File: pg_query_normalize.c

package info (click to toggle)
ruby-gitlab-pg-query 2.0.4-3
  • links: PTS, VCS
  • area: main
  • in suites: experimental
  • size: 15,584 kB
  • sloc: ansic: 143,939; ruby: 2,096; makefile: 4
file content (439 lines) | stat: -rw-r--r-- 12,558 bytes parent folder | download
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
#include "pg_query.h"
#include "pg_query_internal.h"

#include "parser/parser.h"
#include "parser/scanner.h"
#include "parser/scansup.h"
#include "mb/pg_wchar.h"
#include "nodes/nodeFuncs.h"

/*
 * Struct for tracking locations/lengths of constants during normalization
 */
typedef struct pgssLocationLen
{
	int			location;		/* start offset in query text */
	int			length;			/* length in bytes, or -1 to ignore */
} pgssLocationLen;

/*
 * Working state for constant tree walker
 */
typedef struct pgssConstLocations
{
	/* Array of locations of constants that should be removed */
	pgssLocationLen *clocations;

	/* Allocated length of clocations array */
	int			clocations_buf_size;

	/* Current number of valid entries in clocations array */
	int			clocations_count;

	/* highest Param id we've seen, in order to start normalization correctly */
	int			highest_extern_param_id;

	/* query text */
	const char * query;
	int			query_len;
} pgssConstLocations;

/*
 * comp_location: comparator for qsorting pgssLocationLen structs by location
 */
static int
comp_location(const void *a, const void *b)
{
	int			l = ((const pgssLocationLen *) a)->location;
	int			r = ((const pgssLocationLen *) b)->location;

	if (l < r)
		return -1;
	else if (l > r)
		return +1;
	else
		return 0;
}

/*
 * Given a valid SQL string and an array of constant-location records,
 * fill in the textual lengths of those constants.
 *
 * The constants may use any allowed constant syntax, such as float literals,
 * bit-strings, single-quoted strings and dollar-quoted strings.  This is
 * accomplished by using the public API for the core scanner.
 *
 * It is the caller's job to ensure that the string is a valid SQL statement
 * with constants at the indicated locations.  Since in practice the string
 * has already been parsed, and the locations that the caller provides will
 * have originated from within the authoritative parser, this should not be
 * a problem.
 *
 * Duplicate constant pointers are possible, and will have their lengths
 * marked as '-1', so that they are later ignored.  (Actually, we assume the
 * lengths were initialized as -1 to start with, and don't change them here.)
 *
 * N.B. There is an assumption that a '-' character at a Const location begins
 * a negative numeric constant.  This precludes there ever being another
 * reason for a constant to start with a '-'.
 */
static void
fill_in_constant_lengths(pgssConstLocations *jstate, const char *query)
{
	pgssLocationLen *locs;
	core_yyscan_t yyscanner;
	core_yy_extra_type yyextra;
	core_YYSTYPE yylval;
	YYLTYPE		yylloc;
	int			last_loc = -1;
	int			i;

	/*
	 * Sort the records by location so that we can process them in order while
	 * scanning the query text.
	 */
	if (jstate->clocations_count > 1)
		qsort(jstate->clocations, jstate->clocations_count,
			  sizeof(pgssLocationLen), comp_location);
	locs = jstate->clocations;

	/* initialize the flex scanner --- should match raw_parser() */
	yyscanner = scanner_init(query,
							 &yyextra,
							 &ScanKeywords,
							 ScanKeywordTokens);

	/* Search for each constant, in sequence */
	for (i = 0; i < jstate->clocations_count; i++)
	{
		int			loc = locs[i].location;
		int			tok;

		Assert(loc >= 0);

		if (loc <= last_loc)
			continue;			/* Duplicate constant, ignore */

		/* Lex tokens until we find the desired constant */
		for (;;)
		{
			tok = core_yylex(&yylval, &yylloc, yyscanner);

			/* We should not hit end-of-string, but if we do, behave sanely */
			if (tok == 0)
				break;			/* out of inner for-loop */

			/*
			 * We should find the token position exactly, but if we somehow
			 * run past it, work with that.
			 */
			if (yylloc >= loc)
			{
				if (query[loc] == '-')
				{
					/*
					 * It's a negative value - this is the one and only case
					 * where we replace more than a single token.
					 *
					 * Do not compensate for the core system's special-case
					 * adjustment of location to that of the leading '-'
					 * operator in the event of a negative constant.  It is
					 * also useful for our purposes to start from the minus
					 * symbol.  In this way, queries like "select * from foo
					 * where bar = 1" and "select * from foo where bar = -2"
					 * will have identical normalized query strings.
					 */
					tok = core_yylex(&yylval, &yylloc, yyscanner);
					if (tok == 0)
						break;	/* out of inner for-loop */
				}

				/*
				 * We now rely on the assumption that flex has placed a zero
				 * byte after the text of the current token in scanbuf.
				 */
				locs[i].length = (int) strlen(yyextra.scanbuf + loc);

				/* Quoted string with Unicode escapes
				 *
				 * The lexer consumes trailing whitespace in order to find UESCAPE, but if there
				 * is no UESCAPE it has still consumed it - don't include it in constant length.
				 */
				if (locs[i].length > 4 && /* U&'' */
					(yyextra.scanbuf[loc] == 'u' || yyextra.scanbuf[loc] == 'U') &&
					 yyextra.scanbuf[loc + 1] == '&' && yyextra.scanbuf[loc + 2] == '\'')
				{
					int j = locs[i].length - 1; /* Skip the \0 */
					for (; j >= 0 && scanner_isspace(yyextra.scanbuf[loc + j]); j--) {}
					locs[i].length = j + 1; /* Count the \0 */
				}

				break;			/* out of inner for-loop */
			}
		}

		/* If we hit end-of-string, give up, leaving remaining lengths -1 */
		if (tok == 0)
			break;

		last_loc = loc;
	}

	scanner_finish(yyscanner);
}

/*
 * Generate a normalized version of the query string that will be used to
 * represent all similar queries.
 *
 * Note that the normalized representation may well vary depending on
 * just which "equivalent" query is used to create the hashtable entry.
 * We assume this is OK.
 *
 * *query_len_p contains the input string length, and is updated with
 * the result string length (which cannot be longer) on exit.
 *
 * Returns a palloc'd string.
 */
static char *
generate_normalized_query(pgssConstLocations *jstate, int query_loc, int* query_len_p, int encoding)
{
	char	   *norm_query;
	const char *query = jstate->query;
	int			query_len = *query_len_p;
	int			i,
				norm_query_buflen,		/* Space allowed for norm_query */
				len_to_wrt,		/* Length (in bytes) to write */
				quer_loc = 0,	/* Source query byte location */
				n_quer_loc = 0, /* Normalized query byte location */
				last_off = 0,	/* Offset from start for previous tok */
				last_tok_len = 0;		/* Length (in bytes) of that tok */

	/*
	 * Get constants' lengths (core system only gives us locations).  Note
	 * this also ensures the items are sorted by location.
	 */
	fill_in_constant_lengths(jstate, query);

	/*
	 * Allow for $n symbols to be longer than the constants they replace.
	 * Constants must take at least one byte in text form, while a $n symbol
	 * certainly isn't more than 11 bytes, even if n reaches INT_MAX.  We
	 * could refine that limit based on the max value of n for the current
	 * query, but it hardly seems worth any extra effort to do so.
	 */
	norm_query_buflen = query_len + jstate->clocations_count * 10;

	/* Allocate result buffer */
	norm_query = palloc(norm_query_buflen + 1);

	for (i = 0; i < jstate->clocations_count; i++)
	{
		int			off,		/* Offset from start for cur tok */
					tok_len;	/* Length (in bytes) of that tok */

		off = jstate->clocations[i].location;
		/* Adjust recorded location if we're dealing with partial string */
		off -= query_loc;

		tok_len = jstate->clocations[i].length;

		if (tok_len < 0)
			continue;			/* ignore any duplicates */

		/* Copy next chunk (what precedes the next constant) */
		len_to_wrt = off - last_off;
		len_to_wrt -= last_tok_len;

		Assert(len_to_wrt >= 0);
		memcpy(norm_query + n_quer_loc, query + quer_loc, len_to_wrt);
		n_quer_loc += len_to_wrt;

		/* And insert a param symbol in place of the constant token */
		n_quer_loc += sprintf(norm_query + n_quer_loc, "$%d",
							  i + 1 + jstate->highest_extern_param_id);

		quer_loc = off + tok_len;
		last_off = off;
		last_tok_len = tok_len;
	}

	/*
	 * We've copied up until the last ignorable constant.  Copy over the
	 * remaining bytes of the original query string.
	 */
	len_to_wrt = query_len - quer_loc;

	Assert(len_to_wrt >= 0);
	memcpy(norm_query + n_quer_loc, query + quer_loc, len_to_wrt);
	n_quer_loc += len_to_wrt;

	Assert(n_quer_loc <= norm_query_buflen);
	norm_query[n_quer_loc] = '\0';

	*query_len_p = n_quer_loc;
	return norm_query;
}

static void RecordConstLocation(pgssConstLocations *jstate, int location)
{
	/* -1 indicates unknown or undefined location */
	if (location >= 0)
	{
		/* enlarge array if needed */
		if (jstate->clocations_count >= jstate->clocations_buf_size)
		{
			jstate->clocations_buf_size *= 2;
			jstate->clocations = (pgssLocationLen *)
				repalloc(jstate->clocations,
						 jstate->clocations_buf_size *
						 sizeof(pgssLocationLen));
		}
		jstate->clocations[jstate->clocations_count].location = location;
		/* initialize lengths to -1 to simplify fill_in_constant_lengths */
		jstate->clocations[jstate->clocations_count].length = -1;
		jstate->clocations_count++;
	}
}

static bool const_record_walker(Node *node, pgssConstLocations *jstate)
{
	bool result;
	MemoryContext normalize_context = CurrentMemoryContext;

	if (node == NULL) return false;

	if (IsA(node, A_Const))
	{
		RecordConstLocation(jstate, castNode(A_Const, node)->location);
	}
	else if (IsA(node, ParamRef))
	{
		/* Track the highest ParamRef number */
		if (((ParamRef *) node)->number > jstate->highest_extern_param_id)
			jstate->highest_extern_param_id = castNode(ParamRef, node)->number;
	}
	else if (IsA(node, DefElem))
	{
		DefElem * defElem = (DefElem *) node;
		if (defElem->arg != NULL && IsA(defElem->arg, String)) {
			for (int i = defElem->location; i < jstate->query_len; i++) {
				if (jstate->query[i] == '\'') {
					RecordConstLocation(jstate, i);
					break;
			  }
			}
		}
		return const_record_walker((Node *) ((DefElem *) node)->arg, jstate);
	}
	else if (IsA(node, RawStmt))
	{
		return const_record_walker((Node *) ((RawStmt *) node)->stmt, jstate);
	}
	else if (IsA(node, VariableSetStmt))
	{
		return const_record_walker((Node *) ((VariableSetStmt *) node)->args, jstate);
	}
	else if (IsA(node, CopyStmt))
	{
		return const_record_walker((Node *) ((CopyStmt *) node)->query, jstate);
	}
	else if (IsA(node, ExplainStmt))
	{
		return const_record_walker((Node *) ((ExplainStmt *) node)->query, jstate);
	}
	else if (IsA(node, CreateRoleStmt))
	{
		return const_record_walker((Node *) ((CreateRoleStmt *) node)->options, jstate);
	}
	else if (IsA(node, AlterRoleStmt))
	{
		return const_record_walker((Node *) ((AlterRoleStmt *) node)->options, jstate);
	}
	else if (IsA(node, DeclareCursorStmt))
	{
		return const_record_walker((Node *) ((DeclareCursorStmt *) node)->query, jstate);
	}

	PG_TRY();
	{
		result = raw_expression_tree_walker(node, const_record_walker, (void*) jstate);
	}
	PG_CATCH();
	{
		MemoryContextSwitchTo(normalize_context);
		result = false;
		FlushErrorState();
	}
	PG_END_TRY();

	return result;
}

PgQueryNormalizeResult pg_query_normalize(const char* input)
{
	MemoryContext ctx = NULL;
	PgQueryNormalizeResult result = {0};

	ctx = pg_query_enter_memory_context();

	PG_TRY();
	{
		List *tree;
		pgssConstLocations jstate;
		int query_len;

		/* Parse query */
		tree = raw_parser(input);

		query_len = (int) strlen(input);

		/* Set up workspace for constant recording */
		jstate.clocations_buf_size = 32;
		jstate.clocations = (pgssLocationLen *)
			palloc(jstate.clocations_buf_size * sizeof(pgssLocationLen));
		jstate.clocations_count = 0;
		jstate.highest_extern_param_id = 0;
		jstate.query = input;
		jstate.query_len = query_len;

		/* Walk tree and record const locations */
		const_record_walker((Node *) tree, &jstate);

		/* Normalize query */
		result.normalized_query = strdup(generate_normalized_query(&jstate, 0, &query_len, PG_UTF8));
	}
	PG_CATCH();
	{
		ErrorData* error_data;
		PgQueryError* error;

		MemoryContextSwitchTo(ctx);
		error_data = CopyErrorData();

		error = malloc(sizeof(PgQueryError));
		error->message   = strdup(error_data->message);
		error->filename  = strdup(error_data->filename);
		error->lineno    = error_data->lineno;
		error->cursorpos = error_data->cursorpos;

		result.error = error;
		FlushErrorState();
	}
	PG_END_TRY();

	pg_query_exit_memory_context(ctx);

	return result;
}

void pg_query_free_normalize_result(PgQueryNormalizeResult result)
{
  if (result.error) {
    free(result.error->message);
    free(result.error->filename);
    free(result.error);
  }

  free(result.normalized_query);
}