pinyin-match

src/node_modules/pinyin-match/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2020 All contributors to pinyin-match
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

src/node_modules/pinyin-match/README.md

@@ -0,0 +1,72 @@
+# pinyin-match
+
+能够使用拼音快速检索目标。
+
+1. 28.5KB (gzip => 20.3KB)
+2. 支持多音字、拼音首字母匹配,具备分词功能
+3. 覆盖 6763 个汉字
+4. 返回位置信息，可用于高亮匹配字符
+5. 在长多音字串下依然有高性能
+
+在线演示：<http://139.199.181.200:8686>;
+
+## 安装
+
+```shell
+npm install pinyin-match --save
+```
+
+也支持`<script>`引入
+
+`<script src="pinyin-match/dist/main.js"></script>`
+
+`PinyinMatch.match('xxx', 'x')`
+
+## API
+
+### .match(input, keyword)
+
+查询匹配拼音的数据。
+
+参数：
+
+1. input `{string}` 目标字符串
+2. keyword `{string}` 输入的拼音或其他关键词
+
+返回：
+
+`{[Array]|{Boolean}}`
+
+## 使用范例
+
+列表项为字符串：
+
+```js
+
+const PinyinMatch = require('pinyin-match');
+let test = '123曾经沧海难为水除却巫山不是云'
+
+PinyinMatch.match(test, '23曾'); // [1, 3]
+
+PinyinMatch.match(test, 'cjc') // [3, 5]
+
+PinyinMatch.match(test, 'cengjingcanghai') // [3, 6]
+
+PinyinMatch.match(test, 'cengjingcangha') // [3, 6]
+
+PinyinMatch.match(test, 'engjingcanghai') // false
+
+PinyinMatch.match(test, 'zengjingcang') // [3, 5]
+
+PinyinMatch.match(test, 'sdjkelwqf') // false
+
+PinyinMatch.match(text, 'zengji ng cang') // [3, 5]
+
+PinyinMatch.match(text, 'zengji ng cangsdjfkl') // false
+
+PinyinMatch.match('   我 爱你 中   国   ', 'nzg') // [6, 12]
+
+PinyinMatch.match('   我 爱你 中   国   ', '爱你中') // [5, 8]
+
+```
+**如果对你项目有帮助请给个Star**

src/node_modules/pinyin-match/index.d.ts

@@ -0,0 +1,6 @@
+declare namespace Pinyin {
+  export function match(input: string, keys: string): [number, number] | boolean;
+}
+
+export as namespace Pinyin;
+export = Pinyin;

src/node_modules/pinyin-match/package.json

@@ -0,0 +1,63 @@
+{
+  "_from": "pinyin-match",
+  "_id": "pinyin-match@1.1.1",
+  "_inBundle": false,
+  "_integrity": "sha512-stJVNJGHOEl3B3qXgeXJhWk3xfYQ3X7VaHBIIQHI2/9E1hNK9cmkigei0F+1l+uBM2XPVgxtmzg08AuY7n5Rnw==",
+  "_location": "/pinyin-match",
+  "_phantomChildren": {},
+  "_requested": {
+    "type": "tag",
+    "registry": true,
+    "raw": "pinyin-match",
+    "name": "pinyin-match",
+    "escapedName": "pinyin-match",
+    "rawSpec": "",
+    "saveSpec": null,
+    "fetchSpec": "latest"
+  },
+  "_requiredBy": [
+    "#USER",
+    "/"
+  ],
+  "_resolved": "https://registry.npmjs.org/pinyin-match/-/pinyin-match-1.1.1.tgz",
+  "_shasum": "b13000800e4c0c2f22904ecf4a07423ddf9c1023",
+  "_spec": "pinyin-match",
+  "_where": "C:\\Users\\fofol\\OneDrive\\Configs\\uTools\\QuickerCommand\\src",
+  "author": {
+    "name": "774898896@qq.com"
+  },
+  "bugs": {
+    "url": "https://github.com/xmflswood/pinyin-match/issues"
+  },
+  "bundleDependencies": false,
+  "deprecated": false,
+  "description": "支持多音字，首字母缩写的拼音搜索引擎",
+  "devDependencies": {
+    "babel-core": "^6.26.3",
+    "babel-loader": "^7.1.5",
+    "babel-preset-env": "^1.7.0",
+    "mocha": "^5.2.0",
+    "webpack": "^4.16.1",
+    "webpack-cli": "^3.1.2"
+  },
+  "homepage": "https://github.com/xmflswood/pinyin-match#readme",
+  "keywords": [
+    "拼音",
+    "chinese",
+    "pinyin",
+    "match"
+  ],
+  "license": "ISC",
+  "main": "dist/main.js",
+  "name": "pinyin-match",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/xmflswood/pinyin-match.git"
+  },
+  "scripts": {
+    "build": "webpack",
+    "test": "mocha"
+  },
+  "typings": "index.d.ts",
+  "version": "1.1.1"
+}

src/node_modules/pinyin-match/src/index.js

@@ -0,0 +1,169 @@
+const dict = require('./pinyin_dict_notone').pinyin_dict_notone
+const allPinyin = require('./pinyin_dict_notone').allPinyin
+const notone = parseDict()
+let storage = {}
+function parseDict() {
+  let parseDict = {}
+  for (let i in dict) {
+    let temp = dict[i]
+    for (let j = 0, len = temp.length; j < len; j++) {
+      if (!parseDict[temp[j]]) {
+        parseDict[temp[j]] = i
+      } else {
+        parseDict[temp[j]] = parseDict[temp[j]] + ' ' + i
+      }
+    }
+  }
+  return parseDict
+}
+
+function getPinyin(cn) {
+  let result = []
+  for (let i = 0, len = cn.length; i < len; i ++) {
+    let temp = cn.charAt(i)
+    result.push(notone[temp] || temp)
+  }
+  return result
+}
+// 对输入拼音进行切分
+function wordBreak(s) {
+  let result = []
+  let solutions = []
+  let len = s.length
+  let possible = []
+  for (let i = 0; i <= s.length; i++) {
+    possible.push(true)
+  }
+  getAllSolutions(0, s, result, solutions, possible)
+  return solutions
+}
+
+function getAllSolutions(start, s, result, solutions, possible) {
+  if (start === s.length) {
+    solutions.push(result.join(' '))
+    return
+  }
+  for (let i = start; i < s.length; i++) {
+    let piece = s.substring(start, i + 1)
+    let match = false
+    // 最后一个音特殊处理，不需要全部打完整
+    if (allPinyin.some(i => i.indexOf(piece) === 0) && !s[i + 1] && possible[i + 1]) {
+      if (piece.length === 1) {
+        result.push(piece)
+      } else {
+        let s = []
+        allPinyin.forEach(i => {
+          if (i.indexOf(piece) === 0) {
+            s.push(i)
+          }
+        })
+        result.push(s)
+      }
+      match = true
+    } else {
+      if (allPinyin.indexOf(piece) !== -1 && possible[i + 1]) {
+        result.push(piece)
+        match = true
+      }
+    }
+    if (match) {
+      let beforeChange = solutions.length
+      getAllSolutions(i + 1, s, result, solutions, possible)
+      if (solutions.length === beforeChange) {
+        possible[i + 1] = false
+      }
+      result.pop()
+    }
+  }
+}
+// 获取输入拼音的所有组合（切分 + 首字母）
+function getFullKey(key) {
+  let result = []
+  wordBreak(key).forEach(i => {
+    let item = i.split(' ')
+    let last = item.length - 1
+    if (item[last].indexOf(',')) {
+      let keys = item[last].split(',')
+      keys.forEach(j => {
+        item.splice(last, 1, j)
+        result.push(JSON.parse(JSON.stringify(item)))
+      })
+    } else {
+      result.push(item)
+    }
+  })
+  if (result.length === 0 || (result[0].length !== key.length)) {
+    result.push(key.split(''))
+  }
+  // 缓存当前结果 避免重复计算
+  storage = {[key]: result}
+  return result
+}
+function point2point(test, key, last, extend) {
+  if (!test) return false
+  let a = test.split(' ')
+  a.forEach(i => {
+    if (i.length > 0 && extend) {
+      a.push(i.charAt(0))
+    }
+  })
+  if (!last) {
+    return a.indexOf(key) !== -1
+  }
+  return a.some((i) => i.indexOf(key) === 0)
+}
+
+function match(input, keys) {
+  input = input.toLowerCase()
+  keys = keys.replace(/\s+/g, '').toLowerCase()
+  let indexOf = input.indexOf(keys)
+  if (indexOf !== -1) {
+    return [indexOf, indexOf + keys.length - 1]
+  }
+  // 原文匹配(带空格)
+  let noPyIndex = getIndex(input.split(''), [keys.split('')], keys)
+  if (noPyIndex) return noPyIndex
+  // pinyin匹配
+  let py = getPinyin(input)
+  let fullString = storage[keys] || getFullKey(keys)
+  return getIndex(py, fullString, keys)
+}
+function getIndex(py, fullString, keys) {
+  for (let p = 0; p < py.length; p++) {
+    for (let k = 0; k < fullString.length; k++) {
+      let key = fullString[k]
+      let keyLength = key.length
+      let extend = (keyLength === keys.length)
+      let isMatch = true
+      let i = 0
+      let preSpaceNum = 0
+      let spaceNum = 0
+      if (keyLength <= py.length) {
+        for (; i < key.length; i++) {
+          if (i === 0 && py[p + i + preSpaceNum] === ' ') {
+            preSpaceNum += 1
+            i -= 1
+          } else {
+            if (py[p + i + spaceNum] === ' ') {
+              spaceNum += 1
+              i -= 1
+            } else {
+              if (!point2point(py[p + i + spaceNum], key[i], (py[p + i + 1] && key[i + 1]) ? false : true, extend)) {
+                isMatch = false
+                break
+              }
+            }
+          }
+        }
+        if (isMatch) {
+          return [p + preSpaceNum, spaceNum + p + i - 1]
+        }
+      }
+    }
+  }
+  return false
+}
+const pinyin = {
+  match
+}
+module.exports = pinyin

src/node_modules/pinyin-match/test/index.test.js

@@ -0,0 +1,50 @@
+const assert = require('assert')
+const PinyinMatch = require('../src/index')
+let text = '123曾经沧海难为水除却巫山不是云'
+
+describe('PinyinMatch', () => {
+  describe('#match', () => {
+    it('精准匹配', () => {
+      assert.deepEqual([1, 3], PinyinMatch.match(text, '23曾'))
+    })
+    it('首字母匹配', () => {
+      assert.deepEqual([3, 5], PinyinMatch.match(text, 'cjc'))
+    })
+    it('完整拼音匹配', () => {
+      assert.deepEqual([3, 6], PinyinMatch.match(text, 'cengjingcanghai'))
+    })
+    it('最后一个拼音不完整', () => {
+      assert.deepEqual([3, 6], PinyinMatch.match(text, 'cengjingcangha'))
+    })
+    it('分词功能', () => {
+      assert.equal(false, PinyinMatch.match(text, 'engjing'))
+    })
+    it('多音字', () => {
+      assert.deepEqual([3, 5], PinyinMatch.match(text, 'zengjingcang'))
+    })
+    it('忽略空格', () => {
+      assert.deepEqual([3, 5], PinyinMatch.match(text, 'zengji ng cang'))
+    })
+    it('超出', () => {
+      assert.deepEqual(false, PinyinMatch.match(text, 'zengji ng cangsdjfkl'))
+    })
+    it('忽略空格', () => {
+      assert.deepEqual([6, 12], PinyinMatch.match('   我 爱你 中   国   ', 'nzg'))
+    })
+    it('忽略空格原文', () => {
+      assert.deepEqual([5, 8], PinyinMatch.match('   我 爱你 中   国s   ', '爱你中'))
+    })
+    it('忽略空格原文', () => {
+      assert.deepEqual([5, 13], PinyinMatch.match('   我 爱你 中   国s   ', '爱你中国s'))
+    })
+    it('超出原文', () => {
+      assert.deepEqual(false, PinyinMatch.match('   我 爱你 中   国s   ', '爱你中国sj'))
+    })
+    it('bao', () => {
+      assert.deepEqual([1, 1], PinyinMatch.match('淘宝', 'bao'))
+    })
+    it('issues 7', () => {
+      assert.deepEqual([0, 0], PinyinMatch.match('卡号打开', 'ka'))
+    })
+  })
+})

src/node_modules/pinyin-match/webpack.config.js

@@ -0,0 +1,29 @@
+const path = require('path')
+const webpack = require('webpack')
+
+module.exports = {
+  entry: path.resolve(__dirname, 'src', 'index.js'),
+  output: {
+    path: path.resolve(__dirname, 'dist'),
+    filename: 'main.js',
+    library: 'PinyinMatch',
+    globalObject: 'typeof self !== \'undefined\' ? self : this',
+    libraryTarget: 'umd'
+  },
+  module: {
+    rules: [{
+      test: /\.js$/,
+      use: [{
+        loader: 'babel-loader',
+        options: {
+          presets: [
+            'env'
+          ]
+        }
+      }]
+    }]
+  },
+  plugins: [
+    new webpack.optimize.ModuleConcatenationPlugin()
+  ]
+}