glnames.py

一个Xpdf应用的例子

0020;space;SPACE
00A0;space;NO-BREAK SPACE;Duplicate
2660;spade;BLACK SPADE SUIT
F6F2;ssuperior;SUPERSCRIPT LATIN SMALL LETTER S
00A3;sterling;POUND SIGN
220B;suchthat;CONTAINS AS MEMBER
2211;summation;N-ARY SUMMATION
263C;sun;WHITE SUN WITH RAYS
0074;t;LATIN SMALL LETTER T
03C4;tau;GREEK SMALL LETTER TAU
0167;tbar;LATIN SMALL LETTER T WITH STROKE
0165;tcaron;LATIN SMALL LETTER T WITH CARON
0163;tcommaaccent;LATIN SMALL LETTER T WITH CEDILLA
021B;tcommaaccent;LATIN SMALL LETTER T WITH COMMA BELOW;Duplicate
2234;therefore;THEREFORE
03B8;theta;GREEK SMALL LETTER THETA
03D1;theta1;GREEK THETA SYMBOL
00FE;thorn;LATIN SMALL LETTER THORN
0033;three;DIGIT THREE
215C;threeeighths;VULGAR FRACTION THREE EIGHTHS
2083;threeinferior;SUBSCRIPT THREE
F733;threeoldstyle;OLDSTYLE DIGIT THREE
00BE;threequarters;VULGAR FRACTION THREE QUARTERS
F6DE;threequartersemdash;THREE QUARTERS EM DASH
00B3;threesuperior;SUPERSCRIPT THREE
02DC;tilde;SMALL TILDE
0303;tildecomb;COMBINING TILDE
0384;tonos;GREEK TONOS
2122;trademark;TRADE MARK SIGN
F8EA;trademarksans;TRADE MARK SIGN SANS SERIF
F6DB;trademarkserif;TRADE MARK SIGN SERIF
25BC;triagdn;BLACK DOWN-POINTING TRIANGLE
25C4;triaglf;BLACK LEFT-POINTING POINTER
25BA;triagrt;BLACK RIGHT-POINTING POINTER
25B2;triagup;BLACK UP-POINTING TRIANGLE
F6F3;tsuperior;SUPERSCRIPT LATIN SMALL LETTER T
0032;two;DIGIT TWO
2025;twodotenleader;TWO DOT LEADER
2082;twoinferior;SUBSCRIPT TWO
F732;twooldstyle;OLDSTYLE DIGIT TWO
00B2;twosuperior;SUPERSCRIPT TWO
2154;twothirds;VULGAR FRACTION TWO THIRDS
0075;u;LATIN SMALL LETTER U
00FA;uacute;LATIN SMALL LETTER U WITH ACUTE
016D;ubreve;LATIN SMALL LETTER U WITH BREVE
00FB;ucircumflex;LATIN SMALL LETTER U WITH CIRCUMFLEX
00FC;udieresis;LATIN SMALL LETTER U WITH DIAERESIS
00F9;ugrave;LATIN SMALL LETTER U WITH GRAVE
01B0;uhorn;LATIN SMALL LETTER U WITH HORN
0171;uhungarumlaut;LATIN SMALL LETTER U WITH DOUBLE ACUTE
016B;umacron;LATIN SMALL LETTER U WITH MACRON
005F;underscore;LOW LINE
2017;underscoredbl;DOUBLE LOW LINE
222A;union;UNION
2200;universal;FOR ALL
0173;uogonek;LATIN SMALL LETTER U WITH OGONEK
2580;upblock;UPPER HALF BLOCK
03C5;upsilon;GREEK SMALL LETTER UPSILON
03CB;upsilondieresis;GREEK SMALL LETTER UPSILON WITH DIALYTIKA
03B0;upsilondieresistonos;GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
03CD;upsilontonos;GREEK SMALL LETTER UPSILON WITH TONOS
016F;uring;LATIN SMALL LETTER U WITH RING ABOVE
0169;utilde;LATIN SMALL LETTER U WITH TILDE
0076;v;LATIN SMALL LETTER V
0077;w;LATIN SMALL LETTER W
1E83;wacute;LATIN SMALL LETTER W WITH ACUTE
0175;wcircumflex;LATIN SMALL LETTER W WITH CIRCUMFLEX
1E85;wdieresis;LATIN SMALL LETTER W WITH DIAERESIS
2118;weierstrass;SCRIPT CAPITAL P
1E81;wgrave;LATIN SMALL LETTER W WITH GRAVE
0078;x;LATIN SMALL LETTER X
03BE;xi;GREEK SMALL LETTER XI
0079;y;LATIN SMALL LETTER Y
00FD;yacute;LATIN SMALL LETTER Y WITH ACUTE
0177;ycircumflex;LATIN SMALL LETTER Y WITH CIRCUMFLEX
00FF;ydieresis;LATIN SMALL LETTER Y WITH DIAERESIS
00A5;yen;YEN SIGN
1EF3;ygrave;LATIN SMALL LETTER Y WITH GRAVE
007A;z;LATIN SMALL LETTER Z
017A;zacute;LATIN SMALL LETTER Z WITH ACUTE
017E;zcaron;LATIN SMALL LETTER Z WITH CARON
017C;zdotaccent;LATIN SMALL LETTER Z WITH DOT ABOVE
0030;zero;DIGIT ZERO
2080;zeroinferior;SUBSCRIPT ZERO
F730;zerooldstyle;OLDSTYLE DIGIT ZERO
2070;zerosuperior;SUPERSCRIPT ZERO
03B6;zeta;GREEK SMALL LETTER ZETA
"""


t1_bias    = 0
glyph_list = []


def adobe_glyph_names():
  """return the list of glyph names from the adobe list"""

  lines  = string.split( adobe_glyph_list, '\n' )
  glyphs = []

  for line in lines:
    if line:
      fields = string.split( line, ';' )
#     print fields[0] + ' - ' + fields[1]
      glyphs.append( fields[1] )

  return glyphs


def adobe_glyph_values():
  """return the list of glyph names and their unicode values"""

  lines  = string.split( adobe_glyph_list, '\n' )
  glyphs = []
  values = []

  for line in lines:
    if line:
      fields = string.split( line, ';' )
#     print fields[0] + ' - ' + fields[1]
      glyphs.append( fields[1] )
      values.append( fields[0] )

  return glyphs, values


def filter_glyph_names( alist, filter ):
  """filter 'alist' by taking _out_ all glyph names that are in 'filter'"""

  count  = 0
  extras = []

  for name in alist:
    try:
      filtered_index = filter.index( name )
    except:
      extras.append( name )

  return extras


def dump_mac_indices( file, all_glyphs ):
  write = file.write

  write( "  static const unsigned short  mac_standard_names[" + \
        repr( len( mac_standard_names ) + 1 ) + "] =\n" )
  write( "  {\n" )

  for name in mac_standard_names:
    write( "    " + repr( all_glyphs.index( name ) ) + ",\n" )

  write( "    0\n" )
  write( "  };\n" )
  write( "\n" )
  write( "\n" )


def dump_glyph_list( file, base_list, adobe_list ):
  write = file.write

  name_list = []

  write( "  static const char* const  ps_glyph_names[] =\n" )
  write( "  {\n" )

  for name in base_list:
    write( '    "' + name + '",\n' )
    name_list.append( name )

  write( "\n" )
  write( "#ifdef FT_CONFIG_OPTION_ADOBE_GLYPH_LIST\n" )
  write( "\n" )

  for name in adobe_list:
    write( '    "' + name + '",\n' )
    name_list.append( name )

  write( "\n" )
  write( "#endif /* FT_CONFIG_OPTION_ADOBE_GLYPH_LIST */\n" )
  write( "\n" )
  write( "    NULL\n" )
  write( "  };\n" )
  write( "\n" )
  write( "\n" )

  return name_list


def dump_unicode_values( file, sid_list, adobe_list ):
  """build the glyph names to unicode values table"""

  write = file.write

  agl_names, agl_unicodes = adobe_glyph_values()

  write( "\n" )
  write( "  static const unsigned short  ps_names_to_unicode[" + \
          repr( len( sid_list ) + len( adobe_list ) + 1 ) + "] =\n" )
  write( "  {\n" )

  for name in sid_list:
    try:
      index = agl_names.index( name )
      write( "    0x" + agl_unicodes[index] + ",\n" )
    except:
      write( "    0,\n" )

  write( "\n" )
  write( "#ifdef FT_CONFIG_OPTION_ADOBE_GLYPH_LIST\n" )
  write( "\n" )

  for name in adobe_list:
    try:
      index = agl_names.index( name )
      write( "    0x" + agl_unicodes[index] + ",\n" )
    except:
      write( "    0,\n" )

  write( "\n" )
  write( "#endif /* FT_CONFIG_OPTION_ADOBE_GLYPH_LIST */\n" )
  write( "    0\n" )
  write( "  };\n" )
  write( "\n" )
  write( "\n" )
  write( "\n" )


def dump_encoding( file, encoding_name, encoding_list ):
  """dumps a given encoding"""

  write = file.write

  write( "  static const unsigned short  " + encoding_name + "[" + \
          repr( len( encoding_list ) + 1 ) + "] =\n" )
  write( "  {\n" )

  for value in encoding_list:
    write( "    " + repr( value ) + ",\n" )
  write( "    0\n" )
  write( "  };\n" )
  write( "\n" )
  write( "\n" )


def main():
  """main program body"""

  if len( sys.argv ) != 2:
    print __doc__ % sys.argv[0]
    sys.exit( 1 )

  file  = open( sys.argv[1], "w\n" )
  write = file.write

  count_sid = len( sid_standard_names )

  # 'mac_extras' contains the list of glyph names in the Macintosh standard
  # encoding which are not in either the Adobe Glyph List or the SID
  # Standard Names.
  #
  mac_extras = filter_glyph_names( mac_standard_names, adobe_glyph_names() )
  mac_extras = filter_glyph_names( mac_extras, sid_standard_names )

  # 'base_list' contains the first names of our final glyph names table.
  # It consists of the 'mac_extras' glyph names, followed by the SID
  # Standard names.
  #
  mac_extras_count = len( mac_extras )
  t1_bias          = mac_extras_count
  base_list        = mac_extras + sid_standard_names

  # 'adobe_list' contains the glyph names that are in the AGL, but not in
  # the base_list; they will be placed after base_list glyph names in
  # our final table.
  #
  adobe_list  = filter_glyph_names( adobe_glyph_names(), base_list )
  adobe_count = len( adobe_list )

  write( "/***************************************************************************/\n" )
  write( "/*                                                                         */\n" )

  write( "/*  %-71s*/\n" % sys.argv[1] )

  write( "/*                                                                         */\n" )
  write( "/*    PostScript glyph names (specification only).                         */\n" )
  write( "/*                                                                         */\n" )
  write( "/*  Copyright 2000-2001 by                                                 */\n" )
  write( "/*  David Turner, Robert Wilhelm, and Werner Lemberg.                      */\n" )
  write( "/*                                                                         */\n" )
  write( "/*  This file is part of the FreeType project, and may only be used,       */\n" )
  write( "/*  modified, and distributed under the terms of the FreeType project      */\n" )
  write( "/*  license, LICENSE.TXT.  By continuing to use, modify, or distribute     */\n" )
  write( "/*  this file you indicate that you have read the license and              */\n" )
  write( "/*  understand and accept it fully.                                        */\n" )
  write( "/*                                                                         */\n" )
  write( "/***************************************************************************/\n" )
  write( "\n" )
  write( "\n" )
  write( "  /* this file has been generated automatically -- do not edit! */\n" )
  write( "\n" )
  write( "\n" )

  # dump final glyph list (mac extras + sid standard names + AGL glyph names)
  #
  name_list = dump_glyph_list( file, base_list, adobe_list )

  # dump t1_standard_list
  write( "  static const char* const * const  sid_standard_names = " \
          + "ps_glyph_names + " + repr( t1_bias ) + ";\n" )
  write( "\n" )
  write( "\n" )

  write( "#define NUM_SID_GLYPHS " + repr( len( sid_standard_names ) ) + "\n" )
  write( "\n" )
  write( "#ifdef FT_CONFIG_OPTION_ADOBE_GLYPH_LIST\n" )
  write( "#define NUM_ADOBE_GLYPHS " + \
          repr( len( base_list ) + len( adobe_list ) - t1_bias ) + "\n" )
  write( "#else\n" )
  write( "#define NUM_ADOBE_GLYPHS " + \
          repr( len( base_list ) - t1_bias )  + "\n" )
  write( "#endif\n" )
  write( "\n" )
  write( "\n" )

  # dump mac indices table
  dump_mac_indices( file, name_list )

  # dump unicode values table
  dump_unicode_values( file, sid_standard_names, adobe_list )

  dump_encoding( file, "t1_standard_encoding", t1_standard_encoding )
  dump_encoding( file, "t1_expert_encoding", t1_expert_encoding )

  write( "/* END */\n" )


# Now run the main routine
#
main()


# END