Examples with POIXMLTextExtractor org.apache.poi.POIXMLTextExtractor used on opensource projects

Example 6 with POIXMLTextExtractor

use of org.apache.poi.POIXMLTextExtractor in project poi by apache.

the class TestExtractorFactory method testPackage.

@Test
public void testPackage() throws Exception {
    // Excel
    POIXMLTextExtractor extractor = ExtractorFactory.createExtractor(OPCPackage.open(xlsx.toString(), PackageAccess.READ));
    assertTrue(extractor instanceof XSSFExcelExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(OPCPackage.open(xlsx.toString()));
    assertTrue(extractor.getText().length() > 200);
    extractor.close();
    // Word
    extractor = ExtractorFactory.createExtractor(OPCPackage.open(docx.toString()));
    assertTrue(extractor instanceof XWPFWordExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(OPCPackage.open(docx.toString()));
    assertTrue(extractor.getText().length() > 120);
    extractor.close();
    // PowerPoint
    extractor = ExtractorFactory.createExtractor(OPCPackage.open(pptx.toString()));
    assertTrue(extractor instanceof XSLFPowerPointExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(OPCPackage.open(pptx.toString()));
    assertTrue(extractor.getText().length() > 120);
    extractor.close();
    // Visio
    extractor = ExtractorFactory.createExtractor(OPCPackage.open(vsdx.toString()));
    assertTrue(extractor instanceof XDGFVisioExtractor);
    assertTrue(extractor.getText().length() > 20);
    extractor.close();
    // Text
    try {
        ExtractorFactory.createExtractor(OPCPackage.open(txt.toString()));
        fail("TestExtractorFactory.testPackage() failed on " + txt);
    } catch (UnsupportedFileFormatException e) {
    // Good
    } catch (Exception e) {
        System.out.println("TestExtractorFactory.testPackage() failed on " + txt);
        throw e;
    }
}

Example 7 with POIXMLTextExtractor

use of org.apache.poi.POIXMLTextExtractor in project poi by apache.

the class XSSFBEventBasedExcelExtractor method main.

public static void main(String[] args) throws Exception {
    if (args.length < 1) {
        System.err.println("Use:");
        System.err.println("  XSSFBEventBasedExcelExtractor <filename.xlsb>");
        System.exit(1);
    }
    POIXMLTextExtractor extractor = new XSSFBEventBasedExcelExtractor(args[0]);
    System.out.println(extractor.getText());
    extractor.close();
}

Example 8 with POIXMLTextExtractor

use of org.apache.poi.POIXMLTextExtractor in project tika by apache.

the class OOXMLExtractorFactory method parse.

public static void parse(InputStream stream, ContentHandler baseHandler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    Locale locale = context.get(Locale.class, Locale.getDefault());
    ExtractorFactory.setThreadPrefersEventExtractors(true);
    try {
        OOXMLExtractor extractor;
        OPCPackage pkg;
        // Locate or Open the OPCPackage for the file
        TikaInputStream tis = TikaInputStream.cast(stream);
        if (tis != null && tis.getOpenContainer() instanceof OPCPackage) {
            pkg = (OPCPackage) tis.getOpenContainer();
        } else if (tis != null && tis.hasFile()) {
            pkg = OPCPackage.open(tis.getFile().getPath(), PackageAccess.READ);
            tis.setOpenContainer(pkg);
        } else {
            InputStream shield = new CloseShieldInputStream(stream);
            pkg = OPCPackage.open(shield);
        }
        // Get the type, and ensure it's one we handle
        MediaType type = ZipContainerDetector.detectOfficeOpenXML(pkg);
        if (type == null || OOXMLParser.UNSUPPORTED_OOXML_TYPES.contains(type)) {
            // Not a supported type, delegate to Empty Parser
            EmptyParser.INSTANCE.parse(stream, baseHandler, metadata, context);
            return;
        }
        metadata.set(Metadata.CONTENT_TYPE, type.toString());
        // Have the appropriate OOXML text extractor picked
        POIXMLTextExtractor poiExtractor = null;
        // This has already been set by OOXMLParser's call to configure()
        // We can rely on this being non-null.
        OfficeParserConfig config = context.get(OfficeParserConfig.class);
        if (config.getUseSAXDocxExtractor()) {
            poiExtractor = trySXWPF(pkg);
        }
        if (poiExtractor == null && config.getUseSAXPptxExtractor()) {
            poiExtractor = trySXSLF(pkg);
        }
        if (poiExtractor == null) {
            poiExtractor = ExtractorFactory.createExtractor(pkg);
        }
        POIXMLDocument document = poiExtractor.getDocument();
        if (poiExtractor instanceof XSSFBEventBasedExcelExtractor) {
            extractor = new XSSFBExcelExtractorDecorator(context, poiExtractor, locale);
        } else if (poiExtractor instanceof XSSFEventBasedExcelExtractor) {
            extractor = new XSSFExcelExtractorDecorator(context, poiExtractor, locale);
        } else if (poiExtractor instanceof XWPFEventBasedWordExtractor) {
            extractor = new SXWPFWordExtractorDecorator(metadata, context, (XWPFEventBasedWordExtractor) poiExtractor);
            metadata.add("X-Parsed-By", XWPFEventBasedWordExtractor.class.getCanonicalName());
        } else if (poiExtractor instanceof XSLFEventBasedPowerPointExtractor) {
            extractor = new SXSLFPowerPointExtractorDecorator(metadata, context, (XSLFEventBasedPowerPointExtractor) poiExtractor);
            metadata.add("X-Parsed-By", XSLFEventBasedPowerPointExtractor.class.getCanonicalName());
        } else if (document == null) {
            throw new TikaException("Expecting UserModel based POI OOXML extractor with a document, but none found. " + "The extractor returned was a " + poiExtractor);
        } else if (document instanceof XMLSlideShow) {
            extractor = new XSLFPowerPointExtractorDecorator(context, (org.apache.poi.xslf.extractor.XSLFPowerPointExtractor) poiExtractor);
        } else if (document instanceof XWPFDocument) {
            extractor = new XWPFWordExtractorDecorator(context, (XWPFWordExtractor) poiExtractor);
        } else {
            extractor = new POIXMLTextExtractorDecorator(context, poiExtractor);
        }
        // Get the bulk of the metadata first, so that it's accessible during
        //  parsing if desired by the client (see TIKA-1109)
        extractor.getMetadataExtractor().extract(metadata);
        // Extract the text, along with any in-document metadata
        extractor.getXHTML(baseHandler, metadata, context);
    } catch (IllegalArgumentException e) {
        if (e.getMessage() != null && e.getMessage().startsWith("No supported documents found")) {
            throw new TikaException("TIKA-418: RuntimeException while getting content" + " for thmx and xps file types", e);
        } else {
            throw new TikaException("Error creating OOXML extractor", e);
        }
    } catch (InvalidFormatException e) {
        throw new TikaException("Error creating OOXML extractor", e);
    } catch (OpenXML4JException e) {
        throw new TikaException("Error creating OOXML extractor", e);
    } catch (XmlException e) {
        throw new TikaException("Error creating OOXML extractor", e);
    }
}