想实现解析简历功能，用poi来解析.doc,docx,rtf,txt。
但是要过滤出来一些信息，像name,tel,email,address这些信息.(简历全是英文的)
请问大家有什么好方法、好的思路吗？？
都好长时间了，一直没有想出什么好方法来实现，请高手指教。，谢谢~
但是要过滤出来一些信息，像name,tel,email,address这些信息.(简历全是英文的)
请问大家有什么好方法、好的思路吗？？
都好长时间了，一直没有想出什么好方法来实现，请高手指教。，谢谢~
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;import org.apache.poi.poifs.filesystem.DocumentEntry;
import org.apache.poi.poifs.filesystem.DocumentInputStream;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.util.LittleEndian;public class WordExtractor {
public WordExtractor() {
} public String extractText(InputStream in) throws IOException {
ArrayList text = new ArrayList();
POIFSFileSystem fsys = new POIFSFileSystem(in); DocumentEntry headerProps = (DocumentEntry) fsys.getRoot().getEntry("WordDocument");
DocumentInputStream din = fsys.createDocumentInputStream("WordDocument");
byte[] header = new byte[headerProps.getSize()]; din.read(header);
din.close();
int info = LittleEndian.getShort(header, 0xa); boolean useTable1 = (info & 0x200) != 0; int complexOffset = LittleEndian.getInt(header, 0x1a2);
String tableName = null;
if (useTable1) {
tableName = "1Table";
} else {
tableName = "0Table";
} DocumentEntry table = (DocumentEntry) fsys.getRoot().getEntry(tableName);
byte[] tableStream = new byte[table.getSize()]; din = fsys.createDocumentInputStream(tableName); din.read(tableStream);
din.close(); din = null;
fsys = null;
table = null;
headerProps = null; int multiple = findText(tableStream, complexOffset, text); StringBuffer sb = new StringBuffer();
int size = text.size();
tableStream = null; for (int x = 0; x < size; x++) {
WordTextPiece nextPiece = (WordTextPiece) text.get(x);
int start = nextPiece.getStart();
int length = nextPiece.getLength(); boolean unicode = nextPiece.usesUnicode();
String toStr = null;
if (unicode) {
toStr = new String(header, start, length * multiple, "UTF-16LE");
} else {
toStr = new String(header, start, length, "ISO-8859-1");
}
sb.append(toStr).append(" "); }
return sb.toString();
} private static int findText(byte[] tableStream, int complexOffset, ArrayList text)
throws IOException {
//actual text
int pos = complexOffset;
int multiple = 2;
//skips through the prms before we reach the piece table. These contain data
//for actual fast saved files
while (tableStream[pos] == 1) {
pos++;
int skip = LittleEndian.getShort(tableStream, pos);
pos += 2 + skip;
}
if (tableStream[pos] != 2) {
throw new IOException("corrupted Word file");
} else {
//parse out the text pieces
int pieceTableSize = LittleEndian.getInt(tableStream, ++pos);
pos += 4;
int pieces = (pieceTableSize - 4) / 12;
for (int x = 0; x < pieces; x++) {
int filePos =
LittleEndian.getInt(tableStream, pos + ((pieces + 1) * 4) + (x * 8) + 2);
boolean unicode = false;
if ((filePos & 0x40000000) == 0) {
unicode = true;
} else {
unicode = false;
multiple = 1;
filePos &= ~(0x40000000); //gives me FC in doc stream
filePos /= 2;
}
int totLength =
LittleEndian.getInt(tableStream, pos + (x + 1) * 4)
- LittleEndian.getInt(tableStream, pos + (x * 4)); WordTextPiece piece = new WordTextPiece(filePos, totLength, unicode);
text.add(piece); } }
return multiple;
}
public static void main(String[] args){
WordExtractor w = new WordExtractor();
//POIFSFileSystem ps = new POIFSFileSystem();
try{
File file = new File("E:\\资料\\相关问题和论文.doc");
InputStream in = new FileInputStream(file);
String s = w.extractText(in);
System.out.println(s);
}catch(Exception e){
e.printStackTrace();
}
}}
class WordTextPiece {
private int _fcStart;
private boolean _usesUnicode;
private int _length; public WordTextPiece(int start, int length, boolean unicode) {
_usesUnicode = unicode;
_length = length;
_fcStart = start;
}
public boolean usesUnicode() {
return _usesUnicode;
} public int getStart() {
return _fcStart;
}
public int getLength() {
return _length;
}}俺不太懂，帮楼主顶一下。
POI是Apache的一个开源项目，可以到Apache网站下载相应的jar包文件，及其源文件。POI提供了提取一些非TXT文本中文本内容的API，比如提取Word，Excel等，使用起来非常方便。为了说明POI提起Word文件的方便和简单，通过提取一个Word文件的文本来，来了解POI API的功能。假设在本地磁盘中存在一个Word文件E:\POI\word\JBoss3.0 下配置和部署EJB简介.doc文件是具有格式的，内容如图所示：
下面看看提取它的内容是多么简单。首先从Apache网站上下载POI的相关jar包。新建一个测试类：package org.shirdrn.word;import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;import org.apache.poi.hwpf.extractor.WordExtractor;public class MyWordExtractor {public static void main(String[] args) {
File file = new File("E:\\POI\\word\\JBoss3.0 下配置和部署EJB简介.doc");
try {
FileInputStream fis = new FileInputStream(file);
WordExtractor wordExtractor = new WordExtractor(fis);
System.out.println("【 使用getText()方法提取的Word文件的内容如下所示：】");
System.out.println(wordExtractor.getText());
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}提取Word文件的文本内容，打印到控制台上，如下所示：使用WordExtractor类的getTextFromPieces()方法提取：wordExtractor.getTextFromPieces();结果和上面是一样的。WordExtractor类还有一个可以提取Word文件的各个段落的方法getParagraphText()，返回一个String[]数组，数组中每个元素为一个段的文本内容。这里，对Word文件中换行也看成是一个段，测试如下：package org.shirdrn.word;import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;import org.apache.poi.hwpf.extractor.WordExtractor;public class MyWordExtractor {public static void main(String[] args) {
File file = new File("E:\\POI\\word\\JBoss3.0 下配置和部署EJB简介.doc");
try {
FileInputStream fis = new FileInputStream(file);
WordExtractor wordExtractor = new WordExtractor(fis);
System.out.println("【 使用getText()方法提取的Word文件的内容如下所示：】");
String[] paragraph = wordExtractor.getParagraphText();
System.out.println("该Word文件共有"+paragraph.length+"段。");
for(int i=0;i<paragraph.length;i++){
System.out.println("< 第 "+(i+1)+" 段的内容为 >");
System.out.println(paragraph[i]);
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}提取Word文件的文本内容，打印到控制台上，如下所示：从上面的Word文件可以看出，最后一行是Word文件的一个换行符，使用WordExtractor提取时，也把它默认成为一个段，因为一个段结束后应该有一个回车换行符。如果有多个Word文件，而且放在不同的目录下，要提取它们的文本内容，可以实现一个递归的函数，通过深度遍历，为每一个Word文件进行提取。如果需要，可以将提取到的Word文件的文本内容输出到本地磁盘中，比如以txt记事本的根式保存。从上面可以看出，提取Word文件的文本内容，实际上是将Word文件的格式去掉了，获取到文本的内容。