String的底层是char类型的数组,所以先需要看一下char类型。
1、char类型
Java中char类型采用16位的Unicode编码,后来由于字符集太多,超过了65536个,所以16位的Unicode已经不能满足需要了。于是自JDK5.0开始,采用代码点表示某个字符对应的代码值,代码点规定十六进制书写,并加上前缀U+,例如U+0041表示A的代码点。Unicode的代码点分为17个代码级别。第一个代码级别是基本的多语言级别(bmp),代码点从U+0000到U+FFFF,其中包括经典的Unicode代码;其余的16个附加级别,代码点从U+10000到U+10FFFF,其中包括了一些辅助字符。
在基本的多语言级别中,每个字符采用16位表示,通常称为代码单元。如下图所示:此时一个代码点只需要一个代码单元(两个字节)即可表示,即一个char字符。而辅助字符则采用一对连续的代码单元表示进行编码(即两个代码单元(四个字节,两个char字符)表示一个代码点)。
2、Sring类型
String底层是由char数组组成,length方法将返回一个UTF-16编码表示的给定字符串所需要的代码单元数量。例如:
String greeting = "Hello";
int n = greeting.length();//5
要想得到实际的长度,即代码点的数量,可以调用:
int cpCount = greeting.length(0,greeting.length());
调用s.charAt(n)将返回位置n的代码单元,n介于0 - s.length()-1之间。例如:
char first = greeting.charAt(0);//H
char last = greeting.charAt(4);//o
要想得到第i个代码点,应该使用下列语句:
int index = greeting.offsetByCodePoint(0,i);
int cp = greeting.codePointAt(index);
3、String源码
JDK:1.7;package:java.lang。省去部分重载方法。
public final class String //final,不能给被继承。
implements java.io.Serializable, Comparable<String>, CharSequence {//可序列化,可排序
//String底层是char数组,被final修饰:value保存的数组引用不能改变,又没有get/set方法能访问到这个引用,
//就更不可能去修改这个引用所指向的数组里的值(实际反射可以做到,但是不推荐),所以一般认为String不可变。
private final char value[];
private int hash; // Default to 0
public String() {
this.value = new char[0]; //初始化为空字符串"",因为String是不可变的,所以基本不用
}
public String(String original) {
this.value = original.value; //初始化Sring,新字符串是该字符串的副本,基本不用
this.hash = original.hash;
}
public String(char value[]) { //根据char数组构建String
this.value = Arrays.copyOf(value, value.length);
}
public String(char value[], int offset, int count) { //截取一部分创建一个字符串
if (offset < 0) { //参数有效性检查
throw new StringIndexOutOfBoundsException(offset);
}
if (count < 0) {
throw new StringIndexOutOfBoundsException(count);
}
// Note: offset or count might be near -1>>>1.
if (offset > value.length - count) {
throw new StringIndexOutOfBoundsException(offset + count);
}
this.value = Arrays.copyOfRange(value, offset, offset+count);
}
//分配一个新的 String,它包含代码点数组参数一个子数组的字符。offset 参数是该子数组第一个代码点的索引,count 参数指定子数组的长度。
public String(int[] codePoints, int offset, int count) {
if (offset < 0) {
throw new StringIndexOutOfBoundsException(offset);
}
if (count < 0) {
throw new StringIndexOutOfBoundsException(count);
}
if (offset > codePoints.length - count) {
throw new StringIndexOutOfBoundsException(offset + count);
}
final int end = offset + count;
int n = count;
for (int i = offset; i < end; i++) {
int c = codePoints[i];
if (Character.isBmpCodePoint(c)) //判断是否属于基本多语言级别,是则true,不会溢出直接下次循环,否则false
continue;
else if (Character.isValidCodePoint(c)) //判断codePoint是不是一个有效的Unicode码值,即是否在0000-10FFFF之间
n++; //n初始值为count,在count基础上增加
else throw new IllegalArgumentException(Integer.toString(c));
}
final char[] v = new char[n];
for (int i = offset, j = 0; i < end; i++, j++) {
int c = codePoints[i];
if (Character.isBmpCodePoint(c)) //同上进行判断是否基本多语言级别
v[j] = (char)c; //若是直接转换类型即可,不会溢出
else
Character.toSurrogates(c, v, j++); //否则就存储两个代码单元表示一个代码点
}
this.value = v;
}
private static void checkBounds(byte[] bytes, int offset, int length) { //参数有效性检查
if (length < 0)
throw new StringIndexOutOfBoundsException(length);
if (offset < 0)
throw new StringIndexOutOfBoundsException(offset);
if (offset > bytes.length - length)
throw new StringIndexOutOfBoundsException(offset + length);
}
public String(byte bytes[], int offset, int length, String charsetName)//使用charsetName编码方式进行解码,构造String
throws UnsupportedEncodingException {
if (charsetName == null)
throw new NullPointerException("charsetName");
checkBounds(bytes, offset, length); //参数有效性检查
this.value = StringCoding.decode(charsetName, bytes, offset, length);
}
public String(byte bytes[], int offset, int length, Charset charset) {
if (charset == null)
throw new NullPointerException("charset");
checkBounds(bytes, offset, length);
this.value = StringCoding.decode(charset, bytes, offset, length);
}
public String(byte bytes[], String charsetName)
throws UnsupportedEncodingException {
this(bytes, 0, bytes.length, charsetName);
}
public String(byte bytes[], Charset charset) {//通过使用指定的 charset 解码指定的 byte 数组,构造一个新的 String
this(bytes, 0, bytes.length, charset);
}
public String(byte bytes[], int offset, int length) {
checkBounds(bytes, offset, length);
this.value = StringCoding.decode(bytes, offset, length);
}
public int length() { //字符串长度,代码单元
return value.length;
}
public boolean isEmpty() {
return value.length == 0; //空串
}
public char charAt(int index) {
if ((index < 0) || (index >= value.length)) {
throw new StringIndexOutOfBoundsException(index);
}
return value[index]; //返回指定位置代码单元的值
}
public int codePointAt(int index) {
if ((index < 0) || (index >= value.length)) {
throw new StringIndexOutOfBoundsException(index);
}
return Character.codePointAtImpl(value, index, value.length); //返回指定位置的代码点
}
public int codePointBefore(int index) { //index的前一个代码点的值
int i = index - 1;
if ((i < 0) || (i >= value.length)) {
throw new StringIndexOutOfBoundsException(index);
}
return Character.codePointBeforeImpl(value, index, 0);
}
public int codePointCount(int beginIndex, int endIndex) { //指定范围的代码点数量
if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) {
throw new IndexOutOfBoundsException();
}
return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex);
}
public int offsetByCodePoints(int index, int codePointOffset) {//偏移指定位置的代码点索引
if (index < 0 || index > value.length) {
throw new IndexOutOfBoundsException();
}
return Character.offsetByCodePointsImpl(value, 0, value.length,
index, codePointOffset);
}
public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {//字符串复制到数组中
if (srcBegin < 0) {
throw new StringIndexOutOfBoundsException(srcBegin);
}
if (srcEnd > value.length) {
throw new StringIndexOutOfBoundsException(srcEnd);
}
if (srcBegin > srcEnd) {
throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
}
System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin);
}
public byte[] getBytes(String charsetName)
throws UnsupportedEncodingException { //字符串转换成给定字符集的字节数组
if (charsetName == null) throw new NullPointerException();
return StringCoding.encode(charsetName, value, 0, value.length);
}
public byte[] getBytes(Charset charset) { //字符串转换成给定charset转换成字节数组
if (charset == null) throw new NullPointerException();
return StringCoding.encode(charset, value, 0, value.length);
}
public byte[] getBytes() { //用系统默认的编码方式进行转换
return StringCoding.encode(value, 0, value.length);
}
public boolean equals(Object anObject) {
if (this == anObject) { //引用相等,则必然相等
return true;
}
if (anObject instanceof String) { //必须是String的实例
String anotherString = (String) anObject;
int n = value.length;
if (n == anotherString.value.length) { //比较长度
char v1[] = value;
char v2[] = anotherString.value;
int i = 0;
while (n-- != 0) {
if (v1[i] != v2[i]) //每一位相等
return false;
i++;
}
return true;
}
}
return false;
}
public boolean contentEquals(StringBuffer sb) { //与StringBuffer的内容比较
synchronized (sb) {
return contentEquals((CharSequence) sb);
}
}
public boolean contentEquals(CharSequence cs) {//与CharSequence的内容比较
if (value.length != cs.length())
return false;
// Argument is a StringBuffer, StringBuilder
if (cs instanceof AbstractStringBuilder) {
char v1[] = value;
char v2[] = ((AbstractStringBuilder) cs).getValue();
int i = 0;
int n = value.length;
while (n-- != 0) {
if (v1[i] != v2[i])
return false;
i++;
}
return true;
}
// Argument is a String
if (cs.equals(this))
return true;
// Argument is a generic CharSequence
char v1[] = value;
int i = 0;
int n = value.length;
while (n-- != 0) {
if (v1[i] != cs.charAt(i))
return false;
i++;
}
return true;
}
public boolean equalsIgnoreCase(String anotherString) { //忽略大小写
return (this == anotherString) ? true //是否同一个引用
: (anotherString != null)
&& (anotherString.value.length == value.length) //长度相等
&& regionMatches(true, 0, anotherString, 0, value.length);//正则表达式匹配
}
public int compareTo(String anotherString) {
int len1 = value.length;
int len2 = anotherString.value.length;
int lim = Math.min(len1, len2);
char v1[] = value;
char v2[] = anotherString.value;
int k = 0;
while (k < lim) {
char c1 = v1[k];//进行比较
char c2 = v2[k];
if (c1 != c2) {
return c1 - c2; //考虑大小写,直接相减
}
k++;
}
return len1 - len2;
}
public static final Comparator<String> CASE_INSENSITIVE_ORDER
= new CaseInsensitiveComparator();
private static class CaseInsensitiveComparator
implements Comparator<String>, java.io.Serializable {
// use serialVersionUID from JDK 1.2.2 for interoperability
private static final long serialVersionUID = 8575799808933029326L;
public int compare(String s1, String s2) {
int n1 = s1.length();
int n2 = s2.length();
int min = Math.min(n1, n2);
for (int i = 0; i < min; i++) {
char c1 = s1.charAt(i);
char c2 = s2.charAt(i);
if (c1 != c2) {
c1 = Character.toUpperCase(c1); //大写比较
c2 = Character.toUpperCase(c2);
if (c1 != c2) {
c1 = Character.toLowerCase(c1); //小写比较
c2 = Character.toLowerCase(c2);
if (c1 != c2) {
return c1 - c2;
}
}
}
}
return n1 - n2;
}
}
public int compareToIgnoreCase(String str) { //忽略大小写
return CASE_INSENSITIVE_ORDER.compare(this, str);
}
public boolean regionMatches(int toffset, String other, int ooffset,
int len) { //字符串从toffset开始,与other从ooffset开始,长度均为len,进行比较
char ta[] = value;
int to = toffset; //字符串的起始位置
char pa[] = other.value;
int po = ooffset; //other字符串的起始位置
// Note: toffset, ooffset, or len might be near -1>>>1.
if ((ooffset < 0) || (toffset < 0) //小于0则false
|| (toffset > (long)value.length - len) //长度超过范围则false
|| (ooffset > (long)other.value.length - len)) {
return false;
}
while (len-- > 0) {
if (ta[to++] != pa[po++]) {
return false;
}
}
return true;
}
public boolean regionMatches(boolean ignoreCase, int toffset,
String other, int ooffset, int len) { //重载方法,是否忽略大小写进行比较
char ta[] = value;
int to = toffset;
char pa[] = other.value;
int po = ooffset;
// Note: toffset, ooffset, or len might be near -1>>>1.
if ((ooffset < 0) || (toffset < 0)
|| (toffset > (long)value.length - len)
|| (ooffset > (long)other.value.length - len)) {
return false;
}
while (len-- > 0) {
char c1 = ta[to++];
char c2 = pa[po++];
if (c1 == c2) {
continue;
}
if (ignoreCase) {
// If characters don't match but case may be ignored,
// try converting both characters to uppercase.
// If the results match, then the comparison scan should
// continue.
char u1 = Character.toUpperCase(c1);
char u2 = Character.toUpperCase(c2);
if (u1 == u2) {
continue;
}
// Unfortunately, conversion to uppercase does not work properly
// for the Georgian alphabet, which has strange rules about case
// conversion. So we need to make one last check before
// exiting.
if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
continue;
}
}
return false;
}
return true;
}
public boolean startsWith(String prefix, int toffset) { //指定位置是否以某个前缀开始
char ta[] = value;
int to = toffset;
char pa[] = prefix.value;
int po = 0;
int pc = prefix.value.length;
// Note: toffset might be near -1>>>1.
if ((toffset < 0) || (toffset > value.length - pc)) {
return false;
}
while (--pc >= 0) {
if (ta[to++] != pa[po++]) { //与前缀的每一位进行比较
return false;
}
}
return true;
}
public boolean startsWith(String prefix) { //同上,重载方法
return startsWith(prefix, 0);
}
public boolean endsWith(String suffix) {//结束
return startsWith(suffix, value.length - suffix.value.length);
}
public int hashCode() { //hash值
int h = hash;
if (h == 0 && value.length > 0) {
char val[] = value;
for (int i = 0; i < value.length; i++) {
h = 31 * h + val[i];
}
hash = h;
}
return h;
}
public int indexOf(int ch) { //第一次出现的索引,ch为代码点
return indexOf(ch, 0);
}
public int indexOf(int ch, int fromIndex) { //第一次出现的索引,从指定位置开始算,ch为代码点
final int max = value.length;
if (fromIndex < 0) {
fromIndex = 0;
} else if (fromIndex >= max) {
return -1; //越界了返回-1
}
if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { //MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
final char[] value = this.value; //此时直接比较值即可
for (int i = fromIndex; i < max; i++) {
if (value[i] == ch) {
return i;
}
}
return -1;
} else {
return indexOfSupplementary(ch, fromIndex); //如果为辅助字符,则要比较两个代码单元
}
}
/**
* Handles (rare) calls of indexOf with a supplementary character.
*/
private int indexOfSupplementary(int ch, int fromIndex) {
if (Character.isValidCodePoint(ch)) { //是否在0x010000到0x10FFFF之间
final char[] value = this.value;
final char hi = Character.highSurrogate(ch); //高位
final char lo = Character.lowSurrogate(ch); //低位
final int max = value.length - 1;
for (int i = fromIndex; i < max; i++) {
if (value[i] == hi && value[i + 1] == lo) { //同时比较两个
return i;
}
}
}
return -1;
}
public int lastIndexOf(int ch) { //最后一次出现的索引
return lastIndexOf(ch, value.length - 1);
}
public int lastIndexOf(int ch, int fromIndex) {//最后一次出现的索引,与第一次出现的类似
if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
// handle most cases here (ch is a BMP code point or a
// negative value (invalid code point))
final char[] value = this.value;
int i = Math.min(fromIndex, value.length - 1);
for (; i >= 0; i--) {
if (value[i] == ch) {
return i;
}
}
return -1;
} else {
return lastIndexOfSupplementary(ch, fromIndex);
}
}
private int lastIndexOfSupplementary(int ch, int fromIndex) {
if (Character.isValidCodePoint(ch)) {
final char[] value = this.value;
char hi = Character.highSurrogate(ch);
char lo = Character.lowSurrogate(ch);
int i = Math.min(fromIndex, value.length - 2);
for (; i >= 0; i--) {
if (value[i] == hi && value[i + 1] == lo) {
return i;
}
}
}
return -1;
}
public int indexOf(String str) { //str第一次出现的索引
return indexOf(str, 0);
}
public int indexOf(String str, int fromIndex) { //同前
return indexOf(value, 0, value.length,
str.value, 0, str.value.length, fromIndex);
}
static int indexOf(char[] source, int sourceOffset, int sourceCount,
char[] target, int targetOffset, int targetCount,
int fromIndex) {
if (fromIndex >= sourceCount) { //指定位置大于等于数组长度
return (targetCount == 0 ? sourceCount : -1);
}
if (fromIndex < 0) {
fromIndex = 0;
}
if (targetCount == 0) {
return fromIndex;
}
char first = target[targetOffset];
int max = sourceOffset + (sourceCount - targetCount);
for (int i = sourceOffset + fromIndex; i <= max; i++) {
/* Look for first character. */
if (source[i] != first) {
while (++i <= max && source[i] != first);
}
/* Found first character, now look at the rest of v2 */
if (i <= max) {
int j = i + 1;
int end = j + targetCount - 1;
for (int k = targetOffset + 1; j < end && source[j]
== target[k]; j++, k++);
if (j == end) {
/* Found whole string. */
return i - sourceOffset;
}
}
}
return -1;
}
public int lastIndexOf(String str) {
return lastIndexOf(str, value.length);
}
public int lastIndexOf(String str, int fromIndex) {
return lastIndexOf(value, 0, value.length,
str.value, 0, str.value.length, fromIndex);
}
static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
char[] target, int targetOffset, int targetCount,
int fromIndex) {
/*
* Check arguments; return immediately where possible. For
* consistency, don't check for null str.
*/
int rightIndex = sourceCount - targetCount;
if (fromIndex < 0) {
return -1;
}
if (fromIndex > rightIndex) {
fromIndex = rightIndex;
}
/* Empty string always matches. */
if (targetCount == 0) {
return fromIndex;
}
int strLastIndex = targetOffset + targetCount - 1;
char strLastChar = target[strLastIndex];
int min = sourceOffset + targetCount - 1;
int i = min + fromIndex;
startSearchForLastChar:
while (true) {
while (i >= min && source[i] != strLastChar) {
i--;
}
if (i < min) {
return -1;
}
int j = i - 1;
int start = j - (targetCount - 1);
int k = strLastIndex - 1;
while (j > start) {
if (source[j--] != target[k--]) {
i--;
continue startSearchForLastChar;
}
}
return start - sourceOffset + 1;
}
}
public String substring(int beginIndex) {//截取该字符串获得子串
if (beginIndex < 0) {
throw new StringIndexOutOfBoundsException(beginIndex);
}
int subLen = value.length - beginIndex;
if (subLen < 0) {
throw new StringIndexOutOfBoundsException(subLen);
}
return (beginIndex == 0) ? this : new String(value, beginIndex, subLen);//相同则返回自身,不同则new一个
}
public String substring(int beginIndex, int endIndex) { //重载方法,同上
if (beginIndex < 0) {
throw new StringIndexOutOfBoundsException(beginIndex);
}
if (endIndex > value.length) {
throw new StringIndexOutOfBoundsException(endIndex);
}
int subLen = endIndex - beginIndex;
if (subLen < 0) {
throw new StringIndexOutOfBoundsException(subLen);
}
return ((beginIndex == 0) && (endIndex == value.length)) ? this
: new String(value, beginIndex, subLen);
}
public CharSequence subSequence(int beginIndex, int endIndex) {
return this.substring(beginIndex, endIndex); //继承CharSequence接口实现其中的方法
}
public String concat(String str) { //将指定字符串连接到此字符串的结尾
int otherLen = str.length();
if (otherLen == 0) {
return this; //str为空串则返回自身
}
int len = value.length;
char buf[] = Arrays.copyOf(value, len + otherLen);//扩充数组长度
str.getChars(buf, len);
return new String(buf, true); //创建一个新串
}
public String replace(char oldChar, char newChar) {//用newChar替代oldChar返回新串
if (oldChar != newChar) {
int len = value.length;
int i = -1;
char[] val = value; /* avoid getfield opcode */
while (++i < len) {
if (val[i] == oldChar) {//找到字符串中第一次出现oldChar的位置i
break;
}
}
if (i < len) {
char buf[] = new char[len];
for (int j = 0; j < i; j++) {
buf[j] = val[j]; //保存第一次出现oldChar字符串之前的字符串
}
while (i < len) {
char c = val[i];
buf[i] = (c == oldChar) ? newChar : c; //替换之后的oldChar并存储
i++;
}
return new String(buf, true);
}
}
return this; //相等则返回自身
}
public boolean matches(String regex) {//正则表达式匹配
return Pattern.matches(regex, this);
}
public boolean contains(CharSequence s) { //包含s则true
return indexOf(s.toString()) > -1;
}
public String replaceFirst(String regex, String replacement) {//替换正则表达式匹配到的第一个字符串
return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
}
public String replaceAll(String regex, String replacement) {//替换全部
return Pattern.compile(regex).matcher(this).replaceAll(replacement);
}
public String replace(CharSequence target, CharSequence replacement) {//替换序列
return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
}
public String[] split(String regex, int limit) { //使用指定正则表达式分割字符串
char ch = 0;
//如果分割符是这些字符,则自行进行分割
if (((regex.value.length == 1 &&
".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
(regex.length() == 2 &&
regex.charAt(0) == '\\' &&
(((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
((ch-'a')|('z'-ch)) < 0 &&
((ch-'A')|('Z'-ch)) < 0)) &&
(ch < Character.MIN_HIGH_SURROGATE ||
ch > Character.MAX_LOW_SURROGATE))
{
int off = 0;
int next = 0;
boolean limited = limit > 0;
ArrayList<String> list = new ArrayList<>();//借助链表来存储分割的元素
while ((next = indexOf(ch, off)) != -1) {//定位元素
if (!limited || list.size() < limit - 1) {//从主串里面substring分割元素
list.add(substring(off, next));
off = next + 1;
} else { // last one
//assert (list.size() == limit - 1);
list.add(substring(off, value.length));//判断模式是否启用,而且已经使用的次数大于limit
off = value.length;
break;
}
}
//没有该字符,则返回完整的串
if (off == 0)
return new String[]{this};
//模式阀值未超过,则添加剩余的串
if (!limited || list.size() < limit)
list.add(substring(off, value.length));
// Construct result
int resultSize = list.size();
if (limit == 0)
while (resultSize > 0 && list.get(resultSize - 1).length() == 0)
resultSize--;
String[] result = new String[resultSize];
return list.subList(0, resultSize).toArray(result);//返回字符数组
}
//否则直接调用正则表达式进行分割
return Pattern.compile(regex).split(this, limit);
}
public String[] split(String regex) {
return split(regex, 0);
}
public String toLowerCase(Locale locale) { //使用给定 Locale 的规则进行字符串小写转化
if (locale == null) {
throw new NullPointerException();
}
int firstUpper;
final int len = value.length;
/* Now check if there are any characters that need to be changed. */
scan: {
for (firstUpper = 0 ; firstUpper < len; ) {
char c = value[firstUpper];
if ((c >= Character.MIN_HIGH_SURROGATE)
&& (c <= Character.MAX_HIGH_SURROGATE)) {
int supplChar = codePointAt(firstUpper);
if (supplChar != Character.toLowerCase(supplChar)) {
break scan;
}
firstUpper += Character.charCount(supplChar);
} else {
if (c != Character.toLowerCase(c)) {
break scan;
}
firstUpper++;
}
}
return this;
}
char[] result = new char[len];
int resultOffset = 0; /* result may grow, so i+resultOffset
* is the write location in result */
/* Just copy the first few lowerCase characters. */
System.arraycopy(value, 0, result, 0, firstUpper);
String lang = locale.getLanguage();
boolean localeDependent =
(lang == "tr" || lang == "az" || lang == "lt");
char[] lowerCharArray;
int lowerChar;
int srcChar;
int srcCount;
for (int i = firstUpper; i < len; i += srcCount) {
srcChar = (int)value[i];
if ((char)srcChar >= Character.MIN_HIGH_SURROGATE
&& (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
srcChar = codePointAt(i);
srcCount = Character.charCount(srcChar);
} else {
srcCount = 1;
}
if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
} else {
lowerChar = Character.toLowerCase(srcChar);
}
if ((lowerChar == Character.ERROR)
|| (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
if (lowerChar == Character.ERROR) {
lowerCharArray =
ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
} else if (srcCount == 2) {
resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount;
continue;
} else {
lowerCharArray = Character.toChars(lowerChar);
}
/* Grow result if needed */
int mapLen = lowerCharArray.length;
if (mapLen > srcCount) {
char[] result2 = new char[result.length + mapLen - srcCount];
System.arraycopy(result, 0, result2, 0, i + resultOffset);
result = result2;
}
for (int x = 0; x < mapLen; ++x) {
result[i + resultOffset + x] = lowerCharArray[x];
}
resultOffset += (mapLen - srcCount);
} else {
result[i + resultOffset] = (char)lowerChar;
}
}
return new String(result, 0, len + resultOffset);
}
public String toLowerCase() { //默认语言环境转化成小写
return toLowerCase(Locale.getDefault());
}
public String toUpperCase(Locale locale) { //转化为大写
if (locale == null) {
throw new NullPointerException();
}
int firstLower;
final int len = value.length;
/* Now check if there are any characters that need to be changed. */
scan: {
for (firstLower = 0 ; firstLower < len; ) {
int c = (int)value[firstLower];
int srcCount;
if ((c >= Character.MIN_HIGH_SURROGATE)
&& (c <= Character.MAX_HIGH_SURROGATE)) {
c = codePointAt(firstLower);
srcCount = Character.charCount(c);
} else {
srcCount = 1;
}
int upperCaseChar = Character.toUpperCaseEx(c);
if ((upperCaseChar == Character.ERROR)
|| (c != upperCaseChar)) {
break scan;
}
firstLower += srcCount;
}
return this;
}
char[] result = new char[len]; /* may grow */
int resultOffset = 0; /* result may grow, so i+resultOffset
* is the write location in result */
/* Just copy the first few upperCase characters. */
System.arraycopy(value, 0, result, 0, firstLower);
String lang = locale.getLanguage();
boolean localeDependent =
(lang == "tr" || lang == "az" || lang == "lt");
char[] upperCharArray;
int upperChar;
int srcChar;
int srcCount;
for (int i = firstLower; i < len; i += srcCount) {
srcChar = (int)value[i];
if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
(char)srcChar <= Character.MAX_HIGH_SURROGATE) {
srcChar = codePointAt(i);
srcCount = Character.charCount(srcChar);
} else {
srcCount = 1;
}
if (localeDependent) {
upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
} else {
upperChar = Character.toUpperCaseEx(srcChar);
}
if ((upperChar == Character.ERROR)
|| (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
if (upperChar == Character.ERROR) {
if (localeDependent) {
upperCharArray =
ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
} else {
upperCharArray = Character.toUpperCaseCharArray(srcChar);
}
} else if (srcCount == 2) {
resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount;
continue;
} else {
upperCharArray = Character.toChars(upperChar);
}
/* Grow result if needed */
int mapLen = upperCharArray.length;
if (mapLen > srcCount) {
char[] result2 = new char[result.length + mapLen - srcCount];
System.arraycopy(result, 0, result2, 0, i + resultOffset);
result = result2;
}
for (int x = 0; x < mapLen; ++x) {
result[i + resultOffset + x] = upperCharArray[x];
}
resultOffset += (mapLen - srcCount);
} else {
result[i + resultOffset] = (char)upperChar;
}
}
return new String(result, 0, len + resultOffset);
}
public String toUpperCase() {
return toUpperCase(Locale.getDefault());
}
public String trim() {//忽略前导空白和后导空白
int len = value.length;
int st = 0;
char[] val = value; /* avoid getfield opcode */
while ((st < len) && (val[st] <= ' ')) {//去掉前导空白' '
st++;
}
while ((st < len) && (val[len - 1] <= ' ')) {//去掉后岛空白 ' '
len--;
}
return ((st > 0) || (len < value.length)) ? substring(st, len) : this;//若存在空白就截取返回,否则返回自身
}
public String toString() { //直接返回自身
return this;
}
public char[] toCharArray() {//转化成char数组
char result[] = new char[value.length];
System.arraycopy(value, 0, result, 0, value.length);
return result;
}
public static String format(String format, Object... args) {//使用指定的格式字符串和参数返回一个格式化字符串
return new Formatter().format(format, args).toString();
}
//使用指定的语言环境、格式字符串和参数返回一个格式化字符串。
public static String format(Locale l, String format, Object... args) {
return new Formatter(l).format(format, args).toString();
}
public static String valueOf(Object obj) {//返回Object的字符串形式
return (obj == null) ? "null" : obj.toString();
}
public static String valueOf(char data[]) {
return new String(data);//char 数组参数的字符串表示形式,新字符串,不影响原数组
}
public static String valueOf(char data[], int offset, int count) {
return new String(data, offset, count); //数组一部分变成新串
}
public static String copyValueOf(char data[], int offset, int count) {
return new String(data, offset, count);
}
public static String copyValueOf(char data[]) {
return new String(data);
}
public static String valueOf(boolean b) {//布尔值转化为字符串值
return b ? "true" : "false";
}
//当调用 intern 方法时,如果常量池已经包含一个等于此 String 对象的字符串(用 equals(Object) 方法确定),则返回池中的字符串
//否则,将此 String 对象添加到池中,并返回此 String 对象的引用。
public native String intern();
}