在做zip文件解压缩的时候碰到一个异常信息,见下面的异常详情:
java.lang.IllegalArgumentException: MALFORMED[1]
at java.util.zip.ZipCoder.toString(ZipCoder.java:65) ~[na:1.8.0_181]
at java.util.zip.ZipFile.getZipEntry(ZipFile.java:583) ~[na:1.8.0_181]
at java.util.zip.ZipFile.access$900(ZipFile.java:60) ~[na:1.8.0_181]
at java.util.zip.ZipFile$ZipEntryIterator.next(ZipFile.java:539) ~[na:1.8.0_181]
at java.util.zip.ZipFile$ZipEntryIterator.nextElement(ZipFile.java:514) ~[na:1.8.0_181]
at java.util.zip.ZipFile$ZipEntryIterator.nextElement(ZipFile.java:495) ~[na:1.8.0_181]
代码:
<!-- ZIP操作 -->
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-compress</artifactId>
<version>1.16.1</version>
</dependency>
ZipFile zipFile = new ZipFile(new File(filePath));
这种网上查下,很快定位问题,就是编码问题
然后各种查获取zip文件的编码,最多的就是cpdetector工具
https://blog.youkuaiyun.com/u014052432/article/details/79243496
pom:
<dependency> <groupId>cpdetector</groupId> <artifactId>cpdetector</artifactId> <version>1.0.10</version> </dependency>
如果下不了的自行网上下载jar到对应的本地目录内,现在网上还真不好找这个jar,我是github内找到的
代码都编写好了,进行测试,确实能获取zip文件的编码,但是异常现象依旧存在。
然后又是各种 “zip获取编码”的查找,终于发现一篇:
guying4875大神写的博客:https://blog.youkuaiyun.com/guying4875/article/details/81034022
拷贝代码测试,顺利通过
/**
*
*/
import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.BitSet;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* @author 自动识别文件编码格式
*
*/
public class EncodeUtil {
private static Logger logger = LoggerFactory.getLogger(EncodeUtil.class);
private static int BYTE_SIZE = 8;
public static String CODE_UTF8 = "UTF-8";
public static String CODE_UTF8_BOM = "UTF-8_BOM";
public static String CODE_GBK = "GBK";
/**
* 通过文件全名称获取编码集名称
*
* @param fullFileName
* @param ignoreBom
* @return
* @throws Exception
*/
public static String getEncode(String fullFileName, boolean ignoreBom) throws Exception {
logger.debug("fullFileName ; {}", fullFileName);
BufferedInputStream bis = new BufferedInputStream(new FileInputStream(fullFileName));
return getEncode(bis, ignoreBom);
}
/**
* 通过文件缓存流获取编码集名称,文件流必须为未曾
*
* @param bis
* @param ignoreBom 是否忽略utf-8 bom
* @return
* @throws Exception
*/
public static String getEncode(BufferedInputStream bis, boolean ignoreBom) throws Exception {
bis.mark(0);
String encodeType = "未识别";
byte[] head = new byte[3];
bis.read(head);
if (head[0] == -1 && head[1] == -2) {
encodeType = "UTF-16";
} else if (head[0] == -2 && head[1] == -1) {
encodeType = "Unicode";
} else if (head[0] == -17 && head[1] == -69 && head[2] == -65) { //带BOM
if (ignoreBom) {
encodeType = CODE_UTF8;
} else {
encodeType = CODE_UTF8_BOM;
}
} else if ("Unicode".equals(encodeType)) {
encodeType = "UTF-16";
} else if (isUTF8(bis)) {
encodeType = CODE_UTF8;
} else {
encodeType = CODE_GBK;
}
logger.info("result encode type : " + encodeType);
return encodeType;
}
/**
* 是否是无BOM的UTF8格式,不判断常规场景,只区分无BOM UTF8和GBK
*
* @param bis
* @return
*/
private static boolean isUTF8( BufferedInputStream bis) throws Exception {
bis.reset();
//读取第一个字节
int code = bis.read();
do {
BitSet bitSet = convert2BitSet(code);
//判断是否为单字节
if (bitSet.get(0)) {//多字节时,再读取N个字节
if (!checkMultiByte(bis, bitSet)) {//未检测通过,直接返回
return false;
}
} else {
//单字节时什么都不用做,再次读取字节
}
code = bis.read();
} while (code != -1);
return true;
}
/**
* 检测多字节,判断是否为utf8,已经读取了一个字节
*
* @param bis
* @param bitSet
* @return
*/
private static boolean checkMultiByte(BufferedInputStream bis, BitSet bitSet) throws Exception {
int count = getCountOfSequential(bitSet);
byte[] bytes = new byte[count - 1];//已经读取了一个字节,不能再读取
bis.read(bytes);
for (byte b : bytes) {
if (!checkUtf8Byte(b)) {
return false;
}
}
return true;
}
/**
* 检测单字节,判断是否为utf8
*
* @param b
* @return
*/
private static boolean checkUtf8Byte(byte b) throws Exception {
BitSet bitSet = convert2BitSet(b);
return bitSet.get(0) && !bitSet.get(1);
}
/**
* 检测bitSet中从开始有多少个连续的1
*
* @param bitSet
* @return
*/
private static int getCountOfSequential( BitSet bitSet) {
int count = 0;
for (int i = 0; i < BYTE_SIZE; i++) {
if (bitSet.get(i)) {
count++;
} else {
break;
}
}
return count;
}
/**
* 将整形转为BitSet
*
* @param code
* @return
*/
private static BitSet convert2BitSet(int code) {
BitSet bitSet = new BitSet(BYTE_SIZE);
for (int i = 0; i < BYTE_SIZE; i++) {
int tmp3 = code >> (BYTE_SIZE - i - 1);
int tmp2 = 0x1 & tmp3;
if (tmp2 == 1) {
bitSet.set(i);
}
}
return bitSet;
}
/**
* 将一指定编码的文件转换为另一编码的文件
*
* @param oldFullFileName
* @param oldCharsetName
* @param newFullFileName
* @param newCharsetName
*/
public static void convert(String oldFullFileName, String oldCharsetName, String newFullFileName, String newCharsetName) throws Exception {
logger.info("the old file name is : {}, The oldCharsetName is : {}", oldFullFileName, oldCharsetName);
logger.info("the new file name is : {}, The newCharsetName is : {}", newFullFileName, newCharsetName);
StringBuffer content = new StringBuffer();
BufferedReader bin = new BufferedReader(new InputStreamReader(new FileInputStream(oldFullFileName), oldCharsetName));
String line;
while ((line = bin.readLine()) != null) {
content.append(line);
content.append(System.getProperty("line.separator"));
}
newFullFileName = newFullFileName.replace("\\", "/");
File dir = new File(newFullFileName.substring(0, newFullFileName.lastIndexOf("/")));
if (!dir.exists()) {
dir.mkdirs();
}
Writer out = new OutputStreamWriter(new FileOutputStream(newFullFileName), newCharsetName);
out.write(content.toString());
}
}
修改后的代码:
String fileEncode = EncodeUtil.getEncode(filePath,true);
ZipFile zipFile = new ZipFile(new File(filePath), Charset.forName(fileEncode));
问题解决
再次感谢@guying4875