算法：js 数组 array 去重，并显示所有重复的元素

算法：js 数组 array 去重，并显示所有重复的元素

遇到这样一个问题，一个数组中查重并提取所有重复的项目，不仅仅只展示多出来的。

[1,2,2,3,4,5,6,7,3,2,3] 得出 [2,2,2,3,3,3]
而不只是得出 [2,3,2,3]

一、问题：

需要处理的数据是这样的，前面是词条，后面是编码
需要实现的是：

• 查出所有词条文字一样的词条，不只是多余的词条

斯蒂芬	aaaw
劳苦功高	aaay
式子	aabb
草草了事	aabg
茕茕孑立	aabu
戒除	aabw
落落难合	aacw
式	aad
葚	aad
工友	aadc
工友	aad1
工友	aad2
工厂	aadg
工友	aad3
工厂	aad1
工厂	aad2
工厂	aad3
落荒而逃	aadi
匿	aadk
花花太岁	aadm
慝	aadn
工厂	aad4
葚	aadn
落花有意	aadu

二、处理源数据

将其拆分后处理得出可操作数据

{"id":73334,"code":"aaaw","word":"斯蒂芬","priority":null},
{"id":73335,"code":"aaay","word":"劳苦功高","priority":null},
{"id":73336,"code":"aabb","word":"式子","priority":null},
{"id":73337,"code":"aabg","word":"草草了事","priority":null},
{"id":73338,"code":"aabu","word":"茕茕孑立","priority":null},
{"id":73339,"code":"aabw","word":"戒除","priority":null},
{"id":73340,"code":"aacw","word":"落落难合","priority":null},
{"id":73341,"code":"aad","word":"式","priority":null},
{"id":73342,"code":"aad","word":"葚","priority":null},
{"id":73343,"code":"aadc","word":"工友","priority":null},
{"id":73344,"code":"aad1","word":"工友","priority":null},
{"id":73345,"code":"aad2","word":"工友","priority":null},
{"id":73346,"code":"aadg","word":"工厂","priority":null},
{"id":73347,"code":"aad3","word":"工友","priority":null},
{"id":73348,"code":"aad1","word":"工厂","priority":null},
{"id":73349,"code":"aad2","word":"工厂","priority":null},
{"id":73350,"code":"aad3","word":"工厂","priority":null},
{"id":73351,"code":"aadi","word":"落荒而逃","priority":null},
{"id":73352,"code":"aadk","word":"匿","priority":null},
{"id":73353,"code":"aadm","word":"花花太岁","priority":null},
{"id":73354,"code":"aadn","word":"慝","priority":null},
{"id":73355,"code":"aad4","word":"工厂","priority":null},
{"id":73356,"code":"aadn","word":"葚","priority":null},
{"id":73357,"code":"aadu","word":"落花有意","priority":null},

三、查重算法

由于需要提取出所有重复的元素，我的解决办法是：

1. 遍历数组，以 word 为 key 生成 一个对照的 Map()
2. 遍历过程中，如果比较的词条已经在 Map 中了，保存对照的元素和被对照元素
3. 以上操作会多出许多重复的元素，这里需要去重，只留一个
4. 最后就是所有重复的元素

实现方法：

// 查重，返回重复定义的字词
    // includeCharacter 当包含单字时
    getRepetitionWords(){
        let startPoint = new Date().getTime()
        let wordMap = new Map() // 1. 定义一个字典文件
        let repetitionWords = [] // 2. 盛放重复的元素
        this.wordsOrigin.forEach(word => { // 3. 遍历
              if (wordMap.has(word.word)){ // 3.1 如果 map 中已经有这个词，
                  repetitionWords.push(word) // 记录这个词
                  let matchedWord = wordMap.get(word.word) // 获取保存在 map 中的源元素
                  repetitionWords.push(matchedWord) // 记录 map 中的这个词。这样每重复一次都会多添加一次源元素，这个在其后进行处理
              } else { // 如果 map 中没有这个词的记录，添加这个记录
                  wordMap.set(word.word, word) // 3.2 如果 map 中没有这个词，记录下来，用于比较
              }
        })
        // 排序后再去除重复项
        repetitionWords.sort((a, b) => {
            // log(a.word + a.code, b.word + b.code)
            return (a.word + a.code) > (b.word + b.code)  ? 1 : -1 // 以词条+编码 作为排序依据
        })
        log('重复词条数量:未去重之前 ', repetitionWords.length)

		// 去除记录的词条里重复的元素
        for (let i = 0; i < repetitionWords.length - 1; i++) {
            if (repetitionWords[i].id === repetitionWords[i + 1].id ) {
                log(repetitionWords[i].toString(), repetitionWords[i+1].toString())
                repetitionWords.splice(i,1)
                i = i - 1
            }
        }
        log(`查重完成，用时 ${new Date().getTime() - startPoint} ms`)
        log('词条字典数量: ', wordMap.size)
        log('重复词条数量: ', repetitionWords.length)
        log('重复 + 词条字典 = ', repetitionWords.length + wordMap.size)
        repetitionWords.forEach(item => log( item.toString()))
        return repetitionWords
    }

四、结果

这是我查出的 8w 条数据中的重复项，很棒！

[{"id":73348,"code":"aad1","word":"工厂","priority":null},
{"id":73349,"code":"aad2","word":"工厂","priority":null},
{"id":73350,"code":"aad3","word":"工厂","priority":null},
{"id":73355,"code":"aad4","word":"工厂","priority":null},
{"id":73346,"code":"aadg","word":"工厂","priority":null},
{"id":73344,"code":"aad1","word":"工友","priority":null},
{"id":73345,"code":"aad2","word":"工友","priority":null},
{"id":73347,"code":"aad3","word":"工友","priority":null},
{"id":73343,"code":"aadc","word":"工友","priority":null},
{"id":117210,"code":"qtqt","word":"狡猾","priority":null},
{"id":117418,"code":"quqm","word":"狡猾","priority":null},
{"id":117211,"code":"qtqt","word":"狼狈","priority":null},
{"id":117927,"code":"qyqm","word":"狼狈","priority":null},
{"id":115794,"code":"qjqd","word":"猖獗","priority":null},
{"id":117209,"code":"qtqt","word":"猖獗","priority":null},
{"id":102180,"code":"khkh","word":"跟踪","priority":null},
{"id":103615,"code":"kvkp","word":"跟踪","priority":null},
{"id":102178,"code":"khkh","word":"跳跃","priority":null},
{"id":102476,"code":"kikt","word":"跳跃","priority":null},
{"id":101472,"code":"kckt","word":"踊跃","priority":null},
{"id":102179,"code":"khkh","word":"踊跃","priority":null}]