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

Still old paragraph format

Browse Source
This commit is contained in:
Sengian 2011-02-05 17:34:57 +01:00
parent 056f97c700
commit ccf856539a
4 changed files with 25 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/calibre/ebooks/rtf/input.py
View File

@ -78,7 +78,6 @@ class RTFInput(InputFormatPlugin):
from calibre.ebooks.rtf2xml.ParseRtf import ParseRtf
ofile = 'dataxml.xml'
run_lev, debug_dir, indent_out = 1, None, 0
#just to check if the debug process is lauched, no need of this directory in fact
if getattr(self.opts, 'debug_pipeline', None) is not None:
try:
os.mkdir('rtfdebug')
@ -322,5 +321,5 @@ class RTFInput(InputFormatPlugin):
return os.path.abspath('metadata.opf')
#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'
# os.makedirs("E:\\Mes eBooks\\Developpement\\rtfdebug")
# debug_dir = "E:\\Mes eBooks\\Developpement\\rtfdebug"

12
src/calibre/ebooks/rtf2xml/ParseRtf.py
View File

@ -226,7 +226,7 @@ class ParseRtf:
try:
return_value = process_tokens_obj.process_tokens()
except InvalidRtfException, msg:
#Check to see if the file is correctly encoded
# Check to see if the file is correctly encoded
encode_obj = default_encoding.DefaultEncoding(
in_file = self.__temp_file,
run_level = self.__run_level,
@ -237,14 +237,14 @@ class ParseRtf:
check_encoding_obj = check_encoding.CheckEncoding(
bug_handler = RtfInvalidCodeException,
)
enc = 'cp' + encode_obj.get_codepage()
if enc == 'cp10000':
enc = 'mac_roman'
msg = 'Exception in token processing'
enc = encode_obj.get_codepage()
if enc != 'mac_roman':
enc = 'cp' + enc
msg = '%s\nException in token processing' % str(msg)
if check_encoding_obj.check_encoding(self.__file, enc):
file_name = self.__file if isinstance(self.__file, str) \
else self.__file.encode('utf-8')
msg = 'File %s does not appear to be correctly encoded.\n' % file_name
msg +='\nFile %s does not appear to be correctly encoded.\n' % file_name
try:
os.remove(self.__temp_file)
except OSError:

14
src/calibre/ebooks/rtf2xml/process_tokens.py
View File

@ -786,21 +786,23 @@ class ProcessTokens:
token = line.replace("\n","")
line_count += 1
if line_count == 1 and token != '\\{':
msg = 'Invalid RTF: document doesn\'t start with {\n'
msg = '\nInvalid RTF: document doesn\'t start with {\n'
raise self.__exception_handler, msg
elif line_count == 2 and token[0:4] != '\\rtf':
msg = 'Invalid RTF: document doesn\'t start with \\rtf \n'
msg = '\nInvalid RTF: document doesn\'t start with \\rtf \n'
raise self.__exception_handler, msg
the_index = token.find('\\ ')
if token is not None and the_index > -1:
msg = 'Invalid RTF: token "\\ " not valid.\n'
msg = '\nInvalid RTF: token "\\ " not valid.\nError at line %d'\
% line_count
raise self.__exception_handler, msg
elif token[:1] == "\\":
try:
token.decode('us-ascii')
except UnicodeError, msg:
msg = 'Invalid RTF: Tokens not ascii encoded.\n%s' % str(msg)
msg = '\nInvalid RTF: Tokens not ascii encoded.\n%s\nError at line %d'\
% (str(msg), line_count)
raise self.__exception_handler, msg
line = self.process_cw(token)
if line is not None:
@ -816,7 +818,7 @@ class ProcessTokens:
write_obj.write('tx<nu<__________<%s\n' % field)
if not line_count:
msg = 'Invalid RTF: file appears to be empty.\n'
msg = '\nInvalid RTF: file appears to be empty.\n'
raise self.__exception_handler, msg
copy_obj = copy.Copy(bug_handler = self.__bug_handler)
@ -827,7 +829,7 @@ class ProcessTokens:
bad_brackets = self.__check_brackets(self.__file)
if bad_brackets:
msg = 'Invalid RTF: document does not have matching brackets.\n'
msg = '\nInvalid RTF: document does not have matching brackets.\n'
raise self.__exception_handler, msg
else:
return self.__return_code

23
src/calibre/ebooks/rtf2xml/tokenize.py
View File

@ -141,17 +141,17 @@ class Tokenize:
"\\_": "\\_ ",
"\\:": "\\: ",
"\\-": "\\- ",
# turn into a generic token to eliminate special
# cases and make processing easier
#turn into a generic token to eliminate special
#cases and make processing easier
"\\{": "\\ob ",
# turn into a generic token to eliminate special
# cases and make processing easier
#turn into a generic token to eliminate special
#cases and make processing easier
"\\}": "\\cb ",
# put a backslash in front of to eliminate special cases and
# make processing easier
#put a backslash in front of to eliminate special cases and
#make processing easier
"{": "\\{",
# put a backslash in front of to eliminate special cases and
# make processing easier
#put a backslash in front of to eliminate special cases and
#make processing easier
"}": "\\}",
}
self.__replace_spchar = MReplace(SIMPLE_RPL)
@ -167,16 +167,11 @@ class Tokenize:
#remove \n from endline char
self.__splitexp = re.compile(r"(\\[{}]|\n|\\[^\s\\{}&]+(?:[ \t\r\f\v])?)")
#this is for old RTF
self.__par_exp = re.compile(r'\\\n+')
self.__par_exp = re.compile(r'(\\\n+|\\ )')
#handle improper cs char-style with \* before without {
self.__cs_ast = re.compile(r'\\\*([\n ]*\\cs\d+[\n \\]+)')
#handle cw using a digit as argument and without space as delimiter
self.__cwdigit_exp = re.compile(r"(\\[a-zA-Z]+[\-0-9]+)([^0-9 \\]+)")
#self.__bin_exp = re.compile(r"\\bin(-?\d{1,8}) {0,1}")
#self.__utf_exp = re.compile(r"^\\u(-?\d{3,6})")
#self.__splitexp = re.compile(r"(\\[\\{}]|{|}|\n|\\[^\s\\{}&]+(?:\s)?)")
#self.__remove_line = re.compile(r'\n+')
##self.num_exp = re.compile(r"(\*|:|[a-zA-Z]+)(.*)")
def tokenize(self):
"""Main class for handling other methods. Reads the file \