String
成员变量
// 底层实现是一个char数组。
private final char value[];
private int hash; // Default to 0
private static final long serialVersionUID = -6849794470754667710L;通过构造器创建String对象
public String() {
this.value = "".value;
}
public String(String original) {
this.value = original.value;
this.hash = original.hash;
}
// 底层复制了一个char数组，修改旧的数组不会影响新创建的
public String(char value[]) {
this.value = Arrays.copyOf(value, value.length);
}
// offset即为char数组的下标，count是从下标开始字符个数。
public String(char value[], int offset, int count) {
if (offset < 0) {
throw new StringIndexOutOfBoundsException(offset);
}
if (count <= 0) {
if (count < 0) {
throw new StringIndexOutOfBoundsException(count);
}
if (offset <= value.length) {
this.value = "".value;
return;
}
}
// Note: offset or count might be near -1>>>1.
// value.length-count，是支持最大下标值，如果offset大于这个值，则会超长越界。
if (offset > value.length - count) {
throw new StringIndexOutOfBoundsException(offset + count);
}
// 底层调用Arrays方法，查看Arrays源码
this.value = Arrays.copyOfRange(value, offset, offset+count);
}
public String(int[] codePoints, int offset, int count) {
if (offset < 0) {
throw new StringIndexOutOfBoundsException(offset);
}
if (count <= 0) {
if (count < 0) {
throw new StringIndexOutOfBoundsException(count);
}
if (offset <= codePoints.length) {
this.value = "".value;
return;
}
}
// Note: offset or count might be near -1>>>1.
if (offset > codePoints.length - count) {
throw new StringIndexOutOfBoundsException(offset + count);
}
// 最后一个字符下标
final int end = offset + count;
// Pass 1: Compute precise size of char[]
// 计算出字符数组长度
int n = count;
for (int i = offset; i < end; i++) {
int c = codePoints[i];
if (Character.isBmpCodePoint(c))
continue;
// 如果是增补字符，则采用2个char表示，这是定义。
else if (Character.isValidCodePoint(c))
n++;
else throw new IllegalArgumentException(Integer.toString(c));
}
// Pass 2: Allocate and fill in char[]
final char[] v = new char[n];
// 这里i用来控制取值，j用来控制如果是增补字符，则需要2个位置，j一次循环需要自增2次。并调用Character方法存放增补字符。
for (int i = offset, j = 0; i < end; i++, j++) {
int c = codePoints[i];
if (Character.isBmpCodePoint(c))
v[j] = (char)c;
else
Character.toSurrogates(c, v, j++);
}
this.value = v;
}
@Deprecated
public String(byte ascii[], int hibyte) {
this(ascii, hibyte, 0, ascii.length);
}
@Deprecated
public String(byte ascii[], int hibyte, int offset, int count) {
checkBounds(ascii, offset, count);
char value[] = new char[count];
if (hibyte == 0) {
for (int i = count; i-- > 0;) {
value[i] = (char)(ascii[i + offset] & 0xff);
}
} else {
hibyte <<= 8;
for (int i = count; i-- > 0;) {
value[i] = (char)(hibyte | (ascii[i + offset] & 0xff));
}
}
this.value = value;
}
// 底层使用StringCoding.decode，不做研究。
public String(byte bytes[], int offset, int length, String charsetName)
throws UnsupportedEncodingException {
if (charsetName == null)
throw new NullPointerException("charsetName");
checkBounds(bytes, offset, length);
this.value = StringCoding.decode(charsetName, bytes, offset, length);
}
// 底层使用StringCoding.decode，不做研究。
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) {
this(bytes, 0, bytes.length, charset);
}
// 不指定字符集，默认是"ISO-8859-1"
public String(byte bytes[], int offset, int length) {
checkBounds(bytes, offset, length);
this.value = StringCoding.decode(bytes, offset, length);
}
public String(byte bytes[]) {
this(bytes, 0, bytes.length);
}
public String(StringBuffer buffer) {
synchronized(buffer) {
this.value = Arrays.copyOf(buffer.getValue(), buffer.length());
}
}
public String(StringBuilder builder) {
this.value = Arrays.copyOf(builder.getValue(), builder.length());
}对象方法
public int length() {
return value.length;
} public boolean isEmpty() {
return value.length == 0;
} public char charAt(int index) {
if ((index < 0) || (index >= value.length)) {
throw new StringIndexOutOfBoundsException(index);
}
return value[index];
} public int codePointAt(int index) {
if ((index < 0) || (index >= value.length)) {
throw new StringIndexOutOfBoundsException(index);
}
return Character.codePointAtImpl(value, index, value.length);
} public int codePointBefore(int index) {
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) {
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) {
if (index < 0 || index > value.length) {
throw new IndexOutOfBoundsException();
}
return Character.offsetByCodePointsImpl(value, 0, value.length,
index, codePointOffset);
} void getChars(char dst[], int dstBegin) {
System.arraycopy(value, 0, dst, dstBegin, value.length);
}
public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
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 {
if (charsetName == null) throw new NullPointerException();
return StringCoding.encode(charsetName, value, 0, value.length);
}
public byte[] getBytes(Charset charset) {
if (charset == null) throw new NullPointerException();
return StringCoding.encode(charset, value, 0, value.length);
}
public byte[] getBytes() {
return StringCoding.encode(value, 0, value.length);
}比较地址，如果相等则字符串相等，其次比较字符串每个char的值是否相等。
public boolean equals(Object anObject) {
if (this == anObject) {
return true;
}
if (anObject instanceof String) {
String anotherString = (String)anObject;
int n = value.length;
if (n == anotherString.value.length) {
char v1[] = value;
char v2[] = anotherString.value;
int i = 0;
while (n-- != 0) {
if (v1[i] != v2[i])
return false;
i++;
}
return true;
}
}
return false;
}
public boolean contentEquals(StringBuffer sb) {
return contentEquals((CharSequence)sb);
}
// 注意，需要判断cs类型，如果是buffer，则需要加锁。
public boolean contentEquals(CharSequence cs) {
// Argument is a StringBuffer, StringBuilder
if (cs instanceof AbstractStringBuilder) {
if (cs instanceof StringBuffer) {
synchronized(cs) {
return nonSyncContentEquals((AbstractStringBuilder)cs);
}
} else {
return nonSyncContentEquals((AbstractStringBuilder)cs);
}
}
// Argument is a String
if (cs instanceof String) {
return equals(cs);
}
// Argument is a generic CharSequence
char v1[] = value;
int n = v1.length;
if (n != cs.length()) {
return false;
}
for (int i = 0; i < n; i++) {
if (v1[i] != cs.charAt(i)) {
return false;
}
}
return true;
}
private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
char v1[] = value;
char v2[] = sb.getValue();
int n = v1.length;
if (n != sb.length()) {
return false;
}
for (int i = 0; i < n; i++) {
if (v1[i] != v2[i]) {
return false;
}
}
return true;
}
public boolean equalsIgnoreCase(String anotherString) {
return (this == anotherString) ? true
: (anotherString != null)
&& (anotherString.value.length == value.length)
&& regionMatches(true, 0, anotherString, 0, value.length);
}指定一个范围段，进行char比较。
public boolean regionMatches(int toffset, String other, int ooffset,
int len) {
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) {
if (ta[to++] != pa[po++]) {
return false;
}
}
return true;
}
public boolean regionMatches(boolean ignoreCase, int toffset,
String other, int ooffset, int len) {
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;
}比较的是2个字符串char数组从头开始，不同字符的差值，如果有包含关系，则返回他们的长度差值。
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];
char c2 = v2[k];
if (c1 != c2) {
return c1 - c2;
}
k++;
}
return len1 - len2;
}
public int compareToIgnoreCase(String str) {
return CASE_INSENSITIVE_ORDER.compare(this, str);
} public boolean startsWith(String prefix, int toffset) {
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++]) {
return false;
}
}
return true;
}
public boolean startsWith(String prefix) {
return startsWith(prefix, 0);
}
public boolean endsWith(String suffix) {
return startsWith(suffix, value.length - suffix.value.length);
}hash算法：s31^(n-1) + s[1]31^(n-2) + … + s[n-1]
public int hashCode() {
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) {
return indexOf(ch, 0);
}
public int indexOf(int ch, int fromIndex) {
final int max = value.length;
if (fromIndex < 0) {
fromIndex = 0;
} else if (fromIndex >= max) {
// Note: fromIndex might be near -1>>>1.
return -1;
}
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;
for (int i = fromIndex; i < max; i++) {
if (value[i] == ch) {
return i;
}
}
return -1;
} else {
return indexOfSupplementary(ch, fromIndex);
}
}
private int indexOfSupplementary(int ch, int fromIndex) {
if (Character.isValidCodePoint(ch)) {
final char[] value = this.value;
final char hi = Character.highSurrogate(ch);
final char lo = Character.lowSurrogate(ch);
final int max = value.length - 1;
for (int i = fromIndex; i < max; i++) {
if (value[i] == hi && value[i + 1] == lo) {
return i;
}
}
}
return -1;
}
public int indexOf(String str) {
return indexOf(str, 0);
}
public int indexOf(String str, int fromIndex) {
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) {
// 如果开始比较位置超出查找字符串长度，则判断目标字符串的长度
if (fromIndex >= sourceCount) {
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++) {
// 找第一个相等的字符。这个while循环有趣。找到了才会结束while循环。
if (source[i] != first) {
while (++i <= max && source[i] != first);
}
// 找到第一个相同字符后，比较后面的字符。这里面的数组下标需要控制好。
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(int ch) {
return lastIndexOf(ch, value.length - 1);
}
public int lastIndexOf(int ch, int fromIndex) {
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 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,
String target, int fromIndex) {
return lastIndexOf(source, sourceOffset, sourceCount,
target.value, 0, target.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;
}
}单例，线程安全体现
比较两个字符串的大小：从第一个字符开始比较，如果字符不同，则返回差值，如果一个字符串包含另一个字符串，则返回他们的长度差值。
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);
c2 = Character.toUpperCase(c2);
if (c1 != c2) {
c1 = Character.toLowerCase(c1);
c2 = Character.toLowerCase(c2);
if (c1 != c2) {
// No overflow because of numeric promotion
return c1 - c2;
}
}
}
}
return n1 - n2;
}
/** Replaces the de-serialized object. */
private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
}