Java Code Examples for org.jsoup.nodes.Document#createShell()

The following examples show how to use org.jsoup.nodes.Document#createShell() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: JavaScriptBootstrapUITest.java    From flow with Apache License 2.0 6 votes vote down vote up 
@Test
public void should_restoreIndexHtmlTitle() {
    AppShellRegistry registry = new AppShellRegistry();
    mocks.setAppShellRegistry(registry);
    VaadinRequest request = mocks.createRequest(mocks, "/foo");

    Document document = Document.createShell("");
    org.jsoup.nodes.Element title = document.createElement("title");
    title.appendText("index-html-title");
    document.head().appendChild(title);

    registry.modifyIndexHtml(document, request);

    ui.navigate("empty");
    assertNull(ui.getInternals().getTitle());
    ui.navigate("dirty");
    assertEquals("index-html-title", ui.getInternals().getTitle());
}
Example 2
Source File: JsoupEx.java    From FairEmail with GNU General Public License v3.0 6 votes vote down vote up 
static Document parse(String html) {
        try {
/*
        org.jsoup.UncheckedIOException: java.io.IOException: Input is binary and unsupported
                at org.jsoup.parser.CharacterReader.<init>(SourceFile:38)
                at org.jsoup.parser.CharacterReader.<init>(SourceFile:43)
                at org.jsoup.parser.TreeBuilder.initialiseParse(SourceFile:38)
                at org.jsoup.parser.HtmlTreeBuilder.initialiseParse(SourceFile:65)
                at org.jsoup.parser.TreeBuilder.parse(SourceFile:46)
                at org.jsoup.parser.Parser.parse(SourceFile:107)
                at org.jsoup.Jsoup.parse(SourceFile:58)
*/
            return Jsoup.parse(html.replace("\0", ""));
        } catch (OutOfMemoryError ex) {
            Log.e(ex);
            Document document = Document.createShell("");
            Element strong = document.createElement("strong");
            strong.text(Log.formatThrowable(ex));
            document.body().appendChild(strong);
            return document;
        }
    }
Example 3
Source File: Cleaner.java    From astor with GNU General Public License v2.0 5 votes vote down vote up 
public boolean isValidBodyHtml(String bodyHtml) {
    Document clean = Document.createShell("");
    Document dirty = Document.createShell("");
    ParseErrorList errorList = ParseErrorList.tracking(1);
    List<Node> nodes = Parser.parseFragment(bodyHtml, dirty.body(), "", errorList);
    dirty.body().insertChildren(0, nodes);
    int numDiscarded = copySafeNodes(dirty.body(), clean.body());
    return numDiscarded == 0 && errorList.size() == 0;
}
Example 4
Source File: Parser.java    From jsoup-learning with MIT License 5 votes vote down vote up 
/**
 * Parse a fragment of HTML into the {@code body} of a Document.
 *
 * @param bodyHtml fragment of HTML
 * @param baseUri base URI of document (i.e. original fetch location), for resolving relative URLs.
 *
 * @return Document, with empty head, and HTML parsed into body
 */
public static Document parseBodyFragment(String bodyHtml, String baseUri) {
    Document doc = Document.createShell(baseUri);
    Element body = doc.body();
    List<Node> nodeList = parseFragment(bodyHtml, body, baseUri);
    Node[] nodes = nodeList.toArray(new Node[nodeList.size()]); // the node list gets modified when re-parented
    for (Node node : nodes) {
        body.appendChild(node);
    }
    return doc;
}
Example 5
Source File: XmlTreeBuilderTest.java    From astor with GNU General Public License v2.0 5 votes vote down vote up 
@Test
public void testCreatesValidProlog() {
    Document document = Document.createShell("");
    document.outputSettings().syntax(Syntax.xml);
    document.charset(Charset.forName("utf-8"));
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
        "<html>\n" +
        " <head></head>\n" +
        " <body></body>\n" +
        "</html>", document.outerHtml());
}
Example 6
Source File: Parser.java    From astor with GNU General Public License v2.0 5 votes vote down vote up 
/**
 * Parse a fragment of HTML into the {@code body} of a Document.
 *
 * @param bodyHtml fragment of HTML
 * @param baseUri base URI of document (i.e. original fetch location), for resolving relative URLs.
 *
 * @return Document, with empty head, and HTML parsed into body
 */
public static Document parseBodyFragment(String bodyHtml, String baseUri) {
    Document doc = Document.createShell(baseUri);
    Element body = doc.body();
    List<Node> nodeList = parseFragment(bodyHtml, body, baseUri);
    Node[] nodes = nodeList.toArray(new Node[nodeList.size()]); // the node list gets modified when re-parented
    for (int i = nodes.length - 1; i > 0; i--) {
        nodes[i].remove();
    }
    for (Node node : nodes) {
        body.appendChild(node);
    }
    return doc;
}
Example 7
Source File: Cleaner.java    From astor with GNU General Public License v2.0 5 votes vote down vote up 
public boolean isValidBodyHtml(String bodyHtml) {
    Document clean = Document.createShell("");
    Document dirty = Document.createShell("");
    ParseErrorList errorList = ParseErrorList.tracking(1);
    List<Node> nodes = Parser.parseFragment(bodyHtml, dirty.body(), "", errorList);
    dirty.body().insertChildren(0, nodes);
    int numDiscarded = copySafeNodes(dirty.body(), clean.body());
    return numDiscarded == 0 && errorList.size() == 0;
}
Example 8
Source File: XmlTreeBuilderTest.java    From astor with GNU General Public License v2.0 5 votes vote down vote up 
@Test
public void testCreatesValidProlog() {
    Document document = Document.createShell("");
    document.outputSettings().syntax(Syntax.xml);
    document.charset(Charset.forName("utf-8"));
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
        "<html>\n" +
        " <head></head>\n" +
        " <body></body>\n" +
        "</html>", document.outerHtml());
}
Example 9
Source File: Parser.java    From astor with GNU General Public License v2.0 5 votes vote down vote up 
/**
 * Parse a fragment of HTML into the {@code body} of a Document.
 *
 * @param bodyHtml fragment of HTML
 * @param baseUri base URI of document (i.e. original fetch location), for resolving relative URLs.
 *
 * @return Document, with empty head, and HTML parsed into body
 */
public static Document parseBodyFragment(String bodyHtml, String baseUri) {
    Document doc = Document.createShell(baseUri);
    Element body = doc.body();
    List<Node> nodeList = parseFragment(bodyHtml, body, baseUri);
    Node[] nodes = nodeList.toArray(new Node[nodeList.size()]); // the node list gets modified when re-parented
    for (int i = nodes.length - 1; i > 0; i--) {
        nodes[i].remove();
    }
    for (Node node : nodes) {
        body.appendChild(node);
    }
    return doc;
}
Example 10
Source File: Parser.java    From astor with GNU General Public License v2.0 5 votes vote down vote up 
/**
 * Parse a fragment of HTML into the {@code body} of a Document.
 *
 * @param bodyHtml fragment of HTML
 * @param baseUri base URI of document (i.e. original fetch location), for resolving relative URLs.
 *
 * @return Document, with empty head, and HTML parsed into body
 */
public static Document parseBodyFragment(String bodyHtml, String baseUri) {
    Document doc = Document.createShell(baseUri);
    Element body = doc.body();
    List<Node> nodeList = parseFragment(bodyHtml, body, baseUri);
    Node[] nodes = nodeList.toArray(new Node[nodeList.size()]); // the node list gets modified when re-parented
    for (int i = nodes.length - 1; i > 0; i--) {
        nodes[i].remove();
    }
    for (Node node : nodes) {
        body.appendChild(node);
    }
    return doc;
}
Example 11
Source File: ElementUtilTest.java    From flow with Apache License 2.0 5 votes vote down vote up 
@Test
public void toAndFromJsoup() {
    final String EXPECTED_TEXT_1 = "Some text";
    final String EXPECTED_TEXT_2 = "Other text";

    Element originalElement = ElementFactory.createDiv();
    originalElement.appendChild(ElementFactory.createParagraph(EXPECTED_TEXT_1)
            .appendChild(ElementFactory.createDiv(EXPECTED_TEXT_2)));

    Document jDocument = Document.createShell("http://example.com");

    Node jNode = ElementUtil.toJsoup(jDocument, originalElement);

    Optional<Element> optionalElement = ElementUtil.fromJsoup(jNode);

    Assert.assertTrue("Element should have been created from jNode",
            optionalElement.isPresent());

    Element recreatedElement = optionalElement.get();

    // root
    Assert.assertEquals("Root element should be div", "div",
            recreatedElement.getTag());
    // child
    Assert.assertEquals("Child element should be a paragraph", "p",
            recreatedElement.getChild(0).getTag());
    Assert.assertEquals("Child element should have text", EXPECTED_TEXT_1,
            recreatedElement.getChild(0).getText());
    // grand-child (#1, since #0 is the text node)
    Assert.assertEquals("Grand-child element should be a div", "div",
            recreatedElement.getChild(0).getChild(1).getTag());
    Assert.assertEquals("Grand-child element should have text",
            EXPECTED_TEXT_2,
            recreatedElement.getChild(0).getChild(1).getText());
}
Example 12
Source File: VaadinAppShellInitializerTest.java    From flow with Apache License 2.0 5 votes vote down vote up 
@Before
public void setup() throws Exception {
    logger = mockLog(VaadinAppShellInitializer.class);
    assertNull(getDevModeHandler());

    servletContext = Mockito.mock(ServletContext.class);
    mocks = new MockServletServiceSessionSetup();
    service = mocks.getService();
    Mockito.when(servletContext.getAttribute(Mockito.anyString()))
            .then(invocationOnMock -> attributeMap
                    .get(invocationOnMock.getArguments()[0].toString()));
    Mockito.doAnswer(invocationOnMock -> attributeMap.put(
            invocationOnMock.getArguments()[0].toString(),
            invocationOnMock.getArguments()[1])).when(servletContext)
            .setAttribute(Mockito.anyString(), Mockito.any());

    ServletRegistration registration = Mockito
            .mock(ServletRegistration.class);
    context = new VaadinServletContext(servletContext);

    initParams = new HashMap<>();
    Mockito.when(registration.getInitParameters()).thenReturn(initParams);

    classes = new HashSet<>();

    Map<String, ServletRegistration> registry = new HashMap<>();
    registry.put("foo", registration);
    Mockito.when(servletContext.getServletRegistrations())
            .thenReturn((Map) registry);
    Mockito.when(servletContext.getInitParameterNames())
            .thenReturn(Collections.emptyEnumeration());

    initializer = new VaadinAppShellInitializer();
    document = Document.createShell("");

    pushConfiguration = Mockito.mock(PushConfiguration.class);
}
Example 13
Source File: HtmlHelper.java    From FairEmail with GNU General Public License v3.0 5 votes vote down vote up 
static Document sanitizeView(Context context, Document parsed, boolean show_images) {
    try {
        return sanitize(context, parsed, true, show_images);
    } catch (Throwable ex) {
        // OutOfMemoryError
        Log.e(ex);
        Document document = Document.createShell("");
        Element strong = document.createElement("strong");
        strong.text(Log.formatThrowable(ex));
        document.body().appendChild(strong);
        return document;
    }
}
Example 14
Source File: HtmlHelper.java    From FairEmail with GNU General Public License v3.0 5 votes vote down vote up 
static Document sanitizeCompose(Context context, String html, boolean show_images) {
    try {
        Document parsed = JsoupEx.parse(html);
        return sanitize(context, parsed, false, show_images);
    } catch (Throwable ex) {
        // OutOfMemoryError
        Log.e(ex);
        Document document = Document.createShell("");
        Element strong = document.createElement("strong");
        strong.text(Log.formatThrowable(ex));
        document.body().appendChild(strong);
        return document;
    }
}
Example 15
Source File: Cleaner.java    From astor with GNU General Public License v2.0 3 votes vote down vote up 
/**
 Determines if the input document <b>body</b>is valid, against the whitelist. It is considered valid if all the tags and attributes
 in the input HTML are allowed by the whitelist, and that there is no content in the <code>head</code>.
 <p>
 This method can be used as a validator for user input. An invalid document will still be cleaned successfully
 using the {@link #clean(Document)} document. If using as a validator, it is recommended to still clean the document
 to ensure enforced attributes are set correctly, and that the output is tidied.
 </p>
 @param dirtyDocument document to test
 @return true if no tags or attributes need to be removed; false if they do
 */
public boolean isValid(Document dirtyDocument) {
    Validate.notNull(dirtyDocument);

    Document clean = Document.createShell(dirtyDocument.baseUri());
    int numDiscarded = copySafeNodes(dirtyDocument.body(), clean.body());
    return numDiscarded == 0
        && dirtyDocument.head().childNodes().size() == 0; // because we only look at the body, but we start from a shell, make sure there's nothing in the head
}
Example 16
Source File: Cleaner.java    From astor with GNU General Public License v2.0 3 votes vote down vote up 
/**
 Determines if the input document <b>body</b>is valid, against the whitelist. It is considered valid if all the tags and attributes
 in the input HTML are allowed by the whitelist, and that there is no content in the <code>head</code>.
 <p>
 This method can be used as a validator for user input. An invalid document will still be cleaned successfully
 using the {@link #clean(Document)} document. If using as a validator, it is recommended to still clean the document
 to ensure enforced attributes are set correctly, and that the output is tidied.
 </p>
 @param dirtyDocument document to test
 @return true if no tags or attributes need to be removed; false if they do
 */
public boolean isValid(Document dirtyDocument) {
    Validate.notNull(dirtyDocument);

    Document clean = Document.createShell(dirtyDocument.baseUri());
    int numDiscarded = copySafeNodes(dirtyDocument.body(), clean.body());
    return numDiscarded == 0
        && dirtyDocument.head().childNodes().size() == 0; // because we only look at the body, but we start from a shell, make sure there's nothing in the head
}
Example 17
Source File: Utils.java    From Man-Man with GNU General Public License v3.0 3 votes vote down vote up 
/**
 * Loads CSS from assets folder according to selected theme.
 * Fragment should be in attached state for this
 *
 * @param context context to retrieve theme properties from
 * @param url base url of page
 * @param htmlContent page with content to splatter color on...
 * @return html string
 */
public static String getWebWithCss(@NonNull Context context, @NonNull String url, @Nullable String htmlContent) {
    SharedPreferences prefs = PreferenceManager.getDefaultSharedPreferences(context);
    final String theme = prefs.getString("app.theme", "light");

    Document doc = Document.createShell(url);
    doc.head().append("<link rel=\"stylesheet\" href=\"file:///android_asset/css/" + theme + ".css\" type=\"text/css\" media=\"all\" title=\"Standard\"/>");
    return doc.html().replace("<body>", "<body>" + htmlContent); // ugly hack, huh? Well, why don't you come up with something?
}