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):
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 _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 _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)