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.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 to_unichr(self, cid): if self.unicode_map: try: return self.unicode_map.get_unichr(cid) except KeyError: pass try: return self.cid2unicode[cid] except KeyError: raise PDFUnicodeNotDefined(None, cid)
class PDFCIDFont(PDFFont): 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 __repr__(self): return "<PDFCIDFont: basefont=%r, cidcoding=%r>" % (self.basefont, self.cidcoding) def is_vertical(self): return self.vertical def is_multibyte(self): return True def decode(self, bytes): return self.cmap.decode(bytes) def char_disp(self, cid): "Returns an integer for horizontal fonts, a tuple for vertical fonts." return self.disps.get(cid, self.default_disp) def to_unichr(self, cid): try: if not self.unicode_map: raise KeyError(cid) return self.unicode_map.get_unichr(cid) except KeyError: raise PDFUnicodeNotDefined(self.cidcoding, cid)