Examples with UnicodeSet android.icu.text.UnicodeSet used on opensource projects

Example 26 with UnicodeSet

use of android.icu.text.UnicodeSet in project j2objc by google.

the class UtilityTest method TestUnicodeSet.

@Test
public void TestUnicodeSet() {
    String[] array = new String[] { "a", "b", "c", "{de}" };
    List list = Arrays.asList(array);
    Set aset = new HashSet(list);
    logln(" *** The source set's size is: " + aset.size());
    // The size reads 4
    UnicodeSet set = new UnicodeSet();
    set.clear();
    set.addAll(aset);
    logln(" *** After addAll, the UnicodeSet size is: " + set.size());
// The size should also read 4, but 0 is seen instead
}

Example 27 with UnicodeSet

use of android.icu.text.UnicodeSet in project j2objc by google.

the class CollationDataBuilder method setDigitTags.

protected void setDigitTags() {
    UnicodeSet digits = new UnicodeSet("[:Nd:]");
    UnicodeSetIterator iter = new UnicodeSetIterator(digits);
    while (iter.next()) {
        assert (iter.codepoint != UnicodeSetIterator.IS_STRING);
        int c = iter.codepoint;
        int ce32 = trie.get(c);
        if (ce32 != Collation.FALLBACK_CE32 && ce32 != Collation.UNASSIGNED_CE32) {
            int index = addCE32(ce32);
            if (index > Collation.MAX_INDEX) {
                throw new IndexOutOfBoundsException("too many mappings");
            // BufferOverflowException is a better fit
            // but cannot be constructed with a message string.
            }
            ce32 = Collation.makeCE32FromTagIndexAndLength(Collation.DIGIT_TAG, index, // u_charDigitValue(c)
            UCharacter.digit(c));
            trie.set(c, ce32);
        }
    }
}

Example 28 with UnicodeSet

use of android.icu.text.UnicodeSet in project j2objc by google.

the class TestBoilerplate method getSet.

public static <T> UnicodeSet getSet(Map<Integer, T> m, T value) {
    UnicodeSet result = new UnicodeSet();
    for (Iterator<Integer> it = m.keySet().iterator(); it.hasNext(); ) {
        Integer key = it.next();
        T val = m.get(key);
        if (!val.equals(value))
            continue;
        result.add(key.intValue());
    }
    return result;
}

Example 29 with UnicodeSet

use of android.icu.text.UnicodeSet in project j2objc by google.

the class StringTokenizer method nextToken.

/**
 * Returns the next token in this string tokenizer's string. First,
 * the set of characters considered to be delimiters by this
 * <tt>StringTokenizer</tt> object is changed to be the characters in
 * the string <tt>delim</tt>. Then the next token in the string
 * after the current position is returned. The current position is
 * advanced beyond the recognized token.  The new delimiter set
 * remains the default after this call.
 * @param delim the new delimiters.
 * @return the next token, after switching to the new delimiter set.
 * @exception NoSuchElementException if there are no more tokens in
 *            this tokenizer's string.
 */
public String nextToken(String delim) {
    m_delimiters_ = EMPTY_DELIMITER_;
    if (delim != null && delim.length() > 0) {
        m_delimiters_ = new UnicodeSet();
        m_delimiters_.addAll(delim);
    }
    return nextToken(m_delimiters_);
}

Example 30 with UnicodeSet

use of android.icu.text.UnicodeSet in project j2objc by google.

the class BasicTest method TestCanonIterData.

@Test
public void TestCanonIterData() {
    // For now, just a regression test.
    Normalizer2Impl impl = Norm2AllModes.getNFCInstance().impl.ensureCanonIterData();
    // but it is not a segment starter because it occurs in a decomposition mapping.
    if (impl.isCanonSegmentStarter(0xfb5)) {
        errln("isCanonSegmentStarter(U+0fb5)=true is wrong");
    }
    // For [:Segment_Starter:] to work right, not just the property function has to work right,
    // UnicodeSet also needs a correct range starts set.
    UnicodeSet segStarters = new UnicodeSet("[:Segment_Starter:]").freeze();
    if (segStarters.contains(0xfb5)) {
        errln("[:Segment_Starter:].contains(U+0fb5)=true is wrong");
    }
    // Try characters up to Kana and miscellaneous CJK but below Han (for expediency).
    for (int c = 0; c <= 0x33ff; ++c) {
        boolean isStarter = impl.isCanonSegmentStarter(c);
        boolean isContained = segStarters.contains(c);
        if (isStarter != isContained) {
            errln(String.format("discrepancy: isCanonSegmentStarter(U+%04x)=%5b != " + "[:Segment_Starter:].contains(same)", c, isStarter));
        }
    }
}