Skip to content

Commit

Permalink
Merge pull request #53 from repairearth/master
Browse files Browse the repository at this point in the history
Add chinese support
  • Loading branch information
MihaiValentin authored Jun 17, 2021
2 parents a62fec9 + bc6b23f commit 1b55cc8
Show file tree
Hide file tree
Showing 5 changed files with 207 additions and 2 deletions.
4 changes: 3 additions & 1 deletion .gitignore
Original file line number Diff line number Diff line change
@@ -1,2 +1,4 @@
node_modules
.idea
.idea
.history
.vscode
143 changes: 143 additions & 0 deletions lunr.zh.js
Original file line number Diff line number Diff line change
@@ -0,0 +1,143 @@
/*!
* Lunr languages, `Chinese` language
* https://github.com/MihaiValentin/lunr-languages
*
* Copyright 2019, Felix Lian (repairearth)
* http://www.mozilla.org/MPL/
*/
/*!
* based on
* Snowball zhvaScript Library v0.3
* http://code.google.com/p/urim/
* http://snowball.tartarus.org/
*
* Copyright 2010, Oleg Mazko
* http://www.mozilla.org/MPL/
*/

/**
* export the module via AMD, CommonJS or as a browser global
* Export code from https://github.com/umdjs/umd/blob/master/returnExports.js
*/
;
(function(root, factory) {
if (typeof define === 'function' && define.amd) {
// AMD. Register as an anonymous module.
define(factory)
} else if (typeof exports === 'object') {
/**
* Node. Does not work with strict CommonJS, but
* only CommonJS-like environments that support module.exports,
* like Node.
*/
module.exports = factory(require('nodejieba'))
} else {
// Browser globals (root is window)
factory()(root.lunr);
}
}(this, function(nodejieba) {
/**
* Just return a value to define the module export.
* This example returns an object, but the module
* can return a function as the exported value.
*/
return function(lunr, nodejiebaDictJson) {
/* throw error if lunr is not yet included */
if ('undefined' === typeof lunr) {
throw new Error('Lunr is not present. Please include / require Lunr before this script.');
}

/* throw error if lunr stemmer support is not yet included */
if ('undefined' === typeof lunr.stemmerSupport) {
throw new Error('Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.');
}

/*
Chinese tokenization is trickier, since it does not
take into account spaces.
Since the tokenization function is represented different
internally for each of the Lunr versions, this had to be done
in order to try to try to pick the best way of doing this based
on the Lunr version
*/
var isLunr2 = lunr.version[0] == "2";

/* register specific locale function */
lunr.zh = function() {
this.pipeline.reset();
this.pipeline.add(
lunr.zh.trimmer,
lunr.zh.stopWordFilter,
lunr.zh.stemmer
);

// change the tokenizer for Chinese one
if (isLunr2) { // for lunr version 2.0.0
this.tokenizer = lunr.zh.tokenizer;
} else {
if (lunr.tokenizer) { // for lunr version 0.6.0
lunr.tokenizer = lunr.zh.tokenizer;
}
if (this.tokenizerFn) { // for lunr version 0.7.0 -> 1.0.0
this.tokenizerFn = lunr.zh.tokenizer;
}
}
};

lunr.zh.tokenizer = function(obj) {
if (!arguments.length || obj == null || obj == undefined) return []
if (Array.isArray(obj)) return obj.map(function (t) { return isLunr2 ? new lunr.Token(t.toLowerCase()) : t.toLowerCase() })

nodejiebaDictJson && nodejieba.load(nodejiebaDictJson)

var str = obj.toString().trim().toLowerCase();
var tokens = [];

nodejieba.cut(str, true).forEach(function (seg) {
tokens = tokens.concat(seg.split(' '))
})

tokens = tokens.filter(function (token) {
return !!token;
});

var fromIndex = 0

return tokens.map(function (token, index) {
if (isLunr2) {
var start = str.indexOf(token, fromIndex)

var tokenMetadata = {}
tokenMetadata["position"] = [start, token.length]
tokenMetadata["index"] = index

fromIndex = start

return new lunr.Token(token, tokenMetadata);
} else {
return token
}
});
}

/* lunr trimmer function */
lunr.zh.wordCharacters = "\\w\u4e00-\u9fa5";
lunr.zh.trimmer = lunr.trimmerSupport.generateTrimmer(lunr.zh.wordCharacters);
lunr.Pipeline.registerFunction(lunr.zh.trimmer, 'trimmer-zh');

/* lunr stemmer function */
lunr.zh.stemmer = (function() {

/* TODO Chinese stemmer */
return function(word) {
return word;
}
})();
lunr.Pipeline.registerFunction(lunr.zh.stemmer, 'stemmer-zh');

/* lunr stop word filter. see https://www.ranks.nl/stopwords/chinese-stopwords */
lunr.zh.stopWordFilter = lunr.generateStopWordFilter(
'的 一 不 在 人 有 是 为 以 于 上 他 而 后 之 来 及 了 因 下 可 到 由 这 与 也 此 但 并 个 其 已 无 小 我 们 起 最 再 今 去 好 只 又 或 很 亦 某 把 那 你 乃 它 吧 被 比 别 趁 当 从 到 得 打 凡 儿 尔 该 各 给 跟 和 何 还 即 几 既 看 据 距 靠 啦 了 另 么 每 们 嘛 拿 哪 那 您 凭 且 却 让 仍 啥 如 若 使 谁 虽 随 同 所 她 哇 嗡 往 哪 些 向 沿 哟 用 于 咱 则 怎 曾 至 致 着 诸 自'.split(' '));
lunr.Pipeline.registerFunction(lunr.zh.stopWordFilter, 'stopWordFilter-zh');
};
}))
3 changes: 3 additions & 0 deletions package.json
Original file line number Diff line number Diff line change
Expand Up @@ -18,5 +18,8 @@
"mocha": "^6.2.0",
"uglify-js": "^2.4.15",
"unicode-8.0.0": "^0.1.5"
},
"dependencies": {
"nodejieba": "^2.3.0"
}
}
3 changes: 2 additions & 1 deletion test/VersionsAndLanguagesTest.js
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,8 @@ var testDocuments = {
sv: require('./testdata/sv'),
tr: require('./testdata/tr'),
th: require('./testdata/th'),
vi: require('./testdata/vi')
vi: require('./testdata/vi'),
zh: require('./testdata/zh')
};

lunrVersions.forEach(function(lunrVersion) {
Expand Down
56 changes: 56 additions & 0 deletions test/testdata/zh.js
Original file line number Diff line number Diff line change
@@ -0,0 +1,56 @@
module.exports = {
fields: [
{
name: 'title',
config: { boost: 10 }
}, {
name: 'body'
}
],
documents: [
{
"title": "【新闻1+1】Mercedes Benz女车主维权 车主到底难在何处?",
"body": "你们说给我3天时间,我给了你3天,我给你们5个3天,15天,15天你不给我个方案,最后给我的方案是换发动机,15天最后给我这个方案,您觉得我接受得了吗?",
"id": 1
}, {
"title": "央视CCTV13新闻1+1正在说奔驰漏油事件",
"body": "我这个车没开出去这个门发动机漏油,你给我说讲三包,给我车主说免费换发动机,我跟你说要求你说可以退款可以换车,你又最后说换发动机,还给我说打12315,大哥你觉得合适吗?",
"id": 2
}, {
"title": "奔驰女车主接受专访,经销商咋就这么强势?",
"body": "我打电话给奔驰金融,我说我这天15天没开过,我可不可以暂停还款,人家说不可以,这是用你个人征信做的贷款,你贷款必须还,我车没开到,我凭什么还这个贷款。",
"id": 3
}
],
tests: [
{
what: "find the word %w",
search: "车主",
found: 3
}, {
what: "find the word %w",
search: "Benz",
found: 1
}, {
what: "find the word %w",
search: "Mercedes Benz",
found: 1
}, {
what: "find the word %w",
search: "12315",
found: 1
}, {
what: "find the word %w",
search: "CCTV13",
found: 1
}, {
what: "never find a word that does not exist, like %w",
search: "美女",
found: 0
}, {
what: "never find a character like %w",
search: ",",
found: 0
}
]
}

0 comments on commit 1b55cc8

Please sign in to comment.