X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2FDOM%2FTiny.pm;h=b2b789cdaa75fd12fe2f0b3749328cf10e587a41;hb=3187745294af04bb4f3ece751c5d947f373039e5;hp=bcaeb8778f06fe8b62f0a80b174f432023dc7b75;hpb=78ba405129a79256aac6d3d2d95a2758630bda0f;p=catagits%2FDOM-Tiny.git
diff --git a/lib/DOM/Tiny.pm b/lib/DOM/Tiny.pm
index bcaeb87..b2b789c 100644
--- a/lib/DOM/Tiny.pm
+++ b/lib/DOM/Tiny.pm
@@ -12,15 +12,15 @@ use overload
use Carp 'croak';
use DOM::Tiny::_Collection;
-use DOM::Tiny::CSS;
-use DOM::Tiny::HTML;
+use DOM::Tiny::_CSS;
+use DOM::Tiny::_HTML;
use Scalar::Util qw(blessed weaken);
our $VERSION = '0.001';
sub new {
my $class = shift;
- my $self = bless \DOM::Tiny::HTML->new, ref $class || $class;
+ my $self = bless \DOM::Tiny::_HTML->new, ref $class || $class;
return @_ ? $self->parse(@_) : $self;
}
@@ -67,7 +67,7 @@ sub content {
my $type = $self->type;
if ($type eq 'root' || $type eq 'tag') {
return $self->_content(0, 1, @_) if @_;
- my $html = DOM::Tiny::HTML->new(xml => $self->xml);
+ my $html = DOM::Tiny::_HTML->new(xml => $self->xml);
return join '', map { $html->tree($_)->render } _nodes($self->tree);
}
@@ -213,7 +213,7 @@ sub _all_text {
sub _ancestors {
my ($self, $root) = @_;
- return unless my $tree = $self->_parent;
+ return () unless my $tree = $self->_parent;
my @ancestors;
do { push @ancestors, $tree }
while ($tree->[0] eq 'tag') && ($tree = $tree->[3]);
@@ -244,7 +244,7 @@ sub _content {
return $self;
}
-sub _css { DOM::Tiny::CSS->new(tree => shift->tree) }
+sub _css { DOM::Tiny::_CSS->new(tree => shift->tree) }
sub _delegate {
my ($self, $method) = (shift, shift);
@@ -269,7 +269,7 @@ sub _link {
sub _maybe { $_[1] ? $_[0]->_build($_[1], $_[0]->xml) : undef }
sub _nodes {
- return unless my $tree = shift;
+ return () unless my $tree = shift;
my @nodes = @$tree[_start($tree) .. $#$tree];
return shift() ? grep { $_->[0] eq 'tag' } @nodes : @nodes;
}
@@ -283,7 +283,7 @@ sub _offset {
sub _parent { $_[0]->tree->[$_[0]->type eq 'tag' ? 3 : 2] }
-sub _parse { DOM::Tiny::HTML->new(xml => shift->xml)->parse(shift)->tree }
+sub _parse { DOM::Tiny::_HTML->new(xml => shift->xml)->parse(shift)->tree }
sub _replace {
my ($self, $parent, $child, @nodes) = @_;
@@ -389,8 +389,6 @@ sub _wrap {
=encoding utf8
-=for Pod::Coverage TO_JSON
-
=head1 NAME
DOM::Tiny - Minimalistic HTML/XML DOM parser with CSS selectors
@@ -424,10 +422,11 @@ DOM::Tiny - Minimalistic HTML/XML DOM parser with CSS selectors
=head1 DESCRIPTION
-L is a minimalistic and relaxed pure-perl HTML/XML DOM parser with
-support for the L and
-L based on L. It
-will even try to interpret broken HTML and XML, so you should not use it for
+L is a minimalistic and relaxed pure-perl HTML/XML DOM parser based
+on L. It supports the L
+and L, and
+matching based on L. It will
+even try to interpret broken HTML and XML, so you should not use it for
validation.
=head1 NODES AND ELEMENTS
@@ -482,6 +481,260 @@ XML detection can also be disabled with the L"xml"> method.
my $dom = DOM::Tiny->new->xml(0)->parse('Hi!
');
say $dom->at('p[id]')->text;
+=head1 SELECTORS
+
+L uses a CSS selector engine based on L. All CSS
+selectors that make sense for a standalone parser are supported.
+
+=head2 *
+
+Any element.
+
+ my $all = $dom->find('*');
+
+=head2 E
+
+An element of type C.
+
+ my $title = $dom->at('title');
+
+=head2 E[foo]
+
+An C element with a C attribute.
+
+ my $links = $dom->find('a[href]');
+
+=head2 E[foo="bar"]
+
+An C element whose C attribute value is exactly equal to C.
+
+ my $case_sensitive = $dom->find('input[type="hidden"]');
+ my $case_sensitive = $dom->find('input[type=hidden]');
+
+=head2 E[foo="bar" i]
+
+An C element whose C attribute value is exactly equal to any
+(ASCII-range) case-permutation of C. Note that this selector is
+EXPERIMENTAL and might change without warning!
+
+ my $case_insensitive = $dom->find('input[type="hidden" i]');
+ my $case_insensitive = $dom->find('input[type=hidden i]');
+ my $case_insensitive = $dom->find('input[class~="foo" i]');
+
+This selector is part of
+L, which is still a work
+in progress.
+
+=head2 E[foo~="bar"]
+
+An C element whose C attribute value is a list of whitespace-separated
+values, one of which is exactly equal to C.
+
+ my $foo = $dom->find('input[class~="foo"]');
+ my $foo = $dom->find('input[class~=foo]');
+
+=head2 E[foo^="bar"]
+
+An C element whose C attribute value begins exactly with the string
+C.
+
+ my $begins_with = $dom->find('input[name^="f"]');
+ my $begins_with = $dom->find('input[name^=f]');
+
+=head2 E[foo$="bar"]
+
+An C element whose C attribute value ends exactly with the string
+C.
+
+ my $ends_with = $dom->find('input[name$="o"]');
+ my $ends_with = $dom->find('input[name$=o]');
+
+=head2 E[foo*="bar"]
+
+An C element whose C attribute value contains the substring C.
+
+ my $contains = $dom->find('input[name*="fo"]');
+ my $contains = $dom->find('input[name*=fo]');
+
+=head2 E:root
+
+An C element, root of the document.
+
+ my $root = $dom->at(':root');
+
+=head2 E:nth-child(n)
+
+An C element, the C child of its parent.
+
+ my $third = $dom->find('div:nth-child(3)');
+ my $odd = $dom->find('div:nth-child(odd)');
+ my $even = $dom->find('div:nth-child(even)');
+ my $top3 = $dom->find('div:nth-child(-n+3)');
+
+=head2 E:nth-last-child(n)
+
+An C element, the C child of its parent, counting from the last one.
+
+ my $third = $dom->find('div:nth-last-child(3)');
+ my $odd = $dom->find('div:nth-last-child(odd)');
+ my $even = $dom->find('div:nth-last-child(even)');
+ my $bottom3 = $dom->find('div:nth-last-child(-n+3)');
+
+=head2 E:nth-of-type(n)
+
+An C element, the C sibling of its type.
+
+ my $third = $dom->find('div:nth-of-type(3)');
+ my $odd = $dom->find('div:nth-of-type(odd)');
+ my $even = $dom->find('div:nth-of-type(even)');
+ my $top3 = $dom->find('div:nth-of-type(-n+3)');
+
+=head2 E:nth-last-of-type(n)
+
+An C element, the C sibling of its type, counting from the last one.
+
+ my $third = $dom->find('div:nth-last-of-type(3)');
+ my $odd = $dom->find('div:nth-last-of-type(odd)');
+ my $even = $dom->find('div:nth-last-of-type(even)');
+ my $bottom3 = $dom->find('div:nth-last-of-type(-n+3)');
+
+=head2 E:first-child
+
+An C element, first child of its parent.
+
+ my $first = $dom->find('div p:first-child');
+
+=head2 E:last-child
+
+An C element, last child of its parent.
+
+ my $last = $dom->find('div p:last-child');
+
+=head2 E:first-of-type
+
+An C element, first sibling of its type.
+
+ my $first = $dom->find('div p:first-of-type');
+
+=head2 E:last-of-type
+
+An C element, last sibling of its type.
+
+ my $last = $dom->find('div p:last-of-type');
+
+=head2 E:only-child
+
+An C element, only child of its parent.
+
+ my $lonely = $dom->find('div p:only-child');
+
+=head2 E:only-of-type
+
+An C element, only sibling of its type.
+
+ my $lonely = $dom->find('div p:only-of-type');
+
+=head2 E:empty
+
+An C element that has no children (including text nodes).
+
+ my $empty = $dom->find(':empty');
+
+=head2 E:checked
+
+A user interface element C which is checked (for instance a radio-button or
+checkbox).
+
+ my $input = $dom->find(':checked');
+
+=head2 E.warning
+
+An C element whose class is "warning".
+
+ my $warning = $dom->find('div.warning');
+
+=head2 E#myid
+
+An C element with C equal to "myid".
+
+ my $foo = $dom->at('div#foo');
+
+=head2 E:not(s)
+
+An C element that does not match simple selector C.
+
+ my $others = $dom->find('div p:not(:first-child)');
+
+=head2 E F
+
+An C element descendant of an C element.
+
+ my $headlines = $dom->find('div h1');
+
+=head2 E E F
+
+An C element child of an C element.
+
+ my $headlines = $dom->find('html > body > div > h1');
+
+=head2 E + F
+
+An C element immediately preceded by an C element.
+
+ my $second = $dom->find('h1 + h2');
+
+=head2 E ~ F
+
+An C element preceded by an C element.
+
+ my $second = $dom->find('h1 ~ h2');
+
+=head2 E, F, G
+
+Elements of type C, C and C.
+
+ my $headlines = $dom->find('h1, h2, h3');
+
+=head2 E[foo=bar][bar=baz]
+
+An C element whose attributes match all following attribute selectors.
+
+ my $links = $dom->find('a[foo^=b][foo$=ar]');
+
+=head1 OPERATORS
+
+L overloads the following operators.
+
+=head2 array
+
+ my @nodes = @$dom;
+
+Alias for L"child_nodes">.
+
+ # ""
+ $dom->parse('123')->[0];
+
+=head2 bool
+
+ my $bool = !!$dom;
+
+Always true.
+
+=head2 hash
+
+ my %attrs = %$dom;
+
+Alias for L"attr">.
+
+ # "test"
+ $dom->parse('Test
')->at('div')->{id};
+
+=head2 stringify
+
+ my $str = "$dom";
+
+Alias for L"to_string">.
+
=head1 METHODS
L implements the following methods.
@@ -514,8 +767,8 @@ whitespace trimming is enabled by default.
my $collection = $dom->ancestors('div ~ p');
Find all ancestor elements of this node matching the CSS selector and return a
-L object containing these elements as L
-objects. All selectors from L are supported.
+L containing these elements as L
+objects. All selectors listed in L"SELECTORS"> are supported.
# List tag names of ancestor elements
say $dom->ancestors->map('tag')->join("\n");
@@ -558,7 +811,7 @@ node's content.
Find first descendant element of this element matching the CSS selector and
return it as a L object or return C if none could be found.
-All selectors from L are supported.
+All selectors listed in L"SELECTORS"> are supported.
# Find first element with "svg" namespace definition
my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'};
@@ -585,7 +838,7 @@ This element's attributes.
my $collection = $dom->child_nodes;
-Return a L object containing all child nodes of this
+Return a L containing all child nodes of this
element as L objects.
# "123
"
@@ -603,8 +856,8 @@ element as L objects.
my $collection = $dom->children('div ~ p');
Find all child elements of this element matching the CSS selector and return a
-L object containing these elements as L
-objects. All selectors from L are supported.
+L containing these elements as L
+objects. All selectors listed in L"SELECTORS"> are supported.
# Show tag name of random child element
say $dom->children->shuffle->first->tag;
@@ -640,7 +893,7 @@ and C nodes) or raw content.
my $collection = $dom->descendant_nodes;
-Return a L object containing all descendant nodes of
+Return a L containing all descendant nodes of
this element as L objects.
# "123
"
@@ -658,9 +911,8 @@ this element as L objects.
my $collection = $dom->find('div ~ p');
Find all descendant elements of this element matching the CSS selector and
-return a L object containing these elements as
-L objects. All selectors from L are
-supported.
+return a L containing these elements as
+L objects. All selectors listed in L"SELECTORS"> are supported.
# Find a specific element and extract information
my $id = $dom->find('div')->[23]{id};
@@ -680,8 +932,8 @@ supported.
my $collection = $dom->following('div ~ p');
Find all sibling elements after this node matching the CSS selector and return
-a L object containing these elements as L
-objects. All selectors from L are supported.
+a L containing these elements as L
+objects. All selectors listen in L"SELECTORS"> are supported.
# List tags of sibling elements after this node
say $dom->following->map('tag')->join("\n");
@@ -690,7 +942,7 @@ objects. All selectors from L are supported.
my $collection = $dom->following_nodes;
-Return a L object containing all sibling nodes after
+Return a L containing all sibling nodes after
this node as L objects.
# "C"
@@ -700,8 +952,8 @@ this node as L objects.
my $bool = $dom->matches('div ~ p');
-Check if this element matches the CSS selector. All selectors from
-L are supported.
+Check if this element matches the CSS selector. All selectors listed in
+L"SELECTORS"> are supported.
# True
$dom->parse('A
')->at('p')->matches('.a');
@@ -759,7 +1011,7 @@ no parent.
$dom = $dom->parse('I ⥠DOM::Tiny!');
-Parse HTML/XML fragment with L.
+Parse HTML/XML fragment.
# Parse XML
my $dom = DOM::Tiny->new->xml(1)->parse($xml);
@@ -770,8 +1022,8 @@ Parse HTML/XML fragment with L.
my $collection = $dom->preceding('div ~ p');
Find all sibling elements before this node matching the CSS selector and return
-a L object containing these elements as L
-objects. All selectors from L are supported.
+a L containing these elements as L
+objects. All selectors listed in L"SELECTORS"> are supported.
# List tags of sibling elements before this node
say $dom->preceding->map('tag')->join("\n");
@@ -780,8 +1032,8 @@ objects. All selectors from L are supported.
my $collection = $dom->preceding_nodes;
-Return a L object containing all sibling nodes before
-this node as L objects.
+Return a L containing all sibling nodes
+before this node as L objects.
# "A"
$dom->parse('AC
')->at('p')->preceding_nodes->first->content;
@@ -1030,45 +1282,11 @@ children of the first innermost element.
Disable HTML semantics in parser and activate case-sensitivity, defaults to
auto detection based on processing instructions.
-=head1 OPERATORS
-
-L overloads the following operators.
-
-=head2 array
-
- my @nodes = @$dom;
-
-Alias for L"child_nodes">.
-
- # ""
- $dom->parse('123')->[0];
-
-=head2 bool
-
- my $bool = !!$dom;
-
-Always true.
-
-=head2 hash
-
- my %attrs = %$dom;
-
-Alias for L"attr">.
-
- # "test"
- $dom->parse('Test
')->at('div')->{id};
-
-=head2 stringify
-
- my $str = "$dom";
-
-Alias for L"to_string">.
-
=head1 COLLECTION METHODS
-Some L methods return an array-based collection object, which can
-either be accessed directly as an array reference, or with the following
-methods.
+Some L methods return an array-based collection object based on
+L, which can either be accessed directly as an array
+reference, or with the following methods.
# Chain methods
$collection->map(sub { ucfirst })->shuffle->each(sub {
@@ -1293,4 +1511,8 @@ This is free software, licensed under:
=head1 SEE ALSO
-L, L, L, L, L
+L, L, L, L, L
+
+=for Pod::Coverage TO_JSON
+
+=cut