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

Fix #908 (Error message when converting LIT file)

Browse Source
This commit is contained in:
Kovid Goyal 2008-07-25 16:30:54 -07:00
commit 4f4af05fa2
1 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
src/calibre/ebooks/lit/reader.py
View File

@ -93,6 +93,10 @@ def read_utf8_char(bytes, pos):
c = (c << 6) | (b & 0x3F) c = (c << 6) | (b & 0x3F)
return unichr(c), pos+elsize return unichr(c), pos+elsize
def consume_utf8_length(bytes):
char, elsize = read_utf8_char(bytes, 0)
return ord(char), bytes[elsize:]
class UnBinary(object): class UnBinary(object):
AMPERSAND_RE = re.compile( AMPERSAND_RE = re.compile(
r'&(?!(?:#[0-9]+|#x[0-9a-fA-F]+|[a-zA-Z_:][a-zA-Z0-9.-_:]+);)') r'&(?!(?:#[0-9]+|#x[0-9a-fA-F]+|[a-zA-Z_:][a-zA-Z0-9.-_:]+);)')
@ -315,8 +319,11 @@ class ManifestItem(object):
self.offset = offset self.offset = offset
self.root = root self.root = root
self.state = state self.state = state
# Some LIT files have Windows-style paths
path = original.replace('\\', '/')
if path[1:3] == ':/': path = path[2:]
# Some paths in Fictionwise "multiformat" LIT files contain '..' (!?) # Some paths in Fictionwise "multiformat" LIT files contain '..' (!?)
path = os.path.normpath(original).replace('\\', '/') path = os.path.normpath(path).replace('\\', '/')
while path.startswith('../'): path = path[3:] while path.startswith('../'): path = path[3:]
self.path = path self.path = path
@ -557,14 +564,15 @@ class LitReader(object):
if len(raw) < 5: if len(raw) < 5:
raise LitError('Truncated manifest') raise LitError('Truncated manifest')
offset, raw = u32(raw), raw[4:] offset, raw = u32(raw), raw[4:]
slen, raw = ord(raw[0]), raw[1:] slen, raw = consume_utf8_length(raw)
internal, raw = raw[:slen].decode('utf8'), raw[slen:] internal, raw = raw[:slen].decode('utf8'), raw[slen:]
slen, raw = ord(raw[0]), raw[1:] slen, raw = consume_utf8_length(raw)
original, raw = raw[:slen].decode('utf8'), raw[slen:] original, raw = raw[:slen].decode('utf8'), raw[slen:]
slen, raw = ord(raw[0]), raw[1:] slen, raw = consume_utf8_length(raw)
mime_type, raw = raw[:slen].decode('utf8'), raw[slen+1:] mime_type, raw = raw[:slen].decode('utf8'), raw[slen+1:]
self.manifest[internal] = ManifestItem( self.manifest[internal] = ManifestItem(
original, internal, mime_type, offset, root, state) original, internal, mime_type, offset, root, state)
# Remove any common path elements
mlist = self.manifest.values() mlist = self.manifest.values()
shared = mlist[0].path shared = mlist[0].path
for item in mlist[1:]: for item in mlist[1:]:
@ -578,6 +586,10 @@ class LitReader(object):
slen = len(shared) slen = len(shared)
for item in mlist: for item in mlist:
item.path = item.path[slen:] item.path = item.path[slen:]
# Fix any straggling absolute paths
for item in mlist:
if item.path[0] == '/':
item.path = os.path.basename(item.path)
def _read_meta(self): def _read_meta(self):
raw = self.get_file('/meta') raw = self.get_file('/meta')