我想将一个非常大的字符串(例如10,000个字符)分割成N个大小的块。
就性能而言,最佳方法是什么?
例如:
"1234567890"
被2分割成["12", "34", "56", "78", "90"]
。
使用这种方法是否可行?String.prototype.match
如果可以,从性能角度来看,这是否是最佳方法?
我想将一个非常大的字符串(例如10,000个字符)分割成N个大小的块。
就性能而言,最佳方法是什么?
例如:
"1234567890"
被2分割成["12", "34", "56", "78", "90"]
。
使用这种方法是否可行?String.prototype.match
如果可以,从性能角度来看,这是否是最佳方法?
Answers:
您可以执行以下操作:
"1234567890".match(/.{1,2}/g);
// Results in:
["12", "34", "56", "78", "90"]
该方法仍可用于大小不是块大小的整数倍的字符串:
"123456789".match(/.{1,2}/g);
// Results in:
["12", "34", "56", "78", "9"]
通常,对于要从中提取最多n个大小的子字符串的任何字符串,都可以执行以下操作:
str.match(/.{1,n}/g); // Replace n with the size of the substring
如果您的字符串可以包含换行符或回车符,则可以执行以下操作:
str.match(/(.|[\r\n]){1,n}/g); // Replace n with the size of the substring
就性能而言,我用大约1万个字符进行了尝试,而在Chrome上花了一点时间。YMMV。
这也可以在可重用的函数中使用:
function chunkString(str, length) {
return str.match(new RegExp('.{1,' + length + '}', 'g'));
}
.
根本不匹配换行符。因此,它需要我会更新的答案\n
和\r
考虑。
var chunks = str.split("").reverse().join().match(/.{1, 4}/).map(function(s) { return s.split("").reverse().join(); });
。这以4为单位进行。我不确定您所说的“更少或更多”是什么意思。请记住,这通常不会起作用,特别是对于包含组合字符并且也可能破坏Unicode字符串的字符串。
[^]
。有了这个,您的示例将导致str.match(/[^]{1,n}/g)
我创建了几个更快的变体,您可以在jsPerf上看到它们。我最喜欢的一个是:
function chunkSubstr(str, size) {
const numChunks = Math.ceil(str.length / size)
const chunks = new Array(numChunks)
for (let i = 0, o = 0; i < numChunks; ++i, o += size) {
chunks[i] = str.substr(o, size)
}
return chunks
}
Math.ceil()
在确定应该正确的块数时应该进行四舍五入。
底线:
match
非常低效,slice
更好,在Firefox上substr
/ substring
还是更好match
对于短字符串甚至效率更低(即使使用缓存的正则表达式,也可能是由于正则表达式解析设置时间所致)match
对于大块数据甚至效率更高(可能是由于无法“跳跃”)match
性能优于slice
,但在所有其他系统上仍然会失败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", ... ]
substr()
代替substring()
。
惊喜!您可以使用split进行拆分。
var parts = "1234567890 ".split(/(.{2})/).filter(O=>O)
结果是 [ '12', '34', '56', '78', '90', ' ' ]
filter (o=>o)
为了什么?
filter(x=>x)
用于过滤那些空元素
我已经编写了扩展函数,因此块长度也可以是数字数组,例如[1,3]
String.prototype.chunkString = function(len) {
var _ret;
if (this.length < 1) {
return [];
}
if (typeof len === 'number' && len > 0) {
var _size = Math.ceil(this.length / len), _offset = 0;
_ret = new Array(_size);
for (var _i = 0; _i < _size; _i++) {
_ret[_i] = this.substring(_offset, _offset = _offset + len);
}
}
else if (typeof len === 'object' && len.length) {
var n = 0, l = this.length, chunk, that = this;
_ret = [];
do {
len.forEach(function(o) {
chunk = that.substring(n, n + o);
if (chunk !== '') {
_ret.push(chunk);
n += chunk.length;
}
});
if (n === 0) {
return undefined; // prevent an endless loop when len = [0]
}
} while (n < l);
}
return _ret;
};
代码
"1234567890123".chunkString([1,3])
将返回:
[ '1', '234', '5', '678', '9', '012', '3' ]
它将大字串拆分为给定单词的小字串。
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;
}
经过一些试验,以下是我为模板字符串想到的解决方案:
用法:
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
这是我正在使用的代码,它使用String.prototype.slice。
是的,答案很长,它试图尽可能接近当前的标准,并且当然包含相当数量的JSDOC注释。但是,一旦压缩,该代码仅为828字节,而一旦压缩以进行传输,则仅为497字节。
这添加到的1方法String.prototype
(使用Object.defineProperty,如果可用)是:
包括许多测试以检查功能。
担心代码的长度会影响性能吗?不用担心,http://jsperf.com/chunk-string/3
有许多额外的代码可以确保这些代码在多个javascript环境中都能做出相同的响应。
/*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>
使用slice()方法:
function returnChunksArray(str, chunkSize) {
var arr = [];
while(str !== '') {
arr.push(str.slice(0, chunkSize));
str = str.slice(chunkSize);
}
return arr;
}
使用substring()方法可以完成相同的操作。
function returnChunksArray(str, chunkSize) {
var arr = [];
while(str !== '') {
arr.push(str.substring(0, chunkSize));
str = str.substring(chunkSize);
}
return arr;
}
我与上述解决方案有关的问题是,不管句子中的位置如何,都将字符串分成正式大小的块。
我认为以下更好的方法;尽管需要一些性能调整:
static chunkString(str, length, size,delimiter='\n' ) {
const result = [];
for (let i = 0; i < str.length; i++) {
const lastIndex = _.lastIndexOf(str, delimiter,size + i);
result.push(str.substr(i, lastIndex - i));
i = lastIndex;
}
return result;
}
你绝对可以做类似的事情
let pieces = "1234567890 ".split(/(.{2})/).filter(x => x.length == 2);
得到这个:
[ '12', '34', '56', '78', '90' ]
如果要动态输入/调整块大小以使块大小为n,则可以执行以下操作:
n = 2;
let pieces = "1234567890 ".split(new RegExp("(.{"+n.toString()+"})")).filter(x => x.length == n);
要在原始字符串中找到所有可能的大小为n的块,请尝试以下操作:
let subs = new Set();
let n = 2;
let str = "1234567890 ";
let regex = new RegExp("(.{"+n.toString()+"})"); //set up regex expression dynamically encoded with n
for (let i = 0; i < n; i++){ //starting from all possible offsets from position 0 in the string
let pieces = str.split(regex).filter(x => x.length == n); //divide the string into chunks of size n...
for (let p of pieces) //...and add the chunks to the set
subs.add(p);
str = str.substr(1); //shift the string reading frame
}
您应该最终得到:
[ '12', '23', '34', '45', '56', '67', '78', '89', '90', '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.
function chunkString(str, length = 10) {
let result = [],
offset = 0;
if (str.length <= length) return result.push(str) && result;
while (offset < str.length) {
result.push(str.substr(offset, length));
offset += length;
}
return result;
}