/usr/share/perl5/XML/LibXML/Iterator.pm is in libxml-libxml-iterator-perl 1.04-1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 | #
#
package XML::LibXML::Iterator;
use strict;
use XML::NodeFilter qw(:results);
use vars qw($VERSION);
$VERSION = '1.04';
use overload
'++' => sub { $_[0]->nextNode(); $_[0]; },
'--' => sub { $_[0]->previousNode(); $_[0]; },
'<>' => sub { return wantarray ? $_[0]->_get_all() : $_[0]->nextNode(); },
;
sub new {
my $class = shift;
my $node = shift;
return undef unless defined $node;
my $self = bless {}, $class;
$self->{FIRST} = $node;
# $self->first;
$self->{CURRENT} = undef;
$self->{INDEX} = -1;
$self->{ITERATOR} = \&default_iterator;
$self->{FILTERS} = [];
return $self;
}
sub iterator_function {
my $self = shift;
my $func = shift;
return if defined $func and ref( $func ) ne "CODE";
$self->first;
if ( defined $func ) {
$self->{ITERATOR} = $func;
}
else {
$self->{ITERATOR} = \&default_iterator;
}
}
sub set_filter {
my $self = shift;
$self->{FILTERS} = [ @_ ];
}
sub add_filter {
my $self = shift;
push @{$self->{FILTERS}}, @_;
}
sub current { return $_[0]->{CURRENT}; }
sub index { return $_[0]->{INDEX}; }
sub next { return $_[0]->nextNode(); }
sub previous { return $_[0]->previousNode(); }
sub nextNode {
my $self = shift;
my @filters = @{$self->{FILTERS}};
my $node = undef;
if ( $self->{INDEX} != -1 ) {
my $fv = FILTER_SKIP;
unless ( scalar @filters > 0 ) {
$fv = FILTER_DECLINED;
}
while ( 1 ) {
$node = $self->{ITERATOR}->( $self, 1 );
last unless defined $node;
foreach my $f ( @filters ) {
$fv = $f->accept_node( $node );
last if $fv;
}
last if $fv == FILTER_ACCEPT or $fv == FILTER_DECLINED;
}
}
else {
$node = $self->first();
}
if ( defined $node ) {
$self->{CURRENT} = $node;
if ( $node->isSameNode( $self->{FIRST} ) ) {
$self->{INDEX} = 0;
}
else {
$self->{INDEX}++;
}
}
return $node;
}
sub previousNode {
my $self = shift;
my @filters = @{$self->{FILTERS}};
my $node = undef;
my $fv = FILTER_SKIP;
unless ( scalar @filters > 0 ) {
$fv = FILTER_DECLINED;
}
while ( 1 ) {
$node = $self->{ITERATOR}->( $self, -1 );
last unless defined $node;
foreach my $f ( @filters ) {
$fv = $f->accept_node( $node );
last if $fv;
}
last if $fv == FILTER_ACCEPT or $fv == FILTER_DECLINED;
}
if ( defined $node ) {
$self->{CURRENT} = $node;
$self->{INDEX}--;
}
return $node;
}
sub first {
my $self = shift;
if ( scalar @_ ) {
$self->{FIRST} = shift;
}
$self->{CURRENT} = $self->{FIRST};
# this logic is required if the node is not allowed to be shown
my @filters = @{$self->{FILTERS}||[]};
my $fv = FILTER_DECLINED;
foreach my $f ( @filters ) {
$fv = $f->accept_node( $self->{CURRENT} );
last if $fv;
}
$fv ||= FILTER_ACCEPT;
unless ( $fv == FILTER_ACCEPT ) {
return undef;
}
$self->{INDEX} = 0;
return $self->current;
}
sub last {
my $self = shift;
while ($self->next) {}
return $self->current;
}
sub iterate {
my $self = shift;
my $function = shift;
return unless defined $function and ref( $function ) eq 'CODE' ;
my $rv;
my $node = $self->first;
while ( $node ) {
$rv = $function->($self,$node);
$node = $self->next;
}
return $rv;
}
sub default_iterator {
my $self = shift;
my $dir = shift;
my $node = undef;
if ( $dir < 0 ) {
return undef if $self->{CURRENT}->isSameNode( $self->{FIRST} )
and $self->{INDEX} <= 0;
$node = $self->{CURRENT}->previousSibling;
return $self->{CURRENT}->parentNode unless defined $node;
while ( $node->hasChildNodes ) {
$node = $node->lastChild;
}
}
else {
if ( defined $self->{CURRENT} ) {
return undef if $self->{CURRENT}->isSameNode( $self->{FIRST} )
and $self->{INDEX} > 0;
if ( $self->{CURRENT}->hasChildNodes ) {
$node = $self->{CURRENT}->firstChild;
}
else {
$node = $self->{CURRENT}->nextSibling;
my $pnode = $self->{CURRENT}->parentNode;
while ( not defined $node ) {
last unless defined $pnode;
$node = $pnode->nextSibling;
$pnode = $pnode->parentNode unless defined $node;
}
}
}
else {
$self->{CURRENT} = $self->{FIRST};
$node = $self->{CURRENT};
}
}
return $node;
}
# helper function for the <> operator
# returns all nodes that have not yet been accessed
sub _get_all {
my $self = shift;
my @retval = ();
my $node;
while ( $node = $self->next() ) {
push @retval, $node;
}
return @retval;
}
1;
__END__
=pod
=head1 NAME
XML::LibXML::Iterator - XML::LibXML's Tree Iteration Class
=head1 SYNOPSIS
use XML::LibXML;
use XML::LibXML::Iterator;
my $doc = XML::LibXML->new->parse_string( $somedata );
my $iter= XML::LibXML::Iterator->new( $doc );
$iter->iterator_function( \&iterator_function );
# more control on the flow
while ( $iter->nextNode ) {
# do something
}
# operate on the entire tree
$iter->iterate( \&callback_function );
=head1 DESCRIPTION
XML::LibXML::Iterator is an iterator class for XML::LibXML parsed
documents. This class allows to iterate the document tree as it were a
linear data structure. It is possible to step back and forth between
the nodes of the tree and do certain operations on that
nodes. Different to XPath the nodes are not prefetched but will be
calculated for each step. Therefore an iterator is sensible towards
the current state of a document tree on each step, while XPath is only
per query executed.
=head2 What is an iterator?
XML::LibXML offers by default a W3C DOM interface on the parsed XML
documents. This tree has per definition four directions to be
traversed: Up, down, foreward and backward. Therefore a tree can be
considered two dimensional. Although a tree is still one more simple
datastructure it is way to complex for some operations. So the
XML::LibXML::Iterator class breaks the for operations down to only
two: backward and forward. For some people this easier to understand
than DOM or SAX as this follows more the way one actually reads an XML
document.
Therefore an iterator has three basic functions:
=over 4
=item * nextNode()
=item * current()
=item * previousNode()
=back
That's it. With an iterator one does not have to decide when to dive
into a subtree or find a parent. It is not even required to care about
the boundaries of a certain level. The iterator will get the next node
for you until there is no node left to handle.
In short: An iterator will answer the question about what to do next.
=head2 How to use XML::LibXML::Iterator?
XML::LibXML::Iterator requires a parsed document or at least a node to
operate on. This node is passed to the iterator class and will be used
as the B<first> node of the iteration. One can allways reset the
iterator to the first node by using the first()-function.
Once XML::LibXML::Iterator is initialized the tree can be traversed by
using either next() or previous(). Both function will return a
XML::LibXML::Node object if there is such object available.
Since the current object hold by the iterator class is always
available via the current() function.
The following example may clearify this:
# get the document from wherever you like
my $doc = XML::LibXML->new->parse_stream( *SOMEINPUT );
# get the iterator for the document root.
my $iter = XML::LibXML::Iterator->new( $doc->documentElement );
# walk through the document
while ( $iter->nextNode() ) {
my $curnode = $iter->current();
print $curnode->nodeType();
}
# now get back to the beginning
$iter->first();
my $curnode = $iter->current();
print $curnode->nodeType();
Actually the functions nextNode(), previousNode(), first(), last() and
current() do return the node which is current after the
operation. E.g. nextNode() moves to the next node if possible and then
returns the node. Thus the while-loop in the example can be written
as
while ( $iter->nextNode() ) {
print $_->nodeType();
}
Note, that just relieing on the return value of next() and previous()
is somewhat dangerous, because both functions return B<undef> in case
of reaching the iteration boundaries. That means it is not possible
to iterate past the last element or before the first one.
=head2 Node Filters
XML::LibXML::Iterator accepts XML::NodeFilters to limit the nodes made
available to the caller. Any nodefilter applied to
XML::LibXML::Iterator will test if a node returned by the iteration
function is visible to the caller.
Different to the DOM Traversal Specification, XML::LibXML::Iterator
allows filter stacks. This means it is possible to apply more than a
single node filter to your node iterator.
=head2 Complex Iterations
By default XML::LibXML::Iterator will access all nodes of a given DOM
tree. An interation based on the default iterator will access each
single node in the given subtree once. The order how the nodes will be
accessed is given by the following order:
node -> node's childnodes -> node's next sibling
In combination with XML::Nodefilter this is best for a wide range of
scripts and applications. Nevertheless this is still to restrictive
for some applications. XML::LibXML::Iterator allows to change that
behaviour. This is done by resetting XML::LibXML::Iterator's iterator
function. By using the method iterator_function() to override the
default iterator function, it is possible to implement iterations
based on any iteration rule imaginable.
A valid iterator function has to take two parameters: As the first
parameter it will recieve the iterator object itself, as second the
direction of the iteration will be passed. The direction is either 1
(for next()) or -1 (for previous()). As the iterator-function is
called by next() and previous() the interator-function has to be aware
about the iteration boundaries. In case the iteration would pass the
boundary for that operation, the function has to return
undefined. Also the iterator function has to return the new current node,
instead of setting it itself.
*DEVELOPER NOTE* In order a single stepping is rather limited, the
direction is given by the sign of the passed integer value. The value
of the passed parameter will be used as an indication how many steps
should be done. Therefor the interation direction should be tested
relative to '0' and not as a equation. A basic template for a iterator
function therefore will look like this:
sub iterator_func_templ {
my $iter = shift;
my $step = shift;
my $node = undef;
my $current = $iter->current();
if ( $step > 0 ) {
# move forward
}
else {
# move backward
$step *= -1; # remove the sign
}
return $node;
}
=head2 Repeated Operation
Another feature of XML::LibXML::Iterator is the ability to repeat a
single operation on all nodes in scope. Instead of writing a loop one
can specify the opeation as a function, that it applied on each node
found. The function that does the trick, is named iterate().
iterate() takes again two parameter: First the iterator object, second
the node to operate on. iterate() will iterate through the entire
document starting with the first node. If one has already started an
iteration, the internal position will be reset to the first node.
The following example will show how this works:
$iter->iterate( sub {my ($iter,$node)=@_; map {$iter->setNodeName( lc $iter->nodeName ) if $iter->nodeType != NAMESPACE_DECLARATION } ($node, $node->attributes); } );
This extra long line lowercases all tagnames and the names of the
attributes in a given subtree.
=head2 Functions
=over 4
=item new($first_node)
=item first()
=item nextNode()
=item previousNode()
=item last()
=item current()
=item index()
=item iterator_function($funcion_ref)
=item set_filter(@filter_list)
=item add_filter(@filter_list)
=item iterate($function_ref)
=back
=head1 SEE ALSO
L<XML::LibXML::Node>, L<XML::NodeFilter>
=head1 AUTHOR
Christian Glahn, E<lt>phish@cpan.orgE<gt>
=head1 COPYRIGHT
(c) 2002-2007, Christian Glahn. All rights reserved.
This package is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.
=cut
|