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

made em-dash unwrapping line length dependent, as sometimes it's used as an ellipsis alternative

Browse Source
This commit is contained in:
ldolse 2010-09-20 09:57:46 +08:00
parent e303babf89
commit 301af532c6
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/calibre/ebooks/conversion/preprocess.py
View File

@ -117,7 +117,7 @@ class Dehyphenator(object):
def __init__(self): def __init__(self):
# Add common suffixes to the regex below to increase the likelihood of a match - # Add common suffixes to the regex below to increase the likelihood of a match -
# don't add suffixes which are also complete words, such as 'able' or 'sex' # don't add suffixes which are also complete words, such as 'able' or 'sex'
self.removesuffixes = re.compile(r"((ed)?ly|('e)?s|a?(t|s)ion(s|al(ly)?)?|ings?|(i)?ous|(i|a)ty|(it)?ies|ive|gence|istic|(e|a)nce|ment(s)?|ism|ated|(e|u)ct(ed)?|ed|(i|ed)?ness|(e|a)ncy|ble|ier|al|ex)$", re.IGNORECASE) self.removesuffixes = re.compile(r"((ed)?ly|('e)?s|a?(t|s)?ion(s|al(ly)?)?|ings?|er|(i)?ous|(i|a)ty|(it)?ies|ive|gence|istic|(e|a)nce|ment(s)?|ism|ated|(e|u)ct(ed)?|ed|(i|ed)?ness|(e|a)ncy|ble|ier|al|ex)$", re.IGNORECASE)
# remove prefixes if the prefix was not already the point of hyphenation # remove prefixes if the prefix was not already the point of hyphenation
self.prefixes = re.compile(r'^(un|in|ex)$', re.IGNORECASE) self.prefixes = re.compile(r'^(un|in|ex)$', re.IGNORECASE)
self.removeprefix = re.compile(r'^(un|in|ex)', re.IGNORECASE) self.removeprefix = re.compile(r'^(un|in|ex)', re.IGNORECASE)
@ -374,10 +374,8 @@ class HTMLPreProcessor(object):
print 'Failed to parse remove_footer regexp' print 'Failed to parse remove_footer regexp'
traceback.print_exc() traceback.print_exc()
# unwrap em/en dashes, delete soft hyphens - moved here so it's executed after header/footer removal # delete soft hyphens - moved here so it's executed after header/footer removal
if is_pdftohtml: if is_pdftohtml:
# unwrap em/en dashes
end_rules.append((re.compile(u'(?<=[–—])\s*<p>\s*(?=[[a-z\d])'), lambda match: ''))
# unwrap/delete soft hyphens # unwrap/delete soft hyphens
end_rules.append((re.compile(u'[­](\s*<p>)+\s*(?=[[a-z\d])'), lambda match: '')) end_rules.append((re.compile(u'[­](\s*<p>)+\s*(?=[[a-z\d])'), lambda match: ''))
# unwrap/delete soft hyphens with formatting # unwrap/delete soft hyphens with formatting
@ -397,6 +395,8 @@ class HTMLPreProcessor(object):
# Un wrap using punctuation # Un wrap using punctuation
(re.compile(r'(?<=.{%i}([a-z,:)\IA]|(?<!\&\w{4});))\s*(?P<ital></(i|b|u)>)?\s*(<p.*?>\s*)+\s*(?=(<(i|b|u)>)?\s*[\w\d$(])' % length, re.UNICODE), wrap_lines), (re.compile(r'(?<=.{%i}([a-z,:)\IA]|(?<!\&\w{4});))\s*(?P<ital></(i|b|u)>)?\s*(<p.*?>\s*)+\s*(?=(<(i|b|u)>)?\s*[\w\d$(])' % length, re.UNICODE), wrap_lines),
) )
# unwrap em/en dashes
end_rules.append((re.compile(u'(?<=.{%i}[–—])\s*<p>\s*(?=[[a-z\d])' % length), lambda match: ''))
for rule in self.PREPROCESS + start_rules: for rule in self.PREPROCESS + start_rules:
html = rule[0].sub(rule[1], html) html = rule[0].sub(rule[1], html)