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

tweaked preprocess for $, added rtf to new preprocess logic, changed last pdf default

Browse Source
This commit is contained in:
ldolse 2010-09-14 02:56:56 +10:00
parent 548417ea6b
commit b73e1b3da5
3 changed files with 5 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -340,7 +340,7 @@ class HTMLPreProcessor(object):
# print "The pdf line length returned is " + str(length) # print "The pdf line length returned is " + str(length)
end_rules.append( end_rules.append(
# Un wrap using punctuation # Un wrap using punctuation
(re.compile(r'(?<=.{%i}[a-z,;:)\-IA])\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])\s*(?P<ital></(i|b|u)>)?\s*(<p.*?>\s*)+\s*(?=(<(i|b|u)>)?\s*[\w\d$(])' % length, re.UNICODE), wrap_lines),
) )
for rule in self.PREPROCESS + start_rules: for rule in self.PREPROCESS + start_rules:

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

@ -8,6 +8,7 @@ from lxml import etree
from calibre.customize.conversion import InputFormatPlugin from calibre.customize.conversion import InputFormatPlugin
from calibre.ebooks.conversion.preprocess import line_length from calibre.ebooks.conversion.preprocess import line_length
from calibre.ebooks.conversion.utils import PreProcessor
class InlineClass(etree.XSLTExtension): class InlineClass(etree.XSLTExtension):
@ -229,16 +230,8 @@ class RTFInput(InputFormatPlugin):
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: if self.options.preprocess_html:
self.log("********* Preprocessing HTML *********") preprocessor = PreProcessor(res)
# Detect Chapters to match the xpath in the GUI res = preprocessor(res)
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)
# Unwrap lines using punctation if the median length of all lines is less than 150
length = line_length('html', res, 0.4)
self.log("*** Median length is " + str(length) + " ***")
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)

2
src/calibre/gui2/convert/pdf_input.ui
View File

@ -46,7 +46,7 @@
<double>0.010000000000000</double> <double>0.010000000000000</double>
</property> </property>
<property name="value"> <property name="value">
<double>0.500000000000000</double> <double>0.450000000000000</double>
</property> </property>
</widget> </widget>
</item> </item>