From 41bfd8d773ddaed4776ab1ec76752e5b90fc4ce7 Mon Sep 17 00:00:00 2001
From: Jess Robinson
Date: Sat, 16 Nov 2019 19:26:56 +0000
Subject: [PATCH 1/6] Initial attempt at HTMLv5 support TODO: Needs docs
---
lib/HTML/Tagset.pm | 227 +++++---------------
lib/HTML/Tagset/v4.pm | 472 ++++++++++++++++++++++++++++++++++++++++
lib/HTML/Tagset/v5.pm | 486 ++++++++++++++++++++++++++++++++++++++++++
t/02_versions.t | 17 ++
4 files changed, 1033 insertions(+), 169 deletions(-)
create mode 100644 lib/HTML/Tagset/v4.pm
create mode 100644 lib/HTML/Tagset/v5.pm
create mode 100644 t/02_versions.t
diff --git a/lib/HTML/Tagset.pm b/lib/HTML/Tagset.pm
index 7c60861..76ca3a6 100644
--- a/lib/HTML/Tagset.pm
+++ b/lib/HTML/Tagset.pm
@@ -2,6 +2,9 @@ package HTML::Tagset;
use strict;
+use HTML::Tagset::v4;
+use HTML::Tagset::v5;
+
=head1 NAME
HTML::Tagset - data tables useful in parsing HTML
@@ -32,10 +35,29 @@ set -- the hash conveys that its keys are there, and the actual values
associated with the keys are not significant. (But what values are
there, are always true.)
+=cut
+
+use vars qw(
+ $VERSION
+ $HTML_VERSION
+ %emptyElement %optionalEndTag %linkElements %boolean_attr
+ %isHeadElement %isBodyElement %isPhraseMarkup
+ %is_Possible_Strict_P_Content
+ %isHeadOrBodyElement
+ %isList %isTableElement %isFormElement
+ %isKnown %canTighten
+ @p_closure_barriers
+ %isCDATA_Parent
+);
+
=head1 VARIABLES
Note that none of these variables are exported.
+=head2 HTML_VERSION
+
+=cut
+
=head2 hashset %HTML::Tagset::emptyElement
This hashset has as values the tag-names (GIs) of elements that cannot
@@ -45,17 +67,42 @@ C<$HTML::Tagset::emptyElement{'dl'}> does not exist, and so is not true.
=cut
-our %emptyElement = map { $_ => 1 } qw(
- base link meta isindex
- img br hr wbr
- input area param
- embed bgsound spacer
- basefont col frame
- ~comment ~literal
- ~declaration ~pi
- );
-# The "~"-initial names are for pseudo-elements used by HTML::Entities
-# and TreeBuilder
+if($HTML_VERSION eq 'v5') {
+ %emptyElement = %HTML::Tagset::v5::emptyElement;
+ %optionalEndTag = %HTML::Tagset::v5::optionalEndTag;
+ %linkElements = %HTML::Tagset::v5::linkElements;
+ %boolean_attr = %HTML::Tagset::v5::boolean_attr;
+ %isPhraseMarkup = %HTML::Tagset::v5::isPhraseMarkup;
+ %is_Possible_Strict_P_Content = %HTML::Tagset::v5::is_Possible_Strict_P_Content;
+ %isHeadElement = %HTML::Tagset::v5::isHeadElement;
+ %isList = %HTML::Tagset::v5::isList;
+ %isTableElement = %HTML::Tagset::v5::isTableElement;
+ %isFormElement = %HTML::Tagset::v5::isFormElement;
+ %isBodyElement = %HTML::Tagset::v5::isBodyElement;
+ %isHeadOrBodyElement = %HTML::Tagset::v5::isHeadOrBodyElement;
+ %isKnown = %HTML::Tagset::v5::isKnown;
+ %canTighten = %HTML::Tagset::v5::canTighten;
+ @p_closure_barriers = @HTML::Tagset::v5::p_closure_barriers;
+ %isCDATA_Parent = %HTML::Tagset::v5::isCDATA_Parent;
+} else {
+ # default to v4
+ %emptyElement = %HTML::Tagset::v4::emptyElement;
+ %optionalEndTag = %HTML::Tagset::v4::optionalEndTag;
+ %linkElements = %HTML::Tagset::v4::linkElements;
+ %boolean_attr = %HTML::Tagset::v4::boolean_attr;
+ %isPhraseMarkup = %HTML::Tagset::v4::isPhraseMarkup;
+ %is_Possible_Strict_P_Content = %HTML::Tagset::v4::is_Possible_Strict_P_Content;
+ %isHeadElement = %HTML::Tagset::v4::isHeadElement;
+ %isList = %HTML::Tagset::v4::isList;
+ %isTableElement = %HTML::Tagset::v4::isTableElement;
+ %isFormElement = %HTML::Tagset::v4::isFormElement;
+ %isBodyElement = %HTML::Tagset::v4::isBodyElement;
+ %isHeadOrBodyElement = %HTML::Tagset::v4::isHeadOrBodyElement;
+ %isKnown = %HTML::Tagset::v4::isKnown;
+ %canTighten = %HTML::Tagset::v4::canTighten;
+ @p_closure_barriers = @HTML::Tagset::v4::p_closure_barriers;
+ %isCDATA_Parent = %HTML::Tagset::v4::isCDATA_Parent;
+}
=head2 hashset %HTML::Tagset::optionalEndTag
@@ -65,10 +112,6 @@ C<$HTML::Tagset::emptyElement{'li'}> exists and is true.
=cut
-our %optionalEndTag = map { $_ => 1 } qw(
- p li dt dd
-); # option th tr td);
-
=head2 hash %HTML::Tagset::linkElements
Values in this hash are tagnames for elements that might contain
@@ -77,38 +120,6 @@ of attributes whose values can be links.
=cut
-our %linkElements =
-(
- 'a' => ['href'],
- 'applet' => ['archive', 'codebase', 'code'],
- 'area' => ['href'],
- 'base' => ['href'],
- 'bgsound' => ['src'],
- 'blockquote' => ['cite'],
- 'body' => ['background'],
- 'del' => ['cite'],
- 'embed' => ['pluginspage', 'src'],
- 'form' => ['action'],
- 'frame' => ['src', 'longdesc'],
- 'iframe' => ['src', 'longdesc'],
- 'ilayer' => ['background'],
- 'img' => ['src', 'lowsrc', 'longdesc', 'usemap'],
- 'input' => ['src', 'usemap'],
- 'ins' => ['cite'],
- 'isindex' => ['action'],
- 'head' => ['profile'],
- 'layer' => ['background', 'src'],
- 'link' => ['href'],
- 'object' => ['classid', 'codebase', 'data', 'archive', 'usemap'],
- 'q' => ['cite'],
- 'script' => ['src', 'for'],
- 'table' => ['background'],
- 'td' => ['background'],
- 'th' => ['background'],
- 'tr' => ['background'],
- 'xmp' => ['href'],
-);
-
=head2 hash %HTML::Tagset::boolean_attr
This hash (not hashset) lists what attributes of what elements can be
@@ -119,23 +130,6 @@ the value is a reference to a hashset containing all such attributes.
=cut
-our %boolean_attr = (
-# TODO: make these all hashes
- 'area' => 'nohref',
- 'dir' => 'compact',
- 'dl' => 'compact',
- 'hr' => 'noshade',
- 'img' => 'ismap',
- 'input' => { 'checked' => 1, 'readonly' => 1, 'disabled' => 1 },
- 'menu' => 'compact',
- 'ol' => 'compact',
- 'option' => 'selected',
- 'select' => 'multiple',
- 'td' => 'nowrap',
- 'th' => 'nowrap',
- 'ul' => 'compact',
-);
-
#==========================================================================
# List of all elements from Extensible HTML version 1.0 Transitional DTD:
#
@@ -164,18 +158,6 @@ This hashset contains all phrasal-level elements.
=cut
-our %isPhraseMarkup = map { $_ => 1 } qw(
- span abbr acronym q sub sup
- cite code em kbd samp strong var dfn strike
- b i u s tt small big
- ins del
- a img br
- wbr nobr blink
- font basefont bdo
- spacer embed noembed
-); # had: center, hr, table
-
-
=head2 hashset %HTML::Tagset::is_Possible_Strict_P_Content
This hashset contains all phrasal-level elements that be content of a
@@ -183,15 +165,6 @@ P element, for a strict model of HTML.
=cut
-our %isFormElement; # Forward declaration
-our %is_Possible_Strict_P_Content = (
- %isPhraseMarkup,
- %isFormElement,
- map {; $_ => 1} qw( object script map )
- # I've no idea why there's these latter exceptions.
- # I'm just following the HTML4.01 DTD.
-);
-
#from html4 strict:
#
#
@@ -213,19 +186,12 @@ present only in the 'head' element of an HTML document.
=cut
-our %isHeadElement = map { $_ => 1 }
- qw(title base link meta isindex script style object bgsound);
-
=head2 hashset %HTML::Tagset::isList
This hashset contains all elements that can contain "li" elements.
=cut
-our %isList = map { $_ => 1 } qw(
- ul ol dir menu
-);
-
=head2 hashset %HTML::Tagset::isTableElement
This hashset contains all elements that are to be found only in/under
@@ -233,9 +199,6 @@ a "table" element.
=cut
-our %isTableElement = map { $_ => 1 }
- qw(tr td th thead tbody tfoot caption col colgroup);
-
=head2 hashset %HTML::Tagset::isFormElement
This hashset contains all elements that are to be found only in/under
@@ -243,10 +206,6 @@ a "form" element.
=cut
-# Declared earlier in the file
-%isFormElement = map { $_ => 1 }
- qw(input select option optgroup textarea button label);
-
=head2 hashset %HTML::Tagset::isBodyElement
This hashset contains all elements that are to be found only in/under
@@ -254,35 +213,6 @@ the "body" element of an HTML document.
=cut
-our %isBodyElement = map { $_ => 1 } qw(
- h1 h2 h3 h4 h5 h6
- p div pre plaintext address blockquote
- xmp listing
- center
-
- multicol
- iframe ilayer nolayer
- bgsound
-
- hr
- ol ul dir menu li
- dl dt dd
- ins del
-
- fieldset legend
-
- map area
- applet param object
- isindex script noscript
- table
- center
- form
- ),
- keys %isFormElement,
- keys %isPhraseMarkup, # And everything phrasal
- keys %isTableElement,
-;
-
=head2 hashset %HTML::Tagset::isHeadOrBodyElement
@@ -291,26 +221,12 @@ the head or in the body.
=cut
-our %isHeadOrBodyElement = map { $_ => 1 }
- qw(script isindex style object map area param noscript bgsound);
- # i.e., if we find 'script' in the 'body' or the 'head', don't freak out.
-
-
=head2 hashset %HTML::Tagset::isKnown
This hashset lists all known HTML elements.
=cut
-our %isKnown = (%isHeadElement, %isBodyElement,
- map{ $_ => 1 }
- qw( head body html
- frame frameset noframes
- ~comment ~pi ~directive ~literal
-));
- # that should be all known tags ever ever
-
-
=head2 hashset %HTML::Tagset::canTighten
This hashset lists elements that might have ignorable whitespace as
@@ -318,20 +234,6 @@ children or siblings.
=cut
-our %canTighten = %isKnown;
-delete @canTighten{
- keys(%isPhraseMarkup), 'input', 'select',
- 'xmp', 'listing', 'plaintext', 'pre',
-};
- # xmp, listing, plaintext, and pre are untightenable, and
- # in a really special way.
-@canTighten{'hr','br'} = (1,1);
- # exceptional 'phrasal' things that ARE subject to tightening.
-
-# The one case where I can think of my tightening rules failing is:
-# foo bar
baz quux ...
-# ^-- that would get deleted.
-# But that's pretty gruesome code anyhow. You gets what you pays for.
#==========================================================================
@@ -378,14 +280,6 @@ barrier-tags.
=cut
-our @p_closure_barriers = qw(
- li blockquote
- ul ol menu dir
- dl dt dd
- td th tr table caption
- div
- );
-
# In an ideal world (i.e., XHTML) we wouldn't have to bother with any of this
# monkey business of barriers to minimization!
@@ -395,11 +289,6 @@ This hashset includes all elements whose content is CDATA.
=cut
-our %isCDATA_Parent = map { $_ => 1 }
- qw(script style xmp listing plaintext);
-
-# TODO: there's nothing else that takes CDATA children, right?
-
# As the HTML3 DTD (Raggett 1995-04-24) noted:
# The XMP, LISTING and PLAINTEXT tags are incompatible with SGML
# and derive from very early versions of HTML. They require non-
diff --git a/lib/HTML/Tagset/v4.pm b/lib/HTML/Tagset/v4.pm
new file mode 100644
index 0000000..c075243
--- /dev/null
+++ b/lib/HTML/Tagset/v4.pm
@@ -0,0 +1,472 @@
+package HTML::Tagset::v4;
+
+use strict;
+
+=head1 NAME
+
+HTML::Tagset::v4 - data tables useful in parsing HTML 4.x
+
+=head1 VERSION
+
+Version 3.20
+
+=cut
+
+use vars qw( $VERSION );
+
+$VERSION = '3.20';
+
+=head1 SYNOPSIS
+
+ use HTML::Tagset;
+ # Then use any of the items in the HTML::Tagset package
+ # as need arises
+
+=head1 DESCRIPTION
+
+This module contains several data tables useful in various kinds of
+HTML parsing operations.
+
+Note that all tag names used are lowercase.
+
+In the following documentation, a "hashset" is a hash being used as a
+set -- the hash conveys that its keys are there, and the actual values
+associated with the keys are not significant. (But what values are
+there, are always true.)
+
+=cut
+
+use vars qw(
+ $VERSION
+ %emptyElement %optionalEndTag %linkElements %boolean_attr
+ %isHeadElement %isBodyElement %isPhraseMarkup
+ %is_Possible_Strict_P_Content
+ %isHeadOrBodyElement
+ %isList %isTableElement %isFormElement
+ %isKnown %canTighten
+ @p_closure_barriers
+ %isCDATA_Parent
+);
+
+=head1 VARIABLES
+
+Note that none of these variables are exported.
+
+=head2 hashset %HTML::Tagset::emptyElement
+
+This hashset has as values the tag-names (GIs) of elements that cannot
+have content. (For example, "base", "br", "hr".) So
+C<$HTML::Tagset::emptyElement{'hr'}> exists and is true.
+C<$HTML::Tagset::emptyElement{'dl'}> does not exist, and so is not true.
+
+=cut
+
+%emptyElement = map {; $_ => 1 } qw(base link meta isindex
+ img br hr wbr
+ input area param
+ embed bgsound spacer
+ basefont col frame
+ ~comment ~literal
+ ~declaration ~pi
+ );
+# The "~"-initial names are for pseudo-elements used by HTML::Entities
+# and TreeBuilder
+
+=head2 hashset %HTML::Tagset::optionalEndTag
+
+This hashset lists tag-names for elements that can have content, but whose
+end-tags are generally, "safely", omissible. Example:
+C<$HTML::Tagset::emptyElement{'li'}> exists and is true.
+
+=cut
+
+%optionalEndTag = map {; $_ => 1 } qw(p li dt dd); # option th tr td);
+
+=head2 hash %HTML::Tagset::linkElements
+
+Values in this hash are tagnames for elements that might contain
+links, and the value for each is a reference to an array of the names
+of attributes whose values can be links.
+
+=cut
+
+%linkElements =
+(
+ 'a' => ['href'],
+ 'applet' => ['archive', 'codebase', 'code'],
+ 'area' => ['href'],
+ 'base' => ['href'],
+ 'bgsound' => ['src'],
+ 'blockquote' => ['cite'],
+ 'body' => ['background'],
+ 'del' => ['cite'],
+ 'embed' => ['pluginspage', 'src'],
+ 'form' => ['action'],
+ 'frame' => ['src', 'longdesc'],
+ 'iframe' => ['src', 'longdesc'],
+ 'ilayer' => ['background'],
+ 'img' => ['src', 'lowsrc', 'longdesc', 'usemap'],
+ 'input' => ['src', 'usemap'],
+ 'ins' => ['cite'],
+ 'isindex' => ['action'],
+ 'head' => ['profile'],
+ 'layer' => ['background', 'src'],
+ 'link' => ['href'],
+ 'object' => ['classid', 'codebase', 'data', 'archive', 'usemap'],
+ 'q' => ['cite'],
+ 'script' => ['src', 'for'],
+ 'table' => ['background'],
+ 'td' => ['background'],
+ 'th' => ['background'],
+ 'tr' => ['background'],
+ 'xmp' => ['href'],
+);
+
+=head2 hash %HTML::Tagset::boolean_attr
+
+This hash (not hashset) lists what attributes of what elements can be
+printed without showing the value (for example, the "noshade" attribute
+of "hr" elements). For elements with only one such attribute, its value
+is simply that attribute name. For elements with many such attributes,
+the value is a reference to a hashset containing all such attributes.
+
+=cut
+
+%boolean_attr = (
+# TODO: make these all hashes
+ 'area' => 'nohref',
+ 'dir' => 'compact',
+ 'dl' => 'compact',
+ 'hr' => 'noshade',
+ 'img' => 'ismap',
+ 'input' => { 'checked' => 1, 'readonly' => 1, 'disabled' => 1 },
+ 'menu' => 'compact',
+ 'ol' => 'compact',
+ 'option' => 'selected',
+ 'select' => 'multiple',
+ 'td' => 'nowrap',
+ 'th' => 'nowrap',
+ 'ul' => 'compact',
+);
+
+#==========================================================================
+# List of all elements from Extensible HTML version 1.0 Transitional DTD:
+#
+# a abbr acronym address applet area b base basefont bdo big
+# blockquote body br button caption center cite code col colgroup
+# dd del dfn dir div dl dt em fieldset font form h1 h2 h3 h4 h5 h6
+# head hr html i iframe img input ins isindex kbd label legend li
+# link map menu meta noframes noscript object ol optgroup option p
+# param pre q s samp script select small span strike strong style
+# sub sup table tbody td textarea tfoot th thead title tr tt u ul
+# var
+#
+# Varia from Mozilla source internal table of tags:
+# Implemented:
+# xmp listing wbr nobr frame frameset noframes ilayer
+# layer nolayer spacer embed multicol
+# But these are unimplemented:
+# sound?? keygen?? server??
+# Also seen here and there:
+# marquee?? app?? (both unimplemented)
+#==========================================================================
+
+=head2 hashset %HTML::Tagset::isPhraseMarkup
+
+This hashset contains all phrasal-level elements.
+
+=cut
+
+%isPhraseMarkup = map {; $_ => 1 } qw(
+ span abbr acronym q sub sup
+ cite code em kbd samp strong var dfn strike
+ b i u s tt small big
+ ins del
+ a img br
+ wbr nobr blink
+ font basefont bdo
+ spacer embed noembed
+); # had: center, hr, table
+
+
+=head2 hashset %HTML::Tagset::is_Possible_Strict_P_Content
+
+This hashset contains all phrasal-level elements that be content of a
+P element, for a strict model of HTML.
+
+=cut
+
+%is_Possible_Strict_P_Content = (
+ %isPhraseMarkup,
+ %isFormElement,
+ map {; $_ => 1} qw( object script map )
+ # I've no idea why there's these latter exceptions.
+ # I'm just following the HTML4.01 DTD.
+);
+
+#from html4 strict:
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+
+=head2 hashset %HTML::Tagset::isHeadElement
+
+This hashset contains all elements that elements that should be
+present only in the 'head' element of an HTML document.
+
+=cut
+
+%isHeadElement = map {; $_ => 1 }
+ qw(title base link meta isindex script style object bgsound);
+
+=head2 hashset %HTML::Tagset::isList
+
+This hashset contains all elements that can contain "li" elements.
+
+=cut
+
+%isList = map {; $_ => 1 } qw(ul ol dir menu);
+
+=head2 hashset %HTML::Tagset::isTableElement
+
+This hashset contains all elements that are to be found only in/under
+a "table" element.
+
+=cut
+
+%isTableElement = map {; $_ => 1 }
+ qw(tr td th thead tbody tfoot caption col colgroup);
+
+=head2 hashset %HTML::Tagset::isFormElement
+
+This hashset contains all elements that are to be found only in/under
+a "form" element.
+
+=cut
+
+%isFormElement = map {; $_ => 1 }
+ qw(input select option optgroup textarea button label);
+
+=head2 hashset %HTML::Tagset::isBodyMarkup
+
+This hashset contains all elements that are to be found only in/under
+the "body" element of an HTML document.
+
+=cut
+
+%isBodyElement = map {; $_ => 1 } qw(
+ h1 h2 h3 h4 h5 h6
+ p div pre plaintext address blockquote
+ xmp listing
+ center
+
+ multicol
+ iframe ilayer nolayer
+ bgsound
+
+ hr
+ ol ul dir menu li
+ dl dt dd
+ ins del
+
+ fieldset legend
+
+ map area
+ applet param object
+ isindex script noscript
+ table
+ center
+ form
+ ),
+ keys %isFormElement,
+ keys %isPhraseMarkup, # And everything phrasal
+ keys %isTableElement,
+;
+
+
+=head2 hashset %HTML::Tagset::isHeadOrBodyElement
+
+This hashset includes all elements that I notice can fall either in
+the head or in the body.
+
+=cut
+
+%isHeadOrBodyElement = map {; $_ => 1 }
+ qw(script isindex style object map area param noscript bgsound);
+ # i.e., if we find 'script' in the 'body' or the 'head', don't freak out.
+
+
+=head2 hashset %HTML::Tagset::isKnown
+
+This hashset lists all known HTML elements.
+
+=cut
+
+%isKnown = (%isHeadElement, %isBodyElement,
+ map{; $_=>1 }
+ qw( head body html
+ frame frameset noframes
+ ~comment ~pi ~directive ~literal
+));
+ # that should be all known tags ever ever
+
+
+=head2 hashset %HTML::Tagset::canTighten
+
+This hashset lists elements that might have ignorable whitespace as
+children or siblings.
+
+=cut
+
+%canTighten = %isKnown;
+delete @canTighten{
+ keys(%isPhraseMarkup), 'input', 'select',
+ 'xmp', 'listing', 'plaintext', 'pre',
+};
+ # xmp, listing, plaintext, and pre are untightenable, and
+ # in a really special way.
+@canTighten{'hr','br'} = (1,1);
+ # exceptional 'phrasal' things that ARE subject to tightening.
+
+# The one case where I can think of my tightening rules failing is:
+# foo bar
baz quux ...
+# ^-- that would get deleted.
+# But that's pretty gruesome code anyhow. You gets what you pays for.
+
+#==========================================================================
+
+=head2 array @HTML::Tagset::p_closure_barriers
+
+This array has a meaning that I have only seen a need for in
+C, but I include it here on the off chance that someone
+might find it of use:
+
+When we see a "EpE" token, we go lookup up the lineage for a p
+element we might have to minimize. At first sight, we might say that
+if there's a p anywhere in the lineage of this new p, it should be
+closed. But that's wrong. Consider this document:
+
+
+
+ foo
+
+
+ foo
+
+
+
+
+
+The second p is quite legally inside a much higher p.
+
+My formalization of the reason why this is legal, but this:
+
+ foo
bar
+
+isn't, is that something about the table constitutes a "barrier" to
+the application of the rule about what p must minimize.
+
+So C<@HTML::Tagset::p_closure_barriers> is the list of all such
+barrier-tags.
+
+=cut
+
+@p_closure_barriers = qw(
+ li blockquote
+ ul ol menu dir
+ dl dt dd
+ td th tr table caption
+ div
+ );
+
+# In an ideal world (i.e., XHTML) we wouldn't have to bother with any of this
+# monkey business of barriers to minimization!
+
+=head2 hashset %isCDATA_Parent
+
+This hashset includes all elements whose content is CDATA.
+
+=cut
+
+%isCDATA_Parent = map {; $_ => 1 }
+ qw(script style xmp listing plaintext);
+
+# TODO: there's nothing else that takes CDATA children, right?
+
+# As the HTML3 DTD (Raggett 1995-04-24) noted:
+# The XMP, LISTING and PLAINTEXT tags are incompatible with SGML
+# and derive from very early versions of HTML. They require non-
+# standard parsers and will cause problems for processing
+# documents with standard SGML tools.
+
+
+=head1 CAVEATS
+
+You may find it useful to alter the behavior of modules (like
+C or C) that use C's
+data tables by altering the data tables themselves. You are welcome
+to try, but be careful; and be aware that different modules may or may
+react differently to the data tables being changed.
+
+Note that it may be inappropriate to use these tables for I
+HTML -- for example, C<%isHeadOrBodyElement> lists the tagnames
+for all elements that can appear either in the head or in the body,
+such as "script". That doesn't mean that I am saying your code that
+produces HTML should feel free to put script elements in either place!
+If you are producing programs that spit out HTML, you should be
+I familiar with the DTDs for HTML or XHTML (available at
+C), and you should slavishly obey them, not
+the data tables in this document.
+
+=head1 SEE ALSO
+
+L, L, L
+
+=head1 COPYRIGHT & LICENSE
+
+Copyright 1995-2000 Gisle Aas.
+
+Copyright 2000-2005 Sean M. Burke.
+
+Copyright 2005-2008 Andy Lester.
+
+This program is free software; you can redistribute it and/or modify it
+under the same terms as Perl itself.
+
+=head1 ACKNOWLEDGEMENTS
+
+Most of the code/data in this module was adapted from code written
+by Gisle Aas for C, C, and
+C. Then it was maintained by Sean M. Burke.
+
+=head1 AUTHOR
+
+Current maintainer: Andy Lester, C<< >>
+
+=head1 BUGS
+
+Please report any bugs or feature requests to
+C, or through the web interface at
+L. I will
+be notified, and then you'll automatically be notified of progress on
+your bug as I make changes.
+
+=cut
+
+1;
diff --git a/lib/HTML/Tagset/v5.pm b/lib/HTML/Tagset/v5.pm
new file mode 100644
index 0000000..ad2abb6
--- /dev/null
+++ b/lib/HTML/Tagset/v5.pm
@@ -0,0 +1,486 @@
+package HTML::Tagset::v5;
+
+use strict;
+
+=head1 NAME
+
+HTML::Tagset::v5 - data tables useful in parsing HTML 5.x
+
+=head1 VERSION
+
+Version 3.20
+
+=cut
+
+use vars qw( $VERSION );
+
+$VERSION = '3.20';
+
+=head1 SYNOPSIS
+
+ $HTML::Tagset::HTML_VERSION='v5';
+ use HTML::Tagset;
+ # Then use any of the items in the HTML::Tagset package
+ # as need arises
+
+=head1 DESCRIPTION
+
+This module contains several data tables useful in various kinds of
+HTML parsing operations.
+
+Note that all tag names used are lowercase.
+
+In the following documentation, a "hashset" is a hash being used as a
+set -- the hash conveys that its keys are there, and the actual values
+associated with the keys are not significant. (But what values are
+there, are always true.)
+
+=cut
+
+use vars qw(
+ $VERSION
+ %emptyElement %optionalEndTag %linkElements %boolean_attr
+ %isHeadElement %isBodyElement %isPhraseMarkup
+ %is_Possible_Strict_P_Content
+ %isHeadOrBodyElement
+ %isList %isTableElement %isFormElement
+ %isKnown %canTighten
+ @p_closure_barriers
+ %isCDATA_Parent
+);
+
+=head1 VARIABLES
+
+Note that none of these variables are exported.
+
+=head2 hashset %HTML::Tagset::emptyElement
+
+This hashset has as values the tag-names (GIs) of elements that cannot
+have content. (For example, "base", "br", "hr".) So
+C<$HTML::Tagset::emptyElement{'hr'}> exists and is true.
+C<$HTML::Tagset::emptyElement{'dl'}> does not exist, and so is not true.
+
+=cut
+
+%emptyElement = map {; $_ => 1 } qw(area base br col embed
+ hr iframe img input link
+ meta param source template
+ track wbr
+ ~comment ~literal
+ ~declaration ~pi
+ );
+# The "~"-initial names are for pseudo-elements used by HTML::Entities
+# and TreeBuilder
+
+=head2 hashset %HTML::Tagset::optionalEndTag
+
+This hashset lists tag-names for elements that can have content, but whose
+end-tags are generally, "safely", omissible. Example:
+C<$HTML::Tagset::emptyElement{'li'}> exists and is true.
+
+=cut
+
+%optionalEndTag = map {; $_ => 1 } qw(p li dt dd);
+#v4
+# option th tr td);
+
+=head2 hash %HTML::Tagset::linkElements
+
+Values in this hash are tagnames for elements that might contain
+links, and the value for each is a reference to an array of the names
+of attributes whose values can be links.
+
+=cut
+
+%linkElements =
+(
+ 'a' => ['href'],
+ 'area' => ['href'],
+ 'base' => ['href'],
+ 'blockquote' => ['cite'],
+ 'del' => ['cite'],
+ 'embed' => ['src'],
+ 'form' => ['action'],
+ 'iframe' => ['src'],
+ 'img' => ['src', 'usemap'],
+ 'input' => ['src'],
+ 'ins' => ['cite'],
+ 'link' => ['href'],
+ 'object' => ['data', 'usemap'],
+ 'q' => ['cite'],
+ 'script' => ['src'],
+);
+
+# v4
+# applet bgsound body embed=pluginspage frame iframe=longdesc ilayer img=lowsrc,longdesc input=usemap isindex head layer object=classid,codebase,archive script=for table td th tr xmp
+
+=head2 hash %HTML::Tagset::boolean_attr
+
+This hash (not hashset) lists what attributes of what elements can be
+printed without showing the value (for example, the "noshade" attribute
+of "hr" elements). For elements with only one such attribute, its value
+is simply that attribute name. For elements with many such attributes,
+the value is a reference to a hashset containing all such attributes.
+
+=cut
+
+# 'hidden', 'itemscope', apply to all elements!
+%boolean_attr = (
+ 'area' => { 'nohref' => 1 },
+ 'audio' => { 'controls' => 1, 'loop' => 1, 'muted' => 1, },
+ 'button' => { 'disabled' => 1, 'formnovalidate' => 1 },
+ 'details' => { 'open' => 1, },
+ 'dialog' => { 'open' => 1, },
+ 'fieldset' => { 'disabled' => 1 },
+ 'form' => { 'novalidate' => 1, },
+ 'img' => { 'ismap' => 1 },
+ 'iframe' => { 'allowfullscreen' => 1, 'allowpaymentrequest' => 1 },
+ 'input' => { 'checked' => 1, 'readonly' => 1, 'disabled' => 1, 'required' => 1, 'multiple' => 1, 'formnovalidate' => 1, 'hidden' => 1, },
+ 'ol' => { 'reversed' => 1 },
+ 'optgroup' => { 'disabled' => 1 },
+ 'option' => { 'disabled' => 1, 'selected' => 1 },
+ 'script' => { 'async' => 1, 'defer' => 1, 'nomodule' => 1, },
+ 'select' => { 'multiple' => 1, 'disabled' => 1, 'readonly' => 1, },
+ 'textarea' => { 'disabled' => 1, 'readonly' => 1, 'required' => 1, },
+ 'track' => { 'default' => 1 },
+ 'video' => { 'controls' => 1, 'loop' => 1, 'muted' => 1, 'playsinline' => 1, },
+ ( map {; { 'hidden' => 1 } } (keys %isKnown) ),
+ ( map {; { 'itemscope' => 1 } } (keys %isKnown) ),
+);
+
+#v4
+# dir hr td th
+
+#==========================================================================
+# List of all elements from Extensible HTML version 1.0 Transitional DTD:
+#
+# a abbr acronym address applet area b base basefont bdo big
+# blockquote body br button caption center cite code col colgroup
+# dd del dfn dir div dl dt em fieldset font form h1 h2 h3 h4 h5 h6
+# head hr html i iframe img input ins isindex kbd label legend li
+# link map menu meta noframes noscript object ol optgroup option p
+# param pre q s samp script select small span strike strong style
+# sub sup table tbody td textarea tfoot th thead title tr tt u ul
+# var
+#
+# Varia from Mozilla source internal table of tags:
+# Implemented:
+# xmp listing wbr nobr frame frameset noframes ilayer
+# layer nolayer spacer embed multicol
+# But these are unimplemented:
+# sound?? keygen?? server??
+# Also seen here and there:
+# marquee?? app?? (both unimplemented)
+#==========================================================================
+
+=head2 hashset %HTML::Tagset::isPhraseMarkup
+
+This hashset contains all phrasal-level elements.
+
+=cut
+
+# https://html.spec.whatwg.org/multipage/dom.html#phrasing-content-2
+%isPhraseMarkup = map {; $_ => 1 } qw(
+ a abbr audio b bdi bdo br button canvas cite code data datalist del dfn em embed i iframe img input ins kbd label map mark math meter noscript object output picture progress q ruby s samp script select slot small span strong sub sup svg template textarea time u var video wbr
+ area link meta
+); # had: center, hr, table
+# v4
+# acronym
+# strike
+# tt big
+# nobr blink
+# font basefont
+# spacer noembed
+
+=head2 hashset %HTML::Tagset::is_Possible_Strict_P_Content
+
+This hashset contains all phrasal-level elements that may be content of a
+P element, for a strict model of HTML.
+
+=cut
+
+%is_Possible_Strict_P_Content = (
+ %isPhraseMarkup,
+ %isFormElement,
+ map {; $_ => 1} qw( object script map )
+ # I've no idea why there's these latter exceptions.
+ # I'm just following the HTML4.01 DTD.
+);
+
+#from html4 strict:
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+
+=head2 hashset %HTML::Tagset::isHeadElement
+
+This hashset contains all elements that elements that should be
+present only in the 'head' element of an HTML document.
+
+=cut
+
+%isHeadElement = map {; $_ => 1 }
+qw(base title);
+#v4
+# isindex object(allowed in body) bgsound link(allowed in body) meta(ditto)
+
+=head2 hashset %HTML::Tagset::isList
+
+This hashset contains all elements that can contain "li" elements.
+
+=cut
+
+%isList = map {; $_ => 1 } qw(ul ol menu);
+#v4
+# dir
+
+=head2 hashset %HTML::Tagset::isTableElement
+
+This hashset contains all elements that are to be found only in/under
+a "table" element.
+
+=cut
+
+%isTableElement = map {; $_ => 1 }
+ qw(caption colgroup col thead tbody tfoot tr td th);
+
+=head2 hashset %HTML::Tagset::isFormElement
+
+This hashset contains all elements that are to be found only in/under
+a "form" element.
+
+=cut
+
+%isFormElement = map {; $_ => 1 }
+qw(input optgroup select textarea label);
+
+# v4
+# button
+
+=head2 hashset %HTML::Tagset::isBodyMarkup
+
+This hashset contains all elements that are to be found only in/under
+the "body" element of an HTML document.
+
+=cut
+
+%isBodyElement = map {; $_ => 1 } qw(
+ h1 h2 h3 h4 h5 h6 hgroup
+ p div pre address blockquote
+
+ iframe
+
+ hr
+ ol ul menu li
+ dl dt dd
+ ins del
+
+ fieldset legend
+
+ map area
+ param object
+ script noscript
+ table
+ form
+ option dl
+
+ article aside details summary dialog footer header main nav section
+ source track
+ figure figcaption
+ rp rt
+ ),
+ keys %isFormElement,
+ keys %isPhraseMarkup, # And everything phrasal
+ keys %isTableElement,
+;
+
+# v4
+# xmp listing plaintext center multicol ilayer nolayer bgsound dir applet isindex
+
+=head2 hashset %HTML::Tagset::isHeadOrBodyElement
+
+This hashset includes all elements that I notice can fall either in
+the head or in the body.
+
+=cut
+
+%isHeadOrBodyElement = map {; $_ => 1 }
+ qw(script style object map area param noscript template link meta);
+ # i.e., if we find 'script' in the 'body' or the 'head', don't freak out.
+
+# isindex bgsound
+
+=head2 hashset %HTML::Tagset::isKnown
+
+This hashset lists all known HTML elements.
+
+=cut
+
+%isKnown = (%isHeadElement, %isBodyElement, %isHeadOrBodyElement,
+ map{; $_=>1 }
+ qw( head body html
+ ~comment ~pi ~directive ~literal
+));
+ # that should be all known tags ever ever
+# v4
+# frame frameset noframes
+
+=head2 hashset %HTML::Tagset::canTighten
+
+This hashset lists elements that might have ignorable whitespace as
+children or siblings.
+
+=cut
+
+%canTighten = %isKnown;
+delete @canTighten{
+ keys(%isPhraseMarkup), 'input', 'select',
+ 'xmp', 'listing', 'plaintext', 'pre',
+};
+ # xmp, listing, plaintext, and pre are untightenable, and
+ # in a really special way.
+@canTighten{'hr','br'} = (1,1);
+ # exceptional 'phrasal' things that ARE subject to tightening.
+
+# The one case where I can think of my tightening rules failing is:
+# foo bar
baz quux ...
+# ^-- that would get deleted.
+# But that's pretty gruesome code anyhow. You gets what you pays for.
+
+#==========================================================================
+
+=head2 array @HTML::Tagset::p_closure_barriers
+
+This array has a meaning that I have only seen a need for in
+C, but I include it here on the off chance that someone
+might find it of use:
+
+When we see a "EpE" token, we go lookup up the lineage for a p
+element we might have to minimize. At first sight, we might say that
+if there's a p anywhere in the lineage of this new p, it should be
+closed. But that's wrong. Consider this document:
+
+
+
+ foo
+
+
+ foo
+
+
+
+
+
+The second p is quite legally inside a much higher p.
+
+My formalization of the reason why this is legal, but this:
+
+ foo
bar
+
+isn't, is that something about the table constitutes a "barrier" to
+the application of the rule about what p must minimize.
+
+So C<@HTML::Tagset::p_closure_barriers> is the list of all such
+barrier-tags.
+
+=cut
+
+@p_closure_barriers = qw(
+ li blockquote
+ ul ol menu dir
+ dl dt dd
+ td th tr table caption
+ div
+ );
+
+# In an ideal world (i.e., XHTML) we wouldn't have to bother with any of this
+# monkey business of barriers to minimization!
+
+=head2 hashset %isCDATA_Parent
+
+This hashset includes all elements whose content is CDATA.
+
+=cut
+
+%isCDATA_Parent = map {; $_ => 1 }
+ qw(script style xmp listing plaintext);
+
+# TODO: there's nothing else that takes CDATA children, right?
+
+# As the HTML3 DTD (Raggett 1995-04-24) noted:
+# The XMP, LISTING and PLAINTEXT tags are incompatible with SGML
+# and derive from very early versions of HTML. They require non-
+# standard parsers and will cause problems for processing
+# documents with standard SGML tools.
+
+
+=head1 CAVEATS
+
+You may find it useful to alter the behavior of modules (like
+C or C) that use C's
+data tables by altering the data tables themselves. You are welcome
+to try, but be careful; and be aware that different modules may or may
+react differently to the data tables being changed.
+
+Note that it may be inappropriate to use these tables for I
+HTML -- for example, C<%isHeadOrBodyElement> lists the tagnames
+for all elements that can appear either in the head or in the body,
+such as "script". That doesn't mean that I am saying your code that
+produces HTML should feel free to put script elements in either place!
+If you are producing programs that spit out HTML, you should be
+I familiar with the DTDs for HTML or XHTML (available at
+C), and you should slavishly obey them, not
+the data tables in this document.
+
+=head1 SEE ALSO
+
+L, L, L
+
+=head1 COPYRIGHT & LICENSE
+
+Copyright 1995-2000 Gisle Aas.
+
+Copyright 2000-2005 Sean M. Burke.
+
+Copyright 2005-2008 Andy Lester.
+
+This program is free software; you can redistribute it and/or modify it
+under the same terms as Perl itself.
+
+=head1 ACKNOWLEDGEMENTS
+
+Most of the code/data in this module was adapted from code written
+by Gisle Aas for C, C, and
+C. Then it was maintained by Sean M. Burke.
+
+=head1 AUTHOR
+
+Current maintainer: Andy Lester, C<< >>
+
+=head1 BUGS
+
+Please report any bugs or feature requests to
+C, or through the web interface at
+L. I will
+be notified, and then you'll automatically be notified of progress on
+your bug as I make changes.
+
+=cut
+
+1;
diff --git a/t/02_versions.t b/t/02_versions.t
new file mode 100644
index 0000000..7c65bc2
--- /dev/null
+++ b/t/02_versions.t
@@ -0,0 +1,17 @@
+use strict;
+use warnings;
+
+use Test::More;
+
+BEGIN {
+ $HTML::Tagset::HTML_VERSION='v5';
+};
+
+use HTML::Tagset;
+use Data::Dumper;
+
+# diag(Dumper(\%HTML::Tagset::emptyElement));
+
+ok($HTML::Tagset::emptyElement{source}, 'Loaded v5');
+
+done_testing;
\ No newline at end of file
From 921bb5b86a882439f506e1cc6eb2c2d5b5e51dd4 Mon Sep 17 00:00:00 2001
From: Jess Robinson
Date: Mon, 18 Nov 2019 10:54:36 +0000
Subject: [PATCH 2/6] Add docs, update version, changelog, hide v4/v5 packages
from pause
---
Changes | 2 ++
lib/HTML/Tagset.pm | 30 ++++++++++++++++++++++++++++--
lib/HTML/Tagset/v4.pm | 7 ++++---
lib/HTML/Tagset/v5.pm | 7 ++++---
4 files changed, 38 insertions(+), 8 deletions(-)
diff --git a/Changes b/Changes
index 7a76384..83a586e 100644
--- a/Changes
+++ b/Changes
@@ -1,5 +1,7 @@
Revision history for Perl extension HTML::Tagset
+ * Release 5.0.0 -- Added HTML5 support (configurable, defaults to HTML4)
+
2024-03-11 Andy Lester
* Release 3.24
diff --git a/lib/HTML/Tagset.pm b/lib/HTML/Tagset.pm
index 76ca3a6..8f506b2 100644
--- a/lib/HTML/Tagset.pm
+++ b/lib/HTML/Tagset.pm
@@ -11,18 +11,30 @@ HTML::Tagset - data tables useful in parsing HTML
=head1 VERSION
-Version 3.24
+Version 5.0.0
=cut
-our $VERSION = '3.24';
+use vars qw( $VERSION );
+
+$VERSION = '5.0.0';
=head1 SYNOPSIS
+ # Load HTML tags pre HTML5:
use HTML::Tagset;
# Then use any of the items in the HTML::Tagset package
# as need arises
+ # Load HTML 5 tags:
+ BEGIN {
+ $HTML::Tagset::HTML_VERSION='v5';
+ };
+ use HTML::Tagset;
+ # Then use as above
+ # This will also work if used before any higher-level
+ # HTML::Tagset-using modules, eg HTML::TreeBuilder;
+
=head1 DESCRIPTION
This module contains several data tables useful in various kinds of
@@ -56,6 +68,20 @@ Note that none of these variables are exported.
=head2 HTML_VERSION
+Used to determine whether to load tags for parsing HTML5
+L or HTML 4 or below
+L. This needs to be set before
+HTML::Tagset is loaded, using BEGIN. Set it to B to get HTML5
+tags, leave empty or set to anything else for HTML4 and below.
+
+NB: This can also be used before HTML::Tagset-using modules, eg
+L.
+
+ BEGIN {
+ $HTML::Tagset::HTML_VERSION='v5';
+ };
+ use HTML::Tagset;
+
=cut
=head2 hashset %HTML::Tagset::emptyElement
diff --git a/lib/HTML/Tagset/v4.pm b/lib/HTML/Tagset/v4.pm
index c075243..5825d41 100644
--- a/lib/HTML/Tagset/v4.pm
+++ b/lib/HTML/Tagset/v4.pm
@@ -1,4 +1,5 @@
-package HTML::Tagset::v4;
+package # Hide package from pause
+ HTML::Tagset::v4;
use strict;
@@ -8,13 +9,13 @@ HTML::Tagset::v4 - data tables useful in parsing HTML 4.x
=head1 VERSION
-Version 3.20
+Version 5.0.0
=cut
use vars qw( $VERSION );
-$VERSION = '3.20';
+$VERSION = '5.0.0';
=head1 SYNOPSIS
diff --git a/lib/HTML/Tagset/v5.pm b/lib/HTML/Tagset/v5.pm
index ad2abb6..77ddd8f 100644
--- a/lib/HTML/Tagset/v5.pm
+++ b/lib/HTML/Tagset/v5.pm
@@ -1,4 +1,5 @@
-package HTML::Tagset::v5;
+package # Hide package from pause
+ HTML::Tagset::v5;
use strict;
@@ -8,13 +9,13 @@ HTML::Tagset::v5 - data tables useful in parsing HTML 5.x
=head1 VERSION
-Version 3.20
+Version 5.0.0
=cut
use vars qw( $VERSION );
-$VERSION = '3.20';
+$VERSION = '5.0.0';
=head1 SYNOPSIS
From b9eb009b1fe72902a7d26256aca3dba064290aa1 Mon Sep 17 00:00:00 2001
From: Andy Lester
Date: Tue, 19 Nov 2019 09:22:40 -0600
Subject: [PATCH 3/6] No need to hide the packages
---
lib/HTML/Tagset/v4.pm | 3 +--
lib/HTML/Tagset/v5.pm | 3 +--
2 files changed, 2 insertions(+), 4 deletions(-)
diff --git a/lib/HTML/Tagset/v4.pm b/lib/HTML/Tagset/v4.pm
index 5825d41..6b4367c 100644
--- a/lib/HTML/Tagset/v4.pm
+++ b/lib/HTML/Tagset/v4.pm
@@ -1,5 +1,4 @@
-package # Hide package from pause
- HTML::Tagset::v4;
+package HTML::Tagset::v4;
use strict;
diff --git a/lib/HTML/Tagset/v5.pm b/lib/HTML/Tagset/v5.pm
index 77ddd8f..03c6287 100644
--- a/lib/HTML/Tagset/v5.pm
+++ b/lib/HTML/Tagset/v5.pm
@@ -1,5 +1,4 @@
-package # Hide package from pause
- HTML::Tagset::v5;
+package HTML::Tagset::v5;
use strict;
From f24b04849bc4fbb38b1e414c2bc94a2d158842e9 Mon Sep 17 00:00:00 2001
From: Jess Robinson
Date: Tue, 19 Nov 2019 16:15:59 +0000
Subject: [PATCH 4/6] Default for new version is now HTML5 tags Updated doc and
added warning message
---
lib/HTML/Tagset.pm | 22 ++++++++++++++--------
1 file changed, 14 insertions(+), 8 deletions(-)
diff --git a/lib/HTML/Tagset.pm b/lib/HTML/Tagset.pm
index 8f506b2..960efe0 100644
--- a/lib/HTML/Tagset.pm
+++ b/lib/HTML/Tagset.pm
@@ -21,14 +21,14 @@ $VERSION = '5.0.0';
=head1 SYNOPSIS
- # Load HTML tags pre HTML5:
+ # Load HTML5 tags
use HTML::Tagset;
# Then use any of the items in the HTML::Tagset package
# as need arises
- # Load HTML 5 tags:
+ # Load HTML3/4 tags:
BEGIN {
- $HTML::Tagset::HTML_VERSION='v5';
+ $HTML::Tagset::HTML_VERSION='v4';
};
use HTML::Tagset;
# Then use as above
@@ -37,6 +37,10 @@ $VERSION = '5.0.0';
=head1 DESCRIPTION
+BREAKING CHANGE: From version 5.0, this module will default to loading
+HTML5 tags (previously HTML4 and below), see docs on how to get the
+previous behaviour.
+
This module contains several data tables useful in various kinds of
HTML parsing operations.
@@ -71,14 +75,15 @@ Note that none of these variables are exported.
Used to determine whether to load tags for parsing HTML5
L or HTML 4 or below
L. This needs to be set before
-HTML::Tagset is loaded, using BEGIN. Set it to B to get HTML5
-tags, leave empty or set to anything else for HTML4 and below.
+HTML::Tagset is loaded, using BEGIN. Set it to B to get HTML4
+tags and below, leave empty or set to anything else for HTML5.
NB: This can also be used before HTML::Tagset-using modules, eg
L.
+ # Load Tagset for HTML4
BEGIN {
- $HTML::Tagset::HTML_VERSION='v5';
+ $HTML::Tagset::HTML_VERSION='v4';
};
use HTML::Tagset;
@@ -93,7 +98,8 @@ C<$HTML::Tagset::emptyElement{'dl'}> does not exist, and so is not true.
=cut
-if($HTML_VERSION eq 'v5') {
+if(!$HTML_VERSION || $HTML_VERSION ne 'v4') {
+ # default to v5
%emptyElement = %HTML::Tagset::v5::emptyElement;
%optionalEndTag = %HTML::Tagset::v5::optionalEndTag;
%linkElements = %HTML::Tagset::v5::linkElements;
@@ -111,7 +117,7 @@ if($HTML_VERSION eq 'v5') {
@p_closure_barriers = @HTML::Tagset::v5::p_closure_barriers;
%isCDATA_Parent = %HTML::Tagset::v5::isCDATA_Parent;
} else {
- # default to v4
+ # v4
%emptyElement = %HTML::Tagset::v4::emptyElement;
%optionalEndTag = %HTML::Tagset::v4::optionalEndTag;
%linkElements = %HTML::Tagset::v4::linkElements;
From 0fb71cab883ce67e00336f25d23d5d5d8924de16 Mon Sep 17 00:00:00 2001
From: Jess Robinson
Date: Tue, 19 Nov 2019 17:13:20 +0000
Subject: [PATCH 5/6] Add tests for ensuring tags appear in v4 or v5 lists
appropriately
---
t/{02_versions.t => 02_version.t} | 4 +-
t/03_tags.t | 75 +++++++++++++++++++++++++++++++
2 files changed, 77 insertions(+), 2 deletions(-)
rename t/{02_versions.t => 02_version.t} (62%)
create mode 100644 t/03_tags.t
diff --git a/t/02_versions.t b/t/02_version.t
similarity index 62%
rename from t/02_versions.t
rename to t/02_version.t
index 7c65bc2..62f6673 100644
--- a/t/02_versions.t
+++ b/t/02_version.t
@@ -4,7 +4,7 @@ use warnings;
use Test::More;
BEGIN {
- $HTML::Tagset::HTML_VERSION='v5';
+ $HTML::Tagset::HTML_VERSION='v4';
};
use HTML::Tagset;
@@ -12,6 +12,6 @@ use Data::Dumper;
# diag(Dumper(\%HTML::Tagset::emptyElement));
-ok($HTML::Tagset::emptyElement{source}, 'Loaded v5');
+ok($HTML::Tagset::emptyElement{bgsound}, 'Loaded v4');
done_testing;
\ No newline at end of file
diff --git a/t/03_tags.t b/t/03_tags.t
new file mode 100644
index 0000000..6e997a4
--- /dev/null
+++ b/t/03_tags.t
@@ -0,0 +1,75 @@
+use strict;
+use warnings;
+
+use Test::More;
+
+use HTML::Tagset::v4;
+use HTML::Tagset::v5;
+
+# From https://developer.mozilla.org/en-US/docs/Web/HTML/Element "Obsolete and deprecated" list
+my @v4_only_tags = qw/acronym applet basefont bgsound big blink center dir font frame frameset isindex listing multicol nobr noembed noframes plaintext spacer strike tt xmp/;
+
+my $found_all = 1;
+
+foreach my $tag (@v4_only_tags) {
+ if(!exists $HTML::Tagset::v4::isKnown{$tag}) {
+ $found_all = 0;
+ diag("Didn't find $tag in v4 list");
+ }
+}
+
+ok($found_all, 'All HTML4-Only tags exist in the v4 tag list');
+
+$found_all = 1;
+foreach my $tag (@v4_only_tags) {
+ if(exists $HTML::Tagset::v5::isKnown{$tag}) {
+ $found_all = 0;
+ diag("Found $tag in v5 list");
+ }
+}
+
+ok($found_all, 'All HTLM4-only tags do not exist in v5 tag list');
+
+my @v5_only_tags = qw/article aside audio datalist details dialog figure figcaption header keygen main mark meter output picture rp rt ruby source summary template track video/;
+
+$found_all = 1;
+foreach my $tag (@v5_only_tags) {
+ if(!exists $HTML::Tagset::v5::isKnown{$tag}) {
+ $found_all = 0;
+ diag("Didn't find $tag in v5 list");
+ }
+}
+
+ok($found_all, 'All HTML5-only tags exist in v5 list');
+
+$found_all = 1;
+foreach my $tag (@v5_only_tags) {
+ if(exists $HTML::Tagset::v4::isKnown{$tag}) {
+ $found_all = 0;
+ diag("Found $tag in v4 list");
+ }
+}
+
+ok($found_all, 'All HTLM5-only tags do not exist in v4 tag list');
+
+my @shared_tags = qw/span abbr q sub sup cite code em kbd samp strong var dfn b i u s small a img br wbr bdo embed title base link meta script style object tr td th thead tbody tfoot caption col colgroup input select option optgroup textarea button label h1 h2 h3 h4 h5 h6 p div pre address blockquote iframe hr ol ul menu li dl dt dd ins del fieldset legend map area object table form/;
+
+$found_all = 1;
+foreach my $tag (@shared_tags) {
+ if(!exists $HTML::Tagset::v5::isKnown{$tag}) {
+ $found_all = 0;
+ diag("Didn't find $tag in v5 list");
+ }
+}
+ok($found_all, 'Shared tags exist in v5 list');
+
+$found_all = 1;
+foreach my $tag (@shared_tags) {
+ if(!exists $HTML::Tagset::v4::isKnown{$tag}) {
+ $found_all = 0;
+ diag("Didn't find $tag in v4 list");
+ }
+}
+ok($found_all, 'Shared tags exist in v4 list');
+
+done_testing;
From af7149b3f6e12d8dadd9db88de38b8e218260521 Mon Sep 17 00:00:00 2001
From: Jess Robinson
Date: Tue, 19 Nov 2019 17:15:52 +0000
Subject: [PATCH 6/6] Add missing HTML5 tags (old ones)
---
lib/HTML/Tagset/v5.pm | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/HTML/Tagset/v5.pm b/lib/HTML/Tagset/v5.pm
index 03c6287..e764011 100644
--- a/lib/HTML/Tagset/v5.pm
+++ b/lib/HTML/Tagset/v5.pm
@@ -181,7 +181,7 @@ This hashset contains all phrasal-level elements.
# https://html.spec.whatwg.org/multipage/dom.html#phrasing-content-2
%isPhraseMarkup = map {; $_ => 1 } qw(
- a abbr audio b bdi bdo br button canvas cite code data datalist del dfn em embed i iframe img input ins kbd label map mark math meter noscript object output picture progress q ruby s samp script select slot small span strong sub sup svg template textarea time u var video wbr
+ a abbr audio b bdi bdo br button canvas cite code data datalist del dfn em embed i iframe img input ins kbd keygen label map mark math meter noscript object output picture progress q ruby s samp script select slot small span strong sub sup svg template textarea time u var video wbr
area link meta
); # had: center, hr, table
# v4
@@ -280,7 +280,7 @@ the "body" element of an HTML document.
iframe
hr
- ol ul menu li
+ ol ul menu li menuitem
dl dt dd
ins del