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

expanded comments

Browse Source
This commit is contained in:
Lee 2012-04-21 00:52:13 +08:00
parent 9217e6bed3
commit 740c812de2
1 changed files with 9 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -316,9 +316,17 @@ class HeuristicProcessor(object):
''' '''
Unwraps lines based on line length and punctuation Unwraps lines based on line length and punctuation
supports a range of html markup and text files supports a range of html markup and text files
'''
# define the pieces of the regex
the lookahead regex below is meant look for any non-full stop characters - punctuation
characters which can be used as a full stop should *not* be added below - e.g. ?!“”. etc
the reason for this is to prevent false positive wrapping. False positives are more
difficult to detect than false negatives during a manual review of the doc
This function intentionally leaves hyphenated content alone as that is handled by the
dehyphenate routine in a future step
'''
# define the pieces of the regex
lookahead = "(?<=.{"+str(length)+u"}([a-zäëïöüàèìòùáćéíĺóŕńśúýâêîôûçąężıãõñæøþðßěľščťžňďřů,:)\IA\u00DF]|(?<!\&\w{4});))" # (?<!\&\w{4});) is a semicolon not part of an entity lookahead = "(?<=.{"+str(length)+u"}([a-zäëïöüàèìòùáćéíĺóŕńśúýâêîôûçąężıãõñæøþðßěľščťžňďřů,:)\IA\u00DF]|(?<!\&\w{4});))" # (?<!\&\w{4});) is a semicolon not part of an entity
em_en_lookahead = "(?<=.{"+str(length)+u"}[\u2013\u2014])" em_en_lookahead = "(?<=.{"+str(length)+u"}[\u2013\u2014])"
soft_hyphen = u"\xad" soft_hyphen = u"\xad"