path: root/admin/charsets/Makefile.in

### @configure_input@

# Copyright (C) 2015-2021 Free Software Foundation, Inc.

# Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
#   National Institute of Advanced Industrial Science and Technology (AIST)
#   Registration Number H13PRO009
#
# This file is part of GNU Emacs.

# GNU Emacs is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.

# GNU Emacs is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.

# You should have received a copy of the GNU General Public License
# along with GNU Emacs.  If not, see <https://www.gnu.org/licenses/>.

### Commentary:

# Generate charset maps in etc/charsets.

SHELL = @SHELL@

AWK = @AWK@

srcdir = @srcdir@
top_srcdir = @top_srcdir@
top_builddir = @top_builddir@

charsetdir = ${top_srcdir}/etc/charsets
lispintdir = ${top_srcdir}/lisp/international
mapfiledir = ${srcdir}/mapfiles

GLIBC_CHARMAPS = ${srcdir}/glibc

-include ${top_builddir}/src/verbose.mk

# Note: We can not prepend "ISO-" to these map files because of file
# name limits on DOS.
ISO8859 = \
	8859-2.map 8859-3.map 8859-4.map 8859-5.map 8859-6.map 8859-7.map \
	8859-8.map 8859-9.map 8859-10.map 8859-11.map 8859-13.map 8859-14.map \
	8859-15.map 8859-16.map

IBM = \
	IBM037.map IBM038.map \
	IBM256.map IBM273.map IBM274.map IBM275.map IBM277.map IBM278.map \
	IBM280.map IBM281.map IBM284.map IBM285.map IBM290.map IBM297.map \
	IBM420.map IBM423.map IBM424.map IBM437.map IBM500.map IBM850.map \
	IBM851.map IBM852.map IBM855.map IBM856.map IBM857.map IBM860.map \
	IBM861.map IBM862.map IBM863.map IBM864.map IBM865.map IBM866.map \
	IBM868.map IBM869.map IBM870.map IBM871.map IBM874.map IBM875.map \
	IBM880.map IBM891.map IBM903.map IBM904.map IBM905.map IBM918.map \
	IBM1004.map IBM1026.map IBM1047.map

CODEPAGE = \
	CP737.map CP775.map CP1125.map\
	CP1250.map CP1251.map CP1252.map CP1253.map CP1254.map \
	CP1255.map CP1256.map CP1257.map CP1258.map \
	CP10007.map \
	CP720.map CP858.map

CJK =   GB2312.map GBK.map GB180302.map GB180304.map \
	BIG5.map BIG5-HKSCS.map\
	CNS-1.map CNS-2.map CNS-3.map CNS-4.map CNS-5.map CNS-6.map CNS-7.map \
	CNS-F.map \
	JISX0201.map JISX0208.map JISX0212.map JISX2131.map JISX2132.map \
	JISC6226.map CP932-2BYTE.map JISX213A.map\
	KSC5601.map KSC5636.map JOHAB.map

MISC =  KOI-8.map KOI8-R.map KOI8-U.map KOI8-T.map ALTERNATIVNYJ.map \
	MIK.map PTCP154.map \
	TIS-620.map VISCII.map VSCII.map VSCII-2.map\
	KA-PS.map KA-ACADEMY.map \
	HP-ROMAN8.map NEXTSTEP.map MACINTOSH.map EBCDICUK.map EBCDICUS.map \
	stdenc.map symbol.map \
	CP949-2BYTE.map \
	BIG5-1.map BIG5-2.map

# Emacs-mule charsets.
MULE =	MULE-ethiopic.map MULE-ipa.map MULE-is13194.map \
	MULE-sisheng.map MULE-tibetan.map \
	MULE-lviscii.map MULE-uviscii.map

SED_SCRIPT = $(srcdir)/jisx2131-filter

TRANS_TABLE = cp51932.el eucjp-ms.el
TRANS_TABLE := $(addprefix ${lispintdir}/,${TRANS_TABLE})

CHARSETS = ${ISO8859} ${IBM} ${CODEPAGE} ${CJK} ${MISC} ${MULE}
CHARSETS := $(addprefix ${charsetdir}/,${CHARSETS})

.PHONY: all

all: ${srcdir}/charsets.stamp

${srcdir}/charsets.stamp: ${CHARSETS} ${TRANS_TABLE}
	${AM_V_GEN}echo timestamp > $@

## Rules for each charset.

mapconv = ${srcdir}/mapconv
run_mapconv = AWK=${AWK} ${srcdir}/mapconv
big5 = ${srcdir}/big5.awk
compact = ${srcdir}/compact.awk
cp51932 = ${srcdir}/cp51932.awk
cp932 = ${srcdir}/cp932.awk
eucjp_ms = ${srcdir}/eucjp-ms.awk
gb180302 = ${srcdir}/gb180302.awk
gb180304 = ${srcdir}/gb180304.awk
kuten = ${srcdir}/kuten.awk

## Short aliases, eg VSCII.map = ${charsetdir}/VSCII.map
define map_template
 .PHONY: $(notdir ${1})
 $(notdir ${1}): ${1}
endef

$(foreach mfile,${CHARSETS} ${TRANS_TABLE},$(eval $(call map_template,$(mfile))))

${charsetdir}/VSCII.map: ${GLIBC_CHARMAPS}/TCVN5712-1.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[0-9a-f].[ 	]/' GLIBC-1 ${compact} > $@

${charsetdir}/VSCII-2.map: ${GLIBC_CHARMAPS}/TCVN5712-1.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[2-7a-f].[ 	]/' GLIBC-1 ${compact} \
	  | sed 's/0x20-0x7F.*/0x00-0x7F 0x0000/' > $@

${charsetdir}/ALTERNATIVNYJ.map: ${charsetdir}/IBM866.map
	${AM_V_GEN}(echo "# Modified from $(notdir $<) according to the chart at" && \
	  echo "# https://web.archive.org/web/20100131045151/http://www.cyrillic.com/ref/cyrillic/koi-8alt.html" && \
	  echo "# with guesses for the Unicodes of the glyphs." && \
	  sed -e '1 d' \
	     -e '/0xF2/ s/ .*/ 0x2019/' \
	     -e '/0xF3/ s/ .*/ 0x2018/' \
	     -e '/0xF4/ s/ .*/ 0x0301/' \
	     -e '/0xF5/ s/ .*/ 0x0300/' \
	     -e '/0xF6/ s/ .*/ 0x203A/' \
	     -e '/0xF7/ s/ .*/ 0x2039/' \
	     -e '/0xF8/ s/ .*/ 0x2191/' \
	     -e '/0xF9/ s/ .*/ 0x2193/' \
	     -e '/0xFA/ s/ .*/ 0x00B1/' \
	     -e '/0xFB/ s/ .*/ 0x00F7/' < $< ) > $@

${charsetdir}/MIK.map: ${mapfiledir}/bulgarian-mik.txt ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '1,$$' CZYBORRA ${compact} > $@

${charsetdir}/PTCP154.map: ${mapfiledir}/PTCP154 ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^0x/' IANA ${compact} > $@

${charsetdir}/stdenc.map: ${mapfiledir}/stdenc.txt ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^[0-9A-Fa-f]/' UNICODE ${compact} > $@

${charsetdir}/symbol.map: ${mapfiledir}/symbol.txt ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^[0-9A-Fa-f]/' UNICODE ${compact} > $@

${charsetdir}/CP720.map: ${mapfiledir}/CP720.map
	${AM_V_GEN}cp $< $@

${charsetdir}/CP858.map: ${mapfiledir}/CP858.map
	${AM_V_GEN}cp $< $@

${charsetdir}/CP949-2BYTE.map: ${GLIBC_CHARMAPS}/CP949.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[89a-f]/' GLIBC-2 ${compact} > $@

${charsetdir}/GB2312.map: ${GLIBC_CHARMAPS}/GB2312.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[a-f]/' GLIBC-2-7 ${compact} > $@

${charsetdir}/GBK.map: ${GLIBC_CHARMAPS}/GBK.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[89a-f]/' GLIBC-2 ${compact} > $@

${charsetdir}/GB180302.map: ${GLIBC_CHARMAPS}/GB18030.gz ${mapconv} ${gb180302}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x..\/x..[ 	]/' GLIBC-2 ${gb180302} > $@

${charsetdir}/GB180304.map: ${charsetdir}/GB180302.map ${gb180304}
	${AM_V_GEN}$(AWK) -f ${gb180304} < $< > $@

${charsetdir}/JISX0201.map: ${GLIBC_CHARMAPS}/JIS_X0201.gz ${mapconv} ${compact}
	${AM_V_GEN}(${mapconv} $< '/^<.*[ 	]\/x[0-9]/' GLIBC-1 ${compact} && \
	  echo "# Generated by hand" && \
	  echo "0xA1-0xDF 0xFF61" ) > $@

${charsetdir}/JISX0208.map: ${GLIBC_CHARMAPS}/EUC-JP.gz ${mapconv}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[a-f]/' GLIBC-2-7 \
	  | sed 's/0x2015/0x2014/' > $@

${charsetdir}/JISX0212.map: ${GLIBC_CHARMAPS}/EUC-JP.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x8f/ s,/x8f,,' GLIBC-2-7 ${compact} > $@

$(SED_SCRIPT): ${mapfiledir}/JISX213A.map
	${AM_V_at}sed -n -e '/^#/d' -e 's,.*0x\([0-9A-Z]*\)$$,/0x0*\1$$/d,p' < $< > $@

${charsetdir}/JISX2131.map: ${GLIBC_CHARMAPS}/EUC-JISX0213.gz ${mapconv} \
  $(SED_SCRIPT)
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[a-f]/' GLIBC-2-7 \
	  | sed -f $(SED_SCRIPT) \
	  | sed -e 's/0x2015/0x2014/' -e 's/0x2299/0x29BF/' > $@

${charsetdir}/JISX2132.map: ${GLIBC_CHARMAPS}/EUC-JISX0213.gz ${mapconv}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x8f/ s,/x8f,,' GLIBC-2-7 > $@

${charsetdir}/JISX213A.map: ${mapfiledir}/JISX213A.map
	${AM_V_GEN}cp $< $@

${charsetdir}/CP932-2BYTE.map: ${mapfiledir}/CP932.TXT ${mapconv} ${cp932}
	${AM_V_GEN}${run_mapconv} $< '/^0x[89A-F][0-9A-F][0-9A-F]/' UNICODE2 ${cp932} > $@

${lispintdir}/cp51932.el: ${charsetdir}/CP932-2BYTE.map ${cp51932}
	${AM_V_GEN}$(AWK) -f ${cp51932} < $< > $@

${lispintdir}/eucjp-ms.el: ${GLIBC_CHARMAPS}/EUC-JP-MS.gz ${eucjp_ms}
	${AM_V_GEN}gunzip -c $< | $(AWK) -f ${eucjp_ms} > $@

# As Uni2JIS doesn't contain mappings of characters added to Unicode
# recently, we add them manually here (including one correction for
# U+005C vs U+FF3C).  These changes are based on bogytech's blog at:
# https://bogytech.blogspot.com/search/label/emacs
${charsetdir}/JISC6226.map: ${mapfiledir}/Uni2JIS ${mapconv} ${kuten}
	${AM_V_GEN}(${run_mapconv} $< '/^[^#].*0-/' YASUOKA ${kuten} \
	  | sed -e '/0x2140/s/005C/FF3C/' && \
	  echo '0x3442 0x3D4E' && echo '0x374E 0x25874' && \
	  echo '0x3764 0x28EF6' && echo '0x513D 0x2F80F' && \
	  echo '0x7045 0x9724' ) > $@

${charsetdir}/KSC5601.map: ${GLIBC_CHARMAPS}/EUC-KR.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[a-f]/' GLIBC-2-7 ${compact} > $@

${charsetdir}/BIG5.map: ${GLIBC_CHARMAPS}/BIG5.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[a-f]/' GLIBC-2 > $@

${charsetdir}/BIG5-1.map: ${charsetdir}/BIG5.map ${mapconv} ${big5}
	${AM_V_GEN}(echo "# Generated from $(notdir $<)" && \
	  sed -n -e '/0xa140/,/0xc8fe/p' < $< | $(AWK) -f ${big5} ) > $@

${charsetdir}/BIG5-2.map: ${charsetdir}/BIG5.map ${mapconv} ${big5}
	${AM_V_GEN}(echo "# Generated from $(notdir $<)" && \
	  sed -n -e '/0xc940/,$$ p' < $< | $(AWK) -f ${big5} ) > $@

${charsetdir}/BIG5-HKSCS.map: ${GLIBC_CHARMAPS}/BIG5-HKSCS.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[89a-f].\//' GLIBC-2 ${compact} > $@

${charsetdir}/JOHAB.map: ${GLIBC_CHARMAPS}/JOHAB.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[89a-f]/' GLIBC-2 ${compact} > $@

${charsetdir}/CNS-1.map: ${GLIBC_CHARMAPS}/EUC-TW.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x[a-f]/' GLIBC-2-7 ${compact} > $@

# ${charsetdir}/CNS-1.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
# 	${AM_V_GEN}${run_mapconv} $< '/^C1/' KANJI-DATABASE ${compact} > $@

${charsetdir}/CNS-2.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^C2/' KANJI-DATABASE ${compact} > $@

${charsetdir}/CNS-3.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^C3/' KANJI-DATABASE ${compact} > $@

${charsetdir}/CNS-4.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^C4/' KANJI-DATABASE ${compact} > $@

${charsetdir}/CNS-5.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^C5/' KANJI-DATABASE ${compact} > $@

${charsetdir}/CNS-6.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^C6/' KANJI-DATABASE ${compact} > $@

${charsetdir}/CNS-7.map: ${mapfiledir}/cns2ucsdkw.txt ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^C7/' KANJI-DATABASE ${compact} > $@

${charsetdir}/CNS-F.map: ${GLIBC_CHARMAPS}/EUC-TW.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*\/x8e\/xaf/ s,/x8e/xaf,,' GLIBC-2-7 ${compact} > $@

# General target to produce map files for mule charsets.
${charsetdir}/MULE-%.map: ${mapfiledir}/MULE-%.map
	${AM_V_GEN}cp $< $@

# General target to produce map files for ISO-8859, GEORGIAN, and
# EBCDIC charsets.  We can not use the original file name because of
# file name limit on DOS.  "KA" is ISO 639 language code for Georgian.

${charsetdir}/8859-%.map: ${GLIBC_CHARMAPS}/ISO-8859-%.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x/' GLIBC-1 ${compact} > $@

${charsetdir}/KA-%.map: ${GLIBC_CHARMAPS}/GEORGIAN-%.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x/' GLIBC-1 ${compact} > $@

${charsetdir}/EBCDIC%.map: ${GLIBC_CHARMAPS}/EBCDIC-%.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x/' GLIBC-1 ${compact} > $@

# General target to produce map files for single-byte charsets.

${charsetdir}/%.map: ${GLIBC_CHARMAPS}/%.gz ${mapconv} ${compact}
	${AM_V_GEN}${run_mapconv} $< '/^<.*[ 	]\/x/' GLIBC-1 ${compact} > $@


.PHONY: clean bootstrap-clean distclean maintainer-clean gen-clean

clean:

## IMO this should also run gen-clean.
bootstrap-clean: clean

distclean: clean
	rm -f Makefile

gen-clean:
	rm -f ${CHARSETS} ${SED_SCRIPT} ${TRANS_TABLE} ${srcdir}/charsets.stamp

maintainer-clean: gen-clean distclean