util/import_unicode.py

   1 #*
   2 #*  GRUB  --  GRand Unified Bootloader
   3 #*  Copyright (C) 2010  Free Software Foundation, Inc.
   4 #*
   5 #*  GRUB is free software: you can redistribute it and/or modify
   6 #*  it under the terms of the GNU General Public License as published by
   7 #*  the Free Software Foundation, either version 3 of the License, or
   8 #*  (at your option) any later version.
   9 #*
  10 #*  GRUB is distributed in the hope that it will be useful,
  11 #*  but WITHOUT ANY WARRANTY; without even the implied warranty of
  12 #*  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13 #*  GNU General Public License for more details.
  14 #*
  15 #*  You should have received a copy of the GNU General Public License
  16 #*  along with GRUB.  If not, see <http://www.gnu.org/licenses/>.
  17 #*
  18
  19 import re
  20 import sys
  21
  22 if len (sys.argv) < 3:
  23     print ("Usage: %s SOURCE DESTINATION" % sys.argv[0])
  24     exit (0)
  25 infile = open (sys.argv[3], "r")
  26 joining = {}
  27 for line in infile:
  28     line = re.sub ("#.*$", "", line)
  29     line = line.replace ("\n", "")
  30     line = line.replace (" ", "")
  31     if len (line) == 0 or line[0] == '\n':
  32         continue
  33     sp = line.split (";")
  34     curcode = int (sp[0], 16)
  35     if sp[2] == "U":
  36         joining[curcode] = "NONJOINING"
  37     elif sp[2] == "L":
  38         joining[curcode] = "LEFT"
  39     elif sp[2] == "R":
  40         joining[curcode] = "RIGHT"
  41     elif sp[2] == "D":
  42         joining[curcode] = "DUAL"
  43     elif sp[2] == "C":
  44         joining[curcode] = "CAUSING"
  45     else:
  46         print ("Unknown joining type '%s'" % sp[2])
  47         exit (1)
  48 infile.close ()
  49
  50 infile = open (sys.argv[1], "r")
  51 outfile = open (sys.argv[4], "w")
  52 outfile.write ("#include <grub/unicode.h>\n")
  53 outfile.write ("\n")
  54 outfile.write ("struct grub_unicode_compact_range grub_unicode_compact[] = {\n")
  55
  56 begincode = -2
  57 lastcode = -2
  58 lastbiditype = "X"
  59 lastmirrortype = False
  60 lastcombtype = -1
  61 arabicsubst = {}
  62 for line in infile:
  63     sp = line.split (";")
  64     curcode = int (sp[0], 16)
  65     curcombtype = int (sp[3], 10)
  66     curbiditype = sp[4]
  67     curmirrortype = (sp[9] == "Y")
  68     if curcombtype <= 255 and curcombtype >= 253:
  69         print ("UnicodeData.txt uses combination type %d. Conflict." \
  70                    % curcombtype)
  71         raise
  72     if sp[2] != "Lu" and sp[2] != "Ll" and sp[2] != "Lt" and sp[2] != "Lm" \
  73             and sp[2] != "Lo"\
  74             and sp[2] != "Me" and sp[2] != "Mc" and sp[2] != "Mn" \
  75             and sp[2] != "Nd" and sp[2] != "Nl" and sp[2] != "No" \
  76             and sp[2] != "Pc" and sp[2] != "Pd" and sp[2] != "Ps" \
  77             and sp[2] != "Pe" and sp[2] != "Pi" and sp[2] != "Pf" \
  78             and sp[2] != "Po" \
  79             and sp[2] != "Sm" and sp[2] != "Sc" and sp[2] != "Sk" \
  80             and sp[2] != "So"\
  81             and sp[2] != "Zs" and sp[2] != "Zl" and sp[2] != "Zp" \
  82             and sp[2] != "Cc" and sp[2] != "Cf" and sp[2] != "Cs" \
  83             and sp[2] != "Co":
  84         print ("WARNING: Unknown type %s" % sp[2])
  85     if curcombtype == 0 and sp[2] == "Me":
  86         curcombtype = 253
  87     if curcombtype == 0 and sp[2] == "Mc":
  88         curcombtype = 254
  89     if curcombtype == 0 and sp[2] == "Mn":
  90         curcombtype = 255
  91     if (curcombtype >= 2 and curcombtype <= 6) \
  92             or (curcombtype >= 37 and curcombtype != 84 and curcombtype != 91  and curcombtype != 103 and curcombtype != 107 and curcombtype != 118 and curcombtype != 122 and curcombtype != 129 and curcombtype != 130 and curcombtype != 132 and curcombtype != 202 and \
  93                 curcombtype != 214 and curcombtype != 216 and \
  94                 curcombtype != 218 and curcombtype != 220 and \
  95                 curcombtype != 222 and curcombtype != 224 and curcombtype != 226 and curcombtype != 228 and \
  96                 curcombtype != 230 and curcombtype != 232 and curcombtype != 233 and \
  97                 curcombtype != 234 and \
  98                 curcombtype != 240 and curcombtype != 253 and \
  99                 curcombtype != 254 and curcombtype != 255):
 100         print ("WARNING: Unknown combining type %d" % curcombtype)
 101     if curcode in joining:
 102         curjoin = joining[curcode]
 103     elif sp[2] == "Me" or sp[2] == "Mn" or sp[2] == "Cf":
 104         curjoin = "TRANSPARENT"
 105     else:
 106         curjoin = "NONJOINING"
 107     if sp[1].startswith ("ARABIC LETTER "):
 108         arabname = sp[1][len ("ARABIC LETTER "):]
 109         form = 0
 110         if arabname.endswith (" ISOLATED FORM"):
 111             arabname = arabname[0:len (arabname) - len (" ISOLATED FORM")]
 112             form = 1
 113         if arabname.endswith (" FINAL FORM"):
 114             arabname = arabname[0:len (arabname) - len (" FINAL FORM")]
 115             form = 2
 116         if arabname.endswith (" MEDIAL FORM"):
 117             arabname = arabname[0:len (arabname) - len (" MEDIAL FORM")]
 118             form = 3
 119         if arabname.endswith (" INITIAL FORM"):
 120             arabname = arabname[0:len (arabname) - len (" INITIAL FORM")]
 121             form = 4
 122         if arabname not in arabicsubst:
 123             arabicsubst[arabname]={}
 124         arabicsubst[arabname][form] = curcode;
 125         if form == 0:
 126             arabicsubst[arabname]['join'] = curjoin
 127     if lastcode + 1 != curcode or curbiditype != lastbiditype \
 128             or curcombtype != lastcombtype or curmirrortype != lastmirrortype \
 129             or curjoin != lastjoin:
 130         if begincode != -2 and (lastbiditype != "L" or lastcombtype != 0 or \
 131                                     lastmirrortype):
 132             outfile.write (("{0x%x, 0x%x, GRUB_BIDI_TYPE_%s, %d, %d, GRUB_JOIN_TYPE_%s},\n" \
 133                                 % (begincode, lastcode - begincode + 1, \
 134                                        lastbiditype, \
 135                                        lastcombtype, lastmirrortype, \
 136                                        lastjoin)))
 137             if lastcode - begincode + 1 >= 0x200:
 138                 print ("Too long range")
 139                 raise
 140         begincode = curcode
 141     lastcode = curcode
 142     lastjoin = curjoin
 143     lastbiditype = curbiditype
 144     lastcombtype = curcombtype
 145     lastmirrortype = curmirrortype
 146 if lastbiditype != "L" or lastcombtype != 0 or lastmirrortype:
 147     outfile.write (("{0x%x, 0x%x, GRUB_BIDI_TYPE_%s, %d, %d, GRUB_JOIN_TYPE_%s},\n" \
 148                         % (begincode, lastcode, lastbiditype, lastcombtype, \
 149                                lastmirrortype, lastjoin)))
 150 outfile.write ("{0, 0, 0, 0, 0, 0},\n")
 151
 152 outfile.write ("};\n")
 153
 154 infile.close ()
 155
 156 infile = open (sys.argv[2], "r")
 157
 158 outfile.write ("struct grub_unicode_bidi_pair grub_unicode_bidi_pairs[] = {\n")
 159
 160 for line in infile:
 161     line = re.sub ("#.*$", "", line)
 162     line = line.replace ("\n", "")
 163     line = line.replace (" ", "")
 164     if len (line) == 0 or line[0] == '\n':
 165         continue
 166     sp = line.split (";")
 167     code1 = int (sp[0], 16)
 168     code2 = int (sp[1], 16)
 169     outfile.write ("{0x%x, 0x%x},\n" % (code1, code2))
 170 outfile.write ("{0, 0},\n")
 171 outfile.write ("};\n")
 172
 173 infile.close ()
 174
 175 outfile.write ("struct grub_unicode_arabic_shape grub_unicode_arabic_shapes[] = {\n ")
 176
 177 for x in arabicsubst:
 178     try:
 179         if arabicsubst[x]['join'] == "DUAL":
 180             outfile.write ("{0x%x, 0x%x, 0x%x, 0x%x, 0x%x},\n " % (arabicsubst[x][0], arabicsubst[x][1], arabicsubst[x][2], arabicsubst[x][3], arabicsubst[x][4]))
 181         elif arabicsubst[x]['join'] == "RIGHT":
 182             outfile.write ("{0x%x, 0x%x, 0x%x, 0x%x, 0x%x},\n " % (arabicsubst[x][0], arabicsubst[x][1], arabicsubst[x][2], 0, 0))
 183         elif arabicsubst[x]['join'] == "LEFT":
 184             outfile.write ("{0x%x, 0x%x, 0x%x, 0x%x, 0x%x},\n " % (arabicsubst[x][0], arabicsubst[x][1], 0, 0, arabicsubst[x][4]))
 185     except:
 186         pass
 187
 188 outfile.write ("{0, 0, 0, 0, 0},\n")
 189 outfile.write ("};\n")
 190
 191
 192 outfile.close ()
 193