annotate jcode.pl @ 1:0b233d5d1944

added .htaccess
author Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
date Sun, 06 Jun 2010 22:01:03 +0900
parents a2f0a2c135cf
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
1 package jcode;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
2 ;######################################################################
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
3 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
4 ;# jcode.pl: Perl library for Japanese character code conversion
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
5 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
6 ;# Copyright (c) 1995-1999 Kazumasa Utashiro <utashiro@iij.ad.jp>
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
7 ;# Internet Initiative Japan Inc.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
8 ;# 3-13 Kanda Nishiki-cho, Chiyoda-ku, Tokyo 101-0054, Japan
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
9 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
10 ;# Copyright (c) 1992,1993,1994 Kazumasa Utashiro
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
11 ;# Software Research Associates, Inc.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
12 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
13 ;# Use and redistribution for ANY PURPOSE are granted as long as all
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
14 ;# copyright notices are retained. Redistribution with modification
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
15 ;# is allowed provided that you make your modified version obviously
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
16 ;# distinguishable from the original one. THIS SOFTWARE IS PROVIDED
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
17 ;# BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES ARE
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
18 ;# DISCLAIMED.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
19 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
20 ;# Original version was developed under the name of srekcah@sra.co.jp
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
21 ;# February 1992 and it was called kconv.pl at the beginning. This
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
22 ;# address was a pen name for group of individuals and it is no longer
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
23 ;# valid.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
24 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
25 ;# The latest version is available here:
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
26 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
27 ;# ftp://ftp.iij.ad.jp/pub/IIJ/dist/utashiro/perl/
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
28 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
29 ;; $rcsid = q$Id: jcode.pl,v 2.11 1999/12/26 17:16:47 utashiro Exp $;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
30 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
31 ;######################################################################
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
32 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
33 ;# PERL4 INTERFACE:
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
34 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
35 ;# &jcode'getcode(*line)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
36 ;# Return 'jis', 'sjis', 'euc' or undef according to
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
37 ;# Japanese character code in $line. Return 'binary' if
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
38 ;# the data has non-character code.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
39 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
40 ;# When evaluated in array context, it returns a list
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
41 ;# contains two items. First value is the number of
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
42 ;# characters which matched to the expected code, and
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
43 ;# second value is the code name. It is useful if and
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
44 ;# only if the number is not 0 and the code is undef;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
45 ;# that case means it couldn't tell 'euc' or 'sjis'
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
46 ;# because the evaluation score was exactly same. This
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
47 ;# interface is too tricky, though.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
48 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
49 ;# Code detection between euc and sjis is very difficult
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
50 ;# or sometimes impossible or even lead to wrong result
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
51 ;# when it includes JIS X0201 KANA characters. So JIS
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
52 ;# X0201 KANA is ignored for automatic code detection.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
53 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
54 ;# &jcode'convert(*line, $ocode [, $icode [, $option]])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
55 ;# Convert the contents of $line to the specified
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
56 ;# Japanese code given in the second argument $ocode.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
57 ;# $ocode can be any of "jis", "sjis" or "euc", or use
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
58 ;# "noconv" when you don't want the code conversion.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
59 ;# Input code is recognized automatically from the line
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
60 ;# itself when $icode is not supplied (JIS X0201 KANA is
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
61 ;# ignored in code detection. See the above descripton
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
62 ;# of &getcode). $icode also can be specified, but
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
63 ;# xxx2yyy routine is more efficient when both codes are
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
64 ;# known.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
65 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
66 ;# It returns the code of input string in scalar context,
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
67 ;# and a list of pointer of convert subroutine and the
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
68 ;# input code in array context.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
69 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
70 ;# Japanese character code JIS X0201, X0208, X0212 and
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
71 ;# ASCII code are supported. X0212 characters can not be
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
72 ;# represented in SJIS and they will be replased by
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
73 ;# "geta" character when converted to SJIS.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
74 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
75 ;# See next paragraph for $option parameter.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
76 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
77 ;# &jcode'xxx2yyy(*line [, $option])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
78 ;# Convert the Japanese code from xxx to yyy. String xxx
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
79 ;# and yyy are any convination from "jis", "euc" or
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
80 ;# "sjis". They return *approximate* number of converted
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
81 ;# bytes. So return value 0 means the line was not
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
82 ;# converted at all.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
83 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
84 ;# Optional parameter $option is used to specify optional
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
85 ;# conversion method. String "z" is for JIS X0201 KANA
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
86 ;# to X0208 KANA, and "h" is for reverse.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
87 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
88 ;# $jcode'convf{'xxx', 'yyy'}
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
89 ;# The value of this associative array is pointer to the
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
90 ;# subroutine jcode'xxx2yyy().
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
91 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
92 ;# &jcode'to($ocode, $line [, $icode [, $option]])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
93 ;# &jcode'jis($line [, $icode [, $option]])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
94 ;# &jcode'euc($line [, $icode [, $option]])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
95 ;# &jcode'sjis($line [, $icode [, $option]])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
96 ;# These functions are prepared for easy use of
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
97 ;# call/return-by-value interface. You can use these
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
98 ;# funcitons in s///e operation or any other place for
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
99 ;# convenience.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
100 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
101 ;# &jcode'jis_inout($in, $out)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
102 ;# Set or inquire JIS start and end sequences. Default
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
103 ;# is "ESC-$-B" and "ESC-(-B". If you supplied only one
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
104 ;# character, "ESC-$" or "ESC-(" is prepended for each
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
105 ;# character respectively. Acutually "ESC-(-B" is not a
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
106 ;# sequence to end JIS code but a sequence to start ASCII
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
107 ;# code set. So `in' and `out' are somewhat misleading.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
108 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
109 ;# &jcode'get_inout($string)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
110 ;# Get JIS start and end sequences from $string.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
111 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
112 ;# &jcode'cache()
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
113 ;# &jcode'nocache()
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
114 ;# &jcode'flush()
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
115 ;# Usually, converted character is cached in memory to
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
116 ;# avoid same calculations have to be done many times.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
117 ;# To disable this caching, call &jcode'nocache(). It
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
118 ;# can be revived by &jcode'cache() and cache is flushed
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
119 ;# by calling &jcode'flush(). &cache() and &nocache()
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
120 ;# functions return previous caching state.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
121 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
122 ;# ---------------------------------------------------------------
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
123 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
124 ;# &jcode'h2z_xxx(*line)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
125 ;# JIS X0201 KANA (so-called Hankaku-KANA) to X0208 KANA
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
126 ;# (Zenkaku-KANA) code conversion routine. String xxx is
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
127 ;# any of "jis", "sjis" and "euc". From the difficulty
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
128 ;# of recognizing code set from 1-byte KATAKANA string,
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
129 ;# automatic code recognition is not supported.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
130 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
131 ;# &jcode'z2h_xxx(*line)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
132 ;# X0208 to X0201 KANA code conversion routine. String
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
133 ;# xxx is any of "jis", "sjis" and "euc".
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
134 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
135 ;# $jcode'z2hf{'xxx'}
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
136 ;# $jcode'h2zf{'xxx'}
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
137 ;# These are pointer to the corresponding function just
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
138 ;# as $jcode'convf.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
139 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
140 ;# ---------------------------------------------------------------
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
141 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
142 ;# &jcode'tr(*line, $from, $to [, $option])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
143 ;# &jcode'tr emulates tr operator for 2 byte code. Only 'd'
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
144 ;# is interpreted as an option.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
145 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
146 ;# Range operator like `A-Z' for 2 byte code is partially
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
147 ;# supported. Code must be JIS or EUC, and first byte
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
148 ;# have to be same on first and last character.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
149 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
150 ;# CAUTION: Handling range operator is a kind of trick
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
151 ;# and it is not perfect. So if you need to transfer `-'
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
152 ;# character, please be sure to put it at the beginning
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
153 ;# or the end of $from and $to strings.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
154 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
155 ;# &jcode'trans($line, $from, $to [, $option)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
156 ;# Same as &jcode'tr but accept string and return string
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
157 ;# after translation.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
158 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
159 ;# ---------------------------------------------------------------
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
160 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
161 ;# &jcode'init()
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
162 ;# Initialize the variables used in this package. You
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
163 ;# don't have to call this when using jocde.pl by `do' or
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
164 ;# `require' interface. Call it first if you embedded
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
165 ;# the jcode.pl at the end of your script.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
166 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
167 ;######################################################################
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
168 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
169 ;# PERL5 INTERFACE:
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
170 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
171 ;# Current jcode.pl is written in Perl 4 but it is possible to use
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
172 ;# from Perl 5 using `references'. Fully perl5 capable version is
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
173 ;# future issue.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
174 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
175 ;# Since lexical variable is not a subject of typeglob, *string style
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
176 ;# call doesn't work if the variable is declared as `my'. Same thing
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
177 ;# happens to special variable $_ if the perl is compiled to use
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
178 ;# thread capability. So using reference is generally recommented to
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
179 ;# avoid the mysterious error.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
180 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
181 ;# jcode::getcode(\$line)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
182 ;# jcode::convert(\$line, $ocode [, $icode [, $option]])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
183 ;# jcode::xxx2yyy(\$line [, $option])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
184 ;# &{$jcode::convf{'xxx', 'yyy'}}(\$line)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
185 ;# jcode::to($ocode, $line [, $icode [, $option]])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
186 ;# jcode::jis($line [, $icode [, $option]])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
187 ;# jcode::euc($line [, $icode [, $option]])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
188 ;# jcode::sjis($line [, $icode [, $option]])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
189 ;# jcode::jis_inout($in, $out)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
190 ;# jcode::get_inout($string)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
191 ;# jcode::cache()
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
192 ;# jcode::nocache()
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
193 ;# jcode::flush()
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
194 ;# jcode::h2z_xxx(\$line)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
195 ;# jcode::z2h_xxx(\$line)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
196 ;# &{$jcode::z2hf{'xxx'}}(\$line)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
197 ;# &{$jcode::h2zf{'xxx'}}(\$line)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
198 ;# jcode::tr(\$line, $from, $to [, $option])
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
199 ;# jcode::trans($line, $from, $to [, $option)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
200 ;# jcode::init()
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
201 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
202 ;######################################################################
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
203 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
204 ;# SAMPLES
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
205 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
206 ;# Convert any Kanji code to JIS and print each line with code name.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
207 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
208 ;# while (defined($s = <>)) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
209 ;# $code = &jcode'convert(*s, 'jis');
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
210 ;# print $code, "\t", $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
211 ;# }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
212 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
213 ;# Convert all lines to JIS according to the first recognized line.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
214 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
215 ;# while (defined($s = <>)) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
216 ;# print, next unless $s =~ /[\033\200-\377]/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
217 ;# (*f, $icode) = &jcode'convert(*s, 'jis');
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
218 ;# print;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
219 ;# defined(&f) || next;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
220 ;# while (<>) { &f(*s); print; }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
221 ;# last;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
222 ;# }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
223 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
224 ;# The safest way of JIS conversion.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
225 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
226 ;# while (defined($s = <>)) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
227 ;# ($matched, $icode) = &jcode'getcode(*s);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
228 ;# if (@buf == 0 && $matched == 0) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
229 ;# print $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
230 ;# next;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
231 ;# }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
232 ;# push(@buf, $s);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
233 ;# next unless $icode;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
234 ;# while (defined($s = shift(@buf))) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
235 ;# &jcode'convert(*s, 'jis', $icode);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
236 ;# print $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
237 ;# }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
238 ;# while (defined($s = <>)) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
239 ;# &jcode'convert(*s, 'jis', $icode);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
240 ;# print $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
241 ;# }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
242 ;# last;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
243 ;# }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
244 ;# print @buf if @buf;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
245 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
246 ;######################################################################
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
247
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
248 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
249 ;# Call initialize function if it is not called yet. This may sound
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
250 ;# strange but it makes easy to embed the jcode.pl at the end of
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
251 ;# script. Call &jcode'init at the beginning of the script in that
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
252 ;# case.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
253 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
254 &init unless defined $version;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
255
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
256 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
257 ;# Initialize variables.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
258 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
259 sub init {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
260 $version = $rcsid =~ /,v ([\d.]+)/ ? $1 : 'unkown';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
261
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
262 $re_bin = '[\000-\006\177\377]';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
263
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
264 $re_jis0208_1978 = '\e\$\@';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
265 $re_jis0208_1983 = '\e\$B';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
266 $re_jis0208_1990 = '\e&\@\e\$B';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
267 $re_jis0208 = "$re_jis0208_1978|$re_jis0208_1983|$re_jis0208_1990";
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
268 $re_jis0212 = '\e\$\(D';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
269 $re_jp = "$re_jis0208|$re_jis0212";
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
270 $re_asc = '\e\([BJ]';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
271 $re_kana = '\e\(I';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
272
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
273 $esc_0208 = "\e\$B";
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
274 $esc_0212 = "\e\$(D";
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
275 $esc_asc = "\e(B";
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
276 $esc_kana = "\e(I";
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
277
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
278 $re_sjis_c = '[\201-\237\340-\374][\100-\176\200-\374]';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
279 $re_sjis_kana = '[\241-\337]';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
280
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
281 $re_euc_c = '[\241-\376][\241-\376]';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
282 $re_euc_kana = '\216[\241-\337]';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
283 $re_euc_0212 = '\217[\241-\376][\241-\376]';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
284
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
285 # Use `geta' for undefined character code
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
286 $undef_sjis = "\x81\xac";
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
287
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
288 $cache = 1;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
289
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
290 # X0201 -> X0208 KANA conversion table. Looks weird? Not that
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
291 # much. This is simply JIS text without escape sequences.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
292 ($h2z_high = $h2z = <<'__TABLE_END__') =~ tr/\041-\176/\241-\376/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
293 ! !# $ !" % !& " !V # !W
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
294 ^ !+ _ !, 0 !<
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
295 ' %! ( %# ) %% * %' + %)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
296 , %c - %e . %g / %C
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
297 1 %" 2 %$ 3 %& 4 %( 5 %*
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
298 6 %+ 7 %- 8 %/ 9 %1 : %3
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
299 6^ %, 7^ %. 8^ %0 9^ %2 :^ %4
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
300 ; %5 < %7 = %9 > %; ? %=
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
301 ;^ %6 <^ %8 =^ %: >^ %< ?^ %>
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
302 @ %? A %A B %D C %F D %H
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
303 @^ %@ A^ %B B^ %E C^ %G D^ %I
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
304 E %J F %K G %L H %M I %N
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
305 J %O K %R L %U M %X N %[
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
306 J^ %P K^ %S L^ %V M^ %Y N^ %\
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
307 J_ %Q K_ %T L_ %W M_ %Z N_ %]
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
308 O %^ P %_ Q %` R %a S %b
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
309 T %d U %f V %h
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
310 W %i X %j Y %k Z %l [ %m
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
311 \ %o ] %s & %r 3^ %t
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
312 __TABLE_END__
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
313 %h2z = split(/\s+/, $h2z . $h2z_high);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
314 %z2h = reverse %h2z;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
315
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
316 $convf{'jis' , 'jis' } = *jis2jis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
317 $convf{'jis' , 'sjis'} = *jis2sjis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
318 $convf{'jis' , 'euc' } = *jis2euc;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
319 $convf{'euc' , 'jis' } = *euc2jis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
320 $convf{'euc' , 'sjis'} = *euc2sjis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
321 $convf{'euc' , 'euc' } = *euc2euc;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
322 $convf{'sjis' , 'jis' } = *sjis2jis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
323 $convf{'sjis' , 'sjis'} = *sjis2sjis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
324 $convf{'sjis' , 'euc' } = *sjis2euc;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
325 $h2zf{'jis' } = *h2z_jis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
326 $z2hf{'jis' } = *z2h_jis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
327 $h2zf{'euc' } = *h2z_euc;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
328 $z2hf{'euc' } = *z2h_euc;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
329 $h2zf{'sjis'} = *h2z_sjis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
330 $z2hf{'sjis'} = *z2h_sjis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
331 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
332
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
333 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
334 ;# Set escape sequences which should be put before and after Japanese
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
335 ;# (JIS X0208) string.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
336 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
337 sub jis_inout {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
338 $esc_0208 = shift || $esc_0208;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
339 $esc_0208 = "\e\$$esc_0208" if length($esc_0208) == 1;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
340 $esc_asc = shift || $esc_asc;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
341 $esc_asc = "\e\($esc_asc" if length($esc_asc) == 1;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
342 ($esc_0208, $esc_asc);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
343 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
344
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
345 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
346 ;# Get JIS in and out sequences from the string.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
347 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
348 sub get_inout {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
349 local($esc_0208, $esc_asc);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
350 $_[$[] =~ /($re_jis0208)/o && ($esc_0208 = $1);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
351 $_[$[] =~ /($re_asc)/o && ($esc_asc = $1);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
352 ($esc_0208, $esc_asc);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
353 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
354
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
355 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
356 ;# Recognize character code.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
357 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
358 sub getcode {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
359 local(*s) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
360 local($matched, $code);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
361
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
362 if ($s !~ /[\e\200-\377]/) { # not Japanese
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
363 $matched = 0;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
364 $code = undef;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
365 } # 'jis'
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
366 elsif ($s =~ /$re_jp|$re_asc|$re_kana/o) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
367 $matched = 1;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
368 $code = 'jis';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
369 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
370 elsif ($s =~ /$re_bin/o) { # 'binary'
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
371 $matched = 0;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
372 $code = 'binary';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
373 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
374 else { # should be 'euc' or 'sjis'
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
375 local($sjis, $euc) = (0, 0);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
376
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
377 while ($s =~ /(($re_sjis_c)+)/go) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
378 $sjis += length($1);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
379 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
380 while ($s =~ /(($re_euc_c|$re_euc_kana|$re_euc_0212)+)/go) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
381 $euc += length($1);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
382 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
383 $matched = &max($sjis, $euc);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
384 $code = ('euc', undef, 'sjis')[($sjis<=>$euc) + $[ + 1];
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
385 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
386 wantarray ? ($matched, $code) : $code;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
387 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
388 sub max { $_[ $[ + ($_[ $[ ] < $_[ $[ + 1 ]) ]; }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
389
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
390 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
391 ;# Convert any code to specified code.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
392 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
393 sub convert {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
394 local(*s, $ocode, $icode, $opt) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
395 return (undef, undef) unless $icode = $icode || &getcode(*s);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
396 return (undef, $icode) if $icode eq 'binary';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
397 $ocode = 'jis' unless $ocode;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
398 $ocode = $icode if $ocode eq 'noconv';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
399 local(*f) = $convf{$icode, $ocode};
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
400 &f(*s, $opt);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
401 wantarray ? (*f, $icode) : $icode;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
402 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
403
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
404 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
405 ;# Easy return-by-value interfaces.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
406 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
407 sub jis { &to('jis', @_); }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
408 sub euc { &to('euc', @_); }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
409 sub sjis { &to('sjis', @_); }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
410 sub to {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
411 local($ocode, $s, $icode, $opt) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
412 &convert(*s, $ocode, $icode, $opt);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
413 $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
414 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
415 sub what {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
416 local($s) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
417 &getcode(*s);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
418 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
419 sub trans {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
420 local($s) = shift;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
421 &tr(*s, @_);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
422 $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
423 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
424
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
425 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
426 ;# SJIS to JIS
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
427 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
428 sub sjis2jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
429 local(*s, $opt, $n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
430 &sjis2sjis(*s, $opt) if $opt;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
431 $s =~ s/(($re_sjis_c|$re_sjis_kana)+)/&_sjis2jis($1) . $esc_asc/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
432 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
433 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
434 sub _sjis2jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
435 local($s) = shift;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
436 $s =~ s/(($re_sjis_c)+|($re_sjis_kana)+)/&__sjis2jis($1)/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
437 $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
438 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
439 sub __sjis2jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
440 local($s) = shift;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
441 if ($s =~ /^$re_sjis_kana/o) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
442 $n += $s =~ tr/\241-\337/\041-\137/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
443 $esc_kana . $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
444 } else {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
445 $n += $s =~ s/($re_sjis_c)/$s2e{$1}||&s2e($1)/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
446 $s =~ tr/\241-\376/\041-\176/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
447 $esc_0208 . $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
448 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
449 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
450
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
451 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
452 ;# EUC to JIS
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
453 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
454 sub euc2jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
455 local(*s, $opt, $n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
456 &euc2euc(*s, $opt) if $opt;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
457 $s =~ s/(($re_euc_c|$re_euc_kana|$re_euc_0212)+)/
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
458 &_euc2jis($1) . $esc_asc
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
459 /geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
460 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
461 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
462 sub _euc2jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
463 local($s) = shift;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
464 $s =~ s/(($re_euc_c)+|($re_euc_kana)+|($re_euc_0212)+)/&__euc2jis($1)/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
465 $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
466 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
467 sub __euc2jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
468 local($s) = shift;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
469 local($esc);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
470
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
471 if ($s =~ tr/\216//d) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
472 $esc = $esc_kana;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
473 } elsif ($s =~ tr/\217//d) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
474 $esc = $esc_0212;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
475 } else {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
476 $esc = $esc_0208;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
477 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
478
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
479 $n += $s =~ tr/\241-\376/\041-\176/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
480 $esc . $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
481 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
482
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
483 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
484 ;# JIS to EUC
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
485 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
486 sub jis2euc {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
487 local(*s, $opt, $n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
488 $s =~ s/($re_jp|$re_asc|$re_kana)([^\e]*)/&_jis2euc($1,$2)/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
489 &euc2euc(*s, $opt) if $opt;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
490 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
491 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
492 sub _jis2euc {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
493 local($esc, $s) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
494 if ($esc !~ /^$re_asc/o) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
495 $n += $s =~ tr/\041-\176/\241-\376/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
496 if ($esc =~ /^$re_kana/o) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
497 $s =~ s/([\241-\337])/\216$1/g;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
498 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
499 elsif ($esc =~ /^$re_jis0212/o) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
500 $s =~ s/([\241-\376][\241-\376])/\217$1/g;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
501 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
502 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
503 $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
504 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
505
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
506 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
507 ;# JIS to SJIS
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
508 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
509 sub jis2sjis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
510 local(*s, $opt, $n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
511 &jis2jis(*s, $opt) if $opt;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
512 $s =~ s/($re_jp|$re_asc|$re_kana)([^\e]*)/&_jis2sjis($1,$2)/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
513 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
514 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
515 sub _jis2sjis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
516 local($esc, $s) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
517 if ($esc =~ /^$re_jis0212/o) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
518 $s =~ s/../$undef_sjis/g;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
519 $n = length;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
520 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
521 elsif ($esc !~ /^$re_asc/o) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
522 $n += $s =~ tr/\041-\176/\241-\376/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
523 if ($esc =~ /^$re_jp/o) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
524 $s =~ s/($re_euc_c)/$e2s{$1}||&e2s($1)/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
525 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
526 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
527 $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
528 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
529
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
530 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
531 ;# SJIS to EUC
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
532 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
533 sub sjis2euc {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
534 local(*s, $opt,$n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
535 $n = $s =~ s/($re_sjis_c|$re_sjis_kana)/$s2e{$1}||&s2e($1)/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
536 &euc2euc(*s, $opt) if $opt;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
537 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
538 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
539 sub s2e {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
540 local($c1, $c2, $code);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
541 ($c1, $c2) = unpack('CC', $code = shift);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
542
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
543 if (0xa1 <= $c1 && $c1 <= 0xdf) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
544 $c2 = $c1;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
545 $c1 = 0x8e;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
546 } elsif (0x9f <= $c2) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
547 $c1 = $c1 * 2 - ($c1 >= 0xe0 ? 0xe0 : 0x60);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
548 $c2 += 2;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
549 } else {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
550 $c1 = $c1 * 2 - ($c1 >= 0xe0 ? 0xe1 : 0x61);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
551 $c2 += 0x60 + ($c2 < 0x7f);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
552 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
553 if ($cache) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
554 $s2e{$code} = pack('CC', $c1, $c2);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
555 } else {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
556 pack('CC', $c1, $c2);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
557 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
558 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
559
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
560 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
561 ;# EUC to SJIS
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
562 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
563 sub euc2sjis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
564 local(*s, $opt,$n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
565 &euc2euc(*s, $opt) if $opt;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
566 $n = $s =~ s/($re_euc_c|$re_euc_kana|$re_euc_0212)/$e2s{$1}||&e2s($1)/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
567 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
568 sub e2s {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
569 local($c1, $c2, $code);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
570 ($c1, $c2) = unpack('CC', $code = shift);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
571
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
572 if ($c1 == 0x8e) { # SS2
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
573 return substr($code, 1, 1);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
574 } elsif ($c1 == 0x8f) { # SS3
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
575 return $undef_sjis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
576 } elsif ($c1 % 2) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
577 $c1 = ($c1>>1) + ($c1 < 0xdf ? 0x31 : 0x71);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
578 $c2 -= 0x60 + ($c2 < 0xe0);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
579 } else {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
580 $c1 = ($c1>>1) + ($c1 < 0xdf ? 0x30 : 0x70);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
581 $c2 -= 2;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
582 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
583 if ($cache) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
584 $e2s{$code} = pack('CC', $c1, $c2);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
585 } else {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
586 pack('CC', $c1, $c2);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
587 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
588 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
589
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
590 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
591 ;# JIS to JIS, SJIS to SJIS, EUC to EUC
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
592 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
593 sub jis2jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
594 local(*s, $opt) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
595 $s =~ s/$re_jis0208/$esc_0208/go;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
596 $s =~ s/$re_asc/$esc_asc/go;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
597 &h2z_jis(*s) if $opt =~ /z/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
598 &z2h_jis(*s) if $opt =~ /h/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
599 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
600 sub sjis2sjis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
601 local(*s, $opt) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
602 &h2z_sjis(*s) if $opt =~ /z/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
603 &z2h_sjis(*s) if $opt =~ /h/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
604 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
605 sub euc2euc {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
606 local(*s, $opt) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
607 &h2z_euc(*s) if $opt =~ /z/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
608 &z2h_euc(*s) if $opt =~ /h/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
609 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
610
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
611 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
612 ;# Cache control functions
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
613 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
614 sub cache {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
615 ($cache, $cache = 1)[$[];
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
616 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
617 sub nocache {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
618 ($cache, $cache = 0)[$[];
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
619 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
620 sub flushcache {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
621 undef %e2s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
622 undef %s2e;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
623 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
624
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
625 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
626 ;# X0201 -> X0208 KANA conversion routine
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
627 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
628 sub h2z_jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
629 local(*s, $n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
630 if ($s =~ s/$re_kana([^\e]*)/$esc_0208 . &_h2z_jis($1)/geo) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
631 1 while $s =~ s/(($re_jis0208)[^\e]*)($re_jis0208)/$1/o;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
632 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
633 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
634 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
635 sub _h2z_jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
636 local($s) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
637 $n += $s =~ s/([\41-\137]([\136\137])?)/$h2z{$1}/g;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
638 $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
639 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
640
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
641 sub h2z_euc {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
642 local(*s) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
643 $s =~ s/\216([\241-\337])(\216([\336\337]))?/$h2z{"$1$3"}/g;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
644 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
645
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
646 sub h2z_sjis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
647 local(*s, $n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
648 $s =~ s/(($re_sjis_c)+)|(([\241-\337])([\336\337])?)/
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
649 $1 || ($n++, $e2s{$h2z{$3}} || &e2s($h2z{$3}))
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
650 /geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
651 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
652 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
653
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
654 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
655 ;# X0208 -> X0201 KANA conversion routine
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
656 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
657 sub z2h_jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
658 local(*s, $n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
659 $s =~ s/($re_jis0208)([^\e]+)/&_z2h_jis($2)/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
660 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
661 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
662 sub _z2h_jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
663 local($s) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
664 $s =~ s/((\%[!-~]|![\#\"&VW+,<])+|([^!%][!-~]|![^\#\"&VW+,<])+)/
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
665 &__z2h_jis($1)
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
666 /ge;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
667 $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
668 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
669 sub __z2h_jis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
670 local($s) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
671 return $esc_0208 . $s unless /^%/ || $s =~ /^![\#\"&VW+,<]/;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
672 $n += length($s) / 2;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
673 $s =~ s/(..)/$z2h{$1}/g;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
674 $esc_kana . $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
675 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
676
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
677 sub z2h_euc {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
678 local(*s, $n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
679 &init_z2h_euc unless defined %z2h_euc;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
680 $s =~ s/($re_euc_c|$re_euc_kana)/
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
681 $z2h_euc{$1} ? ($n++, $z2h_euc{$1}) : $1
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
682 /geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
683 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
684 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
685
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
686 sub z2h_sjis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
687 local(*s, $n) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
688 &init_z2h_sjis unless defined %z2h_sjis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
689 $s =~ s/($re_sjis_c)/$z2h_sjis{$1} ? ($n++, $z2h_sjis{$1}) : $1/geo;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
690 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
691 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
692
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
693 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
694 ;# Initializing JIS X0208 to X0201 KANA table for EUC and SJIS. This
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
695 ;# can be done in &init but it's not worth doing. Similarly,
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
696 ;# precalculated table is not worth to occupy the file space and
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
697 ;# reduce the readability. The author personnaly discourages to use
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
698 ;# X0201 Kana character in the any situation.
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
699 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
700 sub init_z2h_euc {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
701 local($k, $s);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
702 while (($k, $s) = each %z2h) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
703 $s =~ s/([\241-\337])/\216$1/g && ($z2h_euc{$k} = $s);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
704 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
705 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
706 sub init_z2h_sjis {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
707 local($s, $v);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
708 while (($s, $v) = each %z2h) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
709 $s =~ /[\200-\377]/ && ($z2h_sjis{&e2s($s)} = $v);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
710 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
711 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
712
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
713 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
714 ;# TR function for 2-byte code
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
715 ;#
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
716 sub tr {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
717 # $prev_from, $prev_to, %table are persistent variables
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
718 local(*s, $from, $to, $opt) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
719 local(@from, @to);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
720 local($jis, $n) = (0, 0);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
721
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
722 $jis++, &jis2euc(*s) if $s =~ /$re_jp|$re_asc|$re_kana/o;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
723 $jis++ if $to =~ /$re_jp|$re_asc|$re_kana/o;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
724
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
725 if (!defined($prev_from) || $from ne $prev_from || $to ne $prev_to) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
726 ($prev_from, $prev_to) = ($from, $to);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
727 undef %table;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
728 &_maketable;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
729 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
730
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
731 $s =~ s/([\200-\377][\000-\377]|[\000-\377])/
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
732 defined($table{$1}) && ++$n ? $table{$1} : $1
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
733 /ge;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
734
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
735 &euc2jis(*s) if $jis;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
736
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
737 $n;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
738 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
739
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
740 sub _maketable {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
741 local($ascii) = '(\\\\[\\-\\\\]|[\0-\133\135-\177])';
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
742
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
743 &jis2euc(*to) if $to =~ /$re_jp|$re_asc|$re_kana/o;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
744 &jis2euc(*from) if $from =~ /$re_jp|$re_asc|$re_kana/o;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
745
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
746 grep(s/(([\200-\377])[\200-\377]-\2[\200-\377])/&_expnd2($1)/ge,
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
747 $from, $to);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
748 grep(s/($ascii-$ascii)/&_expnd1($1)/geo,
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
749 $from, $to);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
750
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
751 @to = $to =~ /[\200-\377][\000-\377]|[\000-\377]/g;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
752 @from = $from =~ /[\200-\377][\000-\377]|[\000-\377]/g;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
753 push(@to, ($opt =~ /d/ ? '' : $to[$#to]) x (@from - @to)) if @to < @from;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
754 @table{@from} = @to;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
755 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
756
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
757 sub _expnd1 {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
758 local($s) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
759 $s =~ s/\\(.)/$1/g;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
760 local($c1, $c2) = unpack('CxC', $s);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
761 if ($c1 <= $c2) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
762 for ($s = ''; $c1 <= $c2; $c1++) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
763 $s .= pack('C', $c1);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
764 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
765 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
766 $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
767 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
768
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
769 sub _expnd2 {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
770 local($s) = @_;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
771 local($c1, $c2, $c3, $c4) = unpack('CCxCC', $s);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
772 if ($c1 == $c3 && $c2 <= $c4) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
773 for ($s = ''; $c2 <= $c4; $c2++) {
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
774 $s .= pack('CC', $c1, $c2);
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
775 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
776 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
777 $s;
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
778 }
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
779
a2f0a2c135cf hg init
Shoshi TAMAKI <shoshi@cr.ie.u-ryukyu.ac.jp>
parents:
diff changeset
780 1;