/usr/share/perl5/XML/XPath/XMLParser.pm is in libxml-xpath-perl 1.42-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 | package XML::XPath::XMLParser;
$VERSION = '1.42';
use strict; use warnings;
use XML::Parser;
use XML::XPath::Node;
use XML::XPath::Node::Element;
use XML::XPath::Node::Text;
use XML::XPath::Node::Comment;
use XML::XPath::Node::PI;
use XML::XPath::Node::Attribute;
use XML::XPath::Node::Namespace;
my @options = qw(
filename
xml
parser
ioref
);
my ($_current, $_namespaces_on);
my %IdNames;
use vars qw/$xmlns_ns $xml_ns/;
$xmlns_ns = "http://www.w3.org/2000/xmlns/";
$xml_ns = "http://www.w3.org/XML/1998/namespace";
sub new {
my $proto = shift;
my $class = ref($proto) || $proto;
my %args = @_;
my %hash = map(( "_$_" => $args{$_} ), @options);
bless \%hash, $class;
}
sub parse {
my $self = shift;
$self->{IdNames} = {};
$self->{InScopeNamespaceStack} = [ {
'_Default' => undef,
'xmlns' => $xmlns_ns,
'xml' => $xml_ns,
} ];
$self->{NodeStack} = [ ];
$self->set_xml($_[0]) if $_[0];
my $parser = $self->get_parser || XML::Parser->new(
ErrorContext => 2,
ParseParamEnt => $XML::XPath::ParseParamEnt,
);
$parser->setHandlers(
Init => sub { $self->parse_init(@_) },
Char => sub { $self->parse_char(@_) },
Start => sub { $self->parse_start(@_) },
End => sub { $self->parse_end(@_) },
Final => sub { $self->parse_final(@_) },
Proc => sub { $self->parse_pi(@_) },
Comment => sub { $self->parse_comment(@_) },
Attlist => sub { $self->parse_attlist(@_) },
);
my $toparse;
if ($toparse = $self->get_filename) {
return $parser->parsefile($toparse);
}
else {
return $parser->parse($self->get_xml || $self->get_ioref);
}
}
sub parsefile {
my $self = shift;
my ($filename) = @_;
$self->set_filename($filename);
$self->parse;
}
sub parse_init {
my $self = shift;
my $e = shift;
my $document = XML::XPath::Node::Element->new();
my $newns = XML::XPath::Node::Namespace->new('xml', $xml_ns);
$document->appendNamespace($newns);
$self->{current} = $self->{DOC_Node} = $document;
}
sub parse_final {
my $self = shift;
return $self->{DOC_Node};
}
sub parse_char {
my $self = shift;
my $e = shift;
my $text = shift;
my $parent = $self->{current};
my $last = $parent->getLastChild;
if ($last && $last->isTextNode) {
# append to previous text node
$last->appendText($text);
return;
}
my $node = XML::XPath::Node::Text->new($text);
$parent->appendChild($node, 1);
}
sub parse_start {
my $self = shift;
my $e = shift;
my $tag = shift;
push @{ $self->{InScopeNamespaceStack} },
{ %{ $self->{InScopeNamespaceStack}[-1] } };
$self->_scan_namespaces(@_);
my ($prefix, $namespace) = $self->_namespace($tag);
my $node = XML::XPath::Node::Element->new($tag, $prefix);
my @attributes;
for (my $ii = 0; $ii < $#_; $ii += 2) {
my ($name, $value) = ($_[$ii], $_[$ii+1]);
if ($name =~ /^xmlns(:(.*))?$/) {
# namespace node
my $prefix = $2 || '#default';
# warn "Creating NS node: $prefix = $value\n";
my $newns = XML::XPath::Node::Namespace->new($prefix, $value);
$node->appendNamespace($newns);
}
else {
my ($prefix, $namespace) = $self->_namespace($name);
undef $namespace unless $prefix;
my $newattr = XML::XPath::Node::Attribute->new($name, $value, $prefix);
$node->appendAttribute($newattr, 1);
if (exists($self->{IdNames}{$tag}) && ($self->{IdNames}{$tag} eq $name)) {
# warn "appending Id Element: $val for ", $node->getName, "\n";
$self->{DOC_Node}->appendIdElement($value, $node);
}
}
}
$self->{current}->appendChild($node, 1);
$self->{current} = $node;
}
sub parse_end {
my $self = shift;
my $e = shift;
$self->{current} = $self->{current}->getParentNode;
}
sub parse_pi {
my $self = shift;
my $e = shift;
my ($target, $data) = @_;
my $node = XML::XPath::Node::PI->new($target, $data);
$self->{current}->appendChild($node, 1);
}
sub parse_comment {
my $self = shift;
my $e = shift;
my ($data) = @_;
my $node = XML::XPath::Node::Comment->new($data);
$self->{current}->appendChild($node, 1);
}
sub parse_attlist {
my $self = shift;
my $e = shift;
my ($elname, $attname, $type, $default, $fixed) = @_;
if ($type eq 'ID') {
$self->{IdNames}{$elname} = $attname;
}
}
sub _scan_namespaces {
my ($self, %attributes) = @_;
while (my ($attr_name, $value) = each %attributes) {
if ($attr_name eq 'xmlns') {
$self->{InScopeNamespaceStack}[-1]{'_Default'} = $value;
} elsif ($attr_name =~ /^xmlns:(.*)$/) {
my $prefix = $1;
$self->{InScopeNamespaceStack}[-1]{$prefix} = $value;
}
}
}
sub _namespace {
my ($self, $name) = @_;
my ($prefix, $localname) = split(/:/, $name);
if (!defined($localname)) {
if ($prefix eq 'xmlns') {
return '', undef;
} else {
return '', $self->{InScopeNamespaceStack}[-1]{'_Default'};
}
} else {
return $prefix, $self->{InScopeNamespaceStack}[-1]{$prefix};
}
}
sub as_string {
my $node = shift;
$node->toString;
}
sub get_parser { shift->{_parser}; }
sub get_filename { shift->{_filename}; }
sub get_xml { shift->{_xml}; }
sub get_ioref { shift->{_ioref}; }
sub set_parser { $_[0]->{_parser} = $_[1]; }
sub set_filename { $_[0]->{_filename} = $_[1]; }
sub set_xml { $_[0]->{_xml} = $_[1]; }
sub set_ioref { $_[0]->{_ioref} = $_[1]; }
1;
__END__
=head1 NAME
XML::XPath::XMLParser - The default XML parsing class that produces a node tree
=head1 SYNOPSIS
my $parser = XML::XPath::XMLParser->new(
filename => $self->get_filename,
xml => $self->get_xml,
ioref => $self->get_ioref,
parser => $self->get_parser,
);
my $root_node = $parser->parse;
=head1 DESCRIPTION
This module generates a node tree for use as the context node for XPath processing.
It aims to be a quick parser, nothing fancy, and yet has to store more information
than most parsers. To achieve this I've used array refs everywhere - no hashes.
I don't have any performance figures for the speedups achieved, so I make no
apologies for anyone not used to using arrays instead of hashes. I think they
make good sense here where we know the attributes of each type of node.
=head1 Node Structure
All nodes have the same first 2 entries in the array: node_parent
and node_pos. The type of the node is determined using the ref() function.
The node_parent always contains an entry for the parent of the current
node - except for the root node which has undef in there. And node_pos is the
position of this node in the array that it is in (think:
$node == $node->[node_parent]->[node_children]->[$node->[node_pos]] )
Nodes are structured as follows:
=head2 Root Node
The root node is just an element node with no parent.
[
undef, # node_parent - check for undef to identify root node
undef, # node_pos
undef, # node_prefix
[ ... ], # node_children (see below)
]
=head2 Element Node
[
$parent, # node_parent
<position in current array>, # node_pos
'xxx', # node_prefix - namespace prefix on this element
[ ... ], # node_children
'yyy', # node_name - element tag name
[ ... ], # node_attribs - attributes on this element
[ ... ], # node_namespaces - namespaces currently in scope
]
=head2 Attribute Node
[
$parent, # node_parent - the element node
<position in current array>, # node_pos
'xxx', # node_prefix - namespace prefix on this element
'href', # node_key - attribute name
'ftp://ftp.com/', # node_value - value in the node
]
=head2 Namespace Nodes
Each element has an associated set of namespace nodes that are currently
in scope. Each namespace node stores a prefix and the expanded name (retrieved
from the xmlns:prefix="..." attribute).
[
$parent,
<pos>,
'a', # node_prefix - the namespace as it was written as a prefix
'http://my.namespace.com', # node_expanded - the expanded name.
]
=head2 Text Nodes
[
$parent,
<pos>,
'This is some text' # node_text - the text in the node
]
=head2 Comment Nodes
[
$parent,
<pos>,
'This is a comment' # node_comment
]
=head2 Processing Instruction Nodes
[
$parent,
<pos>,
'target', # node_target
'data', # node_data
]
=head1 Usage
If you feel the need to use this module outside of XML::XPath (for example
you might use this module directly so that you can cache parsed trees), you
can follow the following API:
=head2 new
The new method takes either no parameters, or any of the following parameters:
filename
xml
parser
ioref
This uses the familiar hash syntax, so an example might be:
use XML::XPath::XMLParser;
my $parser = XML::XPath::XMLParser->new(filename => 'example.xml');
The parameters represent a filename, a string containing XML, an XML::Parser
instance and an open filehandle ref respectively. You can also set or get all
of these properties using the get_ and set_ functions that have the same
name as the property: e.g. get_filename, set_ioref, etc.
=head2 parse
The parse method generally takes no parameters, however you are free to
pass either an open filehandle reference or an XML string if you so require.
The return value is a tree that XML::XPath can use. The parse method will
die if there is an error in your XML, so be sure to use perl's exception
handling mechanism (eval{};) if you want to avoid this.
=head2 parsefile
The parsefile method is identical to parse() except it expects a single
parameter that is a string naming a file to open and parse. Again it
returns a tree and also dies if there are XML errors.
=head1 NOTICES
This file is distributed as part of the XML::XPath module, and is copyright
2000 Fastnet Software Ltd. Please see the documentation for the module as a
whole for licencing information.
|