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
|
#
# InnoDB FULLTEXT SEARCH: CJK support - ngram parser
#
--source include/no_valgrind_without_big.inc
--source include/have_simple_parser.inc
SET NAMES utf8mb4;
-- echo # Test Case 1: Test Chinese with GB2312 Charset.
CREATE TABLE articles (
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
title VARCHAR(200),
body TEXT
) ENGINE=InnoDB DEFAULT CHARACTER SET gb2312 COLLATE gb2312_chinese_ci;
INSERT INTO articles (title, body) VALUES
('数据库是数据的结构化集合','它可以是任何东西'),
('从简单的购物清单到画展','或企业网络中的海量数据');
ALTER TABLE articles ADD FULLTEXT INDEX (title, body) WITH PARSER ngram;
INSERT INTO articles (title, body) VALUES
('要想将数据添加到数据库','或访问、处理计算机数据库中保存的数据'),
('需要使用数据库管理系统','计算机是处理大量数据的理想工具');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数*' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+数据库 -计算机' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+(数据库 处理) -计算机' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据库');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据库' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('"数据库"' IN BOOLEAN MODE);
DROP TABLE articles;
-- echo # Test Case 2: Test Chinese with GBK Charset.
CREATE TABLE articles (
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
title VARCHAR(200),
body TEXT
) ENGINE=InnoDB DEFAULT CHARACTER SET gbk COLLATE gbk_chinese_ci;
INSERT INTO articles (title, body) VALUES
('数据库是数据的结构化集合','它可以是任何东西'),
('从简单的购物清单到画展','或企业网络中的海量数据');
ALTER TABLE articles ADD FULLTEXT INDEX (title, body) WITH PARSER ngram;
INSERT INTO articles (title, body) VALUES
('要想将数据添加到数据库','或访问、处理计算机数据库中保存的数据'),
('需要使用数据库管理系统','计算机是处理大量数据的理想工具');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数*' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+数据库 -计算机' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+(数据库 处理) -计算机' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据库');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据库' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('"数据库"' IN BOOLEAN MODE);
DROP TABLE articles;
-- echo # Test Case 3: Test Chinese with UTF8 Charset.
CREATE TABLE articles (
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
title VARCHAR(200),
body TEXT
) ENGINE=InnoDB DEFAULT CHARACTER SET utf8mb4 COLLATE utf8mb4_general_ci;
INSERT INTO articles (title, body) VALUES
('数据库是数据的结构化集合','它可以是任何东西'),
('从简单的购物清单到画展','或企业网络中的海量数据');
ALTER TABLE articles ADD FULLTEXT INDEX (title, body) WITH PARSER ngram;
INSERT INTO articles (title, body) VALUES
('要想将数据添加到数据库','或访问、处理计算机数据库中保存的数据'),
('需要使用数据库管理系统','计算机是处理大量数据的理想工具');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数*' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+数据库 -计算机' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+(数据库 处理) -计算机' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据库');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据库' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('"数据库"' IN BOOLEAN MODE);
DROP TABLE articles;
-- echo # Test Case 4: Test Chinese with gb18030 Charset.
CREATE TABLE articles (
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
title VARCHAR(200),
body TEXT
) ENGINE=InnoDB DEFAULT CHARSET=gb18030 COLLATE=gb18030_chinese_ci;
INSERT INTO articles (title, body) VALUES
('数据库是数据的结构化集合','它可以是任何东西'),
('从简单的购物清单到画展','或企业网络中的海量数据');
ALTER TABLE articles ADD FULLTEXT INDEX `idx1` (title, body) WITH PARSER ngram;
INSERT INTO articles (title, body) VALUES
('要想将数据添加到数据库','或访问、处理计算机数据库中保存的数据'),
('需要使用数据库管理系统','计算机是处理大量数据的理想工具');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数*' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+数据库 -计算机' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+(数据库 处理) -计算机' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据库');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据库' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('"数据库"' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据库' WITH QUERY EXPANSION);
ALTER TABLE articles DROP INDEX `idx1`;
SELECT * FROM articles;
DROP TABLE articles;
-- echo # Test Case 5: Test Japanese with UJIS Charset.
CREATE TABLE articles (
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
title VARCHAR(200),
body TEXT
) ENGINE=InnoDB DEFAULT CHARACTER SET ujis COLLATE ujis_japanese_ci;
INSERT INTO articles (title, body) VALUES
('データベースは、構造化されたコレクションです','それは何もすることができます'),
('シンプルな買い物リストから画像ギャラリーへ','または企業ネットワーク内のデータの膨大な量');
ALTER TABLE articles ADD FULLTEXT INDEX (title, body) WITH PARSER ngram;
INSERT INTO articles (title, body) VALUES
('データベースにデータを追加するには','コンピュータのデータベースに格納されているアクセス、およびプロセスデータ'),
('データベース管理システムを使用する必要が','コンピュータは、大量のデータを処理するための理想的なツールである');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('データ');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('デ*' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+データベース -コンピュータ' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+(データベース 処理) -コンピュータ' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('データベース');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('データベース' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('"データベース"' IN BOOLEAN MODE);
DROP TABLE articles;
-- echo # Test Case 6: Test Korean with EUCKR Charset.
CREATE TABLE articles (
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
title VARCHAR(200),
body TEXT
) ENGINE=InnoDB DEFAULT CHARACTER SET euckr COLLATE euckr_korean_ci;
INSERT INTO articles (title, body) VALUES
('데이터베이스의 구조 모음입니다','그것은 무엇이든 될 수 있습니다'),
('간단한 쇼핑 목록에서 사진 갤러리','또는 기업 네트워크에서 데이터의 엄청난 양의');
ALTER TABLE articles ADD FULLTEXT INDEX (title, body) WITH PARSER ngram;
INSERT INTO articles (title, body) VALUES
('데이터베이스에 데이터를 추가하려면','액세스, 프로세스 데이터를 컴퓨터 데이터베이스에 저장'),
('데이터베이스 관리 시스템을 사용해야합니다','컴퓨터는 많은 양의 데이터를 처리하기위한 이상적인 도구입니다');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('데이터');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('데*' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+데이터베이스 -컴퓨터' IN BOOLEAN MODE);
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('+(데이터베이스 처리) -컴퓨터' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('데이터베이스');
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('데이터베이스' IN BOOLEAN MODE);
--sorted_result
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('"데이터베이스"' IN BOOLEAN MODE);
DROP TABLE articles;
-- echo # Test Case 7: Test different ngram token size.
CREATE TABLE articles (
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
title VARCHAR(200),
body TEXT
) ENGINE=InnoDB DEFAULT CHARACTER SET gb2312 COLLATE gb2312_chinese_ci;
INSERT INTO articles (title, body) VALUES
('数据库是数据的结构化集合','它可以是任何东西'),
('从简单的购物清单到画展','或企业网络中的海量数据'),
('要想将数据添加到数据库','或访问、处理计算机数据库中保存的数据'),
('需要使用数据库管理系统','计算机是处理大量数据的理想工具');
# bigram
CREATE FULLTEXT INDEX ft_index ON articles(title, body) WITH PARSER ngram;
# unigram
let $ngram_token_size=1;
-- source suite/innodb_fts/include/ngram_token_size.inc
# trigram
let $ngram_token_size=3;
-- source suite/innodb_fts/include/ngram_token_size.inc
# ngram = 5
let $ngram_token_size=5;
-- source suite/innodb_fts/include/ngram_token_size.inc
# ngram = 7
let $ngram_token_size=7;
-- source suite/innodb_fts/include/ngram_token_size.inc
# Restore to bigram
let $ngram_token_size=2;
-- source suite/innodb_fts/include/ngram_token_size.inc
DROP TABLE articles;
-- echo # Test Case 8: Test Optimize Table.
CREATE TABLE articles (
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
title VARCHAR(200),
body TEXT
) ENGINE=InnoDB DEFAULT CHARACTER SET gb2312 COLLATE gb2312_chinese_ci;
INSERT INTO articles (title, body) VALUES
('数据库是数据的结构化集合','它可以是任何东西'),
('从简单的购物清单到画展','或企业网络中的海量数据');
CREATE FULLTEXT INDEX ft_index ON articles(title, body) WITH PARSER ngram;
SET GLOBAL innodb_ft_aux_table="test/articles";
SELECT * FROM INFORMATION_SCHEMA.INNODB_FT_INDEX_TABLE;
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据');
DELETE FROM articles WHERE id = 1;
SET GLOBAL INNODB_OPTIMIZE_FULLTEXT_ONLY=1;
OPTIMIZE TABLE articles;
SET GLOBAL INNODB_OPTIMIZE_FULLTEXT_ONLY=default;
SELECT * FROM INFORMATION_SCHEMA.INNODB_FT_INDEX_TABLE;
SELECT * FROM articles WHERE
MATCH(title, body) AGAINST('数据');
SET GLOBAL innodb_ft_aux_table=default;
DROP TABLE articles;
-- echo # Test Case 9: Test Rename Index
--replace_regex /\.dll/.so/
eval INSTALL PLUGIN simple_parser SONAME '$SIMPLE_PARSER';
CREATE TABLE articles (
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
title VARCHAR(200),
body TEXT
) ENGINE=InnoDB DEFAULT CHARACTER SET gb2312 COLLATE gb2312_chinese_ci;
INSERT INTO articles (title, body) VALUES ('数据的结合','数据库');
CREATE FULLTEXT INDEX ft_1 ON articles(title) WITH PARSER ngram;
SELECT * FROM articles WHERE MATCH(title) AGAINST('数据');
ALTER TABLE articles RENAME INDEX ft_1 TO ft_2;
INSERT INTO articles (title, body) VALUES ('数据的结合','数据库');
SELECT * FROM articles WHERE MATCH(title) AGAINST('数据');
ALTER TABLE articles RENAME INDEX ft_2 to ft_1,
ADD FULLTEXT INDEX ft_2(body) WITH PARSER simple_parser;
INSERT INTO articles (title, body) VALUES ('数据的结合','数据库');
SELECT * FROM articles WHERE MATCH(title) AGAINST('数据');
SELECT * FROM articles WHERE MATCH(body) AGAINST('数据');
SELECT * FROM articles WHERE MATCH(body) AGAINST('数据库');
ALTER TABLE articles RENAME INDEX ft_2 to ft_1, RENAME INDEX ft_1 to ft_2;
INSERT INTO articles (title, body) VALUES ('数据的结合','数据库');
SELECT * FROM articles WHERE MATCH(title) AGAINST('数据');
SELECT * FROM articles WHERE MATCH(body) AGAINST('数据');
SELECT * FROM articles WHERE MATCH(body) AGAINST('数据库');
DROP TABLE articles;
UNINSTALL PLUGIN simple_parser;
-- echo # Test Case 10: Test Fulltext with UCS2
CREATE TABLE articles (
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
title VARCHAR(200),
body TEXT
) ENGINE=InnoDB DEFAULT CHARACTER SET ucs2;
INSERT INTO articles (title, body) VALUES ('数据的结合','数据库');
# Fulltext with charset UCS2 is not allowed.
-- error ER_BAD_FT_COLUMN
CREATE FULLTEXT INDEX ft_idx ON articles(title) WITH PARSER ngram;
-- error ER_BAD_FT_COLUMN
CREATE FULLTEXT INDEX ft_idx ON articles(title);
DROP TABLE articles;
|
