在JavaScript中将大字符串分割成n个字符大小的块

311

我希望将一个非常大的字符串(比如说 10,000 个字符)分割成 N 大小的块。

从性能方面考虑,最好的方法是什么?

举个例子: "1234567890" 拆分为 2 小块会变成 ["12", "34", "56", "78", "90"]

是否可以使用 String.prototype.match 来实现这样的功能?如果可以,从性能方面考虑,这是否是最佳方式?

23个回答

3
var l = str.length, lc = 0, chunks = [], c = 0, chunkSize = 2;
for (; lc < l; c++) {
  chunks[c] = str.slice(lc, lc += chunkSize);
}

3

it Split将大字符串拆分成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;
}

2

我会使用正则表达式...

var chunkStr = function(str, chunkLength) {
    return str.match(new RegExp('[\\s\\S]{1,' + +chunkLength + '}', 'g'));
}

2

在进行一些尝试后,我为模板字符串想出了一种解决方案:

使用方法:

chunkString(5)`testing123`

function chunkString(nSize) {
    return (strToChunk) => {
        let result = [];
        let chars = String(strToChunk).split('');

        for(let i = 0; i < (String(strToChunk).length / nSize); i++) {
            result = result.concat(chars.slice(i*nSize,(i+1)*nSize).join(''));
        }
        return result
    }
}

document.write(chunkString(5)`testing123`);
// returns: testi,ng123

document.write(chunkString(3)`testing123`);
// returns: tes,tin,g12,3


1

这个小代码片段怎么样:

function splitME(str, size) {
    let subStr = new RegExp('.{1,' + size + '}', 'g');
    return str.match(subStr);
};

1
您可以在不使用任何正则表达式的情况下使用reduce()函数:
(str, n) => {
  return str.split('').reduce(
    (acc, rec, index) => {
      return ((index % n) || !(index)) ? acc.concat(rec) : acc.concat(',', rec)
    },
    ''
  ).split(',')
}

如果您能提供如何使用reduce方法的示例,我认为这将非常有帮助。 - kiatng

1
请使用这个npm库"chkchars",但是要记得确保给定的字符串长度能够被"number"参数完美地整除。
const phrase = "1110010111010011100101110100010000011100101110100111001011101001011101001110010111010001000001110010111010011100101110100"
const number = 7

chkchars.splitToChunks(phrase, number)

// result => ['1110010', '1110100','1110010', '1110100','0100000', '1110010','1110100', '1110010','1110100', '1011101','0011100', '1011101','0001000','0011100','1011101', '0011100','1011101']

// perf => 0.287ms

0
    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.

0
以原型函数的形式:
String.prototype.lsplit = function(){
    return this.match(new RegExp('.{1,'+ ((arguments.length==1)?(isFinite(String(arguments[0]).trim())?arguments[0]:false):1) +'}', 'g'));
}

0

这里是我正在使用的代码,它使用了String.prototype.slice

是的,作为答案,它相当长,因为它尽可能地遵循当前标准,并且当然包含了相当数量的JSDOC注释。但是,一旦被压缩,该代码仅为828字节,一旦被gzip传输,它只有497字节。

这个添加到String.prototype中的1个方法(在可用的情况下使用Object.defineProperty)是:

  1. toChunks

已经包括了许多测试来检查功能。

担心代码长度会影响性能吗?不用担心,http://jsperf.com/chunk-string/3

额外的大部分代码都是为了确保代码在多个JavaScript环境中响应相同。

/*jslint maxlen:80, browser:true, devel:true */

/*
 * Properties used by toChunks.
 */

/*property
    MAX_SAFE_INTEGER, abs, ceil, configurable, defineProperty, enumerable,
    floor, length, max, min, pow, prototype, slice, toChunks, value,
    writable
*/

/*
 * Properties used in the testing of toChunks implimentation.
 */

/*property
    appendChild, createTextNode, floor, fromCharCode, getElementById, length,
    log, pow, push, random, toChunks
*/

(function () {
    'use strict';

    var MAX_SAFE_INTEGER = Number.MAX_SAFE_INTEGER || Math.pow(2, 53) - 1;

    /**
     * Defines a new property directly on an object, or modifies an existing
     * property on an object, and returns the object.
     *
     * @private
     * @function
     * @param {Object} object
     * @param {string} property
     * @param {Object} descriptor
     * @return {Object}
     * @see https://goo.gl/CZnEqg
     */
    function $defineProperty(object, property, descriptor) {
        if (Object.defineProperty) {
            Object.defineProperty(object, property, descriptor);
        } else {
            object[property] = descriptor.value;
        }

        return object;
    }

    /**
     * Returns true if the operands are strictly equal with no type conversion.
     *
     * @private
     * @function
     * @param {*} a
     * @param {*} b
     * @return {boolean}
     * @see http://www.ecma-international.org/ecma-262/5.1/#sec-11.9.4
     */
    function $strictEqual(a, b) {
        return a === b;
    }

    /**
     * Returns true if the operand inputArg is undefined.
     *
     * @private
     * @function
     * @param {*} inputArg
     * @return {boolean}
     */
    function $isUndefined(inputArg) {
        return $strictEqual(typeof inputArg, 'undefined');
    }

    /**
     * The abstract operation throws an error if its argument is a value that
     * cannot be converted to an Object, otherwise returns the argument.
     *
     * @private
     * @function
     * @param {*} inputArg The object to be tested.
     * @throws {TypeError} If inputArg is null or undefined.
     * @return {*} The inputArg if coercible.
     * @see https://goo.gl/5GcmVq
     */
    function $requireObjectCoercible(inputArg) {
        var errStr;

        if (inputArg === null || $isUndefined(inputArg)) {
            errStr = 'Cannot convert argument to object: ' + inputArg;
            throw new TypeError(errStr);
        }

        return inputArg;
    }

    /**
     * The abstract operation converts its argument to a value of type string
     *
     * @private
     * @function
     * @param {*} inputArg
     * @return {string}
     * @see https://people.mozilla.org/~jorendorff/es6-draft.html#sec-tostring
     */
    function $toString(inputArg) {
        var type,
            val;

        if (inputArg === null) {
            val = 'null';
        } else {
            type = typeof inputArg;
            if (type === 'string') {
                val = inputArg;
            } else if (type === 'undefined') {
                val = type;
            } else {
                if (type === 'symbol') {
                    throw new TypeError('Cannot convert symbol to string');
                }

                val = String(inputArg);
            }
        }

        return val;
    }

    /**
     * Returns a string only if the arguments is coercible otherwise throws an
     * error.
     *
     * @private
     * @function
     * @param {*} inputArg
     * @throws {TypeError} If inputArg is null or undefined.
     * @return {string}
     */
    function $onlyCoercibleToString(inputArg) {
        return $toString($requireObjectCoercible(inputArg));
    }

    /**
     * The function evaluates the passed value and converts it to an integer.
     *
     * @private
     * @function
     * @param {*} inputArg The object to be converted to an integer.
     * @return {number} If the target value is NaN, null or undefined, 0 is
     *                   returned. If the target value is false, 0 is returned
     *                   and if true, 1 is returned.
     * @see http://www.ecma-international.org/ecma-262/5.1/#sec-9.4
     */
    function $toInteger(inputArg) {
        var number = +inputArg,
            val = 0;

        if ($strictEqual(number, number)) {
            if (!number || number === Infinity || number === -Infinity) {
                val = number;
            } else {
                val = (number > 0 || -1) * Math.floor(Math.abs(number));
            }
        }

        return val;
    }

    /**
     * The abstract operation ToLength converts its argument to an integer
     * suitable for use as the length of an array-like object.
     *
     * @private
     * @function
     * @param {*} inputArg The object to be converted to a length.
     * @return {number} If len <= +0 then +0 else if len is +INFINITY then
     *                   2^53-1 else min(len, 2^53-1).
     * @see https://people.mozilla.org/~jorendorff/es6-draft.html#sec-tolength
     */
    function $toLength(inputArg) {
        return Math.min(Math.max($toInteger(inputArg), 0), MAX_SAFE_INTEGER);
    }

    if (!String.prototype.toChunks) {
        /**
         * This method chunks a string into an array of strings of a specified
         * chunk size.
         *
         * @function
         * @this {string} The string to be chunked.
         * @param {Number} chunkSize The size of the chunks that the string will
         *                           be chunked into.
         * @returns {Array} Returns an array of the chunked string.
         */
        $defineProperty(String.prototype, 'toChunks', {
            enumerable: false,
            configurable: true,
            writable: true,
            value: function (chunkSize) {
                var str = $onlyCoercibleToString(this),
                    chunkLength = $toInteger(chunkSize),
                    chunked = [],
                    numChunks,
                    length,
                    index,
                    start,
                    end;

                if (chunkLength < 1) {
                    return chunked;
                }

                length = $toLength(str.length);
                numChunks = Math.ceil(length / chunkLength);
                index = 0;
                start = 0;
                end = chunkLength;
                chunked.length = numChunks;
                while (index < numChunks) {
                    chunked[index] = str.slice(start, end);
                    start = end;
                    end += chunkLength;
                    index += 1;
                }

                return chunked;
            }
        });
    }
}());

/*
 * Some tests
 */

(function () {
    'use strict';

    var pre = document.getElementById('out'),
        chunkSizes = [],
        maxChunkSize = 512,
        testString = '',
        maxTestString = 100000,
        chunkSize = 0,
        index = 1;

    while (chunkSize < maxChunkSize) {
        chunkSize = Math.pow(2, index);
        chunkSizes.push(chunkSize);
        index += 1;
    }

    index = 0;
    while (index < maxTestString) {
        testString += String.fromCharCode(Math.floor(Math.random() * 95) + 32);
        index += 1;
    }

    function log(result) {
        pre.appendChild(document.createTextNode(result + '\n'));
    }

    function test() {
        var strLength = testString.length,
            czLength = chunkSizes.length,
            czIndex = 0,
            czValue,
            result,
            numChunks,
            pass;

        while (czIndex < czLength) {
            czValue = chunkSizes[czIndex];
            numChunks = Math.ceil(strLength / czValue);
            result = testString.toChunks(czValue);
            czIndex += 1;
            log('chunksize: ' + czValue);
            log(' Number of chunks:');
            log('  Calculated: ' + numChunks);
            log('  Actual:' + result.length);
            pass = result.length === numChunks;
            log(' First chunk size: ' + result[0].length);
            pass = pass && result[0].length === czValue;
            log(' Passed: ' + pass);
            log('');
        }
    }

    test();
    log('');
    log('Simple test result');
    log('abcdefghijklmnopqrstuvwxyz'.toChunks(3));
}());
<pre id="out"></pre>


网页内容由stack overflow 提供, 点击上面的
可以查看英文原文,
原文链接