tools/Makefile

   1
   2 # Directory containing conversion tables.
   3 # You have to unpack the conversion-tables.tar.gz package.
   4 TABLESDIR = /home/bruno/chs/conversion-tables
   5
   6 ALL = \
   7  ascii.h \
   8  iso8859_1.h \
   9  iso8859_2.h \
  10  iso8859_3.h \
  11  iso8859_4.h \
  12  iso8859_5.h \
  13  iso8859_6.h \
  14  iso8859_7.h \
  15  iso8859_8.h \
  16  iso8859_9.h \
  17  iso8859_10.h \
  18  iso8859_11.h \
  19  iso8859_13.h \
  20  iso8859_14.h \
  21  iso8859_15.h \
  22  iso8859_16.h \
  23  koi8_r.h \
  24  koi8_u.h \
  25  koi8_ru.h \
  26  cp1250.h \
  27  cp1251.h \
  28  cp1252.h \
  29  cp1253.h \
  30  cp1254.h \
  31  cp1255.h \
  32  cp1256.h \
  33  cp1257.h \
  34  cp1258.h \
  35  cp850.h \
  36  cp862.h \
  37  cp866.h \
  38  cp1131.h \
  39  mac_roman.h \
  40  mac_centraleurope.h \
  41  mac_iceland.h \
  42  mac_croatian.h \
  43  mac_romania.h \
  44  mac_cyrillic.h \
  45  mac_ukraine.h \
  46  mac_greek.h \
  47  mac_turkish.h \
  48  mac_hebrew.h \
  49  mac_arabic.h \
  50  mac_thai.h \
  51  hp_roman8.h \
  52  nextstep.h \
  53  armscii_8.h \
  54  georgian_academy.h \
  55  georgian_ps.h \
  56  koi8_t.h \
  57  pt154.h \
  58  rk1048.h \
  59  mulelao.h \
  60  cp1133.h \
  61  tis620.h \
  62  cp874.h \
  63  viscii.h \
  64  tcvn.h \
  65  jisx0201.h \
  66  jisx0208.h \
  67  jisx0212.h \
  68  cp932ext.h \
  69  cp50221_0208_ext.h \
  70  cp50221_0212_ext.h \
  71  gb2312.h \
  72  isoir165ext.h \
  73  gb12345ext.h \
  74  gbkext1.h \
  75  gbkext2.h \
  76  gbkext_inv.h \
  77  cp936ext.h \
  78  gb18030ext.h \
  79  gb18030uni.h \
  80  cns11643_1.h \
  81  cns11643_2.h \
  82  cns11643_3.h \
  83  cns11643_4a.h \
  84  cns11643_4b.h \
  85  cns11643_5.h \
  86  cns11643_6.h \
  87  cns11643_7.h \
  88  cns11643_15.h \
  89  cns11643_inv.h \
  90  big5.h \
  91  cp950ext.h \
  92  hkscs1999.h \
  93  hkscs2001.h \
  94  hkscs2004.h \
  95  hkscs2008.h \
  96  ksc5601.h \
  97  uhc_1.h \
  98  uhc_2.h \
  99  johab_hangul.h \
 100  cp856.h \
 101  cp922.h \
 102  cp1046.h \
 103  cp1124.h \
 104  cp1129.h \
 105  cp1161.h \
 106  cp1162.h \
 107  cp1163.h \
 108  cp437.h \
 109  cp737.h \
 110  cp775.h \
 111  cp852.h \
 112  cp853.h \
 113  cp855.h \
 114  cp857.h \
 115  cp858.h \
 116  cp860.h \
 117  cp861.h \
 118  cp863.h \
 119  cp864.h \
 120  cp865.h \
 121  cp869.h \
 122  cp1125.h \
 123  jisx0213.h \
 124  tds565.h \
 125  atarist.h \
 126  riscos1.h \
 127  cjk_variants.h
 128
 129 all : $(ALL)
 130
 131 ascii.h : $(TABLESDIR)/glibc-2.1-iconv/ASCII.TXT 8bit_tab_to_h
 132         ./8bit_tab_to_h ASCII ascii < $<
 133
 134 iso8859_1.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-1.TXT 8bit_tab_to_h
 135         ./8bit_tab_to_h ISO-8859-1 iso8859_1 < $<
 136
 137 iso8859_2.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-2.TXT 8bit_tab_to_h
 138         ./8bit_tab_to_h ISO-8859-2 iso8859_2 < $<
 139
 140 iso8859_3.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-3.TXT 8bit_tab_to_h
 141         ./8bit_tab_to_h ISO-8859-3 iso8859_3 < $<
 142
 143 iso8859_4.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-4.TXT 8bit_tab_to_h
 144         ./8bit_tab_to_h ISO-8859-4 iso8859_4 < $<
 145
 146 iso8859_5.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-5.TXT 8bit_tab_to_h
 147         ./8bit_tab_to_h ISO-8859-5 iso8859_5 < $<
 148
 149 iso8859_6.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-6.TXT 8bit_tab_to_h
 150         ./8bit_tab_to_h ISO-8859-6 iso8859_6 < $<
 151
 152 iso8859_7.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-7-2003.TXT 8bit_tab_to_h
 153         ./8bit_tab_to_h ISO-8859-7 iso8859_7 < $<
 154
 155 iso8859_8.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-8.TXT 8bit_tab_to_h
 156         ./8bit_tab_to_h ISO-8859-8 iso8859_8 < $<
 157
 158 iso8859_9.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-9.TXT 8bit_tab_to_h
 159         ./8bit_tab_to_h ISO-8859-9 iso8859_9 < $<
 160
 161 iso8859_10.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-10.TXT 8bit_tab_to_h
 162         ./8bit_tab_to_h ISO-8859-10 iso8859_10 < $<
 163
 164 iso8859_11.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-11.TXT 8bit_tab_to_h
 165         ./8bit_tab_to_h ISO-8859-11 iso8859_11 < $<
 166
 167 iso8859_13.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-13.TXT 8bit_tab_to_h
 168         ./8bit_tab_to_h ISO-8859-13 iso8859_13 < $<
 169
 170 iso8859_14.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-14.TXT 8bit_tab_to_h
 171         ./8bit_tab_to_h ISO-8859-14 iso8859_14 < $<
 172
 173 iso8859_15.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-15.TXT 8bit_tab_to_h
 174         ./8bit_tab_to_h ISO-8859-15 iso8859_15 < $<
 175
 176 iso8859_16.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-16.TXT 8bit_tab_to_h
 177         ./8bit_tab_to_h ISO-8859-16 iso8859_16 < $<
 178
 179 koi8_r.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MISC/KOI8-R.TXT 8bit_tab_to_h
 180         ./8bit_tab_to_h KOI8-R koi8_r < $<
 181
 182 koi8_u.h : $(TABLESDIR)/csets-new/KOI8-U.TXT 8bit_tab_to_h
 183         ./8bit_tab_to_h KOI8-U koi8_u < $<
 184
 185 koi8_ru.h : $(TABLESDIR)/freebsd-iconv-0.4/KOI8-RU.TXT 8bit_tab_to_h
 186         ./8bit_tab_to_h KOI8-RU koi8_ru < $<
 187
 188 cp1250.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1250.TXT 8bit_tab_to_h
 189         ./8bit_tab_to_h CP1250 cp1250 < $<
 190
 191 cp1251.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1251.TXT 8bit_tab_to_h
 192         ./8bit_tab_to_h CP1251 cp1251 < $<
 193
 194 cp1252.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1252.TXT 8bit_tab_to_h
 195         ./8bit_tab_to_h CP1252 cp1252 < $<
 196
 197 cp1253.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1253.TXT 8bit_tab_to_h
 198         ./8bit_tab_to_h CP1253 cp1253 < $<
 199
 200 cp1254.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1254.TXT 8bit_tab_to_h
 201         ./8bit_tab_to_h CP1254 cp1254 < $<
 202
 203 cp1255.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1255.TXT 8bit_tab_to_h
 204         ./8bit_tab_to_h CP1255 cp1255 < $<
 205
 206 cp1256.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1256.TXT 8bit_tab_to_h
 207         ./8bit_tab_to_h CP1256 cp1256 < $<
 208
 209 cp1257.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1257.TXT 8bit_tab_to_h
 210         ./8bit_tab_to_h CP1257 cp1257 < $<
 211
 212 cp1258.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1258.TXT 8bit_tab_to_h
 213         ./8bit_tab_to_h CP1258 cp1258 < $<
 214
 215 cp850.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP850.TXT 8bit_tab_to_h
 216         ./8bit_tab_to_h CP850 cp850 < $<
 217
 218 cp862.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP862.TXT 8bit_tab_to_h
 219         ./8bit_tab_to_h CP862 cp862 < $<
 220
 221 cp866.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP866.TXT 8bit_tab_to_h
 222         ./8bit_tab_to_h CP866 cp866 < $<
 223
 224 cp1131.h : $(TABLESDIR)/other/CP1131.TXT 8bit_tab_to_h
 225         (echo '#' ; cat $<) | ./8bit_tab_to_h CP1131 cp1131
 226
 227 mac_roman.h : $(TABLESDIR)/jdk-1.1.7b/MAC-ROMAN.TXT 8bit_tab_to_h
 228         ./8bit_tab_to_h MacRoman mac_roman < $<
 229
 230 mac_centraleurope.h : $(TABLESDIR)/jdk-1.1.7b/MAC-CENTRAL-EUROPE.TXT 8bit_tab_to_h
 231         ./8bit_tab_to_h MacCentralEurope mac_centraleurope < $<
 232
 233 mac_iceland.h : $(TABLESDIR)/jdk-1.1.7b/MAC-ICELAND.TXT 8bit_tab_to_h
 234         ./8bit_tab_to_h MacIceland mac_iceland < $<
 235
 236 mac_croatian.h : $(TABLESDIR)/jdk-1.1.7b/MAC-CROATIAN.TXT 8bit_tab_to_h
 237         ./8bit_tab_to_h MacCroatian mac_croatian < $<
 238
 239 mac_romania.h : $(TABLESDIR)/jdk-1.1.7b/MAC-ROMANIA.TXT 8bit_tab_to_h
 240         ./8bit_tab_to_h MacRomania mac_romania < $<
 241
 242 mac_cyrillic.h : $(TABLESDIR)/jdk-1.1.7b/MAC-CYRILLIC.TXT 8bit_tab_to_h
 243         ./8bit_tab_to_h MacCyrillic mac_cyrillic < $<
 244
 245 mac_ukraine.h : $(TABLESDIR)/jdk-1.1.7b/MAC-UKRAINE.TXT 8bit_tab_to_h
 246         ./8bit_tab_to_h MacUkraine mac_ukraine < $<
 247
 248 mac_greek.h : $(TABLESDIR)/jdk-1.1.7b/MAC-GREEK.TXT 8bit_tab_to_h
 249         ./8bit_tab_to_h MacGreek mac_greek < $<
 250
 251 mac_turkish.h : $(TABLESDIR)/jdk-1.1.7b/MAC-TURKISH.TXT 8bit_tab_to_h
 252         ./8bit_tab_to_h MacTurkish mac_turkish < $<
 253
 254 mac_hebrew.h : $(TABLESDIR)/jdk-1.1.7b/MAC-HEBREW.TXT 8bit_tab_to_h
 255         ./8bit_tab_to_h MacHebrew mac_hebrew < $<
 256
 257 mac_arabic.h : $(TABLESDIR)/jdk-1.1.7b/MAC-ARABIC.TXT 8bit_tab_to_h
 258         ./8bit_tab_to_h MacArabic mac_arabic < $<
 259
 260 mac_thai.h : $(TABLESDIR)/jdk-1.1.7b/MAC-THAI.TXT 8bit_tab_to_h
 261         ./8bit_tab_to_h MacThai mac_thai < $<
 262
 263 hp_roman8.h : $(TABLESDIR)/glibc-2.1-iconv/HP-ROMAN8.TXT 8bit_tab_to_h
 264         ./8bit_tab_to_h HP-ROMAN8 hp_roman8 < $<
 265
 266 nextstep.h : $(TABLESDIR)/clisp/NEXTSTEP.TXT 8bit_tab_to_h
 267         ./8bit_tab_to_h NEXTSTEP nextstep < $<
 268
 269 armscii_8.h : $(TABLESDIR)/glibc-2.2.90-iconv/ARMSCII-8.TXT 8bit_tab_to_h
 270         (echo '#' ; cat $<) | ./8bit_tab_to_h ARMSCII-8 armscii_8
 271
 272 georgian_academy.h : $(TABLESDIR)/csets-1.6/GEO-ITA.TXT 8bit_tab_to_h
 273         ./8bit_tab_to_h GEORGIAN-ACADEMY georgian_academy < $<
 274
 275 georgian_ps.h : $(TABLESDIR)/csets-1.6/GEO-PS.TXT 8bit_tab_to_h
 276         ./8bit_tab_to_h GEORGIAN-PS georgian_ps < $<
 277
 278 koi8_t.h : $(TABLESDIR)/glibc-2.2.90-iconv/KOI8-T.TXT
 279         (echo '#' ; cat $<) | ./8bit_tab_to_h KOI8-T koi8_t
 280
 281 pt154.h : $(TABLESDIR)/IANA/PTCP154.TXT
 282         ./8bit_tab_to_h PT154 pt154 < $<
 283
 284 rk1048.h : $(TABLESDIR)/IANA/KZ-1048.TXT
 285         (echo '#' ; cat $<) | ./8bit_tab_to_h RK1048 rk1048
 286
 287 mulelao.h : $(TABLESDIR)/csets-new/MULELAO1.TXT 8bit_tab_to_h
 288         ./8bit_tab_to_h MULELAO-1 mulelao < $<
 289
 290 cp1133.h : $(TABLESDIR)/csets-new/CP1133.TXT 8bit_tab_to_h
 291         ./8bit_tab_to_h IBM-CP1133 cp1133 < $<
 292
 293 tis620.h : $(TABLESDIR)/glibc-2.1-iconv/TIS-620.TXT 8bit_tab_to_h
 294         ./8bit_tab_to_h TIS620.2533-1 tis620 < $<
 295
 296 cp874.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP874.TXT 8bit_tab_to_h
 297         ./8bit_tab_to_h CP874 cp874 < $<
 298
 299 viscii.h : $(TABLESDIR)/csets-1.6/VISCII.TXT 8bit_tab_to_h
 300         ./8bit_tab_to_h VISCII1.1-1 viscii < $<
 301
 302 tcvn.h : $(TABLESDIR)/csets-1.6/VN5712-1.TXT 8bit_tab_to_h
 303         ./8bit_tab_to_h TCVN-5712 tcvn < $<
 304
 305 jisx0201.h : $(TABLESDIR)/clisp/JIS_X0201.TXT 8bit_tab_to_h
 306         ./8bit_tab_to_h JISX0201.1976-0 jisx0201 < $<
 307
 308 # We use modified JISX0208 and JISX0212 tables. Why?
 309 # Hironori Sakamoto and Tomohiro Kubota explain that
 310 # - EUC-JP and SHIFT_JIS contain JISX0208 exactly,
 311 # - Their round-trip conversion to Unicode and back must be the identity,
 312 # - Conversions between EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP must behave
 313 #   as if no Unicode conversion was involved,
 314 # - When JISX0208 is used as a CES (i.e. combined with ASCII) its mapping of
 315 #   REVERSE SOLIDUS becomes a FULLWIDTH REVERSE SOLIDUS, apparently because
 316 #   round-trip conversion stability is more important than a particular glyph.
 317 #   Only with CCS the character is a REVERSE SOLIDUS.
 318 # As a consequence, we use FULLWIDTH REVERSE SOLIDUS in EUC-JP's JISX0208 part,
 319 # and for consistency also in SHIFT_JIS and ISO-2022-JP, i.e. everywhere.
 320 # JISX0208 never occurs as a CCS in practice. Similarly with JISX0212.
 321
 322 # Unicode.org maps 0x2140 to U+005C. We map it to U+FF3C.
 323 jisx0208.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/JIS/JIS0208.TXT cjk_tab_to_h
 324         sed -e 's,^0x....[      ]*\(0x....[     ]*0x.....*\)$$,\1,' < $< | sed -e 's,\([        ]\)0x005C,\10xFF3C,' | ./cjk_tab_to_h JISX0208.1990-0 jisx0208 > $@
 325
 326 # Unicode.org maps 0x2237 to U+007E. We map it to U+FF5E.
 327 jisx0212.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/JIS/JIS0212.TXT cjk_tab_to_h
 328         sed -e 's,\([   ]\)0x007E,\10xFF5E,' < $< | ./cjk_tab_to_h JISX0212.1990-0 jisx0212 > $@
 329
 330 cp932ext.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP932.TXT cjk_tab_to_h
 331         (echo '#' ; grep '^0x\(87\|E[D-F]\|F[0-9A-F]\)[0-9A-F][0-9A-F]' < $< ) | ./cjk_tab_to_h 'CP932 extensions' cp932ext > $@
 332
 333 cp50221_0208_ext.h : CP50221-0208-EXT.TXT 8bit_tab_to_h
 334         ./8bit_tab_to_h 'CP50221 JISX0208 extensions' cp50221_0208_ext < $<
 335
 336 cp50221_0212_ext.h : CP50221-0212-EXT.TXT 8bit_tab_to_h
 337         ./8bit_tab_to_h 'CP50221 JISX0212 extensions' cp50221_0212_ext < $<
 338
 339 gb2312.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/GB/GB2312.TXT cjk_tab_to_h
 340         ./cjk_tab_to_h GB2312.1980-0 gb2312 < $< > $@
 341
 342 isoir165ext.h : $(TABLESDIR)/csets-new/ISO-IR-165-additions.TXT cjk_tab_to_h
 343         (echo '#' ; grep -v '^0x2[8A]' < $<) | ./cjk_tab_to_h 'ISO-IR-165 extensions' isoir165ext > $@
 344
 345 gb12345ext.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/GB/GB2312.TXT $(TABLESDIR)/unicode.org-mappings/EASTASIA/GB/GB12345-FIXED.TXT $(TABLESDIR)/csets-new/GB12345-more.TXT cjk_tab_to_h
 346         (echo '#' ; sed -e '/^0x..[     ]*#UNDEFINED/d' -e 's/#.*$$//' -e '/^[  ]*$$/d' $(TABLESDIR)/unicode.org-mappings/EASTASIA/GB/GB2312.TXT > tmp1.TXT ; sed -e '/^0x..[   ]*#UNDEFINED/d' -e 's/#.*$$//' -e '/^[  ]*$$/d' $(TABLESDIR)/unicode.org-mappings/EASTASIA/GB/GB12345-FIXED.TXT > tmp2.TXT ; diff tmp1.TXT tmp2.TXT | grep '^> ' | sed -e 's,^> ,,' ; cat $(TABLESDIR)/csets-new/GB12345-more.TXT ) | ./cjk_tab_to_h 'GB/T 12345.1990-0 extensions' gb12345ext > $@ && rm -f tmp1.TXT tmp2.TXT
 347
 348 gbkext1.h : GBKext.TXT cjk_tab_to_h
 349         (echo '#' ; grep '^0x\([89].\|A0\)' < GBKext.TXT) | ./cjk_tab_to_h 'GBK/3 extensions' gbkext1 > $@
 350
 351 gbkext2.h : GBKext.TXT cjk_tab_to_h
 352         (echo '#' ; grep '^0x\(A[1-9A-F]\|[B-F][0-9A-F]\)\([4-9].\|A0\)' < GBKext.TXT) | ./cjk_tab_to_h 'GBK/4 and GBK/5 extensions' gbkext2 > $@
 353
 354 gbkext_inv.h : GBKext.TXT cjk_tab_to_h
 355         (echo '#' ; grep '^0x\([89].\|A0\)' < GBKext.TXT ; grep '^0x\(A[1-9A-F]\|[B-F][0-9A-F]\)\([4-9].\|A0\)' < GBKext.TXT) | ./cjk_tab_to_h 'GBK extensions' gbkext_inv > $@
 356
 357 cp936ext.h : GBKext.TXT cjk_tab_to_h
 358         (echo '#' ; grep '^0xA[1-9][B-F].' < GBKext.TXT) | ./cjk_tab_to_h 'CP936 extensions' cp936ext > $@
 359
 360 GBKext.TXT : $(TABLESDIR)/unicode.org-mappings/EASTASIA/GB/GB2312.TXT $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP936.TXT
 361         sed -e 's,^0x2,0xA,' -e 's,^0x3,0xB,' -e 's,^0x4,0xC,' -e 's,^0x5,0xD,' -e 's,^0x6,0xE,' -e 's,^0x7,0xF,' -e 's,^0x\(..\)2,0x\1A,' -e 's,^0x\(..\)3,0x\1B,' -e 's,^0x\(..\)4,0x\1C,' -e 's,^0x\(..\)5,0x\1D,' -e 's,^0x\(..\)6,0x\1E,' -e 's,^0x\(..\)7,0x\1F,' $(TABLESDIR)/unicode.org-mappings/EASTASIA/GB/GB2312.TXT > tmpEUCCN.TXT ; sed -e '/^0x..[       ]*#UNDEFINED/d' -e 's/#.*$$//' -e '/^[  ]*$$/d' tmpEUCCN.TXT > tmp1.TXT ; sed -e '/^0x..[       ]/d' -e 's/#.*$$//' -e '/^[     ]*$$/d' $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP936.TXT > tmp2.TXT ; diff -c1 tmp1.TXT tmp2.TXT | grep '^+ ' | sed -e 's,^+ ,,' > $@ && rm -f tmpEUCCN.TXT tmp1.TXT tmp2.TXT
 362
 363 gb18030ext.h : GB18030ext.TXT cjk_tab_to_h
 364         (echo '#' ; cat GB18030ext.TXT) | ./cjk_tab_to_h 'GB18030 two-byte extension' gb18030ext > $@
 365
 366 GB18030ext.TXT : $(TABLESDIR)/glibc-2.2.2-iconv/GB18030.TXT $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP936.TXT
 367         cat $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP936.TXT | sed -e 's/[    ]*#.*$$//' | grep '^0x[0-9A-F]* 0x....$$' > tmpGBK.TXT ; diff tmpGBK.TXT $(TABLESDIR)/glibc-2.2.2-iconv/GB18030.TXT | grep '^> 0x....   0x....$$' | sed -e 's/^> //' > $@ && rm -f tmpGBK.TXT
 368
 369 gb18030uni.h : GB18030uni.TXT cjk_tab_to_h
 370         ./cjk_tab_to_h 'GB18030 four-byte extension' gb18030uni < GB18030uni.TXT > $@
 371
 372 GB18030uni.TXT : $(TABLESDIR)/gb18030/filled-GB18030.TXT
 373         grep '^0x........       0x....$$' < $(TABLESDIR)/gb18030/filled-GB18030.TXT > $@
 374
 375 cns11643_1.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
 376         grep '^\(#\|0x1\)' < $< | sed -e 's,^0x1,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 1' cns11643_1 > $@
 377
 378 cns11643_2.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
 379         grep '^\(#\|0x2\)' < $< | sed -e 's,^0x2,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 2' cns11643_2 > $@
 380
 381 cns11643_3.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
 382         grep '^\(#\|0x3\)' < $< | sed -e 's,^0x3,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 3' cns11643_3 > $@
 383
 384 cns11643_4a.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
 385         grep '^\(#\|0x4[0-3]\)' < $< | sed -e 's,^0x4,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 4 part a' cns11643_4a > $@
 386
 387 cns11643_4b.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
 388         grep '^\(#\|0x4[4-7]\)' < $< | sed -e 's,^0x4,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 4 part b' cns11643_4b > $@
 389
 390 cns11643_5.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
 391         grep '^\(#\|0x5\)' < $< | sed -e 's,^0x5,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 5' cns11643_5 > $@
 392
 393 cns11643_6.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
 394         grep '^\(#\|0x6\)' < $< | sed -e 's,^0x6,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 6' cns11643_6 > $@
 395
 396 cns11643_7.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
 397         grep '^\(#\|0x7\)' < $< | sed -e 's,^0x7,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 7' cns11643_7 > $@
 398
 399 cns11643_15.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
 400         grep '^\(#\|0xF\)' < $< | sed -e 's,^0xF,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 15' cns11643_15 > $@
 401
 402 cns11643_inv.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
 403         ./cjk_tab_to_h 'CNS 11643-1992 planes 1-7, CNS 11643-1986 plane 15' cns11643_inv < $< > $@
 404
 405 big5.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/OTHER/BIG5.TXT cjk_tab_to_h
 406         ./cjk_tab_to_h BIG5 big5 < $< > $@
 407
 408 cp950ext.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP950.TXT cjk_tab_to_h
 409         (echo '#' ; grep '^0xF9\(D[6-9A-F]\|[EF][0-9A-F]\)' < $< ) | ./cjk_tab_to_h 'CP950 extensions' cp950ext > $@
 410
 411 hkscs1999.h : $(TABLESDIR)/big5hkscs/HKSCS-1999_2006.TXT cjk_tab_to_h
 412         (echo '#' ; grep -v , $<) | ./cjk_tab_to_h HKSCS:1999 hkscs1999 > $@
 413
 414 hkscs2001.h : $(TABLESDIR)/big5hkscs/HKSCS-2001_2006-DELTA.TXT cjk_tab_to_h
 415         (echo '#' ; grep -v , $<) | ./cjk_tab_to_h HKSCS:2001 hkscs2001 > $@
 416
 417 hkscs2004.h : $(TABLESDIR)/big5hkscs/HKSCS-2004_2006-DELTA.TXT cjk_tab_to_h
 418         (echo '#' ; grep -v , $<) | ./cjk_tab_to_h HKSCS:2004 hkscs2004 > $@
 419
 420 hkscs2008.h : $(TABLESDIR)/big5hkscs/HKSCS-2008_2010-DELTA.TXT cjk_tab_to_h
 421         (echo '#' ; grep -v , $<) | ./cjk_tab_to_h HKSCS:2008 hkscs2008 > $@
 422
 423 # We use a modified KSC 5601 = KSX 1001 table. Jungshik Shin <jshin@mailaps.org>
 424 # reports that Prof. GIM Geongseog (KIM Keyongseok) <gimgs@asadal.cs.pusan.ac.kr>
 425 # (who represents South Korea in ISO/IEC JTC1 SC2/WG2 and SC22/WG20) says that
 426 # these two characters were added to KSX 1001 in December 1998. According to
 427 # http://std.dkuug.dk/jtc1/sc2/wg2/docs/N2815.doc, one more character
 428 # (Korean postal code sign) was added in 2002.
 429 ksc5601.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/KSC/KSC5601.TXT cjk_tab_to_h
 430         (cat $< ; echo '0xA2E6  0x20AC'; echo '0xA2E7   0x00AE'; echo '0xA2E8   0x327E') | ./cjk_tab_to_h 'KSC5601.1987-0, now KS X 1001:2002' ksc5601 > $@
 431
 432 uhc_1.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/KSC/KSC5601.TXT cjk_tab_to_h
 433         (echo '#' ; grep '^0x\([8-9]\|A0\)' < $< ) | ./cjk_tab_to_h 'Unified Hangul Code part 1' uhc_1 > $@
 434
 435 uhc_2.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/KSC/KSC5601.TXT cjk_tab_to_h
 436         (echo '#' ; grep '^0x\(A[1-9A-F]\|[B-F][0-9A-F]\)\([0-9]\|A0\)' < $< ) | ./cjk_tab_to_h 'Unified Hangul Code part 2' uhc_2 > $@
 437
 438 johab_hangul.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/KSC/JOHAB.TXT cjk_tab_to_h
 439         (echo '#' ; grep '^0x\([8-C]...\|D[0-7]..\)' < $< ) | ./cjk_tab_to_h 'JOHAB Hangul' johab_hangul > $@
 440
 441
 442 cp856.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MISC/CP856.TXT 8bit_tab_to_h
 443         ./8bit_tab_to_h CP856 cp856 < $<
 444
 445 cp922.h : $(TABLESDIR)/aix-4.3.2/IBM-922.TXT 8bit_tab_to_h
 446         (echo '#' ; cat $<) | ./8bit_tab_to_h CP922 cp922
 447
 448 cp1046.h : $(TABLESDIR)/aix-4.3.2/IBM-1046.TXT 8bit_tab_to_h
 449         (echo '#' ; cat $<) | ./8bit_tab_to_h CP1046 cp1046
 450
 451 cp1124.h : $(TABLESDIR)/aix-4.3.2/IBM-1124.TXT 8bit_tab_to_h
 452         (echo '#' ; cat $<) | ./8bit_tab_to_h CP1124 cp1124
 453
 454 cp1129.h : $(TABLESDIR)/aix-4.3.2/IBM-1129.TXT 8bit_tab_to_h
 455         (echo '#' ; cat $<) | ./8bit_tab_to_h CP1129 cp1129
 456
 457 cp1161.h : $(TABLESDIR)/glibc-2.2.90-iconv/IBM1161.TXT
 458         (echo '#' ; cat $(TABLESDIR)/glibc-2.2-iconv/ASCII.TXT ; grep -v '^0x[0-7]' $<) | ./8bit_tab_to_h CP1161 cp1161
 459
 460 cp1162.h : $(TABLESDIR)/glibc-2.2.90-iconv/IBM1162.TXT
 461         (echo '#' ; cat $<) | ./8bit_tab_to_h CP1162 cp1162
 462
 463 cp1163.h : $(TABLESDIR)/glibc-2.2.90-iconv/IBM1163.TXT
 464         (echo '#' ; cat $<) | ./8bit_tab_to_h CP1163 cp1163
 465
 466
 467 cp437.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP437.TXT 8bit_tab_to_h
 468         ./8bit_tab_to_h CP437 cp437 < $<
 469
 470 cp737.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP737.TXT 8bit_tab_to_h
 471         ./8bit_tab_to_h CP737 cp737 < $<
 472
 473 cp775.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP775.TXT 8bit_tab_to_h
 474         ./8bit_tab_to_h CP775 cp775 < $<
 475
 476 cp852.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP852.TXT 8bit_tab_to_h
 477         ./8bit_tab_to_h CP852 cp852 < $<
 478
 479 cp853.h : $(TABLESDIR)/other/CP853.TXT 8bit_tab_to_h
 480         (echo '#'; cat $<) | ./8bit_tab_to_h CP853 cp853
 481
 482 cp855.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP855.TXT 8bit_tab_to_h
 483         ./8bit_tab_to_h CP855 cp855 < $<
 484
 485 cp857.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP857.TXT 8bit_tab_to_h
 486         ./8bit_tab_to_h CP857 cp857 < $<
 487
 488 cp858.h : $(TABLESDIR)/windows-2000/CP858.TXT 8bit_tab_to_h
 489         (echo '#' ; cat $<) | ./8bit_tab_to_h CP858 cp858
 490
 491 cp860.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP860.TXT 8bit_tab_to_h
 492         ./8bit_tab_to_h CP860 cp860 < $<
 493
 494 cp861.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP861.TXT 8bit_tab_to_h
 495         ./8bit_tab_to_h CP861 cp861 < $<
 496
 497 cp863.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP863.TXT 8bit_tab_to_h
 498         ./8bit_tab_to_h CP863 cp863 < $<
 499
 500 cp864.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP864.TXT 8bit_tab_to_h
 501         ./8bit_tab_to_h CP864 cp864 < $<
 502
 503 cp865.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP865.TXT 8bit_tab_to_h
 504         ./8bit_tab_to_h CP865 cp865 < $<
 505
 506 cp869.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP869.TXT 8bit_tab_to_h
 507         ./8bit_tab_to_h CP869 cp869 < $<
 508
 509 cp1125.h : $(TABLESDIR)/csets-new/CP1125.TXT 8bit_tab_to_h
 510         ./8bit_tab_to_h CP1125 cp1125 < $<
 511
 512
 513 jisx0213.h : JISX0213.TXT cjk_tab_to_h
 514         ./cjk_tab_to_h JISX0213:2004 jisx0213 < $< > $@
 515
 516 tds565.h : $(TABLESDIR)/recode-cvs/TDS565.TXT 8bit_tab_to_h
 517         (echo '#'; cat $<) | ./8bit_tab_to_h TDS565 tds565 > $@
 518
 519 atarist.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MISC/ATARIST.TXT
 520         ./8bit_tab_to_h 'Atari ST' atarist < $< > $@
 521
 522 riscos1.h : $(TABLESDIR)/recode-cvs/RISCOS-LATIN1.TXT 8bit_tab_to_h
 523         (echo '#'; cat $<) | ./8bit_tab_to_h RISCOS-LATIN1 riscos1 > $@
 524
 525
 526 cjk_variants.h : $(TABLESDIR)/yasuoka/UniVariants cjk_variants
 527         ./cjk_variants < $< > $@
 528
 529
 530 8bit_tab_to_h : 8bit_tab_to_h.c
 531         gcc -O -Wall -g $< -o $@
 532
 533 cjk_tab_to_h : cjk_tab_to_h.c
 534         gcc -O -Wall -g $< -o $@
 535
 536 cjk_variants : cjk_variants.c
 537         gcc -O -Wall -g $< -o $@
 538
 539
 540 clean : force
 541         rm -f 8bit_tab_to_h cjk_tab_to_h cjk_variants $(ALL) GBKext.TXT
 542
 543 force :
 544