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

Example 71 with Transliterator

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

the class TransliteratorTest method TestDevanagariLatinRT.

// ======================================================================
// Ram's tests
// ======================================================================
/* this test performs  test of rules in ISO 15915 */
@Test
public void TestDevanagariLatinRT() {
    String[] source = { "bh\u0101rata", "kra", "k\u1E63a", "khra", "gra", "\u1E45ra", "cra", "chra", "j\u00F1a", "jhra", "\u00F1ra", "\u1E6Dya", "\u1E6Dhra", "\u1E0Dya", // "r\u0323ya", // \u095c is not valid in Devanagari
    "\u1E0Dhya", "\u1E5Bhra", "\u1E47ra", "tta", "thra", "dda", "dhra", "nna", "pra", "phra", "bra", "bhra", "mra", "\u1E49ra", // "l\u0331ra",
    "yra", "\u1E8Fra", // "l-",
    "vra", "\u015Bra", "\u1E63ra", "sra", "hma", "\u1E6D\u1E6Da", "\u1E6D\u1E6Dha", "\u1E6Dh\u1E6Dha", "\u1E0D\u1E0Da", "\u1E0D\u1E0Dha", "\u1E6Dya", "\u1E6Dhya", "\u1E0Dya", "\u1E0Dhya", // CharsToUnicodeString("hma"),
    "hya", "\u015Br\u0325", "\u015Bca", "\u0115", "san\u0304j\u012Bb s\u0113nagupta", "\u0101nand vaddir\u0101ju" };
    String[] expected = { "\u092D\u093E\u0930\u0924", /* bha\u0304rata */
    "\u0915\u094D\u0930", /* kra         */
    "\u0915\u094D\u0937", /* ks\u0323a  */
    "\u0916\u094D\u0930", /* khra        */
    "\u0917\u094D\u0930", /* gra         */
    "\u0919\u094D\u0930", /* n\u0307ra  */
    "\u091A\u094D\u0930", /* cra         */
    "\u091B\u094D\u0930", /* chra        */
    "\u091C\u094D\u091E", /* jn\u0303a  */
    "\u091D\u094D\u0930", /* jhra        */
    "\u091E\u094D\u0930", /* n\u0303ra  */
    "\u091F\u094D\u092F", /* t\u0323ya  */
    "\u0920\u094D\u0930", /* t\u0323hra */
    "\u0921\u094D\u092F", // "\u095C\u094D\u092F",          /* r\u0323ya  */ // \u095c is not valid in Devanagari
    "\u0922\u094D\u092F", /* d\u0323hya */
    "\u0922\u093C\u094D\u0930", /* r\u0323hra */
    "\u0923\u094D\u0930", /* n\u0323ra  */
    "\u0924\u094D\u0924", /* tta         */
    "\u0925\u094D\u0930", /* thra        */
    "\u0926\u094D\u0926", /* dda         */
    "\u0927\u094D\u0930", /* dhra        */
    "\u0928\u094D\u0928", /* nna         */
    "\u092A\u094D\u0930", /* pra         */
    "\u092B\u094D\u0930", /* phra        */
    "\u092C\u094D\u0930", /* bra         */
    "\u092D\u094D\u0930", /* bhra        */
    "\u092E\u094D\u0930", /* mra         */
    "\u0929\u094D\u0930", // "\u0934\u094D\u0930",          /* l\u0331ra  */
    "\u092F\u094D\u0930", /* yra         */
    "\u092F\u093C\u094D\u0930", // "l-",
    "\u0935\u094D\u0930", /* vra         */
    "\u0936\u094D\u0930", /* s\u0301ra  */
    "\u0937\u094D\u0930", /* s\u0323ra  */
    "\u0938\u094D\u0930", /* sra         */
    "\u0939\u094d\u092E", /* hma         */
    "\u091F\u094D\u091F", /* t\u0323t\u0323a  */
    "\u091F\u094D\u0920", /* t\u0323t\u0323ha */
    "\u0920\u094D\u0920", /* t\u0323ht\u0323ha*/
    "\u0921\u094D\u0921", /* d\u0323d\u0323a  */
    "\u0921\u094D\u0922", /* d\u0323d\u0323ha */
    "\u091F\u094D\u092F", /* t\u0323ya  */
    "\u0920\u094D\u092F", /* t\u0323hya */
    "\u0921\u094D\u092F", /* d\u0323ya  */
    "\u0922\u094D\u092F", // "hma",                         /* hma         */
    "\u0939\u094D\u092F", /* hya         */
    "\u0936\u0943", /* s\u0301r\u0325a  */
    "\u0936\u094D\u091A", /* s\u0301ca  */
    "\u090d", /* e\u0306    */
    "\u0938\u0902\u091C\u0940\u092C\u094D \u0938\u0947\u0928\u0917\u0941\u092A\u094D\u0924", "\u0906\u0928\u0902\u0926\u094D \u0935\u0926\u094D\u0926\u093F\u0930\u093E\u091C\u0941" };
    Transliterator latinToDev = Transliterator.getInstance("Latin-Devanagari", Transliterator.FORWARD);
    Transliterator devToLatin = Transliterator.getInstance("Devanagari-Latin", Transliterator.FORWARD);
    for (int i = 0; i < source.length; i++) {
        expect(latinToDev, (source[i]), (expected[i]));
        expect(devToLatin, (expected[i]), (source[i]));
    }
}

Example 72 with Transliterator

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

the class TransliteratorTest method TestCompoundInverseID.

/**
 * Test IDs of inverses of compound transliterators. (J20)
 */
@Test
public void TestCompoundInverseID() {
    String ID = "Latin-Jamo;NFC(NFD)";
    Transliterator t = Transliterator.getInstance(ID);
    Transliterator u = t.getInverse();
    String exp = "NFD(NFC);Jamo-Latin";
    String got = u.getID();
    if (!got.equals(exp)) {
        errln("FAIL: Inverse of " + ID + " is " + got + ", expected " + exp);
    }
}

Example 73 with Transliterator

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

the class TransliteratorTest method TestQuantifiedSegment.

/**
 * Test quantified segment behavior.  We want:
 * ([abc])+ > x $1 x; applied to "cba" produces "xax"
 */
@Test
public void TestQuantifiedSegment() {
    // The normal case
    expect("([abc]+) > x $1 x;", "cba", "xcbax");
    // The tricky case; the quantifier is around the segment
    expect("([abc])+ > x $1 x;", "cba", "xax");
    // Tricky case in reverse direction
    expect("([abc])+ { q > x $1 x;", "cbaq", "cbaxax");
    // Check post-context segment
    expect("{q} ([a-d])+ > '(' $1 ')';", "ddqcba", "dd(a)cba");
    // Test toRule/toPattern for non-quantified segment.
    // Careful with spacing here.
    String r = "([a-c]){q} > x $1 x;";
    Transliterator t = Transliterator.createFromRules("ID", r, Transliterator.FORWARD);
    String rr = t.toRules(true);
    if (!r.equals(rr)) {
        errln("FAIL: \"" + r + "\" x toRules() => \"" + rr + "\"");
    } else {
        logln("Ok: \"" + r + "\" x toRules() => \"" + rr + "\"");
    }
    // Test toRule/toPattern for quantified segment.
    // Careful with spacing here.
    r = "([a-c])+{q} > x $1 x;";
    t = Transliterator.createFromRules("ID", r, Transliterator.FORWARD);
    rr = t.toRules(true);
    if (!r.equals(rr)) {
        errln("FAIL: \"" + r + "\" x toRules() => \"" + rr + "\"");
    } else {
        logln("Ok: \"" + r + "\" x toRules() => \"" + rr + "\"");
    }
}

Example 74 with Transliterator

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

the class TransliteratorTest method TestNewEngine.

/**
 * Test various failure points of the new 2.0 engine.
 */
@Test
public void TestNewEngine() {
    Transliterator t = Transliterator.getInstance("Latin-Hiragana");
    // Katakana should be untouched
    expect(t, "a\u3042\u30A2", "\u3042\u3042\u30A2");
    if (true) {
        // This test will only work if Transliterator.ROLLBACK is
        // true.  Otherwise, this test will fail, revealing a
        // limitation of global filters in incremental mode.
        Transliterator a = Transliterator.createFromRules("a_to_A", "a > A;", Transliterator.FORWARD);
        Transliterator A = Transliterator.createFromRules("A_to_b", "A > b;", Transliterator.FORWARD);
        try {
            Transliterator.registerInstance(a);
            Transliterator.registerInstance(A);
            t = Transliterator.getInstance("[:Ll:];a_to_A;NFD;A_to_b");
            expect(t, "aAaA", "bAbA");
            Transliterator[] u = t.getElements();
            assertTrue("getElements().length", u.length == 3);
            assertEquals("getElements()[0]", u[0].getID(), "a_to_A");
            assertEquals("getElements()[1]", u[1].getID(), "NFD");
            assertEquals("getElements()[2]", u[2].getID(), "A_to_b");
            t = Transliterator.getInstance("a_to_A;NFD;A_to_b");
            t.setFilter(new UnicodeSet("[:Ll:]"));
            expect(t, "aAaA", "bAbA");
        } finally {
            Transliterator.unregister("a_to_A");
            Transliterator.unregister("A_to_b");
        }
    }
    expect("$smooth = x; $macron = q; [:^L:] { ([aeiouyAEIOUY] $macron?) } [^aeiouyAEIOUY$smooth$macron] > | $1 $smooth ;", "a", "ax");
    String gr = "$ddot = \u0308 ;" + "$lcgvowel = [\u03b1\u03b5\u03b7\u03b9\u03bf\u03c5\u03c9] ;" + "$rough = \u0314 ;" + "($lcgvowel+ $ddot?) $rough > h | $1 ;" + "\u03b1 <> a ;" + "$rough <> h ;";
    expect(gr, "\u03B1\u0314", "ha");
}

Example 75 with Transliterator

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

the class TransliteratorTest method TestChinese.

@Test
public void TestChinese() {
    Transliterator hanLatin = Transliterator.getInstance("Han-Latin");
    assertTransform("Transform", "z\u00E0o Unicode", hanLatin, "\u9020Unicode");
    assertTransform("Transform", "z\u00E0i chu\u00E0ng z\u00E0o Unicode zh\u012B qi\u00E1n", hanLatin, "\u5728\u5275\u9020Unicode\u4E4B\u524D");
}