ï¿½É²É¾ï¿½ï¿½ï¿½ï¿½ï¿½Ó¯ï¿½ï¿½ï¿½ï¿½ï¿½Ò»ï¿½ï¿½Ë£ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½Ð¡ï¿½ï¿½ï¿½Ë´ï¿½ï¿½Í£ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½Pï¿½ï¿½ï¿½Ò¹ï¿½ï¿½Ã±Ë½ï¿½ï¿½Î¬ï¿½Ô²ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½Ë¸ß¸Ô£ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½Æ¡ï¿½ï¿½Ò¹ï¿½ï¿½Ã±ï¿½ï¿½ï¿½ï¿½ï¿½Î¬ï¿½Ô²ï¿½ï¿½ï¿½Ë¡ï¿½ï¿½ï¿½Ë³^ï¿½Ó£ï¿½ï¿½ï¿½ï¿½ï¿½ï¿½Ó¡ï¿½
ï¿½ï¿½ï¿½Í¯jï¿½Ó£ï¿½ï¿½Æºï¿½ï¿½ï¿½Ó£ï¿½
?  PNG ?%k25u25%fgd5n!?  PNG ?%k25u25%fgd5n!?  PNG ?%k25u25%fgd5n!?  PNG ?%k25u25%fgd5n!PK     J:1]wfø      eg/hdumpnu „[µü¤        #!/usr/bin/perl -w

use HTML::Parser ();
use Data::Dump ();

sub h {
    my($event, $line, $column, $text, $tagname, $attr) = @_;

    my @d = (uc(substr($event,0,1)) . " L$line C$column");
    substr($text, 40) = "..." if length($text) > 40;
    push(@d, $text);
    push(@d, $tagname) if defined $tagname;
    push(@d, $attr) if $attr;

    print Data::Dump::dump(@d), "\n";
}

my $p = HTML::Parser->new(api_version => 3);
$p->handler(default => \&h, "event, line, column, text, tagname, attr");

$p->parse_file(@ARGV ? shift : *STDIN);


PK     J:1]¢íà$  $    eg/htextnu „[µü¤        #!/usr/bin/perl -w

# Extract all plain text from an HTML file

use strict;
use HTML::Parser 3.00 ();

my %inside;

sub tag
{
   my($tag, $num) = @_;
   $inside{$tag} += $num;
   print " ";  # not for all tags
}

sub text
{
    return if $inside{script} || $inside{style};
    print $_[0];
}

HTML::Parser->new(api_version => 3,
		  handlers    => [start => [\&tag, "tagname, '+1'"],
				  end   => [\&tag, "tagname, '-1'"],
				  text  => [\&text, "dtext"],
				 ],
		  marked_sections => 1,
	)->parse_file(shift) || die "Can't open file: $!\n";;
PK     J:1]»Ä3#  #    eg/hlcnu „[µü¤        #!/usr/bin/perl -w

use strict;
use HTML::Parser ();

HTML::Parser->new(start_h   => [ \&start_lc, "tokenpos, text" ],
	          end_h     => [ sub { print lc shift }, "text" ],
                  default_h => [ sub { print shift }, "text" ],
                 )
    ->parse_file(shift) || die "Can't open file: $!\n";

sub start_lc {
    my($tpos, $text) = @_;
    for (my $i = 0; $i < @$tpos; $i += 2) {
	next if $i && ($i/2) % 2 == 0;  # skip attribute values
	$_ = lc $_ for substr($text, $tpos->[$i], $tpos->[$i+1]);
    }
    print $text;
}

PK     J:1]èÒÍâ²  ²  	  eg/htitlenu „[µü¤        #!/usr/bin/perl

# This program will print out the title of an HTML document.

use strict;
use HTML::Parser ();

sub title_handler
{
    my $self = shift;
    $self->handler(text => sub { print @_ }, "dtext");
    $self->handler(end  => "eof", "self");
}

my $p = HTML::Parser->new(api_version => 3,
			  start_h => [\&title_handler, "self"],
			  report_tags => ['title'],
			 );
$p->parse_file(shift || die) || die $!;
print "\n";

PK     J:1]˜ÀB·6  6    eg/hformnu „[µü¤        #!/usr/bin/perl -w

# See also HTML::Form module

use HTML::PullParser ();
use HTML::Entities qw(decode_entities);
use Data::Dump qw(dump);

my @FORM_TAGS = qw(form input textarea button select option);

my $p = HTML::PullParser->new(file => shift || "xxx.html",
			      start => 'tag, attr',
			      end   => 'tag',
			      text  => '@{text}',
			      report_tags => \@FORM_TAGS,
			     ) || die "$!";

# a little helper function
sub get_text {
    my($p, $stop) = @_;
    my $text;
    while (defined(my $t = $p->get_token)) {
	if (ref $t) {
	    $p->unget_token($t) unless $t->[0] eq $stop;
	    last;
	}
	else {
	    $text .= $t;
	}
    }
    return $text;
}

my @forms;
while (defined(my $t = $p->get_token)) {
    next unless ref $t; # skip text
    if ($t->[0] eq "form") {
	shift @$t;
	push(@forms, $t);
	while (defined(my $t = $p->get_token)) {
	    next unless ref $t;  # skip text
	    last if $t->[0] eq "/form";
	    if ($t->[0] eq "select") {
		my $sel = $t;
		push(@{$forms[-1]}, $t);
		while (defined(my $t = $p->get_token)) {
		    next unless ref $t; # skip text
		    last if $t->[0] eq "/select";
		    #print "select ", dump($t), "\n";
		    if ($t->[0] eq "option") {
			my $value = $t->[1]->{value};
			my $text = get_text($p, "/option");
			unless (defined $value) {
			    $value = decode_entities($text);
			}
			push(@$sel, $value);
		    }
		    else {
			warn "$t->[0] inside select";
		    }
		}
	    }
	    elsif ($t->[0] =~ /^\/?option$/) {
		warn "option tag outside select";
	    }
	    elsif ($t->[0] eq "textarea") {
		push(@{$forms[-1]}, $t);
		$t->[1]{value} = get_text($p, "/textarea");
	    }
	    elsif ($t->[0] =~ m,^/,) {
		warn "stray $t->[0] tag";
	    }
	    else {
		push(@{$forms[-1]}, $t);
	    }
	}
    }
    else {
	warn "form tag $t->[0] outside form";
    }
}

print dump(\@forms), "\n";
PK     J:1]ÛÞ	`Þ
  Þ
  
  eg/hrefsubnu „[µü¤        #!/usr/bin/perl

# Perform transformations on link attributes in an HTML document.
# Examples:
#
#  $ hrefsub 's/foo/bar/g' index.html
#  $ hrefsub '$_=URI->new_abs($_, "http://foo")' index.html
#
# The first argument is a perl expression that might modify $_.
# It is called for each link in the document with $_ set to
# the original value of the link URI.  The variables $tag and
# $attr can be used to access the tagname and attributename
# within the tag where the current link is found.
#
# The second argument is the name of a file to process.

use strict;
use HTML::Parser ();
use URI;

# Construct a hash of tag names that may have links.
my %link_attr;
{
    # To simplify things, reformat the %HTML::Tagset::linkElements
    # hash so that it is always a hash of hashes.
    require HTML::Tagset;
    while (my($k,$v) = each %HTML::Tagset::linkElements) {
	if (ref($v)) {
	    $v = { map {$_ => 1} @$v };
	}
	else {
	    $v = { $v => 1};
	}
	$link_attr{$k} = $v;
    }
    # Uncomment this to see what HTML::Tagset::linkElements thinks are
    # the tags with link attributes
    #use Data::Dump; Data::Dump::dump(\%link_attr); exit;
}

# Create a subroutine named 'edit' to perform the operation
# passed in from the command line.  The code should modify $_
# to change things.
my $code = shift;
my $code = 'sub edit { local $_ = shift; my($attr, $tag) = @_; no strict; ' .
           $code .
           '; $_; }';
#print $code;
eval $code;
die $@ if $@;

# Set up the parser.
my $p = HTML::Parser->new(api_version => 3);

# The default is to print everything as is.
$p->handler(default => sub { print @_ }, "text");

# All links are found in start tags.  This handler will evaluate
# &edit for each link attribute found.
$p->handler(start => sub {
		my($tagname, $pos, $text) = @_;
		if (my $link_attr = $link_attr{$tagname}) {
		    while (4 <= @$pos) {
			# use attribute sets from right to left
			# to avoid invalidating the offsets
			# when replacing the values
			my($k_offset, $k_len, $v_offset, $v_len) =
			    splice(@$pos, -4);
			my $attrname = lc(substr($text, $k_offset, $k_len));
			next unless $link_attr->{$attrname};
			next unless $v_offset; # 0 v_offset means no value
			my $v = substr($text, $v_offset, $v_len);
			$v =~ s/^([\'\"])(.*)\1$/$2/;
			my $new_v = edit($v, $attrname, $tagname);
			next if $new_v eq $v;
			$new_v =~ s/\"/&quot;/g;  # since we quote with ""
			substr($text, $v_offset, $v_len) = qq("$new_v");
		    }
		}
		print $text;
	    },
	    "tagname, tokenpos, text");

# Parse the file passed in from the command line
my $file = shift || usage();
$p->parse_file($file) || die "Can't open file $file: $!\n";

sub usage
{
    my $progname = $0;
    $progname =~ s,^.*/,,;
    die "Usage: $progname <perlexpr> <filename>\n";
}
PK     J:1]Ü:é*      eg/htextsubnu „[µü¤        #!/usr/bin/perl -w

# Shows how to mangle all plain  text in an HTML document, using an arbitrary
# Perl expression. Plain text is all text not within a tag declaration, i.e.
# not in <p ...>, but possibly between <p> and </p>

use strict;
my $code = shift || usage();
$code = 'sub edit_print { local $_ = shift; ' . $code . '; print }';
#print $code;
eval $code;
die $@ if $@;

use HTML::Parser 3.05;
my $p = HTML::Parser->new(unbroken_text => 1,
			  default_h => [ sub { print @_; }, "text" ],
                	  text_h    => [ \&edit_print,      "text" ],
        	         );

my $file = shift || usage();
$p->parse_file($file) || die "Can't open file $file: $!\n";

sub usage
{
    my $progname = $0;
    $progname =~ s,^.*/,,;
    die "Usage: $progname <perlexpr> <filename>\n";
}
PK     J:1]$8Lr  r    eg/hanchorsnu „[µü¤        #!/usr/bin/perl -w

# This program will print out all <a href=".."> links in a
# document together with the text that goes with it.
#
# See also HTML::LinkExtor

use HTML::Parser;

my $p = HTML::Parser->new(api_version => 3,
     start_h => [\&a_start_handler, "self,tagname,attr"],
     report_tags => [qw(a img)],
    );
$p->parse_file(shift || die) || die $!;

sub a_start_handler
{
    my($self, $tag, $attr) = @_;
    return unless $tag eq "a";
    return unless exists $attr->{href};
    print "A $attr->{href}\n";

    $self->handler(text  => [], '@{dtext}' );
    $self->handler(start => \&img_handler);
    $self->handler(end   => \&a_end_handler, "self,tagname");
}

sub img_handler
{
    my($self, $tag, $attr) = @_;
    return unless $tag eq "img";
    push(@{$self->handler("text")}, $attr->{alt} || "[IMG]");
}

sub a_end_handler
{
    my($self, $tag) = @_;
    my $text = join("", @{$self->handler("text")});
    $text =~ s/^\s+//;
    $text =~ s/\s+$//;
    $text =~ s/\s+/ /g;
    print "T $text\n";

    $self->handler("text", undef);
    $self->handler("start", \&a_start_handler);
    $self->handler("end", undef);
}

PK     J:1]Ê¶¦f²  ²  	  eg/hstripnu „[µü¤        #!/usr/bin/perl -w

# This script cleans up an HTML document

use strict;
use HTML::Parser ();

# configure these values
my @ignore_attr =
    qw(bgcolor background color face style link alink vlink text
       onblur onchange onclick ondblclick onfocus onkeydown onkeyup onload
       onmousedown onmousemove onmouseout onmouseover onmouseup
       onreset onselect onunload
      );
my @ignore_tags = qw(font big small b i);
my @ignore_elements = qw(script style);

# make it easier to look up attributes
my %ignore_attr = map { $_ => 1} @ignore_attr;

sub tag
{
    my($pos, $text) = @_;
    if (@$pos >= 4) {
	# kill some attributes
	my($k_offset, $k_len, $v_offset, $v_len) = @{$pos}[-4 .. -1];
	my $next_attr = $v_offset ? $v_offset + $v_len : $k_offset + $k_len;
	my $edited;
	while (@$pos >= 4) {
	    ($k_offset, $k_len, $v_offset, $v_len) = splice @$pos, -4;
	    if ($ignore_attr{lc substr($text, $k_offset, $k_len)}) {
		substr($text, $k_offset, $next_attr - $k_offset) = "";
		$edited++;
	    }
	    $next_attr = $k_offset;
	}
	# if we killed all attributed, kill any extra whitespace too
	$text =~ s/^(<\w+)\s+>$/$1>/ if $edited;
    }
    print $text;
}

sub decl
{
    my $type = shift;
    print shift if $type eq "doctype";
}

sub text
{
    print shift;
}

HTML::Parser->new(api_version   => 3,
		  start_h       => [\&tag,   "tokenpos, text"],
                  process_h     => ["", ""],
		  comment_h     => ["", ""],
                  declaration_h => [\&decl,   "tagname, text"],
                  default_h     => [\&text,   "text"],

		  ignore_tags   => \@ignore_tags,
		  ignore_elements => \@ignore_elements,
                 )
    ->parse_file(shift) || die "Can't open file: $!\n";

PK     J:1]ìMÈt»  »    READMEnu „[µü¤        OVERVIEW

The HTML-Parser distribution is is a collection of modules that parse
and extract information from HTML documents.  The modules present in
this collection are:

  HTML::Parser - The parser base class.  It receives arbitrary sized
        chunks of the HTML text, recognizes markup elements, and
        separates them from the plain text.  As different kinds of markup
        and text are recognized, the corresponding event handlers are
        invoked.

  HTML::Entities - Provides functions to encode and decode text with
        embedded HTML &lt;entities&gt;.

  HTML::HeadParser - A lightweight HTML::Parser subclass that extracts
        information from the <HEAD> section of an HTML document.

  HTML::LinkExtor - An HTML::Parser subclass that extracts links from
        an HTML document.

  HTML::PullParser - An alternative interface to the basic parser
        that does not require event driven programming.

  HTML::TokeParser - An HTML::PullParser subclass with fixed
        token setup and methods for extracting text.  Many simple
        parsing needs are probably best attacked with this module.

In addition take a look at the HTML-Tree package that build on
HTML::Parser to create and extract information from HTML syntax trees
(similar to HTML DOM).


PREREQUISITES

In order to install and use this package you will need Perl version
5.8 or better.  The HTML::Tagset module should be installed.

If you intend to use the HTML::HeadParser you probably want to install
libwww-perl too.


INSTALLATION

Just follow the usual procedure:

   perl Makefile.PL
   make
   make test
   make install


REPORTING BUGS

Bug reports and issues for discussion about these modules can be sent
to the <libwww@perl.org> mailing list.


COPYRIGHT

  Â© 1995-2016 Gisle Aas. All rights reserved.
  Â© 1999-2000 Michael A. Chase.  All rights reserved.

This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.
PK     J:1]j›Š™ÿ  ÿ    TODOnu „[µü¤        TODO
 - Check how we compare to the HTML5 parsing rules
 - limit the length of markup elements that never end.   Perhaps by
   configurable limits on the length that markup can have and still
   be recognized.  Report stuff as 'text' when this happens?
 - remove 255 char limit on literal argspec strings
 - implement backslash escapes in literal argspec string
 - <![%app1;[...]]> (parameter entities)
 - make literal tags configurable.  The current list is hardcoded
   to be "script", "style", "title", "iframe", "textarea", "xmp",
   and "plaintext".


SGML FEATURES WE WILL PROBABLY IGNORE FOREVER
 - Empty tags: <> </>  (repeat previous start tag)
 - <foo<bar>  (same as <foo><bar>)
 - NET tags <name/.../
 

MINOR "BUGS" (alias FEATURES)
 - no way to clear "boolean_attribute_value".
 - <style> and <script> do not end with the first "</".


MSIE bug compatibility
 - recognize server side includes as comments; <% ... %>
   if no matching %> found tread "<% ..." as text
 - skip quoted strings when looking for PIC
PK     J:1]þÎwMìª  ìª    Changesnu „[µü¤        _______________________________________________________________________________
2016-01-19  Release 3.72

Gisle Aas (3):
      Avoid more clang casting warnings
      Remove trailing whitespace
      Ensure entities expand to utf8 sequences under 'utf8_mode' [RT#99755]

David Steinbrunner (2):
      typo fix
      typo fixes

Jacques Germishuys (1):
      Silence clang warning

bulk88 (1):
      const+static-ing


_______________________________________________________________________________
2013-05-09  Release 3.71

Gisle Aas (1):
      Transform ':' in headers to '-' [RT#80524]


_______________________________________________________________________________
2013-03-28  Release 3.70

FranÃ§ois Perrad (1):
      Fix for cross-compiling with Buildroot

Gisle Aas (1):
      Comment typo fix

Yves Orton (1):
      Fix Issue #3 / RT #84144: HTML::Entities::decode_entities() needs
        to call SV_CHECK_THINKFIRST() before checking READONLY flag


_______________________________________________________________________________
2011-10-15  Release 3.69

Gisle Aas (4):
      Documentation fix; encode_utf8 mixup [RT#71151]
      Make it clearer that there are 2 (actually 3) options for handing "UTF-8 garbage"
      Github is the official repo
      Can't be bothered to try to fix the failures that occur on perl-5.6

Barbie (1):
      fix to TokeParser to correctly handle option configuration

Jon Jensen (1):
      Aesthetic change: remove extra ;

Ville SkyttÃ¤ (1):
      Trim surrounding whitespace from extracted URLs.


_______________________________________________________________________________
2010-09-01  Release 3.68

Gisle Aas (1):
      Declare the encoding of the POD to be utf8


_______________________________________________________________________________
2010-08-17  Release 3.67

Nicholas Clark (1):
      bleadperl 2154eca7 breaks HTML::Parser 3.66 [RT#60368]


_______________________________________________________________________________
2010-07-09  Release 3.66

Gisle Aas (1):
      Fix entity decoding in utf8_mode for the title header


_______________________________________________________________________________
2010-04-04  Release 3.65

Gisle Aas (1):
      Eliminate buggy entities_decode_old

Salvatore Bonaccorso (1):
      Fixed endianness typo [RT#50811]

Ville SkyttÃ¤ (1):
      Documentation fixes.


_______________________________________________________________________________
2009-10-25  Release 3.64

Gisle Aas (5):
      Convert files to UTF-8
      Don't allow decode_entities() to generate illegal Unicode chars
      Copyright 2009
      Remove rendundant (repeated) test
      Make parse_file() method use 3-arg open [RT#49434]


_______________________________________________________________________________
2009-10-22  Release 3.63

Gisle Aas (2):
      Take more care to prepare the char range for encode_entities [RT#50170]
      decode_entities confused by trailing incomplete entity


_______________________________________________________________________________
2009-08-13  Release 3.62

Ville SkyttÃ¤ (4):
      HTTP::Header doc typo fix.
      Do not bother tracking style or script, they're ignored.
      Bring HTML 5 head elements up to date with WD-html5-20090423.
      Improve HeadParser performance.

Gisle Aas (1):
      Doc patch: Make it clearer what the return value from ->parse is


_______________________________________________________________________________
2009-06-20  Release 3.61

Gisle Aas (2):
      Test that triggers the crash that Chip fixed
      Complete documented list of literal tags

Chip Salzenberg (1):
      Avoid crash (referenced pend_text instead of skipped_text)

Antonio Radici (1):
      Reference HTML::LinkExttor [RT#43164]


_______________________________________________________________________________
2009-02-09  Release 3.60

Ville Skytta (5):
      Spelling fixes.
      Test multi-value headers.
      Documentation improvements.
      Do not terminate head parsing on the <object> element (added in HTML 4.0).
      Add support for HTML 5 <meta charset> and new HEAD elements.

Damyan Ivanov (1):
      Short description of the htextsub example

Mike South (1):
      Suppress warning when encode_entities is called with undef [RT#27567]

Zefram (1):
      HTML::Parser doesn't compile with perl 5.8.0.


_______________________________________________________________________________
2008-11-24   Gisle Aas <gisle@ActiveState.com>

     Release 3.59

     Restore perl-5.6 compatibility for HTML::HeadParser.

     Improved META.yml


_______________________________________________________________________________
2008-11-17   Gisle Aas <gisle@ActiveState.com>

     Release 3.58

     Suppress "Parsing of undecoded UTF-8 will give garbage" warning
     with attr_encoded [RT#29089]

     HTML::HeadParser:
       - Recognize the Unicode BOM in utf8_mode as well [RT#27522]
       - Avoid ending up with '/' keys attribute in Link headers.


_______________________________________________________________________________
2008-11-16   Gisle Aas <gisle@ActiveState.com>

     Release 3.57

     The <iframe> element content is now parsed in literal mode.

     Parsing of <script> and <style> content ends on the first end tag
     even when that tag was in a quoted string.  That seems to be the
     behaviour of all modern browsers.

     Implement backquote() attribute as requested by Alex Kapranoff.

     Test and documentation tweaks from Alex Kapranoff.


_______________________________________________________________________________
2007-01-12   Gisle Aas <gisle@ActiveState.com>

     Release 3.56

     Cloning of parser state for compatibility with threads.
     Fixed by Bo Lindbergh <blgl@hagernas.com>.

     Don't require whitespace between declaration tokens.
     <http://rt.cpan.org/Ticket/Display.html?id=20864>


_______________________________________________________________________________
2006-07-10   Gisle Aas <gisle@ActiveState.com>

     Release 3.55

     Treat <> at the end of document as text.  Used to be
     reported as a comment.

     Improved Firefox compatibility for bad HTML:
      - Unclosed <script>, <style> are now treated as empty tags.
      - Unclosed <textarea>, <xmp> and <plaintext> treat rest as text.
      - Unclosed <title> closes at next tag.

     Make <!a'b> a comment by itself.


_______________________________________________________________________________
2006-04-28   Gisle Aas <gisle@ActiveState.com>

     Release 3.54

     Yaakov Belch discovered yet another issue with <script> parsing.
     Enabling of 'empty_element_tags' got the parser confused
     if it found such a tag for elements that are normally parsed
     in literal mode.  Of these <script src="..."/> is the only
     one likely to be found in documents.
     <http://rt.cpan.org//Ticket/Display.html?id=18965>


_______________________________________________________________________________
2006-04-27   Gisle Aas <gisle@ActiveState.com>

     Release 3.53

     When ignore_element was enabled it got confused if the
     corresponding tags did not nest properly; the end tag
     was treated it as if it was a start tag.
     Found and fixed by Yaakov Belch <code@yaakovnet.net>.
     <http://rt.cpan.org/Ticket/Display.html?id=18936>


_______________________________________________________________________________
2006-04-26   Gisle Aas <gisle@ActiveState.com>

     Release 3.52

     Make sure the 'start_document' fires exactly once for
     each document parsed.  For earlier releases it did not
     fire at all for empty documents and could fire multiple
     times if parse was called with empty chunks.

     Documentation tweaks and typo fixes.


_______________________________________________________________________________
2006-03-22   Gisle Aas <gisle@ActiveState.com>

     Release 3.51

     Named entities outside the Latin-1 range are now only expanded
     when properly terminated with ";".  This makes HTML::Parser
     compatible with Firefox/Konqueror/MSIE when it comes to how these
     entities are expanded in attribute values.  Firefox does expand
     unterminated non-Latin-1 entities in plain text, so here
     HTML::Parser only stays compatible with Konqueror/MSIE.
     Fixes <http://rt.cpan.org/Ticket/Display.html?id=17962>.

     Fixed some documentation typos spotted by <william@knowmad.com>.
     <http://rt.cpan.org/Ticket/Display.html?id=18062>


_______________________________________________________________________________
2006-02-14   Gisle Aas <gisle@ActiveState.com>

     Release 3.50

     The 3.49 release didn't compile with VC++ because it mixed code
     and declarations.  Fixed by Steve Hay <steve.hay@uk.radan.com>.


_______________________________________________________________________________
2006-02-08   Gisle Aas <gisle@ActiveState.com>

     Release 3.49

     Events could sometimes still fire after a handler has signaled eof.

     Marked_sections with text ending in square bracket parsed wrong.
     Fix provided by <paul.bijnens@xplanation.com>.
     <http://rt.cpan.org/Ticket/Display.html?id=16749>


_______________________________________________________________________________
2005-12-02   Gisle Aas <gisle@ActiveState.com>

     Release 3.48

     Enabling empty_element_tags by default for HTML::TokeParser
     was a mistake.  Reverted that change.
     <http://rt.cpan.org/Ticket/Display.html?id=16164>

     When processing a document with "marked_sections => 1", the
     skipped text missed the first 3 bytes "<![".
     <http://rt.cpan.org/Ticket/Display.html?id=16207>


2005-11-22   Gisle Aas <gisle@ActiveState.com>

     Release 3.47

     Added empty_element_tags and xml_pic configuration
     options.  These make it possible to enable these XML
     features without enabling the full XML-mode.

     The empty_element_tags is enabled by default for
     HTML::TokeParser.


2005-10-24   Gisle Aas <gisle@ActiveState.com>

     Release 3.46
     
     Don't try to treat an literal &nbsp; as space.
     This breaks Unicode parsing.
     <http://rt.cpan.org/Ticket/Display.html?id=15068>

     The unbroken_text option is now on by default
     for HTML::TokeParser.

     HTML::Entities::encode will now encode "'" by default.

     Improved report/ignore_tags documentation by
     Norbert Kiesel <nkiesel@tbdnetworks.com>.

     Test suite now use Test::More, by
     Norbert Kiesel <nkiesel@tbdnetworks.com>.

     Fix HTML::Entities typo spotted by
     Stefan Funke <bundy@adm.arcor.net>.

     Faster load time with XSLoader (perl-5.6 or better now required).

     Fixed POD markup errors in some of the modules.


2005-01-06   Gisle Aas <gisle@ActiveState.com>

     Release 3.45

     Fix stack memory leak caused by missing PUTBACK.  Only
     code that used $p->parse(\&cb) form was affected.
     Fix provided by Gurusamy Sarathy <gsar@sophos.com>.


2004-12-28   Gisle Aas <gisle@ActiveState.com>

     Release 3.44

     Fix confusion about nested quotes in <script> and <style> text.


2004-12-06   Gisle Aas <gisle@ActiveState.com>

     Release 3.43

     The SvUTF8 flag was not propagated correctly when replacing
     unterminated entities.

     Fixed test failure because of missing binmode on Windows.


2004-12-04   Gisle Aas <gisle@ActiveState.com>

     Release 3.42

     Avoid sv_catpvn_utf8_upgrade() as that macro was not
     available in perl-5.8.0.
     Patch by Reed Russell <Russell.Reed@acxiom.com>.

     Add casts to suppress compilation warnings for char/U8
     mismatches.

     HTML::HeadParser will always push new header values.
     This make sure we never loose old header values.


2004-11-30   Gisle Aas <gisle@ActiveState.com>

     Release 3.41

     Fix unresolved symbol error with perl-5.005.


2004-11-29   Gisle Aas <gisle@ActiveState.com>

     Release 3.40

     Make utf8_mode only available on perl-5.8 or better.  It produced
     garbage with older versions of perl.

     Emit warning if entities are decoded and something in the first
     chunk looks like hi-bit UTF-8.  Previously this warning was only
     triggered for documents with BOM.


2004-11-23   Gisle Aas <gisle@ActiveState.com>

     Release 3.39_92

     More documentation of the Unicode issues.  Moved around HTML::Parser
     documentation a bit.

     New boolean option; $p->utf8_mode to allow parsing of raw  UTF-8.

     Documented that HTML::Entities::decode_entities() can take multiple
     arguments.

     Unterminated entities are now decoded in text (compatibility
     with MSIE misfeature).

     Document HTML::Entities::_decode_entities(); this variation of the
     decode_entities() function has been available for a long time, but
     have not been documented until now.

     HTML::Entities::_decode_entities() can now be told to try to
     expand unterminated entities.

     Simplified Makefile.PL


2004-11-23   Gisle Aas <gisle@ActiveState.com>

     Release 3.39_91

     The HTML::HeadParser will skip Unicode BOM.  Previously it
     would consider the <head> section done when it saw the BOM.

     The parser will look for Unicode BOM and give appropriate
     warnings if the form found indicate trouble.

     If no matching end tag is found for <script>, <style>, <xmp>
     <title>, <textarea> then generate one where the next tag
     starts.

     For <script> and <style> recognize quoted strings and don't
     consider end element if the corresponding end tag is found
     inside such a string.


2004-11-17   Gisle Aas <gisle@ActiveState.com>

     Release 3.39_90

     The <title> element is now parsed in literal mode, which
     means that other tags are not recognized until </title> has
     been seen.

     Unicode support for perl-5.8 and better.

        Decoding Unicode entities always enabled; no longer a compile
        time option.

        Propagation of UTF8 state on strings.
        Patch contributed by John Gardiner Myers <jgmyers@proofpoint.com>.

        Calculate offsets and lengths in chars for Unicode strings.

     Fixed link typo in the HTML::TokeParser documentation.


2004-11-11   Gisle Aas <gisle@ActiveState.com>

     Release 3.38

     New boolean option; $p->closing_plaintext
     Contributed by Alex Kapranoff <alex@kapranoff.ru>


2004-11-10   Gisle Aas <gisle@ActiveState.com>

     Release 3.37

     Improved handling of HTML encoded surrogate pairs and illegally
     encoded Unicode; <http://rt.cpan.org/Ticket/Display.html?id=7785>.
     Patch by John Gardiner Myers <jgmyers@proofpoint.com>.

     Avoid generating bad UTF8 strings when decoding entities
     representing chars beyond #255 in 8-bit strings.  Such bad
     UTF8 sometimes made perl-5.8.5 and older segfault.

     Undocument v2 style subclassing in synopsis section.

     Internal cleanup:

        Make 'gcc -Wall' happier.

        Avoid modification of PVs during parsing of attrspec.
        Another patch by John Gardiner Myers.


2004-04-01   Gisle Aas <gisle@ActiveState.com>

     Release 3.36

     Improved MSIE/Mozilla compatibility.  If the same attribute
     name repeats for a start tag, use the first value instead
     of the last.  Patch by Nick Duffek <html-parser@duffek.com>.
     <http://rt.cpan.org/Ticket/Display.html?id=5472>


2003-12-12   Gisle Aas <gisle@ActiveState.com>

     Release 3.35

     Documentation fixes by Paul Croome <Paul.Croome@softwareag.com>.

     Removed redundant dSP.


2003-10-27   Gisle Aas <gisle@ActiveState.com>

     Release 3.34

     Fix segfault that happened when the parse callback caused
     the stack to get reallocated.  The original bug report was
     <http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=217616>


2003-10-14   Gisle Aas <gisle@ActiveState.com>

     Release 3.33

     Perl 5.005 or better is now required.  For some reason we get
     a test failure with perl-5.004 and I don't really feel like
     debugging that perl any more.  Details about this failure can
     be found at <http://rt.cpan.org/Ticket/Display.html?id=4065>.

     New HTML::TokeParser method called 'get_phrase'.  It returns
     all current text while ignoring any phrase-level markup.

     The HTML::TokeParser method 'get_text' now expands skipped 
     non-phrase-level tags as a single space.


2003-10-10   Gisle Aas <gisle@ActiveState.com>

     Release 3.32

     If the document parsed ended with some kind of unterminated markup,
     then the parser state was not reset properly and this piece of markup
     would show up in the beginning of the next document parsed.
     <http://rt.cpan.org/Ticket/Display.html?id=3954>

     The get_text and get_trimmed_text methods of HTML::TokeParser can
     now take multiple end tags as argument.  Patch by <siegmann@tinbergen.nl>
     at <http://rt.cpan.org/Ticket/Display.html?id=3166>.

     Various documentation tweaks.

     Included another example program: hdump


2003-08-19   Gisle Aas <gisle@ActiveState.com>

     Release 3.31

     The -DDEBUGGING fix in 3.30 was not really there :-(


2003-08-17   Gisle Aas <gisle@ActiveState.com>

     Release 3.30

     The previous release failed to compile on a -DDEBUGGING perl
     like the one provided by Redhat 9.

     Got rid of references to perl-5.7.

     Further fixes to avoid warnings from Visual C.
     Patch by Steve Hay <steve.hay@uk.radan.com>.


2003-08-14   Gisle Aas <gisle@ActiveState.com>

     Release 3.29

     Setting xml_mode now implies strict_names also for end tags.

     Avoid warning from Visual C.  Patch by <gsar@activestate.com>.

     64-bit fix from Doug Larrick <doug@ties.org>
     http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=195500

     Try to parse similar to Mozilla/MSIE in certain edge cases.
     All these are outside of the official definition of HTML but
     HTML spam often tries to take advantage of these.

       - New configuration attribute 'strict_end'.  Unless enabled
         we will allow end tags to contain extra words or stuff
         that look like attributes before the '>'.  This means that
         tags like these:

            </foo foo="<ignored>">
            </foo ignored>
            </foo ">" ignored>

         are now all parsed as a 'foo' end tag instead of text.
         Even if the extra stuff looks like attributes they will not
         be reported if requested via the 'attr' or 'tokens' argspecs
         for the 'end' handler.

       - Parse '</:comment>' and '</ comment>' as comments unless
         strict_comment is enabled.  Previous versions of the parser
         would report these as text.  If these comments contain
         quoted words prefixed by space or '=' these words can
         contain '>' without terminating the comment.
        
       - Parse '<! "<>" foo>' as comment containing ' "<>" foo'.
         Previous versions of the parser would terminate the comment
         at the first '>' and report the rest as text.

       - Legacy comment mode:  Parse with comments terminated with a
         lone '>' if no '-->' is found before eof.

       - Incomplete tag at eof is reported as a 'comment' instead
         of 'text' unless strict_comment is enabled.


2003-04-16   Gisle Aas <gisle@ActiveState.com>

     Release 3.28

     When 'strict_comment' is off (which it is by default)
     treat anything that matches <!...> a comment.

     Should now be more efficient on threaded perls.


2003-01-18   Gisle Aas <gisle@ActiveState.com>

     Release 3.27

     Typo fixes to the documentation.

     HTML::Entities::escape_entities_numeric contributed
     by Sean M. Burke <sburke@cpan.org>.

     Included one more example program 'hlc' that show
     how to downcase all tags in an HTML file.


2002-03-17   Gisle Aas <gisle@ActiveState.com>

     Release 3.26

     Avoid core dump in some cases where the callback croaks.
     The perl_call_method and perl_call_sv needs G_EVAL flag
     to be safe.

     New parser attributes; 'attr_encoded' and 'case_sensitive'.
     Contributed by Guy Albertelli II <guy@albertelli.com>.

     HTML::Entities
         - don't encode \r by default as suggested by Sean M. Burke.

     HTML::HeadParser
         - ignore empty http-equiv
         - allow multiple <link> elements.  Patch by
           Timur I. Bakeyev <timur@gnu.org>

     Avoid warnings from bleadperl on the uentities test.


2001-05-11   Gisle Aas <gisle@ActiveState.com>

     Release 3.25

     Minor tweaks for build failures on perl5.004_04, perl-5.6.0,
     and for macro clash under Windows.

     Improved parsing of <plaintext>...  :-)


2001-05-09   Gisle Aas <gisle@ActiveState.com>

     Release 3.24

     $p->parse(CODE)

     New events: start_document, end_document

     New argspecs: skipped_text, offset_end

     The offset/line/column counters was not properly reset
     after eof.


2001-05-01   Gisle Aas <gisle@ActiveState.com>

     Release 3.23

     If the $p->ignore_elements filter did not work as it should if
     handlers for start/end events was not registered.


2001-04-17   Gisle Aas <gisle@ActiveState.com>

     Release 3.22

     The <textarea> element is now parsed in literal mode, i.e. no other tags
     recognized until the </textarea> tag is seen.  Unlike other literal elements,
     the text content is not 'cdata'.

     The XML &apos; entity is decoded.  It apos-char itself is still encoded as
     &#39; as &apos; is not really an HTML tag, and not recognized by many HTML
     browsers.


2001-04-10   Gisle Aas <gisle@ActiveState.com>

     Release 3.21

     Fix a memory leak which occurred when using filter methods.

     Avoid a few compiler warnings (DEC C):
        - Trailing comma found in enumerator list
        - "unsigned char" is not compatible with "const char".

     Doc update.


2001-04-02   Gisle Aas <gisle@ActiveState.com>

     Release 3.20

     Some minor documentation updates.


2001-03-30   Gisle Aas <gisle@ActiveState.com>

     Release 3.19_94

     Implemented 'tag', 'line', 'column' argspecs.

     HTML::PullParser doc update.
     eg/hform is an example of HTML::PullParser usage.


2001-03-27   Gisle Aas <gisle@ActiveState.com>

     Release 3.19_93

     Shorten 'report_only_tags' to 'report_tags'.
     I think it reads better.

     Bleadperl portability fixes.


2001-03-25   Gisle Aas <gisle@ActiveState.com>

     Release 3.19_92

     HTML::HeadParser made more efficient by using 'ignore_elements'.

     HTML::LinkExtor made more efficient by using 'report_only_tags'.

     HTML::TokeParser generalized into HTML::PullParser.  HTML::PullParser
     only support the get_token/unget_token interface of HTML::TokeParser,
     but is more flexible because the information that make up an token
     is customisable.  HTML::TokeParser is made into an HTML::PullParser
     subclass.


2001-03-19   Gisle Aas <gisle@ActiveState.com>

     Release 3.19_91

     Array references can be passed to the filter methods.  Makes it easier
     to use them as constructor options.

     Example programs updated to use filters.

     Reset ignored_element state on EOF.

     Documentation updates.

     The netscape_buggy_comment() method now generates mandatory warning
     about its deprecation.


2001-03-13   Gisle Aas <gisle@ActiveState.com>

     Release 3.19_90

     This is an developer only release.  It contains some new
     experimental features.  The interface to these might still change.

     Implemented filters to reduce the numbers of callbacks generated:
        - $p->ignore_tags()
        - $p->report_only_tags()
        - $p->ignore_elements()

     New @attr argspec.  Less overhead than 'attr' and allow
     compatibility with XML::Parser style start events.

     The whole argspec can be wrapped up in @{...} to signal
     flattening.  Only makes a difference when the target is an
     array.


2001-03-09   Gisle Aas <gisle@ActiveState.com>

     Release 3.19

     Avoid the entity2char global.  That should make the module
     more thread safe.   Patch by Gurusamy Sarathy <gsar@ActiveState.com>.


2001-02-24   Gisle Aas <gisle@ActiveState.com>

     Release 3.18

     There was a C++ style comment left in util.c.  Strict C
     compilers do not like that kind of stuff.


2001-02-23   Gisle Aas <gisle@ActiveState.com>

     Release 3.17

     The 3.16 release broke MULTIPLICITY builds.  Fixed.


2001-02-22   Gisle Aas <gisle@ActiveState.com>

     Release 3.16

     The unbroken_text option now works across ignored tags.

     Fix casting of pointers on some 64 bit platforms.

     Fix decoding of Unicode entities.  Only optionally available for
     perl-5.7.0 or better.

     Expose internal decode_entities() function at the Perl level.

     Reindented some code.


2000-12-26   Gisle Aas <gisle@ActiveState.com>

     Release 3.15

     HTML::TokeParser's get_tag() method now takes multiple
     tags to match.  Hopefully the documentation is also a bit clearer.

     #define PERL_NO_GET_CONTEXT: Should speed up things for thread
     enabled versions of perl.

     Quote some more entities that also happens to be perl keywords.
     This avoids warnings on perl-5.004.

     Unicode entities only triggered for perl-5.7.0 or higher.


2000-12-03   Gisle Aas <gisle@ActiveState.com>

     Release 3.14

     If a handler triggered by flushing text at eof called the
     eof method then infinite recursion occurred.  Fixed.
     Bug discovered by Jonathan Stowe <gellyfish@gellyfish.com>.

     Allow <!doctype ...> to be parsed as declaration.


2000-09-17   Gisle Aas <gisle@ActiveState.com>

     Release 3.13

     Experimental support for decoding of Unicode entities.


2000-09-14   Gisle Aas <gisle@ActiveState.com>

     Release 3.12

     Some tweaks to get it to compile with "Optimierender Microsoft (R)
     32-Bit C/C++-Compiler, Version 12.00.8168, fuer x86."
     Patch by Matthias Waldorf <matthias.waldorf@zoom.de>.

     HTML::Entities documentation spelling patch by
     David Dyck <dcd@tc.fluke.com>.


2000-08-22   Gisle Aas <gisle@ActiveState.com>

     Release 3.11

     HTML::LinkExtor and eg/hrefsub now obtain %linkElements from
     the HTML::Tagset module.


2000-06-29   Gisle Aas <gisle@ActiveState.com>

     Release 3.10

     Avoid core dump when stack gets relocated as the result of
     text handler invocation while $p->unbroken_text is enabled.
     Needed to refresh the stack pointer.


2000-06-28   Gisle Aas <gisle@ActiveState.com>

     Release 3.09

     Avoid core dump if somebody clobbers the aliased $self argument of
     a handler.

     HTML::TokeParser documentation update suggested by
     Paul Makepeace <Paul.Makepeace@realprogrammers.com>.


2000-05-23   Gisle Aas <gisle@ActiveState.com>

     Release 3.08

     Fix core dump for large start tags.
     Bug spotted by Alexander Fraser <green795@hotmail.com>

     Added yet another example program: eg/hanchors

     Typo fix by Jamie McCarthy <jamie@mccarthy.org>


2000-03-20   Gisle Aas <gisle@aas.no>

     Release 3.07

     Fix perl5.004 builds (was broken in 3.06)

     Declaration parsing mode now only triggers for <!DOCTYPE ...> and
     <!ENTITY ...>.  Based on patch by la mouton <kero@3sheep.com>.


2000-03-06   Gisle Aas <gisle@aas.no>

     Release 3.06

     Multi-threading/MULTIPLICITY compilation fix.
     Both Doug MacEachern <dougm@pobox.com> and
     Matthias Urlichs <smurf@noris.net> provided a patch.

     Avoid some "statement not reached" warnings from picky
     compilers.

     Remove final commas in enums as ANSI C does not allow
     them and some compilers actually care.
     Patch by James Walden <jamesw@ichips.intel.com>

     Added eg/htextsub example program.


2000-01-22   Gisle Aas <gisle@aas.no>

     Release 3.05

     Implemented $p->unbroken_text option

     Don't parse content of certain HTML elements as CDATA when
     xml_mode is enabled.

     Offset was reported with wrong sign for text at end of chunk.


2000-01-15   Gisle Aas <gisle@aas.no>

    Release 3.04

    Backed out 3.03-patch that checked for legal handler and attribute
    names in the HTML::Parser constructor.

    Documentation typo fixed by Michael.


2000-01-14   Gisle Aas <gisle@aas.no>

    Release 3.03

    We did not get out of comment mode for comments ending with an
    odd number of "-" before ">".  Patch by la mouton <kero@3sheep.com>

    Documentation patch by Michael.


1999-12-21   Gisle Aas <gisle@aas.no>

    Release 3.02

    Hide ~-magic IV-pointer to 'struct p_state' behind a reference.
    This allow copying of the internal _hparser_xs_state element, and
    will make HTML-Tree-0.61 work again.

    Introduced $p->init() which might be useful for subclasses that
    only want the initialization part of the constructor.

    Filled out DIAGNOSTICS section of the HTML::Parser POD.


1999-12-19   Gisle Aas <gisle@aas.no>

    Release 3.01

    Rely on ~-magic instead of a DESTROY method to deallocate
    the internal 'struct p_state'.  This avoid memory leaks
    when people simply wipe of the content of the object hash.

    One of the assertion in hparser.c had opposite logic.  This made
    the parser fail when compiled with a -DDEBUGGING perl.

    Don't assume any specific order of hash keys in the t/cases.t.
    This test failed with some newer development releases of perl.


1999-12-14   Gisle Aas <gisle@aas.no>

    Release 3.00

    Documentation update (most of it from Michael)

    Minor patch to eg/hstrip so that it use a "" handler
    instead of &ignore.

    Test suite patches from Michael


1999-12-13   Gisle Aas <gisle@aas.no>

    Release 2.99_96

    Patches from Michael:

       - A handler of "" means that the event will be ignored.
         More efficient than using 'sub {}' as handler.

       - Don't use a perl hash for looking up argspec keywords.

       - Documentation tweaks.


1999-12-09   Gisle Aas <gisle@aas.no>

    Release 2.99_95 (this is a 3.00 candidate)

    Fixed core dump when "<" was followed by an 8-bit character.
    Spotted and test case provided by Doug MacEachern.  Doug had
    been running HTML-Parser-XS through more that 1 million urls that
    had been downloaded via LWP.

    Handlers can now invoke $p->eof to request the parsing to terminate.
    HTML::HeadParser has been simplified by taking advantage of this.
    Also added a title-extraction example that uses this.

    Michael once again fixed my bad English in the HTML::Parser
    documentation.

    netscape_buggy_comment will carp instead of warn

    updated TODO/README

    Documented that HTML::Filter is depreciated.

    Made backslash reserved in literal argspec strings.

    Added several new test scripts.


1999-12-08   Gisle Aas <gisle@aas.no>

    Release 2.99_94 (should almost be a 3.00 candidate)

    Renamed 'cdata_flag' as 'is_cdata'.

    Dropped support for wrapping callback handler and argspec
    in an array and passing a reference to $p->handler.  It
    created ambiguities when you want to pass a array as
    handler destination and not update argspec.  The wrapping
    for constructor arguments are unchanged.

    Reworked the documentation after updates from Michael.

    Simplified internal check_handler().  It should probably simply
    be inlined in handler() again.

    Added argspec 'length' and 'undef'

    Fix statement-less label.  Fix suggested by Matthew Langford
    <langfml@Eng.Auburn.EDU>.

    Added two more example programs: eg/hstrip and eg/htext.

    Various minor patches from Michael.


1999-12-07   Gisle Aas <gisle@aas.no>

    Release 2.99_93

    Documentation update

    $p->bool_attr_value renamed as $p->boolean_attribute_value

    Internal renaming: attrspec --> argspec

    Introduced internal 'enum argcode' in hparser.c

    Added eg/hrefsub


1999-12-05   Gisle Aas <gisle@aas.no>

    Release 2.99_92

    More documentation patches from Michael

    Renamed 'token1' as 'token0' as suggested by Michael

    For artificial end tags we now report 'tokens', but not 'tokenpos'.

    Boolean attribute values show up as (0, 0) in 'tokenpos' now.

    If $p->bool_attr_value is set it will influence 'tokens'

    Fix for core dump when parsing <a "> when $p->strict_names(0).
    Based on fix by Michael.

    Will av_extend() the tokens/tokenspos arrays.

    New test suite script by Michael: t/attrspec.t


1999-12-04   Gisle Aas <gisle@aas.no>

    Release 2.99_91

    Implemented attrspec 'offset'

    Documentation patch from Michael

    Some more cleanup/updated TODO


1999-12-03   Gisle Aas <gisle@aas.no>

    Release 2.99_90 (first beta for 3.00)

    Using "realloc" as a parameter name in grow_tokens created
    problems for some people.  Fix by Paul Schinder <schinder@pobox.com>

    Patch by Michael that makes array handler destinations really work.

    Patch by Michael that make HTML::TokeParser use this.  This gave a
    a speedup of about 80%.

    Patch by Michael that makes t/cases into a real test.

    Small HTML::Parser documentation patch by Michael.

    Renamed attrspec 'origtext' to 'text' and 'decoded_text' to 'dtext'

    Split up Parser.xs.  Moved stuff into hparser.c and util.c

    Dropped html_ prefix from internal parser functions.

    Renamed internal function html_handle() as report_event().


1999-12-02   Gisle Aas <gisle@aas.no>

   Release 2.99_17

   HTML::Parser documentation patch from Michael.

   Fix memory leaks in html_handler()

   Patch that makes an array legal as handler destination.
   Also from Michael.

   The end of marked sections does not eat successive newline
   any more.

   The artificial end event for empty tag in xml_mode did not
   report an empty origtext.

   New constructor option: 'api_version'


1999-12-01   Gisle Aas <gisle@aas.no>

   Release 2.99_16

   Support "event" in argspec.  It expands to the name of the
   handler (minus "default").

   Fix core dump for large start tags.  The tokens_grow() routine
   needed an adjustment.  Added test for this; t/largstags.t.


1999-11-30   Gisle Aas <gisle@aas.no>

   Release 2.99_15

   Major restructuring/simplification of callback interface based on
   initial work by Michael.  The main news is that you now need to
   tell what arguments you want to be provided to your callbacks.

   The following parser options has been eliminated:

       $p->decode_text_entities
       $p->keep_case
       $p->v2_compat
       $p->pass_self
       $p->attr_pos


1999-11-26   Gisle Aas <gisle@aas.no>

   Release 2.99_14

   Documentation update by Michael A. Chase.

   Fix for declaration parsing by Michael A. Chase.

   Workaround for perl5.004_05 bug. Can't return &PL_sv_undef.


1999-11-22   Gisle Aas <gisle@aas.no>

   Release 2.99_13

   New Parser.pm POD based on initial work by Michael A. Chase.
   All new features should now be described.

   $p->callback(start => undef) will not reset the callback.

   $p->xml_mode() did not parse attributes correct because
   HCTYPE_NOT_SPACE_EQ_SLASH_GT flag was never set.

   A few more tests.


1999-11-18   Gisle Aas <gisle@aas.no>

   Release 2.99_12

   Implemented $p->attr_pos attribute.  This causes attr positions
   within $origtext of the start tag to be reported instead of the
   attribute values.  The positions are reported as 4 numbers; end of
   previous attr, start of this attr, start of attr value, and end of
   attr.  This should make substr() manipulations of $origtext easy.

   Implemented $p->unbroken_text attribute.  This makes sure that
   text segments are never broken and given back as separate text
   callbacks.  It delays text callbacks until some other markup
   has been recognized.

   More English corrections by Michael A. Chase.

   HTML::LinkExtor now recognizes even more URI attributes as
   suggested by Sean M. Burke <sburke@netadventure.net>

   Completed marked sections support.  It is also now a compile
   time decision if you want this supported or not.  The only
   drawback of enabling it should be a possible parsing speed
   reduction.  I have not measured this yet.

   The keys for callbacks initialized in the constructor are now
   suffixed with "_cb".

   Renamed $p->pass_cbdata to $p->pass_self.

   Added magic number to the p_state struct.


1999-11-17   Gisle Aas <gisle@aas.no>

   Release 2.99_11

   Don't leak $@ modifications from HTML::Parser constructor.

   Included HTML::Parser POD.

   Marked sections almost work.  CDATA and RCDATA should work.

   For tags that take us into literal_mode; <script>, <style>,
   <xmp>, we did not recognize the end tag unless it was written
   in all lower case.


1999-11-16   Gisle Aas <gisle@aas.no>

   Release 2.99_10

   The mkhctype and mkpfunc scripts were using \z inside RE.  This
   did not work for perl5.004.  Replaced them with plain old
   dollar signs.


1999-11-15   Gisle Aas <gisle@aas.no>

   Release 2.99_09

   Grammar fixes by Michael A. Chase <mchase@ix.netcom.com>

   Some more test suite patches for Win32 by Michael A. Chase
   <mchase@ix.netcom.com>

   Implemented $p->strict_names attribute.  By default we now
   allow almost anything in tag and attribute names.  This is much
   closer to the behaviour of some popular browsers.  This allows us
   to parse broken tags like this example from the LWP mailing list:
   <IMG ALIGN=MIDDLE SRC=newprevlstGr.gif ALT=[PREV LIST] BORDER=0>

   Introduced some tables in "hctype.h" and "pfunc.h".  These
   are built by the corresponding "mk..." script.


1999-11-10   Gisle Aas <gisle@aas.no>

   Release 2.99_08

   Make Parser.xs compile on perl5.004_05 too.

   New callback called 'default'.  This will be called for any
   document text no other callback shows an interest in.

   Patch by Michael A. Chase <mchase@ix.netcom.com> that should
   help clean up files for the test suite on Win32.

   Can now set up various attributes with key/value pairs passed to
   the constructor.

   $p->parse_file() will open the file in binmode()

   Pass complete processing instruction tag as second argument
   to process callback.

   New boolean attribute v2_compat.  This influences how attributes
   are reported for start tags.

   HTML::Filter now filters process instructions too.

   Faster HTML::LinkExtor by taking advantage of the new
   callback interface.  The module now also uses URI.pm (instead
   of the old URI::URL) to absolutize URIs.

   Faster HTML::TokeParser by taking advantage of new
   accum interface.


1999-11-09   Gisle Aas <gisle@aas.no>

   Release 2.99_07

   Entities in attribute values are now always expanded.

   If you set the $p->decode_text_entities to a true value, then
   you don't have to decode the text yourself.

   In xml_mode we don't report empty element tags as a start tag
   with an extra parameter any more.  Instead we generate an artificial
   end tag.

   'xml_mode' now implies 'keep_case'.

   The parser now keeps its own copy of the bool_attr_value value.

   Avoid memory leak for text callbacks

   Avoid using ERROR as a goto label.

   Introduced common internal accessor function for all boolean parser
   attributes.

   Tweaks to make Parser.xs compile under perl5.004.


1999-11-08   Gisle Aas <gisle@aas.no>

   Release 2.99_06

   Internal fast decode_entities().   By using it we are able to make
   the HTML::Entities::decode function 6 times faster than the old one
   implemented in pure Perl.

   $p->bool_attr_value() can be set to influence the value that
   boolean attributes will be assigned.  The default is to assign
   a value identical to the attribute name.

   Process instructions are reported as "PI" in @accum
   
   $p->xml_mode(1) modifies how processing instructions are terminated
   and allows "/>" at the end of start tags.

   Turn off optimizations when compiling with gcc on Solaris.  Avoids
   what we believe to be a compiler bug.  Should probably figure out
   which versions of gcc have this bug.


1999-11-05   Gisle Aas <gisle@aas.no>

   Release 2.99_05

   The previous release did not even compile.  I forgot to try 'make test'
   before uploading.


1999-11-05   Gisle Aas <gisle@aas.no>

   Release 2.99_04

   Generalized <XMP>-support to cover all literal parsing.  Currently
   activated for <script>, <style>, <xmp> and <plaintext>.


1999-11-05   Gisle Aas <gisle@aas.no>

   Release 2.99_03

   <XMP>-support.

   Allow ":" in tag and attribute names

   Include rest of the HTML::* files from the old HTML::Parser
   package.  This should make testing easier.


1999-11-04   Gisle Aas <gisle@aas.no>

   Release 2.99_02

   Implemented keep_case() option.  If this attribute is true, then
   we don't lowercase tag and attribute names.

   Implemented accum() that takes an array reference.  Tokens are
   pushed onto this array instead of sent to callbacks.

   Implemented strict_comment().


1999-11-03   Gisle Aas <gisle@aas.no>

   Release 2.99_01

   Baseline of XS implementation


1999-11-05   Gisle Aas <gisle@aas.no>

   Release 2.25

   Allow ":" in attribute names as a workaround for Microsoft Excel
   2000 which generates such files.

   Make deprecate warning if netscape_buggy_comment() method is
   used.  The method is used in strict_comment().

   Avoid duplication of parse_file() method in HTML::HeadParser.


1999-10-29   Gisle Aas <gisle@aas.no>

   Release 2.24

   $p->parse_file() will not close a handle passed to it any more.
   If passed a filename that can't be opened it will return undef
   instead of raising an exception, and strings like "*STDIN" are not
   treated as globs any more.

   HTML::LinkExtor knows about background attribute of <tables>.
   Patch by Clinton Wong <clintdw@netcom.com>

   HTML::TokeParser will parse large inline strings much faster now.
   The string holding the document must not be changed during parsing.


1999-06-09   Gisle Aas <gisle@aas.no>

   Release 2.23

   Documentation updates.


1998-12-18   Gisle Aas <aas@sn.no>

   Release 2.22

   Protect HTML::HeadParser from evil $SIG{__DIE__} hooks.


1998-11-13   Gisle Aas <aas@sn.no>

   Release 2.21

   HTML::TokeParser can now parse strings directly and does the
   right thing if you pass it a GLOB.  Based on patch by
   Sami Itkonen <si@iki.fi>.

   HTML::Parser now allows space before and after "--" in Netscape
   comments.  Patch by Peter Orbaek <poe@daimi.au.dk>.


1998-07-08   Gisle Aas <aas@sn.no>

   Release 2.20

   Added HTML::TokeParser.  Check it out!


1998-07-07   Gisle Aas <aas@sn.no>

   Release 2.19

   Don't end a text chunk with space when we try to avoid breaking up
   words.


1998-06-22   Gisle Aas <aas@sn.no>

   Release 2.18

   HTML::HeadParser->parse_file will now stop parsing when the
   <body> starts as it should.

   HTML::LinkExtor more easily subclassable by introducing the
   $self->_found_link method.


1998-04-28   Gisle Aas <aas@sn.no>

   Release 2.17

   Never split words (a sequence of non-space) between two invocations
   of $self->text.  This is just a simplification of the code that tried
   not to break entities.
   
   HTML::Parser->parse_file now use smaller chunks as already
   suggested by the HTML::Parser documentation.


1998-04-02   Gisle Aas <aas@sn.no>

   Release 2.16
   
   The HTML::Parser could some times break hex entities (like &#xFFFF;)
   in the middle.

   Removed remaining forced dependencies on libwww-perl modules.  It
   means that all tests should now pass, even if libwww-perl was not
   installed previously.

   More tests.


1998-04-01   Gisle Aas <aas@sn.no>

   Release 2.14, HTML::* modules unbundled from libwww-perl-5.22.
PK       J:1]wfø                    eg/hdumpnu „[µü¤        PK       J:1]¢íà$  $              U  eg/htextnu „[µü¤        PK       J:1]»Ä3#  #              ±  eg/hlcnu „[µü¤        PK       J:1]èÒÍâ²  ²  	            
  eg/htitlenu „[µü¤        PK       J:1]˜ÀB·6  6              õ  eg/hformnu „[µü¤        PK       J:1]ÛÞ	`Þ
  Þ
  
            c  eg/hrefsubnu „[µü¤        PK       J:1]Ü:é*                {  eg/htextsubnu „[µü¤        PK       J:1]$8Lr  r              Ê  eg/hanchorsnu „[µü¤        PK       J:1]Ê¶¦f²  ²  	            w#  eg/hstripnu „[µü¤        PK       J:1]ìMÈt»  »              b*  READMEnu „[µü¤        PK       J:1]j›Š™ÿ  ÿ              S2  TODOnu „[µü¤        PK       J:1]þÎwMìª  ìª              †6  Changesnu „[µü¤        PK      a  ©á    