Fav*_*ius 8 java compression parsing mhtml
我需要挖掘大多数已知文档文件的内容,例如:
对于我计划使用的大多数这些文件格式:
但截至目前Tika不支持MHTML(*.mht)文件..(http://en.wikipedia.org/wiki/MHTML)C#中的例子很少(http://www.codeproject.com/KB/ files/MhtBuilder.aspx)但我在Java中找不到.
我尝试在7Zip中打开*.mht文件但它失败了......虽然WinZip能够将文件解压缩为图像和文本(CSS,HTML,脚本)作为文本和二进制文件...
根据MSDN页面(http://msdn.microsoft.com/en-us/library/aa767785%28VS.85%29.aspx#compress_content)和code project我之前提到的页面... mht文件使用GZip压缩... .
尝试在java中解压缩导致以下异常:With java.uti.zip.GZIPInputStream
java.io.IOException: Not in GZIP format
at java.util.zip.GZIPInputStream.readHeader(Unknown Source)
at java.util.zip.GZIPInputStream.<init>(Unknown Source)
at java.util.zip.GZIPInputStream.<init>(Unknown Source)
at GZipTest.main(GZipTest.java:16)
与 java.util.zip.ZipFile
java.util.zip.ZipException: error in opening zip file
at java.util.zip.ZipFile.open(Native Method)
at java.util.zip.ZipFile.<init>(Unknown Source)
at java.util.zip.ZipFile.<init>(Unknown Source)
at GZipTest.main(GZipTest.java:21)
请建议如何解压缩....
谢谢....
Fav*_*ius 13
坦率地说,我不期待在不久的将来找到解决方案并且即将放弃,但有些我偶然发现了这个页面:
http://en.wikipedia.org/wiki/MIME#Multipart_messages
http://msdn.microsoft.com/en-us/library/ms527355%28EXCHG.10%29.aspx
虽然,第一眼看上去并不是很吸引人.但如果仔细观察,你会得到线索.阅读本文后,我启动了我的IE并随机开始将页面保存为*.mht文件.让我一行一行......
不过,让我先解释一下,我的最终目标是分离/解压出来的html内容,并解析它......因为它取决于该解决方案本身并不完整character set或encoding我选择,同时节省.但即使它会轻微提取单个文件......
我希望这对任何试图解析/解压缩*.mht/MHTML文件的人都有用:)
=======解释========**取自mht文件**
From: "Saved by Windows Internet Explorer 7"
它是用于保存文件的软件
Subject: Google
Date: Tue, 13 Jul 2010 21:23:03 +0530
MIME-Version: 1.0
主题,日期和哑剧版......很像邮件格式
Content-Type: multipart/related;
type="text/html";
这是告诉我们它是一份multipart文件的部分.多部分文档在一个主体中组合了一个或多个不同的数据集,multipartContent-Type字段必须出现在实体的标题中.在这里,我们也可以看到类型为"text/html".
boundary="----=_NextPart_000_0007_01CB22D1.93BBD1A0"
最重要的是,这是最重要的部分.这是唯一的分隔符,它分为两个不同的部分(html,图像,css,脚本等).一旦你掌握了这一点,一切都变得简单......现在,我只需要遍历文档并查找不同的部分并按照它们Content-Transfer-Encoding(base64,quoted-printable等)保存它们.... ..
样品
------=_NextPart_000_0007_01CB22D1.93BBD1A0
Content-Type: text/html;
charset="utf-8"
Content-Transfer-Encoding: quoted-printable
Content-Location: http://www.google.com/webhp?sourceid=navclient&ie=UTF-8
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" =
.
.
.
**JAVA代码**
用于定义常量的接口.
public interface IConstants
{
public String BOUNDARY = "boundary";
public String CHAR_SET = "charset";
public String CONTENT_TYPE = "Content-Type";
public String CONTENT_TRANSFER_ENCODING = "Content-Transfer-Encoding";
public String CONTENT_LOCATION = "Content-Location";
public String UTF8_BOM = "=EF=BB=BF";
public String UTF16_BOM1 = "=FF=FE";
public String UTF16_BOM2 = "=FE=FF";
}
主解析器类......
/**
* This program and the accompanying materials are made available under the terms of the Eclipse Public License v1.0
* which accompanies this distribution, and is available at
* http://www.eclipse.org/legal/epl-v10.html
*/
package com.test.mht.core;
import java.io.BufferedOutputStream;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileOutputStream;
import java.io.FileReader;
import java.io.OutputStreamWriter;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import sun.misc.BASE64Decoder;
/**
* File to parse and decompose *.mts file in its constituting parts.
* @author Manish Shukla
*/
public class MHTParser implements IConstants
{
private File mhtFile;
private File outputFolder;
public MHTParser(File mhtFile, File outputFolder) {
this.mhtFile = mhtFile;
this.outputFolder = outputFolder;
}
/**
* @throws Exception
*/
public void decompress() throws Exception
{
BufferedReader reader = null;
String type = "";
String encoding = "";
String location = "";
String filename = "";
String charset = "utf-8";
StringBuilder buffer = null;
try
{
reader = new BufferedReader(new FileReader(mhtFile));
final String boundary = getBoundary(reader);
if(boundary == null)
throw new Exception("Failed to find document 'boundary'... Aborting");
String line = null;
int i = 1;
while((line = reader.readLine()) != null)
{
String temp = line.trim();
if(temp.contains(boundary))
{
if(buffer != null) {
writeBufferContentToFile(buffer,encoding,filename,charset);
buffer = null;
}
buffer = new StringBuilder();
}else if(temp.startsWith(CONTENT_TYPE)) {
type = getType(temp);
}else if(temp.startsWith(CHAR_SET)) {
charset = getCharSet(temp);
}else if(temp.startsWith(CONTENT_TRANSFER_ENCODING)) {
encoding = getEncoding(temp);
}else if(temp.startsWith(CONTENT_LOCATION)) {
location = temp.substring(temp.indexOf(":")+1).trim();
i++;
filename = getFileName(location,type);
}else {
if(buffer != null) {
buffer.append(line + "\n");
}
}
}
}finally
{
if(null != reader)
reader.close();
}
}
private String getCharSet(String temp)
{
String t = temp.split("=")[1].trim();
return t.substring(1, t.length()-1);
}
/**
* Save the file as per character set and encoding
*/
private void writeBufferContentToFile(StringBuilder buffer,String encoding, String filename, String charset)
throws Exception
{
if(!outputFolder.exists())
outputFolder.mkdirs();
byte[] content = null;
boolean text = true;
if(encoding.equalsIgnoreCase("base64")){
content = getBase64EncodedString(buffer);
text = false;
}else if(encoding.equalsIgnoreCase("quoted-printable")) {
content = getQuotedPrintableString(buffer);
}
else
content = buffer.toString().getBytes();
if(!text)
{
BufferedOutputStream bos = null;
try
{
bos = new BufferedOutputStream(new FileOutputStream(filename));
bos.write(content);
bos.flush();
}finally {
bos.close();
}
}else
{
BufferedWriter bw = null;
try
{
bw = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(filename), charset));
bw.write(new String(content));
bw.flush();
}finally {
bw.close();
}
}
}
/**
* When the save the *.mts file with 'utf-8' encoding then it appends '=EF=BB=BF'</br>
* @see http://en.wikipedia.org/wiki/Byte_order_mark
*/
private byte[] getQuotedPrintableString(StringBuilder buffer)
{
//Set<String> uniqueHex = new HashSet<String>();
//final Pattern p = Pattern.compile("(=\\p{XDigit}{2})*");
String temp = buffer.toString().replaceAll(UTF8_BOM, "").replaceAll("=\n", "");
//Matcher m = p.matcher(temp);
//while(m.find()) {
// uniqueHex.add(m.group());
//}
//System.out.println(uniqueHex);
//for (String hex : uniqueHex) {
//temp = temp.replaceAll(hex, getASCIIValue(hex.substring(1)));
//}
return temp.getBytes();
}
/*private String getASCIIValue(String hex) {
return ""+(char)Integer.parseInt(hex, 16);
}*/
/**
* Although system dependent..it works well
*/
private byte[] getBase64EncodedString(StringBuilder buffer) throws Exception {
return new BASE64Decoder().decodeBuffer(buffer.toString());
}
/**
* Tries to get a qualified file name. If the name is not apparent it tries to guess it from the URL.
* Otherwise it returns 'unknown.<type>'
*/
private String getFileName(String location, String type)
{
final Pattern p = Pattern.compile("(\\w|_|-)+\\.\\w+");
String ext = "";
String name = "";
if(type.toLowerCase().endsWith("jpeg"))
ext = "jpg";
else
ext = type.split("/")[1];
if(location.endsWith("/")) {
name = "main";
}else
{
name = location.substring(location.lastIndexOf("/") + 1);
Matcher m = p.matcher(name);
String fname = "";
while(m.find()) {
fname = m.group();
}
if(fname.trim().length() == 0)
name = "unknown";
else
return getUniqueName(fname.substring(0,fname.indexOf(".")), fname.substring(fname.indexOf(".") + 1, fname.length()));
}
return getUniqueName(name,ext);
}
/**
* Returns a qualified unique output file path for the parsed path.</br>
* In case the file already exist it appends a numarical value a continues
*/
private String getUniqueName(String name,String ext)
{
int i = 1;
File file = new File(outputFolder,name + "." + ext);
if(file.exists())
{
while(true)
{
file = new File(outputFolder, name + i + "." + ext);
if(!file.exists())
return file.getAbsolutePath();
i++;
}
}
return file.getAbsolutePath();
}
private String getType(String line) {
return splitUsingColonSpace(line);
}
private String getEncoding(String line){
return splitUsingColonSpace(line);
}
private String splitUsingColonSpace(String line) {
return line.split(":\\s*")[1].replaceAll(";", "");
}
/**
* Gives you the boundary string
*/
private String getBoundary(BufferedReader reader) throws Exception
{
String line = null;
while((line = reader.readLine()) != null)
{
line = line.trim();
if(line.startsWith(BOUNDARY)) {
return line.substring(line.indexOf("\"") + 1, line.lastIndexOf("\""));
}
}
return null;
}
}
问候,