Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

...

Browse Source
This commit is contained in:
Kovid Goyal 2011-02-07 09:41:15 -07:00
commit fbe65b78bd
2 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/calibre/ebooks/conversion/preprocess.py
View File

@ -245,17 +245,17 @@ class Dehyphenator(object):
self.html = html self.html = html
self.format = format self.format = format
if format == 'html': if format == 'html':
intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)\s*(?=<)(?P<wraptags>(</span>)?\s*(</[iubp]>\s*){1,2}(?P<up2threeblanks><(p|div)[^>]*>\s*(<p[^>]*>\s*</p>\s*)?</(p|div)>\s+){0,3}\s*(<[iubp][^>]*>\s*){1,2}(<span[^>]*>)?)\s*(?P<secondpart>[\w\d]+)' % length) intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\W\-]+)(-|‐)\s*(?=<)(?P<wraptags>(</span>)?\s*(</[iubp]>\s*){1,2}(?P<up2threeblanks><(p|div)[^>]*>\s*(<p[^>]*>\s*</p>\s*)?</(p|div)>\s+){0,3}\s*(<[iubp][^>]*>\s*){1,2}(<span[^>]*>)?)\s*(?P<secondpart>[\w\d]+)' % length)
elif format == 'pdf': elif format == 'pdf':
intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)\s*(?P<wraptags><p>|</[iub]>\s*<p>\s*<[iub]>)\s*(?P<secondpart>[\w\d]+)'% length) intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\W\-]+)(-|‐)\s*(?P<wraptags><p>|</[iub]>\s*<p>\s*<[iub]>)\s*(?P<secondpart>[\w\d]+)'% length)
elif format == 'txt': elif format == 'txt':
intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)(\u0020|\u0009)*(?P<wraptags>(\n(\u0020|\u0009)*)+)(?P<secondpart>[\w\d]+)'% length) intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\W\-]+)(-|‐)(\u0020|\u0009)*(?P<wraptags>(\n(\u0020|\u0009)*)+)(?P<secondpart>[\w\d]+)'% length)
elif format == 'individual_words': elif format == 'individual_words':
intextmatch = re.compile(u'(?!<)(?P<firstpart>\w+)(-|‐)\s*(?P<secondpart>\w+)(?![^<]*?>)') intextmatch = re.compile(u'(?!<)(?P<firstpart>[^\W\-]+)(-|‐)\s*(?P<secondpart>\w+)(?![^<]*?>)')
elif format == 'html_cleanup': elif format == 'html_cleanup':
intextmatch = re.compile(u'(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)\s*(?=<)(?P<wraptags></span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*(?P<secondpart>[\w\d]+)') intextmatch = re.compile(u'(?P<firstpart>[^\W\-]+)(-|‐)\s*(?=<)(?P<wraptags></span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*(?P<secondpart>[\w\d]+)')
elif format == 'txt_cleanup': elif format == 'txt_cleanup':
intextmatch = re.compile(u'(?P<firstpart>\w+)(-|‐)(?P<wraptags>\s+)(?P<secondpart>[\w\d]+)') intextmatch = re.compile(u'(?P<firstpart>[^\W\-]+)(-|‐)(?P<wraptags>\s+)(?P<secondpart>[\w\d]+)')
html = intextmatch.sub(self.dehyphenate, html) html = intextmatch.sub(self.dehyphenate, html)

4
src/calibre/ebooks/conversion/utils.py
View File

@ -34,6 +34,8 @@ class HeuristicProcessor(object):
self.line_close = "(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>" self.line_close = "(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>"
self.single_blank = re.compile(r'(\s*<p[^>]*>\s*</p>)', re.IGNORECASE) self.single_blank = re.compile(r'(\s*<p[^>]*>\s*</p>)', re.IGNORECASE)
self.scene_break_open = '<p class="scenebreak" style="text-align:center; text-indent:0%; margin-top:1em; margin-bottom:1em; page-break-before:avoid">' self.scene_break_open = '<p class="scenebreak" style="text-align:center; text-indent:0%; margin-top:1em; margin-bottom:1em; page-break-before:avoid">'
self.common_in_text_endings = u'[\"\'—’”,\.!\?\…\)„\w]'
self.common_in_text_beginnings = u'[\w\'\"“‘‛]'
def is_pdftohtml(self, src): def is_pdftohtml(self, src):
return '<!-- created by calibre\'s pdftohtml -->' in src[:1000] return '<!-- created by calibre\'s pdftohtml -->' in src[:1000]
@ -638,7 +640,7 @@ class HeuristicProcessor(object):
blanks_count = len(self.any_multi_blank.findall(html)) blanks_count = len(self.any_multi_blank.findall(html))
if blanks_count >= 1: if blanks_count >= 1:
html = self.merge_blanks(html, blanks_count) html = self.merge_blanks(html, blanks_count)
scene_break_regex = self.line_open+'(?![\w\'\"])(?P<break>((?P<break_char>((?!\s)\W))\s*(?P=break_char)?)+)\s*'+self.line_close scene_break_regex = self.line_open+'(?!('+self.common_in_text_beginnings+'|.*?'+self.common_in_text_endings+'<))(?P<break>((?P<break_char>((?!\s)\W))\s*(?P=break_char)?)+)\s*'+self.line_close
scene_break = re.compile(r'%s' % scene_break_regex, re.IGNORECASE|re.UNICODE) scene_break = re.compile(r'%s' % scene_break_regex, re.IGNORECASE|re.UNICODE)
# If the user has enabled scene break replacement, then either softbreaks # If the user has enabled scene break replacement, then either softbreaks
# or 'hard' scene breaks are replaced, depending on which is in use # or 'hard' scene breaks are replaced, depending on which is in use