def _getobj_parse(self, pos, objid):
self._parser.seek(pos)
(_, objid1) = self._parser.nexttoken() # objid
if objid1 != objid:
raise PDFSyntaxError('objid mismatch: %r=%r' % (objid1, objid))
(_, genno) = self._parser.nexttoken() # genno
(_, kwd) = self._parser.nexttoken()
if kwd is not self.KEYWORD_OBJ:
raise PDFSyntaxError('Invalid object spec: offset=%r' % pos)
(_, obj) = self._parser.nextobject()
return obj
def __init__(self, parser, password='', caching=True, fallback=True):
"Set the document to use a given PDFParser object."
self.caching = caching
self.xrefs = []
self.info = []
self.catalog = None
self.encryption = None
self.decipher = None
self._parser = None
self._cached_objs = {}
self._parsed_objs = {}
self._parser = parser
self._parser.set_document(self)
self.is_printable = self.is_modifiable = self.is_extractable = True
# Retrieve the information of each header that was appended
# (maybe multiple times) at the end of the document.
try:
pos = self.find_xref(parser)
self.read_xref_from(parser, pos, self.xrefs)
except PDFNoValidXRef:
fallback = True
if fallback:
parser.fallback = True
xref = PDFXRefFallback()
xref.load(parser)
self.xrefs.append(xref)
for xref in self.xrefs:
trailer = xref.get_trailer()
if not trailer:
continue
# If there's an encryption info, remember it.
if 'Encrypt' in trailer:
#assert not self.encryption
self.encryption = (list_value(trailer['ID']),
dict_value(trailer['Encrypt']))
self._initialize_password(password)
if 'Info' in trailer:
self.info.append(dict_value(trailer['Info']))
if 'Root' in trailer:
# Every PDF file must have exactly one /Root dictionary.
self.catalog = dict_value(trailer['Root'])
break
else:
raise PDFSyntaxError('No /Root object! - Is this really a PDF?')
if self.catalog.get('Type') is not LITERAL_CATALOG:
if STRICT:
raise PDFSyntaxError('Catalog not found!')
return
def _get_objects(self, stream):
if stream.get('Type') is not LITERAL_OBJSTM:
if STRICT:
raise PDFSyntaxError('Not a stream object: %r' % stream)
try:
n = stream['N']
except KeyError:
if STRICT:
raise PDFSyntaxError('N is not defined: %r' % stream)
n = 0
parser = PDFStreamParser(stream.get_data())
parser.set_document(self)
objs = []
try:
while 1:
(_, obj) = parser.nextobject()
objs.append(obj)
except PSEOF:
pass
return (objs, n)
def _getobj_objstm(self, stream, index, objid):
if stream.objid in self._parsed_objs:
(objs, n) = self._parsed_objs[stream.objid]
else:
(objs, n) = self._get_objects(stream)
if self.caching:
self._parsed_objs[stream.objid] = (objs, n)
i = n * 2 + index
try:
obj = objs[i]
except IndexError:
raise PDFSyntaxError('index too big: %r' % index)
return obj
def load(self, parser, debug=0):
parser.seek(0)
while 1:
try:
(pos, line) = parser.nextline()
except PSEOF:
break
if line.startswith('trailer'):
parser.seek(pos)
self.load_trailer(parser)
if 1 <= debug:
print >> sys.stderr, 'trailer: %r' % self.get_trailer()
break
m = self.PDFOBJ_CUE.match(line)
if not m:
continue
(objid, genno) = m.groups()
objid = int(objid)
genno = int(genno)
self.offsets[objid] = (None, pos, genno)
# expand ObjStm.
parser.seek(pos)
(_, obj) = parser.nextobject()
if isinstance(obj,
PDFStream) and obj.get('Type') is LITERAL_OBJSTM:
stream = stream_value(obj)
try:
n = stream['N']
except KeyError:
if STRICT:
raise PDFSyntaxError('N is not defined: %r' % stream)
n = 0
parser1 = PDFStreamParser(stream.get_data())
objs = []
try:
while 1:
(_, obj) = parser1.nextobject()
objs.append(obj)
except PSEOF:
pass
n = min(n, len(objs) // 2)
for index in xrange(n):
objid1 = objs[index * 2]
self.offsets[objid1] = (objid, index, 0)
return
def load(self, parser, debug=0):
(_, objid) = parser.nexttoken() # ignored
(_, genno) = parser.nexttoken() # ignored
(_, kwd) = parser.nexttoken()
(_, stream) = parser.nextobject()
if not isinstance(stream, PDFStream) or stream['Type'] is not LITERAL_XREF:
raise PDFNoValidXRef('Invalid PDF stream spec.')
size = stream['Size']
index_array = stream.get('Index', (0, size))
if len(index_array) % 2 != 0:
raise PDFSyntaxError('Invalid index number')
self.ranges.extend(choplist(2, index_array))
(self.fl1, self.fl2, self.fl3) = stream['W']
self.data = stream.get_data()
self.entlen = self.fl1+self.fl2+self.fl3
self.trailer = stream.attrs
if 1 <= debug:
print >>sys.stderr, ('xref stream: objid=%s, fields=%d,%d,%d' %
(', '.join(map(repr, self.ranges)),
self.fl1, self.fl2, self.fl3))
return