/**
* 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;
}
/** Returns the position of next character. */
private int getNextIndex() {
int index = text.getIndex() + getCurrentCodePointCount();
int endIndex = text.getEndIndex();
if (index > endIndex) {
return endIndex;
} else {
return index;
}
}
/** Returns next character */
int getNext() {
int index = text.getIndex();
int endIndex = text.getEndIndex();
if (index == endIndex || (index += getCurrentCodePointCount()) >= endIndex) {
return CharacterIterator.DONE;
}
text.setIndex(index);
return getCurrent();
}
/**
* 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.
*/
@Override
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();
}
/** Returns the count of next character. */
private int getCurrentCodePointCount() {
char c1 = text.current();
if (Character.isHighSurrogate(c1) && text.getIndex() < text.getEndIndex()) {
char c2 = text.next();
text.previous();
if (Character.isLowSurrogate(c2)) {
return 2;
}
}
return 1;
}
/** Returns current character */
int getCurrent() {
char c1 = text.current();
if (Character.isHighSurrogate(c1) && text.getIndex() < text.getEndIndex()) {
char c2 = text.next();
text.previous();
if (Character.isLowSurrogate(c2)) {
return Character.toCodePoint(c1, c2);
}
}
return (int) c1;
}
public void selectionDone(SelectionEvent evt) {
if (!useUnixTextSelection) return;
Object o = evt.getSelection();
if (!(o instanceof CharacterIterator)) return;
CharacterIterator iter = (CharacterIterator) o;
// first see if we can access the clipboard
SecurityManager securityManager;
securityManager = System.getSecurityManager();
if (securityManager != null) {
try {
securityManager.checkSystemClipboardAccess();
} catch (SecurityException e) {
return; // Can't access clipboard.
}
}
int sz = iter.getEndIndex() - iter.getBeginIndex();
if (sz == 0) return;
char[] cbuff = new char[sz];
cbuff[0] = iter.first();
for (int i = 1; i < cbuff.length; ++i) {
cbuff[i] = iter.next();
}
final String strSel = new String(cbuff);
// HACK: getSystemClipboard sometimes deadlocks on
// linux when called from the AWT Thread. The Thread
// creation prevents that.
new Thread() {
public void run() {
Clipboard cb;
cb = Toolkit.getDefaultToolkit().getSystemClipboard();
StringSelection sel;
sel = new StringSelection(strSel);
cb.setContents(sel, sel);
}
}.start();
}
public int getLength() {
return (iterator.getEndIndex() - iterator.getBeginIndex());
}
private char next() {
if (it.getIndex() == it.getEndIndex())
throw new RuntimeException("Reached end of input at the " + it.getIndex() + "th character.");
c = it.next();
return c;
}
/**
* 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()) {
return BreakIterator.DONE;
}
// no matter what, we always advance at least one character forward
int result = getNextIndex();
int lookaheadResult = 0;
// begin in state 1
int state = START_STATE;
int category;
int c = getCurrent();
// loop until we reach the end of the text or transition to state 0
while (c != CharacterIterator.DONE && state != STOP_STATE) {
// look up the current character's character category (which tells us
// which column in the state table to look at)
category = lookupCategory(c);
// if the character isn't an ignore character, look up a state
// transition in the state table
if (category != IGNORE) {
state = lookupState(state, category);
}
// if the state we've just transitioned to is a lookahead state,
// (but not also an end state), save its position. If it's
// both a lookahead state and an end state, update the break position
// to the last saved lookup-state position
if (lookaheadStates[state]) {
if (endStates[state]) {
result = lookaheadResult;
} else {
lookaheadResult = getNextIndex();
}
}
// otherwise, if the state we've just transitioned to is an accepting
// state, update the break position to be the current iteration position
else {
if (endStates[state]) {
result = getNextIndex();
}
}
c = getNext();
}
// if we've run off the end of the text, and the very last character took us into
// a lookahead state, advance the break position to the lookahead position
// (the theory here is that if there are no characters at all after the lookahead
// position, that always matches the lookahead criteria)
if (c == CharacterIterator.DONE && lookaheadResult == text.getEndIndex()) {
result = lookaheadResult;
}
text.setIndex(result);
return result;
}
/** 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");
}
}
SafeCharIterator(CharacterIterator base) {
this.base = base;
this.rangeStart = base.getBeginIndex();
this.rangeLimit = base.getEndIndex();
this.currentIndex = base.getIndex();
}