所以,你有一个文本和一个正则表达式:
txt = "aabccde";
re = /(a).(b)(c.)d/;
第一步是获取与正则表达式匹配的所有子字符串的列表:
subs = re.exec(txt);
然后,您可以对每个子字符串的文本进行简单搜索。您必须将最后一个子字符串的位置保存在一个变量中。我已将这个变量命名为cursor
。
var cursor = subs.index;
for (var i = 1; i < subs.length; i++){
sub = subs[i];
index = txt.indexOf(sub, cursor);
cursor = index + sub.length;
console.log(sub + ' at index ' + index);
}
编辑:感谢@nhahtdh,我改进了机制并制作了完整的功能:
String.prototype.matchIndex = function(re){
var res = [];
var subs = this.match(re);
for (var cursor = subs.index, l = subs.length, i = 1; i < l; i++){
var index = cursor;
if (i+1 !== l && subs[i] !== subs[i+1]) {
nextIndex = this.indexOf(subs[i+1], cursor);
while (true) {
currentIndex = this.indexOf(subs[i], index);
if (currentIndex !== -1 && currentIndex <= nextIndex)
index = currentIndex + 1;
else
break;
}
index--;
} else {
index = this.indexOf(subs[i], cursor);
}
cursor = index + subs[i].length;
res.push([subs[i], index]);
}
return res;
}
console.log("aabccde".matchIndex(/(a).(b)(c.)d/));
// [ [ 'a', 1 ], [ 'b', 2 ], [ 'cc', 3 ] ]
console.log("aaa".matchIndex(/(a).(.)/));
// [ [ 'a', 0 ], [ 'a', 1 ] ] <-- problem here
console.log("bababaaaaa".matchIndex(/(ba)+.(a*)/));
// [ [ 'ba', 4 ], [ 'aaa', 6 ] ]