RandomAccessFile readUTF与我自己写的方法对比，官方为什么那么复杂？

最新推荐文章于 2024-09-28 18:43:38 发布

最新推荐文章于 2024-09-28 18:43:38 发布 · 314 阅读

文章标签：

#C #C++ #C#

Swing 专栏收录该内容

6 篇文章

订阅专栏

本文深入探讨了Java中使用RandomAccessFile读取UTF-8编码字符串的方法及源码解析，详细解释了如何处理不同编码情况下的字节转换，并针对可能出现的异常情况进行了说明。

我写的


RandomAccessFile raf=。。。
int len=raf.readShort()&0xffff;
byte[] name=new byte[len];
raf.read(name);
return new String(name,"utf-8");

readUTF源码


int utflen = in.readUnsignedShort();
        byte[] bytearr = null;
        char[] chararr = null;
        if (in instanceof DataInputStream) {
            DataInputStream dis = (DataInputStream)in;
            if (dis.bytearr.length < utflen){
                dis.bytearr = new byte[utflen*2];
                dis.chararr = new char[utflen*2];
            }
            chararr = dis.chararr;
            bytearr = dis.bytearr;
        } else {
            bytearr = new byte[utflen];
            chararr = new char[utflen];
        }

        int c, char2, char3;
        int count = 0;
        int chararr_count=0;

        in.readFully(bytearr, 0, utflen);

        while (count < utflen) {
            c = (int) bytearr[count] & 0xff;      
            if (c > 127) break;
            count++;
            chararr[chararr_count++]=(char)c;
        }

        while (count < utflen) {
            c = (int) bytearr[count] & 0xff;
            switch (c >> 4) {
                case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7:
                    /* 0xxxxxxx*/
                    count++;
                    chararr[chararr_count++]=(char)c;
                    break;
                case 12: case 13:
                    /* 110x xxxx   10xx xxxx*/
                    count += 2;
                    if (count > utflen)
                        throw new UTFDataFormatException(
                            "malformed input: partial character at end");
                    char2 = (int) bytearr[count-1];
                    if ((char2 & 0xC0) != 0x80)
                        throw new UTFDataFormatException(
                            "malformed input around byte " + count); 
                    chararr[chararr_count++]=(char)(((c & 0x1F) << 6) | 
                                                    (char2 & 0x3F));  
                    break;
                case 14:
                    /* 1110 xxxx  10xx xxxx  10xx xxxx */
                    count += 3;
                    if (count > utflen)
                        throw new UTFDataFormatException(
                            "malformed input: partial character at end");
                    char2 = (int) bytearr[count-2];
                    char3 = (int) bytearr[count-1];
                    if (((char2 & 0xC0) != 0x80) || ((char3 & 0xC0) != 0x80))
                        throw new UTFDataFormatException(
                            "malformed input around byte " + (count-1));
                    chararr[chararr_count++]=(char)(((c     & 0x0F) << 12) |
                                                    ((char2 & 0x3F) << 6)  |
                                                    ((char3 & 0x3F) << 0));
                    break;
                default:
                    /* 10xx xxxx,  1111 xxxx */
                    throw new UTFDataFormatException(
                        "malformed input around byte " + count);
            }
        }
        // The number of chars produced may be less than utflen
        return new String(chararr, 0, chararr_count);

为什么官方要这么复杂？