cjk-tokenizer
Version:
A CJK text tokenizer
43 lines (42 loc) • 909 B
JSON
{
"name": "cjk-tokenizer",
"version": "0.1.0",
"description": "A CJK text tokenizer",
"main": "lib/index.js",
"bin": {
"cjk-tokenizer": "./bin/cjk-tokenizer.js"
},
"scripts": {
"test": "echo \"Error: no test specified\" && exit 1"
},
"repository": {
"type": "git",
"url": "git+https://github.com/leungwensen/cjk-tokenizer.git"
},
"keywords": [
"CJK",
"tokenizer",
"CJK",
"tokenizer",
"n-gram",
"porter-stemmer",
"text",
"corpus",
"Chinese",
"Japanese",
"Korean",
"English"
],
"author": "leungwensen@gmail.com",
"license": "MIT",
"bugs": {
"url": "https://github.com/leungwensen/cjk-tokenizer/issues"
},
"homepage": "https://github.com/leungwensen/cjk-tokenizer#readme",
"dependencies": {
"commander": "^2.9.0",
"japanese": "^1.1.0",
"porter-stemmer": "^0.9.1",
"zero-lang": "^0.2.1"
}
}