public void TestAllCodepoints()
{
int code;
//String oldId="";
//String oldAbbrId="";
for (int i = 0; i <= 0x10ffff; i++)
{
code = UScript.InvalidCode;
code = UScript.GetScript(i);
if (code == UScript.InvalidCode)
{
Errln("UScript.getScript for codepoint 0x" + Hex(i) + " failed");
}
String id = UScript.GetName(code);
if (id.IndexOf("INVALID", StringComparison.Ordinal) >= 0)
{
Errln("UScript.getScript for codepoint 0x" + Hex(i) + " failed");
}
String abbr = UScript.GetShortName(code);
if (abbr.IndexOf("INV", StringComparison.Ordinal) >= 0)
{
Errln("UScript.getScript for codepoint 0x" + Hex(i) + " failed");
}
}
}
public void TestGetShortName(int testCode, string expected)
{
string shortName = UScript.GetShortName(testCode);
if (!expected.Equals(shortName))
{
Errln("Error testing UScript.getShortName(). Got: " + shortName + " Expected: " + expected);
}
}
public void TestScriptMetadata()
{
UnicodeSet rtl = new UnicodeSet("[[:bc=R:][:bc=AL:]-[:Cn:]-[:sc=Common:]]");
// So far, sample characters are uppercase.
// Georgian is special.
UnicodeSet cased = new UnicodeSet("[[:Lu:]-[:sc=Common:]-[:sc=Geor:]]");
for (int sc = 0; sc < UScript.CodeLimit; ++sc)
{
String sn = UScript.GetShortName(sc);
ScriptUsage usage = UScript.GetUsage(sc);
String sample = UScript.GetSampleString(sc);
UnicodeSet scriptSet = new UnicodeSet();
scriptSet.ApplyInt32PropertyValue(UProperty.Script, sc);
if (usage == ScriptUsage.NotEncoded)
{
assertTrue(sn + " not encoded, no sample", sample.Length == 0); // Java 6: sample.isEmpty()
assertFalse(sn + " not encoded, not RTL", UScript.IsRightToLeft(sc));
assertFalse(sn + " not encoded, not LB letters", UScript.BreaksBetweenLetters(sc));
assertFalse(sn + " not encoded, not cased", UScript.IsCased(sc));
assertTrue(sn + " not encoded, no characters", scriptSet.IsEmpty);
}
else
{
assertFalse(sn + " encoded, has a sample character", sample.Length == 0); // Java 6: sample.isEmpty()
int firstChar = sample.CodePointAt(0);
int charScript = GetCharScript(sc);
assertEquals(sn + " script(sample(script))",
charScript, UScript.GetScript(firstChar));
assertEquals(sn + " RTL vs. set", rtl.Contains(firstChar), UScript.IsRightToLeft(sc));
assertEquals(sn + " cased vs. set", cased.Contains(firstChar), UScript.IsCased(sc));
assertEquals(sn + " encoded, has characters", sc == charScript, !scriptSet.IsEmpty);
if (UScript.IsRightToLeft(sc))
{
rtl.RemoveAll(scriptSet);
}
if (UScript.IsCased(sc))
{
cased.RemoveAll(scriptSet);
}
}
}
assertEquals("no remaining RTL characters", "[]", rtl.ToPattern(true));
assertEquals("no remaining cased characters", "[]", cased.ToPattern(true));
assertTrue("Hani breaks between letters", UScript.BreaksBetweenLetters(UScript.Han));
assertTrue("Thai breaks between letters", UScript.BreaksBetweenLetters(UScript.Thai));
assertFalse("Latn does not break between letters", UScript.BreaksBetweenLetters(UScript.Latin));
}
public void TestTokenAttributes()
{
using TokenStream ts = a.GetTokenStream("dummy", "This is a test");
IScriptAttribute scriptAtt = ts.AddAttribute <IScriptAttribute>();
ts.Reset();
while (ts.IncrementToken())
{
assertEquals(UScript.Latin, scriptAtt.Code);
assertEquals(UScript.GetName(UScript.Latin), scriptAtt.GetName());
assertEquals(UScript.GetShortName(UScript.Latin), scriptAtt.GetShortName());
assertTrue(ts.ReflectAsString(false).Contains("script=Latin"));
}
ts.End();
}
public void TestScriptNames()
{
for (int i = 0; i < UScript.CodeLimit; i++)
{
String name = UScript.GetName(i);
if (name.Equals(""))
{
Errln("FAILED: getName for code : " + i);
}
String shortName = UScript.GetShortName(i);
if (shortName.Equals(""))
{
Errln("FAILED: getName for code : " + i);
}
}
}
private static String ScriptsToString(int[] scripts)
{
if (scripts == null)
{
return("null");
}
StringBuilder sb = new StringBuilder();
foreach (int script in scripts)
{
if (sb.Length > 0)
{
sb.Append(' ');
}
sb.Append(UScript.GetShortName(script));
}
return(sb.ToString());
}
public void TestNewCode()
{
/*
* These script codes were originally added to ICU pre-3.6, so that ICU would
* have all ISO 15924 script codes. ICU was then based on Unicode 4.1.
* These script codes were added with only short names because we don't
* want to invent long names ourselves.
* Unicode 5 and later encode some of these scripts and give them long names.
* Whenever this happens, the long script names here need to be updated.
*/
String[] expectedLong = new String[] {
"Balinese", "Batak", "Blis", "Brahmi", "Cham", "Cirt", "Cyrs",
"Egyd", "Egyh", "Egyptian_Hieroglyphs",
"Geok", "Hans", "Hant", "Pahawh_Hmong", "Old_Hungarian", "Inds",
"Javanese", "Kayah_Li", "Latf", "Latg",
"Lepcha", "Linear_A", "Mandaic", "Maya", "Meroitic_Hieroglyphs",
"Nko", "Old_Turkic", "Old_Permic", "Phags_Pa", "Phoenician",
"Miao", "Roro", "Sara", "Syre", "Syrj", "Syrn", "Teng", "Vai", "Visp", "Cuneiform",
"Zxxx", "Unknown",
"Carian", "Jpan", "Tai_Tham", "Lycian", "Lydian", "Ol_Chiki", "Rejang", "Saurashtra", "SignWriting", "Sundanese",
"Moon", "Meetei_Mayek",
/* new in ICU 4.0 */
"Imperial_Aramaic", "Avestan", "Chakma", "Kore",
"Kaithi", "Manichaean", "Inscriptional_Pahlavi", "Psalter_Pahlavi", "Phlv",
"Inscriptional_Parthian", "Samaritan", "Tai_Viet",
"Zmth", "Zsym",
/* new in ICU 4.4 */
"Bamum", "Lisu", "Nkgb", "Old_South_Arabian",
/* new in ICU 4.6 */
"Bassa_Vah", "Duployan", "Elbasan", "Grantha", "Kpel",
"Loma", "Mende_Kikakui", "Meroitic_Cursive",
"Old_North_Arabian", "Nabataean", "Palmyrene", "Khudawadi", "Warang_Citi",
/* new in ICU 4.8 */
"Afak", "Jurc", "Mro", "Nushu", "Sharada", "Sora_Sompeng", "Takri", "Tangut", "Wole",
/* new in ICU 49 */
"Anatolian_Hieroglyphs", "Khojki", "Tirhuta",
/* new in ICU 52 */
"Caucasian_Albanian", "Mahajani",
/* new in ICU 54 */
"Ahom", "Hatran", "Modi", "Multani", "Pau_Cin_Hau", "Siddham",
// new in ICU 58
"Adlam", "Bhaiksuki", "Marchen", "Newa", "Osage", "Hanb", "Jamo", "Zsye",
// new in ICU 60
"Masaram_Gondi", "Soyombo", "Zanabazar_Square"
};
String[] expectedShort = new String[] {
"Bali", "Batk", "Blis", "Brah", "Cham", "Cirt", "Cyrs", "Egyd", "Egyh", "Egyp",
"Geok", "Hans", "Hant", "Hmng", "Hung", "Inds", "Java", "Kali", "Latf", "Latg",
"Lepc", "Lina", "Mand", "Maya", "Mero", "Nkoo", "Orkh", "Perm", "Phag", "Phnx",
"Plrd", "Roro", "Sara", "Syre", "Syrj", "Syrn", "Teng", "Vaii", "Visp", "Xsux",
"Zxxx", "Zzzz",
"Cari", "Jpan", "Lana", "Lyci", "Lydi", "Olck", "Rjng", "Saur", "Sgnw", "Sund",
"Moon", "Mtei",
/* new in ICU 4.0 */
"Armi", "Avst", "Cakm", "Kore",
"Kthi", "Mani", "Phli", "Phlp", "Phlv", "Prti", "Samr", "Tavt",
"Zmth", "Zsym",
/* new in ICU 4.4 */
"Bamu", "Lisu", "Nkgb", "Sarb",
/* new in ICU 4.6 */
"Bass", "Dupl", "Elba", "Gran", "Kpel", "Loma", "Mend", "Merc",
"Narb", "Nbat", "Palm", "Sind", "Wara",
/* new in ICU 4.8 */
"Afak", "Jurc", "Mroo", "Nshu", "Shrd", "Sora", "Takr", "Tang", "Wole",
/* new in ICU 49 */
"Hluw", "Khoj", "Tirh",
/* new in ICU 52 */
"Aghb", "Mahj",
/* new in ICU 54 */
"Ahom", "Hatr", "Modi", "Mult", "Pauc", "Sidd",
// new in ICU 58
"Adlm", "Bhks", "Marc", "Newa", "Osge", "Hanb", "Jamo", "Zsye",
// new in ICU 60
"Gonm", "Soyo", "Zanb"
};
if (expectedLong.Length != (UScript.CodeLimit - UScript.Balinese))
{
Errln("need to add new script codes in lang.TestUScript.java!");
return;
}
int j = 0;
int i = 0;
for (i = UScript.Balinese; i < UScript.CodeLimit; i++, j++)
{
String name = UScript.GetName(i);
if (name == null || !name.Equals(expectedLong[j]))
{
Errln("UScript.getName failed for code" + i + name + "!=" + expectedLong[j]);
}
name = UScript.GetShortName(i);
if (name == null || !name.Equals(expectedShort[j]))
{
Errln("UScript.getShortName failed for code" + i + name + "!=" + expectedShort[j]);
}
}
for (i = 0; i < expectedLong.Length; i++)
{
int[] ret = UScript.GetCode(expectedShort[i]);
if (ret.Length > 1)
{
Errln("UScript.getCode did not return expected number of codes for script" + expectedShort[i] + ". EXPECTED: 1 GOT: " + ret.Length);
}
if (ret[0] != (UScript.Balinese + i))
{
Errln("UScript.getCode did not return expected code for script" + expectedShort[i] + ". EXPECTED: " + (UScript.Balinese + i) + " GOT: %i\n" + ret[0]);
}
}
}
public void TestScripts()
{
// get a couple of characters of each script for testing
StringBuffer testBuffer = new StringBuffer();
for (int script = 0; script < UScript.CodeLimit; ++script)
{
UnicodeSet test = new UnicodeSet().ApplyPropertyAlias("script", UScript.GetName(script));
int count = Math.Min(20, test.Count);
for (int i = 0; i < count; ++i)
{
testBuffer.Append(UTF16.ValueOf(test[i]));
}
}
{
String test = testBuffer.ToString();
Logln("Test line: " + test);
int inclusion = TestFmwk.GetExhaustiveness();
bool testedUnavailableScript = false;
for (int script = 0; script < UScript.CodeLimit; ++script)
{
if (script == UScript.Common || script == UScript.Inherited)
{
continue;
}
// if the inclusion rate is not 10, skip all but a small number of items.
// 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;
}
String scriptName = UScript.GetName(script); // long name
UCultureInfo locale = new UCultureInfo(scriptName);
if (locale.Language.Equals("new") || locale.Language.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);
continue; // we don't handle all scripts
}
Logln("Checking: " + scriptName);
if (t != null)
{
t.Transform(test); // just verify we don't crash
}
String shortScriptName = UScript.GetShortName(script); // 4-letter script code
try
{
t = Transliterator.GetInstance("any-" + shortScriptName);
}
catch (Exception e)
{
Errln("Transliterator.GetInstance() worked for \"any-" + scriptName +
"\" but not for \"any-" + shortScriptName + '\"');
}
t.Transform(test); // just verify we don't crash
}
}
}
public override string GetScriptDisplayName(int scriptCode)
{
return(UScript.GetShortName(scriptCode));
}
public virtual string GetShortName()
{
return(UScript.GetShortName(code));
}
