import java.io.ByteArrayOutputStream;
import java.io.IOException;
+import java.util.Iterator;
+
import org.apache.poi.hslf.HSLFSlideShow;
import org.apache.poi.hslf.record.Record;
+import org.apache.poi.util.HexDump;
+import org.apache.poi.ddf.DefaultEscherRecordFactory;
+import org.apache.poi.ddf.EscherRecord;
+import org.apache.poi.ddf.EscherContainerRecord;
+import org.apache.poi.ddf.EscherTextboxRecord;
+import org.apache.poi.hslf.record.EscherTextboxWrapper;
+import org.apache.poi.hslf.record.TextCharsAtom;
+import org.apache.poi.hslf.record.TextBytesAtom;
+import org.apache.poi.hslf.record.StyleTextPropAtom;
+import org.apache.poi.hslf.record.Record;
/**
* This class provides a way to view the contents of a powerpoint file.
* @author Nick Burch
*/
public final class SlideShowRecordDumper {
+ private boolean optVerbose;
+ private boolean optEscher;
private HSLFSlideShow doc;
/**
*/
public static void main(String args[]) throws IOException
{
- if(args.length == 0) {
- System.err.println("Useage: SlideShowRecordDumper <filename>");
+ String filename = "";
+ boolean verbose = false;
+ boolean escher = false;
+
+ int ndx=0;
+ for (; ndx<args.length; ndx++) {
+ if (!args[ndx].substring(0,1).equals("-"))
+ break;
+
+ if (args[ndx].equals("-escher")) {
+ escher = true;
+ } else if (args[ndx].equals("-verbose")) {
+ verbose = true;
+ } else {
+ printUsage();
+ return;
+ }
+ }
+
+ // parsed any options, expect exactly one remaining arg (filename)
+ if (ndx != args.length-1) {
+ printUsage();
return;
}
+
+ filename = args[ndx];
- String filename = args[0];
-
- SlideShowRecordDumper foo = new SlideShowRecordDumper(filename);
+ SlideShowRecordDumper foo = new SlideShowRecordDumper(filename, verbose, escher);
foo.printDump();
}
+
+ public static void printUsage() {
+ System.err.println("Usage: SlideShowRecordDumper [-escher] [-verbose] <filename>");
+ System.err.println("Valid Options:");
+ System.err.println("-escher\t\t: dump contents of escher records");
+ System.err.println("-verbose\t: dump binary contents of each record");
+ }
/**
* @param fileName The name of the file to read.
* @throws IOException if there is a problem while parsing the document.
*/
- public SlideShowRecordDumper(String fileName) throws IOException
+ public SlideShowRecordDumper(String fileName, boolean verbose, boolean escher) throws IOException
{
+ optVerbose = verbose;
+ optEscher = escher;
doc = new HSLFSlideShow(fileName);
}
}
public int getDiskLen(Record r) throws IOException {
+ if (r == null) return 0;
+
ByteArrayOutputStream baos = new ByteArrayOutputStream();
r.writeOut(baos);
byte[] b = baos.toByteArray();
return b.length;
}
+ public String getPrintableRecordContents(Record r) throws IOException {
+ if (r==null) return "<<null>>";
+
+ ByteArrayOutputStream baos = new ByteArrayOutputStream();
+ r.writeOut(baos);
+ byte[] b = baos.toByteArray();
+ return HexDump.dump(b, 0, 0);
+ }
+
+ public String printEscherRecord( EscherRecord er ) {
+ String nl = System.getProperty( "line.separator" );
+ StringBuffer buf = new StringBuffer();
+
+ if (er instanceof EscherContainerRecord) {
+ buf.append(printEscherContainerRecord( (EscherContainerRecord)er ));
+ } else if (er instanceof EscherTextboxRecord) {
+ buf.append("EscherTextboxRecord:" + nl);
+
+ EscherTextboxWrapper etw = new EscherTextboxWrapper((EscherTextboxRecord)er);
+ Record children[] = etw.getChildRecords();
+ for (int j=0; j<children.length; j++) {
+ if (children[j] instanceof StyleTextPropAtom) {
+
+ // need preceding Text[Chars|Bytes]Atom to initialize the data structure
+ if (j > 0 && (children[j-1] instanceof TextCharsAtom ||
+ children[j-1] instanceof TextBytesAtom)) {
+
+ int size = (children[j-1] instanceof TextCharsAtom) ?
+ ((TextCharsAtom)children[j-1]).getText().length() :
+ ((TextBytesAtom)children[j-1]).getText().length();
+
+ StyleTextPropAtom tsp = (StyleTextPropAtom)children[j];
+ tsp.setParentTextSize(size);
+
+ } else {
+ buf.append("Error! Couldn't find preceding TextAtom for style\n");
+ }
+
+ buf.append(children[j].toString() + nl );
+ } else {
+ buf.append(children[j].toString() + nl );
+ }
+ }
+ } else {
+ buf.append( er.toString() );
+ }
+ return buf.toString();
+ }
+
+ public String printEscherContainerRecord( EscherContainerRecord ecr ) {
+ String indent = "";
+
+ String nl = System.getProperty( "line.separator" );
+
+ StringBuffer children = new StringBuffer();
+ if ( ecr.getChildRecords().size() > 0 )
+ {
+ children.append( " children: " + nl );
+
+ int count = 0;
+ for ( Iterator iterator = ecr.getChildRecords().iterator(); iterator.hasNext(); )
+ {
+ String newIndent = " ";
+
+ EscherRecord record = (EscherRecord) iterator.next();
+ children.append(newIndent + "Child " + count + ":" + nl);
+
+ children.append( printEscherRecord(record) );
+
+ count++;
+ }
+ }
+
+ return
+ indent + ecr.getClass().getName() + " (" + ecr.getRecordName() + "):" + nl +
+ indent + " isContainer: " + ecr.isContainerRecord() + nl +
+ indent + " options: 0x" + HexDump.toHex( ecr.getOptions() ) + nl +
+ indent + " recordId: 0x" + HexDump.toHex( ecr.getRecordId() ) + nl +
+ indent + " numchildren: " + ecr.getChildRecords().size() + nl +
+ indent + children.toString();
+ }
+
public void walkTree(int depth, int pos, Record[] records) throws IOException {
int indent = depth;
for(int i=0; i<records.length; i++) {
Record r = records[i];
+ if (r == null) {
+ System.out.println(ind + "At position " + pos + " (" + makeHex(pos,6) + "):");
+ System.out.println(ind + "Warning! Null record found.");
+ continue;
+ }
// Figure out how big it is
int len = getDiskLen(r);
-
+
// Grab the type as hex
String hexType = makeHex((int)r.getRecordType(),4);
String rHexType = reverseHex(hexType);
System.out.println(ind + " Record is of type " + cname);
System.out.println(ind + " Type is " + r.getRecordType() + " (" + hexType + " -> " + rHexType + " )");
System.out.println(ind + " Len is " + (len-8) + " (" + makeHex((len-8),8) + "), on disk len is " + len );
+
+ // print additional information for drawings and atoms
+ if (optEscher && cname.equals("PPDrawing")) {
+ DefaultEscherRecordFactory factory = new DefaultEscherRecordFactory();
+
+ ByteArrayOutputStream baos = new ByteArrayOutputStream();
+ r.writeOut(baos);
+ byte[] b = baos.toByteArray();
+
+ EscherRecord er = factory.createRecord(b, 0);
+ er.fillFields(b, 0, factory);
+
+ System.out.println( printEscherRecord( er ) );
+
+ } else if(optVerbose && r.getChildRecords() == null) {
+ String recData = getPrintableRecordContents(r);
+ System.out.println(ind + recData );
+ }
+
System.out.println();
// If it has children, show them
import org.apache.poi.hslf.model.textproperties.TextPropCollection;
import org.apache.poi.util.LittleEndian;
import org.apache.poi.util.POILogger;
+import org.apache.poi.util.HexDump;
/**
* A StyleTextPropAtom (type 4001). Holds basic character properties
*/
public String toString(){
StringBuffer out = new StringBuffer();
- out.append("Paragraph properties\n");
- for (Iterator it1 = getParagraphStyles().iterator(); it1.hasNext();) {
- TextPropCollection pr = (TextPropCollection)it1.next();
- out.append(" chars covered: " + pr.getCharactersCovered() + "\n");
- for (Iterator it2 = pr.getTextPropList().iterator(); it2.hasNext(); ) {
- TextProp p = (TextProp)it2.next();
- out.append(" " + p.getName() + " = " + p.getValue() + "\n");
- }
- }
-
- out.append("Character properties\n");
- for (Iterator it1 = getCharacterStyles().iterator(); it1.hasNext();) {
- TextPropCollection pr = (TextPropCollection)it1.next();
- out.append(" chars covered: " + pr.getCharactersCovered() + "\n");
- for (Iterator it2 = pr.getTextPropList().iterator(); it2.hasNext(); ) {
- TextProp p = (TextProp)it2.next();
- out.append(" " + p.getName() + " = " + p.getValue() + "\n");
- }
+
+ out.append("StyleTextPropAtom:\n");
+ if (!initialised) {
+ out.append("Uninitialised, dumping Raw Style Data\n");
+ } else {
+
+ out.append("Paragraph properties\n");
+
+ for (Iterator it1 = getParagraphStyles().iterator(); it1.hasNext();) {
+ TextPropCollection pr = (TextPropCollection)it1.next();
+ out.append(" chars covered: " + pr.getCharactersCovered());
+ out.append(" special mask flags: 0x" + HexDump.toHex(pr.getSpecialMask()) + "\n");
+ for (Iterator it2 = pr.getTextPropList().iterator(); it2.hasNext(); ) {
+ TextProp p = (TextProp)it2.next();
+ out.append(" " + p.getName() + " = " + p.getValue() );
+ out.append(" (0x" + HexDump.toHex(p.getValue()) + ")\n");
+ }
+
+ out.append(" para bytes that would be written: \n");
+
+ try {
+ ByteArrayOutputStream baos = new ByteArrayOutputStream();
+ pr.writeOut(baos);
+ byte[] b = baos.toByteArray();
+ out.append(HexDump.dump(b, 0, 0));
+ } catch (Exception e ) {
+ e.printStackTrace();
+ }
+ }
+
+ out.append("Character properties\n");
+ for (Iterator it1 = getCharacterStyles().iterator(); it1.hasNext();) {
+ TextPropCollection pr = (TextPropCollection)it1.next();
+ out.append(" chars covered: " + pr.getCharactersCovered() );
+ out.append(" special mask flags: 0x" + HexDump.toHex(pr.getSpecialMask()) + "\n");
+ for (Iterator it2 = pr.getTextPropList().iterator(); it2.hasNext(); ) {
+ TextProp p = (TextProp)it2.next();
+ out.append(" " + p.getName() + " = " + p.getValue() );
+ out.append(" (0x" + HexDump.toHex(p.getValue()) + ")\n");
+ }
+
+ out.append(" char bytes that would be written: \n");
+
+ try {
+ ByteArrayOutputStream baos = new ByteArrayOutputStream();
+ pr.writeOut(baos);
+ byte[] b = baos.toByteArray();
+ out.append(HexDump.dump(b, 0, 0));
+ } catch (Exception e ) {
+ e.printStackTrace();
+ }
+ }
}
+
+ out.append(" original byte stream \n");
+ out.append( HexDump.dump(rawContents, 0, 0) );
return out.toString();
}
projects / poi.git / commitdiff