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

adjusted preprocessing regexes for hyphen removal and chapter marking

Browse Source
This commit is contained in:
ldolse 2010-11-21 15:38:18 +08:00
parent 9c2dcfd5af
commit 267eebb9aa
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/calibre/ebooks/conversion/preprocess.py
View File

@ -220,7 +220,7 @@ class Dehyphenator(object):
self.html = html
self.format = format
if format == 'html':
intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)\s*(?=<)(?P<wraptags></span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*(?P<secondpart>[\w\d]+)' % length)
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)
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)
elif format == 'individual_words':

10
src/calibre/ebooks/conversion/utils.py
View File

@ -107,7 +107,7 @@ class PreProcessor(object):
# Arrange line feeds and </p> tags so the line_length and no_markup functions work correctly
html = re.sub(r"\s*</p>", "</p>\n", html)
html = re.sub(r"\s*<p>\s*", "\n<p>", html)
###### Check Markup ######
#
# some lit files don't have any <p> tags or equivalent (generally just plain text between
@ -191,10 +191,10 @@ class PreProcessor(object):
n_lookahead_close = ")"
default_title = r"(\s*[\w\'\"-]+){1,5}?(?=<)"
typical_chapters = r".?(Introduction|Synopsis|Acknowledgements|Chapter|Kapitel|Epilogue|Volume\s|Prologue|Book\s|Part\s|Dedication)\s*([\d\w-]+\:?\s*){0,4}"
numeric_chapters = r".?(\d+\.?|(CHAPTER\s*([\dA-Z\-\'\"\?\.!#,]+\s*){1,10}))\s*"
uppercase_chapters = r"\s*.?([A-Z#]+(\s|-){0,3}){1,5}\s*"
numeric_titles = r".?(\d+\.?\s+([\d\w-]+\:?\'?-?\s?){0,5})\s*"
typical_chapters = r"[^'\"]?(Introduction|Synopsis|Acknowledgements|Chapter|Kapitel|Epilogue|Volume\s|Prologue|Book\s|Part\s|Dedication)\s*([\d\w-]+\:?\s*){0,4}"
numeric_chapters = r"[^'\"]?(\d+\.?|CHAPTER)\s*([\dA-Z\-\'\"\?\.!#,]+\s*){1,10}\s*"
uppercase_chapters = r"\s*[^'\"]?([A-Z#]+(\s|-){0,3}){1,5}\s*"
numeric_titles = r"[^'\"]?(\d+\.?\s+([\d\w-]+\:?\'?-?\s?){0,5})\s*"
emphasized_lines = r"<b[^>]*>\s*(<span[^>]*>)?\s*(?!([*#•]+\s*)+)(\s*(?=[\w#\-*\s]+<)([\w#-*]+\s*){1,5}\s*)(</span>)?\s*</b>"
full_chapter_line = chapter_line_open+chapter_header_open+typical_chapters+chapter_header_close+chapter_line_close