Java源码赏析（五）再识 String 类

在 Java源码赏析（三）初识 String 类   中，我们已经大概理解了String的接口，接下来我们描述一下String的常用工具方法。

/**

 * 为了精简的String结构，之前提到的方法省略，重点介绍剩余的方法（省略构造方法、indexOf、lastIndexOf、valueOf）
 */
public final class String
    implements java.io.Serializable, Comparable<String>, CharSequence {

    private final char value[];

    private int hash; // Default to 0

    private static final long serialVersionUID =         -6849794470754667710L;

    /** 指明需要实例化的字段 */
    private static final ObjectStreamField[] serialPersistentFields =
        new ObjectStreamField[0];

    /** 省略CaseInsensitiveComparator()的实现，主要是用于按ASCII码的排序规则进行排序 */
    public static final Comparator<String> CASE_INSENSITIVE_ORDER
                                         = new CaseInsensitiveComparator();

    /** 实现Comparable<String> */
    public int compareTo(String anotherString) {
        ...
    }

    /** 覆盖hashCode() */
    public int hashCode() {
        ...
    }

    /** 覆盖父类equal() */
    public boolean equals(Object anObject) {
        ...
    }

    /** 覆盖父类toString() */
    public String toString() {
        return this;
    }

    /**
     *   实现CharSequence接口
     *   共有length(), charAt(int index), subSequence(int beginIndex, int endIndex) 等
     *   在实现subSequence()方法时使用了String中substring()方法
     */

    /** 获取字符串长度 */
    public int length() {
        return value.length;
    }

    /** 获取index位置的字符 */
    public char charAt(int index) {
    ...
    }

    /** 获取子字符序列 */
    public CharSequence subSequence(int beginIndex, int endIndex) {
        return this.substring(beginIndex, endIndex);
    }

    /** 获取子串 */
    public String substring(int beginIndex, int endIndex) {
    ...
    }
    /** 将字符串存入常量池并返回在常量池的引用 */
    public native String intern();

    /**分隔线*/

　　将字符串str连接至末尾，创建一个新字符串*/
    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);
    }

    /** 将oldChar字符替换为newChar字符*/
    public String replace(char oldChar, char newChar) {
        if (oldChar != newChar) {
            int len = value.length;
            int i = -1;
            char[] val = value; /* avoid getfield opcode */

            while (++i < len) {
                if (val[i] == oldChar) {
                    break;
                }
            }
            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;
    }

    /** 返回是否被regex匹配*/
    public boolean matches(String regex) {
        return Pattern.matches(regex, this);
    }

    /** 查看字符串s是否被包含*/
    public boolean contains(CharSequence s) {
        return indexOf(s.toString()) > -1;
    }

    /** 替换第一个根据regex匹配到的字符串为replacement*/
    public String replaceFirst(String regex, String replacement) {
        return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
    }

    /** 将regex匹配到的内容全部替换为replacement*/
    public String replaceAll(String regex, String replacement) {
        return Pattern.compile(regex).matcher(this).replaceAll(replacement);
    }

    /** 将字符串target替换为replacement*/
    public String replace(CharSequence target, CharSequence replacement) {
        return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
                this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
    }

    /** 根据regex分割limit次字符串*/
    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);
    }

    /** 根据regex分隔字符串*/
    public String[] split(String regex) {
        return split(regex, 0);
    }

    /** 将elements字符串数组中插入delimiter字符串 比如 String.join(",", {"a", "b", "c"})  == "a,b,c" */
    public static String join(CharSequence delimiter, CharSequence... elements) {
        Objects.requireNonNull(delimiter);
        Objects.requireNonNull(elements);
        // Number of elements not likely worth Arrays.stream overhead.
        StringJoiner joiner = new StringJoiner(delimiter);
        for (CharSequence cs: elements) {
            joiner.add(cs);
        }
        return joiner.toString();
    }

    /** 同上，数组改为了集合*/
    public static String join(CharSequence delimiter,
            Iterable<? extends CharSequence> elements) {
        Objects.requireNonNull(delimiter);
        Objects.requireNonNull(elements);
        StringJoiner joiner = new StringJoiner(delimiter);
        for (CharSequence cs: elements) {
            joiner.add(cs);
        }
        return joiner.toString();
    }

    /** 全部转化为小写字母*/
    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);
    }

    /** 全部转化为小写字母*/
    public String toLowerCase() {
        return toLowerCase(Locale.getDefault());
    }

    /** 全部转化为大写字母*/
    public String toUpperCase(Locale locale) {
        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;
        }

        /* result may grow, so i+resultOffset is the write location in result */
        int resultOffset = 0;
        char[] result = new char[len]; /* may grow */

        /* 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);
    }

    /** 全部转化为大写字母*/
    public String toUpperCase() {
        return toUpperCase(Locale.getDefault());
    }

    /** 去除字符串前后的空格*/
    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;
    }

    /** 转化为字符数组*/
    public char[] toCharArray() {
        // Cannot use Arrays.copyOf because of class initialization order issues
        char result[] = new char[value.length];
        System.arraycopy(value, 0, result, 0, value.length);
        return result;
    }

    /** 格式化字符串，便于输出*/
    public static String format(String format, Object... args) {
        return new Formatter().format(format, args).toString();
    }

    /** 使用指定的地区l，格式化字符串，便于输出*/
    public static String format(Locale l, String format, Object... args) {
        return new Formatter(l).format(format, args).toString();
    }

    /** 根据data字符数组从offset开始复制count个字符*/
    public static String valueOf(char data[], int offset, int count) {
        return new String(data, offset, count);
    }

    /** 根据data字符数组从offset开始拷贝count个字符*/
    public static String copyValueOf(char data[], int offset, int count) {
        return new String(data, offset, count);
    }

    /** 拷贝字符串的值*/
    public static String copyValueOf(char data[]) {
        return new String(data);
    }

    /** 省略大部分的类型转化为字符串*/
    public static String valueOf(boolean b) {
        return b ? "true" : "false";
    }

    ...
}

未完，待续