HTTP协议文本解析

编程语言 2018-05-10 08:28:30 阅读次数: 1

HTTP消息是由普通ASCII文本组成。消息包括消息头和数据体部分。消息头以行为单位，每行以CRLF（回车和换行）结束，消息头结束后，额外增加一个CRLF，之后内容就是数据体部分了。

格式如图：

                                                          http协议格式

那么如果给了一段文本 http文本  我们是否有能力用java解析呢：

GET /doaction?p=123&k=3343 HTTP/1.1
Host: localhost:12345
Connection: keep-alive
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8
User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36
Accept-Encoding: gzip, deflate, sdch
Accept-Language: zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4
Cookie: name=jackey;

  下面是我用java解析这段的http协议的一段代码

import java.io.IOException;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
/**
 * http协议解析
 * @author Mic
 *
 */
public class HttpOperator {
	/**
	 * 协议流
	 */
   private InputStream source;
   private  byte[] buf;//缓存结果
   private  int pos;//偏移
   private int start;//开始
   private int end;//结束
   private int capacity;//缓存容量
   private int lastValid;//每次取数据buf中最有一位字节的下标
   private Request request=new Request();
   public enum METHOD{
	   GET,HEAD,POST,OPTIONS,PUT,Delete,TRACE,CONNECT
   }
   public HttpOperator(int capacity) {
	 pos=0;
	 start=0;
	 end=0;
	 lastValid=-1;
	 this.capacity=capacity;
	 buf=new byte[capacity];
   }
   public HttpOperator() {
       this(4096);
   }
   /**
    *填充缓存
    */
   public boolean  fill(){
	   return fill(buf, 0, capacity);
   }
   public boolean fill(byte[] buf,int offset,int length){
	   int len=-1;
	   try {
		 len=source.read(buf, offset, length);	   
	   }catch (IOException e) {
		  System.out.println("read source failed");
		  return false;
	   }
	   start=0;
	   end=0;
	   lastValid=len==-1?-1:len-1;
	   return len!=-1;
   
   }
   public void skipSpace(){
	   do{		  
		   if(pos>=lastValid){
			   fill();
			   pos=-1;
		   }
		   pos++;
	   }while(buf[pos]==Constant.SP||buf[pos]==Constant.HT);
   }
   
   
   public void  copy(byte[] src ,int srcOff,byte[] dest,int destOff,int len){
	  //扩容
	  if((dest.length-destOff)<len){
	    byte[] newDest=new byte[dest.length*2];
	         System.arraycopy(dest, 0, newDest, 0, dest.length);
	         dest=newDest;
	  }
	  System.arraycopy(src, srcOff, dest, destOff, len);
   }
   
   
   public void parseRequestLine(){
	   boolean quit=false;
	   while(!quit){
		   skipSpace();
		   //Method
		   byte[] v_buf=new byte[1024];
		   int v_pos=0;
		   int v_len=0;
		   start=pos;
		   while(true){
			   if(buf[pos]==Constant.SP||buf[pos]==Constant.HT){
				   copy(buf, start,v_buf,v_pos,pos-start);
				   v_pos+=(pos-start);
				   v_len+=(pos-start);
				   break;
			   }   
			   end=pos;
			   pos++;
			   //判断是否用完
			  if(pos>=lastValid){
				  copy(buf, start,v_buf,v_pos,pos-start);
				  v_pos+=(pos-start);
				  v_len+=(pos-start);
				  start=pos=end=0;
				  fill();
			  }
		   }
			  try {
				request.setMethod(new String(v_buf,0,v_len,"UTF-8"));
			} catch (UnsupportedEncodingException e) {
				 System.out.println("set method failed");
				 throw  new RuntimeException(e);
			}
		
			  
		  //URI
			v_buf=new byte[1024];
			v_pos=0;
			pos--;
			skipSpace();
			start=pos;
			v_len=0;
			while(true){
				   if(buf[pos]==Constant.SP||buf[pos]==Constant.HT){
					   copy(buf, start,v_buf,v_pos,pos-start);
					   v_pos+=(pos-start);
					   v_len+=(pos-start);
					   break;
				   }   
				   end=pos;
				   pos++;
				   //判断是否用完
				  if(pos>=lastValid){
					  copy(buf, start,v_buf,v_pos,pos-start);
					  v_pos+=(pos-start);
					  v_len+=(pos-start);
					  start=pos=end=0;
					  fill();
				  }
			   }
			   try {
					request.setUri(new String(v_buf,0,v_len,"UTF-8"));
				} catch (UnsupportedEncodingException e) {
					 System.out.println("set URI failed");
					 throw  new RuntimeException(e);
				}
			   
			   //协议版本如HTTP/1.1
				v_buf=new byte[1024];
				v_pos=0;
				pos--;
				skipSpace();
				start=pos;
				v_len=0;
				while(true){
					   if(buf[pos]==Constant.LF||buf[end]==Constant.CR){
						   copy(buf, start,v_buf,v_pos,end-start);
						   v_pos+=(pos-start);
						   v_len+=(end-start);
						   quit=true;
						   break;
					   }else if(buf[pos]==Constant.HT||buf[pos]==Constant.SP){
						   skipSpace();
						   continue;
					   }
					   
					   end=pos;
					   pos++;
					   //判断是否用完
					  if(pos>=lastValid){
						  copy(buf, start,v_buf,v_pos,pos-start);
						  v_pos+=(pos-start);
						  v_len+=(pos-start);
						  start=pos=end=0;
						  fill();
					  }
				   }
					  try {
						request.setHttpVersion(new String(v_buf,0,v_len,"UTF-8"));
					} catch (UnsupportedEncodingException e) {
						 System.out.println("set HttpVersion failed");
						 throw  new RuntimeException(e);
					}
				
		   }
}
   public void parseRequestHeaders(){
	   while(parseRequestHeader()){
		   
	   }
   }
   private boolean parseRequestHeader(){
	   boolean quit=true;
		   skipSpace();
		   //Method
		   byte[] v_buf=new byte[1024];
		   int v_pos=0;
		   int v_len=0;
		   start=pos;
		   //name
		   HttpHeader httpHeader=null;
		   while(true){
			   if(buf[pos]==Constant.COLON){
				   copy(buf, start,v_buf,v_pos,pos-start);
				   v_pos+=(pos-start);
				   v_len+=(pos-start);
				   break;
			   }   
			   end=pos;
			   pos++;
			   //判断是否用完
			  if(pos>=lastValid){
				  copy(buf, start,v_buf,v_pos,pos-start);
				  v_pos+=(pos-start);
				  v_len+=(pos-start);
				  start=pos=end=0;
				  fill();
			  }
		   }
		   try {
			httpHeader=HttpHeader.addHeaderName(new String(v_buf,0,v_len,"UTF-8"));
		} catch (UnsupportedEncodingException e1) {
		    return false;
		}
	     //Value
				v_buf=new byte[1024];
				v_pos=0;
				skipSpace();
				start=pos;
				v_len=0;
				while(true){
					   if(buf[pos]==Constant.LF||buf[end]==Constant.CR){
						   copy(buf, start,v_buf,v_pos,end-start);
						   v_pos+=(pos-start);
						   v_len+=(end-start);
						   break;
					   }else if(buf[pos]==Constant.HT||buf[pos]==Constant.SP){
						   skipSpace();
						   continue;
					   }
					   
					   end=pos;
					   pos++;
					   //判断是否用完
					  if(pos>=lastValid){
						  copy(buf, start,v_buf,v_pos,pos-start);
						  v_pos+=(pos-start);
						  v_len+=(pos-start);
						  start=pos=end=0;
						  fill();
					  }
				   }
			 try {
				   httpHeader.setValue(new String(v_buf,0,v_len,"UTF-8"));
			 	} catch (UnsupportedEncodingException e) {
						 System.out.println("set HttpVersion failed");
						 throw  new RuntimeException(e);
		  }
			 request.addHeader(httpHeader);
			 //是否完成
			if(pos>=lastValid){
				  start=pos=end=0;
				  fill();
			}
			if(buf[pos+1]==Constant.CR||buf[pos+2]==Constant.LF){
				quit=false;
				pos+=3;
			}
	   return quit;
}
 
  public void parseRequestBody(){
    	if(pos<=lastValid){
    		byte[] body=new byte[1024];
    		copy(buf, pos,body,0,lastValid-pos+1);
    		while(fill(buf, 0, capacity)){
    			  copy(buf, 0,body,0,lastValid+1);	
    		}
    		request.setBody(body);
    	} 
    	
  }
   
   
public InputStream getSource() {
	return source;
}
public void setSource(InputStream source) {
	this.source = source;
}
public Request getRequest() {
	return request;
}
public void setRequest(Request request) {
	this.request = request;
}
	   
	   
   }

 HttpOperator 用来来解析http协议的一个类，其中三个关键方法：parseRequestLine 请求行的解析，parseRequestHeaders 请求头解析，parseRequestBody请求包体解析

而解析后的内容用Request来封装

import java.io.Serializable;
import java.util.ArrayList;
import java.util.List;

/**
 * 所获得的请求
 * @author Mic
 *
 */
public class Request implements Serializable{
 //请求方法
 private String method;
 //协议版本
 private String httpVersion;
 //uri
 private String uri;
 //域头
 private List<HttpHeader> httpheaders;
 //body
 private byte[] body;
public String getMethod() {
	return method;
}
public void setMethod(String method) {
	this.method = method;
}

public String getHttpVersion() {
	return httpVersion;
}
public void setHttpVersion(String httpVersion) {
	this.httpVersion = httpVersion;
}
public String getUri() {
	return uri;
}
public void setUri(String uri) {
	this.uri = uri;
}
public List<HttpHeader> getHttpheaders() {
	return httpheaders;
}
public void setHttpheaders(List<HttpHeader> httpheaders) {
	this.httpheaders = httpheaders;
}
public byte[] getBody() {
	return body;
}
public void setBody(byte[] body) {
	this.body = body;
}
 
public void addHeader(HttpHeader header){
	if(httpheaders==null) httpheaders=new ArrayList<HttpHeader>();
	httpheaders.add(header);
}
public void addHeader(String name,Object value){
	if(httpheaders==null) httpheaders=new ArrayList<HttpHeader>();
	httpheaders.add(new HttpHeader(name,value));
}
}

 下面是其他的一些附加类

public class Constant {
  /**
  * CRLF.
  */
  public final static String CRLF="\r\n";
  /**
   * CR.
   */
  public final static byte CR=(byte)'\r';
  /**
   * LF
   */
  public final static byte LF=(byte) '\n';
  /**
   * SP.
   */
  public final static byte SP=(byte) ' ';
  /**
   * HT.
   */
  public final static byte HT=(byte) '\t';
  /**
   * COLON.
   */
  public final static byte COLON=(byte) ':';
  /**
   * SEMI_COLON
   */
  public final static byte SEMI_COLON=(byte) ';';
  

  /**
   * 'A'.
   */
  public static final byte A = (byte) 'A';


  /**
   * 'a'.
   */
  public static final byte a = (byte) 'a';


  /**
   * 'Z'.
   */
  public static final byte Z = (byte) 'Z';

public class HttpHeader {
  private String name;//域头名
  private Object value;//域头值
  public String getName() {
		return name;
  }
  
  public HttpHeader(String name, Object value) {
	super();
	this.name = name;
	this.value = value;
}

public HttpHeader(String name) {
	super();
	this.name = name;
}

public void setName(String name) {
		this.name = name;
   }
   public Object getValue() {
		return value;
   }
   public void setValue(Object value) {
		this.value = value;
  }
  public static HttpHeader addHeaderName(String name){
	  return new HttpHeader(name);
  }

@Override
public String toString() {
	return "HttpHeader [name=" + name + ", value=" + value + "]";
}
 
}

 通过上述类我做了一段测试代码如下：

import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.util.Arrays;
import java.util.List;

import org.junit.Before;
import org.junit.Test;

public class HttpOperatorTest {
	HttpOperator operator;
	@Before
	public void setup() throws FileNotFoundException{
		operator=new HttpOperator(1024);
		FileInputStream fis=new FileInputStream(new File(System.getProperty("user.dir"),"resource/httpRequest.txt"));
		operator.setSource(fis);
	}
	@Test
	public void test() {
	    operator.parseRequestLine();
	    Request request=operator.getRequest();
	    System.out.println("Method:"+request.getMethod());
	    System.out.println("URI:"+request.getUri());
	    System.out.println("HttpVersion:"+request.getHttpVersion());
	    System.out.println("=====================parseHeaders=====");
	    operator.parseRequestHeaders();
	   List<HttpHeader> httpHeaders=request.getHttpheaders();
	   if(httpHeaders!=null&&! httpHeaders.isEmpty()){
		   for(HttpHeader header:httpHeaders)
			   System.out.println(header.getName()+":"+header.getValue());
	   }
	   operator.parseRequestBody();
	   System.out.println("=====================parseBody=====");
	   System.out.println(Arrays.toString(request.getBody()));
	}

}

 测试结果如下：

测试结果 写道
Method:GET
URI:/doaction?p=123&k=3343
HttpVersion:HTTP/1.1
=====================parseHeaders=====
Host:localhost:12345
Connection:keep-alive
Accept:text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8
User-Agent:Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36
Accept-Encoding:gzip, deflate, sdch
Accept-Language:zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4
Cookie:name=jackey;
=====================parseBody=====
null

猜你喜欢

转载自584431411.iteye.com/blog/2377204
今日推荐
TIOBE 5 月榜单：Fortran “复活”进入 Top 10
GCC 14.1 发布
面壁智能发布 Eurux-8x22B 开源大模型 —— 堪称「理科状元」
开源日报 | 谷歌扶持鸿蒙上位；开源Rabbit R1；Docker加持的安卓手机；微软的焦虑和野心；海尔电器把开放平台关了
中国码农的“35岁魔咒”
蘭雅 CorelDRAW 插件 2024.5.1 国际劳动节版，免费下载
Arc Browser for Windows 1.0 正式 GA
90后程序员开发视频搬运软件、不到一年获利超 700 万，结局很刑！
周排行
Java自定义时间格式
同步整形电路
在开发中最最最常用的字符串的属性大集合
Linux 查看端口占用并杀掉
Java基础四：ArrayList
多线程之死锁就是这么简单
mysql 基础命令集
awk 命令详解
Centos6.3编译安装nginx+php步骤
OCR （Optical Character Recognition，光学字符识别）
每日归档
更多
2024-05-08(42)
2024-05-07(14)
2024-05-06(40)
2024-05-05(0)
2024-05-04(7)
2024-05-03(19)
2024-05-02(0)
2024-05-01(4)
2024-04-30(1)
2024-04-29(40)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022