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

Sync to trunk.

Browse Source
This commit is contained in:
John Schember 2011-02-05 12:39:56 -05:00
commit 37dd8f6f3a
5 changed files with 26 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -226,7 +226,7 @@ class ParseRtf:
try: try:
return_value = process_tokens_obj.process_tokens() return_value = process_tokens_obj.process_tokens()
except InvalidRtfException, msg: 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( encode_obj = default_encoding.DefaultEncoding(
in_file = self.__temp_file, in_file = self.__temp_file,
run_level = self.__run_level, run_level = self.__run_level,
@ -237,14 +237,14 @@ class ParseRtf:
check_encoding_obj = check_encoding.CheckEncoding( check_encoding_obj = check_encoding.CheckEncoding(
bug_handler = RtfInvalidCodeException, bug_handler = RtfInvalidCodeException,
) )
enc = 'cp' + encode_obj.get_codepage() enc = encode_obj.get_codepage()
if enc == 'cp10000': if enc != 'mac_roman':
enc = 'mac_roman' enc = 'cp' + enc
msg = 'Exception in token processing' msg = '%s\nException in token processing' % str(msg)
if check_encoding_obj.check_encoding(self.__file, enc): if check_encoding_obj.check_encoding(self.__file, enc):
file_name = self.__file if isinstance(self.__file, str) \ file_name = self.__file if isinstance(self.__file, str) \
else self.__file.encode('utf-8') 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: try:
os.remove(self.__temp_file) os.remove(self.__temp_file)
except OSError: except OSError:

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

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

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

@ -786,21 +786,23 @@ class ProcessTokens:
token = line.replace("\n","") token = line.replace("\n","")
line_count += 1 line_count += 1
if line_count == 1 and token != '\\{': 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 raise self.__exception_handler, msg
elif line_count == 2 and token[0:4] != '\\rtf': 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 raise self.__exception_handler, msg
the_index = token.find('\\ ') the_index = token.find('\\ ')
if token is not None and the_index > -1: 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 raise self.__exception_handler, msg
elif token[:1] == "\\": elif token[:1] == "\\":
try: try:
token.decode('us-ascii') token.decode('us-ascii')
except UnicodeError, msg: 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 raise self.__exception_handler, msg
line = self.process_cw(token) line = self.process_cw(token)
if line is not None: if line is not None:
@ -816,7 +818,7 @@ class ProcessTokens:
write_obj.write('tx<nu<__________<%s\n' % field) write_obj.write('tx<nu<__________<%s\n' % field)
if not line_count: 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 raise self.__exception_handler, msg
copy_obj = copy.Copy(bug_handler = self.__bug_handler) copy_obj = copy.Copy(bug_handler = self.__bug_handler)
@ -827,7 +829,7 @@ class ProcessTokens:
bad_brackets = self.__check_brackets(self.__file) bad_brackets = self.__check_brackets(self.__file)
if bad_brackets: 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 raise self.__exception_handler, msg
else: else:
return self.__return_code return self.__return_code

33
src/calibre/ebooks/rtf2xml/tokenize.py
View File

@ -117,6 +117,7 @@ class Tokenize:
input_file = self.__replace_spchar.mreplace(input_file) input_file = self.__replace_spchar.mreplace(input_file)
# this is for older RTF # this is for older RTF
input_file = self.__par_exp.sub('\n\\par \n', input_file) 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.__ms_hex_exp.sub("\\mshex0\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) input_file = self.__utf_ud.sub("\\{\\uc0 \g<1>\\}", input_file)
#remove \n in bin data #remove \n in bin data
@ -139,17 +140,17 @@ class Tokenize:
"\\_": "\\_ ", "\\_": "\\_ ",
"\\:": "\\: ", "\\:": "\\: ",
"\\-": "\\- ", "\\-": "\\- ",
# turn into a generic token to eliminate special #turn into a generic token to eliminate special
# cases and make processing easier #cases and make processing easier
"\\{": "\\ob ", "\\{": "\\ob ",
# turn into a generic token to eliminate special #turn into a generic token to eliminate special
# cases and make processing easier #cases and make processing easier
"\\}": "\\cb ", "\\}": "\\cb ",
# put a backslash in front of to eliminate special cases and #put a backslash in front of to eliminate special cases and
# make processing easier #make processing easier
"{": "\\{", "{": "\\{",
# put a backslash in front of to eliminate special cases and #put a backslash in front of to eliminate special cases and
# make processing easier #make processing easier
"}": "\\}", "}": "\\}",
} }
self.__replace_spchar = MReplace(SIMPLE_RPL) self.__replace_spchar = MReplace(SIMPLE_RPL)
@ -165,21 +166,9 @@ class Tokenize:
#remove \n from endline char #remove \n from endline char
self.__splitexp = re.compile(r"(\\[{}]|\n|\\[^\s\\{}&]+(?:[ \t\r\f\v])?)") self.__splitexp = re.compile(r"(\\[{}]|\n|\\[^\s\\{}&]+(?:[ \t\r\f\v])?)")
#this is for old RTF #this is for old RTF
self.__par_exp = re.compile(r'\\\n+') self.__par_exp = re.compile(r'(\\\n+|\\ )')
#handle cw using a digit as argument and without space as delimiter #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.__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 __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): def tokenize(self):
"""Main class for handling other methods. Reads the file \ """Main class for handling other methods. Reads the file \
@ -196,8 +185,6 @@ class Tokenize:
tokens = map(self.__unicode_process, tokens) tokens = map(self.__unicode_process, tokens)
#remove empty items created by removing \uc #remove empty items created by removing \uc
tokens = filter(lambda x: len(x) > 0, tokens) tokens = filter(lambda x: len(x) > 0, tokens)
#handles bothersome cases
tokens = map(self.__correct_spliting, tokens)
#write #write
with open(self.__write_to, 'wb') as write_obj: with open(self.__write_to, 'wb') as write_obj:

1
src/calibre/gui2/actions/device.py
View File

@ -94,6 +94,7 @@ class ShareConnMenu(QMenu): # {{{
I('mail.png'), _('Email to') + ' ' +account) I('mail.png'), _('Email to') + ' ' +account)
self.addAction(ac) self.addAction(ac)
self.email_actions.append(ac) self.email_actions.append(ac)
ac.a_s.connect(sync_menu.action_triggered)
action1.a_s.connect(sync_menu.action_triggered) action1.a_s.connect(sync_menu.action_triggered)
action2.a_s.connect(sync_menu.action_triggered) action2.a_s.connect(sync_menu.action_triggered)
ac = self.addMenu(self.email_to_and_delete_menu) ac = self.addMenu(self.email_to_and_delete_menu)