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

removed dash unwrap regression from bug #822744

Browse Source
This commit is contained in:
Lee 2012-04-20 21:52:57 +08:00
parent f9efe4995a
commit a6efef3d31
1 changed files with 0 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/calibre/ebooks/conversion/utils.py
View File

@ -322,7 +322,6 @@ class HeuristicProcessor(object):
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"
dash = u"\x2d" # some ocrs doesn't convert dashes to hyphens
line_ending = "\s*</(span|[iubp]|div)>\s*(</(span|[iubp]|div)>)?" line_ending = "\s*</(span|[iubp]|div)>\s*(</(span|[iubp]|div)>)?"
blanklines = "\s*(?P<up2threeblanks><(p|span|div)[^>]*>\s*(<(p|span|div)[^>]*>\s*</(span|p|div)>\s*)</(span|p|div)>\s*){0,3}\s*" blanklines = "\s*(?P<up2threeblanks><(p|span|div)[^>]*>\s*(<(p|span|div)[^>]*>\s*</(span|p|div)>\s*)</(span|p|div)>\s*){0,3}\s*"
line_opening = "<(span|[iubp]|div)[^>]*>\s*(<(span|[iubp]|div)[^>]*>)?\s*" line_opening = "<(span|[iubp]|div)[^>]*>\s*(<(span|[iubp]|div)[^>]*>)?\s*"
@ -331,23 +330,19 @@ class HeuristicProcessor(object):
unwrap_regex = lookahead+line_ending+blanklines+line_opening unwrap_regex = lookahead+line_ending+blanklines+line_opening
em_en_unwrap_regex = em_en_lookahead+line_ending+blanklines+line_opening em_en_unwrap_regex = em_en_lookahead+line_ending+blanklines+line_opening
shy_unwrap_regex = soft_hyphen+line_ending+blanklines+line_opening shy_unwrap_regex = soft_hyphen+line_ending+blanklines+line_opening
dash_unwrap_regex = dash+line_ending+blanklines+line_opening
if format == 'txt': if format == 'txt':
unwrap_regex = lookahead+txt_line_wrap unwrap_regex = lookahead+txt_line_wrap
em_en_unwrap_regex = em_en_lookahead+txt_line_wrap em_en_unwrap_regex = em_en_lookahead+txt_line_wrap
shy_unwrap_regex = soft_hyphen+txt_line_wrap shy_unwrap_regex = soft_hyphen+txt_line_wrap
dash_unwrap_regex = dash+txt_line_wrap
unwrap = re.compile(u"%s" % unwrap_regex, re.UNICODE) unwrap = re.compile(u"%s" % unwrap_regex, re.UNICODE)
em_en_unwrap = re.compile(u"%s" % em_en_unwrap_regex, re.UNICODE) em_en_unwrap = re.compile(u"%s" % em_en_unwrap_regex, re.UNICODE)
shy_unwrap = re.compile(u"%s" % shy_unwrap_regex, re.UNICODE) shy_unwrap = re.compile(u"%s" % shy_unwrap_regex, re.UNICODE)
dash_unwrap = re.compile(u"%s" % dash_unwrap_regex, re.UNICODE)
content = unwrap.sub(' ', content) content = unwrap.sub(' ', content)
content = em_en_unwrap.sub('', content) content = em_en_unwrap.sub('', content)
content = shy_unwrap.sub('', content) content = shy_unwrap.sub('', content)
content = dash_unwrap.sub('', content)
return content return content
def txt_process(self, match): def txt_process(self, match):