使用PostgreSQL数据库进行中文全文搜索的实现方法

CREATE EXTENSION pg_trgm

CREATE EXTENSION zhparser

CREATE TEXT SEARCH CONFIGURATION chinese_zh (PARSER = zhparser)

ALTER TEXT SEARCH CONFIGURATION chinese_zh ADD MAPPING FOR n,v,a,i,e,l WITH simple

select ts_debug('chinese_zh', '春秋、战国是中国历史上思想迸发的时代，出现了百家争鸣的现象');

"(t,""time,时语素"",春秋,{},,)"
"(u,""auxiliary,助词"",、,{},,)"
"(t,""time,时语素"",战国,{},,)"
"(v,""verb,动词"",是,{simple},simple,{是})"
"(n,""noun,名词"",中国,{simple},simple,{中国})"
"(n,""noun,名词"",历史,{simple},simple,{历史})"
"(n,""noun,名词"",上思,{simple},simple,{上思})"
"(v,""verb,动词"",想,{simple},simple,{想})"
"(v,""verb,动词"",迸发,{simple},simple,{迸发})"
"(u,""auxiliary,助词"",的,{},,)"
"(n,""noun,名词"",时代,{simple},simple,{时代})"
"(u,""auxiliary,助词"",，,{},,)"
"(v,""verb,动词"",出现,{simple},simple,{出现})"
"(v,""verb,动词"",了,{simple},simple,{了})"
"(n,""noun,名词"",百家争鸣,{simple},simple,{百家争鸣})"
"(u,""auxiliary,助词"",的,{},,)"
"(n,""noun,名词"",现象,{simple},simple,{现象})"

select to_tsvector('chinese_zh', '春秋、战国是中国历史上思想迸发的时代，出现了百家争鸣的现象');

"'上思':4 '中国':2 '了':9 '出现':8 '历史':3 '想':5 '时代':7 '是':1 '现象':11 '百家争鸣':10 '迸发':6"

ALTER TEXT SEARCH CONFIGURATION chinese_zh ADD MAPPING FOR t WITH simple;

"'上思':6 '中国':4 '了':11 '出现':10 '历史':5 '想':7 '战国':2 '时代':9 '春秋':1 '是':3 '现象':13 '百家争鸣':12 '迸发':8"

select to_tsquery('战国') @@ to_tsvector('chinese_zh', '春秋、战国是中国历史上思想迸发的时代，出现了百家争鸣的现象');

select to_tsquery('二十四节谷') @@  to_tsvector('chinese_zh', '春秋、战国是中国历史上思想迸发的时代，在二十四节谷出现了百家争鸣的现象');
false

'上思':6 '中国':4 '了':11 '出现':10 '历史':5 '想':7

#word TF  IDF ATTR
二十四节谷  1 1 n

select ts_debug('chinese_zh', '春秋、战国是中国历史上思想迸发的时代，在二十四节谷出现了百家争鸣的现象');
(n,"noun,名词",二十四节谷,{simple},simple,{二十四节谷})

create table testing(
  title text
  );
  insert into testing values('春秋、战国是中国历史上思想迸发的时代，出现了百家争鸣的现象');
  insert into testing values('春秋、战国是中国历史上思想迸发的时代，在二十四节谷出现了百家争鸣的现象');
create index ind_testing on testing using gin (to_tsvector('chinese_zh', title));

select * from testing where to_tsquery('chinese_zh', '二十四节谷') @@ to_tsvector('chinese_zh', title);