zhparser

pig build pkg zhparser         # build RPM / DEB packages

pig repo add pgsql -u          # Add repo and update cache

CREATE EXTENSION zhparser;

-- Create the extension
CREATE EXTENSION zhparser;

-- Create a text search configuration using zhparser
CREATE TEXT SEARCH CONFIGURATION chinese (PARSER = zhparser);

-- Add token type mappings
ALTER TEXT SEARCH CONFIGURATION chinese ADD MAPPING FOR n,v,a,i,e,l WITH simple;

-- Test Chinese text segmentation
SELECT to_tsvector('chinese', '小明硕士毕业于中国科学院计算所，后在日本京都大学深造');

-- Create a table and index for Chinese full text search
CREATE TABLE articles (id serial PRIMARY KEY, title text, body text);

CREATE INDEX articles_body_idx ON articles
  USING gin (to_tsvector('chinese', body));

-- Query with Chinese full text search
SELECT * FROM articles
  WHERE to_tsvector('chinese', body) @@ to_tsquery('chinese', '中国');

-- Add custom words via zhparser's built-in table
INSERT INTO zhparser.zhprs_custom_word VALUES ('中国科学院计算所');

-- Reload custom dictionary (reconnect after sync to take effect)
SELECT sync_zhprs_custom_word();

-- Verify segmentation with custom word
SELECT to_tsvector('chinese', '小明硕士毕业于中国科学院计算所');

docker run --name pgzhparser -d \
  -e POSTGRES_PASSWORD=somepassword \
  zhparser/zhparser:bookworm-16