如何在旧版 IE 中使用带 String.split 的捕获组？
How to use a capture group with String.split in old IE versions?
var textt = "L'architecture du système d'information devient";
var pattern = "/(ARCH)/gi";
var array = textt.split(pattern);
console.log(array)
这导致：
[
L',
itecture du système d'information devient
]
预期的结果是：
[
L',
arch,
itecture du système d'information devien
]
另一个例子
var textt = "ARCHIMAG";
var pattern = "/(ARCH)/gi";
var array = textt.split(pattern);
console.log(array)
结果：
[
IMAG
]
预期是：
[
ARCH,
IMAG
]
如果您对替换非捕获拆分的功能测试和功能没有问题，请尝试以下操作。它在加载脚本时测试支持，并为 nonCaptureSplit 分配适当的函数，因此测试只进行一次。
如果您使用的不是字母字符或数字（例如，如果字符串中有标点符号），则需要对模式进行转义。
已编辑
如果不支持非捕获拆分，现在完全手动拆分。
// Do case insensitive, non-capture split
var nonCaptureSplit = (function() {
// Feature test for non-capturing split
if ( 'ab'.split(/(a)/).length == 3) {
return function (str, pattern) {
var re = new RegExp('(' + pattern + ')','i');
return str.split(re);
};
// Otherise, do it with a function
} else {
return function(str, pattern) {
// Do case insensitive split
var result = [];
var ts = str.toLowerCase(); // copy of string in lower case
var tp = pattern.toLowerCase();
var first = true;
while (ts.indexOf(tp) != -1) {
var i = ts.indexOf(tp);
// If first match is at the start, insert empty string + pattern
// Trim pattern from front of temp strings
if (i == 0 && first) {
result.push('', pattern);
ts = ts.substring(tp.length);
str = str.substring(tp.length);
// If match is at the end, append pattern and ''
// Set temp string to '' (i.e. finished)
} else if (i == ts.length - tp.length) {
result.push(str.substr(0,i), pattern);
ts = '';
str = '';
// Otherwise, append the next unmatched part
// and pattern
} else {
result.push(str.substring(0,i), pattern);
ts = ts.substring(i + pattern.length);
str = str.substring(i + pattern.length);
}
first = false;
}
// Append remainder of string or '' if used, i.e. last match
// must have been at end of string
result.push( ts.length? str : '');
return result;
};
}
}());
测试：
alert(nonCaptureSplit('wa', 'wa')); // ,wa,
alert(nonCaptureSplit('qwqwaba', 'wa')); // qwq,wa,ba
alert(nonCaptureSplit('qwqwaba', 'qw')); // ,qw,,qw,aba
alert(nonCaptureSplit('qwqwaba', 'ba')); // qwqwa,ba,
alert(nonCaptureSplit('baaqwqbawaba', 'ba')); // ,ba,aqwq,ba,wa,ba,
alert(nonCaptureSplit("L'architecture du système d'information devient", "ARCH"));
// L',arch,itecture du système d'information devient
alert(nonCaptureSplit("ARCHIMAG", "ARCH")); // ,ARCH,IMAG
对于具有大量匹配项的大字符串，这可能会有点低效，但仅限于不支持非捕获拆分的浏览器。测试结果在 Safari 和 IE 6 中匹配。请彻底测试，如果有问题请告诉我。
哦，这不是一个通用的解决方案，但它应该适用于类似于 OP 的有限情况。
如果您希望解决 String.prototype.split then you need to take a look at Steven Levithan's cross browser fixes And see his original post from back in 2007. This is also used in his XRegExp library. It is also used in ES5 shim 和可能其他浏览器中的已知浏览器问题。
/*!
* Cross-Browser Split 1.1.1
* Copyright 2007-2012 Steven Levithan <stevenlevithan.com>
* Available under the MIT License
* ECMAScript compliant, uniform cross-browser split method
*/
/**
* Splits a string into an array of strings using a regex or string separator. Matches of the
* separator are not included in the result array. However, if `separator` is a regex that contains
* capturing groups, backreferences are spliced into the result each time `separator` is matched.
* Fixes browser bugs compared to the native `String.prototype.split` and can be used reliably
* cross-browser.
* @param {String} str String to split.
* @param {RegExp|String} separator Regex or string to use for separating the string.
* @param {Number} [limit] Maximum number of items to include in the result array.
* @returns {Array} Array of substrings.
* @example
*
* // Basic use
* split('a b c d', ' ');
* // -> ['a', 'b', 'c', 'd']
*
* // With limit
* split('a b c d', ' ', 2);
* // -> ['a', 'b']
*
* // Backreferences in result array
* split('..word1 word2..', /([a-z]+)(\d+)/i);
* // -> ['..', 'word', '1', ' ', 'word', '2', '..']
*/
var split;
// Avoid running twice; that would break the `nativeSplit` reference
split = split || function (undef) {
var nativeSplit = String.prototype.split,
compliantExecNpcg = /()??/.exec("")[1] === undef, // NPCG: nonparticipating capturing group
self;
self = function (str, separator, limit) {
// If `separator` is not a regex, use `nativeSplit`
if (Object.prototype.toString.call(separator) !== "[object RegExp]") {
return nativeSplit.call(str, separator, limit);
}
var output = [],
flags = (separator.ignoreCase ? "i" : "") +
(separator.multiline ? "m" : "") +
(separator.extended ? "x" : "") + // Proposed for ES6
(separator.sticky ? "y" : ""), // Firefox 3+
lastLastIndex = 0,
// Make `global` and avoid `lastIndex` issues by working with a copy
separator = new RegExp(separator.source, flags + "g"),
separator2, match, lastIndex, lastLength;
str += ""; // Type-convert
if (!compliantExecNpcg) {
// Doesn't need flags gy, but they don't hurt
separator2 = new RegExp("^" + separator.source + "$(?!\s)", flags);
}
/* Values for `limit`, per the spec:
* If undefined: 4294967295 // Math.pow(2, 32) - 1
* If 0, Infinity, or NaN: 0
* If positive number: limit = Math.floor(limit); if (limit > 4294967295) limit -= 4294967296;
* If negative number: 4294967296 - Math.floor(Math.abs(limit))
* If other: Type-convert, then use the above rules
*/
limit = limit === undef ?
-1 >>> 0 : // Math.pow(2, 32) - 1
limit >>> 0; // ToUint32(limit)
while (match = separator.exec(str)) {
// `separator.lastIndex` is not reliable cross-browser
lastIndex = match.index + match[0].length;
if (lastIndex > lastLastIndex) {
output.push(str.slice(lastLastIndex, match.index));
// Fix browsers whose `exec` methods don't consistently return `undefined` for
// nonparticipating capturing groups
if (!compliantExecNpcg && match.length > 1) {
match[0].replace(separator2, function () {
for (var i = 1; i < arguments.length - 2; i++) {
if (arguments[i] === undef) {
match[i] = undef;
}
}
});
}
if (match.length > 1 && match.index < str.length) {
Array.prototype.push.apply(output, match.slice(1));
}
lastLength = match[0].length;
lastLastIndex = lastIndex;
if (output.length >= limit) {
break;
}
}
if (separator.lastIndex === match.index) {
separator.lastIndex++; // Avoid an infinite loop
}
}
if (lastLastIndex === str.length) {
if (lastLength || !separator.test("")) {
output.push("");
}
} else {
output.push(str.slice(lastLastIndex));
}
return output.length > limit ? output.slice(0, limit) : output;
};
// For convenience
String.prototype.split = function (separator, limit) {
return self(this, separator, limit);
};
return self;
}();
这是最佳解决方案：
function ieSplit(str, separator) {
var match = str.match(RegExp(separator, 'g'));
var notmatch = str.replace(new RegExp(separator, 'g'), '[|]').split('[|]');
var merge = [];
for(i in notmatch) {
merge.push(notmatch[i]);
if (match != null && match[i] != undefined) {
merge.push(match[i]);
}
}
return merge;
}
var textt = "L'architecture du système d'information devient";
var pattern = "/(ARCH)/gi";
var array = textt.split(pattern);
console.log(array)
这导致：
[
L',
itecture du système d'information devient
]
预期的结果是：
[
L',
arch,
itecture du système d'information devien
]
另一个例子
var textt = "ARCHIMAG";
var pattern = "/(ARCH)/gi";
var array = textt.split(pattern);
console.log(array)
结果：
[
IMAG
]
预期是：
[
ARCH,
IMAG
]
如果您对替换非捕获拆分的功能测试和功能没有问题，请尝试以下操作。它在加载脚本时测试支持，并为 nonCaptureSplit 分配适当的函数，因此测试只进行一次。
如果您使用的不是字母字符或数字（例如，如果字符串中有标点符号），则需要对模式进行转义。
已编辑
如果不支持非捕获拆分，现在完全手动拆分。
// Do case insensitive, non-capture split
var nonCaptureSplit = (function() {
// Feature test for non-capturing split
if ( 'ab'.split(/(a)/).length == 3) {
return function (str, pattern) {
var re = new RegExp('(' + pattern + ')','i');
return str.split(re);
};
// Otherise, do it with a function
} else {
return function(str, pattern) {
// Do case insensitive split
var result = [];
var ts = str.toLowerCase(); // copy of string in lower case
var tp = pattern.toLowerCase();
var first = true;
while (ts.indexOf(tp) != -1) {
var i = ts.indexOf(tp);
// If first match is at the start, insert empty string + pattern
// Trim pattern from front of temp strings
if (i == 0 && first) {
result.push('', pattern);
ts = ts.substring(tp.length);
str = str.substring(tp.length);
// If match is at the end, append pattern and ''
// Set temp string to '' (i.e. finished)
} else if (i == ts.length - tp.length) {
result.push(str.substr(0,i), pattern);
ts = '';
str = '';
// Otherwise, append the next unmatched part
// and pattern
} else {
result.push(str.substring(0,i), pattern);
ts = ts.substring(i + pattern.length);
str = str.substring(i + pattern.length);
}
first = false;
}
// Append remainder of string or '' if used, i.e. last match
// must have been at end of string
result.push( ts.length? str : '');
return result;
};
}
}());
测试：
alert(nonCaptureSplit('wa', 'wa')); // ,wa,
alert(nonCaptureSplit('qwqwaba', 'wa')); // qwq,wa,ba
alert(nonCaptureSplit('qwqwaba', 'qw')); // ,qw,,qw,aba
alert(nonCaptureSplit('qwqwaba', 'ba')); // qwqwa,ba,
alert(nonCaptureSplit('baaqwqbawaba', 'ba')); // ,ba,aqwq,ba,wa,ba,
alert(nonCaptureSplit("L'architecture du système d'information devient", "ARCH"));
// L',arch,itecture du système d'information devient
alert(nonCaptureSplit("ARCHIMAG", "ARCH")); // ,ARCH,IMAG
对于具有大量匹配项的大字符串，这可能会有点低效，但仅限于不支持非捕获拆分的浏览器。测试结果在 Safari 和 IE 6 中匹配。请彻底测试，如果有问题请告诉我。
哦，这不是一个通用的解决方案，但它应该适用于类似于 OP 的有限情况。
如果您希望解决 String.prototype.split then you need to take a look at Steven Levithan's cross browser fixes And see his original post from back in 2007. This is also used in his XRegExp library. It is also used in ES5 shim 和可能其他浏览器中的已知浏览器问题。
/*!
* Cross-Browser Split 1.1.1
* Copyright 2007-2012 Steven Levithan <stevenlevithan.com>
* Available under the MIT License
* ECMAScript compliant, uniform cross-browser split method
*/
/**
* Splits a string into an array of strings using a regex or string separator. Matches of the
* separator are not included in the result array. However, if `separator` is a regex that contains
* capturing groups, backreferences are spliced into the result each time `separator` is matched.
* Fixes browser bugs compared to the native `String.prototype.split` and can be used reliably
* cross-browser.
* @param {String} str String to split.
* @param {RegExp|String} separator Regex or string to use for separating the string.
* @param {Number} [limit] Maximum number of items to include in the result array.
* @returns {Array} Array of substrings.
* @example
*
* // Basic use
* split('a b c d', ' ');
* // -> ['a', 'b', 'c', 'd']
*
* // With limit
* split('a b c d', ' ', 2);
* // -> ['a', 'b']
*
* // Backreferences in result array
* split('..word1 word2..', /([a-z]+)(\d+)/i);
* // -> ['..', 'word', '1', ' ', 'word', '2', '..']
*/
var split;
// Avoid running twice; that would break the `nativeSplit` reference
split = split || function (undef) {
var nativeSplit = String.prototype.split,
compliantExecNpcg = /()??/.exec("")[1] === undef, // NPCG: nonparticipating capturing group
self;
self = function (str, separator, limit) {
// If `separator` is not a regex, use `nativeSplit`
if (Object.prototype.toString.call(separator) !== "[object RegExp]") {
return nativeSplit.call(str, separator, limit);
}
var output = [],
flags = (separator.ignoreCase ? "i" : "") +
(separator.multiline ? "m" : "") +
(separator.extended ? "x" : "") + // Proposed for ES6
(separator.sticky ? "y" : ""), // Firefox 3+
lastLastIndex = 0,
// Make `global` and avoid `lastIndex` issues by working with a copy
separator = new RegExp(separator.source, flags + "g"),
separator2, match, lastIndex, lastLength;
str += ""; // Type-convert
if (!compliantExecNpcg) {
// Doesn't need flags gy, but they don't hurt
separator2 = new RegExp("^" + separator.source + "$(?!\s)", flags);
}
/* Values for `limit`, per the spec:
* If undefined: 4294967295 // Math.pow(2, 32) - 1
* If 0, Infinity, or NaN: 0
* If positive number: limit = Math.floor(limit); if (limit > 4294967295) limit -= 4294967296;
* If negative number: 4294967296 - Math.floor(Math.abs(limit))
* If other: Type-convert, then use the above rules
*/
limit = limit === undef ?
-1 >>> 0 : // Math.pow(2, 32) - 1
limit >>> 0; // ToUint32(limit)
while (match = separator.exec(str)) {
// `separator.lastIndex` is not reliable cross-browser
lastIndex = match.index + match[0].length;
if (lastIndex > lastLastIndex) {
output.push(str.slice(lastLastIndex, match.index));
// Fix browsers whose `exec` methods don't consistently return `undefined` for
// nonparticipating capturing groups
if (!compliantExecNpcg && match.length > 1) {
match[0].replace(separator2, function () {
for (var i = 1; i < arguments.length - 2; i++) {
if (arguments[i] === undef) {
match[i] = undef;
}
}
});
}
if (match.length > 1 && match.index < str.length) {
Array.prototype.push.apply(output, match.slice(1));
}
lastLength = match[0].length;
lastLastIndex = lastIndex;
if (output.length >= limit) {
break;
}
}
if (separator.lastIndex === match.index) {
separator.lastIndex++; // Avoid an infinite loop
}
}
if (lastLastIndex === str.length) {
if (lastLength || !separator.test("")) {
output.push("");
}
} else {
output.push(str.slice(lastLastIndex));
}
return output.length > limit ? output.slice(0, limit) : output;
};
// For convenience
String.prototype.split = function (separator, limit) {
return self(this, separator, limit);
};
return self;
}();
这是最佳解决方案：
function ieSplit(str, separator) {
var match = str.match(RegExp(separator, 'g'));
var notmatch = str.replace(new RegExp(separator, 'g'), '[|]').split('[|]');
var merge = [];
for(i in notmatch) {
merge.push(notmatch[i]);
if (match != null && match[i] != undefined) {
merge.push(match[i]);
}
}
return merge;
}