6.12.1. Conversion functions

     1: #line 104 "ms_codepages.ipk"
     2: import string
     3: import re
     4: from array import array
     5: 
     6: local_file_head = 'interscript/ftp/ftp.unicode.org/public/unidata/Mappings/Vendors/Micsft/'
     7: files =[
     8:   ['Ebcdic_Cp037','Ebcdic'],
     9:   ['Ebcdic_Cp1026','Ebcdic'],
    10:   ['Ebcdic_Cp500','Ebcdic 500V3'],
    11:   ['Ebcdic_Cp875','Ebcdic'],
    12:   ['Mac_Cyrillic','10007'],
    13:   ['Mac_Greek','10006'],
    14:   ['Mac_Iceland','10079'],
    15:   ['Mac_Latin2','10029'],
    16:   ['Mac_Roman','10000'],
    17:   ['Mac_Turkish','10081'],
    18:   ['PC_Cp437','Latin US'],
    19:   ['PC_Cp737','Greek'],
    20:   ['PC_Cp775','Baltic Rim'],
    21:   ['PC_Cp850','Latin 1'],
    22:   ['PC_Cp852','Latin 2'],
    23:   ['PC_Cp855','Cyrillic'],
    24:   ['PC_Cp857','Turkish'],
    25:   ['PC_Cp860','Portuguese'],
    26:   ['PC_Cp861','Icelandic'],
    27:   ['PC_Cp862','Hebrew'],
    28:   ['PC_Cp863','French Canada'],
    29:   ['PC_Cp864','Arabic'],
    30:   ['PC_Cp865','Nordic'],
    31:   ['PC_Cp866','Cyrillic CIS 1'],
    32:   ['PC_Cp869','Greek 2'],
    33:   ['PC_Cp874','Thai'],
    34:   ['Windows_Cp1250','Central Europe'],
    35:   ['Windows_Cp1251','Cyrillic (Slavic)'],
    36:   ['Windows_Cp1252','Latin 1 (ANSI)'],
    37:   ['Windows_Cp1253','Greek'],
    38:   ['Windows_Cp1254','Latin 5 (Turkish)'],
    39:   ['Windows_Cp1255','Hebrew'],
    40:   ['Windows_Cp1256','Arabic'],
    41:   ['Windows_Cp1257','Baltic Rim'],
    42:   ['Windows_Cp1258','?'],
    43:   ['Windows_Cp874','Thai']
    44:   ]
    45: 
    46: tou = {}
    47: for file, descr in files:
    48:   tou[file] = array('H')
    49:   filename = 'interscript/encoding/'+file+'.dat'
    50:   f = open(filename,'rb')
    51:   tou[file].fromfile(f,256)
    52:   f.close()
    53: 
    54: def microsoft_to_unicode(x,ch):
    55:   return tou[x][ch]
    56: 
    57: def microsoft_to_utf8(x,s):
    58:   u = ''
    59:   d = tou[x]
    60:   for ch in s:
    61:     u = a + utf8(d[ch])
    62:   return u
    63: