Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

GwR updates to catalog code using icu.sort_key, resolving some epubcheck and flightcrew errors

Browse Source
This commit is contained in:
GRiker 2012-07-06 11:18:55 -06:00
parent dd179f8fb3
commit 7ec70e67e1
4 changed files with 123 additions and 105 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/calibre/gui2/convert/gui_conversion.py
View File

@ -31,7 +31,7 @@ def gui_convert_override(input, output, recommendations, notification=DummyRepor
override_input_metadata=True) override_input_metadata=True)
def gui_catalog(fmt, title, dbspec, ids, out_file_name, sync, fmt_options, connected_device, def gui_catalog(fmt, title, dbspec, ids, out_file_name, sync, fmt_options, connected_device,
notification=DummyReporter(), log=None): debug_mode, notification=DummyReporter(), log=None):
if log is None: if log is None:
log = Log() log = Log()
from calibre.library import db from calibre.library import db
@ -50,6 +50,7 @@ def gui_catalog(fmt, title, dbspec, ids, out_file_name, sync, fmt_options, conne
# opts.gui_search_text = something # opts.gui_search_text = something
opts.catalog_title = title opts.catalog_title = title
opts.connected_device = connected_device opts.connected_device = connected_device
opts.debug_mode = debug_mode
opts.ids = ids opts.ids = ids
opts.search_text = None opts.search_text = None
opts.sort_by = None opts.sort_by = None

4
src/calibre/gui2/tools.py
View File

@ -11,6 +11,7 @@ import cPickle, os
from PyQt4.Qt import QDialog, QProgressDialog, QString, QTimer from PyQt4.Qt import QDialog, QProgressDialog, QString, QTimer
from calibre.constants import DEBUG
from calibre.ptempfile import PersistentTemporaryFile from calibre.ptempfile import PersistentTemporaryFile
from calibre.gui2 import warning_dialog, question_dialog from calibre.gui2 import warning_dialog, question_dialog
from calibre.gui2.convert.single import NoSupportedInputFormats from calibre.gui2.convert.single import NoSupportedInputFormats
@ -319,7 +320,8 @@ def generate_catalog(parent, dbspec, ids, device_manager, db): # {{{
out.name, out.name,
d.catalog_sync, d.catalog_sync,
d.fmt_options, d.fmt_options,
connected_device connected_device,
DEBUG
] ]
out.close() out.close()

8
src/calibre/library/catalogs/epub_mobi.py
View File

@ -11,7 +11,6 @@ import os
from collections import namedtuple from collections import namedtuple
from calibre import strftime from calibre import strftime
from calibre.constants import DEBUG
from calibre.customize import CatalogPlugin from calibre.customize import CatalogPlugin
from calibre.customize.conversion import OptionRecommendation, DummyReporter from calibre.customize.conversion import OptionRecommendation, DummyReporter
@ -277,13 +276,16 @@ class EPUB_MOBI(CatalogPlugin):
log.error("coercing thumb_width from '%s' to '%s'" % (opts.thumb_width,self.THUMB_SMALLEST)) log.error("coercing thumb_width from '%s' to '%s'" % (opts.thumb_width,self.THUMB_SMALLEST))
opts.thumb_width = "1.0" opts.thumb_width = "1.0"
if opts.debug_mode:
setattr(opts, 'debug_pipeline', os.path.expanduser("~/Desktop/Catalog debug"))
# Display opts # Display opts
keys = opts_dict.keys() keys = opts_dict.keys()
keys.sort() keys.sort()
build_log.append(" opts:") build_log.append(" opts:")
for key in keys: for key in keys:
if key in ['catalog_title','authorClip','connected_kindle','descriptionClip', if key in ['catalog_title','authorClip','connected_kindle','descriptionClip',
'exclude_book_marker','exclude_genre','exclude_tags', 'debug_pipeline','exclude_book_marker','exclude_genre','exclude_tags',
'header_note_source_field','merge_comments', 'header_note_source_field','merge_comments',
'output_profile','read_book_marker', 'output_profile','read_book_marker',
'search_text','sort_by','sort_descriptions_by_author','sync', 'search_text','sort_by','sort_descriptions_by_author','sync',
@ -315,7 +317,7 @@ class EPUB_MOBI(CatalogPlugin):
recommendations = [] recommendations = []
recommendations.append(('remove_fake_margins', False, recommendations.append(('remove_fake_margins', False,
OptionRecommendation.HIGH)) OptionRecommendation.HIGH))
if DEBUG: if opts.debug_mode:
recommendations.append(('comments', '\n'.join(line for line in build_log), recommendations.append(('comments', '\n'.join(line for line in build_log),
OptionRecommendation.HIGH)) OptionRecommendation.HIGH))
else: else:

213
src/calibre/library/catalogs/epub_mobi_builder.py
View File

@ -3,7 +3,7 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Greg Riker' __copyright__ = '2010, Greg Riker'
import datetime, htmlentitydefs, os, re, shutil, zlib import datetime, htmlentitydefs, os, re, shutil, unicodedata, zlib
from copy import deepcopy from copy import deepcopy
from xml.sax.saxutils import escape from xml.sax.saxutils import escape
@ -15,12 +15,11 @@ from calibre.ptempfile import PersistentTemporaryDirectory
from calibre.utils.config import config_dir from calibre.utils.config import config_dir
from calibre.utils.date import format_date, is_date_undefined, now as nowf from calibre.utils.date import format_date, is_date_undefined, now as nowf
from calibre.utils.filenames import ascii_text from calibre.utils.filenames import ascii_text
from calibre.utils.icu import capitalize from calibre.utils.icu import capitalize, sort_key
from calibre.utils.magick.draw import thumbnail from calibre.utils.magick.draw import thumbnail
from calibre.utils.zipfile import ZipFile from calibre.utils.zipfile import ZipFile
class CatalogBuilder(object): class CatalogBuilder(object):
''' '''
Generates catalog source files from calibre database Generates catalog source files from calibre database
@ -42,6 +41,9 @@ class CatalogBuilder(object):
# [] = No date ranges added # [] = No date ranges added
DATE_RANGE=[30] DATE_RANGE=[30]
# Text used in generated catalog for title section with other-than-ASCII leading letter
SYMBOLS = 'Symbols'
# basename output file basename # basename output file basename
# creator dc:creator in OPF metadata # creator dc:creator in OPF metadata
# descriptionClip limits size of NCX descriptions (Kindle only) # descriptionClip limits size of NCX descriptions (Kindle only)
@ -565,10 +567,9 @@ class CatalogBuilder(object):
self.updateProgressFullStep("Sorting database") self.updateProgressFullStep("Sorting database")
self.booksByAuthor = list(self.booksByTitle) self.booksByAuthor = list(self.booksByTitle)
# Test for author_sort mismatches
self.booksByAuthor = sorted(self.booksByAuthor, key=self.booksByAuthorSorter_author) self.booksByAuthor = sorted(self.booksByAuthor, key=self.booksByAuthorSorter_author)
# Build the unique_authors set from existing data
# Build the unique_authors set from existing data, test for author_sort mismatches
authors = [(record['author'], record['author_sort']) for record in self.booksByAuthor] authors = [(record['author'], record['author_sort']) for record in self.booksByAuthor]
current_author = authors[0] current_author = authors[0]
for (i,author) in enumerate(authors): for (i,author) in enumerate(authors):
@ -603,7 +604,8 @@ Author '{0}':
current_author = author current_author = author
self.booksByAuthor = sorted(self.booksByAuthor, key=self.booksByAuthorSorter_author_sort) self.booksByAuthor = sorted(self.booksByAuthor,
key=lambda x: sort_key(self.booksByAuthorSorter_author_sort(x)))
# Build the unique_authors set from existing data # Build the unique_authors set from existing data
authors = [(record['author'], capitalize(record['author_sort'])) for record in self.booksByAuthor] authors = [(record['author'], capitalize(record['author_sort'])) for record in self.booksByAuthor]
@ -690,7 +692,7 @@ Author '{0}':
this_title['series'] = None this_title['series'] = None
this_title['series_index'] = 0.0 this_title['series_index'] = 0.0
this_title['title_sort'] = self.generateSortTitle(ascii_text(this_title['title'])) this_title['title_sort'] = self.generateSortTitle(this_title['title'])
if 'authors' in record: if 'authors' in record:
# from calibre.ebooks.metadata import authors_to_string # from calibre.ebooks.metadata import authors_to_string
# return authors_to_string(self.authors) # return authors_to_string(self.authors)
@ -705,7 +707,6 @@ Author '{0}':
this_title['author_sort'] = record['author_sort'] this_title['author_sort'] = record['author_sort']
else: else:
this_title['author_sort'] = self.author_to_author_sort(this_title['author']) this_title['author_sort'] = self.author_to_author_sort(this_title['author'])
this_title['author_sort'] = ascii_text(this_title['author_sort'])
if record['publisher']: if record['publisher']:
this_title['publisher'] = re.sub('&', '&', record['publisher']) this_title['publisher'] = re.sub('&', '&', record['publisher'])
@ -780,8 +781,11 @@ Author '{0}':
# Re-sort based on title_sort # Re-sort based on title_sort
if len(titles): if len(titles):
self.booksByTitle = sorted(titles, #self.booksByTitle = sorted(titles,
key=lambda x:(x['title_sort'].upper(), x['title_sort'].upper())) # key=lambda x:(x['title_sort'].upper(), x['title_sort'].upper()))
self.booksByTitle = sorted(titles, key=lambda x: sort_key(x['title_sort'].upper()))
if False and self.verbose: if False and self.verbose:
self.opts.log.info("fetchBooksByTitle(): %d books" % len(self.booksByTitle)) self.opts.log.info("fetchBooksByTitle(): %d books" % len(self.booksByTitle))
self.opts.log.info(" %-40s %-40s" % ('title', 'title_sort')) self.opts.log.info(" %-40s %-40s" % ('title', 'title_sort'))
@ -923,29 +927,24 @@ Author '{0}':
body = soup.find('body') body = soup.find('body')
btc = 0 btc = 0
# Insert section tag pTag = Tag(soup, "p")
pTag['class'] = 'title'
ptc = 0
aTag = Tag(soup,'a') aTag = Tag(soup,'a')
aTag['name'] = 'section_start' aTag['id'] = 'section_start'
body.insert(btc, aTag) pTag.insert(ptc, aTag)
btc += 1 ptc += 1
# Insert the anchor
aTag = Tag(soup, "a")
aTag['name'] = "bytitle"
body.insert(btc, aTag)
btc += 1
if not self.__generateForKindle: if not self.__generateForKindle:
# We don't need this because the Kindle shows section titles # Kindle don't need this because it shows section titles in Periodical format
#<h2><a name="byalphatitle" id="byalphatitle"></a>By Title</h2>
pTag = Tag(soup, "p")
pTag['class'] = 'title'
aTag = Tag(soup, "a") aTag = Tag(soup, "a")
aTag['name'] = "bytitle" aTag['id'] = "bytitle"
pTag.insert(0,aTag) pTag.insert(ptc,aTag)
pTag.insert(1,NavigableString('Titles')) ptc += 1
body.insert(btc,pTag) pTag.insert(ptc,NavigableString('Titles'))
btc += 1
body.insert(btc,pTag)
btc += 1
divTag = Tag(soup, "div") divTag = Tag(soup, "div")
dtc = 0 dtc = 0
@ -955,7 +954,7 @@ Author '{0}':
# Incoming title <series> <series_index>: <title> # Incoming title <series> <series_index>: <title>
if not self.useSeriesPrefixInTitlesSection: if not self.useSeriesPrefixInTitlesSection:
nspt = deepcopy(self.booksByTitle) nspt = deepcopy(self.booksByTitle)
nspt = sorted(nspt, key=lambda x:(x['title_sort'].upper(), x['title_sort'].upper())) nspt = sorted(nspt, key=lambda x: sort_key(x['title_sort'].upper()))
self.booksByTitle_noSeriesPrefix = nspt self.booksByTitle_noSeriesPrefix = nspt
# Loop through the books by title # Loop through the books by title
@ -977,11 +976,14 @@ Author '{0}':
if dtc > 0: if dtc > 0:
divRunningTag['class'] = "initial_letter" divRunningTag['class'] = "initial_letter"
drtc = 0 drtc = 0
current_letter = self.letter_or_symbol(book['title_sort'][0])
pIndexTag = Tag(soup, "p") pIndexTag = Tag(soup, "p")
pIndexTag['class'] = "author_title_letter_index" pIndexTag['class'] = "author_title_letter_index"
aTag = Tag(soup, "a") aTag = Tag(soup, "a")
aTag['name'] = "%s" % self.letter_or_symbol(book['title_sort'][0]) current_letter = self.letter_or_symbol(book['title_sort'][0])
if current_letter == self.SYMBOLS:
aTag['id'] = self.SYMBOLS
else:
aTag['id'] = "%s" % self.generateUnicodeName(current_letter)
pIndexTag.insert(0,aTag) pIndexTag.insert(0,aTag)
pIndexTag.insert(1,NavigableString(self.letter_or_symbol(book['title_sort'][0]))) pIndexTag.insert(1,NavigableString(self.letter_or_symbol(book['title_sort'][0])))
divRunningTag.insert(dtc,pIndexTag) divRunningTag.insert(dtc,pIndexTag)
@ -1074,19 +1076,6 @@ Author '{0}':
btc = 0 btc = 0
# Insert section tag
aTag = Tag(soup,'a')
aTag['name'] = 'section_start'
body.insert(btc, aTag)
btc += 1
# Insert the anchor
aTag = Tag(soup, "a")
anchor_name = friendly_name.lower()
aTag['name'] = anchor_name.replace(" ","")
body.insert(btc, aTag)
btc += 1
divTag = Tag(soup, "div") divTag = Tag(soup, "div")
dtc = 0 dtc = 0
divOpeningTag = None divOpeningTag = None
@ -1117,7 +1106,6 @@ Author '{0}':
drtc = 0 drtc = 0
divRunningTag = None divRunningTag = None
current_letter = self.letter_or_symbol(book['author_sort'][0].upper())
author_count = 0 author_count = 0
divOpeningTag = Tag(soup, 'div') divOpeningTag = Tag(soup, 'div')
if dtc > 0: if dtc > 0:
@ -1126,7 +1114,11 @@ Author '{0}':
pIndexTag = Tag(soup, "p") pIndexTag = Tag(soup, "p")
pIndexTag['class'] = "author_title_letter_index" pIndexTag['class'] = "author_title_letter_index"
aTag = Tag(soup, "a") aTag = Tag(soup, "a")
aTag['name'] = "%sauthors" % self.letter_or_symbol(current_letter) current_letter = self.letter_or_symbol(book['author_sort'][0].upper())
if current_letter == self.SYMBOLS:
aTag['id'] = self.SYMBOLS
else:
aTag['id'] = "%s_authors" % self.generateUnicodeName(current_letter)
pIndexTag.insert(0,aTag) pIndexTag.insert(0,aTag)
pIndexTag.insert(1,NavigableString(self.letter_or_symbol(book['author_sort'][0].upper()))) pIndexTag.insert(1,NavigableString(self.letter_or_symbol(book['author_sort'][0].upper())))
divOpeningTag.insert(dotc,pIndexTag) divOpeningTag.insert(dotc,pIndexTag)
@ -1158,7 +1150,7 @@ Author '{0}':
pAuthorTag = Tag(soup, "p") pAuthorTag = Tag(soup, "p")
pAuthorTag['class'] = "author_index" pAuthorTag['class'] = "author_index"
aTag = Tag(soup, "a") aTag = Tag(soup, "a")
aTag['name'] = "%s" % self.generateAuthorAnchor(current_author) aTag['id'] = "%s" % self.generateAuthorAnchor(current_author)
aTag.insert(0,NavigableString(current_author)) aTag.insert(0,NavigableString(current_author))
pAuthorTag.insert(0,aTag) pAuthorTag.insert(0,aTag)
if author_count == 1: if author_count == 1:
@ -1247,19 +1239,25 @@ Author '{0}':
# Loop ends here # Loop ends here
pTag = Tag(soup, "p")
pTag['class'] = 'title'
ptc = 0
aTag = Tag(soup,'a')
aTag['id'] = 'section_start'
pTag.insert(ptc, aTag)
ptc += 1
if not self.__generateForKindle: if not self.__generateForKindle:
# Insert the <h2> tag with book_count at the head # Kindle don't need this because it shows section titles in Periodical format
#<h2><a name="byalphaauthor" id="byalphaauthor"></a>By Author</h2>
pTag = Tag(soup, "p")
pTag['class'] = 'title'
aTag = Tag(soup, "a") aTag = Tag(soup, "a")
anchor_name = friendly_name.lower() anchor_name = friendly_name.lower()
aTag['name'] = anchor_name.replace(" ","") aTag['id'] = anchor_name.replace(" ","")
pTag.insert(0,aTag) pTag.insert(ptc,aTag)
#h2Tag.insert(1,NavigableString('%s (%d)' % (friendly_name, book_count))) ptc += 1
pTag.insert(1,NavigableString('%s' % (friendly_name))) pTag.insert(ptc,NavigableString('%s' % (friendly_name)))
body.insert(btc,pTag)
btc += 1 body.insert(btc,pTag)
btc += 1
if author_count == 1: if author_count == 1:
divTag.insert(dtc, divOpeningTag) divTag.insert(dtc, divOpeningTag)
@ -1294,7 +1292,7 @@ Author '{0}':
pIndexTag = Tag(soup, "p") pIndexTag = Tag(soup, "p")
pIndexTag['class'] = "date_index" pIndexTag['class'] = "date_index"
aTag = Tag(soup, "a") aTag = Tag(soup, "a")
aTag['name'] = "bda_%s-%s" % (current_date.year, current_date.month) aTag['id'] = "bda_%s-%s" % (current_date.year, current_date.month)
pIndexTag.insert(0,aTag) pIndexTag.insert(0,aTag)
pIndexTag.insert(1,NavigableString(date_string)) pIndexTag.insert(1,NavigableString(date_string))
divTag.insert(dtc,pIndexTag) divTag.insert(dtc,pIndexTag)
@ -1312,7 +1310,7 @@ Author '{0}':
pAuthorTag['class'] = "author_index" pAuthorTag['class'] = "author_index"
aTag = Tag(soup, "a") aTag = Tag(soup, "a")
if self.opts.generate_authors: if self.opts.generate_authors:
aTag['name'] = "%s" % self.generateAuthorAnchor(current_author) aTag['id'] = "%s" % self.generateAuthorAnchor(current_author)
aTag.insert(0,NavigableString(current_author)) aTag.insert(0,NavigableString(current_author))
pAuthorTag.insert(0,aTag) pAuthorTag.insert(0,aTag)
divTag.insert(dtc,pAuthorTag) divTag.insert(dtc,pAuthorTag)
@ -1386,7 +1384,7 @@ Author '{0}':
pIndexTag = Tag(soup, "p") pIndexTag = Tag(soup, "p")
pIndexTag['class'] = "date_index" pIndexTag['class'] = "date_index"
aTag = Tag(soup, "a") aTag = Tag(soup, "a")
aTag['name'] = "bda_%s" % date_range.replace(' ','') aTag['id'] = "bda_%s" % date_range.replace(' ','')
pIndexTag.insert(0,aTag) pIndexTag.insert(0,aTag)
pIndexTag.insert(1,NavigableString(date_range)) pIndexTag.insert(1,NavigableString(date_range))
divTag.insert(dtc,pIndexTag) divTag.insert(dtc,pIndexTag)
@ -1457,30 +1455,27 @@ Author '{0}':
btc = 0 btc = 0
# Insert section tag pTag = Tag(soup, "p")
aTag = Tag(soup,'a') pTag['class'] = 'title'
aTag['name'] = 'section_start' ptc = 0
body.insert(btc, aTag)
btc += 1
# Insert the anchor aTag = Tag(soup,'a')
aTag = Tag(soup, "a") aTag['id'] = 'section_start'
anchor_name = friendly_name.lower() pTag.insert(ptc, aTag)
aTag['name'] = anchor_name.replace(" ","") ptc += 1
body.insert(btc, aTag)
btc += 1
if not self.__generateForKindle: if not self.__generateForKindle:
#<h2><a name="byalphaauthor" id="byalphaauthor"></a>By Author</h2> # Kindle don't need this because it shows section titles in Periodical format
pTag = Tag(soup, "p")
pTag['class'] = 'title'
aTag = Tag(soup, "a") aTag = Tag(soup, "a")
anchor_name = friendly_name.lower() anchor_name = friendly_name.lower()
aTag['name'] = anchor_name.replace(" ","") aTag['id'] = anchor_name.replace(" ","")
pTag.insert(0,aTag)
pTag.insert(1,NavigableString('%s' % friendly_name)) pTag.insert(ptc,aTag)
body.insert(btc,pTag) ptc += 1
btc += 1 pTag.insert(ptc, NavigableString('%s' % friendly_name))
body.insert(btc,pTag)
btc += 1
divTag = Tag(soup, "div") divTag = Tag(soup, "div")
dtc = 0 dtc = 0
@ -1895,11 +1890,10 @@ Author '{0}':
self.updateProgressFullStep("'Genres'") self.updateProgressFullStep("'Genres'")
self.genre_tags_dict = self.filterDbTags(self.db.all_tags()) self.genre_tags_dict = self.filterDbTags(self.db.all_tags())
# Extract books matching filtered_tags # Extract books matching filtered_tags
genre_list = [] genre_list = []
for friendly_tag in sorted(self.genre_tags_dict): for friendly_tag in sorted(self.genre_tags_dict, key=sort_key):
#print "\ngenerateHTMLByTags(): looking for books with friendly_tag '%s'" % friendly_tag #print("\ngenerateHTMLByTags(): looking for books with friendly_tag '%s'" % friendly_tag)
# tag_list => { normalized_genre_tag : [{book},{},{}], # tag_list => { normalized_genre_tag : [{book},{},{}],
# normalized_genre_tag : [{book},{},{}] } # normalized_genre_tag : [{book},{},{}] }
@ -2268,7 +2262,7 @@ Author '{0}':
navPointTag.insert(1, contentTag) navPointTag.insert(1, contentTag)
cmiTag = Tag(soup, '%s' % 'calibre:meta-img') cmiTag = Tag(soup, '%s' % 'calibre:meta-img')
cmiTag['name'] = "mastheadImage" cmiTag['id'] = "mastheadImage"
cmiTag['src'] = "images/mastheadImage.gif" cmiTag['src'] = "images/mastheadImage.gif"
navPointTag.insert(2,cmiTag) navPointTag.insert(2,cmiTag)
navMapTag.insert(0,navPointTag) navMapTag.insert(0,navPointTag)
@ -2552,7 +2546,10 @@ Author '{0}':
navLabelTag.insert(0, textTag) navLabelTag.insert(0, textTag)
navPointByLetterTag.insert(0,navLabelTag) navPointByLetterTag.insert(0,navLabelTag)
contentTag = Tag(soup, 'content') contentTag = Tag(soup, 'content')
contentTag['src'] = "content/%s.html#%s" % (output, title_letters[i]) if title_letters[i] == self.SYMBOLS:
contentTag['src'] = "content/%s.html#%s" % (output, title_letters[i])
else:
contentTag['src'] = "content/%s.html#%s" % (output, self.generateUnicodeName(title_letters[i]))
navPointByLetterTag.insert(1,contentTag) navPointByLetterTag.insert(1,contentTag)
if self.generateForKindle: if self.generateForKindle:
@ -2640,7 +2637,7 @@ Author '{0}':
navLabelTag.insert(0, textTag) navLabelTag.insert(0, textTag)
navPointByLetterTag.insert(0,navLabelTag) navPointByLetterTag.insert(0,navLabelTag)
contentTag = Tag(soup, 'content') contentTag = Tag(soup, 'content')
contentTag['src'] = "%s#%sauthors" % (HTML_file, authors_by_letter[1]) contentTag['src'] = "%s#%s_authors" % (HTML_file, self.generateUnicodeName(authors_by_letter[1]))
navPointByLetterTag.insert(1,contentTag) navPointByLetterTag.insert(1,contentTag)
@ -3213,7 +3210,7 @@ Author '{0}':
ans = '%s%d %s:\n' % (' ' * indent, len(tags), header) ans = '%s%d %s:\n' % (' ' * indent, len(tags), header)
ans += ' ' * (indent + 1) ans += ' ' * (indent + 1)
out_str = '' out_str = ''
sorted_tags = sorted(tags) sorted_tags = sorted(tags, key=sort_key)
for tag in next_tag(sorted_tags): for tag in next_tag(sorted_tags):
out_str += tag out_str += tag
if len(out_str) >= line_break: if len(out_str) >= line_break:
@ -3234,7 +3231,7 @@ Author '{0}':
if tag == ' ': if tag == ' ':
continue continue
normalized_tags.append(re.sub('\W','',tag).lower()) normalized_tags.append(re.sub('\W','',ascii_text(tag)).lower())
friendly_tags.append(tag) friendly_tags.append(tag)
genre_tags_dict = dict(zip(friendly_tags,normalized_tags)) genre_tags_dict = dict(zip(friendly_tags,normalized_tags))
@ -3293,18 +3290,24 @@ Author '{0}':
body = soup.find('body') body = soup.find('body')
btc = 0 btc = 0
divTag = Tag(soup, 'div')
dtc = 0
# Insert section tag if this is the section start - first article only # Insert section tag if this is the section start - first article only
if section_head: if section_head:
aTag = Tag(soup,'a') aTag = Tag(soup,'a')
aTag['name'] = 'section_start' aTag['id'] = 'section_start'
body.insert(btc, aTag) divTag.insert(dtc, aTag)
btc += 1 dtc += 1
#body.insert(btc, aTag)
#btc += 1
# Create an anchor from the tag # Create an anchor from the tag
aTag = Tag(soup, 'a') aTag = Tag(soup, 'a')
aTag['name'] = "Genre_%s" % genre aTag['id'] = "Genre_%s" % genre
body.insert(btc,aTag) divTag.insert(dtc, aTag)
body.insert(btc,divTag)
btc += 1 btc += 1
titleTag = body.find(attrs={'class':'title'}) titleTag = body.find(attrs={'class':'title'})
@ -3477,7 +3480,7 @@ Author '{0}':
for (i, tag) in enumerate(sorted(book.get('tags', []))): for (i, tag) in enumerate(sorted(book.get('tags', []))):
aTag = Tag(_soup,'a') aTag = Tag(_soup,'a')
if self.opts.generate_genres: if self.opts.generate_genres:
aTag['href'] = "Genre_%s.html" % re.sub("\W","",tag.lower()) aTag['href'] = "Genre_%s.html" % re.sub("\W","",ascii_text(tag).lower())
aTag.insert(0,escape(NavigableString(tag))) aTag.insert(0,escape(NavigableString(tag)))
genresTag.insert(gtc, aTag) genresTag.insert(gtc, aTag)
gtc += 1 gtc += 1
@ -3544,8 +3547,10 @@ Author '{0}':
btc = 0 btc = 0
# Insert the title anchor for inbound links # Insert the title anchor for inbound links
aTag = Tag(soup, "a") aTag = Tag(soup, "a")
aTag['name'] = "book%d" % int(book['id']) aTag['id'] = "book%d" % int(book['id'])
body.insert(btc, aTag) divTag = Tag(soup, 'div')
divTag.insert(0, aTag)
body.insert(btc, divTag)
btc += 1 btc += 1
# Insert the link to the series or remove <a class="series"> # Insert the link to the series or remove <a class="series">
@ -3770,7 +3775,7 @@ Author '{0}':
else: else:
word = '%10.0f' % (float(word)) word = '%10.0f' % (float(word))
translated.append(word) translated.append(word)
return ascii_text(' '.join(translated)) return ' '.join(translated)
def generateThumbnail(self, title, image_dir, thumb_file): def generateThumbnail(self, title, image_dir, thumb_file):
''' '''
@ -3824,6 +3829,14 @@ Author '{0}':
with zf: with zf:
zf.writestr(title['uuid']+cover_crc, thumb_data) zf.writestr(title['uuid']+cover_crc, thumb_data)
def generateUnicodeName(self, c):
'''
Generate an anchor name string
'''
fullname = unicodedata.name(unicode(c))
terms = fullname.split()
return "_".join(terms)
def getFriendlyGenreTag(self, genre): def getFriendlyGenreTag(self, genre):
# Find the first instance of friendly_tag matching genre # Find the first instance of friendly_tag matching genre
for friendly_tag in self.genre_tags_dict: for friendly_tag in self.genre_tags_dict:
@ -3837,8 +3850,8 @@ Author '{0}':
return markerTags return markerTags
def letter_or_symbol(self,char): def letter_or_symbol(self,char):
if not re.search('[a-zA-Z]',char): if not re.search('[a-zA-Z]', ascii_text(char)):
return 'Symbols' return self.SYMBOLS
else: else:
return char return char