_id {
margin-top:0em;
margin-bottom:0em;
text-align:center;
}
a.series_id {
font-style:normal;
font-size:large;
}
p.author {
font-size:large;
margin-top:0em;
margin-bottom:0em;
text-align: center;
text-indent: 0em;
}
p.author_index {
font-size:large;
font-weight:bold;
text-align:left;
margin-top:0px;
margin-bottom:-2px;
text-indent: 0em;
}
p.genres {
font-style:normal;
margin-top:0.5em;
margin-bottom:0em;
text-align: left;
text-indent: 0.0in;
}
p.formats {
font-size:90%;
margin-top:0em;
margin-bottom:0.5em;
text-align: left;
text-indent: 0.0in;
}
/*
* Minimize widows and orphans by logically grouping chunks
* Some reports of problems with Sony (ADE) ereaders
@ -77,71 +30,6 @@ div.initial_letter {
page-break-before:always;
}
p.author_title_letter_index {
font-size:x-large;
text-align:center;
font-weight:bold;
margin-top:0px;
margin-bottom:0px;
}
p.date_index {
font-size:x-large;
text-align:center;
font-weight:bold;
margin-top:1em;
margin-bottom:0px;
}
p.series {
font-style:italic;
margin-top:2px;
margin-bottom:0px;
margin-left:2em;
text-align:left;
text-indent:-2em;
}
p.series_letter_index {
font-size:x-large;
text-align:center;
font-weight:bold;
margin-top:1em;
margin-bottom:0px;
}
p.read_book {
text-align:left;
margin-top:0px;
margin-bottom:0px;
margin-left:2em;
text-indent:-2em;
}
p.unread_book {
text-align:left;
margin-top:0px;
margin-bottom:0px;
margin-left:2em;
text-indent:-2em;
}
p.wishlist_item {
text-align:left;
margin-top:0px;
margin-bottom:0px;
margin-left:2em;
text-indent:-2em;
}
p.date_read {
text-align:left;
margin-top:0px;
margin-bottom:0px;
margin-left:6em;
text-indent:-6em;
}
hr.annotations_divider {
width:50%;
margin-left:1em;
@ -175,6 +63,102 @@ hr.merged_comments_divider {
border-left: solid white 0px;
}
p.date_read {
text-align:left;
margin-top:0px;
margin-bottom:0px;
margin-left:6em;
text-indent:-6em;
}
p.author {
font-size:large;
margin-top:0em;
margin-bottom:0em;
text-align: center;
text-indent: 0em;
}
p.author_index {
font-size:large;
font-weight:bold;
text-align:left;
margin-top:0px;
margin-bottom:-2px;
text-indent: 0em;
}
p.author_title_letter_index {
font-size:x-large;
text-align:center;
font-weight:bold;
margin-top:0px;
margin-bottom:0px;
}
p.date_index {
font-size:x-large;
text-align:center;
font-weight:bold;
margin-top:1em;
margin-bottom:0px;
}
p.formats {
font-size:90%;
margin-top:0em;
margin-bottom:0.5em;
text-align: left;
text-indent: 0.0in;
}
p.genres {
font-style:normal;
margin-top:0.5em;
margin-bottom:0em;
text-align: left;
text-indent: 0.0in;
}
p.series {
font-style:italic;
margin-top:0.25em;
margin-bottom:0em;
margin-left:2em;
text-align:left;
text-indent:-2em;
}
p.series_id {
margin-top:0em;
margin-bottom:0em;
text-align:center;
}
p.series_letter_index {
font-size:x-large;
text-align:center;
font-weight:bold;
margin-top:1em;
margin-bottom:0px;
}
p.title {
margin-top:0em;
margin-bottom:0em;
text-align:center;
font-style:italic;
font-size:xx-large;
}
p.wishlist_item, p.unread_book, p.read_book {
text-align:left;
margin-top:0px;
margin-bottom:0px;
margin-left:2em;
text-indent:-2em;
}
td.publisher, td.date {
font-weight:bold;
text-align:center;

View File

@ -30,6 +30,13 @@ defaults.
series_index_auto_increment = 'next'
# Should the completion separator be append
# to the end of the completed text to
# automatically begin a new completion operation.
# Can be either True or False
completer_append_separator = False
# The algorithm used to copy author to author_sort
# Possible values are:
# invert: use "fn ln" -> "ln, fn" (the original algorithm)

Binary file not shown.

After

Width:  |  Height:  |  Size: 466 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 860 B

View File

@ -113,8 +113,8 @@ table.cbj_header tr.cbj_series {
/* display:none; */
}
table.cbj_header tr.cbj_pubdate {
/* Uncomment the next line to remove 'Published' from banner section */
table.cbj_header tr.cbj_pubdata {
/* Uncomment the next line to remove 'Published (year of publication)' from banner section */
/* display:none; */
}

View File

@ -0,0 +1,55 @@
__license__ = 'GPL v3'
__author__ = 'Luis Hernandez'
__copyright__ = 'Luis Hernandez<tolyluis@gmail.com>'
__version__ = 'v1.0'
__date__ = '30 January 2011'
'''
www.europapress.es
'''
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1294946868(BasicNewsRecipe):
title = u'Europa Press'
author = 'Luis Hernandez'
description = 'spanish news agency'
oldest_article = 2
max_articles_per_feed = 100
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
language = 'es'
timefmt = '[%a, %d %b, %Y]'
remove_tags_before = dict(name='div' , attrs={'class':['nivel1 bg_3col']})
remove_tags_after = dict(name='div' , attrs={'id':['ImprimirEnviarNoticia']})
remove_tags = [
dict(name='ul', attrs={'id':['entidadesNoticia','MenuSecciones']})
,dict(name='div', attrs={'id':['ImprimirEnviarNoticia','PublicidadSuperior','CabeceraDerecha','Comentarios','comentarios full fbConnectAPI','ComentarEstaNoticia','ctl00_Superior_Main_MasEnChance_cajamasnoticias','gl_chn','videos_portada_derecha','galeria_portada_central','galeria_portada_central_boxes']})
,dict(name='div', attrs={'class':['infoRelacionada','col_1','buscador','caja doblecolumna strong','CHANCE_EP_Encuesta_frontal text','seccionportada col_0','seccion header','text','pie caption_over']})
,dict(name='a', attrs={'class':['buscadorLabel']})
,dict(name='span', attrs={'class':['editado']})
,dict(name='table')
,dict(name='li')
]
feeds = [
(u'Portada' , u'http://www.europapress.es/rss/rss.aspx')
,(u'Nacional' , u'http://www.europapress.es/rss/rss.aspx?ch=66')
,(u'Internacional' , u'http://www.europapress.es/rss/rss.aspx?ch=69')
,(u'Economia' , u'http://www.europapress.es/rss/rss.aspx?ch=136')
,(u'Deportes' , u'http://www.europapress.es/rss/rss.aspx?ch=67')
,(u'Cultura' , u'http://www.europapress.es/rss/rss.aspx?ch=126')
,(u'Sociedad' , u'http://www.europapress.es/rss/rss.aspx?ch=73')
,(u'Motor' , u'http://www.europapress.es/rss/rss.aspx?ch=435')
,(u'CHANCE' , u'http://www.europapress.es/rss/rss.aspx?ch=549')
,(u'Comunicados' , u'http://www.europapress.es/rss/rss.aspx?ch=137')
]

View File

@ -35,7 +35,7 @@ class IrishTimes(BasicNewsRecipe):
def print_version(self, url):
if url.count('rss.feedsportal.com'):
u = 'http://www.irishtimes.com' + \
(((url[69:].replace('0C','/')).replace('0A','0'))).replace('0Bhtml/story01.htm','_pf.html')
(((url[70:].replace('0C','/')).replace('0A','0'))).replace('0Bhtml/story01.htm','_pf.html')
else:
u = url.replace('.html','_pf.html')
return u

View File

@ -0,0 +1,80 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2011, Attis <attis@attis.one.pl>'
__version__ = 'v. 0.1'
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class KopalniaWiedzy(BasicNewsRecipe):
title = u'Kopalnia Wiedzy'
publisher = u'Kopalnia Wiedzy'
description = u'Ciekawostki ze świata nauki i techniki'
encoding = 'utf-8'
__author__ = 'Attis'
language = 'pl'
oldest_article = 7
max_articles_per_feed = 100
INDEX = u'http://kopalniawiedzy.pl/'
remove_javascript = True
no_stylesheets = True
remove_tags = [{'name':'p', 'attrs': {'class': 'keywords'} }]
remove_tags_after = dict(attrs={'class':'ad-square'})
keep_only_tags = [dict(name="div", attrs={'id':'articleContent'})]
extra_css = '.topimage {margin-top: 30px}'
preprocess_regexps = [
(re.compile(u'<a .* rel="lightboxText" .*><img (.*)></a>'),
lambda match: '<img class="topimage" ' + match.group(1) + '>' ),
(re.compile(u'<br /><br />'),
lambda match: '<br\/>')
]
feeds = [
(u'Biologia', u'http://kopalniawiedzy.pl/wiadomosci_biologia.rss'),
(u'Medycyna', u'http://kopalniawiedzy.pl/wiadomosci_medycyna.rss'),
(u'Psychologia', u'http://kopalniawiedzy.pl/wiadomosci_psychologia.rss'),
(u'Technologie', u'http://kopalniawiedzy.pl/wiadomosci_technologie.rss'),
(u'Ciekawostki', u'http://kopalniawiedzy.pl/wiadomosci_ciekawostki.rss'),
(u'Artykuły', u'http://kopalniawiedzy.pl/artykuly.rss')
]
def is_link_wanted(self, url, tag):
return tag['class'] == 'next'
def remove_beyond(self, tag, next):
while tag is not None and getattr(tag, 'name', None) != 'body':
after = getattr(tag, next)
while after is not None:
ns = getattr(tag, next)
after.extract()
after = ns
tag = tag.parent
def append_page(self, soup, appendtag, position):
pager = soup.find('a',attrs={'class':'next'})
if pager:
nexturl = self.INDEX + pager['href']
soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'id':'articleContent'})
tag = texttag.find(attrs={'class':'pages'})
self.remove_beyond(tag, 'nextSibling')
newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos)
appendtag.insert(position,texttag)
def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3)
for item in soup.findAll('div',attrs={'class':'pages'}):
item.extract()
for item in soup.findAll('p', attrs={'class':'wykop'}):
item.extract()
return soup

View File

@ -0,0 +1,40 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2011, Attis <attis@attis.one.pl>'
__version__ = 'v. 0.1'
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class KorespondentPL(BasicNewsRecipe):
title = u'Korespondent.pl'
publisher = u'Korespondent.pl'
description = u'Centrum wolnorynkowe - serwis ludzi wolnych'
encoding = 'utf-8'
__author__ = 'Attis'
language = 'pl'
oldest_article = 15
max_articles_per_feed = 100
remove_javascript = True
no_stylesheets = True
keep_only_tags = [dict(name='div', attrs={'class':'publicystyka'})]
remove_tags = [{'name': 'meta'}, {'name':'div', 'attrs': {'class': 'zdjecie'} }]
extra_css = '.naglowek {font-size: small}\n .tytul {font-size: x-large; padding-bottom: 10px; padding-top: 30px} \n .external {font-size: small}'
preprocess_regexps = [
(re.compile(u'<a href="index\.php.*>(.*)</a>'),
lambda match: match.group(1) ),
(re.compile(u'<i>'),
lambda match:'<i class="external">' ),
(re.compile(u'<p></p>Więcej'),
lambda match:'Więcej' ),
(re.compile(u'target="_blank"'),
lambda match:'target="_blank" class="external"' ),
(re.compile(u'<p align="center">\nPoczytaj inne teksty w <a href="http://www.korespondent.pl">Serwisie wolnorynkowym Korespondent.pl</a>.*</body>', re.DOTALL|re.IGNORECASE),
lambda match: '</div></body>'),
]
feeds = [(u'Serwis informacyjny', u'http://korespondent.pl/rss.xml')]

View File

@ -0,0 +1,43 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1291540961(BasicNewsRecipe):
title = u'Radio Praha'
__author__ = 'Francois Pellicaan'
description = 'News and information from and about The Czech republic. '
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_empty_feeds = True
encoding = 'utf8'
publisher = 'Radio Prague'
category = 'News'
language = 'en_CZ'
publication_type = 'newsportal'
extra_css = 'h1 .section { display: block; text-transform: uppercase; font-size: 10px; margin-top: 4em; } \n .title { font-size: 14px; margin-top: 4em; } \n a.photo { display: block; clear:both; } \n .caption { font-size: 9px; display: block; clear:both; padding:0px 0px 20px 0px; } \n a { font-type: normal; }'
keep_only_tags = [
dict(name='div', attrs={'class':['main']})
]
remove_tags = [
dict(name='div', attrs={'class':['cleaner', 'options', 'toolsXXL']}),
dict(name='ul', attrs={'class':['tools']})
]
feeds = [
(u'Current Affairs', 'http://www.radio.cz/feeds/rss/en/themes/curraffrs.xml'),
(u'Society', 'http://www.radio.cz/feeds/rss/en/themes/society.xml'),
(u'European Union', 'http:http://www.radio.cz/feeds/rss/en/themes/eu.xml'),
(u'Foreign policy', 'http://www.radio.cz/feeds/rss/en/themes/foreignpolicy.xml'),
(u'Business', 'http://www.radio.cz/feeds/rss/en/themes/business.xml'),
(u'Culture', 'http://www.radio.cz/feeds/rss/en/themes/culture.xml'),
(u'Czechs abroad', 'http://www.radio.cz/feeds/rss/en/themes/czechabroad.xml'),
(u'History', 'http://www.radio.cz/feeds/rss/en/themes/history.xml'),
(u'Nature', 'http://www.radio.cz/feeds/rss/en/themes/nature.xml'),
(u'Science', 'http://www.radio.cz/feeds/rss/en/themes/science.xml'),
(u'Sport', 'http://www.radio.cz/feeds/rss/en/themes/sport.xml'),
(u'Travel', 'http://www.radio.cz/feeds/rss/en/themes/travel.xml'),
]

View File

@ -0,0 +1,44 @@
# -*- coding: utf-8 -*-
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1291540961(BasicNewsRecipe):
title = u'Radio Praha'
__author__ = 'Francois Pellicaan'
description = u'Česká oficiální mezinárodní vysílací stanice.'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_empty_feeds = True
encoding = 'utf8'
publisher = u'Český rozhlas'
category = 'News'
language = 'cs'
publication_type = 'newsportal'
extra_css = u'h1 .section { display: block; text-transform: uppercase; font-size: 10px; margin-top: 4em; } \n .title { font-size: 14px; margin-top: 4em; } \n a.photo { display: block; clear:both; } \n .caption { font-size: 9px; display: block; clear:both; padding:0px 0px 20px 0px; } \n a { font-type: normal; }'
keep_only_tags = [
dict(name='div', attrs={'class':['main']})
]
remove_tags = [
dict(name='div', attrs={'class':['cleaner', 'options', 'toolsXXL']}),
dict(name='ul', attrs={'class':['tools']})
]
feeds = [
(u'Domácí politika', 'http://www.radio.cz/feeds/rss/cs/oblast/dompol.xml'),
(u'Společnost', 'http://www.radio.cz/feeds/rss/cs/oblast/spolecnost.xml'),
(u'Evropská unie', 'http://www.radio.cz/feeds/rss/cs/oblast/eu.xml'),
(u'Zahraniční politika', 'http://www.radio.cz/feeds/rss/cs/oblast/zahrpol.xml'),
(u'Ekonomika', 'http://www.radio.cz/feeds/rss/cs/oblast/ekonomika.xml'),
(u'Kultura', 'http://www.radio.cz/feeds/rss/cs/oblast/kultura.xml'),
(u'Krajané', 'http://www.radio.cz/feeds/rss/cs/oblast/krajane.xml'),
(u'Historie', 'http://www.radio.cz/feeds/rss/cs/oblast/historie.xml'),
(u'Příroda', 'http://www.radio.cz/feeds/rss/cs/oblast/priroda.xml'),
(u'Věda', 'http://www.radio.cz/feeds/rss/cs/oblast/veda.xml'),
(u'Sport', 'http://www.radio.cz/feeds/rss/cs/oblast/sport.xml'),
(u'Cestování', 'http://www.radio.cz/feeds/rss/cs/oblast/cestovani.xml'),
]

View File

@ -131,6 +131,7 @@ class WallStreetJournal(BasicNewsRecipe):
'description':desc, 'date':''})
self.log('\tFound WN article:', title)
self.log('\t\t', desc)
return articles
@ -157,17 +158,23 @@ class WallStreetJournal(BasicNewsRecipe):
meta = a.find(attrs={'class':'meta_sectionName'})
if meta is not None:
meta.extract()
title = self.tag_to_string(a).strip() + ' [%s]'%self.tag_to_string(meta)
meta = self.tag_to_string(meta).strip()
if meta:
title = self.tag_to_string(a).strip() + ' [%s]'%meta
else:
title = self.tag_to_string(a).strip()
url = 'http://online.wsj.com'+a['href']
desc = ''
p = container.find('p')
if p is not None:
for p in container.findAll('p'):
desc = self.tag_to_string(p)
if not 'Subscriber Content' in desc:
break
articles.append({'title':title, 'url':url,
'description':desc, 'date':''})
self.log('\tFound article:', title)
self.log('\t\t', desc)
return articles

View File

@ -140,12 +140,17 @@ class WallStreetJournal(BasicNewsRecipe):
meta = a.find(attrs={'class':'meta_sectionName'})
if meta is not None:
meta.extract()
title = self.tag_to_string(a).strip() + ' [%s]'%self.tag_to_string(meta)
meta = self.tag_to_string(meta).strip()
if meta:
title = self.tag_to_string(a).strip() + ' [%s]'%meta
else:
title = self.tag_to_string(a).strip()
url = 'http://online.wsj.com'+a['href']
desc = ''
p = container.find('p')
if p is not None:
for p in container.findAll('p'):
desc = self.tag_to_string(p)
if not 'Subscriber Content' in desc:
break
articles.append({'title':title, 'url':url,
'description':desc, 'date':''})

View File

@ -12,7 +12,7 @@
"re": "def evaluate(self, formatter, kwargs, mi, locals, val, pattern, replacement):\n return re.sub(pattern, replacement, val)\n",
"add": "def evaluate(self, formatter, kwargs, mi, locals, x, y):\n x = float(x if x else 0)\n y = float(y if y else 0)\n return unicode(x + y)\n",
"lookup": "def evaluate(self, formatter, kwargs, mi, locals, val, *args):\n if len(args) == 2: # here for backwards compatibility\n if val:\n return formatter.vformat('{'+args[0].strip()+'}', [], kwargs)\n else:\n return formatter.vformat('{'+args[1].strip()+'}', [], kwargs)\n if (len(args) % 2) != 1:\n raise ValueError(_('lookup requires either 2 or an odd number of arguments'))\n i = 0\n while i < len(args):\n if i + 1 >= len(args):\n return formatter.vformat('{' + args[i].strip() + '}', [], kwargs)\n if re.search(args[i], val):\n return formatter.vformat('{'+args[i+1].strip() + '}', [], kwargs)\n i += 2\n",
"template": "def evaluate(self, formatter, kwargs, mi, locals, template):\n template = template.replace('[[', '{').replace(']]', '}')\n return formatter.safe_format(template, kwargs, 'TEMPLATE', mi)\n",
"template": "def evaluate(self, formatter, kwargs, mi, locals, template):\n template = template.replace('[[', '{').replace(']]', '}')\n return formatter.__class__().safe_format(template, kwargs, 'TEMPLATE', mi)\n",
"print": "def evaluate(self, formatter, kwargs, mi, locals, *args):\n print args\n return None\n",
"titlecase": "def evaluate(self, formatter, kwargs, mi, locals, val):\n return titlecase(val)\n",
"test": "def evaluate(self, formatter, kwargs, mi, locals, val, value_if_set, value_not_set):\n if val:\n return value_if_set\n else:\n return value_not_set\n",

View File

@ -43,7 +43,7 @@ class Stage3(Command):
description = 'Stage 3 of the publish process'
sub_commands = ['upload_user_manual', 'upload_demo', 'sdist',
'upload_to_google_code', 'upload_to_sourceforge',
'upload_to_sourceforge', 'upload_to_google_code',
'tag_release', 'upload_to_server',
'upload_to_mobileread',
]

View File

@ -324,7 +324,7 @@ class UploadToServer(Command):
def run(self, opts):
check_call('ssh divok rm -f %s/calibre-\*.tar.gz'%DOWNLOADS, shell=True)
check_call('scp dist/calibre-*.tar.gz divok:%s/'%DOWNLOADS, shell=True)
#check_call('scp dist/calibre-*.tar.gz divok:%s/'%DOWNLOADS, shell=True)
check_call('gpg --armor --detach-sign dist/calibre-*.tar.gz',
shell=True)
check_call('scp dist/calibre-*.tar.gz.asc divok:%s/signatures/'%DOWNLOADS,

View File

@ -2,7 +2,7 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
__appname__ = 'calibre'
__version__ = '0.7.43'
__version__ = '0.7.44'
__author__ = "Kovid Goyal <kovid@kovidgoyal.net>"
import re

View File

@ -28,8 +28,8 @@ class HeuristicProcessor(object):
self.linereg = re.compile('(?<=<p).*?(?=</p>)', re.IGNORECASE|re.DOTALL)
self.blankreg = re.compile(r'\s*(?P<openline><p(?!\sclass=\"(softbreak|whitespace)\")[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE)
self.anyblank = re.compile(r'\s*(?P<openline><p[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE)
self.multi_blank = re.compile(r'(\s*<p[^>]*>\s*</p>){2,}(?!\s*<h\d)', re.IGNORECASE)
self.any_multi_blank = re.compile(r'(\s*<p[^>]*>\s*</p>){2,}', re.IGNORECASE)
self.multi_blank = re.compile(r'(\s*<p[^>]*>\s*</p>(\s*<div[^>]*>\s*</div>\s*)*){2,}(?!\s*<h\d)', re.IGNORECASE)
self.any_multi_blank = re.compile(r'(\s*<p[^>]*>\s*</p>(\s*<div[^>]*>\s*</div>\s*)*){2,}', re.IGNORECASE)
self.line_open = "<(?P<outer>p|div)[^>]*>\s*(<(?P<inner1>font|span|[ibu])[^>]*>)?\s*(<(?P<inner2>font|span|[ibu])[^>]*>)?\s*(<(?P<inner3>font|span|[ibu])[^>]*>)?\s*"
self.line_close = "(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>"
self.single_blank = re.compile(r'(\s*<p[^>]*>\s*</p>)', re.IGNORECASE)
@ -149,17 +149,17 @@ class HeuristicProcessor(object):
]
ITALICIZE_STYLE_PATS = [
r'(?msu)(?<=\s)_(?P<words>\S[^_]{0,40}?\S)?_(?=[\s\.,\!\?])',
r'(?msu)(?<=\s)/(?P<words>\S[^/]{0,40}?\S)?/(?=[\s\.,\!\?])',
r'(?msu)(?<=\s)~~(?P<words>\S[^~]{0,40}?\S)?~~(?=[\s\.,\!\?])',
r'(?msu)(?<=\s)\*(?P<words>\S[^\*]{0,40}?\S)?\*(?=[\s\.,\!\?])',
r'(?msu)(?<=\s)~(?P<words>\S[^~]{0,40}?\S)?~(?=[\s\.,\!\?])',
r'(?msu)(?<=\s)_/(?P<words>\S[^/_]{0,40}?\S)?/_(?=[\s\.,\!\?])',
r'(?msu)(?<=\s)_\*(?P<words>\S[^\*_]{0,40}?\S)?\*_(?=[\s\.,\!\?])',
r'(?msu)(?<=\s)\*/(?P<words>\S[^/\*]{0,40}?\S)?/\*(?=[\s\.,\!\?])',
r'(?msu)(?<=\s)_\*/(?P<words>\S[^\*_]{0,40}?\S)?/\*_(?=[\s\.,\!\?])',
r'(?msu)(?<=\s)/:(?P<words>\S[^:/]{0,40}?\S)?:/(?=[\s\.,\!\?])',
r'(?msu)(?<=\s)\|:(?P<words>\S[^:\|]{0,40}?\S)?:\|(?=[\s\.,\!\?])',
r'(?msu)(?<=[\s>])_(?P<words>[^_]+)?_',
r'(?msu)(?<=[\s>])/(?P<words>[^/]+)?/',
r'(?msu)(?<=[\s>])~~(?P<words>[^~]+)?~~',
r'(?msu)(?<=[\s>])\*(?P<words>[^\*]+)?\*',
r'(?msu)(?<=[\s>])~(?P<words>[^~]+)?~',
r'(?msu)(?<=[\s>])_/(?P<words>[^/_]+)?/_',
r'(?msu)(?<=[\s>])_\*(?P<words>[^\*_]+)?\*_',
r'(?msu)(?<=[\s>])\*/(?P<words>[^/\*]+)?/\*',
r'(?msu)(?<=[\s>])_\*/(?P<words>[^\*_]+)?/\*_',
r'(?msu)(?<=[\s>])/:(?P<words>[^:/]+)?:/',
r'(?msu)(?<=[\s>])\|:(?P<words>[^:\|]+)?:\|',
]
for word in ITALICIZE_WORDS:
@ -384,6 +384,8 @@ class HeuristicProcessor(object):
html = re.sub(r"\s*<(font|[ibu]|em|strong)[^>]*>\s*(<(font|[ibu]|em|strong)[^>]*>\s*</(font|[ibu]|em|strong)>\s*){0,2}\s*</(font|[ibu]|em|strong)>", " ", html)
html = re.sub(r"\s*<span[^>]*>\s*(<span[^>]>\s*</span>){0,2}\s*</span>\s*", " ", html)
html = re.sub(r"\s*<(font|[ibu]|em|strong)[^>]*>\s*(<(font|[ibu]|em|strong)[^>]*>\s*</(font|[ibu]|em|strong)>\s*){0,2}\s*</(font|[ibu]|em|strong)>", " ", html)
# delete surrounding divs from empty paragraphs
html = re.sub('<div[^>]*>\s*<p[^>]*>\s*</p>\s*</div>', '<p> </p>', html)
# Empty heading tags
html = re.sub(r'(?i)<h\d+>\s*</h\d+>', '', html)
self.deleted_nbsps = True
@ -561,7 +563,6 @@ class HeuristicProcessor(object):
# Determine whether the document uses interleaved blank lines
self.blanks_between_paragraphs = self.analyze_blanks(html)
#self.dump(html, 'before_chapter_markup')
# detect chapters/sections to match xpath or splitting logic
if getattr(self.extra_opts, 'markup_chapter_headings', False):

View File

@ -15,6 +15,7 @@ from calibre import guess_type, strftime
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.ebooks.oeb.base import XPath, XHTML_NS, XHTML
from calibre.library.comments import comments_to_html
from calibre.utils.date import is_date_undefined
JACKET_XPATH = '//h:meta[@name="calibre-content" and @content="jacket"]'
@ -109,7 +110,7 @@ def get_rating(rating, rchar, e_rchar):
def render_jacket(mi, output_profile,
alt_title=_('Unknown'), alt_tags=[], alt_comments='',
alt_publisher=('Unknown publisher')):
alt_publisher=('')):
css = P('jacket/stylesheet.css', data=True).decode('utf-8')
try:
@ -127,10 +128,13 @@ def render_jacket(mi, output_profile,
try:
publisher = mi.publisher if mi.publisher else alt_publisher
except:
publisher = _('Unknown publisher')
publisher = ''
try:
pubdate = strftime(u'%Y', mi.pubdate.timetuple())
if is_date_undefined(mi.pubdate):
pubdate = ''
else:
pubdate = strftime(u'%Y', mi.pubdate.timetuple())
except:
pubdate = ''
@ -175,19 +179,24 @@ def render_jacket(mi, output_profile,
soup = BeautifulSoup(generated_html)
if not series:
series_tag = soup.find(attrs={'class':'cbj_series'})
series_tag.extract()
if series_tag is not None:
series_tag.extract()
if not rating:
rating_tag = soup.find(attrs={'class':'cbj_rating'})
rating_tag.extract()
if rating_tag is not None:
rating_tag.extract()
if not tags:
tags_tag = soup.find(attrs={'class':'cbj_tags'})
tags_tag.extract()
if tags_tag is not None:
tags_tag.extract()
if not pubdate:
pubdate_tag = soup.find(attrs={'class':'cbj_pubdate'})
pubdate_tag.extract()
pubdate_tag = soup.find(attrs={'class':'cbj_pubdata'})
if pubdate_tag is not None:
pubdate_tag.extract()
if output_profile.short_name != 'kindle':
hr_tag = soup.find('hr', attrs={'class':'cbj_kindle_banner_hr'})
hr_tag.extract()
if hr_tag is not None:
hr_tag.extract()
return soup.renderContents(None)

View File

@ -86,14 +86,18 @@ class PMLMLizer(object):
# This is used for adding \CX tags chapter markers. This is separate
# from the optional inline toc.
self.toc = {}
for item in oeb_book.toc:
self.create_flat_toc(self.oeb_book.toc)
return self.pmlmlize_spine()
def create_flat_toc(self, nodes, level=0):
for item in nodes:
href, mid, id = item.href.partition('#')
self.get_anchor_id(href, id)
if not self.toc.get(href, None):
self.toc[href] = {}
self.toc[href][id] = item.title
return self.pmlmlize_spine()
self.toc[href][id] = (item.title, level)
self.create_flat_toc(item.nodes, level + 1)
def pmlmlize_spine(self):
self.image_hrefs = {}
@ -255,9 +259,10 @@ class PMLMLizer(object):
toc_page = page.href
if self.toc.get(toc_page, None):
for toc_x in (toc_name, toc_id):
toc_title = self.toc[toc_page].get(toc_x, None)
toc_title, toc_depth = self.toc[toc_page].get(toc_x, (None, 0))
if toc_title:
text.append('\\C0="%s"' % toc_title)
toc_depth = max(min(toc_depth, 4), 0)
text.append('\\C%s="%s"' % (toc_depth, toc_title))
# Process style information that needs holds a single tag
# Commented out because every page in an OEB book starts with this style

View File

@ -226,7 +226,7 @@ class ParseRtf:
try:
return_value = process_tokens_obj.process_tokens()
except InvalidRtfException, msg:
#Check to see if the file is correctly encoded
# Check to see if the file is correctly encoded
encode_obj = default_encoding.DefaultEncoding(
in_file = self.__temp_file,
run_level = self.__run_level,
@ -237,14 +237,14 @@ class ParseRtf:
check_encoding_obj = check_encoding.CheckEncoding(
bug_handler = RtfInvalidCodeException,
)
enc = 'cp' + encode_obj.get_codepage()
if enc == 'cp10000':
enc = 'mac_roman'
msg = 'Exception in token processing'
enc = encode_obj.get_codepage()
if enc != 'mac_roman':
enc = 'cp' + enc
msg = '%s\nException in token processing' % str(msg)
if check_encoding_obj.check_encoding(self.__file, enc):
file_name = self.__file if isinstance(self.__file, str) \
else self.__file.encode('utf-8')
msg = 'File %s does not appear to be correctly encoded.\n' % file_name
msg +='\nFile %s does not appear to be correctly encoded.\n' % file_name
try:
os.remove(self.__temp_file)
except OSError:

View File

@ -210,7 +210,7 @@ class Colors:
hex_num = self.__color_dict.get(num)
if hex_num is None:
hex_num = '0'
if self.__run_level > 5:
if self.__run_level > 3:
msg = 'no value in self.__color_dict' \
'for key %s at line %d\n' % (num, self.__line)
raise self.__bug_handler, msg

View File

@ -786,21 +786,23 @@ class ProcessTokens:
token = line.replace("\n","")
line_count += 1
if line_count == 1 and token != '\\{':
msg = 'Invalid RTF: document doesn\'t start with {\n'
msg = '\nInvalid RTF: document doesn\'t start with {\n'
raise self.__exception_handler, msg
elif line_count == 2 and token[0:4] != '\\rtf':
msg = 'Invalid RTF: document doesn\'t start with \\rtf \n'
msg = '\nInvalid RTF: document doesn\'t start with \\rtf \n'
raise self.__exception_handler, msg
the_index = token.find('\\ ')
if token is not None and the_index > -1:
msg = 'Invalid RTF: token "\\ " not valid.\n'
msg = '\nInvalid RTF: token "\\ " not valid.\nError at line %d'\
% line_count
raise self.__exception_handler, msg
elif token[:1] == "\\":
try:
token.decode('us-ascii')
except UnicodeError, msg:
msg = 'Invalid RTF: Tokens not ascii encoded.\n%s' % str(msg)
msg = '\nInvalid RTF: Tokens not ascii encoded.\n%s\nError at line %d'\
% (str(msg), line_count)
raise self.__exception_handler, msg
line = self.process_cw(token)
if line is not None:
@ -816,7 +818,7 @@ class ProcessTokens:
write_obj.write('tx<nu<__________<%s\n' % field)
if not line_count:
msg = 'Invalid RTF: file appears to be empty.\n'
msg = '\nInvalid RTF: file appears to be empty.\n'
raise self.__exception_handler, msg
copy_obj = copy.Copy(bug_handler = self.__bug_handler)
@ -827,7 +829,7 @@ class ProcessTokens:
bad_brackets = self.__check_brackets(self.__file)
if bad_brackets:
msg = 'Invalid RTF: document does not have matching brackets.\n'
msg = '\nInvalid RTF: document does not have matching brackets.\n'
raise self.__exception_handler, msg
else:
return self.__return_code

View File

@ -117,6 +117,7 @@ class Tokenize:
input_file = self.__replace_spchar.mreplace(input_file)
# this is for older RTF
input_file = self.__par_exp.sub('\n\\par \n', input_file)
input_file = self.__cwdigit_exp.sub("\g<1>\n\g<2>", input_file)
input_file = self.__ms_hex_exp.sub("\\mshex0\g<1> ", input_file)
input_file = self.__utf_ud.sub("\\{\\uc0 \g<1>\\}", input_file)
#remove \n in bin data
@ -139,17 +140,17 @@ class Tokenize:
"\\_": "\\_ ",
"\\:": "\\: ",
"\\-": "\\- ",
# turn into a generic token to eliminate special
# cases and make processing easier
#turn into a generic token to eliminate special
#cases and make processing easier
"\\{": "\\ob ",
# turn into a generic token to eliminate special
# cases and make processing easier
#turn into a generic token to eliminate special
#cases and make processing easier
"\\}": "\\cb ",
# put a backslash in front of to eliminate special cases and
# make processing easier
#put a backslash in front of to eliminate special cases and
#make processing easier
"{": "\\{",
# put a backslash in front of to eliminate special cases and
# make processing easier
#put a backslash in front of to eliminate special cases and
#make processing easier
"}": "\\}",
}
self.__replace_spchar = MReplace(SIMPLE_RPL)
@ -165,21 +166,9 @@ class Tokenize:
#remove \n from endline char
self.__splitexp = re.compile(r"(\\[{}]|\n|\\[^\s\\{}&]+(?:[ \t\r\f\v])?)")
#this is for old RTF
self.__par_exp = re.compile(r'\\\n+')
self.__par_exp = re.compile(r'(\\\n+|\\ )')
#handle cw using a digit as argument and without space as delimiter
self.__cwdigit_exp = re.compile(r"(\\[a-zA-Z]+[\-0-9]+)([^0-9 \\]+)")
#self.__bin_exp = re.compile(r"\\bin(-?\d{1,8}) {0,1}")
#self.__utf_exp = re.compile(r"^\\u(-?\d{3,6})")
#self.__splitexp = re.compile(r"(\\[\\{}]|{|}|\n|\\[^\s\\{}&]+(?:\s)?)")
#self.__remove_line = re.compile(r'\n+')
##self.num_exp = re.compile(r"(\*|:|[a-zA-Z]+)(.*)")
def __correct_spliting(self, token):
match_obj = re.search(self.__cwdigit_exp, token)
if match_obj is None:
return token
else:
return '%s\n%s' % (match_obj.group(1), match_obj.group(2))
def tokenize(self):
"""Main class for handling other methods. Reads the file \
@ -196,8 +185,6 @@ class Tokenize:
tokens = map(self.__unicode_process, tokens)
#remove empty items created by removing \uc
tokens = filter(lambda x: len(x) > 0, tokens)
#handles bothersome cases
tokens = map(self.__correct_spliting, tokens)
#write
with open(self.__write_to, 'wb') as write_obj:

View File

@ -12,7 +12,7 @@ from calibre.ebooks.chardet import detect
from calibre.ebooks.txt.processor import convert_basic, convert_markdown, \
separate_paragraphs_single_line, separate_paragraphs_print_formatted, \
preserve_spaces, detect_paragraph_type, detect_formatting_type, \
normalize_line_endings, convert_textile
normalize_line_endings, convert_textile, remove_indents, block_to_single_line
from calibre import _ent_pat, xml_entity_to_unicode
class TXTInput(InputFormatPlugin):
@ -47,6 +47,9 @@ class TXTInput(InputFormatPlugin):
OptionRecommendation(name='preserve_spaces', recommended_value=False,
help=_('Normally extra spaces are condensed into a single space. '
'With this option all spaces will be displayed.')),
OptionRecommendation(name='txt_in_remove_indents', recommended_value=False,
help=_('Normally extra space at the beginning of lines is retained. '
'With this option they will be removed.')),
OptionRecommendation(name="markdown_disable_toc", recommended_value=False,
help=_('Do not insert a Table of Contents into the output text.')),
])
@ -55,8 +58,10 @@ class TXTInput(InputFormatPlugin):
accelerators):
self.log = log
log.debug('Reading text from file...')
length = 0
txt = stream.read()
# Get the encoding of the document.
if options.input_encoding:
ienc = options.input_encoding
@ -70,23 +75,12 @@ class TXTInput(InputFormatPlugin):
log.debug('No input encoding specified and could not auto detect using %s' % ienc)
txt = txt.decode(ienc, 'replace')
# Replace entities
txt = _ent_pat.sub(xml_entity_to_unicode, txt)
# Normalize line endings
txt = normalize_line_endings(txt)
if options.formatting_type == 'auto':
options.formatting_type = detect_formatting_type(txt)
if options.formatting_type == 'heuristic':
setattr(options, 'enable_heuristics', True)
setattr(options, 'markup_chapter_headings', True)
setattr(options, 'italicize_common_cases', True)
setattr(options, 'fix_indents', True)
setattr(options, 'delete_blank_paragraphs', True)
setattr(options, 'format_scene_breaks', True)
setattr(options, 'dehyphenate', True)
# Determine the paragraph type of the document.
if options.paragraph_type == 'auto':
options.paragraph_type = detect_paragraph_type(txt)
@ -96,50 +90,68 @@ class TXTInput(InputFormatPlugin):
else:
log.debug('Auto detected paragraph type as %s' % options.paragraph_type)
# Detect formatting
if options.formatting_type == 'auto':
options.formatting_type = detect_formatting_type(txt)
log.debug('Auto detected formatting as %s' % options.formatting_type)
if options.formatting_type == 'heuristic':
setattr(options, 'enable_heuristics', True)
setattr(options, 'unwrap_lines', False)
# Reformat paragraphs to block formatting based on the detected type.
# We don't check for block because the processor assumes block.
# single and print at transformed to block for processing.
if options.paragraph_type == 'single':
txt = separate_paragraphs_single_line(txt)
elif options.paragraph_type == 'print':
txt = separate_paragraphs_print_formatted(txt)
txt = block_to_single_line(txt)
elif options.paragraph_type == 'unformatted':
from calibre.ebooks.conversion.utils import HeuristicProcessor
# unwrap lines based on punctuation
docanalysis = DocAnalysis('txt', txt)
length = docanalysis.line_length(.5)
preprocessor = HeuristicProcessor(options, log=getattr(self, 'log', None))
txt = preprocessor.punctuation_unwrap(length, txt, 'txt')
txt = separate_paragraphs_single_line(txt)
else:
txt = block_to_single_line(txt)
if getattr(options, 'enable_heuristics', False) and getattr(options, 'dehyphenate', False):
docanalysis = DocAnalysis('txt', txt)
if not length:
length = docanalysis.line_length(.5)
dehyphenator = Dehyphenator(options.verbose, log=self.log)
txt = dehyphenator(txt,'txt', length)
# User requested transformation on the text.
if options.txt_in_remove_indents:
txt = remove_indents(txt)
# Preserve spaces will replace multiple spaces to a space
# followed by the &nbsp; entity.
if options.preserve_spaces:
txt = preserve_spaces(txt)
# Get length for hyphen removal and punctuation unwrap
docanalysis = DocAnalysis('txt', txt)
length = docanalysis.line_length(.5)
# Process the text using the appropriate text processor.
html = ''
if options.formatting_type == 'markdown':
log.debug('Running text though markdown conversion...')
log.debug('Running text through markdown conversion...')
try:
html = convert_markdown(txt, disable_toc=options.markdown_disable_toc)
except RuntimeError:
raise ValueError('This txt file has malformed markup, it cannot be'
' converted by calibre. See http://daringfireball.net/projects/markdown/syntax')
elif options.formatting_type == 'textile':
log.debug('Running text though textile conversion...')
log.debug('Running text through textile conversion...')
html = convert_textile(txt)
else:
# Dehyphenate
dehyphenator = Dehyphenator(options.verbose, log=self.log)
txt = dehyphenator(txt,'txt', length)
# We don't check for block because the processor assumes block.
# single and print at transformed to block for processing.
if options.paragraph_type == 'single' or options.paragraph_type == 'unformatted':
txt = separate_paragraphs_single_line(txt)
elif options.paragraph_type == 'print':
txt = separate_paragraphs_print_formatted(txt)
if options.paragraph_type == 'unformatted':
from calibre.ebooks.conversion.utils import HeuristicProcessor
# get length
# unwrap lines based on punctuation
preprocessor = HeuristicProcessor(options, log=getattr(self, 'log', None))
txt = preprocessor.punctuation_unwrap(length, txt, 'txt')
log.debug('Running text through basic conversion...')
flow_size = getattr(options, 'flow_size', 0)
html = convert_basic(txt, epub_split_size_kb=flow_size)
# Run the HTMLized text through the html processing plugin.
from calibre.customize.ui import plugin_for_input_format
html_input = plugin_for_input_format('html')
for opt in html_input.options:
@ -158,6 +170,7 @@ class TXTInput(InputFormatPlugin):
htmlfile.write(html.encode('utf-8'))
odi = options.debug_pipeline
options.debug_pipeline = None
# Generate oeb from htl conversion.
oeb = html_input.convert(open(htmlfile.name, 'rb'), options, 'html', log,
{})
options.debug_pipeline = odi

View File

@ -18,20 +18,24 @@ from calibre.utils.cleantext import clean_ascii_chars
HTML_TEMPLATE = u'<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/><title>%s</title></head><body>\n%s\n</body></html>'
def clean_txt(txt):
'''
Run transformations on the text to put it into
consistent state.
'''
if isbytestring(txt):
txt = txt.decode('utf-8', 'replace')
# Strip whitespace from the end of the line. Also replace
# all line breaks with \n.
txt = '\n'.join([line.rstrip() for line in txt.splitlines()])
# Replace whitespace at the beginning of the list with &nbsp;
txt = re.sub('(?m)(?P<space>[ ]+)', lambda mo: '&nbsp;' * mo.groups('space').count(' '), txt)
txt = re.sub('(?m)(?P<space>[\t]+)', lambda mo: '&nbsp;' * 4 * mo.groups('space').count('\t'), txt)
# Replace whitespace at the beginning of the line with &nbsp;
txt = re.sub('(?m)(?P<space>^[ ]+)(?=.)', lambda mo: '&nbsp;' * mo.groups('space').count(' '), txt)
txt = re.sub('(?m)(?P<space>^[\t]+)(?=.)', lambda mo: '&nbsp;' * 4 * mo.groups('space').count('\t'), txt)
# Condense redundant spaces
txt = re.sub('[ ]{2,}', ' ', txt)
# Remove blank lines from the beginning and end of the document.
# Remove blank space from the beginning and end of the document.
txt = re.sub('^\s+(?=.)', '', txt)
txt = re.sub('(?<=.)\s+$', '', txt)
# Remove excessive line breaks.
@ -42,6 +46,15 @@ def clean_txt(txt):
return txt
def split_txt(txt, epub_split_size_kb=0):
'''
Ensure there are split points for converting
to EPUB. A misdetected paragraph type can
result in the entire document being one giant
paragraph. In this case the EPUB parser will not
be able to determine where to split the file
to accomidate the EPUB file size limitation
and will fail.
'''
#Takes care if there is no point to split
if epub_split_size_kb > 0:
if isinstance(txt, unicode):
@ -59,6 +72,12 @@ def split_txt(txt, epub_split_size_kb=0):
return txt
def convert_basic(txt, title='', epub_split_size_kb=0):
'''
Converts plain text to html by putting all paragraphs in
<p> tags. It condense and retains blank lines when necessary.
Requires paragraphs to be in single line format.
'''
txt = clean_txt(txt)
txt = split_txt(txt, epub_split_size_kb)
@ -99,14 +118,28 @@ def separate_paragraphs_single_line(txt):
return txt
def separate_paragraphs_print_formatted(txt):
txt = re.sub(u'(?miu)^(\t+|[ ]{2,})(?=.)', '\n\t', txt)
txt = re.sub(u'(?miu)^(?P<indent>\t+|[ ]{2,})(?=.)', lambda mo: '\n%s' % mo.group('indent'), txt)
return txt
def block_to_single_line(txt):
txt = re.sub(r'(?<=.)\n(?=.)', ' ', txt)
return txt
def preserve_spaces(txt):
'''
Replaces spaces multiple spaces with &nbsp; entities.
'''
txt = re.sub('(?P<space>[ ]{2,})', lambda mo: ' ' + ('&nbsp;' * (len(mo.group('space')) - 1)), txt)
txt = txt.replace('\t', '&nbsp;&nbsp;&nbsp;&nbsp;')
return txt
def remove_indents(txt):
'''
Remove whitespace at the beginning of each line.
'''
txt = re.sub('(?miu)^\s+', '', txt)
return txt
def opf_writer(path, opf_name, manifest, spine, mi):
opf = OPFCreator(path, mi)
opf.create_manifest(manifest)
@ -114,7 +147,10 @@ def opf_writer(path, opf_name, manifest, spine, mi):
with open(os.path.join(path, opf_name), 'wb') as opffile:
opf.render(opffile)
def split_string_separator(txt, size) :
def split_string_separator(txt, size):
'''
Splits the text by putting \n\n at the point size.
'''
if len(txt) > size:
txt = ''.join([re.sub(u'\.(?P<ends>[^.]*)$', '.\n\n\g<ends>',
txt[i:i+size], 1) for i in
@ -123,7 +159,7 @@ def split_string_separator(txt, size) :
def detect_paragraph_type(txt):
'''
Tries to determine the formatting of the document.
Tries to determine the paragraph type of the document.
block: Paragraphs are separated by a blank line.
single: Each line is a paragraph.
@ -166,6 +202,16 @@ def detect_paragraph_type(txt):
def detect_formatting_type(txt):
'''
Tries to determine the formatting of the document.
markdown: Markdown formatting is used.
textile: Textile formatting is used.
heuristic: When none of the above formatting types are
detected heuristic is returned.
'''
# Keep a count of the number of format specific object
# that are found in the text.
markdown_count = 0
textile_count = 0
@ -189,6 +235,8 @@ def detect_formatting_type(txt):
# Links
textile_count += len(re.findall(r'"(?=".*?\()(\(.+?\))*[^\(]+?(\(.+?\))*":[^\s]+', txt))
# Decide if either markdown or textile is used in the text
# based on the number of unique formatting elements found.
if markdown_count > 5 or textile_count > 5:
if markdown_count > textile_count:
return 'markdown'

View File

@ -55,6 +55,7 @@ class TXTMLizer(object):
self.log.info('Converting XHTML to TXT...')
self.oeb_book = oeb_book
self.opts = opts
self.toc_titles = []
self.toc_ids = []
self.last_was_heading = False
@ -94,8 +95,8 @@ class TXTMLizer(object):
if getattr(self.opts, 'inline_toc', None):
self.log.debug('Generating table of contents...')
toc.append(u'%s\n\n' % _(u'Table of Contents:'))
for item in self.oeb_book.toc:
toc.append(u'* %s\n\n' % item.title)
for item in self.toc_titles:
toc.append(u'* %s\n\n' % item)
return ''.join(toc)
def create_flat_toc(self, nodes):
@ -103,6 +104,7 @@ class TXTMLizer(object):
Turns a hierarchical list of TOC href's into a flat list.
'''
for item in nodes:
self.toc_titles.append(item.title)
self.toc_ids.append(item.href)
self.create_flat_toc(item.nodes)

View File

@ -94,6 +94,7 @@ class ShareConnMenu(QMenu): # {{{
I('mail.png'), _('Email to') + ' ' +account)
self.addAction(ac)
self.email_actions.append(ac)
ac.a_s.connect(sync_menu.action_triggered)
action1.a_s.connect(sync_menu.action_triggered)
action2.a_s.connect(sync_menu.action_triggered)
ac = self.addMenu(self.email_to_and_delete_menu)

View File

@ -6,156 +6,38 @@ __copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
from PyQt4.Qt import QLineEdit, QListView, QAbstractListModel, Qt, QTimer, \
QApplication, QPoint, QItemDelegate, QStyleOptionViewItem, \
QStyle, QEvent, pyqtSignal
from PyQt4.Qt import QLineEdit, QAbstractListModel, Qt, \
QApplication, QCompleter
from calibre.utils.config import tweaks
from calibre.utils.icu import sort_key, lower
from calibre.gui2 import NONE
from calibre.gui2.widgets import EnComboBox
class CompleterItemDelegate(QItemDelegate): # {{{
''' Renders the current item as thought it were selected '''
def __init__(self, view):
self.view = view
QItemDelegate.__init__(self, view)
def paint(self, p, opt, idx):
opt = QStyleOptionViewItem(opt)
opt.showDecorationSelected = True
if self.view.currentIndex() == idx:
opt.state |= QStyle.State_HasFocus
QItemDelegate.paint(self, p, opt, idx)
# }}}
class CompleteWindow(QListView): # {{{
'''
The completion popup. For keyboard and mouse handling see
:meth:`eventFilter`.
'''
#: This signal is emitted when the user selects one of the listed
#: completions, by mouse or keyboard
completion_selected = pyqtSignal(object)
def __init__(self, widget, model):
self.widget = widget
QListView.__init__(self)
self.setVisible(False)
self.setParent(None, Qt.Popup)
self.setAlternatingRowColors(True)
self.setFocusPolicy(Qt.NoFocus)
self._d = CompleterItemDelegate(self)
self.setItemDelegate(self._d)
self.setModel(model)
self.setFocusProxy(widget)
self.installEventFilter(self)
self.clicked.connect(self.do_selected)
self.entered.connect(self.do_entered)
self.setMouseTracking(True)
def do_entered(self, idx):
if idx.isValid():
self.setCurrentIndex(idx)
def do_selected(self, idx=None):
idx = self.currentIndex() if idx is None else idx
if idx.isValid():
data = unicode(self.model().data(idx, Qt.DisplayRole))
self.completion_selected.emit(data)
self.hide()
def eventFilter(self, o, e):
if o is not self:
return False
if e.type() == e.KeyPress:
key = e.key()
if key in (Qt.Key_Escape, Qt.Key_Backtab) or \
(key == Qt.Key_F4 and (e.modifiers() & Qt.AltModifier)):
self.hide()
return True
elif key in (Qt.Key_Enter, Qt.Key_Return, Qt.Key_Tab):
if key == Qt.Key_Tab and not self.currentIndex().isValid():
if self.model().rowCount() > 0:
self.setCurrentIndex(self.model().index(0))
self.do_selected()
return True
elif key in (Qt.Key_Up, Qt.Key_Down, Qt.Key_PageUp,
Qt.Key_PageDown):
return False
# Send key event to associated line edit
self.widget.eat_focus_out = False
try:
self.widget.event(e)
finally:
self.widget.eat_focus_out = True
if not self.widget.hasFocus():
# Line edit lost focus
self.hide()
if e.isAccepted():
# Line edit consumed event
return True
elif e.type() == e.MouseButtonPress:
# Hide popup if user clicks outside it, otherwise
# pass event to popup
if not self.underMouse():
self.hide()
return True
elif e.type() in (e.InputMethod, e.ShortcutOverride):
QApplication.sendEvent(self.widget, e)
return False # Do not filter this event
# }}}
class CompleteModel(QAbstractListModel):
def __init__(self, parent=None):
QAbstractListModel.__init__(self, parent)
self.sep = ','
self.space_before_sep = False
self.items = []
self.lowered_items = []
self.matches = []
def set_items(self, items):
items = [unicode(x.strip()) for x in items]
self.items = list(sorted(items, key=lambda x: sort_key(x)))
self.lowered_items = [lower(x) for x in self.items]
self.matches = []
self.reset()
def rowCount(self, *args):
return len(self.matches)
return len(self.items)
def data(self, index, role):
if role == Qt.DisplayRole:
r = index.row()
try:
return self.matches[r]
return self.items[r]
except IndexError:
pass
return NONE
def get_matches(self, prefix):
'''
Return all matches that (case insensitively) start with prefix
'''
prefix = lower(prefix)
ans = []
if prefix:
for i, test in enumerate(self.lowered_items):
if test.startswith(prefix):
ans.append(self.items[i])
return ans
def update_matches(self, matches):
self.matches = matches
self.reset()
class MultiCompleteLineEdit(QLineEdit):
'''
@ -169,16 +51,26 @@ class MultiCompleteLineEdit(QLineEdit):
'''
def __init__(self, parent=None):
self.eat_focus_out = True
self.max_visible_items = 7
self.current_prefix = None
QLineEdit.__init__(self, parent)
self.sep = ','
self.space_before_sep = False
self._model = CompleteModel(parent=self)
self.complete_window = CompleteWindow(self, self._model)
self._completer = c = QCompleter(self._model, self)
c.setWidget(self)
c.setCompletionMode(QCompleter.PopupCompletion)
c.setCaseSensitivity(Qt.CaseInsensitive)
c.setModelSorting(QCompleter.CaseInsensitivelySortedModel)
c.setCompletionRole(Qt.DisplayRole)
p = c.popup()
p.setMouseTracking(True)
p.entered.connect(self.item_entered)
c.popup().setAlternatingRowColors(True)
c.activated.connect(self.completion_selected,
type=Qt.QueuedConnection)
self.textEdited.connect(self.text_edited)
self.complete_window.completion_selected.connect(self.completion_selected)
self.installEventFilter(self)
# Interface {{{
def update_items_cache(self, complete_items):
@ -192,33 +84,23 @@ class MultiCompleteLineEdit(QLineEdit):
# }}}
def eventFilter(self, o, e):
if self.eat_focus_out and o is self and e.type() == QEvent.FocusOut:
if self.complete_window.isVisible():
return True # Filter this event since the cw is visible
return QLineEdit.eventFilter(self, o, e)
def hide_completion_window(self):
self.complete_window.hide()
def item_entered(self, idx):
self._completer.popup().setCurrentIndex(idx)
def text_edited(self, *args):
self.update_completions()
self._completer.complete()
def update_completions(self):
' Update the list of completions '
if not self.complete_window.isVisible() and not self.hasFocus():
return
cpos = self.cursorPosition()
text = unicode(self.text())
prefix = text[:cpos]
self.current_prefix = prefix
complete_prefix = prefix.lstrip()
if self.sep:
complete_prefix = prefix = prefix.split(self.sep)[-1].lstrip()
matches = self._model.get_matches(complete_prefix)
self.update_complete_window(matches)
complete_prefix = prefix.split(self.sep)[-1].lstrip()
self._completer.setCompletionPrefix(complete_prefix)
def get_completed_text(self, text):
'''
@ -231,15 +113,21 @@ class MultiCompleteLineEdit(QLineEdit):
cursor_pos = self.cursorPosition()
before_text = unicode(self.text())[:cursor_pos]
after_text = unicode(self.text())[cursor_pos:]
after_parts = after_text.split(self.sep)
if len(after_parts) < 3 and not after_parts[-1].strip():
after_text = u''
prefix_len = len(before_text.split(self.sep)[-1].lstrip())
return prefix_len, \
before_text[:cursor_pos - prefix_len] + text + after_text
if tweaks['completer_append_separator']:
prefix_len = len(before_text.split(self.sep)[-1].lstrip())
completed_text = before_text[:cursor_pos - prefix_len] + text + self.sep + ' ' + after_text
prefix_len = prefix_len - len(self.sep) - 1
if prefix_len < 0:
prefix_len = 0
else:
prefix_len = len(before_text.split(self.sep)[-1].lstrip())
completed_text = before_text[:cursor_pos - prefix_len] + text + after_text
return prefix_len, completed_text
def completion_selected(self, text):
prefix_len, ctext = self.get_completed_text(text)
prefix_len, ctext = self.get_completed_text(unicode(text))
if self.sep is None:
self.setText(ctext)
self.setCursorPosition(len(ctext))
@ -248,60 +136,6 @@ class MultiCompleteLineEdit(QLineEdit):
self.setText(ctext)
self.setCursorPosition(cursor_pos - prefix_len + len(text))
def update_complete_window(self, matches):
self._model.update_matches(matches)
if matches:
self.show_complete_window()
else:
self.complete_window.hide()
def position_complete_window(self):
popup = self.complete_window
screen = QApplication.desktop().availableGeometry(self)
h = (popup.sizeHintForRow(0) * min(self.max_visible_items,
popup.model().rowCount()) + 3) + 3
hsb = popup.horizontalScrollBar()
if hsb and hsb.isVisible():
h += hsb.sizeHint().height()
rh = self.height()
pos = self.mapToGlobal(QPoint(0, self.height() - 2))
w = self.width()
if w > screen.width():
w = screen.width()
if (pos.x() + w) > (screen.x() + screen.width()):
pos.setX(screen.x() + screen.width() - w)
if (pos.x() < screen.x()):
pos.setX(screen.x())
top = pos.y() - rh - screen.top() + 2
bottom = screen.bottom() - pos.y()
h = max(h, popup.minimumHeight())
if h > bottom:
h = min(max(top, bottom), h)
if top > bottom:
pos.setY(pos.y() - h - rh + 2)
popup.setGeometry(pos.x(), pos.y(), w, h)
def show_complete_window(self):
self.position_complete_window()
self.complete_window.show()
def moveEvent(self, ev):
ret = QLineEdit.moveEvent(self, ev)
QTimer.singleShot(0, self.position_complete_window)
return ret
def resizeEvent(self, ev):
ret = QLineEdit.resizeEvent(self, ev)
QTimer.singleShot(0, self.position_complete_window)
return ret
@dynamic_property
def all_items(self):
def fget(self):
@ -310,22 +144,6 @@ class MultiCompleteLineEdit(QLineEdit):
self._model.set_items(items)
return property(fget=fget, fset=fset)
@dynamic_property
def sep(self):
def fget(self):
return self._model.sep
def fset(self, val):
self._model.sep = val
return property(fget=fget, fset=fset)
@dynamic_property
def space_before_sep(self):
def fget(self):
return self._model.space_before_sep
def fset(self, val):
self._model.space_before_sep = val
return property(fget=fget, fset=fset)
class MultiCompleteComboBox(EnComboBox):
def __init__(self, *args):

View File

@ -16,7 +16,8 @@ class PluginWidget(Widget, Ui_Form):
def __init__(self, parent, get_option, get_help, db=None, book_id=None):
Widget.__init__(self, parent,
['paragraph_type', 'formatting_type', 'markdown_disable_toc', 'preserve_spaces'])
['paragraph_type', 'formatting_type', 'markdown_disable_toc',
'preserve_spaces', 'txt_in_remove_indents'])
self.db, self.book_id = db, book_id
for x in get_option('paragraph_type').option.choices:
self.opt_paragraph_type.addItem(x)

View File

@ -7,57 +7,95 @@
<x>0</x>
<y>0</y>
<width>518</width>
<height>300</height>
<height>353</height>
</rect>
</property>
<property name="windowTitle">
<string>Form</string>
</property>
<layout class="QGridLayout" name="gridLayout">
<item row="0" column="0">
<widget class="QLabel" name="label_2">
<property name="text">
<string>Paragraph style:</string>
<layout class="QVBoxLayout" name="verticalLayout_3">
<item>
<widget class="QGroupBox" name="groupBox_3">
<property name="title">
<string>Structure</string>
</property>
<layout class="QGridLayout" name="gridLayout">
<item row="0" column="0">
<widget class="QLabel" name="label_2">
<property name="sizePolicy">
<sizepolicy hsizetype="Minimum" vsizetype="Preferred">
<horstretch>0</horstretch>
<verstretch>0</verstretch>
</sizepolicy>
</property>
<property name="text">
<string>Paragraph style:</string>
</property>
</widget>
</item>
<item row="0" column="1">
<widget class="QComboBox" name="opt_paragraph_type">
<property name="sizePolicy">
<sizepolicy hsizetype="Expanding" vsizetype="Fixed">
<horstretch>0</horstretch>
<verstretch>0</verstretch>
</sizepolicy>
</property>
</widget>
</item>
<item row="1" column="0">
<widget class="QLabel" name="label_3">
<property name="sizePolicy">
<sizepolicy hsizetype="Minimum" vsizetype="Preferred">
<horstretch>0</horstretch>
<verstretch>0</verstretch>
</sizepolicy>
</property>
<property name="text">
<string>Formatting style:</string>
</property>
</widget>
</item>
<item row="1" column="1">
<widget class="QComboBox" name="opt_formatting_type">
<property name="sizePolicy">
<sizepolicy hsizetype="Expanding" vsizetype="Fixed">
<horstretch>0</horstretch>
<verstretch>0</verstretch>
</sizepolicy>
</property>
</widget>
</item>
</layout>
</widget>
</item>
<item row="0" column="1">
<widget class="QComboBox" name="opt_paragraph_type"/>
</item>
<item row="5" column="0" colspan="2">
<widget class="QCheckBox" name="opt_preserve_spaces">
<property name="text">
<string>Preserve &amp;spaces</string>
<item>
<widget class="QGroupBox" name="groupBox_2">
<property name="title">
<string>Common</string>
</property>
<layout class="QVBoxLayout" name="verticalLayout_2">
<item>
<widget class="QCheckBox" name="opt_preserve_spaces">
<property name="text">
<string>Preserve &amp;spaces</string>
</property>
</widget>
</item>
<item>
<widget class="QCheckBox" name="opt_txt_in_remove_indents">
<property name="text">
<string>Remove indents at the beginning of lines</string>
</property>
</widget>
</item>
</layout>
</widget>
</item>
<item row="6" column="0" colspan="2">
<spacer name="verticalSpacer">
<property name="orientation">
<enum>Qt::Vertical</enum>
</property>
<property name="sizeHint" stdset="0">
<size>
<width>20</width>
<height>213</height>
</size>
</property>
</spacer>
</item>
<item row="1" column="1">
<widget class="QComboBox" name="opt_formatting_type"/>
</item>
<item row="1" column="0">
<widget class="QLabel" name="label_3">
<property name="text">
<string>Formatting style:</string>
</property>
</widget>
</item>
<item row="2" column="0" rowspan="2" colspan="2">
<item>
<widget class="QGroupBox" name="groupBox">
<property name="title">
<string>Markdown Options</string>
<string>Markdown</string>
</property>
<layout class="QVBoxLayout" name="verticalLayout">
<item>
@ -83,6 +121,19 @@
</layout>
</widget>
</item>
<item>
<spacer name="verticalSpacer">
<property name="orientation">
<enum>Qt::Vertical</enum>
</property>
<property name="sizeHint" stdset="0">
<size>
<width>20</width>
<height>213</height>
</size>
</property>
</spacer>
</item>
</layout>
</widget>
<resources/>

View File

@ -89,7 +89,8 @@ class MessageBox(QDialog, Ui_Dialog):
(__version__, unicode(self.windowTitle()),
unicode(self.msg.text()),
unicode(self.det_msg.toPlainText())))
self.ctc_button.setText(_('Copied'))
if hasattr(self, 'ctc_button'):
self.ctc_button.setText(_('Copied'))
def showEvent(self, ev):
ret = QDialog.showEvent(self, ev)

View File

@ -951,8 +951,8 @@ class MetadataSingleDialog(ResizableDialog, Ui_MetadataSingleDialog):
for w in getattr(self, 'custom_column_widgets', []):
self.books_to_refresh |= w.commit(self.id)
self.db.commit()
except IOError, err:
if err.errno == 13: # Permission denied
except (IOError, OSError) as err:
if getattr(err, 'errno', -1) == 13: # Permission denied
fname = err.filename if err.filename else 'file'
return error_dialog(self, _('Permission denied'),
_('Could not open %s. Is it being used by another'

View File

@ -11,7 +11,7 @@ from threading import Thread
from Queue import Queue, Empty
from functools import partial
from PyQt4.Qt import QObject, Qt, pyqtSignal, QTimer, QDialog, \
from PyQt4.Qt import QObject, QTimer, QDialog, \
QVBoxLayout, QTextBrowser, QLabel, QGroupBox, QDialogButtonBox
from calibre.ebooks.metadata.fetch import search, get_social_metadata
@ -163,27 +163,23 @@ class DownloadMetadata(Thread):
class DoDownload(QObject):
idle_process = pyqtSignal()
def __init__(self, parent, title, db, ids, get_covers, set_metadata=True,
get_social_metadata=True):
QObject.__init__(self, parent)
self.pd = ProgressDialog(title, min=0, max=0, parent=parent)
self.pd.canceled_signal.connect(self.cancel)
self.idle_process.connect(self.do_one, type=Qt.QueuedConnection)
self.downloader = None
self.create = partial(DownloadMetadata, db, ids, get_covers,
set_metadata=set_metadata,
get_social_metadata=get_social_metadata)
self.timer = QTimer(self)
self.get_covers = get_covers
self.timer.timeout.connect(self.do_one, type=Qt.QueuedConnection)
self.db = db
self.updated = set([])
self.total = len(ids)
self.keep_going = True
def exec_(self):
self.timer.start(50)
QTimer.singleShot(50, self.do_one)
ret = self.pd.exec_()
if getattr(self.downloader, 'exception', None) is not None and \
ret == self.pd.Accepted:
@ -194,30 +190,37 @@ class DoDownload(QObject):
return ret
def cancel(self, *args):
self.timer.stop()
self.keep_going = False
self.downloader.keep_going = False
self.pd.reject()
def do_one(self):
if self.downloader is None:
self.downloader = self.create()
self.downloader.start()
self.pd.set_min(0)
self.pd.set_max(self.downloader.total)
try:
r = self.downloader.results.get_nowait()
self.handle_result(r)
except Empty:
pass
if not self.downloader.is_alive():
self.timer.stop()
while True:
try:
r = self.downloader.results.get_nowait()
self.handle_result(r)
except Empty:
break
self.pd.accept()
if not self.keep_going:
return
if self.downloader is None:
self.downloader = self.create()
self.downloader.start()
self.pd.set_min(0)
self.pd.set_max(self.downloader.total)
try:
r = self.downloader.results.get_nowait()
self.handle_result(r)
except Empty:
pass
if not self.downloader.is_alive():
while True:
try:
r = self.downloader.results.get_nowait()
self.handle_result(r)
except Empty:
break
self.pd.accept()
return
except:
self.cancel()
raise
QTimer.singleShot(50, self.do_one)
def handle_result(self, r):
id_, typ, ok, title = r

View File

@ -9,7 +9,7 @@ Logic for setting up conversion jobs
import cPickle, os
from PyQt4.Qt import QDialog, QProgressDialog, QString, QTimer, SIGNAL
from PyQt4.Qt import QDialog, QProgressDialog, QString, QTimer
from calibre.ptempfile import PersistentTemporaryFile
from calibre.gui2 import warning_dialog, question_dialog
@ -24,7 +24,8 @@ from calibre.ebooks.conversion.config import GuiRecommendations, \
load_defaults, load_specifics, save_specifics
from calibre.gui2.convert import bulk_defaults_for_input_format
def convert_single_ebook(parent, db, book_ids, auto_conversion=False, out_format=None):
def convert_single_ebook(parent, db, book_ids, auto_conversion=False, # {{{
out_format=None):
changed = False
jobs = []
bad = []
@ -95,7 +96,9 @@ def convert_single_ebook(parent, db, book_ids, auto_conversion=False, out_format
msg).exec_()
return jobs, changed, bad
# }}}
# Bulk convert {{{
def convert_bulk_ebook(parent, queue, db, book_ids, out_format=None, args=[]):
total = len(book_ids)
if total == 0:
@ -125,14 +128,11 @@ class QueueBulk(QProgressDialog):
self.parent = parent
self.use_saved_single_settings = use_saved_single_settings
self.i, self.bad, self.jobs, self.changed = 0, [], [], False
self.timer = QTimer(self)
self.connect(self.timer, SIGNAL('timeout()'), self.do_book)
self.timer.start()
QTimer.singleShot(0, self.do_book)
self.exec_()
def do_book(self):
if self.i >= len(self.book_ids):
self.timer.stop()
return self.do_queue()
book_id = self.book_ids[self.i]
self.i += 1
@ -191,6 +191,7 @@ class QueueBulk(QProgressDialog):
self.setValue(self.i)
except NoSupportedInputFormats:
self.bad.append(book_id)
QTimer.singleShot(0, self.do_book)
def do_queue(self):
self.hide()
@ -209,7 +210,9 @@ class QueueBulk(QProgressDialog):
self.jobs.reverse()
self.queue(self.jobs, self.changed, self.bad, *self.args)
def fetch_scheduled_recipe(arg):
# }}}
def fetch_scheduled_recipe(arg): # {{{
fmt = prefs['output_format'].lower()
pt = PersistentTemporaryFile(suffix='_recipe_out.%s'%fmt.lower())
pt.close()
@ -250,7 +253,9 @@ def fetch_scheduled_recipe(arg):
return 'gui_convert', args, _('Fetch news from ')+arg['title'], fmt.upper(), [pt]
def generate_catalog(parent, dbspec, ids, device_manager, db):
# }}}
def generate_catalog(parent, dbspec, ids, device_manager, db): # {{{
from calibre.gui2.dialogs.catalog import Catalog
# Build the Catalog dialog in gui2.dialogs.catalog
@ -308,8 +313,9 @@ def generate_catalog(parent, dbspec, ids, device_manager, db):
# Which then calls gui2.convert.gui_conversion:gui_catalog() with the args inline
return 'gui_catalog', args, _('Generate catalog'), out.name, d.catalog_sync, \
d.catalog_title
# }}}
def convert_existing(parent, db, book_ids, output_format):
def convert_existing(parent, db, book_ids, output_format): # {{{
already_converted_ids = []
already_converted_titles = []
for book_id in book_ids:
@ -325,3 +331,5 @@ def convert_existing(parent, db, book_ids, output_format):
book_ids = [x for x in book_ids if x not in already_converted_ids]
return book_ids
# }}}

View File

@ -4442,34 +4442,39 @@ then rebuild the catalog.\n''').format(author[0],author[1],current_author[1])
# Insert the link to the series or remove <a class="series">
aTag = body.find('a', attrs={'class':'series_id'})
if book['series']:
if self.opts.generate_series:
aTag['href'] = "%s.html#%s_series" % ('BySeries',
re.sub('\W','',book['series']).lower())
else:
aTag.extract()
if aTag:
if book['series']:
if self.opts.generate_series:
aTag['href'] = "%s.html#%s_series" % ('BySeries',
re.sub('\W','',book['series']).lower())
else:
aTag.extract()
# Insert the author link (always)
# Insert the author link
aTag = body.find('a', attrs={'class':'author'})
if self.opts.generate_authors:
if self.opts.generate_authors and aTag:
aTag['href'] = "%s.html#%s" % ("ByAlphaAuthor",
self.generateAuthorAnchor(book['author']))
if publisher == ' ':
publisherTag = body.find('td', attrs={'class':'publisher'})
publisherTag.contents[0].replaceWith('&nbsp;')
if publisherTag:
publisherTag.contents[0].replaceWith('&nbsp;')
if not genres:
genresTag = body.find('p',attrs={'class':'genres'})
genresTag.extract()
if genresTag:
genresTag.extract()
if not formats:
formatsTag = body.find('p',attrs={'class':'formats'})
formatsTag.extract()
if formatsTag:
formatsTag.extract()
if note_content == '':
tdTag = body.find('td', attrs={'class':'notes'})
tdTag.contents[0].replaceWith('&nbsp;')
if tdTag:
tdTag.contents[0].replaceWith('&nbsp;')
emptyTags = body.findAll('td', attrs={'class':'empty'})
for mt in emptyTags:

View File

@ -445,7 +445,7 @@ class CustomColumns(object):
rv = self._set_custom(id, val, label=label, num=num, append=append,
notify=notify, extra=extra,
allow_case_change=allow_case_change)
self.dirtied([id], commit=False)
self.dirtied(set([id])|rv, commit=False)
if commit:
self.conn.commit()
return rv

View File

@ -414,7 +414,6 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
row = self.data._data[index] if index_is_id else self.data[index]
return row[self.FIELD_MAP['path']].replace('/', os.sep)
def abspath(self, index, index_is_id=False, create_dirs=True):
'Return the absolute path to the directory containing this books files as a unicode string.'
path = os.path.join(self.library_path, self.path(index, index_is_id=index_is_id))
@ -422,7 +421,6 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
os.makedirs(path)
return path
def construct_path_name(self, id):
'''
Construct the directory name for this book based on its metadata.
@ -432,7 +430,11 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
authors = _('Unknown')
author = ascii_filename(authors.split(',')[0])[:self.PATH_LIMIT].decode(filesystem_encoding, 'replace')
title = ascii_filename(self.title(id, index_is_id=True))[:self.PATH_LIMIT].decode(filesystem_encoding, 'replace')
path = author + '/' + title + ' (%d)'%id
while author[-1] in (' ', '.'):
author = author[:-1]
if not author:
author = ascii_filename(_('Unknown')).decode(filesystem_encoding, 'replace')
path = author + '/' + title + ' (%d)'%id
return path
def construct_file_name(self, id):
@ -1692,7 +1694,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
'''
books_to_refresh = self._set_authors(id, authors,
allow_case_change=allow_case_change)
self.dirtied([id], commit=False)
self.dirtied(set([id])|books_to_refresh, commit=False)
if commit:
self.conn.commit()
self.set_path(id, index_is_id=True)
@ -1768,7 +1770,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
self.conn.execute('''DELETE FROM publishers WHERE (SELECT COUNT(id)
FROM books_publishers_link
WHERE publisher=publishers.id) < 1''')
books_to_refresh = set()
books_to_refresh = set([])
if publisher:
case_change = False
if not isinstance(publisher, unicode):
@ -1793,7 +1795,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
bks = self.conn.get('''SELECT book FROM books_publishers_link
WHERE publisher=?''', (aid,))
books_to_refresh |= set([bk[0] for bk in bks])
self.dirtied([id], commit=False)
self.dirtied(set([id])|books_to_refresh, commit=False)
if commit:
self.conn.commit()
self.data.set(id, self.FIELD_MAP['publisher'], publisher, row_is_id=True)
@ -2206,7 +2208,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
bks = self.conn.get('SELECT book FROM books_tags_link WHERE tag=?',
(tid,))
books_to_refresh |= set([bk[0] for bk in bks])
self.dirtied([id], commit=False)
self.dirtied(set([id])|books_to_refresh, commit=False)
if commit:
self.conn.commit()
tags = u','.join(self.get_tags(id))

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

View File

@ -4,9 +4,9 @@
#
msgid ""
msgstr ""
"Project-Id-Version: calibre 0.7.43\n"
"POT-Creation-Date: 2011-02-03 22:52+MST\n"
"PO-Revision-Date: 2011-02-03 22:52+MST\n"
"Project-Id-Version: calibre 0.7.44\n"
"POT-Creation-Date: 2011-02-04 11:04+MST\n"
"PO-Revision-Date: 2011-02-04 11:04+MST\n"
"Last-Translator: Automatically generated\n"
"Language-Team: LANGUAGE\n"
"MIME-Version: 1.0\n"
@ -10663,11 +10663,11 @@ msgstr ""
msgid "The saved search name %s is already used."
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1313
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1321
msgid "Find item in tag browser"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1316
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1324
msgid ""
"Search for items. This is a \"contains\" search; items containing the\n"
"text anywhere in the name will be found. You can limit the search\n"
@ -10677,59 +10677,59 @@ msgid ""
"containing the text \"foo\""
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1325
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1333
msgid "ALT+f"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1329
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1337
msgid "F&ind"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1330
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1338
msgid "Find the first/next matching item"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1337
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1345
msgid "Collapse all categories"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1358
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1366
msgid "No More Matches.</b><p> Click Find again to go to first match"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1371
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1379
msgid "Sort by name"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1371
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1379
msgid "Sort by popularity"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1372
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1380
msgid "Sort by average rating"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1375
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1383
msgid "Set the sort order for entries in the Tag Browser"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1381
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1389
msgid "Match all"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1381
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1389
msgid "Match any"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1386
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1394
msgid "When selecting multiple entries in the Tag Browser match any or all of them"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1390
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1398
msgid "Manage &user categories"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1393
#: /home/kovid/work/calibre/src/calibre/gui2/tag_view.py:1401
msgid "Add your own categories to the Tag Browser"
msgstr ""
@ -11905,7 +11905,7 @@ msgstr ""
msgid "No books available to include in catalog"
msgstr ""
#: /home/kovid/work/calibre/src/calibre/library/catalog.py:5012
#: /home/kovid/work/calibre/src/calibre/library/catalog.py:5024
msgid ""
"\n"
"*** Adding 'By Authors' Section required for MOBI output ***"

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