TextGlob.pm 5.82 KB
Newer Older
1
2
3
#-----------------------------------------------------------------------
# Fault InJection Instrumenter (FIJI)
# https://embsys.technikum-wien.at/projects/vecs/fiji
4
#
5
6
7
8
# The creation of this file has been supported by the publicly funded
# R&D project Josef Ressel Center for Verification of Embedded Computing
# Systems (VECS) managed by the Christian Doppler Gesellschaft (CDG).
#
9
10
11
# Authors:
# Christian Fibich <fibich@technikum-wien.at>
# Stefan Tauner <tauner@technikum-wien.at>
12
#
13
14
# This module is free software; you can redistribute it and/or modify
# it under the same terms as Perl itself.
15
#
16
17
18
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
19
#
20
21
22
23
24
25
26
27
28
# See the LICENSE file for more details.
#-----------------------------------------------------------------------

## @file Tests.pm
# @brief Contains class \ref FIJI::TextGlob

## @class FIJI::Tests
#
# @brief Glob strings to regexes based on Text::Glob by Richard Clamp
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

package FIJI::TextGlob;
use strict;
use Exporter;
use vars qw/$VERSION @ISA @EXPORT_OK
            $strict_leading_dot $strict_wildcard_slash/;
$VERSION = '0.11';
@ISA = 'Exporter';
@EXPORT_OK = qw( glob_to_regex glob_to_regex_string match_glob );

$strict_leading_dot    = 1;
$strict_wildcard_slash = 1;

use constant debug => 0;

sub glob_to_regex {
    my $glob = shift;
    my $regex = glob_to_regex_string($glob);
47
    return "^$regex\$";
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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
}

sub glob_to_regex_string
{
    my $glob = shift;

    my $seperator = $Text::Glob::seperator;
    $seperator = "/" unless defined $seperator;
    $seperator = quotemeta($seperator);

    my ($regex, $in_curlies, $escaping);
    local $_;
    my $first_byte = 1;
    for ($glob =~ m/(.)/gs) {
        if ($first_byte) {
            if ($strict_leading_dot) {
                $regex .= '(?=[^\.])' unless $_ eq '.';
            }
            $first_byte = 0;
        }
        if ($_ eq '/') {
            $first_byte = 1;
        }
        if ($_ eq '.' || $_ eq '(' || $_ eq ')' || $_ eq '|' ||
            $_ eq '+' || $_ eq '^' || $_ eq '$' || $_ eq '@' || $_ eq '%' ) {
            $regex .= "\\$_";
        }
        elsif ($_ eq '*') {
            $regex .= $escaping ? "\\*" :
              $strict_wildcard_slash ? "(?:(?!$seperator).)*" : ".*";
        }
        elsif ($_ eq '?') {
            $regex .= $escaping ? "\\?" :
              $strict_wildcard_slash ? "(?!$seperator)." : ".";
        }
        elsif ($_ eq '{') {
            $regex .= $escaping ? "\\{" : "(";
            ++$in_curlies unless $escaping;
        }
        elsif ($_ eq '}' && $in_curlies) {
            $regex .= $escaping ? "}" : ")";
            --$in_curlies unless $escaping;
        }
        elsif ($_ eq ',' && $in_curlies) {
            $regex .= $escaping ? "," : "|";
        }
        elsif ($_ eq "\\") {
            if ($escaping) {
                $regex .= "\\\\";
                $escaping = 0;
            }
            else {
                $escaping = 1;
            }
            next;
        }
        elsif ($_ eq "[") {
            $regex .= "\\[";
        }
        else {
            $regex .= $_;
            $escaping = 0;
        }
        $escaping = 0;
    }
    print "# $glob $regex\n" if debug;

    return $regex;
}

sub match_glob {
    print "# ", join(', ', map { "'$_'" } @_), "\n" if debug;
    my $glob = shift;
    my $regex = glob_to_regex $glob;
    local $_;
    grep { $_ =~ $regex } @_;
}

1;
__END__

=head1 NAME

Text::Glob - match globbing patterns against text

=head1 SYNOPSIS

 use FIJI::TextGlob qw( match_glob glob_to_regex );

 print "matched\n" if match_glob( "foo.*", "foo.bar" );

 # prints foo.bar and foo.baz
 my $regex = glob_to_regex( "foo.*" );
 for ( qw( foo.bar foo.baz foo bar ) ) {
     print "matched: $_\n" if /$regex/;
 }

=head1 DESCRIPTION

Text::Glob implements glob(3) style matching that can be used to match
against text, rather than fetching names from a filesystem.  If you
want to do full file globbing use the File::Glob module instead.

=head2 Routines

=over

=item match_glob( $glob, @things_to_test )

Returns the list of things which match the glob from the source list.

=item glob_to_regex( $glob )

Returns a compiled regex which is the equivalent of the globbing
pattern.

=item glob_to_regex_string( $glob )

Returns a regex string which is the equivalent of the globbing
pattern.

=back

=head1 SYNTAX

The following metacharacters and rules are respected.

=over

=item C<*> - match zero or more characters

C<a*> matches C<a>, C<aa>, C<aaaa> and many many more.

=item C<?> - match exactly one character

C<a?> matches C<aa>, but not C<a>, or C<aaa>

=item Character sets/ranges

C<example.[ch]> matches C<example.c> and C<example.h>

C<demo.[a-c]> matches C<demo.a>, C<demo.b>, and C<demo.c>

=item alternation

C<example.{foo,bar,baz}> matches C<example.foo>, C<example.bar>, and
C<example.baz>

=item leading . must be explicitly matched

C<*.foo> does not match C<.bar.foo>.  For this you must either specify
the leading . in the glob pattern (C<.*.foo>), or set
C<$Text::Glob::strict_leading_dot> to a false value while compiling
the regex.

=item C<*> and C<?> do not match the seperator (i.e. do not match C</>)

C<*.foo> does not match C<bar/baz.foo>.  For this you must either
explicitly match the / in the glob (C<*/*.foo>), or set
C<$Text::Glob::strict_wildcard_slash> to a false value while compiling
the regex, or change the seperator that Text::Glob uses by setting
C<$Text::Glob::seperator> to an alternative value while compiling the
the regex.

=back

=head1 COPYRIGHT

Based on Text::Glob by Richard Clamp <richardc@unixbeard.net>

Original Copyright notice:

Copyright (C) 2002, 2003, 2006, 2007 Richard Clamp.  All Rights Reserved.

This module is free software; you can redistribute it and/or modify it
under the same terms as Perl itself.

=cut