summaryrefslogtreecommitdiff
path: root/test/tokeniser3.c
blob: 523bfcd59afbc06ed23c9a11264c5482e4bb8be9 (plain)
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
#include <inttypes.h>
#include <stdio.h>
#include <string.h>

#include <json.h>

#include <hubbub/hubbub.h>

#include "utils/utils.h"

#include "input/inputstream.h"
#include "tokeniser/tokeniser.h"

#include "testutils.h"

typedef struct context {
	const uint8_t *pbuffer;

	const uint8_t *input;
	size_t input_len;

	struct array_list *output;
	int output_index;
	size_t char_off;

	const char *last_start_tag;
	struct array_list *content_model;
	bool process_cdata;
} context;

static void run_test(context *ctx);
static void buffer_handler(const uint8_t *buffer, size_t len, void *pw);
static void token_handler(const hubbub_token *token, void *pw);

static void *myrealloc(void *ptr, size_t len, void *pw)
{
	UNUSED(pw);

	return realloc(ptr, len);
}

int main(int argc, char **argv)
{
	struct json_object *json;
	struct array_list *tests;
	struct lh_entry *entry;
	char *key;
	struct json_object *val;
	int i;
	context ctx;

	if (argc != 3) {
		printf("Usage: %s <aliases_file> <filename>\n", argv[0]);
		return 1;
	}

	/* Initialise library */
	assert(hubbub_initialise(argv[1], myrealloc, NULL) == HUBBUB_OK);

	json = json_object_from_file(argv[2]);
	assert(!is_error(json));

	assert(strcmp((char *) ((json_object_get_object(json)->head)->k),
			"tests") == 0);

	/* Get array of tests */
	tests = json_object_get_array((struct json_object *)
			(json_object_get_object(json)->head)->v);

	for (i = 0; i < array_list_length(tests); i++) {
		/* Get test */
		struct json_object *test =
			(struct json_object *) array_list_get_idx(tests, i);

		ctx.last_start_tag = NULL;
		ctx.content_model = NULL;

		/* Extract settings */
		for (entry = json_object_get_object(test)->head; entry;
				entry = entry->next) {
			key = (char *) entry->k;
			val = (struct json_object *) entry->v;

			if (strcmp(key, "description") == 0) {
				printf("Test: %s\n",
					json_object_get_string(val));
			} else if (strcmp(key, "input") == 0) {
				ctx.input = (const uint8_t *)
						json_object_get_string_len(val,
						(int *) &ctx.input_len);
			} else if (strcmp(key, "output") == 0) {
				ctx.output = json_object_get_array(val);
				ctx.output_index = 0;
				ctx.char_off = 0;
			} else if (strcmp(key, "lastStartTag") == 0) {
				ctx.last_start_tag = (const char *)
						json_object_get_string(val);
			} else if (strcmp(key, "contentModelFlags") == 0) {
				ctx.content_model =
						json_object_get_array(val);
			} else if (strcmp(key, "processCDATA") == 0) {
				ctx.process_cdata =
					json_object_get_boolean(val);
			}
		}

		/* And run the test */
		run_test(&ctx);
	}

	assert(hubbub_finalise(myrealloc, NULL) == HUBBUB_OK);

	printf("PASS\n");

	return 0;
}

void run_test(context *ctx)
{
	hubbub_inputstream *stream;
	hubbub_tokeniser *tok;
	hubbub_tokeniser_optparams params;
	int i, max_i;
	size_t j;
	struct array_list *outputsave = ctx->output;

	if (ctx->content_model == NULL) {
		max_i = 1;
	} else {
		max_i = array_list_length(ctx->content_model);
	}

	/* We test for each of the content models specified */
	for (i = 0; i < max_i; i++) {
		/* Reset expected output */
		ctx->output = outputsave;
		ctx->output_index = 0;
		ctx->char_off = 0;

		stream = hubbub_inputstream_create("UTF-8", "UTF-8",
				myrealloc, NULL);
		assert(stream != NULL);

		tok = hubbub_tokeniser_create(stream, myrealloc, NULL);
		assert(tok != NULL);

		if (ctx->last_start_tag != NULL) {
			/* Fake up a start tag, in PCDATA state */
			uint8_t buf [strlen(ctx->last_start_tag) + 3];

			snprintf((char *) buf, sizeof buf, "<%s>",
					ctx->last_start_tag);

			assert(hubbub_inputstream_append(stream,
				buf, strlen(ctx->last_start_tag) + 2) ==
				HUBBUB_OK);

			assert(hubbub_tokeniser_run(tok) == HUBBUB_OK);
		}

		if (ctx->process_cdata) {
			params.process_cdata = ctx->process_cdata;
			assert(hubbub_tokeniser_setopt(tok,
					HUBBUB_TOKENISER_PROCESS_CDATA,
					&params) == HUBBUB_OK);
		}

		params.buffer_handler.handler = buffer_handler;
		params.buffer_handler.pw = ctx;
		assert(hubbub_tokeniser_setopt(tok,
				HUBBUB_TOKENISER_BUFFER_HANDLER,
				&params) == HUBBUB_OK);

		params.token_handler.handler = token_handler;
		params.token_handler.pw = ctx;
		assert(hubbub_tokeniser_setopt(tok,
				HUBBUB_TOKENISER_TOKEN_HANDLER,
				&params) == HUBBUB_OK);

		if (ctx->content_model == NULL) {
			params.content_model.model =
					HUBBUB_CONTENT_MODEL_PCDATA;
		} else {
			char *cm = json_object_get_string(
				(struct json_object *)
				array_list_get_idx(ctx->content_model, i));

			if (strcmp(cm, "PCDATA") == 0) {
				params.content_model.model =
						HUBBUB_CONTENT_MODEL_PCDATA;
			} else if (strcmp(cm, "RCDATA") == 0) {
				params.content_model.model =
						HUBBUB_CONTENT_MODEL_RCDATA;
			} else if (strcmp(cm, "CDATA") == 0) {
				params.content_model.model =
						HUBBUB_CONTENT_MODEL_CDATA;
			} else {
				params.content_model.model =
					HUBBUB_CONTENT_MODEL_PLAINTEXT;
			}
		}
		assert(hubbub_tokeniser_setopt(tok,
				HUBBUB_TOKENISER_CONTENT_MODEL,
				&params) == HUBBUB_OK);

		printf("Input: '%.*s' (%d)\n", (int) ctx->input_len,
				(const char *) ctx->input, ctx->input_len);

		for (j = 0; j < ctx->input_len; j++) {
			assert(hubbub_inputstream_append(stream,
					ctx->input + j, 1) ==
							HUBBUB_OK);

			assert(hubbub_tokeniser_run(tok) == HUBBUB_OK);
		}

		assert(hubbub_inputstream_append(stream, NULL, 0) ==
				HUBBUB_OK);

		assert(hubbub_tokeniser_run(tok) == HUBBUB_OK);

		hubbub_tokeniser_destroy(tok);

		hubbub_inputstream_destroy(stream);
	}
}

void buffer_handler(const uint8_t *buffer, size_t len, void *pw)
{
	context *ctx = (context *) pw;

	UNUSED(len);

	ctx->pbuffer = buffer;
}

void token_handler(const hubbub_token *token, void *pw)
{
	static const char *token_names[] = {
		"DOCTYPE", "StartTag", "EndTag",
		"Comment", "Character", "EOF"
	};
	size_t i;
	context *ctx = (context *) pw;
	struct json_object *obj = NULL;
	struct array_list *items;

	for (; ctx->output_index < array_list_length(ctx->output);
			ctx->output_index++) {
		/* Get object for index */
		obj = (struct json_object *)
				array_list_get_idx(ctx->output,
						ctx->output_index);

		/* If it's not a string, we've found the expected output */
		if (json_object_get_type(obj) != json_type_string)
			break;

		/* Otherwise, it must be a parse error */
		assert(strcmp(json_object_get_string(obj),
				 "ParseError") == 0);
	}

	/* If we've run off the end, this is an error -- the tokeniser has
	 * produced more tokens than expected. We allow for the generation
	 * of a terminating EOF token, however. */
	assert("too many tokens" &&
			(ctx->output_index < array_list_length(ctx->output) ||
			token->type == HUBBUB_TOKEN_EOF));

	/* Got a terminating EOF -- no error */
	if (ctx->output_index >= array_list_length(ctx->output))
		return;

	/* Now increment the output index so we don't re-expect this token */
	ctx->output_index++;

	/* Expected output must be an array */
	assert(json_object_get_type(obj) == json_type_array);

	items = json_object_get_array(obj);

	printf("got %s: expected %s\n", token_names[token->type],
			json_object_get_string((struct json_object *)
				array_list_get_idx(items, 0)));

	/* Make sure we got the token we expected */
	assert(strcmp(token_names[token->type],
			json_object_get_string((struct json_object *)
				array_list_get_idx(items, 0))) == 0);

	switch (token->type) {
	case HUBBUB_TOKEN_DOCTYPE:
	{
		char *expname = json_object_get_string(
				array_list_get_idx(items, 1));
		char *exppub = json_object_get_string(
				array_list_get_idx(items, 2));
		char *expsys = json_object_get_string(
				array_list_get_idx(items, 3));
		bool expquirks = !json_object_get_boolean(
				array_list_get_idx(items, 4));
		char *gotname = (char *) (ctx->pbuffer +
				token->data.doctype.name.data.off);
		char *gotpub, *gotsys;

		printf("'%.*s' %sids:\n",
				(int) token->data.doctype.name.len,
				gotname,
				token->data.doctype.force_quirks ?
						"(force-quirks) " : "");

		if (token->data.doctype.public_missing) {
			gotpub = NULL;
			printf("\tpublic: missing\n");
		} else {
			gotpub = (char *) (ctx->pbuffer +
				token->data.doctype.public_id.data.off);
			printf("\tpublic: '%.*s'\n",
				(int) token->data.doctype.public_id.len,
				gotpub);
		}

		if (token->data.doctype.system_missing) {
			gotsys = NULL;
			printf("\tsystem: missing\n");
		} else {
			gotsys = (char *) (ctx->pbuffer +
				token->data.doctype.system_id.data.off);
			printf("\tsystem: '%.*s'\n",
				(int) token->data.doctype.system_id.len,
				gotsys);
		}

		assert(token->data.doctype.name.len == strlen(expname));
		assert(strncmp(gotname, expname, strlen(expname)) == 0);

		assert((exppub == NULL) == (gotpub == NULL));
		if (exppub) {
			assert(token->data.doctype.public_id.len == strlen(exppub));
			assert(strncmp(gotpub, exppub, strlen(exppub)) == 0);
		}

		assert((expsys == NULL) == (gotsys == NULL));
		if (gotsys) {
			assert(token->data.doctype.system_id.len == strlen(expsys));
			assert(strncmp(gotsys, expsys, strlen(expsys)) == 0);
		}

		assert(expquirks == token->data.doctype.force_quirks);
	}
		break;
	case HUBBUB_TOKEN_START_TAG:
	{
		char *expname = json_object_get_string(
				array_list_get_idx(items, 1));
		struct lh_entry *expattrs = json_object_get_object(
				array_list_get_idx(items, 2))->head;
		bool self_closing = json_object_get_boolean(
				array_list_get_idx(items, 3));

		char *tagname = (char *) (ctx->pbuffer +
				token->data.tag.name.data.off);

		printf("'%.*s' %s%s\n",
				(int) token->data.tag.name.len,
				tagname,
				(token->data.tag.self_closing) ?
						"(self-closing) " : "",
				(token->data.tag.n_attributes > 0) ?
						"attributes:" : "");

		assert(token->data.tag.name.len == strlen(expname));
		assert(strncmp(tagname, expname, strlen(expname)) == 0);

		assert((token->data.tag.n_attributes == 0) ==
				(expattrs == NULL));

		assert(self_closing == token->data.tag.self_closing);

		for (i = 0; i < token->data.tag.n_attributes; i++) {
			char *expname = (char *) expattrs->k;
			char *expval = json_object_get_string(
					(struct json_object *) expattrs->v);
			char *gotname = (char *) (ctx->pbuffer +
				token->data.tag.attributes[i].name.data.off);
			size_t namelen =
				token->data.tag.attributes[i].name.len;
			char *gotval = (char *) (ctx->pbuffer +
				token->data.tag.attributes[i].value.data.off);
			size_t vallen =
				token->data.tag.attributes[i].value.len;

			printf("\t'%.*s' = '%.*s'\n",
					(int) namelen, gotname,
					(int) vallen, gotval);

			assert(namelen == strlen(expname));
			assert(strncmp(gotname, expname,
						strlen(expname)) == 0);
			assert(vallen == strlen(expval));
			assert(strncmp(gotval, expval, strlen(expval)) == 0);

			expattrs = expattrs->next;
		}

		assert(expattrs == NULL);
	}
		break;
	case HUBBUB_TOKEN_END_TAG:
	{
		char *expname = json_object_get_string(
				array_list_get_idx(items, 1));
		char *tagname = (char *) (ctx->pbuffer +
				token->data.tag.name.data.off);

		printf("'%.*s' %s\n",
				(int) token->data.tag.name.len,
				tagname,
				(token->data.tag.n_attributes > 0) ?
						"attributes:" : "");

		assert(token->data.tag.name.len == strlen(expname));
		assert(strncmp(tagname, expname, strlen(expname)) == 0);
	}
		break;
	case HUBBUB_TOKEN_COMMENT:
	{
		char *expstr = json_object_get_string(
				array_list_get_idx(items, 1));
		char *gotstr = (char *) (ctx->pbuffer +
				token->data.comment.data.off);

		printf("'%.*s'\n", (int) token->data.comment.len, gotstr);

		assert(token->data.comment.len == strlen(expstr));
		assert(strncmp(gotstr, expstr, strlen(expstr)) == 0);
	}
		break;
	case HUBBUB_TOKEN_CHARACTER:
	{
		int expstrlen;
		char *expstr = json_object_get_string_len(
				array_list_get_idx(items, 1), &expstrlen);
		char *gotstr = (char *) (ctx->pbuffer +
				token->data.character.data.off);
		size_t len = min(token->data.character.len,
				expstrlen - ctx->char_off);

		printf("expected: '%.*s'\n",
				len, expstr + ctx->char_off);
		printf("     got: '%.*s'\n",
				(int) token->data.character.len, gotstr);

		assert(memcmp(gotstr, expstr + ctx->char_off, len) == 0);

		if (len < token->data.character.len) {
			/* Expected token only contained part of the data
			 * Calculate how much is left, then try again with
			 * the next expected token */
			hubbub_token t;

			t.type = HUBBUB_TOKEN_CHARACTER;
			t.data.character.data.off += len;
			t.data.character.len -= len;

			ctx->char_off = 0;

			token_handler(&t, pw);
		} else if (strlen(expstr + ctx->char_off) >
				token->data.character.len) {
			/* Tokeniser output only contained part of the data
			 * in the expected token; calculate the offset into
			 * the token and process the remainder next time */
			ctx->char_off += len;
			ctx->output_index--;
		} else {
			/* Exact match - clear offset */
			ctx->char_off = 0;
		}
	}
		break;
	case HUBBUB_TOKEN_EOF:
		printf("\n");
		break;
	}
}