我有一个字符串:
var string = "aaaaaa<br />† bbbb<br />‡ cccc"
我想用分隔符<br />拆分这个字符串,后面跟着一个特殊字符。
要做到这一点,我使用这个:
string.split(/<br \/>&#?[a-zA-Z0-9]+;/g);
我得到了我需要的东西,只是我丢失了分隔符。 示例如下:http://jsfiddle.net/JwrZ6/1/
如何保留分隔符?
我有一个字符串:
var string = "aaaaaa<br />† bbbb<br />‡ cccc"
我想用分隔符<br />拆分这个字符串,后面跟着一个特殊字符。
要做到这一点,我使用这个:
string.split(/<br \/>&#?[a-zA-Z0-9]+;/g);
我得到了我需要的东西,只是我丢失了分隔符。 示例如下:http://jsfiddle.net/JwrZ6/1/
如何保留分隔符?
当前回答
我对jichi的回答做了修改,并把它放在一个支持多字母的函数中。
String.prototype.splitAndKeep = function(separator, method='seperate'){
var str = this;
if(method == 'seperate'){
str = str.split(new RegExp(`(${separator})`, 'g'));
}else if(method == 'infront'){
str = str.split(new RegExp(`(?=${separator})`, 'g'));
}else if(method == 'behind'){
str = str.split(new RegExp(`(.*?${separator})`, 'g'));
str = str.filter(function(el){return el !== "";});
}
return str;
};
jichi的答案第三种方法在这个函数中不起作用,所以我采用了第四种方法,并删除了空白区域以获得相同的结果。
编辑: 第二种方法,除了一个数组来拆分char1或char2
String.prototype.splitAndKeep = function(separator, method='seperate'){
var str = this;
function splitAndKeep(str, separator, method='seperate'){
if(method == 'seperate'){
str = str.split(new RegExp(`(${separator})`, 'g'));
}else if(method == 'infront'){
str = str.split(new RegExp(`(?=${separator})`, 'g'));
}else if(method == 'behind'){
str = str.split(new RegExp(`(.*?${separator})`, 'g'));
str = str.filter(function(el){return el !== "";});
}
return str;
}
if(Array.isArray(separator)){
var parts = splitAndKeep(str, separator[0], method);
for(var i = 1; i < separator.length; i++){
var partsTemp = parts;
parts = [];
for(var p = 0; p < partsTemp.length; p++){
parts = parts.concat(splitAndKeep(partsTemp[p], separator[i], method));
}
}
return parts;
}else{
return splitAndKeep(str, separator, method);
}
};
用法:
str = "first1-second2-third3-last";
str.splitAndKeep(["1", "2", "3"]) == ["first", "1", "-second", "2", "-third", "3", "-last"];
str.splitAndKeep("-") == ["first1", "-", "second2", "-", "third3", "-", "last"];
其他回答
我遇到了类似但略有不同的问题。无论如何,这里有三种不同场景的示例,用于说明在何处保存分隔符。
"1、2、3".split("、") == ["1", "2", "3"]
"1、2、3".split(/(、)/g) == ["1", "、", "2", "、", "3"]
"1、2、3".split(/(?=、)/g) == ["1", "、2", "、3"]
"1、2、3".split(/(?!、)/g) == ["1、", "2、", "3"]
"1、2、3".split(/(.*?、)/g) == ["", "1、", "", "2、", "3"]
警告:第四个只适用于拆分单个字符。ConnorsFan提供了一个替代方案:
// Split a path, but keep the slashes that follow directories
var str = 'Animation/rawr/javascript.js';
var tokens = str.match(/[^\/]+\/?|\//g);
如果你对拆分模式进行分组,它的匹配将被保留在输出中,这是通过设计的:
如果separator是带有捕获括号的正则表达式,则 每次分隔符匹配时,结果(包括任何未定义的 捕获括号的结果)拼接到输出中 数组中。 https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/split#description
除非您的搜索模式使用前瞻性或全局标志,否则您不需要这些标志。
const str = '如果一只土拨鼠会扔木头,它会扔多少木头?` Const result = str.split(/(\s+)/); console.log(结果); //我们可以验证结果 const isSame = result.join(") === str; console.log({isSame});
您可以使用多个组。你可以尽情发挥你的创造力,小组之外的内容将被删除:
const str = '如果一只土拨鼠会扔木头,它会扔多少木头?` Const result = str.split(/(\s+)(\w{1,2})\w+/); console.log(结果,result.join ("));
Most of the existing answers predate the introduction of lookbehind assertions in JavaScript in 2018. You didn't specify how you wanted the delimiters to be included in the result. One typical use case would be sentences delimited by punctuation ([.?!]), where one would want the delimiters to be included at the ends of the resulting strings. This corresponds to the fourth case in the accepted answer, but as noted there, that solution only works for single characters. Arbitrary strings with the delimiters appended at the end can be formed with a lookbehind assertion:
'It is. Is it? It is!'.split(/(?<=[.?!])/)
/* [ 'It is.', ' Is it?', ' It is!' ] */
扩展函数将字符串与子字符串或RegEx分开,分隔符根据第二个参数放在前面或后面。
String.prototype.splitKeep = function (splitter, ahead) {
var self = this;
var result = [];
if (splitter != '') {
var matches = [];
// Getting mached value and its index
var replaceName = splitter instanceof RegExp ? "replace" : "replaceAll";
var r = self[replaceName](splitter, function (m, i, e) {
matches.push({ value: m, index: i });
return getSubst(m);
});
// Finds split substrings
var lastIndex = 0;
for (var i = 0; i < matches.length; i++) {
var m = matches[i];
var nextIndex = ahead == true ? m.index : m.index + m.value.length;
if (nextIndex != lastIndex) {
var part = self.substring(lastIndex, nextIndex);
result.push(part);
lastIndex = nextIndex;
}
};
if (lastIndex < self.length) {
var part = self.substring(lastIndex, self.length);
result.push(part);
};
// Substitution of matched string
function getSubst(value) {
var substChar = value[0] == '0' ? '1' : '0';
var subst = '';
for (var i = 0; i < value.length; i++) {
subst += substChar;
}
return subst;
};
}
else {
result.add(self);
};
return result;
};
测试:
test('splitKeep', function () {
// String
deepEqual("1231451".splitKeep('1'), ["1", "231", "451"]);
deepEqual("123145".splitKeep('1', true), ["123", "145"]);
deepEqual("1231451".splitKeep('1', true), ["123", "145", "1"]);
deepEqual("hello man how are you!".splitKeep(' '), ["hello ", "man ", "how ", "are ", "you!"]);
deepEqual("hello man how are you!".splitKeep(' ', true), ["hello", " man", " how", " are", " you!"]);
// Regex
deepEqual("mhellommhellommmhello".splitKeep(/m+/g), ["m", "hellomm", "hellommm", "hello"]);
deepEqual("mhellommhellommmhello".splitKeep(/m+/g, true), ["mhello", "mmhello", "mmmhello"]);
});
如果将分隔符括在parantheses中,它将是返回数组的一部分。
string.split(/(<br \/>&#?[a-zA-Z0-9]+);/g);
// returns ["aaaaaa", "<br />†", "bbbb", "<br />‡", "cccc"]
根据你想保留的部分来改变你匹配的子组
string.split(/(<br \/>)&#?[a-zA-Z0-9]+;/g);
// returns ["aaaaaa", "<br />", "bbbb", "<br />", "cccc"]
您可以通过忽略字母的大小写来改进表达式 string.split (/ () & # ? [a-z0-9] +, / gi);
你可以这样匹配预定义的组:\d =[0-9]和\w = [a-zA-Z0-9_]。这意味着表达式可以是这样的。
string.split(/<br \/>(&#?[a-z\d]+;)/gi);
JavaScriptKit上有一个很好的正则表达式参考。