Question

我试图用一个显示带有频率的单词的段落来制作一个对象。

var pattern = /\w+/g,
//the farsi paragraph
    string = "من امروز در مورد مهر خروج مشمولین اطلاعات جدیدی از سفارت ایران در مالزی گرفتم",
    matchedWords = string.match( pattern );

/* The Array.prototype.reduce method assists us in producing a single value from an
   array. In this case, we're going to use it to output an object with results. */
var counts = matchedWords.reduce(function ( stats, word ) {

    /* `stats` is the object that we'll be building up over time.
       `word` is each individual entry in the `matchedWords` array */
    if ( stats.hasOwnProperty( word ) ) {
        /* `stats` already has an entry for the current `word`.
           As a result, let's increment the count for that `word`. */
        stats[ word ] = stats[ word ] + 1;
    } else {
        /* `stats` does not yet have an entry for the current `word`.
           As a result, let's add a new entry, and set count to 1. */
        stats[ word ] = 1;
    }

    /* Because we are building up `stats` over numerous iterations,
       we need to return it for the next pass to modify it. */
    return stats;

}, {})

var dict = []; // create an empty array
// this for loop makes a dictionary for you
for (i in counts){
dict.push({'text':i, "size": counts[i]});


};

/* lets print and see if you can solve your problem */

console.log( dict);

最初为英文段落编写的代码。但是我需要将它用于波斯语。我知道它应该是别的而不是＆＃34; / \ w + / g＆＃34;在：

var pattern = /\w+/g,

但我不知道是什么。

Answer 1

在你的正则表达式中使用变量为\S的“任何字符但空白”。编辑：空格被视为换行符，选项卡和空格）

var pattern = /\S+/g,
//the farsi paragraph
    string = "من امروز در مورد مهر خروج مشمولین اطلاعات جدیدی از سفارت ایران در مالزی گرفتم",
    matchedWords = string.match( pattern );

/* The Array.prototype.reduce method assists us in producing a single value from an
   array. In this case, we're going to use it to output an object with results. */
var counts = matchedWords.reduce(function ( stats, word ) {

    /* `stats` is the object that we'll be building up over time.
       `word` is each individual entry in the `matchedWords` array */
    if ( stats.hasOwnProperty( word ) ) {
        /* `stats` already has an entry for the current `word`.
           As a result, let's increment the count for that `word`. */
        stats[ word ] = stats[ word ] + 1;
    } else {
        /* `stats` does not yet have an entry for the current `word`.
           As a result, let's add a new entry, and set count to 1. */
        stats[ word ] = 1;
    }

    /* Because we are building up `stats` over numerous iterations,
       we need to return it for the next pass to modify it. */
    return stats;

}, {})

var dict = []; // create an empty array
// this for loop makes a dictionary for you
for (i in counts){
dict.push({'text':i, "size": counts[i]});


};

/* lets print and see if you can solve your problem */

console.log( dict);

Answer 2

要匹配任何字母，您需要使用XRegExp包和\pL Unicode属性类：

＆＃13;

var pattern = new XRegExp("[_\\pL\\pN]+", "g");
var s = "من امروز در مورد مهر خروج مشمولین اطلاعات جدیدی از سفارت ایران در مالزی گرفتم";
var matchedWords = s.match( pattern );
var counts = matchedWords.reduce(function ( stats, word ) {
 if ( stats.hasOwnProperty( word ) ) {
    stats[ word ] = stats[ word ] + 1;
 } else {
    stats[ word ] = 1;
 }
 return stats;
}, {})

var dict = [];
for (i in counts){
	dict.push({'text':i, "size": counts[i]});
 }
console.log(dict);

＆＃13;

<script src="https://cdnjs.cloudflare.com/ajax/libs/xregexp/3.2.0/xregexp-all.min.js"></script>

＆＃13;

[_\\pL\\pN]+模式匹配一个或多个下划线（_，我将其包括在内，因为原始正则表达式中的\w也匹配_），Unicode字母（{{1} }}和数字（\pL）。

要仅计算由字母组成的单词，请使用

\pN

Answer 3

为什么不在你的情况下使用split与reduce结合使用？例如：

const p = 'من امروز در مورد مهر خروج مشمولین اطلاعات جدیدی از سفارت ایران در مالزی گرفتم';

const counted = p.split( ' ' ).reduce( ( collected, item ) => {
  collected[ item ] = ( collected[ item ] || 0 ) + 1;
  return collected;
}, { /* initial empty object */ } );
const dict = Object.keys( counted ).map( key => {
  return {
    text: key,
    size: counted[ key ],
  };
} );

console.log( 'در:', counted[ 'در' ] );
console.log( dict );

它更简单，表现更好。你甚至可以省略const dict...部分。

Answer 4

您可以使用JS等效词和量词"This is articles ViewModel: public ArticlesViewModel() { public string ArticleName { get; set; } }"
这将匹配大约119,000 Unicode 9 字符这包括所有非字母，非数字，其他字符
像下划线一样，其中大约有1,100个。

注意 - 它运行得非常快，但我会使这个正则表达式全局和
编译一次以供以后使用。

此外，这是从ICU数据库生成的，它提供了完整的数据在U + 000000到U + 10FFFF之间的单词\w+的样本，从这个正则表达式中是使用UCD Interface应用中的RegexFormat生成的。

这是 XRegExp 无法做到的事情。

演示：

https://regex101.com/r/sjLmMC/1

\w

如何将波斯语（波斯语）段落转换为Javascript中的单词列表

4 个答案: