Example usage for org.jsoup.nodes Element text

List of usage examples for org.jsoup.nodes Element text

  1. HOME
  2. Java
  3. org.jsoup
  4. org.jsoup.nodes.*
  5. Element
  6. text

Introduction

In this page you can find the example usage for org.jsoup.nodes Element text.

Prototype

public String text()

Source Link

Document

Gets the combined text of this element and all its children.

Usage

From source file:de.luhmer.owncloudnewsreader.reader.GoogleReaderApi.GoogleReaderMethods.java

public static ArrayList<String[]> getTagList(String _USERNAME, String _PASSWORD) {
    Log.d(GoogleReaderConstants.APP_NAME, "METHOD: getTagList()");
    ArrayList<String[]> _TAGTITLE_ARRAYLIST = new ArrayList<String[]>();
    String _TAG_LABEL = null;//from   w w  w  .  ja  va2  s.co m
    try {
        _TAG_LABEL = "user/" + AuthenticationManager.getGoogleUserID(_USERNAME, _PASSWORD) + "/label/";
    } catch (IOException e) {
        e.printStackTrace();
    }

    Document doc = null;
    try {
        doc = Jsoup.connect(GoogleReaderConstants._TAG_LIST_URL)
                .header("Authorization",
                        GoogleReaderConstants._AUTHPARAMS
                                + AuthenticationManager.getGoogleAuthKey(_USERNAME, _PASSWORD))
                .userAgent(GoogleReaderConstants.APP_NAME).timeout(6000).get();
    } catch (IOException e) {
        e.printStackTrace();
    }

    Elements links = doc.select("string");
    for (Element link : links) {
        //String tagAttrib = link.attr("name");
        String tagText = link.text();
        if (Func_Strings.FindWordInString(tagText, _TAG_LABEL)) {
            _TAGTITLE_ARRAYLIST.add(new String[] { tagText.substring(32), tagText });
        }
    }

    //String[] _TAGTITLE_ARRAY = new String[_TAGTITLE_ARRAYLIST.size()];
    //_TAGTITLE_ARRAYLIST.toArray(_TAGTITLE_ARRAY);
    //return _TAGTITLE_ARRAY;
    return _TAGTITLE_ARRAYLIST;
}

From source file:io.jari.geenstijl.API.API.java

/**
 * Get article and comments (note that getArticles doesn't get the comments)
 *
 * @param url The direct url to the geenstijl article
 * @return Artikel The fetched article//from w  w  w.  ja  va 2 s  .  c o m
 * @throws IOException
 * @throws ParseException
 */
public static Artikel getArticle(String url, Context context) throws IOException, ParseException {
    ensureCookies();
    domain = context.getSharedPreferences("geenstijl", 0).getString("gsdomain", "www.geenstijl.nl");
    Artikel artikel;
    Log.i(TAG, "GETARTICLE STEP 1/2: Getting/parsing article page & images... " + url);
    Document document = Jsoup.connect(url).get();
    Element artikel_el = document.select("#content>article").first();
    artikel = parseArtikel(artikel_el, context);

    Log.i(TAG, "GETARTICLE STEP 2/2: Parsing comments...");
    ArrayList<Comment> comments = new ArrayList<Comment>();
    int i = 0;
    Elements comments_el = document.select("#comments article");
    for (Element comment_el : comments_el) {
        i++;
        Comment comment = new Comment();
        comment.id = Integer.parseInt(comment_el.attr("id").substring(1));
        Element footer = comment_el.select("footer").first();
        StringTokenizer footer_items = new StringTokenizer(footer.text(), "|");
        comment.auteur = footer_items.nextToken().trim();

        try {
            SimpleDateFormat simpleDateFormat = new SimpleDateFormat("dd-MM-yyHH:mm", Locale.US);
            comment.datum = simpleDateFormat
                    .parse(footer_items.nextToken().trim() + footer_items.nextToken().trim());
        } catch (ParseException parseEx) {
            //fuck gebruikers met pipe chars in hun naam, pech, gehad.
            continue;
        }

        comment.inhoud = comment_el.select("p").first().html();

        Log.d(TAG + ".perf", "CommentParser: Parsed " + comment.id + ": " + i + "/" + comments_el.size());

        comments.add(comment);
    }

    Comment[] comm = new Comment[comments.size()];
    comments.toArray(comm);
    artikel.comments = comm;

    Log.i(TAG, "GETARTICLE: DONE");

    return artikel;
}

From source file:de.luhmer.owncloudnewsreader.reader.GoogleReaderApi.GoogleReaderMethods.java

@SuppressWarnings("unused")
public static ArrayList<FolderSubscribtionItem> getSubList(String _USERNAME, String _PASSWORD)
        throws UnsupportedEncodingException, IOException {
    ArrayList<FolderSubscribtionItem> _SUBTITLE_ARRAYLIST = new ArrayList<FolderSubscribtionItem>();

    Document doc = Jsoup.connect(GoogleReaderConstants._SUBSCRIPTION_LIST_URL)
            .header("Authorization",
                    GoogleReaderConstants._AUTHPARAMS
                            + AuthenticationManager.getGoogleAuthKey(_USERNAME, _PASSWORD))
            .userAgent(GoogleReaderConstants.APP_NAME).timeout(5000).get();

    Elements objects = doc.select("object");
    Element element = objects.get(0);
    Node childTemp = element.childNodes().get(0);
    List<Node> childs = childTemp.childNodes();

    for (Node node : childs) {
        Elements links = ((Element) node).select("string");
        String idFeed = null;/* w  w w.j a v  a 2s  .c  o m*/
        String feedName;
        String parentSubscriptionName;

        for (Element link : links) {
            String tagAttrib = link.attr("name");
            String tagText = link.text();
            if (tagAttrib.equals("id") && idFeed == null)
                idFeed = tagText;
            else if (tagAttrib.equals("title"))
                feedName = tagText;
            else if (tagAttrib.equals("label"))
                parentSubscriptionName = tagText;
        }

        //String idFeed = node.attr("id");
        //String name = node.attr("title");

        //_SUBTITLE_ARRAYLIST.add(new FolderSubscribtionItem(feedName, -1, idFeed, parentSubscriptionName));//TODO implements this again... ? Update FolderSubscribtionItem
    }

    //String[] _SUBTITLE_ARRAY = new String[_SUBTITLE_ARRAYLIST.size()];
    //_SUBTITLE_ARRAYLIST.toArray(_SUBTITLE_ARRAY);
    return _SUBTITLE_ARRAYLIST;
}

From source file:io.apiman.tools.i18n.TemplateScanner.java

/**
 * Scan the given html template using jsoup and find all strings that require translation.  This is
 * done by finding all elements with a "apiman-i18n-key" attribute.
 * @param file//from  w  w w  .  j a v a 2 s  .  c o m
 * @param strings
 * @throws IOException
 */
private static void scanFile(File file, TreeMap<String, String> strings) throws IOException {
    Document doc = Jsoup.parse(file, "UTF-8");

    // First, scan for elements with the 'apiman-i18n-key' attribute.  These require translating.
    Elements elements = doc.select("*[apiman-i18n-key]");
    for (Element element : elements) {
        String i18nKey = element.attr("apiman-i18n-key");
        boolean isNecessary = false;

        // Process the element text (if the element has no children)
        if (strings.containsKey(i18nKey)) {
            if (hasNoChildren(element)) {
                isNecessary = true;
                String elementVal = element.text();
                if (elementVal.trim().length() > 0 && !elementVal.contains("{{")) {
                    String currentValue = strings.get(i18nKey);
                    if (!currentValue.equals(elementVal)) {
                        throw new IOException("Duplicate i18n key found with different default values.  Key="
                                + i18nKey + "  Value1=" + elementVal + "  Value2=" + currentValue);
                    }
                }
            }
        } else {
            if (hasNoChildren(element)) {
                String elementVal = element.text();
                if (elementVal.trim().length() > 0 && !elementVal.contains("{{")) {
                    isNecessary = true;
                    strings.put(i18nKey, elementVal);
                }
            }
        }

        // Process the translatable attributes
        for (String tattr : TRANSLATABLE_ATTRIBUTES) {
            if (element.hasAttr(tattr)) {
                String attrValue = element.attr(tattr);
                if (attrValue.contains("{{")) {
                    continue;
                }
                String attrI18nKey = i18nKey + '.' + tattr;
                String currentAttrValue = strings.get(attrI18nKey);
                if (currentAttrValue == null) {
                    isNecessary = true;
                    strings.put(attrI18nKey, attrValue);
                } else if (!currentAttrValue.equals(attrValue)) {
                    throw new IOException(
                            "Duplicate i18n key found with different default values (for attribute '" + tattr
                                    + "').  Key=" + attrI18nKey + "  Value1=" + attrValue + "  Value2="
                                    + currentAttrValue);
                } else {
                    isNecessary = true;
                }
            }
        }

        if (!isNecessary) {
            throw new IOException("Detected an unnecessary apiman-i18n-key attribute in file '" + file.getName()
                    + "' on element: " + element);
        }
    }

    // Next, scan all elements to see if the element *should* be marked for translation
    elements = doc.select("*");
    for (Element element : elements) {
        if (element.hasAttr("apiman-i18n-key") || element.hasAttr("apiman-i18n-skip")) {
            continue;
        }
        if (hasNoChildren(element)) {
            String value = element.text();
            if (value != null && value.trim().length() > 0) {
                if (!value.contains("{{")) {
                    throw new IOException("Found an element in '" + file.getName()
                            + "' that should be translated:  " + element);
                }
            }
        }
    }

    // Next scan elements with a translatable attribute and fail if any of those elements
    // are missing the apiman-i18n-key attribute.
    for (String tattr : TRANSLATABLE_ATTRIBUTES) {
        elements = doc.select("*[" + tattr + "]");
        for (Element element : elements) {
            if (element.hasAttr("apiman-i18n-key") || element.hasAttr("apiman-i18n-skip")
                    || element.attr(tattr).contains("{{")) {
                continue;
            } else {
                throw new IOException("In template '" + file.getName() + "', found an element with a '" + tattr
                        + "' attribute but missing 'apiman-i18n-key': " + element);
            }
        }
    }

}

From source file:com.kantenkugel.discordbot.jdocparser.JDocParser.java

private static List<DocBlock> getDocBlock(String jdocBase, Element elem, ClassDocumentation reference) {
    if (elem != null) {
        String baseLink = JDocUtil.getLink(jdocBase, reference);
        List<DocBlock> blocks = new ArrayList<>(10);
        String hashLink = null;/* w  w  w  .j  a  va  2s.  co  m*/
        for (elem = elem.nextElementSibling(); elem != null; elem = elem.nextElementSibling()) {
            if (elem.tagName().equals("a")) {
                hashLink = '#' + elem.attr("name");
            } else if (elem.tagName().equals("ul")) {
                Element tmp = elem.getElementsByTag("h4").first();
                String title = JDocUtil.fixSpaces(tmp.text().trim());
                String description = "", signature = "";
                OrderedMap<String, List<String>> fields = new ListOrderedMap<>();
                for (; tmp != null; tmp = tmp.nextElementSibling()) {
                    if (tmp.tagName().equals("pre")) {
                        //contains full signature
                        signature = JDocUtil.fixSpaces(tmp.text().trim());
                    } else if (tmp.tagName().equals("div") && tmp.className().equals("block")) {
                        //main block of content (description or deprecation)
                        Element deprecationElem = tmp.getElementsByClass("deprecationComment").first();
                        if (deprecationElem != null) {
                            //deprecation block
                            fields.put("Deprecated:", Collections
                                    .singletonList(JDocUtil.formatText(deprecationElem.html(), baseLink)));
                        } else {
                            //description block
                            description = JDocUtil.formatText(tmp.html(), baseLink);
                        }
                    } else if (tmp.tagName().equals("dl")) {
                        //a field
                        String fieldName = null;
                        List<String> fieldValues = new ArrayList<>();
                        for (Element element : tmp.children()) {
                            if (element.tagName().equals("dt")) {
                                if (fieldName != null) {
                                    fields.put(fieldName, fieldValues);
                                    fieldValues = new ArrayList<>();
                                }
                                fieldName = JDocUtil.fixSpaces(element.text().trim());
                            } else if (element.tagName().equals("dd")) {
                                fieldValues.add(JDocUtil.formatText(element.html(), baseLink));
                            }
                        }
                        if (fieldName != null) {
                            fields.put(fieldName, fieldValues);
                        }
                    }
                }
                blocks.add(new DocBlock(title, hashLink, signature, description, fields));
            }
        }
        return blocks;
    }
    return null;
}

From source file:me.vertretungsplan.parser.DaVinciParser.java

static void parseDaVinciTable(Element table, SubstitutionSchedule v, String klasse, SubstitutionScheduleDay day,
        ColorProvider colorProvider) {//from   www.  java 2  s  . com
    List<String> headers = new ArrayList<>();
    for (Element header : table.select("thead tr th, tr td[bgcolor=#9999FF]")) {
        headers.add(header.text());
    }

    // These three variables can
    Set<String> classes = new HashSet<>();
    String lesson = null;
    LocalDate currentDate = null;

    Pattern previousCurrentPattern = Pattern.compile("\\+([^\\s]+) \\(([^)]+)\\)");
    Pattern previousPattern = Pattern.compile("\\(([^)]+)\\)");

    for (Element row : table.select("tr:not(thead tr, tr:has(td[bgcolor=#9999FF]))")) {
        Substitution subst = new Substitution();
        LocalDate substDate = null;
        Elements columns = row.select("td");
        for (int i = 0; i < headers.size(); i++) {
            String value = columns.get(i).text().replace("\u00a0", "");
            String header = headers.get(i);

            if (value.isEmpty()) {
                if (header.equals("Klasse"))
                    subst.setClasses(classes);
                if (header.equals("Pos") || header.equals("Stunde") || header.equals("Std.")) {
                    subst.setLesson(lesson);
                }
                if (header.equals("Art") || header.equals("Merkmal"))
                    subst.setType("Vertretung");
                if (header.equals("Datum"))
                    substDate = currentDate;
                continue;
            }

            Matcher previousCurrentMatcher = previousCurrentPattern.matcher(value);
            Matcher previousMatcher = previousPattern.matcher(value);

            switch (header) {
            case "Klasse":
                String classesStr = value;
                if (previousMatcher.find()) {
                    classesStr = previousMatcher.group(1);
                }
                classes = new HashSet<>(Arrays.asList(classesStr.split(", ")));
                subst.setClasses(classes);
                break;
            case "Pos":
            case "Stunde":
            case "Std.":
                lesson = value;
                subst.setLesson(lesson);
                break;
            case "VLehrer Krzel":
            case "VLehrer":
            case "Vertreter":
            case "Vertretungslehrkraft":
                if (!value.startsWith("*")) {
                    subst.setTeacher(value);
                } else {
                    subst.setType(value.substring(1));
                }
                break;
            case "Lehrer":
            case "Lehrer Krzel":
            case "Lehrer Name":
            case "Lehrkraft":
                if (previousCurrentMatcher.find()) {
                    subst.setTeacher(previousCurrentMatcher.group(1));
                    subst.setPreviousTeacher(previousCurrentMatcher.group(2));
                } else if (previousMatcher.find()) {
                    subst.setPreviousTeacher(previousMatcher.group(1));
                } else {
                    subst.setPreviousTeacher(value);
                }
                break;
            case "VFach":
            case "V Fach":
                subst.setSubject(value);
                break;
            case "Fach":
            case "Original Fach":
                if (previousCurrentMatcher.find()) {
                    subst.setSubject(previousCurrentMatcher.group(1));
                    subst.setPreviousSubject(previousCurrentMatcher.group(2));
                } else {
                    subst.setPreviousSubject(value);
                }
                break;
            case "VRaum":
            case "V Raum":
                subst.setRoom(value);
                break;
            case "Raum":
            case "Original Raum":
                if (previousCurrentMatcher.find()) {
                    subst.setRoom(previousCurrentMatcher.group(1));
                    subst.setPreviousRoom(previousCurrentMatcher.group(2));
                } else {
                    subst.setPreviousRoom(value);
                }
                break;
            case "Art":
            case "Merkmal":
                subst.setType(value);
                break;
            case "Info":
            case "Mitteilung":
                subst.setDesc(value);
                break;
            case "Datum":
                substDate = ParserUtils.parseDate(value);
                currentDate = substDate;
                break;
            }
        }
        if (klasse != null) {
            Set<String> fixedClasses = new HashSet<>();
            fixedClasses.add(klasse);
            subst.setClasses(fixedClasses);
        }
        if (subst.getType() == null) {
            String recognizedType = null;
            if (subst.getDesc() != null)
                recognizedType = recognizeType(subst.getDesc());
            subst.setType(recognizedType != null ? recognizedType : "Vertretung");
        }
        subst.setColor(colorProvider.getColor(subst.getType()));

        if (substDate == null && day == null)
            continue;

        if (day == null || substDate != null && !substDate.equals(day.getDate())) {
            day = null;
            for (SubstitutionScheduleDay d : v.getDays()) {
                if (d.getDate().equals(substDate)) {
                    day = d;
                }
            }
            if (day == null) {
                day = new SubstitutionScheduleDay();
                day.setDate(substDate);
                v.addDay(day);
            }
        }

        day.addSubstitution(subst);

    }
}

From source file:com.kantenkugel.discordbot.jdocparser.JDocParser.java

private static Map<String, String> getInheritedMethods(Element summaryAnchor) {
    Map<String, String> inherited = new HashMap<>();
    if (summaryAnchor == null)
        return inherited;
    summaryAnchor = summaryAnchor.parent();
    Elements inheritAnchors = summaryAnchor.select("a[name^=\"methods.inherited.from.class\"]");
    for (Element inheritAnchor : inheritAnchors) {
        if (inheritAnchor.siblingElements().size() != 2)
            throw new RuntimeException("Got unexpected html while parsing inherited methods from class "
                    + inheritAnchor.attr("name"));
        Element next = inheritAnchor.nextElementSibling();
        if (!next.tagName().equals("h3"))
            throw new RuntimeException("Got unexpected html while parsing inherited methods from class "
                    + inheritAnchor.attr("name"));
        Element sub = next.children().last();
        if (sub == null || !sub.tagName().equals("a"))
            continue;
        String parent = sub.text().toLowerCase();
        next = next.nextElementSibling();
        if (!next.tagName().equals("code"))
            throw new RuntimeException("Got unexpected html while parsing inherited methods from class "
                    + inheritAnchor.attr("name"));
        for (sub = next.children().first(); sub != null; sub = sub.nextElementSibling()) {
            if (sub.tagName().equals("a")) {
                inherited.putIfAbsent(sub.text().toLowerCase(), parent);
            }//w w  w  . j a va2  s.c  om
        }
    }
    return inherited;
}

From source file:net.sf.texprinter.utils.StringUtils.java

/**
 * Escapes HTML entities and tags to a TeX format. This method tries to
 * replace HTML code by the TeX equivalent macros.
 *
 * @param text The input text./*  w w w  . j a v a2  s .c o m*/
 * @return A new text formatted from HTML to TeX.
 */
public static String escapeHTMLtoTeX(String text) {

    // replace bold tags
    String newText = text.replaceAll("<b>", "\\\\textbf{");
    newText = newText.replaceAll("</b>", "}");

    // replace bold tags
    newText = newText.replaceAll("<strong>", "\\\\textbf{");
    newText = newText.replaceAll("</strong>", "}");

    // replace italic tags
    newText = newText.replaceAll("<i>", "\\\\textit{");
    newText = newText.replaceAll("</i>", "}");

    // replace emphasized tags
    newText = newText.replaceAll("<em>", "\\\\emph{");
    newText = newText.replaceAll("</em>", "}");

    // replace paragraphs tags
    newText = newText.replaceAll("<p>", "");
    newText = newText.replaceAll("</p>", "\n\n");

    // replace ordered lists tags
    newText = newText.replaceAll("<ol>", "\\\\begin{enumerate}\n");
    newText = newText.replaceAll("</ol>", "\\\\end{enumerate}\n");

    // replace unordered lists tags
    newText = newText.replaceAll("<ul>", "\\\\begin{itemize}\n");
    newText = newText.replaceAll("</ul>", "\\\\end{itemize}\n");

    // replace item tags
    newText = newText.replaceAll("<li>", "\\\\item ");
    newText = newText.replaceAll("</li>", "\n");

    // replace blockquote tags
    newText = newText.replaceAll("<blockquote>", "\\\\begin{quotation}\n");
    newText = newText.replaceAll("</blockquote>", "\\\\end{quotation}\n");

    // replace code tags
    newText = newText.replaceAll("<pre><code>", "\\\\begin{TeXPrinterListing}\n");
    newText = newText.replaceAll("<pre class=.*\"><code>", "\\\\begin{TeXPrinterListing}\n");
    newText = newText.replaceAll("</code></pre>", "\\\\end{TeXPrinterListing}\n\n");

    // replace inline code tags
    newText = newText.replaceAll("<code>", "\\\\lstinline|");
    newText = newText.replaceAll("</code>", "|");

    // replace links tags
    newText = newText.replaceAll("alt=\".*\" ", "");

    // parse the text
    Document docLinks = Jsoup.parse(newText);

    // get all the links
    Elements links = docLinks.getElementsByTag("a");

    // if there are links
    if (links.size() > 0) {

        // for every link
        for (Element link : links) {

            // get the outer HTML
            String temp = link.outerHtml();

            // replace it
            newText = newText.replaceFirst(Pattern.quote(temp),
                    "\\\\href{" + link.attr("href") + "}{" + link.text() + "}");

        }
    }

    // create a list of images
    ArrayList<ImageGroup> images = new ArrayList<ImageGroup>();

    // parse the current text
    Document doc = Jsoup.parse(text);

    // fetch all the media found
    Elements media = doc.select("[src]");

    // for all media found
    for (Element m : media) {

        // if it's an image tag
        if (m.tagName().equals("img")) {

            // create a new image group with the image link
            ImageGroup image = new ImageGroup(m.attr("abs:src"));

            // add to the list of images
            images.add(image);

            // set the current image to null
            image = null;
        }
    }

    // create a new loop saver
    LoopSaver lps = null;

    // for every image in the list of images
    for (ImageGroup img : images) {

        // create a new object
        lps = new LoopSaver();

        // while there are references for that image in the text
        while (newText.indexOf(img.getURL()) != -1) {

            // tick loop
            lps.tick();

            // replace the occurrence of that image
            newText = newText.replaceFirst("<img src=\"" + img.getURL() + "\" />",
                    "\\\\begin{figure}[h!]\n\\\\centering\n\\\\includegraphics[scale=0.5]{" + img.getName()
                            + "}\n\\\\end{figure}");
        }

        // lets try
        try {

            // finally, download the image to the current directory
            Downloader.download(img.getURL(), img.getName());

        } catch (Exception exception) {

            // log message
            log.log(Level.WARNING,
                    "An error occurred while getting the current image. Trying to set the replacement image instead. MESSAGE: {0}",
                    StringUtils.printStackTrace(exception));

            // image could not be downloaded for any reason
            try {

                // open a file stream
                FileOutputStream f = new FileOutputStream(img.getName());

                // write a replacement image
                f.write(Base64.decode(
                        "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"));

                // close the file
                f.close();

            } catch (IOException ioexception) {

                // log message
                log.log(Level.SEVERE,
                        "An IO exception occured while trying to create the image replacement. MESSAGE: {0}",
                        StringUtils.printStackTrace(ioexception));

            } catch (Exception except) {

                // log message
                log.log(Level.SEVERE,
                        "An error occured while trying to create the image replacement. MESSAGE: {0}",
                        StringUtils.printStackTrace(except));

            }

        }

    }

    // unescape all HTML entities
    newText = StringEscapeUtils.unescapeHtml(newText);

    // return new text
    return newText;
}

From source file:com.kantenkugel.discordbot.jdocparser.JDocParser.java

static void parse(final String jdocBase, final String name, final InputStream inputStream,
        Map<String, ClassDocumentation> docs) {
    final String[] pathSplits = name.split("/");
    final String fileName = pathSplits[pathSplits.length - 1];
    if (!Character.isUpperCase(fileName.charAt(0))) {
        //ignore jdoc structure html
        return;//from   ww w . j av a 2s. c  om
    }
    final String[] nameSplits = fileName.split("\\.");
    final String className = nameSplits[nameSplits.length - 2];
    final String fullName = fileName.substring(0,
            fileName.length() - nameSplits[nameSplits.length - 1].length() - 1);
    try (BufferedReader buffer = new BufferedReader(new InputStreamReader(inputStream))) {
        //create dom Document
        final String content = buffer.lines().collect(Collectors.joining("\n"));
        Document document = Jsoup.parse(content);

        //classDocument (classname, package, description)
        Element titleElem = getSingleElementByClass(document, "title");
        final String classSig = JDocUtil.fixSpaces(titleElem.text());
        Element packageElem = titleElem.previousElementSibling();
        if (packageElem.children().size() > 1) {
            packageElem = packageElem.children().last();
        }
        final String pack = JDocUtil.fixSpaces(packageElem.text());
        final String link = JDocUtil.getLink(jdocBase, pack, fullName);
        Element descriptionElement = null;
        Elements descriptionCandidates = document.select(".description .block");
        if (descriptionCandidates.size() > 1) {
            List<Element> removed = descriptionCandidates.stream().map(elem -> elem.child(0))
                    .filter(child -> child != null && !child.className().startsWith("deprecat"))
                    .map(Element::parent).collect(Collectors.toList());
            if (removed.size() != 1)
                throw new RuntimeException("Found too many description candidates");
            descriptionElement = removed.get(0);
        } else if (descriptionCandidates.size() == 1) {
            descriptionElement = descriptionCandidates.get(0);
        }
        final String description = descriptionElement == null ? ""
                : JDocUtil.formatText(descriptionElement.html(), link);
        final ClassDocumentation classDoc = new ClassDocumentation(pack, fullName, classSig, description,
                classSig.startsWith("Enum"));

        //methods, fields
        final Element details = document.getElementsByClass("details").first();
        if (details != null) {
            //methods
            Element tmp = getSingleElementByQuery(details, "a[name=\"method.detail\"]");
            List<DocBlock> docBlock = getDocBlock(jdocBase, tmp, classDoc);
            if (docBlock != null) {
                for (DocBlock block : docBlock) {
                    Set<MethodDocumentation> mdocs = classDoc.methodDocs
                            .computeIfAbsent(block.title.toLowerCase(), key -> new HashSet<>());
                    mdocs.add(new MethodDocumentation(classDoc, block.signature, block.hashLink,
                            block.description, block.fields));
                }
            }
            //vars
            tmp = getSingleElementByQuery(details, "a[name=\"field.detail\"]");
            docBlock = getDocBlock(jdocBase, tmp, classDoc);
            if (docBlock != null) {
                for (DocBlock block : docBlock) {
                    classDoc.classValues.put(block.title.toLowerCase(), new ValueDocumentation(classDoc,
                            block.title, block.hashLink, block.signature, block.description));
                }
            }
            //enum-values
            tmp = getSingleElementByQuery(details, "a[name=\"enum.constant.detail\"]");
            docBlock = getDocBlock(jdocBase, tmp, classDoc);
            if (docBlock != null) {
                for (DocBlock block : docBlock) {
                    classDoc.classValues.put(block.title.toLowerCase(), new ValueDocumentation(classDoc,
                            block.title, block.hashLink, block.signature, block.description));
                }
            }
        }
        final Element methodSummary = getSingleElementByQuery(document, "a[name=\"method.summary\"]");
        classDoc.inheritedMethods.putAll(getInheritedMethods(methodSummary));

        //storing
        if (nameSplits.length > 2) {
            if (!docs.containsKey(nameSplits[0].toLowerCase()))
                docs.put(nameSplits[0].toLowerCase(), new ClassDocumentation(null, null, null, null, false));
            ClassDocumentation parent = docs.get(nameSplits[0].toLowerCase());
            for (int i = 1; i < nameSplits.length - 2; i++) {
                if (!parent.subClasses.containsKey(nameSplits[i].toLowerCase()))
                    parent.subClasses.put(nameSplits[i].toLowerCase(),
                            new ClassDocumentation(null, null, null, null, false));
                parent = parent.subClasses.get(nameSplits[i].toLowerCase());
            }
            if (parent.subClasses.containsKey(className.toLowerCase()))
                classDoc.subClasses.putAll(parent.subClasses.get(className.toLowerCase()).subClasses);
            parent.subClasses.put(className.toLowerCase(), classDoc);
        }
        if (docs.containsKey(fullName.toLowerCase())) {
            ClassDocumentation current = docs.get(fullName.toLowerCase());
            if (current.classSig != null)
                throw new RuntimeException("Got a class-name conflict with classes " + classDoc.classSig + "("
                        + classDoc.className + ") AND " + current.classSig + "(" + current.className + ")");
            classDoc.subClasses.putAll(current.subClasses);
        }
        docs.put(fullName.toLowerCase(), classDoc);
    } catch (final IOException | NullPointerException ex) {
        JDocUtil.LOG.error("Got excaption for element {}", fullName, ex);
    }
    try {
        inputStream.close();
    } catch (final IOException e) {
        JDocUtil.LOG.error("Error closing inputstream", e);
    }
}

From source file:me.vertretungsplan.parser.UntisInfoParser.java

private static List<Substitution> parseTimetableCell(Element cell, String lesson, String klasse,
        JSONArray cellFormat, ColorProvider colorProvider) throws JSONException {
    List<Substitution> substitutions = new ArrayList<>();
    if (cell.text().trim().equals("")) {
        return substitutions;
    }/* w  ww.ja v  a  2 s.  co  m*/

    final Elements rows = cell.select("table").first().select("tr");

    int cols = rows.get(0).select("td").size();
    int courseCount = cols / cellFormat.getJSONArray(0).length();

    for (int course = 0; course < courseCount; course++) {
        Substitution s = new Substitution();
        s.setLesson(lesson);

        final HashSet<String> classes = new HashSet<>();
        classes.add(klasse);
        s.setClasses(classes);

        boolean isChange = false;

        for (int row = 0; row < cellFormat.length() && row < rows.size(); row++) {
            JSONArray rowData = cellFormat.getJSONArray(row);
            Element tr = rows.get(row);
            for (int col = 0; col < rowData.length(); col++) {
                if (rowData.getString(col) == null)
                    continue;
                String type = rowData.getString(col);

                try {
                    Element td = tr.select("td").get(col + course * cellFormat.getJSONArray(0).length());
                    if (td.select("font[color=#FF0000]").size() > 0) {
                        isChange = true;
                    }

                    parseTimetableCellContent(s, type, td);
                } catch (IndexOutOfBoundsException e) {
                    if (course == 0)
                        throw e;
                }
            }
        }

        if (s.getSubject() == null && s.getTeacher() == null && s.getRoom() == null) {
            s.setType("Entfall");
        } else {
            s.setType("Vertretung");
        }
        s.setColor(colorProvider.getColor(s.getType()));

        if (isChange) {
            substitutions.add(s);
        }
    }

    return substitutions;
}