1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
|
#!/usr/bin/perl -w -s
# PODNAME: tmxgrep
# ABSTRACT: grep translation units in a TMX file
## use utf8::all;
use Data::Dumper;
our ($all,$w,$max,$pdf, $o, $n, $a,$debug, $i, $html);
$a //= "p" if $pdf || $html;
my ($ab,$ae); ## emphatise marker
my $browser="";
$browser = "=$html" if ($html and $html ne "1");
if($a){
if($a eq "1"){
$ab="=(";
$ae=")=";
}
elsif($a){
$ab="<$a>";
$ae="</$a>";
}
}
if($html){
if($html eq "1"){
$ab="<b>";
$ae="</b>";
}
elsif($html){
$ab="<$html>";
$ae="</$html>";
}
}
$max //= 500;
$max = 1000000000 if ($max == 0 or $all);
use strict;
use warnings;
my $p = shift or die("Usage: $0 [options] pattern f.tmx\n");
if ($p =~ m{(\w+):(.+?);(\w+):(.+)}){
if($i and $w){ $p = +{$1=> qr{(?i)\b$2\b}, $3 => qr{(?i)\b$4\b}} }
elsif($i) { $p = +{$1=> qr{(?i)$2}, $3 => qr{(?i)$4}} }
elsif($w) { $p = +{$1=> qr{\b$2\b}, $3 => qr{\b$4\b}} }
else { $p = +{$1=> $2, $3 => $4} }
}
elsif($p =~ m{(\w+):(.+)} ){
if($i and $w){ $p = +{$1=> qr{(?i)\b$2\b}} }
elsif($i) { $p = +{$1=> qr{(?i)$2}} }
elsif($w) { $p = +{$1=> qr{\b$2\b}} }
else { $p = +{$1=> $2} }
}
else{
if($i and $w){ $p = qr{(?i)\b$p\b} }
elsif($i) { $p = qr{(?i)$p} }
elsif($w) { $p = qr{\b$p\b} }
}
use XML::TMX;
use XML::TMX::Reader;
$o //= "__.tmx" if $pdf || $html;
our ($icons);
my $tmx = shift;
my $tmx_obj = XML::TMX::Reader->new($tmx);
print STDERR Dumper($p) if $main::debug;
$tmx_obj->for_tu(
{ patt => $p,
gen_tu=> $max,
n => $n || 0,
output => $o || undef }, #### "__tmxgrep.tmx"
sub { my($tu,$at) = @_;
print STDERR Dumper($tu,$at,$p) if $main::debug;
# print STDERR ".";
if($main::a ){
for my $li(keys %$tu){
next if $li =~ /^-/;
for(keys %{$tu->{$li}}){
if(ref($p)){
my $pli = $p->{lc($li)} or next;
$tu->{$li}{$_} =~ s!($pli)!$ab$1$ae!g;
}
else{
$tu->{$li}{$_} =~ s!($p)!$ab$1$ae!g;
}
}
}
}
return $tu;
}
);
if($pdf){ system("tmx2pdf-prince -v $o");}
if($html){ system("tmx2html -v$browser $o");}
__END__
=pod
=encoding UTF-8
=head1 NAME
tmxgrep - grep translation units in a TMX file
=head1 VERSION
version 0.39
=head1 SYNOPSIS
tmxgrep patt file.tmx
options:
-max=300 -- extract up to 300 TU (def=500)
-max=0 -- all matches
-all -- all matches
-a -- annotate matches with '=(...)='
-a=xx -- annotate matches with '<xx>...</xx>'
-o=out.tmx -- define output file (defaut= STDOUT)
-n -- print original TU number (eg: <tu n="35">)
-i -- ignore case
-w -- whole words
-pdf -- output is transformed in a PDF file and show
-html -- output is transformed in a HTML file and show
-html=chromium -- idem and show it with chromium (def:firefox)
Where patt can be:
RegExp
l1:RegExp
l1:RegExp;l2:RegExp
=head1 DESCRIPTION
Creates a TMX file with the translation units that macth the provided
regular expression.
=head1 AUTHORS
=over 4
=item *
Alberto Simões <ambs@cpan.org>
=item *
José João Almeida <jj@di.uminho.pt>
=back
=head1 COPYRIGHT AND LICENSE
This software is copyright (c) 2010-2017 by Projeto Natura <natura@di.uminho.pt>.
This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.
=cut
|
