X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2FDOM%2FTiny.pm;h=960c4801adbd6fb5d5825a15ac869e4d7ce707f4;hb=63873d67e780fce26d459e74222f627ccebc9392;hp=699ffd94e496389b37027ae88782fd0e1d8502e7;hpb=5a70ee9d2295cf74db3b0e2476e906cdcaee1ff3;p=catagits%2FDOM-Tiny.git diff --git a/lib/DOM/Tiny.pm b/lib/DOM/Tiny.pm index 699ffd9..960c480 100644 --- a/lib/DOM/Tiny.pm +++ b/lib/DOM/Tiny.pm @@ -11,19 +11,21 @@ use overload fallback => 1; use Carp 'croak'; -use DOM::Tiny::Collection; -use DOM::Tiny::CSS; -use DOM::Tiny::HTML; +use DOM::Tiny::_Collection; +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(@_) : $self; } +sub TO_JSON { shift->_delegate('render') } + sub all_text { shift->_all_text(1, @_) } sub ancestors { _select($_[0]->_collect($_[0]->_ancestors), $_[1]) } @@ -65,7 +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); } @@ -151,7 +153,7 @@ sub tag { return $self; } -sub tap { shift->DOM::Tiny::Collection::tap(@_) } +sub tap { shift->DOM::Tiny::_Collection::tap(@_) } sub text { shift->_all_text(0, @_) } @@ -223,7 +225,7 @@ sub _build { shift->new->tree(shift)->xml(shift) } sub _collect { my $self = shift; my $xml = $self->xml; - return DOM::Tiny::Collection->new(map { $self->_build($_, $xml) } @_); + return DOM::Tiny::_Collection->new(map { $self->_build($_, $xml) } @_); } sub _content { @@ -242,7 +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); @@ -281,7 +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) = @_; @@ -420,10 +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 @@ -478,6 +481,260 @@ XML detection can also be disabled with the L 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. + + # "" + $dom->parse('123')->[0]; + +=head2 bool + + my $bool = !!$dom; + +Always true. + +=head2 hash + + my %attrs = %$dom; + +Alias for L. + + # "test" + $dom->parse('
Test
')->at('div')->{id}; + +=head2 stringify + + my $str = "$dom"; + +Alias for L. + =head1 METHODS L implements the following methods. @@ -510,8 +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 are supported. # List tag names of ancestor elements say $dom->ancestors->map('tag')->join("\n"); @@ -554,7 +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 are supported. # Find first element with "svg" namespace definition my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'}; @@ -581,7 +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

" @@ -599,8 +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 are supported. # Show tag name of random child element say $dom->children->shuffle->first->tag; @@ -636,7 +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

" @@ -654,9 +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 are supported. # Find a specific element and extract information my $id = $dom->find('div')->[23]{id}; @@ -676,8 +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 are supported. # List tags of sibling elements after this node say $dom->following->map('tag')->join("\n"); @@ -686,7 +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" @@ -696,8 +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 are supported. # True $dom->parse('

A

')->at('p')->matches('.a'); @@ -755,7 +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); @@ -766,8 +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 are supported. # List tags of sibling elements before this node say $dom->preceding->map('tag')->join("\n"); @@ -776,8 +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('A

C

')->at('p')->preceding_nodes->first->content; @@ -1026,39 +1282,216 @@ 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 +=head1 COLLECTION METHODS -L overloads the following operators. +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. -=head2 array + # Chain methods + $collection->map(sub { ucfirst })->shuffle->each(sub { + my ($word, $num) = @_; + say "$num: $word"; + }); - my @nodes = @$dom; + # Access array directly to manipulate collection + $collection->[23] += 100; + say for @$collection; -Alias for L. +=head2 compact - # "" - $dom->parse('123')->[0]; + my $new = $collection->compact; -=head2 bool +Create a new collection with all elements that are defined and not an empty +string. - my $bool = !!$dom; + # $collection contains (0, 1, undef, 2, '', 3) + $collection->compact->join(', '); # "0, 1, 2, 3" -Always true. +=head2 each -=head2 hash + my @elements = $collection->each; + $collection = $collection->each(sub {...}); - my %attrs = %$dom; +Evaluate callback for each element in collection or return all elements as a +list if none has been provided. The element will be the first argument passed +to the callback and is also available as C<$_>. -Alias for L. + # Make a numbered list + $collection->each(sub { + my ($e, $num) = @_; + say "$num: $e"; + }); - # "test" - $dom->parse('
Test
')->at('div')->{id}; +=head2 first -=head2 stringify + my $first = $collection->first; + my $first = $collection->first(qr/foo/); + my $first = $collection->first(sub {...}); + my $first = $collection->first($method); + my $first = $collection->first($method, @args); - my $str = "$dom"; +Evaluate regular expression/callback for, or call method on, each element in +collection and return the first one that matched the regular expression, or for +which the callback/method returned true. The element will be the first argument +passed to the callback and is also available as C<$_>. -Alias for L. + # Longer version + my $first = $collection->first(sub { $_->$method(@args) }); + + # Find first value that contains the word "dom" + my $interesting = $collection->first(qr/dom/i); + + # Find first value that is greater than 5 + my $greater = $collection->first(sub { $_ > 5 }); + +=head2 flatten + + my $new = $collection->flatten; + +Flatten nested collections/arrays recursively and create a new collection with +all elements. + + # $collection contains (1, [2, [3, 4], 5, [6]], 7) + $collection->flatten->join(', '); # "1, 2, 3, 4, 5, 6, 7" + +=head2 grep + + my $new = $collection->grep(qr/foo/); + my $new = $collection->grep(sub {...}); + my $new = $collection->grep($method); + my $new = $collection->grep($method, @args); + +Evaluate regular expression/callback for, or call method on, each element in +collection and create a new collection with all elements that matched the +regular expression, or for which the callback/method returned true. The element +will be the first argument passed to the callback and is also available as +C<$_>. + + # Longer version + my $new = $collection->grep(sub { $_->$method(@args) }); + + # Find all values that contain the word "dom" + my $interesting = $collection->grep(qr/dom/i); + + # Find all values that are greater than 5 + my $greater = $collection->grep(sub { $_ > 5 }); + +=head2 join + + my $stream = $collection->join; + my $stream = $collection->join("\n"); + +Turn collection into string. + + # Join all values with commas + $collection->join(', '); + +=head2 last + + my $last = $collection->last; + +Return the last element in collection. + +=head2 map + + my $new = $collection->map(sub {...}); + my $new = $collection->map($method); + my $new = $collection->map($method, @args); + +Evaluate callback for, or call method on, each element in collection and create +a new collection from the results. The element will be the first argument +passed to the callback and is also available as C<$_>. + + # Longer version + my $new = $collection->map(sub { $_->$method(@args) }); + + # Append the word "dom" to all values + my $domified = $collection->map(sub { $_ . 'dom' }); + +=head2 reduce + + my $result = $collection->reduce(sub {...}); + my $result = $collection->reduce(sub {...}, $initial); + +Reduce elements in collection with callback, the first element will be used as +initial value if none has been provided. + + # Calculate the sum of all values + my $sum = $collection->reduce(sub { $a + $b }); + + # Count how often each value occurs in collection + my $hash = $collection->reduce(sub { $a->{$b}++; $a }, {}); + +=head2 reverse + + my $new = $collection->reverse; + +Create a new collection with all elements in reverse order. + +=head2 slice + + my $new = $collection->slice(4 .. 7); + +Create a new collection with all selected elements. + + # $collection contains ('A', 'B', 'C', 'D', 'E') + $collection->slice(1, 2, 4)->join(' '); # "B C E" + +=head2 shuffle + + my $new = $collection->shuffle; + +Create a new collection with all elements in random order. + +=head2 size + + my $size = $collection->size; + +Number of elements in collection. + +=head2 sort + + my $new = $collection->sort; + my $new = $collection->sort(sub {...}); + +Sort elements based on return value of callback and create a new collection +from the results. + + # Sort values case-insensitive + my $case_insensitive = $collection->sort(sub { uc($a) cmp uc($b) }); + +=head2 tap + + $collection = $collection->tap(sub {...}); + +Equivalent to L. + +=head2 to_array + + my $array = $collection->to_array; + +Turn collection into array reference. + +=head2 uniq + + my $new = $collection->uniq; + my $new = $collection->uniq(sub {...}); + my $new = $collection->uniq($method); + my $new = $collection->uniq($method, @args); + +Create a new collection without duplicate elements, using the string +representation of either the elements or the return value of the +callback/method. + + # Longer version + my $new = $collection->uniq(sub { $_->$method(@args) }); + + # $collection contains ('foo', 'bar', 'bar', 'baz') + $collection->uniq->join(' '); # "foo bar baz" + + # $collection contains ([1, 2], [2, 1], [3, 2]) + $collection->uniq(sub{ $_->[1] })->to_array; # "[[1, 2], [2, 1]]" =head1 BUGS @@ -1079,3 +1512,7 @@ This is free software, licensed under: =head1 SEE ALSO L, L, L, L, L + +=for Pod::Coverage TO_JSON + +=cut