Java 类org.jsoup.helper.StringUtil 实例源码

项目：eclipse.jdt.ls 文件：HtmlToPlainText.java

@Override
public void head(Node node, int depth) {
    String name = node.nodeName();
    if (node instanceof TextNode) {
        append(((TextNode) node).text()); // TextNodes carry all user-readable text in the DOM.
    } else if (name.equals("ul")) {
        listNesting++;
    } else if (name.equals("li")) {
        append("\n ");
        for (int i = 1; i < listNesting; i++) {
            append("  ");
        }
        if (listNesting == 1) {
            append("* ");
        } else {
            append("- ");
        }
    } else if (name.equals("dt")) {
        append("  ");
    } else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5", "tr")) {
        append("\n");
    }
}

项目：common 文件：HtmlTreeBuilder.java

boolean inSelectScope(String targetName) {
    for (int pos = stack.size() -1; pos >= 0; pos--) {
        Element el = stack.get(pos);
        String elName = el.nodeName();
        if (elName.equals(targetName))
            return true;
        if (!StringUtil.in(elName, TagSearchSelectScope)) // all elements except
            return false;
    }
    Validate.fail("Should not be reachable");
    return false;
}

项目：hybris-commerce-eclipse-plugin 文件：AbstractHACCommunicationManager.java

/**
 * Send HTTP GET request to {@link #endpointUrl}, updates {@link #csrfToken}
 * token
 *
 * @return true if {@link #endpointUrl} is accessible
 * @throws IOException
 * @throws ClientProtocolException
 * @throws AuthenticationException 
 */
protected void fetchCsrfTokenFromHac() throws ClientProtocolException, IOException, AuthenticationException {
    final HttpGet getRequest = new HttpGet(getEndpointUrl());

    try {
        final HttpResponse response = httpClient.execute(getRequest, getContext());
        final String responseString = new BasicResponseHandler().handleResponse(response);
        csrfToken = getCsrfToken(responseString);

        if( StringUtil.isBlank(csrfToken) ) {
            throw new AuthenticationException(ErrorMessage.CSRF_TOKEN_CANNOT_BE_OBTAINED);
        }
    } catch (UnknownHostException error) {
        final String errorMessage = error.getMessage();
        final Matcher matcher = HACPreferenceConstants.HOST_REGEXP_PATTERN.matcher(getEndpointUrl());

        if (matcher.find() && matcher.group(1).equals(errorMessage)) {
            throw new UnknownHostException(
                    String.format(ErrorMessage.UNKNOWN_HOST_EXCEPTION_MESSAGE_FORMAT, matcher.group(1)));
        }
        throw error;
    }
}

项目：hybris-commerce-eclipse-plugin 文件：ScriptExecutorManager.java

/**
 * Prints script execution result to the console
 * 
 * @param jsonResult
 *            result of script import in JSON format.
 */
protected void displayScriptExecutionResult(final String jsonResult) {
    final JSONObject result = new JSONObject(jsonResult);
    final String output = result.getString(ScriptExecution.Response.OUPUT_KEY);
    final String stacktrace = result.getString(ScriptExecution.Response.STACK_TRACE_KEY);
    final String executionResult = result.getString(ScriptExecution.Response.RESULT_KEY);

    if (StringUtil.isBlank(stacktrace)) {
        ConsoleUtils.printMessage(RESULT_LABEL);
        ConsoleUtils.printMessage(executionResult);
        ConsoleUtils.printLine();
        ConsoleUtils.printMessage(OUTPUT_LABEL);
        ConsoleUtils.printMessage(output);
    } else {
        ConsoleUtils.printError(stacktrace);
        ConsoleUtils.printMessage(output);
    }
}

项目：common 文件：HtmlToPlainText.java

public void head(Node node, int depth) {
    String name = node.nodeName();
    if (node instanceof TextNode)
        append(((TextNode) node).text()); // TextNodes carry all user-readable text in the DOM.
    else if (name.equals("li"))
        append("\n * ");
    else if (name.equals("dt"))
        append("  ");
    else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5", "tr"))
        append("\n");
}

项目：common 文件：Element.java

/**
 * Get a CSS selector that will uniquely select this element.
 * <p>
 * If the element has an ID, returns #id;
 * otherwise returns the parent (if any) CSS selector, followed by {@literal '>'},
 * followed by a unique selector for the element (tag.class.class:nth-child(n)).
 * </p>
 *
 * @return the CSS Path that can be used to retrieve the element in a selector.
 */
public String cssSelector() {
    if (id().length() > 0)
        return "#" + id();

    // Translate HTML namespace ns:tag to CSS namespace syntax ns|tag
    String tagName = tagName().replace(':', '|');
    StringBuilder selector = new StringBuilder(tagName);
    String classes = StringUtil.join(classNames(), ".");
    if (classes.length() > 0)
        selector.append('.').append(classes);

    if (parent() == null || parent() instanceof Document) // don't add Document to selector, as will always have a html node
        return selector.toString();

    selector.insert(0, " > ");
    if (parent().select(selector.toString()).size() > 1)
        selector.append(String.format(
            ":nth-child(%d)", elementSiblingIndex() + 1));

    return parent().cssSelector() + selector.toString();
}

项目：common 文件：UrlConnectTest.java

@Test
public void fetchHandlesXml() throws IOException {
    // should auto-detect xml and use XML parser, unless explicitly requested the html parser
    String xmlUrl = "http://direct.infohound.net/tools/parse-xml.xml";
    Connection con = Jsoup.connect(xmlUrl);
    Document doc = con.get();
    Connection.Request req = con.request();
    assertTrue(req.parser().getTreeBuilder() instanceof XmlTreeBuilder);
    assertEquals("<xml> <link> one </link> <table> Two </table> </xml>", StringUtil.normaliseWhitespace(doc.outerHtml()));
}

项目：common 文件：HtmlParserTest.java

@Test public void handlesInvalidDoctypes() {
    // would previously throw invalid name exception on empty doctype
    Document doc = Jsoup.parse("<!DOCTYPE>");
    assertEquals(
            "<!doctype> <html> <head></head> <body></body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));

    doc = Jsoup.parse("<!DOCTYPE><html><p>Foo</p></html>");
    assertEquals(
            "<!doctype> <html> <head></head> <body> <p>Foo</p> </body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));

    doc = Jsoup.parse("<!DOCTYPE \u0000>");
    assertEquals(
            "<!doctype �> <html> <head></head> <body></body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));
}

项目：gestock 文件：HtmlTreeBuilder.java

boolean inSelectScope(String targetName) {
    for (int pos = stack.size() -1; pos >= 0; pos--) {
        Element el = stack.get(pos);
        String elName = el.nodeName();
        if (elName.equals(targetName))
            return true;
        if (!StringUtil.in(elName, TagSearchSelectScope)) // all elements except
            return false;
    }
    Validate.fail("Should not be reachable");
    return false;
}

项目：gestock 文件：HtmlToPlainText.java

public void head(Node node, int depth) {
    String name = node.nodeName();
    if (node instanceof TextNode)
        append(((TextNode) node).text()); // TextNodes carry all user-readable text in the DOM.
    else if (name.equals("li"))
        append("\n * ");
    else if (name.equals("dt"))
        append("  ");
    else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5", "tr"))
        append("\n");
}

项目：gestock 文件：HtmlToPlainText.java

public void tail(Node node, int depth) {
    String name = node.nodeName();
    if (StringUtil.in(name, "br", "dd", "dt", "p", "h1", "h2", "h3", "h4", "h5"))
        append("\n");
    else if (name.equals("a"))
        append(String.format(" <%s>", node.absUrl("href")));
}

项目：gestock 文件：HtmlToPlainText.java

private void append(String text) {
    if (text.startsWith("\n"))
        width = 0; // reset counter if starts with a newline. only from formats above, not in natural text
    if (text.equals(" ") &&
            (accum.length() == 0 || StringUtil.in(accum.substring(accum.length() - 1), " ", "\n")))
        return; // don't accumulate long runs of empty spaces

    if (text.length() + width > maxWidth) { // won't fit, needs to wrap
        String words[] = text.split("\\s+");
        for (int i = 0; i < words.length; i++) {
            String word = words[i];
            boolean last = i == words.length - 1;
            if (!last) // insert a space if not the last word
                word = word + " ";
            if (word.length() + width > maxWidth) { // wrap and reset counter
                accum.append("\n").append(word);
                width = word.length();
            } else {
                accum.append(word);
                width += word.length();
            }
        }
    } else { // fits as is, without need to wrap text
        accum.append(text);
        width += text.length();
    }
}

项目：gestock 文件：Element.java

/**
 * Get a CSS selector that will uniquely select this element.
 * <p>
 * If the element has an ID, returns #id;
 * otherwise returns the parent (if any) CSS selector, followed by {@literal '>'},
 * followed by a unique selector for the element (tag.class.class:nth-child(n)).
 * </p>
 *
 * @return the CSS Path that can be used to retrieve the element in a selector.
 */
public String cssSelector() {
    if (id().length() > 0)
        return "#" + id();

    StringBuilder selector = new StringBuilder(tagName());
    String classes = StringUtil.join(classNames(), ".");
    if (classes.length() > 0)
        selector.append('.').append(classes);

    if (parent() == null || parent() instanceof Document) // don't add Document to selector, as will always have a html node
        return selector.toString();

    selector.insert(0, " > ");
    if (parent().select(selector.toString()).size() > 1)
        selector.append(String.format(
            ":nth-child(%d)", elementSiblingIndex() + 1));

    return parent().cssSelector() + selector.toString();
}

项目：zongtui-webcrawler 文件：XTokenQueue.java

public static String trimQuotes(String str) {
    Validate.isTrue(str != null && str.length() > 0);
    String quote = str.substring(0, 1);
    if (StringUtil.in(quote, "\"", "'")) {
        Validate.isTrue(str.endsWith(quote), "Quote" + " for " + str + " is incomplete!");
        str = str.substring(1, str.length() - 1);
    }
    return str;
}

项目：ShanBay 文件：SpellView.java

protected void showDefinition(ReviewData paramReviewData)
{
  VocabularyData localVocabularyData = paramReviewData.getVocabulary();
  int i = AppletUtil.getAppletStatus(mActivity, "collins");
  if ((i == 2) || (i == 1))
  {
    if (!StringUtil.isBlank(localVocabularyData.getEnDefn()))
    {
      String str1 = localVocabularyData.getEnDefn();
      Matcher localMatcher = Pattern.compile("<vocab>(.*?)</vocab>").matcher(str1);
      String str2 = getBlank(this.mTvWordDefiniton, localVocabularyData.getContent());
      while (localMatcher.find())
        str1 = str1.replaceFirst(localMatcher.group(0), str2);
      mTvWordDefiniton.setText(str1.trim());
      return;
    }
    mTvWordDefiniton.setText(localVocabularyData.getCnDefinition().trim());
    return;
  }
  mTvWordDefiniton.setText(localVocabularyData.getCnDefinition().trim());
}

项目：ShanBay 文件：ExpSpellView.java

protected void showDefinition(ReviewData paramReviewData)
{
  VocabularyData localVocabularyData = paramReviewData.getVocabulary();
  if (this.mIsEnableCollins)
  {
    if (!StringUtil.isBlank(localVocabularyData.getEnDefn()))
    {
      String str1 = localVocabularyData.getEnDefn();
      Matcher localMatcher = Pattern.compile("<vocab>(.*?)</vocab>").matcher(str1);
      String str2 = getBlank(this.mTvWordDefiniton, localVocabularyData.getContent());
      while (localMatcher.find())
        str1 = str1.replaceFirst(localMatcher.group(0), str2);
      this.mTvWordDefiniton.setText(str1.trim());
      return;
    }
    this.mTvWordDefiniton.setText(StringUtils.trimToEmpty(localVocabularyData.getCnDefinition()));
    return;
  }
  this.mTvWordDefiniton.setText(StringUtils.trimToEmpty(localVocabularyData.getCnDefinition()));
}

项目：CN1ML-NetbeansModule 文件：HtmlTreeBuilder.java

void popStackToClose(String... elNames) {
    Iterator<Element> it = stack.descendingIterator();
    while (it.hasNext()) {
        Element next = it.next();
        if (StringUtil.in(next.nodeName(), elNames)) {
            it.remove();
            break;
        } else {
            it.remove();
        }
    }
}

项目：jabref 文件：IsbnFetcher.java

@Override
public Optional<BibEntry> performSearchById(String identifier) throws FetcherException {
    if (StringUtil.isBlank(identifier)) {
        return Optional.empty();
    }

    this.ensureThatIsbnIsValid(identifier);

    IsbnViaEbookDeFetcher isbnViaEbookDeFetcher = new IsbnViaEbookDeFetcher(importFormatPreferences);
    Optional<BibEntry> bibEntry = isbnViaEbookDeFetcher.performSearchById(identifier);
    // nothing found at ebook.de, try chimbori.com
    if (!bibEntry.isPresent()) {
        LOGGER.debug("No entry found at ebook.de try chimbori.com");
        IsbnViaChimboriFetcher isbnViaChimboriFetcher = new IsbnViaChimboriFetcher(importFormatPreferences);
        bibEntry = isbnViaChimboriFetcher.performSearchById(identifier);

    }

    return bibEntry;
}

项目：JabRefAutocomplete 文件：TreeBuilder.java

private void clearStackToContext(String... nodeNames) {
    Iterator<Element> it = stack.descendingIterator();
    while (it.hasNext()) {
        Element next = it.next();
        if (StringUtil.in(next.nodeName(), nodeNames) || next.nodeName().equals("html"))
            break;
        else
            it.remove();
    }
}

项目：astor 文件：HtmlTreeBuilder.java

boolean inSelectScope(String targetName) {
    for (int pos = stack.size() -1; pos >= 0; pos--) {
        Element el = stack.get(pos);
        String elName = el.nodeName();
        if (elName.equals(targetName))
            return true;
        if (!StringUtil.in(elName, TagSearchSelectScope)) // all elements except
            return false;
    }
    Validate.fail("Should not be reachable");
    return false;
}

项目：astor 文件：Tokeniser.java

/**
 * Utility method to consume reader and unescape entities found within.
 * @param inAttribute
 * @return unescaped string from reader
 */
String unescapeEntities(boolean inAttribute) {
    StringBuilder builder = StringUtil.stringBuilder();
    while (!reader.isEmpty()) {
        builder.append(reader.consumeTo('&'));
        if (reader.matches('&')) {
            reader.consume();
            int[] c = consumeCharacterReference(null, inAttribute);
            if (c == null || c.length==0)
                builder.append('&');
            else {
                builder.appendCodePoint(c[0]);
                if (c.length == 2)
                    builder.appendCodePoint(c[1]);
            }

        }
    }
    return builder.toString();
}

项目：astor 文件：Element.java

/**
 * Get a CSS selector that will uniquely select this element.
 * <p>
 * If the element has an ID, returns #id;
 * otherwise returns the parent (if any) CSS selector, followed by {@literal '>'},
 * followed by a unique selector for the element (tag.class.class:nth-child(n)).
 * </p>
 *
 * @return the CSS Path that can be used to retrieve the element in a selector.
 */
public String cssSelector() {
    if (id().length() > 0)
        return "#" + id();

    // Translate HTML namespace ns:tag to CSS namespace syntax ns|tag
    String tagName = tagName().replace(':', '|');
    StringBuilder selector = new StringBuilder(tagName);
    String classes = StringUtil.join(classNames(), ".");
    if (classes.length() > 0)
        selector.append('.').append(classes);

    if (parent() == null || parent() instanceof Document) // don't add Document to selector, as will always have a html node
        return selector.toString();

    selector.insert(0, " > ");
    if (parent().select(selector.toString()).size() > 1)
        selector.append(String.format(
            ":nth-child(%d)", elementSiblingIndex() + 1));

    return parent().cssSelector() + selector.toString();
}

项目：astor 文件：Element.java

/**
 * Get a CSS selector that will uniquely select this element.
 * <p>
 * If the element has an ID, returns #id;
 * otherwise returns the parent (if any) CSS selector, followed by {@literal '>'},
 * followed by a unique selector for the element (tag.class.class:nth-child(n)).
 * </p>
 *
 * @return the CSS Path that can be used to retrieve the element in a selector.
 */
public String cssSelector() {
    if (id().length() > 0)
        return "#" + id();

    // Translate HTML namespace ns:tag to CSS namespace syntax ns|tag
    String tagName = tagName().replace(':', '|');
    StringBuilder selector = new StringBuilder(tagName);
    String classes = StringUtil.join(classNames(), ".");
    if (classes.length() > 0)
        selector.append('.').append(classes);

    if (parent() == null || parent() instanceof Document) // don't add Document to selector, as will always have a html node
        return selector.toString();

    selector.insert(0, " > ");
    if (parent().select(selector.toString()).size() > 1)
        selector.append(String.format(
            ":nth-child(%d)", elementSiblingIndex() + 1));

    return parent().cssSelector() + selector.toString();
}

项目：astor 文件：HtmlToPlainText.java

public void head(Node node, int depth) {
    String name = node.nodeName();
    if (node instanceof TextNode)
        append(((TextNode) node).text()); // TextNodes carry all user-readable text in the DOM.
    else if (name.equals("li"))
        append("\n * ");
    else if (name.equals("dt"))
        append("  ");
    else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5", "tr"))
        append("\n");
}

项目：astor 文件：HtmlParserTest.java

@Test public void handlesInvalidDoctypes() {
    // would previously throw invalid name exception on empty doctype
    Document doc = Jsoup.parse("<!DOCTYPE>");
    assertEquals(
            "<!doctype> <html> <head></head> <body></body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));

    doc = Jsoup.parse("<!DOCTYPE><html><p>Foo</p></html>");
    assertEquals(
            "<!doctype> <html> <head></head> <body> <p>Foo</p> </body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));

    doc = Jsoup.parse("<!DOCTYPE \u0000>");
    assertEquals(
            "<!doctype �> <html> <head></head> <body></body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));
}

项目：JabRefAutocomplete 文件：TreeBuilder.java

void popStackToClose(String... elNames) {
    Iterator<Element> it = stack.descendingIterator();
    while (it.hasNext()) {
        Element next = it.next();
        if (StringUtil.in(next.nodeName(), elNames)) {
            it.remove();
            break;
        } else {
            it.remove();
        }
    }
}

项目：astor 文件：Element.java

/**
 * Get a CSS selector that will uniquely select this element.
 * <p>
 * If the element has an ID, returns #id;
 * otherwise returns the parent (if any) CSS selector, followed by {@literal '>'},
 * followed by a unique selector for the element (tag.class.class:nth-child(n)).
 * </p>
 *
 * @return the CSS Path that can be used to retrieve the element in a selector.
 */
public String cssSelector() {
    if (id().length() > 0)
        return "#" + id();

    // Translate HTML namespace ns:tag to CSS namespace syntax ns|tag
    String tagName = tagName().replace(':', '|');
    StringBuilder selector = new StringBuilder(tagName);
    String classes = StringUtil.join(classNames(), ".");
    if (classes.length() > 0)
        selector.append('.').append(classes);

    if (parent() == null || parent() instanceof Document) // don't add Document to selector, as will always have a html node
        return selector.toString();

    selector.insert(0, " > ");
    if (parent().select(selector.toString()).size() > 1)
        selector.append(String.format(
            ":nth-child(%d)", elementSiblingIndex() + 1));

    return parent().cssSelector() + selector.toString();
}

项目：astor 文件：HtmlParserTest.java

@Test public void handlesInvalidDoctypes() {
    // would previously throw invalid name exception on empty doctype
    Document doc = Jsoup.parse("<!DOCTYPE>");
    assertEquals(
            "<!doctype> <html> <head></head> <body></body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));

    doc = Jsoup.parse("<!DOCTYPE><html><p>Foo</p></html>");
    assertEquals(
            "<!doctype> <html> <head></head> <body> <p>Foo</p> </body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));

    doc = Jsoup.parse("<!DOCTYPE \u0000>");
    assertEquals(
            "<!doctype �> <html> <head></head> <body></body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));
}

项目：astor 文件：HtmlParserTest.java

@Test public void handlesInvalidDoctypes() {
    // would previously throw invalid name exception on empty doctype
    Document doc = Jsoup.parse("<!DOCTYPE>");
    assertEquals(
            "<!doctype> <html> <head></head> <body></body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));

    doc = Jsoup.parse("<!DOCTYPE><html><p>Foo</p></html>");
    assertEquals(
            "<!doctype> <html> <head></head> <body> <p>Foo</p> </body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));

    doc = Jsoup.parse("<!DOCTYPE \u0000>");
    assertEquals(
            "<!doctype �> <html> <head></head> <body></body> </html>",
            StringUtil.normaliseWhitespace(doc.outerHtml()));
}

项目：BoL-API-Parser 文件：HtmlTreeBuilder.java

void popStackToClose(String... elNames) {
    Iterator<Element> it = stack.descendingIterator();
    while (it.hasNext()) {
        Element next = it.next();
        if (StringUtil.in(next.nodeName(), elNames)) {
            it.remove();
            break;
        } else {
            it.remove();
        }
    }
}

项目：astor 文件：HtmlTreeBuilder.java

private boolean inSpecificScope(String[] targetNames, String[] baseTypes, String[] extraTypes) {
    for (int pos = stack.size() -1; pos >= 0; pos--) {
        Element el = stack.get(pos);
        String elName = el.nodeName();
        if (StringUtil.in(elName, targetNames))
            return true;
        if (StringUtil.in(elName, baseTypes))
            return false;
        if (extraTypes != null && StringUtil.in(elName, extraTypes))
            return false;
    }
    Validate.fail("Should not be reachable");
    return false;
}

项目：generator-thundr-gae-react 文件：HtmlFormattingUtil.java

public void head(Node node, int depth) {
    String name = node.nodeName();
    if (node instanceof TextNode)
        append(((TextNode) node).text()); // TextNodes carry all user-readable text in the DOM.
    else if (name.equals("li"))
        append("\n * ");
    else if (name.equals("dt"))
        append("  ");
    else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5", "tr"))
        append("\n");
}

项目：generator-thundr-gae-react 文件：HtmlFormattingUtil.java

public void tail(Node node, int depth) {
    String name = node.nodeName();
    if (StringUtil.in(name, "br", "dd", "dt", "p", "h1", "h2", "h3", "h4", "h5"))
        append("\n");
    else if (name.equals("a"))
        append(String.format(" <%s>", node.absUrl("href")));
}

项目：generator-thundr-gae-react 文件：HtmlFormattingUtil.java

private void append(String text) {
    if (text.startsWith("\n"))
        width = 0; // reset counter if starts with a newline. only from formats above, not in natural text
    if (text.equals(" ") &&
        (accum.length() == 0 || StringUtil.in(accum.substring(accum.length() - 1), " ", "\n")))
        return; // don't accumulate long runs of empty spaces

    if (text.length() + width > maxWidth) { // won't fit, needs to wrap
        String words[] = text.split("\\s+");
        for (int i = 0; i < words.length; i++) {
            String word = words[i];
            boolean last = i == words.length - 1;
            if (!last) // insert a space if not the last word
                word = word + " ";
            if (word.length() + width > maxWidth) { // wrap and reset counter
                accum.append("\n").append(word);
                width = word.length();
            } else {
                accum.append(word);
                width += word.length();
            }
        }
    } else { // fits as is, without need to wrap text
        accum.append(text);
        width += text.length();
    }
}

项目：jspider 文件：Page.java

public void addTargetRequests(List<String> requests, ResponseType responseType) {
    synchronized (targetRequests) {
        for (String url : requests) {
            if (isValidUrl(url)) {
                targetRequests.add(new Request(StringUtil.resolve(currentUrl, url), responseType));
            }
        }
    }
}

项目：jspider 文件：Page.java

public void addTargetRequest(String url, ResponseType responseType) {
    if (isValidUrl(url)) {
        synchronized (targetRequests) {
            targetRequests.add(new Request(StringUtil.resolve(currentUrl, url), responseType));
        }
    }
}

项目：Saber-Bot 文件：HTMLStripper.java

public void head(Node node, int i)
{
    String name = node.nodeName();
    if (node instanceof TextNode)
        accum.append(((TextNode) node).text()); // TextNodes carry all user-readable text in the DOM.
    else if (name.equals("li"))
        accum.append("\n * ");
    else if (name.equals("dt"))
        accum.append("  ");
    else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5", "tr"))
        accum.append("\n");
}

项目：Saber-Bot 文件：HTMLStripper.java

public void tail(Node node, int depth)
{
    String name = node.nodeName();
    if (StringUtil.in(name, "br", "dd", "dt", "p", "h1", "h2", "h3", "h4", "h5"))
        accum.append("\n");
}

项目：NetDiscovery 文件：LinksSelector.java

@Override
public List<String> selectList(Element element) {
    Elements elements = element.select("a");
    List<String> links = new ArrayList<String>(elements.size());
    for (Element element0 : elements) {
        if (!StringUtil.isBlank(element0.baseUri())) {
            links.add(element0.attr("abs:href"));
        } else {
            links.add(element0.attr("href"));
        }
    }
    return links;
}

项目：sigir2016-collection-for-focused-retrieval 文件：NodeHelper.java

public static boolean isEmptyElement(Node node) {
    if (node == null) {
        return false;
    }
    if (node instanceof TextNode) {
        return StringUtil.isBlank(((TextNode) node).text());
    }
    if (!(node instanceof Element)) {
        return false;
    }
    boolean isEmptyTag = ((Element) node).tag().isEmpty();
    return !isEmptyTag && hasEmptyChidren(node);
}