Java源码分析之String

仰慕了已久的String类

成员变量

//内部就是char数组保存，注意是final哦
private final char value[];
private int hash; // Default to 0

构造函数

public String() {
this.value = "".value;
}

public String(String original) {
this.value = original.value;
this.hash = original.hash;
}

//不需要计算hashcode？
public String(char value[]) {
this.value = Arrays.copyOf(value, value.length);
}

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.
if (offset > value.length - count) {
throw new StringIndexOutOfBoundsException(offset + count);
    }
this.value = Arrays.copyOfRange(value, offset, offset+count);
}

//hibyte是什么意思，不太懂，byte转char，必须得& 0xff,否则会出问题
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;
}

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);
}

public String(byte bytes[], int offset, int length) {
    checkBounds(bytes, offset, length);
this.value = StringCoding.decode(bytes, offset, length);
}

//注意是synchronized
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());
}

基本方法

length && isEmpty

public int length() {
return value.length;
}

public boolean isEmpty() {
return value.length == 0;
}

charAt

public char charAt(int index) {
if ((index < 0) || (index >= value.length)) {
throw new StringIndexOutOfBoundsException(index);
    }
return value[index];
}

getChars

void getChars(char dst[], int dstBegin) {
    System.arraycopy(value, 0, dst, dstBegin, value.length);
}

//将srcBegin-srcEnd拷贝至dst
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);
}

equals

//如果先比hashcode是不更好一点儿？如果相等，再一位一位比较
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 equalsIgnoreCase(String anotherString) {
return (this == anotherString) ? true
            : (anotherString != null)
            && (anotherString.value.length == value.length)
            && regionMatches(true, 0, anotherString, 0, value.length);
}

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;
}

compareTo

//按字典序比较
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;
}

startsWith

//找value从toffest开始，与prefix是否相等
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);
}

hashCode

//string的hashcode的算法，依旧用的31，这里初始是0，hashmap里初始是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;
}

indexOf

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);
    }
}

//为何参数这么多
static int indexOf(char[] source, int sourceOffset, int sourceCount,
        char[] target, int targetOffset, int targetCount,
int fromIndex) {
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);

//暴力找，居然不是kmp什么的
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;
}

subString

// 当子串刚好是本串时，就返回this，这也是String的一大思想，不可变，对于一个确定的字符串，可以用同一个对象表示
public String substring(int beginIndex) {
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);
}

public String substring(int beginIndex, int endIndex) {
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);
}

concat

//讲str添加到value的后面，这里也给出了一种字符串相加的方法
public String concat(String str) {
int otherLen = str.length();
if (otherLen == 0) {
return this;
    }
int len = value.length;
char buf[] = Arrays.copyOf(value, len + otherLen);
    str.getChars(buf, len);
return new String(buf, true);
}

replace

//将字符串中所有的oldChar替换为newChar
public String replace(char oldChar, char newChar) {
//如果两个字符相等，直接返回本串
if (oldChar != newChar) {
int len = value.length;
int i = -1;
char[] val = value; /* avoid getfield opcode */

while (++i < len) {
if (val[i] == oldChar) {
break;
            }
        }
//如果本串中没有oldChar，直接返回本串
if (i < len) {
char buf[] = new char[len];
for (int j = 0; j < i; j++) {
                buf[j] = val[j];
            }
while (i < len) {
char c = val[i];
                buf[i] = (c == oldChar) ? newChar : c;
                i++;
            }
return new String(buf, true);
        }
    }
return this;
}

toLowerCase

//locale，居然可以选语言！真厉害了！当然，默认是英语的
public String toLowerCase(Locale locale) {
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
            srcChar == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE
            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);
}

//默认英语
public String toLowerCase() {
    returntoLowerCase(Locale.getDefault());
}
//toUpperCase基本同理，就不贴了

trim

//判断条件是 <=' '，所以前面的tab，换行之类的，都可以去掉
public String trim() {
int len = value.length;
int st = 0;
char[] val = value;    /* avoid getfield opcode */

while ((st < len) && (val[st] <= ' ')) {
        st++;
    }
while ((st < len) && (val[len - 1] <= ' ')) {
        len--;
    }
return ((st > 0) || (len < value.length)) ? substring(st, len) : this;
}

toString

//String.toString，感觉蛮搞笑的
public String toString() {
return this;
}

toCharArray

public char[] toCharArray() {
// Cannotuse Arrays.copyOf because of class initialization order issues
char result[] = new char[value.length];
    System.arraycopy(value, 0, result, 0, value.length);
return result;
}

valueOf

//对于char，直接构造就好
public static String valueOf(char data[]) {
return new String(data);
}
//咦，这俩不一样的吗
public static String copyValueOf(char data[]) {
return new String(data);
}
public static String valueOf(char data[], int offset, int count) {
return new String(data, offset, count);
}
//咦，这俩不一样的吗
public static String copyValueOf(char data[], int offset, int count) {
return new String(data, offset, count);
}

//boolean
public static String valueOf(boolean b) {
return b ? "true" : "false";
}
//int，调用的Integer.toString
public static String valueOf(int i) {
return Integer.toString(i);
}
//对于long，float，double都是调用toString

matches

//匹配正则
public boolean matches(String regex) {
return Pattern.matches(regex, this);
}

split

//有点儿复杂
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 ".$|()[{^?*+\\", or
 (2)two-char String and the first char is the backslash and
 the second is not the ascii digit or ascii letter.
 */
char ch = 0;
if (((regex.value.length == 1 &&
".$|()[{^?*+\\".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<>();
while ((next = indexOf(ch, off)) != -1) {
if (!limited || list.size() < limit - 1) {
list.add(substring(off, next));
                off = next + 1;
            } else {    // last one
//assert (list.size() == limit - 1);
list.add(substring(off, value.length));
                off = value.length;
break;
            }
        }
// If no match was found, return this
if (off == 0)
return new String[]{this};

// Add remaining segment
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);
    }
return Pattern.compile(regex).split(this, limit);
}

getBytes

public void getBytes(int srcBegin, int srcEnd, byte 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);
    }
    Objects.requireNonNull(dst);

//为何要重新赋值？
int j = dstBegin;
int n = srcEnd;
int i = srcBegin;
char[] val = value;   /* avoid getfield opcode */

while (i < n) {
        dst[j++] = (byte)val[i++];
    }
}

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);
}