Newer
Older
#include "common.hpp"
TEST(parse_pi_skip)
{
xml_document doc;
unsigned int flag_sets[] = {parse_fragment, parse_fragment | parse_declaration};
for (unsigned int i = 0; i < sizeof(flag_sets) / sizeof(flag_sets[0]); ++i)
{
unsigned int flags = flag_sets[i];
CHECK(doc.load(STR("<?pi?><?pi value?>"), flags));
CHECK(!doc.first_child());
CHECK(doc.load(STR("<?pi <tag/> value?>"), flags));
CHECK(!doc.first_child());
}
}
TEST(parse_pi_parse)
{
xml_document doc;
CHECK(doc.load(STR("<?pi1?><?pi2 value?>"), parse_fragment | parse_pi));
xml_node pi1 = doc.first_child();
xml_node pi2 = doc.last_child();
CHECK(pi1 != pi2);
CHECK(pi1.type() == node_pi);
CHECK_STRING(pi1.name(), STR("pi1"));
CHECK_STRING(pi1.value(), STR(""));
CHECK(pi2.type() == node_pi);
CHECK_STRING(pi2.name(), STR("pi2"));
CHECK_STRING(pi2.value(), STR("value"));
}
TEST(parse_pi_parse_spaces)
{
xml_document doc;
CHECK(doc.load(STR("<?target \r\n\t value ?>"), parse_fragment | parse_pi));
xml_node pi = doc.first_child();
CHECK(pi.type() == node_pi);
CHECK_STRING(pi.name(), STR("target"));
CHECK_STRING(pi.value(), STR("value "));
}
TEST(parse_pi_error)
{
xml_document doc;
unsigned int flag_sets[] = {parse_fragment, parse_fragment | parse_pi};
for (unsigned int i = 0; i < sizeof(flag_sets) / sizeof(flag_sets[0]); ++i)
{
unsigned int flags = flag_sets[i];
CHECK(doc.load(STR("<?"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<??"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?>"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?#?>"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name>"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name ?"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name?"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name? "), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name? "), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name "), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name "), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name "), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name value"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name value "), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name value "), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name value ?"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name value ? "), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name value ? >"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name value ? > "), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name&"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?name&?"), flags).status == status_bad_pi);
}
CHECK(doc.load(STR("<?xx#?>"), parse_fragment | parse_pi).status == status_bad_pi);
CHECK(doc.load(STR("<?name&?>"), parse_fragment | parse_pi).status == status_bad_pi);
CHECK(doc.load(STR("<?name& x?>"), parse_fragment | parse_pi).status == status_bad_pi);
}
TEST(parse_comments_skip)
{
xml_document doc;
CHECK(doc.load(STR("<!----><!--value-->"), parse_fragment));
CHECK(!doc.first_child());
}
TEST(parse_comments_parse)
{
xml_document doc;
CHECK(doc.load(STR("<!----><!--value-->"), parse_fragment | parse_comments));
xml_node c1 = doc.first_child();
xml_node c2 = doc.last_child();
CHECK(c1 != c2);
CHECK(c1.type() == node_comment);
CHECK_STRING(c1.name(), STR(""));
CHECK_STRING(c1.value(), STR(""));
CHECK(c2.type() == node_comment);
CHECK_STRING(c2.name(), STR(""));
CHECK_STRING(c2.value(), STR("value"));
}
TEST(parse_comments_parse_no_eol)
{
xml_document doc;
CHECK(doc.load(STR("<!--\r\rval1\rval2\r\nval3\nval4\r\r-->"), parse_fragment | parse_comments));
xml_node c = doc.first_child();
CHECK(c.type() == node_comment);
CHECK_STRING(c.value(), STR("\r\rval1\rval2\r\nval3\nval4\r\r"));
}
TEST(parse_comments_parse_eol)
{
xml_document doc;
CHECK(doc.load(STR("<!--\r\rval1\rval2\r\nval3\nval4\r\r-->"), parse_fragment | parse_comments | parse_eol));
xml_node c = doc.first_child();
CHECK(c.type() == node_comment);
CHECK_STRING(c.value(), STR("\n\nval1\nval2\nval3\nval4\n\n"));
}
TEST(parse_comments_error)
{
xml_document doc;
unsigned int flag_sets[] = {parse_fragment, parse_fragment | parse_comments, parse_fragment | parse_comments | parse_eol};
for (unsigned int i = 0; i < sizeof(flag_sets) / sizeof(flag_sets[0]); ++i)
{
unsigned int flags = flag_sets[i];
CHECK(doc.load(STR("<!-"), flags).status == status_bad_comment);
CHECK(doc.load(STR("<!--"), flags).status == status_bad_comment);
CHECK(doc.load(STR("<!--v"), flags).status == status_bad_comment);
CHECK(doc.load(STR("<!-->"), flags).status == status_bad_comment);
CHECK(doc.load(STR("<!--->"), flags).status == status_bad_comment);
CHECK(doc.load(STR("<!-- <!-- --><!- -->"), flags).status == status_bad_comment);
}
}
TEST(parse_cdata_skip)
{
xml_document doc;
CHECK(doc.load(STR("<![CDATA[]]><![CDATA[value]]>"), parse_fragment));
CHECK(!doc.first_child());
}
TEST(parse_cdata_skip_contents)
{
xml_document doc;
CHECK(doc.load(STR("<node><![CDATA[]]>hello<![CDATA[value]]>, world!</node>"), parse_fragment));
CHECK_NODE(doc, STR("<node>hello, world!</node>"));
}
TEST(parse_cdata_parse)
{
xml_document doc;
CHECK(doc.load(STR("<![CDATA[]]><![CDATA[value]]>"), parse_fragment | parse_cdata));
xml_node c1 = doc.first_child();
xml_node c2 = doc.last_child();
CHECK(c1 != c2);
CHECK(c1.type() == node_cdata);
CHECK_STRING(c1.name(), STR(""));
CHECK_STRING(c1.value(), STR(""));
CHECK(c2.type() == node_cdata);
CHECK_STRING(c2.name(), STR(""));
CHECK_STRING(c2.value(), STR("value"));
}
TEST(parse_cdata_parse_no_eol)
{
xml_document doc;
CHECK(doc.load(STR("<![CDATA[\r\rval1\rval2\r\nval3\nval4\r\r]]>"), parse_fragment | parse_cdata));
xml_node c = doc.first_child();
CHECK(c.type() == node_cdata);
CHECK_STRING(c.value(), STR("\r\rval1\rval2\r\nval3\nval4\r\r"));
}
TEST(parse_cdata_parse_eol)
{
xml_document doc;
CHECK(doc.load(STR("<![CDATA[\r\rval1\rval2\r\nval3\nval4\r\r]]>"), parse_fragment | parse_cdata | parse_eol));
xml_node c = doc.first_child();
CHECK(c.type() == node_cdata);
CHECK_STRING(c.value(), STR("\n\nval1\nval2\nval3\nval4\n\n"));
}
TEST(parse_cdata_error)
{
xml_document doc;
unsigned int flag_sets[] = {parse_fragment, parse_fragment | parse_cdata, parse_fragment | parse_cdata | parse_eol};
for (unsigned int i = 0; i < sizeof(flag_sets) / sizeof(flag_sets[0]); ++i)
{
unsigned int flags = flag_sets[i];
CHECK(doc.load(STR("<!["), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![C"), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CD"), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CDA"), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CDAT"), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CDATA"), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CDATA["), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CDATA[]"), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CDATA[data"), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CDATA[data]"), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CDATA[data]]"), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CDATA[>"), flags).status == status_bad_cdata);
CHECK(doc.load(STR("<![CDATA[ <![CDATA[]]><![CDATA ]]>"), flags).status == status_bad_cdata);
}
}
TEST(parse_ws_pcdata_skip)
{
xml_document doc;
CHECK(doc.load(STR(" "), parse_fragment));
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
CHECK(!doc.first_child());
CHECK(doc.load(STR("<root> <node> </node> </root>"), parse_minimal));
xml_node root = doc.child(STR("root"));
CHECK(root.first_child() == root.last_child());
CHECK(!root.first_child().first_child());
}
TEST(parse_ws_pcdata_parse)
{
xml_document doc;
CHECK(doc.load(STR("<root> <node> </node> </root>"), parse_minimal | parse_ws_pcdata));
xml_node root = doc.child(STR("root"));
xml_node c1 = root.first_child();
xml_node c2 = c1.next_sibling();
xml_node c3 = c2.next_sibling();
CHECK(c3 == root.last_child());
CHECK(c1.type() == node_pcdata);
CHECK_STRING(c1.value(), STR(" "));
CHECK(c3.type() == node_pcdata);
CHECK_STRING(c3.value(), STR(" "));
CHECK(c2.first_child() == c2.last_child());
CHECK(c2.first_child().type() == node_pcdata);
CHECK_STRING(c2.first_child().value(), STR(" "));
}
arseny.kapoulkine
committed
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
static int get_tree_node_count(xml_node n)
{
int result = 1;
for (xml_node c = n.first_child(); c; c = c.next_sibling())
result += get_tree_node_count(c);
return result;
}
TEST(parse_ws_pcdata_permutations)
{
struct test_data_t
{
unsigned int mask; // 1 = default flags, 2 = parse_ws_pcdata, 4 = parse_ws_pcdata_single
const pugi::char_t* source;
const pugi::char_t* result;
int nodes; // negative if parsing should fail
};
test_data_t test_data[] =
{
// external pcdata should be discarded (whitespace or not)
{7, STR("ext1<node/>"), STR("<node />"), 2},
{7, STR("ext1<node/>ext2"), STR("<node />"), 2},
{7, STR(" <node/>"), STR("<node />"), 2},
{7, STR("<node/> "), STR("<node />"), 2},
{7, STR(" <node/> "), STR("<node />"), 2},
// inner pcdata should be preserved
{7, STR("<node>inner</node>"), STR("<node>inner</node>"), 3},
{7, STR("<node>inner1<child/>inner2</node>"), STR("<node>inner1<child />inner2</node>"), 5},
{7, STR("<node>inner1<child>deep</child>inner2</node>"), STR("<node>inner1<child>deep</child>inner2</node>"), 6},
// empty pcdata nodes should never be created
{7, STR("<node>inner1<child></child>inner2</node>"), STR("<node>inner1<child />inner2</node>"), 5},
{7, STR("<node><child></child>inner2</node>"), STR("<node><child />inner2</node>"), 4},
{7, STR("<node>inner1<child></child></node>"), STR("<node>inner1<child /></node>"), 4},
{7, STR("<node><child></child></node>"), STR("<node><child /></node>"), 3},
// comments, pi or other nodes should not cause pcdata creation either
{7, STR("<node><!----><child><?pi?></child><![CDATA[x]]></node>"), STR("<node><child /><![CDATA[x]]></node>"), 4},
// leading/trailing pcdata whitespace should be preserved (note: this will change if parse_ws_pcdata_trim is introduced)
{7, STR("<node>\t \tinner1<child> deep </child>\t\ninner2\n\t</node>"), STR("<node>\t \tinner1<child> deep </child>\t\ninner2\n\t</node>"), 6},
// whitespace-only pcdata preservation depends on the parsing mode
{1, STR("<node>\n\t<child> </child>\n\t<child> <deep> </deep> </child>\n\t<!---->\n\t</node>"), STR("<node><child /><child><deep /></child></node>"), 5},
{2, STR("<node>\n\t<child> </child>\n\t<child> <deep> </deep> </child>\n\t<!---->\n\t</node>"), STR("<node>\n\t<child> </child>\n\t<child> <deep> </deep> </child>\n\t\n\t</node>"), 13},
{4, STR("<node>\n\t<child> </child>\n\t<child> <deep> </deep> </child>\n\t<!---->\n\t</node>"), STR("<node><child> </child><child><deep> </deep></child></node>"), 7},
// current implementation of parse_ws_pcdata_single has an unfortunate bug; reproduce it here
{4, STR("<node>\t\t<!---->\n\n</node>"), STR("<node>\n\n</node>"), 3},
// error case: terminate PCDATA in the middle
{7, STR("<node>abcdef"), STR("<node>abcdef</node>"), -3},
{5, STR("<node> "), STR("<node />"), -2},
{2, STR("<node> "), STR("<node> </node>"), -3},
arseny.kapoulkine
committed
// error case: terminate PCDATA as early as possible
{7, STR("<node>"), STR("<node />"), -2},
{7, STR("<node>a"), STR("<node>a</node>"), -3},
{5, STR("<node> "), STR("<node />"), -2},
{2, STR("<node> "), STR("<node> </node>"), -3},
arseny.kapoulkine
committed
};
for (size_t i = 0; i < sizeof(test_data) / sizeof(test_data[0]); ++i)
{
const test_data_t& td = test_data[i];
for (int flag = 0; flag < 3; ++flag)
{
if (td.mask & (1 << flag))
{
unsigned int flags[] = {parse_default, parse_default | parse_ws_pcdata, parse_default | parse_ws_pcdata_single};
xml_document doc;
CHECK((td.nodes > 0) == doc.load(td.source, flags[flag]));
CHECK_NODE(doc, td.result);
int nodes = get_tree_node_count(doc);
CHECK((td.nodes < 0 ? -td.nodes : td.nodes) == nodes);
}
}
}
}
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
TEST(parse_ws_pcdata_fragment_permutations)
{
struct test_data_t
{
unsigned int mask; // 1 = default flags, 2 = parse_ws_pcdata, 4 = parse_ws_pcdata_single
const pugi::char_t* source;
const pugi::char_t* result;
int nodes; // negative if parsing should fail
};
test_data_t test_data[] =
{
// external pcdata should be preserved
{7, STR("ext1"), STR("ext1"), 2},
{5, STR(" "), STR(""), 1},
{2, STR(" "), STR(" "), 2},
{7, STR("ext1<node/>"), STR("ext1<node />"), 3},
{7, STR("<node/>ext2"), STR("<node />ext2"), 3},
{7, STR("ext1<node/>ext2"), STR("ext1<node />ext2"), 4},
{7, STR("ext1<node1/>ext2<node2/>ext3"), STR("ext1<node1 />ext2<node2 />ext3"), 6},
{5, STR(" <node/>"), STR("<node />"), 2},
{2, STR(" <node/>"), STR(" <node />"), 3},
{5, STR("<node/> "), STR("<node />"), 2},
{2, STR("<node/> "), STR("<node /> "), 3},
{5, STR(" <node/> "), STR("<node />"), 2},
{2, STR(" <node/> "), STR(" <node /> "), 4},
{5, STR(" <node1/> <node2/> "), STR("<node1 /><node2 />"), 3},
{2, STR(" <node1/> <node2/> "), STR(" <node1 /> <node2 /> "), 6},
};
for (size_t i = 0; i < sizeof(test_data) / sizeof(test_data[0]); ++i)
{
const test_data_t& td = test_data[i];
for (int flag = 0; flag < 3; ++flag)
{
if (td.mask & (1 << flag))
{
unsigned int flags[] = {parse_default, parse_default | parse_ws_pcdata, parse_default | parse_ws_pcdata_single};
xml_document doc;
CHECK((td.nodes > 0) == doc.load(td.source, flags[flag] | parse_fragment));
CHECK_NODE(doc, td.result);
int nodes = get_tree_node_count(doc);
CHECK((td.nodes < 0 ? -td.nodes : td.nodes) == nodes);
}
}
}
}
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
TEST(parse_pcdata_no_eol)
{
xml_document doc;
CHECK(doc.load(STR("<root>\r\rval1\rval2\r\nval3\nval4\r\r</root>"), parse_minimal));
CHECK_STRING(doc.child_value(STR("root")), STR("\r\rval1\rval2\r\nval3\nval4\r\r"));
}
TEST(parse_pcdata_eol)
{
xml_document doc;
CHECK(doc.load(STR("<root>\r\rval1\rval2\r\nval3\nval4\r\r</root>"), parse_minimal | parse_eol));
CHECK_STRING(doc.child_value(STR("root")), STR("\n\nval1\nval2\nval3\nval4\n\n"));
}
TEST(parse_pcdata_skip_ext)
{
xml_document doc;
CHECK(doc.load(STR("pre<root/>post"), parse_minimal));
CHECK(doc.first_child() == doc.last_child());
CHECK(doc.first_child().type() == node_element);
}
TEST(parse_pcdata_error)
{
xml_document doc;
CHECK(doc.load(STR("<root>pcdata"), parse_minimal).status == status_end_element_mismatch);
}
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
TEST(parse_pcdata_trim)
{
struct test_data_t
{
const pugi::char_t* source;
const pugi::char_t* result;
unsigned int flags;
};
test_data_t test_data[] =
{
{ STR("<node> text</node>"), STR("text"), 0 },
{ STR("<node>\t\n text</node>"), STR("text"), 0 },
{ STR("<node>text </node>"), STR("text"), 0 },
{ STR("<node>text \t\n</node>"), STR("text"), 0 },
{ STR("<node>\r\n\t text \t\n\r</node>"), STR("text"), 0 },
{ STR(" text"), STR("text"), parse_fragment },
{ STR("\t\n text"), STR("text"), parse_fragment },
{ STR("text "), STR("text"), parse_fragment },
{ STR("text \t\n"), STR("text"), parse_fragment },
{ STR("\r\n\t text \t\n\r"), STR("text"), parse_fragment },
{ STR("<node>\r\n\t text \t\n\r more \r\n\t</node>"), STR("text \t\n\r more"), 0 },
{ STR("<node>\r\n\t text \t\n\r more \r\n\t</node>"), STR("text \t\n\n more"), parse_eol },
{ STR("<node>\r\n\t text \r\n\r\n\r\n\r\n\r\n\r\n\r\n more \r\n\t</node>"), STR("text \n\n\n\n\n\n\n more"), parse_eol },
{ STR("<node> test&&&&&&& </node>"), STR("test&&&&&&&"), 0 },
{ STR("<node> test&&&&&&& </node>"), STR("test&&&&&&&"), parse_escapes },
{ STR(" test&&&&&&& "), STR("test&&&&&&&"), parse_fragment | parse_escapes },
{ STR("<node>\r\n\t text \t\n\r m&&e \r\n\t</node>"), STR("text \t\n\n m&&e"), parse_eol | parse_escapes }
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
};
for (size_t i = 0; i < sizeof(test_data) / sizeof(test_data[0]); ++i)
{
const test_data_t& td = test_data[i];
xml_document doc;
CHECK(doc.load(td.source, td.flags | parse_trim_pcdata));
const pugi::char_t* value = doc.child(STR("node")) ? doc.child_value(STR("node")) : doc.text().get();
CHECK_STRING(value, td.result);
}
}
TEST(parse_pcdata_trim_empty)
{
unsigned int flags[] = { 0, parse_ws_pcdata, parse_ws_pcdata_single, parse_ws_pcdata | parse_ws_pcdata_single };
for (size_t i = 0; i < sizeof(flags) / sizeof(flags[0]); ++i)
{
xml_document doc;
CHECK(doc.load(STR("<node> </node>"), flags[i] | parse_trim_pcdata));
xml_node node = doc.child(STR("node"));
CHECK(node);
CHECK(!node.first_child());
}
}
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
TEST(parse_escapes_skip)
{
xml_document doc;
CHECK(doc.load(STR("<node id='<>&'"'><>&'"</node>"), parse_minimal));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id")).value(), STR("<>&'""));
}
TEST(parse_escapes_parse)
{
xml_document doc;
CHECK(doc.load(STR("<node id='<>&'"'><>&'"</node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("<>&'\""));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id")).value(), STR("<>&'\""));
}
TEST(parse_escapes_code)
{
xml_document doc;
CHECK(doc.load(STR("<node>  </node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("\01 "));
}
TEST(parse_escapes_code_exhaustive_dec)
{
xml_document doc;
CHECK(doc.load(STR("<node>&#/;	&#:;&#a;&#A;
</node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("&#/;\x1\x2\x3\x4\x5\x6\x7\x8\x9&#:;&#a;&#A;
"));
}
TEST(parse_escapes_code_exhaustive_hex)
{
xml_document doc;
CHECK(doc.load(STR("<node>&#x/;	&#x:;&#x@;

&#xG;&#x`;

&#xg;</node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("&#x/;\x1\x2\x3\x4\x5\x6\x7\x8\x9&#x:;&#x@;\xa\xb\xc\xd\xe\xf&#xG;&#x`;\xa\xb\xc\xd\xe\xf&#xg;"));
}
TEST(parse_escapes_code_restore)
{
xml_document doc;
CHECK(doc.load(STR("<node>  - - </node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("  - - "));
}
TEST(parse_escapes_char_restore)
{
xml_document doc;
CHECK(doc.load(STR("<node>&q &qu &quo " </node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("&q &qu &quo " "));
CHECK(doc.load(STR("<node>&a &ap &apo &apos </node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("&a &ap &apo &apos "));
CHECK(doc.load(STR("<node>&a &am & </node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("&a &am & "));
CHECK(doc.load(STR("<node>&l < </node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("&l < "));
CHECK(doc.load(STR("<node>&g > </node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("&g > "));
}
TEST(parse_escapes_unicode)
{
xml_document doc;
CHECK(doc.load(STR("<node>γγ𤭢</node>"), parse_minimal | parse_escapes));
#ifdef PUGIXML_WCHAR_MODE
const pugi::char_t* v = doc.child_value(STR("node"));
size_t wcharsize = sizeof(wchar_t);
CHECK(v[0] == 0x3b3 && v[1] == 0x3b3 && (wcharsize == 2 ? v[2] == wchar_cast(0xd852) && v[3] == wchar_cast(0xdf62) : v[2] == wchar_cast(0x24b62)));
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
#else
CHECK_STRING(doc.child_value(STR("node")), "\xce\xb3\xce\xb3\xf0\xa4\xad\xa2");
#endif
}
TEST(parse_escapes_error)
{
xml_document doc;
CHECK(doc.load(STR("<node>g;&#ab;"</node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("g;&#ab;""));
CHECK(!doc.load(STR("<node id='")));
CHECK(!doc.load(STR("<node id='&g")));
CHECK(!doc.load(STR("<node id='>")));
CHECK(!doc.load(STR("<node id='&l")));
CHECK(!doc.load(STR("<node id='<")));
CHECK(!doc.load(STR("<node id='&a")));
CHECK(!doc.load(STR("<node id='&")));
CHECK(!doc.load(STR("<node id='&apos")));
}
TEST(parse_escapes_code_invalid)
{
xml_document doc;
CHECK(doc.load(STR("<node>&#;&#x;&;&#x-;&#-;</node>"), parse_minimal | parse_escapes));
CHECK_STRING(doc.child_value(STR("node")), STR("&#;&#x;&;&#x-;&#-;"));
}
TEST(parse_escapes_attribute)
{
xml_document doc;
for (int wnorm = 0; wnorm < 2; ++wnorm)
for (int eol = 0; eol < 2; ++eol)
for (int wconv = 0; wconv < 2; ++wconv)
{
unsigned int flags = parse_escapes;
flags |= (wnorm ? parse_wnorm_attribute : 0);
flags |= (eol ? parse_eol : 0);
flags |= (wconv ? parse_wconv_attribute : 0);
CHECK(doc.load(STR("<node id='"'/>"), flags));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id")).value(), STR("\""));
}
}
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
TEST(parse_attribute_spaces)
{
xml_document doc;
CHECK(doc.load(STR("<node id1='v1' id2 ='v2' id3= 'v3' id4 = 'v4' id5 \n\r\t = \r\t\n 'v5' />"), parse_minimal));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id1")).value(), STR("v1"));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id2")).value(), STR("v2"));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id3")).value(), STR("v3"));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id4")).value(), STR("v4"));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id5")).value(), STR("v5"));
}
TEST(parse_attribute_quot)
{
xml_document doc;
CHECK(doc.load(STR("<node id1='v1' id2=\"v2\"/>"), parse_minimal));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id1")).value(), STR("v1"));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id2")).value(), STR("v2"));
}
TEST(parse_attribute_no_eol_no_wconv)
{
xml_document doc;
CHECK(doc.load(STR("<node id=' \t\r\rval1 \rval2\r\nval3\nval4\r\r'/>"), parse_minimal));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id")).value(), STR(" \t\r\rval1 \rval2\r\nval3\nval4\r\r"));
}
TEST(parse_attribute_eol_no_wconv)
{
xml_document doc;
CHECK(doc.load(STR("<node id=' \t\r\rval1 \rval2\r\nval3\nval4\r\r'/>"), parse_minimal | parse_eol));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id")).value(), STR(" \t\n\nval1 \nval2\nval3\nval4\n\n"));
}
TEST(parse_attribute_no_eol_wconv)
{
xml_document doc;
CHECK(doc.load(STR("<node id=' \t\r\rval1 \rval2\r\nval3\nval4\r\r'/>"), parse_minimal | parse_wconv_attribute));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id")).value(), STR(" val1 val2 val3 val4 "));
}
TEST(parse_attribute_eol_wconv)
{
xml_document doc;
CHECK(doc.load(STR("<node id=' \t\r\rval1 \rval2\r\nval3\nval4\r\r'/>"), parse_minimal | parse_eol | parse_wconv_attribute));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id")).value(), STR(" val1 val2 val3 val4 "));
}
TEST(parse_attribute_wnorm)
{
xml_document doc;
for (int eol = 0; eol < 2; ++eol)
for (int wconv = 0; wconv < 2; ++wconv)
{
unsigned int flags = parse_minimal | parse_wnorm_attribute | (eol ? parse_eol : 0) | (wconv ? parse_wconv_attribute : 0);
CHECK(doc.load(STR("<node id=' \t\r\rval1 \rval2\r\nval3\nval4\r\r'/>"), flags));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id")).value(), STR("val1 val2 val3 val4"));
}
}
TEST(parse_attribute_variations)
{
xml_document doc;
for (int wnorm = 0; wnorm < 2; ++wnorm)
for (int eol = 0; eol < 2; ++eol)
for (int wconv = 0; wconv < 2; ++wconv)
for (int escapes = 0; escapes < 2; ++escapes)
{
unsigned int flags = parse_minimal;
flags |= (wnorm ? parse_wnorm_attribute : 0);
flags |= (eol ? parse_eol : 0);
flags |= (wconv ? parse_wconv_attribute : 0);
flags |= (escapes ? parse_escapes : 0);
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
CHECK(doc.load(STR("<node id='1'/>"), flags));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id")).value(), STR("1"));
}
}
TEST(parse_attribute_error)
{
xml_document doc;
CHECK(doc.load(STR("<node id"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id "), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id "), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id "), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id/"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id/>"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id?/>"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id=/>"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id='/>"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id=\"/>"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id=\"'/>"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id='\"/>"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id='\"/>"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node #/>"), parse_minimal).status == status_bad_start_element);
CHECK(doc.load(STR("<node#/>"), parse_minimal).status == status_bad_start_element);
CHECK(doc.load(STR("<node id1='1'id2='2'/>"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node id&='1'/>"), parse_minimal).status == status_bad_attribute);
CHECK(doc.load(STR("<node &='1'/>"), parse_minimal).status == status_bad_start_element);
}
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
TEST(parse_attribute_termination_error)
{
xml_document doc;
for (int wnorm = 0; wnorm < 2; ++wnorm)
for (int eol = 0; eol < 2; ++eol)
for (int wconv = 0; wconv < 2; ++wconv)
{
unsigned int flags = parse_minimal;
flags |= (wnorm ? parse_wnorm_attribute : 0);
flags |= (eol ? parse_eol : 0);
flags |= (wconv ? parse_wconv_attribute : 0);
CHECK(doc.load(STR("<node id='value"), flags).status == status_bad_attribute);
}
}
TEST(parse_attribute_quot_inside)
{
xml_document doc;
for (int wnorm = 0; wnorm < 2; ++wnorm)
for (int eol = 0; eol < 2; ++eol)
for (int wconv = 0; wconv < 2; ++wconv)
{
unsigned int flags = parse_escapes;
flags |= (wnorm ? parse_wnorm_attribute : 0);
flags |= (eol ? parse_eol : 0);
flags |= (wconv ? parse_wconv_attribute : 0);
CHECK(doc.load(STR("<node id1='\"' id2=\"'\"/>"), flags));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id1")).value(), STR("\""));
CHECK_STRING(doc.child(STR("node")).attribute(STR("id2")).value(), STR("'"));
}
}
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
TEST(parse_tag_single)
{
xml_document doc;
CHECK(doc.load(STR("<node/><node /><node\n/>"), parse_minimal));
CHECK_NODE(doc, STR("<node /><node /><node />"));
}
TEST(parse_tag_hierarchy)
{
xml_document doc;
CHECK(doc.load(STR("<node><n1><n2/></n1><n3><n4><n5></n5></n4></n3 \r\n></node>"), parse_minimal));
CHECK_NODE(doc, STR("<node><n1><n2 /></n1><n3><n4><n5 /></n4></n3></node>"));
}
TEST(parse_tag_error)
{
xml_document doc;
CHECK(doc.load(STR("<"), parse_minimal).status == status_unrecognized_tag);
CHECK(doc.load(STR("<!"), parse_minimal).status == status_unrecognized_tag);
CHECK(doc.load(STR("<!D"), parse_minimal).status == status_unrecognized_tag);
CHECK(doc.load(STR("<#"), parse_minimal).status == status_unrecognized_tag);
CHECK(doc.load(STR("<node#"), parse_minimal).status == status_bad_start_element);
CHECK(doc.load(STR("<node"), parse_minimal).status == status_bad_start_element);
CHECK(doc.load(STR("<node/"), parse_minimal).status == status_bad_start_element);
CHECK(doc.load(STR("<node /"), parse_minimal).status == status_bad_start_element);
CHECK(doc.load(STR("<node / "), parse_minimal).status == status_bad_start_element);
CHECK(doc.load(STR("<node / >"), parse_minimal).status == status_bad_start_element);
CHECK(doc.load(STR("<node/ >"), parse_minimal).status == status_bad_start_element);
CHECK(doc.load(STR("</ node>"), parse_minimal).status == status_end_element_mismatch);
CHECK(doc.load(STR("</node"), parse_minimal).status == status_end_element_mismatch);
CHECK(doc.load(STR("</node "), parse_minimal).status == status_end_element_mismatch);
CHECK(doc.load(STR("<node></ node>"), parse_minimal).status == status_end_element_mismatch);
CHECK(doc.load(STR("<node></node"), parse_minimal).status == status_bad_end_element);
CHECK(doc.load(STR("<node></node "), parse_minimal).status == status_bad_end_element);
CHECK(doc.load(STR("<node></nodes>"), parse_minimal).status == status_end_element_mismatch);
CHECK(doc.load(STR("<node>"), parse_minimal).status == status_end_element_mismatch);
CHECK(doc.load(STR("<node/><"), parse_minimal).status == status_unrecognized_tag);
CHECK(doc.load(STR("<node attr='value'>"), parse_minimal).status == status_end_element_mismatch);
CHECK(doc.load(STR("</></node>"), parse_minimal).status == status_end_element_mismatch);
CHECK(doc.load(STR("</node>"), parse_minimal).status == status_end_element_mismatch);
CHECK(doc.load(STR("</>"), parse_minimal).status == status_end_element_mismatch);
CHECK(doc.load(STR("<node></node v>"), parse_minimal).status == status_bad_end_element);
CHECK(doc.load(STR("<node&/>"), parse_minimal).status == status_bad_start_element);
CHECK(doc.load(STR("<node& v='1'/>"), parse_minimal).status == status_bad_start_element);
}
TEST(parse_declaration_cases)
{
xml_document doc;
CHECK(doc.load(STR("<?xml?><?xmL?><?xMl?><?xML?><?Xml?><?XmL?><?XMl?><?XML?>"), parse_fragment | parse_pi));
CHECK(!doc.first_child());
}
TEST(parse_declaration_attr_cases)
{
xml_document doc;
CHECK(doc.load(STR("<?xml ?><?xmL ?><?xMl ?><?xML ?><?Xml ?><?XmL ?><?XMl ?><?XML ?>"), parse_fragment | parse_pi));
CHECK(!doc.first_child());
}
TEST(parse_declaration_skip)
{
xml_document doc;
unsigned int flag_sets[] = {parse_fragment, parse_fragment | parse_pi};
for (unsigned int i = 0; i < sizeof(flag_sets) / sizeof(flag_sets[0]); ++i)
{
unsigned int flags = flag_sets[i];
CHECK(doc.load(STR("<?xml?><?xml version='1.0'?>"), flags));
CHECK(!doc.first_child());
CHECK(doc.load(STR("<?xml <tag/> ?>"), flags));
CHECK(!doc.first_child());
}
}
TEST(parse_declaration_parse)
{
xml_document doc;
CHECK(doc.load(STR("<?xml?><?xml version='1.0'?>"), parse_fragment | parse_declaration));
xml_node d1 = doc.first_child();
xml_node d2 = doc.last_child();
CHECK(d1 != d2);
CHECK(d1.type() == node_declaration);
CHECK_STRING(d1.name(), STR("xml"));
CHECK(d2.type() == node_declaration);
CHECK_STRING(d2.name(), STR("xml"));
CHECK_STRING(d2.attribute(STR("version")).value(), STR("1.0"));
}
TEST(parse_declaration_error)
{
xml_document doc;
unsigned int flag_sets[] = {parse_fragment, parse_fragment | parse_declaration};
for (unsigned int i = 0; i < sizeof(flag_sets) / sizeof(flag_sets[0]); ++i)
{
unsigned int flags = flag_sets[i];
CHECK(doc.load(STR("<?xml"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?xml?"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?xml>"), flags).status == status_bad_pi);
CHECK(doc.load(STR("<?xml version='1>"), flags).status == status_bad_pi);
}
CHECK(doc.load(STR("<?xml version='1?>"), parse_fragment | parse_declaration).status == status_bad_attribute);
CHECK(doc.load(STR("<foo><?xml version='1'?></foo>"), parse_fragment | parse_declaration).status == status_bad_pi);
}
TEST(parse_empty)
{
xml_document doc;
CHECK(doc.load(STR("")).status == status_no_document_element && !doc.first_child());
CHECK(doc.load(STR(""), parse_fragment) && !doc.first_child());
}
TEST(parse_out_of_memory)
{
test_runner::_memory_fail_threshold = 256;
xml_document doc;
CHECK(doc.load(STR("<foo a='1'/>")).status == status_out_of_memory);
CHECK(!doc.first_child());
}
const unsigned int count = 10000;
static char_t text[count * 4];
for (unsigned int i = 0; i < count; ++i)
{
text[4*i + 0] = '<';
text[4*i + 1] = 'n';
text[4*i + 2] = '/';
text[4*i + 3] = '>';
}
test_runner::_memory_fail_threshold = 65536;
xml_document doc;
CHECK(doc.load_buffer_inplace(text, count * 4).status == status_out_of_memory);
CHECK_NODE(doc.first_child(), STR("<n />"));
}
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
TEST(parse_out_of_memory_halfway_attr)
{
const unsigned int count = 10000;
static char_t text[count * 5 + 4];
text[0] = '<';
text[1] = 'n';
for (unsigned int i = 0; i < count; ++i)
{
text[5*i + 2] = ' ';
text[5*i + 3] = 'a';
text[5*i + 4] = '=';
text[5*i + 5] = '"';
text[5*i + 6] = '"';
}
text[5 * count + 2] = '/';
text[5 * count + 3] = '>';
test_runner::_memory_fail_threshold = 65536;
xml_document doc;
CHECK(doc.load_buffer_inplace(text, count * 5 + 4).status == status_out_of_memory);
CHECK_STRING(doc.first_child().name(), STR("n"));
CHECK_STRING(doc.first_child().first_attribute().name(), STR("a"));
CHECK_STRING(doc.first_child().last_attribute().name(), STR("a"));
}
static bool test_offset(const char_t* contents, unsigned int options, pugi::xml_parse_status status, ptrdiff_t offset)
{
xml_document doc;
xml_parse_result res = doc.load(contents, options);
return res.status == status && res.offset == offset;
}
#define CHECK_OFFSET(contents, options, status, offset) CHECK(test_offset(STR(contents), options, status, offset))
TEST(parse_error_offset)
{
CHECK_OFFSET("<node/>", parse_default, status_ok, 0);
test_runner::_memory_fail_threshold = 1;
CHECK_OFFSET("<node/>", parse_default, status_out_of_memory, 0);
test_runner::_memory_fail_threshold = 0;
CHECK_OFFSET("<3d/>", parse_default, status_unrecognized_tag, 1);
CHECK_OFFSET(" <3d/>", parse_default, status_unrecognized_tag, 2);
CHECK_OFFSET(" <", parse_default, status_unrecognized_tag, 1);
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
CHECK_OFFSET("<?pi", parse_default, status_bad_pi, 3);
CHECK_OFFSET("<?pi", parse_default | parse_pi, status_bad_pi, 3);
CHECK_OFFSET("<?xml", parse_default | parse_declaration, status_bad_pi, 4);
CHECK_OFFSET("<!----", parse_default, status_bad_comment, 5);
CHECK_OFFSET("<!----", parse_default | parse_comments, status_bad_comment, 4);
CHECK_OFFSET("<![CDA", parse_default, status_bad_cdata, 5);
CHECK_OFFSET("<![CDATA[non-terminated]]", parse_default, status_bad_cdata, 9);
CHECK_OFFSET("<!DOCTYPE doc", parse_default, status_bad_doctype, 12);
CHECK_OFFSET("<!DOCTYPE greeting [ <!ATTLIST list type (bullets|ordered|glossary) \"orde", parse_default, status_bad_doctype, 76);
CHECK_OFFSET("<node", parse_default, status_bad_start_element, 4);
CHECK_OFFSET("<node ", parse_default, status_bad_start_element, 5);
CHECK_OFFSET("<nod%>", parse_default, status_bad_start_element, 5);
CHECK_OFFSET("<node a=2>", parse_default, status_bad_attribute, 8);
CHECK_OFFSET("<node a='2>", parse_default, status_bad_attribute, 9);
CHECK_OFFSET("<n></n $>", parse_default, status_bad_end_element, 7);
CHECK_OFFSET("<n></n", parse_default, status_bad_end_element, 5);
CHECK_OFFSET("<no></na>", parse_default, status_end_element_mismatch, 8);
CHECK_OFFSET("<no></nod>", parse_default, status_end_element_mismatch, 9);
}
TEST(parse_result_default)
{
xml_parse_result result;
CHECK(!result);
CHECK(result.status == status_internal_error);
CHECK(result.offset == 0);
CHECK(result.encoding == encoding_auto);
TEST(parse_bom_fragment)
{
struct test_data_t
{
xml_encoding encoding;
const char* data;
size_t size;
const char_t* text;
};
const test_data_t data[] =
{
{ encoding_utf8, "\xef\xbb\xbf", 3, STR("") },
{ encoding_utf8, "\xef\xbb\xbftest", 7, STR("test") },