{
   "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.",
   "version": "0.7.0",
   "date": "2026-05-02T09:07:42Z",
   "maintainer": [
      "Preedee Ponchevin <nickmsft@mac.com>"
   ],
   "release_status": "stable",
   "user": "nix",
   "sha1": "ed66069ff576b702e633c7a7bb83d0a2e0c698ad",
   "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--0.7.0.sql",
         "version": "0.7.0"
      }
   },
   "tags": ["thai", "full-text-search", "nlp", "tokenizer", "soundex", "romanization", "named-entity", "parser"],
   "resources": {
      "bugtracker": {
         "web": "https://github.com/preedep/kham/issues"
      },
      "homepage": "https://github.com/preedep/kham",
      "repository": {
         "type": "git",
         "url": "https://github.com/preedep/kham.git",
         "web": "https://github.com/preedep/kham"
      }
   }
}