/usr/share/perl5/Test/WWW/Mechanize.pm is in libtest-www-mechanize-perl 1.50-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 | package Test::WWW::Mechanize;
use strict;
use warnings;
=head1 NAME
Test::WWW::Mechanize - Testing-specific WWW::Mechanize subclass
=head1 VERSION
Version 1.50
=cut
our $VERSION = '1.50';
=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->text_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( format => 'text' ), '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 - Text contains 'Andy Lester'
ok - Content is like '(?-xism:(cpan|perl)\.org)'
=cut
use HTML::TokeParser ();
use WWW::Mechanize ();
use Test::LongString;
use Test::Builder ();
use Carp ();
use Carp::Assert::More;
use parent 'WWW::Mechanize';
my $TB = Test::Builder->new();
=head1 CONSTRUCTOR
=head2 new( %args )
Behaves like, and calls, L<WWW::Mechanize>'s C<new> method. Any parms
passed in get passed to WWW::Mechanize's constructor.
You can pass in C<< autolint => 1 >> to make Test::WWW::Mechanize
automatically run HTML::Lint after any of the following methods are
called. You can also pass in an HTML::Lint object like this:
my $lint = HTML::Lint->new( only_types => HTML::Lint::Error::STRUCTURE );
my $mech = Test::WWW::Mechanize->new( autolint => $lint );
The same is also possible with C<< autotidy => 1 >> to use HTML::Tidy5.
=over
=item * get_ok()
=item * post_ok()
=item * submit_form_ok()
=item * follow_link_ok()
=item * click_ok()
=back
This means you no longer have to do the following:
my $mech = Test::WWW::Mechanize->new();
$mech->get_ok( $url, 'Fetch the intro page' );
$mech->html_lint_ok( 'Intro page looks OK' );
and can simply do
my $mech = Test::WWW::Mechanize->new( autolint => 1 );
$mech->get_ok( $url, 'Fetch the intro page' );
The C<< $mech->get_ok() >> only counts as one test in the test count. Both the
main IO operation and the linting must pass for the entire test to pass.
You can control autolint and autotidy on the fly with the C<autolint>
and C<autotidy> methods.
=cut
sub new {
my $class = shift;
my %args = (
agent => "Test-WWW-Mechanize/$VERSION",
@_
);
my $autolint = delete $args{autolint};
my $autotidy = delete $args{autotidy};
my $self = $class->SUPER::new( %args );
$self->autolint( $autolint );
$self->autotidy( $autotidy );
return $self;
}
=head1 METHODS: HTTP VERBS
=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,$desc,%opts) = $self->_unpack_args( 'GET', @_ );
$self->get( $url, %opts );
my $ok = $self->success;
$ok = $self->_post_load_validation( $ok, $desc );
return $ok;
}
sub _post_load_validation {
my $self = shift;
my $ok = shift;
my $desc = shift;
local $Test::Builder::Level = $Test::Builder::Level + 1;
if ( $ok ) {
my $emitted_ok = 0;
if ( $self->is_html ) {
if ( $self->autolint && $self->autotidy ) {
my $msg = 'autolint & autotidy';
$msg .= ": $desc" if defined $desc;
$TB->subtest(
$desc,
sub {
$self->_lint_content_ok();
$self->_tidy_content_ok();
}
);
++$emitted_ok;
}
else {
if ( $self->autolint ) {
$ok = $self->_lint_content_ok( $desc );
++$emitted_ok;
}
elsif ( $self->autotidy ) {
$ok = $self->_tidy_content_ok( $desc );
++$emitted_ok;
}
}
}
if ( !$emitted_ok ) {
$TB->ok( $ok, $desc );
}
}
else {
$TB->ok( $ok, $desc );
$TB->diag( $self->status );
$TB->diag( $self->response->message ) if $self->response;
}
return $ok;
}
=head2 $mech->head_ok($url, [ \%LWP_options ,] $desc)
A wrapper around WWW::Mechanize's head(), 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 "HEAD $url" is used if none if provided.
=cut
sub head_ok {
my $self = shift;
my ($url,$desc,%opts) = $self->_unpack_args( 'HEAD', @_ );
$self->head( $url, %opts );
my $ok = $self->success;
$TB->ok( $ok, $desc );
if ( !$ok ) {
$TB->diag( $self->status );
$TB->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.
B<NOTE> Due to compatibility reasons it is not possible to pass
additional LWP_options beyond form data via this method (such as
Content or Content-Type). It is recommend that you use WWW::Mechanize's
post() directly for instances where more granular control of the post
is needed.
A default description of "POST to $url" is used if none if provided.
=cut
sub post_ok {
my $self = shift;
my ($url,$desc,%opts) = $self->_unpack_args( 'POST', @_ );
$self->post( $url, \%opts );
my $ok = $self->success;
$ok = $self->_post_load_validation( $ok, $desc );
return $ok;
}
=head2 $mech->put_ok( $url, [ \%LWP_options ,] $desc )
A wrapper around WWW::Mechanize's put(), 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 "PUT to $url" is used if none if provided.
=cut
sub put_ok {
my $self = shift;
my ($url,$desc,%opts) = $self->_unpack_args( 'PUT', @_ );
$opts{content} = '' if !exists $opts{content};
$self->put( $url, %opts );
my $ok = $self->success;
$TB->ok( $ok, $desc );
if ( !$ok ) {
$TB->diag( $self->status );
$TB->diag( $self->response->message ) if $self->response;
}
return $ok;
}
=head2 $mech->delete_ok( $url, [ \%LWP_options ,] $desc )
A wrapper around WWW::Mechanize's delete(), 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 "DELETE to $url" is used if none if provided.
=cut
sub delete_ok {
my $self = shift;
my ($url,$desc,%opts) = $self->_unpack_args( 'DELETE', @_ );
if ($self->can('delete')) {
$self->delete( $url, %opts );
}
else {
# When version of LWP::UserAgent is older than 6.04.
$self->_delete( $url, %opts );
}
my $ok = $self->success;
$ok = $self->_post_load_validation( $ok, $desc );
return $ok;
}
sub _delete {
require URI;
require HTTP::Request::Common;
my $self = shift;
my $uri = shift;
$uri = $uri->url if ref($uri) eq 'WWW::Mechanize::Link';
$uri = $self->base
? URI->new_abs( $uri, $self->base )
: URI->new($uri);
my @parameters = ( $uri->as_string, @_ );
my @suff = $self->_process_colonic_headers( \@parameters, 1 );
return $self->request( HTTP::Request::Common::DELETE(@parameters), @suff );
}
=head2 $mech->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:
$mech->submit_form_ok( {
form_number => 3,
fields => {
answer => 42
},
}, 'now we just need the question'
);
As with other test functions, C<$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 = $response && $response->is_success;
$ok = $self->_post_load_validation( $ok, $desc );
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}));
$desc = qq{Followed link with "$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 = $response && $response->is_success;
$ok = $self->_post_load_validation( $ok, $desc );
return $ok;
}
=head2 $mech->click_ok( $button[, $desc] )
Clicks the button named by C<$button>. An optional C<$desc> can
be given for the test.
=cut
sub click_ok {
my $self = shift;
my $button = shift;
my $desc = shift;
my $response = $self->click( $button );
if ( !$response ) {
return $TB->ok( 0, $desc );
}
my $ok = $response->is_success;
$ok = $self->_post_load_validation( $ok, $desc );
return $ok;
}
sub _unpack_args {
my $self = shift;
my $method = 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';
$desc = "$method $url";
}
return ($url, $desc, %opts);
}
=head1 METHODS: HEADER CHECKING
=head2 $mech->header_exists_ok( $header [, $desc ] )
Assures that a given response header exists. The actual value of the
response header is not checked, only that the header exists.
=cut
sub header_exists_ok {
my $self = shift;
my $header = shift;
my $desc = shift || qq{Response has $header header};
return $TB->ok( defined($self->response->header($header)), $desc );
}
=head2 $mech->lacks_header_ok( $header [, $desc ] )
Assures that a given response header does NOT exist.
=cut
sub lacks_header_ok {
my $self = shift;
my $header = shift;
my $desc = shift || qq{Response lacks $header header};
return $TB->ok( !defined($self->response->header($header)), $desc );
}
=head2 $mech->header_is( $header, $value [, $desc ] )
Assures that a given response header exists and has the given value.
=cut
sub header_is {
my $self = shift;
my $header = shift;
my $value = shift;
my $desc = shift || qq{Response has $header header with value "$value"};
# Force scalar context.
my $actual_value = $self->response->header($header);
my $ok;
if ( defined( $actual_value ) ) {
$ok = $TB->is_eq( $actual_value, $value, $desc );
}
else {
$ok = $TB->ok( 0, $desc );
$TB->diag( "Header $header does not exist" );
}
return $ok;
}
=head2 $mech->header_like( $header, $value [, $desc ] )
Assures that a given response header exists and has the given value.
=cut
sub header_like {
my $self = shift;
my $header = shift;
my $regex = shift;
my $desc = shift || qq{Response has $header header that matches regex $regex};
# Force scalar context.
my $actual_value = $self->response->header($header);
return $TB->like( $self->response->header($header), $regex, $desc );
}
=head1 METHODS: CONTENT CHECKING
=head2 $mech->html_lint_ok( [$desc] )
Checks the validity of the HTML on the current page using the HTML::Lint
module. If the page is not HTML, then it fails. The URI is automatically
appended to the I<$desc>.
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 $desc = shift;
my $uri = $self->uri;
$desc = $desc ? "$desc ($uri)" : $uri;
my $ok;
if ( $self->is_html ) {
$ok = $self->_lint_content_ok( $desc );
}
else {
$ok = $TB->ok( 0, $desc );
$TB->diag( q{This page doesn't appear to be HTML, or didn't get the proper text/html content type returned.} );
}
return $ok;
}
sub _lint_content_ok {
local $Test::Builder::Level = $Test::Builder::Level + 1;
my $self = shift;
my $desc = shift;
my $module = "HTML::Lint 2.20";
if ( not ( eval "use $module; 1;" ) ) {
die "Test::WWW::Mechanize can't do linting without $module: $@";
}
my $lint = $self->{autolint};
if ( ref $lint && $lint->isa('HTML::Lint') ) {
$lint->newfile;
$lint->clear_errors;
}
else {
$lint = HTML::Lint->new();
}
$lint->parse( $self->content );
$lint->eof();
my @errors = $lint->errors;
my $nerrors = @errors;
my $ok;
if ( $nerrors ) {
$ok = $TB->ok( 0, $desc );
$TB->diag( 'HTML::Lint errors for ' . $self->uri );
$TB->diag( $_->as_string ) for @errors;
my $s = $nerrors == 1 ? '' : 's';
$TB->diag( "$nerrors error$s on the page" );
}
else {
$ok = $TB->ok( 1, $desc );
}
return $ok;
}
=head2 $mech->html_tidy_ok( [$desc] )
Checks the validity of the HTML on the current page using the HTML::Tidy
module. If the page is not HTML, then it fails. The URI is automatically
appended to the I<$desc>.
Note that HTML::tidy must be installed for this to work. Otherwise,
it will blow up.
=cut
sub html_tidy_ok {
my $self = shift;
my $desc = shift;
my $uri = $self->uri;
$desc = $desc ? "$desc ($uri)" : $uri;
my $ok;
if ( $self->is_html ) {
$ok = $self->_tidy_content_ok( $desc );
}
else {
$ok = $TB->ok( 0, $desc );
$TB->diag( q{This page doesn't appear to be HTML, or didn't get the proper text/html content type returned.} );
}
return $ok;
}
sub _tidy_content_ok {
local $Test::Builder::Level = $Test::Builder::Level + 1;
my $self = shift;
my $desc = shift;
my $module = 'HTML::Tidy5 1.00';
if ( not ( eval "use $module; 1;" ) ) {
die "Test::WWW::Mechanize can't do tidying without $module: $@";
}
my $tidy = $self->{autotidy};
if ( ref $tidy && $tidy->isa('HTML::Tidy5') ) {
$tidy->clear_messages();
}
else {
$tidy = HTML::Tidy5->new();
}
$tidy->parse( '', $self->content );
my @messages = $tidy->messages;
my $nmessages = @messages;
my $ok;
if ( $nmessages ) {
$ok = $TB->ok( 0, $desc );
$TB->diag( 'HTML::Tidy5 messages for ' . $self->uri );
$TB->diag( $_->as_string ) for @messages;
my $s = $nmessages == 1 ? '' : 's';
$TB->diag( "$nmessages message$s on the page" );
}
else {
$ok = $TB->ok( 1, $desc );
}
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;
$desc = qq{Title is "$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;
$desc = qq{Title is like "$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;
$desc = qq{Title is unlike "$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;
$desc = qq{Base is "$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;
$desc = qq{Base is like "$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;
$desc = qq{Base is unlike "$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) ) {
return $TB->ok( 0, 'Test::WWW::Mechanize->content_contains called incorrectly. It requires a scalar, not a reference.' );
}
$desc = qq{Content contains "$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) ) {
return $TB->ok( 0, 'Test::WWW::Mechanize->content_lacks called incorrectly. It requires a scalar, not a reference.' );
}
$desc = qq{Content lacks "$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;
$desc = qq{Content is like "$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 $desc = shift || qq{Content is unlike "$regex"};
local $Test::Builder::Level = $Test::Builder::Level + 1;
return unlike_string( $self->content, $regex, $desc );
}
=head2 $mech->text_contains( $str [, $desc ] )
Tells if the text form of the page's content contains I<$str>.
When your page contains HTML which is difficult, unimportant, or
unlikely to match over time as designers alter markup, use
C<text_contains> instead of L</content_contains>.
# <b>Hi, <i><a href="some/path">User</a></i>!</b>
$mech->content_contains('Hi, User'); # Fails.
$mech->text_contains('Hi, User'); # Passes.
Text is determined by calling C<< $mech->text() >>.
See L<WWW::Mechanize/content>.
=cut
sub text_contains {
my $self = shift;
my $str = shift;
my $desc = shift || qq{Text contains "$str"};
local $Test::Builder::Level = $Test::Builder::Level + 1;
if ( ref($str) ) {
return $TB->ok( 0, 'Test::WWW::Mechanize->text_contains called incorrectly. It requires a scalar, not a reference.' );
}
return contains_string( $self->text, $str, $desc );
}
=head2 $mech->text_lacks( $str [, $desc ] )
Tells if the text of the page lacks I<$str>.
=cut
sub text_lacks {
my $self = shift;
my $str = shift;
my $desc = shift;
local $Test::Builder::Level = $Test::Builder::Level + 1;
if ( ref($str) ) {
return $TB->ok( 0, 'Test::WWW::Mechanize->text_lacks called incorrectly. It requires a scalar, not a reference.' );
}
$desc = qq{Text lacks "$str"} if !defined($desc);
return lacks_string( $self->text, $str, $desc );
}
=head2 $mech->text_like( $regex [, $desc ] )
Tells if the text form of the page's content matches I<$regex>.
=cut
sub text_like {
my $self = shift;
my $regex = shift;
my $desc = shift || qq{Text is like "$regex"};
local $Test::Builder::Level = $Test::Builder::Level + 1;
return like_string( $self->text, $regex, $desc );
}
=head2 $mech->text_unlike( $regex [, $desc ] )
Tells if the text format of the page's content does NOT match I<$regex>.
=cut
sub text_unlike {
my $self = shift;
my $regex = shift;
my $desc = shift || qq{Text is unlike "$regex"};
local $Test::Builder::Level = $Test::Builder::Level + 1;
return unlike_string( $self->text, $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 || qq{Page has $tag tag with "$text"};
my $found = $self->_tag_walk( $tag, sub { $text eq $_[0] } );
return $TB->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 = qq{Page has $tag tag like "$regex"} if !defined($desc);
my $found = $self->_tag_walk( $tag, sub { $_[0] =~ $regex } );
return $TB->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();
return 1 if $match->( $tagtext );
}
return;
}
=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);
$TB->ok( $ok, $desc );
$TB->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 $usable_regex=$TB->maybe_regex( $regex );
if ( !defined( $usable_regex ) ) {
my $ok = $TB->ok( 0, 'page_links_content_like' );
$TB->diag(qq{ "$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);
$TB->ok( $ok, $desc );
$TB->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;
$desc = qq{All links are unlike "$regex"} unless defined($desc);
my $usable_regex=$TB->maybe_regex( $regex );
if ( !defined( $usable_regex ) ) {
my $ok = $TB->ok( 0, 'page_links_content_unlike' );
$TB->diag(qq{ "$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);
$TB->ok( $ok, $desc );
$TB->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);
$TB->ok( $ok, $desc );
$TB->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);
$TB->ok( $ok, $desc );
$TB->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);
$TB->ok( $ok, $desc );
$TB->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 $usable_regex=$TB->maybe_regex( $regex );
if ( !defined( $usable_regex ) ) {
my $ok = $TB->ok( 0, 'link_content_like' );
$TB->diag(qq{ "$regex" doesn't look much like a regex to me.});
return $ok;
}
my @urls = _format_links( $links );
$desc = _default_links_desc( \@urls, qq{are like "$regex"} ) if !defined($desc);
my @failures = $self->_check_links_content( \@urls, $regex );
my $ok = (@failures == 0);
$TB->ok( $ok, $desc );
$TB->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 $usable_regex=$TB->maybe_regex( $regex );
if ( !defined( $usable_regex ) ) {
my $ok = $TB->ok( 0, 'link_content_unlike' );
$TB->diag(qq{ "$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);
$TB->ok( $ok, $desc );
$TB->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 ) if $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 ) if $content =~ /$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') {
my $link = $links->[0];
if ( defined($link) ) {
if ( ref($link) eq 'WWW::Mechanize::Link' ) {
@urls = map { $_->url() } @{$links};
}
else {
@urls = @{$links};
}
}
}
else {
push(@urls,$links);
}
return @urls;
}
=head1 METHODS: SCRAPING
=head2 $mech->scrape_text_by_attr( $attr, $attr_value [, $html ] )
=head2 $mech->scrape_text_by_attr( $attr, $attr_regex [, $html ] )
Returns an array of strings, each string the text surrounded by an
element with attribute I<$attr> of value I<$value>. You can also pass in
a regular expression. If nothing is found the return is an empty list.
In scalar context the return is the first string found.
If passed, I<$html> is scraped instead of the current page's content.
=cut
sub scrape_text_by_attr {
my $self = shift;
my $attr = shift;
my $value = shift;
my $html = $self->_get_optional_html( @_ );
my @results;
if ( defined $html ) {
my $parser = HTML::TokeParser->new(\$html);
while ( my $token = $parser->get_tag() ) {
if ( ref $token->[1] eq 'HASH' ) {
if ( exists $token->[1]->{$attr} ) {
my $matched =
(ref $value eq 'Regexp')
? $token->[1]->{$attr} =~ $value
: $token->[1]->{$attr} eq $value;
if ( $matched ) {
my $tag = $token->[ 0 ];
push @results, $parser->get_trimmed_text( "/$tag" );
if ( !wantarray ) {
last;
}
}
}
}
}
}
return $results[0] if !wantarray;
return @results;
}
=head2 $mech->scrape_text_by_id( $id [, $html ] )
Finds all elements with the given ID attribute and pulls out the text that that element encloses.
In list context, returns a list of all strings found. In scalar context, returns the first one found.
If C<$html> is not provided then the current content is used.
=cut
sub scrape_text_by_id {
my $self = shift;
my $id = shift;
my $html = $self->_get_optional_html( @_ );
my @results;
if ( defined $html ) {
# If the ID doesn't appear anywhere in the text, then there's no point in parsing.
my $found = index( $html, $id );
if ( $found >= 0 ) {
my $parser = HTML::TokeParser->new( \$html );
while ( my $token = $parser->get_tag() ) {
if ( ref $token->[1] eq 'HASH' ) {
my $actual_id = $token->[1]->{id};
$actual_id = '' unless defined $actual_id;
if ( $actual_id eq $id ) {
my $tag = $token->[ 0 ];
push @results, $parser->get_trimmed_text( "/$tag" );
if ( !wantarray ) {
last;
}
}
}
}
}
}
return $results[0] if !wantarray;
return @results;
}
sub _get_optional_html {
my $self = shift;
my $html;
if ( @_ ) {
$html = shift;
assert_nonblank( $html, '$html passed in is a populated scalar' );
}
else {
if ( $self->is_html ) {
$html = $self->content();
}
}
return $html;
}
=head2 $mech->scraped_id_is( $id, $expected [, $msg] )
Scrapes the current page for given ID and tests that it matches the expected value.
=cut
sub scraped_id_is {
my $self = shift;
my $id = shift;
my $expected = shift;
my $msg = shift;
my $ok;
my $got = $self->scrape_text_by_id( $id );
if ( defined( $got ) ) {
$ok = $TB->is_eq( $got, $expected, $msg );
}
else {
$ok = $TB->ok( 0, $msg );
$TB->diag( qq{Can't find ID "$id" to compare to "$expected"} );
}
return $ok;
}
=head2 $mech->scraped_id_like( $id, $expected_regex [, $msg] )
Scrapes the current page for given id and tests that it matches the expected regex.
=cut
sub scraped_id_like {
my $self = shift;
my $id = shift;
my $expected = shift;
my $msg = shift;
my $ok;
my $got = $self->scrape_text_by_id( $id );
if ( defined($got) ) {
$ok = $TB->like( $got, $expected, $msg );
}
else {
$ok = $TB->ok( 0, $msg );
$TB->diag( qq{Can't find ID "$id" to match against $expected} );
}
return $ok;
}
=head1 METHODS: MISCELLANEOUS
=head2 $mech->autolint( [$status] )
Without an argument, this method returns a true or false value indicating
whether autolint is active.
When passed an argument, autolint is turned on or off depending on whether
the argument is true or false, and the previous autolint status is returned.
As with the autolint option of C<< new >>, C<< $status >> can be an
L<< HTML::Lint >> object.
If autolint is currently using an L<< HTML::Lint >> object you provided,
the return is that object, so you can change and exactly restore
autolint status:
my $old_status = $mech->autolint( 0 );
... operations that should not be linted ...
$mech->autolint( $old_status );
=cut
sub autolint {
my $self = shift;
my $ret = $self->{autolint};
if ( @_ ) {
$self->{autolint} = shift;
}
return $ret;
}
=head2 $mech->autotidy( [$status] )
Without an argument, this method returns a true or false value indicating
whether autotidy is active.
When passed an argument, autotidy is turned on or off depending on whether
the argument is true or false, and the previous autotidy status is returned.
As with the autotidy option of C<< new >>, C<< $status >> can be an
L<< HTML::Tidy5 >> object.
If autotidy is currently using an L<< HTML::Tidy5 >> object you provided,
the return is that object, so you can change and exactly restore
autotidy status:
my $old_status = $mech->autotidy( 0 );
... operations that should not be tidied ...
$mech->autotidy( $old_status );
=cut
sub autotidy {
my $self = shift;
my $ret = $self->{autotidy};
if ( @_ ) {
$self->{autotidy} = shift;
}
return $ret;
}
=head2 $mech->grep_inputs( \%properties )
grep_inputs() returns an array of all the input controls in the
current form whose properties match all of the regexes in $properties.
The controls returned are all descended from HTML::Form::Input.
If $properties is undef or empty then all inputs will be
returned.
If there is no current page, there is no form on the current
page, or there are no submit controls in the current form
then the return will be an empty array.
# get all text controls whose names begin with "customer"
my @customer_text_inputs =
$mech->grep_inputs( {
type => qr/^(text|textarea)$/,
name => qr/^customer/
}
);
=cut
sub grep_inputs {
my $self = shift;
my $properties = shift;
my @found;
my $form = $self->current_form();
if ( $form ) {
my @inputs = $form->inputs();
@found = _grep_hashes( \@inputs, $properties );
}
return @found;
}
=head2 $mech->grep_submits( \%properties )
grep_submits() does the same thing as grep_inputs() except that
it only returns controls that are submit controls, ignoring
other types of input controls like text and checkboxes.
=cut
sub grep_submits {
my $self = shift;
my $properties = shift || {};
$properties->{type} = qr/^(?:submit|image)$/; # submits only
my @found = $self->grep_inputs( $properties );
return @found;
}
# search an array of hashrefs, returning an array of the incoming
# hashrefs that match *all* the pattern in $patterns.
sub _grep_hashes {
my $hashes = shift;
my $patterns = shift || {};
my @found;
if ( ! %{$patterns} ) {
# nothing to match on, so return them all
@found = @{$hashes};
}
else {
foreach my $hash ( @{$hashes} ) {
# check every pattern for a match on the current hash
my $matches_everything = 1;
foreach my $pattern_key ( keys %{$patterns} ) {
$matches_everything = 0 unless exists $hash->{$pattern_key} && $hash->{$pattern_key} =~ $patterns->{$pattern_key};
last if !$matches_everything;
}
push @found, $hash if $matches_everything;
}
}
return @found;
}
=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 receptacle.
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;
}
=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?|file)://} );
}
=head2 $mech->lacks_uncapped_inputs( [$comment] )
Executes a test to make sure that the current form content has no
text input fields that lack the C<maxlength> attribute, and that each
C<maxlength> value is a positive integer. The test fails if the current
form has such a field, and succeeds otherwise.
Checks that all text input fields in the current form specify a maximum
input length. Fields for which the concept of input length is irrelevant,
and controls that HTML does not allow to be capped (e.g. textarea)
are ignored.
The inputs in the returned array are descended from HTML::Form::Input.
The return is true if the test succeeded, false otherwise.
=cut
sub lacks_uncapped_inputs {
my $self = shift;
my $comment = shift;
local $Test::Builder::Level = $Test::Builder::Level + 1;
my @uncapped;
my @inputs = $self->grep_inputs( { type => qr/^(?:text|password)$/ } );
foreach my $field ( @inputs ) {
next if $field->readonly();
next if $field->disabled();
if ( not defined($field->{maxlength}) ) {
push( @uncapped, $field->name . ' has no maxlength attribute' );
next;
}
my $val = $field->{maxlength};
if ( ($val !~ /^\s*\d+\s*$/) || ($val+0 <= 0) ) {
push( @uncapped, $field->name . qq{ has an invalid maxlength attribute of "$val"} );
}
}
my $ok = $TB->cmp_ok( scalar @uncapped, '==', 0, $comment );
$TB->diag( $_ ) for @uncapped;
return $ok;
}
=head1 TODO
Add HTML::Tidy capabilities.
Other ideas for features are at https://github.com/petdance/test-www-mechanize
=head1 AUTHOR
Andy Lester, C<< <andy at petdance.com> >>
=head1 BUGS
Please report any bugs or feature requests to
<https://github.com/petdance/test-www-mechanize>.
=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 * Bug tracker
L<https://github.com/petdance/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
Eric A. Zarko,
moznion,
Robert Stone,
tynovsky,
Jerry Gay,
Jonathan "Duke" Leto,
Philip G. Potter,
Niko Tyni,
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 2004-2018 Andy Lester.
This library is free software; you can redistribute it and/or modify it
under the terms of the Artistic License version 2.0.
=cut
1; # End of Test::WWW::Mechanize
|