From: ntakahas <ntakahas>
Date: Mon, 5 Sep 2005 12:52:27 +0000 (+0000)
Subject: Add CASED.tab, SOFT-DOTTED.tab, and CASE-MAPPING.tab.
X-Git-Tag: REL-1-3-0~133
X-Git-Url: http://git.chise.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=c9f53dba3adae4e0946d8fdd315e8a861d52d9ad;p=m17n%2Fm17n-db.git

Add CASED.tab, SOFT-DOTTED.tab, and CASE-MAPPING.tab.
---

diff --git a/Makefile.am b/Makefile.am
index 171aa17..14fd0cb 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -37,6 +37,7 @@ EXTRA_DIST = \
 	${UNIDATA} \
 	mapconv compact.awk gb180302.awk gb180304.awk \
 	CHARTAB.awk NAME.awk \
+	CASED.awk SOFT-DOTTED.awk CASE-MAPPING.awk \
 	get-glibc.sh \
 	${FORMATS}
 
@@ -78,8 +79,8 @@ MISC =  KOI-8.map KOI8-R.map KOI8-U.map KOI8-T.map \
 
 CHAR_TABLE = \
 	NAME.tab SCRIPT.tab CASE-S.tab CASE-C.tab \
-	CATEGORY.tab COMBINE.tab BIDI.tab LINEBREAK.tab
-
+	CATEGORY.tab COMBINE.tab BIDI.tab LINEBREAK.tab \
+	CASED.tab SOFT-DOTTED.tab CASE-MAPPING.tab
 
 FONT_LAYOUT_TABLE = \
 	ARAB.flt ARAB-OTF.flt ARAB-OTF-NO-GPOS.flt \
@@ -88,7 +89,7 @@ FONT_LAYOUT_TABLE = \
 	GUJR-OTF.flt \
 	GURU-OTF.flt \
 	HEBR.flt HEBR-FF.flt \
-	KHMR-MULE.flt KHMR-ANLONG.flt KHMR-OTF.flt\
+	KHMR-MULE.flt KHMR-ANLONG.flt KHMR-OTF.flt \
 	KNDA-OTF.flt \
 	LAOO-MULE.flt LAOO-ALICE.flt LAOO-GENERIC.flt \
 	MLYM-CDAC.flt MLYM-OTF.flt MLYM-RACHANA.flt \
@@ -154,7 +155,9 @@ MISC_TABLE = \
 
 UNIDATA = \
 	UNIDATA/README \
-	UNIDATA/UnicodeData.txt UNIDATA/Scripts.txt UNIDATA/CaseFolding.txt
+	UNIDATA/UnicodeData.txt UNIDATA/Scripts.txt UNIDATA/CaseFolding.txt \
+	UNIDATA/PropList.txt UNIDATA/WordBreakProperty.txt \
+	UNIDATA/SpecialCasing.txt
 
 FORMATS = \
 	FORMATS/README \
@@ -321,6 +324,23 @@ SCRIPT.tab: UNIDATA/Scripts.txt Makefile
 	  sed -e 's/\.\./-0x/' | \
 	  tr '[:upper:]' '[:lower:]' >> $@
 
+CASED.tab: UNIDATA/UnicodeData.txt UNIDATA/PropList.txt UNIDATA/WordBreakProperty.txt CASED.awk
+	echo "# Generated from UNIDATA/UnicodeData.txt, UNIDATA/PropList.txt, and UNIDATA/WordBreakProperty.txt." > $@
+	@cat UNIDATA/UnicodeData.txt UNIDATA/PropList.txt UNIDATA/WordBreakProperty.txt | $(AWK) -f CASED.awk >> $@
+
+SOFT-DOTTED.tab: UNIDATA/PropList.txt Makefile
+	echo "# Generated from $<." > $@
+	@$(AWK) '/^[^#;]+; *Soft_Dotted/ { \
+	  if (index ($$1, ".")) { \
+	    split ($$1, A, "\.\."); \
+	    print "0x"A[1]"-0x"A[2]" t"; } \
+	  else print "0x"$$1" t"; }' \
+	  $< >> $@
+
+CASE-MAPPING.tab: UNIDATA/SpecialCasing.txt UNIDATA/UnicodeData.txt CASE-MAPPING.awk
+	echo "# Generated from UNIDATA/SpecialCasing.txt and UNIDATA/UnicodeData.txt." > $@
+	@cat UNIDATA/SpecialCasing.txt UNIDATA/UnicodeData.txt | $(AWK) -f CASE-MAPPING.awk >> $@
+
 LINEBREAK.tab: UNIDATA/LineBreak.txt LINEBREAK.awk
 	echo "# Generated from $<." > $@
 	@$(AWK) -f LINEBREAK.awk $< >> $@
diff --git a/mdb.dir b/mdb.dir
index 9dd4ad7..b54e6a3 100644
--- a/mdb.dir
+++ b/mdb.dir
@@ -79,6 +79,26 @@
 ;;; Unicode script name for each character that is available as
 ;;; #Mscript property.
 (char-table symbol script "SCRIPT.tab")
+
+;;; <li> CASED.tab
+;;;
+;;; Unicode properties for case operations.  Integer value 1 means
+;;; cased (D47, Unicode 4.0, p.89), 2 means case-ignorable (D47a,
+;;; Unicode 4.1.0), and 3 means both.  Available as #Mcased property.
+(char-table integer cased "CASED.tab")
+
+;;; <li> SOFT-DOTTED.tab
+;;;
+;;; Unicode property for case operations.  Available as #Msoft_dotted
+;;; property.
+(char-table symbol soft-dotted "SOFT-DOTTED.tab")
+
+;;; <li> CASE-MAPPING.tab
+;;;
+;;; Unicode case mapping of each character that is available as
+;;; #Mcase_mapping property.
+(char-table plist case-mapping "CASE-MAPPING.tab")
+
 ;;; </ul>
 
 ;;; @section mim-list Input method