merged tcl 8.1 branch back into the main trunk

1 files changed, 110 insertions, 0 deletions

diff --git a/tools/encoding/Makefile b/tools/encoding/Makefile
new file mode 100644
index 0000000..4c10673
--- /dev/null
+++ b/tools/encoding/Makefile
@@ -0,0 +1,110 @@
+#
+# This file is a Makefile to compile all the encoding files.  
+#
+# Run "make" to compile all the encoding files (*.txt,*.esc) into the
+# format that Tcl can use (*.enc).  It is your responsibility to move the
+# encoding files to the appropriate place ($TCL_ROOT/library/encoding
+#
+# The .txt files in this directory come from the Unicode CD and are covered
+# by the following copyright notice:
+#
+#---------------------------------------------------------------------------
+#
+# Copyright (c) 1996 Unicode, Inc.  All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose.  No
+# warranties of any kind are expressed or implied.  The recipient
+# agrees to determine applicability of information provided.  If this
+# file has been provided on magnetic media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Recipient is granted the right to make copies in any form for
+# internal distribution and to freely use the information supplied
+# in the creation of products supporting Unicode.  Unicode, Inc.
+# specifically excludes the right to re-distribute this file directly
+# to third parties or other organizations whether for profit or not.
+#
+# In other words:  Don't put this file on the Internet.  People who want to 
+# get it over the Internet should do so directly from ftp://unicode.org.  They
+# can therefore be assured of getting the most recent and accurate version.
+#
+#----------------------------------------------------------------------------
+#
+# The txt2enc program built by this makefile is used to compile individual
+# .txt files into .enc files, the format that Tcl understands for encoding 
+# files.  This compilation to a different format is allowed by the above
+# restriction. 
+#
+# The files shiftjis.txt and jis0208.txt were modified from the original
+# ones provided on the Unicode CD.  The double-width backslash character
+# 0x815F in these two Japanese encodings was being mapped to Unicode 005C
+# (REVERSE SOLIDUS), the normal backslash character.  They have been
+# changed to map 0x815F to Unicode FF3C (FULLWIDTH REVERSE SOLIDUS) and let
+# the regular backslash character map to itself.  This follows how cp932
+# behaves.
+#
+# Copyright (c) 1998 Sun Microsystems, Inc.
+#
+# See the file "license.terms" for information on usage and redistribution
+# of this file, and for a DISCLAIMER OF ALL WARRANTIES.
+#
+# SCCS: @(#) Makefile 1.1 98/01/28 11:41:36
+#
+
+EUC_ENCODINGS = euc-cn.txt euc-kr.txt euc-jp.txt 
+
+encodings: clean txt2enc $(EUC_ENCODINGS)
+	@echo Compiling encoding files.
+	@for p in *.esc; do \
+	    base=`echo $$p | sed 's/\..*$$//'`; \
+	    echo $$base.enc; \
+	    echo "# Encoding file: $$base, escape-driven" > $$base.enc; \
+	    echo "E" >> $$base.enc; \
+	    cat $$p >> $$base.enc; \
+	done
+	@for p in *.txt; do \
+	    enc=`echo $$p | sed 's/\..*$$/\.enc/'`; \
+	    echo $$enc; \
+	    ./txt2enc -e 0 -u 1 $$p > $$enc; \
+	done
+	@echo 
+	@echo Compiling special versions of encoding files.
+	@for p in ascii.txt; do \
+	    enc=`echo $$p | sed 's/\..*$$/\.enc/'`; \
+	    echo $$enc; \
+	    ./txt2enc -m $$p > $$enc; \
+	done
+	@for p in jis0208.txt; do \
+	    enc=`echo $$p | sed 's/\..*$$/\.enc/'`; \
+	    echo $$enc; \
+	    ./txt2enc -e 1 -u 2 $$p > $$enc; \
+	done
+	@for p in symbol.txt dingbats.txt macDingbats.txt; do \
+	    enc=`echo $$p | sed 's/\..*$$/\.enc/'`; \
+	    echo $$enc; \
+	    ./txt2enc -e 0 -u 1 -s $$p > $$enc; \
+	done
+
+clean:
+	@rm -f txt2enc *.enc $(EUC_ENCODINGS)
+
+txt2enc: txt2enc.c
+	@gcc -o txt2enc txt2enc.c
+
+euc-jp.txt: ascii.txt jis0208.txt Makefile
+	@echo Building euc-jp.txt from components.
+	@cat ascii.txt > euc-jp.txt
+	@grep '^0x[A-F]' jis0201.txt | sed 's/0x/0x8E/' >> euc-jp.txt
+	@cat jis0208.txt | awk 'BEGIN {print "ibase=16"} index($$1,"#") != 1 {print substr($$2,3) "+" 8080; print substr($$3,3)}' | bc | awk '{ str = $$1; getline; printf "0x%04x 0x%04x\n", str, $$0}' >> euc-jp.txt
+
+euc-kr.txt: ascii.txt ksc5601.txt Makefile
+	@echo Building euc-kr.txt from components.
+	@cat ascii.txt > euc-kr.txt
+	@cat ksc5601.txt | awk 'BEGIN {print "ibase=16"} index($$1,"#") != 1 {print substr($$1,3) "+" 8080; print substr($$2,3)}' | bc | awk '{ str = $$1; getline; printf "0x%04x 0x%04x\n", str, $$0}' >> euc-kr.txt
+
+euc-cn.txt: ascii.txt gb2312.txt Makefile
+	@echo Building euc-cn.txt from components.
+	@cat ascii.txt > euc-cn.txt
+	@cat gb2312.txt | awk 'BEGIN {print "ibase=16"} index($$1,"#") != 1 {print substr($$1,3) "+" 8080; print substr($$2,3)}' | bc | awk '{ str = $$1; getline; printf "0x%04x 0x%04x\n", str, $$0}' >> euc-cn.txt