Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix use of UTF-8 raw string

Browse Source
This commit is contained in:
Kovid Goyal 2010-09-17 10:42:11 -06:00
parent cc3082135b
commit ffe8fe5fd2
2 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/calibre/ebooks/conversion/preprocess.py
View File

@ -144,7 +144,6 @@ class HTMLPreProcessor(object):
# Fix pdftohtml markup # Fix pdftohtml markup
PDFTOHTML = [ PDFTOHTML = [
# Fix umlauts # Fix umlauts
# ¨
(re.compile(u'¨\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'ä'), (re.compile(u'¨\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'ä'),
(re.compile(u'¨\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'Ä'), (re.compile(u'¨\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'Ä'),
(re.compile(u'¨\s*(<br.*?>)*\s*e', re.UNICODE), lambda match: u'ë'), (re.compile(u'¨\s*(<br.*?>)*\s*e', re.UNICODE), lambda match: u'ë'),

6
src/calibre/ebooks/conversion/utils.py
View File

@ -176,8 +176,8 @@ class PreProcessor(object):
self.log("*** Median line length is " + str(length) + ", calculated with " + format + " format ***") self.log("*** Median line length is " + str(length) + ", calculated with " + format + " format ***")
# #
# Unwrap and/or delete soft-hyphens, hyphens # Unwrap and/or delete soft-hyphens, hyphens
html = re.sub(u'­\s*(</span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*', '', html) html = re.sub(u'\xad\s*(</span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*', '', html)
html = re.sub(u'(?<=[-–—])\s*(?=<)(</span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*(?=[[a-z\d])', '', html) html = re.sub(u'(?<=[-\u2013\u2014])\s*(?=<)(</span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*(?=[[a-z\d])', '', html)
# Unwrap lines using punctation and line length # Unwrap lines using punctation and line length
unwrap = re.compile(r"(?<=.{%i}([a-z,;):\IA]|(?<!\&\w{4});))\s*</(span|p|div)>\s*(</(p|span|div)>)?\s*(?P<up2threeblanks><(p|span|div)[^>]*>\s*(<(p|span|div)[^>]*>\s*</(span|p|div)>\s*)</(span|p|div)>\s*){0,3}\s*<(span|div|p)[^>]*>\s*(<(span|div|p)[^>]*>)?\s*" % length, re.UNICODE) unwrap = re.compile(r"(?<=.{%i}([a-z,;):\IA]|(?<!\&\w{4});))\s*</(span|p|div)>\s*(</(p|span|div)>)?\s*(?P<up2threeblanks><(p|span|div)[^>]*>\s*(<(p|span|div)[^>]*>\s*</(span|p|div)>\s*)</(span|p|div)>\s*){0,3}\s*<(span|div|p)[^>]*>\s*(<(span|div|p)[^>]*>)?\s*" % length, re.UNICODE)
@ -195,6 +195,6 @@ class PreProcessor(object):
html = doubleheading.sub('\g<firsthead>'+'\n<h3'+'\g<secondhead>'+'</h3>', html) html = doubleheading.sub('\g<firsthead>'+'\n<h3'+'\g<secondhead>'+'</h3>', html)
# put back non-breaking spaces in empty paragraphs to preserve original formatting # put back non-breaking spaces in empty paragraphs to preserve original formatting
html = blankreg.sub('\n'+'\g<openline>'+' '+'\g<closeline>', html) html = blankreg.sub('\n'+r'\g<openline>'+u'\u00a0'+r'\g<closeline>', html)
return html return html