mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-08-05 08:40:13 -04:00
pep8
This commit is contained in:
Kovid Goyal
parent
3d699bb357
commit
826d5ab725
@ -22,7 +22,7 @@ class WeeklyLWN(BasicNewsRecipe):
|
||||
remove_javascript = True
|
||||
|
||||
cover_url = site_url + '/images/lcorner.png'
|
||||
#masthead_url = 'http://lwn.net/images/lcorner.png'
|
||||
# masthead_url = 'http://lwn.net/images/lcorner.png'
|
||||
publication_type = 'magazine'
|
||||
|
||||
remove_tags_before = dict(attrs={'class':'PageHeadline'})
|
||||
@ -83,9 +83,9 @@ class WeeklyLWN(BasicNewsRecipe):
|
||||
subsection = None
|
||||
|
||||
while True:
|
||||
curr = curr.findNext(attrs = {'class': ['SummaryHL', 'Cat1HL', 'Cat2HL'] })
|
||||
curr = curr.findNext(attrs={'class': ['SummaryHL', 'Cat1HL', 'Cat2HL']})
|
||||
|
||||
if curr == None:
|
||||
if curr is None:
|
||||
break
|
||||
|
||||
text = curr.contents[0].string
|
||||
@ -106,7 +106,7 @@ class WeeklyLWN(BasicNewsRecipe):
|
||||
section_title = section
|
||||
|
||||
# Most articles have anchors in their titles, *except* the security vulnerabilities
|
||||
article_anchor = curr.findNext(name = 'a', attrs = { 'href': re.compile('^/Articles/') } )
|
||||
article_anchor = curr.findNext(name='a', attrs={'href': re.compile('^/Articles/')})
|
||||
|
||||
if article_anchor:
|
||||
article_url = article_anchor.get('href')
|
||||
@ -134,10 +134,11 @@ class WeeklyLWN(BasicNewsRecipe):
|
||||
else:
|
||||
print >>sys.stderr, "lwn_weekly.recipe: something bad happened; should not be able to reach this"
|
||||
|
||||
ans = [(section, articles[section]) for section in ans if section in articles]
|
||||
#from pprint import pprint
|
||||
#pprint(ans)
|
||||
ans = [(section2, articles[section2]) for section2 in ans if section2 in articles]
|
||||
# from pprint import pprint
|
||||
# pprint(ans)
|
||||
|
||||
return ans
|
||||
|
||||
# vim: expandtab:ts=4:sw=4
|
||||
|
||||
|
||||
@ -1,42 +1,43 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
## History:
|
||||
## 1: Base Version
|
||||
## 2: Added rules for wdr.de, ndr.de, br-online.de
|
||||
## 3: Added rules for rbb-online.de, boerse.ard.de, sportschau.de
|
||||
## 4: New design of tagesschau.de implemented. Simplyfied.
|
||||
## 5: Taken out the pictures.
|
||||
import re
|
||||
# History:
|
||||
# 1: Base Version
|
||||
# 2: Added rules for wdr.de, ndr.de, br-online.de
|
||||
# 3: Added rules for rbb-online.de, boerse.ard.de, sportschau.de
|
||||
# 4: New design of tagesschau.de implemented. Simplyfied.
|
||||
# 5: Taken out the pictures.
|
||||
|
||||
class Tagesschau(BasicNewsRecipe):
|
||||
title = 'Tagesschau'
|
||||
description = 'Nachrichten der ARD'
|
||||
publisher = 'ARD'
|
||||
language = 'de'
|
||||
version = 5
|
||||
title = 'Tagesschau'
|
||||
description = 'Nachrichten der ARD'
|
||||
publisher = 'ARD'
|
||||
language = 'de'
|
||||
version = 5
|
||||
|
||||
__author__ = 'Florian Andreas Pfaff, a.peter'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
__author__ = 'Florian Andreas Pfaff, a.peter'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
|
||||
feeds = [('Tagesschau', 'http://www.tagesschau.de/xml/rss2')]
|
||||
feeds = [('Tagesschau', 'http://www.tagesschau.de/xml/rss2')]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':['inline']}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*linklist.*')}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*media(Left|Right|Top|Bottom|Info).*')}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*mod(Socialbar|ConComments).*')}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*infokasten.*')}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*articlePictureA.*')}),
|
||||
dict(name='div', attrs={'id': re.compile(r'.*zoomTeaser.*')}),
|
||||
dict(name='h2', attrs={'class':re.compile(r'.*conHeadline.*')}),
|
||||
dict(name='ul', attrs={'class':['iconList']})
|
||||
]
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class':['section sectionZ sectionArticle']}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*containerArticle.*')})
|
||||
]
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':['inline']}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*linklist.*')}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*media(Left|Right|Top|Bottom|Info).*')}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*mod(Socialbar|ConComments).*')}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*infokasten.*')}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*articlePictureA.*')}),
|
||||
dict(name='div', attrs={'id': re.compile(r'.*zoomTeaser.*')}),
|
||||
dict(name='h2', attrs={'class':re.compile(r'.*conHeadline.*')}),
|
||||
dict(name='ul', attrs={'class':['iconList']})
|
||||
]
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class':['section sectionZ sectionArticle']}),
|
||||
dict(name='div', attrs={'class':re.compile(r'.*containerArticle.*')})
|
||||
]
|
||||
|
||||
def get_masthead_url(self):
|
||||
return 'http://intern.tagesschau.de/html/img/image.jpg'
|
||||
|
||||
def get_masthead_url(self):
|
||||
return 'http://intern.tagesschau.de/html/img/image.jpg'
|
||||
|
||||
|
||||
@ -114,7 +114,7 @@ class FB2Input(InputFormatPlugin):
|
||||
break
|
||||
|
||||
opf = OPFCreator(os.getcwdu(), mi)
|
||||
entries = [(f, guess_type(f)[0]) for f in os.listdir(u'.')]
|
||||
entries = [(f2, guess_type(f)[0]) for f2 in os.listdir(u'.')]
|
||||
opf.create_manifest(entries)
|
||||
opf.create_spine([u'index.xhtml'])
|
||||
if cpath:
|
||||
@ -127,7 +127,7 @@ class FB2Input(InputFormatPlugin):
|
||||
from calibre.ebooks.fb2 import base64_decode
|
||||
self.binary_map = {}
|
||||
for elem in doc.xpath('./*'):
|
||||
if elem.text and 'binary' in elem.tag and elem.attrib.has_key('id'):
|
||||
if elem.text and 'binary' in elem.tag and 'id' in elem.attrib:
|
||||
ct = elem.get('content-type', '')
|
||||
fname = elem.attrib['id']
|
||||
ext = ct.rpartition('/')[-1].lower()
|
||||
@ -146,3 +146,4 @@ class FB2Input(InputFormatPlugin):
|
||||
with open(fname, 'wb') as f:
|
||||
f.write(data)
|
||||
|
||||
|
||||
|
||||
@ -15,7 +15,7 @@ from collections import OrderedDict, defaultdict
|
||||
from calibre.ebooks.mobi.utils import (encint, encode_number_as_hex,
|
||||
encode_tbs, align_block, RECORD_SIZE, CNCX as CNCX_)
|
||||
|
||||
class CNCX(CNCX_): # {{{
|
||||
class CNCX(CNCX_): # {{{
|
||||
|
||||
def __init__(self, toc, is_periodical):
|
||||
strings = []
|
||||
@ -30,7 +30,7 @@ class CNCX(CNCX_): # {{{
|
||||
CNCX_.__init__(self, strings)
|
||||
# }}}
|
||||
|
||||
class TAGX(object): # {{{
|
||||
class TAGX(object): # {{{
|
||||
|
||||
BITMASKS = {11:0b1}
|
||||
BITMASKS.update({x:(1 << i) for i, x in enumerate([1, 2, 3, 4, 5, 21, 22, 23])})
|
||||
@ -105,8 +105,7 @@ class IndexEntry(object):
|
||||
'author_offset': 71,
|
||||
|
||||
}
|
||||
RTAG_MAP = {v:k for k, v in TAG_VALUES.iteritems()}
|
||||
|
||||
RTAG_MAP = {v:k for k, v in TAG_VALUES.iteritems()} # noqa
|
||||
|
||||
def __init__(self, offset, label_offset):
|
||||
self.offset, self.label_offset = offset, label_offset
|
||||
@ -131,8 +130,10 @@ class IndexEntry(object):
|
||||
|
||||
@dynamic_property
|
||||
def size(self):
|
||||
def fget(self): return self.length
|
||||
def fset(self, val): self.length = val
|
||||
def fget(self):
|
||||
return self.length
|
||||
def fset(self, val):
|
||||
self.length = val
|
||||
return property(fget=fget, fset=fset, doc='Alias for length')
|
||||
|
||||
@property
|
||||
@ -237,7 +238,7 @@ class SecondaryIndexEntry(IndexEntry):
|
||||
|
||||
# }}}
|
||||
|
||||
class TBS(object): # {{{
|
||||
class TBS(object): # {{{
|
||||
|
||||
'''
|
||||
Take the list of index nodes starting/ending on a record and calculate the
|
||||
@ -383,7 +384,6 @@ class TBS(object): # {{{
|
||||
buf.write(encode_tbs(last_article.index-next_sec.index,
|
||||
{0b1000: 0}))
|
||||
|
||||
|
||||
# If a section TOC starts and extends into the next record add
|
||||
# a trailing vwi. We detect this by TBS type==3, processing last
|
||||
# section present in the record, and the last article in that
|
||||
@ -424,7 +424,7 @@ class TBS(object): # {{{
|
||||
|
||||
# }}}
|
||||
|
||||
class Indexer(object): # {{{
|
||||
class Indexer(object): # {{{
|
||||
|
||||
def __init__(self, serializer, number_of_text_records,
|
||||
size_of_last_text_record, masthead_offset, is_periodical,
|
||||
@ -460,8 +460,10 @@ class Indexer(object): # {{{
|
||||
for node in oeb.toc.iterdescendants():
|
||||
if node.klass == 'article':
|
||||
aut, desc = node.author, node.description
|
||||
if not aut: aut = _('Unknown')
|
||||
if not desc: desc = _('No details available')
|
||||
if not aut:
|
||||
aut = _('Unknown')
|
||||
if not desc:
|
||||
desc = _('No details available')
|
||||
node.author, node.description = aut, desc
|
||||
|
||||
self.cncx = CNCX(oeb.toc, self.is_periodical)
|
||||
@ -485,7 +487,7 @@ class Indexer(object): # {{{
|
||||
|
||||
self.calculate_trailing_byte_sequences()
|
||||
|
||||
def create_index_record(self, secondary=False): # {{{
|
||||
def create_index_record(self, secondary=False): # {{{
|
||||
header_length = 192
|
||||
buf = StringIO()
|
||||
indices = list(SecondaryIndexEntry.entries()) if secondary else self.indices
|
||||
@ -509,9 +511,9 @@ class Indexer(object): # {{{
|
||||
header = b'INDX'
|
||||
buf.seek(0), buf.truncate(0)
|
||||
buf.write(pack(b'>I', header_length))
|
||||
buf.write(b'\0'*4) # Unknown
|
||||
buf.write(pack(b'>I', 1)) # Header type? Or index record number?
|
||||
buf.write(b'\0'*4) # Unknown
|
||||
buf.write(b'\0'*4) # Unknown
|
||||
buf.write(pack(b'>I', 1)) # Header type? Or index record number?
|
||||
buf.write(b'\0'*4) # Unknown
|
||||
# IDXT block offset
|
||||
buf.write(pack(b'>I', header_length + len(index_block)))
|
||||
# Number of index entries
|
||||
@ -529,7 +531,7 @@ class Indexer(object): # {{{
|
||||
return ans
|
||||
# }}}
|
||||
|
||||
def create_header(self, secondary=False): # {{{
|
||||
def create_header(self, secondary=False): # {{{
|
||||
buf = StringIO()
|
||||
if secondary:
|
||||
tagx_block = TAGX().secondary
|
||||
@ -551,13 +553,13 @@ class Indexer(object): # {{{
|
||||
buf.write(pack(b'>I', 2))
|
||||
|
||||
# IDXT offset 20-24
|
||||
buf.write(pack(b'>I', 0)) # Filled in later
|
||||
buf.write(pack(b'>I', 0)) # Filled in later
|
||||
|
||||
# Number of index records 24-28
|
||||
buf.write(pack(b'>I', 1 if secondary else len(self.records)))
|
||||
|
||||
# Index Encoding 28-32
|
||||
buf.write(pack(b'>I', 65001)) # utf-8
|
||||
buf.write(pack(b'>I', 65001)) # utf-8
|
||||
|
||||
# Unknown 32-36
|
||||
buf.write(b'\xff'*4)
|
||||
@ -620,7 +622,7 @@ class Indexer(object): # {{{
|
||||
return align_block(buf.getvalue())
|
||||
# }}}
|
||||
|
||||
def create_book_index(self): # {{{
|
||||
def create_book_index(self): # {{{
|
||||
indices = []
|
||||
seen = set()
|
||||
id_offsets = self.serializer.id_offsets
|
||||
@ -652,7 +654,6 @@ class Indexer(object): # {{{
|
||||
next_offset = self.serializer.body_end_offset
|
||||
index.length = next_offset - index.offset
|
||||
|
||||
|
||||
# Remove empty indices
|
||||
indices = [x for x in indices if x.length > 0]
|
||||
|
||||
@ -672,7 +673,7 @@ class Indexer(object): # {{{
|
||||
|
||||
# }}}
|
||||
|
||||
def create_periodical_index(self): # {{{
|
||||
def create_periodical_index(self): # {{{
|
||||
periodical_node = iter(self.oeb.toc).next()
|
||||
periodical_node_offset = self.serializer.body_start_offset
|
||||
periodical_node_size = (self.serializer.body_end_offset -
|
||||
@ -727,7 +728,7 @@ class Indexer(object): # {{{
|
||||
if ii > -1:
|
||||
article.image_index = ii
|
||||
except KeyError:
|
||||
pass # Image not found in serializer
|
||||
pass # Image not found in serializer
|
||||
|
||||
if normalized_articles:
|
||||
normalized_articles.sort(key=lambda x:x.offset)
|
||||
@ -885,3 +886,4 @@ class Indexer(object): # {{{
|
||||
|
||||
# }}}
|
||||
|
||||
|
||||
|
||||
@ -64,7 +64,8 @@ class Extract(ODF2XHTML):
|
||||
f.write(css.encode('utf-8'))
|
||||
|
||||
def get_css_for_class(self, cls):
|
||||
if not cls: return None
|
||||
if not cls:
|
||||
return None
|
||||
for rule in self.css.cssRules.rulesOfType(CSSRule.STYLE_RULE):
|
||||
for sel in rule.selectorList:
|
||||
q = sel.selectorText
|
||||
@ -94,7 +95,7 @@ class Extract(ODF2XHTML):
|
||||
style = div.attrib.get('style', '')
|
||||
if style and not style.endswith(';'):
|
||||
style = style + ';'
|
||||
style += 'position:static' # Ensures position of containing
|
||||
style += 'position:static' # Ensures position of containing
|
||||
# div is static
|
||||
# Ensure that the img is always contained in its frame
|
||||
div.attrib['style'] = style
|
||||
@ -112,7 +113,8 @@ class Extract(ODF2XHTML):
|
||||
for img in imgpath(root):
|
||||
div2 = img.getparent()
|
||||
div1 = div2.getparent()
|
||||
if (len(div1), len(div2)) != (1, 1): continue
|
||||
if (len(div1), len(div2)) != (1, 1):
|
||||
continue
|
||||
cls = div1.get('class', '')
|
||||
first_rules = filter(None, [self.get_css_for_class(x) for x in
|
||||
cls.split()])
|
||||
@ -151,7 +153,6 @@ class Extract(ODF2XHTML):
|
||||
style = div2.attrib['style']
|
||||
div2.attrib['style'] = 'display:inline;'+style
|
||||
|
||||
|
||||
def filter_css(self, root, log):
|
||||
style = root.xpath('//*[local-name() = "style" and @type="text/css"]')
|
||||
if style:
|
||||
@ -236,7 +237,7 @@ class Extract(ODF2XHTML):
|
||||
self.lines = []
|
||||
self._wfunc = self._wlines
|
||||
if isinstance(odffile, basestring) \
|
||||
or hasattr(odffile, 'read'): # Added by Kovid
|
||||
or hasattr(odffile, 'read'): # Added by Kovid
|
||||
self.document = odLoad(odffile)
|
||||
else:
|
||||
self.document = odffile
|
||||
@ -282,7 +283,7 @@ class Extract(ODF2XHTML):
|
||||
zf = ZipFile(stream, 'r')
|
||||
self.extract_pictures(zf)
|
||||
opf = OPFCreator(os.path.abspath(os.getcwdu()), mi)
|
||||
opf.create_manifest([(os.path.abspath(f), None) for f in
|
||||
opf.create_manifest([(os.path.abspath(f2), None) for f2 in
|
||||
walk(os.getcwdu())])
|
||||
opf.create_spine([os.path.abspath('index.xhtml')])
|
||||
with open('metadata.opf', 'wb') as f:
|
||||
@ -291,3 +292,4 @@ class Extract(ODF2XHTML):
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@ -18,7 +18,7 @@ from calibre import prints, force_unicode, as_unicode
|
||||
|
||||
single_shot = partial(QTimer.singleShot, 75)
|
||||
|
||||
class DuplicatesAdder(QObject): # {{{
|
||||
class DuplicatesAdder(QObject): # {{{
|
||||
|
||||
added = pyqtSignal(object)
|
||||
adding_done = pyqtSignal()
|
||||
@ -49,7 +49,7 @@ class DuplicatesAdder(QObject): # {{{
|
||||
|
||||
# }}}
|
||||
|
||||
class RecursiveFind(QThread): # {{{
|
||||
class RecursiveFind(QThread): # {{{
|
||||
|
||||
update = pyqtSignal(object)
|
||||
found = pyqtSignal(object)
|
||||
@ -95,7 +95,7 @@ class RecursiveFind(QThread): # {{{
|
||||
|
||||
# }}}
|
||||
|
||||
class DBAdder(QObject): # {{{
|
||||
class DBAdder(QObject): # {{{
|
||||
|
||||
def __init__(self, parent, db, ids, nmap):
|
||||
QObject.__init__(self, parent)
|
||||
@ -185,8 +185,8 @@ class DBAdder(QObject): # {{{
|
||||
with open(cover, 'rb') as f:
|
||||
cover = f.read()
|
||||
orig_formats = formats
|
||||
formats = [f for f in formats if not f.lower().endswith('.opf')]
|
||||
if prefs['add_formats_to_existing']: #automerge is on
|
||||
formats = [f2 for f2 in formats if not f2.lower().endswith('.opf')]
|
||||
if prefs['add_formats_to_existing']: # automerge is on
|
||||
identical_book_list = self.db.find_identical_books(mi)
|
||||
if identical_book_list: # books with same author and nearly same title exist in db
|
||||
self.merged_books.add(mi.title)
|
||||
@ -221,7 +221,7 @@ class DBAdder(QObject): # {{{
|
||||
self.number_of_books_added += 1
|
||||
self.add_formats(id_, formats)
|
||||
|
||||
else: #automerge is off
|
||||
else: # automerge is off
|
||||
id_ = self.db.create_book_entry(mi, cover=cover, add_duplicates=False)
|
||||
if id_ is None:
|
||||
self.duplicates.append((mi, cover, orig_formats))
|
||||
@ -244,9 +244,9 @@ class DBAdder(QObject): # {{{
|
||||
|
||||
# }}}
|
||||
|
||||
class Adder(QObject): # {{{
|
||||
class Adder(QObject): # {{{
|
||||
|
||||
ADD_TIMEOUT = 900 # seconds (15 minutes)
|
||||
ADD_TIMEOUT = 900 # seconds (15 minutes)
|
||||
|
||||
def __init__(self, parent, db, callback, spare_server=None):
|
||||
QObject.__init__(self, parent)
|
||||
@ -385,7 +385,6 @@ class Adder(QObject): # {{{
|
||||
if self.continue_updating:
|
||||
single_shot(self.update)
|
||||
|
||||
|
||||
def process_duplicates(self):
|
||||
duplicates = self.db_adder.duplicates
|
||||
if not duplicates:
|
||||
@ -427,7 +426,6 @@ class Adder(QObject): # {{{
|
||||
del self.db_adder
|
||||
self.db_adder = None
|
||||
|
||||
|
||||
@property
|
||||
def number_of_books_added(self):
|
||||
return getattr(getattr(self, 'db_adder', None), 'number_of_books_added',
|
||||
@ -459,7 +457,7 @@ class Adder(QObject): # {{{
|
||||
|
||||
# }}}
|
||||
|
||||
class Saver(QObject): # {{{
|
||||
class Saver(QObject): # {{{
|
||||
|
||||
def __init__(self, parent, db, callback, rows, path, opts,
|
||||
spare_server=None):
|
||||
@ -489,7 +487,6 @@ class Saver(QObject): # {{{
|
||||
self.continue_updating = True
|
||||
single_shot(self.update)
|
||||
|
||||
|
||||
def canceled(self):
|
||||
self.continue_updating = False
|
||||
if self.worker is not None:
|
||||
@ -499,7 +496,6 @@ class Saver(QObject): # {{{
|
||||
self.callback(self.worker.path, self.failures, self.worker.error)
|
||||
self.callback_called = True
|
||||
|
||||
|
||||
def update(self):
|
||||
if not self.continue_updating:
|
||||
return
|
||||
@ -523,7 +519,7 @@ class Saver(QObject): # {{{
|
||||
# Give the worker time to clean up and set worker.error
|
||||
self.worker.join(2)
|
||||
except:
|
||||
pass # The worker was not yet started
|
||||
pass # The worker was not yet started
|
||||
self.callback_called = True
|
||||
self.callback(self.worker.path, self.failures, self.worker.error)
|
||||
|
||||
@ -531,7 +527,6 @@ class Saver(QObject): # {{{
|
||||
self.get_result()
|
||||
single_shot(self.update)
|
||||
|
||||
|
||||
def get_result(self):
|
||||
try:
|
||||
id, title, ok, tb = self.rq.get_nowait()
|
||||
@ -549,3 +544,4 @@ class Saver(QObject): # {{{
|
||||
self.failures.add((title, tb))
|
||||
# }}}
|
||||
|
||||
|
||||
|
||||
@ -22,7 +22,7 @@ from calibre.gui2 import error_dialog
|
||||
|
||||
IMAGE_EXTENSIONS = ['jpg', 'jpeg', 'gif', 'png', 'bmp']
|
||||
|
||||
class Worker(Thread): # {{{
|
||||
class Worker(Thread): # {{{
|
||||
|
||||
def __init__(self, url, fpath, rq):
|
||||
Thread.__init__(self)
|
||||
@ -44,7 +44,7 @@ class Worker(Thread): # {{{
|
||||
self.rq.put((a, b, c))
|
||||
# }}}
|
||||
|
||||
class DownloadDialog(QDialog): # {{{
|
||||
class DownloadDialog(QDialog): # {{{
|
||||
|
||||
def __init__(self, url, fname, parent):
|
||||
QDialog.__init__(self, parent)
|
||||
@ -248,7 +248,7 @@ def dnd_get_files(md, exts):
|
||||
purls = [urlparse(u) for u in urls]
|
||||
# First look for a local file
|
||||
local_files = [u2p(x) for x in purls if x.scheme in ('', 'file')]
|
||||
local_files = [ p for p in local_files if
|
||||
local_files = [p for p in local_files if
|
||||
posixpath.splitext(urllib.unquote(p))[1][1:].lower() in
|
||||
exts]
|
||||
local_files = [x for x in local_files if os.path.exists(x)]
|
||||
@ -266,7 +266,7 @@ def dnd_get_files(md, exts):
|
||||
remote_urls = [x for x in purls if x.scheme in ('http', 'https',
|
||||
'ftp') and posixpath.splitext(x.path)[1][1:].lower() in exts]
|
||||
if remote_urls:
|
||||
filenames = [posixpath.basename(urllib.unquote(rurl.path)) for rurl in
|
||||
filenames = [posixpath.basename(urllib.unquote(rurl2.path)) for rurl2 in
|
||||
remote_urls]
|
||||
return [urlunparse(x) for x in remote_urls], filenames
|
||||
|
||||
@ -336,3 +336,4 @@ def get_firefox_rurl(md, exts):
|
||||
def has_firefox_ext(md, exts):
|
||||
return bool(get_firefox_rurl(md, exts)[0])
|
||||
|
||||
|
||||
|
||||
@ -77,35 +77,35 @@ utf8enc2latex_mapping = {
|
||||
# The extraction has been done by the "create_unimap.py" script
|
||||
# located at <http://docutils.sf.net/tools/dev/create_unimap.py>.
|
||||
|
||||
#Fix some encoding problem between cp1252 and latin1
|
||||
# Fix some encoding problem between cp1252 and latin1
|
||||
# from http://www.microsoft.com/typography/unicode/1252.htm
|
||||
u'\x80': '{\\texteuro}', # EURO SIGN
|
||||
u'\x82': '{,}', # SINGLE LOW-9 QUOTATION MARK
|
||||
u'\x83': '$f$', # LATIN SMALL LETTER F WITH HOOK
|
||||
u'\x84': '{,,}', # DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\x85': '{\\ldots}', # HORIZONTAL ELLIPSIS
|
||||
u'\x86': '{\\textdagger}', # DAGGER
|
||||
u'\x87': '{\\textdaggerdbl}', # DOUBLE DAGGER
|
||||
u'\x88': '{\textasciicircum}', # MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
u'\x89': '{\\textperthousand}', # PER MILLE SIGN
|
||||
u'\x8A': '{\\v{S}}', # LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\x8B': '{\\guilsinglleft}', # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\x8C': '{\\OE}', # LATIN CAPITAL LIGATURE OE
|
||||
u'\x8E': '{\\v{Z}}', # LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\x91': '{`}', # LEFT SINGLE QUOTATION MARK
|
||||
u'\x92': "{'}", # RIGHT SINGLE QUOTATION MARK
|
||||
u'\x93': '{\\textquotedblleft}', # LEFT DOUBLE QUOTATION MARK
|
||||
u'\x94': '{\\textquotedblright}', # RIGHT DOUBLE QUOTATION MARK
|
||||
u'\x95': '{\\textbullet}', # BULLET
|
||||
u'\x96': '{\\textendash}', # EN DASH
|
||||
u'\x97': '{\\textemdash}', # EM DASH
|
||||
u'\x98': '{\\texttildelow}', # SMALL TILDE
|
||||
u'\x99': '{\\texttrademark}', # TRADE MARK SIGN
|
||||
u'\x9A': '{\\v{s}}', # LATIN SMALL LETTER S WITH CARON
|
||||
u'\x9B': '{\\guilsinglright}', # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\x9C': '{\\oe}', # LATIN SMALL LIGATURE OE
|
||||
u'\x9E': '{\\v{z}}', # LATIN SMALL LETTER Z WITH CARON
|
||||
u'\x9F': '{\\"{Y}}', # LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
u'\x80': '{\\texteuro}', # EURO SIGN
|
||||
u'\x82': '{,}', # SINGLE LOW-9 QUOTATION MARK
|
||||
u'\x83': '$f$', # LATIN SMALL LETTER F WITH HOOK
|
||||
u'\x84': '{,,}', # DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\x85': '{\\ldots}', # HORIZONTAL ELLIPSIS
|
||||
u'\x86': '{\\textdagger}', # DAGGER
|
||||
u'\x87': '{\\textdaggerdbl}', # DOUBLE DAGGER
|
||||
u'\x88': '{\textasciicircum}', # MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
u'\x89': '{\\textperthousand}', # PER MILLE SIGN
|
||||
u'\x8A': '{\\v{S}}', # LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\x8B': '{\\guilsinglleft}', # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\x8C': '{\\OE}', # LATIN CAPITAL LIGATURE OE
|
||||
u'\x8E': '{\\v{Z}}', # LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\x91': '{`}', # LEFT SINGLE QUOTATION MARK
|
||||
u'\x92': "{'}", # RIGHT SINGLE QUOTATION MARK
|
||||
u'\x93': '{\\textquotedblleft}', # LEFT DOUBLE QUOTATION MARK
|
||||
u'\x94': '{\\textquotedblright}', # RIGHT DOUBLE QUOTATION MARK
|
||||
u'\x95': '{\\textbullet}', # BULLET
|
||||
u'\x96': '{\\textendash}', # EN DASH
|
||||
u'\x97': '{\\textemdash}', # EM DASH
|
||||
u'\x98': '{\\texttildelow}', # SMALL TILDE
|
||||
u'\x99': '{\\texttrademark}', # TRADE MARK SIGN
|
||||
u'\x9A': '{\\v{s}}', # LATIN SMALL LETTER S WITH CARON
|
||||
u'\x9B': '{\\guilsinglright}', # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\x9C': '{\\oe}', # LATIN SMALL LIGATURE OE
|
||||
u'\x9E': '{\\v{z}}', # LATIN SMALL LETTER Z WITH CARON
|
||||
u'\x9F': '{\\"{Y}}', # LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
|
||||
u'\xa0': '$~$',
|
||||
u'\xa1': '{\\textexclamdown}',
|
||||
@ -2465,7 +2465,7 @@ utf8enc2latex_mapping = {
|
||||
u'\U0001d7fe': '$\\mathtt{8}$',
|
||||
u'\U0001d7ff': '$\\mathtt{9}$',
|
||||
|
||||
#Items from simple list
|
||||
# Items from simple list
|
||||
u'\u0106': "{\\a\\'C}",
|
||||
u'\u0408': '{\\CYRJE}',
|
||||
u'\u20ac': '{\\texteuro}',
|
||||
@ -2796,45 +2796,45 @@ utf8enc2latex_mapping = {
|
||||
u'\u016f': '{\\r u}',
|
||||
u'\xfa': "{\\'u}"
|
||||
|
||||
#Items to add at a latter date (check first)
|
||||
#u'\u0000': r'{$\alpha$}',
|
||||
#u'\u0000': r'{$\beta$}',
|
||||
#u'\u0000': r'{$\gamma$}',
|
||||
#u'\u0000': r'{$\delta$}',
|
||||
#u'\u0000': r'{$\epsilon$}',
|
||||
#u'\u0000': r'{$\varepsilon$}',
|
||||
#u'\u0000': r'{$\zeta$}',
|
||||
#u'\u0000': r'{$\eta$}',
|
||||
#u'\u0000': r'{$\theta$}',
|
||||
#u'\u0000': r'{$\vartheta$}',
|
||||
#u'\u0000': r'{$\iota$}',
|
||||
#u'\u0000': r'{$\kappa$}',
|
||||
#u'\u0000': r'{$\lambda$}',
|
||||
#u'\u0000': r'{$\mu$}',
|
||||
#u'\u0000': r'{$\xi$}',
|
||||
#u'\u0000': r'{$\pi$}',
|
||||
#u'\u0000': r'{$\varpi$}',
|
||||
#u'\u0000': r'{$\rho$}',
|
||||
#u'\u0000': r'{$\varrho$}',
|
||||
#u'\u0000': r'{$\sigma$}',
|
||||
#u'\u0000': r'{$\varsigma$}',
|
||||
#u'\u0000': r'{$\tau$}',
|
||||
#u'\u0000': r'{$\upsilon$}',
|
||||
#u'\u0000': r'{$\phi$}',
|
||||
#u'\u0000': r'{$\varphi$}',
|
||||
#u'\u0000': r'{$\psi$}',
|
||||
#u'\u0000': r'{$\omega$}',
|
||||
#u'\u0000': r'{$\Gamma$}',
|
||||
#u'\u0000': r'{$\Delta$}',
|
||||
#u'\u0000': r'{$\Theta$}',
|
||||
#u'\u0000': r'{$\Lambda$}',
|
||||
#u'\u0000': r'{$\Xi$}',
|
||||
#u'\u0000': r'{$\Pi$}',
|
||||
#u'\u0000': r'{$\Sigma$}',
|
||||
#u'\u0000': r'{$\Upsilon$}',
|
||||
#u'\u0000': r'{$\Phi$}',
|
||||
#u'\u0000': r'{$\Psi$}',
|
||||
#u'\u0000': r'{$\Omega$}',
|
||||
# Items to add at a latter date (check first)
|
||||
# u'\u0000': r'{$\alpha$}',
|
||||
# u'\u0000': r'{$\beta$}',
|
||||
# u'\u0000': r'{$\gamma$}',
|
||||
# u'\u0000': r'{$\delta$}',
|
||||
# u'\u0000': r'{$\epsilon$}',
|
||||
# u'\u0000': r'{$\varepsilon$}',
|
||||
# u'\u0000': r'{$\zeta$}',
|
||||
# u'\u0000': r'{$\eta$}',
|
||||
# u'\u0000': r'{$\theta$}',
|
||||
# u'\u0000': r'{$\vartheta$}',
|
||||
# u'\u0000': r'{$\iota$}',
|
||||
# u'\u0000': r'{$\kappa$}',
|
||||
# u'\u0000': r'{$\lambda$}',
|
||||
# u'\u0000': r'{$\mu$}',
|
||||
# u'\u0000': r'{$\xi$}',
|
||||
# u'\u0000': r'{$\pi$}',
|
||||
# u'\u0000': r'{$\varpi$}',
|
||||
# u'\u0000': r'{$\rho$}',
|
||||
# u'\u0000': r'{$\varrho$}',
|
||||
# u'\u0000': r'{$\sigma$}',
|
||||
# u'\u0000': r'{$\varsigma$}',
|
||||
# u'\u0000': r'{$\tau$}',
|
||||
# u'\u0000': r'{$\upsilon$}',
|
||||
# u'\u0000': r'{$\phi$}',
|
||||
# u'\u0000': r'{$\varphi$}',
|
||||
# u'\u0000': r'{$\psi$}',
|
||||
# u'\u0000': r'{$\omega$}',
|
||||
# u'\u0000': r'{$\Gamma$}',
|
||||
# u'\u0000': r'{$\Delta$}',
|
||||
# u'\u0000': r'{$\Theta$}',
|
||||
# u'\u0000': r'{$\Lambda$}',
|
||||
# u'\u0000': r'{$\Xi$}',
|
||||
# u'\u0000': r'{$\Pi$}',
|
||||
# u'\u0000': r'{$\Sigma$}',
|
||||
# u'\u0000': r'{$\Upsilon$}',
|
||||
# u'\u0000': r'{$\Phi$}',
|
||||
# u'\u0000': r'{$\Psi$}',
|
||||
# u'\u0000': r'{$\Omega$}',
|
||||
}
|
||||
|
||||
entity_mapping = {
|
||||
@ -2847,7 +2847,7 @@ class BibTeX:
|
||||
def __init__(self):
|
||||
self.rep_utf8 = MReplace(utf8enc2latex_mapping)
|
||||
self.rep_ent = MReplace(entity_mapping)
|
||||
#Set default conversion to ASCII BibTeX
|
||||
# Set default conversion to ASCII BibTeX
|
||||
self.ascii_bibtex = True
|
||||
# This substitution is based on the description of cite key restrictions at
|
||||
# http://bibdesk.sourceforge.net/manual/BibDesk%20Help_2.html
|
||||
@ -2859,27 +2859,23 @@ class BibTeX:
|
||||
def ValidateCitationKey(self, text):
|
||||
"""
|
||||
removes characters not allowed in BibTeX keys
|
||||
>>> ValidateCitationKey(DummyEntry('my@id'))
|
||||
'myid'
|
||||
"""
|
||||
return self.invalid_cit.sub(u'', text)
|
||||
|
||||
def braceUppercase(self, text):
|
||||
""" Convert uppercase letters to bibtex encoded uppercase
|
||||
>>> braceUppercase('Foo Bar')
|
||||
'{F}oo {B}ar'
|
||||
"""
|
||||
return self.upper.sub(lambda m: u'{%s}' % m.group(), text)
|
||||
|
||||
def resolveEntities(self, text):
|
||||
#for entity, entity_map in entity_mapping.iteritems():
|
||||
# for entity, entity_map in entity_mapping.iteritems():
|
||||
# text = text.replace(entity, entity_map)
|
||||
#return text
|
||||
# return text
|
||||
return self.rep_ent.mreplace(text)
|
||||
|
||||
def resolveUnicode(self, text):
|
||||
#UTF-8 text as entry
|
||||
#for unichar, latexenc in utf8enc2latex_mapping.iteritems() :
|
||||
# UTF-8 text as entry
|
||||
# for unichar, latexenc in utf8enc2latex_mapping.iteritems() :
|
||||
# text = text.replace(unichar, latexenc)
|
||||
text = self.rep_utf8.mreplace(text)
|
||||
return text.replace(u'$}{$', u'')
|
||||
@ -2891,9 +2887,9 @@ class BibTeX:
|
||||
text.replace('\\', '\\\\')
|
||||
return self.escape.sub(lambda m: u'\\%s' % m.group(), text)
|
||||
|
||||
#Calibre functions
|
||||
#Option to go to official ASCII Bibtex or unofficial UTF-8
|
||||
#Go from an unicode entry to ASCII Bibtex format without encoding
|
||||
# Calibre functions
|
||||
# Option to go to official ASCII Bibtex or unofficial UTF-8
|
||||
# Go from an unicode entry to ASCII Bibtex format without encoding
|
||||
def utf8ToBibtex(self, text):
|
||||
if len(text) == 0:
|
||||
return ''
|
||||
@ -2904,5 +2900,6 @@ class BibTeX:
|
||||
return self.escapeSpecialCharacters(text)
|
||||
|
||||
def bibtex_author_format(self, item):
|
||||
#Format authors for Bibtex compliance (get a list as input)
|
||||
# Format authors for Bibtex compliance (get a list as input)
|
||||
return self.utf8ToBibtex(u' and '.join([author for author in item]))
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user