New directory
[bpt/emacs.git] / admin / charsets / mapconv
1 #!/bin/sh
2 #
3 # Copyright (C) 2003
4 # National Institute of Advanced Industrial Science and Technology (AIST)
5 # Registration Number H13PRO009
6 #
7 # This file is part of GNU Emacs.
8 #
9 # GNU Emacs is free software; you can redistribute it and/or modify
10 # it under the terms of the GNU General Public License as published by
11 # the Free Software Foundation; either version 2, or (at your option)
12 # any later version.
13 #
14 # GNU Emacs is distributed in the hope that it will be useful,
15 # but WITHOUT ANY WARRANTY; without even the implied warranty of
16 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17 # GNU General Public License for more details.
18 #
19 # You should have received a copy of the GNU General Public License
20 # along with GNU Emacs; see the file COPYING. If not, write to the
21 # Free Software Foundation, Inc., 59 Temple Place - Suite 330,
22 # Boston, MA 02111-1307, USA.
23
24 # Comment:
25 # Convert charset map of various format into this:
26 # 0xXX 0xYYYY
27 # where,
28 # XX is a code point of the charset in hexa-decimal,
29 # YYYY is the corresponding Unicode character code in hexa-decimal.
30 # Arguments are:
31 # $1: source map file
32 # $2: address pattern for sed (optionally with substitution command)
33 # $3: format of source map file
34 # GLIBC-1 GLIBC-2 GLIBC-2-7 CZYBORRA IANA UNICODE YASUOKA MICROSOFT
35 # $4: awk script
36
37 BASE=`basename $1`
38
39 case "$3" in
40 GLIBC*)
41 SOURCE=`echo $1 | sed 's/.*\(glibc.*$\)/\1/'`;;
42 CZYBORRA)
43 SOURCE="http://czyborra.com/charsets/${BASE}";;
44 IANA)
45 SOURCE="http://www.iana.org/assignments/charset-reg/${BASE}";;
46 UNICODE)
47 SOURCE="http://www.unicode.org/Public/MAPPINGS/.../${BASE}";;
48 YASUOKA)
49 SOURCE="http://kanji.zinbun.kyoto-u.ac.jp/~yasuoka/.../${BASE}";;
50 MICROSOFT)
51 SOURCE="http://www.microsoft.com/globaldev/reference/oem/${BASE}";;
52 *)
53 echo "Unknown file type: $3";
54 exit 1;;
55 esac
56
57 echo "# Generated from $SOURCE"
58
59 if [ -n "$4" ] ; then
60 if [ -f "$4" ] ; then
61 AWKPROG="gawk -f $4"
62 else
63 echo "Awk program does not exist: $4"
64 exit 1
65 fi
66 else
67 AWKPROG=cat
68 fi
69
70 if [ "$3" == "GLIBC-1" ] ; then
71 # Source format is:
72 # <UYYYY> /xXX
73 sed -n -e "$2 p" < $1 \
74 | sed -e 's,<U\([^>]*\)>[ ]*/x\(..\).*,0x\2 0x\1,' \
75 | sort | ${AWKPROG}
76 elif [ "$3" == "GLIBC-2" ] ; then
77 # Source format is:
78 # <UYYYY> /xXX/xZZ
79 sed -n -e "$2 p" < $1 \
80 | sed -e 's,<U\([^>]*\)>[ ]*/x\(..\)/x\(..\).*,0x\2\3 0x\1,' \
81 | sort | ${AWKPROG}
82 elif [ "$3" == "GLIBC-2-7" ] ; then
83 # Source format is:
84 # <UYYYY> /xXX/xZZ
85 # We must drop MSBs of XX and ZZ
86 sed -n -e "$2 p" < $1 \
87 | sed -e 's/xa/x2/g' -e 's/xb/x3/g' -e 's/xc/x4/g' \
88 -e 's/xd/x5/g' -e 's/xe/x6/g' -e 's/xf/x7/g' \
89 -e 's,<U\([^>]*\)>[ ]*/x\(..\)/x\(..\).*,0x\2\3 0x\1,' \
90 | tee temp \
91 | sort | ${AWKPROG}
92 elif [ "$3" == "CZYBORRA" ] ; then
93 # Source format is:
94 # =XX U+YYYY
95 zcat $1 | sed -n -e "$2 p" \
96 | sed -e 's/=\(..\)[^U]*U+\([0-9A-F]*\).*/0x\1 0x\2/' \
97 | sort | ${AWKPROG}
98 elif [ "$3" == "IANA" ] ; then
99 # Source format is:
100 # 0xXX 0xYYYY
101 sed -n -e "$2 p" < $1 \
102 | sed -e 's/\(0x[0-9A-Fa-f]*\)[^0]*\(0x[0-9A-Fa-f]*\).*/\1 \2/' \
103 | sort | ${AWKPROG}
104 elif [ "$3" == "UNICODE" ] ; then
105 # Source format is:
106 # YYYY XX
107 sed -n -e "$2 p" < $1 \
108 | sed -e 's/\([0-9A-F]*\)[^0-9A-F]*\([0-9A-F]*\).*/0x\2 0x\1/' \
109 | sort | ${AWKPROG}
110 elif [ "$3" == "YASUOKA" ] ; then
111 # Source format is:
112 # YYYY 0-XXXX (XXXX is a Kuten code)
113 sed -n -e "$2 p" < $1 \
114 | sed -e 's/\([0-9A-F]*\)[^0]*0-\([0-9]*\).*/0x\2 0x\1/' \
115 | sort | ${AWKPROG}
116 elif [ "$3" == "MICROSOFT" ] ; then
117 # Source format is:
118 # XX = U+YYYY
119 sed -n -e "$2 p" < $1 \
120 | sed -e 's/\([0-9A-F]*\).*U+\([0-9A-F]*\).*/0x\1 0x\2/' \
121 | sort | ${AWKPROG}
122 else
123 echo "Invalid arguments"
124 exit 1
125 fi