Examples with WordExtractor org.apache.poi.hwpf.extractor.WordExtractor used on opensource projects

Example 11 with WordExtractor

use of org.apache.poi.hwpf.extractor.WordExtractor in project poi by apache.

the class TestBugs method test45473.

/**
     * Bug 45473 - HWPF cannot read file after save
     */
@Test
public void test45473() throws IOException {
    // Fetch the current text
    HWPFDocument doc1 = HWPFTestDataSamples.openSampleFile("Bug45473.doc");
    WordExtractor wordExtractor = new WordExtractor(doc1);
    final String text1;
    try {
        text1 = wordExtractor.getText().trim();
    } finally {
        wordExtractor.close();
        doc1.close();
    }
    // Re-load, then re-save and re-check
    doc1 = HWPFTestDataSamples.openSampleFile("Bug45473.doc");
    HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack(doc1);
    WordExtractor wordExtractor2 = new WordExtractor(doc2);
    final String text2;
    try {
        text2 = wordExtractor2.getText().trim();
    } finally {
        wordExtractor2.close();
        doc1.close();
    }
    // the text in the saved document has some differences in line
    // separators but we tolerate that
    assertEqualsIgnoreNewline(text1.replaceAll("\n", ""), text2.replaceAll("\n", ""));
}

Example 12 with WordExtractor

use of org.apache.poi.hwpf.extractor.WordExtractor in project Gargoyle by callakrsos.

the class DocFileParser method DocFileContentParser.

public String DocFileContentParser(String fileName) {
    POIFSFileSystem fs = null;
    try {
        fs = new POIFSFileSystem(new FileInputStream(fileName));
        if (fileName.endsWith(".doc")) {
            HWPFDocument doc = new HWPFDocument(fs);
            WordExtractor we = new WordExtractor(doc);
            return we.getText();
        } else if (fileName.endsWith(".xls")) {
            ExcelExtractor ex = new ExcelExtractor(fs);
            ex.setFormulasNotResults(true);
            ex.setIncludeSheetNames(true);
            return ex.getText();
        } else if (fileName.endsWith(".ppt")) {
            PowerPointExtractor extractor = new PowerPointExtractor(fs);
            return extractor.getText();
        }
    } catch (Exception e) {
        LOGGER.debug("document file cant be indexed");
    }
    return "";
}

Example 13 with WordExtractor

use of org.apache.poi.hwpf.extractor.WordExtractor in project poi by apache.

the class HWPFFileHandler method test.

// a test-case to test this locally without executing the full TestAllFiles
@Override
@Test
public void test() throws Exception {
    File file = new File("test-data/document/52117.doc");
    InputStream stream = new FileInputStream(file);
    try {
        handleFile(stream, file.getPath());
    } 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();
    }
}

Example 14 with WordExtractor

use of org.apache.poi.hwpf.extractor.WordExtractor in project poi by apache.

the class TestBugs method test47286.

/**
     * [FAILING] Bug 47286 - Word documents saves in wrong format if source
     * contains form elements
     */
@SuppressWarnings("deprecation")
@Test
public void test47286() throws IOException {
    // Fetch the current text
    HWPFDocument doc1 = HWPFTestDataSamples.openSampleFile("Bug47286.doc");
    WordExtractor wordExtractor = new WordExtractor(doc1);
    final String text1;
    try {
        text1 = wordExtractor.getText().trim();
    } finally {
        wordExtractor.close();
        doc1.close();
    }
    // Re-load, then re-save and re-check
    doc1 = HWPFTestDataSamples.openSampleFile("Bug47286.doc");
    HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack(doc1);
    WordExtractor wordExtractor2 = new WordExtractor(doc2);
    final String text2;
    try {
        text2 = wordExtractor2.getText().trim();
    } finally {
        wordExtractor2.close();
        doc1.close();
    }
    // the text in the saved document has some differences in line
    // separators but we tolerate that
    assertEqualsIgnoreNewline(text1.replaceAll("\n", ""), text2.replaceAll("\n", ""));
    assertEquals(doc1.getCharacterTable().getTextRuns().size(), doc2.getCharacterTable().getTextRuns().size());
    List<PlexOfField> expectedFields = doc1.getFieldsTables().getFieldsPLCF(FieldsDocumentPart.MAIN);
    List<PlexOfField> actualFields = doc2.getFieldsTables().getFieldsPLCF(FieldsDocumentPart.MAIN);
    assertEquals(expectedFields.size(), actualFields.size());
    assertTableStructures(doc1.getRange(), doc2.getRange());
}

Example 15 with WordExtractor

use of org.apache.poi.hwpf.extractor.WordExtractor in project poi by apache.

the class TestExtractorFactory method testPOIFS.

@Test
public void testPOIFS() throws Exception {
    // Excel
    assertTrue(ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(xls))) instanceof ExcelExtractor);
    assertTrue(ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(xls))).getText().length() > 200);
    // Word
    assertTrue(ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(doc))) instanceof WordExtractor);
    assertTrue(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))) instanceof PowerPointExtractor);
    assertTrue(ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(ppt))).getText().length() > 120);
    // Visio
    assertTrue(ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(vsd))) instanceof VisioTextExtractor);
    assertTrue(ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(vsd))).getText().length() > 50);
    // Publisher
    assertTrue(ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(pub))) instanceof PublisherTextExtractor);
    assertTrue(ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(pub))).getText().length() > 50);
    // Outlook msg
    assertTrue(ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(msg))) instanceof OutlookTextExtactor);
    assertTrue(ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(msg))).getText().length() > 50);
    // Text
    try {
        ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(txt)));
        fail();
    } catch (IOException e) {
    // Good
    }
}