String的split源代码分析
public String[] split(String regex, int limit) {
/* fastpath if the regex is a
(1)one-char String and this character is not one of the
RegEx's meta characters ".$|()[{^?*+\\", or
(2)two-char String and the first char is the backslash and
the second is not the ascii digit or ascii letter.
*/
char ch = 0;
if (((regex.value.length == 1 &&//判断参数长度为1
".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||//判断参数不在特殊符号".$|()[{^?*+\\"中
(regex.length() == 2 && //或者参数长度为2
regex.charAt(0) == '\\' && //且第一位为转义符"\\"
(((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && //且第二位不是0-9之间 '0'转换为int为48 '9'转换为int为57 因为0-9是连着的,所以直接判断小于48,大于57
((ch-'a')|('z'-ch)) < 0 && // 且不在 a-z之间
((ch-'A')|('Z'-ch)) < 0)) && // 且不在A-Z之间
(ch < Character.MIN_HIGH_SURROGATE ||
ch > Character.MAX_LOW_SURROGATE)) //且分隔符不在特殊符号?中
{
int off = 0;//当前索引
int next = 0;//下一个分割符出现的索引
boolean limited = limit > 0;//只分割前limit份还是全部分割
ArrayList<String> list = new ArrayList<>(); //新建一个集合
while ((next = indexOf(ch, off)) != -1) { //获取下个分隔符的索引,如果有则循环
if (!limited || list.size() < limit - 1) {//判断是全部分割或当前分割次数小于总分割次数
list.add(substring(off, next));//分割当前索引到下一个分隔符的字符串添加到list
off = next + 1;//当前索引变为下一个分隔符索引+1
} else { // last one
//assert (list.size() == limit - 1);
list.add(substring(off, value.length));//分割当前索引到尾的字符串添加到list
off = value.length;//当前索引变为字符串长度
break;
}
}
// If no match was found, return this
if (off == 0)//如果找不到分隔符则返回只有本字符串的数组
return new String[]{this};
// Add remaining segment
if (!limited || list.size() < limit)//如果是全部分割(进入不到else),或者没有达到分割数(limit大于分隔符数量,进入不到else),则追加最后一项
list.add(substring(off, value.length));
// Construct result
int resultSize = list.size();
if (limit == 0) {//去除多余集合项
while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
resultSize--;
}
}
String[] result = new String[resultSize];//创建对应长度数组
return list.subList(0, resultSize).toArray(result);//集合转数组返回
}
return Pattern.compile(regex).split(this, limit);
}