Examples with XHTMLOfficeDocument org.xwiki.officeimporter.document.XHTMLOfficeDocument used on opensource projects

Example 1 with XHTMLOfficeDocument

use of org.xwiki.officeimporter.document.XHTMLOfficeDocument in project xwiki-platform by xwiki.

the class DefaultXHTMLOfficeDocumentBuilder method build.

@Override
public XHTMLOfficeDocument build(InputStream officeFileStream, String officeFileName, DocumentReference reference, boolean filterStyles) throws OfficeImporterException {
    // Accents seems to cause issues in some conditions
    // See https://jira.xwiki.org/browse/XWIKI-14692
    String cleanedOfficeFileName = StringUtils.stripAccents(officeFileName);
    // Invoke the office document converter.
    Map<String, InputStream> inputStreams = new HashMap<String, InputStream>();
    inputStreams.put(cleanedOfficeFileName, officeFileStream);
    Map<String, byte[]> artifacts;
    // The office converter uses the output file name extension to determine the output format/syntax.
    String outputFileName = StringUtils.substringBeforeLast(cleanedOfficeFileName, ".") + ".html";
    try {
        artifacts = this.officeServer.getConverter().convert(inputStreams, cleanedOfficeFileName, outputFileName);
    } catch (OfficeConverterException ex) {
        String message = "Error while converting document [%s] into html.";
        throw new OfficeImporterException(String.format(message, officeFileName), ex);
    }
    // Prepare the parameters for HTML cleaning.
    Map<String, String> params = new HashMap<String, String>();
    params.put("targetDocument", this.entityReferenceSerializer.serialize(reference));
    // Extract the images that are embedded through the Data URI scheme and add them to the other artifacts so that
    // they end up as attachments.
    params.put("attachEmbeddedImages", "true");
    if (filterStyles) {
        params.put("filterStyles", "strict");
    }
    // Parse and clean the HTML output.
    HTMLCleanerConfiguration configuration = this.officeHtmlCleaner.getDefaultConfiguration();
    configuration.setParameters(params);
    Reader html = getReader(artifacts.remove(outputFileName));
    Document xhtmlDoc = this.officeHtmlCleaner.clean(html, configuration);
    @SuppressWarnings("unchecked") Map<String, byte[]> embeddedImages = (Map<String, byte[]>) xhtmlDoc.getUserData("embeddedImages");
    if (embeddedImages != null) {
        artifacts.putAll(embeddedImages);
    }
    // Return a new XHTMLOfficeDocument instance.
    return new XHTMLOfficeDocument(xhtmlDoc, artifacts);
}

Example 2 with XHTMLOfficeDocument

use of org.xwiki.officeimporter.document.XHTMLOfficeDocument in project xwiki-platform by xwiki.

the class DefaultXHTMLOfficeDocumentBuilderTest method testXHTMLOfficeDocumentBuilding.

@Test
public void testXHTMLOfficeDocumentBuilding() throws Exception {
    DocumentReference documentReference = new DocumentReference("wiki", Arrays.asList("Path", "To"), "Page");
    when(this.entityReferenceSerializer.serialize(documentReference)).thenReturn("wiki:Path.To.Page");
    InputStream officeFileStream = new ByteArrayInputStream("office content".getBytes());
    Map<String, byte[]> artifacts = new HashMap<String, byte[]>();
    artifacts.put("file.html", "HTML content".getBytes());
    artifacts.put("file.txt", "Text content".getBytes());
    when(this.officeConverter.convert(Collections.singletonMap("file.odt", officeFileStream), "file.odt", "file.html")).thenReturn(artifacts);
    Map<String, byte[]> embeddedImages = Collections.singletonMap("image.png", "Image content".getBytes());
    Document xhtmlDoc = mock(Document.class);
    when(xhtmlDoc.getUserData("embeddedImages")).thenReturn(embeddedImages);
    HTMLCleanerConfiguration config = mock(HTMLCleanerConfiguration.class);
    when(this.officeHTMLCleaner.getDefaultConfiguration()).thenReturn(config);
    when(this.officeHTMLCleaner.clean(any(Reader.class), eq(config))).thenReturn(xhtmlDoc);
    XHTMLOfficeDocument result = this.mocker.getComponentUnderTest().build(officeFileStream, "file.odt", documentReference, true);
    Map<String, String> params = new HashMap<String, String>();
    params.put("targetDocument", "wiki:Path.To.Page");
    params.put("attachEmbeddedImages", "true");
    params.put("filterStyles", "strict");
    verify(config).setParameters(params);
    assertEquals(xhtmlDoc, result.getContentDocument());
    Map<String, byte[]> expectedArtifacts = new HashMap<String, byte[]>();
    expectedArtifacts.put("file.txt", artifacts.get("file.txt"));
    expectedArtifacts.put("image.png", embeddedImages.get("image.png"));
    assertEquals(expectedArtifacts, result.getArtifacts());
}

Example 3 with XHTMLOfficeDocument

use of org.xwiki.officeimporter.document.XHTMLOfficeDocument in project xwiki-platform by xwiki.

the class DefaultXDOMOfficeDocumentBuilder method build.

@Override
public XDOMOfficeDocument build(XHTMLOfficeDocument xhtmlOfficeDocument) throws OfficeImporterException {
    Document xhtmlDoc = xhtmlOfficeDocument.getContentDocument();
    HTMLUtils.stripHTMLEnvelope(xhtmlDoc);
    XDOM xdom = null;
    try {
        xdom = this.xHtmlParser.parse(new StringReader(HTMLUtils.toString(xhtmlDoc)));
    } catch (ParseException ex) {
        throw new OfficeImporterException("Error: Could not parse xhtml office content.", ex);
    }
    return new XDOMOfficeDocument(xdom, xhtmlOfficeDocument.getArtifacts(), this.componentManager);
}