def get_colorspace(spec):
if isinstance(spec, list):
name = literal_name(spec[0])
else:
name = literal_name(spec)
if name == 'ICCBased' and isinstance(spec, list) and 2 <= len(spec):
return PDFColorSpace(name, stream_value(spec[1])['N'])
elif name == 'DeviceN' and isinstance(spec, list) and 2 <= len(spec):
return PDFColorSpace(name, len(list_value(spec[1])))
else:
return PREDEFINED_COLORSPACE[name]
def do_Do(self, xobjid):
xobjid = literal_name(xobjid)
try:
xobj = stream_value(self.xobjmap[xobjid])
except KeyError:
if STRICT:
raise PDFInterpreterError('Undefined xobject id: %r' % xobjid)
return
if 1 <= self.debug:
print(('Processing xobj: %r' % xobj))
subtype = xobj.get('Subtype')
if subtype is LITERAL_FORM and 'BBox' in xobj:
interpreter = self.dup()
bbox = list_value(xobj['BBox'])
matrix = list_value(xobj.get('Matrix', MATRIX_IDENTITY))
# According to PDF reference 1.7 section 4.9.1, XObjects in
# earlier PDFs (prior to v1.2) use the page's Resources entry
# instead of having their own Resources entry.
resources = dict_value(xobj.get('Resources')) or self.resources.copy()
self.device.begin_figure(xobjid, bbox, matrix)
interpreter.render_contents(resources, [xobj], ctm=mult_matrix(matrix, self.ctm))
self.device.end_figure(xobjid)
elif subtype is LITERAL_IMAGE and 'Width' in xobj and 'Height' in xobj:
self.device.begin_figure(xobjid, (0,0,1,1), MATRIX_IDENTITY)
self.device.render_image(xobjid, xobj)
self.device.end_figure(xobjid)
else:
# unsupported xobject type.
pass
return
def do_Tf(self, fontid, fontsize):
try:
self.textstate.font = self.fontmap[literal_name(fontid)]
except KeyError:
raise
if STRICT:
raise PDFInterpreterError('Undefined Font id: %r' % fontid)
return
self.textstate.fontsize = fontsize
return
def initialize(self, password=''):
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
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 range(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 range(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
return
def __init__(self, descriptor, widths, spec):
# Font encoding is specified either by a name of
# built-in encoding or a dictionary that describes
# the differences.
if "Encoding" in spec:
encoding = resolve1(spec["Encoding"])
else:
encoding = LITERAL_STANDARD_ENCODING
if isinstance(encoding, dict):
name = literal_name(encoding.get("BaseEncoding", LITERAL_STANDARD_ENCODING))
diff = list_value(encoding.get("Differences", None))
self.cid2unicode = EncodingDB.get_encoding(name, diff)
else:
self.cid2unicode = EncodingDB.get_encoding(literal_name(encoding))
self.unicode_map = None
if "ToUnicode" in spec:
strm = stream_value(spec["ToUnicode"])
self.unicode_map = FileUnicodeMap()
CMapParser(self.unicode_map, StringIO(strm.get_data())).run()
PDFFont.__init__(self, descriptor, widths)
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 get_font(self, objid, spec):
if objid and objid in self._cached_fonts:
font = self._cached_fonts[objid]
else:
if 2 <= self.debug:
print(('get_font: create: objid=%r, spec=%r' % (objid, spec)))
if STRICT:
if spec['Type'] is not LITERAL_FONT:
raise PDFFontError('Type is not /Font')
# Create a Font object.
if 'Subtype' in spec:
subtype = literal_name(spec['Subtype'])
else:
if STRICT:
raise PDFFontError('Font Subtype is not specified.')
subtype = 'Type1'
if subtype in ('Type1', 'MMType1'):
# Type1 Font
font = PDFType1Font(self, spec)
elif subtype == 'TrueType':
# TrueType Font
font = PDFTrueTypeFont(self, spec)
elif subtype == 'Type3':
# Type3 Font
font = PDFType3Font(self, spec)
elif subtype in ('CIDFontType0', 'CIDFontType2'):
# CID Font
font = PDFCIDFont(self, spec)
elif subtype == 'Type0':
# Type0 Font
dfonts = list_value(spec['DescendantFonts'])
assert dfonts
subspec = dict_value(dfonts[0]).copy()
for k in ('Encoding', 'ToUnicode'):
if k in spec:
subspec[k] = resolve1(spec[k])
font = self.get_font(None, subspec)
else:
if STRICT:
raise PDFFontError('Invalid Font spec: %r' % spec)
font = PDFType1Font(self, spec) # this is so wrong!
if objid and self.caching:
self._cached_fonts[objid] = font
return font
def do_keyword(self, pos, token):
if token is self.KEYWORD_BI:
# inline image within a content stream
self.start_type(pos, 'inline')
elif token is self.KEYWORD_ID:
try:
(_, objs) = self.end_type('inline')
if len(objs) % 2 != 0:
raise PSTypeError('Invalid dictionary construct: %r' % objs)
d = dict( (literal_name(k), v) for (k,v) in choplist(2, objs) )
(pos, data) = self.get_inline_data(pos+len('ID '))
obj = PDFStream(d, data)
self.push((pos, obj))
self.push((pos, self.KEYWORD_EI))
except PSTypeError:
if STRICT: raise
else:
self.push((pos, token))
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 do_cs(self, name):
self.ncs = self.csmap[literal_name(name)]
return
def do_CS(self, name):
self.scs = self.csmap[literal_name(name)]
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"
self.cidsysteminfo = dict_value(spec.get("CIDSystemInfo", {}))
self.cidcoding = "%s-%s" % (
self.cidsysteminfo.get("Registry", "unknown"),
self.cidsysteminfo.get("Ordering", "unknown"),
)
try:
name = literal_name(spec["Encoding"])
except KeyError:
if STRICT:
raise PDFFontError("Encoding is unspecified")
name = "unknown"
try:
self.cmap = CMapDB.get_cmap(name)
except CMapDB.CMapNotFound as e:
if STRICT:
raise PDFFontError(e)
self.cmap = CMap()
try:
descriptor = dict_value(spec["FontDescriptor"])
except KeyError:
if STRICT:
raise PDFFontError("FontDescriptor is missing")
descriptor = {}
ttf = None
if "FontFile2" in descriptor:
self.fontfile = stream_value(descriptor.get("FontFile2"))
ttf = TrueTypeFont(self.basefont, StringIO(self.fontfile.get_data()))
self.unicode_map = None
if "ToUnicode" in spec:
strm = stream_value(spec["ToUnicode"])
self.unicode_map = FileUnicodeMap()
CMapParser(self.unicode_map, StringIO(strm.get_data())).run()
elif self.cidcoding == "Adobe-Identity":
if ttf:
try:
self.unicode_map = ttf.create_unicode_map()
except TrueTypeFont.CMapNotFound:
pass
else:
try:
self.unicode_map = CMapDB.get_unicode_map(self.cidcoding, self.cmap.is_vertical())
except CMapDB.CMapNotFound as e:
pass
self.vertical = self.cmap.is_vertical()
if self.vertical:
# writing mode: vertical
widths = get_widths2(list_value(spec.get("W2", [])))
self.disps = dict((cid, (vx, vy)) for (cid, (_, (vx, vy))) in list(widths.items()))
(vy, w) = spec.get("DW2", [880, -1000])
self.default_disp = (None, vy)
widths = dict((cid, w) for (cid, (w, _)) in list(widths.items()))
default_width = w
else:
# writing mode: horizontal
self.disps = {}
self.default_disp = 0
widths = get_widths(list_value(spec.get("W", [])))
default_width = spec.get("DW", 1000)
PDFFont.__init__(self, descriptor, widths, default_width=default_width)
return
def do_keyword(self, pos, token):
if token is self.KEYWORD_PUT:
((_, key), (_, value)) = self.pop(2)
if isinstance(key, int) and isinstance(value, PSLiteral):
self.add_results((key, literal_name(value)))
return
def do_keyword(self, pos, token):
name = token.name
if name == 'begincmap':
self._in_cmap = True
self.popall()
return
elif name == 'endcmap':
self._in_cmap = False
return
if not self._in_cmap: return
#
if name == 'def':
try:
((_,k),(_,v)) = self.pop(2)
self.cmap.set_attr(literal_name(k), v)
except PSSyntaxError:
pass
return
if name == 'usecmap':
try:
((_,cmapname),) = self.pop(1)
self.cmap.use_cmap(CMapDB.get_cmap(literal_name(cmapname)))
except PSSyntaxError:
pass
except CMapDB.CMapNotFound:
pass
return
if name == 'begincodespacerange':
self.popall()
return
if name == 'endcodespacerange':
self.popall()
return
if name == 'begincidrange':
self.popall()
return
if name == 'endcidrange':
objs = [ obj for (_,obj) in self.popall() ]
for (s,e,cid) in choplist(3, objs):
if (not isinstance(s, str) or not isinstance(e, str) or
not isinstance(cid, int) or len(s) != len(e)): continue
sprefix = s[:-4]
eprefix = e[:-4]
if sprefix != eprefix: continue
svar = s[-4:]
evar = e[-4:]
s1 = nunpack(svar)
e1 = nunpack(evar)
vlen = len(svar)
#assert s1 <= e1
for i in range(e1-s1+1):
x = sprefix+struct.pack('>L',s1+i)[-vlen:]
self.cmap.add_code2cid(x, cid+i)
return
if name == 'begincidchar':
self.popall()
return
if name == 'endcidchar':
objs = [ obj for (_,obj) in self.popall() ]
for (cid,code) in choplist(2, objs):
if isinstance(code, str) and isinstance(cid, str):
self.cmap.add_code2cid(code, nunpack(cid))
return
if name == 'beginbfrange':
self.popall()
return
if name == 'endbfrange':
objs = [ obj for (_,obj) in self.popall() ]
for (s,e,code) in choplist(3, objs):
if (not isinstance(s, str) or not isinstance(e, str) or
len(s) != len(e)): continue
s1 = nunpack(s)
e1 = nunpack(e)
#assert s1 <= e1
if isinstance(code, list):
for i in range(e1-s1+1):
self.cmap.add_cid2unichr(s1+i, code[i])
else:
var = code[-4:]
base = nunpack(var)
prefix = code[:-4]
vlen = len(var)
for i in range(e1-s1+1):
x = prefix+struct.pack('>L',base+i)[-vlen:]
self.cmap.add_cid2unichr(s1+i, x)
return
if name == 'beginbfchar':
self.popall()
return
if name == 'endbfchar':
objs = [ obj for (_,obj) in self.popall() ]
for (cid,code) in choplist(2, objs):
if isinstance(cid, str) and isinstance(code, str):
self.cmap.add_cid2unichr(nunpack(cid), code)
return
if name == 'beginnotdefrange':
self.popall()
return
if name == 'endnotdefrange':
self.popall()
return
self.push((pos, token))
return