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

Example 11 with UnicodeSet

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

the class CollationAPITest method TestSubClass.

/**
 * Simple test to see if Collator is subclassable.
 * Also test coverage of base class methods that are overridden by RuleBasedCollator.
 */
@Test
public void TestSubClass() {
    class TestCollator extends Collator {

        @Override
        public boolean equals(Object that) {
            return this == that;
        }

        @Override
        public int hashCode() {
            return 0;
        }

        @Override
        public int compare(String source, String target) {
            return source.compareTo(target);
        }

        @Override
        public CollationKey getCollationKey(String source) {
            return new CollationKey(source, getRawCollationKey(source, new RawCollationKey()));
        }

        @Override
        public RawCollationKey getRawCollationKey(String source, RawCollationKey key) {
            byte[] temp1 = source.getBytes();
            byte[] temp2 = new byte[temp1.length + 1];
            System.arraycopy(temp1, 0, temp2, 0, temp1.length);
            temp2[temp1.length] = 0;
            if (key == null) {
                key = new RawCollationKey();
            }
            key.bytes = temp2;
            key.size = temp2.length;
            return key;
        }

        @Override
        public void setVariableTop(int ce) {
            if (isFrozen()) {
                throw new UnsupportedOperationException("Attempt to modify frozen object");
            }
        }

        @Override
        public int setVariableTop(String str) {
            if (isFrozen()) {
                throw new UnsupportedOperationException("Attempt to modify frozen object");
            }
            return 0;
        }

        @Override
        public int getVariableTop() {
            return 0;
        }

        @Override
        public VersionInfo getVersion() {
            return VersionInfo.getInstance(0);
        }

        @Override
        public VersionInfo getUCAVersion() {
            return VersionInfo.getInstance(0);
        }
    }
    Collator col1 = new TestCollator();
    Collator col2 = new TestCollator();
    if (col1.equals(col2)) {
        errln("2 different instance of TestCollator should fail");
    }
    if (col1.hashCode() != col2.hashCode()) {
        errln("Every TestCollator has the same hashcode");
    }
    String abc = "abc";
    String bcd = "bcd";
    if (col1.compare(abc, bcd) != abc.compareTo(bcd)) {
        errln("TestCollator compare should be the same as the default " + "string comparison");
    }
    CollationKey key = col1.getCollationKey(abc);
    byte[] temp1 = abc.getBytes();
    byte[] temp2 = new byte[temp1.length + 1];
    System.arraycopy(temp1, 0, temp2, 0, temp1.length);
    temp2[temp1.length] = 0;
    if (!java.util.Arrays.equals(key.toByteArray(), temp2) || !key.getSourceString().equals(abc)) {
        errln("TestCollator collationkey API is returning wrong values");
    }
    UnicodeSet set = col1.getTailoredSet();
    if (!set.equals(new UnicodeSet(0, 0x10FFFF))) {
        errln("Error getting default tailored set");
    }
    // Base class code coverage.
    // Most of these methods are dummies;
    // they are overridden by any subclass that supports their features.
    assertEquals("compare(strings as Object)", 0, col1.compare(new StringBuilder("abc"), new StringBuffer("abc")));
    col1.setStrength(Collator.SECONDARY);
    assertNotEquals("getStrength()", Collator.PRIMARY, col1.getStrength());
    // setStrength2() is @internal and returns this.
    // The base class getStrength() always returns the same value,
    // since the base class does not have a field to store the strength.
    assertNotEquals("setStrength2().getStrength()", Collator.PRIMARY, col1.setStrength2(Collator.IDENTICAL).getStrength());
    // (base class).setDecomposition() may or may not be implemented.
    try {
        col1.setDecomposition(Collator.CANONICAL_DECOMPOSITION);
    } catch (UnsupportedOperationException expected) {
    }
    // don't care about the value
    assertNotEquals("getDecomposition()", -1, col1.getDecomposition());
    // (base class).setMaxVariable() may or may not be implemented.
    try {
        col1.setMaxVariable(Collator.ReorderCodes.CURRENCY);
    } catch (UnsupportedOperationException expected) {
    }
    // don't care about the value
    assertNotEquals("getMaxVariable()", -1, col1.getMaxVariable());
    // (base class).setReorderCodes() may or may not be implemented.
    try {
        col1.setReorderCodes(0, 1, 2);
    } catch (UnsupportedOperationException expected) {
    }
    try {
        col1.getReorderCodes();
    } catch (UnsupportedOperationException expected) {
    }
    assertFalse("getDisplayName()", Collator.getDisplayName(Locale.GERMAN).isEmpty());
    assertFalse("getDisplayName()", Collator.getDisplayName(Locale.GERMAN, Locale.ITALIAN).isEmpty());
    assertNotEquals("getLocale()", ULocale.GERMAN, col1.getLocale(ULocale.ACTUAL_LOCALE));
    // Cover Collator.setLocale() which is only package-visible.
    Object token = Collator.registerInstance(new TestCollator(), new ULocale("de-Japn-419"));
    Collator.unregister(token);
    // Freezable default implementations. freeze() may or may not be implemented.
    assertFalse("not yet frozen", col2.isFrozen());
    try {
        col2.freeze();
        assertTrue("now frozen", col2.isFrozen());
    } catch (UnsupportedOperationException expected) {
    }
    try {
        col2.setStrength(Collator.PRIMARY);
        if (col2.isFrozen()) {
            fail("(frozen Collator).setStrength() should throw an exception");
        }
    } catch (UnsupportedOperationException expected) {
    }
    try {
        Collator col3 = col2.cloneAsThawed();
        assertFalse("!cloneAsThawed().isFrozen()", col3.isFrozen());
    } catch (UnsupportedOperationException expected) {
    }
}

Example 12 with UnicodeSet

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

the class CollationAPITest method TestGetContractions.

// capitst.c/TestGetContractionsAndUnsafes()
@Test
public void TestGetContractions() throws Exception {
    /*        static struct {
         const char* locale;
         const char* inConts;
         const char* outConts;
         const char* inExp;
         const char* outExp;
         const char* unsafeCodeUnits;
         const char* safeCodeUnits;
         }
         */
    String[][] tests = { { "ru", "[{\u0418\u0306}{\u0438\u0306}]", "[\u0439\u0457]", "[\u00e6]", "[ae]", "[\u0418\u0438]", "[aAbBxv]" }, { "uk", "[{\u0406\u0308}{\u0456\u0308}{\u0418\u0306}{\u0438\u0306}]", "[\u0407\u0419\u0439\u0457]", "[\u00e6]", "[ae]", "[\u0406\u0456\u0418\u0438]", "[aAbBxv]" }, { "sh", "[{C\u0301}{C\u030C}{C\u0341}{DZ\u030C}{Dz\u030C}{D\u017D}{D\u017E}{lj}{nj}]", "[{\u309d\u3099}{\u30fd\u3099}]", "[\u00e6]", "[a]", "[nlcdzNLCDZ]", "[jabv]" }, { "ja", /*
                     * The "collv2" builder omits mappings if the collator maps their
                     * character sequences to the same CEs.
                     * For example, it omits Japanese contractions for NFD forms
                     * of the voiced iteration mark (U+309E = U+309D + U+3099), such as
                     * {\u3053\u3099\u309D\u3099}{\u3053\u309D\u3099}
                     * {\u30B3\u3099\u30FD\u3099}{\u30B3\u30FD\u3099}.
                     * It does add mappings for the precomposed forms.
                     */
    "[{\u3053\u3099\u309D}{\u3053\u3099\u309E}{\u3053\u3099\u30FC}" + "{\u3053\u309D}{\u3053\u309E}{\u3053\u30FC}" + "{\u30B3\u3099\u30FC}{\u30B3\u3099\u30FD}{\u30B3\u3099\u30FE}" + "{\u30B3\u30FC}{\u30B3\u30FD}{\u30B3\u30FE}]", "[{\u30FD\u3099}{\u309D\u3099}{\u3053\u3099}{\u30B3\u3099}{lj}{nj}]", "[\u30FE\u00e6]", "[a]", "[\u3099]", "[]" } };
    RuleBasedCollator coll = null;
    int i = 0;
    UnicodeSet conts = new UnicodeSet();
    UnicodeSet exp = new UnicodeSet();
    UnicodeSet set = new UnicodeSet();
    for (i = 0; i < tests.length; i++) {
        logln("Testing locale: " + tests[i][0]);
        coll = (RuleBasedCollator) Collator.getInstance(new ULocale(tests[i][0]));
        coll.getContractionsAndExpansions(conts, exp, true);
        boolean ok = true;
        logln("Contractions " + conts.size() + ":\n" + conts.toPattern(true));
        ok &= doSetsTest(conts, set, tests[i][1], tests[i][2]);
        logln("Expansions " + exp.size() + ":\n" + exp.toPattern(true));
        ok &= doSetsTest(exp, set, tests[i][3], tests[i][4]);
        if (!ok) {
            // In case of failure, log the rule string for better diagnostics.
            String rules = coll.getRules(false);
            logln("Collation rules (getLocale()=" + coll.getLocale(ULocale.ACTUAL_LOCALE).toString() + "): " + Utility.escape(rules));
        }
    // No unsafe set in ICU4J
    // noConts = ucol_getUnsafeSet(coll, conts, &status);
    // doSetsTest(conts, set, tests[i][5], tests[i][6]);
    // log_verbose("Unsafes "+conts.size()+":\n"+conts.toPattern(true)+"\n");
    }
}

Example 13 with UnicodeSet

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

the class CollationAPITest method TestGetTailoredSet.

@Test
public void TestGetTailoredSet() {
    logln("testing getTailoredSet...");
    String[] rules = { "&a < \u212b", "& S < \u0161 <<< \u0160" };
    String[][] data = { { "\u212b", "A\u030a", "\u00c5" }, { "\u0161", "s\u030C", "\u0160", "S\u030C" } };
    int i = 0, j = 0;
    RuleBasedCollator coll;
    UnicodeSet set;
    for (i = 0; i < rules.length; i++) {
        try {
            logln("Instantiating a collator from " + rules[i]);
            coll = new RuleBasedCollator(rules[i]);
            set = coll.getTailoredSet();
            logln("Got set: " + set.toPattern(true));
            if (set.size() < data[i].length) {
                errln("Tailored set size smaller (" + set.size() + ") than expected (" + data[i].length + ")");
            }
            for (j = 0; j < data[i].length; j++) {
                logln("Checking to see whether " + data[i][j] + " is in set");
                if (!set.contains(data[i][j])) {
                    errln("Tailored set doesn't contain " + data[i][j] + "... It should");
                }
            }
        } catch (Exception e) {
            warnln("Couldn't open collator with rules " + rules[i]);
        }
    }
}

Example 14 with UnicodeSet

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

the class UnicodeMapTest method TestUnicodeMapGeneralCategory.

public void TestUnicodeMapGeneralCategory() {
    logln("Setting General Category");
    UnicodeMap<String> map1 = new UnicodeMap();
    Map<Integer, String> map2 = new HashMap<Integer, String>();
    // Map<Integer, String> map3 = new TreeMap<Integer, String>();
    map1 = new UnicodeMap<String>();
    map2 = new TreeMap<Integer, String>();
    for (int cp = 0; cp <= SET_LIMIT; ++cp) {
        int enumValue = UCharacter.getIntPropertyValue(cp, propEnum);
        // if (enumValue <= 0) continue; // for smaller set
        String value = UCharacter.getPropertyValueName(propEnum, enumValue, UProperty.NameChoice.LONG);
        map1.put(cp, value);
        map2.put(cp, value);
    }
    checkNext(map1, map2, Integer.MAX_VALUE);
    logln("Comparing General Category");
    check(map1, map2, -1);
    logln("Comparing Values");
    Set<String> values1 = map1.getAvailableValues(new TreeSet<String>());
    Set<String> values2 = new TreeSet<String>(map2.values());
    if (!TestBoilerplate.verifySetsIdentical(this, values1, values2)) {
        throw new IllegalArgumentException("Halting");
    }
    logln("Comparing Sets");
    for (Iterator<String> it = values1.iterator(); it.hasNext(); ) {
        String value = it.next();
        logln(value == null ? "null" : value);
        UnicodeSet set1 = map1.keySet(value);
        UnicodeSet set2 = TestBoilerplate.getSet(map2, value);
        if (!TestBoilerplate.verifySetsIdentical(this, set1, set2)) {
            throw new IllegalArgumentException("Halting");
        }
    }
}

Example 15 with UnicodeSet

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

the class WriteCharts method printSet.

public static void printSet(String source) {
    UnicodeSet s = new UnicodeSet(source);
    System.out.println("Printout for '" + source + "'");
    int count = s.getRangeCount();
    for (int i = 0; i < count; ++i) {
        int start = s.getRangeStart(i);
        int end = s.getRangeEnd(i);
        System.out.println(Integer.toString(start, 16) + ".." + Integer.toString(end, 16));
    }
}