class PDFSimpleFont(PDFFont):
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.encoding = EncodingDB.get_encoding(name, diff)
else:
self.encoding = EncodingDB.get_encoding(literal_name(encoding))
self.ucs2_cmap = None
if 'ToUnicode' in spec:
strm = stream_value(spec['ToUnicode'])
self.ucs2_cmap = CMap()
CMapParser(self.ucs2_cmap, StringIO(strm.get_data())).run()
PDFFont.__init__(self, descriptor, widths)
return
def to_unicode(self, cid):
if not self.ucs2_cmap:
try:
return self.encoding[cid]
except KeyError:
raise PDFUnicodeNotDefined(None, cid)
code = self.ucs2_cmap.tocode(cid)
if not code:
raise PDFUnicodeNotDefined(None, cid)
chars = unpack('>%dH' % (len(code) / 2), code)
return ''.join(unichr(c) for c in chars)
class PDFSimpleFont(PDFFont):
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.encoding = EncodingDB.get_encoding(name, diff)
else:
self.encoding = EncodingDB.get_encoding(literal_name(encoding))
self.ucs2_cmap = None
if "ToUnicode" in spec:
strm = stream_value(spec["ToUnicode"])
self.ucs2_cmap = CMap()
CMapParser(self.ucs2_cmap, StringIO(strm.get_data())).run()
PDFFont.__init__(self, descriptor, widths)
return
def to_unicode(self, cid):
if not self.ucs2_cmap:
try:
return self.encoding[cid]
except KeyError:
raise PDFUnicodeNotDefined(None, cid)
code = self.ucs2_cmap.tocode(cid)
if not code:
raise PDFUnicodeNotDefined(None, cid)
chars = unpack(">%dH" % (len(code) / 2), code)
return "".join(unichr(c) for c in chars)
