Fresh start

1 files changed, 532 insertions, 0 deletions

diff --git a/jni/iconv/tools/Makefile b/jni/iconv/tools/Makefile
new file mode 100644
index 0000000..2bf7d84
--- /dev/null
+++ b/jni/iconv/tools/Makefile
@@ -0,0 +1,532 @@
+
+# Directory containing conversion tables.
+# You have to unpack the conversion-tables.tar.gz package.
+TABLESDIR = /home/bruno/chs/conversion-tables
+
+ALL = \
+ ascii.h \
+ iso8859_1.h \
+ iso8859_2.h \
+ iso8859_3.h \
+ iso8859_4.h \
+ iso8859_5.h \
+ iso8859_6.h \
+ iso8859_7.h \
+ iso8859_8.h \
+ iso8859_9.h \
+ iso8859_10.h \
+ iso8859_11.h \
+ iso8859_13.h \
+ iso8859_14.h \
+ iso8859_15.h \
+ iso8859_16.h \
+ koi8_r.h \
+ koi8_u.h \
+ koi8_ru.h \
+ cp1250.h \
+ cp1251.h \
+ cp1252.h \
+ cp1253.h \
+ cp1254.h \
+ cp1255.h \
+ cp1256.h \
+ cp1257.h \
+ cp1258.h \
+ cp850.h \
+ cp862.h \
+ cp866.h \
+ cp1131.h \
+ mac_roman.h \
+ mac_centraleurope.h \
+ mac_iceland.h \
+ mac_croatian.h \
+ mac_romania.h \
+ mac_cyrillic.h \
+ mac_ukraine.h \
+ mac_greek.h \
+ mac_turkish.h \
+ mac_hebrew.h \
+ mac_arabic.h \
+ mac_thai.h \
+ hp_roman8.h \
+ nextstep.h \
+ armscii_8.h \
+ georgian_academy.h \
+ georgian_ps.h \
+ koi8_t.h \
+ pt154.h \
+ rk1048.h \
+ mulelao.h \
+ cp1133.h \
+ tis620.h \
+ cp874.h \
+ viscii.h \
+ tcvn.h \
+ jisx0201.h \
+ jisx0208.h \
+ jisx0212.h \
+ cp932ext.h \
+ gb2312.h \
+ isoir165ext.h \
+ gb12345ext.h \
+ gbkext1.h \
+ gbkext2.h \
+ gbkext_inv.h \
+ cp936ext.h \
+ gb18030ext.h \
+ gb18030uni.h \
+ cns11643_1.h \
+ cns11643_2.h \
+ cns11643_3.h \
+ cns11643_4a.h \
+ cns11643_4b.h \
+ cns11643_5.h \
+ cns11643_6.h \
+ cns11643_7.h \
+ cns11643_15.h \
+ cns11643_inv.h \
+ big5.h \
+ cp950ext.h \
+ hkscs1999.h \
+ hkscs2001.h \
+ hkscs2004.h \
+ ksc5601.h \
+ uhc_1.h \
+ uhc_2.h \
+ johab_hangul.h \
+ cp856.h \
+ cp922.h \
+ cp1046.h \
+ cp1124.h \
+ cp1129.h \
+ cp1161.h \
+ cp1162.h \
+ cp1163.h \
+ cp437.h \
+ cp737.h \
+ cp775.h \
+ cp852.h \
+ cp853.h \
+ cp855.h \
+ cp857.h \
+ cp858.h \
+ cp860.h \
+ cp861.h \
+ cp863.h \
+ cp864.h \
+ cp865.h \
+ cp869.h \
+ cp1125.h \
+ jisx0213.h \
+ tds565.h \
+ atarist.h \
+ riscos1.h \
+ cjk_variants.h
+
+all : $(ALL)
+
+ascii.h : $(TABLESDIR)/glibc-2.1-iconv/ASCII.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ASCII ascii < $<
+
+iso8859_1.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-1.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-1 iso8859_1 < $<
+
+iso8859_2.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-2.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-2 iso8859_2 < $<
+
+iso8859_3.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-3.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-3 iso8859_3 < $<
+
+iso8859_4.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-4.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-4 iso8859_4 < $<
+
+iso8859_5.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-5.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-5 iso8859_5 < $<
+
+iso8859_6.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-6.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-6 iso8859_6 < $<
+
+iso8859_7.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-7-2003.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-7 iso8859_7 < $<
+
+iso8859_8.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-8.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-8 iso8859_8 < $<
+
+iso8859_9.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-9.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-9 iso8859_9 < $<
+
+iso8859_10.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-10.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-10 iso8859_10 < $<
+
+iso8859_11.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-11.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-11 iso8859_11 < $<
+
+iso8859_13.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-13.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-13 iso8859_13 < $<
+
+iso8859_14.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-14.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-14 iso8859_14 < $<
+
+iso8859_15.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-15.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-15 iso8859_15 < $<
+
+iso8859_16.h : $(TABLESDIR)/unicode.org-mappings/ISO8859/8859-16.TXT 8bit_tab_to_h
+	./8bit_tab_to_h ISO-8859-16 iso8859_16 < $<
+
+koi8_r.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MISC/KOI8-R.TXT 8bit_tab_to_h
+	./8bit_tab_to_h KOI8-R koi8_r < $<
+
+koi8_u.h : $(TABLESDIR)/csets-new/KOI8-U.TXT 8bit_tab_to_h
+	./8bit_tab_to_h KOI8-U koi8_u < $<
+
+koi8_ru.h : $(TABLESDIR)/freebsd-iconv-0.4/KOI8-RU.TXT 8bit_tab_to_h
+	./8bit_tab_to_h KOI8-RU koi8_ru < $<
+
+cp1250.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1250.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP1250 cp1250 < $<
+
+cp1251.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1251.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP1251 cp1251 < $<
+
+cp1252.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1252.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP1252 cp1252 < $<
+
+cp1253.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1253.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP1253 cp1253 < $<
+
+cp1254.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1254.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP1254 cp1254 < $<
+
+cp1255.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1255.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP1255 cp1255 < $<
+
+cp1256.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1256.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP1256 cp1256 < $<
+
+cp1257.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1257.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP1257 cp1257 < $<
+
+cp1258.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP1258.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP1258 cp1258 < $<
+
+cp850.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP850.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP850 cp850 < $<
+
+cp862.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP862.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP862 cp862 < $<
+
+cp866.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP866.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP866 cp866 < $<
+
+cp1131.h : $(TABLESDIR)/other/CP1131.TXT 8bit_tab_to_h
+	(echo '#' ; cat $<) | ./8bit_tab_to_h CP1131 cp1131
+
+mac_roman.h : $(TABLESDIR)/jdk-1.1.7b/MAC-ROMAN.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacRoman mac_roman < $<
+
+mac_centraleurope.h : $(TABLESDIR)/jdk-1.1.7b/MAC-CENTRAL-EUROPE.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacCentralEurope mac_centraleurope < $<
+
+mac_iceland.h : $(TABLESDIR)/jdk-1.1.7b/MAC-ICELAND.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacIceland mac_iceland < $<
+
+mac_croatian.h : $(TABLESDIR)/jdk-1.1.7b/MAC-CROATIAN.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacCroatian mac_croatian < $<
+
+mac_romania.h : $(TABLESDIR)/jdk-1.1.7b/MAC-ROMANIA.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacRomania mac_romania < $<
+
+mac_cyrillic.h : $(TABLESDIR)/jdk-1.1.7b/MAC-CYRILLIC.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacCyrillic mac_cyrillic < $<
+
+mac_ukraine.h : $(TABLESDIR)/jdk-1.1.7b/MAC-UKRAINE.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacUkraine mac_ukraine < $<
+
+mac_greek.h : $(TABLESDIR)/jdk-1.1.7b/MAC-GREEK.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacGreek mac_greek < $<
+
+mac_turkish.h : $(TABLESDIR)/jdk-1.1.7b/MAC-TURKISH.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacTurkish mac_turkish < $<
+
+mac_hebrew.h : $(TABLESDIR)/jdk-1.1.7b/MAC-HEBREW.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacHebrew mac_hebrew < $<
+
+mac_arabic.h : $(TABLESDIR)/jdk-1.1.7b/MAC-ARABIC.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacArabic mac_arabic < $<
+
+mac_thai.h : $(TABLESDIR)/jdk-1.1.7b/MAC-THAI.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MacThai mac_thai < $<
+
+hp_roman8.h : $(TABLESDIR)/glibc-2.1-iconv/HP-ROMAN8.TXT 8bit_tab_to_h
+	./8bit_tab_to_h HP-ROMAN8 hp_roman8 < $<
+
+nextstep.h : $(TABLESDIR)/clisp/NEXTSTEP.TXT 8bit_tab_to_h
+	./8bit_tab_to_h NEXTSTEP nextstep < $<
+
+armscii_8.h : $(TABLESDIR)/glibc-2.2.90-iconv/ARMSCII-8.TXT 8bit_tab_to_h
+	(echo '#' ; cat $<) | ./8bit_tab_to_h ARMSCII-8 armscii_8
+
+georgian_academy.h : $(TABLESDIR)/csets-1.6/GEO-ITA.TXT 8bit_tab_to_h
+	./8bit_tab_to_h GEORGIAN-ACADEMY georgian_academy < $<
+
+georgian_ps.h : $(TABLESDIR)/csets-1.6/GEO-PS.TXT 8bit_tab_to_h
+	./8bit_tab_to_h GEORGIAN-PS georgian_ps < $<
+
+koi8_t.h : $(TABLESDIR)/glibc-2.2.90-iconv/KOI8-T.TXT
+	(echo '#' ; cat $<) | ./8bit_tab_to_h KOI8-T koi8_t
+
+pt154.h : $(TABLESDIR)/IANA/PTCP154.TXT
+	./8bit_tab_to_h PT154 pt154 < $<
+
+rk1048.h : $(TABLESDIR)/IANA/KZ-1048.TXT
+	(echo '#' ; cat $<) | ./8bit_tab_to_h RK1048 rk1048
+
+mulelao.h : $(TABLESDIR)/csets-new/MULELAO1.TXT 8bit_tab_to_h
+	./8bit_tab_to_h MULELAO-1 mulelao < $<
+
+cp1133.h : $(TABLESDIR)/csets-new/CP1133.TXT 8bit_tab_to_h
+	./8bit_tab_to_h IBM-CP1133 cp1133 < $<
+
+tis620.h : $(TABLESDIR)/glibc-2.1-iconv/TIS-620.TXT 8bit_tab_to_h
+	./8bit_tab_to_h TIS620.2533-1 tis620 < $<
+
+cp874.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP874.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP874 cp874 < $<
+
+viscii.h : $(TABLESDIR)/csets-1.6/VISCII.TXT 8bit_tab_to_h
+	./8bit_tab_to_h VISCII1.1-1 viscii < $<
+
+tcvn.h : $(TABLESDIR)/csets-1.6/VN5712-1.TXT 8bit_tab_to_h
+	./8bit_tab_to_h TCVN-5712 tcvn < $<
+
+jisx0201.h : $(TABLESDIR)/clisp/JIS_X0201.TXT 8bit_tab_to_h
+	./8bit_tab_to_h JISX0201.1976-0 jisx0201 < $<
+
+# We use modified JISX0208 and JISX0212 tables. Why?
+# Hironori Sakamoto and Tomohiro Kubota explain that
+# - EUC-JP and SHIFT_JIS contain JISX0208 exactly,
+# - Their round-trip conversion to Unicode and back must be the identity,
+# - Conversions between EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP must behave
+#   as if no Unicode conversion was involved,
+# - When JISX0208 is used as a CES (i.e. combined with ASCII) its mapping of
+#   REVERSE SOLIDUS becomes a FULLWIDTH REVERSE SOLIDUS, apparently because
+#   round-trip conversion stability is more important than a particular glyph.
+#   Only with CCS the character is a REVERSE SOLIDUS.
+# As a consequence, we use FULLWIDTH REVERSE SOLIDUS in EUC-JP's JISX0208 part,
+# and for consistency also in SHIFT_JIS and ISO-2022-JP, i.e. everywhere.
+# JISX0208 never occurs as a CCS in practice. Similarly with JISX0212.
+
+# Unicode.org maps 0x2140 to U+005C. We map it to U+FF3C.
+jisx0208.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/JIS/JIS0208.TXT cjk_tab_to_h
+	sed -e 's,^0x....[ 	]*\(0x....[ 	]*0x.....*\)$$,\1,' < $< | sed -e 's,\([ 	]\)0x005C,\10xFF3C,' | ./cjk_tab_to_h JISX0208.1990-0 jisx0208 > $@
+
+# Unicode.org maps 0x2237 to U+007E. We map it to U+FF5E.
+jisx0212.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/JIS/JIS0212.TXT cjk_tab_to_h
+	sed -e 's,\([ 	]\)0x007E,\10xFF5E,' < $< | ./cjk_tab_to_h JISX0212.1990-0 jisx0212 > $@
+
+cp932ext.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP932.TXT cjk_tab_to_h
+	(echo '#' ; grep '^0x\(87\|E[D-F]\|F[0-9A-F]\)[0-9A-F][0-9A-F]' < $< ) | ./cjk_tab_to_h 'CP932 extensions' cp932ext > $@
+
+gb2312.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/GB/GB2312.TXT cjk_tab_to_h
+	./cjk_tab_to_h GB2312.1980-0 gb2312 < $< > $@
+
+isoir165ext.h : $(TABLESDIR)/csets-new/ISO-IR-165-additions.TXT cjk_tab_to_h
+	(echo '#' ; grep -v '^0x2[8A]' < $<) | ./cjk_tab_to_h 'ISO-IR-165 extensions' isoir165ext > $@
+
+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
+	(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
+
+gbkext1.h : GBKext.TXT cjk_tab_to_h
+	(echo '#' ; grep '^0x\([89].\|A0\)' < GBKext.TXT) | ./cjk_tab_to_h 'GBK/3 extensions' gbkext1 > $@
+
+gbkext2.h : GBKext.TXT cjk_tab_to_h
+	(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 > $@
+
+gbkext_inv.h : GBKext.TXT cjk_tab_to_h
+	(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 > $@
+
+cp936ext.h : GBKext.TXT cjk_tab_to_h
+	(echo '#' ; grep '^0xA[1-9][B-F].' < GBKext.TXT) | ./cjk_tab_to_h 'CP936 extensions' cp936ext > $@
+
+GBKext.TXT : $(TABLESDIR)/unicode.org-mappings/EASTASIA/GB/GB2312.TXT $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP936.TXT
+	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
+
+gb18030ext.h : GB18030ext.TXT cjk_tab_to_h
+	(echo '#' ; cat GB18030ext.TXT) | ./cjk_tab_to_h 'GB18030 two-byte extension' gb18030ext > $@
+
+GB18030ext.TXT : $(TABLESDIR)/glibc-2.2.2-iconv/GB18030.TXT $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP936.TXT
+	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....$$' | sed -e 's/^> //' > $@ && rm -f tmpGBK.TXT
+
+gb18030uni.h : GB18030uni.TXT cjk_tab_to_h
+	./cjk_tab_to_h 'GB18030 four-byte extension' gb18030uni < GB18030uni.TXT > $@
+
+GB18030uni.TXT : $(TABLESDIR)/gb18030/filled-GB18030.TXT
+	grep '^0x........	0x....$$' < $(TABLESDIR)/gb18030/filled-GB18030.TXT > $@
+
+cns11643_1.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
+	grep '^\(#\|0x1\)' < $< | sed -e 's,^0x1,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 1' cns11643_1 > $@
+
+cns11643_2.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
+	grep '^\(#\|0x2\)' < $< | sed -e 's,^0x2,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 2' cns11643_2 > $@
+
+cns11643_3.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
+	grep '^\(#\|0x3\)' < $< | sed -e 's,^0x3,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 3' cns11643_3 > $@
+
+cns11643_4a.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
+	grep '^\(#\|0x4[0-3]\)' < $< | sed -e 's,^0x4,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 4 part a' cns11643_4a > $@
+
+cns11643_4b.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
+	grep '^\(#\|0x4[4-7]\)' < $< | sed -e 's,^0x4,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 4 part b' cns11643_4b > $@
+
+cns11643_5.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
+	grep '^\(#\|0x5\)' < $< | sed -e 's,^0x5,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 5' cns11643_5 > $@
+
+cns11643_6.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
+	grep '^\(#\|0x6\)' < $< | sed -e 's,^0x6,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 6' cns11643_6 > $@
+
+cns11643_7.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
+	grep '^\(#\|0x7\)' < $< | sed -e 's,^0x7,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 7' cns11643_7 > $@
+
+cns11643_15.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
+	grep '^\(#\|0xF\)' < $< | sed -e 's,^0xF,0x,' | ./cjk_tab_to_h 'CNS 11643-1992 plane 15' cns11643_15 > $@
+
+cns11643_inv.h : $(TABLESDIR)/csets-new/CNS11643-Unicode32.TXT cjk_tab_to_h
+	./cjk_tab_to_h 'CNS 11643-1992 planes 1-7, CNS 11643-1986 plane 15' cns11643_inv < $< > $@
+
+big5.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/OTHER/BIG5.TXT cjk_tab_to_h
+	./cjk_tab_to_h BIG5 big5 < $< > $@
+
+cp950ext.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/WINDOWS/CP950.TXT cjk_tab_to_h
+	(echo '#' ; grep '^0xF9\(D[6-9A-F]\|[EF][0-9A-F]\)' < $< ) | ./cjk_tab_to_h 'CP950 extensions' cp950ext > $@
+
+hkscs1999.h : $(TABLESDIR)/big5hkscs/HKSCS-1999_2006.TXT cjk_tab_to_h
+	(echo '#' ; grep -v , $<) | ./cjk_tab_to_h HKSCS:1999 hkscs1999 > $@
+
+hkscs2001.h : $(TABLESDIR)/big5hkscs/HKSCS-2001_2006-DELTA.TXT cjk_tab_to_h
+	(echo '#' ; grep -v , $<) | ./cjk_tab_to_h HKSCS:2001 hkscs2001 > $@
+
+hkscs2004.h : $(TABLESDIR)/big5hkscs/HKSCS-2004_2006-DELTA.TXT cjk_tab_to_h
+	(echo '#' ; grep -v , $<) | ./cjk_tab_to_h HKSCS:2004 hkscs2004 > $@
+
+# We use a modified KSC 5601 = KSX 1001 table. Jungshik Shin <jshin@mailaps.org>
+# reports that Prof. GIM Geongseog (KIM Keyongseok) <gimgs@asadal.cs.pusan.ac.kr>
+# (who represents South Korea in ISO/IEC JTC1 SC2/WG2 and SC22/WG20) says that
+# these two characters were added to KSX 1001 in December 1998. According to
+# http://std.dkuug.dk/jtc1/sc2/wg2/docs/N2815.doc, one more character
+# (Korean postal code sign) was added in 2002.
+ksc5601.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/KSC/KSC5601.TXT cjk_tab_to_h
+	(cat $< ; echo '0xA2E6	0x20AC'; echo '0xA2E7	0x00AE'; echo '0xA2E8	0x327E') | ./cjk_tab_to_h 'KSC5601.1987-0, now KS X 1001:2002' ksc5601 > $@
+
+uhc_1.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/KSC/KSC5601.TXT cjk_tab_to_h
+	(echo '#' ; grep '^0x\([8-9]\|A0\)' < $< ) | ./cjk_tab_to_h 'Unified Hangul Code part 1' uhc_1 > $@
+
+uhc_2.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/KSC/KSC5601.TXT cjk_tab_to_h
+	(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 > $@
+
+johab_hangul.h : $(TABLESDIR)/unicode.org-mappings/EASTASIA/KSC/JOHAB.TXT cjk_tab_to_h
+	(echo '#' ; grep '^0x\([8-C]...\|D[0-7]..\)' < $< ) | ./cjk_tab_to_h 'JOHAB Hangul' johab_hangul > $@
+
+
+cp856.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MISC/CP856.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP856 cp856 < $<
+
+cp922.h : $(TABLESDIR)/aix-4.3.2/IBM-922.TXT 8bit_tab_to_h
+	(echo '#' ; cat $<) | ./8bit_tab_to_h CP922 cp922
+
+cp1046.h : $(TABLESDIR)/aix-4.3.2/IBM-1046.TXT 8bit_tab_to_h
+	(echo '#' ; cat $<) | ./8bit_tab_to_h CP1046 cp1046
+
+cp1124.h : $(TABLESDIR)/aix-4.3.2/IBM-1124.TXT 8bit_tab_to_h
+	(echo '#' ; cat $<) | ./8bit_tab_to_h CP1124 cp1124
+
+cp1129.h : $(TABLESDIR)/aix-4.3.2/IBM-1129.TXT 8bit_tab_to_h
+	(echo '#' ; cat $<) | ./8bit_tab_to_h CP1129 cp1129
+
+cp1161.h : $(TABLESDIR)/glibc-2.2.90-iconv/IBM1161.TXT
+	(echo '#' ; cat $(TABLESDIR)/glibc-2.2-iconv/ASCII.TXT ; grep -v '^0x[0-7]' $<) | ./8bit_tab_to_h CP1161 cp1161
+
+cp1162.h : $(TABLESDIR)/glibc-2.2.90-iconv/IBM1162.TXT
+	(echo '#' ; cat $<) | ./8bit_tab_to_h CP1162 cp1162
+
+cp1163.h : $(TABLESDIR)/glibc-2.2.90-iconv/IBM1163.TXT
+	(echo '#' ; cat $<) | ./8bit_tab_to_h CP1163 cp1163
+
+
+cp437.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP437.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP437 cp437 < $<
+
+cp737.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP737.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP737 cp737 < $<
+
+cp775.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP775.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP775 cp775 < $<
+
+cp852.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP852.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP852 cp852 < $<
+
+cp853.h : $(TABLESDIR)/other/CP853.TXT 8bit_tab_to_h
+	(echo '#'; cat $<) | ./8bit_tab_to_h CP853 cp853
+
+cp855.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP855.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP855 cp855 < $<
+
+cp857.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP857.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP857 cp857 < $<
+
+cp858.h : $(TABLESDIR)/windows-2000/CP858.TXT 8bit_tab_to_h
+	(echo '#' ; cat $<) | ./8bit_tab_to_h CP858 cp858
+
+cp860.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP860.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP860 cp860 < $<
+
+cp861.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP861.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP861 cp861 < $<
+
+cp863.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP863.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP863 cp863 < $<
+
+cp864.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP864.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP864 cp864 < $<
+
+cp865.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP865.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP865 cp865 < $<
+
+cp869.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MICSFT/PC/CP869.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP869 cp869 < $<
+
+cp1125.h : $(TABLESDIR)/csets-new/CP1125.TXT 8bit_tab_to_h
+	./8bit_tab_to_h CP1125 cp1125 < $<
+
+
+jisx0213.h : JISX0213.TXT cjk_tab_to_h
+	./cjk_tab_to_h JISX0213:2004 jisx0213 < $< > $@
+
+tds565.h : $(TABLESDIR)/recode-cvs/TDS565.TXT 8bit_tab_to_h
+	(echo '#'; cat $<) | ./8bit_tab_to_h TDS565 tds565 > $@
+
+atarist.h : $(TABLESDIR)/unicode.org-mappings/VENDORS/MISC/ATARIST.TXT
+	./8bit_tab_to_h 'Atari ST' atarist < $< > $@
+
+riscos1.h : $(TABLESDIR)/recode-cvs/RISCOS-LATIN1.TXT 8bit_tab_to_h
+	(echo '#'; cat $<) | ./8bit_tab_to_h RISCOS-LATIN1 riscos1 > $@
+
+
+cjk_variants.h : $(TABLESDIR)/yasuoka/UniVariants cjk_variants
+	./cjk_variants < $< > $@
+
+
+8bit_tab_to_h : 8bit_tab_to_h.c
+	gcc -O -Wall -g $< -o $@
+
+cjk_tab_to_h : cjk_tab_to_h.c
+	gcc -O -Wall -g $< -o $@
+
+cjk_variants : cjk_variants.c
+	gcc -O -Wall -g $< -o $@
+
+
+clean : force
+	rm -f 8bit_tab_to_h cjk_tab_to_h cjk_variants $(ALL) GBKext.TXT
+
+force :
+