Example usage for java.text BreakIterator first

Introduction

In this page you can find the example usage for java.text BreakIterator first.

Prototype

public abstract int first();

Source Link

Document

Returns the first boundary.

Usage

From source file:Main.java

public TextBoundaryFrame() {
    getContentPane().add(new JScrollPane(outputText));

    Locale currentLocale = Locale.getDefault();
    BreakIterator currentBreakIterator = null;
    currentBreakIterator = BreakIterator.getCharacterInstance(currentLocale);

    String text = "The quick, brown fox jump-ed\n" + "over the lazy \"dog.\" And then...what happened?";
    currentBreakIterator.setText(text);//w  w w  . j a  va  2s.c o m
    outputText.setText("");

    int from = currentBreakIterator.first();
    int to;
    while ((to = currentBreakIterator.next()) != BreakIterator.DONE) {
        outputText.append(text.substring(from, to) + "|");
        from = to;
    }
    outputText.append(text.substring(from));
}

---

From source file:be.idamediafoundry.sofa.livecycle.dsc.util.AbstractQDoxComponentInfoExtractor.java

final protected String getFirstSentence(String text) {
    String result = text;//from   w w  w  .  j  a va  2  s. c o  m
    if (text != null) {
        BreakIterator iterator = BreakIterator.getSentenceInstance();
        iterator.setText(text);
        int start = iterator.first();
        int end = iterator.next();
        if (end != BreakIterator.DONE) {
            result = text.substring(start, end).trim();
        }
    }
    return result;
}

---

From source file:com.norconex.importer.handler.tagger.impl.TextStatisticsTagger.java

@Override
protected void tagTextDocument(String reference, Reader input, ImporterMetadata metadata, boolean parsed)
        throws ImporterHandlerException {
    long charCount = 0;
    long wordCharCount = 0;
    long wordCount = 0;
    long sentenceCount = 0;
    long sentenceCharCount = 0;
    long paragraphCount = 0;

    //TODO make this more efficient, by doing all this in one pass.
    LineIterator it = IOUtils.lineIterator(input);
    while (it.hasNext()) {
        String line = it.nextLine().trim();
        if (StringUtils.isBlank(line)) {
            continue;
        }//  w  ww.j a  va 2  s  .  c  om

        // Paragraph
        paragraphCount++;

        // Character
        charCount += line.length();

        // Word
        Matcher matcher = PATTERN_WORD.matcher(line);
        while (matcher.find()) {
            int wordLength = matcher.end() - matcher.start();
            wordCount++;
            wordCharCount += wordLength;
        }

        // Sentence
        BreakIterator boundary = BreakIterator.getSentenceInstance();
        boundary.setText(line);
        int start = boundary.first();
        for (int end = boundary.next(); end != BreakIterator.DONE; start = end, end = boundary.next()) {
            sentenceCharCount += (end - start);
            sentenceCount++;
        }
    }

    String field = StringUtils.EMPTY;
    if (StringUtils.isNotBlank(fieldName)) {
        field = fieldName.trim() + ".";
    }

    //--- Add fields ---
    metadata.addLong("document.stat." + field + "characterCount", charCount);
    metadata.addLong("document.stat." + field + "wordCount", wordCount);
    metadata.addLong("document.stat." + field + "sentenceCount", sentenceCount);
    metadata.addLong("document.stat." + field + "paragraphCount", paragraphCount);
    metadata.addString("document.stat." + field + "averageWordCharacterCount",
            divide(wordCharCount, wordCount));
    metadata.addString("document.stat." + field + "averageSentenceCharacterCount",
            divide(sentenceCharCount, sentenceCount));
    metadata.addString("document.stat." + field + "averageSentenceWordCount", divide(wordCount, sentenceCount));
    metadata.addString("document.stat." + field + "averageParagraphCharacterCount",
            divide(charCount, paragraphCount));
    metadata.addString("document.stat." + field + "averageParagraphSentenceCount",
            divide(sentenceCount, paragraphCount));
    metadata.addString("document.stat." + field + "averageParagraphWordCount",
            divide(wordCount, paragraphCount));

}

---

From source file:com.redhat.rcm.version.Cli.java

private static void printTextLine(final String line, final String indent, final int max, final PrintWriter pw) {
    final String fmt = "%s%-" + max + "s\n";

    final List<String> lines = new ArrayList<String>();

    final BreakIterator iter = BreakIterator.getLineInstance();
    iter.setText(line);//from www.j a va2 s . c  o  m

    int start = iter.first();
    int end = BreakIterator.DONE;
    final StringBuilder currentLine = new StringBuilder();
    String seg;
    while (start != BreakIterator.DONE && (end = iter.next()) != BreakIterator.DONE) {
        seg = line.substring(start, end);
        if (currentLine.length() + seg.length() > max) {
            lines.add(currentLine.toString());
            currentLine.setLength(0);
        }

        currentLine.append(seg);
        start = end;
    }

    if (currentLine.length() > 0) {
        lines.add(currentLine.toString());
    }

    for (final String ln : lines) {
        pw.printf(fmt, indent, ln);
    }
}

---

From source file:com.redhat.rcm.version.Cli.java

private static void printKVLine(final String key, final String value, final String fmt, final int valMax,
        final PrintWriter pw) {
    final List<String> lines = new ArrayList<String>();

    final BreakIterator iter = BreakIterator.getLineInstance();
    iter.setText(value);/* ww w.  ja v  a 2  s .  c o m*/

    int start = iter.first();
    int end = BreakIterator.DONE;
    final StringBuilder currentLine = new StringBuilder();
    String seg;
    while (start != BreakIterator.DONE && (end = iter.next()) != BreakIterator.DONE) {
        seg = value.substring(start, end);
        if (currentLine.length() + seg.length() > valMax) {
            lines.add(currentLine.toString());
            currentLine.setLength(0);
        }

        currentLine.append(seg);
        start = end;
    }

    if (currentLine.length() > 0) {
        lines.add(currentLine.toString());
    }

    pw.printf(fmt, key, lines.isEmpty() ? "" : lines.get(0));
    if (lines.size() > 1) {
        for (int i = 1; i < lines.size(); i++) {
            // blank string to serve for indentation in format with two fields.
            pw.printf(fmt, "", lines.get(i));
        }
    }
}

---

From source file:IteratorTest.java

protected void refreshDisplay() {
    int startIndex, nextIndex;
    Vector items = new Vector();
    String msgText = textArea.getText();
    Locale locale = (Locale) (localeButton.getSelectedItem());
    BreakIterator iterator = null;
    if (charButton.isSelected()) {
        iterator = BreakIterator.getCharacterInstance(locale);
    } else if (wordButton.isSelected()) {
        iterator = BreakIterator.getWordInstance(locale);
    } else if (lineButton.isSelected()) {
        iterator = BreakIterator.getLineInstance(locale);
    } else if (sentButton.isSelected()) {
        iterator = BreakIterator.getSentenceInstance(locale);
    }//  w ww .j  a  v a 2 s . c om
    iterator.setText(msgText);
    startIndex = iterator.first();
    nextIndex = iterator.next();

    while (nextIndex != BreakIterator.DONE) {
        items.addElement(msgText.substring(startIndex, nextIndex));
        startIndex = nextIndex;
        nextIndex = iterator.next();
    }
    itemList.setListData(items);
}

---

From source file:org.cloudgraph.examples.test.model.NLPWikiParseTest.java

private void parse(StringBuilder buf) throws IOException {
    BreakIterator iterator = BreakIterator.getSentenceInstance(Locale.US);

    String text = buf.toString();
    int counter = 0;
    iterator.setText(text);/*  ww  w .ja v  a 2s.c om*/

    int lastIndex = iterator.first();
    while (lastIndex != BreakIterator.DONE) {
        int firstIndex = lastIndex;
        lastIndex = iterator.next();

        if (lastIndex != BreakIterator.DONE) {
            String sentence = text.substring(firstIndex, lastIndex);
            long before = System.currentTimeMillis();
            //parse(sentence);
            long after = System.currentTimeMillis();
            log.info("time4: " + String.valueOf(after - before) + ": " + sentence);
            counter++;
        }
    }

}

---

From source file:org.cloudgraph.examples.test.model.StanfordCoreNLPTest.java

private void parse(StringBuilder buf) throws IOException {
    BreakIterator iterator = BreakIterator.getSentenceInstance(Locale.US);

    String text = buf.toString();
    int counter = 0;
    iterator.setText(text);//from ww w. j a  va  2s.c  o  m

    int lastIndex = iterator.first();
    while (lastIndex != BreakIterator.DONE) {
        int firstIndex = lastIndex;
        lastIndex = iterator.next();

        if (lastIndex != BreakIterator.DONE) {
            String sentence = text.substring(firstIndex, lastIndex);
            long before = System.currentTimeMillis();
            parse(sentence);
            long after = System.currentTimeMillis();
            log.info("time4: " + String.valueOf(after - before) + ": " + sentence);
            counter++;
        }
    }

}

---

From source file:org.lnicholls.galleon.util.Tools.java

public static String[] layout(int width, FontMetrics metrics, String text) {
    ArrayList lines = new ArrayList();

    if (text != null) {
        String line = "";
        BreakIterator boundary = BreakIterator.getWordInstance();
        boundary.setText(text);/*from   w ww . j  a  v a 2  s.  c  om*/
        int start = boundary.first();
        for (int end = boundary.next(); end != BreakIterator.DONE; start = end, end = boundary.next()) {
            String word = text.substring(start, end);
            String trimmed = word.replaceAll(" ", "");
            int metricsWidth = (line + word).length() * 20;
            if (metrics != null)
                metricsWidth = metrics.stringWidth(line + word);

            if (trimmed.equals("\n") || trimmed.equals("\r") || trimmed.equals("\r\n")) {
                lines.add(line.trim());
                line = "";
            } else if (metricsWidth > width) {
                lines.add(line.trim());
                line = word;
            } else
                line = line + word;
        }
        if (line.trim().length() > 0)
            lines.add(line.trim());
    }

    return (String[]) lines.toArray(new String[0]);
}

---

From source file:pl.edu.icm.coansys.kwdextraction.RakeExtractor.java

/**
 * Finding words or word sequences separated by stopwords, punctuation marks
 * etc.// w  w  w. ja  v  a  2 s. c om
 */
private void extractKeywordCandidates() {

    Map<String, KeywordCandidate> candidatesMap = new HashMap<String, KeywordCandidate>();

    BreakIterator wordIterator = BreakIterator.getWordInstance();

    wordIterator.setText(content);
    int wordStart = wordIterator.first();

    int candidateStart = wordStart;
    String candidateStr = null;
    KeywordCandidate kwdCand = new KeywordCandidate();

    for (int wordEnd = wordIterator
            .next(); wordEnd != BreakIterator.DONE; wordStart = wordEnd, wordEnd = wordIterator.next()) {

        String word = content.substring(wordStart, wordEnd).trim().toLowerCase();
        String alpha = word.replaceAll(ILLEGAL_CHARS, "");

        if (!word.isEmpty()) {

            if (stopwords.get(lang).contains(word) || word.matches("\\W+") || isNum(word)
                    || !word.equals(alpha)) {
                candidateStr = content.substring(candidateStart, wordStart);
            } else {
                kwdCand.addWord(word);
                if (wordEnd == content.length()) {
                    candidateStr = content.substring(candidateStart, wordEnd);
                }
            }
            if (candidateStr != null) {
                candidateStr = candidateStr.trim().toLowerCase().replaceAll(ILLEGAL_CHARS, "")
                        .replaceAll("\\s+", " ");
                if (!candidateStr.isEmpty()) {
                    if (candidatesMap.containsKey(candidateStr)) {
                        candidatesMap.get(candidateStr).incCounter();
                    } else {
                        kwdCand.setKeyword(candidateStr);
                        candidatesMap.put(candidateStr, kwdCand);
                    }
                }
                candidateStr = null;
                candidateStart = wordEnd;
                kwdCand = new KeywordCandidate();
            }
        }
    }

    keywordCandidates = new ArrayList<KeywordCandidate>();
    for (Entry<String, KeywordCandidate> e : candidatesMap.entrySet()) {
        keywordCandidates.add(e.getValue());
    }
}

---

• «
• 1
• 2
• 3
• »