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

Handle non ascii charset in RTF if declared as codepage

Browse Source
This commit is contained in:
Sengian 2011-01-07 08:07:39 +01:00
parent b2187360ec
commit ac07ff853e
4 changed files with 41 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -326,7 +326,6 @@ class ParseRtf:
invalid_rtf_handler = InvalidRtfException, invalid_rtf_handler = InvalidRtfException,
) )
hex2utf_obj.convert_hex_2_utf8() hex2utf_obj.convert_hex_2_utf8()
# raise RtfInvalidCodeException, 'stop'
self.__bracket_match('hex_2_utf_preamble') self.__bracket_match('hex_2_utf_preamble')
fonts_obj = fonts.Fonts( fonts_obj = fonts.Fonts(
in_file = self.__temp_file, in_file = self.__temp_file,
@ -523,6 +522,7 @@ class ParseRtf:
indent = self.__indent, indent = self.__indent,
run_level = self.__run_level, run_level = self.__run_level,
no_dtd = self.__no_dtd, no_dtd = self.__no_dtd,
encoding = encode_obj.get_codepage(),
bug_handler = RtfInvalidCodeException, bug_handler = RtfInvalidCodeException,
) )
tags_obj.convert_to_tags() tags_obj.convert_to_tags()

1
src/calibre/ebooks/rtf2xml/check_encoding.py
View File

@ -1,5 +1,6 @@
#!/usr/bin/env python #!/usr/bin/env python
import sys import sys
class CheckEncoding: class CheckEncoding:
def __init__(self, bug_handler): def __init__(self, bug_handler):

50
src/calibre/ebooks/rtf2xml/convert_to_tags.py
View File

@ -1,6 +1,9 @@
import os, tempfile import os, tempfile
from calibre.ebooks.rtf2xml import copy
from calibre.ebooks.rtf2xml import copy, check_encoding
public_dtd = 'rtf2xml1.0.dtd' public_dtd = 'rtf2xml1.0.dtd'
class ConvertToTags: class ConvertToTags:
""" """
Convert file to XML Convert file to XML
@ -10,6 +13,7 @@ class ConvertToTags:
bug_handler, bug_handler,
dtd_path, dtd_path,
no_dtd, no_dtd,
encoding,
indent = None, indent = None,
copy = None, copy = None,
run_level = 1, run_level = 1,
@ -29,9 +33,14 @@ class ConvertToTags:
self.__copy = copy self.__copy = copy
self.__dtd_path = dtd_path self.__dtd_path = dtd_path
self.__no_dtd = no_dtd self.__no_dtd = no_dtd
if encoding != 'mac_roman':
self.__encoding = 'cp' + encoding
else:
self.__encoding = 'mac_roman'
self.__indent = indent self.__indent = indent
self.__run_level = run_level self.__run_level = run_level
self.__write_to = tempfile.mktemp() self.__write_to = tempfile.mktemp()
def __initiate_values(self): def __initiate_values(self):
""" """
Set values, including those for the dictionary. Set values, including those for the dictionary.
@ -61,6 +70,7 @@ class ConvertToTags:
'tx<ut<__________' : self.__text_func, 'tx<ut<__________' : self.__text_func,
'mi<tg<empty_____' : self.__empty_func, 'mi<tg<empty_____' : self.__empty_func,
} }
def __open_func(self, line): def __open_func(self, line):
""" """
Print the opening tag and newlines when needed. Print the opening tag and newlines when needed.
@ -73,6 +83,7 @@ class ConvertToTags:
if info in self.__two_new_line: if info in self.__two_new_line:
self.__write_extra_new_line() self.__write_extra_new_line()
self.__write_obj.write('<%s>' % info) self.__write_obj.write('<%s>' % info)
def __empty_func(self, line): def __empty_func(self, line):
""" """
Print out empty tag and newlines when needed. Print out empty tag and newlines when needed.
@ -85,6 +96,7 @@ class ConvertToTags:
self.__write_new_line() self.__write_new_line()
if info in self.__two_new_line: if info in self.__two_new_line:
self.__write_extra_new_line() self.__write_extra_new_line()
def __open_att_func(self, line): def __open_att_func(self, line):
""" """
Process lines for open tags that have attributes. Process lines for open tags that have attributes.
@ -119,6 +131,7 @@ class ConvertToTags:
self.__write_new_line() self.__write_new_line()
if element_name in self.__two_new_line: if element_name in self.__two_new_line:
self.__write_extra_new_line() self.__write_extra_new_line()
def __empty_att_func(self, line): def __empty_att_func(self, line):
""" """
Same as the __open_att_func, except a '/' is placed at the end of the tag. Same as the __open_att_func, except a '/' is placed at the end of the tag.
@ -143,6 +156,7 @@ class ConvertToTags:
self.__write_new_line() self.__write_new_line()
if element_name in self.__two_new_line: if element_name in self.__two_new_line:
self.__write_extra_new_line() self.__write_extra_new_line()
def __close_func(self, line): def __close_func(self, line):
""" """
Print out the closed tag and new lines, if appropriate. Print out the closed tag and new lines, if appropriate.
@ -156,6 +170,7 @@ class ConvertToTags:
self.__write_new_line() self.__write_new_line()
if info in self.__two_new_line: if info in self.__two_new_line:
self.__write_extra_new_line() self.__write_extra_new_line()
def __text_func(self, line): def __text_func(self, line):
""" """
Simply print out the information between [17:-1] Simply print out the information between [17:-1]
@ -163,6 +178,7 @@ class ConvertToTags:
#tx<nu<__________<Normal; #tx<nu<__________<Normal;
# change this! # change this!
self.__write_obj.write(line[17:-1]) self.__write_obj.write(line[17:-1])
def __write_extra_new_line(self): def __write_extra_new_line(self):
""" """
Print out extra new lines if the new lines have not exceeded two. If Print out extra new lines if the new lines have not exceeded two. If
@ -172,8 +188,10 @@ class ConvertToTags:
return return
if self.__new_line < 2: if self.__new_line < 2:
self.__write_obj.write('\n') self.__write_obj.write('\n')
def __default_func(self, line): def __default_func(self, line):
pass pass
def __write_new_line(self): def __write_new_line(self):
""" """
Print out a new line if a new line has not already been printed out. Print out a new line if a new line has not already been printed out.
@ -183,11 +201,22 @@ class ConvertToTags:
if not self.__new_line: if not self.__new_line:
self.__write_obj.write('\n') self.__write_obj.write('\n')
self.__new_line += 1 self.__new_line += 1
def __write_dec(self): def __write_dec(self):
""" """
Write the XML declaration at the top of the document. Write the XML declaration at the top of the document.
""" """
self.__write_obj.write('<?xml version="1.0" encoding="US-ASCII" ?>') #keep maximum compatibility with previous version
check_encoding_obj = check_encoding.CheckEncoding(
bug_handler = self.__bug_handler,
)
if not check_encoding_obj.check_encoding(self.__file):
self.__write_obj.write('<?xml version="1.0" encoding="US-ASCII" ?>')
elif not check_encoding_obj.check_encoding(self.__file, self.__encoding):
self.__write_obj.write('<?xml version="1.0" encoding="%s" ?>' % self.__encoding)
else:
self.__write_obj.write('<?xml version="1.0" encoding="US-ASCII" ?>')
sys.stderr.write(_('Bad RTF encoding, revert to US-ASCII chars and hope for the best'))
self.__new_line = 0 self.__new_line = 0
self.__write_new_line() self.__write_new_line()
if self.__no_dtd: if self.__no_dtd:
@ -207,6 +236,7 @@ class ConvertToTags:
) )
self.__new_line = 0 self.__new_line = 0
self.__write_new_line() self.__write_new_line()
def convert_to_tags(self): def convert_to_tags(self):
""" """
Read in the file one line at a time. Get the important info, between Read in the file one line at a time. Get the important info, between
@ -222,18 +252,14 @@ class ConvertToTags:
an empty tag function. an empty tag function.
""" """
self.__initiate_values() self.__initiate_values()
read_obj = open(self.__file, 'r')
self.__write_obj = open(self.__write_to, 'w') self.__write_obj = open(self.__write_to, 'w')
self.__write_dec() self.__write_dec()
line_to_read = 1 with open(self.__file, 'r') as read_obj:
while line_to_read: for line in read_obj:
line_to_read = read_obj.readline() self.__token_info = line[:16]
line = line_to_read action = self.__state_dict.get(self.__token_info)
self.__token_info = line[:16] if action is not None:
action = self.__state_dict.get(self.__token_info) action(line)
if action != None:
action(line)
read_obj.close()
self.__write_obj.close() self.__write_obj.close()
copy_obj = copy.Copy(bug_handler = self.__bug_handler) copy_obj = copy.Copy(bug_handler = self.__bug_handler)
if self.__copy: if self.__copy:

3
src/calibre/ebooks/rtf2xml/default_encoding.py
View File

@ -132,8 +132,7 @@ class DefaultEncoding:
self.__code_page = '850' self.__code_page = '850'
# if __name__ == '__main__': # if __name__ == '__main__':
# from calibre.ebooks.rtf2xml import default_encoding # encode_obj = DefaultEncoding(
# encode_obj = default_encoding.DefaultEncoding(
# in_file = sys.argv[1], # in_file = sys.argv[1],
# bug_handler = Exception, # bug_handler = Exception,
# check_raw = True, # check_raw = True,