POI 关于对 ms word的读写代码

Java代码

1. publicclassWordExtractor{
2. publicWordExtractor(){
3. }
5. publicStringextractText(InputStreamin)throwsIOException{
6. ArrayListtext=newArrayList();
7. POIFSFileSystemfsys=newPOIFSFileSystem(in);
9. DocumentEntryheaderProps=(DocumentEntry)fsys.getRoot().getEntry("WordDocument");
10. DocumentInputStreamdin=fsys.createDocumentInputStream("WordDocument");
11. byte[]header=newbyte[headerProps.getSize()];
13. din.read(header);
14. din.close();
15. //Prendeleinformazionidall'headerdeldocumento
16. intinfo=LittleEndian.getShort(header,0xa);
18. booleanuseTable1=(info&0x200)!=0;
20. //booleanuseTable1=true;
22. //Prendeinformazionidallapiecetable
23. intcomplexOffset=LittleEndian.getInt(header,0x1a2);
24. //intcomplexOffset=LittleEndian.getInt(header);
26. StringtableName=null;
27. if(useTable1){
28. tableName="1Table";
29. }else{
30. tableName="0Table";
31. }
33. DocumentEntrytable=(DocumentEntry)fsys.getRoot().getEntry(tableName);
34. byte[]tableStream=newbyte[table.getSize()];
36. din=fsys.createDocumentInputStream(tableName);
38. din.read(tableStream);
39. din.close();
41. din=null;
42. fsys=null;
43. table=null;
44. headerProps=null;
46. intmultiple=findText(tableStream,complexOffset,text);
48. StringBuffersb=newStringBuffer();
49. intsize=text.size();
50. tableStream=null;
52. for(intx=0;x<size;x++){
54. WordTextPiecenextPiece=(WordTextPiece)text.get(x);
55. intstart=nextPiece.getStart();
56. intlength=nextPiece.getLength();
58. booleanunicode=nextPiece.usesUnicode();
59. StringtoStr=null;
60. if(unicode){
61. toStr=newString(header,start,length*multiple,"UTF-16LE");
62. }else{
63. toStr=newString(header,start,length,"ISO-8859-1");
64. }
65. sb.append(toStr).append("");
67. }
68. returnsb.toString();
69. }
71. privatestaticintfindText(byte[]tableStream,intcomplexOffset,ArrayListtext)
72. throwsIOException{
73. //actualtext
74. intpos=complexOffset;
75. intmultiple=2;
76. //skipsthroughtheprmsbeforewereachthepiecetable.Thesecontaindata
77. //foractualfastsavedfiles
78. while(tableStream[pos]==1){
79. pos++;
80. intskip=LittleEndian.getShort(tableStream,pos);
81. pos+=2+skip;
82. }
83. if(tableStream[pos]!=2){
84. thrownewIOException("corruptedWordfile");
85. }else{
86. //parseoutthetextpieces
87. intpieceTableSize=LittleEndian.getInt(tableStream,++pos);
88. pos+=4;
89. intpieces=(pieceTableSize-4)/12;
90. for(intx=0;x<pieces;x++){
91. intfilePos=
92. LittleEndian.getInt(tableStream,pos+((pieces+1)*4)+(x*8)+2);
93. booleanunicode=false;
94. if((filePos&0x40000000)==0){
95. unicode=true;
96. }else{
97. unicode=false;
98. multiple=1;
99. filePos&=~(0x40000000);//givesmeFCindocstream
100. filePos/=2;
101. }
102. inttotLength=
103. LittleEndian.getInt(tableStream,pos+(x+1)*4)
104. -LittleEndian.getInt(tableStream,pos+(x*4));
106. WordTextPiecepiece=newWordTextPiece(filePos,totLength,unicode);
107. text.add(piece);
109. }
111. }
112. returnmultiple;
113. }
114. publicstaticvoidmain(String[]args){
115. WordExtractorw=newWordExtractor();
116. POIFSFileSystemps=newPOIFSFileSystem();
117. try{
119. Filefile=newFile("C:\\test.doc");
121. InputStreamin=newFileInputStream(file);
122. Strings=w.extractText(in);
123. System.out.println(s);
126. }catch(Exceptione){
127. e.printStackTrace();
128. }
130. }
132. }
133. classWordTextPiece{
134. privateint_fcStart;
135. privateboolean_usesUnicode;
136. privateint_length;
138. publicWordTextPiece(intstart,intlength,booleanunicode){
139. _usesUnicode=unicode;
140. _length=length;
141. _fcStart=start;
142. }
143. publicbooleanusesUnicode(){
144. return_usesUnicode;
145. }
147. publicintgetStart(){
148. return_fcStart;
149. }
150. publicintgetLength(){
151. return_length;
152. }
154. }

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();
		// Prende le informazioni dall'header del documento
		int info = LittleEndian.getShort(header, 0xa);

		boolean useTable1 = (info & 0x200) != 0;

		//boolean useTable1 = true;
		
		// Prende informazioni dalla piece table
		int complexOffset = LittleEndian.getInt(header, 0x1a2);
		//int complexOffset = LittleEndian.getInt(header);
		
		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("C:\\test.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;
	}

}

Java代码

1. publicbooleanwriteWordFile(Stringpath,Stringcontent){
2. booleanw=false;
3. try{
5. //byteb[]=content.getBytes("ISO-8859-1");
6. byteb[]=content.getBytes();
8. ByteArrayInputStreambais=newByteArrayInputStream(b);
10. POIFSFileSystemfs=newPOIFSFileSystem();
11. DirectoryEntrydirectory=fs.getRoot();
13. DocumentEntryde=directory.createDocument("WordDocument",bais);
15. FileOutputStreamostream=newFileOutputStream(path);
17. fs.writeFilesystem(ostream);
19. bais.close();
20. ostream.close();
22. }catch(IOExceptione){
23. e.printStackTrace();
24. }
26. returnw;
27. }

	public boolean writeWordFile(String path, String content) {
		boolean w = false;
		try {
	
		//	byte b[] = content.getBytes("ISO-8859-1");
			byte b[] = content.getBytes();
			
			ByteArrayInputStream bais = new ByteArrayInputStream(b);

			POIFSFileSystem fs = new POIFSFileSystem();
			DirectoryEntry directory = fs.getRoot();

			DocumentEntry de = directory.createDocument("WordDocument", bais);

			FileOutputStream ostream = new FileOutputStream(path);

			fs.writeFilesystem(ostream);
			
			bais.close();
			ostream.close();

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

		return w;
	}