admin/charsets/Makefile.in

   1 ### @configure_input@
   2
   3 # Copyright (C) 2015-2024 Free Software Foundation, Inc.
   4
   5 # Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
   6 #   National Institute of Advanced Industrial Science and Technology (AIST)
   7 #   Registration Number H13PRO009
   8 #
   9 # This file is part of GNU Emacs.
  10
  11 # GNU Emacs is free software: you can redistribute it and/or modify
  12 # it under the terms of the GNU General Public License as published by
  13 # the Free Software Foundation, either version 3 of the License, or
  14 # (at your option) any later version.
  15
  16 # GNU Emacs is distributed in the hope that it will be useful,
  17 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  18 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  19 # GNU General Public License for more details.
  20
  21 # You should have received a copy of the GNU General Public License
  22 # along with GNU Emacs.  If not, see <https://www.gnu.org/licenses/>.
  23
  24 ### Commentary:
  25
  26 # Generate charset maps in etc/charsets.
  27
  28 SHELL = @SHELL@
  29
  30 AWK = @AWK@
  31
  32 srcdir = @srcdir@
  33 top_srcdir = @top_srcdir@
  34 top_builddir = @top_builddir@
  35
  36 charsetdir = ${top_srcdir}/etc/charsets
  37 lispintdir = ${top_srcdir}/lisp/international
  38 mapfiledir = ${srcdir}/mapfiles
  39
  40 GLIBC_CHARMAPS = ${srcdir}/glibc
  41
  42 -include ${top_builddir}/src/verbose.mk
  43
  44 # Note: We can not prepend "ISO-" to these map files because of file
  45 # name limits on DOS.
  46 ISO8859 = \
  47         8859-2.map 8859-3.map 8859-4.map 8859-5.map 8859-6.map 8859-7.map \
  48         8859-8.map 8859-9.map 8859-10.map 8859-11.map 8859-13.map 8859-14.map \
  49         8859-15.map 8859-16.map
  50
  51 IBM = \
  52         IBM037.map IBM038.map \
  53         IBM256.map IBM273.map IBM274.map IBM275.map IBM277.map IBM278.map \
  54         IBM280.map IBM281.map IBM284.map IBM285.map IBM290.map IBM297.map \
  55         IBM420.map IBM423.map IBM424.map IBM437.map IBM500.map IBM850.map \
  56         IBM851.map IBM852.map IBM855.map IBM856.map IBM857.map IBM860.map \
  57         IBM861.map IBM862.map IBM863.map IBM864.map IBM865.map IBM866.map \
  58         IBM868.map IBM869.map IBM870.map IBM871.map IBM874.map IBM875.map \
  59         IBM880.map IBM891.map IBM903.map IBM904.map IBM905.map IBM918.map \
  60         IBM1004.map IBM1026.map IBM1047.map
  61
  62 CODEPAGE = \
  63         CP737.map CP775.map CP1125.map\
  64         CP1250.map CP1251.map CP1252.map CP1253.map CP1254.map \
  65         CP1255.map CP1256.map CP1257.map CP1258.map \
  66         CP10007.map \
  67         CP720.map CP858.map
  68
  69 CJK =   GB2312.map GBK.map GB180302.map GB180304.map \
  70         BIG5.map BIG5-HKSCS.map\
  71         CNS-1.map CNS-2.map CNS-3.map CNS-4.map CNS-5.map CNS-6.map CNS-7.map \
  72         CNS-F.map \
  73         JISX0201.map JISX0208.map JISX0212.map JISX2131.map JISX2132.map \
  74         JISC6226.map CP932-2BYTE.map JISX213A.map\
  75         KSC5601.map KSC5636.map JOHAB.map
  76
  77 MISC =  KOI-8.map KOI8-R.map KOI8-U.map KOI8-T.map ALTERNATIVNYJ.map \
  78         MIK.map PTCP154.map \
  79         TIS-620.map VISCII.map VSCII.map VSCII-2.map\
  80         KA-PS.map KA-ACADEMY.map \
  81         HP-ROMAN8.map NEXTSTEP.map MACINTOSH.map EBCDICUK.map EBCDICUS.map \
  82         stdenc.map symbol.map \
  83         CP949-2BYTE.map \
  84         BIG5-1.map BIG5-2.map
  85
  86 # Emacs-mule charsets.
  87 MULE =  MULE-ethiopic.map MULE-ipa.map MULE-is13194.map \
  88         MULE-sisheng.map MULE-tibetan.map \
  89         MULE-lviscii.map MULE-uviscii.map
  90
  91 SED_SCRIPT = $(srcdir)/jisx2131-filter
  92
  93 TRANS_TABLE = cp51932.el eucjp-ms.el
  94 TRANS_TABLE := $(addprefix ${lispintdir}/,${TRANS_TABLE})
  95
  96 CHARSETS = ${ISO8859} ${IBM} ${CODEPAGE} ${CJK} ${MISC} ${MULE}
  97 CHARSETS := $(addprefix ${charsetdir}/,${CHARSETS})
  98
  99 .PHONY: all
 100
 101 all: ${srcdir}/charsets.stamp
 102
 103 ${srcdir}/charsets.stamp: ${CHARSETS} ${TRANS_TABLE}
 104         ${AM_V_GEN}echo timestamp > $@
 105
 106 ## Rules for each charset.
 107
 108 mapconv = ${srcdir}/mapconv
 109 run_mapconv = AWK=${AWK} ${srcdir}/mapconv
 110 big5 = ${srcdir}/big5.awk
 111 compact = ${srcdir}/compact.awk
 112 cp51932 = ${srcdir}/cp51932.awk
 113 cp932 = ${srcdir}/cp932.awk
 114 eucjp_ms = ${srcdir}/eucjp-ms.awk
 115 gb180302 = ${srcdir}/gb180302.awk
 116 gb180304 = ${srcdir}/gb180304.awk
 117 kuten = ${srcdir}/kuten.awk
 118
 119 ## Short aliases, eg VSCII.map = ${charsetdir}/VSCII.map
 120 define map_template
 121  .PHONY: $(notdir ${1})
 122  $(notdir ${1}): ${1}
 123 endef
 124
 125 $(foreach mfile,${CHARSETS} ${TRANS_TABLE},$(eval $(call map_template,$(mfile))))
 126
 127 ${charsetdir}/VSCII.map: ${GLIBC_CHARMAPS}/TCVN5712-1.gz ${mapconv} ${compact}
 128         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[0-9a-f].[  ]/' GLIBC-1 ${compact} > $@
 129
 130 ${charsetdir}/VSCII-2.map: ${GLIBC_CHARMAPS}/TCVN5712-1.gz ${mapconv} ${compact}
 131         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[2-7a-f].[  ]/' GLIBC-1 ${compact} \
 132           | sed 's/0x20-0x7F.*/0x00-0x7F 0x0000/' > $@
 133
 134 ${charsetdir}/ALTERNATIVNYJ.map: ${charsetdir}/IBM866.map
 135         ${AM_V_GEN}(echo "# Modified from $(notdir $<) according to the chart at" && \
 136           echo "# https://web.archive.org/web/20100131045151/http://www.cyrillic.com/ref/cyrillic/koi-8alt.html" && \
 137           echo "# with guesses for the Unicodes of the glyphs." && \
 138           sed -e '1 d' \
 139              -e '/0xF2/ s/ .*/ 0x2019/' \
 140              -e '/0xF3/ s/ .*/ 0x2018/' \
 141              -e '/0xF4/ s/ .*/ 0x0301/' \
 142              -e '/0xF5/ s/ .*/ 0x0300/' \
 143              -e '/0xF6/ s/ .*/ 0x203A/' \
 144              -e '/0xF7/ s/ .*/ 0x2039/' \
 145              -e '/0xF8/ s/ .*/ 0x2191/' \
 146              -e '/0xF9/ s/ .*/ 0x2193/' \
 147              -e '/0xFA/ s/ .*/ 0x00B1/' \
 148              -e '/0xFB/ s/ .*/ 0x00F7/' < $< ) > $@
 149
 150 ${charsetdir}/MIK.map: ${mapfiledir}/bulgarian-mik.txt ${mapconv} ${compact}
 151         ${AM_V_GEN}${run_mapconv} $< '1,$$' CZYBORRA ${compact} > $@
 152
 153 ${charsetdir}/PTCP154.map: ${mapfiledir}/PTCP154 ${mapconv} ${compact}
 154         ${AM_V_GEN}${run_mapconv} $< '/^0x/' IANA ${compact} > $@
 155
 156 ${charsetdir}/stdenc.map: ${mapfiledir}/stdenc.txt ${mapconv} ${compact}
 157         ${AM_V_GEN}${run_mapconv} $< '/^[0-9A-Fa-f]/' UNICODE ${compact} > $@
 158
 159 ${charsetdir}/symbol.map: ${mapfiledir}/symbol.txt ${mapconv} ${compact}
 160         ${AM_V_GEN}${run_mapconv} $< '/^[0-9A-Fa-f]/' UNICODE ${compact} > $@
 161
 162 ${charsetdir}/CP720.map: ${mapfiledir}/CP720.map
 163         ${AM_V_GEN}cp $< $@
 164
 165 ${charsetdir}/CP858.map: ${mapfiledir}/CP858.map
 166         ${AM_V_GEN}cp $< $@
 167
 168 ${charsetdir}/CP949-2BYTE.map: ${GLIBC_CHARMAPS}/CP949.gz ${mapconv} ${compact}
 169         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[89a-f]/' GLIBC-2 ${compact} > $@
 170
 171 ${charsetdir}/GB2312.map: ${GLIBC_CHARMAPS}/GB2312.gz ${mapconv} ${compact}
 172         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[a-f]/' GLIBC-2-7 ${compact} > $@
 173
 174 ${charsetdir}/GBK.map: ${GLIBC_CHARMAPS}/GBK.gz ${mapconv} ${compact}
 175         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[89a-f]/' GLIBC-2 ${compact} > $@
 176
 177 ${charsetdir}/GB180302.map: ${GLIBC_CHARMAPS}/GB18030.gz ${mapconv} ${gb180302}
 178         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x..\/x..[    ]/' GLIBC-2 ${gb180302} > $@
 179
 180 ${charsetdir}/GB180304.map: ${charsetdir}/GB180302.map ${gb180304}
 181         ${AM_V_GEN}$(AWK) -f ${gb180304} < $< > $@
 182
 183 ${charsetdir}/JISX0201.map: ${GLIBC_CHARMAPS}/JIS_X0201.gz ${mapconv} ${compact}
 184         ${AM_V_GEN}(${run_mapconv} $< '/^<.*[   ]\/x[0-9]/' GLIBC-1 ${compact} && \
 185           echo "# Generated by hand" && \
 186           echo "0xA1-0xDF 0xFF61" ) > $@
 187
 188 ${charsetdir}/JISX0208.map: ${GLIBC_CHARMAPS}/EUC-JP.gz ${mapconv}
 189         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[a-f]/' GLIBC-2-7 \
 190           | sed 's/0x2015/0x2014/' > $@
 191
 192 ${charsetdir}/JISX0212.map: ${GLIBC_CHARMAPS}/EUC-JP.gz ${mapconv} ${compact}
 193         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x8f/ s,/x8f,,' GLIBC-2-7 ${compact} > $@
 194
 195 $(SED_SCRIPT): ${mapfiledir}/JISX213A.map
 196         ${AM_V_at}sed -n -e '/^#/d' -e 's,.*0x\([0-9A-Z]*\)$$,/0x0*\1$$/d,p' < $< > $@
 197
 198 ${charsetdir}/JISX2131.map: ${GLIBC_CHARMAPS}/EUC-JISX0213.gz ${mapconv} \
 199   $(SED_SCRIPT)
 200         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[a-f]/' GLIBC-2-7 \
 201           | sed -f $(SED_SCRIPT) \
 202           | sed -e 's/0x2015/0x2014/' -e 's/0x2299/0x29BF/' > $@
 203
 204 ${charsetdir}/JISX2132.map: ${GLIBC_CHARMAPS}/EUC-JISX0213.gz ${mapconv}
 205         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x8f/ s,/x8f,,' GLIBC-2-7 > $@
 206
 207 ${charsetdir}/JISX213A.map: ${mapfiledir}/JISX213A.map
 208         ${AM_V_GEN}cp $< $@
 209
 210 ${charsetdir}/CP932-2BYTE.map: ${mapfiledir}/CP932.TXT ${mapconv} ${cp932}
 211         ${AM_V_GEN}${run_mapconv} $< '/^0x[89A-F][0-9A-F][0-9A-F]/' UNICODE2 ${cp932} > $@
 212
 213 ${lispintdir}/cp51932.el: ${charsetdir}/CP932-2BYTE.map ${cp51932}
 214         ${AM_V_GEN}$(AWK) -f ${cp51932} < $< > $@
 215
 216 ${lispintdir}/eucjp-ms.el: ${GLIBC_CHARMAPS}/EUC-JP-MS.gz ${eucjp_ms}
 217         ${AM_V_GEN}gunzip -c $< | $(AWK) -f ${eucjp_ms} > $@
 218
 219 # As Uni2JIS doesn't contain mappings of characters added to Unicode
 220 # recently, we add them manually here (including one correction for
 221 # U+005C vs U+FF3C).  These changes are based on bogytech's blog at:
 222 # https://bogytech.blogspot.com/search/label/emacs
 223 ${charsetdir}/JISC6226.map: ${mapfiledir}/Uni2JIS ${mapconv} ${kuten}
 224         ${AM_V_GEN}(${run_mapconv} $< '/^[^#].*0-/' YASUOKA ${kuten} \
 225           | sed -e '/0x2140/s/005C/FF3C/' && \
 226           echo '0x3442 0x3D4E' && echo '0x374E 0x25874' && \
 227           echo '0x3764 0x28EF6' && echo '0x513D 0x2F80F' && \
 228           echo '0x7045 0x9724' ) > $@
 229
 230 ${charsetdir}/KSC5601.map: ${GLIBC_CHARMAPS}/EUC-KR.gz ${mapconv} ${compact}
 231         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[a-f]/' GLIBC-2-7 ${compact} > $@
 232
 233 ${charsetdir}/BIG5.map: ${GLIBC_CHARMAPS}/BIG5.gz ${mapconv} ${compact}
 234         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[a-f]/' GLIBC-2 > $@
 235
 236 ${charsetdir}/BIG5-1.map: ${charsetdir}/BIG5.map ${mapconv} ${big5}
 237         ${AM_V_GEN}(echo "# Generated from $(notdir $<)" && \
 238           sed -n -e '/0xa140/,/0xc8fe/p' < $< | $(AWK) -f ${big5} ) > $@
 239
 240 ${charsetdir}/BIG5-2.map: ${charsetdir}/BIG5.map ${mapconv} ${big5}
 241         ${AM_V_GEN}(echo "# Generated from $(notdir $<)" && \
 242           sed -n -e '/0xc940/,$$ p' < $< | $(AWK) -f ${big5} ) > $@
 243
 244 ${charsetdir}/BIG5-HKSCS.map: ${GLIBC_CHARMAPS}/BIG5-HKSCS.gz ${mapconv} ${compact}
 245         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[89a-f].\//' GLIBC-2 ${compact} > $@
 246
 247 ${charsetdir}/JOHAB.map: ${GLIBC_CHARMAPS}/JOHAB.gz ${mapconv} ${compact}
 248         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[89a-f]/' GLIBC-2 ${compact} > $@
 249
 250 ${charsetdir}/CNS-1.map: ${GLIBC_CHARMAPS}/EUC-TW.gz ${mapconv} ${compact}
 251         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x[a-f]/' GLIBC-2-7 ${compact} > $@
 252
 253 # ${charsetdir}/CNS-1.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
 254 #       ${AM_V_GEN}${run_mapconv} $< '/^C1/' KANJI-DATABASE ${compact} > $@
 255
 256 ${charsetdir}/CNS-2.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
 257         ${AM_V_GEN}${run_mapconv} $< '/^C2/' KANJI-DATABASE ${compact} > $@
 258
 259 ${charsetdir}/CNS-3.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
 260         ${AM_V_GEN}${run_mapconv} $< '/^C3/' KANJI-DATABASE ${compact} > $@
 261
 262 ${charsetdir}/CNS-4.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
 263         ${AM_V_GEN}${run_mapconv} $< '/^C4/' KANJI-DATABASE ${compact} > $@
 264
 265 ${charsetdir}/CNS-5.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
 266         ${AM_V_GEN}${run_mapconv} $< '/^C5/' KANJI-DATABASE ${compact} > $@
 267
 268 ${charsetdir}/CNS-6.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
 269         ${AM_V_GEN}${run_mapconv} $< '/^C6/' KANJI-DATABASE ${compact} > $@
 270
 271 ${charsetdir}/CNS-7.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
 272         ${AM_V_GEN}${run_mapconv} $< '/^C7/' KANJI-DATABASE ${compact} > $@
 273
 274 ${charsetdir}/CNS-F.map: ${GLIBC_CHARMAPS}/EUC-TW.gz ${mapconv} ${compact}
 275         ${AM_V_GEN}${run_mapconv} $< '/^<.*\/x8e\/xaf/ s,/x8e/xaf,,' GLIBC-2-7 ${compact} > $@
 276
 277 # General target to produce map files for mule charsets.
 278 ${charsetdir}/MULE-%.map: ${mapfiledir}/MULE-%.map
 279         ${AM_V_GEN}cp $< $@
 280
 281 # General target to produce map files for ISO-8859, GEORGIAN, and
 282 # EBCDIC charsets.  We can not use the original file name because of
 283 # file name limit on DOS.  "KA" is ISO 639 language code for Georgian.
 284
 285 ${charsetdir}/8859-%.map: ${GLIBC_CHARMAPS}/ISO-8859-%.gz ${mapconv} ${compact}
 286         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x/' GLIBC-1 ${compact} > $@
 287
 288 ${charsetdir}/KA-%.map: ${GLIBC_CHARMAPS}/GEORGIAN-%.gz ${mapconv} ${compact}
 289         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x/' GLIBC-1 ${compact} > $@
 290
 291 ${charsetdir}/EBCDIC%.map: ${GLIBC_CHARMAPS}/EBCDIC-%.gz ${mapconv} ${compact}
 292         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x/' GLIBC-1 ${compact} > $@
 293
 294 # General target to produce map files for single-byte charsets.
 295
 296 ${charsetdir}/%.map: ${GLIBC_CHARMAPS}/%.gz ${mapconv} ${compact}
 297         ${AM_V_GEN}${run_mapconv} $< '/^<.*[    ]\/x/' GLIBC-1 ${compact} > $@
 298
 299
 300 .PHONY: clean bootstrap-clean distclean maintainer-clean gen-clean
 301
 302 clean:
 303
 304 ## IMO this should also run gen-clean.
 305 bootstrap-clean: clean
 306
 307 distclean: clean
 308         rm -f Makefile
 309
 310 gen-clean:
 311         rm -f ${CHARSETS} ${SED_SCRIPT} ${TRANS_TABLE} ${srcdir}/charsets.stamp
 312
 313 maintainer-clean: gen-clean distclean
 314