// 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;
}
protected void setUp() throws Exception {
ModelFactory mf = new ModelFactory();
assertTrue("listeners member cannot be null", mf.listeners != null);
models = new ArrayList(3);
factory = new ModelFactory();
book = new HSSFWorkbook();
ByteArrayOutputStream stream = setupRunFile(book);
POIFSFileSystem fs = new POIFSFileSystem(new ByteArrayInputStream(stream.toByteArray()));
in = fs.createDocumentInputStream("Workbook");
}
public void testWriteProperties() throws Exception {
// Just check we can write them back out into a filesystem
POIFSFileSystem outFS = new POIFSFileSystem();
doc.readProperties();
doc.writeProperties(outFS);
// Should now hold them
assertNotNull(outFS.createDocumentInputStream("\005SummaryInformation"));
assertNotNull(outFS.createDocumentInputStream("\005DocumentSummaryInformation"));
}
/**
* Setup is used to get the document ready. Gets the DocumentSummaryInformation and the
* SummaryInformation to reasonable values
*/
public void setUp() {
bout = new ByteArrayOutputStream();
poifs = new POIFSFileSystem();
dir = poifs.getRoot();
dsi = null;
try {
DocumentEntry dsiEntry =
(DocumentEntry) dir.getEntry(DocumentSummaryInformation.DEFAULT_STREAM_NAME);
DocumentInputStream dis = new DocumentInputStream(dsiEntry);
PropertySet ps = new PropertySet(dis);
dis.close();
dsi = new DocumentSummaryInformation(ps);
} catch (FileNotFoundException ex) {
/* There is no document summary information yet. We have to create a
* new one. */
dsi = PropertySetFactory.newDocumentSummaryInformation();
assertNotNull(dsi);
} catch (IOException e) {
e.printStackTrace();
fail();
} catch (NoPropertySetStreamException e) {
e.printStackTrace();
fail();
} catch (MarkUnsupportedException e) {
e.printStackTrace();
fail();
} catch (UnexpectedPropertySetTypeException e) {
e.printStackTrace();
fail();
}
assertNotNull(dsi);
try {
DocumentEntry dsiEntry = (DocumentEntry) dir.getEntry(SummaryInformation.DEFAULT_STREAM_NAME);
DocumentInputStream dis = new DocumentInputStream(dsiEntry);
PropertySet ps = new PropertySet(dis);
dis.close();
si = new SummaryInformation(ps);
} catch (FileNotFoundException ex) {
/* There is no document summary information yet. We have to create a
* new one. */
si = PropertySetFactory.newSummaryInformation();
assertNotNull(si);
} catch (IOException e) {
e.printStackTrace();
fail();
} catch (NoPropertySetStreamException e) {
e.printStackTrace();
fail();
} catch (MarkUnsupportedException e) {
e.printStackTrace();
fail();
} catch (UnexpectedPropertySetTypeException e) {
e.printStackTrace();
fail();
}
assertNotNull(dsi);
}
/**
* Read an excel file and spit out what we find.
*
* @param args Expect one argument that is the file to read.
* @throws IOException When there is an error processing the file.
*/
public static void main(String[] args) throws IOException {
try {
Class.forName("com.microsoft.sqlserver.jdbc.SQLServerDriver");
// con = DriverManager
// .getConnection("jdbc:sqlserver://10.130.133.3:1433;DatabaseName=RTB;user=i264678;password=;SelectMethod=cursor ");
con =
DriverManager.getConnection(
"jdbc:sqlserver://10.135.128.227:1433;DatabaseName=RTBWTC;user=i264678;password=;SelectMethod=cursor ");
System.out.println("connected");
// create a new file input stream with the input file specified
// at the command line
FileInputStream fin = new FileInputStream(args[0]);
// create a new org.apache.poi.poifs.filesystem.Filesystem
POIFSFileSystem poifs = new POIFSFileSystem(fin);
// get the Workbook (excel part) stream in a InputStream
InputStream din = poifs.createDocumentInputStream("Workbook");
// construct out HSSFRequest object
HSSFRequest req = new HSSFRequest();
// lazy listen for ALL records with the listener shown above
req.addListenerForAllRecords(new LoadServiceFromExcel());
// create our event factory
HSSFEventFactory factory = new HSSFEventFactory();
// process our events based on the document input stream
factory.processEvents(req, din);
// once all the events are processed close our file input stream
fin.close();
// and our document input stream (don't want to leak these!)
din.close();
System.out.println("done.");
} catch (ClassNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (SQLException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally {
try {
con.close();
} catch (SQLException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
public void testWriteReadProperties() throws Exception {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
// Write them out
POIFSFileSystem outFS = new POIFSFileSystem();
doc.readProperties();
doc.writeProperties(outFS);
outFS.writeFilesystem(baos);
// Create a new version
ByteArrayInputStream bais = new ByteArrayInputStream(baos.toByteArray());
POIFSFileSystem inFS = new POIFSFileSystem(bais);
// Check they're still there
doc.filesystem = inFS;
doc.readProperties();
// Delegate test
testReadProperties();
}
/**
* Runs the example program. The application expects one or two arguments:
*
* <ol>
* <li>
* <p>The first argument is the disk file name of the POI filesystem to copy.
* <li>
* <p>The second argument is optional. If it is given, it is the name of a disk file the
* copy of the POI filesystem will be written to. If it is not given, the copy will be
* written to a temporary file which will be deleted at the end of the program.
* </ol>
*
* @param args Command-line arguments.
* @exception MarkUnsupportedException if a POI document stream does not support the mark()
* operation.
* @exception NoPropertySetStreamException if the application tries to create a property set from
* a POI document stream that is not a property set stream.
* @exception IOException if any I/O exception occurs.
* @exception UnsupportedEncodingException if a character encoding is not supported.
*/
public static void main(final String[] args)
throws NoPropertySetStreamException, MarkUnsupportedException, UnsupportedEncodingException,
IOException {
String originalFileName = null;
String copyFileName = null;
/* Check the command-line arguments. */
if (args.length == 1) {
originalFileName = args[0];
File f = TempFile.createTempFile("CopyOfPOIFileSystem-", ".ole2");
f.deleteOnExit();
copyFileName = f.getAbsolutePath();
} else if (args.length == 2) {
originalFileName = args[0];
copyFileName = args[1];
} else {
System.err.println("Usage: " + CopyCompare.class.getName() + "originPOIFS [copyPOIFS]");
System.exit(1);
}
/* Read the origin POIFS using the eventing API. The real work is done
* in the class CopyFile which is registered here as a POIFSReader. */
final POIFSReader r = new POIFSReader();
final CopyFile cf = new CopyFile(copyFileName);
r.registerListener(cf);
r.read(new FileInputStream(originalFileName));
/* Write the new POIFS to disk. */
cf.close();
/* Read all documents from the original POI file system and compare them
* with the equivalent document from the copy. */
final POIFSFileSystem opfs = new POIFSFileSystem(new FileInputStream(originalFileName));
final POIFSFileSystem cpfs = new POIFSFileSystem(new FileInputStream(copyFileName));
final DirectoryEntry oRoot = opfs.getRoot();
final DirectoryEntry cRoot = cpfs.getRoot();
final StringBuffer messages = new StringBuffer();
if (equal(oRoot, cRoot, messages)) System.out.println("Equal");
else System.out.println("Not equal: " + messages.toString());
}
/** 导入 excel 2003 biff格式 如果是xml格式的 可以使用SAX（未测试） */
@Test
public void testImportExcel2003() throws Exception {
long beginTime = System.currentTimeMillis();
String fileName = "D:\\Backup\\Book1.xls";
List<ExcelData> dataList = Lists.newArrayList();
// 输入流
InputStream fis = new BufferedInputStream(new FileInputStream(fileName));
// 创建 org.apache.poi.poifs.filesystem.Filesystem
POIFSFileSystem poifs = new POIFSFileSystem(fis);
// 从输入流 得到 Workbook(excel 部分)流
InputStream din = poifs.createDocumentInputStream("Workbook");
// 构造 HSSFRequest
HSSFRequest req = new HSSFRequest();
// 添加监听器
req.addListenerForAllRecords(new Excel2003Listener(dataList));
// 创建事件工厂
HSSFEventFactory factory = new HSSFEventFactory();
// 根据文档输入流处理事件
factory.processEvents(req, din);
// 关闭输入流
fis.close();
// 关闭文档流
din.close();
System.out.println(dataList.size());
// 把最后剩下的不足batchSize大小
if (dataList.size() > 0) {
doBatchSave(dataList);
}
long endTime = System.currentTimeMillis();
log.info("耗时(秒):" + (endTime - beginTime) / 1000);
}
/**
* Creates the appropriate HSSFWorkbook / XSSFWorkbook from the given InputStream, which may be
* password protected.
*
* <p>Your input stream MUST either support mark/reset, or be wrapped as a {@link
* PushbackInputStream}! Note that using an {@link InputStream} has a higher memory footprint than
* using a {@link File}.
*
* <p>Note that in order to properly release resources the Workbook should be closed after use.
* Note also that loading from an InputStream requires more memory than loading from a File, so
* prefer {@link #create(File)} where possible.
*
* @throws EncryptedDocumentException If the wrong password is given for a protected file
* @throws EmptyFileException If an empty stream is given
*/
public static Workbook create(InputStream inp, String password)
throws IOException, InvalidFormatException, EncryptedDocumentException {
// If clearly doesn't do mark/reset, wrap up
if (!inp.markSupported()) {
inp = new PushbackInputStream(inp, 8);
}
// Ensure that there is at least some data there
byte[] header8 = IOUtils.peekFirst8Bytes(inp);
// Try to create
if (POIFSFileSystem.hasPOIFSHeader(header8)) {
NPOIFSFileSystem fs = new NPOIFSFileSystem(inp);
return create(fs, password);
}
if (POIXMLDocument.hasOOXMLHeader(inp)) {
return new XSSFWorkbook(OPCPackage.open(inp));
}
throw new IllegalArgumentException(
"Your InputStream was neither an OLE2 stream, nor an OOXML stream");
}
/**
* Ensures that the directory hierarchy for a document in a POI fileystem is in place. When a
* document is to be created somewhere in a POI filesystem its directory must be created first.
* This method creates all directories between the POI filesystem root and the directory the
* document should belong to which do not yet exist.
*
* <p>Unfortunately POI does not offer a simple method to interrogate the POIFS whether a
* certain child node (file or directory) exists in a directory. However, since we always start
* with an empty POIFS which contains the root directory only and since each directory in the
* POIFS is created by this method we can maintain the POIFS's directory hierarchy ourselves:
* The {@link DirectoryEntry} of each directory created is stored in a {@link Map}. The
* directories' path names map to the corresponding {@link DirectoryEntry} instances.
*
* @param poiFs The POI filesystem the directory hierarchy is created in, if needed.
* @param path The document's path. This method creates those directory components of this
* hierarchy which do not yet exist.
* @return The directory entry of the document path's parent. The caller should use this {@link
* DirectoryEntry} to create documents in it.
*/
public DirectoryEntry getPath(final POIFSFileSystem poiFs, final POIFSDocumentPath path) {
try {
/* Check whether this directory has already been created. */
final String s = path.toString();
DirectoryEntry de = (DirectoryEntry) paths.get(s);
if (de != null)
/* Yes: return the corresponding DirectoryEntry. */
return de;
/* No: We have to create the directory - or return the root's
* DirectoryEntry. */
int l = path.length();
if (l == 0)
/* Get the root directory. It does not have to be created
* since it always exists in a POIFS. */
de = poiFs.getRoot();
else {
/* Create a subordinate directory. The first step is to
* ensure that the parent directory exists: */
de = getPath(poiFs, path.getParent());
/* Now create the target directory: */
de = de.createDirectory(path.getComponent(path.length() - 1));
}
paths.put(s, de);
return de;
} catch (IOException ex) {
/* This exception will be thrown if the directory already
* exists. However, since we have full control about directory
* creation we can ensure that this will never happen. */
ex.printStackTrace(System.err);
throw new RuntimeException(ex.toString());
/* FIXME (2): Replace the previous line by the following once we
* no longer need JDK 1.3 compatibility. */
// throw new RuntimeException(ex);
}
}
protected HSSFWorkbook makeWorkbook(final Report report, final ELContext ctx) throws Exception {
final byte[] emptyWorkbookData = new HSSFWorkbook().getBytes();
final POIFSFileSystem fs;
if (report.getTemplate() != null) {
fs = new POIFSFileSystem(new ByteArrayInputStream(report.getTemplate()));
} else {
fs = new POIFSFileSystem();
fs.createDocument(new ByteArrayInputStream(emptyWorkbookData), "Workbook");
}
final MutablePropertySet siProperties = new MutablePropertySet();
final MutableSection siSection = (MutableSection) siProperties.getSections().get(0);
siSection.setFormatID(SectionIDMap.SUMMARY_INFORMATION_ID);
final MutableProperty p0 = new MutableProperty();
p0.setID(PropertyIDMap.PID_CREATE_DTM);
p0.setType(Variant.VT_FILETIME);
p0.setValue(new Date());
siSection.setProperty(p0);
final String application = report.getDescription().getApplication(ctx);
if (application != null) {
final MutableProperty p = new MutableProperty();
p.setID(PropertyIDMap.PID_APPNAME);
p.setType(Variant.VT_LPWSTR);
p.setValue(application);
siSection.setProperty(p);
}
final String author = report.getDescription().getAuthor(ctx);
if (author != null) {
final MutableProperty p = new MutableProperty();
p.setID(PropertyIDMap.PID_AUTHOR);
p.setType(Variant.VT_LPWSTR);
p.setValue(author);
siSection.setProperty(p);
}
final String version = report.getDescription().getVersion(ctx);
if (version != null) {
final MutableProperty p = new MutableProperty();
p.setID(PropertyIDMap.PID_REVNUMBER);
p.setType(Variant.VT_LPWSTR);
p.setValue(version);
siSection.setProperty(p);
}
final String title = report.getDescription().getTitle(ctx);
if (title != null) {
final MutableProperty p = new MutableProperty();
p.setID(PropertyIDMap.PID_TITLE);
p.setType(Variant.VT_LPWSTR);
p.setValue(title);
siSection.setProperty(p);
}
final String subject = report.getDescription().getSubject(ctx);
if (subject != null) {
final MutableProperty p = new MutableProperty();
p.setID(PropertyIDMap.PID_SUBJECT);
p.setType(Variant.VT_LPWSTR);
p.setValue(subject);
siSection.setProperty(p);
}
final String comments = report.getDescription().getComments(ctx);
if (comments != null) {
final MutableProperty p = new MutableProperty();
p.setID(PropertyIDMap.PID_COMMENTS);
p.setType(Variant.VT_LPWSTR);
p.setValue(comments);
siSection.setProperty(p);
}
final MutablePropertySet dsiProperties = new MutablePropertySet();
final MutableSection dsiSection = (MutableSection) dsiProperties.getSections().get(0);
dsiSection.setFormatID(SectionIDMap.DOCUMENT_SUMMARY_INFORMATION_ID[0]);
final String company = report.getDescription().getCompany(ctx);
if (company != null) {
final MutableProperty p = new MutableProperty();
p.setID(PropertyIDMap.PID_COMPANY);
p.setType(Variant.VT_LPWSTR);
p.setValue(company);
dsiSection.setProperty(p);
}
final String category = report.getDescription().getCategory(ctx);
if (category != null) {
final MutableProperty p = new MutableProperty();
p.setID(PropertyIDMap.PID_CATEGORY);
p.setType(Variant.VT_LPWSTR);
p.setValue(category);
dsiSection.setProperty(p);
}
fs.createDocument(siProperties.toInputStream(), SummaryInformation.DEFAULT_STREAM_NAME);
fs.createDocument(
dsiProperties.toInputStream(), DocumentSummaryInformation.DEFAULT_STREAM_NAME);
return new HSSFWorkbook(fs, true);
}
public String extractText(InputStream in) throws IOException {
ArrayList<WordTextPiece> text = new ArrayList<WordTextPiece>();
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();
tableStream = null;
for (int x = 0; x < text.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-8");
} else {
toStr = new String(header, start, length, "big5");
}
sb.append(toStr).append(" ");
}
return sb.toString();
}
/**
* Writes the POI file system to a disk file.
*
* @throws FileNotFoundException
* @throws IOException
*/
public void close() throws FileNotFoundException, IOException {
out = new FileOutputStream(dstName);
poiFs.writeFilesystem(out);
out.close();
}
/**
* Writes out the word file that is represented by an instance of this class.
*
* @param out The OutputStream to write to.
* @throws IOException If there is an unexpected IOException from the passed in OutputStream.
*/
public void write(OutputStream out) throws IOException {
// initialize our streams for writing.
HWPFFileSystem docSys = new HWPFFileSystem();
HWPFOutputStream wordDocumentStream = docSys.getStream(STREAM_WORD_DOCUMENT);
HWPFOutputStream tableStream = docSys.getStream(STREAM_TABLE_1);
// HWPFOutputStream dataStream = docSys.getStream("Data");
int tableOffset = 0;
// FileInformationBlock fib = (FileInformationBlock)_fib.clone();
// clear the offsets and sizes in our FileInformationBlock.
_fib.clearOffsetsSizes();
// determine the FileInformationBLock size
int fibSize = _fib.getSize();
fibSize +=
POIFSConstants.SMALLER_BIG_BLOCK_SIZE - (fibSize % POIFSConstants.SMALLER_BIG_BLOCK_SIZE);
// preserve space for the FileInformationBlock because we will be writing
// it after we write everything else.
byte[] placeHolder = new byte[fibSize];
wordDocumentStream.write(placeHolder);
int mainOffset = wordDocumentStream.getOffset();
// write out the StyleSheet.
_fib.setFcStshf(tableOffset);
_ss.writeTo(tableStream);
_fib.setLcbStshf(tableStream.getOffset() - tableOffset);
tableOffset = tableStream.getOffset();
// get fcMin and fcMac because we will be writing the actual text with the
// complex table.
int fcMin = mainOffset;
/*
* clx (encoding of the sprm lists for a complex file and piece table
* for a any file) Written immediately after the end of the previously
* recorded structure. This is recorded in all Word documents
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 23 of 210
*/
// write out the Complex table, includes text.
_fib.setFcClx(tableOffset);
_cft.writeTo(wordDocumentStream, tableStream);
_fib.setLcbClx(tableStream.getOffset() - tableOffset);
tableOffset = tableStream.getOffset();
int fcMac = wordDocumentStream.getOffset();
/*
* dop (document properties record) Written immediately after the end of
* the previously recorded structure. This is recorded in all Word
* documents
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 23 of 210
*/
// write out the DocumentProperties.
_fib.setFcDop(tableOffset);
_dop.writeTo(tableStream);
_fib.setLcbDop(tableStream.getOffset() - tableOffset);
tableOffset = tableStream.getOffset();
/*
* plcfBkmkf (table recording beginning CPs of bookmarks) Written
* immediately after the sttbfBkmk, if the document contains bookmarks.
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 24 of 210
*/
if (_bookmarksTables != null) {
_bookmarksTables.writePlcfBkmkf(_fib, tableStream);
tableOffset = tableStream.getOffset();
}
/*
* plcfBkmkl (table recording limit CPs of bookmarks) Written
* immediately after the plcfBkmkf, if the document contains bookmarks.
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 24 of 210
*/
if (_bookmarksTables != null) {
_bookmarksTables.writePlcfBkmkl(_fib, tableStream);
tableOffset = tableStream.getOffset();
}
/*
* plcfbteChpx (bin table for CHP FKPs) Written immediately after the
* previously recorded table. This is recorded in all Word documents.
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 24 of 210
*/
// write out the CHPBinTable.
_fib.setFcPlcfbteChpx(tableOffset);
_cbt.writeTo(wordDocumentStream, tableStream, fcMin, _cft.getTextPieceTable());
_fib.setLcbPlcfbteChpx(tableStream.getOffset() - tableOffset);
tableOffset = tableStream.getOffset();
/*
* plcfbtePapx (bin table for PAP FKPs) Written immediately after the
* plcfbteChpx. This is recorded in all Word documents.
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 24 of 210
*/
// write out the PAPBinTable.
_fib.setFcPlcfbtePapx(tableOffset);
_pbt.writeTo(wordDocumentStream, tableStream, _cft.getTextPieceTable());
_fib.setLcbPlcfbtePapx(tableStream.getOffset() - tableOffset);
tableOffset = tableStream.getOffset();
/*
* plcfendRef (endnote reference position table) Written immediately
* after the previously recorded table if the document contains endnotes
*
* plcfendTxt (endnote text position table) Written immediately after
* the plcfendRef if the document contains endnotes
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 24 of 210
*/
_endnotesTables.writeRef(_fib, tableStream);
_endnotesTables.writeTxt(_fib, tableStream);
tableOffset = tableStream.getOffset();
/*
* plcffld*** (table of field positions and statuses for annotation
* subdocument) Written immediately after the previously recorded table,
* if the ******* subdocument contains fields.
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 24 of 210
*/
if (_fieldsTables != null) {
_fieldsTables.write(_fib, tableStream);
tableOffset = tableStream.getOffset();
}
/*
* plcffndRef (footnote reference position table) Written immediately
* after the stsh if the document contains footnotes
*
* plcffndTxt (footnote text position table) Written immediately after
* the plcffndRef if the document contains footnotes
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 24 of 210
*/
_footnotesTables.writeRef(_fib, tableStream);
_footnotesTables.writeTxt(_fib, tableStream);
tableOffset = tableStream.getOffset();
/*
* plcfsed (section table) Written immediately after the previously
* recorded table. Recorded in all Word documents
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 25 of 210
*/
// write out the SectionTable.
_fib.setFcPlcfsed(tableOffset);
_st.writeTo(wordDocumentStream, tableStream);
_fib.setLcbPlcfsed(tableStream.getOffset() - tableOffset);
tableOffset = tableStream.getOffset();
// write out the list tables
if (_lt != null) {
/*
* plcflst (list formats) Written immediately after the end of the
* previously recorded, if there are any lists defined in the
* document. This begins with a short count of LSTF structures
* followed by those LSTF structures. This is immediately followed
* by the allocated data hanging off the LSTFs. This data consists
* of the array of LVLs for each LSTF. (Each LVL consists of an LVLF
* followed by two grpprls and an XST.)
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 25 of 210
*/
_lt.writeListDataTo(_fib, tableStream);
tableOffset = tableStream.getOffset();
/*
* plflfo (more list formats) Written immediately after the end of
* the plcflst and its accompanying data, if there are any lists
* defined in the document. This consists first of a PL of LFO
* records, followed by the allocated data (if any) hanging off the
* LFOs. The allocated data consists of the array of LFOLVLFs for
* each LFO (and each LFOLVLF is immediately followed by some LVLs).
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 26 of 210
*/
_fib.setFcPlfLfo(tableStream.getOffset());
_lt.writeListOverridesTo(tableStream);
_fib.setLcbPlfLfo(tableStream.getOffset() - tableOffset);
tableOffset = tableStream.getOffset();
}
/*
* sttbfBkmk (table of bookmark name strings) Written immediately after
* the previously recorded table, if the document contains bookmarks.
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 27 of 210
*/
if (_bookmarksTables != null) {
_bookmarksTables.writeSttbfBkmk(_fib, tableStream);
tableOffset = tableStream.getOffset();
}
/*
* sttbSavedBy (last saved by string table) Written immediately after
* the previously recorded table.
*
* Microsoft Office Word 97-2007 Binary File Format (.doc)
* Specification; Page 27 of 210
*/
// write out the saved-by table.
if (_sbt != null) {
_fib.setFcSttbSavedBy(tableOffset);
_sbt.writeTo(tableStream);
_fib.setLcbSttbSavedBy(tableStream.getOffset() - tableOffset);
tableOffset = tableStream.getOffset();
}
// write out the revision mark authors table.
if (_rmat != null) {
_fib.setFcSttbfRMark(tableOffset);
_rmat.writeTo(tableStream);
_fib.setLcbSttbfRMark(tableStream.getOffset() - tableOffset);
tableOffset = tableStream.getOffset();
}
// write out the FontTable.
_fib.setFcSttbfffn(tableOffset);
_ft.writeTo(tableStream);
_fib.setLcbSttbfffn(tableStream.getOffset() - tableOffset);
tableOffset = tableStream.getOffset();
// set some variables in the FileInformationBlock.
_fib.getFibBase().setFcMin(fcMin);
_fib.getFibBase().setFcMac(fcMac);
_fib.setCbMac(wordDocumentStream.getOffset());
// make sure that the table, doc and data streams use big blocks.
byte[] mainBuf = wordDocumentStream.toByteArray();
if (mainBuf.length < 4096) {
byte[] tempBuf = new byte[4096];
System.arraycopy(mainBuf, 0, tempBuf, 0, mainBuf.length);
mainBuf = tempBuf;
}
// Table1 stream will be used
_fib.getFibBase().setFWhichTblStm(true);
// write out the FileInformationBlock.
// _fib.serialize(mainBuf, 0);
_fib.writeTo(mainBuf, tableStream);
byte[] tableBuf = tableStream.toByteArray();
if (tableBuf.length < 4096) {
byte[] tempBuf = new byte[4096];
System.arraycopy(tableBuf, 0, tempBuf, 0, tableBuf.length);
tableBuf = tempBuf;
}
byte[] dataBuf = _dataStream;
if (dataBuf == null) {
dataBuf = new byte[4096];
}
if (dataBuf.length < 4096) {
byte[] tempBuf = new byte[4096];
System.arraycopy(dataBuf, 0, tempBuf, 0, dataBuf.length);
dataBuf = tempBuf;
}
// create new document preserving order of entries
POIFSFileSystem pfs = new POIFSFileSystem();
boolean docWritten = false;
boolean dataWritten = false;
boolean objectPoolWritten = false;
boolean tableWritten = false;
boolean propertiesWritten = false;
for (Iterator<Entry> iter = directory.getEntries(); iter.hasNext(); ) {
Entry entry = iter.next();
if (entry.getName().equals(STREAM_WORD_DOCUMENT)) {
if (!docWritten) {
pfs.createDocument(new ByteArrayInputStream(mainBuf), STREAM_WORD_DOCUMENT);
docWritten = true;
}
} else if (entry.getName().equals(STREAM_OBJECT_POOL)) {
if (!objectPoolWritten) {
_objectPool.writeTo(pfs.getRoot());
objectPoolWritten = true;
}
} else if (entry.getName().equals(STREAM_TABLE_0) || entry.getName().equals(STREAM_TABLE_1)) {
if (!tableWritten) {
pfs.createDocument(new ByteArrayInputStream(tableBuf), STREAM_TABLE_1);
tableWritten = true;
}
} else if (entry.getName().equals(SummaryInformation.DEFAULT_STREAM_NAME)
|| entry.getName().equals(DocumentSummaryInformation.DEFAULT_STREAM_NAME)) {
if (!propertiesWritten) {
writeProperties(pfs);
propertiesWritten = true;
}
} else if (entry.getName().equals(STREAM_DATA)) {
if (!dataWritten) {
pfs.createDocument(new ByteArrayInputStream(dataBuf), STREAM_DATA);
dataWritten = true;
}
} else {
EntryUtils.copyNodeRecursively(entry, pfs.getRoot());
}
}
if (!docWritten) pfs.createDocument(new ByteArrayInputStream(mainBuf), STREAM_WORD_DOCUMENT);
if (!tableWritten) pfs.createDocument(new ByteArrayInputStream(tableBuf), STREAM_TABLE_1);
if (!propertiesWritten) writeProperties(pfs);
if (!dataWritten) pfs.createDocument(new ByteArrayInputStream(dataBuf), STREAM_DATA);
if (!objectPoolWritten) _objectPool.writeTo(pfs.getRoot());
pfs.writeFilesystem(out);
this.directory = pfs.getRoot();
/*
* since we updated all references in FIB and etc, using new arrays to
* access data
*/
this.directory = pfs.getRoot();
this._tableStream = tableStream.toByteArray();
this._dataStream = dataBuf;
}
/**
* This constructor loads a Word document from a POIFSFileSystem
*
* @param pfilesystem The POIFSFileSystem that contains the Word document.
* @throws IOException If there is an unexpected IOException from the passed in POIFSFileSystem.
*/
public HWPFDocumentCore(POIFSFileSystem pfilesystem) throws IOException {
this(pfilesystem.getRoot());
}
public void parseEmbedded(
InputStream inputStream,
ContentHandler contentHandler,
Metadata metadata,
boolean outputHtml)
throws SAXException, IOException {
String name = metadata.get(Metadata.RESOURCE_NAME_KEY);
if (name == null) {
name = "file" + count++;
}
MediaType contentType = detector.detect(inputStream, metadata);
if (name.indexOf('.') == -1 && contentType != null) {
try {
name += config.getMimeRepository().forName(contentType.toString()).getExtension();
} catch (MimeTypeException e) {
e.printStackTrace();
}
}
String relID = metadata.get(Metadata.EMBEDDED_RELATIONSHIP_ID);
if (relID != null && !name.startsWith(relID)) {
name = relID + "_" + name;
}
File outputFile = new File(extractDir, name);
File parent = outputFile.getParentFile();
if (!parent.exists()) {
if (!parent.mkdirs()) {
throw new IOException("unable to create directory \"" + parent + "\"");
}
}
System.out.println("Extracting '" + name + "' (" + contentType + ") to " + outputFile);
FileOutputStream os = null;
try {
os = new FileOutputStream(outputFile);
if (inputStream instanceof TikaInputStream) {
TikaInputStream tin = (TikaInputStream) inputStream;
if (tin.getOpenContainer() != null && tin.getOpenContainer() instanceof DirectoryEntry) {
POIFSFileSystem fs = new POIFSFileSystem();
copy((DirectoryEntry) tin.getOpenContainer(), fs.getRoot());
fs.writeFilesystem(os);
} else {
IOUtils.copy(inputStream, os);
}
} else {
IOUtils.copy(inputStream, os);
}
} catch (Exception e) {
logger.warn("Ignoring unexpected exception trying to save embedded file " + name, e);
} finally {
if (os != null) {
os.close();
}
}
}
/**
* Closes the ByteArrayOutputStream and reads it into a ByteArrayInputStream. When finished
* writing information this method is used in the tests to start reading from the created document
* and then the see if the results match.
*/
public void closeAndReOpen() {
try {
dsi.write(dir, DocumentSummaryInformation.DEFAULT_STREAM_NAME);
si.write(dir, SummaryInformation.DEFAULT_STREAM_NAME);
} catch (WritingNotSupportedException e) {
e.printStackTrace();
fail();
} catch (IOException e) {
e.printStackTrace();
fail();
}
si = null;
dsi = null;
try {
poifs.writeFilesystem(bout);
bout.flush();
} catch (IOException e) {
e.printStackTrace();
fail();
}
InputStream is = new ByteArrayInputStream(bout.toByteArray());
assertNotNull(is);
POIFSFileSystem poifs = null;
try {
poifs = new POIFSFileSystem(is);
} catch (IOException e) {
e.printStackTrace();
fail();
}
try {
is.close();
} catch (IOException e) {
e.printStackTrace();
fail();
}
assertNotNull(poifs);
/* Read the document summary information. */
DirectoryEntry dir = poifs.getRoot();
try {
DocumentEntry dsiEntry =
(DocumentEntry) dir.getEntry(DocumentSummaryInformation.DEFAULT_STREAM_NAME);
DocumentInputStream dis = new DocumentInputStream(dsiEntry);
PropertySet ps = new PropertySet(dis);
dis.close();
dsi = new DocumentSummaryInformation(ps);
} catch (FileNotFoundException ex) {
fail();
} catch (IOException e) {
e.printStackTrace();
fail();
} catch (NoPropertySetStreamException e) {
e.printStackTrace();
fail();
} catch (MarkUnsupportedException e) {
e.printStackTrace();
fail();
} catch (UnexpectedPropertySetTypeException e) {
e.printStackTrace();
fail();
}
try {
DocumentEntry dsiEntry = (DocumentEntry) dir.getEntry(SummaryInformation.DEFAULT_STREAM_NAME);
DocumentInputStream dis = new DocumentInputStream(dsiEntry);
PropertySet ps = new PropertySet(dis);
dis.close();
si = new SummaryInformation(ps);
} catch (FileNotFoundException ex) {
/* There is no document summary information yet. We have to create a
* new one. */
si = PropertySetFactory.newSummaryInformation();
assertNotNull(si);
} catch (IOException e) {
e.printStackTrace();
fail();
} catch (NoPropertySetStreamException e) {
e.printStackTrace();
fail();
} catch (MarkUnsupportedException e) {
e.printStackTrace();
fail();
} catch (UnexpectedPropertySetTypeException e) {
e.printStackTrace();
fail();
}
}
/**
* Add a embedded object to this presentation
*
* @return 0-based index of the embedded object
*/
public int addEmbed(POIFSFileSystem poiData) {
DirectoryNode root = poiData.getRoot();
// prepare embedded data
if (new ClassID().equals(root.getStorageClsid())) {
// need to set class id
Map<String, ClassID> olemap = getOleMap();
ClassID classID = null;
for (Map.Entry<String, ClassID> entry : olemap.entrySet()) {
if (root.hasEntry(entry.getKey())) {
classID = entry.getValue();
break;
}
}
if (classID == null) {
throw new IllegalArgumentException("Unsupported embedded document");
}
root.setStorageClsid(classID);
}
ExEmbed exEmbed = new ExEmbed();
// remove unneccessary infos, so we don't need to specify the type
// of the ole object multiple times
Record children[] = exEmbed.getChildRecords();
exEmbed.removeChild(children[2]);
exEmbed.removeChild(children[3]);
exEmbed.removeChild(children[4]);
ExEmbedAtom eeEmbed = exEmbed.getExEmbedAtom();
eeEmbed.setCantLockServerB(true);
ExOleObjAtom eeAtom = exEmbed.getExOleObjAtom();
eeAtom.setDrawAspect(ExOleObjAtom.DRAW_ASPECT_VISIBLE);
eeAtom.setType(ExOleObjAtom.TYPE_EMBEDDED);
// eeAtom.setSubType(ExOleObjAtom.SUBTYPE_EXCEL);
// should be ignored?!?, see MS-PPT ExOleObjAtom, but Libre Office sets it ...
eeAtom.setOptions(1226240);
ExOleObjStg exOleObjStg = new ExOleObjStg();
try {
final String OLESTREAM_NAME = "\u0001Ole";
if (!root.hasEntry(OLESTREAM_NAME)) {
// the following data was taken from an example libre office document
// beside this "\u0001Ole" record there were several other records, e.g. CompObj,
// OlePresXXX, but it seems, that they aren't neccessary
byte oleBytes[] = {1, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
poiData.createDocument(new ByteArrayInputStream(oleBytes), OLESTREAM_NAME);
}
ByteArrayOutputStream bos = new ByteArrayOutputStream();
poiData.writeFilesystem(bos);
exOleObjStg.setData(bos.toByteArray());
} catch (IOException e) {
throw new HSLFException(e);
}
int psrId = addPersistentObject(exOleObjStg);
exOleObjStg.setPersistId(psrId);
eeAtom.setObjStgDataRef(psrId);
int objectId = addToObjListAtom(exEmbed);
eeAtom.setObjID(objectId);
return objectId;
}
public ExcelExtractor(POIFSFileSystem fs) throws IOException {
this(fs.getRoot(), fs);
}
public InputStream getDataStream(POIFSFileSystem fs)
throws IOException, GeneralSecurityException {
return getDataStream(fs.getRoot());
}
/**
* Processes a file into essentially record events.
*
* @param req an Instance of HSSFRequest which has your registered listeners
* @param fs a POIFS filesystem containing your workbook
* @return numeric user-specified result code.
*/
public short abortableProcessWorkbookEvents(HSSFRequest req, POIFSFileSystem fs)
throws IOException, HSSFUserException {
return abortableProcessWorkbookEvents(req, fs.getRoot());
}
/**
* Processes a file into essentially record events.
*
* @param req an Instance of HSSFRequest which has your registered listeners
* @param fs a POIFS filesystem containing your workbook
*/
public void processWorkbookEvents(HSSFRequest req, POIFSFileSystem fs) throws IOException {
processWorkbookEvents(req, fs.getRoot());
}