Debian Codegraph @

bin/ujconv

raw
1 #! /usr/bin/perl -w
2 ## ----------------------------------------------------------------------------
3 # ujconv
4 # -----------------------------------------------------------------------------
5 # Mastering programmed by YAMASHINA Hio
6 #
7 # Copyright 2005 YAMASHINA Hio
8 # -----------------------------------------------------------------------------
9 # $Id: ujconv 4697 2007-09-14 06:17:00Z pho $
10 # -----------------------------------------------------------------------------
11 package Unicode::Japanese::UJConv;
12 use strict;
13 use Unicode::Japanese;
14 our $VERSION = '0.02';
15
16 if( !caller )
17 {
18 __PACKAGE__->do_work(@ARGV);
19 }
20
21 # -----------------------------------------------------------------------------
22 # main.
23 #
24 sub do_work
25 {
26 my $pkg = shift;
27
28 my $from = 'auto';
29 my $to = 'auto';
30 my $string;
31 my @files;
32
33 while(@_)
34 {
35 my $key = shift;
36 if( $key !~ /^-/ )
37 {
38 push(@files,$key);
39 next;
40 }elsif( $key eq '--' )
41 {
42 push(@files,@_);
43 last;
44 }
45 if( $key eq '-f' )
46 {
47 $from = shift;
48 next;
49 }elsif( $key eq '-t' )
50 {
51 $to = shift;
52 next;
53 }elsif( $key eq '-s' )
54 {
55 my $value = shift;
56 push(@files,[$key,$value]);
57 next;
58 }elsif( $key =~ /^(-h|--help)$/ )
59 {
60 print_usage();
61 return 1;
62 }elsif( $key =~ /^(-V|--version)$/ )
63 {
64 print_version();
65 return 1;
66 }elsif( $key =~ /^(-l|--list)$/ )
67 {
68 print_list();
69 return 1;
70 }else
71 {
72 die "unkown argument [$key]";
73 }
74 }
75
76 if( $to eq 'auto' )
77 {
78 my $lang = $ENV{LANG};
79 if( $lang && $lang=~/\.(.*)/ )
80 {
81 my $code = $1;
82 if( $code=~/^(ujis|jis|iso-2022-jp)$/i )
83 {
84 $to = 'jis';
85 }elsif( $code=~/^(ujis|eucJP)$/i )
86 {
87 $to = 'euc';
88 }elsif( $code=~/^(sjis|shift_?jis)$/i )
89 {
90 $to = 'sjis';
91 }elsif( $code=~/^(utf-?8)$/i )
92 {
93 $to = 'utf8';
94 }
95 }
96 if( $to eq 'auto' )
97 {
98 $to = $^O eq 'MSWin32' ? 'sjis' : 'euc';
99 }
100 }
101
102 if( !@files )
103 {
104 print Unicode::Japanese->new($_,$from)->conv($to) while(<STDIN>);
105 }
106 foreach my $file (@files)
107 {
108 my $text;
109 if( ref($file) )
110 {
111 $text = $file->[1];
112 print Unicode::Japanese->new($text,$from)->conv($to);
113 }elsif( $file eq '-' )
114 {
115 print Unicode::Japanese->new($_,$from)->conv($to) while(<STDIN>);
116 }else
117 {
118 open(FILE, '<:mmap', $file) or die "could not open file [$file] : $!";
119 print Unicode::Japanese->new($_,$from)->conv($to) while(<FILE>);
120 close(FILE);
121 }
122 }
123 1;
124 }
125
126 # -----------------------------------------------------------------------------
127 # print_usage();
128 #
129 sub print_usage
130 {
131 print "usage: ujconv [-f from_encode] [-t to_encode] [-s string] [files...]\n";
132 print "see \`perldoc ujconv' for details.\n";
133 }
134
135 # -----------------------------------------------------------------------------
136 # print_version();
137 #
138 sub print_version
139 {
140 print "ujconv $VERSION\n";
141 print "Unicode::Janaese $Unicode::Japanese::VERSION\n";
142 }
143
144 # -----------------------------------------------------------------------------
145 # print_list();
146 #
147 sub print_list
148 {
149 foreach my $enc (qw(
150 utf8
151 ucs2
152 ucs4
153 utf16
154 jis
155 euc
156 euc-jp
157 sjis
158 cp932
159 sjis-imode
160 sjis-doti
161 sjis-jsky
162 jis-jsky
163 jis-au
164 sjis-icon-au
165 euc-icon-au
166 jis-icon-au
167 utf8-icon-au
168 ))
169 {
170 print "$enc\n";
171 }
172 }
173
174 __END__
175
176 =head1 NAME
177
178 ujconv -- reinvented iconv(1) using Unicode::Japanese
179
180 =head1 SYNOPSIS
181
182 ujconv [-f from_encoding] [-t to_encoding] [-s string] [files...]
183 ujconv -l
184 ujconv -h
185 ujconv -V
186
187 =head1 VERSION
188
189 ujconv 0.02
190
191 =head1 DESCRIPTION
192
193 B<ujconv> is an iconv-like tool which is written in perl using
194 Unicode::Japanese.
195
196 B<ujconv> reads text from STDIN or files, convert them, and print them to
197 STDOUT.
198
199 Available options are as follows. Each options can be in short form (-f) or long
200 form (--from):
201
202 =over 4
203
204 =item -f,--from I<from_encoding>
205
206 Convert characters from I<from_encoding>. Unlike B<iconv> this option can be
207 omitted. In that case, the encoding of the input is guessed by B<ujconv>.
208
209 =item -t,--to I<to_encoding>
210
211 Convert characters to I<to_encoding>.
212
213 =item -s,--string I<string>
214
215 Input from the argument string instead of file or STDIN.
216
217 =item -l,--list
218
219 List all available encodings, one name per each lines.
220
221 =item -h,--help
222
223 Print a short help message.
224
225 =item -V,--version
226
227 Print the version of B<ujconv>.
228
229 =back
230
231 =head1 SEE ALSO
232
233 L<Unicode::Japanese>,
234 L<piconv(1)>,
235 L<iconv(1)>,
236 L<ujguess>
237
238 =cut
239
240 # -----------------------------------------------------------------------------
241 # End of File.
242 # -----------------------------------------------------------------------------