今天,按照徐进挺之“Oracle全文检索”进行测试，发现Context类型索引对中文不能分词，结果如下：

Create table docs (id number primary key, text varchar2(200));
Insert into docs values(1, 'california is a state in the us.');
Insert into docs values(2, 'paris is a city in france.');
Insert into docs values(3, 'france is in europe.');
Commit;
/
--建立context 索引
Create index idx_docs on docs(text)
indextype is ctxsys.context parameters
('filter ctxsys.null_filter section group ctxsys.html_section_group');
--查询
Column text format a40;
Select id, text from docs where contains(text, 'france') > 0;

        ID TEXT
---------- ----------------------------------------
         2 paris is a city in france.
         3 france is in europe.

        
--继续插入数据
Insert into docs values(4, 'los angeles is a city in california.');
Insert into docs values(5, 'mexico city is big.');
commit;
Select id, text from docs where contains(text, 'city') > 0;--新插入的数据没有查询到

        ID TEXT
---------- ----------------------------------------
         2 paris is a city in france.

--索引同步
exec ctx_ddl.sync_index('idx_docs', '2m');

Select id, text from docs where contains(text, 'city') > 0; --查到数据
        ID TEXT
---------- ----------------------------------------------------------------------
         2 paris is a city in france.
         4 los angeles is a city in california.
         5 mexico city is big.

Select id, text from docs where contains(text, 'city or state ') > 0;

        ID TEXT
---------- ----------------------------------------------------------------------
         1 california is a state in the us.
         2 paris is a city in france.
         4 los angeles is a city in california.
         5 mexico city is big.

Select id, text from docs where contains(text, 'city and state ') > 0;
Select id, text from docs where contains(text, 'city state ') > 0;
        ID TEXT
---------- ----------------------------------------------------------------------

SQL> Select SCORE(1),id, text from docs where contains(text, 'city or state',1) > 0;

  SCORE(1)         ID TEXT
---------- ---------- ----------------------------------------------------------------------
         5          1 california is a state in the us.
         4          2 paris is a city in france.
         4          4 los angeles is a city in california.
         4          5 mexico city is big.

--下面中文
Insert into docs values(14, '新华网东京4月12日电（记者蓝建中）日本经济产业省原子能安全保安院与日本原子能安全委员会12日上午举行联合新闻发布会，正式宣布根据国际核事件分级表，将福岛第一核电站事故的严重程度评价提高到最高级别7级。');
Insert into docs values(15, '原子能安全保安院宣布，福岛第一核电站向大气泄漏的放射性物质已达到37万万亿贝克勒尔，而原子能安全委员会推断为63万万亿贝克勒尔，虽然数值存在差异，但都已经远远超过核电站事故7级的标准。');
Insert into docs values(16, '国际核事件分级表规定，如果放射性物质向外部的泄漏量达到数万万亿贝克勒尔，就应定为7级。');
commit;

SQL> Select id, text from docs where contains(text, '原子能') > 0;

        ID TEXT
---------- ----------------------------------------------------------------------

SQL> Select id, text from docs;

        ID TEXT
---------- ----------------------------------------------------------------------
         1 california is a state in the us.
         2 paris is a city in france.
         3 france is in europe.
         4 los angeles is a city in california.
         5 mexico city is big.
        14 原子能安全保安院宣布，福岛第一核电站向大气泄漏的放射性物质已达到37万万
           亿贝克勒尔，而原子能安全委员会推断为63万万亿贝克勒尔，虽然数值存在差异
           ，但都已经远远超过核电站事故7级的标准。');
          
        15 原子能安全保安院宣布，福岛第一核电站向大气泄漏的放射性物质已达到37万万
           亿贝克勒尔，而原子能安全委员会推断为63万万亿贝克勒尔，虽然数值存在差异
           ，但都已经远远超过核电站事故7级的标准。

        16 国际核事件分级表规定，如果放射性物质向外部的泄漏量达到数万万亿贝克勒尔
           ，就应定为7级。

8 rows selected