File: Mechanize.pm

package info (click to toggle)
libtest-www-mechanize-perl 1.20-1
  • links: PTS, VCS
  • area: main
  • in suites: lenny
  • size: 200 kB
  • ctags: 39
  • sloc: perl: 1,489; makefile: 43
file content (1191 lines) | stat: -rw-r--r-- 30,519 bytes parent folder | download
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
744
745
746
747
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
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
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
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
package Test::WWW::Mechanize;

use strict;
use warnings;

=head1 NAME

Test::WWW::Mechanize - Testing-specific WWW::Mechanize subclass

=head1 VERSION

Version 1.18

=cut

our $VERSION = '1.20';

=head1 SYNOPSIS

Test::WWW::Mechanize is a subclass of L<WWW::Mechanize> that incorporates
features for web application testing.  For example:

    use Test::More tests => 5;
    use Test::WWW::Mechanize;

    my $mech = Test::WWW::Mechanize->new;
    $mech->get_ok( $page );
    $mech->base_is( 'http://petdance.com/', 'Proper <BASE HREF>' );
    $mech->title_is( "Invoice Status", "Make sure we're on the invoice page" );
    $mech->content_contains( "Andy Lester", "My name somewhere" );
    $mech->content_like( qr/(cpan|perl)\.org/, "Link to perl.org or CPAN" );

This is equivalent to:

    use Test::More tests => 5;
    use WWW::Mechanize;

    my $mech = WWW::Mechanize->new;
    $mech->get( $page );
    ok( $mech->success );
    is( $mech->base, 'http://petdance.com', 'Proper <BASE HREF>' );
    is( $mech->title, "Invoice Status", "Make sure we're on the invoice page" );
    ok( index( $mech->content, "Andy Lester" ) >= 0, "My name somewhere" );
    like( $mech->content, qr/(cpan|perl)\.org/, "Link to perl.org or CPAN" );

but has nicer diagnostics if they fail.

Default descriptions will be supplied for most methods if you omit them. e.g.

    my $mech = Test::WWW::Mechanize->new;
    $mech->get_ok( 'http://petdance.com/' );
    $mech->base_is( 'http://petdance.com/' );
    $mech->title_is( "Invoice Status" );
    $mech->content_contains( "Andy Lester" );
    $mech->content_like( qr/(cpan|perl)\.org/ );

results in

    ok - Got 'http://petdance.com/' ok
    ok - Base is 'http://petdance.com/'
    ok - Title is 'Invoice Status'
    ok - Content contains 'Andy Lester'
    ok - Content is like '(?-xism:(cpan|perl)\.org)'

=cut

use WWW::Mechanize ();
use Test::LongString;
use Test::Builder ();
use Carp ();
use Carp::Assert::More;

use base 'WWW::Mechanize';

my $Test = Test::Builder->new();


=head1 CONSTRUCTOR

=head2 new

Behaves like, and calls, L<WWW::Mechanize>'s C<new> method.  Any parms
passed in get passed to WWW::Mechanize's constructor.

=cut

sub new {
    my $class = shift;
    my %mech_args = @_;

    my $self = $class->SUPER::new( %mech_args );

    return $self;
}

=head1 METHODS: GETTING & POSTING

=head2 $mech->get_ok($url, [ \%LWP_options ,] $desc)

A wrapper around WWW::Mechanize's get(), with similar options, except
the second argument needs to be a hash reference, not a hash. Like
well-behaved C<*_ok()> functions, it returns true if the test passed,
or false if not.

A default description of "GET $url" is used if none if provided.

=cut

sub get_ok {
    my $self = shift;
    my $url = shift;

    my $desc;
    my %opts;

    if ( @_ ) {
        my $flex = shift; # The flexible argument

        if ( !defined( $flex ) ) {
            $desc = shift;
        }
        elsif ( ref $flex eq 'HASH' ) {
            %opts = %{$flex};
            $desc = shift;
        }
        elsif ( ref $flex eq 'ARRAY' ) {
            %opts = @{$flex};
            $desc = shift;
        }
        else {
            $desc = $flex;
        }
    } # parms left

    $self->get( $url, %opts );
    my $ok = $self->success;

    if ( not defined $desc ) {
        $url = $url->url if ref($url) eq 'WWW::Mechanize::Link';
        $desc = "GET $url";
    }
    $Test->ok( $ok, $desc );
    if ( !$ok ) {
        $Test->diag( $self->status );
        $Test->diag( $self->response->message ) if $self->response;
    }

    return $ok;
}

=head2 $mech->post_ok( $url, [ \%LWP_options ,] $desc )

A wrapper around WWW::Mechanize's post(), with similar options, except
the second argument needs to be a hash reference, not a hash. Like
well-behaved C<*_ok()> functions, it returns true if the test passed,
or false if not.

A default description of "POST to $url" is used if none if provided.

=cut

sub post_ok {
    my $self = shift;
    my $url = shift;

    my $desc;
    my %opts;

    if ( @_ ) {
        my $flex = shift; # The flexible argument

        if ( !defined( $flex ) ) {
            $desc = shift;
        }
        elsif ( ref $flex eq 'HASH' ) {
            %opts = %{$flex};
            $desc = shift;
        }
        elsif ( ref $flex eq 'ARRAY' ) {
            %opts = @{$flex};
            $desc = shift;
        }
        else {
            $desc = $flex;
        }
    } # parms left

    if ( not defined $desc ) {
        $url = $url->url if ref($url) eq 'WWW::Mechanize::Link';
        $desc = "POST $url";
    }
    $self->post( $url, \%opts );
    my $ok = $self->success;
    $Test->ok( $ok, $desc );
    if ( !$ok ) {
        $Test->diag( $self->status );
        $Test->diag( $self->response->message ) if $self->response;
    }

    return $ok;
}


=head2 submit_form_ok( \%parms [, $desc] )

Makes a C<submit_form()> call and executes tests on the results.
The form must be found, and then submitted successfully.  Otherwise,
this test fails.

I<%parms> is a hashref containing the parms to pass to C<submit_form()>.
Note that the parms to C<submit_form()> are a hash whereas the parms to
this function are a hashref.  You have to call this function like:

    $agent->submit_form_ok( {n=>3}, "looking for 3rd link" );

As with other test functions, C<$desc> is optional.  If it is supplied
then it will display when running the test harness in verbose mode.

Returns true value if the specified link was found and followed
successfully.  The L<HTTP::Response> object returned by submit_form()
is not available.

=cut

sub submit_form_ok {
    my $self = shift;
    my $parms = shift || {};
    my $desc = shift;

    if ( ref $parms ne 'HASH' ) {
       Carp::croak "FATAL: parameters must be given as a hashref";
    }

    # return from submit_form() is an HTTP::Response or undef
    my $response = $self->submit_form( %{$parms} );

    my $ok;
    my $error;
    if ( !$response ) {
        $error = "No matching form found";
    }
    else {
        if ( $response->is_success ) {
            $ok = 1;
        }
        else {
            $error = $response->as_string;
        }
    }

    $Test->ok( $ok, $desc );
    $Test->diag( $error ) if $error;

    return $ok;
}


=head2 $mech->follow_link_ok( \%parms [, $desc] )

Makes a C<follow_link()> call and executes tests on the results.
The link must be found, and then followed successfully.  Otherwise,
this test fails.

I<%parms> is a hashref containing the parms to pass to C<follow_link()>.
Note that the parms to C<follow_link()> are a hash whereas the parms to
this function are a hashref.  You have to call this function like:

    $mech->follow_link_ok( {n=>3}, "looking for 3rd link" );

As with other test functions, C<$desc> is optional.  If it is supplied
then it will display when running the test harness in verbose mode.

Returns a true value if the specified link was found and followed
successfully.  The L<HTTP::Response> object returned by follow_link()
is not available.

=cut

sub follow_link_ok {
    my $self = shift;
    my $parms = shift || {};
    my $desc = shift;

    if (!defined($desc)) {
        my $parms_str = join(", ", map { join("=", $_, $parms->{$_}) } keys(%{$parms}));
        $desc = "Followed link with '$parms_str'" if !defined($desc);
    }

    if ( ref $parms ne 'HASH' ) {
       Carp::croak "FATAL: parameters must be given as a hashref";
    }

    # return from follow_link() is an HTTP::Response or undef
    my $response = $self->follow_link( %{$parms} );

    my $ok;
    my $error;
    if ( !$response ) {
        $error = "No matching link found";
    }
    else {
        if ( $response->is_success ) {
            $ok = 1;
        }
        else {
            $error = $response->as_string;
        }
    }

    $Test->ok( $ok, $desc );
    $Test->diag( $error ) if $error;

    return $ok;
}

=head1 METHODS: CONTENT CHECKING

=head2 $mech->html_lint_ok( [$msg] )

Checks the validity of the HTML on the current page.  If the page is not
HTML, then it fails.  The URI is automatically appended to the I<$msg>.

Note that HTML::Lint must be installed for this to work.  Otherwise,
it will blow up.

=cut

sub html_lint_ok {
    my $self = shift;
    my $msg = shift;

    eval 'require HTML::Lint';
    $@ and die 'html_lint_ok cannot run without HTML::Lint';

    my $uri = $self->uri;
    $msg = $msg ? "$msg ($uri)" : $uri;

    my $ok;

    if ( $self->is_html ) {

        my $lint = HTML::Lint->new;
        $lint->parse( $self->content );

        my @errors = $lint->errors;
        my $nerrors = @errors;
        if ( $nerrors ) {
            $ok = $Test->ok( 0, $msg );
            $Test->diag( "HTML::Lint errors for $uri" );
            $Test->diag( $_->as_string ) for @errors;
            my $s = $nerrors == 1 ? '' : 's';
            $Test->diag( "$nerrors error$s on the page" );
        }
        else {
            $ok = $Test->ok( 1, $msg );
        }
    }
    else {
        $ok = $Test->ok( 0, $msg );
        $Test->diag( q{This page doesn't appear to be HTML, or didn't get the proper text/html content type returned.} );
    }

    return $ok;
}


=head2 $mech->title_is( $str [, $desc ] )

Tells if the title of the page is the given string.

    $mech->title_is( "Invoice Summary" );

=cut

sub title_is {
    my $self = shift;
    my $str = shift;
    my $desc = shift;
    $desc = "Title is '$str'" if !defined($desc);

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    return is_string( $self->title, $str, $desc );
}

=head2 $mech->title_like( $regex [, $desc ] )

Tells if the title of the page matches the given regex.

    $mech->title_like( qr/Invoices for (.+)/

=cut

sub title_like {
    my $self = shift;
    my $regex = shift;
    my $desc = shift;
    $desc = "Title is like '$regex'" if !defined($desc);

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    return like_string( $self->title, $regex, $desc );
}

=head2 $mech->title_unlike( $regex [, $desc ] )

Tells if the title of the page matches the given regex.

    $mech->title_unlike( qr/Invoices for (.+)/

=cut

sub title_unlike {
    my $self = shift;
    my $regex = shift;
    my $desc = shift;
    $desc = "Title unlike '$regex'" if !defined($desc);

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    return unlike_string( $self->title, $regex, $desc );
}

=head2 $mech->base_is( $str [, $desc ] )

Tells if the base of the page is the given string.

    $mech->base_is( "http://example.com/" );

=cut

sub base_is {
    my $self = shift;
    my $str = shift;
    my $desc = shift;
    $desc = "Base is '$str'" if !defined($desc);

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    return is_string( $self->base, $str, $desc );
}

=head2 $mech->base_like( $regex [, $desc ] )

Tells if the base of the page matches the given regex.

    $mech->base_like( qr{http://example.com/index.php?PHPSESSID=(.+)});

=cut

sub base_like {
    my $self = shift;
    my $regex = shift;
    my $desc = shift;
    $desc = "Base is like '$regex'" if !defined($desc);

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    return like_string( $self->base, $regex, $desc );
}

=head2 $mech->base_unlike( $regex [, $desc ] )

Tells if the base of the page matches the given regex.

    $mech->base_unlike( qr{http://example.com/index.php?PHPSESSID=(.+)});

=cut

sub base_unlike {
    my $self = shift;
    my $regex = shift;
    my $desc = shift;
    $desc = "Base unlike '$regex'" if !defined($desc);

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    return unlike_string( $self->base, $regex, $desc );
}

=head2 $mech->content_is( $str [, $desc ] )

Tells if the content of the page matches the given string

=cut

sub content_is {
    my $self = shift;
    my $str = shift;
    my $desc = shift;

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    $desc = qq{Content is "$str"} if !defined($desc);

    return is_string( $self->content, $str, $desc );
}

=head2 $mech->content_contains( $str [, $desc ] )

Tells if the content of the page contains I<$str>.

=cut

sub content_contains {
    my $self = shift;
    my $str = shift;
    my $desc = shift;

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    if ( ref($str) eq 'REGEX' ) {
        diag( "content_contains takes a string, not a regex" );
    }
    $desc = qq{Content contains "$str"} if !defined($desc);

    return contains_string( $self->content, $str, $desc );
}

=head2 $mech->content_lacks( $str [, $desc ] )

Tells if the content of the page lacks I<$str>.

=cut

sub content_lacks {
    my $self = shift;
    my $str = shift;
    my $desc = shift;

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    if ( ref($str) eq 'REGEX' ) {
        diag( 'content_lacks takes a string, not a regex' );
    }
    $desc = qq{Content lacks "$str"} if !defined($desc);

    return lacks_string( $self->content, $str, $desc );
}

=head2 $mech->content_like( $regex [, $desc ] )

Tells if the content of the page matches I<$regex>.

=cut

sub content_like {
    my $self = shift;
    my $regex = shift;
    my $desc = shift;
    $desc = "Content is like '$regex'" if !defined($desc);

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    return like_string( $self->content, $regex, $desc );
}

=head2 $mech->content_unlike( $regex [, $desc ] )

Tells if the content of the page does NOT match I<$regex>.

=cut

sub content_unlike {
    my $self = shift;
    my $regex = shift;
    my $desc = shift;
    $desc = "Content unlike '$regex'" if !defined($desc);

    local $Test::Builder::Level = $Test::Builder::Level + 1;
    return unlike_string( $self->content, $regex, $desc );
}

=head2 $mech->has_tag( $tag, $text [, $desc ] )

Tells if the page has a C<$tag> tag with the given content in its text.

=cut

sub has_tag {
    my $self = shift;
    my $tag  = shift;
    my $text = shift;
    my $desc = shift;
    $desc = "Page has $tag tag with '$text'" if !defined($desc);

    my $found = $self->_tag_walk( $tag, sub { $text eq $_[0] } );

    return $Test->ok( $found, $desc );
}


=head2 $mech->has_tag_like( $tag, $regex [, $desc ] )

Tells if the page has a C<$tag> tag with the given content in its text.

=cut

sub has_tag_like {
    my $self = shift;
    my $tag  = shift;
    my $regex = shift;
    my $desc = shift;
    $desc = "Page has $tag tag like '$regex'" if !defined($desc);

    my $found = $self->_tag_walk( $tag, sub { $_[0] =~ $regex } );

    return $Test->ok( $found, $desc );
}


sub _tag_walk {
    my $self = shift;
    my $tag  = shift;
    my $match = shift;

    my $p = HTML::TokeParser->new( \($self->content) );

    while ( my $token = $p->get_tag( $tag ) ) {
        my $tagtext = $p->get_trimmed_text( "/$tag" );
        return 1 if $match->( $tagtext );
    }
    return;
}

=head2 $mech->followable_links()

Returns a list of links that Mech can follow.  This is only http and
https links.

=cut

sub followable_links {
    my $self = shift;

    return $self->find_all_links( url_abs_regex => qr[^https?://] );
}

=head2 $mech->page_links_ok( [ $desc ] )

Follow all links on the current page and test for HTTP status 200

    $mech->page_links_ok('Check all links');

=cut

sub page_links_ok {
    my $self = shift;
    my $desc = shift;

    $desc = 'All links ok' unless defined $desc;

    my @links = $self->followable_links();
    my @urls = _format_links(\@links);

    my @failures = $self->_check_links_status( \@urls );
    my $ok = (@failures==0);

    $Test->ok( $ok, $desc );
    $Test->diag( $_ ) for @failures;

    return $ok;
}

=head2 $mech->page_links_content_like( $regex [, $desc ] )

Follow all links on the current page and test their contents for I<$regex>.

    $mech->page_links_content_like( qr/foo/,
      'Check all links contain "foo"' );

=cut

sub page_links_content_like {
    my $self = shift;
    my $regex = shift;
    my $desc = shift;

    $desc = qq{All links are like "$regex"} unless defined $desc;

    my $usable_regex=$Test->maybe_regex( $regex );
    unless(defined( $usable_regex )) {
        my $ok = $Test->ok( 0, 'page_links_content_like' );
        $Test->diag(qq{     "$regex" doesn't look much like a regex to me.});
        return $ok;
    }

    my @links = $self->followable_links();
    my @urls = _format_links(\@links);

    my @failures = $self->_check_links_content( \@urls, $regex );
    my $ok = (@failures==0);

    $Test->ok( $ok, $desc );
    $Test->diag( $_ ) for @failures;

    return $ok;
}

=head2 $mech->page_links_content_unlike( $regex [, $desc ] )

Follow all links on the current page and test their contents do not
contain the specified regex.

    $mech->page_links_content_unlike(qr/Restricted/,
      'Check all links do not contain Restricted');

=cut

sub page_links_content_unlike {
    my $self = shift;
    my $regex = shift;
    my $desc = shift;
    $desc = "All links are unlike '$regex'" if !defined($desc);

    my $usable_regex=$Test->maybe_regex( $regex );
    unless(defined( $usable_regex )) {
        my $ok = $Test->ok( 0, 'page_links_content_unlike' );
        $Test->diag(qq{     "$regex" doesn't look much like a regex to me.});
        return $ok;
    }

    my @links = $self->followable_links();
    my @urls = _format_links(\@links);

    my @failures = $self->_check_links_content( \@urls, $regex, 'unlike' );
    my $ok = (@failures==0);

    $Test->ok( $ok, $desc );
    $Test->diag( $_ ) for @failures;

    return $ok;
}

=head2 $mech->links_ok( $links [, $desc ] )

Follow specified links on the current page and test for HTTP status
200.  The links may be specified as a reference to an array containing
L<WWW::Mechanize::Link> objects, an array of URLs, or a scalar URL
name.

    my @links = $mech->find_all_links( url_regex => qr/cnn\.com$/ );
    $mech->links_ok( \@links, 'Check all links for cnn.com' );

    my @links = qw( index.html search.html about.html );
    $mech->links_ok( \@links, 'Check main links' );

    $mech->links_ok( 'index.html', 'Check link to index' );

=cut

sub links_ok {
    my $self = shift;
    my $links = shift;
    my $desc = shift;

    my @urls = _format_links( $links );
    $desc = _default_links_desc(\@urls, 'are ok') unless defined $desc;
    my @failures = $self->_check_links_status( \@urls );
    my $ok = (@failures == 0);

    $Test->ok( $ok, $desc );
    $Test->diag( $_ ) for @failures;

    return $ok;
}

=head2 $mech->link_status_is( $links, $status [, $desc ] )

Follow specified links on the current page and test for HTTP status
passed.  The links may be specified as a reference to an array
containing L<WWW::Mechanize::Link> objects, an array of URLs, or a
scalar URL name.

    my @links = $mech->followable_links();
    $mech->link_status_is( \@links, 403,
      'Check all links are restricted' );

=cut

sub link_status_is {
    my $self = shift;
    my $links = shift;
    my $status = shift;
    my $desc = shift;

    my @urls = _format_links( $links );
    $desc = _default_links_desc(\@urls, "have status $status") if !defined($desc);
    my @failures = $self->_check_links_status( \@urls, $status );
    my $ok = (@failures == 0);

    $Test->ok( $ok, $desc );
    $Test->diag( $_ ) for @failures;

    return $ok;
}

=head2 $mech->link_status_isnt( $links, $status [, $desc ] )

Follow specified links on the current page and test for HTTP status
passed.  The links may be specified as a reference to an array
containing L<WWW::Mechanize::Link> objects, an array of URLs, or a
scalar URL name.

    my @links = $mech->followable_links();
    $mech->link_status_isnt( \@links, 404,
      'Check all links are not 404' );

=cut

sub link_status_isnt {
    my $self = shift;
    my $links = shift;
    my $status = shift;
    my $desc = shift;

    my @urls = _format_links( $links );
    $desc = _default_links_desc(\@urls, "do not have status $status") if !defined($desc);
    my @failures = $self->_check_links_status( \@urls, $status, 'isnt' );
    my $ok = (@failures == 0);

    $Test->ok( $ok, $desc );
    $Test->diag( $_ ) for @failures;

    return $ok;
}


=head2 $mech->link_content_like( $links, $regex [, $desc ] )

Follow specified links on the current page and test the resulting
content of each against I<$regex>.  The links may be specified as a
reference to an array containing L<WWW::Mechanize::Link> objects, an
array of URLs, or a scalar URL name.

    my @links = $mech->followable_links();
    $mech->link_content_like( \@links, qr/Restricted/,
        'Check all links are restricted' );

=cut

sub link_content_like {
    my $self = shift;
    my $links = shift;
    my $regex = shift;
    my $desc = shift;

    my $usable_regex=$Test->maybe_regex( $regex );
    unless(defined( $usable_regex )) {
        my $ok = $Test->ok( 0, 'link_content_like' );
        $Test->diag(qq{     "$regex" doesn't look much like a regex to me.});
        return $ok;
    }

    my @urls = _format_links( $links );
    $desc = _default_links_desc(\@urls, "are like '$regex'") if !defined($desc);
    my @failures = $self->_check_links_content( \@urls, $regex );
    my $ok = (@failures == 0);

    $Test->ok( $ok, $desc );
    $Test->diag( $_ ) for @failures;

    return $ok;
}

=head2 $mech->link_content_unlike( $links, $regex [, $desc ] )

Follow specified links on the current page and test that the resulting
content of each does not match I<$regex>.  The links may be specified as a
reference to an array containing L<WWW::Mechanize::Link> objects, an array
of URLs, or a scalar URL name.

    my @links = $mech->followable_links();
    $mech->link_content_unlike( \@links, qr/Restricted/,
      'No restricted links' );

=cut

sub link_content_unlike {
    my $self = shift;
    my $links = shift;
    my $regex = shift;
    my $desc = shift;

    my $usable_regex=$Test->maybe_regex( $regex );
    unless(defined( $usable_regex )) {
        my $ok = $Test->ok( 0, 'link_content_unlike' );
        $Test->diag(qq{     "$regex" doesn't look much like a regex to me.});
        return $ok;
    }

    my @urls = _format_links( $links );
    $desc = _default_links_desc(\@urls, qq{are not like "$regex"}) if !defined($desc);
    my @failures = $self->_check_links_content( \@urls, $regex, 'unlike' );
    my $ok = (@failures == 0);

    $Test->ok( $ok, $desc );
    $Test->diag( $_ ) for @failures;

    return $ok;
}

# Create a default description for the link_* methods, including the link count.
sub _default_links_desc {
    my ($urls, $desc_suffix) = @_;
    my $url_count = scalar(@$urls);
    return sprintf("%d link%s %s", $url_count, $url_count == 1 ? "" : "s", $desc_suffix);
}

# This actually performs the status check of each url.
sub _check_links_status {
    my $self = shift;
    my $urls = shift;
    my $status = shift || 200;
    my $test = shift || 'is';

    # Create a clone of the $mech used during the test as to not disrupt
    # the original.
    my $mech = $self->clone();

    my @failures;

    for my $url ( @$urls ) {
        if ( $mech->follow_link( url => $url ) ) {
            if ( $test eq 'is' ) {
                push( @failures, $url ) unless $mech->status() == $status;
            }
            else {
                push( @failures, $url ) unless $mech->status() != $status;
            }
            $mech->back();
        }
        else {
            push( @failures, $url );
        }
    } # for

    return @failures;
}

# This actually performs the content check of each url. 
sub _check_links_content {
    my $self = shift;
    my $urls = shift;
    my $regex = shift || qr/<html>/;
    my $test = shift || 'like';

    # Create a clone of the $mech used during the test as to not disrupt
    # the original.
    my $mech = $self->clone();

    my @failures;
    for my $url ( @$urls ) {
        if ( $mech->follow_link( url => $url ) ) {
            my $content=$mech->content();
            if ( $test eq 'like' ) {
                push( @failures, $url ) unless $content=~/$regex/;
            }
            else {
                push( @failures, $url ) unless $content!~/$regex/;
            }
            $mech->back();
        }
        else {
            push( @failures, $url );
        }
    } # for

    return @failures;
}

# Create an array of urls to match for mech to follow.
sub _format_links {
    my $links = shift;

    my @urls;
    if (ref($links) eq 'ARRAY') {
        if (defined($$links[0])) {
            if (ref($$links[0]) eq 'WWW::Mechanize::Link') {
                @urls = map { $_->url() } @{$links};
            }
            else {
                @urls = @{$links};
            }
        }
    }
    else {
        push(@urls,$links);
    }
    return @urls;
}

=head2 $mech->stuff_inputs( [\%options] )

Finds all free-text input fields (text, textarea, and password) in the
current form and fills them to their maximum length in hopes of finding
application code that can't handle it.  Fields with no maximum length
and all textarea fields are set to 66000 bytes, which will often be
enough to overflow the data's eventual recepticle.

There is no return value.

If there is no current form then nothing is done.

The hashref $options can contain the following keys:

=over

=item * ignore

hash value is arrayref of field names to not touch, e.g.:

    $mech->stuff_inputs( {
        ignore => [qw( specialfield1 specialfield2 )],
    } );

=item * fill

hash value is default string to use when stuffing fields.  Copies
of the string are repeated up to the max length of each field.  E.g.:

    $mech->stuff_inputs( {
        fill => '@'  # stuff all fields with something easy to recognize
    } );

=item * specs

hash value is arrayref of hashrefs with which you can pass detailed
instructions about how to stuff a given field.  E.g.:

    $mech->stuff_inputs( {
        specs=>{
            # Some fields are datatype-constrained.  It's most common to
            # want the field stuffed with valid data.
            widget_quantity => { fill=>'9' },
            notes => { maxlength=>2000 },
        }
    } );

The specs allowed are I<fill> (use this fill for the field rather than
the default) and I<maxlength> (use this as the field's maxlength instead
of any maxlength specified in the HTML).

=back

=cut

sub stuff_inputs {
    my $self = shift;

    my $options = shift || {};
    assert_isa( $options, 'HASH' );
    assert_in( $_, ['ignore', 'fill', 'specs'] ) foreach ( keys %{$options} );

    # set up the fill we'll use unless a field overrides it
    my $default_fill = '@';
    if ( exists $options->{fill} && defined $options->{fill} && length($options->{fill}) > 0 ) {
        $default_fill = $options->{fill};
    }

    # fields in the form to not stuff
    my $ignore = {};
    if ( exists $options->{ignore} ) {
        assert_isa( $options->{ignore}, 'ARRAY' );
        $ignore = { map {($_, 1)} @{$options->{ignore}} };
    }

    my $specs = {};
    if ( exists $options->{specs} ) {
        assert_isa( $options->{specs}, 'HASH' );
        $specs = $options->{specs};
        foreach my $field_name ( keys %{$specs} ) {
            assert_isa( $specs->{$field_name}, 'HASH' );
            assert_in( $_, ['fill', 'maxlength'] ) foreach ( keys %{$specs->{$field_name}} );
        }
    }

    my @inputs = $self->find_all_inputs( type_regex => qr/^(text|textarea|password)$/ );

    foreach my $field ( @inputs ) {
        next if $field->readonly();
        next if $field->disabled();  # TODO: HTML::Form::TextInput allows setting disabled--allow it here?

        my $name = $field->name();

        # skip if it's one of the fields to ignore
        next if exists $ignore->{ $name };

        # fields with no maxlength will get this many characters
        my $maxlength = 66000;

        # maxlength from the HTML
        if ( $field->type ne 'textarea' ) {
            if ( exists $field->{maxlength} ) {
                $maxlength = $field->{maxlength};
                # TODO: what to do about maxlength==0 ?  non-numeric? less than 0 ?
            }
        }

        my $fill = $default_fill;

        if ( exists $specs->{$name} ) {
            # process the per-field info

            if ( exists $specs->{$name}->{fill} && defined $specs->{$name}->{fill} && length($specs->{$name}->{fill}) > 0 ) {
                $fill = $specs->{$name}->{fill};
            }

            # maxlength override from specs
            if ( exists $specs->{$name}->{maxlength} && defined $specs->{$name}->{maxlength} ) {
                $maxlength = $specs->{$name}->{maxlength};
                # TODO: what to do about maxlength==0 ?  non-numeric? less than 0?
            }
        }

        # stuff it
        if ( ($maxlength % length($fill)) == 0 ) {
            # the simple case
            $field->value( $fill x ($maxlength/length($fill)) );
        }
        else {
            # can be improved later
            $field->value( substr( $fill x int(($maxlength + length($fill) - 1)/length($fill)), 0, $maxlength ) );
        }
    } # for @inputs

    return;
}

=head1 TODO

Add HTML::Tidy capabilities.

Add a broken image check.

=head1 AUTHOR

Andy Lester, C<< <andy at petdance.com> >>

=head1 BUGS

Please report any bugs or feature requests to
<http://code.google.com/p/www-mechanize/issues/list>.  I will be
notified, and then you'll automatically be notified of progress on
your bug as I make changes.

=head1 SUPPORT

You can find documentation for this module with the perldoc command.

    perldoc Test::WWW::Mechanize

You can also look for information at:

=over 4

=item * Google Code bug tracker

L<http://code.google.com/p/www-mechanize/issues/list>

Please B<do not use> the old queues for WWW::Mechanize and
Test::WWW::Mechanize at
L<http://rt.cpan.org/NoAuth/Bugs.html?Dist=Test-WWW-Mechanize>

=item * AnnoCPAN: Annotated CPAN documentation

L<http://annocpan.org/dist/Test-WWW-Mechanize>

=item * CPAN Ratings

L<http://cpanratings.perl.org/d/Test-WWW-Mechanize>

=item * Search CPAN

L<http://search.cpan.org/dist/Test-WWW-Mechanize>

=back

=head1 ACKNOWLEDGEMENTS

Thanks to
Greg Sheard,
Michael Schwern,
Mark Blackman,
Mike O'Regan,
Shawn Sorichetti,
Chris Dolan,
Matt Trout,
MATSUNO Tokuhiro,
and Pete Krawczyk for patches.

=head1 COPYRIGHT & LICENSE

Copyright 2004-2007 Andy Lester, all rights reserved.

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

=cut

1; # End of Test::WWW::Mechanize