我想把一个非常大的字符串(比如10,000个字符)分割成n大小的块。

就性能而言,最好的方法是什么?

例如: "1234567890"除以2将变成["12","34","56","78","90"]。

使用string。prototype。match可以实现这样的事情吗如果可以,从性能来看,这是最好的方式吗?


当前回答

var str = "123456789";
var chunks = [];
var chunkSize = 2;

while (str) {
    if (str.length < chunkSize) {
        chunks.push(str);
        break;
    }
    else {
        chunks.push(str.substr(0, chunkSize));
        str = str.substr(chunkSize);
    }
}

alert(chunks); // chunks == 12,34,56,78,9

其他回答

你可以在没有正则表达式的情况下使用reduce():

(str, n) => {
  return str.split('').reduce(
    (acc, rec, index) => {
      return ((index % n) || !(index)) ? acc.concat(rec) : acc.concat(',', rec)
    },
    ''
  ).split(',')
}

它将大字符串拆分为给定单词的小字符串。

function chunkSubstr(str, words) {
  var parts = str.split(" ") , values = [] , i = 0 , tmpVar = "";
  $.each(parts, function(index, value) {
      if(tmpVar.length < words){
          tmpVar += " " + value;
      }else{
          values[i] = tmpVar.replace(/\s+/g, " ");
          i++;
          tmpVar = value;
      }
  });
  if(values.length < 1 &&  parts.length > 0){
      values[0] = tmpVar;
  }
  return values;
}

包括左版本和右版本的预分配。 对于小块,这和RegExp impl一样快,但是随着块大小的增加,速度会更快。它的内存效率很高。

function chunkLeft (str, size = 3) {
  if (typeof str === 'string') {
    const length = str.length
    const chunks = Array(Math.ceil(length / size))
    for (let i = 0, index = 0; index < length; i++) {
      chunks[i] = str.slice(index, index += size)
    }
    return chunks
  }
}

function chunkRight (str, size = 3) {
  if (typeof str === 'string') {
    const length = str.length
    const chunks = Array(Math.ceil(length / size))
    if (length) {
      chunks[0] = str.slice(0, length % size || size)
      for (let i = 1, index = chunks[0].length; index < length; i++) {
        chunks[i] = str.slice(index, index += size)
      }
    }
    return chunks
  }
}

console.log(chunkRight())  // undefined
console.log(chunkRight(''))  // []
console.log(chunkRight('1'))  // ["1"]
console.log(chunkRight('123'))  // ["123"]
console.log(chunkRight('1234'))  // ["1", "234"]
console.log(chunkRight('12345'))  // ["12", "345"]
console.log(chunkRight('123456'))  // ["123", "456"]
console.log(chunkRight('1234567'))  // ["1", "234", "567"]
    window.format = function(b, a) {
        if (!b || isNaN(+a)) return a;
        var a = b.charAt(0) == "-" ? -a : +a,
            j = a < 0 ? a = -a : 0,
            e = b.match(/[^\d\-\+#]/g),
            h = e && e[e.length - 1] || ".",
            e = e && e[1] && e[0] || ",",
            b = b.split(h),
            a = a.toFixed(b[1] && b[1].length),
            a = +a + "",
            d = b[1] && b[1].lastIndexOf("0"),
            c = a.split(".");
        if (!c[1] || c[1] && c[1].length <= d) a = (+a).toFixed(d + 1);
        d = b[0].split(e);
        b[0] = d.join("");
        var f = b[0] && b[0].indexOf("0");
        if (f > -1)
            for (; c[0].length < b[0].length - f;) c[0] = "0" + c[0];
        else +c[0] == 0 && (c[0] = "");
        a = a.split(".");
        a[0] = c[0];
        if (c = d[1] && d[d.length -
                1].length) {
            for (var d = a[0], f = "", k = d.length % c, g = 0, i = d.length; g < i; g++) f += d.charAt(g), !((g - k + 1) % c) && g < i - c && (f += e);
            a[0] = f
        }
        a[1] = b[1] && a[1] ? h + a[1] : "";
        return (j ? "-" : "") + a[0] + a[1]
    };

var str="1234567890";
var formatstr=format( "##,###.", str);
alert(formatstr);


This will split the string in reverse order with comma separated after 3 char's. If you want you can change the position.

这是一个快速而直接的解决方案

function chunkString (str, len) { const size = Math.ceil(str.length/len) const r = Array(size) let offset = 0 for (let i = 0; i < size; i++) { r[i] = str.substr(offset, len) offset += len } return r } console.log(chunkString("helloworld", 3)) // => [ "hel", "low", "orl", "d" ] // 10,000 char string const bigString = "helloworld".repeat(1000) console.time("perf") const result = chunkString(bigString, 3) console.timeEnd("perf") console.log(result) // => perf: 0.385 ms // => [ "hel", "low", "orl", "dhe", "llo", "wor", ... ]