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

Enabled preprocess_html option for rtf

Browse Source
This commit is contained in:
ldolse 2010-08-24 00:56:06 +10:00
parent aca34337d1
commit 0bd3cf4009
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/calibre/ebooks/rtf/input.py
View File

@ -7,6 +7,7 @@ import os, glob, re, textwrap
from lxml import etree from lxml import etree
from calibre.customize.conversion import InputFormatPlugin from calibre.customize.conversion import InputFormatPlugin
from calibre.ebooks.conversion.preprocess import line_length
class InlineClass(etree.XSLTExtension): class InlineClass(etree.XSLTExtension):
@ -184,6 +185,7 @@ class RTFInput(InputFormatPlugin):
from calibre.ebooks.metadata.meta import get_metadata from calibre.ebooks.metadata.meta import get_metadata
from calibre.ebooks.metadata.opf2 import OPFCreator from calibre.ebooks.metadata.opf2 import OPFCreator
from calibre.ebooks.rtf2xml.ParseRtf import RtfInvalidCodeException from calibre.ebooks.rtf2xml.ParseRtf import RtfInvalidCodeException
self.options = options
self.log = log self.log = log
self.log('Converting RTF to XML...') self.log('Converting RTF to XML...')
#Name of the preprocesssed RTF file #Name of the preprocesssed RTF file
@ -226,6 +228,17 @@ class RTFInput(InputFormatPlugin):
with open(html, 'wb') as f: with open(html, 'wb') as f:
res = transform.tostring(result) res = transform.tostring(result)
res = res[:100].replace('xmlns:html', 'xmlns') + res[100:] res = res[:100].replace('xmlns:html', 'xmlns') + res[100:]
if self.options.preprocess_html:
print "********* Preprocessing HTML *********\n"
# 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)
res = chapdetect.sub('<h2>'+'\g<chap>'+'</h2>\n', res)
# Unwrap lines using punctation if the median length of all lines is less than 150
length = line_length('html', res, 0.4)
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)
if length < 150:
res = unwrap.sub(' ', res)
f.write(res) f.write(res)
self.write_inline_css(inline_class) self.write_inline_css(inline_class)
stream.seek(0) stream.seek(0)