Examples with UnicodeMap android.icu.dev.util.UnicodeMap used on opensource projects

Example 1 with UnicodeMap

use of android.icu.dev.util.UnicodeMap 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 2 with UnicodeMap

use of android.icu.dev.util.UnicodeMap in project j2objc by google.

the class UnicodeMapTest method checkNext.

private void checkNext(UnicodeMap<String> map1, Map<Integer, String> map2, int limit) {
    logln("Comparing nextRange");
    Map localMap = new TreeMap();
    UnicodeMapIterator<String> mi = new UnicodeMapIterator<String>(map1);
    while (mi.nextRange()) {
        logln(Utility.hex(mi.codepoint) + ".." + Utility.hex(mi.codepointEnd) + " => " + mi.value);
        for (int i = mi.codepoint; i <= mi.codepointEnd; ++i) {
            // if (i >= limit) continue;
            localMap.put(i, mi.value);
        }
    }
    checkMap(map2, localMap);
    logln("Comparing next");
    mi.reset();
    localMap = new TreeMap();
    // String lastValue = null;
    while (mi.next()) {
        // if (!UnicodeMap.areEqual(lastValue, mi.value)) {
        // // System.out.println("Change: " + Utility.hex(mi.codepoint) + " => " + mi.value);
        // lastValue = mi.value;
        // }
        // if (mi.codepoint >= limit) continue;
        localMap.put(mi.codepoint, mi.value);
    }
    checkMap(map2, localMap);
}

Example 3 with UnicodeMap

use of android.icu.dev.util.UnicodeMap in project j2objc by google.

the class UnicodeMapTest method TestModify.

@Test
public void TestModify() {
    Random random = new Random(0);
    UnicodeMap unicodeMap = new UnicodeMap();
    HashMap hashMap = new HashMap();
    String[] values = { null, "the", "quick", "brown", "fox" };
    for (int count = 1; count <= MODIFY_TEST_ITERATIONS; ++count) {
        String value = values[random.nextInt(values.length)];
        // test limited range
        int start = random.nextInt(MODIFY_TEST_LIMIT);
        int end = random.nextInt(MODIFY_TEST_LIMIT);
        if (start > end) {
            int temp = start;
            start = end;
            end = temp;
        }
        int modCount = count & 0xFF;
        if (modCount == 0 && isVerbose()) {
            logln("***" + count);
            logln(unicodeMap.toString());
        }
        unicodeMap.putAll(start, end, value);
        if (modCount == 1 && isVerbose()) {
            logln(">>>\t" + Utility.hex(start) + ".." + Utility.hex(end) + "\t" + value);
            logln(unicodeMap.toString());
        }
        for (int i = start; i <= end; ++i) {
            hashMap.put(new Integer(i), value);
        }
        if (!hasSameValues(unicodeMap, hashMap)) {
            errln("Failed at " + count);
        }
    }
}

Example 4 with UnicodeMap

use of android.icu.dev.util.UnicodeMap in project j2objc by google.

the class TransliteratorTest method TestSourceTargetSet2.

@Test
public void TestSourceTargetSet2() {
    Normalizer2 nfc = Normalizer2.getNFCInstance();
    Normalizer2 nfd = Normalizer2.getNFDInstance();
    // Normalizer2 nfkd = Normalizer2.getInstance(null, "nfkd", Mode.DECOMPOSE);
    // UnicodeSet nfkdSource = new UnicodeSet();
    // UnicodeSet nfkdTarget = new UnicodeSet();
    // for (int i = 0; i <= 0x10FFFF; ++i) {
    // if (nfkd.isInert(i)) {
    // continue;
    // }
    // nfkdSource.add(i);
    // String t = nfkd.getDecomposition(i);
    // if (t != null) {
    // nfkdTarget.addAll(t);
    // } else {
    // nfkdTarget.add(i);
    // }
    // }
    // nfkdSource.freeze();
    // nfkdTarget.freeze();
    // logln("NFKD Source: " + nfkdSource.toPattern(false));
    // logln("NFKD Target: " + nfkdTarget.toPattern(false));
    UnicodeMap<UnicodeSet> leadToTrail = new UnicodeMap();
    UnicodeMap<UnicodeSet> leadToSources = new UnicodeMap();
    UnicodeSet nonStarters = new UnicodeSet("[:^ccc=0:]").freeze();
    CanonicalIterator can = new CanonicalIterator("");
    UnicodeSet disorderedMarks = new UnicodeSet();
    for (int i = 0; i <= 0x10FFFF; ++i) {
        String s = nfd.getDecomposition(i);
        if (s == null) {
            continue;
        }
        can.setSource(s);
        for (String t = can.next(); t != null; t = can.next()) {
            disorderedMarks.add(t);
        }
        // if s has two code points, (or more), add the lead/trail information
        int first = s.codePointAt(0);
        int firstCount = Character.charCount(first);
        if (s.length() == firstCount)
            continue;
        String trailString = s.substring(firstCount);
        // add all the trail characters
        if (!nonStarters.containsSome(trailString)) {
            continue;
        }
        UnicodeSet trailSet = leadToTrail.get(first);
        if (trailSet == null) {
            leadToTrail.put(first, trailSet = new UnicodeSet());
        }
        // add remaining trails
        trailSet.addAll(trailString);
        // add the sources
        UnicodeSet sourcesSet = leadToSources.get(first);
        if (sourcesSet == null) {
            leadToSources.put(first, sourcesSet = new UnicodeSet());
        }
        sourcesSet.add(i);
    }
    for (Entry<String, UnicodeSet> x : leadToSources.entrySet()) {
        String lead = x.getKey();
        UnicodeSet sources = x.getValue();
        UnicodeSet trailSet = leadToTrail.get(lead);
        for (String source : sources) {
            for (String trail : trailSet) {
                can.setSource(source + trail);
                for (String t = can.next(); t != null; t = can.next()) {
                    if (t.endsWith(trail))
                        continue;
                    disorderedMarks.add(t);
                }
            }
        }
    }
    for (String s : nonStarters) {
        disorderedMarks.add("\u0345" + s);
        disorderedMarks.add(s + "\u0323");
        String xx = nfc.normalize("\u01EC" + s);
        if (!xx.startsWith("\u01EC")) {
            logln("??");
        }
    }
    // for (int i = 0; i <= 0x10FFFF; ++i) {
    // String s = nfkd.getDecomposition(i);
    // if (s != null) {
    // disorderedMarks.add(s);
    // disorderedMarks.add(nfc.normalize(s));
    // addDerivedStrings(nfc, disorderedMarks, s);
    // }
    // s = nfd.getDecomposition(i);
    // if (s != null) {
    // disorderedMarks.add(s);
    // }
    // if (!nfc.isInert(i)) {
    // if (i == 0x00C0) {
    // logln("\u00C0");
    // }
    // can.setSource(s+"\u0334");
    // for (String t = can.next(); t != null; t = can.next()) {
    // addDerivedStrings(nfc, disorderedMarks, t);
    // }
    // can.setSource(s+"\u0345");
    // for (String t = can.next(); t != null; t = can.next()) {
    // addDerivedStrings(nfc, disorderedMarks, t);
    // }
    // can.setSource(s+"\u0323");
    // for (String t = can.next(); t != null; t = can.next()) {
    // addDerivedStrings(nfc, disorderedMarks, t);
    // }
    // }
    // }
    logln("Test cases: " + disorderedMarks.size());
    disorderedMarks.addAll(0, 0x10FFFF).freeze();
    logln("isInert \u0104 " + nfc.isInert('\u0104'));
    Object[][] rules = { { ":: [:sc=COMMON:] any-name;", null }, { ":: [:Greek:] hex-any/C;", null }, { ":: [:Greek:] any-hex/C;", null }, { ":: [[:Mn:][:Me:]] remove;", null }, { ":: [[:Mn:][:Me:]] null;", null }, { ":: lower;", null }, { ":: upper;", null }, { ":: title;", null }, { ":: CaseFold;", null }, { ":: NFD;", null }, { ":: NFC;", null }, { ":: NFKD;", null }, { ":: NFKC;", null }, { ":: [[:Mn:][:Me:]] NFKD;", null }, { ":: Latin-Greek;", null }, { ":: [:Latin:] NFKD;", null }, { ":: NFKD;", null }, { ":: NFKD;\n" + ":: [[:Mn:][:Me:]] remove;\n" + ":: NFC;", null } };
    for (Object[] rulex : rules) {
        String rule = (String) rulex[0];
        Transliterator trans = Transliterator.createFromRules("temp", rule, Transliterator.FORWARD);
        UnicodeSet actualSource = trans.getSourceSet();
        UnicodeSet actualTarget = trans.getTargetSet();
        UnicodeSet empiricalSource = new UnicodeSet();
        UnicodeSet empiricalTarget = new UnicodeSet();
        String ruleDisplay = rule.replace("\n", "\t\t");
        UnicodeSet toTest = disorderedMarks;
        // if (rulex[1] != null) {
        // toTest = new UnicodeSet(disorderedMarks);
        // toTest.addAll((UnicodeSet) rulex[1]);
        // }
        String test = nfd.normalize("\u0104");
        boolean DEBUG = true;
        @SuppressWarnings("unused") int // for debugging
        count = 0;
        for (String s : toTest) {
            if (s.equals(test)) {
                logln(test);
            }
            String t = trans.transform(s);
            if (!s.equals(t)) {
                if (!isAtomic(s, t, trans)) {
                    isAtomic(s, t, trans);
                    continue;
                }
                // }
                if (DEBUG) {
                    if (!actualSource.containsAll(s)) {
                        count++;
                    }
                    if (!actualTarget.containsAll(t)) {
                        count++;
                    }
                }
                addSourceTarget(s, empiricalSource, t, empiricalTarget);
            }
        }
        assertEquals("getSource(" + ruleDisplay + ")", empiricalSource, actualSource, SetAssert.MISSING_OK);
        assertEquals("getTarget(" + ruleDisplay + ")", empiricalTarget, actualTarget, SetAssert.MISSING_OK);
    }
}

Example 5 with UnicodeMap

use of android.icu.dev.util.UnicodeMap in project j2objc by google.

the class UnicodeMapBoilerplateTest method _addTestObject.

/* (non-Javadoc)
     * @see android.icu.dev.test.TestBoilerplate#_addTestObject(java.util.List)
     */
protected boolean _addTestObject(List<UnicodeMap> list) {
    if (list.size() > 30)
        return false;
    UnicodeMap result = new UnicodeMap();
    for (int i = 0; i < 50; ++i) {
        int start = random.nextInt(25);
        String value = TEST_VALUES[random.nextInt(TEST_VALUES.length)];
        result.put(start, value);
    }
    list.add(result);
    return true;
}