第二十课 openGauss全文检索
学习目标
学习openGauss全文检索
openGauss提供了两种数据类型用于支持全文检索。tsvector类型表示为文本搜索优化的文件格式，tsquery类型表示文本查询
课程学习
连接数据库
#第一次进入等待15秒
#数据库启动中…
su - omm
gsql -r
学习内容如下
1.tsvector
–把一个字符串按照空格进行分词，分词的顺序是按照长短和字母排序的, 自动去掉分词中重复的词条
SELECT ‘The Fat Rats’::tsvector;
–词条位置常量也可以放到词汇中
SELECT ‘a:1 fat:2 cat:3 sat:4 on:5 a:6 mat:7 and:8 ate:9 a:10 fat:11 rat:12’::tsvector;
–拥有位置的词汇甚至可以用一个权来标记，反映文档结构，这个权可以是A，B，C或D。默认的是D，因此输出中不会出现
SELECT ‘a:1A fat:2B,4C cat:5D’::tsvector;
–to_tsvector函数对这些单词进行规范化处理, 罗列出词条并连同它们文档中的位置
SELECT to_tsvector(‘english’, ‘The Fat Rats’);
2.tsquery
SELECT ‘fat & rat’::tsquery;
–规范化转为tsquery类型
SELECT to_tsquery(‘Fat:ab & Cats’);
3.基本文本匹配
–全文检索基于匹配算子@@，当一个tsvector匹配到一个tsquery时，则返回true, tsvector和tsquery两种数据类型可以任意排序。
SELECT ‘a fat cat sat on a mat and ate a fat rat’::tsvector @@ ‘cat & rat’::tsquery AS RESULT;
SELECT ‘fat & cow’::tsquery @@ ‘a fat cat sat on a mat and ate a fat rat’::tsvector AS RESULT;
– to_tsvector和to_tsquery标准化处理
SELECT to_tsvector(‘fat cats ate fat rats’) @@ to_tsquery(‘fat & rat’) AS RESULT;
SELECT to_tsvector(‘fat cats ate fat rats’) @@ to_tsquery(‘fat & cow’) AS RESULT;
4.分词器
–查看所有分词器
\dF
–查看默认分词器
show default_text_search_config;
5.表和索引
CREATE SCHEMA tsearch;
CREATE TABLE tsearch.pgweb(id int, body text, title text, last_mod_date date);
INSERT INTO tsearch.pgweb VALUES(1, ‘China, officially the People’‘s Republic of China(PRC), located in Asia, is the world’‘s most populous state.’, ‘China’, ‘2010-1-1’);
INSERT INTO tsearch.pgweb VALUES(2, ‘America is a rock band, formed in England in 1970 by multi-instrumentalists Dewey Bunnell, Dan Peek, and Gerry Beckley.’, ‘America’, ‘2010-1-1’);
INSERT INTO tsearch.pgweb VALUES(3, ‘England is a country that is part of the United Kingdom. It shares land borders with Scotland to the north and Wales to the west.’, ‘England’,‘2010-1-1’);
–将body字段中包含america的行打印出来
SELECT id, body, title FROM tsearch.pgweb WHERE to_tsvector(body) @@ to_tsquery(‘america’);
–检索出在title或者body字段中包含china和asia的行
SELECT title FROM tsearch.pgweb WHERE to_tsvector(title || ’ ’ || body) @@ to_tsquery(‘china & asia’);
–为了加速文本搜索，可以创建GIN索引(指定english配置来解析和规范化字符串)
CREATE INDEX pgweb_idx_1 ON tsearch.pgweb USING gin(to_tsvector(‘english’, body));
–连接列的索引
CREATE INDEX pgweb_idx_3 ON tsearch.pgweb USING gin(to_tsvector(‘english’, title || ’ ’ ||
body));
–查看索引定义
\d+ tsearch.pgweb
6.清理数据
drop schema tsearch cascade;
课程作业
1.用tsvector @@ tsquery和tsquery @@ tsvector完成两个基本文本匹配
2.创建表且至少有两个字段的类型为 text类型，在创建索引前进行全文检索
3.创建GIN索引
4.清理数据
select
复制课后作业记录
omm=#
omm=# SELECT 'The Fat Rats'::tsvector;
tsvector
--------------------
'Fat' 'Rats' 'The'
(1 row)
omm=#
omm=# SELECT 'a:1 fat:2 cat:3 sat:4 on:5 a:6 mat:7 and:8 ate:9 a:10 fat:11 rat:12'::tsvector;
tsvector
-------------------------------------------------------------------------------
'a':1,6,10 'and':8 'ate':9 'cat':3 'fat':2,11 'mat':7 'on':5 'rat':12 'sat':4
(1 row)
omm=#
omm=#
omm=# SELECT 'a:1A fat:2B,4C cat:5D'::tsvector;
tsvector
----------------------------
'a':1A 'cat':5 'fat':2B,4C
(1 row)
omm=#
omm=#
omm=# SELECT to_tsvector('english', 'The Fat Rats');
to_tsvector
-----------------
'fat':2 'rat':3
(1 row)
omm=#
omm=# SELECT 'fat & rat'::tsquery;
tsquery
---------------
'fat' & 'rat'
(1 row)
omm=#
omm=# SELECT to_tsquery('Fat:ab & Cats');
to_tsquery
------------------
'fat':AB & 'cat'
(1 row)
omm=#
omm=# SELECT 'a fat cat sat on a mat and ate a fat rat'::tsvector @@ 'cat & rat'::tsquery AS RESULT;
result
--------
t
(1 row)
omm=# SELECT 'fat & cow'::tsquery @@ 'a fat cat sat on a mat and ate a fat rat'::tsvector AS RESULT;
result
--------
f
(1 row)
omm=#
omm=#
omm=# SELECT to_tsvector('fat cats ate fat rats') @@ to_tsquery('fat & rat') AS RESULT;
result
--------
t
(1 row)
omm=# SELECT to_tsvector('fat cats ate fat rats') @@ to_tsquery('fat & cow') AS RESULT;
result
--------
f
(1 row)
omm=#
omm=# \dF
List of text search configurations
Schema | Name | Description
------------+------------+---------------------------------------
pg_catalog | danish | configuration for danish language
pg_catalog | dutch | configuration for dutch language
pg_catalog | english | configuration for english language
pg_catalog | finnish | configuration for finnish language
pg_catalog | french | configuration for french language
pg_catalog | german | configuration for german language
pg_catalog | hungarian | configuration for hungarian language
pg_catalog | italian | configuration for italian language
pg_catalog | ngram | ngram configuration
pg_catalog | norwegian | configuration for norwegian language
pg_catalog | portuguese | configuration for portuguese language
pg_catalog | pound | pound configuration
pg_catalog | romanian | configuration for romanian language
pg_catalog | russian | configuration for russian language
pg_catalog | simple | simple configuration
pg_catalog | spanish | configuration for spanish language
pg_catalog | swedish | configuration for swedish language
pg_catalog | turkish | configuration for turkish language
pg_catalog | zhparser | zhparser configuration
(19 rows)
omm=#
omm=#
omm=#
omm=# show default_text_search_config;
default_text_search_config
----------------------------
pg_catalog.english
(1 row)
omm=#
omm=#
omm=# CREATE SCHEMA tsearch;
CREATE SCHEMA
omm=# CREATE TABLE tsearch.pgweb(id int, body text, title text, last_mod_date date);
CREATE TABLE
omm=# INSERT INTO tsearch.pgweb VALUES(1, 'China, officially the People''s Republic of China(PRC), located in Asia, is the world''s most populous state.', 'China', '2010-1-1');
INSERT 0 1
omm=# INSERT INTO tsearch.pgweb VALUES(2, 'America is a rock band, formed in England in 1970 by multi-instrumentalists Dewey Bunnell, Dan Peek, and Gerry Beckley.', 'America', '2010-1-1');
INSERT 0 1
omm=# INSERT INTO tsearch.pgweb VALUES(3, 'England is a country that is part of the United Kingdom. It shares land borders with Scotland to the north and Wales to the west.', 'England','2010-1-1');
INSERT 0 1
omm=#
omm=#
omm=# SELECT id, body, title FROM tsearch.pgweb WHERE to_tsvector(body) @@ to_tsquery('america');
id | body | title
----+-------------------------------------------------------------------------------------------------------------------------+---------
2 | America is a rock band, formed in England in 1970 by multi-instrumentalists Dewey Bunnell, Dan Peek, and Gerry Beckley. | America
(1 row)
omm=#
omm=# SELECT title FROM tsearch.pgweb WHERE to_tsvector(title || ' ' || body) @@ to_tsquery('china & asia');
title
-------
China
(1 row)
omm=#
omm=# CREATE INDEX pgweb_idx_1 ON tsearch.pgweb USING gin(to_tsvector('english', body));
CREATE INDEX
omm=#
omm=# CREATE INDEX pgweb_idx_3 ON tsearch.pgweb USING gin(to_tsvector('english', title || ' ' ||
omm(# body));
CREATE INDEX
omm=#
omm=#
omm=#
omm=# \d+ tsearch.pgweb
Table "tsearch.pgweb"
Column | Type | Modifiers | Storage | Stats target | Description
---------------+---------+-----------+----------+--------------+-------------
id | integer | | plain | |
body | text | | extended | |
title | text | | extended | |
last_mod_date | date | | plain | |
Indexes:
"pgweb_idx_1" gin (to_tsvector('english'::regconfig, body)) TABLESPACE pg_default
"pgweb_idx_3" gin (to_tsvector('english'::regconfig, (title || ' '::text) || body)) TABLESPACE pg_default
Has OIDs: no
Options: orientation=row, compression=no
omm=#
omm=#
omm=# drop schema tsearch cascade;
NOTICE: drop cascades to table tsearch.pgweb
DROP SCHEMA
omm=#
复制