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

Example 76 with UnicodeSet

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

the class AnyScriptTest method TestCommonDigits.

@Test
public void TestCommonDigits() {
    UnicodeSet westernDigitSet = new UnicodeSet("[0-9]");
    UnicodeSet westernDigitSetAndMarks = new UnicodeSet("[[0-9][:Mn:]]");
    UnicodeSet arabicDigitSet = new UnicodeSet("[[:Nd:]&[:block=Arabic:]]");
    Transliterator latin = Transliterator.getInstance("Any-Latn");
    Transliterator arabic = Transliterator.getInstance("Any-Arabic");
    String westernDigits = getList(westernDigitSet);
    String arabicDigits = getList(arabicDigitSet);
    String fromArabic = latin.transform(arabicDigits);
    assertContainsAll("Any-Latin transforms Arabic digits", westernDigitSetAndMarks, fromArabic);
    if (false) {
        // we don't require conversion to Arabic digits
        String fromLatin = arabic.transform(westernDigits);
        assertContainsAll("Any-Arabic transforms Western digits", arabicDigitSet, fromLatin);
    }
}

Example 77 with UnicodeSet

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

the class AnyScriptTest method TestScripts.

@Test
public void TestScripts() {
    // get a couple of characters of each script for testing
    StringBuffer testBuffer = new StringBuffer();
    for (int script = 0; script < UScript.CODE_LIMIT; ++script) {
        UnicodeSet test = new UnicodeSet().applyPropertyAlias("script", UScript.getName(script));
        int count = Math.min(20, test.size());
        for (int i = 0; i < count; ++i) {
            testBuffer.append(UTF16.valueOf(test.charAt(i)));
        }
    }
    String test = testBuffer.toString();
    logln("Test line: " + test);
    int inclusion = TestFmwk.getExhaustiveness();
    boolean testedUnavailableScript = false;
    for (int script = 0; script < UScript.CODE_LIMIT; ++script) {
        if (script == UScript.COMMON || script == UScript.INHERITED) {
            continue;
        }
        // Make sure, however, that we test at least one unavailable script
        if (inclusion < 10 && script != UScript.LATIN && script != UScript.HAN && script != UScript.HIRAGANA && testedUnavailableScript) {
            continue;
        }
        // long name
        String scriptName = UScript.getName(script);
        ULocale locale = new ULocale(scriptName);
        if (locale.getLanguage().equals("new") || locale.getLanguage().equals("pau")) {
            if (logKnownIssue("11171", "long script name loosely looks like a locale ID with a known likely script")) {
                continue;
            }
        }
        Transliterator t;
        try {
            t = Transliterator.getInstance("any-" + scriptName);
        } catch (Exception e) {
            testedUnavailableScript = true;
            logln("Skipping unavailable: " + scriptName);
            // we don't handle all scripts
            continue;
        }
        logln("Checking: " + scriptName);
        if (t != null) {
            // just verify we don't crash
            t.transform(test);
        }
        // 4-letter script code
        String shortScriptName = UScript.getShortName(script);
        try {
            t = Transliterator.getInstance("any-" + shortScriptName);
        } catch (Exception e) {
            errln("Transliterator.getInstance() worked for \"any-" + scriptName + "\" but not for \"any-" + shortScriptName + '\"');
        }
        // just verify we don't crash
        t.transform(test);
    }
}

Example 78 with UnicodeSet

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

the class ErrorTest method TestRBTErrors.

// public void TestUniToHexErrors() {
// Transliterator t = null;
// try {
// t = new UnicodeToHexTransliterator("", true, null);
// if (t != null) {
// errln("FAIL: Created a UnicodeToHexTransliterator with an empty pattern.");
// }
// } catch (IllegalArgumentException e) {
// }
// try {
// t = new UnicodeToHexTransliterator("\\x", true, null);
// if (t != null) {
// errln("FAIL: Created a UnicodeToHexTransliterator with a bad pattern.");
// }
// } catch (IllegalArgumentException e) {
// }
// t = new UnicodeToHexTransliterator();
// try {
// ((UnicodeToHexTransliterator) t).applyPattern("\\x");
// errln("FAIL: UnicodeToHexTransliterator::applyPattern succeeded with a bad pattern.");
// } catch (Exception e) {
// }
// }
@Test
public void TestRBTErrors() {
    String rules = "ab>y";
    String id = "MyRandom-YReverse";
    String goodPattern = "[[:L:]&[\\u0000-\\uFFFF]]";
    /* all BMP letters */
    UnicodeSet set = null;
    try {
        set = new UnicodeSet(goodPattern);
        try {
            Transliterator t = Transliterator.createFromRules(id, rules, Transliterator.REVERSE);
            t.setFilter(set);
            Transliterator.registerClass(id, t.getClass(), null);
            Transliterator.unregister(id);
            try {
                Transliterator.getInstance(id, Transliterator.REVERSE);
                errln("FAIL: construction of unregistered ID should have failed.");
            } catch (IllegalArgumentException e) {
            }
        } catch (IllegalArgumentException e) {
            errln("FAIL: Was not able to create a good RBT to test registration.");
        }
    } catch (IllegalArgumentException e) {
        errln("FAIL: Was not able to create a good UnicodeSet based on valid patterns.");
        return;
    }
}

Example 79 with UnicodeSet

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

the class SpoofCheckerTest method TestGetSetAllowedChars.

/*
     * get & setAllowedChars
     */
@Test
public void TestGetSetAllowedChars() {
    SpoofChecker sc = new SpoofChecker.Builder().setChecks(SpoofChecker.CHAR_LIMIT).build();
    UnicodeSet us;
    UnicodeSet uset;
    uset = sc.getAllowedChars();
    assertTrue("", uset.isFrozen());
    us = new UnicodeSet(0x41, 0x5A);
    /* [A-Z] */
    sc = new SpoofChecker.Builder().setChecks(SpoofChecker.CHAR_LIMIT).setAllowedChars(us).build();
    assertEquals("", us, sc.getAllowedChars());
}

Example 80 with UnicodeSet

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

the class SpoofCheckerTest method TestMixedNumbers.

@Test
public void TestMixedNumbers() {
    Object[][] tests = { { "1", "[0]" }, { "१", "[०]" }, { "1१", "[0०]" }, { "١۱", "[٠۰]" }, { "a♥", "[]" }, { "a\u303c", "[]" }, { "aー\u303c", "[]" }, { "aー\u303cア", "[]" }, { "アaー\u303c", "[]" }, { "a1١", "[0٠]" }, { "a1١۱", "[0٠۰]" }, { "١ー\u303caア1१۱", "[0٠۰०]" }, { "aアー\u303c1१١۱", "[0٠۰०]" } };
    CheckResult checkResult = new CheckResult();
    for (Object[] test : tests) {
        String testString = (String) test[0];
        UnicodeSet expected = new UnicodeSet((String) test[1]);
        SpoofChecker sc = new SpoofChecker.Builder().setChecks(// only check this
        SpoofChecker.MIXED_NUMBERS).build();
        boolean actualValue = sc.failsChecks(testString, checkResult);
        assertEquals("", expected, checkResult.numerics);
        assertEquals("Testing spoof mixed numbers for '" + testString + "', ", expected.size() > 1, actualValue);
    }
}