Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

KG updates

Browse Source
This commit is contained in:
GRiker 2011-01-12 03:23:19 -07:00
commit 93ff7258e6
24 changed files with 1414 additions and 208 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
resources/recipes/nytimes.recipe
View File

@ -685,3 +685,28 @@ class NYTimes(BasicNewsRecipe):
divTag.replaceWith(tag)
return soup
def populate_article_metadata(self, article, soup, first):
shortparagraph = ""
try:
if len(article.text_summary.strip()) == 0:
articlebodies = soup.findAll('div',attrs={'class':'articleBody'})
if articlebodies:
for articlebody in articlebodies:
if articlebody:
paras = articlebody.findAll('p')
for p in paras:
refparagraph = self.massageNCXText(self.tag_to_string(p,use_alt=False)).strip()
#account for blank paragraphs and short paragraphs by appending them to longer ones
if len(refparagraph) > 0:
if len(refparagraph) > 70: #approximately one line of text
article.summary = article.text_summary = shortparagraph + refparagraph
return
else:
shortparagraph = refparagraph + " "
if shortparagraph.strip().find(" ") == -1 and not shortparagraph.strip().endswith(":"):
shortparagraph = shortparagraph + "- "
except:
self.log("Error creating article descriptions")
return

23
resources/recipes/nytimes_sub.recipe
View File

@ -685,4 +685,27 @@ class NYTimes(BasicNewsRecipe):
divTag.replaceWith(tag)
return soup
def populate_article_metadata(self, article, soup, first):
shortparagraph = ""
try:
if len(article.text_summary.strip()) == 0:
articlebodies = soup.findAll('div',attrs={'class':'articleBody'})
if articlebodies:
for articlebody in articlebodies:
if articlebody:
paras = articlebody.findAll('p')
for p in paras:
refparagraph = self.massageNCXText(self.tag_to_string(p,use_alt=False)).strip()
#account for blank paragraphs and short paragraphs by appending them to longer ones
if len(refparagraph) > 0:
if len(refparagraph) > 70: #approximately one line of text
article.summary = article.text_summary = shortparagraph + refparagraph
return
else:
shortparagraph = refparagraph + " "
if shortparagraph.strip().find(" ") == -1 and not shortparagraph.strip().endswith(":"):
shortparagraph = shortparagraph + "- "
except:
self.log("Error creating article descriptions")
return

2
resources/recipes/tyzden.recipe
View File

@ -28,7 +28,7 @@ class TyzdenRecipe(BasicNewsRecipe):
if (weeknum > 1):
weeknum -= 1
title = u'.tyzden ' + str(weeknum) + '/' + str(year)
title = u'tyzden'
base_url_path = 'http://www.tyzden.sk/casopis/' + str(year) + '/' + str(weeknum)
base_url = base_url_path + '.html'

16
src/calibre/devices/nook/driver.py
View File

@ -91,3 +91,19 @@ class NOOK_COLOR(NOOK):
EBOOK_DIR_MAIN = 'My Files/Books'
'''
def create_upload_path(self, path, mdata, fname, create_dirs=True):
filepath = NOOK.create_upload_path(self, path, mdata, fname,
create_dirs=create_dirs)
edm = self.EBOOK_DIR_MAIN.replace('/', os.sep)
npath = os.path.join(edm, _('News')) + os.sep
if npath in filepath:
filepath = filepath.replace(npath, os.sep.join('My Files',
'Magazines')+os.sep)
filedir = os.path.dirname(filepath)
if create_dirs and not os.path.exists(filedir):
os.makedirs(filedir)
return filepath
'''

2
src/calibre/ebooks/conversion/plumber.py
View File

@ -88,6 +88,7 @@ class Plumber(object):
self.ui_reporter = report_progress
self.abort_after_input_dump = abort_after_input_dump
# Pipeline options {{{
# Initialize the conversion options that are independent of input and
# output formats. The input and output plugins can still disable these
# options via recommendations.
@ -527,6 +528,7 @@ OptionRecommendation(name='timestamp',
help=_('Set the book timestamp (used by the date column in calibre).')),
]
# }}}
input_fmt = os.path.splitext(self.input)[1]
if not input_fmt:

65
src/calibre/ebooks/fb2/fb2ml.py
View File

@ -16,7 +16,6 @@ import uuid
from lxml import etree
from calibre import guess_type
from calibre import prepare_string_for_xml
from calibre.constants import __appname__, __version__
from calibre.ebooks.oeb.base import XHTML, XHTML_NS, barename, namespace
@ -102,6 +101,7 @@ class FB2MLizer(object):
metadata['date'] = '%i.%i.%i' % (datetime.now().day, datetime.now().month, datetime.now().year)
metadata['lang'] = u''.join(self.oeb_book.metadata.lang) if self.oeb_book.metadata.lang else 'en'
metadata['id'] = None
metadata['cover'] = self.get_cover()
author_parts = self.oeb_book.metadata.creator[0].value.split(' ')
if len(author_parts) == 1:
@ -124,6 +124,7 @@ class FB2MLizer(object):
metadata['id'] = str(uuid.uuid4())
for key, value in metadata.items():
if not key == 'cover':
metadata[key] = prepare_string_for_xml(value)
return u'<FictionBook xmlns="http://www.gribuser.ru/xml/fictionbook/2.0" xmlns:xlink="http://www.w3.org/1999/xlink">' \
@ -136,6 +137,7 @@ class FB2MLizer(object):
'<last-name>%(author_last)s</last-name>' \
'</author>' \
'<book-title>%(title)s</book-title>' \
'%(cover)s' \
'<lang>%(lang)s</lang>' \
'</title-info>' \
'<document-info>' \
@ -154,6 +156,39 @@ class FB2MLizer(object):
def fb2_footer(self):
return u'</FictionBook>'
def get_cover(self):
cover_href = None
# Get the raster cover if it's available.
if self.oeb_book.metadata.cover and unicode(self.oeb_book.metadata.cover[0]) in self.oeb_book.manifest.ids:
id = unicode(self.oeb_book.metadata.cover[0])
cover_item = self.oeb_book.manifest.ids[id]
if cover_item.media_type in OEB_RASTER_IMAGES:
cover_href = cover_item.href
else:
# Figure out if we have a title page or a cover page
page_name = ''
if 'titlepage' in self.oeb_book.guide:
page_name = 'titlepage'
elif 'cover' in self.oeb_book.guide:
page_name = 'cover'
if page_name:
cover_item = self.oeb_book.manifest.hrefs[self.oeb_book.guide[page_name].href]
# Get the first image in the page
for img in cover_item.xpath('//img'):
cover_href = cover_item.abshref(img.get('src'))
break
if cover_href:
# Only write the image tag if it is in the manifest.
if cover_href in self.oeb_book.manifest.hrefs.keys():
if cover_href not in self.image_hrefs.keys():
self.image_hrefs[cover_href] = '_%s.jpg' % len(self.image_hrefs.keys())
return u'<coverpage><image xlink:href="#%s" /></coverpage>' % self.image_hrefs[cover_href]
return u''
def get_text(self):
text = ['<body>']
@ -162,23 +197,6 @@ class FB2MLizer(object):
text.append('<section>')
self.section_level += 1
# Insert the title page / cover into the spine if it is not already referenced.
title_name = u''
if 'titlepage' in self.oeb_book.guide:
title_name = 'titlepage'
elif 'cover' in self.oeb_book.guide:
title_name = 'cover'
if title_name:
title_item = self.oeb_book.manifest.hrefs[self.oeb_book.guide[title_name].href]
if title_item.spine_position is None and title_item.media_type == 'application/xhtml+xml':
self.oeb_book.spine.insert(0, title_item, True)
# Create xhtml page to reference cover image so it can be used.
if not title_name and self.oeb_book.metadata.cover and unicode(self.oeb_book.metadata.cover[0]) in self.oeb_book.manifest.ids:
id = unicode(self.oeb_book.metadata.cover[0])
cover_item = self.oeb_book.manifest.ids[id]
if cover_item.media_type in OEB_RASTER_IMAGES:
self.insert_image_cover(cover_item.href)
for item in self.oeb_book.spine:
self.log.debug('Converting %s to FictionBook2 XML' % item.href)
stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts, self.opts.output_profile)
@ -203,17 +221,6 @@ class FB2MLizer(object):
return ''.join(text) + '</body>'
def insert_image_cover(self, image_href):
from calibre.ebooks.oeb.base import RECOVER_PARSER
try:
root = etree.fromstring(u'<html xmlns="%s"><body><img src="%s" /></body></html>' % (XHTML_NS, image_href), parser=RECOVER_PARSER)
except:
root = etree.fromstring(u'', parser=RECOVER_PARSER)
id, href = self.oeb_book.manifest.generate('fb2_cover', 'fb2_cover.xhtml')
item = self.oeb_book.manifest.add(id, href, guess_type(href)[0], data=root)
self.oeb_book.spine.insert(0, item, True)
def fb2mlize_images(self):
'''
This function uses the self.image_hrefs dictionary mapping. It is populated by the dump_text function.

28
src/calibre/ebooks/rtf/input.py
View File

@ -159,11 +159,31 @@ class RTFInput(InputFormatPlugin):
return imap
def convert_image(self, name):
from calibre.utils.magick import Image
img = Image()
img.open(name)
try:
return self.rasterize_wmf(name)
except:
self.log.exception('Failed to convert WMF image %r'%name)
return self.replace_wmf(name)
def replace_wmf(self, name):
from calibre.ebooks import calibre_cover
data = calibre_cover('Conversion of WMF images is not supported',
'Use Microsoft Word or OpenOffice to save this RTF file'
' as HTML and convert that in calibre.', title_size=36,
author_size=20)
name = name.replace('.wmf', '.jpg')
img.save(name)
with open(name, 'wb') as f:
f.write(data)
return name
def rasterize_wmf(self, name):
from calibre.utils.wmf import extract_raster_image
with open(name, 'rb') as f:
data = f.read()
data = extract_raster_image(data)
name = name.replace('.wmf', '.jpg')
with open(name, 'wb') as f:
f.write(data)
return name

6
src/calibre/ebooks/textile/__init__.py Normal file
View File

@ -0,0 +1,6 @@
from functions import textile, textile_restricted, Textile
if False:
textile, textile_restricted, Textile
__all__ = ['textile', 'textile_restricted']

981
src/calibre/ebooks/textile/functions.py Normal file
View File

@ -0,0 +1,981 @@
#!/usr/bin/env python
"""
PyTextile
A Humane Web Text Generator
"""
__version__ = '2.1.4'
__date__ = '2009/12/04'
__copyright__ = """
Copyright (c) 2009, Jason Samsa, http://jsamsa.com/
Copyright (c) 2004, Roberto A. F. De Almeida, http://dealmeida.net/
Copyright (c) 2003, Mark Pilgrim, http://diveintomark.org/
Original PHP Version:
Copyright (c) 2003-2004, Dean Allen <dean@textism.com>
All rights reserved.
Thanks to Carlo Zottmann <carlo@g-blog.net> for refactoring
Textile's procedural code into a class framework
Additions and fixes Copyright (c) 2006 Alex Shiels http://thresholdstate.com/
"""
__license__ = """
L I C E N S E
=============
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
* Neither the name Textile nor the names of its contributors may be used to
endorse or promote products derived from this software without specific
prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
"""
import re
import uuid
from urlparse import urlparse
def _normalize_newlines(string):
out = re.sub(r'\r\n', '\n', string)
out = re.sub(r'\n{3,}', '\n\n', out)
out = re.sub(r'\n\s*\n', '\n\n', out)
out = re.sub(r'"$', '" ', out)
return out
def getimagesize(url):
"""
Attempts to determine an image's width and height, and returns a string
suitable for use in an <img> tag, or None in case of failure.
Requires that PIL is installed.
>>> getimagesize("http://www.google.com/intl/en_ALL/images/logo.gif")
... #doctest: +ELLIPSIS, +SKIP
'width="..." height="..."'
"""
try:
import ImageFile
import urllib2
except ImportError:
return None
try:
p = ImageFile.Parser()
f = urllib2.urlopen(url)
while True:
s = f.read(1024)
if not s:
break
p.feed(s)
if p.image:
return 'width="%i" height="%i"' % p.image.size
except (IOError, ValueError):
return None
class Textile(object):
hlgn = r'(?:\<(?!>)|(?<!<)\>|\<\>|\=|[()]+(?! ))'
vlgn = r'[\-^~]'
clas = r'(?:\([^)]+\))'
lnge = r'(?:\[[^\]]+\])'
styl = r'(?:\{[^}]+\})'
cspn = r'(?:\\\d+)'
rspn = r'(?:\/\d+)'
a = r'(?:%s|%s)*' % (hlgn, vlgn)
s = r'(?:%s|%s)*' % (cspn, rspn)
c = r'(?:%s)*' % '|'.join([clas, styl, lnge, hlgn])
pnct = r'[-!"#$%&()*+,/:;<=>?@\'\[\\\]\.^_`{|}~]'
# urlch = r'[\w"$\-_.+!*\'(),";/?:@=&%#{}|\\^~\[\]`]'
urlch = '[\w"$\-_.+*\'(),";\/?:@=&%#{}|\\^~\[\]`]'
url_schemes = ('http', 'https', 'ftp', 'mailto')
btag = ('bq', 'bc', 'notextile', 'pre', 'h[1-6]', 'fn\d+', 'p')
btag_lite = ('bq', 'bc', 'p')
glyph_defaults = (
('txt_quote_single_open', '&#8216;'),
('txt_quote_single_close', '&#8217;'),
('txt_quote_double_open', '&#8220;'),
('txt_quote_double_close', '&#8221;'),
('txt_apostrophe', '&#8217;'),
('txt_prime', '&#8242;'),
('txt_prime_double', '&#8243;'),
('txt_ellipsis', '&#8230;'),
('txt_emdash', '&#8212;'),
('txt_endash', '&#8211;'),
('txt_dimension', '&#215;'),
('txt_trademark', '&#8482;'),
('txt_registered', '&#174;'),
('txt_copyright', '&#169;'),
)
def __init__(self, restricted=False, lite=False, noimage=False):
"""docstring for __init__"""
self.restricted = restricted
self.lite = lite
self.noimage = noimage
self.get_sizes = False
self.fn = {}
self.urlrefs = {}
self.shelf = {}
self.rel = ''
self.html_type = 'xhtml'
def textile(self, text, rel=None, head_offset=0, html_type='xhtml'):
"""
>>> import textile
>>> textile.textile('some textile')
u'\\t<p>some textile</p>'
"""
self.html_type = html_type
# text = unicode(text)
text = _normalize_newlines(text)
if self.restricted:
text = self.encode_html(text, quotes=False)
if rel:
self.rel = ' rel="%s"' % rel
text = self.getRefs(text)
text = self.block(text, int(head_offset))
text = self.retrieve(text)
return text
def pba(self, input, element=None):
"""
Parse block attributes.
>>> t = Textile()
>>> t.pba(r'\3')
''
>>> t.pba(r'\\3', element='td')
' colspan="3"'
>>> t.pba(r'/4', element='td')
' rowspan="4"'
>>> t.pba(r'\\3/4', element='td')
' colspan="3" rowspan="4"'
>>> t.vAlign('^')
'top'
>>> t.pba('^', element='td')
' style="vertical-align:top;"'
>>> t.pba('{line-height:18px}')
' style="line-height:18px;"'
>>> t.pba('(foo-bar)')
' class="foo-bar"'
>>> t.pba('(#myid)')
' id="myid"'
>>> t.pba('(foo-bar#myid)')
' class="foo-bar" id="myid"'
>>> t.pba('((((')
' style="padding-left:4em;"'
>>> t.pba(')))')
' style="padding-right:3em;"'
>>> t.pba('[fr]')
' lang="fr"'
"""
style = []
aclass = ''
lang = ''
colspan = ''
rowspan = ''
id = ''
if not input:
return ''
matched = input
if element == 'td':
m = re.search(r'\\(\d+)', matched)
if m:
colspan = m.group(1)
m = re.search(r'/(\d+)', matched)
if m:
rowspan = m.group(1)
if element == 'td' or element == 'tr':
m = re.search(r'(%s)' % self.vlgn, matched)
if m:
style.append("vertical-align:%s;" % self.vAlign(m.group(1)))
m = re.search(r'\{([^}]*)\}', matched)
if m:
style.append(m.group(1).rstrip(';') + ';')
matched = matched.replace(m.group(0), '')
m = re.search(r'\[([^\]]+)\]', matched, re.U)
if m:
lang = m.group(1)
matched = matched.replace(m.group(0), '')
m = re.search(r'\(([^()]+)\)', matched, re.U)
if m:
aclass = m.group(1)
matched = matched.replace(m.group(0), '')
m = re.search(r'([(]+)', matched)
if m:
style.append("padding-left:%sem;" % len(m.group(1)))
matched = matched.replace(m.group(0), '')
m = re.search(r'([)]+)', matched)
if m:
style.append("padding-right:%sem;" % len(m.group(1)))
matched = matched.replace(m.group(0), '')
m = re.search(r'(%s)' % self.hlgn, matched)
if m:
style.append("text-align:%s;" % self.hAlign(m.group(1)))
m = re.search(r'^(.*)#(.*)$', aclass)
if m:
id = m.group(2)
aclass = m.group(1)
if self.restricted:
if lang:
return ' lang="%s"'
else:
return ''
result = []
if style:
result.append(' style="%s"' % "".join(style))
if aclass:
result.append(' class="%s"' % aclass)
if lang:
result.append(' lang="%s"' % lang)
if id:
result.append(' id="%s"' % id)
if colspan:
result.append(' colspan="%s"' % colspan)
if rowspan:
result.append(' rowspan="%s"' % rowspan)
return ''.join(result)
def hasRawText(self, text):
"""
checks whether the text has text not already enclosed by a block tag
>>> t = Textile()
>>> t.hasRawText('<p>foo bar biz baz</p>')
False
>>> t.hasRawText(' why yes, yes it does')
True
"""
r = re.compile(r'<(p|blockquote|div|form|table|ul|ol|pre|h\d)[^>]*?>.*</\1>', re.S).sub('', text.strip()).strip()
r = re.compile(r'<(hr|br)[^>]*?/>').sub('', r)
return '' != r
def table(self, text):
r"""
>>> t = Textile()
>>> t.table('|one|two|three|\n|a|b|c|')
'\t<table>\n\t\t<tr>\n\t\t\t<td>one</td>\n\t\t\t<td>two</td>\n\t\t\t<td>three</td>\n\t\t</tr>\n\t\t<tr>\n\t\t\t<td>a</td>\n\t\t\t<td>b</td>\n\t\t\t<td>c</td>\n\t\t</tr>\n\t</table>\n\n'
"""
text = text + "\n\n"
pattern = re.compile(r'^(?:table(_?%(s)s%(a)s%(c)s)\. ?\n)?^(%(a)s%(c)s\.? ?\|.*\|)\n\n' % {'s':self.s, 'a':self.a, 'c':self.c}, re.S|re.M|re.U)
return pattern.sub(self.fTable, text)
def fTable(self, match):
tatts = self.pba(match.group(1), 'table')
rows = []
for row in [ x for x in match.group(2).split('\n') if x]:
rmtch = re.search(r'^(%s%s\. )(.*)' % (self.a, self.c), row.lstrip())
if rmtch:
ratts = self.pba(rmtch.group(1), 'tr')
row = rmtch.group(2)
else:
ratts = ''
cells = []
for cell in row.split('|')[1:-1]:
ctyp = 'd'
if re.search(r'^_', cell):
ctyp = "h"
cmtch = re.search(r'^(_?%s%s%s\. )(.*)' % (self.s, self.a, self.c), cell)
if cmtch:
catts = self.pba(cmtch.group(1), 'td')
cell = cmtch.group(2)
else:
catts = ''
cell = self.graf(self.span(cell))
cells.append('\t\t\t<t%s%s>%s</t%s>' % (ctyp, catts, cell, ctyp))
rows.append("\t\t<tr%s>\n%s\n\t\t</tr>" % (ratts, '\n'.join(cells)))
cells = []
catts = None
return "\t<table%s>\n%s\n\t</table>\n\n" % (tatts, '\n'.join(rows))
def lists(self, text):
"""
>>> t = Textile()
>>> t.lists("* one\\n* two\\n* three")
'\\t<ul>\\n\\t\\t<li>one</li>\\n\\t\\t<li>two</li>\\n\\t\\t<li>three</li>\\n\\t</ul>'
"""
pattern = re.compile(r'^([#*]+%s .*)$(?![^#*])' % self.c, re.U|re.M|re.S)
return pattern.sub(self.fList, text)
def fList(self, match):
text = match.group(0).split("\n")
result = []
lists = []
for i, line in enumerate(text):
try:
nextline = text[i+1]
except IndexError:
nextline = ''
m = re.search(r"^([#*]+)(%s%s) (.*)$" % (self.a, self.c), line, re.S)
if m:
tl, atts, content = m.groups()
nl = ''
nm = re.search(r'^([#*]+)\s.*', nextline)
if nm:
nl = nm.group(1)
if tl not in lists:
lists.append(tl)
atts = self.pba(atts)
line = "\t<%sl%s>\n\t\t<li>%s" % (self.lT(tl), atts, self.graf(content))
else:
line = "\t\t<li>" + self.graf(content)
if len(nl) <= len(tl):
line = line + "</li>"
for k in reversed(lists):
if len(k) > len(nl):
line = line + "\n\t</%sl>" % self.lT(k)
if len(k) > 1:
line = line + "</li>"
lists.remove(k)
result.append(line)
return "\n".join(result)
def lT(self, input):
if re.search(r'^#+', input):
return 'o'
else:
return 'u'
def doPBr(self, in_):
return re.compile(r'<(p)([^>]*?)>(.*)(</\1>)', re.S).sub(self.doBr, in_)
def doBr(self, match):
if self.html_type == 'html':
content = re.sub(r'(.+)(?:(?<!<br>)|(?<!<br />))\n(?![#*\s|])', '\\1<br>', match.group(3))
else:
content = re.sub(r'(.+)(?:(?<!<br>)|(?<!<br />))\n(?![#*\s|])', '\\1<br />', match.group(3))
return '<%s%s>%s%s' % (match.group(1), match.group(2), content, match.group(4))
def block(self, text, head_offset = 0):
"""
>>> t = Textile()
>>> t.block('h1. foobar baby')
'\\t<h1>foobar baby</h1>'
"""
if not self.lite:
tre = '|'.join(self.btag)
else:
tre = '|'.join(self.btag_lite)
text = text.split('\n\n')
tag = 'p'
atts = cite = graf = ext = c1 = ''
out = []
anon = False
for line in text:
pattern = r'^(%s)(%s%s)\.(\.?)(?::(\S+))? (.*)$' % (tre, self.a, self.c)
match = re.search(pattern, line, re.S)
if match:
if ext:
out.append(out.pop() + c1)
tag, atts, ext, cite, graf = match.groups()
h_match = re.search(r'h([1-6])', tag)
if h_match:
head_level, = h_match.groups()
tag = 'h%i' % max(1,
min(int(head_level) + head_offset,
6))
o1, o2, content, c2, c1 = self.fBlock(tag, atts, ext,
cite, graf)
# leave off c1 if this block is extended,
# we'll close it at the start of the next block
if ext:
line = "%s%s%s%s" % (o1, o2, content, c2)
else:
line = "%s%s%s%s%s" % (o1, o2, content, c2, c1)
else:
anon = True
if ext or not re.search(r'^\s', line):
o1, o2, content, c2, c1 = self.fBlock(tag, atts, ext,
cite, line)
# skip $o1/$c1 because this is part of a continuing
# extended block
if tag == 'p' and not self.hasRawText(content):
line = content
else:
line = "%s%s%s" % (o2, content, c2)
else:
line = self.graf(line)
line = self.doPBr(line)
if self.html_type == 'xhtml':
line = re.sub(r'<br>', '<br />', line)
if ext and anon:
out.append(out.pop() + "\n" + line)
else:
out.append(line)
if not ext:
tag = 'p'
atts = ''
cite = ''
graf = ''
if ext:
out.append(out.pop() + c1)
return '\n\n'.join(out)
def fBlock(self, tag, atts, ext, cite, content):
"""
>>> t = Textile()
>>> t.fBlock("bq", "", None, "", "Hello BlockQuote")
('\\t<blockquote>\\n', '\\t\\t<p>', 'Hello BlockQuote', '</p>', '\\n\\t</blockquote>')
>>> t.fBlock("bq", "", None, "http://google.com", "Hello BlockQuote")
('\\t<blockquote cite="http://google.com">\\n', '\\t\\t<p>', 'Hello BlockQuote', '</p>', '\\n\\t</blockquote>')
>>> t.fBlock("bc", "", None, "", 'printf "Hello, World";') # doctest: +ELLIPSIS
('<pre>', '<code>', ..., '</code>', '</pre>')
>>> t.fBlock("h1", "", None, "", "foobar")
('', '\\t<h1>', 'foobar', '</h1>', '')
"""
atts = self.pba(atts)
o1 = o2 = c2 = c1 = ''
m = re.search(r'fn(\d+)', tag)
if m:
tag = 'p'
if m.group(1) in self.fn:
fnid = self.fn[m.group(1)]
else:
fnid = m.group(1)
atts = atts + ' id="fn%s"' % fnid
if atts.find('class=') < 0:
atts = atts + ' class="footnote"'
content = ('<sup>%s</sup>' % m.group(1)) + content
if tag == 'bq':
cite = self.checkRefs(cite)
if cite:
cite = ' cite="%s"' % cite
else:
cite = ''
o1 = "\t<blockquote%s%s>\n" % (cite, atts)
o2 = "\t\t<p%s>" % atts
c2 = "</p>"
c1 = "\n\t</blockquote>"
elif tag == 'bc':
o1 = "<pre%s>" % atts
o2 = "<code%s>" % atts
c2 = "</code>"
c1 = "</pre>"
content = self.shelve(self.encode_html(content.rstrip("\n") + "\n"))
elif tag == 'notextile':
content = self.shelve(content)
o1 = o2 = ''
c1 = c2 = ''
elif tag == 'pre':
content = self.shelve(self.encode_html(content.rstrip("\n") + "\n"))
o1 = "<pre%s>" % atts
o2 = c2 = ''
c1 = '</pre>'
else:
o2 = "\t<%s%s>" % (tag, atts)
c2 = "</%s>" % tag
content = self.graf(content)
return o1, o2, content, c2, c1
def footnoteRef(self, text):
"""
>>> t = Textile()
>>> t.footnoteRef('foo[1] ') # doctest: +ELLIPSIS
'foo<sup class="footnote"><a href="#fn...">1</a></sup> '
"""
return re.sub(r'\b\[([0-9]+)\](\s)?', self.footnoteID, text)
def footnoteID(self, match):
id, t = match.groups()
if id not in self.fn:
self.fn[id] = str(uuid.uuid4())
fnid = self.fn[id]
if not t:
t = ''
return '<sup class="footnote"><a href="#fn%s">%s</a></sup>%s' % (fnid, id, t)
def glyphs(self, text):
"""
>>> t = Textile()
>>> t.glyphs("apostrophe's")
'apostrophe&#8217;s'
>>> t.glyphs("back in '88")
'back in &#8217;88'
>>> t.glyphs('foo ...')
'foo &#8230;'
>>> t.glyphs('--')
'&#8212;'
>>> t.glyphs('FooBar[tm]')
'FooBar&#8482;'
>>> t.glyphs("<p><cite>Cat's Cradle</cite> by Vonnegut</p>")
'<p><cite>Cat&#8217;s Cradle</cite> by Vonnegut</p>'
"""
# fix: hackish
text = re.sub(r'"\Z', '\" ', text)
glyph_search = (
re.compile(r"(\w)\'(\w)"), # apostrophe's
re.compile(r'(\s)\'(\d+\w?)\b(?!\')'), # back in '88
re.compile(r'(\S)\'(?=\s|'+self.pnct+'|<|$)'), # single closing
re.compile(r'\'/'), # single opening
re.compile(r'(\S)\"(?=\s|'+self.pnct+'|<|$)'), # double closing
re.compile(r'"'), # double opening
re.compile(r'\b([A-Z][A-Z0-9]{2,})\b(?:[(]([^)]*)[)])'), # 3+ uppercase acronym
re.compile(r'\b([A-Z][A-Z\'\-]+[A-Z])(?=[\s.,\)>])'), # 3+ uppercase
re.compile(r'\b(\s{0,1})?\.{3}'), # ellipsis
re.compile(r'(\s?)--(\s?)'), # em dash
re.compile(r'\s-(?:\s|$)'), # en dash
re.compile(r'(\d+)( ?)x( ?)(?=\d+)'), # dimension sign
re.compile(r'\b ?[([]TM[])]', re.I), # trademark
re.compile(r'\b ?[([]R[])]', re.I), # registered
re.compile(r'\b ?[([]C[])]', re.I), # copyright
)
glyph_replace = [x % dict(self.glyph_defaults) for x in (
r'\1%(txt_apostrophe)s\2', # apostrophe's
r'\1%(txt_apostrophe)s\2', # back in '88
r'\1%(txt_quote_single_close)s', # single closing
r'%(txt_quote_single_open)s', # single opening
r'\1%(txt_quote_double_close)s', # double closing
r'%(txt_quote_double_open)s', # double opening
r'<acronym title="\2">\1</acronym>', # 3+ uppercase acronym
r'<span class="caps">\1</span>', # 3+ uppercase
r'\1%(txt_ellipsis)s', # ellipsis
r'\1%(txt_emdash)s\2', # em dash
r' %(txt_endash)s ', # en dash
r'\1\2%(txt_dimension)s\3', # dimension sign
r'%(txt_trademark)s', # trademark
r'%(txt_registered)s', # registered
r'%(txt_copyright)s', # copyright
)]
result = []
for line in re.compile(r'(<.*?>)', re.U).split(text):
if not re.search(r'<.*>', line):
for s, r in zip(glyph_search, glyph_replace):
line = s.sub(r, line)
result.append(line)
return ''.join(result)
def vAlign(self, input):
d = {'^':'top', '-':'middle', '~':'bottom'}
return d.get(input, '')
def hAlign(self, input):
d = {'<':'left', '=':'center', '>':'right', '<>': 'justify'}
return d.get(input, '')
def getRefs(self, text):
"""
what is this for?
"""
pattern = re.compile(r'(?:(?<=^)|(?<=\s))\[(.+)\]((?:http(?:s?):\/\/|\/)\S+)(?=\s|$)', re.U)
text = pattern.sub(self.refs, text)
return text
def refs(self, match):
flag, url = match.groups()
self.urlrefs[flag] = url
return ''
def checkRefs(self, url):
return self.urlrefs.get(url, url)
def isRelURL(self, url):
"""
Identify relative urls.
>>> t = Textile()
>>> t.isRelURL("http://www.google.com/")
False
>>> t.isRelURL("/foo")
True
"""
(scheme, netloc) = urlparse(url)[0:2]
return not scheme and not netloc
def relURL(self, url):
scheme = urlparse(url)[0]
if self.restricted and scheme and scheme not in self.url_schemes:
return '#'
return url
def shelve(self, text):
id = str(uuid.uuid4())
self.shelf[id] = text
return id
def retrieve(self, text):
"""
>>> t = Textile()
>>> id = t.shelve("foobar")
>>> t.retrieve(id)
'foobar'
"""
while True:
old = text
for k, v in self.shelf.items():
text = text.replace(k, v)
if text == old:
break
return text
def encode_html(self, text, quotes=True):
a = (
('&', '&#38;'),
('<', '&#60;'),
('>', '&#62;')
)
if quotes:
a = a + (
("'", '&#39;'),
('"', '&#34;')
)
for k, v in a:
text = text.replace(k, v)
return text
def graf(self, text):
if not self.lite:
text = self.noTextile(text)
text = self.code(text)
text = self.links(text)
if not self.noimage:
text = self.image(text)
if not self.lite:
text = self.lists(text)
text = self.table(text)
text = self.span(text)
text = self.footnoteRef(text)
text = self.glyphs(text)
return text.rstrip('\n')
def links(self, text):
"""
>>> t = Textile()
>>> t.links('fooobar "Google":http://google.com/foobar/ and hello world "flickr":http://flickr.com/photos/jsamsa/ ') # doctest: +ELLIPSIS
'fooobar ... and hello world ...'
"""
punct = '!"#$%&\'*+,-./:;=?@\\^_`|~'
pattern = r'''
(?P<pre> [\s\[{(]|[%s] )?
" # start
(?P<atts> %s )
(?P<text> [^"]+? )
\s?
(?: \(([^)]+?)\)(?=") )? # $title
":
(?P<url> (?:ftp|https?)? (?: :// )? [-A-Za-z0-9+&@#/?=~_()|!:,.;]*[-A-Za-z0-9+&@#/=~_()|] )
(?P<post> [^\w\/;]*? )
(?=<|\s|$)
''' % (re.escape(punct), self.c)
text = re.compile(pattern, re.X).sub(self.fLink, text)
return text
def fLink(self, match):
pre, atts, text, title, url, post = match.groups()
if pre == None:
pre = ''
# assume ) at the end of the url is not actually part of the url
# unless the url also contains a (
if url.endswith(')') and not url.find('(') > -1:
post = url[-1] + post
url = url[:-1]
url = self.checkRefs(url)
atts = self.pba(atts)
if title:
atts = atts + ' title="%s"' % self.encode_html(title)
if not self.noimage:
text = self.image(text)
text = self.span(text)
text = self.glyphs(text)
url = self.relURL(url)
out = '<a href="%s"%s%s>%s</a>' % (self.encode_html(url), atts, self.rel, text)
out = self.shelve(out)
return ''.join([pre, out, post])
def span(self, text):
"""
>>> t = Textile()
>>> t.span(r"hello %(bob)span *strong* and **bold**% goodbye")
'hello <span class="bob">span <strong>strong</strong> and <b>bold</b></span> goodbye'
"""
qtags = (r'\*\*', r'\*', r'\?\?', r'\-', r'__', r'_', r'%', r'\+', r'~', r'\^')
pnct = ".,\"'?!;:"
for qtag in qtags:
pattern = re.compile(r"""
(?:^|(?<=[\s>%(pnct)s])|([\]}]))
(%(qtag)s)(?!%(qtag)s)
(%(c)s)
(?::(\S+))?
([^\s%(qtag)s]+|\S[^%(qtag)s\n]*[^\s%(qtag)s\n])
([%(pnct)s]*)
%(qtag)s
(?:$|([\]}])|(?=%(selfpnct)s{1,2}|\s))
""" % {'qtag':qtag, 'c':self.c, 'pnct':pnct,
'selfpnct':self.pnct}, re.X)
text = pattern.sub(self.fSpan, text)
return text
def fSpan(self, match):
_, tag, atts, cite, content, end, _ = match.groups()
qtags = {
'*': 'strong',
'**': 'b',
'??': 'cite',
'_' : 'em',
'__': 'i',
'-' : 'del',
'%' : 'span',
'+' : 'ins',
'~' : 'sub',
'^' : 'sup'
}
tag = qtags[tag]
atts = self.pba(atts)
if cite:
atts = atts + 'cite="%s"' % cite
content = self.span(content)
out = "<%s%s>%s%s</%s>" % (tag, atts, content, end, tag)
return out
def image(self, text):
"""
>>> t = Textile()
>>> t.image('!/imgs/myphoto.jpg!:http://jsamsa.com')
'<a href="http://jsamsa.com"><img src="/imgs/myphoto.jpg" alt="" /></a>'
"""
pattern = re.compile(r"""
(?:[\[{])? # pre
\! # opening !
(%s) # optional style,class atts
(?:\. )? # optional dot-space
([^\s(!]+) # presume this is the src
\s? # optional space
(?:\(([^\)]+)\))? # optional title
\! # closing
(?::(\S+))? # optional href
(?:[\]}]|(?=\s|$)) # lookahead: space or end of string
""" % self.c, re.U|re.X)
return pattern.sub(self.fImage, text)
def fImage(self, match):
# (None, '', '/imgs/myphoto.jpg', None, None)
atts, url, title, href = match.groups()
atts = self.pba(atts)
if title:
atts = atts + ' title="%s" alt="%s"' % (title, title)
else:
atts = atts + ' alt=""'
if not self.isRelURL(url) and self.get_sizes:
size = getimagesize(url)
if (size):
atts += " %s" % size
if href:
href = self.checkRefs(href)
url = self.checkRefs(url)
url = self.relURL(url)
out = []
if href:
out.append('<a href="%s" class="img">' % href)
if self.html_type == 'html':
out.append('<img src="%s"%s>' % (url, atts))
else:
out.append('<img src="%s"%s />' % (url, atts))
if href:
out.append('</a>')
return ''.join(out)
def code(self, text):
text = self.doSpecial(text, '<code>', '</code>', self.fCode)
text = self.doSpecial(text, '@', '@', self.fCode)
text = self.doSpecial(text, '<pre>', '</pre>', self.fPre)
return text
def fCode(self, match):
before, text, after = match.groups()
if after == None:
after = ''
# text needs to be escaped
if not self.restricted:
text = self.encode_html(text)
return ''.join([before, self.shelve('<code>%s</code>' % text), after])
def fPre(self, match):
before, text, after = match.groups()
if after == None:
after = ''
# text needs to be escapedd
if not self.restricted:
text = self.encode_html(text)
return ''.join([before, '<pre>', self.shelve(text), '</pre>', after])
def doSpecial(self, text, start, end, method=None):
if method == None:
method = self.fSpecial
pattern = re.compile(r'(^|\s|[\[({>])%s(.*?)%s(\s|$|[\])}])?' % (re.escape(start), re.escape(end)), re.M|re.S)
return pattern.sub(method, text)
def fSpecial(self, match):
"""
special blocks like notextile or code
"""
before, text, after = match.groups()
if after == None:
after = ''
return ''.join([before, self.shelve(self.encode_html(text)), after])
def noTextile(self, text):
text = self.doSpecial(text, '<notextile>', '</notextile>', self.fTextile)
return self.doSpecial(text, '==', '==', self.fTextile)
def fTextile(self, match):
before, notextile, after = match.groups()
if after == None:
after = ''
return ''.join([before, self.shelve(notextile), after])
def textile(text, head_offset=0, html_type='xhtml', encoding=None, output=None):
"""
this function takes additional parameters:
head_offset - offset to apply to heading levels (default: 0)
html_type - 'xhtml' or 'html' style tags (default: 'xhtml')
"""
return Textile().textile(text, head_offset=head_offset,
html_type=html_type)
def textile_restricted(text, lite=True, noimage=True, html_type='xhtml'):
"""
Restricted version of Textile designed for weblog comments and other
untrusted input.
Raw HTML is escaped.
Style attributes are disabled.
rel='nofollow' is added to external links.
When lite=True is set (the default):
Block tags are restricted to p, bq, and bc.
Lists and tables are disabled.
When noimage=True is set (the default):
Image tags are disabled.
"""
return Textile(restricted=True, lite=lite,
noimage=noimage).textile(text, rel='nofollow',
html_type=html_type)

6
src/calibre/ebooks/txt/input.py
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, \
convert_heuristic, normalize_line_endings
convert_heuristic, normalize_line_endings, convert_textile
from calibre import _ent_pat, xml_entity_to_unicode
class TXTInput(InputFormatPlugin):
@ -41,6 +41,7 @@ class TXTInput(InputFormatPlugin):
'paragraph and no styling is applied.\n'
'* heuristic: Process using heuristics to determine formatting such '
'as chapter headings and italic text.\n'
'* textile: Processing using textile formatting.\n'
'* markdown: Processing using markdown formatting. '
'To learn more about markdown see')+' http://daringfireball.net/projects/markdown/'),
OptionRecommendation(name='preserve_spaces', recommended_value=False,
@ -91,6 +92,9 @@ class TXTInput(InputFormatPlugin):
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...')
html = convert_textile(txt)
else:
# Determine the paragraph type of the document.
if options.paragraph_type == 'auto':

44
src/calibre/ebooks/txt/processor.py
View File

@ -7,7 +7,6 @@ Read content from txt file.
import os, re
from calibre import prepare_string_for_xml, isbytestring
from calibre.ebooks.markdown import markdown
from calibre.ebooks.metadata.opf2 import OPFCreator
from calibre.ebooks.txt.heuristicprocessor import TXTHeuristicProcessor
from calibre.ebooks.conversion.preprocess import DocAnalysis
@ -74,12 +73,18 @@ def convert_heuristic(txt, title='', epub_split_size_kb=0):
return tp.convert(txt, title, epub_split_size_kb)
def convert_markdown(txt, title='', disable_toc=False):
from calibre.ebooks.markdown import markdown
md = markdown.Markdown(
extensions=['footnotes', 'tables', 'toc'],
extension_configs={"toc": {"disable_toc": disable_toc}},
safe_mode=False)
return HTML_TEMPLATE % (title, md.convert(txt))
def convert_textile(txt, title=''):
from calibre.ebooks.textile import textile
html = textile(txt, encoding='utf-8')
return HTML_TEMPLATE % (title, html)
def normalize_line_endings(txt):
txt = txt.replace('\r\n', '\n')
txt = txt.replace('\r', '\n')
@ -157,24 +162,33 @@ def detect_paragraph_type(txt):
def detect_formatting_type(txt):
markdown_count = 0
textile_count = 0
# Check for markdown
# Headings
if len(re.findall('(?mu)^#+', txt)) >= 5:
return 'markdown'
if len(re.findall('(?mu)^=+$', txt)) >= 5:
return 'markdown'
if len(re.findall('(?mu)^-+$', txt)) >= 5:
return 'markdown'
markdown_count += len(re.findall('(?mu)^#+', txt))
markdown_count += len(re.findall('(?mu)^=+$', txt))
markdown_count += len(re.findall('(?mu)^-+$', txt))
# Images
if len(re.findall('(?u)!\[.*?\]\(.+?\)', txt)) >= 5:
return 'markdown'
markdown_count += len(re.findall('(?u)!\[.*?\]\(.+?\)', txt))
# Links
if len(re.findall('(?u)(^|(?P<pre>[^!]))\[.*?\]\([^)]+\)', txt)) >= 5:
return 'markdown'
# Escaped characters
md_escapted_characters = ['\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '#', '+', '-', '.', '!']
for c in md_escapted_characters:
if txt.count('\\'+c) > 10:
markdown_count += len(re.findall('(?u)(^|(?P<pre>[^!]))\[.*?\]\([^)]+\)', txt))
# Check for textile
# Headings
textile_count += len(re.findall(r'(?mu)^h[1-6]\.', txt))
# Block quote.
textile_count += len(re.findall(r'(?mu)^bq\.', txt))
# Images
textile_count += len(re.findall(r'\![^\s]+(:[^\s]+)*', txt))
# Links
textile_count += len(re.findall(r'"(\(.+?\))*[^\(]+?(\(.+?\))*":[^\s]+', txt))
if markdown_count > 5 or textile_count > 5:
if markdown_count > textile_count:
return 'markdown'
else:
return 'textile'
return 'heuristic'

6
src/calibre/gui2/__init__.py
View File

@ -269,10 +269,14 @@ def question_dialog(parent, title, msg, det_msg='', show_copy_button=True,
return d.exec_() == yes_button
def info_dialog(parent, title, msg, det_msg='', show=False):
def info_dialog(parent, title, msg, det_msg='', show=False,
show_copy_button=True):
d = MessageBox(QMessageBox.Information, title, msg, QMessageBox.Ok,
parent, det_msg)
d.setIconPixmap(QPixmap(I('dialog_information.png')))
if not show_copy_button:
d.cb.setVisible(False)
if show:
return d.exec_()
return d

53
src/calibre/gui2/dialogs/user_profiles.py
View File

@ -4,7 +4,7 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
import time, os
from PyQt4.Qt import SIGNAL, QUrl, QAbstractListModel, Qt, \
QVariant, QInputDialog
QVariant
from calibre.web.feeds.recipes import compile_recipe
from calibre.web.feeds.news import AutomaticNewsRecipe
@ -256,15 +256,52 @@ class %(classname)s(%(base_class)s):
def add_builtin_recipe(self):
from calibre.web.feeds.recipes.collection import \
get_builtin_recipe_by_title, get_builtin_recipe_titles
items = sorted(get_builtin_recipe_titles(), key=sort_key)
get_builtin_recipe_collection, get_builtin_recipe_by_id
from PyQt4.Qt import QDialog, QVBoxLayout, QListWidgetItem, \
QListWidget, QDialogButtonBox, QSize
d = QDialog(self)
d.l = QVBoxLayout()
d.setLayout(d.l)
d.list = QListWidget(d)
d.list.doubleClicked.connect(lambda x: d.accept())
d.l.addWidget(d.list)
d.bb = QDialogButtonBox(QDialogButtonBox.Ok|QDialogButtonBox.Cancel,
Qt.Horizontal, d)
d.bb.accepted.connect(d.accept)
d.bb.rejected.connect(d.reject)
d.l.addWidget(d.bb)
d.setWindowTitle(_('Choose builtin recipe'))
items = []
for r in get_builtin_recipe_collection():
id_ = r.get('id', '')
title = r.get('title', '')
lang = r.get('language', '')
if id_ and title:
items.append((title + ' [%s]'%lang, id_))
items.sort(key=lambda x:sort_key(x[0]))
for title, id_ in items:
item = QListWidgetItem(title)
item.setData(Qt.UserRole, id_)
d.list.addItem(item)
d.resize(QSize(450, 400))
ret = d.exec_()
d.list.doubleClicked.disconnect()
if ret != d.Accepted:
return
items = list(d.list.selectedItems())
if not items:
return
item = items[-1]
id_ = unicode(item.data(Qt.UserRole).toString())
title = unicode(item.data(Qt.DisplayRole).toString()).rpartition(' [')[0]
profile = get_builtin_recipe_by_id(id_)
if profile is None:
raise Exception('Something weird happened')
title, ok = QInputDialog.getItem(self, _('Pick recipe'), _('Pick the recipe to customize'),
items, 0, False)
if ok:
title = unicode(title)
profile = get_builtin_recipe_by_title(title)
if self._model.has_title(title):
if question_dialog(self, _('Replace recipe?'),
_('A custom recipe named %s already exists. Do you want to '

51
src/calibre/gui2/preferences/plugins.py
View File

@ -15,7 +15,8 @@ from calibre.gui2.preferences.plugins_ui import Ui_Form
from calibre.customize.ui import initialized_plugins, is_disabled, enable_plugin, \
disable_plugin, plugin_customization, add_plugin, \
remove_plugin
from calibre.gui2 import NONE, error_dialog, info_dialog, choose_files
from calibre.gui2 import NONE, error_dialog, info_dialog, choose_files, \
question_dialog
class PluginModel(QAbstractItemModel): # {{{
@ -76,6 +77,16 @@ class PluginModel(QAbstractItemModel): # {{{
return self.index(j, 0, parent)
return QModelIndex()
def plugin_to_index_by_properties(self, plugin):
for i, category in enumerate(self.categories):
parent = self.index(i, 0, QModelIndex())
for j, p in enumerate(self._data[category]):
if plugin.name == p.name and plugin.type == p.type and \
plugin.author == p.author and plugin.version == p.version:
return self.index(j, 0, parent)
return QModelIndex()
def refresh_plugin(self, plugin, rescan=False):
if rescan:
self.populate()
@ -132,7 +143,6 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
self.toggle_plugin_button.clicked.connect(self.toggle_plugin)
self.customize_plugin_button.clicked.connect(self.customize_plugin)
self.remove_plugin_button.clicked.connect(self.remove_plugin)
self.button_plugin_browse.clicked.connect(self.find_plugin)
self.button_plugin_add.clicked.connect(self.add_plugin)
def toggle_plugin(self, *args):
@ -149,23 +159,39 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
self.modify_plugin(op='remove')
def add_plugin(self):
path = unicode(self.plugin_path.text())
path = choose_files(self, 'add a plugin dialog', _('Add plugin'),
filters=[(_('Plugins'), ['zip'])], all_files=False,
select_only_single_file=True)
if not path:
return
path = path[0]
if path and os.access(path, os.R_OK) and path.lower().endswith('.zip'):
add_plugin(path)
if not question_dialog(self, _('Are you sure?'), '<p>' + \
_('Installing plugins is a <b>security risk</b>. '
'Plugins can contain a virus/malware. '
'Only install it if you got it from a trusted source.'
' Are you sure you want to proceed?'),
show_copy_button=False):
return
plugin = add_plugin(path)
self._plugin_model.populate()
self._plugin_model.reset()
self.changed_signal.emit()
self.plugin_path.setText('')
info_dialog(self, _('Success'),
_('Plugin <b>{0}</b> successfully installed under <b>'
' {1} plugins</b>. You may have to restart calibre '
'for the plugin to take effect.').format(plugin.name, plugin.type),
show=True, show_copy_button=False)
idx = self._plugin_model.plugin_to_index_by_properties(plugin)
if idx.isValid():
self.plugin_view.scrollTo(idx,
self.plugin_view.PositionAtCenter)
self.plugin_view.scrollTo(idx,
self.plugin_view.PositionAtCenter)
else:
error_dialog(self, _('No valid plugin path'),
_('%s is not a valid plugin path')%path).exec_()
def find_plugin(self):
path = choose_files(self, 'choose plugin dialog', _('Choose plugin'),
filters=[('Plugins', ['zip'])], all_files=False,
select_only_single_file=True)
if path:
self.plugin_path.setText(path[0])
def modify_plugin(self, op=''):
index = self.plugin_view.currentIndex()
@ -191,10 +217,13 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
if plugin.do_user_config():
self._plugin_model.refresh_plugin(plugin)
elif op == 'remove':
msg = _('Plugin {0} successfully removed').format(plugin.name)
if remove_plugin(plugin):
self._plugin_model.populate()
self._plugin_model.reset()
self.changed_signal.emit()
info_dialog(self, _('Success'), msg, show=True,
show_copy_button=False)
else:
error_dialog(self, _('Cannot remove builtin plugin'),
plugin.name + _(' cannot be removed. It is a '

56
src/calibre/gui2/preferences/plugins.ui
View File

@ -72,67 +72,17 @@
</layout>
</item>
<item>
<widget class="QGroupBox" name="groupBox_4">
<property name="title">
<string>Add new plugin</string>
</property>
<layout class="QVBoxLayout" name="verticalLayout_5">
<item>
<layout class="QHBoxLayout" name="horizontalLayout_5">
<item>
<widget class="QLabel" name="label_14">
<widget class="QPushButton" name="button_plugin_add">
<property name="text">
<string>Plugin &amp;file:</string>
</property>
<property name="buddy">
<cstring>plugin_path</cstring>
</property>
</widget>
</item>
<item>
<widget class="QLineEdit" name="plugin_path"/>
</item>
<item>
<widget class="QToolButton" name="button_plugin_browse">
<property name="text">
<string>...</string>
<string>&amp;Add a new plugin</string>
</property>
<property name="icon">
<iconset resource="../../../../resources/images.qrc">
<normaloff>:/images/document_open.png</normaloff>:/images/document_open.png</iconset>
<normaloff>:/images/plugins.png</normaloff>:/images/plugins.png</iconset>
</property>
</widget>
</item>
</layout>
</item>
<item>
<layout class="QHBoxLayout" name="horizontalLayout_4">
<item>
<spacer name="horizontalSpacer_2">
<property name="orientation">
<enum>Qt::Horizontal</enum>
</property>
<property name="sizeHint" stdset="0">
<size>
<width>40</width>
<height>20</height>
</size>
</property>
</spacer>
</item>
<item>
<widget class="QPushButton" name="button_plugin_add">
<property name="text">
<string>&amp;Add</string>
</property>
</widget>
</item>
</layout>
</item>
</layout>
</widget>
</item>
</layout>
</widget>
<resources>
<include location="../../../../resources/images.qrc"/>

7
src/calibre/gui2/shortcuts.py
View File

@ -150,7 +150,7 @@ class Delegate(QStyledItemDelegate):
custom = []
if editor.custom.isChecked():
for x in ('1', '2'):
sc = getattr(editor, 'shortcut'+x)
sc = getattr(editor, 'shortcut'+x, None)
if sc is not None:
custom.append(sc)
@ -266,6 +266,11 @@ class ShortcutConfig(QWidget):
self.view.scrollTo(index)
@property
def is_editing(self):
return self.view.state() == self.view.EditingState
if __name__ == '__main__':
from calibre.gui2 import is_ok_to_use_qt
from calibre.gui2.viewer.keys import SHORTCUTS

13
src/calibre/gui2/ui.py
View File

@ -19,7 +19,7 @@ from PyQt4.Qt import Qt, SIGNAL, QTimer, \
QMessageBox, QHelpEvent
from calibre import prints
from calibre.constants import __appname__, isosx, DEBUG
from calibre.constants import __appname__, isosx
from calibre.ptempfile import PersistentTemporaryFile
from calibre.utils.config import prefs, dynamic
from calibre.utils.ipc.server import Server
@ -103,7 +103,15 @@ class Main(MainWindow, MainWindowMixin, DeviceMixin, EmailMixin, # {{{
self.gui_debug = gui_debug
acmap = OrderedDict()
for action in interface_actions():
try:
ac = action.load_actual_plugin(self)
except:
# Ignore errors in loading user supplied plugins
import traceback
traceback.print_exc()
if ac.plugin_path is None:
raise
ac.plugin_path = action.plugin_path
ac.interface_action_base_plugin = action
if ac.name in acmap:
@ -582,9 +590,6 @@ class Main(MainWindow, MainWindowMixin, DeviceMixin, EmailMixin, # {{{
# Goes here, because if cf is valid, db is valid.
db.prefs['field_metadata'] = db.field_metadata.all_metadata()
db.commit_dirty_cache()
if DEBUG and db.gm_count > 0:
print 'get_metadata cache: {0:d} calls, {1:4.2f}% misses'.format(
db.gm_count, (db.gm_missed*100.0)/db.gm_count)
for action in self.iactions.values():
if not action.shutting_down():
return

9
src/calibre/gui2/viewer/documentview.py
View File

@ -120,6 +120,13 @@ class ConfigDialog(QDialog, Ui_Dialog):
def accept(self, *args):
if self.shortcut_config.is_editing:
from calibre.gui2 import info_dialog
info_dialog(self, _('Still editing'),
_('You are in the middle of editing a keyboard shortcut'
' first complete that, by clicking outside the '
' shortcut editing box.'), show=True)
return
c = config()
c.set('serif_family', unicode(self.serif_family.currentFont().family()))
c.set('sans_family', unicode(self.sans_family.currentFont().family()))
@ -279,7 +286,7 @@ class Document(QWebPage): # {{{
@pyqtSignature("")
def init_hyphenate(self):
if self.hyphenate:
if self.hyphenate and getattr(self, 'loaded_lang', ''):
self.javascript('do_hyphenation("%s")'%self.loaded_lang)
def after_load(self):

4
src/calibre/library/caches.py
View File

@ -598,7 +598,6 @@ class ResultCache(SearchQueryParser): # {{{
def set(self, row, col, val, row_is_id=False):
id = row if row_is_id else self._map_filtered[row]
self._data[id][self.FIELD_MAP['all_metadata']] = None
self._data[id][col] = val
def get(self, row, col, row_is_id=False):
@ -629,7 +628,6 @@ class ResultCache(SearchQueryParser): # {{{
self._data[id] = CacheRow(db, self.composites,
db.conn.get('SELECT * from meta2 WHERE id=?', (id,))[0])
self._data[id].append(db.book_on_device_string(id))
self._data[id].append(None)
except IndexError:
return None
try:
@ -646,7 +644,6 @@ class ResultCache(SearchQueryParser): # {{{
self._data[id] = CacheRow(db, self.composites,
db.conn.get('SELECT * from meta2 WHERE id=?', (id,))[0])
self._data[id].append(db.book_on_device_string(id))
self._data[id].append(None)
self._map[0:0] = ids
self._map_filtered[0:0] = ids
@ -671,7 +668,6 @@ class ResultCache(SearchQueryParser): # {{{
for item in self._data:
if item is not None:
item.append(db.book_on_device_string(item[0]))
item.append(None)
self._map = [i[0] for i in self._data if i is not None]
if field is not None:
self.sort(field, ascending)

21
src/calibre/library/database2.py
View File

@ -298,10 +298,8 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
base,
prefer_custom=True)
self.FIELD_MAP['ondevice'] = base+1
self.field_metadata.set_field_record_index('ondevice', base+1, prefer_custom=False)
self.FIELD_MAP['all_metadata'] = base+2
self.field_metadata.set_field_record_index('all_metadata', base+2, prefer_custom=False)
self.FIELD_MAP['ondevice'] = base = base+1
self.field_metadata.set_field_record_index('ondevice', base, prefer_custom=False)
script = '''
DROP VIEW IF EXISTS meta2;
@ -690,19 +688,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
'''
row = self.data._data[idx] if index_is_id else self.data[idx]
fm = self.FIELD_MAP
self.gm_count += 1
mi = row[self.FIELD_MAP['all_metadata']]
if mi is not None:
if get_cover:
# Always get the cover, because the value can be wrong if the
# original mi was from the OPF
mi.cover = self.cover(idx, index_is_id=index_is_id, as_path=True)
return mi
self.gm_missed += 1
mi = Metadata(None)
self.data.set(idx, fm['all_metadata'], mi, row_is_id = index_is_id)
aut_list = row[fm['au_map']]
aut_list = [p.split(':::') for p in aut_list.split(':#:')]
@ -1387,7 +1373,8 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
if r is not None:
if (now - r[self.FIELD_MAP['timestamp']]) > delta:
tags = r[self.FIELD_MAP['tags']]
if tags and tag in tags.lower():
if tags and tag in [x.strip() for x in
tags.lower().split(',')]:
yield r[self.FIELD_MAP['id']]
def get_next_series_num_for(self, series):

9
src/calibre/library/field_metadata.py
View File

@ -162,15 +162,6 @@ class FieldMetadata(dict):
'search_terms':['tags', 'tag'],
'is_custom':False,
'is_category':True}),
('all_metadata',{'table':None,
'column':None,
'datatype':None,
'is_multiple':None,
'kind':'field',
'name':None,
'search_terms':[],
'is_custom':False,
'is_category':False}),
('author_sort',{'table':None,
'column':None,
'datatype':'text',

47
src/calibre/utils/wmf/__init__.py
View File

@ -5,5 +5,52 @@ __license__ = 'GPL v3'
__copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
import glob
from calibre.constants import plugins, iswindows, filesystem_encoding
from calibre.ptempfile import TemporaryDirectory
from calibre import CurrentDir
from calibre.utils.magick import Image, PixelWand
class Unavailable(Exception):
pass
class NoRaster(Exception):
pass
def extract_raster_image(wmf_data):
try:
wmf, wmf_err = plugins['wmf']
except KeyError:
raise Unavailable('libwmf not available on this platform')
if wmf_err:
raise Unavailable(wmf_err)
if iswindows:
import sys, os
appdir = sys.app_dir
if isinstance(appdir, unicode):
appdir = appdir.encode(filesystem_encoding)
fdir = os.path.join(appdir, 'wmffonts')
wmf.set_font_dir(fdir)
data = ''
with TemporaryDirectory('wmf2png') as tdir:
with CurrentDir(tdir):
wmf.render(wmf_data)
images = list(sorted(glob.glob('*.png')))
if not images:
raise NoRaster('No raster images in WMF')
data = open(images[0], 'rb').read()
im = Image()
im.load(data)
pw = PixelWand()
pw.color = '#ffffff'
im.rotate(pw, 180)
return im.export('png')

49
src/calibre/utils/wmf/wmf.c
View File

@ -4,6 +4,7 @@
#include <libwmf/api.h>
#include <libwmf/svg.h>
//#include <libwmf/gd.h>
typedef struct {
char *data;
@ -13,7 +14,7 @@ typedef struct {
//This code is taken mostly from the Abiword wmf plugin
// Buffer read {{{
// returns unsigned char cast to int, or EOF
static int wmf_WMF_read(void * context) {
char c;
@ -22,11 +23,11 @@ static int wmf_WMF_read(void * context) {
if (info->pos == info->len)
return EOF;
c = info->data[pos];
c = info->data[info->pos];
info->pos++;
return (int)c;
return (int)((unsigned char)c);
}
// returns (-1) on error, else 0
@ -44,8 +45,17 @@ static long wmf_WMF_tell(void * context) {
return (long) info->pos;
}
// }}}
char _png_name_buf[100];
char *wmf_png_name(void *ctxt) {
int *num = (int*)ctxt;
*num = *num + 1;
snprintf(_png_name_buf, 90, "%04d.png", *num);
return _png_name_buf;
}
#define CLEANUP if(API) { if (stream) wmf_free(API, stream); wmf_api_destroy(API); };
static PyObject *
@ -66,9 +76,9 @@ wmf_render(PyObject *self, PyObject *args) {
unsigned int max_width = 1600;
unsigned int max_height = 1200;
unsigned long max_flags = 0;
static const char* Default_Description = "wmf2svg";
int fname_counter = 0;
wmf_error_t err;
@ -125,6 +135,8 @@ wmf_render(PyObject *self, PyObject *args) {
ddata->Description = (char *)Default_Description;
ddata->bbox = bbox;
ddata->image.context = (void *)&fname_counter;
ddata->image.name = wmf_png_name;
wmf_display_size(API, &disp_width, &disp_height, 96, 96);
@ -156,9 +168,9 @@ wmf_render(PyObject *self, PyObject *args) {
ddata->height = (unsigned int) ceil ((double) wmf_height);
}
ddata->flags |= WMF_SVG_INLINE_IMAGES;
ddata->flags |= WMF_GD_OUTPUT_MEMORY | WMF_GD_OWN_BUFFER;
// Needs GD
//ddata->flags |= WMF_SVG_INLINE_IMAGES;
//ddata->flags |= WMF_GD_OUTPUT_MEMORY | WMF_GD_OWN_BUFFER;
err = wmf_play(API, 0, &(bbox));
@ -178,11 +190,32 @@ wmf_render(PyObject *self, PyObject *args) {
return ans;
}
#ifdef _WIN32
void set_libwmf_fontdir(const char *);
static PyObject *
wmf_setfontdir(PyObject *self, PyObject *args) {
char *path;
if (!PyArg_ParseTuple(args, "s", &path))
return NULL;
set_libwmf_fontdir(path);
Py_RETURN_NONE;
}
#endif
static PyMethodDef wmf_methods[] = {
{"render", wmf_render, METH_VARARGS,
"render(path) -> Render wmf as svg."
"render(data) -> Render wmf as svg."
},
#ifdef _WIN32
{"set_font_dir", wmf_setfontdir, METH_VARARGS,
"set_font_dir(path) -> Set the path to the fonts dir on windows, must be called at least once before using render()"
},
#endif
{NULL} /* Sentinel */
};

19
src/calibre/web/feeds/recipes/collection.py
View File

@ -108,7 +108,6 @@ def download_builtin_recipe(urn):
br = browser()
return br.open_novisit('http://status.calibre-ebook.com/recipe/'+urn).read()
def get_builtin_recipe_by_title(title, log=None, download_recipe=False):
for x in get_builtin_recipe_collection():
if x.get('title') == title:
@ -127,6 +126,24 @@ def get_builtin_recipe_by_title(title, log=None, download_recipe=False):
'Failed to download recipe, using builtin version')
return P('recipes/%s.recipe'%urn, data=True)
def get_builtin_recipe_by_id(id_, log=None, download_recipe=False):
for x in get_builtin_recipe_collection():
if x.get('id') == id_:
urn = x.get('id')[8:]
if download_recipe:
try:
if log is not None:
log('Trying to get latest version of recipe:', urn)
return download_builtin_recipe(urn)
except:
if log is None:
import traceback
traceback.print_exc()
else:
log.exception(
'Failed to download recipe, using builtin version')
return P('recipes/%s.recipe'%urn, data=True)
class SchedulerConfig(object):
def __init__(self):