moparisthebest/poi
1
0
Fork 0
Code Issues Pull Requests Releases 1 Wiki Activity

New HPSF based TextExtractor for document metadata, org.apache.poi.hpsf.extractor.HPFSPropertiesExtractor

Browse Source 
git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@685260 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Nick Burch 2008-08-12 18:44:50 +00:00
parent 2e33f41e90
commit 0f5af26377
9 changed files with 293 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/documentation/content/xdocs/changes.xml
View File

@ -37,6 +37,7 @@
<!-- Don't forget to update status.xml too! -->
<release version="3.1.1-alpha1" date="2008-??-??">
<action dev="POI-DEVELOPERS" type="add">New HPSF based TextExtractor for document metadata, org.apache.poi.hpsf.extractor.HPFSPropertiesExtractor</action>
<action dev="POI-DEVELOPERS" type="fix">Properly update the array of Slide's text runs in HSLF when new text shapes are added</action>
<action dev="POI-DEVELOPERS" type="fix">45590 - Fix for Header/footer extraction for .ppt files saved in Office 2007</action>
<action dev="POI-DEVELOPERS" type="fix">Big improvement in how HWPF handles unicode text, and more sanity checking of text ranges within HWPF</action>

1
src/documentation/content/xdocs/status.xml
View File

@ -34,6 +34,7 @@
<!-- Don't forget to update changes.xml too! -->
<changes>
<release version="3.1.1-alpha1" date="2008-??-??">
<action dev="POI-DEVELOPERS" type="add">New HPSF based TextExtractor for document metadata, org.apache.poi.hpsf.extractor.HPFSPropertiesExtractor</action>
<action dev="POI-DEVELOPERS" type="fix">Properly update the array of Slide's text runs in HSLF when new text shapes are added</action>
<action dev="POI-DEVELOPERS" type="fix">45590 - Fix for Header/footer extraction for .ppt files saved in Office 2007</action>
<action dev="POI-DEVELOPERS" type="fix">Big improvement in how HWPF handles unicode text, and more sanity checking of text ranges within HWPF</action>

8
src/java/org/apache/poi/POITextExtractor.java
View File

@ -37,6 +37,14 @@ public abstract class POITextExtractor {
public POITextExtractor(POIDocument document) {
this.document = document;
}
/**
* Creates a new text extractor, using the same
* document as another text extractor. Normally
* only used by properties extractors.
*/
protected POITextExtractor(POITextExtractor otherExtractor) {
this.document = otherExtractor.document;
}
/**
* Retrieves all the text from the document.

13
src/java/org/apache/poi/hpsf/CustomProperties.java
View File

@ -21,6 +21,7 @@ import java.util.Date;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Map;
import java.util.Set;
import org.apache.poi.hpsf.wellknown.PropertyIDMap;
@ -293,8 +294,18 @@ public class CustomProperties extends HashMap
final CustomProperty cp = new CustomProperty(p, name);
return put(cp);
}
/**
* Returns a set of all the names of our
* custom properties
*/
public Set keySet() {
return dictionaryNameToID.keySet();
}
/**
* <p>Sets the codepage.</p>
*
* @param codepage the codepage

3
src/java/org/apache/poi/hpsf/DocumentSummaryInformation.java
View File

@ -45,6 +45,9 @@ public class DocumentSummaryInformation extends SpecialPropertySet
public static final String DEFAULT_STREAM_NAME =
"\005DocumentSummaryInformation";
public PropertyIDMap getPropertySetIDMap() {
return PropertyIDMap.getDocumentSummaryInformationProperties();
}
/**

6
src/java/org/apache/poi/hpsf/SpecialPropertySet.java
View File

@ -22,6 +22,7 @@ import java.io.InputStream;
import java.io.OutputStream;
import java.util.List;
import org.apache.poi.hpsf.wellknown.PropertyIDMap;
import org.apache.poi.poifs.filesystem.DirectoryEntry;
/**
@ -57,6 +58,11 @@ import org.apache.poi.poifs.filesystem.DirectoryEntry;
*/
public abstract class SpecialPropertySet extends MutablePropertySet
{
/**
* The id to name mapping of the properties
* in this set.
*/
public abstract PropertyIDMap getPropertySetIDMap();
/**
* <p>The "real" property set <code>SpecialPropertySet</code>

3
src/java/org/apache/poi/hpsf/SummaryInformation.java
View File

@ -40,6 +40,9 @@ public class SummaryInformation extends SpecialPropertySet
*/
public static final String DEFAULT_STREAM_NAME = "\005SummaryInformation";
public PropertyIDMap getPropertySetIDMap() {
return PropertyIDMap.getSummaryInformationProperties();
}
/**

144
src/java/org/apache/poi/hpsf/extractor/HPFSPropertiesExtractor.java Normal file
View File

@ -0,0 +1,144 @@
/* ====================================================================
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
==================================================================== */
package org.apache.poi.hpsf.extractor;
import java.io.IOException;
import java.io.OutputStream;
import java.util.Iterator;
import org.apache.poi.POIDocument;
import org.apache.poi.POITextExtractor;
import org.apache.poi.hpsf.CustomProperties;
import org.apache.poi.hpsf.DocumentSummaryInformation;
import org.apache.poi.hpsf.Property;
import org.apache.poi.hpsf.SpecialPropertySet;
import org.apache.poi.hpsf.SummaryInformation;
import org.apache.poi.hpsf.wellknown.PropertyIDMap;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.util.LittleEndian;
/**
* Extracts all of the HPSF properties, both
* build in and custom, returning them in
* textual form.
*/
public class HPFSPropertiesExtractor extends POITextExtractor {
public HPFSPropertiesExtractor(POITextExtractor mainExtractor) {
super(mainExtractor);
}
public HPFSPropertiesExtractor(POIDocument doc) {
super(doc);
}
public HPFSPropertiesExtractor(POIFSFileSystem fs) {
super(new PropertiesOnlyDocument(fs));
}
public String getDocumentSummaryInformationText() {
DocumentSummaryInformation dsi = document.getDocumentSummaryInformation();
StringBuffer text = new StringBuffer();
// Normal properties
text.append( getPropertiesText(dsi) );
// Now custom ones
CustomProperties cps = dsi.getCustomProperties();
Iterator keys = cps.keySet().iterator();
while(keys.hasNext()) {
String key = (String)keys.next();
String val = getPropertyValueText( cps.get(key) );
text.append(key + " = " + val + "\n");
}
// All done
return text.toString();
}
public String getSummaryInformationText() {
SummaryInformation si = document.getSummaryInformation();
// Just normal properties
return getPropertiesText(si);
}
private static String getPropertiesText(SpecialPropertySet ps) {
if(ps == null) {
// Not defined, oh well
return "";
}
StringBuffer text = new StringBuffer();
PropertyIDMap idMap = ps.getPropertySetIDMap();
Property[] props = ps.getProperties();
for(int i=0; i<props.length; i++) {
String type = Long.toString( props[i].getID() );
Object typeObj = idMap.get(props[i].getID());
if(typeObj != null) {
type = typeObj.toString();
}
String val = getPropertyValueText( props[i].getValue() );
text.append(type + " = " + val + "\n");
}
return text.toString();
}
private static String getPropertyValueText(Object val) {
if(val == null) {
return "(not set)";
}
if(val instanceof byte[]) {
byte[] b = (byte[])val;
if(b.length == 0) {
return "";
}
if(b.length == 1) {
return Byte.toString(b[0]);
}
if(b.length == 2) {
return Integer.toString( LittleEndian.getUShort(b) );
}
if(b.length == 4) {
return Long.toString( LittleEndian.getUInt(b) );
}
// Maybe it's a string? who knows!
return new String(b);
}
return val.toString();
}
/**
* Return the text of all the properties defined in
* the document.
*/
public String getText() {
return getSummaryInformationText() + getDocumentSummaryInformationText();
}
/**
* So we can get at the properties of any
* random OLE2 document.
*/
private static class PropertiesOnlyDocument extends POIDocument {
private PropertiesOnlyDocument(POIFSFileSystem fs) {
super(fs);
}
public void write(OutputStream out) throws IOException {
throw new IllegalStateException("Unable to write, only for properties!");
}
}
}

115
src/testcases/org/apache/poi/hpsf/extractor/TestHPFSPropertiesExtractor.java Normal file
View File

@ -0,0 +1,115 @@
/* ====================================================================
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
==================================================================== */
package org.apache.poi.hpsf.extractor;
import java.io.File;
import java.io.FileInputStream;
import org.apache.poi.hssf.extractor.ExcelExtractor;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import junit.framework.TestCase;
public class TestHPFSPropertiesExtractor extends TestCase {
private String dir;
protected void setUp() throws Exception {
dir = System.getProperty("HPSF.testdata.path");
assertNotNull("HPSF.testdata.path not set", dir);
}
public void testNormalProperties() throws Exception {
POIFSFileSystem fs = new POIFSFileSystem(
new FileInputStream(new File(dir, "TestMickey.doc"))
);
HPFSPropertiesExtractor ext = new HPFSPropertiesExtractor(fs);
ext.getText();
// Check each bit in turn
String sinfText = ext.getSummaryInformationText();
String dinfText = ext.getDocumentSummaryInformationText();
assertTrue(sinfText.indexOf("TEMPLATE = Normal") > -1);
assertTrue(sinfText.indexOf("SUBJECT = sample subject") > -1);
assertTrue(dinfText.indexOf("MANAGER = sample manager") > -1);
assertTrue(dinfText.indexOf("COMPANY = sample company") > -1);
// Now overall
String text = ext.getText();
assertTrue(text.indexOf("TEMPLATE = Normal") > -1);
assertTrue(text.indexOf("SUBJECT = sample subject") > -1);
assertTrue(text.indexOf("MANAGER = sample manager") > -1);
assertTrue(text.indexOf("COMPANY = sample company") > -1);
}
public void testNormalUnicodeProperties() throws Exception {
POIFSFileSystem fs = new POIFSFileSystem(
new FileInputStream(new File(dir, "TestUnicode.xls"))
);
HPFSPropertiesExtractor ext = new HPFSPropertiesExtractor(fs);
ext.getText();
// Check each bit in turn
String sinfText = ext.getSummaryInformationText();
String dinfText = ext.getDocumentSummaryInformationText();
assertTrue(sinfText.indexOf("AUTHOR = marshall") > -1);
assertTrue(sinfText.indexOf("TITLE = Titel: \u00c4h") > -1);
assertTrue(dinfText.indexOf("COMPANY = Schreiner") > -1);
assertTrue(dinfText.indexOf("SCALE = false") > -1);
// Now overall
String text = ext.getText();
assertTrue(text.indexOf("AUTHOR = marshall") > -1);
assertTrue(text.indexOf("TITLE = Titel: \u00c4h") > -1);
assertTrue(text.indexOf("COMPANY = Schreiner") > -1);
assertTrue(text.indexOf("SCALE = false") > -1);
}
public void testCustomProperties() throws Exception {
POIFSFileSystem fs = new POIFSFileSystem(
new FileInputStream(new File(dir, "TestMickey.doc"))
);
HPFSPropertiesExtractor ext = new HPFSPropertiesExtractor(fs);
// Custom properties are part of the document info stream
String dinfText = ext.getDocumentSummaryInformationText();
assertTrue(dinfText.indexOf("Client = sample client") > -1);
assertTrue(dinfText.indexOf("Division = sample division") > -1);
String text = ext.getText();
assertTrue(text.indexOf("Client = sample client") > -1);
assertTrue(text.indexOf("Division = sample division") > -1);
}
public void testConstructors() throws Exception {
POIFSFileSystem fs = new POIFSFileSystem(
new FileInputStream(new File(dir, "TestUnicode.xls"))
);
HSSFWorkbook wb = new HSSFWorkbook(fs);
ExcelExtractor excelExt = new ExcelExtractor(wb);
String fsText = (new HPFSPropertiesExtractor(fs)).getText();
String hwText = (new HPFSPropertiesExtractor(wb)).getText();
String eeText = (new HPFSPropertiesExtractor(excelExt)).getText();
assertEquals(fsText, hwText);
assertEquals(fsText, eeText);
assertTrue(fsText.indexOf("AUTHOR = marshall") > -1);
assertTrue(fsText.indexOf("TITLE = Titel: \u00c4h") > -1);
}
}