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

...

Browse Source
This commit is contained in:
Kovid Goyal 2011-01-06 19:25:52 -07:00
commit 0e7eab2d1e
8 changed files with 38 additions and 134 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/calibre/ebooks/conversion/preprocess.py
View File

@ -51,16 +51,16 @@ def chap_head(match):
chap = match.group('chap')
title = match.group('title')
if not title:
return '<h1>'+chap+'</h1><br/>\n'
return '<h1>'+chap+'</h1><br/>\n'
else:
return '<h1>'+chap+'</h1>\n<h3>'+title+'</h3>\n'
return '<h1>'+chap+'</h1>\n<h3>'+title+'</h3>\n'
def wrap_lines(match):
ital = match.group('ital')
if not ital:
return ' '
return ' '
else:
return ital+' '
return ital+' '
class DocAnalysis(object):
'''
@ -191,7 +191,7 @@ class Dehyphenator(object):
dehyphenated = unicode(firsthalf) + unicode(secondhalf)
lookupword = self.removesuffixes.sub('', dehyphenated)
if self.prefixes.match(firsthalf) is None:
lookupword = self.removeprefix.sub('', lookupword)
lookupword = self.removeprefix.sub('', lookupword)
#print "lookup word is: "+str(lookupword)+", orig is: " + str(hyphenated)
try:
searchresult = self.html.find(lookupword.lower())

40
src/calibre/ebooks/conversion/utils.py
View File

@ -113,24 +113,24 @@ class PreProcessor(object):
# some lit files don't have any <p> tags or equivalent (generally just plain text between
# <pre> tags), check and mark up line endings if required before proceeding
if self.no_markup(html, 0.1):
self.log("not enough paragraph markers, adding now")
# check if content is in pre tags, use txt processor to mark up if so
pre = re.compile(r'<pre>', re.IGNORECASE)
if len(pre.findall(html)) == 1:
self.log("Running Text Processing")
from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \
separate_paragraphs_single_line
outerhtml = re.compile(r'.*?(?<=<pre>)(?P<text>.*)(?=</pre>).*', re.IGNORECASE|re.DOTALL)
html = outerhtml.sub('\g<text>', html)
html = separate_paragraphs_single_line(html)
html = preserve_spaces(html)
html = convert_basic(html, epub_split_size_kb=0)
else:
# Add markup naively
# TODO - find out if there are cases where there are more than one <pre> tag or
# other types of unmarked html and handle them in some better fashion
add_markup = re.compile('(?<!>)(\n)')
html = add_markup.sub('</p>\n<p>', html)
self.log("not enough paragraph markers, adding now")
# check if content is in pre tags, use txt processor to mark up if so
pre = re.compile(r'<pre>', re.IGNORECASE)
if len(pre.findall(html)) == 1:
self.log("Running Text Processing")
from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \
separate_paragraphs_single_line
outerhtml = re.compile(r'.*?(?<=<pre>)(?P<text>.*)(?=</pre>).*', re.IGNORECASE|re.DOTALL)
html = outerhtml.sub('\g<text>', html)
html = separate_paragraphs_single_line(html)
html = preserve_spaces(html)
html = convert_basic(html, epub_split_size_kb=0)
else:
# Add markup naively
# TODO - find out if there are cases where there are more than one <pre> tag or
# other types of unmarked html and handle them in some better fashion
add_markup = re.compile('(?<!>)(\n)')
html = add_markup.sub('</p>\n<p>', html)
###### Mark Indents/Cleanup ######
#
@ -164,8 +164,8 @@ class PreProcessor(object):
self.log("deleting blank lines")
html = blankreg.sub('', html)
elif float(len(blanklines)) / float(len(lines)) > 0.40:
blanks_between_paragraphs = True
#print "blanks between paragraphs is marked True"
blanks_between_paragraphs = True
#print "blanks between paragraphs is marked True"
else:
blanks_between_paragraphs = False
#self.dump(html, 'before_chapter_markup')

2
src/calibre/ebooks/fb2/fb2ml.py
View File

@ -173,7 +173,7 @@ class FB2MLizer(object):
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 self.oeb_book.metadata.cover and unicode(self.oeb_book.metadata.cover[0]) in self.oeb_book.manifest.ids:
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:

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

@ -6,7 +6,7 @@ __docformat__ = 'restructuredtext en'
import os
from calibre.customize.conversion import InputFormatPlugin, OptionRecommendation
from calibre.customize.conversion import InputFormatPlugin
from calibre.ebooks.pdb.header import PdbHeaderReader
from calibre.ebooks.pdb import PDBError, IDENTITY_TO_NAME, get_reader
from calibre.ebooks.conversion.utils import PreProcessor
@ -18,30 +18,6 @@ class PDBInput(InputFormatPlugin):
description = 'Convert PDB to HTML'
file_types = set(['pdb'])
options = set([
OptionRecommendation(name='paragraph_type', recommended_value='auto',
choices=['auto', 'block', 'single', 'print'],
help=_('Paragraph structure.\n'
'choices are [\'auto\', \'block\', \'single\', \'print\', \'markdown\']\n'
'* auto: Try to auto detect paragraph type.\n'
'* block: Treat a blank line as a paragraph break.\n'
'* single: Assume every line is a paragraph.\n'
'* print: Assume every line starting with 2+ spaces or a tab '
'starts a paragraph.')),
OptionRecommendation(name='formatting_type', recommended_value='auto',
choices=['auto', 'none', 'markdown'],
help=_('Formatting used within the document.'
'* auto: Try to auto detect the document formatting.\n'
'* none: Do not modify the paragraph formatting. Everything is a paragraph.\n'
'* markdown: Run the input though the markdown pre-processor. '
'To learn more about markdown see')+' http://daringfireball.net/projects/markdown/'),
OptionRecommendation(name='preserve_spaces', recommended_value=False,
help=_('Normally extra spaces are condensed into a single space. '
'With this option all spaces will be displayed.')),
OptionRecommendation(name="markdown_disable_toc", recommended_value=False,
help=_('Do not insert a Table of Contents into the output text.')),
])
def convert(self, stream, options, file_ext, log,
accelerators):
header = PdbHeaderReader(stream)
@ -60,4 +36,4 @@ class PDBInput(InputFormatPlugin):
def preprocess_html(self, options, html):
self.options = options
preprocessor = PreProcessor(self.options, log=getattr(self, 'log', None))
return preprocessor(html)
return preprocessor(html)

16
src/calibre/ebooks/pdb/pdf/reader.py
View File

@ -19,9 +19,6 @@ class Reader(FormatReader):
self.stream = stream
self.log = log
self.options = options
setattr(self.options, 'new_pdf_engine', False)
setattr(self.options, 'no_images', False)
setattr(self.options, 'unwrap_factor', 0.45)
def extract_content(self, output_dir):
self.log.info('Extracting PDF...')
@ -31,7 +28,12 @@ class Reader(FormatReader):
for x in xrange(self.header.section_count()):
pdf.write(self.header.section_data(x))
from calibre.customize.ui import plugin_for_input_format
pdf.seek(0)
return plugin_for_input_format('pdf').convert(pdf, self.options,
'pdf', self.log, [])
from calibre.customize.ui import plugin_for_input_format
pdf_plugin = plugin_for_input_format('pdf')
for option in pdf_plugin.options:
if not hasattr(self.options, option.option.name):
setattr(self.options, option.name, option.recommended_value)
pdf.seek(0)
return pdf_plugin.convert(pdf, self.options, 'pdf', self.log, {})

26
src/calibre/ebooks/tcr/input.py
View File

@ -6,7 +6,7 @@ __docformat__ = 'restructuredtext en'
from cStringIO import StringIO
from calibre.customize.conversion import InputFormatPlugin, OptionRecommendation
from calibre.customize.conversion import InputFormatPlugin
from calibre.ebooks.compression.tcr import decompress
class TCRInput(InputFormatPlugin):
@ -16,30 +16,6 @@ class TCRInput(InputFormatPlugin):
description = 'Convert TCR files to HTML'
file_types = set(['tcr'])
options = set([
OptionRecommendation(name='paragraph_type', recommended_value='auto',
choices=['auto', 'block', 'single', 'print'],
help=_('Paragraph structure.\n'
'choices are [\'auto\', \'block\', \'single\', \'print\', \'markdown\']\n'
'* auto: Try to auto detect paragraph type.\n'
'* block: Treat a blank line as a paragraph break.\n'
'* single: Assume every line is a paragraph.\n'
'* print: Assume every line starting with 2+ spaces or a tab '
'starts a paragraph.')),
OptionRecommendation(name='formatting_type', recommended_value='auto',
choices=['auto', 'none', 'markdown'],
help=_('Formatting used within the document.'
'* auto: Try to auto detect the document formatting.\n'
'* none: Do not modify the paragraph formatting. Everything is a paragraph.\n'
'* markdown: Run the input though the markdown pre-processor. '
'To learn more about markdown see')+' http://daringfireball.net/projects/markdown/'),
OptionRecommendation(name='preserve_spaces', recommended_value=False,
help=_('Normally extra spaces are condensed into a single space. '
'With this option all spaces will be displayed.')),
OptionRecommendation(name="markdown_disable_toc", recommended_value=False,
help=_('Do not insert a Table of Contents into the output text.')),
])
def convert(self, stream, options, file_ext, log, accelerators):
log.info('Decompressing text...')
raw_txt = decompress(stream)

25
src/calibre/gui2/convert/pdb_input.py
View File

@ -1,25 +0,0 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
from calibre.gui2.convert.txt_input_ui import Ui_Form
from calibre.gui2.convert import Widget
class PluginWidget(Widget, Ui_Form):
TITLE = _('PDB Input')
HELP = _('Options specific to')+' PDB '+_('input')
COMMIT_NAME = 'pdb_input'
ICON = I('mimetypes/txt.png')
def __init__(self, parent, get_option, get_help, db=None, book_id=None):
Widget.__init__(self, parent,
['paragraph_type', 'formatting_type', 'markdown_disable_toc', 'preserve_spaces'])
self.db, self.book_id = db, book_id
for x in get_option('paragraph_type').option.choices:
self.opt_paragraph_type.addItem(x)
for x in get_option('formatting_type').option.choices:
self.opt_formatting_type.addItem(x)
self.initialize_options(get_option, get_help, db, book_id)

25
src/calibre/gui2/convert/tcr_input.py
View File

@ -1,25 +0,0 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
from calibre.gui2.convert.txt_input_ui import Ui_Form
from calibre.gui2.convert import Widget
class PluginWidget(Widget, Ui_Form):
TITLE = _('TCR Input')
HELP = _('Options specific to')+' TCR '+_('input')
COMMIT_NAME = 'tcr_input'
ICON = I('mimetypes/txt.png')
def __init__(self, parent, get_option, get_help, db=None, book_id=None):
Widget.__init__(self, parent,
['paragraph_type', 'formatting_type', 'markdown_disable_toc', 'preserve_spaces'])
self.db, self.book_id = db, book_id
for x in get_option('paragraph_type').option.choices:
self.opt_paragraph_type.addItem(x)
for x in get_option('formatting_type').option.choices:
self.opt_formatting_type.addItem(x)
self.initialize_options(get_option, get_help, db, book_id)