其实不用重复造轮子[StringUtils][002]，stringutils002
分享于 点击 2161 次 点评：145
其实不用重复造轮子[StringUtils][002]，stringutils002
一、Substring
1.包含空指针异常处理的subString，开始
public static String substring(String str, int start) {
if (str == null) {
return null;
}
// handle negatives, which means last n characters
if (start < 0) {
start = str.length() + start; // remember start is negative
}
if (start < 0) {
start = 0;
}
if (start > str.length()) {
return EMPTY;
}
return str.substring(start);
}
2.包含空指针异常处理的SubString，开始，结束
public static String substring(String str, int start, int end) {
if (str == null) {
return null;
}
// handle negatives
if (end < 0) {
end = str.length() + end; // remember end is negative
}
if (start < 0) {
start = str.length() + start; // remember start is negative
}
// check length next
if (end > str.length()) {
end = str.length();
}
// if start is greater than end, return ""
if (start > end) {
return EMPTY;
}
if (start < 0) {
start = 0;
}
if (end < 0) {
end = 0;
}
return str.substring(start, end);
}
二、字符截取（Left/Right/Mid）
1.截取左边len个字符
public static String left(String str, int len) {
if (str == null) {
return null;
}
if (len < 0) {
return EMPTY;
}
if (str.length() <= len) {
return str;
}
return str.substring(0, len);
}
2.截取右边len个字符
public static String right(String str, int len) {
if (str == null) {
return null;
}
if (len < 0) {
return EMPTY;
}
if (str.length() <= len) {
return str;
}
return str.substring(str.length() - len);
}
3.截取中间len个字符
public static String mid(String str, int pos, int len) {
if (str == null) {
return null;
}
if (len < 0 || pos > str.length()) {
return EMPTY;
}
if (pos < 0) {
pos = 0;
}
if (str.length() <= (pos + len)) {
return str.substring(pos);
}
return str.substring(pos, pos + len);
}
三、字符截取（SubStringAfter/SubStringBefore）
1.指定字符串之前的字符
public static String substringBefore(String str, String separator) {
if (isEmpty(str) || separator == null) {
return str;
}
if (separator.length() == 0) {
return EMPTY;
}
int pos = str.indexOf(separator);
if (pos == -1) {
return str;
}
return str.substring(0, pos);
}
2.指定字符串之后的字符
public static String substringAfter(String str, String separator) {
if (isEmpty(str)) {
return str;
}
if (separator == null) {
return EMPTY;
}
int pos = str.indexOf(separator);
if (pos == -1) {
return EMPTY;
}
return str.substring(pos + separator.length());
}
3.倒数。指定字符串之前的字符
public static String substringBeforeLast(String str, String separator) {
if (isEmpty(str) || isEmpty(separator)) {
return str;
}
int pos = str.lastIndexOf(separator);
if (pos == -1) {
return str;
}
return str.substring(0, pos);
}
4.倒数。指定在字符串之后的字符
public static String substringAfterLast(String str, String separator) {
if (isEmpty(str)) {
return str;
}
if (isEmpty(separator)) {
return EMPTY;
}
int pos = str.lastIndexOf(separator);
if (pos == -1 || pos == (str.length() - separator.length())) {
return EMPTY;
}
return str.substring(pos + separator.length());
}
四、子字符串（Substring between）
1. 在某指定字符串中的子字符串
public static String substringBetween(String str, String tag) {
return substringBetween(str, tag, tag);
}
2.在某两个指定字符串中间的子字符串，只返回第一个有效值
public static String substringBetween(String str, String open, String close) {
if (str == null || open == null || close == null) {
return null;
}
int start = str.indexOf(open);
if (start != -1) {
int end = str.indexOf(close, start + open.length());
if (end != -1) {
return str.substring(start + open.length(), end);
}
}
return null;
}
3. 在某两个指定字符串之间的子字符串，以数组形式返回所有有效值
public static String[] substringsBetween(String str, String open, String close) {
if (str == null || isEmpty(open) || isEmpty(close)) {
return null;
}
int strLen = str.length();
if (strLen == 0) {
return ArrayUtils.EMPTY_STRING_ARRAY;
}
int closeLen = close.length();
int openLen = open.length();
List list = new ArrayList();
int pos = 0;
while (pos < (strLen - closeLen)) {
int start = str.indexOf(open, pos);
if (start < 0) {
break;
}
start += openLen;
int end = str.indexOf(close, start);
if (end < 0) {
break;
}
list.add(str.substring(start, end));
pos = end + closeLen;
}
if (list.isEmpty()) {
return null;
}
return (String[]) list.toArray(new String [list.size()]);
}
五、拆分（Splitting）
1.将包含空白字符的字符串拆分成一个数组，以空白字符作为分隔符条件
public static String[] split(String str) {
return split(str, null, -1);
}
2.将字符串中按照指定字符作为分隔符，拆分成一个数组
public static String[] split(String str, char separatorChar) {
return splitWorker(str, separatorChar, false);
}
public static String[] split(String str, String separatorChars) {
return splitWorker(str, separatorChars, -1, false);
}
3.将字符串拆分成指定max大小的数组
public static String[] split(String str, String separatorChars, int max) {
return splitWorker(str, separatorChars, max, false);
}
4.将字符串按照指定字符串拆分成数据
public static String[] splitByWholeSeparator(String str, String separator) {
return splitByWholeSeparatorWorker( str, separator, -1, false ) ;
}
public static String[] splitByWholeSeparator( String str, String separator, int max ) {
return splitByWholeSeparatorWorker(str, separator, max, false);
}
5.将字符串按照指定字符串拆分成数组，如果含有多个separator，则separtor也会作为数组值返回
public static String[] splitByWholeSeparatorPreserveAllTokens(String str, String separator) {
return splitByWholeSeparatorWorker(str, separator, -1, true);
}
public static String[] splitByWholeSeparatorPreserveAllTokens(String str, String separator, int max) {
return splitByWholeSeparatorWorker(str, separator, max, true);
}
拆分
private static String[] splitByWholeSeparatorWorker(String str, String separator, int max,
boolean preserveAllTokens)
{
if (str == null) {
return null;
}
int len = str.length();
if (len == 0) {
return ArrayUtils.EMPTY_STRING_ARRAY;
}
if ((separator == null) || (EMPTY.equals(separator))) {
// Split on whitespace.
return splitWorker(str, null, max, preserveAllTokens);
}
int separatorLength = separator.length();
ArrayList substrings = new ArrayList();
int numberOfSubstrings = 0;
int beg = 0;
int end = 0;
while (end < len) {
end = str.indexOf(separator, beg);
if (end > -1) {
if (end > beg) {
numberOfSubstrings += 1;
if (numberOfSubstrings == max) {
end = len;
substrings.add(str.substring(beg));
} else {
// The following is OK, because String.substring( beg, end ) excludes
// the character at the position 'end'.
substrings.add(str.substring(beg, end));
// Set the starting point for the next search.
// The following is equivalent to beg = end + (separatorLength - 1) + 1,
// which is the right calculation:
beg = end + separatorLength;
}
} else {
// We found a consecutive occurrence of the separator, so skip it.
if (preserveAllTokens) {
numberOfSubstrings += 1;
if (numberOfSubstrings == max) {
end = len;
substrings.add(str.substring(beg));
} else {
substrings.add(EMPTY);
}
}
beg = end + separatorLength;
}
} else {
// String.substring( beg ) goes from 'beg' to the end of the String.
substrings.add(str.substring(beg));
end = len;
}
}
return (String[]) substrings.toArray(new String[substrings.size()]);
}
6.返回包含separator的数组
public static String[] splitPreserveAllTokens(String str) {
return splitWorker(str, null, -1, true);
}
public static String[] splitPreserveAllTokens(String str, char separatorChar) {
return splitWorker(str, separatorChar, true);
}
拆分
private static String[] splitWorker(String str, char separatorChar, boolean preserveAllTokens) {
// Performance tuned for 2.0 (JDK1.4)
if (str == null) {
return null;
}
int len = str.length();
if (len == 0) {
return ArrayUtils.EMPTY_STRING_ARRAY;
}
List list = new ArrayList();
int i = 0, start = 0;
boolean match = false;
boolean lastMatch = false;
while (i < len) {
if (str.charAt(i) == separatorChar) {
if (match || preserveAllTokens) {
list.add(str.substring(start, i));
match = false;
lastMatch = true;
}
start = ++i;
continue;
}
lastMatch = false;
match = true;
i++;
}
if (match || (preserveAllTokens && lastMatch)) {
list.add(str.substring(start, i));
}
return (String[]) list.toArray(new String[list.size()]);
}
7.拆分为数组（StringUtils.splitPreserveAllTokens("ab::cd:ef", ":") = ["ab", "", cd", "ef"]）
public static String[] splitPreserveAllTokens(String str, String separatorChars) {
return splitWorker(str, separatorChars, -1, true);
}
public static String[] splitPreserveAllTokens(String str, String separatorChars, int max) {
return splitWorker(str, separatorChars, max, true);
}
private static String[] splitWorker(String str, String separatorChars, int max, boolean preserveAllTokens) {
// Performance tuned for 2.0 (JDK1.4)
// Direct code is quicker than StringTokenizer.
// Also, StringTokenizer uses isSpace() not isWhitespace()
if (str == null) {
return null;
}
int len = str.length();
if (len == 0) {
return ArrayUtils.EMPTY_STRING_ARRAY;
}
List list = new ArrayList();
int sizePlus1 = 1;
int i = 0, start = 0;
boolean match = false;
boolean lastMatch = false;
if (separatorChars == null) {
// Null separator means use whitespace
while (i < len) {
if (Character.isWhitespace(str.charAt(i))) {
if (match || preserveAllTokens) {
lastMatch = true;
if (sizePlus1++ == max) {
i = len;
lastMatch = false;
}
list.add(str.substring(start, i));
match = false;
}
start = ++i;
continue;
}
lastMatch = false;
match = true;
i++;
}
} else if (separatorChars.length() == 1) {
// Optimise 1 character case
char sep = separatorChars.charAt(0);
while (i < len) {
if (str.charAt(i) == sep) {
if (match || preserveAllTokens) {
lastMatch = true;
if (sizePlus1++ == max) {
i = len;
lastMatch = false;
}
list.add(str.substring(start, i));
match = false;
}
start = ++i;
continue;
}
lastMatch = false;
match = true;
i++;
}
} else {
// standard case
while (i < len) {
if (separatorChars.indexOf(str.charAt(i)) >= 0) {
if (match || preserveAllTokens) {
lastMatch = true;
if (sizePlus1++ == max) {
i = len;
lastMatch = false;
}
list.add(str.substring(start, i));
match = false;
}
start = ++i;
continue;
}
lastMatch = false;
match = true;
i++;
}
}
if (match || (preserveAllTokens && lastMatch)) {
list.add(str.substring(start, i));
}
return (String[]) list.toArray(new String[list.size()]);
}
7.根据字符类型进行拆分（StringUtils.splitByCharacterType("foo200Bar") = ["foo", "200", "B", "ar"]）
public static String[] splitByCharacterType(String str) {
return splitByCharacterType(str, false);
}
8.根据字符类型进行拆分，不区分大小写（StringUtils.splitByCharacterTypeCamelCase("foo200Bar") = ["foo", "200", "Bar"]；StringUtils.splitByCharacterTypeCamelCase("ASFRules") = ["ASF", "Rules"]）
public static String[] splitByCharacterTypeCamelCase(String str) {
return splitByCharacterType(str, true);
}
private static String[] splitByCharacterType(String str, boolean camelCase) {
if (str == null) {
return null;
}
if (str.length() == 0) {
return ArrayUtils.EMPTY_STRING_ARRAY;
}
char[] c = str.toCharArray();
List list = new ArrayList();
int tokenStart = 0;
int currentType = Character.getType(c[tokenStart]);
for (int pos = tokenStart + 1; pos < c.length; pos++) {
int type = Character.getType(c[pos]);
if (type == currentType) {
continue;
}
if (camelCase && type == Character.LOWERCASE_LETTER && currentType == Character.UPPERCASE_LETTER) {
int newTokenStart = pos - 1;
if (newTokenStart != tokenStart) {
list.add(new String(c, tokenStart, newTokenStart - tokenStart));
tokenStart = newTokenStart;
}
} else {
list.add(new String(c, tokenStart, pos - tokenStart));
tokenStart = pos;
}
currentType = type;
}
list.add(new String(c, tokenStart, c.length - tokenStart));
return (String[]) list.toArray(new String[list.size()]);
}
相关文章
- 暂无相关文章
用户点评