{
  "name": "kham_pg",
  "abstract": "Thai word-segmentation FTS parser — tsvector, soundex, RTGS romanization, NER",
  "description": "kham_pg is a PostgreSQL text-search parser for the Thai language. Thai has no spaces between words, so standard PostgreSQL parsers produce incorrect token boundaries. kham_pg uses the kham newmm segmentation engine to split Thai text correctly, then expands each token into up to three lexemes at the same tsvector position: the normalised word, its lk82 Thai Soundex code (phonetic-fuzzy search), and its RTGS romanization (Latin-script search). Named entities (persons, places, organisations) are tagged automatically. Supports to_tsvector, plainto_tsquery, ts_rank, ts_headline, and GIN/GiST indexes. Tested on PostgreSQL 14–18.",
  "tags": ["thai", "full-text-search", "nlp", "tokenizer", "soundex", "romanization", "named-entity", "parser"],
  "version": "0.8.2",
  "maintainer": [
    "Preedee Ponchevin <nickmsft@mac.com>"
  ],
  "license": "mit",
  "prereqs": {
    "runtime": {
      "requires": {
        "PostgreSQL": "0"
      }
    }
  },
  "provides": {
    "kham_pg": {
      "abstract": "Thai word-segmentation FTS parser — tsvector, soundex, RTGS romanization, NER",
      "file": "sql/kham_pg--0.8.2.sql",
      "version": "0.8.2"
    }
  },
  "resources": {
    "homepage": "https://github.com/preedep/kham",
    "bugtracker": {
      "web": "https://github.com/preedep/kham/issues"
    },
    "repository": {
      "url": "https://github.com/preedep/kham.git",
      "web": "https://github.com/preedep/kham",
      "type": "git"
    }
  },
  "generated_by": "Preedee Ponchevin",
  "meta-spec": {
    "version": "1.0.0",
    "url": "http://pgxn.org/meta/spec.txt"
  }
}