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

Correct splitting problem

Browse Source
This commit is contained in:
Sengian 2011-02-05 12:19:46 +01:00
parent 1f10817e13
commit 056f97c700
3 changed files with 5 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/calibre/ebooks/rtf/input.py
View File

@ -321,6 +321,6 @@ class RTFInput(InputFormatPlugin):
opf.render(open('metadata.opf', 'wb'))
return os.path.abspath('metadata.opf')
#ebook-convert "bad.rtf" test.epub -v -d "D:\Mes eBooks\Developpement\debug"
# os.makedirs('D:\\Mes eBooks\\Developpement\\rtfdebug')
# debug_dir = 'D:\\Mes eBooks\\Developpement\\rtfdebug'
#ebook-convert "bad.rtf" test.epub -v -d "E:\Mes eBooks\Developpement\debug"
# os.makedirs('E:\\Mes eBooks\\Developpement\\rtfdebug')
# debug_dir = 'E:\\Mes eBooks\\Developpement\\rtfdebug'

2
src/calibre/ebooks/rtf2xml/colors.py
View File

@ -210,7 +210,7 @@ class Colors:
hex_num = self.__color_dict.get(num)
if hex_num is None:
hex_num = '0'
if self.__run_level > 5:
if self.__run_level > 3:
msg = 'no value in self.__color_dict' \
'for key %s at line %d\n' % (num, self.__line)
raise self.__bug_handler, msg

10
src/calibre/ebooks/rtf2xml/tokenize.py
View File

@ -117,6 +117,7 @@ class Tokenize:
input_file = self.__replace_spchar.mreplace(input_file)
# this is for older RTF
input_file = self.__par_exp.sub('\n\\par \n', input_file)
input_file = self.__cwdigit_exp.sub("\g<1>\n\g<2>", input_file)
input_file = self.__cs_ast.sub("\g<1>", input_file)
input_file = self.__ms_hex_exp.sub("\\mshex0\g<1> ", input_file)
input_file = self.__utf_ud.sub("\\{\\uc0 \g<1>\\}", input_file)
@ -177,13 +178,6 @@ class Tokenize:
#self.__remove_line = re.compile(r'\n+')
##self.num_exp = re.compile(r"(\*|:|[a-zA-Z]+)(.*)")
def __correct_spliting(self, token):
match_obj = re.search(self.__cwdigit_exp, token)
if match_obj is None:
return token
else:
return '%s\n%s' % (match_obj.group(1), match_obj.group(2))
def tokenize(self):
"""Main class for handling other methods. Reads the file \
, uses method self.sub_reg to make basic substitutions,\
@ -199,8 +193,6 @@ class Tokenize:
tokens = map(self.__unicode_process, tokens)
#remove empty items created by removing \uc
tokens = filter(lambda x: len(x) > 0, tokens)
#handles bothersome cases
tokens = map(self.__correct_spliting, tokens)
#write
with open(self.__write_to, 'wb') as write_obj: