Enable Word6Extractor in ExtractorFactory

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@959360 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Nick Burch 2010-06-30 16:08:10 +00:00
parent 999aecbaa1
commit fd922298ef
4 changed files with 70 additions and 8 deletions

View File

@ -34,6 +34,7 @@
<changes>
<release version="3.7-beta2" date="2010-??-??">
<action dev="POI-DEVELOPERS" type="add">Text Extraction support for older Word 6 and Word 95 files via HWPF</action>
<action dev="POI-DEVELOPERS" type="add">49508 - Allow the addition of paragraphs to XWPF Table Cells</action>
<action dev="POI-DEVELOPERS" type="fix">49446 - Don't consider 17.16.23 field codes as properly part of the paragraph's text</action>
<action dev="POI-DEVELOPERS" type="fix">XSLFSlideShow shouldn't break on .thmx (theme) files. Support for them is still very limited though</action>

View File

@ -38,6 +38,8 @@ import org.apache.poi.hsmf.datatypes.AttachmentChunks;
import org.apache.poi.hsmf.extractor.OutlookTextExtactor;
import org.apache.poi.hssf.extractor.EventBasedExcelExtractor;
import org.apache.poi.hssf.extractor.ExcelExtractor;
import org.apache.poi.hwpf.OldWordFileFormatException;
import org.apache.poi.hwpf.extractor.Word6Extractor;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
@ -218,7 +220,12 @@ public class ExtractorFactory {
}
}
if(entry.getName().equals("WordDocument")) {
// Old or new style word document?
try {
return new WordExtractor(poifsDir, fs);
} catch(OldWordFileFormatException e) {
return new Word6Extractor(poifsDir, fs);
}
}
if(entry.getName().equals("PowerPoint Document")) {
return new PowerPointExtractor(poifsDir, fs);

View File

@ -29,6 +29,7 @@ import org.apache.poi.hslf.extractor.PowerPointExtractor;
import org.apache.poi.hsmf.extractor.OutlookTextExtactor;
import org.apache.poi.hssf.extractor.EventBasedExcelExtractor;
import org.apache.poi.hssf.extractor.ExcelExtractor;
import org.apache.poi.hwpf.extractor.Word6Extractor;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.xslf.extractor.XSLFPowerPointExtractor;
@ -54,6 +55,8 @@ public class TestExtractorFactory extends TestCase {
private File xlsEmb;
private File doc;
private File doc6;
private File doc95;
private File docx;
private File dotx;
private File docEmb;
@ -79,6 +82,8 @@ public class TestExtractorFactory extends TestCase {
POIDataSamples wpTests = POIDataSamples.getDocumentInstance();
doc = wpTests.getFile("SampleDoc.doc");
doc6 = wpTests.getFile("Word6.doc");
doc95 = wpTests.getFile("Word95.doc");
docx = wpTests.getFile("SampleDoc.docx");
dotx = wpTests.getFile("test.dotx");
docEmb = wpTests.getFile("word_with_embeded.doc");
@ -135,6 +140,23 @@ public class TestExtractorFactory extends TestCase {
ExtractorFactory.createExtractor(doc).getText().length() > 120
);
assertTrue(
ExtractorFactory.createExtractor(doc6)
instanceof Word6Extractor
);
assertTrue(
ExtractorFactory.createExtractor(doc6).getText().length() > 20
);
assertTrue(
ExtractorFactory.createExtractor(doc95)
instanceof Word6Extractor
);
assertTrue(
ExtractorFactory.createExtractor(doc95).getText().length() > 120
);
assertTrue(
ExtractorFactory.createExtractor(docx)
instanceof XWPFWordExtractor
@ -231,6 +253,22 @@ public class TestExtractorFactory extends TestCase {
ExtractorFactory.createExtractor(new FileInputStream(doc)).getText().length() > 120
);
assertTrue(
ExtractorFactory.createExtractor(new FileInputStream(doc6))
instanceof Word6Extractor
);
assertTrue(
ExtractorFactory.createExtractor(new FileInputStream(doc6)).getText().length() > 20
);
assertTrue(
ExtractorFactory.createExtractor(new FileInputStream(doc95))
instanceof Word6Extractor
);
assertTrue(
ExtractorFactory.createExtractor(new FileInputStream(doc95)).getText().length() > 120
);
assertTrue(
ExtractorFactory.createExtractor(new FileInputStream(docx))
instanceof XWPFWordExtractor
@ -311,6 +349,22 @@ public class TestExtractorFactory extends TestCase {
ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(doc))).getText().length() > 120
);
assertTrue(
ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(doc6)))
instanceof Word6Extractor
);
assertTrue(
ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(doc6))).getText().length() > 20
);
assertTrue(
ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(doc95)))
instanceof Word6Extractor
);
assertTrue(
ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(doc95))).getText().length() > 120
);
// PowerPoint
assertTrue(
ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(ppt)))

View File

@ -169,7 +169,7 @@ public final class HWPFDocument extends HWPFDocumentCore
// Is this document too old for us?
if(_fib.getNFib() < 106) {
throw new OldWordFileFormatException("The document is too old (Word 95 or older) ");
throw new OldWordFileFormatException("The document is too old - Word 95 or older. Try HWPFOldDocument instead?");
}
// use the fib to determine the name of the table stream.