关于UTF-8与UTF-8+BOM的问题

在某些时候解析XML文件时，会出现root element is missing类似错误，一般为文件编码问题，之前碰到一个问题客户提供一份XML文件，进行测试，一直提示该错误，用文本编辑软件查看，没有问题，但是新建xml文件，将其中内容复制进去，再次测试正常，发现该文件为带BOM的UTF-8。查找将BOM去除的java代码，目前只找到一个方法，并测试有用。

 /**
     *
     * @param resultFileName
     */
    public static Set getFileNamesFromCompileResult(String resultFileName)
            throws IOException {
        Set<String> set = new HashSet();
        BufferedReader reader = new BufferedReader(new FileReader(
                resultFileName));
        String start = "[javac] ";
        int startLen = start.length();
        String end = ".java:";
        int endLen = end.length();

        String errMsg = "\\65279";
        while (reader.ready()) {
            String line = reader.readLine();
            int indexStart = line.indexOf(start);

            if (line.indexOf(errMsg) == -1) {
                continue;
            }
            if (indexStart != -1) {
                int indexEnd = line.indexOf(end);
                if (indexEnd != -1) {
                    String name = line.substring(indexStart + startLen,
                            indexEnd + endLen - 1);
                    set.add(name.trim());
                }
            }
        }
        return set;

    }

    public static void DealSrcFiles(String path) {
        if (path.charAt(path.length() - 1) != '\\') {
            path += '\\';
        }
        File file = new File(path);
        if (!file.exists()) {
            System.out.println("Error: Path not Existed! Please Check it out!");
            return;
        }
        String[] filelist = file.list();
        for (int i = 0; i < filelist.length; i++) {
            File temp = new File(path + filelist[i]);
            if ((temp.isDirectory() && !temp.isHidden() && temp.exists())) {
                DealSrcFiles(path + filelist[i]);
            } else {
                if (filelist[i].endsWith(".java")) {
                    try {
                        trimBom(path + filelist[i]);
                    } catch (Exception eee) {
                    }
                }
            }
        }
    }

    /**
     * 读取流中前面的字符，看是否有bom，如果有bom，将bom头先读掉丢弃
     *
     * @param in
     * @return
     * @throws java.io.IOException
     */
    public static InputStream getInputStream(InputStream in) throws IOException {

        PushbackInputStream testin = new PushbackInputStream(in);
        int ch = testin.read();
        if (ch != 0xEF) {
            testin.unread(ch);
        } else if ((ch = testin.read()) != 0xBB) {
            testin.unread(ch);
            testin.unread(0xef);
        } else if ((ch = testin.read()) != 0xBF) {
            throw new IOException("错误的UTF-8格式文件");
        } else {
// 不需要做，这里是bom头被读完了
// // System.out.println("still exist bom");
        }
        return testin;

    }

    /**
     * 根据一个文件名，读取完文件，干掉bom头。
     *
     * @param fileName
     * @throws java.io.IOException
     */
    public static void trimBom(String fileName) throws IOException {

        FileInputStream fin = new FileInputStream(fileName);
// 开始写临时文件
        InputStream in = getInputStream(fin);
        ByteArrayOutputStream bos = new ByteArrayOutputStream();
        byte b[] = new byte[4096];

        int len = 0;
        while (in.available() > 0) {
            len = in.read(b, 0, 4096);
//            out.write(b, 0, len);
            bos.write(b, 0, len);
        }

        in.close();
        fin.close();
        bos.close();

// 临时文件写完，开始将临时文件写回本文件。
        System.out.println("[" + fileName + "]");
        FileOutputStream out = new FileOutputStream(fileName);
        out.write(bos.toByteArray());
        out.close();
        System.out.println("处理文件" + fileName);
    }

    /**
     * 根据ant编译错误来去除bom
     *
     * @param resultFile
     * @throws java.io.IOException
     */
    static void trimBomByCompileResult(String resultFile) throws IOException {
        Set<String> set = getFileNamesFromCompileResult(resultFile);
        for (String fName : set) {
            trimBom(fName);
        }
    }

    public static void main(String[] args) throws IOException {
        DealSrcFiles("D:/ttt/p");
    }

以下是该作者方法链接

点击打开链接