Build.PL 000644 001750 001750 3461 12145273365 16042 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23 # =========================================================================
# THIS FILE IS AUTOMATICALLY GENERATED BY MINILLA.
# DO NOT EDIT DIRECTLY.
# =========================================================================
use 5.008_001;
use strict;
use warnings;
use utf8;
use Module::Build;
use File::Basename;
use File::Spec;
use CPAN::Meta;
use CPAN::Meta::Prereqs;
my %args = (
license => 'perl',
dynamic_config => 0,
configure_requires => {
'Module::Build' => 0.38,
},
name => 'HTML-TreeBuilder-LibXML',
module_name => 'HTML::TreeBuilder::LibXML',
allow_pure_perl => 0,
script_files => [glob('script/*'), glob('bin/*')],
test_files => ((-d '.git' || $ENV{RELEASE_TESTING}) && -d 'xt') ? 't/ xt/' : 't/',
recursive_test_files => 1,
);
if (-d 'share') {
$args{share_dir} = 'share';
}
my $builder = Module::Build->subclass(
class => 'MyBuilder',
code => q{
sub ACTION_distmeta {
die "Do not run distmeta. Install Minilla and `minil install` instead.\n";
}
sub ACTION_installdeps {
die "Do not run installdeps. Run `cpanm --installdeps .` instead.\n";
}
}
)->new(%args);
$builder->create_build_script();
my $mbmeta = CPAN::Meta->load_file('MYMETA.json');
my $meta = CPAN::Meta->load_file('META.json');
my $prereqs_hash = CPAN::Meta::Prereqs->new(
$meta->prereqs
)->with_merged_prereqs(
CPAN::Meta::Prereqs->new($mbmeta->prereqs)
)->as_string_hash;
my $mymeta = CPAN::Meta->new(
{
%{$meta->as_struct},
prereqs => $prereqs_hash
}
);
print "Merging cpanfile prereqs to MYMETA.yml\n";
$mymeta->save('MYMETA.yml', { version => 1.4 });
print "Merging cpanfile prereqs to MYMETA.json\n";
$mymeta->save('MYMETA.json', { version => 2 });
Changes 000644 001750 001750 11153 12145273365 16056 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23 Revision history for Perl extension HTML::TreeBuilder::LibXML
0.23 2013-05-17T00:16:48Z
- fixed guts(), clone() and replace_with() to properly handle XML::LibXML::Dtd nodes
- guts() now includes the Dtd node in the returned document (unless it were implicitly created)
- clone() calls createInternalSubset() on the new document
- replace_with() calls createInternalSubset() if the replacement is a XML::LibXML::Dtd (can't import Dtd node)
(cafe01)
0.22 2013-05-13T00:04:09Z
- improved guts(), calling nonBlankChildNodes() instead of childNodes()
- improved HTML::TreeBuilder::LibXML::Node documentation
(cafe01)
0.21 2013-05-12T19:12:53Z
- fixed guts(),
- now returning nodes from and instead of just
- now returning text and comment nodes instead of just element nodes
- returned nodes now belong to the same document
- fixed to_HTML to render valid html, not xml
(cafe01)
0.20 2013-05-10T20:44:16Z
- improved replace_with() on document node.
- fixed push_content() and unshift_content() to work with document mode.
(cafe01)
0.19 2013-05-10T01:03:58Z
- fixed replace_with() and parent(),
to avoid calling appendChild() on a Document node, which is not supported by XML::LibXML.
(cafe01)
0.18 2013-05-09T20:49:04Z
- implemented all node methods needed for Web::Query::LibXML to work
- clone_list
- detach
- delete_content
- content_list
- replace_with
- push_content
- unshift_content
- postinsert
- preinsert
- disembowel (HTML::TreeBuilder::LibXML)
(cafe01)
- modified parse_file() to read file content, then call parse_content()
- thats because parse_content() will detect (heuristically) when the parser will add implict tags, so guts() can work properly.
(cafe01)
0.18 2013-05-09T01:27:46Z
- implemented matches(), parent(), guts() node method
(Carlos Fernando Avila Gratz)
0.17
handle /(de)?objectify_text/ for
wassr
});
$tree->eof;
{
my @nodes = $tree->look_down('_tag' => 'a');
is scalar(@nodes), 2;
is $nodes[0]->attr('href'), 'http://wassr.jp/';
}
{
my @nodes = $tree->look_down(href => qr/mixi/);
is scalar(@nodes), 1;
is $nodes[0]->attr('href'), 'http://mixi.jp/';
}
{
my @nodes = $tree->look_down('_tag' => 'a', sub { $_[0]->attr('href') =~ /mixi/ });
is scalar(@nodes), 1;
is $nodes[0]->attr('href'), 'http://mixi.jp/';
}
{
my $none = $tree->look_down('_tag' => 'a', sub { 0 });
ok !defined $none, "none because sub ref returns 0";
}
{
$tree->elementify;
$tree->objectify_text;
my @nodes = $tree->look_down('_tag' => '~text', sub { $_[0]->attr('text') =~ /alert/ });
is scalar(@nodes), 1;
is $nodes[0]->attr('text'), 'alert("hello world")';
}
$tree = $tree->delete;
}
sub _id {
my $klass = shift;
my $tree = $klass->new;
$tree->parse($HTML);
$tree->eof;
my ($a) = $tree->look_down('_tag' => 'a');
is $a->id, undef;
$a->id("OK");
is $a->id, 'OK';
is strip($a->as_HTML), 'wassr';
$a->id(undef);
is strip($a->as_HTML), 'wassr';
$tree = $tree->delete;
}
sub _attr {
my $klass = shift;
my $tree = $klass->new;
$tree->parse($HTML);
$tree->eof;
my ($a) = $tree->look_down('_tag' => 'a');
is $a->attr('href'), 'http://wassr.jp/';
$a->attr('href', 'http://ficia.com/');
is strip($a->as_HTML), 'wassr';
$a->attr('href', undef);
is strip($a->as_HTML), 'wassr';
$tree = $tree->delete;
}
sub strip {
local $_ = shift;
s/\n$//g;
s/>\s+ "this test requires Web::Scraper" unless eval "use Web::Scraper; 1";
plan tests => 2*3+1;
can_ok 'HTML::TreeBuilder::LibXML', 'ignore_unknown';
my $html = <<'...';
wassr
...
my $code = <<'...';
use Web::Scraper;
my $ret = scraper {
process '//a', 'text[]', 'TEXT';
process '//a', 'href[]', '@href';
process '//div', 'div[]', scraper {
process '//a', 'link[]', 'TEXT';
};
}->scrape($html);
is_deeply($ret->{text}, ['wassr', 'mixi']);
is_deeply($ret->{href}, ['http://wassr.jp/', 'http://mixi.jp/']);
is_deeply($ret->{div}, [{link => ['mixi']}]);
...
&run;
HTML::TreeBuilder::LibXML->replace_original();
&run;
sub run {
eval $code;
die $@ if $@;
}
03_destructor.t 000644 001750 001750 635 12145273365 17656 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use HTML::TreeBuilder::LibXML;
plan skip_all => 'this test requires HTML::TreeBuilder::XPath' unless eval 'use HTML::TreeBuilder::XPath;1;';
plan tests => 2;
{
my $destructor = HTML::TreeBuilder::LibXML->replace_original;
isa_ok(HTML::TreeBuilder::XPath->new, 'HTML::TreeBuilder::LibXML');
}
isa_ok(HTML::TreeBuilder::XPath->new, 'HTML::TreeBuilder::XPath');
04_new_methods.t 000644 001750 001750 547 12145273365 17777 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use HTML::TreeBuilder::LibXML;
plan tests => 2;
{
my $root = HTML::TreeBuilder::LibXML->new_from_content("", "foo
", "");
is $root->findvalue("//p"), "foo";
}
{
my $root = HTML::TreeBuilder::LibXML->new_from_file("t/test.html");
is $root->findvalue("//p"), "bar";
}
05_empty.t 000644 001750 001750 573 12145273365 16621 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use HTML::TreeBuilder::LibXML;
my @tests = ("foo", "bar\nbaz", " ", " \n ", "");
plan tests => 3 * @tests;
for my $t (@tests) {
my $tree = HTML::TreeBuilder::LibXML->new;
$tree->parse($t);
$tree->eof;
ok $tree;
eval { $tree->findnodes('//a') };
ok !$@ or diag $@;
like $tree->as_HTML, qr//;
}
06_web_query.t 000644 001750 001750 3636 12145273365 17511 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use HTML::TreeBuilder::LibXML;
plan skip_all => "this test requires Web::Query" unless eval "use Web::Query; 1";
plan tests => 6;
can_ok 'HTML::TreeBuilder::LibXML', 'parse_content';
can_ok 'HTML::TreeBuilder::LibXML', 'elementify';
my $html = <<'...';
...
sub run {
my @classes;
my $text = wq($html)->find("ul#user-links li")->each(sub {
push @classes, $_->find("a span")->attr("class");
})->end->find(".logout")->text;
return (\@classes, $text);
}
isa_ok(HTML::TreeBuilder::XPath->new, 'HTML::TreeBuilder::XPath');
my ($their_classes, $their_text) = &run;
HTML::TreeBuilder::LibXML->replace_original();
isa_ok(HTML::TreeBuilder::XPath->new, 'HTML::TreeBuilder::LibXML');
my ($our_classes, $our_text) = &run;
is($our_text, $their_text);
is_deeply($our_classes, $their_classes);
HTML-TreeBuilder-XPath.t 000644 001750 001750 10034 12145273365 21202 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t # Before `make install' is performed this script should be runnable with
# `make test'. After `make install' it should work as `perl HTML-TreeBuilder-XPath.t'
#########################
use Test::More tests => 31;
BEGIN { use_ok('HTML::TreeBuilder::XPath') };
use HTML::TreeBuilder::LibXML;
HTML::TreeBuilder::LibXML->replace_original;
#########################
my $doc='
Example
Example header
Intro p1
Intro p2
Intro p3 with bold text
para including links, more links,
and even spans, several,
and that is all folks.
0
';
my $html= HTML::TreeBuilder::XPath->new_from_content( $doc);
is( $html->findvalue( '//p[@id]/@id'), 'toto', 'attribute value');
is( $html->findvalue( '//title'), 'Example', 'element text');
is( $html->findvalue( '//span[1]'), 'spans', '[1]');
is( $html->findvalue( '/html/body//p[@id="toto"]/*[@id="bar"]/@class'), 'myspan', 'attribute');
is( $html->findvalue( '//p[@id="toto"]/text()[2]'), ', ', 'text node');
# test sorting
TODO: {
local $TODO = "I don't know, this order is required for xpath spec, or not??";
is( $html->findvalue( '//*[@id="foo"]/@*'), 'myspanfoo', '2 atts on same element');
is( $html->findvalue( '//*[@id="foo"]/@id|//*[@id="foo"]/@class'), 'myspanfoo', '2 atts on same element');
is( $html->findvalue( '//*[@id="foo"]/@class|//*[@id="foo"]/@id'), 'myspanfoo', '2 atts on same element (unsorted)');
is( $html->findvalue( '//b'), 'boldall', '2 texts');
is( $html->findvalue( '//p[@id="toto"]/a'), 'linksmore links', '2 siblings');
is( $html->findvalue( '//p[@id="toto"]/a[1]|//p[@id="toto"]/a[2]'), 'linksmore links', '2 siblings');
is( $html->findvalue( '//@id[.="toto"]|//*[@id="bar"]|/html/body/h1|//@id[.="toto"]/../a[1]|//*[@id="foo"]'), 'Example headertotolinksspansseveral',
'query on various types of nodes');
};
is( $html->findvalue( './/*[@bgcolor="0"]'),'0', 'one child has a value of "0"');
{
my $p= $html->findnodes( '//p[@id="toto"]')->[0];
is( $p->findvalue( './a'), 'linksmore links', 'query on siblings of an element');
is( $p->findvalue( './a[1]|./a[2]'), 'linksmore links', 'query on siblings of an element (ordered)');
is( $p->findvalue( './a[2]|./a[1]'), 'linksmore links', 'query on siblings of an element (not ordered)');
is( $html->findvalue('id("foo")'), 'spans', 'id function');
is( $html->findvalue('id("foo")/@id'), 'foo', 'id function (attribute)');
}
is( $html->exists( '//p[@id]/@id' ) , 1 , 'does exist');
is( $html->exists( '//p[@id]/@id2' ) , 0 , 'does not exist' );
{
my @p = $html->find( 'p' );
is( scalar @p , 4 , '4 ');
is( $p[0]->getValue , 'Intro p1' , '
1');
my( $bq ) = $html->find( 'blockquote' );
is( $bq->getValue , 0 , 'bq' );
}
{
my @val = $html->findvalues('//span[@class="myspan"]');
is_deeply( \@val , [ qw/ spans several / ] , 'findvalues on multi element');
my( $val2 ) = $html->findvalues('//*[@id="bq"]');
is( $val2 , 0 , 'findvalues on unique element')
}
{
my @children = $html->findnodes( '//p[@id="toto"]')->[0]->childNodes;
is( scalar @children , 11 , 'child count');
is( $children[1]->getValue , 'links' , 'first child');
}
{
my @filter_nodes = $html->findnodes_filter( '//p' , sub { shift->getValue =~ /Intro / } );
is( scalar @filter_nodes , 3 , '3
' );
}
{
my ($div ) = $html->findnodes( '//div[@class="intro"]' );
my $left = $div->left;
is( $left->tag , 'h1' );
my $right = $div->right;
is( $right->tag , 'p' );
}
__END__
/html/body/h1 1 Example header
//@id[.="toto"] 2 toto
//@id[.="toto"]/../a[1] 3 links
//*[@id="foo"] 4 spans
//*[@id="bar"] 5 several
clone_list.t 000644 001750 001750 1066 12145273365 17330 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use Test::Exception;
use HTML::TreeBuilder::LibXML;
use HTML::TreeBuilder::LibXML::Node;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('
foo
bar');
my @original = $tree->guts;
my @clones = HTML::TreeBuilder::LibXML::Node->clone_list(@original);
is join('|', map{$_->as_HTML} @clones), 'foo
|bar', 'clone_list';
is $clones[0]->{node}->isSameNode($original[0]->{node}), 0, 'clone is not the same as original';
done_testing;
content_list.t 000644 001750 001750 645 12145273365 17664 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use HTML::TreeBuilder::LibXML;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('');
my $guts = $tree->guts;
is join('|', map {$_->as_HTML} $guts->content_list), '|', 'content_list - list context';
is $guts->content_list, 2, 'content_list - scalar context';
done_testing;
delete_content.t 000644 001750 001750 515 12145273365 20147 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use Test::Exception;
use HTML::TreeBuilder::LibXML;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('');
my ($el) = $tree->guts;
$el->delete_content;
is $el->as_HTML, '', 'delete_content';
done_testing;
detach.t 000644 001750 001750 714 12145273365 16404 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use Test::Exception;
use HTML::TreeBuilder::LibXML;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('');
my ($el) = $tree->guts;
my ($p) = $el->findnodes('./p');
my $parent = $p->detach;
is $parent->as_HTML, '', 'detach returns old parent';
isa_ok $p->{node}->parentNode, 'XML::LibXML::Document', 'element new parent';
done_testing; disembowel.t 000644 001750 001750 1703 12145273365 17325 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use HTML::TreeBuilder::LibXML;
use Data::Dumper;
# list context
my $tree = HTML::TreeBuilder::LibXML->new_from_content('');
my @nodes = $tree->disembowel;
is join('|', map {$_->as_HTML} @nodes), '|', 'disembowel - list context';
isa_ok $nodes[0]->parent->{node}, 'XML::LibXML::Document', 'first node parent';
isa_ok $nodes[1]->parent->{node}, 'XML::LibXML::Document', 'second node parent';
ok $nodes[0]->parent->{node}->isSameNode($nodes[1]->parent->{node}), 'nodes belong to the same document';
# scalar context
$tree = HTML::TreeBuilder::LibXML->new_from_content('');
my $node = $tree->disembowel;
is $node->as_HTML, '', 'disembowel - scalar context';
isa_ok $node->parent->{node}, 'XML::LibXML::Document', 'node parent';
done_testing;
guts.t 000644 001750 001750 2723 12145273365 16160 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use HTML::TreeBuilder::LibXML;
use Data::Dumper;
# list context
my $tree = HTML::TreeBuilder::LibXML->new_from_content('');
my @guts = $tree->guts;
is join('|', map {$_->as_HTML} @guts), '|', 'guts - list context';
# scalar context
my $guts = $tree->guts;
isa_ok $guts->{node}->ownerDocument, 'XML::LibXML::Document';
is $guts->as_HTML, '', 'guts - scalar context';
# guts() must return tags from implicit as well
my @nodes = HTML::TreeBuilder::LibXML->new_from_content('head tagbody tag
')->guts;
is join('|', map {$_->as_HTML} @nodes), 'head tag|body tag
';
# guts must include text and comments
@nodes = HTML::TreeBuilder::LibXML->new_from_content('head tagbody tag
some text')->guts;
is join('|', map {$_->as_HTML} @nodes), "head tag|\n|body tag
|\n| some text";
# guts must include DOCTYPE if its not implicit
my $html_with_dtd = "\n\n";
$guts = HTML::TreeBuilder::LibXML->new_from_content($html_with_dtd)->guts;
isa_ok $guts->{node}->ownerDocument->internalSubset, 'XML::LibXML::Dtd', "doctype";
is $guts->parent->as_HTML, $html_with_dtd, "document with doctype";
done_testing;
matches.t 000644 001750 001750 540 12145273365 16575 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use HTML::TreeBuilder::LibXML;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('bar
');
my ($el) = $tree->guts;
is $el->matches('//p[@class="foo"]'), 1, 'matches - positive';
is $el->matches('//p[@class="bar"]'), undef, 'matches - negative';
done_testing;
parent.t 000644 001750 001750 2157 12145273365 16470 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use Test::Exception;
use HTML::TreeBuilder::LibXML;
use HTML::TreeBuilder::LibXML::Node;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('foo
');
my ($div) = $tree->guts;
# get parent
isa_ok $div->parent, 'HTML::TreeBuilder::LibXML::Node', 'parent()';
is $div->parent->as_HTML, 'foo
', 'parent()->as_HTML';
# unset parent
$div->parent(undef);
is $div->parent, undef;
# set parent
dies_ok { $div->parent($div) } "can't set itself as parent";
# set a doc as parent
my $doc = HTML::TreeBuilder::LibXML::Node->new(XML::LibXML->createDocument);
$tree = HTML::TreeBuilder::LibXML->new_from_content('foo
');
($div) = $tree->guts;
$div->parent($doc);
is $doc->as_HTML, "foo
\n", 'set a doc as parent';
# set a doc with child as parent
$tree = HTML::TreeBuilder::LibXML->new_from_content('foo
bar
');
my ($div_foo, $div_bar) = $tree->guts(1);
$div_foo->parent($div_bar->parent);
is $div_foo->parent->as_HTML, "bar
foo
\n", 'set a doc with child as parent';
done_testing;
postinsert.t 000644 001750 001750 1002 12145273365 17375 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use Test::Exception;
use HTML::TreeBuilder::LibXML;
use HTML::TreeBuilder::LibXML::Node;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('foo
bar');
my @nodes = $tree->guts;
my ($p) = HTML::TreeBuilder::LibXML->new_from_content('')->findnodes('//p');
$p->postinsert(@nodes);
is $p->parent->as_HTML, '', 'postinsert';
done_testing;
preinsert.t 000644 001750 001750 1000 12145273365 17174 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use Test::Exception;
use HTML::TreeBuilder::LibXML;
use HTML::TreeBuilder::LibXML::Node;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('foo
bar');
my @nodes = $tree->guts;
my ($p) = HTML::TreeBuilder::LibXML->new_from_content('')->findnodes('//p');
$p->preinsert(@nodes);
is $p->parent->as_HTML, '', 'preinsert';
done_testing;
push_content.t 000644 001750 001750 1265 12145273365 17707 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use Test::Exception;
use HTML::TreeBuilder::LibXML;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('');
my ($el) = $tree->disembowel;
$el->push_content('foo', scalar HTML::TreeBuilder::LibXML->new_from_content('baz
')->guts, 'bar');
is $el->as_HTML, '', 'push_content';
my $doc = $el->parent;
isa_ok $doc->{node}, 'XML::LibXML::Document';
$doc->push_content(HTML::TreeBuilder::LibXML->new_from_content('cool
')->disembowel);
is $doc->as_HTML, "cool
\n", 'when node is a document';
done_testing;
replace_with.t 000644 001750 001750 2206 12145273365 17640 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use Test::Exception;
use HTML::TreeBuilder::LibXML;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('');
my ($div) = $tree->guts;
my ($p) = $div->findnodes('//p');
my $p2 = $p->replace_with('foo', scalar HTML::TreeBuilder::LibXML->new_from_content('baz
')->guts, 'bar');
isa_ok $p2, 'HTML::TreeBuilder::LibXML::Node', 'returned element';
ok $p2->{node}->isSameNode($p->{node}), 'returns same node';
isa_ok $p->{node}->parentNode, 'XML::LibXML::Document', 'replaced node has a document';
is $div->as_HTML, '', 'replace_with';
# when parent is a document
$tree = HTML::TreeBuilder::LibXML->new_from_content('');
($div) = $tree->disembowel;
my $doc = $div->{node}->parentNode;
$div = $div->replace_with('foo', scalar HTML::TreeBuilder::LibXML->new_from_content('baz
')->guts, 'bar');
is $doc->toString, "\nfoo\nbaz
\nbar\n", 'replace_with when parent is a document';
#diag $div->as_HTML;
#diag ref $div->{node}->parentNode;
done_testing; test.html 000644 001750 001750 51 12145273365 16606 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t
bar
unshift_content.t 000644 001750 001750 1315 12145273365 20404 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/t use strict;
use warnings;
use Test::More;
use Test::Exception;
use HTML::TreeBuilder::LibXML;
use Data::Dumper;
my $tree = HTML::TreeBuilder::LibXML->new_from_content('STUFF
');
my ($el) = $tree->disembowel;
$el->unshift_content('foo', scalar HTML::TreeBuilder::LibXML->new_from_content('baz
')->guts, 'bar');
is $el->as_HTML, '', 'unshift_content';
my $doc = $el->parent;
isa_ok $doc->{node}, 'XML::LibXML::Document';
$doc->unshift_content(HTML::TreeBuilder::LibXML->new_from_content('cool
')->disembowel);
is $doc->as_HTML, 'cool
'."\n", 'when node is a document';
done_testing;
benchmark.pl 000644 001750 001750 1674 12145273365 20201 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/tools #!/usr/bin/perl
use strict;
use warnings;
use FindBin;
use lib "$FindBin::Bin/../lib/";
use Web::Scraper;
use URI;
use Benchmark 'cmpthese';
use LWP::UserAgent;
use HTML::TreeBuilder::LibXML;
my $html = get_content();
my $scraper = scraper {
process 'a > img', 'image[]' => '@src';
};
print "Web::Scraper: $Web::Scraper::VERSION\n";
print "HTML::TreeBuilder::XPath: $HTML::TreeBuilder::XPath::VERSION\n";
print "HTML::TreeBuilder::LibXML: $HTML::TreeBuilder::LibXML::VERSION\n";
cmpthese(50, {
no_libxml => \&no_libxml,
use_libxml => \&use_libxml,
});
sub no_libxml {
my $res = $scraper->scrape($html);
}
sub use_libxml {
local *HTML::TreeBuilder::XPath::new = sub {
HTML::TreeBuilder::LibXML->new();
};
my $res = $scraper->scrape($html);
}
sub get_content {
my $ua = LWP::UserAgent->new;
my $res = $ua->get('http://www.nicovideo.jp/');
$res->is_success or die 'cannot get html';
$res->content;
}
02_perlcritic.t 000644 001750 001750 2403 12145273365 20022 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23/xt use strict;
use warnings;
use Test::More;
eval {
require Perl::Critic;
Perl::Critic->VERSION(1.105);
require Test::Perl::Critic;
Test::Perl::Critic->VERSION(1.02);
Test::Perl::Critic->import(
-profile => \(join q{}, )
);
};
note $@ if $@;
plan skip_all => "Perl::Critic 1.105+ or Test::Perl::Critic 1.02+ is not installed." if $@;
all_critic_ok('lib', 'script', 'bin');
__END__
only=1
# -------------------------------------------------------------------------
# Not important.
[BuiltinFunctions::ProhibitSleepViaSelect]
[BuiltinFunctions::RequireGlobFunction]
[ClassHierarchies::ProhibitOneArgBless]
# -------------------------------------------------------------------------
# Bug detection
[InputOutput::ProhibitBarewordFileHandles]
[Modules::RequireFilenameMatchesPackage]
[Subroutines::ProhibitNestedSubs]
[Subroutines::ProhibitReturnSort]
[TestingAndDebugging::RequireUseStrict]
[Variables::ProhibitConditionalDeclarations]
[Variables::RequireLexicalLoopIterators]
[TestingAndDebugging::ProhibitNoStrict]
allow=refs
# -------------------------------------------------------------------------
# Security issue detection
[InputOutput::RequireEncodingWithUTF8Layer]
[Modules::ProhibitEvilModules]
[InputOutput::ProhibitTwoArgOpen]
META.yml 000644 001750 001750 3050 12145273365 16011 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23 ---
abstract: 'HTML::TreeBuilder and XPath compatible interface with libxml'
author:
- 'Tokuhiro Matsuno '
build_requires:
Test::Exception: 0
Test::More: 0.98
configure_requires:
CPAN::Meta: 0
CPAN::Meta::Prereqs: 0
Module::Build: 0.38
dynamic_config: 0
generated_by: 'Minilla/v0.4.2, CPAN::Meta::Converter version 2.120921'
license: perl
meta-spec:
url: http://module-build.sourceforge.net/META-spec-v1.4.html
version: 1.4
name: HTML-TreeBuilder-LibXML
no_index:
directory:
- t
- xt
- inc
- share
- eg
- examples
- author
provides:
HTML::TreeBuilder::LibXML:
file: lib/HTML/TreeBuilder/LibXML.pm
version: 0.23
HTML::TreeBuilder::LibXML::Node:
file: lib/HTML/TreeBuilder/LibXML/Node.pm
version: 0
requires:
HTML::TreeBuilder::XPath: 0.14
LWP::UserAgent: 6
URI: 0
Web::Scraper: 0
XML::LibXML: 1.7
perl: 5.008001
resources:
bugtracker: https://github.com/tokuhirom/HTML-TreeBuilder-LibXML/issues
homepage: https://github.com/tokuhirom/HTML-TreeBuilder-LibXML
repository: git://github.com/tokuhirom/HTML-TreeBuilder-LibXML.git
version: 0.23
x_contributors:
- 'Masahiro Chiba '
- 'kimura.hideo '
- 'Tatsuhiko Miyagawa '
- 'Perlover '
- 'John SJ Anderson '
- 'Oleg G '
- 'Stanislaw Pusep '
- 'Carlos Fernando Avila Gratz '
- 'Carlos Fernando Avila Gratz '
MANIFEST 000644 001750 001750 1012 12145273365 15665 0 ustar 00cafe cafe 000000 000000 HTML-TreeBuilder-LibXML-0.23 Build.PL
Changes
LICENSE
META.json
README.md
cpanfile
lib/HTML/TreeBuilder/LibXML.pm
lib/HTML/TreeBuilder/LibXML/Node.pm
t/00_compile.t
t/01_simple.t
t/02_web_scraper.t
t/03_destructor.t
t/04_new_methods.t
t/05_empty.t
t/06_web_query.t
t/HTML-TreeBuilder-XPath.t
t/clone_list.t
t/content_list.t
t/delete_content.t
t/detach.t
t/disembowel.t
t/guts.t
t/matches.t
t/parent.t
t/postinsert.t
t/preinsert.t
t/push_content.t
t/replace_with.t
t/test.html
t/unshift_content.t
tools/benchmark.pl
xt/02_perlcritic.t
META.yml
MANIFEST 