diff --git a/tools/tools/locale/Makefile b/tools/tools/locale/Makefile
index 27ff255d7f9a..92f890b2f4d3 100644
--- a/tools/tools/locale/Makefile
+++ b/tools/tools/locale/Makefile
@@ -1,258 +1,260 @@
 # $FreeBSD$
 # See https://wiki.freebsd.org/LocaleNewApproach
 # Taken from FreeBSD svn [base]/user/edwin/locale/cldr
 #
 # needs:
 # devel/p5-Tie-IxHash
 #
 # Modified by John Marino to suit DragonFly needs
 #
 .if ${.CURDIR} == ${.OBJDIR}
 .error Do make obj first.
 .endif
 
 LOCALESRCDIR?=	${SRCTOP}/share
 TMPDIR?=	/tmp
 
 BASEDIR=	${.CURDIR}
 ETCDIR=		${BASEDIR}/etc
 TOOLSDIR=	${BASEDIR}/tools
 PATCHDIR=	${BASEDIR}/patch
 UNIDIR=		${.OBJDIR:tA}/unicode
 
 PKGS=	openjdk8 \
 	apache-ant \
 	p5-XML-Parser \
 	p5-Tie-IxHash \
 	p5-Text-Iconv
 tools-test:
 	pkg info -e ${PKGS}
 	@echo tools ok.
 
 KNOWN=		monetdef numericdef msgdef colldef ctypedef # timedef
 TYPES?=		${KNOWN}
 
 COLLATION_SPECIAL?= \
 	cs_CZ ISO8859-2 \
 	da_DK ISO8859-1 \
 	da_DK ISO8859-15 \
 	hr_HR ISO8859-2 \
 	hu_HU ISO8859-2 \
 	nb_NO ISO8859-1 \
 	nb_NO ISO8859-15 \
 	sk_SK ISO8859-2 \
 	sr_Latn_RS ISO8859-2 \
 	sr_Cyrl_RS ISO8859-5 \
 	zh_Hans_CN GB2312 \
 	zh_Hans_CN eucCN \
 	zh_Hant_TW Big5 \
 	zh_Hans_CN GB18030 \
 	zh_Hans_CN GBK \
 	ja_JP eucJP \
 	nn_NO ISO8859-15 \
 	nn_NO ISO8859-1
 
 .for area enc in ${COLLATION_SPECIAL}
 COLLATIONS_SPECIAL_ENV+=	${area}.${enc}
 .endfor
 SETENV=	env -i \
 	PATH="${PATH}" \
 	TMPDIR="${TMPDIR}" \
 	COLLATIONS_SPECIAL="${COLLATIONS_SPECIAL_ENV}" \
 	UNIDIR="${UNIDIR}" \
 	BASEDIR="${BASEDIR}" \
 	TOOLSDIR="${TOOLSDIR}" \
 	ETCDIR="${ETCDIR}"
 
 all: posix build afterbuild
 .ORDER: posix build afterbuild
 
 afterbuild: build
 	@echo ""
 	@find . -name *failed
 
 .for t in ${TYPES}
 .  if ${KNOWN:M${t}}
 build: build-${t}
 .ORDER: build-${t} afterbuild
 .  endif
 .endfor
 
 diff:
 .for t in ${TYPES}
 .  if ${KNOWN:M${t}}
 diff: diff-${t}
 diff-${t}:
 	-/usr/bin/diff -ruN -x Makefile -x Makefile.depend \
 	    ${LOCALESRCDIR}/${t} ${t}
 .  endif
 .endfor
 
 install:
 .for t in ${TYPES}
 .  if ${KNOWN:M${t}}
 install: install-${t}
 install-${t}:
 	cd ${LOCALESRCDIR}/${t} && \
 	    rm -f Makefile *.src && \
 	    cd ${.OBJDIR} && \
 	    install -m 644 ${t}/* ${LOCALESRCDIR}/${t}
 .  endif
 .endfor
 
 post-install:
 .for t in ${TYPES}
 .  if ${KNOWN:M${t}}
 	cd ${LOCALSRCDIR}/${t} && \
 	    make && make install && make clean
 .  endif
 .endfor
 
 .for t in ${TYPES}
 CLEANDIRS+=	${t} ${t}.draft
 ${t}:
 	mkdir -p ${t} ${t}.draft && \
 	perl -I ${TOOLSDIR} ${TOOLSDIR}/cldr2def.pl \
 		--unidir=${UNIDIR:tA} \
 		--etc=${ETCDIR:tA} \
 		--type=${t}
 
 build-${t}: ${t}
 	${SETENV} OUTBASEDIR="${.OBJDIR}/${t}" ${TOOLSDIR}/finalize ${t}
 .endfor
 
 static-colldef: colldef
 build-colldef:	static-colldef
 
 static-colldef:
 .for area enc in ${COLLATION_SPECIAL}
 	awk -f ${TOOLSDIR}/extract-colldef.awk \
 	    posix/${area}.${enc}.src > colldef.draft/${area}.${enc}.src
 .endfor
 
 BASE_LOCALES_OF_INTEREST?= \
 	af_ZA am_ET ar_AE ar_EG ar_JO ar_MA ar_QA ar_SA \
 	be_BY bg_BG ca_AD ca_ES ca_FR ca_IT \
 	cs_CZ da_DK de_AT de_CH de_DE el_GR en_AU en_CA \
 	en_GB en_HK en_IE en_NZ en_PH en_SG en_US en_ZA \
 	es_AR es_CR es_ES es_MX et_EE eu_ES fi_FI fr_BE \
 	fr_CA fr_CH fr_FR ga_IE he_IL hi_IN hr_HR hu_HU hy_AM \
 	is_IS it_CH it_IT ja_JP ko_KR lt_LT lv_LV \
 	nb_NO nl_BE nl_NL nn_NO pl_PL pt_BR pt_PT ro_RO \
 	ru_RU se_FI se_NO sk_SK sl_SI sv_FI sv_SE tr_TR \
 	uk_UA \
 	kk_KZ mn_MN sr_Cyrl_RS sr_Latn_RS \
 	zh_Hans_CN zh_Hant_HK zh_Hant_TW \
 	bn_IN gu_IN or_IN ta_IN te_IN kn_IN ml_IN si_LK \
 	th_TH lo_LA bo_IN my_MM pa_Guru_IN ka_GE chr_US \
 	km_KH shi_Tfng_MA ii_CN vai_Vaii_LR vi_VN
 
 ENCODINGS=	Big5 \
 		CP1251 \
 		CP866 \
 		CP949 \
 		eucCN \
 		eucJP \
 		eucKR \
 		GB18030 \
 		GB2312 \
 		GBK \
 		ISO8859-1 \
 		ISO8859-13 \
 		ISO8859-15 \
 		ISO8859-2 \
 		ISO8859-5 \
 		ISO8859-7 \
 		ISO8859-9 \
 		KOI8-R \
 		KOI8-U \
 		SJIS \
 		US-ASCII \
-		UTF-8
+		UTF-8 \
+		UTF-32
 
 # CLDR files
 CLDRFILES_CORE= https://unicode.org/Public/cldr/35/core.zip
 CLDRFILES_KEY=	https://unicode.org/Public/cldr/35/keyboards.zip
 CLDRFILES_TOOLS=https://unicode.org/Public/cldr/35/tools.zip
 CLDRFILES_UCD=	http://www.unicode.org/Public/zipped/latest/UCD.zip
 
 # fetch and extract targets
 ${UNIDIR}:
 	mkdir -p ${UNIDIR}
 .for N in CORE KEY TOOLS UCD
 ${CLDRFILES_${N}:T}:
 	fetch ${CLDRFILES_${N}}
 fetch: ${CLDRFILES_${N}:T}
 extract-${CLDRFILES_${N}:T}:: ${CLDRFILES_${N}:T} ${UNIDIR}
 	cd ${UNIDIR} && unzip -o ../${CLDRFILES_${N}:T}
 extract: extract-${CLDRFILES_${N}:T}
 .endfor
 	grep 'name="version"' ${UNIDIR}/tools/build.xml | \
 		sed 's/.* value="//;s/".*//' > ${UNIDIR}/cldr-version
 patch::
 .if exists(${PATCHDIR})
 	cd ${UNIDIR} && cat ${PATCHDIR}/patch-* | patch
 .endif
 
 .if !exists(${UNIDIR}/tools/java/cldr.jar)
 .ORDER: extract patch
 build-tools: extract patch tools-test ${UNIDIR}
 	cd ${UNIDIR}/tools/java && ${SETENV} ant all jar
 .else
 build-tools:
 	@echo cldr.jar is ready.
 .endif
 
 JAVA_CLDR= java -DCLDR_DIR=${UNIDIR:Q} -jar ${UNIDIR}/tools/java/cldr.jar
 
 posix: posixcm post-posixcm posixsrc posixcol
 .ORDER: posixcm post-posixcm posixsrc posixcol
 ${UNIDIR}/posix:
 	ln -s -f ../posix ${.TARGET}
 clean-posix:
 	rm -rf posix ${UNIDIR}/posix
-post-posixcm: ${UNIDIR}/posix
+${UNIDIR}/posix/xx_Comm_C.UTF-8.src: ${UNIDIR}/posix
 	perl -I ${TOOLSDIR} ${TOOLSDIR}/utf8-rollup.pl \
 	    --unidir=${UNIDIR}
+post-posixcm: ${UNIDIR}/posix/xx_Comm_C.UTF-8.src
 .for enc in ${ENCODINGS}
 posixcm: build-tools posix/${enc}.cm
 .ORDER: build-tools posix/${enc}.cm
 posix/${enc}.cm:
 	mkdir -p posix && \
 	    ${JAVA_CLDR} org.unicode.cldr.posix.GenerateCharmap \
 		-d posix -c ${enc}
 .endfor
 .for area in ${BASE_LOCALES_OF_INTEREST}
 posixsrc: build-tools posix/${area}.UTF-8.src
 .ORDER: build-tools posix/${area}.UTF-8.src
 posix/${area}.UTF-8.src:
 	mkdir -p posix && \
 	    ${JAVA_CLDR} org.unicode.cldr.posix.GeneratePOSIX \
 		-d posix -m ${area} -c UTF-8
 .endfor
 .for area encoding in ${COLLATION_SPECIAL}
 posixcol: build-tools posix/${area}.${encoding}.src
 .ORDER: build-tools posix/${area}.${encoding}.src
 posix/${area}.${encoding}.src:
 	mkdir -p posix && \
 	    ${JAVA_CLDR} org.unicode.cldr.posix.GeneratePOSIX \
 		-d posix -m ${area} -c ${encoding}
 .endfor
 
 # generate widths.txt using the data from libut8proc
 GETWIDTHS=${TOOLSDIR}/getwidths
 MKWIDTHS=${TOOLSDIR}/mkwidths.pl
 WIDTHS=	${ETCDIR}/final-maps/widths.txt
 
 U8CFLAGS!=pkgconf --cflags libutf8proc
 U8LIBS!=pkgconf --libs libutf8proc
 CFLAGS+=${U8CFLAGS}
 LDFLAGS+=${U8LIBS}
 
 CLEANFILES+=${TOOLSDIR}/getwidths
 
 widths:	${WIDTHS}
 ${WIDTHS}: posixcm ${GETWIDTHS}
 	${GETWIDTHS} | ${MKWIDTHS} ${.OBJDIR}/posix/UTF-8.cm ${.TARGET}
 
 .include <bsd.obj.mk>
diff --git a/tools/tools/locale/README b/tools/tools/locale/README
index 0b5ce24b51cd..380786929b7c 100644
--- a/tools/tools/locale/README
+++ b/tools/tools/locale/README
@@ -1,62 +1,67 @@
 # $FreeBSD$
 
 Files in this directory are used to generate locale source files
 from files in CLDR (Unicode Common Locale Data Repository). 
 
 To generate the files, do the following:
 
 	cd /usr/src/tools/tools/locale
 	make obj	(mandatory)
 	make -j16	(-jN recommended)
 	make diff	(check if the changes are reasonable)
 	make install
 
 "make" downloads the necessary files, build them, and install the
 results into /usr/src/share/* as source files for locales.
 
 More details are as follows:
 
 Variables:
 	LOCALESRCDIR
 		Destination path for the generated locale files.
-		Default: $DESTDIR/usr/src/share.
+		Default: ${SRCTOP}/share.
 	TMPDIR
 		Temporary directory.
 		Default: /tmp
 
 Targets:
 	make obj
 		Create a temporary directory for building.
 
 	make clean
-		Clean up the obj directories.
+		Clean up the obj directories.  Note that this does not
+		clean up tools or posix locale source files generated
+		from the CLDR files because it takes a long time to generate
+		them and they are not changed as long as using the same
+		CLDR files.  "make clean && make build" will
+		regenerate the locale source files for src/share/*def.
 
 	make cleandir
 		Remove the obj directories completely.
 
 	make tools-test
 		Check if necessary tools are installed or not.
 		If something is missing, install them.
 
 	make fetch
 		Download necessary files from CLDR.
 
 	make build-tools
 		Build a tool to generate locale source files.
 
 	make posix
 		Build POSIX locale source files.
 
 	make build
 		Build locale files.
 
 	make diff
 		Run diff(1) the build results against $LOCALESRCDIR.
 
 	make install
 		Install the build results into $LOCALESRCDIR.
 
 	make widths
 		Generate widths.txt.  Requires pkgconf and utf8proc
 		packages to be installed.
 [EOF]
diff --git a/tools/tools/locale/etc/charmaps.xml b/tools/tools/locale/etc/charmaps.xml
index 78a344d6929e..52e80f2dee05 100644
--- a/tools/tools/locale/etc/charmaps.xml
+++ b/tools/tools/locale/etc/charmaps.xml
@@ -1,750 +1,759 @@
 <!-- $FreeBSD$ -->
 <data>
 <languages>
 	<!-- Attributes known:
 		name = language name - only one
 		encoding = encodings to be done - separated by space
 		countries = countries to create - separated by space
 		family = which font family - only one
 		countryname_link = only with family, link this original file \
 			too - only one
 		encoding_link = link this original encoding too - separated \
 			by space
 		fallback = read this file if name_countries doesn't exist - \
 			only one
 		definitions = only use in these definitions (msgdef, timedef, \
 			numericdef, monetdef)
 
 		By default, the name of the input file is name_countries.
 		If family is defined, the name of the input file will be \
 			name_family_countries.
 		If fallback is defined, the name of the input file will be that.
 
 		By default, the name of the output file is name_countries.
 		If family is defined, the name of the output file will be \
 			name_family_countries.
 		For backwards compatibility you use link which is \
 			name_countries.
 
 	-->
 	<language name="af"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="ZA" />
 	<language name="am"
 		countries="ET" />		<!-- UTF-8 only -->
 	<language name="ar"
 		countries="AE EG JO MA QA SA" />
 	<language name="be"
 		encoding="CP1131 CP1251 ISO8859-5"
 		countries="BY" />
 	<language name="bg"
 		encoding="CP1251"
 		countries="BG" />
 	<language name="ca"
 		fallback="ca_ES"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="AD ES FR IT" />	<!-- only ca_ES defined -->
 	<language name="cs"
 		encoding="ISO8859-2"
 		countries="CZ" />
 	<language name="da"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="DK" />
 	<language name="de"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="AT CH DE" />
 	<language name="el"
 		encoding="ISO8859-7"
 		countries="GR" />
 	<language name="en"
 		encoding="ISO8859-1 ISO8859-15 US-ASCII"
 		countries="GB" />
 	<language name="en"
 		encoding="ISO8859-1 ISO8859-15 US-ASCII"
 		countries="AU CA NZ US ZA" />
 	<language name="en"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="IE" />
 	<language name="en"
 		encoding="ISO8859-1"
 		countries="HK SG" />
 	<language name="en"
 		countries="PH" />               <!-- UTF-8 only -->
 	<language name="es"
 		countries="CR" />               <!-- UTF-8 only -->
 	<language name="es"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="ES" />
 	<language name="es"
 		encoding="ISO8859-1"
 		countries="AR MX" />
 	<language name="et"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="EE" />
 	<language name="eu"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="ES" />
 	<language name="fi"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="FI" />
 	<language name="fr"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="BE CH FR" />
 	<language name="fr"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="CA" />
 	<language name="ga"
 		countries="IE" />		<!-- UTF-8 only -->
 	<language name="he"
 		countries="IL" />
 	<language name="hi"
 		encoding="ISCII-DEV"
 		countries="IN" />
 	<language name="hr"
 		encoding="ISO8859-2"
 		countries="HR" />
 	<language name="hu"
 		encoding="ISO8859-2"
 		countries="HU" />
 	<language name="hy"
 		encoding="ARMSCII-8"
 		countries="AM" />
 	<language name="is"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="IS" />
 	<language name="it"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="CH IT" />
 	<language name="ja"
 		encoding="SJIS eucJP"
 		countries="JP" />
 	<language name="kk"
 		countries="KZ" />  <!-- PT154 not available, UTF-8 -->
 	<language name="ko"
 		encoding="eucKR"
 		encoding_link="eucKR:CP949"
 		countries="KR" />
 	<language name="lt"
 		encoding="ISO8859-13"
 		countries="LT" />
 	<language name="lv"
 		encoding="ISO8859-13"
 		countries="LV" />
 	<language name="mn"
 		countries="MN" />
 	<language name="nb"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="NO" />
 	<language name="nl"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="BE NL" />
 	<language name="nn"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="NO" />
 	<language name="pl"
 		encoding="ISO8859-2"
 		countries="PL" />
 	<language name="pt"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="PT" />
 	<language name="pt"
 		encoding="ISO8859-1"
 		countries="BR" />
 	<language name="ro"
 		encoding="ISO8859-2"
 		countries="RO" />
 	<language name="ru"
 		encoding="CP1251 CP866 ISO8859-5 KOI8-R"
 		countries="RU" />
 	<language name="se"
 		countries="NO FI" />
 	<language name="sk"
 		encoding="ISO8859-2"
 		countries="SK" />
 	<language name="sl"
 		encoding="ISO8859-2"
 		countries="SI" />
 	<language name="sr"
 		family="Latn"
 		encoding="ISO8859-2"
 		countries="RS" />
 	<language name="sr"
 		family="Cyrl"
 		encoding="ISO8859-5"
 		countries="RS" />
 	<language name="sv"
 		encoding="ISO8859-1 ISO8859-15"
 		countries="SE FI" />
 	<language name="tr"
 		encoding="ISO8859-9"
 		countries="TR" />
 	<language name="uk"
 		encoding="CP1251 ISO8859-5 KOI8-U"
 		countries="UA" />
 	<language name="zh"
 		family="Hans"
 		encoding="GB18030 GB2312 GBK eucCN"
 		countries="CN" />
 	<language name="zh"
 		family="Hant"
 		countries="HK" />
 	<language name="zh"
 		family="Hant"
 		encoding="Big5"
 		countries="TW" />
 </languages>
 
 <translations>
+	<!--
+		encoding: Space-separated list of encodings
+		cldr: Symbol to be replaced with hex, string, unicode, or ucc.
+		  The symbol name should be defined in posix/*.cm files.
+		string: raw code in string.
+		hex: raw code in hex.
+		unicode: Symbol name in Unicode.
+		ucc: Unicode code point in hex.
+	-->
 	<!-- These don't have a special Euro sign so just use Eu for it -->
-	<translation encoding="ISO8859-1" cldr="EURO SIGN" string="Eu" />
-	<translation encoding="ISO8859-2" cldr="EURO SIGN" string="Eu" />
-	<translation encoding="ISO8859-4" cldr="EURO SIGN" string="Eu" />
-	<translation encoding="ISO8859-13" cldr="EURO SIGN" string="Eu" />
+	<translation encoding="ISO8859-1" cldr="EURO_SIGN" string="Eu" />
+	<translation encoding="ISO8859-2" cldr="EURO_SIGN" string="Eu" />
+	<translation encoding="ISO8859-4" cldr="EURO_SIGN" string="Eu" />
+	<translation encoding="ISO8859-13" cldr="EURO_SIGN" string="Eu" />
 
 	<!-- Minus and dashes -->
 	<translation encoding="ISO8859-1 ISO8859-2 ISO8859-4 ISO8859-13 ISO8859-15"
-	    cldr="MINUS SIGN" unicode="HYPHEN-MINUS" />
+	    cldr="MINUS_SIGN" unicode="HYPHEN-MINUS" />
 	<translation encoding="ISO8859-2"
-	    cldr="EN DASH" unicode="HYPHEN-MINUS" />
+	    cldr="EN_DASH" unicode="HYPHEN-MINUS" />
 
 	<!-- Got these from http://www.decodeunicode.org/en/u+0400.
 	     Where possible use the international or ISO translation!
 	-->
 	<translation encoding="ISO8859-2" ucc="0408"
-	    cldr="CYRILLIC CAPITAL LETTER JE"
-	    unicode="LATIN CAPITAL LETTER J" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_JE"
+	    unicode="LATIN_CAPITAL_LETTER_J" />
 	<translation encoding="ISO8859-2" ucc="0458"
-	    cldr="CYRILLIC SMALL LETTER JE" unicode="LATIN SMALL LETTER J" />
+	    cldr="CYRILLIC_SMALL_LETTER_JE" unicode="LATIN_SMALL_LETTER_J" />
 	<translation encoding="ISO8859-2" ucc="0409"
-	    cldr="CYRILLIC CAPITAL LETTER LJE" string="lj" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_LJE" string="lj" />
 	<translation encoding="ISO8859-2" ucc="0459"
-	    cldr="CYRILLIC SMALL LETTER LJE" string="lj" />
+	    cldr="CYRILLIC_SMALL_LETTER_LJE" string="lj" />
 	<translation encoding="ISO8859-2" ucc="0410"
-	    cldr="CYRILLIC CAPITAL LETTER A" unicode="LATIN CAPITAL LETTER A" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_A" unicode="LATIN_CAPITAL_LETTER_A" />
 	<translation encoding="ISO8859-2" ucc="0430"
-	    cldr="CYRILLIC SMALL LETTER A" unicode="LATIN SMALL LETTER A" />
+	    cldr="CYRILLIC_SMALL_LETTER_A" unicode="LATIN_SMALL_LETTER_A" />
 	<translation encoding="ISO8859-2" ucc="0411"
-	    cldr="CYRILLIC CAPITAL LETTER BE"
-	    unicode="LATIN CAPITAL LETTER B" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_BE"
+	    unicode="LATIN_CAPITAL_LETTER_B" />
 	<translation encoding="ISO8859-2" ucc="0431"
-	    cldr="CYRILLIC SMALL LETTER BE" unicode="LATIN SMALL LETTER B" />
+	    cldr="CYRILLIC_SMALL_LETTER_BE" unicode="LATIN_SMALL_LETTER_B" />
 	<translation encoding="ISO8859-2" ucc="0412"
-	    cldr="CYRILLIC CAPITAL LETTER VE"
-	    unicode="LATIN CAPITAL LETTER B" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_VE"
+	    unicode="LATIN_CAPITAL_LETTER_B" />
 	<translation encoding="ISO8859-2" ucc="0432"
-	    cldr="CYRILLIC SMALL LETTER VE" unicode="LATIN SMALL LETTER B" />
+	    cldr="CYRILLIC_SMALL_LETTER_VE" unicode="LATIN_SMALL_LETTER_B" />
 	<translation encoding="ISO8859-2" ucc="0413"
-	    cldr="CYRILLIC CAPITAL LETTER GHE"
-	    unicode="LATIN CAPITAL LETTER G" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_GHE"
+	    unicode="LATIN_CAPITAL_LETTER_G" />
 	<translation encoding="ISO8859-2" ucc="0433"
-	    cldr="CYRILLIC SMALL LETTER GHE" unicode="LATIN SMALL LETTER G" />
+	    cldr="CYRILLIC_SMALL_LETTER_GHE" unicode="LATIN_SMALL_LETTER_G" />
 	<translation encoding="ISO8859-2" ucc="0414"
-	    cldr="CYRILLIC CAPITAL LETTER DE" string="D" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_DE" string="D" />
 	<translation encoding="ISO8859-2" ucc="0434"
-	    cldr="CYRILLIC SMALL LETTER DE" string="d" />
+	    cldr="CYRILLIC_SMALL_LETTER_DE" string="d" />
 	<translation encoding="ISO8859-2" ucc="0415"
-	    cldr="CYRILLIC CAPITAL LETTER IE"
-	    unicode="LATIN CAPITAL LETTER E" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_IE"
+	    unicode="LATIN_CAPITAL_LETTER_E" />
 	<translation encoding="ISO8859-2" ucc="0435"
-	    cldr="CYRILLIC SMALL LETTER IE" unicode="LATIN SMALL LETTER E" />
+	    cldr="CYRILLIC_SMALL_LETTER_IE" unicode="LATIN_SMALL_LETTER_E" />
 	<translation encoding="ISO8859-2" ucc="0416"
-	    cldr="CYRILLIC CAPITAL LETTER ZHE" string="ZH" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_ZHE" string="ZH" />
 	<translation encoding="ISO8859-2" ucc="0436"
-	    cldr="CYRILLIC SMALL LETTER ZHE" string="zh" />
+	    cldr="CYRILLIC_SMALL_LETTER_ZHE" string="zh" />
 	<translation encoding="ISO8859-2" ucc="0417"
-	    cldr="CYRILLIC CAPITAL LETTER ZE" string="z" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_ZE" string="z" />
 	<translation encoding="ISO8859-2" ucc="0437"
-	    cldr="CYRILLIC SMALL LETTER ZE" string="z" />
+	    cldr="CYRILLIC_SMALL_LETTER_ZE" string="z" />
 	<translation encoding="ISO8859-2" ucc="0418"
-	    cldr="CYRILLIC CAPITAL LETTER I" unicode="LATIN CAPITAL LETTER J" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_I" unicode="LATIN_CAPITAL_LETTER_J" />
 	<translation encoding="ISO8859-2" ucc="0438"
-	    cldr="CYRILLIC SMALL LETTER I" unicode="LATIN CAPITAL LETTER J" />
+	    cldr="CYRILLIC_SMALL_LETTER_I" unicode="LATIN_CAPITAL_LETTER_J" />
 	<translation encoding="ISO8859-2" ucc="0419"
-	    cldr="CYRILLIC CAPITAL LETTER I" unicode="LATIN SMALL LETTER J" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_I" unicode="LATIN_SMALL_LETTER_J" />
 	<translation encoding="ISO8859-2" ucc="0439"
-	    cldr="CYRILLIC SMALL LETTER I" unicode="LATIN SMALL LETTER J" />
+	    cldr="CYRILLIC_SMALL_LETTER_I" unicode="LATIN_SMALL_LETTER_J" />
 	<translation encoding="ISO8859-2" ucc="041A"
-	    cldr="CYRILLIC CAPITAL LETTER KA"
-	    unicode="LATIN CAPITAL LETTER K" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_KA"
+	    unicode="LATIN_CAPITAL_LETTER_K" />
 	<translation encoding="ISO8859-2" ucc="043A"
-	    cldr="CYRILLIC SMALL LETTER KA" unicode="LATIN SMALL LETTER K" />
+	    cldr="CYRILLIC_SMALL_LETTER_KA" unicode="LATIN_SMALL_LETTER_K" />
 	<translation encoding="ISO8859-2" ucc="041B"
-	    cldr="CYRILLIC CAPITAL LETTER EL"
-	    unicode="LATIN CAPITAL LETTER L" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_EL"
+	    unicode="LATIN_CAPITAL_LETTER_L" />
 	<translation encoding="ISO8859-2" ucc="043B"
-	    cldr="CYRILLIC SMALL LETTER EL" unicode="LATIN SMALL LETTER L" />
+	    cldr="CYRILLIC_SMALL_LETTER_EL" unicode="LATIN_SMALL_LETTER_L" />
 	<translation encoding="ISO8859-2" ucc="041C"
-	    cldr="CYRILLIC CAPITAL LETTER EM"
-	    unicode="LATIN CAPITAL LETTER M" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_EM"
+	    unicode="LATIN_CAPITAL_LETTER_M" />
 	<translation encoding="ISO8859-2" ucc="043C"
-	    cldr="CYRILLIC SMALL LETTER EM" unicode="LATIN SMALL LETTER M" />
+	    cldr="CYRILLIC_SMALL_LETTER_EM" unicode="LATIN_SMALL_LETTER_M" />
 	<translation encoding="ISO8859-2" ucc="041D"
-	    cldr="CYRILLIC CAPITAL LETTER EN"
-	    unicode="LATIN CAPITAL LETTER H" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_EN"
+	    unicode="LATIN_CAPITAL_LETTER_H" />
 	<translation encoding="ISO8859-2" ucc="043D"
-	    cldr="CYRILLIC SMALL LETTER EN" unicode="LATIN SMALL LETTER H" />
+	    cldr="CYRILLIC_SMALL_LETTER_EN" unicode="LATIN_SMALL_LETTER_H" />
 	<translation encoding="ISO8859-2" ucc="041E"
-	    cldr="CYRILLIC CAPITAL LETTER O" unicode="LATIN CAPITAL LETTER O" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_O" unicode="LATIN_CAPITAL_LETTER_O" />
 	<translation encoding="ISO8859-2" ucc="043E"
-	    cldr="CYRILLIC SMALL LETTER O" unicode="LATIN SMALL LETTER O" />
+	    cldr="CYRILLIC_SMALL_LETTER_O" unicode="LATIN_SMALL_LETTER_O" />
 	<translation encoding="ISO8859-2" ucc="041F"
-	    cldr="CYRILLIC CAPITAL LETTER PE"
-	    unicode="LATIN CAPITAL LETTER P" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_PE"
+	    unicode="LATIN_CAPITAL_LETTER_P" />
 	<translation encoding="ISO8859-2" ucc="043F"
-	    cldr="CYRILLIC SMALL LETTER PE" unicode="LATIN SMALL LETTER P" />
+	    cldr="CYRILLIC_SMALL_LETTER_PE" unicode="LATIN_SMALL_LETTER_P" />
 	<translation encoding="ISO8859-2" ucc="0420"
-	    cldr="CYRILLIC CAPITAL LETTER ER"
-	    unicode="LATIN CAPITAL LETTER R" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_ER"
+	    unicode="LATIN_CAPITAL_LETTER_R" />
 	<translation encoding="ISO8859-2" ucc="0440"
-	    cldr="CYRILLIC SMALL LETTER ER" unicode="LATIN SMALL LETTER R" />
+	    cldr="CYRILLIC_SMALL_LETTER_ER" unicode="LATIN_SMALL_LETTER_R" />
 	<translation encoding="ISO8859-2" ucc="0421"
-	    cldr="CYRILLIC CAPITAL LETTER ES"
-	    unicode="LATIN CAPITAL LETTER C" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_ES"
+	    unicode="LATIN_CAPITAL_LETTER_C" />
 	<translation encoding="ISO8859-2" ucc="0441"
-	    cldr="CYRILLIC SMALL LETTER ES" unicode="LATIN SMALL LETTER C" />
+	    cldr="CYRILLIC_SMALL_LETTER_ES" unicode="LATIN_SMALL_LETTER_C" />
 	<translation encoding="ISO8859-2" ucc="0422"
-	    cldr="CYRILLIC CAPITAL LETTER TE"
-	    unicode="LATIN CAPITAL LETTER T" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_TE"
+	    unicode="LATIN_CAPITAL_LETTER_T" />
 	<translation encoding="ISO8859-2" ucc="0442"
-	    cldr="CYRILLIC SMALL LETTER TE" unicode="LATIN SMALL LETTER T" />
+	    cldr="CYRILLIC_SMALL_LETTER_TE" unicode="LATIN_SMALL_LETTER_T" />
 	<translation encoding="ISO8859-2" ucc="0423"
-	    cldr="CYRILLIC CAPITAL LETTER U" unicode="LATIN CAPITAL LETTER U" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_U" unicode="LATIN_CAPITAL_LETTER_U" />
 	<translation encoding="ISO8859-2" ucc="0443"
-	    cldr="CYRILLIC SMALL LETTER U" unicode="LATIN SMALL LETTER U" />
+	    cldr="CYRILLIC_SMALL_LETTER_U" unicode="LATIN_SMALL_LETTER_U" />
 	<translation encoding="ISO8859-2" ucc="0424"
-	    cldr="CYRILLIC CAPITAL LETTER EF"
-	    unicode="LATIN CAPITAL LETTER F" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_EF"
+	    unicode="LATIN_CAPITAL_LETTER_F" />
 	<translation encoding="ISO8859-2" ucc="0444"
-	    cldr="CYRILLIC SMALL LETTER EF" unicode="LATIN SMALL LETTER F" />
+	    cldr="CYRILLIC_SMALL_LETTER_EF" unicode="LATIN_SMALL_LETTER_F" />
 	<translation encoding="ISO8859-2" ucc="0425"
-	    cldr="CYRILLIC CAPITAL LETTER HA"
-	    unicode="LATIN CAPITAL LETTER H" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_HA"
+	    unicode="LATIN_CAPITAL_LETTER_H" />
 	<translation encoding="ISO8859-2" ucc="0445"
-	    cldr="CYRILLIC SMALL LETTER HA" unicode="LATIN SMALL LETTER H" />
+	    cldr="CYRILLIC_SMALL_LETTER_HA" unicode="LATIN_SMALL_LETTER_H" />
 	<translation encoding="ISO8859-2" ucc="0426"
-	    cldr="CYRILLIC CAPITAL LETTER TSE"
-	    unicode="LATIN CAPITAL LETTER C" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_TSE"
+	    unicode="LATIN_CAPITAL_LETTER_C" />
 	<translation encoding="ISO8859-2" ucc="0446"
-	    cldr="CYRILLIC SMALL LETTER TSE" unicode="LATIN SMALL LETTER C" />
+	    cldr="CYRILLIC_SMALL_LETTER_TSE" unicode="LATIN_SMALL_LETTER_C" />
 	<translation encoding="ISO8859-2" ucc="0427"
-	    cldr="CYRILLIC CAPITAL LETTER CHE"
-	    unicode="LATIN CAPITAL LETTER C WITH CARON" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_CHE"
+	    unicode="LATIN_CAPITAL_LETTER_C_WITH_CARON" />
 	<translation encoding="ISO8859-2" ucc="0447"
-	    cldr="CYRILLIC SMALL LETTER CHE"
-	    unicode="LATIN SMALL LETTER C WITH CARON" />
+	    cldr="CYRILLIC_SMALL_LETTER_CHE"
+	    unicode="LATIN_SMALL_LETTER_C_WITH_CARON" />
 	<translation encoding="ISO8859-2" ucc="0428"
-	    cldr="CYRILLIC CAPITAL LETTER SHA"
-	    unicode="LATIN CAPITAL LETTER S WITH CARON" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_SHA"
+	    unicode="LATIN_CAPITAL_LETTER_S_WITH_CARON" />
 	<translation encoding="ISO8859-2" ucc="0448"
-	    cldr="CYRILLIC SMALL LETTER SHA"
-	    unicode="LATIN SMALL LETTER S WITH CARON" />
+	    cldr="CYRILLIC_SMALL_LETTER_SHA"
+	    unicode="LATIN_SMALL_LETTER_S_WITH_CARON" />
 	<translation encoding="ISO8859-2" ucc="0429"
-	    cldr="CYRILLIC CAPITAL LETTER SHCHA"
-	    unicode="LATIN CAPITAL LETTER S WITH CIRCUMFLEX" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_SHCHA"
+	    unicode="LATIN_CAPITAL_LETTER_S_WITH_CIRCUMFLEX" />
 	<translation encoding="ISO8859-2" ucc="0449"
-	    cldr="CYRILLIC SMALL LETTER SHCHA"
-	    unicode="LATIN SMALL LETTER S WITH CIRCUMFLEX" />
+	    cldr="CYRILLIC_SMALL_LETTER_SHCHA"
+	    unicode="LATIN_SMALL_LETTER_S_WITH_CIRCUMFLEX" />
 	<translation encoding="ISO8859-2" ucc="042A"
-	    cldr="?CYRILLIC CAPITAL LETTER HARD SIGN" unicode="?" />
+	    cldr="?CYRILLIC_CAPITAL_LETTER_HARD_SIGN" unicode="?" />
 	<translation encoding="ISO8859-2" ucc="044A"
-	    cldr="?CYRILLIC SMALL LETTER HARD SIGN" unicode="?" />
+	    cldr="?CYRILLIC_SMALL_LETTER_HARD_SIGN" unicode="?" />
 	<translation encoding="ISO8859-2" ucc="042B"
-	    cldr="?CYRILLIC CAPITAL LETTER YERU" unicode="?" />
+	    cldr="?CYRILLIC_CAPITAL_LETTER_YERU" unicode="?" />
 	<translation encoding="ISO8859-2" ucc="044B"
-	    cldr="?CYRILLIC SMALL LETTER YERU" unicode="?" />
+	    cldr="?CYRILLIC_SMALL_LETTER_YERU" unicode="?" />
 	<translation encoding="ISO8859-2" ucc="042C"
-	    cldr="?CYRILLIC CAPITAL LETTER SOFT SIGN" unicode="?" />
+	    cldr="?CYRILLIC_CAPITAL_LETTER_SOFT_SIGN" unicode="?" />
 	<translation encoding="ISO8859-2" ucc="044C"
-	    cldr="?CYRILLIC SMALL LETTER SOFT SIGN" unicode="?" />
+	    cldr="?CYRILLIC_SMALL_LETTER_SOFT_SIGN" unicode="?" />
 	<translation encoding="ISO8859-2" ucc="042D"
-	    cldr="CYRILLIC CAPITAL LETTER E"
-	    unicode="LATIN CAPITAL LETTER E WITH GRAVE" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_E"
+	    unicode="LATIN_CAPITAL_LETTER_E_WITH_GRAVE" />
 	<translation encoding="ISO8859-2" ucc="044D"
-	    cldr="CYRILLIC SMALL LETTER E"
-	    unicode="LATIN SMALL LETTER E WITH GRAVE" />
+	    cldr="CYRILLIC_SMALL_LETTER_E"
+	    unicode="LATIN_SMALL_LETTER_E_WITH_GRAVE" />
 	<translation encoding="ISO8859-2" ucc="042E"
-	    cldr="?CYRILLIC CAPITAL LETTER YU" unicode="?" />
+	    cldr="?CYRILLIC_CAPITAL_LETTER_YU" unicode="?" />
 	<translation encoding="ISO8859-2" ucc="044E"
-	    cldr="?CYRILLIC SMALL LETTER YU" unicode="?" />
+	    cldr="?CYRILLIC_SMALL_LETTER_YU" unicode="?" />
 	<translation encoding="ISO8859-2" ucc="042F"
-	    cldr="CYRILLIC CAPITAL LETTER YA"
-	    unicode="LATIN CAPITAL LETTER A WITH CIRCUMFLEX" />
+	    cldr="CYRILLIC_CAPITAL_LETTER_YA"
+	    unicode="LATIN_CAPITAL_LETTER_A_WITH_CIRCUMFLEX" />
 	<translation encoding="ISO8859-2" ucc="044F"
-	    cldr="CYRILLIC SMALL LETTER YA"
-	    unicode="LATIN SMALL LETTER A WITH CIRCUMFLEX" />
+	    cldr="CYRILLIC_SMALL_LETTER_YA"
+	    unicode="LATIN_SMALL_LETTER_A_WITH_CIRCUMFLEX" />
 
 	<translation encoding="ISO8859-2"
-	    cldr="LATIN SMALL LETTER T WITH COMMA BELOW"
-	    unicode="LATIN SMALL LETTER T" />
+	    cldr="LATIN_SMALL_LETTER_T_WITH_COMMA_BELOW"
+	    unicode="LATIN_SMALL_LETTER_T" />
 
 	<translation encoding="ISO8859-5"
-	    cldr="MODIFIER LETTER APOSTROPHE" unicode="APOSTROPHE" />
+	    cldr="MODIFIER_LETTER_APOSTROPHE" unicode="APOSTROPHE" />
 	<translation encoding="ISO8859-5"
-	    cldr="LATIN SMALL LETTER C WITH CARON"
-	    unicode="LATIN SMALL LETTER C" />
+	    cldr="LATIN_SMALL_LETTER_C_WITH_CARON"
+	    unicode="LATIN_SMALL_LETTER_C" />
 
 	<translation encoding="KOI8-U"
-	    cldr="MODIFIER LETTER APOSTROPHE" unicode="APOSTROPHE" />
+	    cldr="MODIFIER_LETTER_APOSTROPHE" unicode="APOSTROPHE" />
 
 	<translation encoding="CP1251"
-	    cldr="MODIFIER LETTER APOSTROPHE" unicode="APOSTROPHE" />
+	    cldr="MODIFIER_LETTER_APOSTROPHE" unicode="APOSTROPHE" />
 
 	<!-- Copied from the original FreeBSD src/share/monetdef -->
-	<translation encoding="CP1251" cldr="HRYVNIA SIGN" hex="E3F0ED" />
-	<translation encoding="ISO8859-5" cldr="HRYVNIA SIGN" hex="D3E0DD" />
-	<translation encoding="KOI8-U" cldr="HRYVNIA SIGN" hex="C7D2CE" />
-	<translation encoding="CP866" cldr="RUBLE SIGN" hex="E0E3A1" />
-	<translation encoding="ISO8859-5" cldr="RUBLE SIGN" hex="E0E3D1" />
-	<translation encoding="CP1251" cldr="RUBLE SIGN" hex="E0E3D1" />
-	<translation encoding="KOI8-R" cldr="RUBLE SIGN" hex="D2D5C2" />
+	<translation encoding="CP1251" cldr="HRYVNIA_SIGN" hex="E3F0ED" />
+	<translation encoding="ISO8859-5" cldr="HRYVNIA_SIGN" hex="D3E0DD" />
+	<translation encoding="KOI8-U" cldr="HRYVNIA_SIGN" hex="C7D2CE" />
+	<translation encoding="CP866" cldr="RUBLE_SIGN" hex="E0E3A1" />
+	<translation encoding="ISO8859-5" cldr="RUBLE_SIGN" hex="E0E3D1" />
+	<translation encoding="CP1251" cldr="RUBLE_SIGN" hex="E0E3D1" />
+	<translation encoding="KOI8-R" cldr="RUBLE_SIGN" hex="D2D5C2" />
 
 	<!-- These don't have a special Kow sign so just use KRW for it -->
-	<translation encoding="CP949" cldr="WON SIGN" hex="5C" />
-	<translation encoding="eucKR" cldr="WON SIGN" hex="5C" />
+	<translation encoding="CP949" cldr="WON_SIGN" hex="5C" />
+	<translation encoding="eucKR" cldr="WON_SIGN" hex="5C" />
 
 	<!-- Asian characters -->
 	<translation encoding="GB2312 eucCN" cldr="C"
-	    unicode="FULLWIDTH LATIN CAPITAL LETTER C" />
+	    unicode="FULLWIDTH_LATIN_CAPITAL_LETTER_C" />
 	<translation encoding="Big5" cldr="D"
-	    unicode="FULLWIDTH LATIN CAPITAL LETTER D" />
+	    unicode="FULLWIDTH_LATIN_CAPITAL_LETTER_D" />
 	<translation encoding="GB2312 eucCN Big5" cldr="N"
-	    unicode="FULLWIDTH LATIN CAPITAL LETTER N" />
+	    unicode="FULLWIDTH_LATIN_CAPITAL_LETTER_N" />
 	<translation encoding="Big5" cldr="T"
-	    unicode="FULLWIDTH LATIN CAPITAL LETTER T" />
+	    unicode="FULLWIDTH_LATIN_CAPITAL_LETTER_T" />
 	<translation encoding="Big5" cldr="W"
-	    unicode="FULLWIDTH LATIN CAPITAL LETTER W" />
+	    unicode="FULLWIDTH_LATIN_CAPITAL_LETTER_W" />
 	<translation encoding="GB2312 eucCN" cldr="Y"
-	    unicode="FULLWIDTH LATIN CAPITAL LETTER Y" />
+	    unicode="FULLWIDTH_LATIN_CAPITAL_LETTER_Y" />
 	<translation encoding="GB2312 Big5 eucCN" cldr="one"
-	    unicode="FULLWIDTH DIGIT ONE" />
+	    unicode="FULLWIDTH_DIGIT_ONE" />
 	<translation encoding="GB2312 Big5 eucCN" cldr="two"
-	    unicode="FULLWIDTH DIGIT TWO" />
+	    unicode="FULLWIDTH_DIGIT_TWO" />
 	<translation encoding="GB2312 Big5 eucCN" cldr="three"
-	    unicode="FULLWIDTH DIGIT THREE" />
+	    unicode="FULLWIDTH_DIGIT_THREE" />
 	<translation encoding="GB2312 Big5 eucCN" cldr="four"
-	    unicode="FULLWIDTH DIGIT FOUR" />
+	    unicode="FULLWIDTH_DIGIT_FOUR" />
 	<translation encoding="GB2312 Big5 eucCN" cldr="five"
-	    unicode="FULLWIDTH DIGIT FIVE" />
+	    unicode="FULLWIDTH_DIGIT_FIVE" />
 	<translation encoding="GB2312 Big5 eucCN" cldr="six"
-	    unicode="FULLWIDTH DIGIT SIX" />
+	    unicode="FULLWIDTH_DIGIT_SIX" />
 	<translation encoding="GB2312 Big5 eucCN" cldr="seven"
-	    unicode="FULLWIDTH DIGIT SEVEN" />
+	    unicode="FULLWIDTH_DIGIT_SEVEN" />
 	<translation encoding="GB2312 Big5 eucCN" cldr="eight"
-	    unicode="FULLWIDTH DIGIT EIGHT" />
+	    unicode="FULLWIDTH_DIGIT_EIGHT" />
 	<translation encoding="GB2312 Big5 eucCN" cldr="nine"
-	    unicode="FULLWIDTH DIGIT NINE" />
+	    unicode="FULLWIDTH_DIGIT_NINE" />
 	<translation encoding="GB2312 Big5 eucCN" cldr="zero"
-	    unicode="FULLWIDTH DIGIT ZERO" />
+	    unicode="FULLWIDTH_DIGIT_ZERO" />
 	<translation encoding="GB2312 eucCN Big5" cldr="space"
-	    unicode="IDEOGRAPHIC SPACE" />
-	<translation encoding="GB2312 eucCN Big5" cldr="FULL STOP"
-	    unicode="FULLWIDTH FULL STOP" />
+	    unicode="IDEOGRAPHIC_SPACE" />
+	<translation encoding="GB2312 eucCN Big5" cldr="FULL_STOP"
+	    unicode="FULLWIDTH_FULL_STOP" />
 	<translation encoding="GB2312 eucCN Big5" cldr="SOLIDUS"
-	    unicode="FULLWIDTH SOLIDUS" />
+	    unicode="FULLWIDTH_SOLIDUS" />
 	<translation encoding="GB2312 eucCN Big5" cldr="COMMA"
-	    unicode="FULLWIDTH COMMA" />
+	    unicode="FULLWIDTH_COMMA" />
 	<translation encoding="GB2312 eucCN Big5" cldr="HYPHEN-MINUS"
-	    unicode="FULLWIDTH HYPHEN-MINUS" />
-	<translation encoding="Big5" cldr="DOLLAR SIGN"
-	    unicode="FULLWIDTH DOLLAR SIGN" />
+	    unicode="FULLWIDTH_HYPHEN-MINUS" />
+	<translation encoding="Big5" cldr="DOLLAR_SIGN"
+	    unicode="FULLWIDTH_DOLLAR_SIGN" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-4E00" ucc="4E00" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-4E00" ucc="4E00" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-4E03" ucc="4E03" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-4E03" ucc="4E03" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-4E09" ucc="4E09" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-4E09" ucc="4E09" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-4E0A" ucc="4E0A" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-4E0A" ucc="4E0A" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-4E0B" ucc="4E0B" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-4E0B" ucc="4E0B" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-4E0D" ucc="4E0D" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-4E0D" ucc="4E0D" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-4E5D" ucc="4E5D" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-4E5D" ucc="4E5D" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-4E8C" ucc="4E8C" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-4E8C" ucc="4E8C" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-4E94" ucc="4E94" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-4E94" ucc="4E94" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-516B" ucc="516B" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-516B" ucc="516B" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-516D" ucc="516D" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-516D" ucc="516D" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-5206" ucc="5206" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-5206" ucc="5206" />
 	<translation encoding="eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-524D" ucc="524D" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-524D" ucc="524D" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-5341" ucc="5341" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-5341" ucc="5341" />
 	<translation
 	    encoding="GB2312 GB18030 GBK Big5 eucCN eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-5348" ucc="5348" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-5348" ucc="5348" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-5426" ucc="5426" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-5426" ucc="5426" />
 	<translation encoding="GB2312 GB18030 GBK eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-5468" ucc="5468" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-5468" ucc="5468" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-56DB" ucc="56DB" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-56DB" ucc="56DB" />
 	<translation encoding="eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-571F" ucc="571F" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-571F" ucc="571F" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-5B9A" ucc="5B9A" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-5B9A" ucc="5B9A" />
 	<translation
 	    encoding="GB2312 GB18030 GBK Big5 eucCN eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-5E74" ucc="5E74" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-5E74" ucc="5E74" />
 	<translation encoding="eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-5F8C" ucc="5F8C" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-5F8C" ucc="5F8C" />
 	<translation
 	    encoding="GB2312 GB18030 GBK Big5 eucCN eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-65E5" ucc="65E5" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-65E5" ucc="65E5" />
 	<translation encoding="GB2312 GB18030 GBK eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-65F6" ucc="65F6" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-65F6" ucc="65F6" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-661F" ucc="661F" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-661F" ucc="661F" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-662F" ucc="662F" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-662F" ucc="662F" />
 	<translation encoding="Big5 "
-	    cldr="CJK UNIFIED IDEOGRAPH-6642" ucc="6642" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-6642" ucc="6642" />
 	<translation encoding="eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-66DC" ucc="66DC" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-66DC" ucc="66DC" />
 	<translation
 	    encoding="GB2312 GB18030 GBK Big5 eucCN eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-6708" ucc="6708" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-6708" ucc="6708" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-671F" ucc="671F" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-671F" ucc="671F" />
 	<translation encoding="eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-6728" ucc="6728" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-6728" ucc="6728" />
 	<translation encoding="eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-6C34" ucc="6C34" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-6C34" ucc="6C34" />
 	<translation encoding="eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-706B" ucc="706B" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-706B" ucc="706B" />
 	<translation encoding="GB2312 GB18030 GBK eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-786E" ucc="786E" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-786E" ucc="786E" />
 	<translation encoding="Big5 "
-	    cldr="CJK UNIFIED IDEOGRAPH-78BA" ucc="78BA" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-78BA" ucc="78BA" />
 	<translation encoding="GB2312 GB18030 GBK Big5 eucCN"
-	    cldr="CJK UNIFIED IDEOGRAPH-79D2" ucc="79D2" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-79D2" ucc="79D2" />
 	<translation encoding="Big5 "
-	    cldr="CJK UNIFIED IDEOGRAPH-9031" ucc="9031" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-9031" ucc="9031" />
 	<translation encoding="eucJP SJIS"
-	    cldr="CJK UNIFIED IDEOGRAPH-91D1" ucc="91D1" />
+	    cldr="CJK_UNIFIED_IDEOGRAPH-91D1" ucc="91D1" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE GEUM" ucc="AE08" />
+	    cldr="HANGUL_SYLLABLE_GEUM" ucc="AE08" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE NYEON" ucc="B144" />
+	    cldr="HANGUL_SYLLABLE_NYEON" ucc="B144" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE NI" ucc="B2C8" />
+	    cldr="HANGUL_SYLLABLE_NI" ucc="B2C8" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE MOG" ucc="BAA9" />
+	    cldr="HANGUL_SYLLABLE_MOG" ucc="BAA9" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE BUN" ucc="BD84" />
+	    cldr="HANGUL_SYLLABLE_BUN" ucc="BD84" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE SU" ucc="C218" />
+	    cldr="HANGUL_SYLLABLE_SU" ucc="C218" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE SI" ucc="C2DC" />
+	    cldr="HANGUL_SYLLABLE_SI" ucc="C2DC" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE A" ucc="C544" />
+	    cldr="HANGUL_SYLLABLE_A" ucc="C544" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE YE" ucc="C608" />
+	    cldr="HANGUL_SYLLABLE_YE" ucc="C608" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE O" ucc="C624" />
+	    cldr="HANGUL_SYLLABLE_O" ucc="C624" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE YO" ucc="C694" />
+	    cldr="HANGUL_SYLLABLE_YO" ucc="C694" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE WEOL" ucc="C6D4" />
+	    cldr="HANGUL_SYLLABLE_WEOL" ucc="C6D4" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE IL" ucc="C77C" />
+	    cldr="HANGUL_SYLLABLE_IL" ucc="C77C" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE JEON" ucc="C804" />
+	    cldr="HANGUL_SYLLABLE_JEON" ucc="C804" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE CO" ucc="CD08" />
+	    cldr="HANGUL_SYLLABLE_CO" ucc="CD08" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE TO" ucc="D1A0" />
+	    cldr="HANGUL_SYLLABLE_TO" ucc="D1A0" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE HWA" ucc="D654" />
+	    cldr="HANGUL_SYLLABLE_HWA" ucc="D654" />
 	<translation encoding="eucKR"
-	    cldr="HANGUL SYLLABLE HU" ucc="D6C4" />
+	    cldr="HANGUL_SYLLABLE_HU" ucc="D6C4" />
 
 	<translation encoding="ARMSCII-8"
-	    cldr="ONE DOT LEADER" unicode="FULL STOP" />
+	    cldr="ONE_DOT_LEADER" unicode="FULL_STOP" />
 
-	<translation encoding="US-ASCII" cldr="POUND SIGN" string="GBP" />
+	<translation encoding="US-ASCII" cldr="POUND_SIGN" string="GBP" />
 	<translation encoding="US-ASCII"
-	    cldr="NO-BREAK SPACE" unicode="SPACE" />
+	    cldr="NO-BREAK_SPACE" unicode="SPACE" />
 
 	<translation encoding="ISO8859-1 ISO8859-15"
-	    cldr="NARROW NO-BREAK SPACE" unicode="NO-BREAK SPACE" />
+	    cldr="NARROW_NO-BREAK_SPACE" unicode="NO-BREAK_SPACE" />
 
 	<!-- punctuation and currency -->
 	<translation encoding="ISO8859-1 ISO8859-15"
-	    cldr="RIGHT SINGLE QUOTATION MARK" unicode="APOSTROPHE" />
+	    cldr="RIGHT_SINGLE_QUOTATION_MARK" unicode="APOSTROPHE" />
 
-	<translation encoding="ISCII-DEV" cldr="INDIAN RUPEE SIGN" hex="FC" />
-	<translation encoding="ISO8859-1" cldr="PESO SIGN" hex="A4" />
-	<translation encoding="ISO8859-1" cldr="COLON SIGN" hex="A4" />
-	<translation encoding="ARMSCII-8" cldr="ARMENIAN DRAM SIGN"
+	<translation encoding="ISCII-DEV" cldr="INDIAN_RUPEE_SIGN" hex="FC" />
+	<translation encoding="ISO8859-1" cldr="PESO_SIGN" hex="A4" />
+	<translation encoding="ISO8859-1" cldr="COLON_SIGN" hex="A4" />
+	<translation encoding="ARMSCII-8" cldr="ARMENIAN_DRAM_SIGN"
 	    hex="B9F12E" />
-	<translation encoding="ISO8859-9" cldr="TURKISH LIRA SIGN"
+	<translation encoding="ISO8859-9" cldr="TURKISH_LIRA_SIGN"
 	    string="TL" />
 
 </translations>
 
 <c_fmt>
 	<!-- The format of the output of date(1) and ctime(3) is different:
 	-->
 </c_fmt>
 
 <alternativemonths>
 	<!-- Months which are different in dates ("21 december 1980") and in
 		sentence usage ("We will do that in December.").
 		The CLDR doesn't understand them, therefore we have
 		to define them inline. Fortunately it doesn't happen
 		often...
 	  -->
 	<language name="be" countries="BY">
 		<![CDATA[
 		"<CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER ZE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER YU><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER YERU>";
 		"<CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER KA><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I><CYRILLIC SMALL LETTER KA>";
 		"<CYRILLIC SMALL LETTER KA><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I><CYRILLIC SMALL LETTER KA>";
 		"<CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER CHE><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I><CYRILLIC SMALL LETTER PE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER ZHE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER KA><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER YERU><CYRILLIC SMALL LETTER CHE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I><CYRILLIC SMALL LETTER KA>";
 		"<CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER PE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER DE>";
 		"<CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER ZHE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>"
 		]]>
 	</language>
 	<language name="cs" countries="CZ">
 		<![CDATA[
 		"<l><e><d><e><n>";
 		"<LATIN SMALL LETTER U WITH ACUTE><n><o><r>";
 		"<b><LATIN SMALL LETTER R WITH CARON><e><z><e><n>";
 		"<d><u><b><e><n>";
 		"<k><v><LATIN SMALL LETTER E WITH CARON><t><e><n>";
 		"<LATIN SMALL LETTER C WITH CARON><e><r><v><e><n>";
 		"<LATIN SMALL LETTER C WITH CARON><e><r><v><e><n><e><c>";
 		"<s><r><p><e><n>";
 		"<z><LATIN SMALL LETTER A WITH ACUTE><LATIN SMALL LETTER R WITH CARON><LATIN SMALL LETTER I WITH ACUTE>";
 		"<LATIN SMALL LETTER R WITH CARON><LATIN SMALL LETTER I WITH ACUTE><j><e><n>";
 		"<l><i><s><t><o><p><a><d>";
 		"<p><r><o><s><i><n><e><c>"
 		]]>
 	</language>
 	<language name="el" countries="GR">
 		<![CDATA[
 		"<GREEK CAPITAL LETTER IOTA><GREEK SMALL LETTER ALPHA><GREEK SMALL LETTER NU><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER UPSILON><GREEK SMALL LETTER ALPHA WITH TONOS><GREEK SMALL LETTER RHO><GREEK SMALL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER PHI><GREEK SMALL LETTER EPSILON><GREEK SMALL LETTER BETA><GREEK SMALL LETTER RHO><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER UPSILON><GREEK SMALL LETTER ALPHA WITH TONOS><GREEK SMALL LETTER RHO><GREEK SMALL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER MU><GREEK SMALL LETTER ALPHA WITH TONOS><GREEK SMALL LETTER RHO><GREEK SMALL LETTER TAU><GREEK SMALL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER ALPHA><GREEK SMALL LETTER PI><GREEK SMALL LETTER RHO><GREEK SMALL LETTER IOTA WITH TONOS><GREEK SMALL LETTER LAMDA><GREEK SMALL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER MU><GREEK SMALL LETTER ALPHA WITH TONOS><GREEK SMALL LETTER IOTA WITH DIALYTIKA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER UPSILON WITH TONOS><GREEK SMALL LETTER NU><GREEK SMALL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER UPSILON WITH TONOS><GREEK SMALL LETTER LAMDA><GREEK SMALL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER ALPHA><GREEK SMALL LETTER UPSILON WITH TONOS><GREEK SMALL LETTER GAMMA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER UPSILON><GREEK SMALL LETTER SIGMA><GREEK SMALL LETTER TAU><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER SIGMA><GREEK SMALL LETTER EPSILON><GREEK SMALL LETTER PI><GREEK SMALL LETTER TAU><GREEK SMALL LETTER EPSILON WITH TONOS><GREEK SMALL LETTER MU><GREEK SMALL LETTER BETA><GREEK SMALL LETTER RHO><GREEK SMALL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER OMICRON><GREEK SMALL LETTER KAPPA><GREEK SMALL LETTER TAU><GREEK SMALL LETTER OMEGA WITH TONOS><GREEK SMALL LETTER BETA><GREEK SMALL LETTER RHO><GREEK SMALL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER NU><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER EPSILON WITH TONOS><GREEK SMALL LETTER MU><GREEK SMALL LETTER BETA><GREEK SMALL LETTER RHO><GREEK SMALL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>";
 		"<GREEK CAPITAL LETTER DELTA><GREEK SMALL LETTER EPSILON><GREEK SMALL LETTER KAPPA><GREEK SMALL LETTER EPSILON WITH TONOS><GREEK SMALL LETTER MU><GREEK SMALL LETTER BETA><GREEK SMALL LETTER RHO><GREEK SMALL LETTER IOTA><GREEK SMALL LETTER OMICRON><GREEK SMALL LETTER FINAL SIGMA>"
 		]]>
 	</language>
 	<language name="kk" countries="KZ">
 		<![CDATA[
 		"<CYRILLIC SMALL LETTER KA WITH DESCENDER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER KA WITH DESCENDER><CYRILLIC SMALL LETTER PE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER EN>";
 		"<CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER YERU><CYRILLIC SMALL LETTER ZE>";
 		"<CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER SCHWA><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC SMALL LETTER EM><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER EM><CYRILLIC SMALL LETTER YERU><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC SMALL LETTER EM><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER YERU><CYRILLIC SMALL LETTER EM>";
 		"<CYRILLIC SMALL LETTER SHA><CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I><CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER IE>";
 		"<CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER EM><CYRILLIC SMALL LETTER YERU><CYRILLIC SMALL LETTER ZE>";
 		"<CYRILLIC SMALL LETTER KA WITH DESCENDER><CYRILLIC SMALL LETTER YERU><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER KA><CYRILLIC SMALL LETTER STRAIGHT U><CYRILLIC SMALL LETTER SHORT I><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER KA>";
 		"<CYRILLIC SMALL LETTER KA WITH DESCENDER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ZE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER EN>";
 		"<CYRILLIC SMALL LETTER KA WITH DESCENDER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER SHA><CYRILLIC SMALL LETTER A>";
 		"<CYRILLIC SMALL LETTER ZHE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER O><CYRILLIC SMALL LETTER KA WITH DESCENDER><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER EN>"
 		]]>
 	</language>
 	<language name="lt" countries="LT">
 		<![CDATA[
 		"<s><a><u><s><i><s>";
 		"<v><a><s><a><r><i><s>";
 		"<k><o><v><a><s>";
 		"<b><a><l><a><n><d><i><s>";
 		"<g><e><g><u><LATIN SMALL LETTER Z WITH CARON><LATIN SMALL LETTER E WITH DOT ABOVE>";
 		"<b><i><r><LATIN SMALL LETTER Z WITH CARON><e><l><i><s>";
 		"<l><i><e><p><a>";
 		"<r><u><g><p><j><LATIN SMALL LETTER U WITH MACRON><t><i><s>";
 		"<r><u><g><s><LATIN SMALL LETTER E WITH DOT ABOVE><j><i><s>";
 		"<s><p><a><l><i><s>";
 		"<l><a><p><k><r><i><t><i><s>";
 		"<g><r><u><o><d><i><s>"
 		]]>
 	</language>
 	<language name="mn" countries="MN">
 		<![CDATA[
 		"<CYRILLIC CAPITAL LETTER EN><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER STRAIGHT U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER HA><CYRILLIC SMALL LETTER O><CYRILLIC SMALL LETTER IO><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER GHE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER DE><CYRILLIC SMALL LETTER BARRED O><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER BARRED O><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER STRAIGHT U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER TE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER ZE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER DE><CYRILLIC SMALL LETTER O><CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER O><CYRILLIC SMALL LETTER O><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER EN><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER SHORT I><CYRILLIC SMALL LETTER EM><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER IE><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER STRAIGHT U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER A><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER A><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER EN><space><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER STRAIGHT U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER E><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>";
 		"<CYRILLIC CAPITAL LETTER A><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER EN><space><CYRILLIC SMALL LETTER HA><CYRILLIC SMALL LETTER O><CYRILLIC SMALL LETTER IO><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><space><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER>"
 		]]>
 	</language>
 	<language name="pl" countries="PL">
 		<![CDATA[
 		"<s><t><y><c><z><e><LATIN SMALL LETTER N WITH ACUTE>";
 		"<l><u><t><y>";
 		"<m><a><r><z><e><c>";
 		"<k><w><i><e><c><i><e><LATIN SMALL LETTER N WITH ACUTE>";
 		"<m><a><j>";
 		"<c><z><e><r><w><i><e><c>";
 		"<l><i><p><i><e><c>";
 		"<s><i><e><r><p><i><e><LATIN SMALL LETTER N WITH ACUTE>";
 		"<w><r><z><e><s><i><e><LATIN SMALL LETTER N WITH ACUTE>";
 		"<p><a><LATIN SMALL LETTER Z WITH ACUTE><d><z><i><e><r><n><i><k>";
 		"<l><i><s><t><o><p><a><d>";
 		"<g><r><u><d><z><i><e><LATIN SMALL LETTER N WITH ACUTE>"
 		]]>
 	</language>
 	<language name="ru" countries="RU">
 		<![CDATA[
 		"<CYRILLIC SMALL LETTER YA><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER EF><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER EM><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER TE>";
 		"<CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER PE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER EM><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER SHORT I>";
 		"<CYRILLIC SMALL LETTER I><CYRILLIC SMALL LETTER YU><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER I><CYRILLIC SMALL LETTER YU><CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER TE>";
 		"<CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER YA><CYRILLIC SMALL LETTER BE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER O><CYRILLIC SMALL LETTER KA><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER YA><CYRILLIC SMALL LETTER BE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER O><CYRILLIC SMALL LETTER YA><CYRILLIC SMALL LETTER BE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER KA><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER BE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER SOFT SIGN>"
 		]]>
 	</language>
 	<language name="uk" countries="UA">
 		<![CDATA[
 		"<CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I><CYRILLIC SMALL LETTER CHE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER YU><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER I><CYRILLIC SMALL LETTER SHORT I>";
 		"<CYRILLIC SMALL LETTER BE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER ZE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER KA><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER CHE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER I><CYRILLIC SMALL LETTER PE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER PE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER ZHE><CYRILLIC SMALL LETTER O><CYRILLIC SMALL LETTER VE><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>";
 		"<CYRILLIC SMALL LETTER EL><CYRILLIC SMALL LETTER I><CYRILLIC SMALL LETTER ES><CYRILLIC SMALL LETTER TE><CYRILLIC SMALL LETTER O><CYRILLIC SMALL LETTER PE><CYRILLIC SMALL LETTER A><CYRILLIC SMALL LETTER DE>";
 		"<CYRILLIC SMALL LETTER GHE><CYRILLIC SMALL LETTER ER><CYRILLIC SMALL LETTER U><CYRILLIC SMALL LETTER DE><CYRILLIC SMALL LETTER IE><CYRILLIC SMALL LETTER EN><CYRILLIC SMALL LETTER SOFT SIGN>"
 		]]>
 	</language>
 
 </alternativemonths>
 
 </data>
diff --git a/tools/tools/locale/tools/cldr2def.pl b/tools/tools/locale/tools/cldr2def.pl
index 8617ca81ca40..fd475db714a0 100755
--- a/tools/tools/locale/tools/cldr2def.pl
+++ b/tools/tools/locale/tools/cldr2def.pl
@@ -1,1068 +1,1132 @@
 #!/usr/local/bin/perl -wC
 
 # SPDX-License-Identifier: BSD-2-Clause-FreeBSD
 #
 # Copyright 2009 Edwin Groothuis <edwin@FreeBSD.org>
 # Copyright 2015 John Marino <draco@marino.st>
+# Copyright 2020 Hiroki Sato <hrs@FreeBSD.org>
 #
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions
 # are met:
 # 1. Redistributions of source code must retain the above copyright
 #    notice, this list of conditions and the following disclaimer.
 # 2. Redistributions in binary form must reproduce the above copyright
 #    notice, this list of conditions and the following disclaimer in the
 #    documentation and/or other materials provided with the distribution.
 #
 # THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
 # ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 # IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 # ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
 # FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 # DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 # OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 # HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 # LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 # OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 # SUCH DAMAGE.
 #
 # $FreeBSD$
 
 use strict;
 use File::Copy;
 use XML::Parser;
 use Tie::IxHash;
 use Text::Iconv;
 #use Data::Dumper;
 use Getopt::Long;
 use Digest::SHA qw(sha1_hex);
 require "charmaps.pm";
 
-
 if ($#ARGV < 2) {
 	print "Usage: $0 --unidir=<unidir> --etc=<etcdir> --type=<type>\n";
 	exit(1);
 }
 
 my $DEFENCODING = "UTF-8";
 
 my $UNIDIR = undef;
 my $ETCDIR = undef;
 my $TYPE = undef;
 
 my $CLDR_VERSION = undef;
 
 my $result = GetOptions (
 		"unidir=s"	=> \$UNIDIR,
 		"etc=s"		=> \$ETCDIR,
 		"type=s"	=> \$TYPE,
 	    );
 
 my %convertors = ();
 
 my %ucd = ();
 my %values = ();
 my %hashtable = ();
 my %languages = ();
 my %translations = ();
 my %encodings = ();
 my %alternativemonths = ();
 get_languages();
 
-my %utf8map = ();
-my %utf8aliases = ();
-get_unidata($UNIDIR);
-get_utf8map("$UNIDIR/posix/$DEFENCODING.cm");
+my %utfmap = ();
+$utfmap{'UTF-8'} = {};
+$utfmap{'UTF-32'} = {};
+get_utfmap("$UNIDIR/posix/$DEFENCODING.cm", $utfmap{'UTF-8'});
+get_utfmap("$UNIDIR/posix/UTF-32.cm", $utfmap{'UTF-32'});
 get_encodings("$ETCDIR/charmaps");
 
 my %keys = ();
 tie(%keys, "Tie::IxHash");
 tie(%hashtable, "Tie::IxHash");
 
 my %FILESNAMES = (
 	"monetdef"	=> "LC_MONETARY",
 	"timedef"	=> "LC_TIME",
 	"msgdef"	=> "LC_MESSAGES",
 	"numericdef"	=> "LC_NUMERIC",
 	"colldef"	=> "LC_COLLATE",
 	"ctypedef"	=> "LC_CTYPE"
 );
 
 my %callback = (
 	mdorder => \&callback_mdorder,
 	altmon => \&callback_altmon,
 	cformat => \&callback_cformat,
 	dformat => \&callback_dformat,
 	dtformat => \&callback_dtformat,
 	cbabmon => \&callback_abmon,
 	cbampm => \&callback_ampm,
 	data => undef,
 );
 
 my %DESC = (
 
 	# numericdef
 	"decimal_point"	=> "decimal_point",
 	"thousands_sep"	=> "thousands_sep",
 	"grouping"	=> "grouping",
 
 	# monetdef
 	"int_curr_symbol"	=> "int_curr_symbol (last character always " .
 				   "SPACE)",
 	"currency_symbol"	=> "currency_symbol",
 	"mon_decimal_point"	=> "mon_decimal_point",
 	"mon_thousands_sep"	=> "mon_thousands_sep",
 	"mon_grouping"		=> "mon_grouping",
 	"positive_sign"		=> "positive_sign",
 	"negative_sign"		=> "negative_sign",
 	"int_frac_digits"	=> "int_frac_digits",
 	"frac_digits"		=> "frac_digits",
 	"p_cs_precedes"		=> "p_cs_precedes",
 	"p_sep_by_space"	=> "p_sep_by_space",
 	"n_cs_precedes"		=> "n_cs_precedes",
 	"n_sep_by_space"	=> "n_sep_by_space",
 	"p_sign_posn"		=> "p_sign_posn",
 	"n_sign_posn"		=> "n_sign_posn",
 
 	# msgdef
 	"yesexpr"	=> "yesexpr",
 	"noexpr"	=> "noexpr",
 	"yesstr"	=> "yesstr",
 	"nostr"		=> "nostr",
 
 	# timedef
 	"abmon"		=> "Short month names",
 	"mon"		=> "Long month names (as in a date)",
 	"abday"		=> "Short weekday names",
 	"day"		=> "Long weekday names",
 	"t_fmt"		=> "X_fmt",
 	"d_fmt"		=> "x_fmt",
 	"c_fmt"		=> "c_fmt",
 	"am_pm"		=> "AM/PM",
 	"d_t_fmt"	=> "date_fmt",
 	"altmon"	=> "Long month names (without case ending)",
 	"md_order"	=> "md_order",
 	"t_fmt_ampm"	=> "ampm_fmt",
 );
 
 if ($TYPE eq "colldef") {
 	transform_collation();
 	make_makefile();
 }
 
 if ($TYPE eq "ctypedef") {
 	transform_ctypes();
 	make_makefile();
 }
 
 if ($TYPE eq "numericdef") {
 	%keys = (
 	    "decimal_point"	=> "s",
 	    "thousands_sep"	=> "s",
 	    "grouping"		=> "ai",
 	);
 	get_fields();
 	print_fields();
 	make_makefile();
 }
 
 if ($TYPE eq "monetdef") {
 	%keys = (
 	    "int_curr_symbol"	=> "s",
 	    "currency_symbol"	=> "s",
 	    "mon_decimal_point"	=> "s",
 	    "mon_thousands_sep"	=> "s",
 	    "mon_grouping"	=> "ai",
 	    "positive_sign"	=> "s",
 	    "negative_sign"	=> "s",
 	    "int_frac_digits"	=> "i",
 	    "frac_digits"	=> "i",
 	    "p_cs_precedes"	=> "i",
 	    "p_sep_by_space"	=> "i",
 	    "n_cs_precedes"	=> "i",
 	    "n_sep_by_space"	=> "i",
 	    "p_sign_posn"	=> "i",
 	    "n_sign_posn"	=> "i"
 	);
 	get_fields();
 	print_fields();
 	make_makefile();
 }
 
 if ($TYPE eq "msgdef") {
 	%keys = (
 	    "yesexpr"		=> "s",
 	    "noexpr"		=> "s",
 	    "yesstr"		=> "s",
 	    "nostr"		=> "s"
 	);
 	get_fields();
 	print_fields();
 	make_makefile();
 }
 
 if ($TYPE eq "timedef") {
 	%keys = (
 	    "abmon"		=> "<cbabmon<abmon<as",
 	    "mon"		=> "as",
 	    "abday"		=> "as",
 	    "day"		=> "as",
 	    "t_fmt"		=> "s",
 	    "d_fmt"		=> "<dformat<d_fmt<s",
 	    "c_fmt"		=> "<cformat<d_t_fmt<s",
 	    "am_pm"		=> "<cbampm<am_pm<as",
 	    "d_t_fmt"		=> "<dtformat<d_t_fmt<s",
 	    "altmon"		=> "<altmon<mon<as",
 	    "md_order"		=> "<mdorder<d_fmt<s",
 	    "t_fmt_ampm"	=> "s",
 	);
 	get_fields();
 	print_fields();
 	make_makefile();
 }
 
 sub callback_ampm {
 	my $s = shift;
 	my $nl = $callback{data}{l} . "_" . $callback{data}{c};
 	my $enc = $callback{data}{e};
 
 	if ($nl eq 'ru_RU') {
 		if ($enc eq 'UTF-8') {
 			$s = 'дп;пп';
 		} else {
 			my  $converter = Text::Iconv->new("utf-8", "$enc");
 			$s = $converter->convert("дп;пп");
 		}
 	}
 	return $s;
 }
 
 sub callback_cformat {
 	my $s = shift;
 	my $nl = $callback{data}{l} . "_" . $callback{data}{c};
 
 	if ($nl eq 'ko_KR') {
 		$s =~ s/(> )(%p)/$1%A $2/;
 	}
 	$s =~ s/\.,/\./;
 	$s =~ s/ %Z//;
 	$s =~ s/ %z//;
 	$s =~ s/^"%e\./%A %e/;
 	$s =~ s/^"(%B %e, )/"%A, $1/;
 	$s =~ s/^"(%e %B )/"%A $1/;
 	return $s;
 };
 
 sub callback_dformat {
 	my $s = shift;
 
 	$s =~ s/(%m(<SOLIDUS>|[-.]))%e/$1%d/;
 	$s =~ s/%e((<SOLIDUS>|[-.])%m)/%d$1/;
 	return $s;
 };
 
 sub callback_dtformat {
 	my $s = shift;
 	my $nl = $callback{data}{l} . "_" . $callback{data}{c};
 
 	if ($nl eq 'ja_JP') {
 		$s =~ s/(> )(%H)/$1%A $2/;
 	} elsif ($nl eq 'ko_KR' || $nl eq 'zh_CN' || $nl eq 'zh_TW') {
 		if ($nl ne 'ko_KR') {
 			$s =~ s/%m/%_m/;
 		}
 		$s =~ s/(> )(%p)/$1%A $2/;
 	}
 	$s =~ s/\.,/\./;
 	$s =~ s/^"%e\./%A %e/;
 	$s =~ s/^"(%B %e, )/"%A, $1/;
 	$s =~ s/^"(%e %B )/"%A $1/;
 	return $s;
 };
 
 sub callback_mdorder {
 	my $s = shift;
 	return undef if (!defined $s);
 	$s =~ s/[^dem]//g;
 	$s =~ s/e/d/g;
 	return $s;
 };
 
 sub callback_altmon {
 	# if the language/country is known in %alternative months then
 	# return that, otherwise repeat mon
 	my $s = shift;
 
 	if (defined $alternativemonths{$callback{data}{l}}{$callback{data}{c}}) {
 		my @altnames = split(";",$alternativemonths{$callback{data}{l}}{$callback{data}{c}});
 		my @cleaned;
 		foreach (@altnames)
 		{
 			$_ =~ s/^\s+//;
 			$_ =~ s/\s+$//;
 			push @cleaned, $_;
 		}
 		return join(";",@cleaned);
 	}
 
 	return $s;
 }
 
 sub callback_abmon {
 	# for specified CJK locales, pad result with a space to enable
 	# columns to line up (style established in FreeBSD in 2001)
 	my $s = shift;
 	my $nl = $callback{data}{l} . "_" . $callback{data}{c};
 
 	if ($nl eq 'ja_JP' || $nl eq 'ko_KR' || $nl eq 'zh_CN' ||
 	    $nl eq 'zh_HK' || $nl eq 'zh_TW') {
 		my @monthnames = split(";", $s);
 		my @cleaned;
 		foreach (@monthnames)
 		{
 			if ($_ =~ /^"<(two|three|four|five|six|seven|eight|nine)>/ ||
 			   ($_ =~ /^"<one>/ && $_ !~ /^"<one>(<zero>|<one>|<two>)/))
 			{
 				$_ =~ s/^"/"<space>/;
 			}
 			push @cleaned, $_;
 		}
 		return join(";",@cleaned);
 	}
 	return $s;
 }
 
 ############################
 
-sub get_unidata {
-	my $directory = shift;
-
-	open(FIN, "$directory/UnicodeData.txt")
-	    or die("Cannot open $directory/UnicodeData.txt");;
-	my @lines = <FIN>;
-	chomp(@lines);
-	close(FIN);
-
-	foreach my $l (@lines) {
-		my @a = split(/;/, $l);
-
-		$ucd{code2name}{"$a[0]"} = $a[1];	# Unicode name
-		$ucd{name2code}{"$a[1]"} = $a[0];	# Unicode code
-	}
-}
-
-sub get_utf8map {
-	my $file = shift;
+sub get_utfmap {
+	my ($file, $db) = @_;
 
 	open(FIN, $file);
 	my @lines = <FIN>;
 	close(FIN);
 	chomp(@lines);
 
 	my $prev_k = undef;
 	my $prev_v = "";
 	my $incharmap = 0;
 	foreach my $l (@lines) {
-		$l =~ s/\r//;
+		chomp($l);
 		next if ($l =~ /^\#/);
 		next if ($l eq "");
 
 		if ($l eq "CHARMAP") {
 			$incharmap = 1;
 			next;
 		}
 
 		next if (!$incharmap);
 		last if ($l eq "END CHARMAP");
 
 		$l =~ /^<([^\s]+)>\s+(.*)/;
 		my $k = $1;
 		my $v = $2;
-		$k =~ s/_/ /g;		# unicode char string
 		$v =~ s/\\x//g;		# UTF-8 char code
-		$utf8map{$k} = $v;
+		$db->{$k} = $v;
+#		print STDERR "UTF $k = $v\n";
 
-		$utf8aliases{$k} = $prev_k if ($prev_v eq $v);
+		# XXX: no longer needed
+		# $db_alias->{$k} = $prev_k if ($prev_v eq $v);
 
 		$prev_v = $v;
 		$prev_k = $k;
 	}
 }
 
+sub resolve_enc_addition {
+	my $ret = '';
+
+	foreach my $t (split(/\+/, $_[0])) {
+		$t =~ s/^0[xX]//;
+		$ret .= $t;
+	}
+	return $ret;
+}
+
 sub get_encodings {
 	my $dir = shift;
 	foreach my $e (sort(keys(%encodings))) {
 		if (!open(FIN, "$dir/$e.TXT")) {
 			print "Cannot open charmap for $e\n";
 			next;
 
 		}
 		$encodings{$e} = 1;
 		my @lines = <FIN>;
 		close(FIN);
 		chomp(@lines);
 		foreach my $l (@lines) {
 			$l =~ s/\r//;
-			next if ($l =~ /^\#/);
 			next if ($l eq "");
 
 			my @a = split(" ", $l);
 			next if ($#a < 1);
-			$a[0] =~ s/^0[xX]//;	# local char code
-			$a[1] =~ s/^0[xX]//;	# unicode char code
-			$convertors{$e}{uc($a[1])} = uc($a[0]);
+			next if ($a[0] =~ /^\#/ or $a[1] =~ /^\#/);
+			next if ($a[0] eq '' or $a[1] eq '');
+
+			$a[0] = resolve_enc_addition($a[0]);	# local
+			$a[1] = resolve_enc_addition($a[1]);	# UTF-32
+			my $u32 = sprintf("%08X", hex($a[1]));
+#			print STDERR "$a[1] => $u32\n";
+
+			# Use UTF-32 as the indices.
+			$convertors{$e}{$u32} = uc($a[0]);
 		}
 	}
 }
 
 sub get_languages {
 	my %data = get_xmldata($ETCDIR);
 	%languages = %{$data{L}}; 
 	%translations = %{$data{T}}; 
 	%alternativemonths = %{$data{AM}}; 
 	%encodings = %{$data{E}}; 
 }
 
 sub transform_ctypes {
 	# Add the C.UTF-8
 	$languages{"C"}{"x"}{data}{"x"}{$DEFENCODING} = undef;
 
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 0;	# unread
 		my $file = $l;
 		$file .= "_" . $f if ($f ne "x");
 		$file .= "_" . $c if ($c ne "x");
 		my $actfile = $file;
 
 		my $filename = "$UNIDIR/posix/xx_Comm_C.UTF-8.src";
 		if (! -f $filename) {
 			print STDERR "Cannot open $filename\n";
 			next;
 		}
 		open(FIN, "$filename");
 		print "Reading from $filename for ${l}_${f}_${c}\n";
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 1;	# read
 		my @lines;
 		my $shex;
 		my $uhex;
 		while (<FIN>) {
 			push @lines, $_;
 		}
 		close(FIN);
 		$shex = sha1_hex(join("\n", @lines));
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = $shex;
 		$hashtable{$shex}{"${l}_${f}_${c}.$DEFENCODING"} = 1;
 		open(FOUT, ">$TYPE.draft/$actfile.$DEFENCODING.src");
 		print FOUT @lines;
 		close(FOUT);
 		foreach my $enc (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
 			next if ($enc eq $DEFENCODING);
 			$filename = "$UNIDIR/posix/$file.$DEFENCODING.src";
 			if ($file eq 'ja_JP') {
 				# Override $filename for ja_JP because
 				# its CTYPE is not compatible with UTF-8.
 				$filename = "$UNIDIR/posix/$file.eucJP.src";
 			}
 			if (! -f $filename) {
 				print STDERR "Cannot open $filename\n";
 				next;
 			}
 			@lines = ();
 			open(FIN, "$filename");
 			while (<FIN>) {
 				if ((/^comment_char\s/) || (/^escape_char\s/)){
 					push @lines, $_;
 				}
 				if (/^LC_CTYPE/../^END LC_CTYPE/) {
 					push @lines, $_;
 				}
 			}
 			close(FIN);
 			$uhex = sha1_hex(join("\n", @lines) . $enc);
 			$languages{$l}{$f}{data}{$c}{$enc} = $uhex;
 			$hashtable{$uhex}{"${l}_${f}_${c}.$enc"} = 1;
 			open(FOUT, ">$TYPE.draft/$actfile.$enc.src");
 			print FOUT <<EOF;
 # Warning: Do not edit. This file is automatically extracted from the
 # tools in /usr/src/tools/tools/locale. The data is obtained from the
 # CLDR project, obtained from http://cldr.unicode.org/
 # -----------------------------------------------------------------------------
 EOF
 			print FOUT @lines;
 			close(FOUT);
 		}
 	}
 	}
 	}
 }
 
 
 sub transform_collation {
 	# Read the CLDR version
 	open(FIN, "$UNIDIR/cldr-version") or die "Cannot open cldr-version";
 	read FIN, $CLDR_VERSION, -s FIN;
 	close(FIN);
 	$CLDR_VERSION =~ s/\s*$//;
 
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 0;	# unread
 		my $file;
 		$file = $l . "_";
 		$file .= $f . "_" if ($f ne "x");
 		$file .= $c;
 		my $actfile = $file;
 
 		my $filename = "$UNIDIR/posix/$file.$DEFENCODING.src";
 		$filename = "$ETCDIR/$file.$DEFENCODING.src"
 		    if (! -f $filename);
 		if (! -f $filename
 		 && defined $languages{$l}{$f}{fallback}) {
 			$file = $languages{$l}{$f}{fallback};
 			$filename = "$UNIDIR/posix/$file.$DEFENCODING.src";
 		}
 		$filename = "$UNIDIR/posix/$file.$DEFENCODING.src"
 		    if (! -f $filename);
 		if (! -f $filename) {
 			print STDERR
 			    "Cannot open $file.$DEFENCODING.src or fallback\n";
 			next;
 		}
 		open(FIN, "$filename");
 		print "Reading from $filename for ${l}_${f}_${c}\n";
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 1;	# read
 		my @lines;
 		my $shex;
 		while (<FIN>) {
 			if ((/^comment_char\s/) || (/^escape_char\s/)){
 				push @lines, $_;
 			}
 			if (/^LC_COLLATE/../^END LC_COLLATE/) {
 				$_ =~ s/[ ]+/ /g;
 				push @lines, $_;
 			}
 		}
 		close(FIN);
 		$shex = sha1_hex(join("\n", @lines));
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = $shex;
 		$hashtable{$shex}{"${l}_${f}_${c}.$DEFENCODING"} = 1;
 		open(FOUT, ">$TYPE.draft/$actfile.$DEFENCODING.src");
 		print FOUT <<EOF;
 # Warning: Do not edit. This file is automatically extracted from the
 # tools in /usr/src/tools/tools/locale. The data is obtained from the
 # CLDR project, obtained from http://cldr.unicode.org/
 # -----------------------------------------------------------------------------
 EOF
 		print FOUT @lines;
 		close(FOUT);
 
 		foreach my $enc (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
 			next if ($enc eq $DEFENCODING);
-			copy ("$TYPE.draft/$actfile.$DEFENCODING.src",
-			      "$TYPE.draft/$actfile.$enc.src");
+
+			open FIN, "<$TYPE.draft/$actfile.$DEFENCODING.src";
+			open FOUT, ">$TYPE.draft/$actfile.$enc.src";
+			my $order_start = 0;
+			my $print_p = 0;
+			#
+			# %c_elem: collation elements
+			#
+			#   undef: not defined
+			#   1: defined
+			#   2: invalid in this encoding
+			#
+			my %c_elem = ();
+			while (<FIN>) {	# XXX: this loop should be refactored.
+				chomp;
+				$print_p = 1;
+				if ($order_start) {
+					$order_start = 0 if (m/^order_end/);
+					if (m/^<([^>]+)>/) {
+						if (not defined $c_elem{$1}) {
+#							print STDERR "$1:\n";
+
+							my $u32 = $utfmap{'UTF-32'}->{$1};
+							die "order, $1\n" if (not defined $u32);
+#							print STDERR "u32 for $1 = $u32\n";
+							if (not defined $convertors{$enc}{$u32}) {
+#								print STDERR "$1 - $u32 not defined in $enc\n";
+								$print_p = 0;
+							}
+						} elsif ($c_elem{$1} == 2) {
+#							print STDERR "$1 is marked as invalid in $enc\n";
+							$print_p = 0;
+						}
+					}
+				} elsif (m/^collating-element/) {
+					my ($elem, $l);
+					if (m/<([^>]+)> from (.+)/) {
+						($elem, $l) = ($1, $2);
+					}
+#					print STDERR "$elem: enter ($print_p, $l,)\n";
+					while ($print_p and
+					    defined $l and
+					    $l =~ m/<([^>]+)>/g) {
+#						print STDERR "$elem: $1\n";
+						my $u32 = $utfmap{'UTF-32'}->{$1};
+						die "collating-element, $1\n" if (not defined $u32);
+#						print STDERR "u32 for $1 = $u32\n";
+						if (not $convertors{$enc}{$u32}) {
+#							print STDERR "$1 - $u32 not defined in $enc\n";
+							$print_p = 0;
+#							print STDERR "Mark $elem as invalid\n";
+							$c_elem{$elem} = 2;
+						}
+					}
+					if ($print_p) {
+#						print STDERR "Add $elem\n";
+						$c_elem{$elem} = 1;
+					}
+				} elsif (m/^collating-symbol <([^>]+)>/) {
+#					print STDERR "Add $1\n";
+					$c_elem{$1} = 1;
+				} elsif (m/^order_start/) {
+					$order_start = 1;
+					# do nothing
+				}
+				print FOUT $_, "\n" if ($print_p);
+			}
+			close FOUT;
+			close FIN;
 			$languages{$l}{$f}{data}{$c}{$enc} = $shex;
 			$hashtable{$shex}{"${l}_${f}_${c}.$enc"} = 1;
 		}
 	}
 	}
 	}
 }
 
 sub get_fields {
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 0;	# unread
 		my $file;
 		$file = $l . "_";
 		$file .= $f . "_" if ($f ne "x");
 		$file .= $c;
 
 		my $filename = "$UNIDIR/posix/$file.$DEFENCODING.src";
 		$filename = "$ETCDIR/$file.$DEFENCODING.src"
 		    if (! -f $filename);
 		if (! -f $filename
 		 && defined $languages{$l}{$f}{fallback}) {
 			$file = $languages{$l}{$f}{fallback};
 			$filename = "$UNIDIR/posix/$file.$DEFENCODING.src";
 		}
 		$filename = "$UNIDIR/posix/$file.$DEFENCODING.src"
 		    if (! -f $filename);
 		if (! -f $filename) {
 			print STDERR
 			    "Cannot open $file.$DEFENCODING.src or fallback\n";
 			next;
 		}
 		open(FIN, "$filename");
 		print "Reading from $filename for ${l}_${f}_${c}\n";
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 1;	# read
 		my @lines = <FIN>;
 		chomp(@lines);
 		close(FIN);
 		my $continue = 0;
 		foreach my $k (keys(%keys)) {
 			foreach my $line (@lines) {
 				$line =~ s/\r//;
 				next if (!$continue && $line !~ /^$k\s/);
 				if ($continue) {
 					$line =~ s/^\s+//;
 				} else {
 					$line =~ s/^$k\s+//;
 				}
 
 				$values{$l}{$f}{$c}{$k} = ""
 					if (!defined $values{$l}{$f}{$c}{$k});
 
 				$continue = ($line =~ /\/$/);
 				$line =~ s/\/$// if ($continue);
 
-				while ($line =~ /_/) {
-					$line =~
-					    s/\<([^>_]+)_([^>]+)\>/<$1 $2>/;
-				}
-				die "_ in data - $line" if ($line =~ /_/);
+#				while ($line =~ /_/) {
+#					$line =~
+#					    s/\<([^>_]+)_([^>]+)\>/<$1 $2>/;
+#				}
+#				die "_ in data - $line" if ($line =~ /_/);
 				$values{$l}{$f}{$c}{$k} .= $line;
 
 				last if (!$continue);
 			}
 		}
 	}
 	}
 	}
 }
 
 sub decodecldr {
 	my $e = shift;
 	my $s = shift;
 
 	my $v = undef;
 
 	if ($e eq "UTF-8") {
 		#
 		# Conversion to UTF-8 can be done from the Unicode name to
 		# the UTF-8 character code.
 		#
-		$v = $utf8map{$s};
+		$v = $utfmap{'UTF-8'}->{$s};
 		die "Cannot convert $s in $e (charmap)" if (!defined $v);
 	} else {
 		#
 		# Conversion to these encodings can be done from the Unicode
 		# name to Unicode code to the encodings code.
 		#
-		my $ucc = undef;
-		$ucc = $ucd{name2code}{$s} if (defined $ucd{name2code}{$s});
-		$ucc = $ucd{name2code}{$utf8aliases{$s}}
-			if (!defined $ucc
-			 && $utf8aliases{$s}
-			 && defined $ucd{name2code}{$utf8aliases{$s}});
-
-		if (!defined $ucc) {
-			if (defined $translations{$e}{$s}{hex}) {
-				$v = $translations{$e}{$s}{hex};
-				$ucc = 0;
-			} elsif (defined $translations{$e}{$s}{ucc}) {
-				$ucc = $translations{$e}{$s}{ucc};
+		# hex - hex or string attr
+		# unicode - unicode attr
+		# ucc - ucc attr
+		my $hex = $translations{$e}{$s}{hex};
+		my $ucc = $utfmap{'UTF-32'}->{$s};
+		my $ucc_attr = $translations{$e}{$s}{ucc};
+		my $unicode = $translations{$e}{$s}{unicode};
+
+		if (defined $hex) {		# hex is in local encoding
+			$v = $hex;
+		} elsif (defined $unicode) {	# unicode is in name
+			$v = $convertors{$e}{$utfmap{'UTF-32'}->{$unicode}};
+		} elsif (defined $ucc_attr) {	# ucc is in code point
+			if (defined $ucc) {
+#				print STDERR "INFO: ucc=$ucc_attr ",
+#				    "overrides $ucc in UTF-32\n";
 			}
-		}
-
-		die "Cannot convert $s in $e (ucd string)" if (!defined $ucc);
-		$v = $convertors{$e}{$ucc} if (!defined $v);
-
-		$v = $translations{$e}{$s}{hex}
-			if (!defined $v && defined $translations{$e}{$s}{hex});
-
-		if (!defined $v && defined $translations{$e}{$s}{unicode}) {
-			my $ucn = $translations{$e}{$s}{unicode};
-			$ucc = $ucd{name2code}{$ucn}
-				if (defined $ucd{name2code}{$ucn});
-			$ucc = $ucd{name2code}{$utf8aliases{$ucn}}
-				if (!defined $ucc
-				 && defined $ucd{name2code}{$utf8aliases{$ucn}});
+			# normalize
+			$ucc_attr = sprintf("%08X", hex($ucc_attr));
+#			print STDERR "convert $ucc_attr into $e\n";
+			$v = $convertors{$e}{$ucc_attr};
+		} elsif (defined $ucc) {
+			# normalize
+			$ucc = sprintf("%08X", hex($ucc));
+#			print STDERR "convert $ucc into $e\n";
 			$v = $convertors{$e}{$ucc};
 		}
-
-		die "Cannot convert $s in $e (charmap)" if (!defined $v);
+		die "Cannot convert $s in $e" if (!defined $v);
 	}
 
+	# XXX: length = 8 is not supported yet.
+	$v =~ s/^[0]+//g;
+	$v = "0" . $v if (length($v) % 2);
 	return pack("C", hex($v)) if (length($v) == 2);
 	return pack("CC", hex(substr($v, 0, 2)), hex(substr($v, 2, 2)))
 		if (length($v) == 4);
 	return pack("CCC", hex(substr($v, 0, 2)), hex(substr($v, 2, 2)),
 	    hex(substr($v, 4, 2))) if (length($v) == 6);
-	print STDERR "Cannot convert $e $s\n";
-	return "length = " . length($v);
-
+	die "Cannot convert $s in $e (length = " . length($v) . "\n";
 }
 
 sub translate {
 	my $enc = shift;
 	my $v = shift;
 
 	return $translations{$enc}{$v} if (defined $translations{$enc}{$v});
 	return undef;
 }
 
 sub print_fields {
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 		foreach my $enc (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
 			if ($languages{$l}{$f}{data}{$c}{$DEFENCODING} eq "0") {
 				print "Skipping ${l}_" .
 				    ($f eq "x" ? "" : "${f}_") .
 				    "${c} - not read\n";
 				next;
 			}
 			my $file = $l;
 			$file .= "_" . $f if ($f ne "x");
 			$file .= "_" . $c;
 			print "Writing to $file in $enc\n";
 
 			if ($enc ne $DEFENCODING &&
 			    !defined $convertors{$enc}) {
 				print "Failed! Cannot convert to $enc.\n";
 				next;
 			};
 
 			open(FOUT, ">$TYPE.draft/$file.$enc.new");
 			my $okay = 1;
 			my $output = "";
 			print FOUT <<EOF;
 # Warning: Do not edit. This file is automatically generated from the
 # tools in /usr/src/tools/tools/locale. The data is obtained from the
 # CLDR project, obtained from http://cldr.unicode.org/
 # -----------------------------------------------------------------------------
 EOF
 			foreach my $k (keys(%keys)) {
 				my $g = $keys{$k};
 
 				die("Unknown $k in \%DESC")
 					if (!defined $DESC{$k});
 
 				$output .= "#\n# $DESC{$k}\n";
 
 				# Replace one row with another
 				if ($g =~ /^>/) {
 					$k = substr($g, 1);
 					$g = $keys{$k};
 				}
 
 				# Callback function
 				if ($g =~ /^\</) {
 					$callback{data}{c} = $c;
 					$callback{data}{k} = $k;
 					$callback{data}{f} = $f;
 					$callback{data}{l} = $l;
 					$callback{data}{e} = $enc;
 					my @a = split(/\</, substr($g, 1));
 					my $rv =
 					    &{$callback{$a[0]}}($values{$l}{$f}{$c}{$a[1]});
 					$values{$l}{$f}{$c}{$k} = $rv;
 					$g = $a[2];
 					$callback{data} = ();
 				}
 
 				my $v = $values{$l}{$f}{$c}{$k};
 				$v = "undef" if (!defined $v);
 
 				if ($g eq "i") {
 					$output .= "$v\n";
 					next;
 				}
 				if ($g eq "ai") {
 					$output .= "$v\n";
 					next;
 				}
 				if ($g eq "s") {
 					$v =~ s/^"//;
 					$v =~ s/"$//;
 					my $cm = "";
 					while ($v =~ /^(.*?)<(.*?)>(.*)/) {
 						my $p1 = $1;
 						$cm = $2;
 						my $p3 = $3;
 
 						my $rv = decodecldr($enc, $cm);
 #						$rv = translate($enc, $cm)
 #							if (!defined $rv);
 						if (!defined $rv) {
 							print STDERR 
 "Could not convert $k ($cm) from $DEFENCODING to $enc\n";
 							$okay = 0;
 							next;
 						}
 
 						$v = $p1 . $rv . $p3;
 					}
 					$output .= "$v\n";
 					next;
 				}
 				if ($g eq "as") {
 					foreach my $v (split(/;/, $v)) {
 						$v =~ s/^"//;
 						$v =~ s/"$//;
 						my $cm = "";
 						while ($v =~ /^(.*?)<(.*?)>(.*)/) {
 							my $p1 = $1;
 							$cm = $2;
 							my $p3 = $3;
 
 							my $rv =
 							    decodecldr($enc,
 								$cm);
 #							$rv = translate($enc,
 #							    $cm)
 #							    if (!defined $rv);
 							if (!defined $rv) {
 								print STDERR 
 "Could not convert $k ($cm) from $DEFENCODING to $enc\n";
 								$okay = 0;
 								next;
 							}
 
 							$v = $1 . $rv . $3;
 						}
 						$output .= "$v\n";
 					}
 					next;
 				}
 
 				die("$k is '$g'");
 
 			}
 
 			$languages{$l}{$f}{data}{$c}{$enc} = sha1_hex($output);
 			$hashtable{sha1_hex($output)}{"${l}_${f}_${c}.$enc"} = 1;
 			print FOUT "$output# EOF\n";
 			close(FOUT);
 
 			if ($okay) {
 				rename("$TYPE.draft/$file.$enc.new",
 				    "$TYPE.draft/$file.$enc.src");
 			} else {
 				rename("$TYPE.draft/$file.$enc.new",
 				    "$TYPE.draft/$file.$enc.failed");
 			}
 		}
 	}
 	}
 	}
 }
 
 sub make_makefile {
 	print "Creating Makefile for $TYPE\n";
 	my $SRCOUT;
 	my $SRCOUT2;
 	my $SRCOUT3 = "";
 	my $SRCOUT4 = "";
 	my $MAPLOC;
 	if ($TYPE eq "colldef") {
 		# In future, we might want to try to put the CLDR version into
 		# the .src files with some new syntax, instead of the makefile.
 		$SRCOUT = "localedef \${LOCALEDEF_ENDIAN} -D -U " .
 			"-i \${.IMPSRC} \\\n" .
 			"\t-V \${CLDR_VERSION} \\\n" .
 			"\t-f \${MAPLOC}/map.\${.TARGET:T:R:E:C/@.*//} " .
 			"\${.OBJDIR}/\${.IMPSRC:T:R}";
 		$MAPLOC = "MAPLOC=\t\t\${.CURDIR}/../../tools/tools/" .
 				"locale/etc/final-maps\n";
 		$SRCOUT2 = "LC_COLLATE";
 		$SRCOUT3 = "" .
 			".for f t in \${LOCALES_MAPPED}\n" .
 			"FILES+=\t\$t.LC_COLLATE\n" .
 			"FILESDIR_\$t.LC_COLLATE=\t\${LOCALEDIR}/\$t\n" .
 			"\$t.LC_COLLATE: \${.CURDIR}/\$f.src\n" .
 			"\tlocaledef \${LOCALEDEF_ENDIAN} -D -U " .
 			"-i \${.ALLSRC} \\\n" .
 			"\t-V \${CLDR_VERSION} \\\n" .
 			"\t\t-f \${MAPLOC}/map.\${.TARGET:T:R:E:C/@.*//} \\\n" .
 			"\t\t\${.OBJDIR}/\${.TARGET:T:R}\n" .
 			".endfor\n\n";
 		$SRCOUT4 = "## LOCALES_MAPPED\n";
 	}
 	elsif ($TYPE eq "ctypedef") {
 		$SRCOUT = "localedef \${LOCALEDEF_ENDIAN} -D -U -c " .
 			"-w \${MAPLOC}/widths.txt \\\n" .
 			"\t-f \${MAPLOC}/map.\${.IMPSRC:T:R:E} " .
 			"\\\n\t-i \${.IMPSRC} \${.OBJDIR}/\${.IMPSRC:T:R} " .
 			" || true";
 		$SRCOUT2 = "LC_CTYPE";
 		$MAPLOC = "MAPLOC=\t\t\${.CURDIR}/../../tools/tools/" .
 				"locale/etc/final-maps\n";
 		$SRCOUT3 = "## SYMPAIRS\n\n" .
 			".for s t in \${SYMPAIRS}\n" .
 			"\${t:S/src\$/LC_CTYPE/}: " .
 			"\$s\n" .
 			"\tlocaledef \${LOCALEDEF_ENDIAN} -D -U -c " .
 			"-w \${MAPLOC}/widths.txt \\\n" .
 			"\t-f \${MAPLOC}/map.\${.TARGET:T:R:C/^.*\\.//} " .
 			"\\\n\t-i \${.ALLSRC} \${.OBJDIR}/\${.TARGET:T:R} " .
 			" || true\n" .
 			".endfor\n\n";
 	}
 	else {
 		$SRCOUT = "grep -v -E '^(\#\$\$|\#[ ])' < \${.IMPSRC} > \${.TARGET}";
 		$SRCOUT2 = "out";
 		$MAPLOC = "";
 	}
 	open(FOUT, ">$TYPE.draft/Makefile");
 	print FOUT <<EOF;
 # \$FreeBSD\$
 # Warning: Do not edit. This file is automatically generated from the
 # tools in /usr/src/tools/tools/locale.
 
 LOCALEDIR=	\${SHAREDIR}/locale
 FILESNAME=	$FILESNAMES{$TYPE}
 .SUFFIXES:	.src .${SRCOUT2}
 ${MAPLOC}
 EOF
 
 	if ($TYPE eq "colldef") {
 		print FOUT <<EOF;
 CLDR_VERSION=	"${CLDR_VERSION}"
 
 EOF
 	}
 
 	if ($TYPE eq "colldef" || $TYPE eq "ctypedef") {
 		print FOUT <<EOF;
 .include <bsd.endian.mk>
 
 EOF
 	}
 
 	print FOUT <<EOF;
 .src.${SRCOUT2}:
 	$SRCOUT
 
 ## PLACEHOLDER
 
 ${SRCOUT4}
 
 EOF
 
 	foreach my $hash (keys(%hashtable)) {
 		# For colldef, weight LOCALES to UTF-8
 		#     Sort as upper-case and reverse to achieve it
 		#     Make en_US, ru_RU, and ca_AD preferred
 		my @files;
 		if ($TYPE eq "colldef") {
 			@files = sort {
 				if ($a eq 'en_x_US.UTF-8' ||
 				    $a eq 'ru_x_RU.UTF-8' ||
 				    $a eq 'ca_x_AD.UTF-8') { return -1; }
 				elsif ($b eq 'en_x_US.UTF-8' ||
 				       $b eq 'ru_x_RU.UTF-8' ||
 				       $b eq 'ca_x_AD.UTF-8') { return 1; }
 				else { return uc($b) cmp uc($a); }
 				} keys(%{$hashtable{$hash}});
 		} elsif ($TYPE eq "ctypedef") {
 			@files = sort {
 				if ($a eq 'C_x_x.UTF-8') { return -1; }
 				elsif ($b eq 'C_x_x.UTF-8') { return 1; }
 				if ($a =~ /^en_x_US/) { return -1; }
 				elsif ($b =~ /^en_x_US/) { return 1; }
 
 				if ($a =~ /^en_x_GB.ISO8859-15/ ||
 				    $a =~ /^ru_x_RU/) { return -1; }
 				elsif ($b =~ /^en_x_GB.ISO8859-15/ ||
 				       $b =~ /ru_x_RU/) { return 1; }
 				else { return uc($b) cmp uc($a); }
 
 				} keys(%{$hashtable{$hash}});
 		} else {
 			@files = sort {
 				if ($a =~ /_Comm_/ ||
 				    $b eq 'en_x_US.UTF-8') { return 1; }
 				elsif ($b =~ /_Comm_/ ||
 				       $a eq 'en_x_US.UTF-8') { return -1; }
 				else { return uc($b) cmp uc($a); }
 				} keys(%{$hashtable{$hash}});
 		}
 		if ($#files > 0) {
 			my $link = shift(@files);
 			$link =~ s/_x_x//;	# special case for C
 			$link =~ s/_x_/_/;	# strip family if none there
 			foreach my $file (@files) {
 				my @a = split(/_/, $file);
 				my @b = split(/\./, $a[-1]);
 				$file =~ s/_x_/_/;
 				print FOUT "SAME+=\t\t$link $file\n";
 				undef($languages{$a[0]}{$a[1]}{data}{$b[0]}{$b[1]});
 			}
 		}
 	}
 
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 		if (defined $languages{$l}{$f}{data}{$c}{$DEFENCODING}
 		 && $languages{$l}{$f}{data}{$c}{$DEFENCODING} eq "0") {
 			print "Skipping ${l}_" . ($f eq "x" ? "" : "${f}_") .
 			    "${c} - not read\n";
 			next;
 		}
 		foreach my $e (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
 			my $file = $l;
 			$file .= "_" . $f if ($f ne "x");
 			$file .= "_" . $c if ($c ne "x");
 			next if (!defined $languages{$l}{$f}{data}{$c}{$e});
 			print FOUT "LOCALES+=\t$file.$e\n";
 		}
 
 		if (defined $languages{$l}{$f}{nc_link}) {
 			foreach my $e (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
 				my $file = $l . "_";
 				$file .= $f . "_" if ($f ne "x");
 				$file .= $c;
 				print FOUT "SAME+=\t\t$file.$e $languages{$l}{$f}{nc_link}.$e\t# legacy (lang/country change)\n";
 			}
 		}
 
 		if (defined $languages{$l}{$f}{e_link}) {
 			foreach my $el (split(" ", $languages{$l}{$f}{e_link})) {
 				my @a = split(/:/, $el);
 				my $file = $l . "_";
 				$file .= $f . "_" if ($f ne "x");
 				$file .= $c;
 				print FOUT "SAME+=\t\t$file.$a[0] $file.$a[1]\t# legacy (same charset)\n";
 			}
 		}
 
 	}
 	}
 	}
 
 	print FOUT <<EOF;
 
 FILES=		\${LOCALES:S/\$/.${SRCOUT2}/}
 CLEANFILES=	\${FILES}
 
 .for f t in \${SAME}
 SYMLINKS+=	../\$f/\${FILESNAME} \\
     \${LOCALEDIR}/\$t/\${FILESNAME}
 .endfor
 
 .for f in \${LOCALES}
 FILESDIR_\${f}.${SRCOUT2}= \${LOCALEDIR}/\${f}
 .endfor
 
 ${SRCOUT3}.include <bsd.prog.mk>
 EOF
 
 	close(FOUT);
 }