changeset 103389:24af3ac0cac1

Mostly re-written to handle "gzip"ed input files.

--- a/admin/charsets/mapconv	Fri Jun 12 07:22:28 2009 +0000
+++ b/admin/charsets/mapconv	Fri Jun 12 07:22:48 2009 +0000
@@ -30,34 +30,42 @@
 #   $1: source map file
 #   $2: address pattern for sed (optionally with substitution command)
 #   $3: format of source map file
-#	GLIBC-1 GLIBC-2 GLIBC-2-7 CZYBORRA IANA UNICODE YASUOKA MICROSOFT
+#	GLIBC-1 GLIBC-2 GLIBC-2-7 CZYBORRA IANA UNICODE YASUOKA
 #   $4: awk script
 
-BASE=`basename $1`
+FILE="admin/charsets/$1"
+BASE=`basename $1 .gz`
 
 case "$3" in
     GLIBC*)
-	SOURCE="glibc-2.3.2/localedata/charmaps/${BASE}";;
+	FILE="$BASE in localedate/charmaps of glibc";
+	SOURCE="";;
     CZYBORRA)
+	BASE="$BASE.gz";
 	SOURCE="http://czyborra.com/charsets/${BASE}";;
     IANA)
 	SOURCE="http://www.iana.org/assignments/charset-reg/${BASE}";;
     UNICODE)
-	SOURCE="http://www.unicode.org/Public/MAPPINGS/.../${BASE}";;
+	SOURCE="http://www.unicode.org/Public/MAPPINGS/VENDORS/ADOBE/${BASE}";;
     UNICODE2)
-	SOURCE="http://www.unicode.org/Public/MAPPINGS/.../${BASE}";;
+	SOURCE="http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/${BASE}";;
     YASUOKA)
-	SOURCE="http://kanji.zinbun.kyoto-u.ac.jp/~yasuoka/.../${BASE}";;
-    MICROSOFT)
-	SOURCE="http://www.microsoft.com/globaldev/reference/oem/${BASE}";;
+	BASE="$BASE.Z";
+	SOURCE="http://kanji.zinbun.kyoto-u.ac.jp/~yasuoka/ftp/CJKtable/${BASE}";;
     KANJI-DATABASE)
-	SOURCE="data at http://sourceforge.net/cvs/?group_id=26261";;
+	SOURCE="http://kanji-database.cvs.sourceforge.net/viewvc/*checkout*/kanji-database/kanji-database/data/cns2ucsdkw.txt?revision=1.4";;
     *)
 	echo "Unknown file type: $3";
 	exit 1;;
 esac
 
-echo "# Generated from $SOURCE"
+if [ -n "$SOURCE" ] ; then
+    echo "# Generated from $FILE which is a copy of";
+    echo "# $SOURCE"
+else
+    echo "# Generated from $FILE"
+fi
+
 
 if [ -n "$4" ] ; then
     if [ -f "$4" ] ; then
@@ -70,72 +78,66 @@
     AWKPROG=cat
 fi
 
-if [ "$3" == "GLIBC-1" ] ; then
+if [ "$3" = "GLIBC-1" ] ; then
     # Source format is:
     #   <UYYYY>	/xXX
-    sed -n -e "$2 p" < $1 \
+    zcat $1 | sed -n -e "$2 p" \
 	| sed -e 's,<U\([^>]*\)>[ 	]*/x\(..\).*,0x\2 0x\1,' \
 	| sort | ${AWKPROG}
-elif [ "$3" == "GLIBC-2" ] ; then
+elif [ "$3" = "GLIBC-2" ] ; then
     # Source format is:
     #   <UYYYY>	/xXX/xZZ
-    sed -n -e "$2 p" < $1 \
+    zcat $1 | sed -n -e "$2 p" \
 	| sed -e 's,<U\([^>]*\)>[ 	]*/x\(..\)/x\(..\).*,0x\2\3 0x\1,' \
 	| sort | ${AWKPROG}
-elif [ "$3" == "GLIBC-2-7" ] ; then
+elif [ "$3" = "GLIBC-2-7" ] ; then
     # Source format is:
     #   <UYYYY>	/xXX/xZZ
     # We must drop MSBs of XX and ZZ
-    sed -n -e "$2 p" < $1 \
+    zcat $1 | sed -n -e "$2 p" \
 	| sed -e 's/xa/x2/g' -e 's/xb/x3/g' -e 's/xc/x4/g' \
 	      -e 's/xd/x5/g' -e 's/xe/x6/g' -e 's/xf/x7/g' \
 	      -e 's,<U\([^>]*\)>[ 	]*/x\(..\)/x\(..\).*,0x\2\3 0x\1,' \
 	| tee temp \
 	| sort | ${AWKPROG}
-elif [ "$3" == "CZYBORRA" ] ; then
+elif [ "$3" = "CZYBORRA" ] ; then
     # Source format is:
     #   =XX	U+YYYY
     zcat $1 | sed -n -e "$2 p" \
 	| sed -e 's/=\(..\)[^U]*U+\([0-9A-F]*\).*/0x\1 0x\2/' \
 	| sort | ${AWKPROG}
-elif [ "$3" == "IANA" ] ; then
+elif [ "$3" = "IANA" ] ; then
     # Source format is:
     #   0xXX	0xYYYY
-    sed -n -e "$2 p" < $1 \
+    zcat $1 | sed -n -e "$2 p" \
 	| sed -e 's/\(0x[0-9A-Fa-f]*\)[^0]*\(0x[0-9A-Fa-f]*\).*/\1 \2/' \
 	| sort | ${AWKPROG}
-elif [ "$3" == "UNICODE" ] ; then
+elif [ "$3" = "UNICODE" ] ; then
     # Source format is:
     #   YYYY	XX
-    sed -n -e "$2 p" < $1 \
+    zcat $1 | sed -n -e "$2 p" \
 	| sed -e 's/\([0-9A-F]*\)[^0-9A-F]*\([0-9A-F]*\).*/0x\2 0x\1/' \
 	| sort | ${AWKPROG}
-elif [ "$3" == "UNICODE2" ] ; then
+elif [ "$3" = "UNICODE2" ] ; then
     # Source format is:
     #   0xXXXX	0xYYYY	# ...
-    sed -n -e "$2 p" < $1 \
+    zcat $1 | sed -n -e "$2 p" \
 	| sed -e 's/\([0-9A-Fx]*\)[^0]*\([0-9A-Fx]*\).*/\1 \2/' \
 	| ${AWKPROG} | sort -n -k 4,4
-elif [ "$3" == "YASUOKA" ] ; then
+elif [ "$3" = "YASUOKA" ] ; then
     # Source format is:
     # YYYY	0-XXXX (XXXX is a Kuten code)
-    sed -n -e "$2 p" < $1 \
+    zcat $1 | sed -n -e "$2 p" \
 	| sed -e 's/\([0-9A-F]*\)[^0]*0-\([0-9]*\).*/0x\2 0x\1/' \
 	| sort | ${AWKPROG}
-elif [ "$3" == "MICROSOFT" ] ; then
-    # Source format is:
-    # XX = U+YYYY
-    sed -n -e "$2 p" < $1 \
-	| sed -e 's/\([0-9A-F]*\).*U+\([0-9A-F]*\).*/0x\1 0x\2/' \
-	| sort | ${AWKPROG}
-elif [ "$3" == "KANJI-DATABASE" ] ; then
+elif [ "$3" = "KANJI-DATABASE" ] ; then
     # Source format is:
     # C?-XXXX U+YYYYY .....
-    sed -n -e "$2 p" < $1 \
+    zcat $1 | sed -n -e "$2 p" \
 	| sed -e 's/...\(....\) U+\([0-9A-F]*\).*/0x\1 0x\2/' \
 	| sort | ${AWKPROG}
 else
-    echo "Invalid arguments"
+    echo "Invalid arguments: $3"
     exit 1
 fi