rulebasedbreakiterator.java

java源代码 请看看啊 提点宝贵的意见

     */
    public Object clone()
    {
        RuleBasedBreakIterator result = (RuleBasedBreakIterator) super.clone();
        if (text != null) {
            result.text = (CharacterIterator) text.clone();
        }
        return result;
    }

    /**
     * Returns true if both BreakIterators are of the same class, have the same
     * rules, and iterate over the same text.
     */
    public boolean equals(Object that) {
        try {
            RuleBasedBreakIterator other = (RuleBasedBreakIterator) that;
            if (!description.equals(other.description)) {
                return false;
            }
            if (text == null) {
                return other.text == null;
            }
            else {
                return text.equals(other.text);
            }
        }
        catch(ClassCastException e) {
            return false;
        }
    }

    /**
     * Returns the description used to create this iterator
     */
    public String toString() {
        return description;
    }

    /**
     * Compute a hashcode for this BreakIterator
     * @return A hash code
     */
    public int hashCode()
    {
        return description.hashCode();
    }

    //=======================================================================
    // BreakIterator overrides
    //=======================================================================

    /**
     * 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.
     */
    public int first() {
        CharacterIterator t = getText();

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

    /**
     * Sets the current iteration position to the end of the text.
     * (i.e., the CharacterIterator's ending offset).
     * @return The text's past-the-end offset.
     */
    public int last() {
        CharacterIterator t = getText();

        // I'm not sure why, but t.last() returns the offset of the last character,
        // rather than the past-the-end offset
        t.setIndex(t.getEndIndex());
        return t.getIndex();
    }

    /**
     * Advances the iterator either forward or backward the specified number of steps.
     * Negative values move backward, and positive values move forward.  This is
     * equivalent to repeatedly calling next() or previous().
     * @param n The number of steps to move.  The sign indicates the direction
     * (negative is backwards, and positive is forwards).
     * @return The character offset of the boundary position n boundaries away from
     * the current one.
     */
    public int next(int n) {
        int result = current();
        while (n > 0) {
            result = handleNext();
            --n;
        }
        while (n < 0) {
            result = previous();
            ++n;
        }
        return result;
    }

    /**
     * Advances the iterator to the next boundary position.
     * @return The position of the first boundary after this one.
     */
    public int next() {
        return handleNext();
    }

    /**
     * Advances the iterator backwards, to the last boundary preceding this one.
     * @return The position of the last boundary position preceding this one.
     */
    public int previous() {
        // if we're already sitting at the beginning of the text, return DONE
        CharacterIterator text = getText();
        if (current() == text.getBeginIndex()) {
            return BreakIterator.DONE;
        }

        // set things up.  handlePrevious() will back us up to some valid
        // break position before the current position (we back our internal
        // iterator up one step to prevent handlePrevious() from returning
        // the current position), but not necessarily the last one before
        // where we started
        int start = current();
        text.previous();
        int lastResult = handlePrevious();
        int result = lastResult;

        // iterate forward from the known break position until we pass our
        // starting point.  The last break position before the starting
        // point is our return value
        while (result != BreakIterator.DONE && result < start) {
            lastResult = result;
            result = handleNext();
        }

        // set the current iteration position to be the last break position
        // before where we started, and then return that value
        text.setIndex(lastResult);
        return lastResult;
    }

    /**
     * Throw IllegalArgumentException unless begin <= offset < end.
     */
    protected static final void checkOffset(int offset, CharacterIterator text) {
        if (offset < text.getBeginIndex() || offset >= text.getEndIndex()) {
            throw new IllegalArgumentException("offset out of bounds");
        }
    }

    /**
     * Sets the iterator to refer to the first boundary position following
     * the specified position.
     * @offset The position from which to begin searching for a break position.
     * @return The position of the first break after the current position.
     */
    public int following(int offset) {

        CharacterIterator text = getText();
        checkOffset(offset, text);

        // Set our internal iteration position (temporarily)
        // to the position passed in.  If this is the _beginning_ position,
        // then we can just use next() to get our return value
        text.setIndex(offset);
        if (offset == text.getBeginIndex()) {
            return handleNext();
        }

        // otherwise, we have to sync up first.  Use handlePrevious() to back
        // us up to a known break position before the specified position (if
        // we can determine that the specified position is a break position,
        // we don't back up at all).  This may or may not be the last break
        // position at or before our starting position.  Advance forward
        // from here until we've passed the starting position.  The position
        // we stop on will be the first break position after the specified one.
        int result = handlePrevious();
        while (result != BreakIterator.DONE && result <= offset) {
            result = handleNext();
        }
        return result;
    }

    /**
     * Sets the iterator to refer to the last boundary position before the
     * specified position.
     * @offset The position to begin searching for a break from.
     * @return The position of the last boundary before the starting position.
     */
    public int preceding(int offset) {
        // if we start by updating the current iteration position to the
        // position specified by the caller, we can just use previous()
        // to carry out this operation
        CharacterIterator text = getText();
        checkOffset(offset, text);
        text.setIndex(offset);
        return previous();
    }

    /**
     * Returns true if the specfied position is a boundary position.  As a side
     * effect, leaves the iterator pointing to the first boundary position at
     * or after "offset".
     * @param offset the offset to check.
     * @return True if "offset" is a boundary position.
     */
    public boolean isBoundary(int offset) {
        CharacterIterator text = getText();
        checkOffset(offset, text);
        if (offset == text.getBeginIndex()) {
            return true;
        }

        // to check whether this is a boundary, we can use following() on the
        // position before the specified one and return true if the position we
        // get back is the one the user specified
        else {
            return following(offset - 1) == offset;
        }
    }

    /**
     * Returns the current iteration position.
     * @return The current iteration position.
     */
    public int current() {
        return getText().getIndex();
    }

    /**
     * Return a CharacterIterator over the text being analyzed.  This version
     * of this method returns the actual CharacterIterator we're using internally.
     * Changing the state of this iterator can have undefined consequences.  If
     * you need to change it, clone it first.
     * @return An iterator over the text being analyzed.
     */
    public CharacterIterator getText() {
        // The iterator is initialized pointing to no text at all, so if this
        // function is called while we're in that state, we have to fudge an
        // an iterator to return.
        if (text == null) {
            text = new StringCharacterIterator("");
        }
        return text;
    }

    /**
     * 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.
     */
    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();
    }


    //=======================================================================
    // implementation
    //=======================================================================

    /**
     * This method is the actual implementation of the next() method.  All iteration
     * vectors through here.  This method initializes the state machine to state 1
     * and advances through the text character by character until we reach the end
     * of the text or the state machine transitions to state 0.  We update our return
     * value every time the state machine passes through a possible end state.
     */
    protected int handleNext() {
        // if we're already at the end of the text, return DONE.
        CharacterIterator text = getText();
        if (text.getIndex() == text.getEndIndex()) {