Home | History | Annotate | Download | only in encodings
      1 """ Python Character Mapping Codec cp775 generated from 'VENDORS/MICSFT/PC/CP775.TXT' with gencodec.py.
      2 
      3 """#"
      4 
      5 import codecs
      6 
      7 ### Codec APIs
      8 
      9 class Codec(codecs.Codec):
     10 
     11     def encode(self,input,errors='strict'):
     12         return codecs.charmap_encode(input,errors,encoding_map)
     13 
     14     def decode(self,input,errors='strict'):
     15         return codecs.charmap_decode(input,errors,decoding_table)
     16 
     17 class IncrementalEncoder(codecs.IncrementalEncoder):
     18     def encode(self, input, final=False):
     19         return codecs.charmap_encode(input,self.errors,encoding_map)[0]
     20 
     21 class IncrementalDecoder(codecs.IncrementalDecoder):
     22     def decode(self, input, final=False):
     23         return codecs.charmap_decode(input,self.errors,decoding_table)[0]
     24 
     25 class StreamWriter(Codec,codecs.StreamWriter):
     26     pass
     27 
     28 class StreamReader(Codec,codecs.StreamReader):
     29     pass
     30 
     31 ### encodings module API
     32 
     33 def getregentry():
     34     return codecs.CodecInfo(
     35         name='cp775',
     36         encode=Codec().encode,
     37         decode=Codec().decode,
     38         incrementalencoder=IncrementalEncoder,
     39         incrementaldecoder=IncrementalDecoder,
     40         streamreader=StreamReader,
     41         streamwriter=StreamWriter,
     42     )
     43 ### Decoding Map
     44 
     45 decoding_map = codecs.make_identity_dict(range(256))
     46 decoding_map.update({
     47     0x0080: 0x0106,     #  LATIN CAPITAL LETTER C WITH ACUTE
     48     0x0081: 0x00fc,     #  LATIN SMALL LETTER U WITH DIAERESIS
     49     0x0082: 0x00e9,     #  LATIN SMALL LETTER E WITH ACUTE
     50     0x0083: 0x0101,     #  LATIN SMALL LETTER A WITH MACRON
     51     0x0084: 0x00e4,     #  LATIN SMALL LETTER A WITH DIAERESIS
     52     0x0085: 0x0123,     #  LATIN SMALL LETTER G WITH CEDILLA
     53     0x0086: 0x00e5,     #  LATIN SMALL LETTER A WITH RING ABOVE
     54     0x0087: 0x0107,     #  LATIN SMALL LETTER C WITH ACUTE
     55     0x0088: 0x0142,     #  LATIN SMALL LETTER L WITH STROKE
     56     0x0089: 0x0113,     #  LATIN SMALL LETTER E WITH MACRON
     57     0x008a: 0x0156,     #  LATIN CAPITAL LETTER R WITH CEDILLA
     58     0x008b: 0x0157,     #  LATIN SMALL LETTER R WITH CEDILLA
     59     0x008c: 0x012b,     #  LATIN SMALL LETTER I WITH MACRON
     60     0x008d: 0x0179,     #  LATIN CAPITAL LETTER Z WITH ACUTE
     61     0x008e: 0x00c4,     #  LATIN CAPITAL LETTER A WITH DIAERESIS
     62     0x008f: 0x00c5,     #  LATIN CAPITAL LETTER A WITH RING ABOVE
     63     0x0090: 0x00c9,     #  LATIN CAPITAL LETTER E WITH ACUTE
     64     0x0091: 0x00e6,     #  LATIN SMALL LIGATURE AE
     65     0x0092: 0x00c6,     #  LATIN CAPITAL LIGATURE AE
     66     0x0093: 0x014d,     #  LATIN SMALL LETTER O WITH MACRON
     67     0x0094: 0x00f6,     #  LATIN SMALL LETTER O WITH DIAERESIS
     68     0x0095: 0x0122,     #  LATIN CAPITAL LETTER G WITH CEDILLA
     69     0x0096: 0x00a2,     #  CENT SIGN
     70     0x0097: 0x015a,     #  LATIN CAPITAL LETTER S WITH ACUTE
     71     0x0098: 0x015b,     #  LATIN SMALL LETTER S WITH ACUTE
     72     0x0099: 0x00d6,     #  LATIN CAPITAL LETTER O WITH DIAERESIS
     73     0x009a: 0x00dc,     #  LATIN CAPITAL LETTER U WITH DIAERESIS
     74     0x009b: 0x00f8,     #  LATIN SMALL LETTER O WITH STROKE
     75     0x009c: 0x00a3,     #  POUND SIGN
     76     0x009d: 0x00d8,     #  LATIN CAPITAL LETTER O WITH STROKE
     77     0x009e: 0x00d7,     #  MULTIPLICATION SIGN
     78     0x009f: 0x00a4,     #  CURRENCY SIGN
     79     0x00a0: 0x0100,     #  LATIN CAPITAL LETTER A WITH MACRON
     80     0x00a1: 0x012a,     #  LATIN CAPITAL LETTER I WITH MACRON
     81     0x00a2: 0x00f3,     #  LATIN SMALL LETTER O WITH ACUTE
     82     0x00a3: 0x017b,     #  LATIN CAPITAL LETTER Z WITH DOT ABOVE
     83     0x00a4: 0x017c,     #  LATIN SMALL LETTER Z WITH DOT ABOVE
     84     0x00a5: 0x017a,     #  LATIN SMALL LETTER Z WITH ACUTE
     85     0x00a6: 0x201d,     #  RIGHT DOUBLE QUOTATION MARK
     86     0x00a7: 0x00a6,     #  BROKEN BAR
     87     0x00a8: 0x00a9,     #  COPYRIGHT SIGN
     88     0x00a9: 0x00ae,     #  REGISTERED SIGN
     89     0x00aa: 0x00ac,     #  NOT SIGN
     90     0x00ab: 0x00bd,     #  VULGAR FRACTION ONE HALF
     91     0x00ac: 0x00bc,     #  VULGAR FRACTION ONE QUARTER
     92     0x00ad: 0x0141,     #  LATIN CAPITAL LETTER L WITH STROKE
     93     0x00ae: 0x00ab,     #  LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
     94     0x00af: 0x00bb,     #  RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
     95     0x00b0: 0x2591,     #  LIGHT SHADE
     96     0x00b1: 0x2592,     #  MEDIUM SHADE
     97     0x00b2: 0x2593,     #  DARK SHADE
     98     0x00b3: 0x2502,     #  BOX DRAWINGS LIGHT VERTICAL
     99     0x00b4: 0x2524,     #  BOX DRAWINGS LIGHT VERTICAL AND LEFT
    100     0x00b5: 0x0104,     #  LATIN CAPITAL LETTER A WITH OGONEK
    101     0x00b6: 0x010c,     #  LATIN CAPITAL LETTER C WITH CARON
    102     0x00b7: 0x0118,     #  LATIN CAPITAL LETTER E WITH OGONEK
    103     0x00b8: 0x0116,     #  LATIN CAPITAL LETTER E WITH DOT ABOVE
    104     0x00b9: 0x2563,     #  BOX DRAWINGS DOUBLE VERTICAL AND LEFT
    105     0x00ba: 0x2551,     #  BOX DRAWINGS DOUBLE VERTICAL
    106     0x00bb: 0x2557,     #  BOX DRAWINGS DOUBLE DOWN AND LEFT
    107     0x00bc: 0x255d,     #  BOX DRAWINGS DOUBLE UP AND LEFT
    108     0x00bd: 0x012e,     #  LATIN CAPITAL LETTER I WITH OGONEK
    109     0x00be: 0x0160,     #  LATIN CAPITAL LETTER S WITH CARON
    110     0x00bf: 0x2510,     #  BOX DRAWINGS LIGHT DOWN AND LEFT
    111     0x00c0: 0x2514,     #  BOX DRAWINGS LIGHT UP AND RIGHT
    112     0x00c1: 0x2534,     #  BOX DRAWINGS LIGHT UP AND HORIZONTAL
    113     0x00c2: 0x252c,     #  BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
    114     0x00c3: 0x251c,     #  BOX DRAWINGS LIGHT VERTICAL AND RIGHT
    115     0x00c4: 0x2500,     #  BOX DRAWINGS LIGHT HORIZONTAL
    116     0x00c5: 0x253c,     #  BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
    117     0x00c6: 0x0172,     #  LATIN CAPITAL LETTER U WITH OGONEK
    118     0x00c7: 0x016a,     #  LATIN CAPITAL LETTER U WITH MACRON
    119     0x00c8: 0x255a,     #  BOX DRAWINGS DOUBLE UP AND RIGHT
    120     0x00c9: 0x2554,     #  BOX DRAWINGS DOUBLE DOWN AND RIGHT
    121     0x00ca: 0x2569,     #  BOX DRAWINGS DOUBLE UP AND HORIZONTAL
    122     0x00cb: 0x2566,     #  BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
    123     0x00cc: 0x2560,     #  BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
    124     0x00cd: 0x2550,     #  BOX DRAWINGS DOUBLE HORIZONTAL
    125     0x00ce: 0x256c,     #  BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
    126     0x00cf: 0x017d,     #  LATIN CAPITAL LETTER Z WITH CARON
    127     0x00d0: 0x0105,     #  LATIN SMALL LETTER A WITH OGONEK
    128     0x00d1: 0x010d,     #  LATIN SMALL LETTER C WITH CARON
    129     0x00d2: 0x0119,     #  LATIN SMALL LETTER E WITH OGONEK
    130     0x00d3: 0x0117,     #  LATIN SMALL LETTER E WITH DOT ABOVE
    131     0x00d4: 0x012f,     #  LATIN SMALL LETTER I WITH OGONEK
    132     0x00d5: 0x0161,     #  LATIN SMALL LETTER S WITH CARON
    133     0x00d6: 0x0173,     #  LATIN SMALL LETTER U WITH OGONEK
    134     0x00d7: 0x016b,     #  LATIN SMALL LETTER U WITH MACRON
    135     0x00d8: 0x017e,     #  LATIN SMALL LETTER Z WITH CARON
    136     0x00d9: 0x2518,     #  BOX DRAWINGS LIGHT UP AND LEFT
    137     0x00da: 0x250c,     #  BOX DRAWINGS LIGHT DOWN AND RIGHT
    138     0x00db: 0x2588,     #  FULL BLOCK
    139     0x00dc: 0x2584,     #  LOWER HALF BLOCK
    140     0x00dd: 0x258c,     #  LEFT HALF BLOCK
    141     0x00de: 0x2590,     #  RIGHT HALF BLOCK
    142     0x00df: 0x2580,     #  UPPER HALF BLOCK
    143     0x00e0: 0x00d3,     #  LATIN CAPITAL LETTER O WITH ACUTE
    144     0x00e1: 0x00df,     #  LATIN SMALL LETTER SHARP S (GERMAN)
    145     0x00e2: 0x014c,     #  LATIN CAPITAL LETTER O WITH MACRON
    146     0x00e3: 0x0143,     #  LATIN CAPITAL LETTER N WITH ACUTE
    147     0x00e4: 0x00f5,     #  LATIN SMALL LETTER O WITH TILDE
    148     0x00e5: 0x00d5,     #  LATIN CAPITAL LETTER O WITH TILDE
    149     0x00e6: 0x00b5,     #  MICRO SIGN
    150     0x00e7: 0x0144,     #  LATIN SMALL LETTER N WITH ACUTE
    151     0x00e8: 0x0136,     #  LATIN CAPITAL LETTER K WITH CEDILLA
    152     0x00e9: 0x0137,     #  LATIN SMALL LETTER K WITH CEDILLA
    153     0x00ea: 0x013b,     #  LATIN CAPITAL LETTER L WITH CEDILLA
    154     0x00eb: 0x013c,     #  LATIN SMALL LETTER L WITH CEDILLA
    155     0x00ec: 0x0146,     #  LATIN SMALL LETTER N WITH CEDILLA
    156     0x00ed: 0x0112,     #  LATIN CAPITAL LETTER E WITH MACRON
    157     0x00ee: 0x0145,     #  LATIN CAPITAL LETTER N WITH CEDILLA
    158     0x00ef: 0x2019,     #  RIGHT SINGLE QUOTATION MARK
    159     0x00f0: 0x00ad,     #  SOFT HYPHEN
    160     0x00f1: 0x00b1,     #  PLUS-MINUS SIGN
    161     0x00f2: 0x201c,     #  LEFT DOUBLE QUOTATION MARK
    162     0x00f3: 0x00be,     #  VULGAR FRACTION THREE QUARTERS
    163     0x00f4: 0x00b6,     #  PILCROW SIGN
    164     0x00f5: 0x00a7,     #  SECTION SIGN
    165     0x00f6: 0x00f7,     #  DIVISION SIGN
    166     0x00f7: 0x201e,     #  DOUBLE LOW-9 QUOTATION MARK
    167     0x00f8: 0x00b0,     #  DEGREE SIGN
    168     0x00f9: 0x2219,     #  BULLET OPERATOR
    169     0x00fa: 0x00b7,     #  MIDDLE DOT
    170     0x00fb: 0x00b9,     #  SUPERSCRIPT ONE
    171     0x00fc: 0x00b3,     #  SUPERSCRIPT THREE
    172     0x00fd: 0x00b2,     #  SUPERSCRIPT TWO
    173     0x00fe: 0x25a0,     #  BLACK SQUARE
    174     0x00ff: 0x00a0,     #  NO-BREAK SPACE
    175 })
    176 
    177 ### Decoding Table
    178 
    179 decoding_table = (
    180     u'\x00'     #  0x0000 -> NULL
    181     u'\x01'     #  0x0001 -> START OF HEADING
    182     u'\x02'     #  0x0002 -> START OF TEXT
    183     u'\x03'     #  0x0003 -> END OF TEXT
    184     u'\x04'     #  0x0004 -> END OF TRANSMISSION
    185     u'\x05'     #  0x0005 -> ENQUIRY
    186     u'\x06'     #  0x0006 -> ACKNOWLEDGE
    187     u'\x07'     #  0x0007 -> BELL
    188     u'\x08'     #  0x0008 -> BACKSPACE
    189     u'\t'       #  0x0009 -> HORIZONTAL TABULATION
    190     u'\n'       #  0x000a -> LINE FEED
    191     u'\x0b'     #  0x000b -> VERTICAL TABULATION
    192     u'\x0c'     #  0x000c -> FORM FEED
    193     u'\r'       #  0x000d -> CARRIAGE RETURN
    194     u'\x0e'     #  0x000e -> SHIFT OUT
    195     u'\x0f'     #  0x000f -> SHIFT IN
    196     u'\x10'     #  0x0010 -> DATA LINK ESCAPE
    197     u'\x11'     #  0x0011 -> DEVICE CONTROL ONE
    198     u'\x12'     #  0x0012 -> DEVICE CONTROL TWO
    199     u'\x13'     #  0x0013 -> DEVICE CONTROL THREE
    200     u'\x14'     #  0x0014 -> DEVICE CONTROL FOUR
    201     u'\x15'     #  0x0015 -> NEGATIVE ACKNOWLEDGE
    202     u'\x16'     #  0x0016 -> SYNCHRONOUS IDLE
    203     u'\x17'     #  0x0017 -> END OF TRANSMISSION BLOCK
    204     u'\x18'     #  0x0018 -> CANCEL
    205     u'\x19'     #  0x0019 -> END OF MEDIUM
    206     u'\x1a'     #  0x001a -> SUBSTITUTE
    207     u'\x1b'     #  0x001b -> ESCAPE
    208     u'\x1c'     #  0x001c -> FILE SEPARATOR
    209     u'\x1d'     #  0x001d -> GROUP SEPARATOR
    210     u'\x1e'     #  0x001e -> RECORD SEPARATOR
    211     u'\x1f'     #  0x001f -> UNIT SEPARATOR
    212     u' '        #  0x0020 -> SPACE
    213     u'!'        #  0x0021 -> EXCLAMATION MARK
    214     u'"'        #  0x0022 -> QUOTATION MARK
    215     u'#'        #  0x0023 -> NUMBER SIGN
    216     u'$'        #  0x0024 -> DOLLAR SIGN
    217     u'%'        #  0x0025 -> PERCENT SIGN
    218     u'&'        #  0x0026 -> AMPERSAND
    219     u"'"        #  0x0027 -> APOSTROPHE
    220     u'('        #  0x0028 -> LEFT PARENTHESIS
    221     u')'        #  0x0029 -> RIGHT PARENTHESIS
    222     u'*'        #  0x002a -> ASTERISK
    223     u'+'        #  0x002b -> PLUS SIGN
    224     u','        #  0x002c -> COMMA
    225     u'-'        #  0x002d -> HYPHEN-MINUS
    226     u'.'        #  0x002e -> FULL STOP
    227     u'/'        #  0x002f -> SOLIDUS
    228     u'0'        #  0x0030 -> DIGIT ZERO
    229     u'1'        #  0x0031 -> DIGIT ONE
    230     u'2'        #  0x0032 -> DIGIT TWO
    231     u'3'        #  0x0033 -> DIGIT THREE
    232     u'4'        #  0x0034 -> DIGIT FOUR
    233     u'5'        #  0x0035 -> DIGIT FIVE
    234     u'6'        #  0x0036 -> DIGIT SIX
    235     u'7'        #  0x0037 -> DIGIT SEVEN
    236     u'8'        #  0x0038 -> DIGIT EIGHT
    237     u'9'        #  0x0039 -> DIGIT NINE
    238     u':'        #  0x003a -> COLON
    239     u';'        #  0x003b -> SEMICOLON
    240     u'<'        #  0x003c -> LESS-THAN SIGN
    241     u'='        #  0x003d -> EQUALS SIGN
    242     u'>'        #  0x003e -> GREATER-THAN SIGN
    243     u'?'        #  0x003f -> QUESTION MARK
    244     u'@'        #  0x0040 -> COMMERCIAL AT
    245     u'A'        #  0x0041 -> LATIN CAPITAL LETTER A
    246     u'B'        #  0x0042 -> LATIN CAPITAL LETTER B
    247     u'C'        #  0x0043 -> LATIN CAPITAL LETTER C
    248     u'D'        #  0x0044 -> LATIN CAPITAL LETTER D
    249     u'E'        #  0x0045 -> LATIN CAPITAL LETTER E
    250     u'F'        #  0x0046 -> LATIN CAPITAL LETTER F
    251     u'G'        #  0x0047 -> LATIN CAPITAL LETTER G
    252     u'H'        #  0x0048 -> LATIN CAPITAL LETTER H
    253     u'I'        #  0x0049 -> LATIN CAPITAL LETTER I
    254     u'J'        #  0x004a -> LATIN CAPITAL LETTER J
    255     u'K'        #  0x004b -> LATIN CAPITAL LETTER K
    256     u'L'        #  0x004c -> LATIN CAPITAL LETTER L
    257     u'M'        #  0x004d -> LATIN CAPITAL LETTER M
    258     u'N'        #  0x004e -> LATIN CAPITAL LETTER N
    259     u'O'        #  0x004f -> LATIN CAPITAL LETTER O
    260     u'P'        #  0x0050 -> LATIN CAPITAL LETTER P
    261     u'Q'        #  0x0051 -> LATIN CAPITAL LETTER Q
    262     u'R'        #  0x0052 -> LATIN CAPITAL LETTER R
    263     u'S'        #  0x0053 -> LATIN CAPITAL LETTER S
    264     u'T'        #  0x0054 -> LATIN CAPITAL LETTER T
    265     u'U'        #  0x0055 -> LATIN CAPITAL LETTER U
    266     u'V'        #  0x0056 -> LATIN CAPITAL LETTER V
    267     u'W'        #  0x0057 -> LATIN CAPITAL LETTER W
    268     u'X'        #  0x0058 -> LATIN CAPITAL LETTER X
    269     u'Y'        #  0x0059 -> LATIN CAPITAL LETTER Y
    270     u'Z'        #  0x005a -> LATIN CAPITAL LETTER Z
    271     u'['        #  0x005b -> LEFT SQUARE BRACKET
    272     u'\\'       #  0x005c -> REVERSE SOLIDUS
    273     u']'        #  0x005d -> RIGHT SQUARE BRACKET
    274     u'^'        #  0x005e -> CIRCUMFLEX ACCENT
    275     u'_'        #  0x005f -> LOW LINE
    276     u'`'        #  0x0060 -> GRAVE ACCENT
    277     u'a'        #  0x0061 -> LATIN SMALL LETTER A
    278     u'b'        #  0x0062 -> LATIN SMALL LETTER B
    279     u'c'        #  0x0063 -> LATIN SMALL LETTER C
    280     u'd'        #  0x0064 -> LATIN SMALL LETTER D
    281     u'e'        #  0x0065 -> LATIN SMALL LETTER E
    282     u'f'        #  0x0066 -> LATIN SMALL LETTER F
    283     u'g'        #  0x0067 -> LATIN SMALL LETTER G
    284     u'h'        #  0x0068 -> LATIN SMALL LETTER H
    285     u'i'        #  0x0069 -> LATIN SMALL LETTER I
    286     u'j'        #  0x006a -> LATIN SMALL LETTER J
    287     u'k'        #  0x006b -> LATIN SMALL LETTER K
    288     u'l'        #  0x006c -> LATIN SMALL LETTER L
    289     u'm'        #  0x006d -> LATIN SMALL LETTER M
    290     u'n'        #  0x006e -> LATIN SMALL LETTER N
    291     u'o'        #  0x006f -> LATIN SMALL LETTER O
    292     u'p'        #  0x0070 -> LATIN SMALL LETTER P
    293     u'q'        #  0x0071 -> LATIN SMALL LETTER Q
    294     u'r'        #  0x0072 -> LATIN SMALL LETTER R
    295     u's'        #  0x0073 -> LATIN SMALL LETTER S
    296     u't'        #  0x0074 -> LATIN SMALL LETTER T
    297     u'u'        #  0x0075 -> LATIN SMALL LETTER U
    298     u'v'        #  0x0076 -> LATIN SMALL LETTER V
    299     u'w'        #  0x0077 -> LATIN SMALL LETTER W
    300     u'x'        #  0x0078 -> LATIN SMALL LETTER X
    301     u'y'        #  0x0079 -> LATIN SMALL LETTER Y
    302     u'z'        #  0x007a -> LATIN SMALL LETTER Z
    303     u'{'        #  0x007b -> LEFT CURLY BRACKET
    304     u'|'        #  0x007c -> VERTICAL LINE
    305     u'}'        #  0x007d -> RIGHT CURLY BRACKET
    306     u'~'        #  0x007e -> TILDE
    307     u'\x7f'     #  0x007f -> DELETE
    308     u'\u0106'   #  0x0080 -> LATIN CAPITAL LETTER C WITH ACUTE
    309     u'\xfc'     #  0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
    310     u'\xe9'     #  0x0082 -> LATIN SMALL LETTER E WITH ACUTE
    311     u'\u0101'   #  0x0083 -> LATIN SMALL LETTER A WITH MACRON
    312     u'\xe4'     #  0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
    313     u'\u0123'   #  0x0085 -> LATIN SMALL LETTER G WITH CEDILLA
    314     u'\xe5'     #  0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
    315     u'\u0107'   #  0x0087 -> LATIN SMALL LETTER C WITH ACUTE
    316     u'\u0142'   #  0x0088 -> LATIN SMALL LETTER L WITH STROKE
    317     u'\u0113'   #  0x0089 -> LATIN SMALL LETTER E WITH MACRON
    318     u'\u0156'   #  0x008a -> LATIN CAPITAL LETTER R WITH CEDILLA
    319     u'\u0157'   #  0x008b -> LATIN SMALL LETTER R WITH CEDILLA
    320     u'\u012b'   #  0x008c -> LATIN SMALL LETTER I WITH MACRON
    321     u'\u0179'   #  0x008d -> LATIN CAPITAL LETTER Z WITH ACUTE
    322     u'\xc4'     #  0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
    323     u'\xc5'     #  0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
    324     u'\xc9'     #  0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
    325     u'\xe6'     #  0x0091 -> LATIN SMALL LIGATURE AE
    326     u'\xc6'     #  0x0092 -> LATIN CAPITAL LIGATURE AE
    327     u'\u014d'   #  0x0093 -> LATIN SMALL LETTER O WITH MACRON
    328     u'\xf6'     #  0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
    329     u'\u0122'   #  0x0095 -> LATIN CAPITAL LETTER G WITH CEDILLA
    330     u'\xa2'     #  0x0096 -> CENT SIGN
    331     u'\u015a'   #  0x0097 -> LATIN CAPITAL LETTER S WITH ACUTE
    332     u'\u015b'   #  0x0098 -> LATIN SMALL LETTER S WITH ACUTE
    333     u'\xd6'     #  0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
    334     u'\xdc'     #  0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
    335     u'\xf8'     #  0x009b -> LATIN SMALL LETTER O WITH STROKE
    336     u'\xa3'     #  0x009c -> POUND SIGN
    337     u'\xd8'     #  0x009d -> LATIN CAPITAL LETTER O WITH STROKE
    338     u'\xd7'     #  0x009e -> MULTIPLICATION SIGN
    339     u'\xa4'     #  0x009f -> CURRENCY SIGN
    340     u'\u0100'   #  0x00a0 -> LATIN CAPITAL LETTER A WITH MACRON
    341     u'\u012a'   #  0x00a1 -> LATIN CAPITAL LETTER I WITH MACRON
    342     u'\xf3'     #  0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
    343     u'\u017b'   #  0x00a3 -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
    344     u'\u017c'   #  0x00a4 -> LATIN SMALL LETTER Z WITH DOT ABOVE
    345     u'\u017a'   #  0x00a5 -> LATIN SMALL LETTER Z WITH ACUTE
    346     u'\u201d'   #  0x00a6 -> RIGHT DOUBLE QUOTATION MARK
    347     u'\xa6'     #  0x00a7 -> BROKEN BAR
    348     u'\xa9'     #  0x00a8 -> COPYRIGHT SIGN
    349     u'\xae'     #  0x00a9 -> REGISTERED SIGN
    350     u'\xac'     #  0x00aa -> NOT SIGN
    351     u'\xbd'     #  0x00ab -> VULGAR FRACTION ONE HALF
    352     u'\xbc'     #  0x00ac -> VULGAR FRACTION ONE QUARTER
    353     u'\u0141'   #  0x00ad -> LATIN CAPITAL LETTER L WITH STROKE
    354     u'\xab'     #  0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
    355     u'\xbb'     #  0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
    356     u'\u2591'   #  0x00b0 -> LIGHT SHADE
    357     u'\u2592'   #  0x00b1 -> MEDIUM SHADE
    358     u'\u2593'   #  0x00b2 -> DARK SHADE
    359     u'\u2502'   #  0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
    360     u'\u2524'   #  0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
    361     u'\u0104'   #  0x00b5 -> LATIN CAPITAL LETTER A WITH OGONEK
    362     u'\u010c'   #  0x00b6 -> LATIN CAPITAL LETTER C WITH CARON
    363     u'\u0118'   #  0x00b7 -> LATIN CAPITAL LETTER E WITH OGONEK
    364     u'\u0116'   #  0x00b8 -> LATIN CAPITAL LETTER E WITH DOT ABOVE
    365     u'\u2563'   #  0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
    366     u'\u2551'   #  0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
    367     u'\u2557'   #  0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
    368     u'\u255d'   #  0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
    369     u'\u012e'   #  0x00bd -> LATIN CAPITAL LETTER I WITH OGONEK
    370     u'\u0160'   #  0x00be -> LATIN CAPITAL LETTER S WITH CARON
    371     u'\u2510'   #  0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
    372     u'\u2514'   #  0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
    373     u'\u2534'   #  0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
    374     u'\u252c'   #  0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
    375     u'\u251c'   #  0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
    376     u'\u2500'   #  0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
    377     u'\u253c'   #  0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
    378     u'\u0172'   #  0x00c6 -> LATIN CAPITAL LETTER U WITH OGONEK
    379     u'\u016a'   #  0x00c7 -> LATIN CAPITAL LETTER U WITH MACRON
    380     u'\u255a'   #  0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
    381     u'\u2554'   #  0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
    382     u'\u2569'   #  0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
    383     u'\u2566'   #  0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
    384     u'\u2560'   #  0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
    385     u'\u2550'   #  0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
    386     u'\u256c'   #  0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
    387     u'\u017d'   #  0x00cf -> LATIN CAPITAL LETTER Z WITH CARON
    388     u'\u0105'   #  0x00d0 -> LATIN SMALL LETTER A WITH OGONEK
    389     u'\u010d'   #  0x00d1 -> LATIN SMALL LETTER C WITH CARON
    390     u'\u0119'   #  0x00d2 -> LATIN SMALL LETTER E WITH OGONEK
    391     u'\u0117'   #  0x00d3 -> LATIN SMALL LETTER E WITH DOT ABOVE
    392     u'\u012f'   #  0x00d4 -> LATIN SMALL LETTER I WITH OGONEK
    393     u'\u0161'   #  0x00d5 -> LATIN SMALL LETTER S WITH CARON
    394     u'\u0173'   #  0x00d6 -> LATIN SMALL LETTER U WITH OGONEK
    395     u'\u016b'   #  0x00d7 -> LATIN SMALL LETTER U WITH MACRON
    396     u'\u017e'   #  0x00d8 -> LATIN SMALL LETTER Z WITH CARON
    397     u'\u2518'   #  0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
    398     u'\u250c'   #  0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
    399     u'\u2588'   #  0x00db -> FULL BLOCK
    400     u'\u2584'   #  0x00dc -> LOWER HALF BLOCK
    401     u'\u258c'   #  0x00dd -> LEFT HALF BLOCK
    402     u'\u2590'   #  0x00de -> RIGHT HALF BLOCK
    403     u'\u2580'   #  0x00df -> UPPER HALF BLOCK
    404     u'\xd3'     #  0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
    405     u'\xdf'     #  0x00e1 -> LATIN SMALL LETTER SHARP S (GERMAN)
    406     u'\u014c'   #  0x00e2 -> LATIN CAPITAL LETTER O WITH MACRON
    407     u'\u0143'   #  0x00e3 -> LATIN CAPITAL LETTER N WITH ACUTE
    408     u'\xf5'     #  0x00e4 -> LATIN SMALL LETTER O WITH TILDE
    409     u'\xd5'     #  0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE
    410     u'\xb5'     #  0x00e6 -> MICRO SIGN
    411     u'\u0144'   #  0x00e7 -> LATIN SMALL LETTER N WITH ACUTE
    412     u'\u0136'   #  0x00e8 -> LATIN CAPITAL LETTER K WITH CEDILLA
    413     u'\u0137'   #  0x00e9 -> LATIN SMALL LETTER K WITH CEDILLA
    414     u'\u013b'   #  0x00ea -> LATIN CAPITAL LETTER L WITH CEDILLA
    415     u'\u013c'   #  0x00eb -> LATIN SMALL LETTER L WITH CEDILLA
    416     u'\u0146'   #  0x00ec -> LATIN SMALL LETTER N WITH CEDILLA
    417     u'\u0112'   #  0x00ed -> LATIN CAPITAL LETTER E WITH MACRON
    418     u'\u0145'   #  0x00ee -> LATIN CAPITAL LETTER N WITH CEDILLA
    419     u'\u2019'   #  0x00ef -> RIGHT SINGLE QUOTATION MARK
    420     u'\xad'     #  0x00f0 -> SOFT HYPHEN
    421     u'\xb1'     #  0x00f1 -> PLUS-MINUS SIGN
    422     u'\u201c'   #  0x00f2 -> LEFT DOUBLE QUOTATION MARK
    423     u'\xbe'     #  0x00f3 -> VULGAR FRACTION THREE QUARTERS
    424     u'\xb6'     #  0x00f4 -> PILCROW SIGN
    425     u'\xa7'     #  0x00f5 -> SECTION SIGN
    426     u'\xf7'     #  0x00f6 -> DIVISION SIGN
    427     u'\u201e'   #  0x00f7 -> DOUBLE LOW-9 QUOTATION MARK
    428     u'\xb0'     #  0x00f8 -> DEGREE SIGN
    429     u'\u2219'   #  0x00f9 -> BULLET OPERATOR
    430     u'\xb7'     #  0x00fa -> MIDDLE DOT
    431     u'\xb9'     #  0x00fb -> SUPERSCRIPT ONE
    432     u'\xb3'     #  0x00fc -> SUPERSCRIPT THREE
    433     u'\xb2'     #  0x00fd -> SUPERSCRIPT TWO
    434     u'\u25a0'   #  0x00fe -> BLACK SQUARE
    435     u'\xa0'     #  0x00ff -> NO-BREAK SPACE
    436 )
    437 
    438 ### Encoding Map
    439 
    440 encoding_map = {
    441     0x0000: 0x0000,     #  NULL
    442     0x0001: 0x0001,     #  START OF HEADING
    443     0x0002: 0x0002,     #  START OF TEXT
    444     0x0003: 0x0003,     #  END OF TEXT
    445     0x0004: 0x0004,     #  END OF TRANSMISSION
    446     0x0005: 0x0005,     #  ENQUIRY
    447     0x0006: 0x0006,     #  ACKNOWLEDGE
    448     0x0007: 0x0007,     #  BELL
    449     0x0008: 0x0008,     #  BACKSPACE
    450     0x0009: 0x0009,     #  HORIZONTAL TABULATION
    451     0x000a: 0x000a,     #  LINE FEED
    452     0x000b: 0x000b,     #  VERTICAL TABULATION
    453     0x000c: 0x000c,     #  FORM FEED
    454     0x000d: 0x000d,     #  CARRIAGE RETURN
    455     0x000e: 0x000e,     #  SHIFT OUT
    456     0x000f: 0x000f,     #  SHIFT IN
    457     0x0010: 0x0010,     #  DATA LINK ESCAPE
    458     0x0011: 0x0011,     #  DEVICE CONTROL ONE
    459     0x0012: 0x0012,     #  DEVICE CONTROL TWO
    460     0x0013: 0x0013,     #  DEVICE CONTROL THREE
    461     0x0014: 0x0014,     #  DEVICE CONTROL FOUR
    462     0x0015: 0x0015,     #  NEGATIVE ACKNOWLEDGE
    463     0x0016: 0x0016,     #  SYNCHRONOUS IDLE
    464     0x0017: 0x0017,     #  END OF TRANSMISSION BLOCK
    465     0x0018: 0x0018,     #  CANCEL
    466     0x0019: 0x0019,     #  END OF MEDIUM
    467     0x001a: 0x001a,     #  SUBSTITUTE
    468     0x001b: 0x001b,     #  ESCAPE
    469     0x001c: 0x001c,     #  FILE SEPARATOR
    470     0x001d: 0x001d,     #  GROUP SEPARATOR
    471     0x001e: 0x001e,     #  RECORD SEPARATOR
    472     0x001f: 0x001f,     #  UNIT SEPARATOR
    473     0x0020: 0x0020,     #  SPACE
    474     0x0021: 0x0021,     #  EXCLAMATION MARK
    475     0x0022: 0x0022,     #  QUOTATION MARK
    476     0x0023: 0x0023,     #  NUMBER SIGN
    477     0x0024: 0x0024,     #  DOLLAR SIGN
    478     0x0025: 0x0025,     #  PERCENT SIGN
    479     0x0026: 0x0026,     #  AMPERSAND
    480     0x0027: 0x0027,     #  APOSTROPHE
    481     0x0028: 0x0028,     #  LEFT PARENTHESIS
    482     0x0029: 0x0029,     #  RIGHT PARENTHESIS
    483     0x002a: 0x002a,     #  ASTERISK
    484     0x002b: 0x002b,     #  PLUS SIGN
    485     0x002c: 0x002c,     #  COMMA
    486     0x002d: 0x002d,     #  HYPHEN-MINUS
    487     0x002e: 0x002e,     #  FULL STOP
    488     0x002f: 0x002f,     #  SOLIDUS
    489     0x0030: 0x0030,     #  DIGIT ZERO
    490     0x0031: 0x0031,     #  DIGIT ONE
    491     0x0032: 0x0032,     #  DIGIT TWO
    492     0x0033: 0x0033,     #  DIGIT THREE
    493     0x0034: 0x0034,     #  DIGIT FOUR
    494     0x0035: 0x0035,     #  DIGIT FIVE
    495     0x0036: 0x0036,     #  DIGIT SIX
    496     0x0037: 0x0037,     #  DIGIT SEVEN
    497     0x0038: 0x0038,     #  DIGIT EIGHT
    498     0x0039: 0x0039,     #  DIGIT NINE
    499     0x003a: 0x003a,     #  COLON
    500     0x003b: 0x003b,     #  SEMICOLON
    501     0x003c: 0x003c,     #  LESS-THAN SIGN
    502     0x003d: 0x003d,     #  EQUALS SIGN
    503     0x003e: 0x003e,     #  GREATER-THAN SIGN
    504     0x003f: 0x003f,     #  QUESTION MARK
    505     0x0040: 0x0040,     #  COMMERCIAL AT
    506     0x0041: 0x0041,     #  LATIN CAPITAL LETTER A
    507     0x0042: 0x0042,     #  LATIN CAPITAL LETTER B
    508     0x0043: 0x0043,     #  LATIN CAPITAL LETTER C
    509     0x0044: 0x0044,     #  LATIN CAPITAL LETTER D
    510     0x0045: 0x0045,     #  LATIN CAPITAL LETTER E
    511     0x0046: 0x0046,     #  LATIN CAPITAL LETTER F
    512     0x0047: 0x0047,     #  LATIN CAPITAL LETTER G
    513     0x0048: 0x0048,     #  LATIN CAPITAL LETTER H
    514     0x0049: 0x0049,     #  LATIN CAPITAL LETTER I
    515     0x004a: 0x004a,     #  LATIN CAPITAL LETTER J
    516     0x004b: 0x004b,     #  LATIN CAPITAL LETTER K
    517     0x004c: 0x004c,     #  LATIN CAPITAL LETTER L
    518     0x004d: 0x004d,     #  LATIN CAPITAL LETTER M
    519     0x004e: 0x004e,     #  LATIN CAPITAL LETTER N
    520     0x004f: 0x004f,     #  LATIN CAPITAL LETTER O
    521     0x0050: 0x0050,     #  LATIN CAPITAL LETTER P
    522     0x0051: 0x0051,     #  LATIN CAPITAL LETTER Q
    523     0x0052: 0x0052,     #  LATIN CAPITAL LETTER R
    524     0x0053: 0x0053,     #  LATIN CAPITAL LETTER S
    525     0x0054: 0x0054,     #  LATIN CAPITAL LETTER T
    526     0x0055: 0x0055,     #  LATIN CAPITAL LETTER U
    527     0x0056: 0x0056,     #  LATIN CAPITAL LETTER V
    528     0x0057: 0x0057,     #  LATIN CAPITAL LETTER W
    529     0x0058: 0x0058,     #  LATIN CAPITAL LETTER X
    530     0x0059: 0x0059,     #  LATIN CAPITAL LETTER Y
    531     0x005a: 0x005a,     #  LATIN CAPITAL LETTER Z
    532     0x005b: 0x005b,     #  LEFT SQUARE BRACKET
    533     0x005c: 0x005c,     #  REVERSE SOLIDUS
    534     0x005d: 0x005d,     #  RIGHT SQUARE BRACKET
    535     0x005e: 0x005e,     #  CIRCUMFLEX ACCENT
    536     0x005f: 0x005f,     #  LOW LINE
    537     0x0060: 0x0060,     #  GRAVE ACCENT
    538     0x0061: 0x0061,     #  LATIN SMALL LETTER A
    539     0x0062: 0x0062,     #  LATIN SMALL LETTER B
    540     0x0063: 0x0063,     #  LATIN SMALL LETTER C
    541     0x0064: 0x0064,     #  LATIN SMALL LETTER D
    542     0x0065: 0x0065,     #  LATIN SMALL LETTER E
    543     0x0066: 0x0066,     #  LATIN SMALL LETTER F
    544     0x0067: 0x0067,     #  LATIN SMALL LETTER G
    545     0x0068: 0x0068,     #  LATIN SMALL LETTER H
    546     0x0069: 0x0069,     #  LATIN SMALL LETTER I
    547     0x006a: 0x006a,     #  LATIN SMALL LETTER J
    548     0x006b: 0x006b,     #  LATIN SMALL LETTER K
    549     0x006c: 0x006c,     #  LATIN SMALL LETTER L
    550     0x006d: 0x006d,     #  LATIN SMALL LETTER M
    551     0x006e: 0x006e,     #  LATIN SMALL LETTER N
    552     0x006f: 0x006f,     #  LATIN SMALL LETTER O
    553     0x0070: 0x0070,     #  LATIN SMALL LETTER P
    554     0x0071: 0x0071,     #  LATIN SMALL LETTER Q
    555     0x0072: 0x0072,     #  LATIN SMALL LETTER R
    556     0x0073: 0x0073,     #  LATIN SMALL LETTER S
    557     0x0074: 0x0074,     #  LATIN SMALL LETTER T
    558     0x0075: 0x0075,     #  LATIN SMALL LETTER U
    559     0x0076: 0x0076,     #  LATIN SMALL LETTER V
    560     0x0077: 0x0077,     #  LATIN SMALL LETTER W
    561     0x0078: 0x0078,     #  LATIN SMALL LETTER X
    562     0x0079: 0x0079,     #  LATIN SMALL LETTER Y
    563     0x007a: 0x007a,     #  LATIN SMALL LETTER Z
    564     0x007b: 0x007b,     #  LEFT CURLY BRACKET
    565     0x007c: 0x007c,     #  VERTICAL LINE
    566     0x007d: 0x007d,     #  RIGHT CURLY BRACKET
    567     0x007e: 0x007e,     #  TILDE
    568     0x007f: 0x007f,     #  DELETE
    569     0x00a0: 0x00ff,     #  NO-BREAK SPACE
    570     0x00a2: 0x0096,     #  CENT SIGN
    571     0x00a3: 0x009c,     #  POUND SIGN
    572     0x00a4: 0x009f,     #  CURRENCY SIGN
    573     0x00a6: 0x00a7,     #  BROKEN BAR
    574     0x00a7: 0x00f5,     #  SECTION SIGN
    575     0x00a9: 0x00a8,     #  COPYRIGHT SIGN
    576     0x00ab: 0x00ae,     #  LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
    577     0x00ac: 0x00aa,     #  NOT SIGN
    578     0x00ad: 0x00f0,     #  SOFT HYPHEN
    579     0x00ae: 0x00a9,     #  REGISTERED SIGN
    580     0x00b0: 0x00f8,     #  DEGREE SIGN
    581     0x00b1: 0x00f1,     #  PLUS-MINUS SIGN
    582     0x00b2: 0x00fd,     #  SUPERSCRIPT TWO
    583     0x00b3: 0x00fc,     #  SUPERSCRIPT THREE
    584     0x00b5: 0x00e6,     #  MICRO SIGN
    585     0x00b6: 0x00f4,     #  PILCROW SIGN
    586     0x00b7: 0x00fa,     #  MIDDLE DOT
    587     0x00b9: 0x00fb,     #  SUPERSCRIPT ONE
    588     0x00bb: 0x00af,     #  RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
    589     0x00bc: 0x00ac,     #  VULGAR FRACTION ONE QUARTER
    590     0x00bd: 0x00ab,     #  VULGAR FRACTION ONE HALF
    591     0x00be: 0x00f3,     #  VULGAR FRACTION THREE QUARTERS
    592     0x00c4: 0x008e,     #  LATIN CAPITAL LETTER A WITH DIAERESIS
    593     0x00c5: 0x008f,     #  LATIN CAPITAL LETTER A WITH RING ABOVE
    594     0x00c6: 0x0092,     #  LATIN CAPITAL LIGATURE AE
    595     0x00c9: 0x0090,     #  LATIN CAPITAL LETTER E WITH ACUTE
    596     0x00d3: 0x00e0,     #  LATIN CAPITAL LETTER O WITH ACUTE
    597     0x00d5: 0x00e5,     #  LATIN CAPITAL LETTER O WITH TILDE
    598     0x00d6: 0x0099,     #  LATIN CAPITAL LETTER O WITH DIAERESIS
    599     0x00d7: 0x009e,     #  MULTIPLICATION SIGN
    600     0x00d8: 0x009d,     #  LATIN CAPITAL LETTER O WITH STROKE
    601     0x00dc: 0x009a,     #  LATIN CAPITAL LETTER U WITH DIAERESIS
    602     0x00df: 0x00e1,     #  LATIN SMALL LETTER SHARP S (GERMAN)
    603     0x00e4: 0x0084,     #  LATIN SMALL LETTER A WITH DIAERESIS
    604     0x00e5: 0x0086,     #  LATIN SMALL LETTER A WITH RING ABOVE
    605     0x00e6: 0x0091,     #  LATIN SMALL LIGATURE AE
    606     0x00e9: 0x0082,     #  LATIN SMALL LETTER E WITH ACUTE
    607     0x00f3: 0x00a2,     #  LATIN SMALL LETTER O WITH ACUTE
    608     0x00f5: 0x00e4,     #  LATIN SMALL LETTER O WITH TILDE
    609     0x00f6: 0x0094,     #  LATIN SMALL LETTER O WITH DIAERESIS
    610     0x00f7: 0x00f6,     #  DIVISION SIGN
    611     0x00f8: 0x009b,     #  LATIN SMALL LETTER O WITH STROKE
    612     0x00fc: 0x0081,     #  LATIN SMALL LETTER U WITH DIAERESIS
    613     0x0100: 0x00a0,     #  LATIN CAPITAL LETTER A WITH MACRON
    614     0x0101: 0x0083,     #  LATIN SMALL LETTER A WITH MACRON
    615     0x0104: 0x00b5,     #  LATIN CAPITAL LETTER A WITH OGONEK
    616     0x0105: 0x00d0,     #  LATIN SMALL LETTER A WITH OGONEK
    617     0x0106: 0x0080,     #  LATIN CAPITAL LETTER C WITH ACUTE
    618     0x0107: 0x0087,     #  LATIN SMALL LETTER C WITH ACUTE
    619     0x010c: 0x00b6,     #  LATIN CAPITAL LETTER C WITH CARON
    620     0x010d: 0x00d1,     #  LATIN SMALL LETTER C WITH CARON
    621     0x0112: 0x00ed,     #  LATIN CAPITAL LETTER E WITH MACRON
    622     0x0113: 0x0089,     #  LATIN SMALL LETTER E WITH MACRON
    623     0x0116: 0x00b8,     #  LATIN CAPITAL LETTER E WITH DOT ABOVE
    624     0x0117: 0x00d3,     #  LATIN SMALL LETTER E WITH DOT ABOVE
    625     0x0118: 0x00b7,     #  LATIN CAPITAL LETTER E WITH OGONEK
    626     0x0119: 0x00d2,     #  LATIN SMALL LETTER E WITH OGONEK
    627     0x0122: 0x0095,     #  LATIN CAPITAL LETTER G WITH CEDILLA
    628     0x0123: 0x0085,     #  LATIN SMALL LETTER G WITH CEDILLA
    629     0x012a: 0x00a1,     #  LATIN CAPITAL LETTER I WITH MACRON
    630     0x012b: 0x008c,     #  LATIN SMALL LETTER I WITH MACRON
    631     0x012e: 0x00bd,     #  LATIN CAPITAL LETTER I WITH OGONEK
    632     0x012f: 0x00d4,     #  LATIN SMALL LETTER I WITH OGONEK
    633     0x0136: 0x00e8,     #  LATIN CAPITAL LETTER K WITH CEDILLA
    634     0x0137: 0x00e9,     #  LATIN SMALL LETTER K WITH CEDILLA
    635     0x013b: 0x00ea,     #  LATIN CAPITAL LETTER L WITH CEDILLA
    636     0x013c: 0x00eb,     #  LATIN SMALL LETTER L WITH CEDILLA
    637     0x0141: 0x00ad,     #  LATIN CAPITAL LETTER L WITH STROKE
    638     0x0142: 0x0088,     #  LATIN SMALL LETTER L WITH STROKE
    639     0x0143: 0x00e3,     #  LATIN CAPITAL LETTER N WITH ACUTE
    640     0x0144: 0x00e7,     #  LATIN SMALL LETTER N WITH ACUTE
    641     0x0145: 0x00ee,     #  LATIN CAPITAL LETTER N WITH CEDILLA
    642     0x0146: 0x00ec,     #  LATIN SMALL LETTER N WITH CEDILLA
    643     0x014c: 0x00e2,     #  LATIN CAPITAL LETTER O WITH MACRON
    644     0x014d: 0x0093,     #  LATIN SMALL LETTER O WITH MACRON
    645     0x0156: 0x008a,     #  LATIN CAPITAL LETTER R WITH CEDILLA
    646     0x0157: 0x008b,     #  LATIN SMALL LETTER R WITH CEDILLA
    647     0x015a: 0x0097,     #  LATIN CAPITAL LETTER S WITH ACUTE
    648     0x015b: 0x0098,     #  LATIN SMALL LETTER S WITH ACUTE
    649     0x0160: 0x00be,     #  LATIN CAPITAL LETTER S WITH CARON
    650     0x0161: 0x00d5,     #  LATIN SMALL LETTER S WITH CARON
    651     0x016a: 0x00c7,     #  LATIN CAPITAL LETTER U WITH MACRON
    652     0x016b: 0x00d7,     #  LATIN SMALL LETTER U WITH MACRON
    653     0x0172: 0x00c6,     #  LATIN CAPITAL LETTER U WITH OGONEK
    654     0x0173: 0x00d6,     #  LATIN SMALL LETTER U WITH OGONEK
    655     0x0179: 0x008d,     #  LATIN CAPITAL LETTER Z WITH ACUTE
    656     0x017a: 0x00a5,     #  LATIN SMALL LETTER Z WITH ACUTE
    657     0x017b: 0x00a3,     #  LATIN CAPITAL LETTER Z WITH DOT ABOVE
    658     0x017c: 0x00a4,     #  LATIN SMALL LETTER Z WITH DOT ABOVE
    659     0x017d: 0x00cf,     #  LATIN CAPITAL LETTER Z WITH CARON
    660     0x017e: 0x00d8,     #  LATIN SMALL LETTER Z WITH CARON
    661     0x2019: 0x00ef,     #  RIGHT SINGLE QUOTATION MARK
    662     0x201c: 0x00f2,     #  LEFT DOUBLE QUOTATION MARK
    663     0x201d: 0x00a6,     #  RIGHT DOUBLE QUOTATION MARK
    664     0x201e: 0x00f7,     #  DOUBLE LOW-9 QUOTATION MARK
    665     0x2219: 0x00f9,     #  BULLET OPERATOR
    666     0x2500: 0x00c4,     #  BOX DRAWINGS LIGHT HORIZONTAL
    667     0x2502: 0x00b3,     #  BOX DRAWINGS LIGHT VERTICAL
    668     0x250c: 0x00da,     #  BOX DRAWINGS LIGHT DOWN AND RIGHT
    669     0x2510: 0x00bf,     #  BOX DRAWINGS LIGHT DOWN AND LEFT
    670     0x2514: 0x00c0,     #  BOX DRAWINGS LIGHT UP AND RIGHT
    671     0x2518: 0x00d9,     #  BOX DRAWINGS LIGHT UP AND LEFT
    672     0x251c: 0x00c3,     #  BOX DRAWINGS LIGHT VERTICAL AND RIGHT
    673     0x2524: 0x00b4,     #  BOX DRAWINGS LIGHT VERTICAL AND LEFT
    674     0x252c: 0x00c2,     #  BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
    675     0x2534: 0x00c1,     #  BOX DRAWINGS LIGHT UP AND HORIZONTAL
    676     0x253c: 0x00c5,     #  BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
    677     0x2550: 0x00cd,     #  BOX DRAWINGS DOUBLE HORIZONTAL
    678     0x2551: 0x00ba,     #  BOX DRAWINGS DOUBLE VERTICAL
    679     0x2554: 0x00c9,     #  BOX DRAWINGS DOUBLE DOWN AND RIGHT
    680     0x2557: 0x00bb,     #  BOX DRAWINGS DOUBLE DOWN AND LEFT
    681     0x255a: 0x00c8,     #  BOX DRAWINGS DOUBLE UP AND RIGHT
    682     0x255d: 0x00bc,     #  BOX DRAWINGS DOUBLE UP AND LEFT
    683     0x2560: 0x00cc,     #  BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
    684     0x2563: 0x00b9,     #  BOX DRAWINGS DOUBLE VERTICAL AND LEFT
    685     0x2566: 0x00cb,     #  BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
    686     0x2569: 0x00ca,     #  BOX DRAWINGS DOUBLE UP AND HORIZONTAL
    687     0x256c: 0x00ce,     #  BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
    688     0x2580: 0x00df,     #  UPPER HALF BLOCK
    689     0x2584: 0x00dc,     #  LOWER HALF BLOCK
    690     0x2588: 0x00db,     #  FULL BLOCK
    691     0x258c: 0x00dd,     #  LEFT HALF BLOCK
    692     0x2590: 0x00de,     #  RIGHT HALF BLOCK
    693     0x2591: 0x00b0,     #  LIGHT SHADE
    694     0x2592: 0x00b1,     #  MEDIUM SHADE
    695     0x2593: 0x00b2,     #  DARK SHADE
    696     0x25a0: 0x00fe,     #  BLACK SQUARE
    697 }
    698