Browse Source

Bug 47304: use fixed encoding when extracting text in WordDocument

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1668367 13f79535-47bb-0310-9956-ffa450edef68
tags/REL_3_12_FINAL
Dominik Stadler 9 years ago
parent
commit
0850e7d846

+ 47
- 1
src/integrationtest/org/apache/poi/stress/HWPFFileHandler.java View File

@@ -18,12 +18,21 @@ package org.apache.poi.stress;

import static org.junit.Assert.assertNotNull;

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.PrintWriter;
import java.io.StringWriter;

import org.apache.poi.hdf.extractor.WordDocument;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.junit.Test;

@SuppressWarnings("deprecation")
public class HWPFFileHandler extends POIFSFileHandler {
@Override
public void handleFile(InputStream stream) throws Exception {
@@ -33,16 +42,53 @@ public class HWPFFileHandler extends POIFSFileHandler {
assertNotNull(doc.getEndnotes());
handlePOIDocument(doc);
// fails for many documents, but is deprecated anyway...
// handleWordDocument(doc);
}

protected void handleWordDocument(HWPFDocument doc) throws IOException {
ByteArrayOutputStream outStream = new ByteArrayOutputStream();
doc.write(outStream);

WordDocument wordDoc = new WordDocument(new ByteArrayInputStream(outStream.toByteArray()));
StringWriter docTextWriter = new StringWriter();
PrintWriter out = new PrintWriter(docTextWriter);
try {
wordDoc.writeAllText(out);
} finally {
out.close();
}
docTextWriter.close();
}



// a test-case to test this locally without executing the full TestAllFiles
@Test
public void test() throws Exception {
InputStream stream = new FileInputStream("test-data/document/HeaderFooterUnicode.doc");
File file = new File("test-data/document/47304.doc");

InputStream stream = new FileInputStream(file);
try {
handleFile(stream);
} finally {
stream.close();
}
handleExtracting(file);
stream = new FileInputStream(file);
try {
WordExtractor extractor = new WordExtractor(stream);
try {
assertNotNull(extractor.getText());
} finally {
extractor.close();
}
} finally {
stream.close();
}
}
}

+ 1
- 1
src/scratchpad/src/org/apache/poi/hdf/extractor/WordDocument.java View File

@@ -177,7 +177,7 @@ public final class WordDocument {
}
else
{
String sText = new String(_header, start, end-start);
String sText = new String(_header, start, end-start, "windows-1252");
out.write(sText);
}
}

+ 36
- 0
src/scratchpad/testcases/org/apache/poi/hdf/extractor/TestWordDocument.java View File

@@ -17,6 +17,15 @@

package org.apache.poi.hdf.extractor;

import static org.junit.Assert.*;

import java.io.IOException;
import java.io.PrintWriter;
import java.io.StringWriter;

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.HWPFTestDataSamples;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.junit.Test;


@@ -31,4 +40,31 @@ public class TestWordDocument {
//WordDocument.main(new String[] {"test-data/document/Word6.doc", "/tmp/test.doc"});
WordDocument.main(new String[] {"test-data/document/53446.doc", "/tmp/test.doc"});
}

@SuppressWarnings("deprecation")
@Test
public void test47304() throws IOException {
HWPFDocument doc = HWPFTestDataSamples.openSampleFile("47304.doc");
assertNotNull(doc);
WordExtractor extractor = new WordExtractor(doc);
String text = extractor.getText();
//System.out.println(text);
assertTrue("Had: " + text, text.contains("Just a \u201Ctest\u201D"));
extractor.close();
WordDocument wordDoc = new WordDocument("test-data/document/47304.doc");
StringWriter docTextWriter = new StringWriter();
PrintWriter out = new PrintWriter(docTextWriter);
try {
wordDoc.writeAllText(out);
} finally {
out.close();
}
docTextWriter.close();

//System.out.println(docTextWriter.toString());
assertTrue("Had: " + docTextWriter.toString(), docTextWriter.toString().contains("Just a \u201Ctest\u201D"));
}
}

BIN
test-data/document/47304.doc View File


Loading…
Cancel
Save