openSUSE Build Service

Overview Repositories Revisions Requests Users Attributes Meta

File utf8.patch of Package groff

diff -ru groff-1.18.1.1.orig//src/roff/nroff/nroff.sh groff-1.18.1.1/src/roff/nroff/nroff.sh
--- groff-1.18.1.1.orig//src/roff/nroff/nroff.sh	2009-02-02 18:44:00.000000000 +0100
+++ groff-1.18.1.1/src/roff/nroff/nroff.sh	2009-02-02 18:44:40.000000000 +0100
@@ -87,11 +87,177 @@
   shift
 done
 
+# special hacks to display Japanese, Chinese, ...man pages correctly in UTF-8 locale:
+
+guess_legacy_encoding () {
+    # Guess the legacy encoding used by the language/country
+    # found in the current LC_CTYPE value.
+
+    # First determine the LC_CTYPE locale category setting
+    ctype=${LC_ALL-${LC_CTYPE-${LANG-en_US}}}
+
+    case $ctype in
+	  zh_TW*)
+             LEGACY_ENCODING=Big5
+	     ;;
+  	  zh_HK*)
+             LEGACY_ENCODING=Big5HKSCS
+	     ;;
+	  zh*)
+             LEGACY_ENCODING=GB18030
+	     ;;
+	  ja*)
+             LEGACY_ENCODING=EUC-JP
+	     ;;
+	  ko*)
+             LEGACY_ENCODING=EUC-KR
+	     ;;
+	  ru*)
+             LEGACY_ENCODING=KOI8-R
+	     ;;
+	  uk*)
+             LEGACY_ENCODING=KOI8-U
+	     ;;
+	  pl*|hr*|hu*|cs*|sk*|sl*)
+             LEGACY_ENCODING=ISO-8859-2
+	     ;;
+	  eo*|mt*)
+             LEGACY_ENCODING=ISO-8859-3
+	     ;;
+	  el*)
+             LEGACY_ENCODING=ISO-8859-7
+	     ;;
+	  he*)
+             LEGACY_ENCODING=ISO-8859-8
+	     ;;
+	  tr*)
+             LEGACY_ENCODING=ISO-8859-9
+	     ;;
+	  th*)
+             LEGACY_ENCODING=TIS-620      # or ISO-8859-11
+	     ;;
+	  lt*)
+             LEGACY_ENCODING=ISO-8859-13
+	     ;;
+	  cy*)
+             LEGACY_ENCODING=ISO-8859-14
+	     ;;
+	  ro*)
+             LEGACY_ENCODING=ISO-8859-14  # or ISO-8859-16
+	     ;;
+	  am*|vi*)
+             LEGACY_ENCODING=UTF-8
+	     ;;
+          *)
+             LEGACY_ENCODING=ISO-8859-1
+             ;;
+    esac
+}
+
+guess_legacy_encoding;
+
+TMPDIR=`mktemp -d /tmp/nroff.XXXXXX`
+if [ $? -ne 0 ]; then
+        echo "$0: Can't create temp directory, exiting..."
+        exit 1
+fi
+trap "exec rm -rf $TMPDIR" EXIT SIGHUP SIGINT SIGPIPE SIGTERM SIGIO
+
+# parse groff options to find out whether a file was given as argument or whether the
+# input is read from stdin:
+OLDARGS=""
+TEMP=$(getopt --options  "abcCd:eEf:F:gGhiI:lL:m:M:n:No:pP:r:RsStT:UvVw:W:XzZ" --longoptions help,version -- ${1+"$@"})
+eval set -- "$TEMP"
+while true ; do
+    case "$1" in
+	--)
+	    if [ -n "$2" ] ; then
+		INPUTFILE="$2"
+		shift 2
+	    else
+		INPUTFILE=""
+		shift 1
+	    fi
+	    break
+	    ;;
+	*)
+	    OLDARGS="$OLDARGS $1"
+	    echo $1
+	    shift 1
+	    ;;
+    esac
+done
+eval set -- "$OLDARGS"
+
+if [ -n "$INPUTFILE" ] ; then
+    # input comes from a file
+    cat "$INPUTFILE" > $TMPDIR/input
+else
+    # input comes from stdin
+    cat > $TMPDIR/input
+fi
+
+#iconv -s -c -f utf-8 -t utf-8 < $TMPDIR/input > /dev/null
+#if [ $? -eq 0 ]; then
+#    iconv -s -c -f utf-8 -t $LEGACY_ENCODING < $TMPDIR/input > $TMPDIR/input.new
+#    mv $TMPDIR/input.new $TMPDIR/input
+#fi
+
+ICONV="cat"
+case "`locale charmap 2>/dev/null`" in
+    UTF-8)
+    case "${LANGUAGE-${LC_ALL-${LC_MESSAGES-${LANG}}}}" in
+        ja*)
+        # Japanese man page in UTF-8 locale, special case!
+        # force the device 'nippon' to run groff in ja_JP.eucJP locale
+        # and convert the result to UTF-8 using iconv:
+        T=-Tnippon
+        export LC_ALL=ja_JP.eucJP
+        ICONV="iconv -f EUC-JP -t UTF-8"
+        ;;
+        zh_TW*)
+        T=-Tnippon
+        export LC_ALL=zh_TW.Big5
+        ICONV="iconv -f Big5 -t UTF-8"
+        ;;
+        zh_HK*)
+        T=-Tnippon
+        export LC_ALL=zh_HK.Big5HKSCS
+        ICONV="iconv -f Big5HKSCS -t UTF-8"
+        ;;
+        zh*)
+        T=-Tnippon
+        export LC_ALL=zh_CN.GB18030
+        ICONV="iconv -f GB18030 -t UTF-8"
+        ;;
+        ko*)
+        T=-Tlatin1
+        export LC_ALL=ko_KR.EUC-KR
+        # See https://bugzilla.novell.com/show_bug.cgi?id=470921
+        # for the reason why the "-c" is needed and
+        # why a conversion from ISO-8859-1 instead of EUC-KR to
+        # UTF-8 may be needed if an English man-page is displayed:
+        ICONV="iconv -c -f EUC-KR -t UTF-8"
+        iconv -s -f ASCII -t UTF-8 < $TMPDIR/input > /dev/null
+        if [ $? -eq 0 ]; then
+            ICONV="iconv -f ISO-8859-1 -t UTF-8"
+        fi
+        ;;
+        # make 'man iso-8859-15' display correctly in UTF-8 locales using Euro
+        ca_ES*|de_AT*|de_BE*|de_DE*|de_LU*|en_BE*|en_IE*|es_ES*|eu_ES*|fi_FI*|fr_BE*|fr_FR*|fr_LU*|ga_IE*|gl_ES*|it_IT*|nl_BE*|nl_NL*|pt_PT*|sv_FI*|wa_BE*)
+        T=-Tlatin1
+        export LC_ALL=de_DE@euro
+        ICONV="iconv -f ISO-8859-15 -t UTF-8"
+        ;;
+    esac
+    ;;
+esac
+
 # This shell script is intended for use with man, so warnings are
 # probably not wanted.  Also load nroff-style character definitions.
 
-: ${GROFF_BIN_PATH=@BINDIR@}
+: ${GROFF_BIN_PATH=@BINDIR@}
 export GROFF_BIN_PATH
-PATH=$GROFF_BIN_PATH:$PATH groff -mtty-char $T $opts ${1+"$@"}
+PATH=$GROFF_BIN_PATH:$PATH groff -mtty-char $T $opts ${1+"$@"} < $TMPDIR/input | $ICONV
 
 # eof

Places

File utf8.patch of Package groff

Places