Группа :: Разработка/Perl
Пакет: perl-XML-TokeParser
навигация по пакетам
Главная Изменения Спек Патчи Исходники Загрузить Gear Bugs and FR Repocop
pax_global_header 0000666 0000000 0000000 00000000064 11325314315 0014510 g ustar 00root root 0000000 0000000 52 comment=0fed155a6414112c5632ec4c6ff2652b75186639
XML-TokeParser-0.05/ 0000755 0000000 0000000 00000000000 11325314315 0014147 5 ustar 00root root 0000000 0000000 XML-TokeParser-0.05/Changes 0000755 0000000 0000000 00000002506 11325314315 0015450 0 ustar 00root root 0000000 0000000 Revision history for Perl extension XML::TokeParser.
0.01 Tue Jan 16 17:59:21 2001
- original version; created by h2xs 1.19
0.02 Mon Jan 29 21:20:00 2001
- fixed bug in unget_token
0.03 Fri Jun 01 06:30:00 2001
- unget_token can now handle partial tokens returned by get_tag
- added begin_saving and restore_saved methods
- fixed bug causing warning when reaching the end of XML passed
in as string reference
- fixed bug preventing Latin conversion for tag and attribute names
0.04 Sat Jul 20 00:10:00 2001
- fixed bugs causing warnings under some circumstances
0.05 Sun Jun 8 08:08:25 2003
- PODMASTER takes over maintenance (with original authors "blessing")
and makes all tokens of type XML::TokeParser::Token
with the following methods:
is_text
is_comment
is_pi which is short for is_process_instruction
is_start_tag
is_end_tag
is_tag
target
data
raw
attr
attrseq
tag
text
** WARNING: The tokens will probably change
as per http://perlmonks.com/index.pl?node_id=264094
which shouldn't affect how you use them.
- more tests, more pod, added TODO
XML-TokeParser-0.05/MANIFEST 0000755 0000000 0000000 00000000272 11325314315 0015304 0 ustar 00root root 0000000 0000000 Changes
Makefile.PL
MANIFEST
TokeParser.pm
README
TODO
TokeParser.xml
t/1.normal.t
t/2.extended.t
META.yml Module meta-data (added by MakeMaker)
XML-TokeParser-0.05/META.yml 0000755 0000000 0000000 00000000455 11325314315 0015427 0 ustar 00root root 0000000 0000000 #XXXXXXX This is a prototype!!! It will change in the future!!! XXXXX#
name: XML-TokeParser
version: 0.05
version_from: TokeParser.pm
installdirs: site
requires:
XML::Parser: 2
distribution_type: module
generated_by: ExtUtils::MakeMaker version 6.10_06
XML-TokeParser-0.05/Makefile.PL 0000755 0000000 0000000 00000000774 11325314315 0016134 0 ustar 00root root 0000000 0000000 use ExtUtils::MakeMaker;
# See lib/ExtUtils/MakeMaker.pm for details of how to influence
# the contents of the Makefile that is written.
my $file = 'TokeParser.pm';
WriteMakefile(
'NAME' => 'XML::TokeParser',
'VERSION_FROM' => $file,
'PREREQ_PM' => {
'XML::Parser' => 2,
},
($] >= 5.005 ? ## Add these new keywords supported since 5.005
(ABSTRACT_FROM => $file, # retrieve abstract from module
AUTHOR => 'D.H. aka PodMaster'
) : ()),
);
XML-TokeParser-0.05/README 0000755 0000000 0000000 00000031217 11325314315 0015036 0 ustar 00root root 0000000 0000000 XML/TokeParser version 0.05
=======================
INSTALLATION
To install this module type the following:
perl Makefile.PL
make
make test
make install
NAME
XML::TokeParser - Simplified interface to XML::Parser
SYNOPSIS
use XML::TokeParser;
#
#parse from file
my $p = XML::TokeParser->new('file.xml')
#
#parse from open handle
open IN, 'file.xml' or die $!;
my $p = XML::TokeParser->new( \*IN, Noempty => 1 );
#
#parse literal text
my $text = '<tag xmlns="http://www.omsdev.com">text</tag>';
my $p = XML::TokeParser->new( \$text, Namespaces => 1 );
#
#read next token
my $token = $p->get_token();
#
#skip to <title> and read text
$p->get_tag('title');
$p->get_text();
#
#read text of next <para>, ignoring any internal markup
$p->get_tag('para');
$p->get_trimmed_text('/para');
#
#process <para> if interesting text
$t = $p->get_tag('para');
$p->begin_saving($t);
if ( $p->get_trimmed_text('/para') =~ /interesting stuff/ ) {
$p->restore_saved();
process_para($p);
}
DESCRIPTION
XML::TokeParser provides a procedural ("pull mode") interface to
XML::Parser in much the same way that Gisle Aas' HTML::TokeParser
provides a procedural interface to HTML::Parser. XML::TokeParser splits
its XML input up into "tokens," each corresponding to an XML::Parser
event.
A token is a bless'd reference to an array whose first element is an
event-type string and whose last element is the literal text of the XML
input that generated the event, with intermediate elements varying
according to the event type.
Each token is an *object* of type XML::TokeParser::Token. Read
"XML::TokeParser::Token" to learn what methods are available for
inspecting the token, and retrieving data from it.
METHODS
$p = XML::TokeParser->new($input, [options])
Creates a new parser, specifying the input source and any options.
If $input is a string, it is the name of the file to parse. If
$input is a reference to a string, that string is the actual text to
parse. If $input is a reference to a typeglob or an IO::Handle
object corresponding to an open file or socket, the text read from
the handle will be parsed.
Options are name=>value pairs and can be any of the following:
Namespaces
If set to a true value, namespace processing is enabled.
ParseParamEnt
This option is passed on to the underlying XML::Parser object;
see that module's documentation for details.
Noempty
If set to a true value, text tokens consisting of only
whitespace (such as those created by indentation and line breaks
in between tags) will be ignored.
Latin
If set to a true value, all text other than the literal text
elements of tokens will be translated into the ISO 8859-1
(Latin-1) character encoding rather than the normal UTF-8
encoding.
Catalog
The value is the URI of a catalog file used to resolve PUBLIC
and SYSTEM identifiers. See XML::Catalog for details.
$token = $p->get_token()
Returns the next token, as an array reference, from the input.
Returns undef if there are no remaining tokens.
$p->unget_token($token,...)
Pushes tokens back so they will be re-read. Useful if you've read
one or more tokens too far. Correctly handles "partial" tokens
returned by get_tag().
$token = $p->get_tag( [$token] )
If no argument given, skips tokens until the next start tag or end
tag token. If an argument is given, skips tokens until the start tag
or end tag (if the argument begins with '/') for the named element.
The returned token does not include an event type code; its first
element is the element name, prefixed by a '/' if the token is for
an end tag.
$text = $p->get_text( [$token] )
If no argument given, returns the text at the current position, or
an empty string if the next token is not a 'T' token. If an argument
is given, gathers up all text between the current position and the
specified start or end tag, stripping out any intervening tags (much
like the way a typical Web browser deals with unknown tags).
$text = $p->get_trimmed_text( [$token] )
Like get_text(), but deletes any leading or trailing whitespaces and
collapses multiple whitespace (including newlines) into single
spaces.
$p->begin_saving( [$token] )
Causes subsequent calls to get_token(), get_tag(), get_text(), and
get_trimmed_text() to save the returned tokens. In conjunction with
restore_saved(), allows you to "back up" within a token stream. If
an argument is supplied, it is placed at the beginning of the list
of saved tokens (useful because you often won't know you want to
begin saving until you've already read the first token you want
saved).
$p->restore_saved()
Pushes all the tokens saved by begin_saving() back onto the token
stream. Stops saving tokens. To cancel saving without backing up,
call begin_saving() and restore_saved() in succession.
XML::TokeParser::Token
A token is a blessed array reference, that you acquire using
"$p->get_token" or "$p->get_tag", and that might look like:
["S", $tag, $attr, $attrseq, $raw]
["E", $tag, $raw]
["T", $text, $raw]
["C", $text, $raw]
["PI", $target, $data, $raw]
If you don't like remembering array indices (you're a real programmer),
you may access the attributes of a token like:
"$t->tag", "$t->attr", "$t->attrseq", "$t->raw", "$t->text",
"$t->target", "$t->data".
****Please note that this may change in the future, where as there will
be 4 token types, XML::TokeParser::Token::StartTag ....
What kind of token is it?
To find out, inspect your token using any of these is_* methods (1 ==
true, 0 == false, d'oh):
is_text
is_comment
is_pi which is short for is_process_instruction
is_start_tag
is_end_tag
is_tag
What's that token made of? To retrieve data from your token, use any of
the following methods, depending on the kind of token you have:
target
only for process instructions
data
only for process instructions
raw for all tokens
attr
only for start tags, returns a hashref ( "print "#link ",
""$t->attr""->{href}" ).
my $attrseq = $t->attrseq
only for start tags, returns an array ref of the keys found in
"$t->attr" in the order they originally appeared in.
my $tagname = $t->tag
only for tags ( "print "opening ", ""$t->tag"" if
""$t->is_start_tag" ).
my $text = $token->text
only for tokens of type text and comment
Here's more detailed info about the tokens.
Start tag
The token has five elements: 'S', the element's name, a reference to
a hash of attribute values keyed by attribute names, a reference to
an array of attribute names in the order in which they appeared in
the tag, and the literal text.
End tag
The token has three elements: 'E', the element's name, and the
literal text.
Character data (text)
The token has three elements: 'T', the parsed text, and the literal
text. All contiguous runs of text are gathered into single tokens;
there will never be two 'T' tokens in a row.
Comment
The token has three elements: 'C', the parsed text of the comment,
and the literal text.
Processing instruction
The token has four elements: 'PI', the target, the data, and the
literal text.
The literal text includes any markup delimiters (pointy brackets,
<![CDATA[, etc.), entity references, and numeric character references
and is in the XML document's original character encoding. All other text
is in UTF-8 (unless the Latin option is set, in which case it's in
ISO-8859-1) regardless of the original encoding, and all entity and
character references are expanded.
If the Namespaces option is set, element and attribute names are
prefixed by their (possibly empty) namespace URIs enclosed in curly
brackets and xmlns:* attributes do not appear in 'S' tokens.
DIFFERENCES FROM HTML::TokeParser
Uses a true XML parser rather than a modified HTML parser.
Text and comment tokens include extracted text as well as literal text.
PI tokens include target and data as well as literal text.
No tokens for declarations.
No "textify" hash.
unget_token correctly handles partial tokens returned by get_tag().
begin_saving() and restore_saved()
EXAMPLES
Example:
use XML::TokeParser;
use strict;
#
my $text = '<tag foo="bar" foy="floy"> some text <!--comment--></tag>';
my $p = XML::TokeParser->new( \$text );
#
print $/;
#
while( defined( my $t = $p->get_token() ) ){
local $\="\n";
print ' raw = ', $t->raw;
#
if( $t->tag ){
print ' tag = ', $t->tag;
#
if( $t->is_start_tag ) {
print ' attr = ', join ',', %{$t->attr};
print ' attrseq = ', join ',', @{$t->attrseq};
}
#
print 'is_tag ', $t->is_tag;
print 'is_start_tag ', $t->is_start_tag;
print 'is_end_tag ', $t->is_end_tag;
}
elsif( $t->is_pi ){
print ' target = ', $t->target;
print ' data = ', $t->data;
print 'is_pi ', $t->is_pi;
}
else {
print ' text = ', $t->text;
print 'is_text ', $t->is_text;
print 'is_comment ', $t->is_comment;
}
#
print $/;
}
__END__
Output:
raw = <tag foo="bar" foy="floy">
tag = tag
attr = foo,bar,foy,floy
attrseq = foo,foy
is_tag 1
is_start_tag 1
is_end_tag 0
raw = some text
text = some text
is_text 1
is_comment 0
raw = <!--comment-->
text = comment
is_text 0
is_comment 1
raw = </tag>
tag = tag
is_tag 1
is_start_tag 0
is_end_tag 1
BUGS
To report bugs, go to
<http://rt.cpan.org/NoAuth/Bugs.html?Dist=XML-TokeParser> or send mail
to <bug-XML-Tokeparser@rt.cpan.org>
AUTHOR
Copyright (c) 2003 D.H. aka PodMaster (current maintainer). Copyright
(c) 2001 Eric Bohlman (original author).
All rights reserved. This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself. If you don't
know what this means, visit <http://perl.com/> or <http://cpan.org/>.
SEE ALSO
HTML::TokeParser, XML::Parser, XML::Catalog, XML::Smart, XML::Twig.
XML-TokeParser-0.05/TODO 0000755 0000000 0000000 00000000477 11325314315 0014652 0 ustar 00root root 0000000 0000000 Here's the TODO list, in no particular order:
- cleanup code, maybe refactor (as per http://perlmonks.com/index.pl?node_id=264094 ).
- XML::Parser will die on bad xml, so I might wrap some calls in eval ...
- Improve test suite (add optional Catalog tests for one).
- Improve documentation (add more examples).
XML-TokeParser-0.05/TokeParser.pm 0000755 0000000 0000000 00000051760 11325314315 0016600 0 ustar 00root root 0000000 0000000 =head1 NAME
XML::TokeParser - Simplified interface to XML::Parser
=head1 SYNOPSIS
use XML::TokeParser;
#
#parse from file
my $p = XML::TokeParser->new('file.xml')
#
#parse from open handle
open IN, 'file.xml' or die $!;
my $p = XML::TokeParser->new( \*IN, Noempty => 1 );
#
#parse literal text
my $text = '<tag xmlns="http://www.omsdev.com">text</tag>';
my $p = XML::TokeParser->new( \$text, Namespaces => 1 );
#
#read next token
my $token = $p->get_token();
#
#skip to <title> and read text
$p->get_tag('title');
$p->get_text();
#
#read text of next <para>, ignoring any internal markup
$p->get_tag('para');
$p->get_trimmed_text('/para');
#
#process <para> if interesting text
$t = $p->get_tag('para');
$p->begin_saving($t);
if ( $p->get_trimmed_text('/para') =~ /interesting stuff/ ) {
$p->restore_saved();
process_para($p);
}
=head1 DESCRIPTION
XML::TokeParser provides a procedural ("pull mode") interface to XML::Parser
in much the same way that Gisle Aas' HTML::TokeParser provides a procedural
interface to HTML::Parser. XML::TokeParser splits its XML input up into
"tokens," each corresponding to an XML::Parser event.
A token is a B<L<bless'd|"XML::TokeParser::Token">> reference to an array whose first element is an event-type
string and whose last element is the literal text of the XML input that
generated the event, with intermediate elements varying according to the
event type.
Each token is an I<object> of type L<XML::TokeParser::Token|"XML::TokeParser::Token">.
Read
L<"XML::TokeParser::Token"|"XML::TokeParser::Token">
to learn what methods are available for inspecting the token,
and retrieving data from it.
=cut
package XML::TokeParser;
use strict;
use vars qw($VERSION);
use Carp;# qw( carp croak );
use XML::Parser;
$VERSION = '0.05';
=head1 METHODS
=over 4
=item $p = XML::TokeParser->new($input, [options])
Creates a new parser, specifying the input source and any options. If
$input is a string, it is the name of the file to parse. If $input is a
reference to a string, that string is the actual text to parse. If $input
is a reference to a typeglob or an IO::Handle object corresponding to an
open file or socket, the text read from the handle will be parsed.
Options are name=>value pairs and can be any of the following:
=over 4
=item Namespaces
If set to a true value, namespace processing is enabled.
=item ParseParamEnt
This option is passed on to the underlying XML::Parser object; see that
module's documentation for details.
=item Noempty
If set to a true value, text tokens consisting of only whitespace (such as
those created by indentation and line breaks in between tags) will be
ignored.
=item Latin
If set to a true value, all text other than the literal text elements of
tokens will be translated into the ISO 8859-1 (Latin-1) character encoding
rather than the normal UTF-8 encoding.
=item Catalog
The value is the URI of a catalog file used to resolve PUBLIC and SYSTEM
identifiers. See XML::Catalog for details.
=back
=cut
sub new {
my $class = shift;
my $source = shift;
my %args = ( Noempty => 0, Latin => 0, Catalog => 0, @_ );
my $self = { output => [], EOF => 0 };
$self->{noempty} = delete $args{Noempty};
$self->{latin} = delete $args{Latin};
my $catname = delete $args{Catalog};
my $parser = XML::Parser->new(%args) or croak "$!";
$parser->setHandlers(
Start => \&start,
End => \&end,
Char => \&char,
Proc => \&proc,
Comment => \&comment
);
if ($catname) {
require XML::Catalog;
my $catalog = XML::Catalog->new($catname) or croak "$!";
$parser->setHandlers( ExternEnt => $catalog->get_handler($parser) );
}
$self->{parser} = $parser->parse_start( TokeParser => $self ) or croak "$!";
if ( ref($source) eq 'SCALAR' ) {
$self->{src} = $source;
$self->{src_offset} = 0;
}
elsif ( ref($source) =~ /^IO:|^GLOB$/ ) {
$self->{srcfile} = $source;
}
else {
require IO::File;
$self->{srcfile} = IO::File->new( $source, 'r' ) or return undef;
$self->{opened} = 1;
}
bless $self, $class;
}
sub DESTROY {
my $self = shift;
$self->{srcfile}->close() if $self->{srcfile} && $self->{opened};
$self->{parser} = undef;
}
=item $token = $p->get_token()
Returns the next token, as an array reference, from the input. Returns
undef if there are no remaining tokens.
=cut
sub get_token {
local $_;
my $self = shift;
$self->parsechunks();
my $token = shift @{ $self->{output} };
while ($self->{noempty}
&& $token
&& $token->[0] eq 'T'
&& $token->[1] =~ /^\s*$/ )
{
$self->parsechunks();
$token = shift @{ $self->{output} };
}
if ( defined $token and exists $self->{savebuff} ) {
push @{ $self->{savebuff} }, [@$token];
}
return() unless defined $token;
bless $token, 'XML::TokeParser::Token';
}
=item $p->unget_token($token,...)
Pushes tokens back so they will be re-read. Useful if you've read one or
more tokens too far. Correctly handles "partial" tokens returned by
get_tag().
=cut
sub unget_token {
my $self = shift;
while ( my $token = pop @_ ) {
if ( @$token == 4 && ref( $token->[1] ) eq 'HASH' ) {
$token = [ 'S', @$token ];
}
elsif ( @$token == 2 && substr( $token->[0], 0, 1 ) eq '/' ) {
$token = [ 'E', substr( $token->[0], 1 ), $token->[1] ];
}
unshift @{ $self->{output} }, $token;
}
}
=item $token = $p->get_tag( [$token] )
If no argument given, skips tokens until the next start tag or end tag
token. If an argument is given, skips tokens until the start tag or end tag
(if the argument begins with '/') for the named element. The returned
token does not include an event type code; its first element is the element
name, prefixed by a '/' if the token is for an end tag.
=cut
sub get_tag {
my ( $self, $tag ) = @_;
my $token;
while ( $token = $self->get_token() ) {
my $type = shift @$token;
next unless $type =~ /[SE]/;
substr( $token->[0], 0, 0 ) = '/' if $type eq 'E';
last unless ( defined($tag) && $token->[0] ne $tag );
}
$token;
}
=item $text = $p->get_text( [$token] )
If no argument given, returns the text at the current position, or an empty
string if the next token is not a 'T' token. If an argument is given,
gathers up all text between the current position and the specified start or
end tag, stripping out any intervening tags (much like the way a typical
Web browser deals with unknown tags).
=cut
sub get_text {
my ( $self, $tag ) = @_;
my $text = "";
my $token;
while ( $token = $self->get_token() ) {
my $type = $token->[0];
if ( $type eq 'T' ) {
$text .= $token->[1];
}
elsif ( $type =~ /[SE]/ ) {
my $tt = $token->[1];
$tt = "/$tt" if $type eq 'E';
last if ( !defined($tag) || $tt eq $tag );
}
elsif ( $type eq 'PI' ) {
last;
}
}
if ($token) {
$self->unget_token($token);
pop @{ $self->{savebuff} } if exists $self->{savebuff};
}
$text;
}
=item $text = $p->get_trimmed_text( [$token] )
Like get_text(), but deletes any leading or trailing whitespaces and
collapses multiple whitespace (including newlines) into single spaces.
=cut
sub get_trimmed_text {
my $self = shift;
my $text = $self->get_text(@_);
$text =~ s/^\s+//;
$text =~ s/\s+$//;
$text =~ s/\s+/ /g;
$text;
}
=item $p->begin_saving( [$token] )
Causes subsequent calls to get_token(), get_tag(), get_text(), and
get_trimmed_text() to save the returned tokens. In conjunction with
restore_saved(), allows you to "back up" within a token stream. If an
argument is supplied, it is placed at the beginning of the list of saved
tokens (useful because you often won't know you want to begin saving until
you've already read the first token you want saved).
=cut
sub begin_saving {
my $self = shift;
delete $self->{savebuff} if exists $self->{savebuff};
$self->{savebuff} = [];
push @{ $self->{savebuff} }, @_ if @_;
}
=item $p->restore_saved()
Pushes all the tokens saved by begin_saving() back onto the token stream.
Stops saving tokens. To cancel saving without backing up, call
begin_saving() and restore_saved() in succession.
=back
=cut
sub restore_saved {
my $self = shift;
if ( exists $self->{savebuff} ) {
$self->unget_token( @{ $self->{savebuff} } );
delete $self->{savebuff};
}
}
=for comment
=cut
sub parsechunks {
my ($self) = @_;
my $buf = '';
while ( ( !@{ $self->{output} } || $self->{output}[-1][0] eq 'T' )
&& !$self->{EOF} )
{
# if (defined($self->{src}) && ($self->{src_offset}<length(${$self->{src}}))) {
# $buf=substr(${$self->{src}},$self->{src_offset},4096);
# $self->{src_offset}+=4096;
# }
if ( defined( $self->{src} ) ) {
if ( $self->{src_offset} < length( ${ $self->{src} } ) ) {
$buf = substr( ${ $self->{src} }, $self->{src_offset}, 4096 );
$self->{src_offset} += 4096;
}
}
else {
read( $self->{srcfile}, $buf, 4096 );
}
if ( length($buf) == 0 ) {
$self->{EOF} = 1;
$self->{parser}->parse_done();
}
else {
$self->{parser}->parse_more($buf);
}
}
}
=for comment Start handler
=cut
sub start {
my ( $parser, $element, @attrs ) = @_;
my $self = $parser->{TokeParser};
push @{ $self->{output} },
[ 'S', $self->nsname($element), {}, [], $parser->original_string() ];
while (@attrs) {
my ( $name, $val ) = ( shift @attrs, shift @attrs );
$name = $self->nsname($name);
$val = $self->encode($val);
$self->{output}[-1][2]{$name} = $val;
push @{ $self->{output}[-1][3] }, $name;
}
}
=for comment End handler
=cut
sub end {
my ( $parser, $element ) = @_;
my $self = $parser->{TokeParser};
push @{ $self->{output} },
[ 'E', $self->nsname($element), $parser->original_string() ];
}
=for comment Char handler
=cut
sub char {
my ( $parser, $text ) = @_;
my $self = $parser->{TokeParser};
$text = $self->encode($text);
if ( @{ $self->{output} } && $self->{output}[-1][0] eq 'T' ) {
$self->{output}[-1][1] .= $text;
$self->{output}[-1][-1] .= $parser->original_string();
}
else {
push @{ $self->{output} }, [ 'T', $text, $parser->original_string() ];
}
}
=for comment
=cut
sub proc {
my ( $parser, $target, $value ) = @_;
my $self = $parser->{TokeParser};
push @{ $self->{output} },
[
"PI", $self->encode($target),
$self->encode($value), $parser->original_string()
];
}
=for comment Comment handler
=cut
sub comment {
my ( $parser, $text ) = @_;
my $self = $parser->{TokeParser};
push @{ $self->{output} },
[ "C", $self->encode($text), $parser->original_string() ];
}
=for comment nsname
figures out the Namespace if Namespaces is on
=cut
sub nsname {
my ( $self, $name ) = @_;
my $parser = $self->{parser};
if ( $parser->{Namespaces} ) {
my $ns = $parser->namespace($name) || '';
$name = "{$ns}" . $name;
}
return $self->encode($name);
}
=for comment
=cut
sub encode {
my ( $self, $text ) = @_;
if ( $self->{latin} ) {
$text =~ s{([\xc0-\xc3])(.)}{
my $hi = ord($1);
my $lo = ord($2);
chr((($hi & 0x03) <<6) | ($lo & 0x3F))
}ge;
}
$text;
}
package XML::TokeParser::Token;
use strict;
=head2 XML::TokeParser::Token
A token is a blessed array reference,
that you acquire using C<$p-E<gt>get_token> or C<$p-E<gt>get_tag>,
and that might look like:
["S", $tag, $attr, $attrseq, $raw]
["E", $tag, $raw]
["T", $text, $raw]
["C", $text, $raw]
["PI", $target, $data, $raw]
If you don't like remembering array indices (you're a real programmer),
you may access the attributes of a token like:
C<$t-E<gt>tag>, C<$t-E<gt>attr>, C<$t-E<gt>attrseq>, C<$t-E<gt>raw>,
C<$t-E<gt>text>, C<$t-E<gt>target>, C<$t-E<gt>data>.
B<****Please note that this may change in the future,>
B<where as there will be 4 token types, XML::TokeParser::Token::StartTag ....>
What kind of token is it?
To find out, inspect your token using any of these is_* methods
(1 == true, 0 == false, d'oh):
=over 4
=item is_text
=item is_comment
=item is_pi which is short for is_process_instruction
=item is_start_tag
=item is_end_tag
=item is_tag
=back
=cut
# test your token, but don't toke
#sub toke { croak "Don't toke!!!!"; }
sub is_text { return 1 if $_[0]->[0] eq 'T'; return 0;}
sub is_comment { return 1 if $_[0]->[0] eq 'C'; return 0;}
sub is_pi { return 1 if $_[0]->[0] eq 'PI'; return 0;}
#sub is_process_instruction { goto &is_pi; }
{
no strict;
*is_process_instruction = *is_pi;
}
sub is_start_tag {
if( $_[0]->[0] eq 'S'
or ( @{$_[0]} == 4 && ref( $_[0]->[1] ) eq 'HASH' )
){
if(defined $_[1]){
return 1 if $_[0]->[1] eq $_[1];
} else {
return 1;
}
}
return 0;
}
sub is_end_tag {
if( $_[0]->[0] eq 'E'
or ( @{$_[0]} == 2 && substr( $_[0]->[0], 0, 1 ) eq '/' )
){
if(defined $_[1]){
return 1 if $_[0]->[1] eq $_[1];
} else {
return 1;
}
}
return 0;
}
sub is_tag {
if( $_[0]->[0] eq 'S'
or $_[0]->[0] eq 'E'
or ( @{$_[0]} == 4 && ref( $_[0]->[1] ) eq 'HASH' )
or ( @{$_[0]} == 2 && substr( $_[0]->[0], 0, 1 ) eq '/' )
){
if( defined $_[1] ){
return 1 if $_[0]->[1] eq $_[1];
} else {
return 1;
}
}
return 0;
}
=pod
What's that token made of?
To retrieve data from your token, use any of the following methods,
depending on the kind of token you have:
=over 4
=item target
only for process instructions
=cut
sub target { return $_[0]->[1] if $_[0]->is_pi; }
=item data
only for process instructions
=cut
sub data { return $_[0]->[2] if $_[0]->is_pi; }
=item raw
for all tokens
=cut
sub raw { return $_[0]->[-1]; }
=item attr
only for start tags, returns a hashref ( C<print "#link ", >C<$t-E<gt>attr>C<-E<gt>{href}> ).
=cut
#sub attr { return $_[0]->[2] if $_[0]->is_start_tag(); }
sub attr { return $_[0]->[-3] if $_[0]->is_start_tag(); }
=item my $attrseq = $t->attrseq
only for start tags, returns an array ref of the keys found in C<$t-E<gt>attr>
in the order they originally appeared in.
=cut
#sub attrseq { return $_[0]->[3] if $_[0]->is_start_tag(); }
sub attrseq { return $_[0]->[-2] if $_[0]->is_start_tag(); }
#for S|E
=item my $tagname = $t->tag
only for tags ( C<print "opening ", >C<$t-E<gt>tag>C< if >C<$t-E<gt>is_start_tag> ).
=cut
sub tag { return $_[0]->[1] if $_[0]->is_tag; }
=item my $text = $token->text
only for tokens of type text and comment
=back
=cut
sub text { return $_[0]->[1] if $_[0]->is_text or $_[0]->is_comment; }
1;
=pod
Here's more detailed info about the tokens.
=over 4
=item Start tag
The token has five elements: 'S', the element's name, a reference to a hash
of attribute values keyed by attribute names, a reference to an array of
attribute names in the order in which they appeared in the tag, and the
literal text.
=item End tag
The token has three elements: 'E', the element's name, and the literal text.
=item Character data (text)
The token has three elements: 'T', the parsed text, and the literal text.
All contiguous runs of text are gathered into single tokens; there will
never be two 'T' tokens in a row.
=item Comment
The token has three elements: 'C', the parsed text of the comment, and the
literal text.
=item Processing instruction
The token has four elements: 'PI', the target, the data, and the literal
text.
=back
The literal text includes any markup delimiters (pointy brackets,
<![CDATA[, etc.), entity references, and numeric character references and
is in the XML document's original character encoding. All other text is in
UTF-8 (unless the Latin option is set, in which case it's in ISO-8859-1)
regardless of the original encoding, and all entity and character
references are expanded.
If the Namespaces option is set, element and attribute names are prefixed
by their (possibly empty) namespace URIs enclosed in curly brackets and
xmlns:* attributes do not appear in 'S' tokens.
=head1 DIFFERENCES FROM HTML::TokeParser
Uses a true XML parser rather than a modified HTML parser.
Text and comment tokens include extracted text as well as literal text.
PI tokens include target and data as well as literal text.
No tokens for declarations.
No "textify" hash.
unget_token correctly handles partial tokens returned by get_tag().
begin_saving() and restore_saved()
=head1 EXAMPLES
Example:
use XML::TokeParser;
use strict;
#
my $text = '<tag foo="bar" foy="floy"> some text <!--comment--></tag>';
my $p = XML::TokeParser->new( \$text );
#
print $/;
#
while( defined( my $t = $p->get_token() ) ){
local $\="\n";
print ' raw = ', $t->raw;
#
if( $t->tag ){
print ' tag = ', $t->tag;
#
if( $t->is_start_tag ) {
print ' attr = ', join ',', %{$t->attr};
print ' attrseq = ', join ',', @{$t->attrseq};
}
#
print 'is_tag ', $t->is_tag;
print 'is_start_tag ', $t->is_start_tag;
print 'is_end_tag ', $t->is_end_tag;
}
elsif( $t->is_pi ){
print ' target = ', $t->target;
print ' data = ', $t->data;
print 'is_pi ', $t->is_pi;
}
else {
print ' text = ', $t->text;
print 'is_text ', $t->is_text;
print 'is_comment ', $t->is_comment;
}
#
print $/;
}
__END__
Output:
raw = <tag foo="bar" foy="floy">
tag = tag
attr = foo,bar,foy,floy
attrseq = foo,foy
is_tag 1
is_start_tag 1
is_end_tag 0
raw = some text
text = some text
is_text 1
is_comment 0
raw = <!--comment-->
text = comment
is_text 0
is_comment 1
raw = </tag>
tag = tag
is_tag 1
is_start_tag 0
is_end_tag 1
=head1 BUGS
To report bugs, go to
E<lt>http://rt.cpan.org/NoAuth/Bugs.html?Dist=XML-TokeParserE<gt>
or send mail to E<lt>bug-XML-Tokeparser@rt.cpan.orgE<gt>
=head1 AUTHOR
Copyright (c) 2003 D.H. aka PodMaster (current maintainer).
Copyright (c) 2001 Eric Bohlman (original author).
All rights reserved.
This program is free software;
you can redistribute it and/or modify it
under the same terms as Perl itself.
If you don't know what this means,
visit E<lt>http://perl.com/E<gt> or E<lt>http://cpan.org/E<gt>.
=head1 SEE ALSO
L<HTML::TokeParser>,
L<XML::Parser>,
L<XML::Catalog>,
L<XML::Smart>,
L<XML::Twig>.
=cut
XML-TokeParser-0.05/TokeParser.xml 0000755 0000000 0000000 00000017303 11325314315 0016757 0 ustar 00root root 0000000 0000000 <?xml version='1.0' encoding='iso-8859-1'?>
<pod xmlns="http://axkit.org/ns/2000/pod2xml">
<head>
<title>XML::TokeParser - Simplified interface to XML::Parser</title>
</head>
<sect1>
<title>SYNOPSIS</title>
<verbatim><![CDATA[
use XML::TokeParser;
]]></verbatim>
<verbatim><![CDATA[
#parse from file
my $p=XML::TokeParser->new('file.xml')
]]></verbatim>
<verbatim><![CDATA[
#parse from open handle
open IN,'file.xml' or die $!;
my $p=XML::TokeParser->new(\*IN,Noempty=>1);
]]></verbatim>
<verbatim><![CDATA[
#parse literal text
my $text='<tag xmlns="http://www.omsdev.com">text</tag>';
my $p=XML::TokeParser->new(\$text,Namespaces=>1);
]]></verbatim>
<verbatim><![CDATA[
#read next token
my $token=$p->get_token();
]]></verbatim>
<verbatim><![CDATA[
#skip to <title> and read text
$p->get_tag('title');
$p->get_text();
]]></verbatim>
<verbatim><![CDATA[
#read text of next <para>, ignoring any internal markup
$p->get_tag('para');
$p->get_trimmed_text('/para');
]]></verbatim>
</sect1>
<sect1>
<title>DESCRIPTION</title>
<para>
XML::TokeParser provides a procedural ("pull mode") interface to XML::Parser
in much the same way that Gisle Aas' HTML::TokeParser provides a procedural
interface to HTML::Parser. XML::TokeParser splits its XML input up into
"tokens," each corresponding to an XML::Parser event.
</para>
<para>
A token is a reference to an array whose first element is an event-type
string and whose last element is the literal text of the XML input that
generated the event, with intermediate elements varying according to the
event type:
</para>
<list>
<item><itemtext>Start tag</itemtext>
<para>
The token has five elements: 'S', the element's name, a reference to a hash
of attribute values keyed by attribute names, a reference to an array of
attribute names in the order in which they appeared in the tag, and the
literal text.
</para>
</item>
<item><itemtext>End tag</itemtext>
<para>
The token has three elements: 'E', the element's name, and the literal text.
</para>
</item>
<item><itemtext>Character data (text)</itemtext>
<para>
The token has three elements: 'T', the parsed text, and the literal text.
All contiguous runs of text are gathered into single tokens; there will
never be two 'T' tokens in a row.
</para>
</item>
<item><itemtext>Comment</itemtext>
<para>
The token has three elements: 'C', the parsed text of the comment, and the
literal text.
</para>
</item>
<item><itemtext>Processing instruction</itemtext>
<para>
The token has four elements: 'PI', the target, the data, and the literal
text.
</para>
</item>
</list>
<para>
The literal text includes any markup delimiters (pointy brackets,
<![CDATA[, etc.), entity references, and numeric character references and
is in the XML document's original character encoding. All other text is in
UTF-8 (unless the Latin option is set, in which case it's in ISO-8859-1)
regardless of the original encoding, and all entity and character
references are expanded.
</para>
<para>
If the Namespaces option is set, element and attribute names are prefixed
by their (possibly empty) namespace URIs enclosed in curly brackets and
xmlns:* attributes do not appear in 'S' tokens.
</para>
</sect1>
<sect1>
<title>METHODS</title>
<list>
<item><itemtext>$p = XML::TokeParser->new($input, [options])</itemtext>
<para>
Creates a new parser, specifying the input source and any options. If
$input is a string, it is the name of the file to parse. If $input is a
reference to a string, that string is the actual text to parse. If $input
is a reference to a typeglob or an IO::Handle object corresponding to an
open file or socket, the text read from the handle will be parsed.
</para>
<para>
Options are name=>value pairs and can be any of the following:
</para>
</item>
<list>
<item><itemtext>Namespaces</itemtext>
<para>
If set to a true value, namespace processing is enabled.
</para>
</item>
<item><itemtext>ParseParamEnt</itemtext>
<para>
This option is passed on to the underlying XML::Parser object; see that
module's documentation for details.
</para>
</item>
<item><itemtext>Noempty</itemtext>
<para>
If set to a true value, text tokens consisting of only whitespace (such as
those created by indentation and line breaks in between tags) will be
ignored.
</para>
</item>
<item><itemtext>Latin</itemtext>
<para>
If set to a true value, all text other than the literal text elements of
tokens will be translated into the ISO 8859-1 (Latin-1) character encoding
rather than the normal UTF-8 encoding.
</para>
</item>
<item><itemtext>Catalog</itemtext>
<para>
The value is the URI of a catalog file used to resolve PUBLIC and SYSTEM
identifiers. See XML::Catalog for details.
</para>
</item>
</list>
<item><itemtext>$token = $p->get_token()</itemtext>
<para>
Returns the next token, as an array reference, from the input. Returns
undef if there are no remaining tokens.
</para>
</item>
<item><itemtext>$p->unget_token($token,...)</itemtext>
<para>
Pushes tokens back so they will be re-read. Useful if you've read one or
more tokens to far.
</para>
</item>
<item><itemtext>$token = $p->get_tag( [$token] )</itemtext>
<para>
If no argument given, skips tokens until the next start tag or end tag
token. If an argument is given, skips tokens until the start tag or end tag
(if the argument begins with '/') for the named element. The returned
token does not include an event type code; its first element is the element
name, prefixed by a '/' if the token is for an end tag.
</para>
</item>
<item><itemtext>$text = $p->get_text( [$token] )</itemtext>
<para>
If no argument given, returns the text at the current position, or an empty
string if the next token is not a 'T' token. If an argument is given,
gathers up all text between the current position and the specified start or
end tag, stripping out any intervening tags (much like the way a typical
Web browser deals with unknown tags).
</para>
</item>
<item><itemtext>$text = $p->get_trimmed_text( [$token])</itemtext>
<para>
Like get_text(), but deletes any leading or trailing whitespaces and
collapses multiple whitespace (including newlines) into single spaces.
</para>
</item>
</list>
</sect1>
<sect1>
<title>DIFFERENCES FROM HTML::TokeParser</title>
<para>
Uses a true XML parser rather than a modified HTML parser.
</para>
<para>
Text and comment tokens include extracted text as well as literal text.
</para>
<para>
PI tokens include target and data as well as literal text.
</para>
<para>
No tokens for declarations.
</para>
<para>
No "textify" hash.
</para>
</sect1>
<sect1>
<title>EXAMPLES</title>
<sect2>
<title>Print method signatures from the XML version of this PODpage</title>
<verbatim><![CDATA[
#!/usr/bin/perl -w
use strict;
use XML::TokeParser;
my $t;
my $p=XML::TokeParser->new('tokeparser.xml',Noempty=>1) or die $!;
while ($p->get_tag('title') && $p->get_text('/title') ne 'METHODS') {
;
}
$p->get_tag('list');
while (($t=$p->get_tag()->[0]) ne '/list') {
if ($t eq 'item') {
$p->get_tag('itemtext');
print $p->get_text('/itemtext'),"\n";
$p->get_tag('/item');
}
else {
$p->get_tag('/list'); # assumes no nesting here!
}
}
]]></verbatim>
</sect2>
</sect1>
<sect1>
<title>AUTHOR</title>
<para>
Eric Bohlman (ebohlman@omsdev.com)
</para>
<para>
Copyright (c) 2001 Eric Bohlman. All rights reserved. This program
is free software; you can redistribute it and/or modify it under the same
terms as Perl itself.
</para>
</sect1>
<sect1>
<title>SEE ALSO</title>
<verbatim><![CDATA[
XML::Parser
XML::Catalog
HTML::TokeParser
]]></verbatim>
</sect1>
</pod>
XML-TokeParser-0.05/t/ 0000755 0000000 0000000 00000000000 11325314315 0014412 5 ustar 00root root 0000000 0000000 XML-TokeParser-0.05/t/1.normal.t 0000755 0000000 0000000 00000006560 11325314315 0016240 0 ustar 00root root 0000000 0000000 # Before `make install' is performed this script should be runnable with
# `make test'. After `make install' it should work as `perl test.pl'
#print "#",q[],"\n";
#print "#",q[],"\n";
#print "#",q[],"\n";
use Test;
BEGIN { plan tests => 34, todo => [] }
use XML::TokeParser;
ok(1);
#parse from file
my $p = XML::TokeParser->new('TokeParser.xml');
ok($p);
my @tokens = (
[
'S',
qq[\Q<pod xmlns="http://axkit.org/ns/2000/pod2xml">]
],
[
'T',
'\s+'
],
[
'S',
qq[\Q<head>]
],
[
'T',
'\s+'
],
[
'S',
qq[\Q<title>]
],
[
'T',
qq[\QXML::TokeParser - Simplified interface to XML::Parser]
],
[
'E',
qq[\Q</title>]
],
[
'T',
'\s+'
],
[
'E',
qq[\Q</head>]
],
[
'T',
'\s+'
],
[
'S',
qq[\Q<sect1>]
],
[
'T',
'\s+'
],
[
'S',
qq[\Q<title>]
],
[
'T',
qq[\QSYNOPSIS]
],
[
'E',
qq[\Q</title>]
],
[
'T',
'\s+'
],
[
'S',
qq[\Q<verbatim>]
],
[
'T',
qq[\Quse XML::TokeParser;]
],
[
'E',
qq[\Q</verbatim>]
],
[
'T',
'\s+'
]
);
for( 0.. $#tokens ) {
my $token = $p->get_token();
ok(2+$_) if $tokens[$_][0] eq $token->[0] and $token->[-1] =~ m{$tokens[$_][1]};
}
print "#",q[],"\n";
print "#",q[ Now testing get_tag, get_trimmed_text],"\n";
ok( $p->get_tag('title') );
print "#",q[$p->get_tag('title')],"\n";
ok( $p->get_trimmed_text('/title') eq 'DESCRIPTION' );
print "#",q[$p->get_trimmed_text('/title')],"\n";
ok( $p->get_tag('item') );
print "#",q[$p->get_tag('item')],"\n";
ok( $p->get_tag('itemtext') );
print "#",q[$p->get_tag('itemtext')],"\n";
ok( $p->get_trimmed_text('/itemtext') eq 'Start tag' );
print "#",q[$p->get_trimmed_text('/itemtext')],"\n";
print "#",q[],"\n";
print "#",q[ Now testing saving tokens so you can go return to this point in the stream],"\n";
ok( not $p->begin_saving() );
print "#",q[$p->begin_saving() ],"\n";
ok( $p->get_tag('para') );
print "#",q[$p->get_tag('para') 1],"\n";
ok( $p->get_tag('para') );
print "#",q[$p->get_tag('para') 2],"\n";
ok( $p->restore_saved() );
print "#",q[$p->restore_saved()],"\n";
print "#",q[],"\n";
print "#",q[ Now to see if we've backed up correctly (i think so)],"\n";
ok( $p->get_tag('para') );
print "#",q[$p->get_tag('para') 1],"\n";
ok( $p->get_tag('para') );
print "#",q[$p->get_tag('para') 2],"\n";
ok( $p->get_trimmed_text('/para') eq "The token has three elements: 'E', the element's name, and the literal text." );
#use Data::Dumper;die Dumper( );
#push @tokens, $p->get_token() for 1..10;use Data::Dumper;die Dumper\@tokens;
XML-TokeParser-0.05/t/2.extended.t 0000755 0000000 0000000 00000004720 11325314315 0016545 0 ustar 00root root 0000000 0000000 # Before `make install' is performed this script should be runnable with
# `make test'. After `make install' it should work as `perl test.pl'
#print "#",q[],"\n";
#print "#",q[],"\n";
#print "#",q[],"\n";
use Test;
BEGIN { plan tests => 42, todo => [] }
use XML::TokeParser;
ok(1);
#parse from file
my $p = XML::TokeParser->new('TokeParser.xml');
ok($p);
my @tokens =(
'S',
'T',
'S',
'T',
'S',
'T',
'E',
'T',
'E',
'T',
'S',
'T',
'S',
'T',
'E',
'T',
'S',
'T',
'E',
'T',
'S',
'T',
'E',
'T',
'S',
'T',
'E',
'T',
'S',
'T',
'E',
'T',
'S',
'T',
'E',
'T',
'S',
'T',
'E',
'T'
);
my %Token2Method = (
S => 'is_start_tag',
E => 'is_end_tag',
T => 'is_text',
C => 'is_comment',
PI => 'is_pi',
);
print "#",q[],"\n";
#push @tokens, ( $p->get_token() )->[0] for 1..40;use Data::Dumper;die Dumper\@tokens;
for( 0.. $#tokens ) {
my $token = $p->get_token();
#use Data::Dumper;print Dumper $token;
my $method = $Token2Method{$token->[0]} || 'is_tag';
print '#$ ', $token->$method() ,$/;
print '#$ ', $token->is_start_tag(),$/;
ok( $token->$method() );
}
#$p->get_token()->toke;
__END__
sub is_start_tag {
if( $_[0]->[0] eq 'S' ){
if(defined $_[1]){
return 1 if $_[0]->[1] eq $_[1];
} else {
return 1;
}
}
}
sub is_end_tag {
if( $_[0]->[0] eq 'E' ){
if(defined $_[1]){
return 1 if $_[0]->[1] eq $_[1];
} else {
return 1;
}
}
}
sub is_tag {
if( $_[0]->[0] eq 'S' or $_[0]->[0] eq 'E' ){
if(defined $_[1]){
return 1 if $_[0]->[1] eq $_[1];
} else {
return 1;
}
}
}
## the old ones
sub is_start_tag { return $_[0]->_is( S => $_[1] ); }
sub is_end_tag { return $_[0]->_is( E => $_[1] ); }
sub is_tag { return $_[0]->_is( S => $_[1] )
|| $_[0]->_is( E => $_[1] ); }
sub _is {
if($_[0]->[0] eq $_[1]){
if(defined $_[2]){
return 1 if $_[0]->[1] eq $_[2];
}else{
return 1;
}
}
return 0;
}