diff --git a/CN/modules/ROOT/nav.adoc b/CN/modules/ROOT/nav.adoc index b62fe4a5..7498e1d6 100644 --- a/CN/modules/ROOT/nav.adoc +++ b/CN/modules/ROOT/nav.adoc @@ -76,6 +76,7 @@ *** xref:master/ecosystem_components/zhparser.adoc[zhparser] *** xref:master/ecosystem_components/pgbackrest.adoc[pgBackRest] *** xref:master/ecosystem_components/set_user.adoc[set_user] +*** xref:master/ecosystem_components/pg_jieba.adoc[pg_jieba] * 监控运维 ** xref:master/getting-started/daily_monitoring.adoc[日常监控] ** xref:master/getting-started/daily_maintenance.adoc[日常维护] diff --git a/CN/modules/ROOT/pages/master/ecosystem_components/pg_jieba.adoc b/CN/modules/ROOT/pages/master/ecosystem_components/pg_jieba.adoc new file mode 100644 index 00000000..71b30a93 --- /dev/null +++ b/CN/modules/ROOT/pages/master/ecosystem_components/pg_jieba.adoc @@ -0,0 +1,68 @@ + +:sectnums: +:sectnumlevels: 5 + += pg_jieba + +== 概述 + +pg_jieba 是PostgreSQL的一个中文分词扩展,基于著名的结巴分词(Jieba)开发。它能够将连续的中文文本切分成有意义的词语序列,为中文全文搜索提供基础支持。 + +== 功能特点 + +* *支持三种分词模式*:精确模式、全模式和搜索引擎模式。 +* *与PostgreSQL/IvorySQL无缝集成* +* *支持自定义词典* +* *支持词性标注* + +== 安装部署 + +=== 编译安装 pg_jieba + +假设IvorySQL已经安装在 ~/ivy_5/inst 目录中。 + +[source,shell] +---- +git clone https://github.com/jaiminpan/pg_jieba.git +cd pg_jieba +git submodule update --init --recursive +mkdir build;cd build +cmake -DCMAKE_PREFIX_PATH=~/ivy_5/inst .. +make; make install +---- + +安装成功后,`pg_jieba.so` 等文件会被放置到 IvorySQL 的安装目录中。 + +=== 创建扩展并验证 + +[source,sql] +---- +CREATE EXTENSION IF NOT EXISTS pg_jieba; +SELECT name, + default_version, + installed_version, + comment + FROM pg_available_extensions + WHERE name = 'pg_jieba'; +---- + +== 使用 + +执行如下sql示例: + +[source,sql] +---- +select * from to_tsquery('jiebacfg', '是拖拉机学院手扶拖拉机专业的。不用多久,我就会升职加薪,当上CEO,走上人生巅峰。'); + to_tsquery +----------------------------------------------------------------------------------------------- +'拖拉机' & '学院' & '手扶拖拉机' & '专业' & '不用' & '多久' & '会' & '升职' & '加薪' & '当上' & 'ceo' & '走上' & '人生' & '巅峰' +(1 row) + +select * from to_tsvector('jiebacfg', '是拖拉机学院手扶拖拉机专业的。不用多久,我就会升职加薪,当上CEO,走上人生巅峰。'); + to_tsvector +----------------------------------------------------------------------------------------------------- +'ceo':18 '不用':8 '专业':5 '人生':21 '会':13 '加薪':15 '升职':14 '多久':9 '学院':3 '巅峰':22 '当上':17 '手扶拖拉机':4 '拖拉机':2 '走上':20 +(1 row) +---- + + diff --git a/EN/modules/ROOT/nav.adoc b/EN/modules/ROOT/nav.adoc index e4221c78..6983cf77 100644 --- a/EN/modules/ROOT/nav.adoc +++ b/EN/modules/ROOT/nav.adoc @@ -76,6 +76,7 @@ *** xref:master/ecosystem_components/zhparser_en.adoc[zhparser] *** xref:master/ecosystem_components/pgbackrest.adoc[pgBackRest] *** xref:master/ecosystem_components/set_user.adoc[set_user] +*** xref:master/ecosystem_components/pg_jieba.adoc[pg_jieba] * Monitor and O&M ** xref:master/getting-started/daily_monitoring.adoc[Monitoring] ** xref:master/getting-started/daily_maintenance.adoc[Maintenance] diff --git a/EN/modules/ROOT/pages/master/ecosystem_components/pg_jieba.adoc b/EN/modules/ROOT/pages/master/ecosystem_components/pg_jieba.adoc new file mode 100644 index 00000000..5c3df871 --- /dev/null +++ b/EN/modules/ROOT/pages/master/ecosystem_components/pg_jieba.adoc @@ -0,0 +1,67 @@ + +:sectnums: +:sectnumlevels: 5 + += pg_jieba + +== Overview + +pg_jieba is a Chinese word segmentation extension for PostgreSQL, developed based on the well-known Jieba (结巴分词) segmentation library. It can split continuous Chinese text into meaningful sequences of words, providing foundational support for Chinese full-text search. + +== Features + +* *Supports three segmentation modes*: precise mode, full mode, and search engine mode. +* *Seamless integration with PostgreSQL/IvorySQL* +* *Supports custom dictionaries* +* *Supports part-of-speech tagging* + +== Installation and Deployment + +=== Building and Installing pg_jieba + +Assume IvorySQL has already been installed in the `~/ivy_5/inst` directory. + +[source,shell] +---- +git clone https://github.com/jaiminpan/pg_jieba.git +cd pg_jieba +git submodule update --init --recursive +mkdir build;cd build +cmake -DCMAKE_PREFIX_PATH=~/ivy_5/inst .. +make; make install +---- + +After a successful installation, files such as `pg_jieba.so` will be placed into IvorySQL's installation directory. + +=== Creating and Verifying the Extension + +[source,sql] +---- +CREATE EXTENSION IF NOT EXISTS pg_jieba; +SELECT name, + default_version, + installed_version, + comment + FROM pg_available_extensions + WHERE name = 'pg_jieba'; +---- + +== Usage + +Run the following SQL example: + +[source,sql] +---- +select * from to_tsquery('jiebacfg', '是拖拉机学院手扶拖拉机专业的。不用多久,我就会升职加薪,当上CEO,走上人生巅峰。'); + to_tsquery +----------------------------------------------------------------------------------------------- +'拖拉机' & '学院' & '手扶拖拉机' & '专业' & '不用' & '多久' & '会' & '升职' & '加薪' & '当上' & 'ceo' & '走上' & '人生' & '巅峰' +(1 row) + +select * from to_tsvector('jiebacfg', '是拖拉机学院手扶拖拉机专业的。不用多久,我就会升职加薪,当上CEO,走上人生巅峰。'); + to_tsvector +----------------------------------------------------------------------------------------------------- +'ceo':18 '不用':8 '专业':5 '人生':21 '会':13 '加薪':15 '升职':14 '多久':9 '学院':3 '巅峰':22 '当上':17 '手扶拖拉机':4 '拖拉机':2 '走上':20 +(1 row) +---- +