Text.pm 10.8 KB
Newer Older
1
2
3
4
5
6
7
8
9
# -*- indent-tabs-mode: nil; -*-
# vim:ft=perl:et:sw=4
# $Id$

# Sympa - SYsteme de Multi-Postage Automatique
#
# Copyright (c) 1997, 1998, 1999 Institut Pasteur & Christophe Wolfhugel
# Copyright (c) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005,
# 2006, 2007, 2008, 2009, 2010, 2011 Comite Reseau des Universites
10
# Copyright (c) 2011, 2012, 2013, 2014, 2015, 2016 GIP RENATER
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# 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.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

package Sympa::Tools::Text;

use strict;
use warnings;
29
use Encode qw();
30
31
32
use English;                 # FIXME: drop $MATCH usage
use Encode::MIME::Header;    # 'MIME-Q' encoding.
use MIME::EncWords;
33
34
use Text::LineFold;
use if (5.008 < $] && $] < 5.016), qw(Unicode::CaseFold fc);
35
use if (5.016 <= $]), qw(feature fc);
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
use Sympa::Regexps;

# Old name: tools::addrencode().
sub addrencode {
    my $addr    = shift;
    my $phrase  = (shift || '');
    my $charset = (shift || 'utf8');
    my $comment = (shift || '');

    return undef unless $addr =~ /\S/;

    if ($phrase =~ /[^\s\x21-\x7E]/) {
        $phrase = MIME::EncWords::encode_mimewords(
            Encode::decode('utf8', $phrase),
            'Encoding'    => 'A',
            'Charset'     => $charset,
            'Replacement' => 'FALLBACK',
            'Field'       => 'Resent-Sender', # almost longest
            'Minimal'     => 'DISPNAME',      # needs MIME::EncWords >= 1.012.
        );
    } elsif ($phrase =~ /\S/) {
        $phrase =~ s/([\\\"])/\\$1/g;
        $phrase = '"' . $phrase . '"';
    }
    if ($comment =~ /[^\s\x21-\x27\x2A-\x5B\x5D-\x7E]/) {
        $comment = MIME::EncWords::encode_mimewords(
            Encode::decode('utf8', $comment),
            'Encoding'    => 'A',
            'Charset'     => $charset,
            'Replacement' => 'FALLBACK',
            'Minimal'     => 'DISPNAME',
        );
    } elsif ($comment =~ /\S/) {
        $comment =~ s/([\\\"])/\\$1/g;
    }

    return
          ($phrase  =~ /\S/ ? "$phrase "    : '')
        . ($comment =~ /\S/ ? "($comment) " : '')
        . "<$addr>";
}

79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
# Old names: tools::clean_email(), tools::get_canonical_email().
sub canonic_email {
    my $email = shift;

    return undef unless defined $email;

    # Remove leading and trailing white spaces.
    $email =~ s/\A\s+//;
    $email =~ s/\s+\z//;

    # Lower-case.
    $email =~ tr/A-Z/a-z/;

    return (length $email) ? $email : undef;
}

95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
# Old name: tools::clean_msg_id().
sub canonic_message_id {
    my $msg_id = shift;

    return $msg_id unless defined $msg_id;

    chomp $msg_id;

    if ($msg_id =~ /\<(.+)\>/) {
        $msg_id = $1;
    }

    return $msg_id;
}

110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
sub wrap_text {
    my $text = shift;
    my $init = shift;
    my $subs = shift;
    my $cols = shift;
    $cols = 78 unless defined $cols;
    return $text unless $cols;

    $text = Text::LineFold->new(
        Language      => Sympa::Language->instance->get_lang,
        OutputCharset => (Encode::is_utf8($text) ? '_UNICODE_' : 'utf8'),
        Prep          => 'NONBREAKURI',
        ColumnsMax    => $cols
    )->fold($init, $subs, $text);

    return $text;
}

128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
sub decode_filesystem_safe {
    my $str = shift;
    return '' unless defined $str and length $str;

    $str = Encode::encode_utf8($str) if Encode::is_utf8($str);
    # On case-insensitive filesystem "_XX" along with "_xx" should be decoded.
    $str =~ s/_([0-9A-Fa-f]{2})/chr hex "0x$1"/eg;
    return $str;
}

sub encode_filesystem_safe {
    my $str = shift;
    return '' unless defined $str and length $str;

    $str = Encode::encode_utf8($str) if Encode::is_utf8($str);
    $str =~ s/([^-+.0-9\@A-Za-z])/sprintf '_%02x', ord $1/eg;
    return $str;
}

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
# Old name: tools::escape_chars().
sub escape_chars {
    my $s          = shift;
    my $except     = shift;                            ## Exceptions
    my $ord_except = ord $except if defined $except;

    ## Escape chars
    ##  !"#$%&'()+,:;<=>?[] AND accented chars
    ## escape % first
    foreach my $i (
        0x25,
        0x20 .. 0x24,
        0x26 .. 0x2c,
        0x3a .. 0x3f,
        0x5b, 0x5d,
        0x80 .. 0x9f,
        0xa0 .. 0xff
        ) {
        next if defined $ord_except and $i == $ord_except;
        my $hex_i = sprintf "%lx", $i;
        $s =~ s/\x$hex_i/%$hex_i/g;
    }
    ## Special traetment for '/'
    $s =~ s/\//%a5/g unless defined $except and $except eq '/';

    return $s;
}

# Old name: tt2::escape_url().
sub escape_url {
    my $string = shift;

    $string =~ s/[\s+]/sprintf('%%%02x', ord($MATCH))/eg;
    # Some MUAs aren't able to decode ``%40'' (escaped ``@'') in e-mail
    # address of mailto: URL, or take ``@'' in query component for a
    # delimiter to separate URL from the rest.
    my ($body, $query) = split(/\?/, $string, 2);
    if (defined $query) {
        $query =~ s/\@/sprintf('%%%02x', ord($MATCH))/eg;
        $string = $body . '?' . $query;
    }

    return $string;
}

192
193
194
195
196
197
198
199
200
201
202
203
204
sub foldcase {
    my $str = shift;
    return '' unless defined $str and length $str;

    if ($] <= 5.008) {
        # Perl 5.8.0 does not support Unicode::CaseFold. Use lc() instead.
        return Encode::encode_utf8(lc(Encode::decode_utf8($str)));
    } else {
        # later supports it. Perl 5.16.0 and later have built-in fc().
        return Encode::encode_utf8(fc(Encode::decode_utf8($str)));
    }
}

205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
# Old name: tools::qdecode_filename().
sub qdecode_filename {
    my $filename = shift;

    ## We don't use MIME::Words here because it does not encode properly
    ## Unicode
    ## Check if string is already Q-encoded first
    #if ($filename =~ /\=\?UTF-8\?/) {
    $filename = Encode::encode_utf8(Encode::decode('MIME-Q', $filename));
    #}

    return $filename;
}

# Old name: tools::qencode_filename().
sub qencode_filename {
    my $filename = shift;

    ## We don't use MIME::Words here because it does not encode properly
    ## Unicode
    ## Check if string is already Q-encoded first
    ## Also check if the string contains 8bit chars
    unless ($filename =~ /\=\?UTF-8\?/
        || $filename =~ /^[\x00-\x7f]*$/) {

        ## Don't encode elements such as .desc. or .url or .moderate
        ## or .extension
        my $part = $filename;
        my ($leading, $trailing);
        $leading  = $1 if ($part =~ s/^(\.desc\.)//);    ## leading .desc
        $trailing = $1 if ($part =~ s/((\.\w+)+)$//);    ## trailing .xx

        my $encoded_part = MIME::EncWords::encode_mimewords(
            $part,
            Charset    => 'utf8',
            Encoding   => 'q',
            MaxLineLen => 1000,
            Minimal    => 'NO'
        );

        $filename = $leading . $encoded_part . $trailing;
    }

    return $filename;
}

# Old name: tools::unescape_chars().
sub unescape_chars {
    my $s = shift;

    $s =~ s/%a5/\//g;    ## Special traetment for '/'
    foreach my $i (0x20 .. 0x2c, 0x3a .. 0x3f, 0x5b, 0x5d, 0x80 .. 0x9f,
        0xa0 .. 0xff) {
        my $hex_i = sprintf "%lx", $i;
        my $hex_s = sprintf "%c",  $i;
        $s =~ s/%$hex_i/$hex_s/g;
    }

    return $s;
}

# Old name: tools::valid_email().
sub valid_email {
    my $email = shift;

    my $email_re = Sympa::Regexps::email();
    return undef unless $email =~ /^${email_re}$/;

    # Forbidden characters.
    return undef if $email =~ /[\|\$\*\?\!]/;

    return 1;
}

279
1;
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
__END__

=encoding utf-8

=head1 NAME

Sympa::Tools::Text - Text-related functions

=head1 DESCRIPTION

This package provides some text-related functions.

=head2 Functions

=over

296
297
298
299
=item addrencode ( $addr, [ $phrase, [ $charset, [ $comment ] ] ] )

Returns formatted (and encoded) name-addr as RFC5322 3.4.

300
301
302
303
304
305
306
307
308
309
=item canonic_email ( $email )

I<Function>.
Returns canonical form of e-mail address.

Leading and trailing whilte spaces are removed.
Latin letters without accents are lower-cased.

For malformed inputs returns C<undef>.

310
311
312
313
314
=item canonic_message_id ( $message_id )

Returns canonical form of message ID without trailing or leading whitespaces
or C<E<lt>>, C<E<gt>>.

315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
=item wrap_text ( $text, [ $init_tab, [ $subsequent_tab, [ $cols ] ] ] )

I<Function>.
Returns line-wrapped text.

Parameters:

=over

=item $text

The text to be folded.

=item $init_tab

Indentation prepended to the first line of paragraph.
Default is C<''>, no indentation.

=item $subsequent_tab

Indentation prepended to each subsequent line of folded paragraph.
Default is C<''>, no indentation.

=item $cols

Max number of columns of folded text.
Default is C<78>.

=back

345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
=item decode_filesystem_safe ( $str )

I<Function>.
Decodes a string encoded by encode_filesystem_safe().

Parameter:

=over

=item $str

String to be decoded.

=back

Returns:

Decoded string, stripped C<utf8> flag if any.

=item encode_filesystem_safe ( $str )

I<Function>.
Encodes a string $str to be suitable for filesystem.

Parameter:

=over

=item $str

String to be encoded.

=back

Returns:

Encoded string, stripped C<utf8> flag if any.
All bytes except C<'-'>, C<'+'>, C<'.'>, C<'@'>
and alphanumeric characters are encoded to sequences C<'_'> followed by
two hexdigits.

Note that C<'/'> will also be encoded.

388
389
390
391
392
393
394
395
396
397
398
=item escape_chars ( $str )

Escape weird characters.

ToDo: This should be obsoleted in the future release: Would be better to use
L</encode_filesystem_safe>.

=item escape_url ( $str )

Escapes string using URL encoding.

399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
=item foldcase ( $str )

I<Function>.
Returns "fold-case" string suitable for case-insensitive match.
For example, a code below looks for a needle in haystack not regarding case,
even if they are non-ASCII UTF-8 strings.

  $haystack = Sympa::Tools::Text::foldcase($HayStack);
  $needle   = Sympa::Tools::Text::foldcase($NeedLe);
  if (index $haystack, $needle >= 0) {
      ...
  }

Parameter:

=over

=item $str

A string.

=back

422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
=item qdecode_filename ( $filename )

Q-Decodes web file name.

ToDo:
This should be obsoleted in the future release: Would be better to use
L</decode_filesystem_safe>.

=item qencode_filename ( $filename )

Q-Encodes web file name.

ToDo:
This should be obsoleted in the future release: Would be better to use
L</encode_filesystem_safe>.

=item unescape_chars ( $str )

Unescape weird characters.

ToDo: This should be obsoleted in the future release: Would be better to use
L</decode_filesystem_safe>.

=item valid_email ( $string )

Basic check of an email address.

449
450
=back

451
452
453
454
455
456
457
=head1 HISTORY

L<Sympa::Tools::Text> appeared on Sympa 6.2a.41.

decode_filesystem_safe() and encode_filesystem_safe() were added
on Sympa 6.2.10.

458
=cut