def init_params(self):
self.v = int_value(self.param.get('V', 0))
self.r = int_value(self.param['R'])
self.p = int_value(self.param['P'])
self.o = str_value(self.param['O'])
self.u = str_value(self.param['U'])
self.length = int_value(self.param.get('Length', 40))
def read_xref_from(self, start, xrefs):
"""Reads XRefs from the given location."""
self.seek(start)
self.reset()
try:
(pos, token) = self.nexttoken()
except PSEOF:
raise PDFNoValidXRef('Unexpected EOF')
if 2 <= self.debug:
print >>sys.stderr, 'read_xref_from: start=%d, token=%r' % (start, token)
if isinstance(token, int):
# XRefStream: PDF-1.5
self.seek(pos)
self.reset()
xref = PDFXRefStream()
xref.load(self, debug=self.debug)
else:
if token is self.KEYWORD_XREF:
self.nextline()
xref = PDFXRef()
xref.load(self, debug=self.debug)
xrefs.append(xref)
trailer = xref.get_trailer()
if 1 <= self.debug:
print >>sys.stderr, 'trailer: %r' % trailer
if 'XRefStm' in trailer:
pos = int_value(trailer['XRefStm'])
self.read_xref_from(pos, xrefs)
if 'Prev' in trailer:
# find previous xref
pos = int_value(trailer['Prev'])
self.read_xref_from(pos, xrefs)
return
def read_xref_from(self, parser, start, xrefs):
"""Reads XRefs from the given location."""
parser.seek(start)
parser.reset()
try:
(pos, token) = parser.nexttoken()
except PSEOF:
raise PDFNoValidXRef('Unexpected EOF')
logging.info('read_xref_from: start=%d, token=%r' % (start, token))
if isinstance(token, int):
# XRefStream: PDF-1.5
parser.seek(pos)
parser.reset()
xref = PDFXRefStream()
xref.load(parser)
else:
if token is parser.KEYWORD_XREF:
parser.nextline()
xref = PDFXRef()
xref.load(parser)
xrefs.append(xref)
trailer = xref.get_trailer()
logging.info('trailer: %r' % trailer)
if 'XRefStm' in trailer:
pos = int_value(trailer['XRefStm'])
self.read_xref_from(parser, pos, xrefs)
if 'Prev' in trailer:
# find previous xref
pos = int_value(trailer['Prev'])
self.read_xref_from(parser, pos, xrefs)
return
def read_xref_from(self, parser, start, xrefs):
"""Reads XRefs from the given location."""
parser.seek(start)
parser.reset()
try:
(pos, token) = parser.nexttoken()
except PSEOF:
raise PDFNoValidXRef('Unexpected EOF')
if 2 <= self.debug:
print >> sys.stderr, 'read_xref_from: start=%d, token=%r' % (start,
token)
if isinstance(token, int):
# XRefStream: PDF-1.5
parser.seek(pos)
parser.reset()
xref = PDFXRefStream()
xref.load(parser, debug=self.debug)
else:
if token is parser.KEYWORD_XREF:
parser.nextline()
xref = PDFXRef()
xref.load(parser, debug=self.debug)
xrefs.append(xref)
trailer = xref.get_trailer()
if 1 <= self.debug:
print >> sys.stderr, 'trailer: %r' % trailer
if 'XRefStm' in trailer:
pos = int_value(trailer['XRefStm'])
self.read_xref_from(parser, pos, xrefs)
if 'Prev' in trailer:
# find previous xref
pos = int_value(trailer['Prev'])
self.read_xref_from(parser, pos, xrefs)
return
def initialize(self, password=''):
"""Perform the initialization with a given password.
This step is mandatory even if there's no password associated with the document.
"""
if not self.encryption:
self.is_printable = self.is_modifiable = self.is_extractable = True
return
(docid, param) = self.encryption
if literal_name(param.get('Filter')) != 'Standard':
raise PDFEncryptionError('Unknown filter: param=%r' % param)
V = int_value(param.get('V', 0))
if not (V == 1 or V == 2):
raise PDFEncryptionError('Unknown algorithm: param=%r' % param)
length = int_value(param.get('Length', 40)) # Key length (bits)
O = str_value(param['O'])
R = int_value(param['R']) # Revision
if 5 <= R:
raise PDFEncryptionError('Unknown revision: %r' % R)
U = str_value(param['U'])
P = int_value(param['P'])
self.is_printable = bool(P & 4)
self.is_modifiable = bool(P & 8)
self.is_extractable = bool(P & 16)
# Algorithm 3.2
password = (password + self.PASSWORD_PADDING)[:32] # 1
md5hash = md5.md5(password) # 2
md5hash.update(O) # 3
md5hash.update(struct.pack('<l', P)) # 4
md5hash.update(docid[0]) # 5
if 4 <= R:
# 6
raise PDFNotImplementedError('Revision 4 encryption is currently unsupported')
if 3 <= R:
# 8
for _ in xrange(50):
md5hash = md5.md5(md5hash.digest()[:length / 8])
key = md5hash.digest()[:length / 8]
if R == 2:
# Algorithm 3.4
u1 = Arcfour(key).process(self.PASSWORD_PADDING)
elif R == 3:
# Algorithm 3.5
md5hash = md5.md5(self.PASSWORD_PADDING) # 2
md5hash.update(docid[0]) # 3
x = Arcfour(key).process(md5hash.digest()[:16]) # 4
for i in xrange(1, 19 + 1):
k = ''.join(chr(ord(c) ^ i) for c in key)
x = Arcfour(k).process(x)
u1 = x + x # 32bytes total
if R == 2:
is_authenticated = (u1 == U)
else:
is_authenticated = (u1[:16] == U[:16])
if not is_authenticated:
raise PDFPasswordIncorrect
self.decrypt_key = key
self.decipher = self.decrypt_rc4 # XXX may be AES
def initialize(self, password=''):
if not self.encryption:
self.is_printable = self.is_modifiable = self.is_extractable = True
self._initialized = True
return
(docid, param) = self.encryption
if literal_name(param['Filter']) != 'Standard':
raise PDFEncryptionError('Unknown filter: param=%r' % param)
V = int_value(param.get('V', 0))
if not (V == 1 or V == 2):
raise PDFEncryptionError('Unknown algorithm: param=%r' % param)
length = int_value(param.get('Length', 40)) # Key length (bits)
O = str_value(param['O'])
R = int_value(param['R']) # Revision
if 5 <= R:
raise PDFEncryptionError('Unknown revision: %r' % R)
U = str_value(param['U'])
P = int_value(param['P'])
self.is_printable = bool(P & 4)
self.is_modifiable = bool(P & 8)
self.is_extractable = bool(P & 16)
# Algorithm 3.2
password = (password + self.PASSWORD_PADDING)[:32] # 1
hash = md5.md5(password) # 2
hash.update(O) # 3
hash.update(struct.pack('<l', P)) # 4
hash.update(docid[0]) # 5
if 4 <= R:
# 6
raise PDFNotImplementedError(
'Revision 4 encryption is currently unsupported')
if 3 <= R:
# 8
for _ in xrange(50):
hash = md5.md5(hash.digest()[:length / 8])
key = hash.digest()[:length / 8]
if R == 2:
# Algorithm 3.4
u1 = Arcfour(key).process(self.PASSWORD_PADDING)
elif R == 3:
# Algorithm 3.5
hash = md5.md5(self.PASSWORD_PADDING) # 2
hash.update(docid[0]) # 3
x = Arcfour(key).process(hash.digest()[:16]) # 4
for i in xrange(1, 19 + 1):
k = ''.join(chr(ord(c) ^ i) for c in key)
x = Arcfour(k).process(x)
u1 = x + x # 32bytes total
if R == 2:
is_authenticated = (u1 == U)
else:
is_authenticated = (u1[:16] == U[:16])
if not is_authenticated:
raise PDFPasswordIncorrect
self.decrypt_key = key
self.decipher = self.decrypt_rc4 # XXX may be AES
self._initialized = True
return
def __init__(self, rsrcmgr, spec):
firstchar = int_value(spec.get("FirstChar", 0))
lastchar = int_value(spec.get("LastChar", 0))
widths = list_value(spec.get("Widths", [0] * 256))
widths = dict((i + firstchar, w) for (i, w) in enumerate(widths))
if "FontDescriptor" in spec:
descriptor = dict_value(spec["FontDescriptor"])
else:
descriptor = {"Ascent": 0, "Descent": 0, "FontBBox": spec["FontBBox"]}
PDFSimpleFont.__init__(self, descriptor, widths, spec)
self.matrix = tuple(list_value(spec.get("FontMatrix")))
(_, self.descent, _, self.ascent) = self.bbox
(self.hscale, self.vscale) = apply_matrix_norm(self.matrix, (1, 1))
return
def __init__(self, rsrcmgr, spec):
firstchar = int_value(spec.get('FirstChar', 0))
lastchar = int_value(spec.get('LastChar', 0))
widths = list_value(spec.get('Widths', [0] * 256))
widths = dict((i + firstchar, w) for (i, w) in enumerate(widths))
if 'FontDescriptor' in spec:
descriptor = dict_value(spec['FontDescriptor'])
else:
descriptor = {'Ascent': 0, 'Descent': 0,
'FontBBox': spec['FontBBox']}
PDFSimpleFont.__init__(self, descriptor, widths, spec)
self.matrix = tuple(list_value(spec.get('FontMatrix')))
(_, self.descent, _, self.ascent) = self.bbox
(self.hscale, self.vscale) = apply_matrix_norm(self.matrix, (1, 1))
def __init__(self, rsrcmgr, spec):
firstchar = int_value(spec.get('FirstChar', 0))
lastchar = int_value(spec.get('LastChar', 0))
widths = list_value(spec.get('Widths', [0]*256))
widths = dict( (i+firstchar,w) for (i,w) in enumerate(widths))
if 'FontDescriptor' in spec:
descriptor = dict_value(spec['FontDescriptor'])
else:
descriptor = {'Ascent':0, 'Descent':0,
'FontBBox':spec['FontBBox']}
PDFSimpleFont.__init__(self, descriptor, widths, spec)
self.matrix = tuple(list_value(spec.get('FontMatrix')))
(_,self.descent,_,self.ascent) = self.bbox
(self.hscale,self.vscale) = apply_matrix_norm(self.matrix, (1,1))
return
def __init__(self, doc, pageid, attrs):
"""Initialize a page object.
doc: a PDFDocument object.
pageid: any Python object that can uniquely identify the page.
attrs: a dictionary of page attributes.
"""
self.doc = doc
self.pageid = pageid
self.attrs = dict_value(attrs)
self.lastmod = resolve1(self.attrs.get('LastModified'))
self.resources = resolve1(self.attrs['Resources'])
self.mediabox = resolve1(self.attrs['MediaBox'])
if 'CropBox' in self.attrs:
self.cropbox = resolve1(self.attrs['CropBox'])
else:
self.cropbox = self.mediabox
self.rotate = (int_value(self.attrs.get('Rotate', 0))+360) % 360
self.annots = self.attrs.get('Annots')
self.beads = self.attrs.get('B')
if 'Contents' in self.attrs:
contents = resolve1(self.attrs['Contents'])
else:
contents = []
if not isinstance(contents, list):
contents = [ contents ]
self.contents = contents
return
def __init__(self, doc, pageid, attrs):
"""Initialize a page object.
doc: a PDFDocument object.
pageid: any Python object that can uniquely identify the page.
attrs: a dictionary of page attributes.
"""
self.doc = doc
self.pageid = pageid
self.attrs = dict_value(attrs)
self.lastmod = resolve1(self.attrs.get('LastModified'))
self.resources = resolve1(self.attrs['Resources'])
self.mediabox = resolve1(self.attrs['MediaBox'])
if 'CropBox' in self.attrs:
self.cropbox = resolve1(self.attrs['CropBox'])
else:
self.cropbox = self.mediabox
self.rotate = (int_value(self.attrs.get('Rotate', 0)) + 360) % 360
self.annots = self.attrs.get('Annots')
self.beads = self.attrs.get('B')
if 'Contents' in self.attrs:
contents = resolve1(self.attrs['Contents'])
else:
contents = []
if not isinstance(contents, list):
contents = [contents]
self.contents = contents
return
def do_keyword(self, pos, token):
"""Handles PDF-related keywords."""
if token in (self.KEYWORD_XREF, self.KEYWORD_STARTXREF):
self.add_results(*self.pop(1))
elif token is self.KEYWORD_ENDOBJ:
self.add_results(*self.pop(4))
elif token is self.KEYWORD_NULL:
# null object
self.push((pos, None))
elif token is self.KEYWORD_R:
# reference to indirect object
try:
((_, objid), (_, genno)) = self.pop(2)
(objid, genno) = (int(objid), int(genno))
obj = PDFObjRef(self.doc, objid, genno)
self.push((pos, obj))
except PSSyntaxError:
pass
elif token is self.KEYWORD_STREAM:
# stream object
((_, dic),) = self.pop(1)
dic = dict_value(dic)
objlen = 0
if not self.fallback:
try:
objlen = int_value(dic['Length'])
except KeyError:
handle_error(PDFSyntaxError, '/Length is undefined: %r' % dic)
self.seek(pos)
try:
(_, line) = self.nextline() # 'stream'
except PSEOF:
handle_error(PDFSyntaxError, 'Unexpected EOF')
return
pos += len(line)
self.fp.seek(pos)
data = self.fp.read(objlen)
self.seek(pos + objlen)
while 1:
try:
(linepos, line) = self.nextline()
except PSEOF:
handle_error(PDFSyntaxError, 'Unexpected EOF')
break
if 'endstream' in line:
i = line.index('endstream')
objlen += i
data += line[:i]
break
objlen += len(line)
data += line
self.seek(pos+objlen)
# XXX limit objlen not to exceed object boundary
log.debug('Stream: pos=%d, objlen=%d, dic=%r, data=%r...', pos, objlen, dic, data[:10])
obj = PDFStream(dic, data, self.doc.decipher)
self.push((pos, obj))
else:
# others
self.push((pos, token))
def __init__(self, rsrc, spec):
try:
self.basefont = literal_name(spec['BaseFont'])
except KeyError:
if STRICT:
raise PDFFontError('BaseFont is missing')
self.basefont = 'unknown'
try:
(descriptor, widths) = FontMetricsDB.get_metrics(self.basefont)
except KeyError:
descriptor = dict_value(spec.get('FontDescriptor', {}))
firstchar = int_value(spec.get('FirstChar', 0))
lastchar = int_value(spec.get('LastChar', 255))
widths = list_value(spec.get('Widths', [0]*256))
widths = dict( (i+firstchar,w) for (i,w) in enumerate(widths) )
PDFSimpleFont.__init__(self, descriptor, widths, spec)
return
def __init__(self, rsrc, spec):
try:
self.basefont = literal_name(spec['BaseFont'])
except KeyError:
if STRICT:
raise PDFFontError('BaseFont is missing')
self.basefont = 'unknown'
try:
(descriptor, widths) = FontMetricsDB.get_metrics(self.basefont)
except KeyError:
descriptor = dict_value(spec.get('FontDescriptor', {}))
firstchar = int_value(spec.get('FirstChar', 0))
lastchar = int_value(spec.get('LastChar', 255))
widths = list_value(spec.get('Widths', [0] * 256))
widths = dict((i + firstchar, w) for (i, w) in enumerate(widths))
PDFSimpleFont.__init__(self, descriptor, widths, spec)
return
def __init__(self, rsrcmgr, spec):
try:
self.basefont = literal_name(spec['BaseFont'])
except KeyError:
handle_error(PDFFontError, 'BaseFont is missing')
self.basefont = 'unknown'
try:
(descriptor, widths) = FontMetricsDB.get_metrics(self.basefont)
except KeyError:
descriptor = dict_value(spec.get('FontDescriptor', {}))
firstchar = int_value(spec.get('FirstChar', 0))
lastchar = int_value(spec.get('LastChar', 255))
widths = list_value(spec.get('Widths', [0] * 256))
widths = dict((i+firstchar, w) for (i, w) in enumerate(widths))
PDFSimpleFont.__init__(self, descriptor, widths, spec)
if 'Encoding' not in spec and 'FontFile' in descriptor:
# try to recover the missing encoding info from the font file.
self.fontfile = stream_value(descriptor.get('FontFile'))
length1 = int_value(self.fontfile['Length1'])
data = self.fontfile.get_data()[:length1]
parser = Type1FontHeaderParser(StringIO(data))
self.cid2unicode = parser.get_encoding()
def __init__(self, descriptor, widths, default_width=None):
self.descriptor = descriptor
self.widths = widths
self.fontname = resolve1(descriptor.get('FontName', 'unknown'))
if isinstance(self.fontname, PSLiteral):
self.fontname = literal_name(self.fontname)
self.flags = int_value(descriptor.get('Flags', 0))
self.ascent = num_value(descriptor.get('Ascent', 0))
self.descent = num_value(descriptor.get('Descent', 0))
self.italic_angle = num_value(descriptor.get('ItalicAngle', 0))
self.default_width = default_width or num_value(descriptor.get('MissingWidth', 0))
self.leading = num_value(descriptor.get('Leading', 0))
self.bbox = list_value(descriptor.get('FontBBox', (0, 0, 0, 0)))
self.hscale = self.vscale = .001
def __init__(self, rsrcmgr, spec):
try:
self.basefont = literal_name(spec["BaseFont"])
except KeyError:
if STRICT:
raise PDFFontError("BaseFont is missing")
self.basefont = "unknown"
try:
(descriptor, widths) = FontMetricsDB.get_metrics(self.basefont)
except KeyError:
descriptor = dict_value(spec.get("FontDescriptor", {}))
firstchar = int_value(spec.get("FirstChar", 0))
lastchar = int_value(spec.get("LastChar", 255))
widths = list_value(spec.get("Widths", [0] * 256))
widths = dict((i + firstchar, w) for (i, w) in enumerate(widths))
PDFSimpleFont.__init__(self, descriptor, widths, spec)
if "Encoding" not in spec and "FontFile" in descriptor:
# try to recover the missing encoding info from the font file.
self.fontfile = stream_value(descriptor.get("FontFile"))
length1 = int_value(self.fontfile["Length1"])
data = self.fontfile.get_data()[:length1]
parser = Type1FontHeaderParser(StringIO(data))
self.cid2unicode = parser.get_encoding()
return
def __init__(self, rsrcmgr, spec):
try:
self.basefont = literal_name(spec['BaseFont'])
except KeyError:
if STRICT:
raise PDFFontError('BaseFont is missing')
self.basefont = 'unknown'
try:
(descriptor, widths) = FontMetricsDB.get_metrics(self.basefont)
except KeyError:
descriptor = dict_value(spec.get('FontDescriptor', {}))
firstchar = int_value(spec.get('FirstChar', 0))
lastchar = int_value(spec.get('LastChar', 255))
widths = list_value(spec.get('Widths', [0]*256))
widths = dict( (i+firstchar,w) for (i,w) in enumerate(widths) )
PDFSimpleFont.__init__(self, descriptor, widths, spec)
if 'Encoding' not in spec and 'FontFile' in descriptor:
# try to recover the missing encoding info from the font file.
self.fontfile = stream_value(descriptor.get('FontFile'))
length1 = int_value(self.fontfile['Length1'])
data = self.fontfile.get_data()[:length1]
parser = Type1FontHeaderParser(StringIO(data))
self.cid2unicode = parser.get_encoding()
return
def __init__(self, descriptor, widths, default_width=None):
self.descriptor = descriptor
self.widths = widths
self.fontname = resolve1(descriptor.get('FontName', 'unknown'))
if isinstance(self.fontname, PSLiteral):
self.fontname = literal_name(self.fontname)
self.flags = int_value(descriptor.get('Flags', 0))
self.ascent = num_value(descriptor.get('Ascent', 0))
self.descent = num_value(descriptor.get('Descent', 0))
self.italic_angle = num_value(descriptor.get('ItalicAngle', 0))
self.default_width = default_width or num_value(descriptor.get('MissingWidth', 0))
self.leading = num_value(descriptor.get('Leading', 0))
self.bbox = list_value(descriptor.get('FontBBox', (0,0,0,0)))
self.hscale = self.vscale = .001
return
def _initialize_password(self, password=''):
(docid, param) = self.encryption
if literal_name(param.get('Filter')) != 'Standard':
raise PDFEncryptionError('Unknown filter: param=%r' % param)
v = int_value(param.get('V', 0))
factory = self.security_handler_registry.get(v)
if factory is None:
raise PDFEncryptionError('Unknown algorithm: param=%r' % param)
handler = factory(docid, param, password)
self.decipher = handler.decrypt
self.is_printable = handler.is_printable()
self.is_modifiable = handler.is_modifiable()
self.is_extractable = handler.is_extractable()
self._parser.fallback = False # need to read streams with exact length
return
def __init__(self, descriptor, widths, default_width=None):
self.descriptor = descriptor
self.widths = widths
self.fontname = resolve1(descriptor.get("FontName", "unknown"))
if isinstance(self.fontname, PSLiteral):
self.fontname = literal_name(self.fontname)
self.flags = int_value(descriptor.get("Flags", 0))
self.ascent = num_value(descriptor.get("Ascent", 0))
self.descent = num_value(descriptor.get("Descent", 0))
self.italic_angle = num_value(descriptor.get("ItalicAngle", 0))
self.default_width = default_width or num_value(descriptor.get("MissingWidth", 0))
self.leading = num_value(descriptor.get("Leading", 0))
self.bbox = list_value(descriptor.get("FontBBox", (0, 0, 0, 0)))
self.hscale = self.vscale = 0.001
return
def do_keyword(self, pos, token):
"""Handles PDF-related keywords."""
if token in (self.KEYWORD_XREF, self.KEYWORD_STARTXREF):
self.add_results(*self.pop(1))
elif token is self.KEYWORD_ENDOBJ:
self.add_results(*self.pop(4))
elif token is self.KEYWORD_NULL:
# null object
self.push((pos, None))
elif token is self.KEYWORD_R:
# reference to indirect object
try:
((_,objid), (_,genno)) = self.pop(2)
(objid, genno) = (int(objid), int(genno))
obj = PDFObjRef(self.doc, objid, genno)
self.push((pos, obj))
except PSSyntaxError:
pass
elif token is self.KEYWORD_STREAM:
# stream object
((_,dic),) = self.pop(1)
dic = dict_value(dic)
objlen = 0
if not self.fallback:
try:
objlen = int_value(dic['Length'])
except KeyError:
if STRICT:
raise PDFSyntaxError('/Length is undefined: %r' % dic)
self.seek(pos)
try:
(_, line) = self.nextline() # 'stream'
except PSEOF:
if STRICT:
raise PDFSyntaxError('Unexpected EOF')
return
pos += len(line)
self.fp.seek(pos)
data = self.fp.read(objlen)
self.seek(pos+objlen)
while 1:
try:
(linepos, line) = self.nextline()
except PSEOF:
if STRICT:
raise PDFSyntaxError('Unexpected EOF')
break
if 'endstream' in line:
i = line.index('endstream')
objlen += i
data += line[:i]
break
objlen += len(line)
data += line
self.seek(pos+objlen)
# XXX limit objlen not to exceed object boundary
if 2 <= self.debug:
print >>sys.stderr, 'Stream: pos=%d, objlen=%d, dic=%r, data=%r...' % \
(pos, objlen, dic, data[:10])
obj = PDFStream(dic, data, self.doc.decipher)
self.push((pos, obj))
else:
# others
self.push((pos, token))
return
def do_keyword(self, pos, token):
if token in (self.KEYWORD_XREF, self.KEYWORD_STARTXREF):
self.add_results(*self.pop(1))
return
if token is self.KEYWORD_ENDOBJ:
self.add_results(*self.pop(4))
return
if token is self.KEYWORD_R:
# reference to indirect object
try:
((_,objid), (_,genno)) = self.pop(2)
(objid, genno) = (int(objid), int(genno))
obj = PDFObjRef(self.doc, objid, genno)
self.push((pos, obj))
except PSSyntaxError:
pass
return
if token is self.KEYWORD_STREAM:
# stream object
((_,dic),) = self.pop(1)
dic = dict_value(dic)
try:
objlen = int_value(dic['Length'])
except KeyError:
if STRICT:
raise PDFSyntaxError('/Length is undefined: %r' % dic)
objlen = 0
self.seek(pos)
try:
(_, line) = self.nextline() # 'stream'
except PSEOF:
if STRICT:
raise PDFSyntaxError('Unexpected EOF')
return
pos += len(line)
self.fp.seek(pos)
data = self.fp.read(objlen)
self.seek(pos+objlen)
while 1:
try:
(linepos, line) = self.nextline()
except PSEOF:
if STRICT:
raise PDFSyntaxError('Unexpected EOF')
break
if 'endstream' in line:
i = line.index('endstream')
objlen += i
data += line[:i]
break
objlen += len(line)
data += line
self.seek(pos+objlen)
if 1 <= self.debug:
print >>stderr, 'Stream: pos=%d, objlen=%d, dic=%r, data=%r...' % \
(pos, objlen, dic, data[:10])
obj = PDFStream(dic, data, self.doc.decipher)
self.push((pos, obj))
return
# others
self.push((pos, token))
return
def __init__(self, doc, pageid, attrs):
"""Initialize a page object.
doc: a PDFDocument object.
pageid: any Python object that can uniquely identify the page.
attrs: a dictionary of page attributes.
"""
self.doc = doc
self.pageid = pageid
self.attrs = dict_value(attrs)
self.lastmod = resolve1(self.attrs.get('LastModified'))
self.resources = resolve1(self.attrs['Resources'])
self.mediabox = resolve1(self.attrs['MediaBox'])
if 'CropBox' in self.attrs:
self.cropbox = resolve1(self.attrs['CropBox'])
else:
self.cropbox = self.mediabox
self.rotate = (int_value(self.attrs.get('Rotate', 0))+360) % 360
self.annots = list_value(self.attrs.get('Annots'))
self.widgets = []
def get_widget_type(obj):
if 'FT' in obj:
if obj.get('FT') is LITERAL_TX:
return 'text'
elif obj.get('FT') is LITERAL_CH or obj.get('FT') is LITERAL_BTN:
return 'checkbox'
elif obj.get('FT') is LITERAL_SIG:
return 'signature'
else:
return None
def create_widget(obj):
if 'Subtype' in obj and obj.get('Subtype') is LITERAL_WIDGET:
wtype = get_widget_type(obj)
if wtype:
return LTWidget(list_value(obj.get('Rect')), wtype, str_value(obj.get('T')))
elif 'Parent' in obj:
p = resolve1(obj.get('Parent'))
return LTWidget(list_value(obj.get('Rect')), get_widget_type(p), str_value(p.get('T')))
def find_widgets(obj_list, widgets):
for an in obj_list:
try:
obj = resolve1(an)
except PDFObjectNotFound:
print 'object not found'
print an
widgets.append(create_widget(obj))
find_widgets(self.annots, self.widgets)
self.beads = self.attrs.get('B')
if 'Contents' in self.attrs:
contents = resolve1(self.attrs['Contents'])
else:
contents = []
if not isinstance(contents, list):
contents = [contents]
self.contents = contents
return
