java.text.CharacterIterator Java Examples

/**
 * Advances the iterator one step backwards.
 * @return The position of the last boundary position before the
 * current iteration position
 */
@Override
public int previous() {
    CharacterIterator text = getText();

    // if we have cached break positions and we're still in the range
    // covered by them, just move one step backward in the cache
    if (cachedBreakPositions != null && positionInCache > 0) {
        --positionInCache;
        text.setIndex(cachedBreakPositions[positionInCache]);
        return cachedBreakPositions[positionInCache];
    }

    // otherwise, dump the cache and use the inherited previous() method to move
    // backward.  This may fill up the cache with new break positions, in which
    // case we have to mark our position in the cache
    else {
        cachedBreakPositions = null;
        int result = super.previous();
        if (cachedBreakPositions != null) {
            positionInCache = cachedBreakPositions.length - 2;
        }
        return result;
    }
}
 

/**
 * Escape characters for text appearing as XML data, between tags.
 * 
 * <P>The following characters are replaced with corresponding character entities :
 * <table border='1' cellpadding='3' cellspacing='0'>
 * <tr><th> Character </th><th> Encoding </th></tr>
 * <tr><td> < </td><td> &lt; </td></tr>
 * <tr><td> > </td><td> &gt; </td></tr>
 * <tr><td> & </td><td> &amp; </td></tr>
 * <tr><td> " </td><td> &quot;</td></tr>
 * <tr><td> ' </td><td> &#039;</td></tr>
 * </table>
 * 
 * <P>Note that JSTL's {@code <c:out>} escapes the exact same set of 
 * characters as this method. <span class='highlight'>That is, {@code <c:out>}
 *  is good for escaping to produce valid XML, but not for producing safe 
 *  HTML.</span>
 */
public static String forXML(String aText) {
	if (aText == null) return null;
    final StringBuilder result = new StringBuilder();
    final StringCharacterIterator iterator = new StringCharacterIterator(aText);
    char character = iterator.current();
    while (character != CharacterIterator.DONE) {
        if (character == '<') {
            result.append("&lt;");
        } else if (character == '>') {
            result.append("&gt;");
        } else if (character == '\"') {
            result.append("&quot;");
        } else if (character == '\'') {
            result.append("&#039;");
        } else if (character == '&') {
            result.append("&amp;");
        } else {
            //the char is not a special one
            //add it to the result as is
            result.append(character);
        }
        character = iterator.next();
    }
    return result.toString();
}
 

/**
 * Indicates whether or not this <code>Font</code> can display the
 * text specified by the <code>iter</code> starting at
 * <code>start</code> and ending at <code>limit</code>.
 *
 * @param iter  a {@link CharacterIterator} object
 * @param start the specified starting offset into the specified
 *              <code>CharacterIterator</code>.
 * @param limit the specified ending offset into the specified
 *              <code>CharacterIterator</code>.
 * @return an offset into <code>iter</code> that points
 *          to the first character in <code>iter</code> that this
 *          <code>Font</code> cannot display; or <code>-1</code> if
 *          this <code>Font</code> can display all characters in
 *          <code>iter</code>.
 * @since 1.2
 */
public int canDisplayUpTo(CharacterIterator iter, int start, int limit) {
    Font2D font2d = getFont2D();
    char c = iter.setIndex(start);
    for (int i = start; i < limit; i++, c = iter.next()) {
        if (font2d.canDisplay(c)) {
            continue;
        }
        if (!Character.isHighSurrogate(c)) {
            return i;
        }
        char c2 = iter.next();
        // c2 could be CharacterIterator.DONE which is not a low surrogate.
        if (!Character.isLowSurrogate(c2)) {
            return i;
        }
        if (!font2d.canDisplay(Character.toCodePoint(c, c2))) {
            return i;
        }
        i++;
    }
    return -1;
}
 

private static final void checkIteratorText(AttributedCharacterIterator iterator, String expectedText) throws Exception {
    if (iterator.getEndIndex() - iterator.getBeginIndex() != expectedText.length()) {
        throwException(iterator, "text length doesn't match between original text and iterator");
    }

    char c = iterator.first();
    for (int i = 0; i < expectedText.length(); i++) {
        if (c != expectedText.charAt(i)) {
            throwException(iterator, "text content doesn't match between original text and iterator");
        }
        c = iterator.next();
    }
    if (c != CharacterIterator.DONE) {
        throwException(iterator, "iterator text doesn't end with DONE");
    }
}
 

private boolean literal(String text) {
    CharacterIterator ci = new StringCharacterIterator(text);
    char t = ci.first();
    if (c != t) return false;
    
    int start = col;
    boolean ret = true;
    for (t = ci.next(); t != CharacterIterator.DONE; t = ci.next()) {
        if (t != nextCharacter()) {
            ret = false;
            break;
        }
    }
    nextCharacter();

    if (!ret) error("literal " + text, start);
    return ret;
}
 

private static AttributedCharacterIterator getTrimmedTrailingSpacesIterator
        (AttributedCharacterIterator iterator) {
    int curIdx = iterator.getIndex();

    char c = iterator.last();
    while(c != CharacterIterator.DONE && Character.isWhitespace(c)) {
        c = iterator.previous();
    }

    if (c != CharacterIterator.DONE) {
        int endIdx = iterator.getIndex();

        if (endIdx == iterator.getEndIndex() - 1) {
            iterator.setIndex(curIdx);
            return iterator;
        } else {
            AttributedString trimmedText = new AttributedString(iterator,
                    iterator.getBeginIndex(), endIdx + 1);
            return trimmedText.getIterator();
        }
    } else {
        return null;
    }
}
 

private boolean literal(String text) {
    CharacterIterator ci = new StringCharacterIterator(text);
    char t = ci.first();
    if (c != t) { return false; }

    int start = col;
    boolean ret = true;
    for (t = ci.next(); t != CharacterIterator.DONE; t = ci.next()) {
        if (t != nextCharacter()) {
            ret = false;
            break;
        }
    }
    nextCharacter();

    if (!ret) { error("literal " + text, start); }
    return ret;
}
 

public static int append(Appendable result, CharacterIterator iterator) {
    try {
        int start = iterator.getBeginIndex();
        int limit = iterator.getEndIndex();
        int length = limit - start;
        if (start < limit) {
            result.append(iterator.first());
            while (++start < limit) {
                result.append(iterator.next());
            }
        }
        return length;
    } catch(IOException e) {
        throw new ICUUncheckedIOException(e);
    }
}
 

/**
 * Set the target text to be searched. Text iteration will then begin at 
 * the start of the text string. This method is useful if you want to 
 * reuse an iterator to search within a different body of text.
 * 
 * @param text new text iterator to look for match, 
 * @exception IllegalArgumentException thrown when text is null or has
 *               0 length
 * @see #getTarget
 * @stable ICU 2.4
 */
public void setTarget(CharacterIterator text)
{
    if (text == null || text.getEndIndex() == text.getIndex()) {
        throw new IllegalArgumentException("Illegal null or empty text");
    }

    text.setIndex(text.getBeginIndex());
    search_.setTarget(text);
    search_.matchedIndex_ = DONE;
    search_.setMatchedLength(0);
    search_.reset_ = true;
    search_.isForwardSearching_ = true;
    if (search_.breakIter() != null) {
        // Create a clone of CharacterItearator, so it won't
        // affect the position currently held by search_.text()
        search_.breakIter().setText((CharacterIterator)text.clone());
    }
    if (search_.internalBreakIter_ != null) {
        search_.internalBreakIter_.setText((CharacterIterator)text.clone());
    }
}
 

private static final void checkIteratorText(AttributedCharacterIterator iterator, String expectedText) throws Exception {
    if (iterator.getEndIndex() - iterator.getBeginIndex() != expectedText.length()) {
        throwException(iterator, "text length doesn't match between original text and iterator");
    }

    char c = iterator.first();
    for (int i = 0; i < expectedText.length(); i++) {
        if (c != expectedText.charAt(i)) {
            throwException(iterator, "text content doesn't match between original text and iterator");
        }
        c = iterator.next();
    }
    if (c != CharacterIterator.DONE) {
        throwException(iterator, "iterator text doesn't end with DONE");
    }
}
 

private boolean valid(String input) {
    if ("".equals(input)) return true;

    boolean ret = true;
    it = new StringCharacterIterator(input);
    c = it.first();
    col = 1;
    if (!value()) {
        ret = error("value", 1);
    } else {
        skipWhiteSpace();
        if (c != CharacterIterator.DONE) {
            ret = error("end", col);
        }
    }

    return ret;
}
 

/**
 * Sets the current iteration position to the last boundary position
 * before the specified position.
 * @param offset The position to begin searching from
 * @return The position of the last boundary before "offset"
 */
@Override
public int preceding(int offset) {
    CharacterIterator text = getText();
    checkOffset(offset, text);

    // if we have no cached break positions, or "offset" is outside the
    // range covered by the cache, we can just call the inherited routine
    // (which will eventually call other routines in this class that may
    // refresh the cache)
    if (cachedBreakPositions == null || offset <= cachedBreakPositions[0] ||
            offset > cachedBreakPositions[cachedBreakPositions.length - 1]) {
        cachedBreakPositions = null;
        return super.preceding(offset);
    }

    // on the other hand, if "offset" is within the range covered by the cache,
    // then all we have to do is search the cache for the last break position
    // before "offset"
    else {
        positionInCache = 0;
        while (positionInCache < cachedBreakPositions.length
               && offset > cachedBreakPositions[positionInCache]) {
            ++positionInCache;
        }
        --positionInCache;
        text.setIndex(cachedBreakPositions[positionInCache]);
        return text.getIndex();
    }
}
 

public int next() {
    char cp1 = iter.current();
    if (cp1 != CharacterIterator.DONE) {
        char cp2 = iter.next();
        if (Character.isHighSurrogate(cp1) && cp2 != CharacterIterator.DONE) {
            if (Character.isLowSurrogate(cp2)) {
                iter.next();
                return Character.toCodePoint(cp1, cp2);
            }
        }
        return cp1;
    }
    return DONE;
}
 

/**
 * Set the iterator to analyze a new piece of text.  This function resets
 * the current iteration position to the beginning of the text.
 * @param newText An iterator over the text to analyze.
 */
@Override
public void setText(CharacterIterator newText) {
    // Test iterator to see if we need to wrap it in a SafeCharIterator.
    // The correct behavior for CharacterIterators is to allow the
    // position to be set to the endpoint of the iterator.  Many
    // CharacterIterators do not uphold this, so this is a workaround
    // to permit them to use this class.
    int end = newText.getEndIndex();
    boolean goodIterator;
    try {
        newText.setIndex(end);  // some buggy iterators throw an exception here
        goodIterator = newText.getIndex() == end;
    }
    catch(IllegalArgumentException e) {
        goodIterator = false;
    }

    if (goodIterator) {
        text = newText;
    }
    else {
        text = new SafeCharIterator(newText);
    }
    text.first();

    cachedLastKnownBreak = BreakIterator.DONE;
}
 

private static final void checkIteratorSubranges(AttributedCharacterIterator iterator, Set keys, int[] expectedLimits) throws Exception {
    int previous = 0;
    char c = iterator.first();
    for (int i = 0; i < expectedLimits.length; i++) {
         if (iterator.getRunStart(keys) != previous || iterator.getRunLimit(keys) != expectedLimits[i]) {
             throwException(iterator, "run boundaries are not as expected: " + iterator.getRunStart(keys) + ", " + iterator.getRunLimit(keys) + " for keys " + keys);
         }
         previous = expectedLimits[i];
         c = iterator.setIndex(previous);
    }
    if (c != CharacterIterator.DONE) {
        throwException(iterator, "iterator's run sequence doesn't end with DONE");
    }
}
 

public StandardGlyphVector(Font font, CharacterIterator iter, FontRenderContext frc) {
    int offset = iter.getBeginIndex();
    char[] text = new char [iter.getEndIndex() - offset];
    for(char c = iter.first();
        c != CharacterIterator.DONE;
        c = iter.next()) {
        text[iter.getIndex() - offset] = c;
    }
    init(font, text, 0, text.length, frc, UNINITIALIZED_FLAGS);
}
 

private static final void checkIteratorSubranges(AttributedCharacterIterator iterator, Attribute key, int[] expectedLimits) throws Exception {
    int previous = 0;
    char c = iterator.first();
    for (int i = 0; i < expectedLimits.length; i++) {
         if (iterator.getRunStart(key) != previous || iterator.getRunLimit(key) != expectedLimits[i]) {
             throwException(iterator, "run boundaries are not as expected: " + iterator.getRunStart(key) + ", " + iterator.getRunLimit(key) + " for key " + key);
         }
         previous = expectedLimits[i];
         c = iterator.setIndex(previous);
    }
    if (c != CharacterIterator.DONE) {
        throwException(iterator, "iterator's run sequence doesn't end with DONE");
    }
}
 

/**
 * Set the iterator to analyze a new piece of text.  This function resets
 * the current iteration position to the beginning of the text.
 * @param newText An iterator over the text to analyze.
 */
@Override
public void setText(CharacterIterator newText) {
    // Test iterator to see if we need to wrap it in a SafeCharIterator.
    // The correct behavior for CharacterIterators is to allow the
    // position to be set to the endpoint of the iterator.  Many
    // CharacterIterators do not uphold this, so this is a workaround
    // to permit them to use this class.
    int end = newText.getEndIndex();
    boolean goodIterator;
    try {
        newText.setIndex(end);  // some buggy iterators throw an exception here
        goodIterator = newText.getIndex() == end;
    }
    catch(IllegalArgumentException e) {
        goodIterator = false;
    }

    if (goodIterator) {
        text = newText;
    }
    else {
        text = new SafeCharIterator(newText);
    }
    text.first();

    cachedLastKnownBreak = BreakIterator.DONE;
}
 

/**
 * Creates a clone of this iterator.  Clones the underlying character iterator.
 * @see UCharacterIterator#clone()
 */
public Object clone(){
    try {
        CharacterIteratorWrapper result = (CharacterIteratorWrapper) super.clone();
        result.iterator = (CharacterIterator)this.iterator.clone();
        return result;
    } catch (CloneNotSupportedException e) {
        return null; // only invoked if bad underlying character iterator
    }
}
 

ComponentLine(AttributedCharacterIterator it, Font defaultFont, Color defaultColor) {
    for (char c = it.first(); c != CharacterIterator.DONE; c = it.next()) {
        Font font = (Font) it.getAttribute(TextAttribute.FONT);
        Color color = (Color) it.getAttribute(TextAttribute.FOREGROUND);
        mySymbols.add(new Symbol(c, createFont(font, defaultFont), createColor(color, defaultColor)));
    }
    checkSpaces(defaultFont, defaultColor);
}
 

/**
 * Sets the current iteration position to the beginning of the text.
 * (i.e., the CharacterIterator's starting offset).
 * @return The offset of the beginning of the text.
 */
@Override
public int first() {
    CharacterIterator t = getText();

    t.first();
    return t.getIndex();
}
 

public void testSetTextCharacterIterator() {
    try {
        iterator.setText((CharacterIterator) null);
        fail();
    } catch (NullPointerException e) {
    }
    CharacterIterator it = new StringCharacterIterator("abc");
    iterator.setText(it);
    assertSame(it, iterator.getText());
}
 

public void testLast() {
    CharArrayIterator ci = new CharArrayIterator();
    ci.setText("testing".toCharArray(), 0, "testing".length());
    assertEquals('g', ci.last());
    assertEquals(ci.getIndex(), ci.getEndIndex() - 1);
    ci.setText(new char[] {}, 0, 0);
    assertEquals(CharacterIterator.DONE, ci.last());
    assertEquals(ci.getEndIndex(), ci.getIndex());
}
 

private static int codePointAt(CharacterIterator iter, int index) {
    int currentIterIndex = iter.getIndex();
    char codeUnit = iter.setIndex(index);
    int cp = codeUnit;
    if (Character.isHighSurrogate(codeUnit)) {
        char nextUnit = iter.next();
        if (Character.isLowSurrogate(nextUnit)) {
            cp = Character.toCodePoint(codeUnit, nextUnit);
        }
    }
    iter.setIndex(currentIterIndex);  // restore iter position
    return cp;
}
 

/**
 * Set the iterator to analyze a new piece of text.  This function resets
 * the current iteration position to the beginning of the text.
 * @param newText An iterator over the text to analyze.
 */
@Override
public void setText(CharacterIterator newText) {
    // Test iterator to see if we need to wrap it in a SafeCharIterator.
    // The correct behavior for CharacterIterators is to allow the
    // position to be set to the endpoint of the iterator.  Many
    // CharacterIterators do not uphold this, so this is a workaround
    // to permit them to use this class.
    int end = newText.getEndIndex();
    boolean goodIterator;
    try {
        newText.setIndex(end);  // some buggy iterators throw an exception here
        goodIterator = newText.getIndex() == end;
    }
    catch(IllegalArgumentException e) {
        goodIterator = false;
    }

    if (goodIterator) {
        text = newText;
    }
    else {
        text = new SafeCharIterator(newText);
    }
    text.first();

    cachedLastKnownBreak = BreakIterator.DONE;
}
 

private static final void checkIteratorSubranges(AttributedCharacterIterator iterator, int[] expectedLimits) throws Exception {
    int previous = 0;
    char c = iterator.first();
    for (int i = 0; i < expectedLimits.length; i++) {
         if (iterator.getRunStart() != previous || iterator.getRunLimit() != expectedLimits[i]) {
             throwException(iterator, "run boundaries are not as expected: " + iterator.getRunStart() + ", " + iterator.getRunLimit());
         }
         previous = expectedLimits[i];
         c = iterator.setIndex(previous);
    }
    if (c != CharacterIterator.DONE) {
        throwException(iterator, "iterator's run sequence doesn't end with DONE");
    }
}
 

/**
 * @see UCharacterIterator#previous()
 */
public int previous() {
    int i = iterator.previous();
    if(i==CharacterIterator.DONE){
        return DONE;
    }
    return i;
}
 

private static final void checkIteratorSubranges(AttributedCharacterIterator iterator, int[] expectedLimits) throws Exception {
    int previous = 0;
    char c = iterator.first();
    for (int i = 0; i < expectedLimits.length; i++) {
         if (iterator.getRunStart() != previous || iterator.getRunLimit() != expectedLimits[i]) {
             throwException(iterator, "run boundaries are not as expected: " + iterator.getRunStart() + ", " + iterator.getRunLimit());
         }
         previous = expectedLimits[i];
         c = iterator.setIndex(previous);
    }
    if (c != CharacterIterator.DONE) {
        throwException(iterator, "iterator's run sequence doesn't end with DONE");
    }
}
 

/**
 * @see UCharacterIterator#current()
 */
public int current() {
    int c = iterator.current();
    if(c==CharacterIterator.DONE){
      return DONE;
    }
    return c;
}
 

/**
 * Set the iterator to analyze a new piece of text.  This function resets
 * the current iteration position to the beginning of the text.
 * @param newText An iterator over the text to analyze.
 */
@Override
public void setText(CharacterIterator newText) {
    // Test iterator to see if we need to wrap it in a SafeCharIterator.
    // The correct behavior for CharacterIterators is to allow the
    // position to be set to the endpoint of the iterator.  Many
    // CharacterIterators do not uphold this, so this is a workaround
    // to permit them to use this class.
    int end = newText.getEndIndex();
    boolean goodIterator;
    try {
        newText.setIndex(end);  // some buggy iterators throw an exception here
        goodIterator = newText.getIndex() == end;
    }
    catch(IllegalArgumentException e) {
        goodIterator = false;
    }

    if (goodIterator) {
        text = newText;
    }
    else {
        text = new SafeCharIterator(newText);
    }
    text.first();

    cachedLastKnownBreak = BreakIterator.DONE;
}