expat.pm

来自「one of the linux gd libraries」· PM 代码 · 共 1,231 行 · 第 1/3 页

      }
    }
  }
  $text;
}

sub skip_until {
  my $self = shift;
  if ($self->{_State_} <= 1) {
    SkipUntil($self->{Parser}, $_[0]);
  }
}

sub release {
  my $self = shift;
  ParserRelease($self->{Parser});
}

sub DESTROY {
  my $self = shift;
  ParserFree($self->{Parser});
}

sub parse {
  my $self = shift;
  my $arg = shift;
  croak "Parse already in progress (Expat)" if $self->{_State_};
  $self->{_State_} = 1;
  my $parser = $self->{Parser};
  my $ioref;
  my $result = 0;
  
  if (defined $arg) {
    if (ref($arg) and UNIVERSAL::isa($arg, 'IO::Handle')) {
      $ioref = $arg;
    } elsif (tied($arg)) {
      my $class = ref($arg);
      no strict 'refs';
      $ioref = $arg if defined &{"${class}::TIEHANDLE"};
    }
    else {
      require IO::Handle;
      eval {
        no strict 'refs';
        $ioref = *{$arg}{IO} if defined *{$arg};
      };
      undef $@;
    }
  }
  
  if (defined($ioref)) {
    my $delim = $self->{Stream_Delimiter};
    my $prev_rs;
    
    $prev_rs = ref($ioref)->input_record_separator("\n$delim\n")
      if defined($delim);
    
    $result = ParseStream($parser, $ioref, $delim);
    
    ref($ioref)->input_record_separator($prev_rs)
      if defined($delim);
  } else {
    $result = ParseString($parser, $arg);
  }
  
  $self->{_State_} = 2;
  $result or croak $self->{ErrorMessage};
}

sub parsestring {
  my $self = shift;
  $self->parse(@_);
}

sub parsefile {
  my $self = shift;
  croak "Parser has already been used" if $self->{_State_};
  local(*FILE);
  open(FILE, $_[0]) or  croak "Couldn't open $_[0]:\n$!";
  binmode(FILE);
  my $ret = $self->parse(*FILE);
  close(FILE);
  $ret;
}

################################################################
package XML::Parser::ContentModel;
use overload '""' => \&asString, 'eq' => \&thiseq;

sub EMPTY  () {1}
sub ANY    () {2}
sub MIXED  () {3}
sub NAME   () {4}
sub CHOICE () {5}
sub SEQ    () {6}


sub isempty {
  return $_[0]->{Type} == EMPTY;
}

sub isany {
  return $_[0]->{Type} == ANY;
}

sub ismixed {
  return $_[0]->{Type} == MIXED;
}

sub isname {
  return $_[0]->{Type} == NAME;
}

sub name {
  return $_[0]->{Tag};
}

sub ischoice {
  return $_[0]->{Type} == CHOICE;
}

sub isseq {
  return $_[0]->{Type} == SEQ;
}

sub quant {
  return $_[0]->{Quant};
}

sub children {
  my $children = $_[0]->{Children};
  if (defined $children) {
    return @$children;
  }
  return undef;
}

sub asString {
  my ($self) = @_;
  my $ret;

  if ($self->{Type} == NAME) {
    $ret = $self->{Tag};
  }
  elsif ($self->{Type} == EMPTY) {
    return "EMPTY";
  }
  elsif ($self->{Type} == ANY) {
    return "ANY";
  }
  elsif ($self->{Type} == MIXED) {
    $ret = '(#PCDATA';
    foreach (@{$self->{Children}}) {
      $ret .= '|' . $_;
    }
    $ret .= ')';
  }
  else {
    my $sep = $self->{Type} == CHOICE ? '|' : ',';
    $ret = '(' . join($sep, map { $_->asString } @{$self->{Children}}) . ')';
  }

  $ret .= $self->{Quant} if $self->{Quant};
  return $ret;
}

sub thiseq {
  my $self = shift;

  return $self->asString eq $_[0];
}

################################################################
package XML::Parser::ExpatNB;

use vars qw(@ISA);
use Carp;

@ISA = qw(XML::Parser::Expat);

sub parse {
  my $self = shift;
  my $class = ref($self);
  croak "parse method not supported in $class";
}

sub parsestring {
  my $self = shift;
  my $class = ref($self);
  croak "parsestring method not supported in $class";
}

sub parsefile {
  my $self = shift;
  my $class = ref($self);
  croak "parsefile method not supported in $class";
}

sub parse_more {
  my ($self, $data) = @_;

  $self->{_State_} = 1;
  my $ret = XML::Parser::Expat::ParsePartial($self->{Parser}, $data);

  croak $self->{ErrorMessage} unless $ret;
}

sub parse_done {
  my $self = shift;

  my $ret = XML::Parser::Expat::ParseDone($self->{Parser});
  unless ($ret) {
    my $msg = $self->{ErrorMessage};
    $self->release;
    croak $msg;
  }

  $self->{_State_} = 2;

  my $result = $ret;
  my @result = ();
  my $final = $self->{FinalHandler};
  if (defined $final) {
    if (wantarray) {
      @result = &$final($self);
    }
    else {
      $result = &$final($self);
    }
  }

  $self->release;

  return unless defined wantarray;
  return wantarray ? @result : $result;
}

################################################################

package XML::Parser::Encinfo;

sub DESTROY {
  my $self = shift;
  XML::Parser::Expat::FreeEncoding($self);
}

1;

__END__

=head1 NAME

XML::Parser::Expat - Lowlevel access to James Clark's expat XML parser

=head1 SYNOPSIS

 use XML::Parser::Expat;

 $parser = new XML::Parser::Expat;
 $parser->setHandlers('Start' => \&sh,
                      'End'   => \&eh,
                      'Char'  => \&ch);
 open(FOO, 'info.xml') or die "Couldn't open";
 $parser->parse(*FOO);
 close(FOO);
 # $parser->parse('<foo id="me"> here <em>we</em> go </foo>');

 sub sh
 {
   my ($p, $el, %atts) = @_;
   $p->setHandlers('Char' => \&spec)
     if ($el eq 'special');
   ...
 }

 sub eh
 {
   my ($p, $el) = @_;
   $p->setHandlers('Char' => \&ch)  # Special elements won't contain
     if ($el eq 'special');         # other special elements
   ...
 } 

=head1 DESCRIPTION

This module provides an interface to James Clark's XML parser, expat. As in
expat, a single instance of the parser can only parse one document. Calls
to parsestring after the first for a given instance will die.

Expat (and XML::Parser::Expat) are event based. As the parser recognizes
parts of the document (say the start or end of an XML element), then any
handlers registered for that type of an event are called with suitable
parameters.

=head1 METHODS

=over 4

=item new

This is a class method, the constructor for XML::Parser::Expat. Options are
passed as keyword value pairs. The recognized options are:

=over 4

=item * ProtocolEncoding

The protocol encoding name. The default is none. The expat built-in
encodings are: C<UTF-8>, C<ISO-8859-1>, C<UTF-16>, and C<US-ASCII>.
Other encodings may be used if they have encoding maps in one of the
directories in the @Encoding_Path list. Setting the protocol encoding
overrides any encoding in the XML declaration.

=item * Namespaces

When this option is given with a true value, then the parser does namespace
processing. By default, namespace processing is turned off. When it is
turned on, the parser consumes I<xmlns> attributes and strips off prefixes
from element and attributes names where those prefixes have a defined
namespace. A name's namespace can be found using the L<"namespace"> method
and two names can be checked for absolute equality with the L<"eq_name">
method.

=item * NoExpand

Normally, the parser will try to expand references to entities defined in
the internal subset. If this option is set to a true value, and a default
handler is also set, then the default handler will be called when an
entity reference is seen in text. This has no effect if a default handler
has not been registered, and it has no effect on the expansion of entity
references inside attribute values.

=item * Stream_Delimiter

This option takes a string value. When this string is found alone on a line
while parsing from a stream, then the parse is ended as if it saw an end of
file. The intended use is with a stream of xml documents in a MIME multipart
format. The string should not contain a trailing newline.

=item * ErrorContext

When this option is defined, errors are reported in context. The value
of ErrorContext should be the number of lines to show on either side of
the line in which the error occurred.

=item * ParseParamEnt

Unless standalone is set to "yes" in the XML declaration, setting this to
a true value allows the external DTD to be read, and parameter entities
to be parsed and expanded.

=item * Base

The base to use for relative pathnames or URLs. This can also be done by
using the base method.

=back

=item setHandlers(TYPE, HANDLER [, TYPE, HANDLER [...]])

This method registers handlers for the various events. If no handlers are
registered, then a call to parsestring or parsefile will only determine if
the corresponding XML document is well formed (by returning without error.)
This may be called from within a handler, after the parse has started.

Setting a handler to something that evaluates to false unsets that
handler.

This method returns a list of type, handler pairs corresponding to the
input. The handlers returned are the ones that were in effect before the
call to setHandlers.

The recognized events and the parameters passed to the corresponding
handlers are:

=over 4

=item * Start             (Parser, Element [, Attr, Val [,...]])

This event is generated when an XML start tag is recognized. Parser is
an XML::Parser::Expat instance. Element is the name of the XML element that
is opened with the start tag. The Attr & Val pairs are generated for each
attribute in the start tag.

=item * End               (Parser, Element)

This event is generated when an XML end tag is recognized. Note that
an XML empty tag (<foo/>) generates both a start and an end event.

There is always a lower level start and end handler installed that wrap
the corresponding callbacks. This is to handle the context mechanism.
A consequence of this is that the default handler (see below) will not
see a start tag or end tag unless the default_current method is called.

=item * Char              (Parser, String)

This event is generated when non-markup is recognized. The non-markup
sequence of characters is in String. A single non-markup sequence of
characters may generate multiple calls to this handler. Whatever the
encoding of the string in the original document, this is given to the
handler in UTF-8.

=item * Proc              (Parser, Target, Data)

This event is generated when a processing instruction is recognized.

=item * Comment           (Parser, String)

This event is generated when a comment is recognized.

=item * CdataStart        (Parser)