Example usage for org.jdom2 Element getText

List of usage examples for org.jdom2 Element getText

  1. HOME
  2. Java
  3. org.jdom2
  4. org.jdom2.*
  5. Element
  6. getText

Introduction

In this page you can find the example usage for org.jdom2 Element getText.

Prototype

public String getText()

Source Link

Document

Returns the textual content directly held under this element as a string.

Usage

From source file:cz.muni.fi.mir.mathmlcanonicalization.modules.OperatorNormalizer.java

License:Apache License

private boolean isSpareOperator(final Element operator, final Collection<String> spareOperators) {
    assert operator != null && spareOperators != null && isOperator(operator);
    return (isEnabled(REMOVE_EMPTY_OPERATORS) && operator.getText().isEmpty())
            || (spareOperators.contains(operator.getTextTrim()));
}

From source file:cz.muni.fi.mir.mathmlcanonicalization.modules.OperatorNormalizer.java

License:Apache License

private void replaceIdentifiers(final Element ancestor, final Set<String> operators) {
    assert ancestor != null && operators != null;
    final List<Element> toReplace = new ArrayList<Element>();
    for (Element element : ancestor.getDescendants(new ElementFilter(IDENTIFIER))) {
        // TODO: control whole ranges of symbols rather than listed ones
        if (operators.contains(element.getTextTrim())) {
            toReplace.add(element);// www  .j ava2  s  . co m
        }
    }
    for (Element element : toReplace) {
        LOGGER.log(Level.FINE, "Creating an operator from {0}", element.getText());
        replaceElement(element, OPERATOR);
    }
}

From source file:DataWeb.Code.java

License:Open Source License

public Code(Element e, Namespace ns) {
    id = e.getAttributeValue("id");
    idProfesor = e.getChildText("idProfesor", ns);
    nombre = e.getChildText("nombre", ns);
    lenguaje = e.getChildText("lenguaje", ns);
    resaltar = e.getChildText("resaltar", ns);

    linea = new ArrayList<String>();
    comentario = new ArrayList<String>();
    for (Element line : e.getChildren("linea", ns))
        linea.add(line.getText());
    for (Element line : e.getChildren("idComentario", ns))
        comentario.add(line.getText());//from  w  w  w.  j  a v a2 s .c o m
}

From source file:DataWeb.Course.java

License:Open Source License

public Course(Element e, Namespace ns) {
    id = e.getAttributeValue("id");
    idProfesor = e.getChildText("idProfesor", ns);
    nombre = e.getChildText("nombre", ns);

    idAlumno = new ArrayList<String>();
    idCodigo = new ArrayList<String>();
    for (Element alumno : e.getChildren("idAlumno", ns))
        idAlumno.add(alumno.getText());
    for (Element codigo : e.getChildren("idCodigo", ns))
        idCodigo.add(codigo.getText());/*from w  w  w  . jav a  2 s.  c  o m*/
}

From source file:DataWeb.User.java

License:Open Source License

public User(Element e, Namespace ns) {
    id = e.getAttributeValue("id");
    usuario = e.getChildText("usuario", ns);
    password = e.getChildText("password", ns);
    nombres = e.getChildText("nombres", ns);
    apPaterno = e.getChildText("apPat", ns);
    apMaterno = e.getChildText("apMat", ns);
    category = e.getChildText("category", ns);

    idCurso = new ArrayList<String>();
    for (Element curso : e.getChildren("idCurso", ns))
        idCurso.add(curso.getText());
}

From source file:dblp.xml.DBLPParserFirstSchema.java

private void extractElements(Element root, final String type) {
    try {/*from   ww  w .j  a va  2  s.  co  m*/
        //            System.out.println("Root element :" + doc.getDocumentElement().getNodeName());
        List<Element> nList = root.getChildren(type);
        //        System.out.println(nList);
        System.out.println(type + " " + nList.size());
        int index = 0;
        int ignore = 0;
        final Map<Integer, String> filteredConfs = readNodeFile(conf_filter_path);
        Set<String> filteredConfsSet = new HashSet<>();
        filteredConfsSet.addAll(filteredConfs.values());
        for (Element eElement : nList) {
            String booktitle = eElement.getChild("booktitle").getText();
            //TODO: should comment out, now it doesn't filter conferences
            if (!filteredConfsSet.contains(booktitle)) {
                ignore++;
                continue;
            }
            String year = eElement.getChild("year").getText();
            int year_int = Integer.parseInt(year.trim());
            if (year_int < year_threshold) {
                ignore++;
                continue;
            }
            index++;
            if (index % 100 == 0) {
                System.out.println("Node#: " + index + " Ignore#:" + ignore);
            }
            String title = eElement.getChild("title").getText();
            if (titleSet.contains(title)) {
                ignore++;
                continue;
            }
            titleSet.add(title);
            int titleId = titlesCollection.get(title);
            int yearId = yearsCollection.get(year);
            int confId = confsCollection.get(booktitle);
            title_conf_writer.write(titleId + " " + confId + "\n");
            title_year_writer.write(titleId + " " + yearId + "\n");
            final List<Element> authors = eElement.getChildren("author");
            for (Element author : authors) {
                String author_str = author.getText();
                int authorId = authorsCollection.get(author_str);
                title_author_writer.write(titleId + " " + authorId + "\n");
            }

        }
        title_author_writer.close();
        title_conf_writer.close();
        title_year_writer.close();
    } catch (IOException ex) {
        Logger.getLogger(DBLPParserFirstSchema.class.getName()).log(Level.SEVERE, null, ex);
    }
}

From source file:dblp.xml.DBLPParserSecondSchema.java

private void extractElements(Element root, final String type) {
    try {/*  w w w.  j ava  2 s  .c  o m*/
        List<Element> nList = root.getChildren(type);

        System.out.println(type + " " + nList.size());
        int index = 0;
        int ignore = 0;
        final Map<Integer, String> filteredConfs = readNodeFile(conf_filter_path);
        Set<String> filteredConfsSet = new HashSet<>();
        filteredConfsSet.addAll(filteredConfs.values());
        for (Element eElement : nList) {
            String booktitle = eElement.getChild("booktitle").getText();
            if (!filteredConfsSet.contains(booktitle)) {
                ignore++;
                continue;
            }
            String year = eElement.getChild("year").getText();
            int year_int = Integer.parseInt(year.trim());
            if (year_int < year_threshold) {
                ignore++;
                continue;
            }
            index++;
            if (index % 100 == 0) {
                System.out.println("Node#: " + index + " Ignore#:" + ignore);
            }
            String title = eElement.getChild("title").getText();
            int titleId = titlesCollection.get(title);
            int confId = confsCollection.get(booktitle);
            String yearConf = year + " " + booktitle;
            int yearConfId = yearConfsCollection.get(yearConf);
            conf_year_writer.write(confId + " " + yearConfId + "\n");
            title_year_writer.write(titleId + " " + yearConfId + "\n");
            final List<Element> authors = eElement.getChildren("author");
            for (Element author : authors) {
                String author_str = author.getText();
                int authorId = authorsCollection.get(author_str);
                title_author_writer.write(titleId + " " + authorId + "\n");
                author_conf_writer.write(authorId + " " + confId + "\n");
            }

        }
        title_author_writer.close();
        author_conf_writer.close();
        title_year_writer.close();
        conf_year_writer.close();
    } catch (IOException ex) {
        Logger.getLogger(DBLPParserSecondSchema.class.getName()).log(Level.SEVERE, null, ex);
    }
}

From source file:dblp.xml.DBLPParserThirdSchema.java

private void extractElements(Element root, final String type) {
    try {/*  w w w .  ja  v  a  2 s.c o  m*/

        //            System.out.println("Root element :" + doc.getDocumentElement().getNodeName());
        List<Element> nList = root.getChildren(type);
        //        System.out.println(nList);
        System.out.println(type + " " + nList.size());
        int index = 0;
        int ignore = 0;
        final Map<Integer, String> filteredConfs = readNodeFile(conf_filter_path);
        Set<String> filteredConfsSet = new HashSet<>();
        filteredConfsSet.addAll(filteredConfs.values());
        for (Element eElement : nList) {
            String booktitle = eElement.getChild("booktitle").getText();
            if (!filteredConfsSet.contains(booktitle)) {
                ignore++;
                continue;
            }
            String year = eElement.getChild("year").getText();
            int year_int = Integer.parseInt(year.trim());
            if (year_int < year_threshold) {
                ignore++;
                continue;
            }
            index++;
            if (index % 100 == 0) {
                System.out.println("Node#: " + index + " Ignore#:" + ignore);
            }
            String title = eElement.getChild("title").getText();
            int titleId = titlesCollection.get(title);
            int confId = confsCollection.get(booktitle);
            String yearConf = year + " " + booktitle;
            int yearConfId = yearConfsCollection.get(yearConf);
            title_conf_writer.write(titleId + " " + confId + "\n");
            conf_year_writer.write(confId + " " + yearConfId + "\n");
            final List<Element> authors = eElement.getChildren("author");
            for (Element author : authors) {
                String author_str = author.getText();
                int authorId = authorsCollection.get(author_str);
                title_author_writer.write(titleId + " " + authorId + "\n");
            }
        }
        title_author_writer.close();
        title_conf_writer.close();
        conf_year_writer.close();
    } catch (IOException ex) {
        Logger.getLogger(DBLPParserThirdSchema.class.getName()).log(Level.SEVERE, null, ex);
    }
}

From source file:de.andreasschoknecht.LS3.PNMLReader.java

License:Open Source License

/**
 * Creates the term lists for a process model (LS3Document) in a model collection. Adds the terms to the document itself as Bag-of-Words and adds the terms to
 * the HashSet of terms of the document collection. This method is used when parsing a document collection.
 *
 * @param labels The labels contained in the PNML file
 * @param ls3Document The LS3Document representation of the PNML file for updating the term list of the document
 * @param documentCollection The DocumentCollection for updating the term list of the whole collection
 * @throws IOException if stop word file could not be read
 *//*ww  w . ja va 2 s  .c  o  m*/
private void createTermLists(List<Object> labels, LS3Document ls3Document,
        DocumentCollection documentCollection) throws IOException {
    initializeWordList();

    ArrayList<String> tokens = new ArrayList<String>();
    String label = "";
    for (Object temp : labels) {
        Element value = (Element) temp;
        label = label + value.getText() + " ";
    }

    PTBTokenizer<CoreLabel> ptbt = new PTBTokenizer<>(new StringReader(label), new CoreLabelTokenFactory(),
            "untokenizable=allKeep");
    while (ptbt.hasNext()) {
        tokens.add(ptbt.next().value());
    }

    for (int i = 0, j = tokens.size(); i < j; i++) {
        String bereinigt = tokens.get(i).toLowerCase();

        // Clear tokens of empty tokens, stop words, and automatic tool labels
        if (!bereinigt.matches("(p|t)*([0-9]+)") && !stopwords.contains(bereinigt) && !bereinigt.equals("")) {
            String term = bereinigt.replaceAll("[0-9]+", "");
            ls3Document.addTerm(stemString(term));
            documentCollection.addTerm(stemString(term));
        }
    }
}

From source file:de.andreasschoknecht.LS3.PNMLReader.java

License:Open Source License

/**
 * Creates the term list for a process model (LS3Document). It only adds the terms to the document itself as Bag-of-Words.
 * This method is used when parsing a query model.
 *
 * @param labels The labels contained in the PNML file
 * @param ls3Document The LS3Document representation of the PNML file for updating the term list of the document
 * @throws IOException if stop word file could not be read
 *//* w w w  . j a v  a  2  s.c om*/
private void createTermLists(List<Object> labels, LS3Document ls3Document) throws IOException {
    initializeWordList();

    ArrayList<String> tokens = new ArrayList<String>();
    String label = "";
    for (Object temp : labels) {
        Element value = (Element) temp;
        label = label + value.getText() + " ";
    }

    PTBTokenizer<CoreLabel> ptbt = new PTBTokenizer<>(new StringReader(label), new CoreLabelTokenFactory(),
            "untokenizable=allKeep");
    while (ptbt.hasNext()) {
        tokens.add(ptbt.next().value());
    }

    for (int i = 0, j = tokens.size(); i < j; i++) {
        String bereinigt = tokens.get(i).toLowerCase();

        // Clear tokens of empty tokens, stop words, and automatic tool labels
        if (!bereinigt.matches("(p|t)*([0-9]+)") && !stopwords.contains(bereinigt) && !bereinigt.equals("")) {
            String term = bereinigt.replaceAll("[0-9]+", "");
            ls3Document.addTerm(stemString(term));
        }
    }
}