Text.pm 19.8 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, 2017 GIP RENATER
11
12
13
# Copyright 2018 The Sympa Community. See the AUTHORS.md file at the
# top-level directory of this distribution and at
# <https://github.com/sympa-community/sympa.git>.
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
#
# 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;
32
use Encode qw();
sikeda's avatar
sikeda committed
33
use English qw(-no_match_vars);
34
use Encode::MIME::Header;    # 'MIME-Q' encoding.
35
use HTML::Entities qw();
36
use MIME::EncWords;
37
use Text::LineFold;
38
use Unicode::GCString;
39
use URI::Escape qw();
40
use if (5.008 < $] && $] < 5.016), qw(Unicode::CaseFold fc);
41
use if (5.016 <= $]), qw(feature fc);
42
BEGIN { eval 'use Unicode::Normalize qw()'; }
43

IKEDA Soji's avatar
IKEDA Soji committed
44
use Sympa::Language;
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
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
82
          ($phrase =~ /\S/  ? "$phrase "    : '')
83
84
85
86
        . ($comment =~ /\S/ ? "($comment) " : '')
        . "<$addr>";
}

87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
# 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;
}

103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
# 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;
}

118
119
120
121
122
123
124
125
sub wrap_text {
    my $text = shift;
    my $init = shift;
    my $subs = shift;
    my $cols = shift;
    $cols = 78 unless defined $cols;
    return $text unless $cols;

126
    my $email_re = Sympa::Regexps::email();
127
128
129
130
    $text = Text::LineFold->new(
        Language      => Sympa::Language->instance->get_lang,
        OutputCharset => (Encode::is_utf8($text) ? '_UNICODE_' : 'utf8'),
        Prep          => 'NONBREAKURI',
IKEDA Soji's avatar
IKEDA Soji committed
131
        prep          => [$email_re, sub { shift; @_ }],
132
133
134
135
136
137
        ColumnsMax    => $cols
    )->fold($init, $subs, $text);

    return $text;
}

138
139
140
141
142
143
144
145
146
147
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;
}

148
149
150
151
152
153
154
sub decode_html {
    my $str = shift;

    Encode::encode_utf8(
        HTML::Entities::decode_entities(Encode::decode_utf8($str)));
}

155
156
157
158
159
160
161
162
163
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;
}

164
sub encode_html {
Luc Didry's avatar
Luc Didry committed
165
    my $str = shift;
166
    my $additional_unsafe = shift || '';
167

168
    HTML::Entities::encode_entities($str, '<>&"' . $additional_unsafe);
169
170
}

171
172
173
174
175
176
177
178
179
180
181
182
183
sub encode_uri {
    my $str     = shift;
    my %options = @_;

    # Note: URI-1.35 (URI::Escape 3.28) or later is required.
    return Encode::encode_utf8(
        URI::Escape::uri_escape_utf8(
            Encode::decode_utf8($str),
            '^-A-Za-z0-9._~' . (exists $options{omit} ? $options{omit} : '')
        )
    );
}

184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
# 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
Luc Didry's avatar
Luc Didry committed
201
    ) {
202
203
204
205
206
207
208
209
210
211
212
        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().
sikeda's avatar
sikeda committed
213
# DEPRECATED.  Use Sympa::Tools::Text::escape_uri() or
214
# Sympa::Tools::Text::mailtourl().
sikeda's avatar
sikeda committed
215
#sub escape_url;
216

217
218
219
220
221
222
223
224
225
226
227
228
229
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)));
    }
}

230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
my %legacy_charsets = (
    'ar'    => [qw(iso-8859-6)],
    'bs'    => [qw(iso-8859-2)],
    'cs'    => [qw(iso-8859-2)],
    'eo'    => [qw(iso-8859-3)],
    'et'    => [qw(iso-8859-4)],
    'he'    => [qw(iso-8859-8)],
    'hr'    => [qw(iso-8859-2)],
    'hu'    => [qw(iso-8859-2)],
    'ja'    => [qw(euc-jp cp932 MacJapanese)],
    'kl'    => [qw(iso-8859-4)],
    'ko'    => [qw(cp949)],
    'lt'    => [qw(iso-8859-4)],
    'lv'    => [qw(iso-8859-4)],
    'mt'    => [qw(iso-8859-3)],
    'pl'    => [qw(iso-8859-2)],
    'ro'    => [qw(iso-8859-2)],
247
    'ru'    => [qw(koi8-r cp1251)],               # cp866? MacCyrillic?
248
249
    'sk'    => [qw(iso-8859-2)],
    'sl'    => [qw(iso-8859-2)],
250
    'th'    => [qw(iso-8859-11 cp874 MacThai)],
251
    'tr'    => [qw(iso-8859-9)],
252
    'uk'    => [qw(koi8-u)],                      # MacUkrainian?
253
254
255
256
257
258
259
260
261
262
263
    'zh-CN' => [qw(euc-cn)],
    'zh-TW' => [qw(big5-eten)],
);

sub guessed_to_utf8 {
    my $text  = shift;
    my @langs = @_;

    return Encode::encode_utf8($text) if Encode::is_utf8($text);
    return $text
        unless defined $text
264
265
        and length $text
        and $text =~ /[^\x00-\x7F]/;
266
267
268
269
270
271
272
273
274

    my $utf8;
    foreach
        my $charset ('utf-8', map { $_ ? @$_ : () } @legacy_charsets{@langs})
    {
        $utf8 = eval { Encode::decode($charset, $text, Encode::FB_CROAK()) };
        last if defined $utf8;
    }
    $utf8 = Encode::decode('iso-8859-1', $text) unless defined $utf8;
275
276
277
278

    # Apply NFC: e.g. for modified-NFD by Mac OS X.
    $utf8 = Unicode::Normalize::normalize('NFC', $utf8)
        if $Unicode::Normalize::VERSION;
279

280
281
282
    return Encode::encode_utf8($utf8);
}

283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
sub mailtourl {
    my $text    = shift;
    my %options = @_;

    my $dtext =
          (not defined $text)   ? ''
        : $options{decode_html} ? Sympa::Tools::Text::decode_html($text)
        :                         $text;
    $dtext =~ s/\A\s+//;
    $dtext =~ s/\s+\z//;
    $dtext =~ s/(?:\r\n|\r|\n)(?=[ \t])//g;
    $dtext =~ s/\r\n|\r|\n/ /g;

    # The ``@'' in email address should not be encoded because some MUAs
    # aren't able to decode ``%40'' in e-mail address of mailto: URL.
    # Contrary, ``@'' in query component should be encoded because some
    # MUAs take it for a delimiter to separate URL from the rest.
    my ($format, $utext, $qsep);
    if ($dtext =~ /[()<>\[\]:;,\"\s]/) {
        # Use "to" header if source text includes any of RFC 5322
        # "specials", minus ``@'' and ``\'', plus whitespaces.
        $format = 'mailto:?to=%s%s';
        $utext  = Sympa::Tools::Text::encode_uri($dtext);
        $qsep   = '&';
    } else {
        $format = 'mailto:%s%s';
        $utext  = Sympa::Tools::Text::encode_uri($dtext, omit => '@');
        $qsep   = '?';
    }
312
313
314
315
316
317
318
319
320
321
322
323
324
325
    my $qstring = _url_query_string(
        $options{query},
        decode_html => $options{decode_html},
        leadchar    => $qsep,
        sepchar     => '&',
        trim_values => 1,
    );

    return sprintf $format, $utext, $qstring;
}

sub _url_query_string {
    my $query   = shift;
    my %options = @_;
326
327

    unless (ref $query eq 'HASH' and %$query) {
328
        return '';
329
    } else {
330
331
332
333
        my $decode_html = $options{decode_html};
        my $trim_values = $options{trim_values};
        return ($options{leadchar} || '?') . join(
            ($options{sepchar} || ';'),
334
335
            map {
                my ($dkey, $dval) = map {
336
337
338
                          (not defined $_) ? ''
                        : $decode_html ? Sympa::Tools::Text::decode_html($_)
                        :                $_;
339
                } ($_, $query->{$_});
340
                if ($trim_values and lc $dkey ne 'body') {
341
342
343
344
345
346
347
348
349
                    $dval =~ s/\A\s+//;
                    $dval =~ s/\s+\z//;
                    $dval =~ s/(?:\r\n|\r|\n)(?=[ \t])//g;
                    $dval =~ s/\r\n|\r|\n/ /g;
                }

                sprintf '%s=%s',
                    Sympa::Tools::Text::encode_uri($dkey),
                    Sympa::Tools::Text::encode_uri($dval);
350
            } sort keys %$query
351
352
353
354
        );
    }
}

355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
sub pad {
    my $str   = shift;
    my $width = shift;

    return $str unless $width and defined $str;

    my $ustr = Encode::is_utf8($str) ? $str : Encode::decode_utf8($str);
    my $cols = Unicode::GCString->new($ustr)->columns;

    unless ($cols < abs $width) {
        return $str;
    } elsif ($width < 0) {
        return $str . (' ' x (-$width - $cols));
    } else {
        return (' ' x ($width - $cols)) . $str;
    }
}

373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
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
# 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;
}

447
448
449
450
451
452
453
454
455
sub weburl {
    my $base    = shift;
    my $paths   = shift;
    my %options = @_;

    my @paths = map {
        Sympa::Tools::Text::encode_uri(
              (not defined $_)      ? ''
            : $options{decode_html} ? Sympa::Tools::Text::decode_html($_)
456
            :                         $_
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
        );
    } @{$paths || []};

    my $qstring = _url_query_string(
        $options{query},
        decode_html => $options{decode_html},
        sepchar     => '&',
    );

    my $fstring;
    my $fragment = $options{fragment};
    if (defined $fragment) {
        $fstring = '#'
            . Sympa::Tools::Text::encode_uri(
            $options{decode_html}
            ? Sympa::Tools::Text::decode_html($fragment)
            : $fragment
            );
    } else {
        $fstring = '';
    }

    return sprintf '%s%s%s', join('/', grep { defined $_ } ($base, @paths)),
        $qstring, $fstring;
}

483
1;
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
__END__

=encoding utf-8

=head1 NAME

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

=head1 DESCRIPTION

This package provides some text-related functions.

=head2 Functions

=over

500
501
502
503
=item addrencode ( $addr, [ $phrase, [ $charset, [ $comment ] ] ] )

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

504
505
506
507
508
=item canonic_email ( $email )

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

509
Leading and trailing white spaces are removed.
510
511
512
513
Latin letters without accents are lower-cased.

For malformed inputs returns C<undef>.

514
515
516
517
518
=item canonic_message_id ( $message_id )

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

sikeda's avatar
sikeda committed
519
=item decode_filesystem_safe ( $str )
520
521

I<Function>.
sikeda's avatar
sikeda committed
522
Decodes a string encoded by encode_filesystem_safe().
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537

Parameter:

=over

=item $str

String to be decoded.

=back

Returns:

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

sikeda's avatar
sikeda committed
538
=item decode_html ( $str )
539
540

I<Function>.
sikeda's avatar
sikeda committed
541
Decodes HTML entities in a string encoded by UTF-8 or a Unicode string.
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556

Parameter:

=over

=item $str

String to be decoded.

=back

Returns:

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

sikeda's avatar
sikeda committed
557
=item encode_filesystem_safe ( $str )
558
559

I<Function>.
sikeda's avatar
sikeda committed
560
Encodes a string $str to be suitable for filesystem.
561
562
563
564
565
566
567
568
569
570
571
572
573

Parameter:

=over

=item $str

String to be encoded.

=back

Returns:

sikeda's avatar
sikeda committed
574
575
576
577
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.
578

sikeda's avatar
sikeda committed
579
580
Note that C<'/'> will also be encoded.

581
=item encode_html ( $str, [ $additional_unsafe ] )
582
583

I<Function>.
sikeda's avatar
sikeda committed
584
Encodes characters in a string $str to HTML entities.
585
By default
sikeda's avatar
sikeda committed
586
C<'E<lt>'>, C<'E<gt>'>, C<'E<amp>'> and C<'E<quot>'> are encoded.
587
588
589
590
591
592
593
594
595

Parameter:

=over

=item $str

String to be encoded.

596
597
598
599
600
601
=item $additional_unsafe

Character or range of characters additionally encoded as entity references.

This optional parameter was introduced on Sympa 6.2.37b.3.

602
603
604
605
=back

Returns:

sikeda's avatar
sikeda committed
606
Encoded string, I<not> stripping utf8 flag if any.
607

608
609
=item encode_uri ( $str, [ omit => $chars ] )

sikeda's avatar
sikeda committed
610
611
612
I<Function>.
Encodes potentially unsafe characters in the string using "percent" encoding
suitable for URIs.
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633

Parameters:

=over

=item $str

String to be encoded.

=item omit =E<gt> $chars

By default, all characters except those defined as "unreserved" in RFC 3986
are encoded, that is, C<[^-A-Za-z0-9._~]>.
If this parameter is given, it will prevent encoding additional characters.

=back

Returns:

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

634
635
636
637
638
639
640
641
642
=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 )

sikeda's avatar
sikeda committed
643
DEPRECATED.
644
645
Would be better to use L</"encode_uri"> or L</"mailtourl">.

646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
=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

669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
=item guessed_to_utf8( $text, [ lang, ... ] )

I<Function>.
Guesses text charset considering language context
and returns the text reencoded by UTF-8.

Parameters:

=over

=item $text

Text to be reencoded.

=item lang, ...

Language tag(s) which may be given by L<Sympa::Language/"implicated_langs">.

=back

Returns:

Reencoded text.
If any charsets could not be guessed, C<iso-8859-1> will be used
as the last resort, just because it covers full range of 8-bit.

sikeda's avatar
sikeda committed
695
696
697
=item mailtourl ( $email, [ decode_html =E<gt> 1 ],
[ query =E<gt> {key =E<gt> val, ...} ] )

sikeda's avatar
sikeda committed
698
I<Function>.
sikeda's avatar
sikeda committed
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
Constructs a C<mailto:> URL for given e-mail.

Parameters:

=over

=item $email

E-mail address.

=item decode_html =E<gt> 1

If set, arguments are assumed to include HTML entities.

=item query =E<gt> {key =E<gt> val, ...}

Optional query.

=back

Returns:

Constructed URL.

723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
=item pad ( $str, $width )

Pads space a string so that result will not be narrower than given width.

Parameters:

=over

=item $str

A string.

=item $width

If $width is false value or width of $str is not less than $width,
does nothing.
If $width is less than C<0>, pads right.
Otherwise, pads left.

=back

Returns:

Padded string.

748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
=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.

775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
=item weburl ( $base, \@paths, [ decode_html =E<gt> 1 ],
[ fragment =E<gt> $fragment ], [ query =E<gt> \%query ] )

Constructs a C<http:> or C<https:> URL under given base URI.

Parameters:

=over

=item $base

Base URI.

=item \@paths

Additional path components.

=item decode_html =E<gt> 1

If set, arguments are assumed to include HTML entities.
Exception is $base:
It is assumed not to include entities.

=item fragment =E<gt> $fragment

Optional fragment.

=item query =E<gt> \%query

Optional query.

=back

Returns:

A URI.

sikeda's avatar
sikeda committed
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
=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

842
843
=back

844
845
846
847
848
849
850
=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.

851
decode_html(), encode_html(), encode_uri() and mailtourl()
sikeda's avatar
sikeda committed
852
were added on Sympa 6.2.14, and escape_url() was deprecated.
853

854
guessed_to_utf8() and pad() were added on Sympa 6.2.17.
855

856
=cut