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
|
########################################################################
# Writer.pm - write an XML document.
# Copyright (c) 1999 by Megginson Technologies.
# No warranty. Commercial and non-commercial use freely permitted.
#
# $Id: Writer.pm,v 0.3 1999/04/25 13:44:50 david Exp david $
########################################################################
package XML::Writer;
require 5.004;
use strict;
use vars qw($VERSION);
use Carp;
use IO;
$VERSION = "0.3";
########################################################################
# Constructor.
########################################################################
#
# Public constructor.
#
# This actually does most of the work of the module: it defines closures
# for all of the real processing, and selects the appropriate closures
# to use based on the value of the UNSAFE parameter. The actual methods
# are just stubs.
#
sub new {
my ($class, %params) = (@_);
# If the user wants namespaces,
# intercept the request here; it will
# come back to this constructor
# from within XML::Writer::Namespaces::new()
if ($params{NAMESPACES}) {
delete $params{NAMESPACES};
return new XML::Writer::Namespaces(%params);
}
# Set up $self and basic parameters
my $self;
my $output;
my $unsafe = $params{UNSAFE};
my $newlines = $params{NEWLINES};
# If the NEWLINES parameter is specified,
# set the $nl variable appropriately
my $nl = '';
if ($newlines) {
$nl = "\n";
}
# Parse variables
my @elementStack = ();
my $elementLevel = 0;
my %seen = ();
#
# Private method to show attributes.
#
my $showAttributes = sub {
my $atts = $_[0];
my $i = 1;
while ($atts->[$i]) {
my $aname = $atts->[$i++];
my $value = _escapeLiteral($atts->[$i++]);
$output->print(" $aname=\"$value\"");
}
};
# Method implementations: the SAFE_
# versions perform error checking
# and then call the regular ones.
my $end = sub {
$output->print("\n");
};
my $SAFE_end = sub {
if (!$seen{ELEMENT}) {
croak("Document cannot end without a document element");
} elsif ($elementLevel > 0) {
croak("Document ended with unmatched start tag(s): @elementStack");
} else {
@elementStack = ();
$elementLevel = 0;
%seen = ();
&{$end};
}
};
my $xmlDecl = sub {
my ($encoding, $standalone) = (@_);
$encoding = "UTF-8" unless $encoding;
$output->print("<?xml version=\"1.0\"");
if ($encoding) {
$output->print(" encoding=\"$encoding\"");
}
if ($standalone) {
$output->print(" standalone=\"$standalone\"");
}
$output->print("?>\n");
};
my $SAFE_xmlDecl = sub {
if ($seen{ANYTHING}) {
croak("The XML declaration is not the first thing in the document");
} else {
$seen{ANYTHING} = 1;
$seen{XMLDECL} = 1;
&{$xmlDecl};
}
};
my $pi = sub {
my ($target, $data) = (@_);
if ($data) {
$output->print("<?$target $data?>");
} else {
$output->print("<?$target?>");
}
if ($elementLevel == 0) {
$output->print("\n");
}
};
my $SAFE_pi = sub {
my ($name, $data) = (@_);
$seen{ANYTHING} = 1;
if ($name =~ /xml/i) {
carp("Processing instruction target begins with 'xml'");
}
if ($name =~ /\?\>/ || $data =~ /\?\>/) {
croak("Processing instruction may not contain '?>'");
} else {
&{$pi};
}
};
my $comment = sub {
my $data = $_[0];
$output->print("<!-- $data -->");
if ($elementLevel == 0) {
$output->print("\n");
}
};
my $SAFE_comment = sub {
my $data = $_[0];
if ($data =~ /--/) {
carp("Interoperability problem: \"--\" in comment text");
}
if ($data =~ /-->/) {
croak("Comment may not contain '-->'");
} else {
$seen{ANYTHING} = 1;
&{$comment};
}
};
my $doctype = sub {
my ($name, $publicId, $systemId) = (@_);
$output->print("<!DOCTYPE $name");
if ($publicId) {
$output->print(" PUBLIC \"$publicId\" \"$systemId\"");
} elsif ($systemId) {
$output->print(" SYSTEM \"$systemId\"");
}
$output->print(">\n");
};
my $SAFE_doctype = sub {
my $name = $_[0];
if ($seen{DOCTYPE}) {
croak("Attempt to insert second DOCTYPE declaration");
} elsif ($seen{ELEMENT}) {
croak("The DOCTYPE declaration must come before the first start tag");
} else {
$seen{ANYTHING} = 1;
$seen{DOCTYPE} = $name;
&{$doctype};
}
};
my $startTag = sub {
my $name = $_[0];
$elementLevel++;
push @elementStack, $name;
$output->print("<$name");
&{$showAttributes}(\@_);
$output->print("$nl>");
};
my $SAFE_startTag = sub {
my $name = $_[0];
_checkAttributes(\@_);
if ($seen{ELEMENT} && $elementLevel == 0) {
croak("Attempt to insert start tag after close of document element");
} elsif ($elementLevel == 0 && $seen{DOCTYPE} && $name ne $seen{DOCTYPE}) {
croak("Document element is \"$name\", but DOCTYPE is \""
. $seen{DOCTYPE}
. "\"");
} else {
$seen{ANYTHING} = 1;
$seen{ELEMENT} = 1;
&{$startTag};
}
};
my $emptyTag = sub {
my $name = $_[0];
$output->print("<$name");
&{$showAttributes}(\@_);
$output->print("$nl />");
};
my $SAFE_emptyTag = sub {
my $name = $_[0];
_checkAttributes(\@_);
if ($seen{ELEMENT} && $elementLevel == 0) {
croak("Attempt to insert empty tag after close of document element");
} elsif ($elementLevel == 0 && $seen{DOCTYPE} && $name ne $seen{DOCTYPE}) {
croak("Document element is \"$name\", but DOCTYPE is \""
. $seen{DOCTYPE}
. "\"");
} else {
$seen{ANYTHING} = 1;
$seen{ELEMENT} = 1;
&{$emptyTag};
}
};
my $endTag = sub {
my $name = $_[0];
my $currentName = pop @elementStack;
$name = $currentName unless $name;
$elementLevel--;
$output->print("</$name$nl>");
};
my $SAFE_endTag = sub {
my $name = $_[0];
my $oldName = $elementStack[$#elementStack];
if ($elementLevel <= 0) {
croak("End tag \"$name\" does not close any open element");
} elsif ($name && ($name ne $oldName)) {
croak("Attempt to end element \"$oldName\" with \"$name\" tag");
} else {
&{$endTag};
}
};
my $characters = sub {
my $data = $_[0];
if ($data =~ /[\&\<\>]/) {
$data =~ s/\&/\&\;/g;
$data =~ s/\</\<\;/g;
$data =~ s/\>/\>\;/g;
}
$output->print($data);
};
my $SAFE_characters = sub {
if ($elementLevel < 1) {
croak("Attempt to insert characters outside of document element");
} else {
&{$characters};
}
};
# Assign the correct closures based on
# the UNSAFE parameter
if ($unsafe) {
$self = {END => $end,
XMLDECL => $xmlDecl,
PI => $pi,
COMMENT => $comment,
DOCTYPE => $doctype,
STARTTAG => $startTag,
EMPTYTAG => $emptyTag,
ENDTAG => $endTag,
CHARACTERS => $characters};
} else {
$self = {END => $SAFE_end,
XMLDECL => $SAFE_xmlDecl,
PI => $SAFE_pi,
COMMENT => $SAFE_comment,
DOCTYPE => $SAFE_doctype,
STARTTAG => $SAFE_startTag,
EMPTYTAG => $SAFE_emptyTag,
ENDTAG => $SAFE_endTag,
CHARACTERS => $SAFE_characters};
}
# Query methods
$self->{IN_ELEMENT} = sub {
my ($ancestor) = (@_);
return $elementStack[$#elementStack] eq $ancestor;
};
$self->{WITHIN_ELEMENT} = sub {
my ($ancestor) = (@_);
my $el;
foreach $el (@elementStack) {
return 1 if $el eq $ancestor;
}
return 0;
};
$self->{CURRENT_ELEMENT} = sub {
return $elementStack[$#elementStack];
};
$self->{ANCESTOR} = sub {
my ($n) = (@_);
return $elementStack[$#elementStack-$n];
};
# Set and get the output destination.
$self->{GETOUTPUT} = sub {
return $output;
};
$self->{SETOUTPUT} = sub {
my $newOutput = $_[0];
# If there is no OUTPUT parameter,
# use standard output
unless ($newOutput) {
$newOutput = new IO::Handle();
$newOutput->fdopen(fileno(STDOUT), "w") ||
croak("Cannot write to standard output");
}
$output = $newOutput;
};
# Set the output.
&{$self->{SETOUTPUT}}($params{OUTPUT});
# Return the blessed object.
return bless $self, $class;
}
########################################################################
# Public methods
########################################################################
#
# Finish writing the document.
#
sub end {
my $self = shift;
&{$self->{END}};
}
#
# Write an XML declaration.
#
sub xmlDecl {
my $self = shift;
&{$self->{XMLDECL}};
}
#
# Write a processing instruction.
#
sub pi {
my $self = shift;
&{$self->{PI}};
}
#
# Write a comment.
#
sub comment {
my $self = shift;
&{$self->{COMMENT}};
}
#
# Write a DOCTYPE declaration.
#
sub doctype {
my $self = shift;
&{$self->{DOCTYPE}};
}
#
# Write a start tag.
#
sub startTag {
my $self = shift;
&{$self->{STARTTAG}};
}
#
# Write an empty tag.
#
sub emptyTag {
my $self = shift;
&{$self->{EMPTYTAG}};
}
#
# Write an end tag.
#
sub endTag {
my $self = shift;
&{$self->{ENDTAG}};
}
#
# Write character data.
#
sub characters {
my $self = shift;
&{$self->{CHARACTERS}};
}
#
# Query the current element.
#
sub in_element {
my $self = shift;
return &{$self->{IN_ELEMENT}};
}
#
# Query the ancestors.
#
sub within_element {
my $self = shift;
return &{$self->{WITHIN_ELEMENT}};
}
#
# Get the name of the current element.
#
sub current_element {
my $self = shift;
return &{$self->{CURRENT_ELEMENT}};
}
#
# Get the name of the numbered ancestor (zero-based).
#
sub ancestor {
my $self = shift;
return &{$self->{ANCESTOR}};
}
#
# Get the current output destination.
#
sub getOutput {
my $self = shift;
return &{$self->{GETOUTPUT}};
}
#
# Set the current output destination.
#
sub setOutput {
my $self = shift;
return &{$self->{SETOUTPUT}};
}
#
# Empty stub.
#
sub addPrefix {
}
#
# Empty stub.
#
sub removePrefix {
}
########################################################################
# Private functions.
########################################################################
#
# Private: check for duplicate attributes.
# Note - this starts at $_[1], because $_[0] is assumed to be an
# element name.
#
sub _checkAttributes {
my %anames;
my $i = 1;
while ($_[$i]) {
my $name = $_[$i];
$i += 2;
if ($anames{$name}) {
croak("Two attributes named \"$name\"");
} else {
$anames{$name} = 1;
}
}
}
#
# Private: escape an attribute value literal.
#
sub _escapeLiteral {
my $data = $_[0];
if ($data =~ /[\&\<\>\"]/) {
$data =~ s/\&/\&\;/g;
$data =~ s/\</\<\;/g;
$data =~ s/\>/\>\;/g;
$data =~ s/\"/\"\;/g;
}
return $data;
}
########################################################################
# XML::Writer::Namespaces - subclass for Namespace processing.
########################################################################
package XML::Writer::Namespaces;
use strict;
use vars qw(@ISA);
use Carp;
@ISA = qw(XML::Writer);
#
# Constructor
#
sub new {
my ($class, %params) = (@_);
my $unsafe = $params{UNSAFE};
# Snarf the prefix map, if any, and
# note the default prefix.
my %prefixMap = ();
if ($params{PREFIX_MAP}) {
%prefixMap = (%{$params{PREFIX_MAP}});
delete $params{PREFIX_MAP};
}
my $defaultPrefix = $prefixMap{''};
delete $prefixMap{''};
# Generate the reverse map for URIs
my %uriMap = ();
my $key;
foreach $key (keys(%prefixMap)) {
$uriMap{$prefixMap{$key}} = $key;
}
# Create an instance of the parent.
my $self = new XML::Writer(%params);
# Snarf the parent's methods that we're
# going to override.
my $OLD_startTag = $self->{STARTTAG};
my $OLD_emptyTag = $self->{EMPTYTAG};
my $OLD_endTag = $self->{ENDTAG};
# State variables
my $prefixCounter = 1;
my @nsDecls = ();
my $nsDecls = {};
my @nsDefaultDecl = ();
my $nsDefaultDecl = undef;
my @nsCopyFlag = ();
my $nsCopyFlag = 0;
#
# Push the current declaration state.
#
my $pushState = sub {
push @nsDecls, $nsDecls;
push @nsDefaultDecl, $nsDefaultDecl;
push @nsCopyFlag, $nsCopyFlag;
$nsCopyFlag = 0;
};
#
# Pop the current declaration state.
#
my $popState = sub {
$nsDecls = pop @nsDecls;
$nsDefaultDecl = pop @nsDefaultDecl;
$nsCopyFlag = pop @nsCopyFlag;
};
#
# Generate a new prefix.
#
my $genPrefix = sub {
my $prefix;
do {
$prefix = "__NS$prefixCounter";
$prefixCounter++;
} while ($uriMap{$prefix});
return $prefix;
};
#
# Perform namespace processing on a single name.
#
my $processName = sub {
my ($nameref, $atts, $attFlag) = (@_);
my ($uri, $local) = @{$$nameref};
my $prefix = $prefixMap{$uri};
# Is this an element name that matches
# the default NS?
if (!$attFlag && ($uri eq $defaultPrefix)) {
unless ($nsDefaultDecl) {
push @{$atts}, 'xmlns';
push @{$atts}, $uri;
$nsDefaultDecl = 1;
}
$$nameref = $local;
# Is there a straight-forward prefix?
} elsif ($prefix) {
unless ($nsDecls->{$uri}) {
# Copy on write (FIXME: duplicated)
unless ($nsCopyFlag) {
$nsCopyFlag = 1;
my %decls = (%{$nsDecls});
$nsDecls = \%decls;
}
$nsDecls->{$uri} = $prefix;
push @{$atts}, "xmlns:$prefix";
push @{$atts}, $uri;
}
$$nameref = "$prefix:$local";
} else {
$prefix = &{$genPrefix}();
$prefixMap{$uri} = $prefix;
$uriMap{$prefix} = $uri;
unless ($nsCopyFlag) {
$nsCopyFlag = 1;
my %decls = (%{$nsDecls});
$nsDecls = \%decls;
}
$nsDecls->{$uri} = $prefix;
push @{$atts}, "xmlns:$prefix";
push @{$atts}, $uri;
$$nameref = "$prefix:$local";
}
};
#
# Perform namespace processing on element and attribute names.
#
my $nsProcess = sub {
if (ref($_[0]->[0]) eq 'ARRAY') {
&{$processName}(\$_[0]->[0], $_[0], 0);
}
my $i = 1;
while ($_[0]->[$i]) {
if (ref($_[0]->[$i]) eq 'ARRAY') {
&{$processName}(\$_[0]->[$i], $_[0], 1);
}
$i += 2;
}
};
#
# Start tag, with NS processing
#
$self->{STARTTAG} = sub {
my $name = $_[0];
unless ($unsafe) {
_checkNSNames(\@_);
}
&{$pushState}();
&{$nsProcess}(\@_);
&{$OLD_startTag};
};
#
# Empty tag, with NS processing
#
$self->{EMPTYTAG} = sub {
unless ($unsafe) {
_checkNSNames(\@_);
}
&{$pushState}();
&{$nsProcess}(\@_);
&{$OLD_emptyTag};
&{$popState}();
};
#
# End tag, with NS processing
#
$self->{ENDTAG} = sub {
my $name = $_[0];
&{$nsProcess}(\@_);
&{$OLD_endTag};
&{$popState}();
};
#
# Processing instruction, but only if not UNSAFE.
#
unless ($unsafe) {
my $OLD_pi = $self->{PI};
$self->{PI} = sub {
my $target = $_[0];
if ($target =~ /:/) {
croak "PI target '$target' contains a colon.";
}
&{$OLD_pi};
}
};
#
# Add a prefix to the prefix map.
#
$self->{ADDPREFIX} = sub {
my ($uri, $prefix) = (@_);
if ($prefix) {
$prefixMap{$uri} = $prefix;
$uriMap{$prefix} = $uri;
} else {
$defaultPrefix = $uri;
}
};
#
# Remove a prefix from the prefix map.
#
$self->{REMOVEPREFIX} = sub {
my ($uri) = (@_);
if ($defaultPrefix eq $uri) {
$defaultPrefix = undef;
}
delete $prefixMap{$uri};
};
#
# Bless and return the object.
#
return bless $self, $class;
}
#
# Add a preferred prefix for a namespace URI.
#
sub addPrefix {
my $self = shift;
return &{$self->{ADDPREFIX}};
}
#
# Remove a preferred prefix for a namespace URI.
#
sub removePrefix {
my $self = shift;
return &{$self->{REMOVEPREFIX}};
}
#
# Check names.
#
sub _checkNSNames {
my $names = $_[0];
my $i = 1;
my $name = $names->[0];
# Check the element name.
if (ref($name) eq 'ARRAY') {
if ($name->[1] =~ /:/) {
croak("Local part of element name '" .
$name->[1] .
"' contains a colon.");
}
} elsif ($name =~ /:/) {
croak("Element name '$name' contains a colon.");
}
# Check the attribute names.
while ($names->[$i]) {
my $name = $names->[$i];
if (ref($name) eq 'ARRAY') {
my $local = $name->[1];
if ($local =~ /:/) {
croak "Local part of attribute name '$local' contains a colon.";
}
} else {
if ($name =~ /^(xmlns|.*:)/) {
if ($name =~ /^xmlns/) {
croak "Attribute name '$name' begins with 'xmlns'";
} elsif ($name =~ /:/) {
croak "Attribute name '$name' contains ':'";
}
}
}
$i += 2;
}
}
1;
__END__
########################################################################
# POD Documentation
########################################################################
=head1 NAME
XML::Writer - Perl extension for writing XML documents.
=head1 SYNOPSIS
use XML::Writer;
use IO;
my $output = new IO::File(">output.xml");
my $writer = new XML::Writer(OUTPUT => $output);
$writer->startTag("greeting",
"class" => "simple");
$writer->characters("Hello, world!");
$writer->endTag("greeting");
$writer->end();
$output->close();
=head1 DESCRIPTION
XML::Writer is a helper module for Perl programs that write an XML
document. The module handles all escaping for attribute values and
character data and constructs different types of markup, such as tags,
comments, and processing instructions.
By default, the module performs several well-formedness checks to
catch errors during output. This behaviour can be extremely useful
during development and debugging, but it can be turned off for
production-grade code.
The module can operate either in regular mode in or Namespace
processing mode. In Namespace mode, the module will generate
Namespace Declarations itself, and will perform additional checks on
the output.
=head1 METHODS
=head2 Writing XML
=over 4
=item new([$params])
Create a new XML::Writer object:
my $writer = new XML::Writer(OUTPUT => $output, NEWLINES => 1);
Arguments are an anonymous hash array of parameters:
=over 4
=item OUTPUT
An object blessed into IO::Handle or one of its subclasses (such as
IO::File); if this parameter is not present, the module will write to
standard output.
=item NAMESPACES
A true (1) or false (0, undef) value; if this parameter is present and
its value is true, then the module will accept two-member array
reference in the place of element and attribute names, as in the
following example:
my $rdfns = "http://www.w3.org/1999/02/22-rdf-syntax-ns#";
my $writer = new XML::Writer(NAMESPACES => 1);
$writer->startTag([$rdfns, "Description"]);
The first member of the array is a namespace URI, and the second part
is the local part of a qualified name. The module will automatically
generate appropriate namespace declarations and will replace the URI
part with a prefix.
=item PREFIX_MAP
A hash reference; if this parameter is present and the module is
performing namespace processing (see the NAMESPACES parameter), then
the module will use this hash to look up preferred prefixes for
namespace URIs:
my $rdfns = "http://www.w3.org/1999/02/22-rdf-syntax-ns#";
my $writer = new XML::Writer(NAMESPACES => 1,
PREFIX_MAP => {$rdfns => 'rdf'});
The keys in the hash table are namespace URIs, and the values are the
associated prefixes. If there is not a preferred prefix for the
namespace URI in this hash, then the module will automatically
generate prefixes of the form "__NS1", "__NS2", etc.
To set the default namespace, use '' for the prefix.
=item NEWLINES
A true or false value; if this parameter is present and its value is
true, then the module will insert an extra newline before the closing
delimiter of start, end, and empty tags to guarantee that the document
does not end up as a single, long line. If the paramter is not
present, the module will not insert the newlines.
=item UNSAFE
A true or false value; if this parameter is present and its value is
true, then the module will skip most well-formedness error checking.
If the parameter is not present, the module will perform the
well-formedness error checking by default. Turn off error checking at
your own risk!
=back
=item end()
Finish creating an XML document. This method will check that the
document has exactly one document element, and that all start tags are
closed:
$writer->end();
=item xmlDecl([$encoding, $standalone])
Add an XML declaration to the beginning of an XML document. The
version will always be "1.0". If you provide a non-null encoding or
standalone argument, its value will appear in the declaration.
$writer->xmlDecl("UTF-8");
=item doctype($name, [$publicId, $systemId])
Add a DOCTYPE declaration to an XML document. The declaration must
appear before the beginning of the root element. If you provide a
publicId, you must provide a systemId as well, but you may provide
just a system ID.
$writer->doctype("html");
=item comment($text)
Add a comment to an XML document. If the comment appears outside the
document element (either before the first start tag or after the last
end tag), the module will add a carriage return after it to improve
readability:
$writer->comment("This is a comment");
=item pi($target [, $data])
Add a processing instruction to an XML document:
$writer->pi('xml-stylesheet', 'href="style.css" type="text/css"');
If the processing instruction appears outside the document element
(either before the first start tag or after the last end tag), the
module will add a carriage return after it to improve readability.
The $target argument must be a single XML name. If you provide the
$data argument, the module will insert its contents following the
$target argument, separated by a single space.
=item startTag($name [, $aname1 => $value1, ...])
Add a start tag to an XML document. Any arguments after the element
name are assumed to be name/value pairs for attributes: the module
will escape all '&', '<', '>', and '"' characters in the attribute
values using the predefined XML entities:
$writer->startTag('doc', 'version' => '1.0',
'status' => 'draft',
'topic' => 'AT&T');
All start tags must eventually have matching end tags.
=item emptyTag($name [, $aname1 => $value1, ...])
Add an empty tag to an XML document. Any arguments after the element
name are assumed to be name/value pairs for attributes (see startTag()
for details):
$writer->emptyTag('img', 'src' => 'portrait.jpg',
'alt' => 'Portrait of Emma.');
=item endTag([$name])
Add an end tag to an XML document. The end tag must match the closest
open start tag, and there must be a matching and properly-nested end
tag for every start tag:
$writer->endTag('doc');
If the $name argument is omitted, then the module will automatically
supply the name of the currently open element:
$writer->startTag('p');
$writer->endTag();
=item characters($data)
Add character data to an XML document. All '<', '>', and '&'
characters in the $data argument will automatically be escaped using
the predefined XML entities:
$writer->characters("Here is the formula: ");
$writer->characters("a < 100 && a > 5");
You may invoke this method only within the document element
(i.e. after the first start tag and before the last end tag).
=back
=head2 Querying XML
=over 4
=item in_element($name)
Return a true value if the most recent open element matches $name:
if ($writer->in_element('dl')) {
$writer->startTag('dt');
} else {
$writer->startTag('li');
}
=item within_element($name)
Return a true value if any open elemnet matches $name:
if ($writer->within_element('body')) {
$writer->startTag('h1');
} else {
$writer->startTag('title');
}
=item current_element()
Return the name of the currently open element:
my $name = $writer->current_element();
This is the equivalent of
my $name = $writer->ancestor(0);
=item ancestor($n)
Return the name of the nth ancestor, where $n=0 for the current open
element.
=back
=head2 Additional Namespace Support
WARNING: you must not use these methods while you are writing a
document, or the results will be unpredictable.
=over 4
=item addPrefix($uri, $prefix)
Add a preferred mapping between a Namespace URI and a prefix. See
also the PREFIX_MAP constructor parameter.
To set the default namespace, omit the $prefix parameter or set it to
''.
=item removePrefix($uri)
Remove a preferred mapping between a Namespace URI and a prefix.
To set the default namespace, omit the $prefix parameter or set it to
''.
=back
=head1 ERROR REPORTING
With the default settings, the XML::Writer module can detect several
basic XML well-formedness errors:
=over 4
=item *
Lack of a (top-level) document element, or multiple document elements.
=item *
Unclosed start tags.
=item *
Misplaced delimiters in the contents of processing instructions or
comments.
=item *
Misplaced or duplicate XML declaration(s).
=item *
Misplaced or duplicate DOCTYPE declaration(s).
=item *
Mismatch between the document type name in the DOCTYPE declaration and
the name of the document element.
=item *
Mismatched start and end tags.
=item *
Attempts to insert character data outside the document element.
=item *
Duplicate attributes with the same name.
=back
During Namespace processing, the module can detect the following
additional errors:
=over 4
=item *
Attempts to use PI targets or element or attribute names containing a
colon.
=item *
Attempts to use attributes with names beginning "xmlns".
=back
To ensure full error detection, a program must also invoke the end
method when it has finished writing a document:
$writer->startTag('greeting');
$writer->characters("Hello, world!");
$writer->endTag('greeting');
$writer->end();
This error reporting can catch many hidden bugs in Perl programs that
create XML documents; however, if necessary, it can be turned off by
providing an UNSAFE parameter:
my $writer = new XML::Writer(OUTPUT => $output, UNSAFE => 1);
=head1 AUTHOR
David Megginson, david@megginson.com
=head1 SEE ALSO
XML::Parser
=cut
|