p5-xrd-parser / lib / XRD / Parser.pm

   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
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
package XRD::Parser;

use 5.010;
use strict;

use Carp 0;
use Digest::SHA 0 qw(sha1_hex);
use Encode 0 qw(encode_utf8);
use HTTP::Link::Parser 0.102;
use LWP::UserAgent 0;
use Object::AUTHORITY 0;
use RDF::Trine 0.135;
use Scalar::Util 0 qw(blessed);
use URI::Escape 0;
use URI::URL 0;
use XML::LibXML 1.70 qw(:all);

use constant NS_HOSTMETA => 'http://host-meta.net/ns/1.0';
use constant NS_HOSTMETX => 'http://host-meta.net/xrd/1.0';
use constant NS_XML      => XML::LibXML::XML_XML_NS;
use constant NS_XRD      => 'http://docs.oasis-open.org/ns/xri/xrd-1.0';
use constant URI_DCTERMS => 'http://purl.org/dc/terms/';
use constant URI_HOST    => 'http://ontologi.es/xrd#host:';
use constant URI_RDF     => 'http://www.w3.org/1999/02/22-rdf-syntax-ns#';
use constant URI_RDFS    => 'http://www.w3.org/2000/01/rdf-schema#';
use constant URI_SUBLINK => 'http://ontologi.es/xrd#sublink:';
use constant URI_TYPES   => 'http://www.iana.org/assignments/media-types/';
use constant URI_XRD     => 'http://ontologi.es/xrd#';
use constant URI_XSD     => 'http://www.w3.org/2001/XMLSchema#';
use constant SCHEME_TMPL => 'x-xrd+template+for:';

BEGIN {
	$XRD::Parser::AUTHORITY  = 'cpan:TOBYINK';
	$XRD::Parser::VERSION    = '0.200';
}

sub new
{
	my ($class, $content, $baseuri, $options, $store)= @_;
	
	# Rationalise $options
	# ====================
	# If $options is undefined, then use the default configuration
	if (!ref $options)
		{ $options = {}; }

	# Rationalise $baseuri
	# ====================
	croak "Need a valid base URI.\n"
		unless $baseuri =~ /^[a-z][a-z0-9\+\-\.]*:/i;

	# Rationalise $content and set $domtree
	# =====================================
	croak "Need to provide XML content\n"
		unless defined $content;	
	my $domtree;
	if (blessed($content) && $content->isa('XML::LibXML::Document'))
	{
		($domtree, $content) = ($content, $content->toString);
	}
	else
	{
		my $xml_parser = XML::LibXML->new;
		$domtree = $xml_parser->parse_string($content);
	}
	
	# Rationalise $store
	# ==================
	$store = RDF::Trine::Store::DBI->temporary_store
		unless defined $store;
	
	my $self = bless {
		'content'   => $content,
		'baseuri'   => $baseuri,
		'options'   => $options,
		'DOM'       => $domtree,
		'RESULTS'   => RDF::Trine::Model->new($store),
		}, $class;
	
	return $self;
}

sub new_from_url
{
	my ($class, $url, $options, $store)= @_;
	
	if (!ref $options)
		{ $options = {}; }

	my $ua = LWP::UserAgent->new;
	$ua->agent(sprintf('%s/%s (%s) ', __PACKAGE__, __PACKAGE__->VERSION, __PACKAGE__->AUTHORITY));
	$ua->default_header("Accept" => "application/xrd+xml, application/xml;q=0.1, text/xml;q=0.1");
	my $response;
	my $timeout = $options->{timeout} // 60;
	eval {
		local $SIG{ALRM} = sub { die "Request timed out\n"; };
		alarm $timeout;
		$response = $ua->get($url);
		if ($response->code == 406)
		{
			$response = $ua->get($url, Accept=>'application/xrd+xml, application/x-httpd-php');
		}
		alarm 0;
	};
	croak $@ if $@;
	croak "HTTP response not successful\n"
		unless defined $response && $response->is_success;
	croak "Non-XRD HTTP response\n"
		unless $response->content_type =~ m`^(text/xml)|(application/(xrd\+xml|xml))$`
		|| ($options->{'loose_mime'} && $response->content_type =~ m`^(text/plain)|(text/html)|(application/octet-stream)$`);
	
	return $class->new(
		$response->decoded_content,
		$response->base.'',
		$options,
		$store,
		);
}

*new_from_uri = \&new_from_url;

sub hostmeta
{
	my $class = shift;
	my $host = shift;
	my $rv;

	my ($https, $http) = hostmeta_location($host);
	return unless $https;
	
	eval { $rv = $class->new_from_url($https, {timeout=>10, loose_mime=>1,default_subject=>host_uri($host)}); };
	return $rv if $rv;
	
	eval { $rv = $class->new_from_url($http, {timeout=>15, loose_mime=>1,default_subject=>host_uri($host)}); } ;
	return $rv if $rv;
	
	return;
}

sub uri
{
	my $this  = shift;
	my $param = shift // '';
	my $opts  = shift // {};
	
	if ((ref $opts) =~ /^XML::LibXML/)
	{
		my $x = {'element' => $opts};
		$opts = $x;
	}
	
	if ($param =~ /^([a-z][a-z0-9\+\.\-]*)\:/i)
	{
		# seems to be an absolute URI, so can safely return "as is".
		return $param;
	}
	elsif ($opts->{'require-absolute'})
	{
		return undef;
	}
	
	my $base = $this->{baseuri};
	if ($this->{'options'}->{'xml_base'})
	{
		$base = $opts->{'xml_base'} // $this->{baseuri};
	}
	
	my $url = url $param, $base;
	my $rv  = $url->abs->as_string;

	# This is needed to pass test case 0114.
	while ($rv =~ m!^(http://.*)(\.\./|\.)+(\.\.|\.)?$!i)
	{
		$rv = $1;
	}
	
	return $rv;
}

sub dom
{
	my $this = shift;
	return $this->{DOM};
}

sub graph
{
	my $this = shift;
	$this->consume;
	return $this->{RESULTS};
}

sub graphs
{
	my $this = shift;
	$this->consume;
	return { $this->{'baseuri'} => $this->{RESULTS} };
}

sub set_callbacks
# Set callback functions for handling RDF triples.
{
	my $this = shift;

	if ('HASH' eq ref $_[0])
	{
		$this->{'sub'} = $_[0];
		$this->{'sub'}->{'pretriple_resource'} = \&_print0
			if lc $this->{'sub'}->{'pretriple_resource'} eq 'print';
		$this->{'sub'}->{'pretriple_literal'} = \&_print1
			if lc $this->{'sub'}->{'pretriple_literal'} eq 'print';
	}
	elsif (defined $_[0])
	{
		croak("What kind of callback hashref was that??\n");
	}
	else
	{
		$this->{'sub'} = undef;
	}
	
	return $this;
}

sub _print0
# Prints a Turtle triple.
{
	my $this    = shift;
	my $element = shift;
	my $subject = shift;
	my $pred    = shift;
	my $object  = shift;
	my $graph   = shift;
	
	if ($graph)
	{
		print "# GRAPH $graph\n";
	}
	if ($element)
	{
		printf("# Triple on element %s.\n", $element->nodePath);
	}
	else
	{
		printf("# Triple.\n");
	}

	printf("%s %s %s .\n",
		($subject =~ /^_:/ ? $subject : "<$subject>"),
		"<$pred>",
		($object =~ /^_:/ ? $object : "<$object>"));
	
	return undef;
}

sub _print1
# Prints a Turtle triple.
{
	my $this    = shift;
	my $element = shift;
	my $subject = shift;
	my $pred    = shift;
	my $object  = shift;
	my $dt      = shift;
	my $lang    = shift;
	my $graph   = shift;
	
	# Clumsy, but probably works.
	$object =~ s/\\/\\\\/g;
	$object =~ s/\n/\\n/g;
	$object =~ s/\r/\\r/g;
	$object =~ s/\t/\\t/g;
	$object =~ s/\"/\\\"/g;
	
	if ($graph)
	{
		print "# GRAPH $graph\n";
	}
	if ($element)
	{
		printf("# Triple on element %s.\n", $element->nodePath);
	}
	else
	{
		printf("# Triple.\n");
	}

	no warnings;
	printf("%s %s %s%s%s .\n",
		($subject =~ /^_:/ ? $subject : "<$subject>"),
		"<$pred>",
		"\"$object\"",
		(length $dt ? "^^<$dt>" : ''),
		((length $lang && !length $dt) ? "\@$lang" : '')
		);
	use warnings;
	
	return undef;
}

sub consume
{
	my $this = shift;
	
	return $this if $this->{'consumed'};
	
	my @xrds = $this->{'DOM'}->getElementsByTagNameNS(NS_XRD, 'XRD')->get_nodelist;
	
	my $first = 1;
	my $only  = (scalar @xrds == 1) ? 1 : 0;
	
	foreach my $XRD (@xrds)
	{
		$this->_consume_XRD($XRD, $first, $only);
		$first = 0
			if $first;
	}
	
	$this->{'consumed'}++;
	
	return $this;
}

sub _consume_XRD
{
	my $this  = shift;
	my $xrd   = shift;
	my $first = shift // 0;
	my $only  = shift // 0;
	
	my $description_uri;
	if ($xrd->hasAttributeNS(NS_XML, 'id'))
	{
		$description_uri = $this->uri('#'.$xrd->getAttributeNS(NS_XML, 'id'));
	}
	elsif ($only)
	{
		$description_uri = $this->uri;
	}
	else
	{
		$description_uri = $this->bnode;
	}
			
	my $subject_node = $xrd->getChildrenByTagNameNS(NS_XRD, 'Subject')->shift;
	my $subject;
	my @subjects;
	$subject = $this->uri(
		$this->stringify($subject_node),
		{'require-absolute'=>1})
		if $subject_node;
	push @subjects, $subject
		if defined $subject;
	NAMESPACE: foreach my $hostmeta_ns (@{[NS_HOSTMETA, NS_HOSTMETX]})
	{
		my $host_uri;
		ELEMENT: foreach my $host_node ($xrd->getChildrenByTagNameNS($hostmeta_ns, 'Host')->get_nodelist)
		{
			$host_uri = host_uri($this->stringify($host_node));
			$subject = $host_uri
				unless defined $subject;
			push @subjects, $host_uri;
		}
		last NAMESPACE if $host_uri;
	}
	unless (@subjects)
	{
		if ($first && defined $this->{'options'}->{'default_subject'})
		{
			$subject = $this->{'options'}->{'default_subject'};
			push @subjects, $subject;
		}
	}
	unless (@subjects)
	{
		$subject = $this->bnode($xrd);
		push @subjects, $subject;
	}
	
	$this->rdf_triple($xrd, $description_uri, URI_XRD.'subject', $subject);
	
	foreach my $alias ( $xrd->getChildrenByTagNameNS(NS_XRD, 'Alias')->get_nodelist )
	{
		my $alias_uri = $this->uri($this->stringify($alias),{'require-absolute'=>1});
		$this->rdf_triple($alias, $subject, URI_XRD.'alias', $alias_uri);
	}
	
	my $expires_node = $xrd->getChildrenByTagNameNS(NS_XRD, 'Expires')->shift;
	my $expires      = $this->stringify($expires_node) if $expires_node;
	if (length $expires)
	{
		$this->rdf_triple_literal($expires_node,
			$description_uri, URI_XRD.'expires', $expires, URI_XSD.'dateTime');
	}
	
	foreach my $p ($xrd->getChildrenByTagNameNS(NS_XRD, 'Property')->get_nodelist)
	{
		$this->_consume_Property($p, \@subjects);
	}
	
	foreach my $l ($xrd->getChildrenByTagNameNS(NS_XRD, 'Link')->get_nodelist)
	{
		$this->_consume_Link($l, \@subjects);
	}
}

sub _consume_Property
{
	my $this = shift;
	my $p    = shift;
	my $S    = shift;
	
	my $property_uri = $this->uri(
		$p->getAttribute('type'), {'require-absolute'=>1});
	return unless $property_uri;
	
	my $value = $this->stringify($p);
	
	foreach my $subject_uri (@$S)
	{
		$this->rdf_triple_literal(
			$p,
			$subject_uri,
			$property_uri,
			$value);
	}
}

sub _consume_Link
{
	my $this = shift;
	my $l    = shift;
	my $S    = shift;
	
	my $property_uri = HTTP::Link::Parser::relationship_uri(
		$l->getAttribute('rel'));
	return unless $property_uri;
	
	my @value;
	my $value_type;
	my ($p1,$p2);
	if ($l->hasAttribute('href'))
	{
		push @value, $this->uri($l->getAttribute('href'));
		$value_type = 'href';
		($p1,$p2) = ('', $property_uri);
	}
	elsif ($l->hasAttribute('template'))
	{
		push @value, $l->getAttribute('template');
		push @value, URI_XRD . 'URITemplate';
		$value_type = 'template';
		($p1,$p2) = (SCHEME_TMPL, $property_uri);
		$property_uri = template_uri($property_uri);
	}
	else
	{
		return;
	}

	foreach my $subject_uri (@$S)
	{
		if ($value_type eq 'href')
		{
			$this->rdf_triple(
				$l,
				$subject_uri,
				$property_uri,
				@value);
		}
		elsif ($value_type eq 'template')
		{
			$this->rdf_triple_literal(
				$l,
				$subject_uri,
				$property_uri,
				@value);
		}
	}
	
	if ($value_type eq 'href')
	{
		my $type = $l->getAttribute('type');
		if (defined $type)
		{
			$this->rdf_triple_literal($l, @value, URI_XRD.'type', $type);
		}
		
		foreach my $title ($l->getChildrenByTagName('Title')->get_nodelist)
		{
			my $lang = undef;
			if ($title->hasAttributeNS(NS_XML, 'lang'))
			{
				$lang = $title->getAttributeNS(NS_XML, 'lang');
				$lang = undef unless valid_lang($lang);
			}
			$this->rdf_triple_literal(
				$title,
				@value,
				URI_XRD.'title',
				$this->stringify($title),
				undef,
				$lang);
		}		
	}
	
	foreach my $subject_uri (@$S)
	{
		my @link_properties = $l->getChildrenByTagNameNS(NS_XRD, 'Property')->get_nodelist;
		if (@link_properties)
		{
			if ($this->{'options'}->{'link_prop'} & 1)
			{
				my $reified_statement = $this->bnode($l);		
				$this->rdf_triple($l, $reified_statement, URI_RDF.'type', URI_RDF.'Statement');			
				$this->rdf_triple($l, $reified_statement, URI_RDF.'subject', $subject_uri);
				$this->rdf_triple($l, $reified_statement, URI_RDF.'predicate', $property_uri);
				
				if ($value_type eq 'href')
				{
					$this->rdf_triple($l, $reified_statement, URI_RDF.'object', @value);
				}
				else
				{
					$this->rdf_triple_literal($l, $reified_statement, URI_RDF.'object', @value);
				}
				
				foreach my $lp (@link_properties)
				{
					$this->_consume_Property($lp, [$reified_statement]);
				}
			}
			if ($this->{'options'}->{'link_prop'} & 2)
			{
				my $subPropUri = $p1 . URI_SUBLINK . uri_escape($p2);
				my @modifiers;
				foreach my $lp (@link_properties)
				{
					my $k = $this->uri($lp->getAttribute('type'), {'require-absolute'=>1});
					my $v = $this->stringify($lp);
					push @modifiers, sprintf('%s=%s', uri_escape($k), uri_escape($v))
						if length $k;
				}
				my $supermodifier = join '&', sort @modifiers;
				$subPropUri .= '/' . sha1_hex($supermodifier);
				
				if ($value_type eq 'href')
				{
					$this->rdf_triple($l, $subject_uri, $subPropUri, @value);
				}
				else
				{
					$this->rdf_triple_literal($l, $subject_uri, $subPropUri, @value);
				}
				
				$this->rdf_triple($l, $subPropUri, URI_RDF.'type', URI_RDF.'Property');
				$this->rdf_triple($l, $subPropUri, URI_RDFS.'subPropertyOf', $property_uri);
				foreach my $lp (@link_properties)
				{
					$this->_consume_Property($lp, [$subPropUri]);
				}
			}
		}
	}
}

sub rdf_triple
# Function only used internally.
{
	my $this = shift;

	my $suppress_triple = 0;
	$suppress_triple = $this->{'sub'}->{'pretriple_resource'}($this, @_)
		if defined $this->{'sub'}->{'pretriple_resource'};
	return if $suppress_triple;
	
	my $element   = shift;  # A reference to the XML::LibXML element being parsed
	my $subject   = shift;  # Subject URI or bnode
	my $predicate = shift;  # Predicate URI
	my $object    = shift;  # Resource URI or bnode
	my $graph     = shift;  # Graph URI or bnode (if named graphs feature is enabled)

	# First make sure the object node type is ok.
	my $to;
	if ($object =~ m/^_:(.*)/)
	{
		$to = RDF::Trine::Node::Blank->new($1);
	}
	else
	{
		$to = RDF::Trine::Node::Resource->new($object);
	}

	# Run the common function
	return $this->rdf_triple_common($element, $subject, $predicate, $to, $graph);
}

sub rdf_triple_literal
# Function only used internally.
{
	my $this = shift;

	my $suppress_triple = 0;
	$suppress_triple = $this->{'sub'}->{'pretriple_literal'}($this, @_)
		if defined $this->{'sub'}->{'pretriple_literal'};
	return if $suppress_triple;

	my $element   = shift;  # A reference to the XML::LibXML element being parsed
	my $subject   = shift;  # Subject URI or bnode
	my $predicate = shift;  # Predicate URI
	my $object    = shift;  # Resource Literal
	my $datatype  = shift;  # Datatype URI (possibly undef or '')
	my $language  = shift;  # Language (possibly undef or '')
	my $graph     = shift;  # Graph URI or bnode (if named graphs feature is enabled)

	# Now we know there's a literal
	my $to;
	
	# Work around bad Unicode handling in RDF::Trine.
	$object = encode_utf8($object);

	if (defined $datatype)
	{
		if ($datatype eq 'http://www.w3.org/1999/02/22-rdf-syntax-ns#XMLLiteral')
		{
			if ($this->{'options'}->{'use_rtnlx'})
			{
				eval
				{
					require RDF::Trine::Node::Literal::XML;
					$to = RDF::Trine::Node::Literal::XML->new($element->childNodes);
				};
			}
			
			if ( $@ || !defined $to)
			{
				my $orig = $RDF::Trine::Node::Literal::USE_XMLLITERALS;
				$RDF::Trine::Node::Literal::USE_XMLLITERALS = 0;
				$to = RDF::Trine::Node::Literal->new($object, undef, $datatype);
				$RDF::Trine::Node::Literal::USE_XMLLITERALS = $orig;
			}
		}
		else
		{
			$to = RDF::Trine::Node::Literal->new($object, undef, $datatype);
		}
	}
	else
	{
		$to = RDF::Trine::Node::Literal->new($object, $language, undef);
	}

	# Run the common function
	$this->rdf_triple_common($element, $subject, $predicate, $to, $graph);
}

sub rdf_triple_common
# Function only used internally.
{
	my $this      = shift;  # A reference to the RDF::RDFa::Parser object
	my $element   = shift;  # A reference to the XML::LibXML element being parsed
	my $subject   = shift;  # Subject URI or bnode
	my $predicate = shift;  # Predicate URI
	my $to        = shift;  # RDF::Trine::Node Resource URI or bnode
	my $graph     = shift;  # Graph URI or bnode (if named graphs feature is enabled)

	# First, make sure subject and predicates are the right kind of nodes
	my $tp = RDF::Trine::Node::Resource->new($predicate);
	my $ts;
	if ($subject =~ m/^_:(.*)/)
	{
		$ts = RDF::Trine::Node::Blank->new($1);
	}
	else
	{
		$ts = RDF::Trine::Node::Resource->new($subject);
	}

	my $statement;

	# If we are configured for it, and graph name can be found, add it.
	if (ref($this->{'options'}->{'named_graphs'}) && ($graph))
	{
		$this->{Graphs}->{$graph}++;
		
		my $tg;
		if ($graph =~ m/^_:(.*)/)
		{
			$tg = RDF::Trine::Node::Blank->new($1);
		}
		else
		{
			$tg = RDF::Trine::Node::Resource->new($graph);
		}

		$statement = RDF::Trine::Statement::Quad->new($ts, $tp, $to, $tg);
	}
	else
	{
		$statement = RDF::Trine::Statement->new($ts, $tp, $to);
	}

	my $suppress_triple = 0;
	$suppress_triple = $this->{'sub'}->{'ontriple'}($this, $element, $statement)
		if ($this->{'sub'}->{'ontriple'});
	return if $suppress_triple;

	$this->{RESULTS}->add_statement($statement);
}

sub stringify
# Function only used internally.
{
	my $this = shift;
	my $dom  = shift;
	
	if ($dom->nodeType == XML_TEXT_NODE)
	{
		return $dom->getData;
	}
	elsif ($dom->nodeType == XML_ELEMENT_NODE)
	{
		my $rv = '';
		foreach my $kid ($dom->childNodes)
			{ $rv .= $this->stringify($kid); }
		return $rv;
	}

	return '';
}

sub xmlify
# Function only used internally.
{
	my $this = shift;
	my $dom  = shift;
	my $lang = shift;
	my $rv;
	
	foreach my $kid ($dom->childNodes)
	{
		my $fakelang = 0;
		if (($kid->nodeType == XML_ELEMENT_NODE) && defined $lang)
		{
			unless ($kid->hasAttributeNS(NS_XML, 'lang'))
			{
				$kid->setAttributeNS(NS_XML, 'lang', $lang);
				$fakelang++;
			}
		}
		
		$rv .= $kid->toStringEC14N(1);
		
		if ($fakelang)
		{
			$kid->removeAttributeNS(NS_XML, 'lang');
		}
	}
	
	return $rv;
}

sub bnode
# Function only used internally.
{
	my $this    = shift;
	my $element = shift;
	
	return sprintf('http://thing-described-by.org/?%s#%s',
		$this->uri,
		$element->getAttributeNS(NS_XML, 'id'))
		if ($this->{options}->{tdb_service} && $element && length $element->getAttributeNS(NS_XML, 'id'));

	$this->{bnode_prefix} //= do {
		my $uuid = Data::UUID->new->create_str;
		$uuid =~ s/[^A-Za-z0-9]//g;
		$uuid;
		};
	
	return sprintf('_:x%sx%03d', $this->{bnode_prefix}, $this->{bnodes}++);
}

sub valid_lang
{
	my $value_to_test = shift;

	return 1 if (defined $value_to_test) && ($value_to_test eq '');
	return 0 unless defined $value_to_test;
	
	# Regex for recognizing RFC 4646 well-formed tags
	# http://www.rfc-editor.org/rfc/rfc4646.txt
	# http://tools.ietf.org/html/draft-ietf-ltru-4646bis-21

	# The structure requires no forward references, so it reverses the order.
	# It uses Java/Perl syntax instead of the old ABNF
	# The uppercase comments are fragments copied from RFC 4646

	# Note: the tool requires that any real "=" or "#" or ";" in the regex be escaped.

	my $alpha      = '[a-z]';      # ALPHA
	my $digit      = '[0-9]';      # DIGIT
	my $alphanum   = '[a-z0-9]';   # ALPHA / DIGIT
	my $x          = 'x';          # private use singleton
	my $singleton  = '[a-wyz]';    # other singleton
	my $s          = '[_-]';       # separator -- lenient parsers will use [_-] -- strict will use [-]

	# Now do the components. The structure is slightly different to allow for capturing the right components.
	# The notation (?:....) is a non-capturing version of (...): so the "?:" can be deleted if someone doesn't care about capturing.

	my $language   = '([a-z]{2,8}) | ([a-z]{2,3} $s [a-z]{3})';
	
	# ABNF (2*3ALPHA) / 4ALPHA / 5*8ALPHA  --- note: because of how | works in regex, don't use $alpha{2,3} | $alpha{4,8} 
	# We don't have to have the general case of extlang, because there can be only one extlang (except for zh-min-nan).

	# Note: extlang invalid in Unicode language tags

	my $script = '[a-z]{4}' ;   # 4ALPHA 

	my $region = '(?: [a-z]{2}|[0-9]{3})' ;    # 2ALPHA / 3DIGIT

	my $variant    = '(?: [a-z0-9]{5,8} | [0-9] [a-z0-9]{3} )' ;  # 5*8alphanum / (DIGIT 3alphanum)

	my $extension  = '(?: [a-wyz] (?: [_-] [a-z0-9]{2,8} )+ )' ; # singleton 1*("-" (2*8alphanum))

	my $privateUse = '(?: x (?: [_-] [a-z0-9]{1,8} )+ )' ; # "x" 1*("-" (1*8alphanum))

	# Define certain grandfathered codes, since otherwise the regex is pretty useless.
	# Since these are limited, this is safe even later changes to the registry --
	# the only oddity is that it might change the type of the tag, and thus
	# the results from the capturing groups.
	# http://www.iana.org/assignments/language-subtag-registry
	# Note that these have to be compared case insensitively, requiring (?i) below.

	my $grandfathered  = '(?:
			  (en [_-] GB [_-] oed)
			| (i [_-] (?: ami | bnn | default | enochian | hak | klingon | lux | mingo | navajo | pwn | tao | tay | tsu ))
			| (no [_-] (?: bok | nyn ))
			| (sgn [_-] (?: BE [_-] (?: fr | nl) | CH [_-] de ))
			| (zh [_-] min [_-] nan)
			)';

	# old:         | zh $s (?: cmn (?: $s Hans | $s Hant )? | gan | min (?: $s nan)? | wuu | yue );
	# For well-formedness, we don't need the ones that would otherwise pass.
	# For validity, they need to be checked.

	# $grandfatheredWellFormed = (?:
	#         art $s lojban
	#     | cel $s gaulish
	#     | zh $s (?: guoyu | hakka | xiang )
	# );

	# Unicode locales: but we are shifting to a compatible form
	# $keyvalue = (?: $alphanum+ \= $alphanum+);
	# $keywords = ($keyvalue (?: \; $keyvalue)*);

	# We separate items that we want to capture as a single group

	my $variantList   = $variant . '(?:' . $s . $variant . ')*' ;     # special for multiples
	my $extensionList = $extension . '(?:' . $s . $extension . ')*' ; # special for multiples

	my $langtag = "
			($language)
			($s ( $script ) )?
			($s ( $region ) )?
			($s ( $variantList ) )?
			($s ( $extensionList ) )?
			($s ( $privateUse ) )?
			";

	# Here is the final breakdown, with capturing groups for each of these components
	# The variants, extensions, grandfathered, and private-use may have interior '-'
	
	my $r = ($value_to_test =~ 
		/^(
			($langtag)
		 | ($privateUse)
		 | ($grandfathered)
		 )$/xi);
	return $r;
}

sub host_uri
{
	my $uri = shift;

	if ($uri =~ /:/)
	{
		my $tmpuri = URI->new($uri);
		
		if ($tmpuri->can('host'))
		{
			return URI_HOST . $tmpuri->host;
		}
		elsif($tmpuri->can('authority') && $tmpuri->authority =~ /\@/)
		{
			(undef, my $host) = split /\@/, $tmpuri->authority;
			return URI_HOST . $host;
		}
		elsif($tmpuri->can('opaque') && $tmpuri->opaque =~ /\@/)
		{
			(undef, my $host) = split /\@/, $tmpuri->opaque;
			return URI_HOST . $host;
		}
	}
	else
	{
		return URI_HOST . $uri;
	}
	
	return undef;
}

sub template_uri
{
	my $uri = shift;
	return SCHEME_TMPL . $uri;
}


sub hostmeta_location
{
	my $host  = shift;

	if ($host =~ /:/)
	{
		my $u = url $host;
		if ($u->can('host'))
		{
			$host = $u->host;
		}
		elsif ($u->can('authority') && $u->authority =~ /\@/)
		{
			(undef, $host) = split /\@/, $u->authority;
		}
		elsif ($u->can('opaque') && $u->opaque =~ /\@/)
		{
			(undef, $host) = split /\@/, $u->opaque;
		}
	}
	
	if (wantarray)
	{
		return ("https://$host/.well-known/host-meta", "http://$host/.well-known/host-meta");
	}
	else
	{
		return "http://$host/.well-known/host-meta";
	}
}

1;

__END__

=head1 NAME

XRD::Parser - parse XRD and host-meta files into RDF::Trine models

=head1 SYNOPSIS

  use RDF::Query;
  use XRD::Parser;
  
  my $parser = XRD::Parser->new(undef, "http://example.com/foo.xrd");
  my $results = RDF::Query->new(
    "SELECT * WHERE {?who <http://spec.example.net/auth/1.0> ?auth.}")
    ->execute($parser->graph);
	
  while (my $result = $results->next)
  {
    print $result->{'auth'}->uri . "\n";
  }

or maybe:

  my $data = XRD::Parser->hostmeta('gmail.com')
                          ->graph
                            ->as_hashref;

=head1 DESCRIPTION

While XRD has a rather different history, it turns out it can mostly
be thought of as a serialisation format for a limited subset of
RDF.

This package ignores the order of <Link> elements, as RDF is a graph
format with no concept of statements coming in an "order". The XRD spec
says that grokking the order of <Link> elements is only a SHOULD. That
said, if you're concerned about the order of <Link> elements, the
callback routines allowed by this package may be of use.

This package aims to be roughly compatible with RDF::RDFa::Parser's
interface.

=head2 Constructors

=over 4

=item C<< $p = XRD::Parser->new($content, $uri, [\%options], [$store]) >>

This method creates a new XRD::Parser object and returns it.

The $content variable may contain an XML string, or a XML::LibXML::Document.
If a string, the document is parsed using XML::LibXML::Parser, which may throw an
exception. XRD::Parser does not catch the exception.

$uri the base URI of the content; it is used to resolve any relative URIs found
in the XRD document. 

Options [default in brackets]:

=over 8

=item * B<default_subject> - If no <Subject> element. [undef]

=item * B<link_prop> - How to handle <Property> in <Link>?
0=skip, 1=reify, 2=subproperty, 3=both. [0] 

=item * B<loose_mime> - Accept text/plain, text/html and
application/octet-stream media types. [0]

=item * B<tdb_service> - Use thing-described-by.org when possible. [0]

=back

$storage is an RDF::Trine::Storage object. If undef, then a new
temporary store is created.

=item C<< $p = XRD::Parser->new_from_url($url, [\%options], [$storage]) >>

$url is a URL to fetch and parse.

This function can also be called as C<new_from_uri>. Same thing.

=item C<< $p = XRD::Parser->hostmeta($uri) >>

This method creates a new XRD::Parser object and returns it.

The parameter may be a URI (from which the hostname will be extracted) or
just a bare host name (e.g. "example.com"). The resource
"/.well-known/host-meta" will then be fetched from that host using an
appropriate HTTP Accept header, and the parser object returned.

=back

=head2 Public Methods

=over 4

=item C<< $p->uri($uri) >>

Returns the base URI of the document being parsed. This will usually be the
same as the base URI provided to the constructor.

Optionally it may be passed a parameter - an absolute or relative URI - in
which case it returns the same URI which it was passed as a parameter, but
as an absolute URI, resolved relative to the document's base URI.

This seems like two unrelated functions, but if you consider the consequence
of passing a relative URI consisting of a zero-length string, it in fact makes
sense.

=item C<< $p->dom >>

Returns the parsed XML::LibXML::Document.

=item C<< $p->graph >>

This method will return an RDF::Trine::Model object with all
statements of the full graph.

This method will automatically call C<consume> first, if it has not
already been called.

=item $p->set_callbacks(\%callbacks)

Set callback functions for the parser to call on certain events. These are only necessary if
you want to do something especially unusual.

  $p->set_callbacks({
    'pretriple_resource' => sub { ... } ,
    'pretriple_literal'  => sub { ... } ,
    'ontriple'           => undef ,
    });

Either of the two pretriple callbacks can be set to the string 'print' instead of a coderef.
This enables built-in callbacks for printing Turtle to STDOUT.

For details of the callback functions, see the section CALLBACKS. C<set_callbacks> must
be used I<before> C<consume>. C<set_callbacks> itself returns a reference to the parser
object itself.

I<NOTE:> the behaviour of this function was changed in version 0.05.

=item C<< $p->consume >>

This method processes the input DOM and sends the resulting triples to 
the callback functions (if any).

It called again, does nothing.

Returns the parser object itself.

=back

=head2 Utility Functions

=over 4

=item C<< $host_uri = XRD::Parser::host_uri($uri) >>

Returns a URI representing the host. These crop up often in graphs gleaned
from host-meta files.

$uri can be an absolute URI like 'http://example.net/foo#bar' or a host
name like 'example.com'.

=item C<< $uri = XRD::Parser::template_uri($relationship_uri) >>

Returns a URI representing not a normal relationship, but the
relationship between a host and a template URI literal.

=item C<< $hostmeta_uri = XRD::Parser::hostmeta_location($host) >>

The parameter may be a URI (from which the hostname will be extracted) or
just a bare host name (e.g. "example.com"). The location for a host-meta file
relevant to the host of that URI will be calculated.

If called in list context, returns an 'https' URI and an 'http' URI as a list.

=back

=head1 CALLBACKS

Several callback functions are provided. These may be set using the C<set_callbacks> function,
which taskes a hashref of keys pointing to coderefs. The keys are named for the event to fire the
callback on.

=head2 pretriple_resource

This is called when a triple has been found, but before preparing the triple for
adding to the model. It is only called for triples with a non-literal object value.

The parameters passed to the callback function are:

=over 4

=item * A reference to the C<XRD::Parser> object

=item * A reference to the C<XML::LibXML::Element> being parsed

=item * Subject URI or bnode (string)

=item * Predicate URI (string)

=item * Object URI or bnode (string)

=back

The callback should return 1 to tell the parser to skip this triple (not add it to
the graph); return 0 otherwise.

=head2 pretriple_literal

This is the equivalent of pretriple_resource, but is only called for triples with a
literal object value.

The parameters passed to the callback function are:

=over 4

=item * A reference to the C<XRD::Parser> object

=item * A reference to the C<XML::LibXML::Element> being parsed

=item * Subject URI or bnode (string)

=item * Predicate URI (string)

=item * Object literal (string)

=item * Datatype URI (string or undef)

=item * Language (string or undef)

=back

The callback should return 1 to tell the parser to skip this triple (not add it to
the graph); return 0 otherwise.

=head2 ontriple

This is called once a triple is ready to be added to the graph. (After the pretriple
callbacks.) The parameters passed to the callback function are:

=over 4

=item * A reference to the C<XRD::Parser> object

=item * A reference to the C<XML::LibXML::Element> being parsed

=item * An RDF::Trine::Statement object.

=back

The callback should return 1 to tell the parser to skip this triple (not add it to
the graph); return 0 otherwise. The callback may modify the RDF::Trine::Statement
object.

=head1 WHY RDF?

It abstracts away the structure of the XRD file, exposing just the meaning
of its contents. Two XRD files with the same meaning should end up producing
more or less the same RDF data, even if they differ significantly at the
syntactic level.

If you care about the syntax of an XRD file, then use L<XML::LibXML>.

=head1 SEE ALSO

L<RDF::Trine>, L<RDF::Query>, L<RDF::RDFa::Parser>.

L<http://www.perlrdf.org/>.

=head1 AUTHOR

Toby Inkster, E<lt>tobyink@cpan.orgE<gt>

=head1 COPYRIGHT AND LICENCE

Copyright (C) 2009-2012 by Toby Inkster

This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.

=head1 DISCLAIMER OF WARRANTIES

THIS PACKAGE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR IMPLIED
WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE.

=cut
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.