/*
*******************************************************************************
- * Copyright (C) 1996-2012, International Business Machines Corporation and *
+ * Copyright (C) 1996-2013, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*/
*/
public abstract int current();
+ /**
+ * For RuleBasedBreakIterators, return the status tag from the
+ * break rule that determined the most recently
+ * returned break position.
+ * <p>
+ * For break iterator types that do not support a rule status,
+ * a default value of 0 is returned.
+ * <p>
+ * @return The status from the break rule that determined the most recently
+ * returned break position.
+ *
+ * @draft ICU 52
+ * @provisional This is a draft API and might change in a future release of ICU.
+ */
+
+ public int getRuleStatus() {
+ return 0;
+ }
+
+ /**
+ * For RuleBasedBreakIterators, get the status (tag) values from the break rule(s)
+ * that determined the most recently returned break position.
+ * <p>
+ * For break iterator types that do not support rule status,
+ * no values are returned.
+ * <p>
+ * If the size of the output array is insufficient to hold the data,
+ * the output will be truncated to the available length. No exception
+ * will be thrown.
+ *
+ * @param fillInArray an array to be filled in with the status values.
+ * @return The number of rule status values from rules that determined
+ * the most recent boundary returned by the break iterator.
+ * In the event that the array is too small, the return value
+ * is the total number of status values that were available,
+ * not the reduced number that were actually returned.
+ * @draft ICU 52
+ * @provisional This is a draft API and might change in a future release of ICU.
+ */
+ public int getRuleStatusVec(int[] fillInArray) {
+ if (fillInArray != null && fillInArray.length > 0) {
+ fillInArray[0] = 0;
+ }
+ return 1;
+ }
+
/**
* Returns a CharacterIterator over the text being analyzed.
* For at least some subclasses of BreakIterator, this is a reference
* @stable ICU 2.4
*/
public static final int KIND_WORD = 1;
- /**
+ /**
* {@icu}
* @stable ICU 2.4
*/
public static final int KIND_LINE = 2;
- /**
+ /**
* {@icu}
* @stable ICU 2.4
*/
public static final int KIND_SENTENCE = 3;
- /**
+ /**
* {@icu}
* @stable ICU 2.4
*/
/*
* Created on May 5, 2004
- *
+ *
* Copyright (C) 2004-2013 International Business Machines Corporation and others.
* All Rights Reserved.
*
*
*/
public class RBBITestExtended extends TestFmwk {
-
+
public static void main(String[] args)throws Exception {
new RBBITestExtended().run(args);
}
-
-
-public RBBITestExtended() {
+
+
+public RBBITestExtended() {
}
errln("Could not open test data file rbbitst.txt");
return;
}
- isr = new InputStreamReader(is, "UTF-8");
+ isr = new InputStreamReader(is, "UTF-8");
int c;
int count = 0;
for (;;) {
// BOM in the test data file. Discard it.
continue;
}
-
+
UTF16.append(testFileBuf, c);
}
-
+
} catch (IOException e) {
errln(e.toString());
return;
}
-
+
String testString = testFileBuf.toString();
-
+
final int PARSE_COMMENT = 1;
final int PARSE_TAG = 2;
if (c == -1) {
errln("Error in named character in test file at line " + lineNum +
", col " + column);
- } else {
+ } else {
// Named code point was recognized. Insert it
// into the test data.
UTF16.append(tp.dataToBreak, c);
tp.srcLine[i] = lineNum;
tp.srcCol[i] = column;
}
-
+
}
if (nameEndIdx > charIdx) {
charIdx = nameEndIdx+1;
if (c == CH_BACKSLASH) {
// Check for \ at end of line, a line continuation.
// Advance over (discard) the newline
- int cp = UTF16.charAt(testString, charIdx);
+ int cp = UTF16.charAt(testString, charIdx);
if (cp == CH_CR && charIdx<len && UTF16.charAt(testString, charIdx+1) == CH_LF) {
// We have a CR LF
// Need an extra increment of the input ptr to move over both of them
tp.srcLine[i] = lineNum;
tp.srcCol[i] = column;
}
-
+
break;
}
// Normal, non-escaped data char.
UTF16.append(tp.dataToBreak, c);
-
+
// Save the mapping from offset in the data to line/column numbers in
// the original input file. Will be used for better error messages only.
// If there's an expected break before this char, the slot in the mapping
errln("Syntax Error in test file at line "+ lineNum +", col %d" + column);
return;
-
+
// parseState = PARSE_COMMENT; // TODO: unreachable. Don't stop on errors.
// break;
}
-
+
}
}
if (t.bi == null) {
return;
}
-
+
t.bi.setText(t.dataToBreak.toString());
//
// Run the iterator forward
// and this one.
for (i=prevBP+1; i<bp; i++) {
if (t.expectedBreaks[i] != 0) {
- errln("Forward Iteration, break expected, but not found. Pos=" + i +
+ errln("Forward Iteration, break expected, but not found. Pos=" + i +
" File line,col= " + t.srcLine[i] + ", " + t.srcCol[i]);
}
}
// Check that the break we did find was expected
if (t.expectedBreaks[bp] == 0) {
- errln("Forward Iteration, break found, but not expected. Pos=" + bp +
+ errln("Forward Iteration, break found, but not expected. Pos=" + bp +
" File line,col= " + t.srcLine[bp] + ", " + t.srcCol[bp]);
} else {
// The break was expected.
expectedTagVal = 0;
}
int line = t.srcLine[bp];
- int rs = ((RuleBasedBreakIterator)t.bi).getRuleStatus();
+ int rs = t.bi.getRuleStatus();
if (rs != expectedTagVal) {
errln("Incorrect status for forward break. Pos = " + bp +
". File line,col = " + line + ", " + t.srcCol[bp] + "\n" +
" Actual, Expected status = " + rs + ", " + expectedTagVal);
}
+ int[] fillInArray = new int[4];
+ int numStatusVals = t.bi.getRuleStatusVec(fillInArray);
+ assertTrue("", numStatusVals >= 1);
+ assertEquals("", expectedTagVal, fillInArray[0]);
}
// Verify that there were no missed expected breaks after the last one found
for (i=prevBP+1; i<t.dataToBreak.length()+1; i++) {
if (t.expectedBreaks[i] != 0) {
- errln("Forward Iteration, break expected, but not found. Pos=" + i +
+ errln("Forward Iteration, break expected, but not found. Pos=" + i +
" File line,col= " + t.srcLine[i] + ", " + t.srcCol[i]);
}
}
-
+
//
// Run the iterator backwards, verify that the same breaks are found.
//
// and this one. (UVector returns zeros for index out of bounds.)
for (i=prevBP-1; i>bp; i--) {
if (t.expectedBreaks[i] != 0) {
- errln("Reverse Itertion, break expected, but not found. Pos=" + i +
+ errln("Reverse Itertion, break expected, but not found. Pos=" + i +
" File line,col= " + t.srcLine[i] + ", " + t.srcCol[i]);
}
}
// Check that the break we did find was expected
if (t.expectedBreaks[bp] == 0) {
- errln("Reverse Itertion, break found, but not expected. Pos=" + bp +
+ errln("Reverse Itertion, break found, but not expected. Pos=" + bp +
" File line,col= " + t.srcLine[bp] + ", " + t.srcCol[bp]);
} else {
// The break was expected.
expectedTagVal = 0;
}
int line = t.srcLine[bp];
- int rs = ((RuleBasedBreakIterator)t.bi).getRuleStatus();
+ int rs = t.bi.getRuleStatus();
if (rs != expectedTagVal) {
errln("Incorrect status for reverse break. Pos= " + bp +
"File line,col= " + line + ", " + t.srcCol[bp] + "\n" +
" Actual, Expected status = " + rs + ", " + expectedTagVal);
- }
+ }
}
prevBP = bp;
boolean boundaryExpected = (t.expectedBreaks[i] != 0);
boolean boundaryFound = t.bi.isBoundary(i);
if (boundaryExpected != boundaryFound) {
- errln("isBoundary(" + i + ") incorrect.\n" +
+ errln("isBoundary(" + i + ") incorrect.\n" +
" File line,col= " + t.srcLine[i] + ", " + t.srcCol[i] +
" Expected, Actual= " + boundaryExpected + ", " + boundaryFound);
}
projects / icu / commitdiff