如何计算特定字符串在另一个字符串中出现的次数。例如,这就是我试图在Javascript中做的事情:
var temp = "This is a string.";
alert(temp.count("is")); //should output '2'
如何计算特定字符串在另一个字符串中出现的次数。例如,这就是我试图在Javascript中做的事情:
var temp = "This is a string.";
alert(temp.count("is")); //should output '2'
当前回答
/** Function that count occurrences of a substring in a string;
* @param {String} string The string
* @param {String} subString The sub string to search for
* @param {Boolean} [allowOverlapping] Optional. (Default:false)
*
* @author Vitim.us https://gist.github.com/victornpb/7736865
* @see Unit Test https://jsfiddle.net/Victornpb/5axuh96u/
* @see https://stackoverflow.com/a/7924240/938822
*/
function occurrences(string, subString, allowOverlapping) {
string += "";
subString += "";
if (subString.length <= 0) return (string.length + 1);
var n = 0,
pos = 0,
step = allowOverlapping ? 1 : subString.length;
while (true) {
pos = string.indexOf(subString, pos);
if (pos >= 0) {
++n;
pos += step;
} else break;
}
return n;
}
用法
occurrences("foofoofoo", "bar"); //0
occurrences("foofoofoo", "foo"); //3
occurrences("foofoofoo", "foofoo"); //1
允许重叠
occurrences("foofoofoo", "foofoo", true); //2
比赛:
foofoofoo
1 `----´
2 `----´
单元测试
https://jsfiddle.net/Victornpb/5axuh96u/
基准
我做了一个基准测试,我的功能超过了10倍比gumbo发布的regexp匹配函数更快。在我的测试中字符串长度为25个字符。字符“o”出现2次。我在Safari中执行了1000 000次。Safari 5.1基准>执行总时间:5617ms(正则表达式)基准测试>执行总时间:881毫秒(我的功能快6.4倍)Firefox 4基准>执行总时间:8547毫秒(Rexep)基准测试>总执行时间:634毫秒(我的功能更快13.5倍)编辑:我所做的更改缓存的子字符串长度为字符串添加了类型转换。添加了可选的“allowOverlapping”参数修复了“”空子字符串大小写的正确输出。
Gist
https://gist.github.com/victornpb/7736865
其他回答
var temp=“这是一个字符串。”;console.log((temp.match(新RegExp(“is”,“g”))||[]).length);
第二次迭代次数较少(仅当子字符串的第一个字母匹配时),但循环仍使用2:
function findSubstringOccurrences(str, word) {
let occurrences = 0;
for(let i=0; i<str.length; i++){
if(word[0] === str[i]){ // to make it faster and iterate less
for(let j=0; j<word.length; j++){
if(str[i+j] !== word[j]) break;
if(j === word.length - 1) occurrences++;
}
}
}
return occurrences;
}
console.log(findSubstringOccurrences("jdlfkfomgkdjfomglo", "omg"));
正则表达式(global的缩写)中的g表示搜索整个字符串,而不仅仅是查找第一个出现的字符串。此匹配是两次:
var temp=“这是一个字符串。”;var count=(temp.match(/is/g)| |[]).length;console.log(计数);
如果没有匹配项,则返回0:
var temp=“Hello World!”;var count=(temp.match(/is/g)| |[]).length;console.log(计数);
基于@Vittim.us的上述回答。我喜欢他的方法给我的控制,使其易于扩展,但我需要添加不区分大小写的功能,并将匹配限制在支持标点符号的整个单词中。(例如,“洗澡”是指“洗澡”,而不是“洗澡”)
标点正则表达式来自:https://stackoverflow.com/a/25575009/497745(如何使用正则表达式从JavaScript字符串中删除所有标点符号?)
function keywordOccurrences(string, subString, allowOverlapping, caseInsensitive, wholeWord)
{
string += "";
subString += "";
if (subString.length <= 0) return (string.length + 1); //deal with empty strings
if(caseInsensitive)
{
string = string.toLowerCase();
subString = subString.toLowerCase();
}
var n = 0,
pos = 0,
step = allowOverlapping ? 1 : subString.length,
stringLength = string.length,
subStringLength = subString.length;
while (true)
{
pos = string.indexOf(subString, pos);
if (pos >= 0)
{
var matchPos = pos;
pos += step; //slide forward the position pointer no matter what
if(wholeWord) //only whole word matches are desired
{
if(matchPos > 0) //if the string is not at the very beginning we need to check if the previous character is whitespace
{
if(!/[\s\u2000-\u206F\u2E00-\u2E7F\\'!"#$%&\(\)*+,\-.\/:;<=>?@\[\]^_`{|}~]/.test(string[matchPos - 1])) //ignore punctuation
{
continue; //then this is not a match
}
}
var matchEnd = matchPos + subStringLength;
if(matchEnd < stringLength - 1)
{
if (!/[\s\u2000-\u206F\u2E00-\u2E7F\\'!"#$%&\(\)*+,\-.\/:;<=>?@\[\]^_`{|}~]/.test(string[matchEnd])) //ignore punctuation
{
continue; //then this is not a match
}
}
}
++n;
} else break;
}
return n;
}
如果发现错误或改进,请随时修改和重构此答案。
我们可以使用jssplit函数,它的长度减1就是出现的次数。
var temp = "This is a string.";
alert(temp.split('is').length-1);