Examples with HTMLCleanerConfiguration org.xwiki.xml.html.HTMLCleanerConfiguration used on opensource projects

Example 1 with HTMLCleanerConfiguration

use of org.xwiki.xml.html.HTMLCleanerConfiguration 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 HTMLCleanerConfiguration

use of org.xwiki.xml.html.HTMLCleanerConfiguration in project xwiki-platform by xwiki.

the class OfficeHTMLCleaner method clean.

@Override
public Document clean(Reader originalHtmlContent) {
    // Add special parameters used in filters
    HTMLCleanerConfiguration configuration = getDefaultConfiguration();
    configuration.setParameters(Collections.singletonMap("filterStyles", "strict"));
    return clean(originalHtmlContent, configuration);
}

Example 3 with HTMLCleanerConfiguration

use of org.xwiki.xml.html.HTMLCleanerConfiguration in project xwiki-platform by xwiki.

the class DefaultHTMLCleaner method clean.

@Override
public String clean(String dirtyHTML) {
    // Sort the list of specific filters based on their priority.
    Collections.sort(specificFilters, new Comparator<HTMLFilter>() {

        @Override
        public int compare(HTMLFilter alice, HTMLFilter bob) {
            return alice.getPriority() - bob.getPriority();
        }
    });
    // We have to remove or replace the HTML elements that were added by the WYSIWYG editor only for internal
    // reasons, before any cleaning filter is applied. Otherwise cleaning filters might transform these
    // WYSIWYG-specific HTML elements making their removal difficult. We cannot transform the WYSIWYG output on the
    // client side because the editor is a widget that can be used independently inside or outside an HTML form and
    // thus it doesn't know when its current value is submitted.
    HTMLCleanerConfiguration config = cleaner.getDefaultConfiguration();
    List<org.xwiki.xml.html.filter.HTMLFilter> filters = new ArrayList<org.xwiki.xml.html.filter.HTMLFilter>();
    filters.addAll(specificFilters);
    filters.addAll(config.getFilters());
    config.setFilters(filters);
    Document document = cleaner.clean(new StringReader(dirtyHTML), config);
    return HTMLUtils.toString(document);
}

Example 4 with HTMLCleanerConfiguration

use of org.xwiki.xml.html.HTMLCleanerConfiguration in project xwiki-platform by xwiki.

the class DefaultPresentationBuilderTest method build.

@Test
public void build() throws Exception {
    DocumentReference documentReference = new DocumentReference("wiki", Arrays.asList("Path", "To"), "Page");
    when(this.entityReferenceSerializer.serialize(documentReference)).thenReturn("wiki:Path.To.Page");
    DocumentModelBridge document = mock(DocumentModelBridge.class);
    DocumentAccessBridge dab = this.mocker.getInstance(DocumentAccessBridge.class);
    when(dab.getTranslatedDocumentInstance(documentReference)).thenReturn(document);
    when(document.getSyntax()).thenReturn(Syntax.XWIKI_2_1);
    InputStream officeFileStream = new ByteArrayInputStream("Presentation content".getBytes());
    Map<String, byte[]> artifacts = new HashMap<String, byte[]>();
    byte[] firstSlide = "first slide".getBytes();
    byte[] secondSlide = "second slide".getBytes();
    artifacts.put("img0.jpg", firstSlide);
    artifacts.put("img0.html", new byte[0]);
    artifacts.put("text0.html", new byte[0]);
    artifacts.put("img1.jpg", secondSlide);
    artifacts.put("img1.html", new byte[0]);
    artifacts.put("text1.html", new byte[0]);
    when(this.officeConverter.convert(Collections.singletonMap("file.odp", officeFileStream), "file.odp", "img0.html")).thenReturn(artifacts);
    HTMLCleanerConfiguration config = mock(HTMLCleanerConfiguration.class);
    when(this.officeHTMLCleaner.getDefaultConfiguration()).thenReturn(config);
    Document xhtmlDoc = XMLUtils.createDOMDocument();
    xhtmlDoc.appendChild(xhtmlDoc.createElement("html"));
    String presentationHTML = "<p><img src=\"file-slide0.jpg\"/></p><p><img src=\"file-slide1.jpg\"/></p>";
    when(this.officeHTMLCleaner.clean(any(Reader.class), eq(config))).then(returnMatchingDocument(presentationHTML, xhtmlDoc));
    XDOM galleryContent = new XDOM(Collections.<Block>emptyList());
    when(this.xhtmlParser.parse(any(Reader.class))).thenReturn(galleryContent);
    XDOMOfficeDocument result = this.mocker.getComponentUnderTest().build(officeFileStream, "file.odp", documentReference);
    verify(config).setParameters(Collections.singletonMap("targetDocument", "wiki:Path.To.Page"));
    Map<String, byte[]> expectedArtifacts = new HashMap<String, byte[]>();
    expectedArtifacts.put("file-slide0.jpg", firstSlide);
    expectedArtifacts.put("file-slide1.jpg", secondSlide);
    assertEquals(expectedArtifacts, result.getArtifacts());
    assertEquals("wiki:Path.To.Page", result.getContentDocument().getMetaData().getMetaData(MetaData.BASE));
    List<ExpandedMacroBlock> macros = result.getContentDocument().getBlocks(new ClassBlockMatcher(ExpandedMacroBlock.class), Block.Axes.CHILD);
    Assert.assertEquals(1, macros.size());
    Assert.assertEquals("gallery", macros.get(0).getId());
    Assert.assertEquals(galleryContent, macros.get(0).getChildren().get(0));
}

Example 5 with HTMLCleanerConfiguration

use of org.xwiki.xml.html.HTMLCleanerConfiguration in project xwiki-platform by xwiki.

the class PdfExportImpl method convertToStrictXHtml.

/**
 * Cleans up an HTML document, turning it into valid XHTML.
 *
 * @param input the source HTML to process
 * @return the cleaned up source
 */
private String convertToStrictXHtml(String input) {
    LOGGER.debug("Cleaning HTML:\n{}", input);
    HTMLCleaner cleaner = Utils.getComponent(HTMLCleaner.class);
    HTMLCleanerConfiguration config = cleaner.getDefaultConfiguration();
    List<HTMLFilter> filters = new ArrayList<HTMLFilter>(config.getFilters());
    filters.add(Utils.getComponent(HTMLFilter.class, "uniqueId"));
    config.setFilters(filters);
    String result = HTMLUtils.toString(cleaner.clean(new StringReader(input), config));
    LOGGER.debug("Cleaned XHTML:\n{}", result);
    return result;
}