java实现获取文本文件的字符编码TXT和ZIP，解决zip文件读取乱码

柔光的暖阳◎ 2021-09-25 14:24 241阅读 0赞

## 获取file文件字符编码 ##

package com.file;
    
    import java.io.BufferedReader;
    import java.io.FileInputStream;
    import java.io.IOException;
    import java.io.InputStream;
    import java.io.InputStreamReader;
    
    public class CharsetCodeTest { 
    
    	public static void main(String[] args) throws Exception { 
    
    		String filePath = "D:\\1.txt";
    		String content = readTxt(filePath);
    		System.out.println(content);
    	}
    
    	public static String readTxt(String path) { 
    		StringBuilder content = new StringBuilder("");
    		try { 
    			String fileCharsetName = getFileCharsetName(path);
    			System.out.println("文件的编码格式为：" + fileCharsetName);
    			InputStream is = new FileInputStream(path);
    			InputStreamReader isr = new InputStreamReader(is, fileCharsetName);
    			BufferedReader br = new BufferedReader(isr);
    			String str = "";
    			boolean isFirst = true;
    			while (null != (str = br.readLine())) { 
    				if (!isFirst)
    					content.append(System.lineSeparator());
    				// System.getProperty("line.separator");
    				else
    					isFirst = false;
    				content.append(str);
    			}
    			br.close();
    		} catch (Exception e) { 
    			e.printStackTrace();
    			System.err.println("读取文件:" + path + "失败!");
    		}
    		return content.toString();
    	}
    	public static String getFileCharsetName(String fileName) throws IOException { 
    		InputStream inputStream = new FileInputStream(fileName);
    		byte[] head = new byte[3];
    		inputStream.read(head);
    		String charsetName = "GBK";// 或GB2312，即ANSI
    		if (head[0] == -1 && head[1] == -2) // 0xFFFE
    			charsetName = "UTF-16";
    		else if (head[0] == -2 && head[1] == -1) // 0xFEFF
    			charsetName = "Unicode";// 包含两种编码格式：UCS2-Big-Endian和UCS2-Little-Endian
    		else if (head[0] == -27 && head[1] == -101 && head[2] == -98)
    			charsetName = "UTF-8"; // UTF-8(不含BOM)
    		else if (head[0] == -17 && head[1] == -69 && head[2] == -65)
    			charsetName = "UTF-8"; // UTF-8-BOM
    		inputStream.close();
    		System.out.println(charsetName);
    		return charsetName;
    	}
    }

## 获取zip文件编码格式（解决读取乱码） ##

package com.file;
    
    import java.io.BufferedInputStream;
    import java.io.BufferedReader;
    import java.io.File;
    import java.io.FileInputStream;
    import java.io.IOException;
    import java.io.InputStream;
    import java.io.InputStreamReader;
    import java.nio.charset.Charset;
    import java.util.zip.ZipEntry;
    import java.util.zip.ZipFile;
    import java.util.zip.ZipInputStream;
    
    import info.monitorenter.cpdetector.io.ASCIIDetector;
    import info.monitorenter.cpdetector.io.CodepageDetectorProxy;
    import info.monitorenter.cpdetector.io.JChardetFacade;
    import info.monitorenter.cpdetector.io.ParsingDetector;
    import info.monitorenter.cpdetector.io.UnicodeDetector;
    /**
     * 1、cpDetector内置了一些常用的探测实现类,这些探测实现类的实例可以通过add方法加进来,
     *    ParsingDetector、 JChardetFacade、ASCIIDetector、UnicodeDetector. 
     * 2、detector按照“谁最先返回非空的探测结果,就以该结果为准”的原则. 
     * 3、cpDetector是基于统计学原理的,不保证完全正确.
     */
    public class FileCharsetDetector { 
    
        /**
         * 利用第三方开源包cpdetector获取文件编码格式.
         * @param is
         */
        public static String getFileEncode(InputStream is) { 
            //    begin     此段为zip格式文件的处理关键
            BufferedInputStream bis = null;
            if (is instanceof BufferedInputStream) { 
                bis = (BufferedInputStream) is;
            } else { 
                bis = new BufferedInputStream(is);
            }
            //   end
            CodepageDetectorProxy detector = CodepageDetectorProxy.getInstance();
            detector.add(new ParsingDetector(false));
            detector.add(UnicodeDetector.getInstance());
            detector.add(JChardetFacade.getInstance());// 内部引用了 chardet.jar的类
            detector.add(ASCIIDetector.getInstance());
            Charset charset = null;
            try { 
                charset = detector.detectCodepage(bis, Integer.MAX_VALUE);// zip 判断的关键代码
            } catch (Exception e) { 
               
            } finally { 
                if (bis != null) { 
                    try { 
                        bis.close();
                    } catch (IOException e) { 
              
                    }
                }
            }
         // 默认为GBK
            String charsetName = "GBK";
            if (charset != null) { 
                if (charset.name().equals("US-ASCII")) { 
                	charsetName = "ISO_8859_1";
                } else { 
                    charsetName = charset.name();
                }
            }
            System.out.println(charsetName);
            return charsetName;        
        }
        
        public static void main(String[] args) throws IOException { 
        	String path = "D:\\20210827092009_erqi.zip";
        	ZipFile zipFile = new ZipFile(path);
        	File file = new File(path);
        	ZipInputStream zipInput = new ZipInputStream(new FileInputStream(file));
        	ZipEntry  zipEntry = null;
        	while((zipEntry = zipInput.getNextEntry())!=null){ 
    			zipFile = new ZipFile(file);
    			InputStream inputStream = zipFile.getInputStream(zipEntry);
    			String encode=getFileEncode(inputStream);
    			BufferedReader bufferRead = new BufferedReader(new InputStreamReader(zipFile.getInputStream(zipEntry),encode));
    			String strInsert = null;
    			while((strInsert = bufferRead.readLine()) != null){ 
    				System.out.println(strInsert);
    			}
        	}
    	}
    }

jar包下载地址https://download.csdn.net/download/m0\_37987151/21615417