diff options
author | danglassey <danglassey> | 2002-08-14 09:57:17 +0000 |
---|---|---|
committer | danglassey <danglassey> | 2002-08-14 09:57:17 +0000 |
commit | c9458897ebbb739d8db83c80e06512d8a612f743 (patch) | |
tree | f8c5381045887e34388cc6b26cfccc254bf766dc /icu | |
download | sword-sf-cvs-c9458897ebbb739d8db83c80e06512d8a612f743.tar.gz |
*** empty log message ***
Diffstat (limited to 'icu')
-rw-r--r-- | icu/Makefile.am | 48 | ||||
-rw-r--r-- | icu/Makefile.in | 291 | ||||
-rw-r--r-- | icu/translit_Any_Latin1.txt | 89 | ||||
-rw-r--r-- | icu/translit_BETA_Greek.txt | 119 | ||||
-rw-r--r-- | icu/translit_BGreek_Greek.txt | 155 | ||||
-rw-r--r-- | icu/translit_CCAT_Hebrew.txt | 200 | ||||
-rw-r--r-- | icu/translit_CCAT_Syriac.txt | 87 | ||||
-rw-r--r-- | icu/translit_Latin_Arabic.txt | 198 | ||||
-rw-r--r-- | icu/translit_Latin_Armenian.txt | 151 | ||||
-rw-r--r-- | icu/translit_Latin_Coptic.txt | 129 | ||||
-rw-r--r-- | icu/translit_Latin_Ethiopic.txt | 407 | ||||
-rw-r--r-- | icu/translit_Latin_Georgian.txt | 137 | ||||
-rw-r--r-- | icu/translit_Latin_Gothic.txt | 57 | ||||
-rw-r--r-- | icu/translit_Latin_Hebrew.txt | 223 | ||||
-rw-r--r-- | icu/translit_Latin_Syriac.txt | 169 | ||||
-rw-r--r-- | icu/translit_Latin_Thai.txt | 162 | ||||
-rw-r--r-- | icu/translit_Latin_Ugaritic.txt | 63 | ||||
-rw-r--r-- | icu/translit_swordindex.txt | 108 |
18 files changed, 2793 insertions, 0 deletions
diff --git a/icu/Makefile.am b/icu/Makefile.am new file mode 100644 index 0000000..a23316a --- /dev/null +++ b/icu/Makefile.am @@ -0,0 +1,48 @@ +AUTOMAKE_OPTIONS = 1.6 + +if ICU +#pkglib_DATA = swicu.dat +#else +#endif + +swicuSOURCES = translit_BETA_Greek.txt +swicuSOURCES += translit_BGreek_Greek.txt +swicuSOURCES += translit_CCAT_Hebrew.txt +swicuSOURCES += translit_CCAT_Syriac.txt +swicuSOURCES += translit_Latin_Armenian.txt +swicuSOURCES += translit_Latin_Coptic.txt +swicuSOURCES += translit_Latin_Ethiopic.txt +swicuSOURCES += translit_Latin_Georgian.txt +swicuSOURCES += translit_Latin_Gothic.txt +swicuSOURCES += translit_Latin_Syriac.txt +swicuSOURCES += translit_Latin_Thai.txt +swicuSOURCES += translit_Latin_Ugaritic.txt +swicuSOURCES += translit_Any_Latin1.txt +#swicuSOURCES += translit_HTMLEnt_Unicode.txt +#swicuSOURCES += translit_Han_Pinyin.txt +#swicuSOURCES += translit_Kanji_English.txt +#swicuSOURCES += translit_Kanji_OnRomaji.txt +swicuSOURCES += translit_Latin_Arabic.txt +swicuSOURCES += translit_Latin_Hebrew.txt +swicuSOURCES += translit_swordindex.txt +endif + +CLEANFILES = *.res *.lst *.mk *.mak swicu.dat + +pkglib_DATA = $(swicuSOURCES:.txt=.res) + +SUFFIXES = .txt .res .dat + +#swicu.dat: $(swicuDATA) trans.lst icupkg.mk +# $(PKGDATA) -O icupkg.mk -p swicu -m common -T . -s . \ +# -d . -r $(VERSION) trans.lst + +#trans.lst: +# ls -1 *.res > trans.lst + +#icupkg.mk: +# @echo "GENCCODE=@GENCCODE@" > icupkg.mk +# @echo "GENCMN=@GENCMN@" >> icupkg.mk + +.txt.res: + $(GENRB) -s . -d . $< diff --git a/icu/Makefile.in b/icu/Makefile.in new file mode 100644 index 0000000..68520df --- /dev/null +++ b/icu/Makefile.in @@ -0,0 +1,291 @@ +# Makefile.in generated by automake 1.6.2 from Makefile.am. +# @configure_input@ + +# Copyright 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002 +# Free Software Foundation, Inc. +# This Makefile.in is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + +@SET_MAKE@ +SHELL = @SHELL@ + +srcdir = @srcdir@ +top_srcdir = @top_srcdir@ +VPATH = @srcdir@ +prefix = @prefix@ +exec_prefix = @exec_prefix@ + +bindir = @bindir@ +sbindir = @sbindir@ +libexecdir = @libexecdir@ +datadir = @datadir@ +sysconfdir = @sysconfdir@ +sharedstatedir = @sharedstatedir@ +localstatedir = @localstatedir@ +libdir = @libdir@ +infodir = @infodir@ +mandir = @mandir@ +includedir = @includedir@ +oldincludedir = /usr/include +pkgdatadir = $(datadir)/@PACKAGE@ +pkglibdir = $(libdir)/@PACKAGE@ +pkgincludedir = $(includedir)/@PACKAGE@ +top_builddir = .. + +ACLOCAL = @ACLOCAL@ +AUTOCONF = @AUTOCONF@ +AUTOMAKE = @AUTOMAKE@ +AUTOHEADER = @AUTOHEADER@ + +am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd +INSTALL = @INSTALL@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_DATA = @INSTALL_DATA@ +install_sh_DATA = $(install_sh) -c -m 644 +install_sh_PROGRAM = $(install_sh) -c +install_sh_SCRIPT = $(install_sh) -c +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +INSTALL_HEADER = $(INSTALL_DATA) +transform = @program_transform_name@ +NORMAL_INSTALL = : +PRE_INSTALL = : +POST_INSTALL = : +NORMAL_UNINSTALL = : +PRE_UNINSTALL = : +POST_UNINSTALL = : +host_alias = @host_alias@ +host_triplet = @host@ + +EXEEXT = @EXEEXT@ +OBJEXT = @OBJEXT@ +PATH_SEPARATOR = @PATH_SEPARATOR@ +AMTAR = @AMTAR@ +AS = @AS@ +AWK = @AWK@ +CC = @CC@ +CURL_CFLAGS = @CURL_CFLAGS@ +CURL_CONFIG = @CURL_CONFIG@ +CURL_LIBS = @CURL_LIBS@ +CXX = @CXX@ +DEPDIR = @DEPDIR@ +DLLTOOL = @DLLTOOL@ +ECHO = @ECHO@ +GENCCODE = @GENCCODE@ +GENCMN = @GENCMN@ +GENRB = @GENRB@ +INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ +LIBTOOL = @LIBTOOL@ +LN_S = @LN_S@ +MAINT = @MAINT@ +OBJDUMP = @OBJDUMP@ +PACKAGE = @PACKAGE@ +PKGDATA = @PKGDATA@ +RANLIB = @RANLIB@ +STRIP = @STRIP@ +VERSION = @VERSION@ +am__include = @am__include@ +am__quote = @am__quote@ +dir_confdef = @dir_confdef@ +enable_debug = @enable_debug@ +enable_profile = @enable_profile@ +install_sh = @install_sh@ +target_cpu = @target_cpu@ +target_mingw32 = @target_mingw32@ +target_os = @target_os@ +target_system = @target_system@ +target_vendor = @target_vendor@ +with_conf = @with_conf@ +with_icu = @with_icu@ +with_zlib = @with_zlib@ +AUTOMAKE_OPTIONS = 1.6 + + +#pkglib_DATA = swicu.dat +#else +#endif +#swicuSOURCES += translit_HTMLEnt_Unicode.txt +#swicuSOURCES += translit_Han_Pinyin.txt +#swicuSOURCES += translit_Kanji_English.txt +#swicuSOURCES += translit_Kanji_OnRomaji.txt +@ICU_TRUE@swicuSOURCES = translit_BETA_Greek.txt translit_BGreek_Greek.txt translit_CCAT_Hebrew.txt translit_CCAT_Syriac.txt translit_Latin_Armenian.txt translit_Latin_Coptic.txt translit_Latin_Ethiopic.txt translit_Latin_Georgian.txt translit_Latin_Gothic.txt translit_Latin_Syriac.txt translit_Latin_Thai.txt translit_Latin_Ugaritic.txt translit_Any_Latin1.txt translit_Latin_Arabic.txt translit_Latin_Hebrew.txt translit_swordindex.txt + +CLEANFILES = *.res *.lst *.mk *.mak swicu.dat + +pkglib_DATA = $(swicuSOURCES:.txt=.res) + +SUFFIXES = .txt .res .dat +subdir = icu +mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs +CONFIG_HEADER = $(top_builddir)/config.h +CONFIG_CLEAN_FILES = +DIST_SOURCES = +DATA = $(pkglib_DATA) + +DIST_COMMON = Makefile.am Makefile.in +all: all-am + +.SUFFIXES: +.SUFFIXES: .txt .res .dat +$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ Makefile.am $(top_srcdir)/configure.ac $(ACLOCAL_M4) + cd $(top_srcdir) && \ + $(AUTOMAKE) --gnu icu/Makefile +Makefile: @MAINTAINER_MODE_TRUE@ $(srcdir)/Makefile.in $(top_builddir)/config.status + cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe) + +mostlyclean-libtool: + -rm -f *.lo + +clean-libtool: + -rm -rf .libs _libs + +distclean-libtool: + -rm -f libtool +uninstall-info-am: +pkglibDATA_INSTALL = $(INSTALL_DATA) +install-pkglibDATA: $(pkglib_DATA) + @$(NORMAL_INSTALL) + $(mkinstalldirs) $(DESTDIR)$(pkglibdir) + @list='$(pkglib_DATA)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + f="`echo $$p | sed -e 's|^.*/||'`"; \ + echo " $(pkglibDATA_INSTALL) $$d$$p $(DESTDIR)$(pkglibdir)/$$f"; \ + $(pkglibDATA_INSTALL) $$d$$p $(DESTDIR)$(pkglibdir)/$$f; \ + done + +uninstall-pkglibDATA: + @$(NORMAL_UNINSTALL) + @list='$(pkglib_DATA)'; for p in $$list; do \ + f="`echo $$p | sed -e 's|^.*/||'`"; \ + echo " rm -f $(DESTDIR)$(pkglibdir)/$$f"; \ + rm -f $(DESTDIR)$(pkglibdir)/$$f; \ + done +tags: TAGS +TAGS: + +DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) + +top_distdir = .. +distdir = $(top_distdir)/$(PACKAGE)-$(VERSION) + +distdir: $(DISTFILES) + @list='$(DISTFILES)'; for file in $$list; do \ + if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \ + dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \ + if test "$$dir" != "$$file" && test "$$dir" != "."; then \ + dir="/$$dir"; \ + $(mkinstalldirs) "$(distdir)$$dir"; \ + else \ + dir=''; \ + fi; \ + if test -d $$d/$$file; then \ + if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \ + cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \ + fi; \ + cp -pR $$d/$$file $(distdir)$$dir || exit 1; \ + else \ + test -f $(distdir)/$$file \ + || cp -p $$d/$$file $(distdir)/$$file \ + || exit 1; \ + fi; \ + done +check-am: all-am +check: check-am +all-am: Makefile $(DATA) + +installdirs: + $(mkinstalldirs) $(DESTDIR)$(pkglibdir) + +install: install-am +install-exec: install-exec-am +install-data: install-data-am +uninstall: uninstall-am + +install-am: all-am + @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am + +installcheck: installcheck-am +install-strip: + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + INSTALL_STRIP_FLAG=-s \ + `test -z '$(STRIP)' || \ + echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install +mostlyclean-generic: + +clean-generic: + -test -z "$(CLEANFILES)" || rm -f $(CLEANFILES) + +distclean-generic: + -rm -f Makefile $(CONFIG_CLEAN_FILES) + +maintainer-clean-generic: + @echo "This command is intended for maintainers to use" + @echo "it deletes files that may require special tools to rebuild." +clean: clean-am + +clean-am: clean-generic clean-libtool mostlyclean-am + +distclean: distclean-am + +distclean-am: clean-am distclean-generic distclean-libtool + +dvi: dvi-am + +dvi-am: + +info: info-am + +info-am: + +install-data-am: + +install-exec-am: install-pkglibDATA + +install-info: install-info-am + +install-man: + +installcheck-am: + +maintainer-clean: maintainer-clean-am + +maintainer-clean-am: distclean-am maintainer-clean-generic + +mostlyclean: mostlyclean-am + +mostlyclean-am: mostlyclean-generic mostlyclean-libtool + +uninstall-am: uninstall-info-am uninstall-pkglibDATA + +.PHONY: all all-am check check-am clean clean-generic clean-libtool \ + distclean distclean-generic distclean-libtool distdir dvi \ + dvi-am info info-am install install-am install-data \ + install-data-am install-exec install-exec-am install-info \ + install-info-am install-man install-pkglibDATA install-strip \ + installcheck installcheck-am installdirs maintainer-clean \ + maintainer-clean-generic mostlyclean mostlyclean-generic \ + mostlyclean-libtool uninstall uninstall-am uninstall-info-am \ + uninstall-pkglibDATA + + +#swicu.dat: $(swicuDATA) trans.lst icupkg.mk +# $(PKGDATA) -O icupkg.mk -p swicu -m common -T . -s . \ +# -d . -r $(VERSION) trans.lst + +#trans.lst: +# ls -1 *.res > trans.lst + +#icupkg.mk: +# @echo "GENCCODE=@GENCCODE@" > icupkg.mk +# @echo "GENCMN=@GENCMN@" >> icupkg.mk + +.txt.res: + $(GENRB) -s . -d . $< +# Tell versions [3.59,3.63) of GNU make to not export all variables. +# Otherwise a system limit (for SysV at least) may be exceeded. +.NOEXPORT: diff --git a/icu/translit_Any_Latin1.txt b/icu/translit_Any_Latin1.txt new file mode 100644 index 0000000..d049845 --- /dev/null +++ b/icu/translit_Any_Latin1.txt @@ -0,0 +1,89 @@ +// Any_Latin1 + +translit_Any_Latin1 { + Rule { + + //NFKD then NFC; then NFD all non-Latin-1 codepoints + ":: NFKC ();" + ":: [^\u0000-\u00FF] NFD ();" + + //remove non-spacing marks + "[:Mn:] > ;" + + //change some non-Latin-1 codepoints to similar characters in Latin-1 range + " [\u2000-\u200A\u3000] > ' ' ;" + " [\u01C3\u2762]> '!' ;" + " \u203C > '!!' ;" + " [\u203D\u2048] > '?!' ;" + " [\u02BA\u030B\u030E\u2033\u3003\u201C-\u201F] > '\"' ;" + " [\u066A\u2030\u2031] > '%' ;" + " [\u02B9\u02BC\u02C8\u0301\u2032\u2018-\u201B] > '' ;" + " [\u066D\u2217\u2731] > '*' ;" + " [\u060C\u201A\u3001] > ',' ;" + " [\u2010-\u2013\u2212] > '-' ;" + " [\u2023\u06D4\u3002\u0589] > '.' ;" + " [\u0338\u2044\u2215] > '/' ;" + " \u2236 > ':' ;" + " \u061B > ';' ;" + " [\u2039\u2329\u3008] > '<' ;" + " \u2261 > '=' ;" + " [\u203A\u232A\u3009] > '>' ;" + " [\u037E\u061F] > '?' ;" + " \u2049 > '!?' ;" + " \u212C > B ;" + " [\u2102\u212D] > C ;" + " [\u2107\u2130] > E ;" + " [\u2131\u2132] > F ;" + " [\u210B\u210C\u210D] > H ;" + " [\u2110\u2111\u2160] > I ;" + " \u212A > K ;" + " \u2112 > L ;" + " \u2133 > L ;" + " \u2115 > N ;" + " \u2119 > P ;" + " \u211A > Q ;" + " [\u211B\u211C\u211D] > R ;" + " [\u2124\u2128] > Z ;" + " \u2216 > '\\' ;" + " [\u02C4\u02C6\u0302\u2303] > '^' ;" + " [\u02CD\u0331\u0332\u2017] > '_' ;" + " [\u02CB\u0300\u2035] > '`' ;" + " [\u212E\u212F] > e ;" + " [\u0261\u210A] > g ;" + " [\u04BB\u210E] > h ;" + " \u0131 > i ;" + " \u207F > n ;" + " \u2134 > o ;" + " \u01B6 > z ;" + " [\u01C0\u2223\u2758] > '|' ;" + " [\u02DC\u0303\u223C\uFF5E] > '~' ;" + " \u202F > \u00A0 ;" + " \uFFFD > \u001A;" + " \u20A4 > \u00A3 ;" + " [\u20A0-\u20AF] > \u00A4 ;" + " \u0308 > \u00A8 ;" + " \u2117 > \u00A9 ;" + " [\u226A\u300A] > \u00AB ;" + " \u2310 > \u00AC ;" + " \u1806 > \u00AD ;" + " [\u02C9\u0304\u0305] > \u00AF ;" + " [\u02DA\u030A\u2070\u2218] > \u00B0 ;" + " \u2213 > \u00B1 ;" + " [\u02B9\u02CA\u0301\u2032] > \u00B4 ;" + " [\u204B\u2761] > \u00B6 ;" + " [\u2022\u2024\u2027\u2219\u22C5\u30FB] > \u00B7 ;" + " \u0327 > \u00B8 ;" + " [\u226B\u300B] > \u00BB ;" + " \u2014 > '--';" + " \u2015 > '---';" + " \u2024 > '..';" + " \u2025 > '...';" + " \u2016 > '||';" + " \uFEFF > ;" + + //change all spacing character to space + "[^\u0000-\u00FF] > ' ';" + + } +} + diff --git a/icu/translit_BETA_Greek.txt b/icu/translit_BETA_Greek.txt new file mode 100644 index 0000000..d90cec2 --- /dev/null +++ b/icu/translit_BETA_Greek.txt @@ -0,0 +1,119 @@ +//-------------------------------------------------------------------- +// Copyright (c) 2001, CrossWire Bible Society +//-------------------------------------------------------------------- + +// BETA-Greek/Coptic + +translit_BETA_Greek { + Rule { + ":: NFD (NFD);"//this is wrong, but required + + ":: [abdezqiklmncoypruxwv] upper();" + + //Uppercase + "'*A'<>\u0391;" + "'*B'<>\u0392;" + "'*G'<>\u0393;" + "'*D'<>\u0394;" + "'*E'<>\u0395;" + "'*Z'<>\u0396;" + "'*H'<>\u0397;" + "'*Q'<>\u0398;" + "'*I'<>\u0399;" + "'*K'<>\u039A;" + "'*L'<>\u039B;" + "'*M'<>\u039C;" + "'*N'<>\u039D;" + "'*C'<>\u039E;" + "'*O'<>\u039F;" + "'*F'<>\u03A6;" + "'*Y'<>\u03A8;" + "'*P'<>\u03A0;" + "'*R'<>\u03A1;" + "'*S'<>\u03A3;" + "'*T'<>\u03A4;" + "'*U'<>\u03A5;" + "'*X'<>\u03A7;" + "'*W'<>\u03A9;" + + //Archaic + "'*V'<>\u03DC;" + "'*#3'<>\u03DE;" + "'*#5'<>\u03E0;" + + //Coptic + "'*s'<>\u03E2;" + "'*f'<>\u03E4;" + "'*h'<>\u03E8;" + "'*j'<>\u03EA;" + "'*g'<>\u03EC;" + "'*t'<>\u03EE;" + + + //Lowercase + "A<>\u03B1;" + "B<>\u03B2;" + "G<>\u03B3;" + "D<>\u03B4;" + "E<>\u03B5;" + "Z<>\u03B6;" + "H<>\u03B7;" + "Q<>\u03B8;" + "I<>\u03B9;" + "K<>\u03BA;" + "L<>\u03BB;" + "M<>\u03BC;" + "N<>\u03BD;" + "C<>\u03BE;" + "O<>\u03BF;" + "F<>\u03C6;" + "Y<>\u03C8;" + "P<>\u03C0;" + "R<>\u03C1;" + "J<>\u03C2;" + "S<>\u03C3;" + "T<>\u03C4;" + "U<>\u03C5;" + "X<>\u03C7;" + "W<>\u03C9;" + + + //Archaic + "V<>\u03DD;" + "#3<>\u03DF;" + "#5<>\u03E1;" + + //Coptic + "s<>\u03E3;" + "f<>\u03E5;" + "h<>\u03E9;" + "j<>\u03EB;" + "g<>\u03ED;" + "t<>\u03EF;" + + // Non-letter characters //these don't work (this is wrong) + "'V'<>\u037A;" + "'V'<>\u0314;" + "'V'<\u02BD;" + "'V'<>\u0387;" + "'V'<>\u0313;" + "'V'<\u02BC;" + "'V'<>\u0301;" + "'V'<\u00B4;" + "'V'<\u02CA;" + "'V'<\u0384;" + "'V'<>\u0342;" + "'V'<\u0302;" + "'V'<'^';" + "'V'<\u02C6;" + "'V'<>\u0300;" + "'V'<'`';" + "'V'<\u02CB;" + "'V'<>\u0308;" + "'V'<\u00A8;" + "'V'<>\u0307;" + "'V'<\u02D9;" + + ":: NFD (NFD);" //this is wrong, but required + } +} diff --git a/icu/translit_BGreek_Greek.txt b/icu/translit_BGreek_Greek.txt new file mode 100644 index 0000000..1cacd3d --- /dev/null +++ b/icu/translit_BGreek_Greek.txt @@ -0,0 +1,155 @@ +//-------------------------------------------------------------------- +// Copyright (c) 2001, CrossWire Bible Society +//-------------------------------------------------------------------- + +// BGreek-Greek + +translit_BGreek_Greek { + Rule { + ":: NFD (NFC) ;" + + ":: [abgdezqklmnxofyprtucw] upper();" + + // Extra English Letters. Mapped for completeness + "J>I;" + "V>U;" + + "<[:Mn:];" + + // ============================================== + // Variables, used to make the rules more comprehensible + // and for conditionals. + // ============================================== + + // Greek Letters + + "$ALPHA=\u0391;" + "$BETA=\u0392;" + "$GAMMA=\u0393;" + "$DELTA=\u0394;" + "$EPSILON=\u0395;" + "$ZETA=\u0396;" + "$ETA=\u0397;" + "$THETA=\u0398;" + "$IOTA=\u0399;" + "$KAPPA=\u039A;" + "$LAMBDA=\u039B;" + "$MU=\u039C;" + "$NU=\u039D;" + "$XI=\u039E;" + "$OMICRON=\u039F;" + "$PI=\u03A0;" + "$RHO=\u03A1;" + "$SIGMA=\u03A3;" + "$TAU=\u03A4;" + "$YPSILON=\u03A5;" + "$PHI=\u03A6;" + "$CHI=\u03A7;" + "$PSI=\u03A8;" + "$OMEGA=\u03A9;" + + "$alpha=\u03B1;" + "$beta=\u03B2;" + "$gamma=\u03B3;" + "$delta=\u03B4;" + "$epsilon=\u03B5;" + "$zeta=\u03B6;" + "$eta=\u03B7;" + "$theta=\u03B8;" + "$iota=\u03B9;" + "$kappa=\u03BA;" + "$lambda=\u03BB;" + "$mu=\u03BC;" + "$nu=\u03BD;" + "$xi=\u03BE;" + "$omicron=\u03BF;" + "$pi=\u03C0;" + "$rho=\u03C1;" + "$sigma=\u03C3;" + "$tau=\u03C4;" + "$ypsilon=\u03C5;" + "$phi=\u03C6;" + "$chi=\u03C7;" + "$psi=\u03C8;" + "$omega=\u03C9;" + + "$sigma2=\u03C2;" + + "$iota_subscript=\u037A;" + "$comb_rough_breathing=\u0314;" + "$rough_breathing=\u02BD;" + + // Variables for conditional mappings + + // ============================================== + // Rules + // ============================================== + // The following are special titlecases, and should + // not be copied when duplicating the lowercase + // ============================================== + + // Because there is no uppercase forms for final sigma, + // we had to move all the sigma rules up here. + + // Remember to insert ' to preserve round trip, for double letters + // don't need to do this for the digraphs with h, + // since it is not created when mapping back from greek + + // use special form for s + + "S}[[:L:] & [:Latin:]]>$sigma2;" + "S <> $SIGMA;" + + // The following are a bit tricky. 's' takes two forms in greek + // final or non final. + // We use ~s to represent the abnormal form: final before letter + // or non-final before non-letter. + // We use 's to separate p and s (otherwise ps is one letter) + // so, we break out the following forms: + + "S < $sigma;" + "S < $sigma2;" + + // ============================================== + // Uppercase Forms. + // To make lowercase forms, just copy and lowercase below + // ============================================== + + // Basic Letters + + "A<>$ALPHA;" + "B<>$BETA;" + "G<>$GAMMA;" + "D<>$DELTA;" + "E<>$EPSILON;" + "Z<>$ZETA;" + "H<>$ETA;" + "Q<>$THETA;" + "I<>$IOTA;" + "K<>$KAPPA;" + "L<>$LAMBDA;" + "M<>$MU;" + "N<>$NU;" + "X<>$XI;" + "O<>$OMICRON;" + "F<>$PHI;" // needs ordering before P + "Y<>$PSI;" // needs ordering before P + "P<>$PI;" + "R<>$RHO;" + "T<>$TAU;" + "U<>$YPSILON;" + "C<>$CHI;" + "W<>$OMEGA;" + + // Non-letter characters + + "i<>$iota_subscript;" + "h<>$comb_rough_breathing;" + "h<$rough_breathing;" + + ":: [[:Ll:] & [:Greek:]] upper;" + + ":: NFC (NFD) ;" + } +} + diff --git a/icu/translit_CCAT_Hebrew.txt b/icu/translit_CCAT_Hebrew.txt new file mode 100644 index 0000000..2c9fafa --- /dev/null +++ b/icu/translit_CCAT_Hebrew.txt @@ -0,0 +1,200 @@ +//-------------------------------------------------------------------- +// Copyright (c) 2001, CrossWire Bible Society +//-------------------------------------------------------------------- + +// CCAT-Hebrew + +translit_CCAT_Hebrew { + Rule { + ":: NFD (NFC) ;" + + // Variable names, derived from the Unicode names. + "$CANT_ETNAHTA=\u0591;" + "$CANT_SEGOL=\u0592;" + "$CANT_SHALSHELET=\u0593;" + "$CANT_ZAQEF_QATAN=\u0594;" + "$CANT_ZAQEF_GADOL=\u0595;" + "$CANT_TIPEHA=\u0596;" + "$CANT_REVIA=\u0597;" + "$CANT_ZARQA=\u0598;" + "$CANT_PASHTA=\u0599;" + "$CANT_YETIV=\u059A;" + "$CANT_TEVIR=\u059B;" + "$CANT_GERESH=\u059C;" + "$CANT_GERESH_MUQDAM=\u059D;" + "$CANT_GERESHAYIM=\u059E;" + "$CANT_QARNEY_PARA=\u059F;" + "$CANT_TELISHA_GEDOLA=\u05A0;" + "$CANT_PAZER=\u05A1;" + "$CANT_MUNAH=\u05A3;" + "$CANT_MAHAPAKH=\u05A4;" + "$CANT_MERKHA=\u05A5;" + "$CANT_MERKHA_KEFULA=\u05A6;" + "$CANT_DARGA=\u05A7;" + "$CANT_QADMA=\u05A8;" + "$CANT_TELISHA_QETANA=\u05A9;" + "$CANT_YERAH_BEN_YOMO=\u05AA;" + "$CANT_OLE=\u05AB;" + "$CANT_ILUY=\u05AC;" + "$CANT_DEHI=\u05AD;" + "$CANT_ZINOR=\u05AE;" + + "$MASORA_CIRCLE=\u05AF;" + + "$POINT_SHEVA=\u05B0;" + "$POINT_HATAF_SEGOL=\u05B1;" + "$POINT_HATAF_PATAH=\u05B2;" + "$POINT_HATAF_QAMATS=\u05B3;" + "$POINT_HIRIQ=\u05B4;" + "$POINT_TSERE=\u05B5;" + "$POINT_SEGOL=\u05B6;" + "$POINT_PATAH=\u05B7;" + "$POINT_QAMATS=\u05B8;" + "$POINT_HOLAM=\u05B9;" + "$POINT_QUBUTS=\u05BB;" + "$POINT_DAGESH_OR_MAPIQ=\u05BC;" + "$POINT_METEG=\u05BD;" + "$PUNCTUATION_MAQAF=\u05BE;" + "$POINT_RAFE=\u05BF;" + "$PUNCTUATION_PASEQ=\u05C0;" + "$POINT_SHIN_DOT=\u05C1;" + "$POINT_SIN_DOT=\u05C2;" + "$PUNCTUATION_SOF_PASUQ=\u05C3;" + "$MARK_UPPER_DOT=\u05C4;" + "$ALEF=\u05D0;" + "$BET=\u05D1;" + "$GIMEL=\u05D2;" + "$DALET=\u05D3;" + "$HE=\u05D4;" + "$VAV=\u05D5;" + "$ZAYIN=\u05D6;" + "$HET=\u05D7;" + "$TET=\u05D8;" + "$YOD=\u05D9;" + "$FINAL_KAF=\u05DA;" + "$KAF=\u05DB;" + "$LAMED=\u05DC;" + "$FINAL_MEM=\u05DD;" + "$MEM=\u05DE;" + "$FINAL_NUN=\u05DF;" + "$NUN=\u05E0;" + "$SAMEKH=\u05E1;" + "$AYIN=\u05E2;" + "$FINAL_PE=\u05E3;" + "$PE=\u05E4;" + "$FINAL_TSADI=\u05E5;" + "$TSADI=\u05E6;" + "$QOF=\u05E7;" + "$RESH=\u05E8;" + "$SHIN=\u05E9;" + "$TAV=\u05EA;" + + "$YIDDISH_DOUBLE_VAV=\u05F0;" + "$YIDDISH_VAV_YOD=\u05F1;" + "$YIDDISH_DOUBLE_YOD=\u05F2;" + + "$PUNCTUATION_GERESH=\u05F3;" + "$PUNCTUATION_GERSHAYIM=\u05F4;" + + "$letter=[[:LATIN:]&[:L:]];" + "$softvowel=[eiyEIY];" + "$vowellike=[$ALEF $AYIN $YOD $VAV];" + + "'\)'<>$ALEF;" + "''>$ALEF;" + "B<>$BET;" + "G<>$GIMEL;" + "D<>$DALET;" + "H<>$HE;" + "W<>$VAV;" + "Z<>$ZAYIN;" + "X<>$HET;" + "'+'<>$TET;" + "Y<>$YOD;" + "K}$letter>$KAF;" + "K<$KAF;" + "K<>$FINAL_KAF;" + "L<>$LAMED;" + "M}$letter>$MEM;" + "M<$MEM;" + "M<>$FINAL_MEM;" + "N}$letter>$NUN;" + "N<$NUN;" + "N<>$FINAL_NUN;" + "S<>$SAMEKH;" + "P}$letter>$PE;" + "P<$PE;" + "P<>$FINAL_PE;" + "'\('<>$AYIN;" + "'\`'>$AYIN;" + "C}$letter>$TSADI;" + "C<$TSADI;" + "C<>$FINAL_TSADI;" + "Q<>$QOF;" + "R<>$RESH;" + "'&'<> $SHIN $POINT_SIN_DOT;" + "'\$'<> $SHIN $POINT_SHIN_DOT;" + "'\$'<$SHIN;" + "T<>$TAV;" + + "':A'<>$POINT_HATAF_PATAH;" + "':E'<>$POINT_HATAF_SEGOL;" + "':F'<>$POINT_HATAF_QAMATS;" + + "A<>$POINT_PATAH;" + "F<>$POINT_QAMATS;" + "E<>$POINT_SEGOL;" + "'\"'<>$POINT_TSERE;" + "I<>$POINT_HIRIQ;" + "O<>$POINT_HOLAM;" + "U<>$POINT_QUBUTS;" + "':'<>$POINT_SHEVA;" + + "'.'<>$POINT_DAGESH_OR_MAPIQ;" + "'-'<>$PUNCTUATION_MAQAF;" + + "00<>$PUNCTUATION_SOF_PASUQ;" + "01<>$CANT_SEGOL;" + "02<>$CANT_ZARQA;" + "03>$CANT_PASHTA;" + "04>$CANT_TELISHA_QETANA;" + "05<>$PUNCTUATION_PASEQ;" + "10<>$CANT_YETIV;" + "13<>$CANT_DEHI;" + "11<>$CANT_GERESH_MUQDAM;" + "14>$CANT_TELISHA_GEDOLA;" + "24<>$CANT_TELISHA_QETANA;" + "33<>$CANT_PASHTA;" + "44<>$CANT_TELISHA_GEDOLA;" + "60<>$CANT_OLE;" + "61<>$CANT_GERESH;" + "62<>$CANT_GERESHAYIM;" + "63<>$CANT_QADMA;" + "64<>$CANT_ILUY;" + "65<>$CANT_SHALSHELET;" + "80<>$CANT_ZAQEF_GADOL;" + "81<>$CANT_REVIA;" + "82>$CANT_ZARQA;" + "83<>$CANT_PAZER;" + "84<>$CANT_QARNEY_PARA;" + "85<>$CANT_ZAQEF_QATAN;" + "35<>$POINT_METEG;" + "70<>$CANT_MAHAPAKH;" + "71<>$CANT_MERKHA;" + "72<>$CANT_MERKHA_KEFULA;" + "73<>$CANT_TIPEHA;" + "74<>$CANT_MUNAH;" + "75>$POINT_METEG;" + "91<>$CANT_TEVIR;" + "92<>$CANT_ETNAHTA;" + "93<>$CANT_YERAH_BEN_YOMO;" + "94<>$CANT_DARGA;" + "95>$POINT_METEG;" + + //Get rid of anything we didn't recognize + "<[:HEBREW:];" + "$letter>;" + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_CCAT_Syriac.txt b/icu/translit_CCAT_Syriac.txt new file mode 100644 index 0000000..74bf876 --- /dev/null +++ b/icu/translit_CCAT_Syriac.txt @@ -0,0 +1,87 @@ +//-------------------------------------------------------------------- +// Copyright (c) 2001, CrossWire Bible Society +//-------------------------------------------------------------------- + +// CCAT-Syriac + +translit_CCAT_Syriac { + Rule { + ":: NFD (NFC) ;" + + // Variable names, derived from the Unicode names. + "$ALEF=\u0710;" + "$ALEF_SUPERSCRIPT=\u0711;" + "$BET=\u0712;" + "$GIMEL=\u0713;" + "$GIMEL_GARSHUNI=\u0714;" + "$DALET=\u0715;" + "$DALET_DOTLESS=\u0716;" + "$HE=\u0717;" + "$VAV=\u0718;" + "$ZAYIN=\u0719;" + "$HET=\u071A;" + "$TET=\u071B;" + "$TET_GARSHUNI=\u071C;" + "$YOD=\u071D;" + "$YOD_HE=\u071E;" + "$KAF=\u071F;" + "$LAMED=\u0720;" + "$MEM=\u0721;" + "$NUN=\u0722;" + "$SAMEKH=\u0723;" + "$FINAL_SAMEKH=\u0724;" + "$AYIN=\u0725;" + "$PE=\u0726;" + "$PE_REVERSED=\u0727;" + "$TSADI=\u0728;" + "$QOF=\u0729;" + "$RESH=\u072A;" + "$SHIN=\u072B;" + "$TAV=\u072C;" + + "$letter=[[:LATIN:] & [:L:]];" + "$softvowel=[eiyEIY];" + "$vowellike=[$ALEF $AYIN $YOD $VAV $ALEF_SUPERSCRIPT];" + + "'\)'<>$ALEF;" + "''>$ALEF;" + "'\)'<$ALEF_SUPERSCRIPT;" + "B<>$BET;" + "G<>$GIMEL;" + "G<$GIMEL_GARSHUNI;" + "D<>$DALET;" + "D<$DALET_DOTLESS;" + "H<>$HE;" + "W<>$VAV;" + "Z<>$ZAYIN;" + "X<>$HET;" + "'+'<>$TET;" + "'+'<$TET_GARSHUNI;" + "Y<>$YOD;" + "YH<$YOD_HE;" + "K<>$KAF;" + "L<>$LAMED;" + "M<>$MEM;" + "N<>$NUN;" + "S}$letter>$SAMEKH;" + "S<$SAMEKH;" + "S<>$FINAL_SAMEKH;" + "P<>$PE;" + "P<$PE_REVERSED;" + "'\('<>$AYIN;" + "'\`'>$AYIN;" + "C<>$TSADI;" + "Q<>$QOF;" + "R<>$RESH;" + "'#'>$SHIN;" + "'&'>$SHIN;" + "'\$'<>$SHIN;" + "T<>$TAV;" + + //Get rid of anything we didn't recognize + "<[:SYRIAC:];" + "$letter>;" + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_Latin_Arabic.txt b/icu/translit_Latin_Arabic.txt new file mode 100644 index 0000000..b310b64 --- /dev/null +++ b/icu/translit_Latin_Arabic.txt @@ -0,0 +1,198 @@ +//-------------------------------------------------------------------- +// Copyright (c) 1999-2000, International Business Machines +// Corporation and others. All Rights Reserved. +//-------------------------------------------------------------------- +// THIS IS A MACHINE-GENERATED FILE +// Tool: src\com\ibm\tools\translit\dumpICUrules.bat +// Source: src\com\ibm\text\resources/TransliterationRule_Latin_Arabic.java +// Date: Wed Jul 5 16:11:18 2000 +//-------------------------------------------------------------------- + +// Latin-Arabic + +translit_Latin_Arabic { + Rule { + ":: NFD (NFC) ;" + + // To Do: finish adding shadda, add sokoon + // [Is this done? Can someone finish this?] + + "$alefmadda=\u0622;" + "$alefuhamza=\u0623;" + "$wauuhamza=\u0624;" + "$alefhamza=\u0625;" + "$yehuhamza=\u0626;" + "$alef=\u0627;" + "$beh=\u0628;" + "$tehmarbuta=\u0629;" + "$teh=\u062A;" + "$theh=\u062B;" + "$geem=\u062C;" + "$hah=\u062D;" + "$kha=\u062E;" + "$dal=\u062F;" + "$dhal=\u0630;" + "$reh=\u0631;" + "$zain=\u0632;" + "$seen=\u0633;" + "$sheen=\u0634;" + "$sad=\u0635;" + "$dad=\u0636;" + "$tah=\u0637;" + "$zah=\u0638;" + "$ein=\u0639;" + "$ghein=\u063A;" + "$feh=\u0641;" + "$qaaf=\u0642;" + "$kaf=\u0643;" + "$lam=\u0644;" + "$meem=\u0645;" + "$noon=\u0646;" + "$heh=\u0647;" + "$wau=\u0648;" + "$yehmaqsura=\u0649;" + "$yeh=\u064A;" + "$peh=\u06A4;" + + "$hamza=\u0621;" + "$fathatein=\u064B;" + "$dammatein=\u064C;" + "$kasratein=\u064D;" + "$fatha=\u064E;" + "$damma=\u064F;" + "$kasra=\u0650;" + "$shadda=\u0651;" + "$sokoon=\u0652;" + + // Doubles - liu + "t'' < {$teh} [$teh$theh$tehmarbuta$tah];" + "h'' < {$heh} [$heh$hah];" + "s'' < {$seen} $sheen;" + + // A few pathological special cases to make round + // trip work. - liu + "d'~'d <> $dal $dal;" + "dh'~'dh <> $dhal $dhal;" + "dd'~'dd <> $dad $dad;" + + // Shadda: Map x $shadda to x x, where x is dh, dd, or + // d (that is, $dhal, $dad, or $dal). If x is d, d'd is + // output. Net effect is to map s.th. like $dad $shadda + // to dd'dd. - liu + "$dhal {dh} <> dh {$shadda};" + "$dad {dd} <> dd {$shadda};" + "$dal {''d} [^dh] <> d {$shadda};" // Avoid d'dd or d'dh + + // [This should be removed, but it's good for demos] + "Arabic>" + "\u062a\u062a\u0645\u062a\u0639' '" + "\u0627\u0644\u0644\u063a\u0629' '" + "\u0627\u0644\u0639\u0631\u0628\u0628\u064a\u0629' '" + "\u0628\u0628\u0646\u0638\u0645' '" + "\u0643\u062a\u0627\u0628\u0628\u064a\u0629' '" + "\u062c\u0645\u064a\u0644\u0629;" + + // Main rules + "''ai<a{$alefmadda;" + "ai<>$alefmadda;" + "''ae<a{$alefuhamza;" + "ae<>$alefuhamza;" + "''ao<a{$alefhamza;" + "ao<>$alefhamza;" + "''aa<a{$alef;" + "aa<>$alef;" + "''an<a{$fathatein;" + "an<>$fathatein;" + "''a<a{$fatha;" + "a<>$fatha;" + "b<>$beh;" + "''dh<d{$dhal;" + "dh<>$dhal;" + "''dd<d{$dad;" + "dd<>$dad;" + "''d<d{$dal;" + "d<>$dal;" + "''e<a{$ein;" + "''e<w{$ein;" + "''e<y{$ein;" + "e<>$ein;" + "f<>$feh;" + "gh<>$ghein;" + "''hh<d{$hah;" + "''hh<t{$hah;" + "''hh<k{$hah;" + "''hh<s{$hah;" + "hh<>$hah;" + "''h<d{$heh;" + "''h<t{$heh;" + "''h<k{$heh;" + "''h<s{$heh;" + "h<>$heh;" + "''ii<i{$kasratein;" + "ii<>$kasratein;" + "''i<i{$kasra;" + "i<>$kasra;" + "j<>$geem;" + "kh<>$kha;" + "k<>$kaf;" + "l<>$lam;" + "''m<y{$meem;" + "''m<t{$meem;" + "m<>$meem;" + "n<>$noon;" + "''o<a{$hamza;" + "o<>$hamza;" + "p<>$peh;" + "q<>$qaaf;" + "r<>$reh;" + "sh<>$sheen;" + "''ss<s{$sad;" + "ss<>$sad;" + "''s<s{$seen;" + "s<>$seen;" + "th<>$theh;" + "tm<>$tehmarbuta;" + "''tt<t{$tah;" + "tt<>$tah;" + "''t<t{$teh;" + "t<>$teh;" + "''uu<u{$dammatein;" + "uu<>$dammatein;" + "''u<u{$damma;" + "u<>$damma;" + "we<>$wauuhamza;" + "w<>$wau;" + "ye<>$yehuhamza;" + "ym<>$yehmaqsura;" + "''y<y{$yeh;" + "y<>$yeh;" + "''zz<z{$zah;" + "zz<>$zah;" + "''z<z{$zain;" + "z<>$zain;" + + // One-way Latin-Arabic compatability rules + "c>$kaf;" + "g>$geem;" + "x>$kaf$shadda$seen;" + "v>$beh;" + + // Digits + "0<>\u0660;" // Arabic digit 0 + "1<>\u0661;" // Arabic digit 1 + "2<>\u0662;" // Arabic digit 2 + "3<>\u0663;" // Arabic digit 3 + "4<>\u0664;" // Arabic digit 4 + "5<>\u0665;" // Arabic digit 5 + "6<>\u0666;" // Arabic digit 6 + "7<>\u0667;" // Arabic digit 7 + "8<>\u0668;" // Arabic digit 8 + "9<>\u0669;" // Arabic digit 9 + "'%'<>\u066A;" // Arabic % + "'.'<>\u066B;" // Arabic decimal separator + "','<>\u066C;" // Arabic thousands separator + "'*'<>\u066D;" // Arabic five-pointed star + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_Latin_Armenian.txt b/icu/translit_Latin_Armenian.txt new file mode 100644 index 0000000..9ab4f1a --- /dev/null +++ b/icu/translit_Latin_Armenian.txt @@ -0,0 +1,151 @@ +//-------------------------------------------------------------------- +// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org) +// Use freely. +//-------------------------------------------------------------------- +// Based upon UNGEGN recommendations from +// http://www.eki.ee/wgrs/rom2_hy.pdf +//-------------------------------------------------------------------- + +// Latin-Armenian + +translit_Latin_Armenian { + Rule { + ":: NFD (NFC) ;" + + "$armenian = [[:ARMENIAN:] & [:L:]];" + "$armenian_vowels = [\u0531\u0535\u0537\u053B\u0548\u0552\u0555\u0561\u0565\u0567\u056B\u0578\u0582\u0585];" + + "Ye<[:^L:]{\u0535}[:Ll:];" + "Ye<[$armenian_vowels]{\u0535}[:Ll:];" + "YE<[:^L:]{\u0535;" + "YE<[$armenian_vowels]{\u0535;" + + "OV<[:^L:]{\u0548\u054E}[:^L:];" + "Ov<[:^L:]{\u0548\u057E}[:^L:];" + "Vo<[:^L:]{\u0548}[:Ll:];" + "VO<[:^L:]{\u0548;" + + "Ts''<>\u0551}[:Ll:];" + "Ch''<>\u0549}[:Ll:];" + + "Gh<>\u0542}[:Ll:];" + "Dz<>\u0541}[:Ll:];" + "Zh<>\u053A}[:Ll:];" + "Kh<>\u053D}[:Ll:];" + "Ts<>\u053E}[:Ll:];" + "Ch<>\u0543}[:Ll:];" + "Sh<>\u0547}[:Ll:];" + "Rr<>\u054C}[:Ll:];" + + "TS''<>\u0551;" + "CH''<>\u0549;" + + "GH<>\u0542;" + "DZ<>\u0541;" + "T''<>\u0539;" + "ZH<>\u053A;" + "KH<>\u053D;" + "TS<>\u053E;" + "CH<>\u0543;" + "SH<>\u0547;" + "RR<>\u054C;" + "P''<>\u0553;" + "K''<>\u0554;" + + "A<>\u0531;" + "B<>\u0532;" + "G<>\u0533;" + "D<>\u0534;" + "E<>\u0535;" + "Z<>\u0536;" + "E<\u0537;" + "Y<>\u0538;" + "I<>\u053B;" + "L<>\u053C;" + "K<>\u053F;" + "H<>\u0540;" + "M<>\u0544;" + "Y<\u0545;" + "N<>\u0546;" + "O<\u0548;" + "P<>\u054A;" + "J<>\u054B;" + "S<>\u054D;" + "V<>\u054E;" + "T<>\u054F;" + "R<>\u0550;" + "U<>\u0552;" + "O<>\u0555;" + "F<>\u0556;" + + "\u02BF<>\u0559;" + "\u02BE<>\u055A;" + "\u02CA<>\u055B;" + "'!'<>\u055C;" + "','<>\u055D;" + "'?'<>\u055E;" + "\u2026<\u055F;" + + "yev<>[:^L:]{\u0587;" + "yev<[$armenian_vowels]{\u0587;" + "ye<[:^L:]{\u0565;" + "ye<[$armenian_vowels]{\u0565;" + + "ov<>[:^L:]{\u0578\u057E}[:^L:];" + "vo<>[:^L:]{\u0578;" + + "ts''<>\u0581;" + "ch''<>\u0579;" + + "gh<>\u0572;" + "dz<>\u0571;" + "ev<>\u0587;" + "t''<>\u0569;" + "zh<>\u056A;" + "kh<>\u056D;" + "ts<>\u056E;" + "k''<>\u0584;" + "ch<>\u0573;" + "p''<>\u0583;" + "rr<>\u057C;" + "sh<>\u0577;" + + "a<>\u0561;" + "b<>\u0562;" + "g<>\u0563;" + "d<>\u0564;" + "e<>\u0565;" + "z<>\u0566;" + "e<\u0567;" + "y<>\u0568;" + "i<>\u056B;" + "l<>\u056C;" + "k<>\u056F;" + "h<>\u0570;" + "m<>\u0574;" + "y<\u0575;" + "n<>\u0576;" + "o<\u0578;" + "p<>\u057A;" + "j<>\u057B;" + "s<>\u057D;" + "v<>\u057E;" + "t<>\u057F;" + "r<>\u0580;" + "u<>\u0582;" + "o<>\u0585;" + "f<>\u0586;" + + "'.'<>\u0589;" + "'-'<>\u058A;" + + //remove untransliterated + "<[:ARMENIAN:];" + "[:LATIN:]>;" + + ":: NFC (NFD) ;" + } +} + + + diff --git a/icu/translit_Latin_Coptic.txt b/icu/translit_Latin_Coptic.txt new file mode 100644 index 0000000..5f40008 --- /dev/null +++ b/icu/translit_Latin_Coptic.txt @@ -0,0 +1,129 @@ +//-------------------------------------------------------------------- +// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org) +// Use freely. +//-------------------------------------------------------------------- +// Based upon SBL standard Coptic transliteration system from +// The SBL Handbook of Style p. 30 +//-------------------------------------------------------------------- + +// Latin-Coptic + +translit_Latin_Coptic { + Rule { + ":: NFD (NFC) ;" + + "$macron = \u0304;" + "$caron = \u030C;" + + //completeness mappings for latin + "C}[^$caron]>|C $caron;" + "c}[^$caron]>|c $caron;" + "Q>|K;" + "q>|k;" + "V>|U;" + "v>|u;" + "W>|U;" + "w>|u;" + "X>|KS;" + "x>|ks;" + "Y>|U;" + "y>|u;" + + //titlecase digraphs + "Th<>\u0398}[:LowercaseLetter:];" + "Ks<>\u039E}[:LowercaseLetter:];" + "Ph<>\u03A6}[:LowercaseLetter:];" + "Kh<>\u03A7}[:LowercaseLetter:];" + "Ps<>\u03A8}[:LowercaseLetter:];" + + //coptic-unique + "Ti<>\u03EE}[:LowercaseLetter:];" + + //uppercase digraphs + "TH<>\u0398;" + "KS<>\u039E;" + "PH<>\u03A6;" + "KH<>\u03A7;" + "PS<>\u03A8;" + + //coptic-unique + "TI<>\u03EE;" + + "E $macron<>\u0397;" + "O $macron<>\u03A9;" + + //coptic-unique + "S $caron<>\u03E2;" + "C $caron<>\u03EC;" + + "A<>\u0391;" + "B<>\u0392;" + "G<>\u0393;" + "D<>\u0394;" + "E<>\u0395;" + "Z<>\u0396;" + "I<>\u0399;" + "K<>\u039A;" + "L<>\u039B;" + "M<>\u039C;" + "N<>\u039D;" + "O<>\u039F;" + "P<>\u03A0;" + "R<>\u03A1;" + "S<>\u03A3;" + "T<>\u03A4;" + "U<>\u03A5;" + + //coptic-unique + "F<>\u03E4;" + "H<>\u03E8;" + "J<>\u03EA;" + + // lowercase digraphs + "th<>\u03B8;" + "ks<>\u03BE;" + "ph<>\u03C6;" + "kh<>\u03C7;" + "ps<>\u03C8;" + + //coptic-unique + "ti<>\u03EF;" + + "e $macron<>\u03B7;" + "o $macron<>\u03C9;" + + //coptic-unique + "s $caron<>\u03E3;" + "c $caron<>\u03ED;" + + "a<>\u03B1;" + "b<>\u03B2;" + "g<>\u03B3;" + "d<>\u03B4;" + "e<>\u03B5;" + "z<>\u03B6;" + "i<>\u03B9;" + "k<>\u03BA;" + "l<>\u03BB;" + "m<>\u03BC;" + "n<>\u03BD;" + "o<>\u03BF;" + "p<>\u03C0;" + "r<>\u03C1;" + "s<\u03C2;" + "s<>\u03C3;" + "t<>\u03C4;" + "u<>\u03C5;" + + //coptic-unique + "f<>\u03E5;" + "h<>\u03E9;" + "j<>\u03EB;" + + //remove untransliterated + "<[:GREEK:];" + "[:LATIN:]>;" + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_Latin_Ethiopic.txt b/icu/translit_Latin_Ethiopic.txt new file mode 100644 index 0000000..b77114c --- /dev/null +++ b/icu/translit_Latin_Ethiopic.txt @@ -0,0 +1,407 @@ +//-------------------------------------------------------------------- +// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org) +// Use freely. +//-------------------------------------------------------------------- +// Based upon UNGEGN recommendations for Amharic/Ethiopic from +// http://www.eki.ee/wgrs/rom1_am.pdf +//-------------------------------------------------------------------- +// Latin-Ethiopic + +translit_Latin_Ethiopic { + Rule { + ":: NFD (NFC) ;" + + ":: [:LATIN:] lower();" + + "$macron = \u0331;" + + "li$macron<>\u120D;" + "le$macron<>\u1208;" + "lu<>\u1209;" + "li<>\u120A;" + "la<>\u120B;" + "le<>\u120C;" + "lo<>\u120E;" + "lwa<>\u120F;" + + "mi$macron<>\u121D;" + "me$macron<>\u1218;" + "mu<>\u1219;" + "mi<>\u121A;" + "ma<>\u121B;" + "me<>\u121C;" + "mo<>\u121E;" + "mwa<>\u121F;" + + "si$macron<>\u1225;" + "se$macron<>\u1220;" + "su<>\u1221;" + "si<>\u1222;" + "sa<>\u1223;" + "se<>\u1224;" + "so<>\u1226;" + "swa<>\u1227;" + + "ri$macron<>\u122D;" + "re$macron<>\u1228;" + "ru<>\u1229;" + "ri<>\u122A;" + "ra<>\u122B;" + "re<>\u122C;" + "ro<>\u122E;" + "rwa<>\u122F;" + + "si$macron<\u1235;" + "se$macron<\u1230;" + "su<\u1231;" + "si<\u1232;" + "sa<\u1233;" + "se<\u1234;" + "so<\u1236;" + "swa<\u1237;" + + "shi$macron<>\u123D;" + "she$macron<>\u1238;" + "shu<>\u1239;" + "shi<>\u123A;" + "sha<>\u123B;" + "she<>\u123C;" + "sho<>\u123E;" + "shwa<>\u123F;" + + "k''i$macron<>\u1245;" + "k''e$macron<>\u1240;" + "k''u<>\u1241;" + "k''i<>\u1242;" + "k''a<>\u1243;" + "k''e<>\u1244;" + "k''o<>\u1246;" + "k''wi$macron<>\u124D;" + "k''we$macron<>\u1248;" + "k''wi<>\u124A;" + "k''wa<>\u124B;" + "k''we<>\u124C;" + + "khi$macron<>\u1255;" + "khe$macron<>\u1250;" + "khu<>\u1251;" + "khi<>\u1252;" + "kha<>\u1253;" + "khe<>\u1254;" + "kho<>\u1256;" + "khwi$macron<>\u125D;" + "khwe$macron<>\u1258;" + "khwi<>\u125A;" + "khwa<>\u125B;" + "khwe<>\u125C;" + + "bi$macron<>\u1265;" + "be$macron<>\u1260;" + "bu<>\u1261;" + "bi<>\u1262;" + "ba<>\u1263;" + "be<>\u1264;" + "bo<>\u1266;" + "bwa<>\u1267;" + + "vi$macron<>\u126D;" + "ve$macron<>\u1268;" + "vu<>\u1269;" + "vi<>\u126A;" + "va<>\u126B;" + "ve<>\u126C;" + "vo<>\u126E;" + "vwa<>\u126F;" + + "ti$macron<>\u1275;" + "te$macron<>\u1270;" + "tu<>\u1271;" + "ti<>\u1272;" + "ta<>\u1273;" + "te<>\u1274;" + "to<>\u1276;" + "twa<>\u1277;" + + "chi$macron<>\u127D;" + "che$macron<>\u1278;" + "chu<>\u1279;" + "chi<>\u127A;" + "cha<>\u127B;" + "che<>\u127C;" + "cho<>\u127E;" + "chwa<>\u127F;" + + "ni$macron<>\u1295;" + "ne$macron<>\u1290;" + "nu<>\u1291;" + "ni<>\u1292;" + "na<>\u1293;" + "ne<>\u1294;" + "no<>\u1296;" + "nwa<>\u1297;" + + "nyi$macron<>\u129D;" + "nye$macron<>\u1298;" + "nyu<>\u1299;" + "nyi<>\u129A;" + "nya<>\u129B;" + "nye<>\u129C;" + "nyo<>\u129E;" + "nywa<>\u129F;" + + "ki$macron<>\u12AD;" + "ke$macron<>\u12A8;" + "ku<>\u12A9;" + "ki<>\u12AA;" + "ka<>\u12AB;" + "ke<>\u12AC;" + "ko<>\u12AE;" + "kwi$macron<>\u12B5;" + "kwe$macron<>\u12B0;" + "kwi<>\u12B2;" + "kwa<>\u12B3;" + "kwe<>\u12B4;" + + "wi$macron<>\u12CD;" + "we$macron<>\u12C8;" + "wu<>\u12C9;" + "wi<>\u12CA;" + "wa<>\u12CB;" + "we<>\u12CC;" + "wo<>\u12CE;" + + "zi$macron<>\u12DD;" + "ze$macron<>\u12D8;" + "zu<>\u12D9;" + "zi<>\u12DA;" + "za<>\u12DB;" + "ze<>\u12DC;" + "zo<>\u12DE;" + "zwa<>\u12DF;" + + "zhi$macron<>\u12E5;" + "zhe$macron<>\u12E0;" + "zhu<>\u12E1;" + "zhi<>\u12E2;" + "zha<>\u12E3;" + "zhe<>\u12E4;" + "zho<>\u12E6;" + "zhwa<>\u12E7;" + + "yi$macron<>\u12ED;" + "ye$macron<>\u12E8;" + "yu<>\u12E9;" + "yi<>\u12EA;" + "ya<>\u12EB;" + "ye<>\u12EC;" + "yo<>\u12EE;" + + "ddi$macron<>\u12FD;" + "dde$macron<>\u12F8;" + "ddu<>\u12F9;" + "ddi<>\u12FA;" + "dda<>\u12FB;" + "dde<>\u12FC;" + "ddo<>\u12FE;" + "ddwa<>\u12FF;" + + "di$macron<>\u12F5;" + "de$macron<>\u12F0;" + "du<>\u12F1;" + "di<>\u12F2;" + "da<>\u12F3;" + "de<>\u12F4;" + "do<>\u12F6;" + "dwa<>\u12F7;" + + "ji$macron<>\u1305;" + "je$macron<>\u1300;" + "ju<>\u1301;" + "ji<>\u1302;" + "ja<>\u1303;" + "je<>\u1304;" + "jo<>\u1306;" + "jwa<>\u1307;" + + "ggi$macron<>\u131D;" + "gge$macron<>\u1318;" + "ggu<>\u1319;" + "ggi<>\u131A;" + "gga<>\u131B;" + "gge<>\u131C;" + "ggo<>\u131E;" + "ggwa<>\u131F;" + + "gi$macron<>\u130D;" + "ge$macron<>\u1308;" + "gu<>\u1309;" + "gi<>\u130A;" + "ga<>\u130B;" + "ge<>\u130C;" + "go<>\u130E;" + "gwi$macron<>\u1315;" + "gwe$macron<>\u1310;" + "gwi<>\u1312;" + "gwa<>\u1313;" + "gwe<>\u1314;" + + "t''i$macron<>\u1325;" + "t''e$macron<>\u1320;" + "t''u<>\u1321;" + "t''i<>\u1322;" + "t''a<>\u1323;" + "t''e<>\u1324;" + "t''o<>\u1326;" + "t''wa<>\u1327;" + + "ch''i$macron<>\u132D;" + "ch''e$macron<>\u1328;" + "ch''u<>\u1329;" + "ch''i<>\u132A;" + "ch''a<>\u132B;" + "ch''e<>\u132C;" + "ch''o<>\u132E;" + "ch''wa<>\u132F;" + + "p''i$macron<>\u1335;" + "p''e$macron<>\u1330;" + "p''u<>\u1331;" + "p''i<>\u1332;" + "p''a<>\u1333;" + "p''e<>\u1334;" + "p''o<>\u1336;" + "p''wa<>\u1337;" + + "ts''i$macron<>\u133D;" + "ts''e$macron<>\u1338;" + "ts''u<>\u1339;" + "ts''i<>\u133A;" + "ts''a<>\u133B;" + "ts''e<>\u133C;" + "ts''o<>\u133E;" + "ts''wa<>\u133F;" + + "ts''i$macron<\u1345;" + "ts''e$macron<\u1340;" + "ts''u<\u1341;" + "ts''i<\u1342;" + "ts''a<\u1343;" + "ts''e<\u1344;" + "ts''o<\u1346;" + + "fi$macron<>\u134D;" + "fe$macron<>\u1348;" + "fu<>\u1349;" + "fi<>\u134A;" + "fa<>\u134B;" + "fe<>\u134C;" + "fo<>\u134E;" + "fwa<>\u134F;" + + "pi$macron<>\u1355;" + "pe$macron<>\u1350;" + "pu<>\u1351;" + "pi<>\u1352;" + "pa<>\u1353;" + "pe<>\u1354;" + "po<>\u1356;" + "pwa<>\u1357;" + + "rya<>\u1358;" + "mya<>\u1359;" + "fya<>\u135A;" + + "hi$macron<>\u1205;" + "ha<>\u1200;" + "hu<>\u1201;" + "hi<>\u1202;" + "ha<\u1203;" + "he<>\u1204;" + "ho<>\u1206;" + + "hi$macron<\u1215;" + "ha<\u1210;" + "hu<\u1211;" + "hi<\u1212;" + "ha<\u1213;" + "he<\u1214;" + "ho<\u1216;" + "hwa<>\u1217;" + + "hi$macron<\u1285;" + "ha<\u1280;" + "hu<\u1281;" + "hi<\u1282;" + "ha<\u1283;" + "he<\u1284;" + "ho<\u1286;" + "hwi$macron<>\u128D;" + "hwe$macron<>\u1288;" + "hwi<>\u128A;" + "hwa<\u128B;" + "hwe<>\u128C;" + + "hi$macron<\u12BD;" + "he$macron<\u12B8;" + "hu<\u12B9;" + "hi<\u12BA;" + "ha<\u12BB;" + "he<\u12BC;" + "ho<\u12BE;" + "hwa<\u12BF;" + "hwi$macron<\u12C5;" + "hwe$macron<\u12C0;" + "hwi<\u12C2;" + "hwa<\u12C3;" + "hwe<\u12C4;" + + "i$macron<>\u12A5;" + "a<>\u12A0;" + "u<>\u12A1;" + "i<>\u12A2;" + "a<\u12A3;" + "e<>\u12A4;" + "o<>\u12A6;" + + "i$macron<\u12D5;" + "a<\u12D0;" + "u<\u12D1;" + "i<\u12D2;" + "a<\u12D3;" + "e<\u12D4;" + "o<\u12D6;" + + "' '<>\u1361;" + "'.'<>\u1362;" + "','<>\u1363;" + "';'<>\u1364;" + "':'<>\u1365;" + "':'<\u1366;" + "'?'<>\u1367;" + "\u00B6<>\u1368;" + + "1<>\u1369;" + "2<>\u136A;" + "3<>\u136B;" + "4<>\u136C;" + "5<>\u136D;" + "6<>\u136E;" + "7<>\u136F;" + "8<>\u1370;" + "9<>\u1371;" + + "10<\u1372;" + "20<\u1373;" + "30<\u1374;" + "40<\u1375;" + "50<\u1376;" + "60<\u1377;" + "70<\u1378;" + "80<\u1379;" + "90<\u137A;" + "100<\u137B;" + "10000<\u137C;" + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_Latin_Georgian.txt b/icu/translit_Latin_Georgian.txt new file mode 100644 index 0000000..c07d54e --- /dev/null +++ b/icu/translit_Latin_Georgian.txt @@ -0,0 +1,137 @@ +//-------------------------------------------------------------------- +// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org) +// Use freely. +//-------------------------------------------------------------------- +// Based upon UNGEGN recommendations from +// http://www.eki.ee/wgrs/rom2_ka.pdf +//-------------------------------------------------------------------- + +// Latin-Georgian + +translit_Latin_Georgian { + Rule { + ":: NFD (NFC) ;" + + ":: [:LATIN:] lower();" + + //titlecase digraphs + "Ch\'<\u10B9}[:LowercaseLetter:];" + "Ts\'<\u10BA}[:LowercaseLetter:];" + + "Zh<\u10AF}[:LowercaseLetter:];" + "Gh<\u10B6}[:LowercaseLetter:];" + "Sh<\u10B8}[:LowercaseLetter:];" + "Dz<\u10BB}[:LowercaseLetter:];" + "Ts<\u10BC}[:LowercaseLetter:];" + "Ch<\u10BD}[:LowercaseLetter:];" + "Kh<\u10BE}[:LowercaseLetter:];" + + //non-UNGEGN + "Ey<\u10C1}[:Ll:];" + "Ow<\u10C5}[:Ll:];" + + //uppercase digraphs + "CH\'<\u10B9;" + "TS\'<\u10BA;" + + "T\'<\u10A7;" + "ZH<\u10AF;" + "P\'<\u10B4;" + "K\'<\u10B5;" + "GH<\u10B6;" + "SH<\u10B8;" + "DZ<\u10BB;" + "TS<\u10BC;" + "CH<\u10BD;" + "KH<\u10BE;" + + //non-UNGEGN + "EY<\u10C1;" + "Q\'<\u10C4;" + "OW<\u10C5;" + + "A<\u10A0;" + "B<\u10A1;" + "G<\u10A2;" + "D<\u10A3;" + "E<\u10A4;" + "V<\u10A5;" + "Z<\u10A6;" + "I<\u10A8;" + "K<\u10A9;" + "L<\u10AA;" + "M<\u10AB;" + "N<\u10AC;" + "O<\u10AD;" + "P<\u10AE;" + "R<\u10B0;" + "S<\u10B1;" + "T<\u10B2;" + "U<\u10B3;" + "Q<\u10B7;" + "J<\u10BF;" + "H<\u10C0;" + "Y<\u10C2;" + "W<\u10C3;" + + //lowercase digraphs + "ch\'<>\u10E9;" + "ts\'<>\u10EA;" + + "t\'<>\u10D7;" + "zh<>\u10DF;" + "p\'<>\u10E4;" + "k\'<>\u10E5;" + "gh<>\u10E6;" + "sh<>\u10E8;" + "dz<>\u10EB;" + "ts<>\u10EC;" + "ch<>\u10ED;" + "kh<>\u10EE;" + + //non-UNGEGN + "ey<>\u10F1;" + "q\'<>\u10F4;" + "ow<>\u10F5;" + + "a<>\u10D0;" + "b<>\u10D1;" + "g<>\u10D2;" + "d<>\u10D3;" + "e<>\u10D4;" + "v<>\u10D5;" + "z<>\u10D6;" + "i<>\u10D8;" + "k<>\u10D9;" + "l<>\u10DA;" + "m<>\u10DB;" + "n<>\u10DC;" + "o<>\u10DD;" + "p<>\u10DE;" + "r<>\u10E0;" + "s<>\u10E1;" + "t<>\u10E2;" + "u<>\u10E3;" + "q<>\u10E7;" + "j<>\u10EF;" + "h<>\u10F0;" + + //non-UNGEGN + "y<>\u10F2;" + "w<>\u10F3;" + "f<>\u10F6;" + + //paragraph + "\u00B6<>\u10FB;" + + //completeness mappings for latin + "c>\u10D9;" + "x>\u10EE;" + + //remove untransliterated + "<[:GEORGIAN:];" + "[:LATIN:]>;" + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_Latin_Gothic.txt b/icu/translit_Latin_Gothic.txt new file mode 100644 index 0000000..423f65a --- /dev/null +++ b/icu/translit_Latin_Gothic.txt @@ -0,0 +1,57 @@ +๏ปฟ // -*- Coding: utf-8; -*- +//-------------------------------------------------------------------- +// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org) +// Use freely. +//-------------------------------------------------------------------- +// Based upon standard Gothic transliteration system from +// http://www.cs.tut.fi/~dla/gothic.html +//-------------------------------------------------------------------- + +// Latin-Gothic + +translit_Latin_Gothic { + Rule { + ":: NFD (NFC) ;" + + ":: [:Ll:] lower() ;" + + // the hv ligature might not be ligatured + "hv> |ฦ;" + + // completeness mapping for latin + "c> |k;" + "v> |w;" + "y> |i;" + + // latin-gothic transliteration + "a<>๐ฐ;" + "b<>๐ฑ;" + "g<>๐ฒ;" + "d<>๐ณ;" + "e<>๐ด;" + "q<>๐ต;" + "z<>๐ถ;" + "h<>๐ท;" + "รพ<>๐ธ;" + "i<>๐น;" + "k<>๐บ;" + "l<>๐ป;" + "m<>๐ผ;" + "n<>๐ฝ;" + "j<>๐พ;" + "u<>๐ฟ;" + "p<>๐;" + "90<๐;" // 90 + "r<>๐;" + "s<>๐;" + "t<>๐;" + "w<>๐
;" + "f<>๐;" + "x<>๐;" + "ฦ<>๐;" + "o<>๐;" + "900<๐;" // 900 + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_Latin_Hebrew.txt b/icu/translit_Latin_Hebrew.txt new file mode 100644 index 0000000..957a566 --- /dev/null +++ b/icu/translit_Latin_Hebrew.txt @@ -0,0 +1,223 @@ +//-------------------------------------------------------------------- +// Copyright (c) 1999-2000, International Business Machines +// Corporation and others. All Rights Reserved. +//-------------------------------------------------------------------- +// THIS IS A MACHINE-GENERATED FILE +// Tool: src\com\ibm\tools\translit\dumpICUrules.bat +// Source: src\com\ibm\text\resources/TransliterationRule_Latin_Hebrew.java +// Date: Wed Jul 5 16:11:18 2000 +//-------------------------------------------------------------------- + +// Latin-Hebrew + +translit_Latin_Hebrew { + Rule { + ":: NFD (NFC) ;" + + // Variable names, derived from the Unicode names. + "$POINT_SHEVA=\u05B0;" + "$POINT_HATAF_SEGOL=\u05B1;" + "$POINT_HATAF_PATAH=\u05B2;" + "$POINT_HATAF_QAMATS=\u05B3;" + "$POINT_HIRIQ=\u05B4;" + "$POINT_TSERE=\u05B5;" + "$POINT_SEGOL=\u05B6;" + "$POINT_PATAH=\u05B7;" + "$POINT_QAMATS=\u05B8;" + "$POINT_HOLAM=\u05B9;" + "$POINT_QUBUTS=\u05BB;" + "$POINT_DAGESH_OR_MAPIQ=\u05BC;" + "$POINT_METEG=\u05BD;" + "$PUNCTUATION_MAQAF=\u05BE;" + "$POINT_RAFE=\u05BF;" + "$PUNCTUATION_PASEQ=\u05C0;" + "$POINT_SHIN_DOT=\u05C1;" + "$POINT_SIN_DOT=\u05C2;" + "$PUNCTUATION_SOF_PASUQ=\u05C3;" + "$ALEF=\u05D0;" + "$BET=\u05D1;" + "$GIMEL=\u05D2;" + "$DALET=\u05D3;" + "$HE=\u05D4;" + "$VAV=\u05D5;" + "$ZAYIN=\u05D6;" + "$HET=\u05D7;" + "$TET=\u05D8;" + "$YOD=\u05D9;" + "$FINAL_KAF=\u05DA;" + "$KAF=\u05DB;" + "$LAMED=\u05DC;" + "$FINAL_MEM=\u05DD;" + "$MEM=\u05DE;" + "$FINAL_NUN=\u05DF;" + "$NUN=\u05E0;" + "$SAMEKH=\u05E1;" + "$AYIN=\u05E2;" + "$FINAL_PE=\u05E3;" + "$PE=\u05E4;" + "$FINAL_TSADI=\u05E5;" + "$TSADI=\u05E6;" + "$QOF=\u05E7;" + "$RESH=\u05E8;" + "$SHIN=\u05E9;" + "$TAV=\u05EA;" + "$YIDDISH_DOUBLE_VAV=\u05F0;" + "$YIDDISH_VAV_YOD=\u05F1;" + "$YIDDISH_DOUBLE_YOD=\u05F2;" + "$PUNCTUATION_GERESH=\u05F3;" + "$PUNCTUATION_GERSHAYIM=\u05F4;" + + "$letter=[a-zA-Z];" + "$softvowel=[eiyEIY];" + "$vowellike=[$ALEF$AYIN$YOD$VAV];" + "$hebrew=[\u0590-\u05FF];" // the whole block -liu + + // [Why is this a special case? -liu] + "k''h <> $KAF $HE ;" + + // Mark non-final forms in final position as x~ -liu + "k < $KAF } $hebrew ;" + "m < $MEM } $hebrew ;" + "n < $NUN } $hebrew ;" + "p < $PE } $hebrew ;" + "ts < $TSADI } $hebrew ;" + "k'~' <> $KAF ;" + "m'~' <> $MEM ;" + "n'~' <> $NUN ;" + "p'~' <> $PE ;" + "ts'~'<> $TSADI ;" + + // Mark final forms in non-final position as x^ -liu + "k'^' <> $FINAL_KAF } $hebrew ;" + "m'^' <> $FINAL_MEM } $hebrew ;" + "n'^' <> $FINAL_NUN } $hebrew ;" + "p'^' <> $FINAL_PE } $hebrew ;" + "ts'^'<> $FINAL_TSADI } $hebrew ;" + "k < $FINAL_KAF;" + "m < $FINAL_MEM;" + "n < $FINAL_NUN;" + "p < $FINAL_PE;" + "ts < $FINAL_TSADI;" + + // Main rules + "a<>$ALEF;" + "A>$ALEF;" + + "b<>$BET;" + "B>$BET;" + + "c}$softvowel>$SAMEKH;" + "C}$softvowel>$SAMEKH;" + "c}$letter>$KAF;" + "C}$letter>$KAF;" + "c>$FINAL_KAF;" + "C>$FINAL_KAF;" + + "d<>$DALET;" + "D>$DALET;" + + "e<>$AYIN;" + "E>$AYIN;" + + "f}$letter>$PE;" + "f>$FINAL_PE;" + "F}$letter>$PE;" + "F>$FINAL_PE;" + + "g<>$GIMEL;" + "G>$GIMEL;" + + "h<>$HE;" + "H>$HE;" + + "i>$YOD;" + "I>$YOD;" + + "j>$DALET$SHIN;" + "J>$DALET$SHIN;" + + "kh<>$HET;" + "kH>$HET;" + "Kh>$HET;" + "KH>$HET;" + "k}$letter>$KAF;" + "K}$letter>$KAF;" + "k>$FINAL_KAF;" + "K>$FINAL_KAF;" + + "l<>$LAMED;" + "L>$LAMED;" + + "m}$letter>$MEM;" + "m>$FINAL_MEM;" + "M}$letter>$MEM;" + "M>$FINAL_MEM;" + + "n}$letter>$NUN;" + "n>$FINAL_NUN;" + "N}$letter>$NUN;" + "N>$FINAL_NUN;" + + "o>$VAV;" + "O>$VAV;" + + "p}$letter>$PE;" + "p>$FINAL_PE;" + "P}$letter>$PE;" + "P>$FINAL_PE;" + + "q<>$QOF;" + "Q>$QOF;" + + "r<>$RESH;" + "R>$RESH;" + + "sh<>$SHIN;" + "sH>$SHIN;" + "Sh>$SHIN;" + "SH>$SHIN;" + "s''<$SAMEKH}$HE;" + "s<>$SAMEKH;" + "S>$SAMEKH;" + + "th<>$TAV;" + "tH>$TAV;" + "Th>$TAV;" + "TH>$TAV;" + "tS}$letter>$TSADI;" + "ts}$letter>$TSADI;" + "Ts}$letter>$TSADI;" + "TS}$letter>$TSADI;" + "tS>$FINAL_TSADI;" + "ts>$FINAL_TSADI;" + "Ts>$FINAL_TSADI;" + "TS>$FINAL_TSADI;" + "t''<$TET}[$HE $SAMEKH $SHIN];" + "t<>$TET;" + "T>$TET;" + + "v<$VAV}$vowellike;" + "u<>$VAV;" + "U>$VAV;" + + "v>$VAV;" + "V>$VAV;" + + "w>$VAV;" + "W>$VAV;" + + "x>$KAF$SAMEKH;" + "X>$KAF$SAMEKH;" + + "y<>$YOD;" + "Y>$YOD;" + + "z<>$ZAYIN;" + "Z>$ZAYIN;" + + //Delete any Syriac we didn't recognize + "<$hebrew;" + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_Latin_Syriac.txt b/icu/translit_Latin_Syriac.txt new file mode 100644 index 0000000..5f5c140 --- /dev/null +++ b/icu/translit_Latin_Syriac.txt @@ -0,0 +1,169 @@ +// Latin-Syriac + +translit_Latin_Syriac { + Rule { + ":: NFD (NFC) ;" + + // Variable names, derived from the Unicode names. + "$ALEF=\u0710;" + "$ALEF_SUPERSCRIPT=\u0711;" + "$BET=\u0712;" + "$GIMEL=\u0713;" + "$GIMEL_GARSHUNI=\u0714;" + "$DALET=\u0715;" + "$DALET_DOTLESS=\u0716;" + "$HE=\u0717;" + "$VAV=\u0718;" + "$ZAYIN=\u0719;" + "$HET=\u071A;" + "$TET=\u071B;" + "$TET_GARSHUNI=\u071C;" + "$YOD=\u071D;" + "$YOD_HE=\u071E;" + "$KAF=\u071F;" + "$LAMED=\u0720;" + "$MEM=\u0721;" + "$NUN=\u0722;" + "$SAMEKH=\u0723;" + "$FINAL_SAMEKH=\u0724;" + "$AYIN=\u0725;" + "$PE=\u0726;" + "$PE_REVERSED=\u0727;" + "$TSADI=\u0728;" + "$QOF=\u0729;" + "$RESH=\u072A;" + "$SHIN=\u072B;" + "$TAV=\u072C;" + + "$PARAGRAPH=\u0700;" + + "$letter=[a-zA-Z];" + "$softvowel=[eiyEIY];" + "$vowellike=[$ALEF $AYIN $YOD $VAV $ALEF_SUPERSCRIPT];" + + // [Why is this a special case? -liu] + "k''h <> $KAF $HE ;" + + // Mark non-final forms in final position as x~ -liu + "s < $SAMEKH } [[:SYRIAC:]&[:LETTER:]] ;" + "s'~' <> $SAMEKH ;" + + // Mark final forms in non-final position as x^ -liu + "s < $FINAL_SAMEKH;" + + // Main rules + "a<>$ALEF;" + "A>$ALEF;" + "a<$ALEF_SUPERSCRIPT;" + + "b<>$BET;" + "B>$BET;" + + "c}$softvowel>$SAMEKH;" + "C}$softvowel>$SAMEKH;" + "c>$KAF;" + "C>$KAF;" + + "d<>$DALET;" + "D>$DALET;" + "d<$DALET_DOTLESS;" + + "e<>$AYIN;" + "E>$AYIN;" + + "f>$PE;" + "F>$PE;" + + "g<>$GIMEL;" + "G>$GIMEL;" + "g<$GIMEL_GARSHUNI;" + + "h<>$HE;" + "H>$HE;" + + "i>$YOD;" + "I>$YOD;" + "ih<$YOD_HE;" + + "j>$DALET$SHIN;" + "J>$DALET$SHIN;" + + "kh<>$HET;" + "kH>$HET;" + "Kh>$HET;" + "KH>$HET;" + "k<>$KAF;" + "K>$KAF;" + + "l<>$LAMED;" + "L>$LAMED;" + + "m<>$MEM;" + "M>$MEM;" + + "n<>$NUN;" + "N>$NUN;" + + "o>$VAV;" + "O>$VAV;" + + "p<>$PE;" + "P>$PE;" + "p<$PE_REVERSED;" + + "q<>$QOF;" + "Q>$QOF;" + + "r<>$RESH;" + "R>$RESH;" + + "sh<>$SHIN;" + "sH>$SHIN;" + "Sh>$SHIN;" + "SH>$SHIN;" + + "th<>$TAV;" + "tH>$TAV;" + "Th>$TAV;" + "TH>$TAV;" + "tS>$TSADI;" + "ts<>$TSADI;" + "Ts>$TSADI;" + "TS>$TSADI;" + "t''<$TET}[$HE $SAMEKH $SHIN];" + "t<>$TET;" + "T>$TET;" + "t<$TET_GARSHUNI;" + + "s}$letter>$SAMEKH;" + "s>$FINAL_SAMEKH;" + "S}$letter>$SAMEKH;" + "S>$FINAL_SAMEKH;" + + "v<$VAV}$vowellike;" + "u<>$VAV;" + "U>$VAV;" + + "v>$VAV;" + "V>$VAV;" + + "w>$VAV;" + "W>$VAV;" + + "x>$KAF$SAMEKH;" + "X>$KAF$SAMEKH;" + + "y<>$YOD;" + "Y>$YOD;" + + "z<>$ZAYIN;" + "Z>$ZAYIN;" + + "\u00B6<>$PARAGRAPH;" + + //Delete any Syriac we didn't recognize + "<[:SYRIAC:];" + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_Latin_Thai.txt b/icu/translit_Latin_Thai.txt new file mode 100644 index 0000000..956947e --- /dev/null +++ b/icu/translit_Latin_Thai.txt @@ -0,0 +1,162 @@ +//-------------------------------------------------------------------- +// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org) +// Use freely. +//-------------------------------------------------------------------- +// Based upon UNGEGN recommendations from +// http://www.eki.ee/wgrs/rom1_th.pdf +//-------------------------------------------------------------------- + +// Latin-Thai + +translit_Latin_Thai { + Rule { + ":: NFD (NFC) ;" + + ":: [[:LATIN:]-[B]] lower();" + + //completeness mappings + "c}[^h]>|k;" + "g>|ng;" + "q>|k;" + "v>|f;" + "x>|kh;" + "z>|s;" + "j>|i;" + + // latin-thai + "\u2026<>\u0E2F;" + "\u00B7<>\u0E4F;" + + "B<>\u0E3F;" + + "|$1 a $2<([[:THAI:]&[:L:]])\u0E31([[:THAI:]&[:L:]]);" + "|$1 a $2<([[:THAI:]&[:L:]])\u0E23\u0E23([[:THAI:]&[:L:]]);" + "|$1 e<\u0E40([[:THAI:]&[:L:]])\u0E30;" + "|$1 e $2<\u0E40([[:THAI:]&[:L:]])\u0E47([[:THAI:]&[:L:]]);" + "|$1 ae<\u0E41([[:THAI:]&[:L:]])\u0E30;" + "|$1 ae $2<\u0E41([[:THAI:]&[:L:]])\u0E47([[:THAI:]&[:L:]]);" + "|$1 o<\u0E42([[:THAI:]&[:L:]])\u0E30;" + "|$1 o<\u0E40([[:THAI:]&[:L:]])\u0E32\u0E30;" + "|$1 oe<\u0E40([[:THAI:]&[:L:]])\u0E3D\u0E30;" + "|$1 oe $2<\u0E40([[:THAI:]&[:L:]])\u0E34([[:THAI:]&[:L:]]);" + "|$1 oe<\u0E40([[:THAI:]&[:L:]])\u0E2D;" + "|$1 ia<\u0E40([[:THAI:]&[:L:]])\u0E35\u0E22\u0E30;" + "|$1 ia<\u0E40([[:THAI:]&[:L:]])\u0E35\u0E22;" + "|$1 uea<\u0E40([[:THAI:]&[:L:]])\u0E37\u0E2D\u0E30;" + "|$1 uea<\u0E40([[:THAI:]&[:L:]])\u0E37\u0E2D;" + "|$1 ua<([[:THAI:]&[:L:]])\u0E31\u0E27\u0E30;" + "|$1 ua<([[:THAI:]&[:L:]])\u0E31\u0E27;" + "|$1 ua $2<([[:THAI:]&[:L:]])\u0E27([[:THAI:]&[:L:]]);" + "|$1 ai<([[:THAI:]&[:L:]])\u0E31\u0E22;" + "|$1 ai<\u0E44([[:THAI:]&[:L:]])\u0E22;" + "|$1 ai<([[:THAI:]&[:L:]])\u0E32\u0E22;" + "|$1 ao<\u0E40([[:THAI:]&[:L:]])\u0E32;" + "|$1 ao<([[:THAI:]&[:L:]])\u0E32\u0E27;" + "|$1 ui<([[:THAI:]&[:L:]])\u0E38\u0E22;" + "|$1 oi<\u0E42([[:THAI:]&[:L:]])\u0E22;" + "|$1 oi<([[:THAI:]&[:L:]])\u0E2D\u0E22;" + "|$1 oei<\u0E40([[:THAI:]&[:L:]])\u0E22;" + "|$1 ueai<\u0E40([[:THAI:]&[:L:]])\u0E37\u0E2D\u0E22;" + "|$1 uai<([[:THAI:]&[:L:]])\u0E27\u0E22;" + "|$1 io<([[:THAI:]&[:L:]])\u0E34\u0E27;" + "|$1 eo<\u0E40([[:THAI:]&[:L:]])\u0E47\u0E27;" + "|$1 eo<\u0E40([[:THAI:]&[:L:]])\u0E27;" + "|$1 aeo<\u0E41([[:THAI:]&[:L:]])\u0E47\u0E27;" + "|$1 aeo<\u0E41([[:THAI:]&[:L:]])\u0E27;" + "|$1 iao<\u0E40([[:THAI:]&[:L:]])\u0E35\u0E22\u0E27;" + + "|$1 o<([[:THAI:]&[:L:]])\u0E2D;" + "|$1 a<([[:THAI:]&[:L:]])\u0E30;" + "|$1 a<([[:THAI:]&[:L:]])\u0E32;" + "|$1 an<([[:THAI:]&[:L:]])\u0E23\u0E23;" + "|$1 am<([[:THAI:]&[:L:]])\u0E33;" + "|$1 i<([[:THAI:]&[:L:]])\u0E34;" + "|$1 i<([[:THAI:]&[:L:]])\u0E35;" + "|$1 ue<([[:THAI:]&[:L:]])\u0E36;" + "|$1 ue<([[:THAI:]&[:L:]])\u0E37;" + "|$1 u<([[:THAI:]&[:L:]])\u0E38;" + "|$1 u<([[:THAI:]&[:L:]])\u0E39;" + "|$1 e<\u0E40([[:THAI:]&[:L:]]);" + "|$1 ae<\u0E41([[:THAI:]&[:L:]]);" + "|$1 o<\u0E42([[:THAI:]&[:L:]]);" + "|$1 ai<\u0E43([[:THAI:]&[:L:]]);" + "|$1 ai<\u0E44([[:THAI:]&[:L:]]);" + + "0<>\u0E50;" + "1<>\u0E51;" + "2<>\u0E52;" + "3<>\u0E53;" + "4<>\u0E54;" + "5<>\u0E55;" + "6<>\u0E56;" + "7<>\u0E57;" + "8<>\u0E58;" + "9<>\u0E59;" + + // this doesn't work; don't know why + // "| $1 o < ([[:THAI:]&[:L:]]);" + + "kh<>\u0E02;" + "kh<\u0E03;" + "kh<\u0E04;" + "kh<\u0E05;" + "kh<\u0E06;" + "k<>\u0E01;" + "ng<>\u0E07;" + "ch<>\u0E08;" + "ch<\u0E09;" + "ch<\u0E0A;" + "s<>\u0E0B;" + "ch<\u0E0C;" + "y<>\u0E0D;" + "d<>\u0E0E;" + "s<\u0E17\u0E23;" + "th<>\u0E10;" + "th<\u0E11;" + "th<\u0E12;" + "th<\u0E16;" + "th<\u0E17;" + "th<\u0E18;" + "t<>\u0E0F;" + "n<>\u0E13;" + "d<\u0E14;" + "t<\u0E15;" + "n<\u0E19;" + "b<>\u0E1A;" + "ph<>\u0E1C;" + "ph<\u0E1E;" + "ph<\u0E20;" + "p<>\u0E1B;" + "f<>\u0E1D;" + "f<\u0E1F;" + "m<>\u0E21;" + "y<\u0E22;" + "rue<>\u0E24\u0E32;" + "ri<>\u0E24;" + "r<>\u0E23;" + "lue<\u0E26\uE32;" + "lue<>\u0E26;" + "l<>\u0E25;" + "w<>\u0E27;" + "s<\u0E28;" + "s<\u0E29;" + "s<\u0E2A;" + "h<>\u0E2B;" + "l<\u0E2C;" + "o<\u0E2D;" + "h<\u0E2E;" + + //vowels + "a>\u0E30;" + "([:LATIN:])e>|\u0E40 $1;" + "i>\u0E34;" + "([:^L:])o>|$1 \u0E2D;" + "u>\u0E38;" + + //remove untransliterated + "<[:THAI:];" + "[:LATIN:]>;" + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_Latin_Ugaritic.txt b/icu/translit_Latin_Ugaritic.txt new file mode 100644 index 0000000..d22ae45 --- /dev/null +++ b/icu/translit_Latin_Ugaritic.txt @@ -0,0 +1,63 @@ +๏ปฟ // -*- Coding: utf-8; -*- +//-------------------------------------------------------------------- +// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org) +// Use freely. +//-------------------------------------------------------------------- +// Based upon SBL standard transliteration system from +// the SBL Handbook of Style p.31 +//-------------------------------------------------------------------- + +// Latin-Ugaritic + +translit_Latin_Ugaritic { + Rule { + ":: NFD (NFC) ;" + + ":: lower() ;" + + // completeness + "c> | k;" + "e> | i;" + "f> | w;" + "j> | i;" + "o> | a;" + "v> | w;" + "x> | k;" + + // ugaritic cuneiform + "h ฬฃ <> ๐;" + "d ฬฑ <> ๐;" + "z ฬฃ <> ๐;" + "s ฬฃ <> ๐;" + "g ฬ <> ๐;" + "s ฬ <> ๐;" + + "a <> ๐;" + "b <> ๐;" + "g <> ๐;" + "h ฬฎ<> ๐;" + "d <> ๐;" + "h <> ๐
;" + "w <> ๐;" + "z <> ๐;" + "t ฬฃ <> ๐;" + "y <> ๐;" + "k <> ๐;" + "s ฬ <> ๐;" + "l <> ๐;" + "m <> ๐;" + "n <> ๐;" + "s <> ๐;" + "สฟ <> ๐;" + "p <> ๐;" + "q <> ๐;" + "r <> ๐;" + "t ฬฑ <> ๐;" + "t <> ๐;" + "i <> ๐;" + "u <> ๐;" + "' ' <> ๐;" + + ":: NFC (NFD) ;" + } +} diff --git a/icu/translit_swordindex.txt b/icu/translit_swordindex.txt new file mode 100644 index 0000000..37cd93f --- /dev/null +++ b/icu/translit_swordindex.txt @@ -0,0 +1,108 @@ +//-------------------------------------------------------------------- +// Copyright (c) 1999-2001, International Business Machines +// Corporation and others. All Rights Reserved. +//-------------------------------------------------------------------- +// THIS IS A MACHINE-GENERATED FILE +// Tool: dumpicurules.bat +// Source: Transliterator_index.txt +// Date: Mon Dec 3 11:44:30 2001 +//-------------------------------------------------------------------- + +//-------------------------------------------------------------------- +// N.B.: This file has been generated mechanically from the +// corresponding ICU4J file, which is the master file that receives +// primary updates. The colon-delimited fields have been split into +// separate strings. For 'file' and 'internal' lines, the encoding +// field has been deleted, since the encoding is processed at build +// time in ICU4C. Certain large rule sets not intended for general +// use have been commented out with the notation "Java only". +//-------------------------------------------------------------------- + +translit_swordindex { + RuleBasedTransliteratorIDs { +// Copyright (c) 2001, International Business Machines Corporation and +// others. All Rights Reserved. +// +// TRANSLITERATOR INDEX FILE. This file lists the non-algorithmic +// system transliterators. It allows arbitrary mappings between +// transliterator IDs and file names, and also allows the system to +// define aliases for transliterators, so that "Latin-Hangul", for +// example, can be implemented transparently as the compound +// "Latin-Jamo;Jamo-Hangul". Internal IDs may also be defined; these +// are invisible to the user, but can be composed together by the +// system to create visible transliterators. +// +// Blank lines and lines beginning with '#' are ignored. +// +// Lines in this file have one of the following forms (text not +// enclosed by <> is literal): +// +// <id>:file:<resource>:<encoding>:<direction> +// <id>:internal:<resource>:<encoding>:<direction> +// <id>:alias:<getInstanceArg> +// +// <id> is the ID of the system transliterator being defined. These +// are public IDs enumerated by Transliterator.getAvailableIDs(), +// unless the second field is "internal". +// +// <resource> is a ResourceReader resource name. Currently these refer +// to file names under com/ibm/text/resources. This string is passed +// directly to ResourceReader, together with <encoding>. +// +// <encoding> is the character encoding to use when reading <resource>; +// passed directly to ResourceReader. E.g., "UTF8". +// +// <direction> is either "FORWARD" or "REVERSE". +// +// <getInstanceArg> is a string to be passed directly to +// Transliterator.getInstance(). The returned Transliterator object +// then has its ID changed to <id> and is returned. + +// ICU < 2.0 additions +{ "Latin-Hebrew", "file", "translit_Latin_Hebrew", "FORWARD" }, +{ "Hebrew-Latin", "file", "translit_Latin_Hebrew", "REVERSE" }, +{ "Latin-Arabic", "file", "translit_Latin_Arabic", "FORWARD" }, +{ "Arabic-Latin", "file", "translit_Latin_Arabic", "REVERSE" }, + +// xtradata additions +//{ "Han-Pinyin", "file", "translit_Han_Pinyin", "FORWARD" }, +//{ "Kanji-English", "file", "translit_Kanji_English", "FORWARD" }, +//{ "Kanji-OnRomaji", "file", "translit_Kanji_OnRomaji", "FORWARD" }, +//{ "HTMLEntities-Unicode", "file", "translit_HTMLEnt_Unicode", "FORWARD" }, +//{ "Unicode-HTMLEntities", "file", "translit_HTMLEnt_Unicode", "REVERSE" }, + +// SWORD additions for academic Biblical transliteration schemes +{ "BGreek-Greek", "file", "translit_BGreek_Greek", "FORWARD" }, +{ "Greek-BGreek", "file", "translit_BGreek_Greek", "REVERSE" }, +{ "Beta-Greek", "file", "translit_BETA_Greek", "FORWARD" }, +{ "Greek-Beta", "file", "translit_BETA_Greek", "REVERSE" }, +{ "CCAT-Hebrew", "file", "translit_CCAT_Hebrew", "FORWARD" }, +{ "Hebrew-CCAT", "file", "translit_CCAT_Hebrew", "REVERSE" } +{ "CCAT-Syriac", "file", "translit_CCAT_Syriac", "FORWARD" }, +{ "Syriac-CCAT", "file", "translit_CCAT_Syriac", "REVERSE" }, +//{ "Syriac-Hebrew", "alias", "Syriac-CCAT;CCAT-Hebrew", "" }, +//{ "Hebrew-Syriac", "alias", "Hebrew-CCAT;CCAT-Syriac", "" }, +{ "Latin-Syriac", "file", "translit_Latin_Syriac", "FORWARD" }, +{ "Syriac-Latin", "file", "translit_Latin_Syriac", "REVERSE" }, + +// SWORD additions for other languages +{ "Latin-Thai", "file", "translit_Latin_Thai", "FORWARD" }, +{ "Thai-Latin", "file", "translit_Latin_Thai", "REVERSE" }, +{ "Latin-Georgian", "file", "translit_Latin_Georgian", "FORWARD" }, +{ "Georgian-Latin", "file", "translit_Latin_Georgian", "REVERSE" }, +{ "Latin-Armenian", "file", "translit_Latin_Armenian", "FORWARD" }, +{ "Armenian-Latin", "file", "translit_Latin_Armenian", "REVERSE" }, +{ "Latin-Coptic", "file", "translit_Latin_Coptic", "FORWARD" }, +{ "Coptic-Latin", "file", "translit_Latin_Coptic", "REVERSE" }, +{ "Latin-Gothic", "file", "translit_Latin_Gothic", "FORWARD" }, +{ "Gothic-Latin", "file", "translit_Latin_Gothic", "REVERSE" }, +{ "Latin-Ethiopic", "file", "translit_Latin_Ethiopic", "FORWARD" }, +{ "Ethiopic-Latin", "file", "translit_Latin_Ethiopic", "REVERSE" }, +{ "Latin-Ugaritic", "file", "translit_Latin_Ugaritic", "FORWARD" }, +{ "Ugaritic-Latin", "file", "translit_Latin_Ugaritic", "REVERSE" }, + +{ "Any-Latin1", "file", "translit_Any_Latin1", "FORWARD" }, + +// eof + } +} |