String源码详解

1.String的继承实现关系

因为被final修饰,因此是不可继承的String类,避免被他人继承后修改。实现了三个接口。可序列、可比较,有序。

public final class String
    implements java.io.Serializable, Comparable<String>, CharSequence

2.String的本质是什么

String的本质是char 数组

 private final char value[];

3.String的构造函数有那些

我们看下具体的代码:

//无参构造函数
public String() {
        this.value = "".value;
    }
//有参构造函数
public String(String original) {
        this.value = original.value;
        this.hash = original.hash;
    }

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);
    }

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);
        }

        final int end = offset + count;

        // Pass 1: Compute precise size of char[]
        int n = count;
        for (int i = offset; i < end; i++) {
            int c = codePoints[i];
            if (Character.isBmpCodePoint(c))
                continue;
            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];

        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;
    }

//可设置编码格式的
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);
    }

//可设置编码格式的
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);
    }

//可设置编码格式的
public String(byte bytes[], String charsetName)
            throws UnsupportedEncodingException {
        this(bytes, 0, bytes.length, charsetName);
    }

//可设置编码格式的
public String(byte bytes[], Charset charset) {
        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 String(byte bytes[]) {
        this(bytes, 0, bytes.length);
    }

//同步的
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());
    }

String(char[] value, boolean share) {
        // assert share : "unshared not supported";
        this.value = value;
    }

4.String常用的方法

(1)replace、replaceAll及replaceFirst 

replace源码:

/**
     * @param oldChar 待替换的字符
     * @param newChar 替换的字符
     * @return
     */
    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;
    }


 /**
     * @param target 待替换的
     * @param replacement 替换的
     * @return
     */
    public String replace(CharSequence target, CharSequence replacement) {
        return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
                this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
    }

replaceAll源码:

/**
     * 全部替换 支持正则
     * @param regex 待替换的 支持正则
     * @param replacement 替换的字符串
     * @return
     */
    public String replaceAll(String regex, String replacement) {
        return Pattern.compile(regex).matcher(this).replaceAll(replacement);
    }

/**
    *matcher 中的replaceAll 实现
    *
    */

public String replaceAll(String replacement) {
        reset();
        boolean result = find();
        if (result) {
            StringBuffer sb = new StringBuffer();
            do {
                appendReplacement(sb, replacement);
                result = find();
            } while (result);
            appendTail(sb);
            return sb.toString();
        }
        return text.toString();
    }

public Matcher appendReplacement(StringBuffer sb, String replacement) {

        // If no match, return error
        if (first < 0)
            throw new IllegalStateException("No match available");

        // Process substitution string to replace group references with groups
        int cursor = 0;
        StringBuilder result = new StringBuilder();

        while (cursor < replacement.length()) {
            char nextChar = replacement.charAt(cursor);
            if (nextChar == '\\') {
                cursor++;
                if (cursor == replacement.length())
                    throw new IllegalArgumentException(
                        "character to be escaped is missing");
                nextChar = replacement.charAt(cursor);
                result.append(nextChar);
                cursor++;
            } else if (nextChar == '$') {
                // Skip past $
                cursor++;
                // Throw IAE if this "$" is the last character in replacement
                if (cursor == replacement.length())
                   throw new IllegalArgumentException(
                        "Illegal group reference: group index is missing");
                nextChar = replacement.charAt(cursor);
                int refNum = -1;
                if (nextChar == '{') {
                    cursor++;
                    StringBuilder gsb = new StringBuilder();
                    while (cursor < replacement.length()) {
                        nextChar = replacement.charAt(cursor);
                        if (ASCII.isLower(nextChar) ||
                            ASCII.isUpper(nextChar) ||
                            ASCII.isDigit(nextChar)) {
                            gsb.append(nextChar);
                            cursor++;
                        } else {
                            break;
                        }
                    }
                    if (gsb.length() == 0)
                        throw new IllegalArgumentException(
                            "named capturing group has 0 length name");
                    if (nextChar != '}')
                        throw new IllegalArgumentException(
                            "named capturing group is missing trailing '}'");
                    String gname = gsb.toString();
                    if (ASCII.isDigit(gname.charAt(0)))
                        throw new IllegalArgumentException(
                            "capturing group name {" + gname +
                            "} starts with digit character");
                    if (!parentPattern.namedGroups().containsKey(gname))
                        throw new IllegalArgumentException(
                            "No group with name {" + gname + "}");
                    refNum = parentPattern.namedGroups().get(gname);
                    cursor++;
                } else {
                    // The first number is always a group
                    refNum = (int)nextChar - '0';
                    if ((refNum < 0)||(refNum > 9))
                        throw new IllegalArgumentException(
                            "Illegal group reference");
                    cursor++;
                    // Capture the largest legal group string
                    boolean done = false;
                    while (!done) {
                        if (cursor >= replacement.length()) {
                            break;
                        }
                        int nextDigit = replacement.charAt(cursor) - '0';
                        if ((nextDigit < 0)||(nextDigit > 9)) { // not a number
                            break;
                        }
                        int newRefNum = (refNum * 10) + nextDigit;
                        if (groupCount() < newRefNum) {
                            done = true;
                        } else {
                            refNum = newRefNum;
                            cursor++;
                        }
                    }
                }
                // Append group
                if (start(refNum) != -1 && end(refNum) != -1)
                    result.append(text, start(refNum), end(refNum));
            } else {
                result.append(nextChar);
                cursor++;
            }
        }
        // Append the intervening text
        sb.append(text, lastAppendPosition, first);
        // Append the match substitution
        sb.append(result);

        lastAppendPosition = last;
        return this;
    }

replaceFirst 源码:

public String replaceFirst(String regex, String replacement) {
        return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
    }

 public String replaceFirst(String replacement) {
        if (replacement == null)
            throw new NullPointerException("replacement");
        reset();
        if (!find())
            return text.toString();
        StringBuffer sb = new StringBuffer();
        appendReplacement(sb, replacement);
        appendTail(sb);
        return sb.toString();
    }

由以上可以看出

  • replace不支持正则,但是会全部替换掉字符串中对应的数据
  • replaceAll 支持正则,且会全部替换掉字符串中对应的数据
  • replaceFirst 支持正则,但只会替换第一个符合条件的数据

(2)substring截取字符串

源码如下:

 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);
    }

以上可以看出 substring有两种截取方式

  • 第一种输入开始下标,截取该位置后全部被的字符串
  • 第二种输入开始下标结束下标,截取该段范围内的字符串,注意这里的开始结束是前等后不等的 

(3)split 分割字符串

源码如下:

public String[] split(String regex) {
        return split(regex, 0);
    }

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);
    }
  • 以上可以看出,split两种方式,其实是一种实现,支持正则表达式

(4) trim 去除前后空格

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;
    }

(5)startsWith 判断字符串已什么开始,返回Boolean

源码如下:

public boolean startsWith(String prefix) {
        return startsWith(prefix, 0);
    }

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;
    }

以上可以看出startsWith支持下标查询,可以输入对应的开始下标

(6)endsWith 判断字符串已什么结束,返回Boolean

源码如下:

public boolean endsWith(String suffix) {
        return startsWith(suffix, value.length - suffix.value.length);
    }

由此可以看出,endsWith其实是调用的startsWith,只是输入了对应的下标

(7)contains 判断是否包含对应的字符串,返回Boolean

源码如下:

public boolean contains(CharSequence s) {
        return indexOf(s.toString()) > -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) {
        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++) {
            /* 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;
    }

(8)concat 字符串拼接

源码如下:

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);
    }

(9)join 字符串拼接

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();
    }

其实String方法还有一些,这里就不在一一列举了。

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值