循环读取zip包下的所有xml文件

1、最外层为zip. 可包含多个文件夹。

2、每个文件夹中的文件可以为.gz , .zip , .xml 。 gz和xml为xml的压缩文件。

3、输出读取的xml文件

public class readXML {

public static void main(String[] args) {

try {
String path = "E:/oldbak.zip";

ZipFile zf = new ZipFile(path,Charset.forName("gbk"));

Enumeration<? extends ZipEntry> zs = zf.entries();

while (zs.hasMoreElements()) {

ZipEntry ze = zs.nextElement();
//跳过目录
if (!ze.isDirectory() && ze.getSize()>0 ) {

String name = ze.getName();

InputStream input = null;

//判断文件是否包含关键字
if(name.contains("M2000")) {

//将文件读入InputStream中
if(name.endsWith(".gz")) {
input = new GZIPInputStream(zf.getInputStream(ze));

}else if (name.endsWith(".zip")){

input = new ZipInputStream(zf.getInputStream(ze));
((ZipInputStream)input).getNextEntry();

}if(name.endsWith(".XML")) {
input = zf.getInputStream(ze);

}

//处理InputStream中的数据
HashMap<String,String> map = decode(input);
Iterator<Entry<String,String>> iter = map.entrySet().iterator();
while(iter.hasNext()){
Entry<String, String> entry= iter.next();
System.out.println(entry.getKey()+":"+entry.getValue());
}

} else{
//logger.info("文件有误");
//return null;
}


}
}

zf.close();
} catch (IOException e) {
e.printStackTrace();
}


}

public static HashMap<String,String> decode(InputStream input){

HashMap<String,String> hash = new HashMap<String,String>();
Document doc = null;
SAXReader reader = null;

try
{
reader = new SAXReader();
reader.setEncoding("GBK");

if(input == null) return null;

doc = reader.read(input);

}catch (DocumentException e)
{
e.printStackTrace();
return null;
}

if(doc == null) return null ;
Element root = doc.getRootElement();
if(root == null) return null;

Iterator syn = root.elementIterator();
while(syn.hasNext()){
Element syndata = (Element)syn.next() ;
if(syndata==null || !(syndata.getName().equals("syndata")) ) continue;

for (Iterator i = syndata.elementIterator(); i.hasNext();) {
//每解析一个class,休息一下
try {
Thread.sleep(1);
} catch (InterruptedException e) {
e.printStackTrace();
}

Element cls = (Element) i.next();
if( !(cls.getName().equals("class")) ) continue;

Iterator j = cls.elementIterator();
if( !j.hasNext() ) continue;
while(j.hasNext()){

Element table = (Element)j.next();

String tablename= table.getName();
//System.out.println(tablename);
String tablehead = "";
String tableval ="";
int N=0;

Iterator k = table.elementIterator();
if( !k.hasNext() ) continue;

Element attr = (Element)k.next();
for (Iterator l = attr.elementIterator(); l.hasNext();) {
Element node = (Element) l.next();
Iterator n = node.elementIterator();

if(!n.hasNext()){
//表头字段若为关键字，则需要替换掉 --暂时只发现desc
String str = node.getName();
if(str.equalsIgnoreCase("DESC")) str = str + "0";
if(N!=0) tablehead += ",";
tablehead += str ;
//列以逗号分隔，需要将原来数据中的逗号替换为分号
String ss = node.getText()==""?" ":node.getText();
if(ss.contains(",")) ss = ss.replace("," , ";");
if(N!=0) tableval += ",";
tableval += ss;

}else{
String value="";
Integer count=0;
while(n.hasNext()) {
Element ele = (Element) n.next();
Iterator m = ele.elementIterator();
if(!m.hasNext())continue;
Element val = (Element) m.next();
//当一列有多个数据时，以"/"分隔
if(!count.equals(0))value+="/";
value += val.getText();
count++;

}

if(N!=0) tablehead += ",";
tablehead += node.getName();
if(value=="")value=" ";
if(N!=0) tableval += ",";
tableval += value;

}
N++;
}

if(tablehead.split(",").length == tableval.split(",").length){

hash.put(tablename ,tableval);
}else{
System.out.println(tablename+":表头和表内容列数异常");
}



}
}

}

return hash;

}

}

 

转载于:https://www.cnblogs.com/seeYagain/p/9895221.html