/**
* Compares two {@link DocumentEntry} instances of a POI file system. Documents that are not
* property set streams must be bitwise identical. Property set streams must be logically equal.
*
* @param d1 The first document.
* @param d2 The second document.
* @param msg The method may append human-readable comparison messages to this string buffer.
* @return <code>true</code> if the documents are equal, else <code>false</code>.
* @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.
* @throws UnsupportedEncodingException
* @exception IOException if any I/O exception occurs.
*/
private static boolean equal(
final DocumentEntry d1, final DocumentEntry d2, final StringBuffer msg)
throws NoPropertySetStreamException, MarkUnsupportedException, UnsupportedEncodingException,
IOException {
boolean equal = true;
final DocumentInputStream dis1 = new DocumentInputStream(d1);
final DocumentInputStream dis2 = new DocumentInputStream(d2);
if (PropertySet.isPropertySetStream(dis1) && PropertySet.isPropertySetStream(dis2)) {
final PropertySet ps1 = PropertySetFactory.create(dis1);
final PropertySet ps2 = PropertySetFactory.create(dis2);
equal = ps1.equals(ps2);
if (!equal) {
msg.append("Property sets are not equal.\n");
return equal;
}
} else {
int i1;
int i2;
do {
i1 = dis1.read();
i2 = dis2.read();
if (i1 != i2) {
equal = false;
msg.append("Documents are not equal.\n");
break;
}
} while (equal && i1 == -1);
}
return true;
}
/**
* 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);
}
public byte[] getData(int len) throws IOException {
// determine the amount that is possible to read (if len is too much)
int actualAmount = Math.min(input.available(), len);
byte[] b = new byte[actualAmount];
int i = input.read(b);
return b;
}
/**
* Copies the bytes from a {@link DocumentInputStream} to a new stream in a POI filesystem.
*
* @param poiFs The POI filesystem to write to.
* @param path The source document's path.
* @param name The source document's name.
* @param stream The stream containing the source document.
* @throws IOException
*/
public void copy(
final POIFSFileSystem poiFs,
final POIFSDocumentPath path,
final String name,
final DocumentInputStream stream)
throws IOException {
final DirectoryEntry de = getPath(poiFs, path);
final ByteArrayOutputStream out = new ByteArrayOutputStream();
int c;
while ((c = stream.read()) != -1) out.write(c);
stream.close();
out.close();
final InputStream in = new ByteArrayInputStream(out.toByteArray());
de.createDocument(name, in);
}
/**
* Creates a {@link DocumentDescriptor}.
*
* @param name The stream's name.
* @param path The stream's path in the POI filesystem hierarchy.
* @param stream The stream.
* @param nrOfBytes The maximum number of bytes to display in a dump starting at the beginning of
* the stream.
*/
public DocumentDescriptor(
final String name,
final POIFSDocumentPath path,
final DocumentInputStream stream,
final int nrOfBytes) {
this.name = name;
this.path = path;
this.stream = stream;
try {
size = stream.available();
if (stream.markSupported()) {
stream.mark(nrOfBytes);
final byte[] b = new byte[nrOfBytes];
final int read = stream.read(b, 0, Math.min(size, b.length));
bytes = new byte[read];
System.arraycopy(b, 0, bytes, 0, read);
stream.reset();
}
} catch (IOException ex) {
System.out.println(ex);
}
}
public void close() throws IOException {
input.close();
input = null;
}
public void setPosition(long i) throws IOException {
input.reset();
input.skip((int) i);
}
public DocumentDataSource(DocumentInputStream input) {
this.input = input;
// Mark the start of the file
input.mark(0);
}
/**
* 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();
}
}
// will throw IOException if not actually POIFS
// can return null byte[]
private byte[] handleEmbeddedPOIFS(
InputStream is, Metadata metadata, AtomicInteger unknownFilenameCount) throws IOException {
NPOIFSFileSystem fs = null;
byte[] ret = null;
try {
fs = new NPOIFSFileSystem(is);
DirectoryNode root = fs.getRoot();
if (root == null) {
return ret;
}
if (root.hasEntry("Package")) {
Entry ooxml = root.getEntry("Package");
TikaInputStream stream =
TikaInputStream.get(new DocumentInputStream((DocumentEntry) ooxml));
ByteArrayOutputStream out = new ByteArrayOutputStream();
IOUtils.copy(stream, out);
ret = out.toByteArray();
} else {
// try poifs
POIFSDocumentType type = POIFSDocumentType.detectType(root);
if (type == POIFSDocumentType.OLE10_NATIVE) {
try {
// Try to un-wrap the OLE10Native record:
Ole10Native ole = Ole10Native.createFromEmbeddedOleObject(root);
ret = ole.getDataBuffer();
} catch (Ole10NativeException ex) {
// Not a valid OLE10Native record, skip it
}
} else if (type == POIFSDocumentType.COMP_OBJ) {
DocumentEntry contentsEntry;
try {
contentsEntry = (DocumentEntry) root.getEntry("CONTENTS");
} catch (FileNotFoundException ioe) {
contentsEntry = (DocumentEntry) root.getEntry("Contents");
}
DocumentInputStream inp = null;
try {
inp = new DocumentInputStream(contentsEntry);
ret = new byte[contentsEntry.getSize()];
inp.readFully(ret);
} finally {
if (inp != null) {
inp.close();
}
}
} else {
ByteArrayOutputStream out = new ByteArrayOutputStream();
is.reset();
IOUtils.copy(is, out);
ret = out.toByteArray();
metadata.set(
Metadata.RESOURCE_NAME_KEY,
"file_" + unknownFilenameCount.getAndIncrement() + "." + type.getExtension());
metadata.set(Metadata.CONTENT_TYPE, type.getType().toString());
}
}
} finally {
if (fs != null) {
fs.close();
}
}
return ret;
}
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();
}
