summaryrefslogtreecommitdiffstats
path: root/Bugzilla/Util.pm
blob: c5cfc0444282469a377ed6ff08a4b707c3703d87 (plain)
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
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
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
279
280
281
282
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
312
313
314
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
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
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
447
448
449
450
451
452
453
454
455
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
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
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
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
# -*- Mode: perl; indent-tabs-mode: nil -*-
#
# The contents of this file are subject to the Mozilla Public
# License Version 1.1 (the "License"); you may not use this file
# except in compliance with the License. You may obtain a copy of
# the License at http://www.mozilla.org/MPL/
#
# Software distributed under the License is distributed on an "AS
# IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
# implied. See the License for the specific language governing
# rights and limitations under the License.
#
# The Original Code is the Bugzilla Bug Tracking System.
#
# The Initial Developer of the Original Code is Netscape Communications
# Corporation. Portions created by Netscape are
# Copyright (C) 1998 Netscape Communications Corporation. All
# Rights Reserved.
#
# Contributor(s): Terry Weissman <terry@mozilla.org>
#                 Dan Mosedale <dmose@mozilla.org>
#                 Jacob Steenhagen <jake@bugzilla.org>
#                 Bradley Baetz <bbaetz@student.usyd.edu.au>
#                 Christopher Aillon <christopher@aillon.com>
#                 Max Kanat-Alexander <mkanat@bugzilla.org>
#                 Frédéric Buclin <LpSolit@gmail.com>

package Bugzilla::Util;

use strict;

use base qw(Exporter);
@Bugzilla::Util::EXPORT = qw(is_tainted trick_taint detaint_natural
                             detaint_signed
                             html_quote url_quote value_quote xml_quote
                             css_class_quote
                             i_am_cgi get_netaddr
                             lsearch
                             diff_arrays diff_strings
                             trim wrap_comment find_wrap_point
                             perform_substs
                             format_time format_time_decimal validate_date
                             file_mod_time is_7bit_clean
                             bz_crypt generate_random_password
                             validate_email_syntax clean_text);

use Bugzilla::Constants;

use Date::Parse;
use Date::Format;
use Text::Wrap;

# This is from the perlsec page, slightly modified to remove a warning
# From that page:
#      This function makes use of the fact that the presence of
#      tainted data anywhere within an expression renders the
#      entire expression tainted.
# Don't ask me how it works...
sub is_tainted {
    return not eval { my $foo = join('',@_), kill 0; 1; };
}

sub trick_taint {
    require Carp;
    Carp::confess("Undef to trick_taint") unless defined $_[0];
    my ($match) = $_[0] =~ /^(.*)$/s;
    $_[0] = $match;
    return (defined($_[0]));
}

sub detaint_natural {
    my ($match) = $_[0] =~ /^(\d+)$/;
    $_[0] = $match;
    return (defined($_[0]));
}

sub detaint_signed {
    my ($match) = $_[0] =~ /^([-+]?\d+)$/;
    $_[0] = $match;
    # Remove any leading plus sign.
    if (defined($_[0]) && $_[0] =~ /^\+(\d+)$/) {
        $_[0] = $1;
    }
    return (defined($_[0]));
}

sub html_quote {
    my ($var) = (@_);
    $var =~ s/\&/\&amp;/g;
    $var =~ s/</\&lt;/g;
    $var =~ s/>/\&gt;/g;
    $var =~ s/\"/\&quot;/g;
    return $var;
}

# This originally came from CGI.pm, by Lincoln D. Stein
sub url_quote {
    my ($toencode) = (@_);
    $toencode =~ s/([^a-zA-Z0-9_\-.])/uc sprintf("%%%02x",ord($1))/eg;
    return $toencode;
}

sub css_class_quote {
    my ($toencode) = (@_);
    $toencode =~ s/ /_/g;
    $toencode =~ s/([^a-zA-Z0-9_\-.])/uc sprintf("&#x%x;",ord($1))/eg;
    return $toencode;
}

sub value_quote {
    my ($var) = (@_);
    $var =~ s/\&/\&amp;/g;
    $var =~ s/</\&lt;/g;
    $var =~ s/>/\&gt;/g;
    $var =~ s/\"/\&quot;/g;
    # See bug http://bugzilla.mozilla.org/show_bug.cgi?id=4928 for 
    # explanation of why Bugzilla does this linebreak substitution. 
    # This caused form submission problems in mozilla (bug 22983, 32000).
    $var =~ s/\r\n/\&#013;/g;
    $var =~ s/\n\r/\&#013;/g;
    $var =~ s/\r/\&#013;/g;
    $var =~ s/\n/\&#013;/g;
    return $var;
}

sub xml_quote {
    my ($var) = (@_);
    $var =~ s/\&/\&amp;/g;
    $var =~ s/</\&lt;/g;
    $var =~ s/>/\&gt;/g;
    $var =~ s/\"/\&quot;/g;
    $var =~ s/\'/\&apos;/g;
    return $var;
}

sub url_decode {
    my ($todecode) = (@_);
    $todecode =~ tr/+/ /;       # pluses become spaces
    $todecode =~ s/%([0-9a-fA-F]{2})/pack("c",hex($1))/ge;
    return $todecode;
}

sub i_am_cgi {
    # I use SERVER_SOFTWARE because it's required to be
    # defined for all requests in the CGI spec.
    return exists $ENV{'SERVER_SOFTWARE'} ? 1 : 0;
}

sub lsearch {
    my ($list,$item) = (@_);
    my $count = 0;
    foreach my $i (@$list) {
        if ($i eq $item) {
            return $count;
        }
        $count++;
    }
    return -1;
}

sub diff_arrays {
    my ($old_ref, $new_ref) = @_;

    my @old = @$old_ref;
    my @new = @$new_ref;

    # For each pair of (old, new) entries:
    # If they're equal, set them to empty. When done, @old contains entries
    # that were removed; @new contains ones that got added.
    foreach my $oldv (@old) {
        foreach my $newv (@new) {
            next if ($newv eq '');
            if ($oldv eq $newv) {
                $newv = $oldv = '';
            }
        }
    }

    my @removed = grep { $_ ne '' } @old;
    my @added = grep { $_ ne '' } @new;
    return (\@removed, \@added);
}

sub trim {
    my ($str) = @_;
    if ($str) {
      $str =~ s/^\s+//g;
      $str =~ s/\s+$//g;
    }
    return $str;
}

sub diff_strings {
    my ($oldstr, $newstr) = @_;

    # Split the old and new strings into arrays containing their values.
    $oldstr =~ s/[\s,]+/ /g;
    $newstr =~ s/[\s,]+/ /g;
    my @old = split(" ", $oldstr);
    my @new = split(" ", $newstr);

    my ($rem, $add) = diff_arrays(\@old, \@new);

    my $removed = join (", ", @$rem);
    my $added = join (", ", @$add);

    return ($removed, $added);
}

sub wrap_comment {
    my ($comment) = @_;
    my $wrappedcomment = "";

    # Use 'local', as recommended by Text::Wrap's perldoc.
    local $Text::Wrap::columns = COMMENT_COLS;
    # Make words that are longer than COMMENT_COLS not wrap.
    local $Text::Wrap::huge    = 'overflow';
    # Don't mess with tabs.
    local $Text::Wrap::unexpand = 0;

    # If the line starts with ">", don't wrap it. Otherwise, wrap.
    foreach my $line (split(/\r\n|\r|\n/, $comment)) {
      if ($line =~ qr/^>/) {
        $wrappedcomment .= ($line . "\n");
      }
      else {
        $wrappedcomment .= (wrap('', '', $line) . "\n");
      }
    }

    return $wrappedcomment;
}

sub find_wrap_point {
    my ($string, $maxpos) = @_;
    if (!$string) { return 0 }
    if (length($string) < $maxpos) { return length($string) }
    my $wrappoint = rindex($string, ",", $maxpos); # look for comma
    if ($wrappoint < 0) {  # can't find comma
        $wrappoint = rindex($string, " ", $maxpos); # look for space
        if ($wrappoint < 0) {  # can't find space
            $wrappoint = rindex($string, "-", $maxpos); # look for hyphen
            if ($wrappoint < 0) {  # can't find hyphen
                $wrappoint = $maxpos;  # just truncate it
            } else {
                $wrappoint++; # leave hyphen on the left side
            }
        }
    }
    return $wrappoint;
}

sub perform_substs {
    my ($str, $substs) = (@_);
    $str =~ s/%([a-z]*)%/(defined $substs->{$1} ? $substs->{$1} : Bugzilla->params->{$1})/eg;
    return $str;
}

sub format_time {
    my ($date, $format) = @_;

    # If $format is undefined, try to guess the correct date format.    
    my $show_timezone;
    if (!defined($format)) {
        if ($date =~ m/^(\d{4})[-\.](\d{2})[-\.](\d{2}) (\d{2}):(\d{2})(:(\d{2}))?$/) {
            my $sec = $7;
            if (defined $sec) {
                $format = "%Y-%m-%d %T";
            } else {
                $format = "%Y-%m-%d %R";
            }
        } else {
            # Default date format. See Date::Format for other formats available.
            $format = "%Y-%m-%d %R";
        }
        # By default, we want the timezone to be displayed.
        $show_timezone = 1;
    }
    else {
        # Search for %Z or %z, meaning we want the timezone to be displayed.
        # Till bug 182238 gets fixed, we assume Bugzilla->params->{'timezone'}
        # is used.
        $show_timezone = ($format =~ s/\s?%Z$//i);
    }

    # str2time($date) is undefined if $date has an invalid date format.
    my $time = str2time($date);

    if (defined $time) {
        $date = time2str($format, $time);
        $date .= " " . Bugzilla->params->{'timezone'} if $show_timezone;
    }
    else {
        # Don't let invalid (time) strings to be passed to templates!
        $date = '';
    }
    return trim($date);
}

sub format_time_decimal {
    my ($time) = (@_);

    my $newtime = sprintf("%.2f", $time);

    if ($newtime =~ /0\Z/) {
        $newtime = sprintf("%.1f", $time);
    }

    return $newtime;
}

sub file_mod_time {
    my ($filename) = (@_);
    my ($dev,$ino,$mode,$nlink,$uid,$gid,$rdev,$size,
        $atime,$mtime,$ctime,$blksize,$blocks)
        = stat($filename);
    return $mtime;
}

sub bz_crypt {
    my ($password) = @_;

    # The list of characters that can appear in a salt.  Salts and hashes
    # are both encoded as a sequence of characters from a set containing
    # 64 characters, each one of which represents 6 bits of the salt/hash.
    # The encoding is similar to BASE64, the difference being that the
    # BASE64 plus sign (+) is replaced with a forward slash (/).
    my @saltchars = (0..9, 'A'..'Z', 'a'..'z', '.', '/');

    # Generate the salt.  We use an 8 character (48 bit) salt for maximum
    # security on systems whose crypt uses MD5.  Systems with older
    # versions of crypt will just use the first two characters of the salt.
    my $salt = '';
    for ( my $i=0 ; $i < 8 ; ++$i ) {
        $salt .= $saltchars[rand(64)];
    }

    # Crypt the password.
    my $cryptedpassword = crypt($password, $salt);

    # Return the crypted password.
    return $cryptedpassword;
}

sub generate_random_password {
    my $size = shift || 10; # default to 10 chars if nothing specified
    return join("", map{ ('0'..'9','a'..'z','A'..'Z')[rand 62] } (1..$size));
}

sub validate_email_syntax {
    my ($addr) = @_;
    my $match = Bugzilla->params->{'emailregexp'};
    my $ret = ($addr =~ /$match/ && $addr !~ /[\\\(\)<>&,;:"\[\] \t\r\n]/);
    return $ret ? 1 : 0;
}

sub validate_date {
    my ($date) = @_;
    my $date2;

    # $ts is undefined if the parser fails.
    my $ts = str2time($date);
    if ($ts) {
        $date2 = time2str("%Y-%m-%d", $ts);

        $date =~ s/(\d+)-0*(\d+?)-0*(\d+?)/$1-$2-$3/; 
        $date2 =~ s/(\d+)-0*(\d+?)-0*(\d+?)/$1-$2-$3/;
    }
    my $ret = ($ts && $date eq $date2);
    return $ret ? 1 : 0;
}

sub is_7bit_clean {
    return $_[0] !~ /[^\x20-\x7E\x0A\x0D]/;
}

sub clean_text {
    my ($dtext) = shift;
    $dtext =~  s/[\x00-\x1F\x7F]+/ /g;   # change control characters into a space
    return trim($dtext);
}

sub get_netaddr {
    my $ipaddr = shift;

    # Check for a valid IPv4 addr which we know how to parse
    if (!$ipaddr || $ipaddr !~ /^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$/) {
        return undef;
    }

    my $addr = unpack("N", pack("CCCC", split(/\./, $ipaddr)));

    my $maskbits = Bugzilla->params->{'loginnetmask'};

    # Make Bugzilla ignore the IP address if loginnetmask is set to 0
    return "0.0.0.0" if ($maskbits == 0);

    $addr >>= (32-$maskbits);

    $addr <<= (32-$maskbits);
    return join(".", unpack("CCCC", pack("N", $addr)));
}

1;

__END__

=head1 NAME

Bugzilla::Util - Generic utility functions for bugzilla

=head1 SYNOPSIS

  use Bugzilla::Util;

  # Functions for dealing with variable tainting
  $rv = is_tainted($var);
  trick_taint($var);
  detaint_natural($var);
  detaint_signed($var);

  # Functions for quoting
  html_quote($var);
  url_quote($var);
  value_quote($var);
  xml_quote($var);

  # Functions for decoding
  $rv = url_decode($var);

  # Functions that tell you about your environment
  my $is_cgi = i_am_cgi();
  $net_addr = get_netaddr($ip_addr);

  # Functions for searching
  $loc = lsearch(\@arr, $val);

  # Data manipulation
  ($removed, $added) = diff_arrays(\@old, \@new);

  # Functions for manipulating strings
  $val = trim(" abc ");
  ($removed, $added) = diff_strings($old, $new);
  $wrapped = wrap_comment($comment);
  $msg = perform_substs($str, $substs);

  # Functions for formatting time
  format_time($time);

  # Functions for dealing with files
  $time = file_mod_time($filename);

  # Cryptographic Functions
  $crypted_password = bz_crypt($password);
  $new_password = generate_random_password($password_length);

  # Validation Functions
  validate_email_syntax($email);
  validate_date($date);

=head1 DESCRIPTION

This package contains various utility functions which do not belong anywhere
else.

B<It is not intended as a general dumping group for something which
people feel might be useful somewhere, someday>. Do not add methods to this
package unless it is intended to be used for a significant number of files,
and it does not belong anywhere else.

=head1 FUNCTIONS

This package provides several types of routines:

=head2 Tainting

Several functions are available to deal with tainted variables. B<Use these
with care> to avoid security holes.

=over 4

=item C<is_tainted>

Determines whether a particular variable is tainted

=item C<trick_taint($val)>

Tricks perl into untainting a particular variable.

Use trick_taint() when you know that there is no way that the data
in a scalar can be tainted, but taint mode still bails on it.

B<WARNING!! Using this routine on data that really could be tainted defeats
the purpose of taint mode.  It should only be used on variables that have been
sanity checked in some way and have been determined to be OK.>

=item C<detaint_natural($num)>

This routine detaints a natural number. It returns a true value if the
value passed in was a valid natural number, else it returns false. You
B<MUST> check the result of this routine to avoid security holes.

=item C<detaint_signed($num)>

This routine detaints a signed integer. It returns a true value if the
value passed in was a valid signed integer, else it returns false. You
B<MUST> check the result of this routine to avoid security holes.

=back

=head2 Quoting

Some values may need to be quoted from perl. However, this should in general
be done in the template where possible.

=over 4

=item C<html_quote($val)>

Returns a value quoted for use in HTML, with &, E<lt>, E<gt>, and E<34> being
replaced with their appropriate HTML entities.

=item C<url_quote($val)>

Quotes characters so that they may be included as part of a url.

=item C<css_class_quote($val)>

Quotes characters so that they may be used as CSS class names. Spaces
are replaced by underscores.

=item C<value_quote($val)>

As well as escaping html like C<html_quote>, this routine converts newlines
into &#013;, suitable for use in html attributes.

=item C<xml_quote($val)>

This is similar to C<html_quote>, except that ' is escaped to &apos;. This
is kept separate from html_quote partly for compatibility with previous code
(for &apos;) and partly for future handling of non-ASCII characters.

=item C<url_decode($val)>

Converts the %xx encoding from the given URL back to its original form.

=back

=head2 Environment and Location

Functions returning information about your environment or location.

=over 4

=item C<i_am_cgi()>

Tells you whether or not you are being run as a CGI script in a web
server. For example, it would return false if the caller is running
in a command-line script.

=item C<get_netaddr($ipaddr)>

Given an IP address, this returns the associated network address, using
C<Bugzilla->params->{'loginnetmask'}> as the netmask. This can be used
to obtain data in order to restrict weak authentication methods (such as
cookies) to only some addresses.

=back

=head2 Searching

Functions for searching within a set of values.

=over 4

=item C<lsearch($list, $item)>

Returns the position of C<$item> in C<$list>. C<$list> must be a list
reference.

If the item is not in the list, returns -1.

=back

=head2 Data Manipulation

=over 4

=item C<diff_arrays(\@old, \@new)>

 Description: Takes two arrayrefs, and will tell you what it takes to 
              get from @old to @new.
 Params:      @old = array that you are changing from
              @new = array that you are changing to
 Returns:     A list of two arrayrefs. The first is a reference to an 
              array containing items that were removed from @old. The
              second is a reference to an array containing items
              that were added to @old. If both returned arrays are 
              empty, @old and @new contain the same values.

=back

=head2 String Manipulation

=over 4

=item C<trim($str)>

Removes any leading or trailing whitespace from a string. This routine does not
modify the existing string.

=item C<diff_strings($oldstr, $newstr)>

Takes two strings containing a list of comma- or space-separated items
and returns what items were removed from or added to the new one, 
compared to the old one. Returns a list, where the first entry is a scalar
containing removed items, and the second entry is a scalar containing added
items.

=item C<wrap_comment($comment)>

Takes a bug comment, and wraps it to the appropriate length. The length is
currently specified in C<Bugzilla::Constants::COMMENT_COLS>. Lines beginning
with ">" are assumed to be quotes, and they will not be wrapped.

The intended use of this function is to wrap comments that are about to be
displayed or emailed. Generally, wrapped text should not be stored in the
database.

=item C<find_wrap_point($string, $maxpos)>

Search for a comma, a whitespace or a hyphen to split $string, within the first
$maxpos characters. If none of them is found, just split $string at $maxpos.
The search starts at $maxpos and goes back to the beginning of the string.

=item C<perform_substs($str, $substs)>

Performs substitutions for sending out email with variables in it,
or for inserting a parameter into some other string.

Takes a string and a reference to a hash containing substitution 
variables and their values.

If the hash is not specified, or if we need to substitute something
that's not in the hash, then we will use parameters to do the 
substitution instead.

Substitutions are always enclosed with '%' symbols. So they look like:
%some_variable_name%. If "some_variable_name" is a key in the hash, then
its value will be placed into the string. If it's not a key in the hash,
then the value of the parameter called "some_variable_name" will be placed
into the string.

=item C<is_7bit_clean($str)>

Returns true is the string contains only 7-bit characters (ASCII 32 through 126,
ASCII 10 (LineFeed) and ASCII 13 (Carrage Return).

=item C<clean_text($str)>
Returns the parameter "cleaned" by exchanging non-printable characters with spaces.
Specifically characters (ASCII 0 through 31) and (ASCII 127) will become ASCII 32 (Space).

=back

=head2 Formatting Time

=over 4

=item C<format_time($time)>

Takes a time, converts it to the desired format and appends the timezone
as defined in editparams.cgi, if desired. This routine will be expanded
in the future to adjust for user preferences regarding what timezone to
display times in.

This routine is mainly called from templates to filter dates, see
"FILTER time" in Templates.pm. In this case, $format is undefined and
the routine has to "guess" the date format that was passed to $dbh->sql_date_format().


=item C<format_time_decimal($time)>

Returns a number with 2 digit precision, unless the last digit is a 0. Then it 
returns only 1 digit precision.

=back


=head2 Files

=over 4

=item C<file_mod_time($filename)>

Takes a filename and returns the modification time. It returns it in the format
of the "mtime" parameter of the perl "stat" function.

=back

=head2 Cryptography

=over 4

=item C<bz_crypt($password)>

Takes a string and returns a C<crypt>ed value for it, using a random salt.

Please always use this function instead of the built-in perl "crypt"
when initially encrypting a password.

=begin undocumented

Random salts are generated because the alternative is usually
to use the first two characters of the password itself, and since
the salt appears in plaintext at the beginning of the encrypted
password string this has the effect of revealing the first two
characters of the password to anyone who views the encrypted version.

=end undocumented

=item C<generate_random_password($password_length)>

Returns an alphanumeric string with the specified length
(10 characters by default). Use this function to generate passwords
and tokens.

=back

=head2 Validation

=over 4

=item C<validate_email_syntax($email)>

Do a syntax checking for a legal email address and returns 1 if
the check is successful, else returns 0.

=item C<validate_date($date)>

Make sure the date has the correct format and returns 1 if
the check is successful, else returns 0.

=back