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

preprocessing regex tweaks

Browse Source
This commit is contained in:
ldolse 2010-08-25 10:49:42 +10:00
parent 0bd3cf4009
commit 0ad1f3c088
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -209,7 +209,7 @@ class HTMLPreProcessor(object):
(re.compile(ur'\u00a0'), lambda match : ' '), (re.compile(ur'\u00a0'), lambda match : ' '),
# Detect Chapters to match default XPATH in GUI # Detect Chapters to match default XPATH in GUI
(re.compile(r'(?=<(/?br|p))(<(/?br|p)[^>]*)?>\s*(?P<chap>(<(i|b)>(<(i|b)>)?)?(.?Chapter|Epilogue|Prologue|Book|Part)\s*([\d\w-]+(\s\w+)?)?(</(i|b)>(</(i|b)>)?)?)</?(br|p)[^>]*>\s*(?P<title>(<(i|b)>)?\s*\w+(\s*\w+)?\s*(</(i|b)>)?\s*(</?(br|p)[^>]*>))?', re.IGNORECASE), chap_head), (re.compile(r'(?=<(/?br|p))(<(/?br|p)[^>]*)?>\s*(?P<chap>(<(i|b)>(<(i|b)>)?)?(.?Chapter|Epilogue|Prologue|Book|Part|Dedication)\s*([\d\w-]+(\s\w+)?)?(</(i|b)>(</(i|b)>)?)?)</?(br|p)[^>]*>\s*(?P<title>(<(i|b)>)?\s*\w+(\s*\w+)?\s*(</(i|b)>)?\s*(</?(br|p)[^>]*>))?', re.IGNORECASE), chap_head),
(re.compile(r'(?=<(/?br|p))(<(/?br|p)[^>]*)?>\s*(?P<chap>([A-Z \'"!]{5,})\s*(\d+|\w+)?)(</?p[^>]*>|<br[^>]*>)\n?((?=(<i>)?\s*\w+(\s+\w+)?(</i>)?(<br[^>]*>|</?p[^>]*>))((?P<title>.*)(<br[^>]*>|</?p[^>]*>)))?'), chap_head), (re.compile(r'(?=<(/?br|p))(<(/?br|p)[^>]*)?>\s*(?P<chap>([A-Z \'"!]{5,})\s*(\d+|\w+)?)(</?p[^>]*>|<br[^>]*>)\n?((?=(<i>)?\s*\w+(\s+\w+)?(</i>)?(<br[^>]*>|</?p[^>]*>))((?P<title>.*)(<br[^>]*>|</?p[^>]*>)))?'), chap_head),
# Have paragraphs show better # Have paragraphs show better

4
src/calibre/ebooks/rtf/input.py
View File

@ -231,12 +231,12 @@ class RTFInput(InputFormatPlugin):
if self.options.preprocess_html: if self.options.preprocess_html:
print "********* Preprocessing HTML *********\n" print "********* Preprocessing HTML *********\n"
# Detect Chapters to match the xpath in the GUI # Detect Chapters to match the xpath in the GUI
chapdetect = re.compile(r'<p[^>]*>\s*<span[^>]*>\s*(?P<chap>(<(i|b)><(i|b)>|<(i|b)>)?(.?Chapter|Epilogue|Prologue|Book|Part|Dedication)\s*([\d\w-]+(\s\w+)?)?(</(i|b)></(i|b)>|</(i|b)>)?)\s*</span>\s*</p>', re.IGNORECASE) chapdetect = re.compile(r'<p[^>]*>\s*<span[^>]*>\s*(?P<chap>(<(i|b)>(<(i|b)>)?)?(.?Chapter|Epilogue|Prologue|Book|Part|Dedication)\s*([\d\w-]+(\s\w+)?)?(</(i|b)>(<(/i|b)>)?)?)\s*</span>\s*</p>', re.IGNORECASE)
res = chapdetect.sub('<h2>'+'\g<chap>'+'</h2>\n', res) res = chapdetect.sub('<h2>'+'\g<chap>'+'</h2>\n', res)
# Unwrap lines using punctation if the median length of all lines is less than 150 # Unwrap lines using punctation if the median length of all lines is less than 150
length = line_length('html', res, 0.4) length = line_length('html', res, 0.4)
print "*** Median length is " + str(length) + " ***\n" print "*** Median length is " + str(length) + " ***\n"
unwrap = re.compile(r"(?<=.{%i}[a-z,;:\IA])\s*</span>\s*(</p>)?\s*(?P<up2threeblanks><p[^>]*>\s*(<span[^>]*>\s*</span>\s*)</p>\s*){0,3}\s*<p[^>]*>\s*(<span[^>]*>)?\s*" % length, re.UNICODE) unwrap = re.compile(r"(?<=.{%i}[a-z,;:\IA])\s*</span>\s*</p>\s*(?P<up2threeblanks><p[^>]*>\s*(<span[^>]*>\s*</span>\s*)</p>\s*){0,3}\s*<p[^>]*>\s*<span[^>]*>\s*" % length, re.UNICODE)
if length < 150: if length < 150:
res = unwrap.sub(' ', res) res = unwrap.sub(' ', res)
f.write(res) f.write(res)