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

Added preprocess_html to lit input, tweaked pdf preprocess chapter detection

Browse Source
This commit is contained in:
ldolse 2010-08-21 12:08:09 +10:00
parent e947f60154
commit 0ff1622bd4
3 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/calibre/__init__.py
View File

@ -549,5 +549,3 @@ main()
ipshell = IPShellEmbed(user_ns=user_ns) ipshell = IPShellEmbed(user_ns=user_ns)
ipshell() ipshell()
sys.argv = old_argv sys.argv = old_argv

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

@ -206,7 +206,7 @@ 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-]+)?(</i></b>|</i>|</b>)?)(</?p[^>]*>|<br[^>]*>)\n?((?=(<i>)?\s*\w+(\s+\w+)?(</i>)?(<br[^>]*>|</?p[^>]*>))((?P<title>(<i>)?\s*\w+(\s+\w+)?(</i>)?)(<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)\s*([\d\w-]+(\s\w+)?)?(</i></b>|</i>|</b>)?)(</?p[^>]*>|<br[^>]*>)\n?((?=(<i>)?\s*\w+(\s+\w+)?(</i>)?(<br[^>]*>|</?p[^>]*>))((?P<title>(<i>)?\s*\w+(\s+\w+)?(</i>)?)(<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

11
src/calibre/ebooks/lit/input.py
View File

@ -6,8 +6,12 @@ __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import re
from calibre.customize.conversion import InputFormatPlugin from calibre.customize.conversion import InputFormatPlugin
from calibre import entity_to_unicode
class LITInput(InputFormatPlugin): class LITInput(InputFormatPlugin):
name = 'LIT Input' name = 'LIT Input'
@ -48,4 +52,11 @@ class LITInput(InputFormatPlugin):
for elem in body: for elem in body:
ne = copy.deepcopy(elem) ne = copy.deepcopy(elem)
pre.append(ne) pre.append(ne)
def preprocess_html(self, html):
chapdetect = re.compile(r'(?=</?(br|p|span))(</?(br|p|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)>)?)(</?(p|br|span)[^>]*>)', re.IGNORECASE)
html = chapdetect.sub('<h2>'+'\g<chap>'+'</h2>\n', html)
html = re.sub(r"(?<=.{65}[a-z,\IA])\s*</(span|p|div)>\s*(</(p|span|div)>\s*<p[^>]*>(\s*<(p|span|div)>\s*</(p|span|div)[^>]*>)?\s*(</(p|span|div)>\s*<p[^>]*>)?)?\s*<(span|div|p)[^>]*>", " ", html)
return html