hp_roman8.py 7.4 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152
  1. """ Python Character Mapping Codec generated from 'hp_roman8.txt' with gencodec.py.
  2. Based on data from ftp://dkuug.dk/i18n/charmaps/HP-ROMAN8 (Keld Simonsen)
  3. Original source: LaserJet IIP Printer User's Manual HP part no
  4. 33471-90901, Hewlet-Packard, June 1989.
  5. """#"
  6. import codecs
  7. ### Codec APIs
  8. class Codec(codecs.Codec):
  9. def encode(self,input,errors='strict'):
  10. return codecs.charmap_encode(input,errors,encoding_map)
  11. def decode(self,input,errors='strict'):
  12. return codecs.charmap_decode(input,errors,decoding_map)
  13. class IncrementalEncoder(codecs.IncrementalEncoder):
  14. def encode(self, input, final=False):
  15. return codecs.charmap_encode(input,self.errors,encoding_map)[0]
  16. class IncrementalDecoder(codecs.IncrementalDecoder):
  17. def decode(self, input, final=False):
  18. return codecs.charmap_decode(input,self.errors,decoding_map)[0]
  19. class StreamWriter(Codec,codecs.StreamWriter):
  20. pass
  21. class StreamReader(Codec,codecs.StreamReader):
  22. pass
  23. ### encodings module API
  24. def getregentry():
  25. return codecs.CodecInfo(
  26. name='hp-roman8',
  27. encode=Codec().encode,
  28. decode=Codec().decode,
  29. incrementalencoder=IncrementalEncoder,
  30. incrementaldecoder=IncrementalDecoder,
  31. streamwriter=StreamWriter,
  32. streamreader=StreamReader,
  33. )
  34. ### Decoding Map
  35. decoding_map = codecs.make_identity_dict(range(256))
  36. decoding_map.update({
  37. 0x00a1: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
  38. 0x00a2: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
  39. 0x00a3: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
  40. 0x00a4: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
  41. 0x00a5: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
  42. 0x00a6: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
  43. 0x00a7: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
  44. 0x00a8: 0x00b4, # ACUTE ACCENT
  45. 0x00a9: 0x02cb, # MODIFIER LETTER GRAVE ACCENT (Mandarin Chinese fourth tone)
  46. 0x00aa: 0x02c6, # MODIFIER LETTER CIRCUMFLEX ACCENT
  47. 0x00ab: 0x00a8, # DIAERESIS
  48. 0x00ac: 0x02dc, # SMALL TILDE
  49. 0x00ad: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
  50. 0x00ae: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
  51. 0x00af: 0x20a4, # LIRA SIGN
  52. 0x00b0: 0x00af, # MACRON
  53. 0x00b1: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
  54. 0x00b2: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
  55. 0x00b3: 0x00b0, # DEGREE SIGN
  56. 0x00b4: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
  57. 0x00b5: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
  58. 0x00b6: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
  59. 0x00b7: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
  60. 0x00b8: 0x00a1, # INVERTED EXCLAMATION MARK
  61. 0x00b9: 0x00bf, # INVERTED QUESTION MARK
  62. 0x00ba: 0x00a4, # CURRENCY SIGN
  63. 0x00bb: 0x00a3, # POUND SIGN
  64. 0x00bc: 0x00a5, # YEN SIGN
  65. 0x00bd: 0x00a7, # SECTION SIGN
  66. 0x00be: 0x0192, # LATIN SMALL LETTER F WITH HOOK
  67. 0x00bf: 0x00a2, # CENT SIGN
  68. 0x00c0: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
  69. 0x00c1: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
  70. 0x00c2: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
  71. 0x00c3: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
  72. 0x00c4: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
  73. 0x00c5: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
  74. 0x00c6: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
  75. 0x00c7: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
  76. 0x00c8: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
  77. 0x00c9: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
  78. 0x00ca: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
  79. 0x00cb: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
  80. 0x00cc: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
  81. 0x00cd: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
  82. 0x00ce: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
  83. 0x00cf: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
  84. 0x00d0: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
  85. 0x00d1: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
  86. 0x00d2: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
  87. 0x00d3: 0x00c6, # LATIN CAPITAL LETTER AE
  88. 0x00d4: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
  89. 0x00d5: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
  90. 0x00d6: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
  91. 0x00d7: 0x00e6, # LATIN SMALL LETTER AE
  92. 0x00d8: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
  93. 0x00d9: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
  94. 0x00da: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
  95. 0x00db: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
  96. 0x00dc: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
  97. 0x00dd: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
  98. 0x00de: 0x00df, # LATIN SMALL LETTER SHARP S (German)
  99. 0x00df: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
  100. 0x00e0: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
  101. 0x00e1: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
  102. 0x00e2: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
  103. 0x00e3: 0x00d0, # LATIN CAPITAL LETTER ETH (Icelandic)
  104. 0x00e4: 0x00f0, # LATIN SMALL LETTER ETH (Icelandic)
  105. 0x00e5: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
  106. 0x00e6: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
  107. 0x00e7: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
  108. 0x00e8: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
  109. 0x00e9: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
  110. 0x00ea: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
  111. 0x00eb: 0x0160, # LATIN CAPITAL LETTER S WITH CARON
  112. 0x00ec: 0x0161, # LATIN SMALL LETTER S WITH CARON
  113. 0x00ed: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
  114. 0x00ee: 0x0178, # LATIN CAPITAL LETTER Y WITH DIAERESIS
  115. 0x00ef: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
  116. 0x00f0: 0x00de, # LATIN CAPITAL LETTER THORN (Icelandic)
  117. 0x00f1: 0x00fe, # LATIN SMALL LETTER THORN (Icelandic)
  118. 0x00f2: 0x00b7, # MIDDLE DOT
  119. 0x00f3: 0x00b5, # MICRO SIGN
  120. 0x00f4: 0x00b6, # PILCROW SIGN
  121. 0x00f5: 0x00be, # VULGAR FRACTION THREE QUARTERS
  122. 0x00f6: 0x2014, # EM DASH
  123. 0x00f7: 0x00bc, # VULGAR FRACTION ONE QUARTER
  124. 0x00f8: 0x00bd, # VULGAR FRACTION ONE HALF
  125. 0x00f9: 0x00aa, # FEMININE ORDINAL INDICATOR
  126. 0x00fa: 0x00ba, # MASCULINE ORDINAL INDICATOR
  127. 0x00fb: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
  128. 0x00fc: 0x25a0, # BLACK SQUARE
  129. 0x00fd: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
  130. 0x00fe: 0x00b1, # PLUS-MINUS SIGN
  131. 0x00ff: None,
  132. })
  133. ### Encoding Map
  134. encoding_map = codecs.make_encoding_map(decoding_map)