sooba xpdf lucene

XPDF使用文档
XPDF版本 3.0.2
日期 2008-11-26
文档版本 V1.0

1、概述
读取PDF文件中的文本内容，可以使用开源项目xpdf。下载地址：http://www.foolabs.com/xpdf/download.html。
注意使用：xpdf-3.02pl2-win32.zip以及xpdf-chinese-simplified.tar.gz（支持中文）。

2、安装
将xpdf-3.02pl2-win32.zip解压缩到D盘xpdf目录下，我们将以d:\xpdf作为xpdf的工作路径。
将xpdf-chinese-simplified.tar解压缩到xpdf根目录下的xpdf-chinese-simplified目录中。
为了启用中文简体语言包，您必须将xpdf目录下的sample-xpdfrc文件另存为xpdfrc文件。
注意：此文件为配置文件，而且名称必须是xpdfrc。如果是别的名字，即使调用pdftotext.exe时，传入”-cfg xpdfrc2”来告诉xpdf配置文件的名字，好像pdftotext.exe也并没有使用这个配置文件。所以为了减少误解，请您将配置文件直接命名为xpdfrc。
并在这个xpdfrc文件最后加上以下配置，注意Map文件的路径一定要正确。

Java代码
#----- begin Chinese Simplified support package (2004-jul-27)
cidToUnicode Adobe-GB1 D:/xpdf/ xpdf-chinese-simplified/Adobe-GB1.cidToUnicode
unicodeMap ISO-2022-CN D:/xpdf/ xpdf-chinese-simplified/ISO-2022-CN.unicodeMap
unicodeMap EUC-CN D:/xpdf/xpdf-chinese-simplified/EUC-CN.unicodeMap
unicodeMap GBK D:/xpdf/xpdf-chinese-simplified/GBK.unicodeMap
cMapDir Adobe-GB1 D:/xpdf/xpdf-chinese-simplified/Cmap
toUnicodeDir D:/xpdf/xpdf-chinese-simplified/Cmap
#displayCIDFontTT Adobe-GB1 /usr/..../gkai00mp.ttf
#----- end Chinese Simplified support package

#----- begin Chinese Simplified support package (2004-jul-27)
cidToUnicode Adobe-GB1 D:/xpdf/ xpdf-chinese-simplified/Adobe-GB1.cidToUnicode
unicodeMap ISO-2022-CN D:/xpdf/ xpdf-chinese-simplified/ISO-2022-CN.unicodeMap
unicodeMap EUC-CN D:/xpdf/xpdf-chinese-simplified/EUC-CN.unicodeMap
unicodeMap GBK D:/xpdf/xpdf-chinese-simplified/GBK.unicodeMap
cMapDir Adobe-GB1 D:/xpdf/xpdf-chinese-simplified/Cmap
toUnicodeDir D:/xpdf/xpdf-chinese-simplified/Cmap
#displayCIDFontTT Adobe-GB1 /usr/..../gkai00mp.ttf
#----- end Chinese Simplified support package另外，配置文件中原先没有加上一个“textPageBreaks”控制。为了避免这个分页符号，我们需要在xpdfrc文件“text output control”下面加上这么一段话：
Java代码
# If set to "yes", text extraction will insert page
# breaks (form feed characters) between pages. This
# defaults to "yes".
textPageBreaks no

# If set to "yes", text extraction will insert page
# breaks (form feed characters) between pages. This
# defaults to "yes".
textPageBreaks no
设置textPageBreaks为no的意思是：在PDF文档的两页之间不加入分页符号。之所以这样，是因为这个符号有时候会引起SAX解析XML上的困难。
配置文件中原先把textEncoding注释了。这样默认的字符集是Latin1。我们必须打开它
Java代码
#textEncoding UTF-8
textEncoding GBK

#textEncoding UTF-8
textEncoding GBK
3、命令行调用
D:\xpdf\xpdf-3.02pl2-win32>pdftotext.exe -cfg xpdfrc d:\dwr中文文档(pdf).pdf

4、JAVA调用示范
pdftotext.exe的运行参数中，

Java代码
private String excuteStr = "D:\\xpdf\\xpdf-3.02pl2-win32\\pdftotext.exe";

public String getContent() {
String[] cmd = new String[] { excuteStr, "-enc", "UTF-8", "-q", file.getAbsolutePath(),"-" };

Process p = null;
BufferedInputStream bis = null ;
InputStreamReader reader = null;
StringBuffer sb = null;
BufferedReader br = null;

try {
p = Runtime.getRuntime().exec(cmd);
bis = new BufferedInputStream(p.getInputStream());
reader = new InputStreamReader(bis, "UTF-8");

sb = new StringBuffer();
br = new BufferedReader(reader);
String line = br.readLine();
sb = new StringBuffer();
while (line != null) {
System.out.println(line);
sb.append(line);
sb.append(" ");
line = br.readLine();
}

} catch (IOException e) {
e.printStackTrace();
} finally {
try {
br.close() ;
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

content = sb.toString() ;

return content ;
}

private String excuteStr = "D:\\xpdf\\xpdf-3.02pl2-win32\\pdftotext.exe";

public String getContent() {
String[] cmd = new String[] { excuteStr, "-enc", "UTF-8", "-q", file.getAbsolutePath(),"-" };

Process p = null;
BufferedInputStream bis = null ;
InputStreamReader reader = null;
StringBuffer sb = null;
BufferedReader br = null;

try {
p = Runtime.getRuntime().exec(cmd);
bis = new BufferedInputStream(p.getInputStream());
reader = new InputStreamReader(bis, "UTF-8");

sb = new StringBuffer();
br = new BufferedReader(reader);
String line = br.readLine();
sb = new StringBuffer();
while (line != null) {
System.out.println(line);
sb.append(line);
sb.append(" ");
line = br.readLine();
}

} catch (IOException e) {
e.printStackTrace();
} finally {
try {
br.close() ;
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

content = sb.toString() ;

return content ;
}
一个应用的demo
Java代码
package com.cs;

public interface Parsable {

public String getTitle() ;
public String getContent() ;
public String getSummary() ;
}

package com.cs;

public interface Parsable {

public String getTitle() ;
public String getContent() ;
public String getSummary() ;
}

Java代码
package com.cs;

import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.File;
import java.io.IOException;
import java.io.InputStreamReader;

public class PdfParser implements Parsable {
private File file ;
private String content ;//内容

/*
* pdf解读需配置
*/
private String executeStr = "E:\\EclipseStudyWorkspace\\LuceneParse\\xpdf\\xpdf-3.02pl2-win32\\pdftotext.exe" ;

public PdfParser(File file){
this.file = file ;
}

public String getContent(){

if (content != null){
return content ;
}

String[] cmd = new String[]{executeStr,"-enc","UTF-8","-q",file.getAbsolutePath(),"-"} ;
Process p = null ;


BufferedReader br = null ;
StringBuffer sb = new StringBuffer() ;
try {
p = Runtime.getRuntime().exec(cmd) ;

br = new BufferedReader(new InputStreamReader(p.getInputStream(),"UTF-8")) ;

String str = null ;
while((str = br.readLine() ) != null ){
sb.append(str).append("\n") ;
}

} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally{
if (br != null){
try {
br.close() ;
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
content = sb.toString() ;

return content ;
}

public String getSummary() {
String summary ;
if (content == null ) {
getContent() ;
}

if (content.length() > 200) {
summary = content.substring(0, 200) ;
}else {
summary = content ;
}

return summary;
}

public String getTitle(){
return file.getName() ;
}

public static void main(String[] args){
PdfParser parser = new PdfParser(new File("E:\\EclipseStudyWorkspace\\LuceneParse\\fileSource\\123.pdf")) ;
System.out.println("pdf content : "+parser.getContent()) ;
}
}

package com.cs;

import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.File;
import java.io.IOException;
import java.io.InputStreamReader;

public class PdfParser implements Parsable {
private File file ;
private String content ;//内容

/*
* pdf解读需配置
*/
private String executeStr = "E:\\EclipseStudyWorkspace\\LuceneParse\\xpdf\\xpdf-3.02pl2-win32\\pdftotext.exe" ;

public PdfParser(File file){
this.file = file ;
}

public String getContent(){

if (content != null){
return content ;
}

String[] cmd = new String[]{executeStr,"-enc","UTF-8","-q",file.getAbsolutePath(),"-"} ;
Process p = null ;


BufferedReader br = null ;
StringBuffer sb = new StringBuffer() ;
try {
p = Runtime.getRuntime().exec(cmd) ;

br = new BufferedReader(new InputStreamReader(p.getInputStream(),"UTF-8")) ;

String str = null ;
while((str = br.readLine() ) != null ){
sb.append(str).append("\n") ;
}

} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally{
if (br != null){
try {
br.close() ;
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
content = sb.toString() ;

return content ;
}

public String getSummary() {
String summary ;
if (content == null ) {
getContent() ;
}

if (content.length() > 200) {
summary = content.substring(0, 200) ;
}else {
summary = content ;
}

return summary;
}

public String getTitle(){
return file.getName() ;
}

public static void main(String[] args){
PdfParser parser = new PdfParser(new File("E:\\EclipseStudyWorkspace\\LuceneParse\\fileSource\\123.pdf")) ;
System.out.println("pdf content : "+parser.getContent()) ;
}
}


项目的结构
-projectName
------------src
------------webroot
------------xpdf
----xpdf-3.02pl2-win32
----xpdf-chinese-simplified