转载自http://enhydra.iteye.com/blog/24352
read word:
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;
}
}
write word
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;
}
写操作的代码还是有些问题:打开WORD时提示要选择字符类型
希望能改进!
当然这几个jar是少不了的
poi-2.5.1-final-20040804.jar
poi-contrib-2.5.1-final-20040804.jar
poi-scratchpad-2.5.1-final-20040804.jar
分享到:
相关推荐
使用POI读写Word doc文件 Apache poi的hwpf模块是专门用来对word doc文件进行读写操作的。在hwpf里面我们使用HWPFDocument来表示一个word doc文档
poi实现对word读写操作源码,内包含jar包,还有相关的代码
poi实现对word读写操作实例源码Java源码
java读写Excel,POI.JAR,Word内容读取
poi-tl解析Word文档,包含表格类型的也可以
poi读写word模板/JAVA生成word包
使用poi将多个word合并,本方法经过测试,目前只支持多个doc格式合并成一个doc,如果是docx格式生成后打不开
资源描述了poi对于word的操作,poi合并word文档,poi设置word页码,内含maven依赖文档和完整代码,是一个完整工程,打开即可用
poi读写excel,poi总结; poi读写excel,poi总结 poi读写excel,poi总结
这是一个POI读取word 2003 和 word 2007的例子 是一个Eclipse工程 下载后直接导入工程 运行 src 目录下的 Test java 类即可 这个 rar 包中包含着 POI 读取word 2003 和 word 2007 所需要的 jar 包 也有需要读取的 ...
poi生成wordpoi生成wordpoi生成wordpoi生成wordpoi生成wordpoi生成wordpoi生成wordpoi生成wordpoi生成word
poi读取word代码,可以通过此代码实现对word中的文本、图片、表格的读取。
java 使用POI合并两个word文档.docx
Apache poi 根据word模板生成word报表 替换 循环列表 图片,代码调试过了,修改相应的图片位置,word模板路径即可运行
java使用poi操作.doc word模板替换,循环插入表格
一个使用Apache的poi使用word模板循环输出表格行并导出的例子
通过POI将图片插入word文档中,写文字就简单了自己摸索
android使用POI操作word docx文档,根据 【***】这种标识规则,替换掉docx文档中的内容
java使用poi,根据模板,生成word文档.
poi读写excelpoi读写excelpoi读写excelpoi读写excelpoi读写excelpoi读写excelpoi读写excelpoi读写excelpoi读写excel