zoukankan      html  css  js  c++  java
  • java自动探测文件的字符编码

    Mozilla有一个C++版的自动字符集探测算法代码,然后sourceforge上有人将其改成java版的~~

    主页:http://jchardet.sourceforge.net/

    jchardet is a java port of the source from mozilla's automatic charset detection algorithm.
    The original author is Frank Tang. What is available here is the java port of that code.
    The original source in C++ can be found from http://lxr.mozilla.org/mozilla/source/intl/chardet/
    More information can be found at http://www.mozilla.org/projects/intl/chardet.html

    下面是见证奇迹的时刻:

    import java.io.BufferedInputStream;
    import java.io.File;
    import java.io.FileInputStream;
    import java.io.FileNotFoundException;
    import java.io.IOException;
    
    import org.mozilla.intl.chardet.nsDetector;
    import org.mozilla.intl.chardet.nsICharsetDetectionObserver;
    
    public class FileCharsetDetector {
        private boolean found = false;
        private String encoding = null;
    
        public static void main(String[] argv) throws Exception {
            File file1 = new File("C:\test1.txt");
            
            System.out.println("文件编码:" + new FileCharsetDetector().guessFileEncoding(file1));
        }
    
        /**
         * 传入一个文件(File)对象,检查文件编码
         * 
         * @param file
         *            File对象实例
         * @return 文件编码,若无,则返回null
         * @throws FileNotFoundException
         * @throws IOException
         */
        public String guessFileEncoding(File file) throws FileNotFoundException, IOException {
            return guessFileEncoding(file, new nsDetector());
        }
    
        /**
         * <pre>
         * 获取文件的编码
         * @param file
         *            File对象实例
         * @param languageHint
         *            语言提示区域代码 @see #nsPSMDetector ,取值如下:
         *             1 : Japanese
         *             2 : Chinese
         *             3 : Simplified Chinese
         *             4 : Traditional Chinese
         *             5 : Korean
         *             6 : Dont know(default)
         * </pre>
         * 
         * @return 文件编码,eg:UTF-8,GBK,GB2312形式(不确定的时候,返回可能的字符编码序列);若无,则返回null
         * @throws FileNotFoundException
         * @throws IOException
         */
        public String guessFileEncoding(File file, int languageHint) throws FileNotFoundException, IOException {
            return guessFileEncoding(file, new nsDetector(languageHint));
        }
    
        /**
         * 获取文件的编码
         * 
         * @param file
         * @param det
         * @return
         * @throws FileNotFoundException
         * @throws IOException
         */
        private String guessFileEncoding(File file, nsDetector det) throws FileNotFoundException, IOException {
            // Set an observer...
            // The Notify() will be called when a matching charset is found.
            det.Init(new nsICharsetDetectionObserver() {
                public void Notify(String charset) {
                    encoding = charset;
                    found = true;
                }
            });
    
            BufferedInputStream imp = new BufferedInputStream(new FileInputStream(file));
            byte[] buf = new byte[1024];
            int len;
            boolean done = false;
            boolean isAscii = false;
    
            while ((len = imp.read(buf, 0, buf.length)) != -1) {
                // Check if the stream is only ascii.
                isAscii = det.isAscii(buf, len);
                if (isAscii) {
                    break;
                }
                // DoIt if non-ascii and not done yet.
                done = det.DoIt(buf, len, false);
                if (done) {
                    break;
                }
            }
            imp.close();
            det.DataEnd();
    
            if (isAscii) {
                encoding = "ASCII";
                found = true;
            }
    
            if (!found) {
                String[] prob = det.getProbableCharsets();
                //这里将可能的字符集组合起来返回
                for (int i = 0; i < prob.length; i++) {
                    if (i == 0) {
                        encoding = prob[i];
                    } else {
                        encoding += "," + prob[i];
                    }
                }
    
                if (prob.length > 0) {
                    // 在没有发现情况下,也可以只取第一个可能的编码,这里返回的是一个可能的序列
                    return encoding;
                } else {
                    return null;
                }
            }
            return encoding;
        }
    }

    上面是判断文件编码的demo,本人测试了一下,得到的结果还是比较靠谱的~

    上面提到的主页上还有一个HtmlCharsetDetector的demo,感兴趣的话可以去看一下。

  • 相关阅读:
    JZOJ 5870 地图
    20190921
    20190919
    SP703 SERVICE
    UVA323 Jury Compromise
    [note]一类位运算求最值问题
    [BZOJ3674]可持久化并查集
    [luogu3359]改造异或树
    [luogu4755]Beautiful Pair
    [BJWC2012]冻结
  • 原文地址:https://www.cnblogs.com/yejg1212/p/3402322.html
Copyright © 2011-2022 走看看