OOXML pptx text extractor, and test. Also add jar-ooxml ant task

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@607572 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Nick Burch 2007-12-30 18:11:55 +00:00
parent e5fe6f32bd
commit c6d225103f
4 changed files with 238 additions and 1 deletions

View File

@ -1124,6 +1124,21 @@ FORREST_HOME environment variable!</echo>
</manifest>
</jar>
</target>
<target name="jar-ooxml" depends="compile-ooxml" description="Creates the ooxml jar files for distribution">
<jar destfile="${dist.dir}/${jar.name}-ooxml-${version.id}-${DSTAMP}.jar">
<fileset dir="${ooxml.output.dir}" />
<fileset dir="legal/" />
<manifest>
<attribute name="Built-By" value="${user.name}"/>
<attribute name="Specification-Title" value="Apache POI"/>
<attribute name="Specification-Version" value="${version.id}-${DSTAMP}"/>
<attribute name="Specification-Vendor" value="Apache"/>
<attribute name="Implementation-Title" value="Apache POI"/>
<attribute name="Implementation-Version" value="${version.id}-${DSTAMP}"/>
<attribute name="Implementation-Vendor" value="Apache"/>
</manifest>
</jar>
</target>
<target name="dist" depends="clean, fail-unless-tools-are-available, compile, site, jar"
description="Creates the entire distribution into build/dist, from scratch">

View File

@ -0,0 +1,122 @@
/* ====================================================================
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.hslf.extractor;
import java.io.File;
import java.io.IOException;
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.hslf.HSLFXML;
import org.apache.poi.hslf.usermodel.HSLFXMLSlideShow;
import org.apache.poi.hxf.HXFDocument;
import org.apache.xmlbeans.XmlException;
import org.openxml4j.exceptions.OpenXML4JException;
import org.openxml4j.opc.Package;
import org.openxmlformats.schemas.drawingml.x2006.main.CTRegularTextRun;
import org.openxmlformats.schemas.drawingml.x2006.main.CTTextBody;
import org.openxmlformats.schemas.drawingml.x2006.main.CTTextParagraph;
import org.openxmlformats.schemas.presentationml.x2006.main.CTGroupShape;
import org.openxmlformats.schemas.presentationml.x2006.main.CTNotesSlide;
import org.openxmlformats.schemas.presentationml.x2006.main.CTShape;
import org.openxmlformats.schemas.presentationml.x2006.main.CTSlide;
import org.openxmlformats.schemas.presentationml.x2006.main.CTSlideIdListEntry;
public class HXFPowerPointExtractor extends POIXMLTextExtractor {
private HSLFXMLSlideShow slideshow;
public HXFPowerPointExtractor(Package container) throws XmlException, OpenXML4JException, IOException {
this(new HSLFXMLSlideShow(
new HSLFXML(container)
));
}
public HXFPowerPointExtractor(HSLFXMLSlideShow slideshow) {
super(slideshow);
this.slideshow = slideshow;
}
public static void main(String[] args) throws Exception {
if(args.length < 1) {
System.err.println("Use:");
System.err.println(" HXFPowerPointExtractor <filename.pptx>");
System.exit(1);
}
POIXMLTextExtractor extractor =
new HXFPowerPointExtractor(HXFDocument.openPackage(
new File(args[0])
));
System.out.println(extractor.getText());
}
/**
* Gets the slide and notes text
*/
public String getText() {
return getText(true, true);
}
/**
* Gets the requested text from the file
* @param slideText Should we retrieve text from slides?
* @param notesText Should we retrieve text from notes?
*/
public String getText(boolean slideText, boolean notesText) {
StringBuffer text = new StringBuffer();
CTSlideIdListEntry[] slideRefs =
slideshow._getHSLFXML().getSlideReferences().getSldIdArray();
for (int i = 0; i < slideRefs.length; i++) {
try {
CTSlide slide =
slideshow._getHSLFXML().getSlide(slideRefs[i]);
CTNotesSlide notes =
slideshow._getHSLFXML().getNotes(slideRefs[i]);
if(slideText) {
extractText(slide.getCSld().getSpTree(), text);
}
if(notesText && notes != null) {
extractText(notes.getCSld().getSpTree(), text);
}
} catch(Exception e) {
throw new RuntimeException(e);
}
}
return text.toString();
}
private void extractText(CTGroupShape gs, StringBuffer text) {
CTShape[] shapes = gs.getSpArray();
for (int i = 0; i < shapes.length; i++) {
CTTextBody textBody =
shapes[i].getTxBody();
if(textBody != null) {
CTTextParagraph[] paras =
textBody.getPArray();
for (int j = 0; j < paras.length; j++) {
CTRegularTextRun[] textRuns =
paras[j].getRArray();
for (int k = 0; k < textRuns.length; k++) {
text.append( textRuns[k].getT() );
}
// End each paragraph with a new line
text.append("\n");
}
}
}
}
}

View File

@ -21,7 +21,6 @@ import java.io.File;
import org.apache.poi.hxf.HXFDocument;
import org.openxml4j.opc.Package;
import org.openxml4j.opc.PackagePart;
import org.openxmlformats.schemas.presentationml.x2006.main.CTSlideIdList;
import org.openxmlformats.schemas.presentationml.x2006.main.CTSlideIdListEntry;
import org.openxmlformats.schemas.presentationml.x2006.main.CTSlideMasterIdListEntry;

View File

@ -0,0 +1,101 @@
/* ====================================================================
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.hslf.extractor;
import java.io.File;
import org.apache.poi.hslf.HSLFXML;
import org.apache.poi.hslf.usermodel.HSLFXMLSlideShow;
import org.apache.poi.hxf.HXFDocument;
import junit.framework.TestCase;
/**
* Tests for HXFPowerPointExtractor
*/
public class TestHXFPowerPointExtractor extends TestCase {
/**
* A simple file
*/
private HSLFXML xmlA;
protected void setUp() throws Exception {
super.setUp();
File fileA = new File(
System.getProperty("HSLF.testdata.path") +
File.separator + "sample.pptx"
);
xmlA = new HSLFXML(HXFDocument.openPackage(fileA));
}
/**
* Get text out of the simple file
*/
public void testGetSimpleText() throws Exception {
new HXFPowerPointExtractor(xmlA.getPackage());
new HXFPowerPointExtractor(new HSLFXMLSlideShow(xmlA));
HXFPowerPointExtractor extractor =
new HXFPowerPointExtractor(xmlA.getPackage());
extractor.getText();
String text = extractor.getText();
assertTrue(text.length() > 0);
// Check Basics
assertTrue(text.startsWith("Lorem ipsum dolor sit amet\n"));
assertTrue(text.endsWith("amet\n\n\n\n"));
// Just slides, no notes
text = extractor.getText(true, false);
assertEquals(
"Lorem ipsum dolor sit amet\n" +
"Nunc at risus vel erat tempus posuere. Aenean non ante.\n" +
"\n" +
"Lorem ipsum dolor sit amet\n" +
"Lorem\n" +
"ipsum\n" +
"dolor\n" +
"sit\n" +
"amet\n" +
"\n", text
);
// Just notes, no slides
text = extractor.getText(false, true);
assertEquals(
"\n\n\n\n", text
);
// Both
text = extractor.getText(true, true);
assertEquals(
"Lorem ipsum dolor sit amet\n" +
"Nunc at risus vel erat tempus posuere. Aenean non ante.\n" +
"\n\n\n" +
"Lorem ipsum dolor sit amet\n" +
"Lorem\n" +
"ipsum\n" +
"dolor\n" +
"sit\n" +
"amet\n" +
"\n\n\n", text
);
}
}