public void TestPreceding()
{
String words3 = "aaa bbb ccc";
BreakIterator e = BreakIterator.GetWordInstance(CultureInfo.CurrentCulture);
e.SetText(words3);
e.First();
int p1 = e.Next();
int p2 = e.Next();
int p3 = e.Next();
int p4 = e.Next();
int f = e.Following(p2 + 1);
int p = e.Preceding(p2 + 1);
if (f != p3)
{
Errln("IntlTestTextBoundary::TestPreceding: f!=p3");
}
if (p != p2)
{
Errln("IntlTestTextBoundary::TestPreceding: p!=p2");
}
if (p1 + 1 != p2)
{
Errln("IntlTestTextBoundary::TestPreceding: p1+1!=p2");
}
if (p3 + 1 != p4)
{
Errln("IntlTestTextBoundary::TestPreceding: p3+1!=p4");
}
if (!e.IsBoundary(p2) || e.IsBoundary(p2 + 1) || !e.IsBoundary(p3))
{
Errln("IntlTestTextBoundary::TestPreceding: isBoundary err");
}
}
public void TestBug12918()
{
// This test triggered an assertion failure in ICU4C, in dictbe.cpp
// The equivalent code in ICU4J is structured slightly differently,
// and does not appear vulnerable to the same issue.
//
// \u3325 decomposes with normalization, then the CJK dictionary
// finds a break within the decomposition.
String crasherString = "\u3325\u4a16";
BreakIterator iter = BreakIterator.GetWordInstance(ULocale.ENGLISH);
iter.SetText(crasherString);
iter.First();
int pos = 0;
int lastPos = -1;
while ((pos = iter.Next()) != BreakIterator.Done)
{
assertTrue("", pos > lastPos);
}
}
public void TestThaiDictionaryBreakIterator()
{
int position;
int index;
int[] result = { 1, 2, 5, 10, 11, 12, 11, 10, 5, 2, 1, 0 };
char[] ctext =
{
(char)0x0041, (char)0x0020,
(char)0x0E01, (char)0x0E32,(char)0x0E23, (char)0x0E17, (char)0x0E14, (char)0x0E25, (char)0x0E2D, (char)0x0E07,
(char)0x0020, (char)0x0041
};
String text = new String(ctext);
ULocale locale = ULocale.CreateCanonical("th");
BreakIterator b = BreakIterator.GetWordInstance(locale);
b.SetText(text);
index = 0;
// Test forward iteration
while ((position = b.Next()) != BreakIterator.Done)
{
if (position != result[index++])
{
Errln("Error with ThaiDictionaryBreakIterator forward iteration test at " + position + ".\nShould have been " + result[index - 1]);
}
}
// Test backward iteration
while ((position = b.Previous()) != BreakIterator.Done)
{
if (position != result[index++])
{
Errln("Error with ThaiDictionaryBreakIterator backward iteration test at " + position + ".\nShould have been " + result[index - 1]);
}
}
//Test invalid sequence and spaces
char[] text2 =
{
(char)0x0E01, (char)0x0E39, (char)0x0020, (char)0x0E01, (char)0x0E34, (char)0x0E19, (char)0x0E01, (char)0x0E38, (char)0x0E49, (char)0x0E07, (char)0x0020, (char)0x0E1B,
(char)0x0E34, (char)0x0E49, (char)0x0E48, (char)0x0E07, (char)0x0E2D, (char)0x0E22, (char)0x0E39, (char)0x0E48, (char)0x0E43, (char)0x0E19,
(char)0x0E16, (char)0x0E49, (char)0x0E33
};
int[] expectedWordResult =
{
2, 3, 6, 10, 11, 15, 17, 20, 22
};
int[] expectedLineResult =
{
3, 6, 11, 15, 17, 20, 22
};
BreakIterator brk = BreakIterator.GetWordInstance(new ULocale("th"));
brk.SetText(new String(text2));
position = index = 0;
while ((position = brk.Next()) != BreakIterator.Done && position < text2.Length)
{
if (position != expectedWordResult[index++])
{
Errln("Incorrect break given by thai word break iterator. Expected: " + expectedWordResult[index - 1] + " Got: " + position);
}
}
brk = BreakIterator.GetLineInstance(new ULocale("th"));
brk.SetText(new String(text2));
position = index = 0;
while ((position = brk.Next()) != BreakIterator.Done && position < text2.Length)
{
if (position != expectedLineResult[index++])
{
Errln("Incorrect break given by thai line break iterator. Expected: " + expectedLineResult[index - 1] + " Got: " + position);
}
}
// Improve code coverage
if (brk.Preceding(expectedLineResult[1]) != expectedLineResult[0])
{
Errln("Incorrect preceding position.");
}
if (brk.Following(expectedLineResult[1]) != expectedLineResult[2])
{
Errln("Incorrect following position.");
}
int[] fillInArray = new int[2];
if (((RuleBasedBreakIterator)brk).GetRuleStatusVec(fillInArray) != 1 || fillInArray[0] != 0)
{
Errln("Error: Since getRuleStatusVec is not supported in DictionaryBasedBreakIterator, it should return 1 and fillInArray[0] == 0.");
}
}
public void TestExtended()
{
TestParams tp = new TestParams();
//
// Open and read the test data file.
//
StringBuilder testFileBuf = new StringBuilder();
Stream @is = null;
try
{
@is = typeof(RBBITestExtended).GetTypeInfo().Assembly.GetManifestResourceStream("ICU4N.Dev.Test.Rbbi.rbbitst.txt");
if (@is == null)
{
Errln("Could not open test data file rbbitst.txt");
return;
}
StreamReader isr = new StreamReader(@is, Encoding.UTF8);
try
{
int c;
int count = 0;
for (; ;)
{
c = isr.Read();
if (c < 0)
{
break;
}
count++;
if (c == 0xFEFF && count == 1)
{
// BOM in the test data file. Discard it.
continue;
}
testFileBuf.AppendCodePoint(c);
}
}
finally
{
isr.Dispose();
}
}
catch (IOException e)
{
Errln(e.ToString());
try
{
@is.Dispose();
}
catch (IOException ignored)
{
}
return;
}
String testString = testFileBuf.ToString();
const int PARSE_COMMENT = 1;
const int PARSE_TAG = 2;
const int PARSE_DATA = 3;
const int PARSE_NUM = 4;
const int PARSE_RULES = 5;
int parseState = PARSE_TAG;
int savedState = PARSE_TAG;
int lineNum = 1;
int colStart = 0;
int column = 0;
int charIdx = 0;
int i;
int tagValue = 0; // The numeric value of a <nnn> tag.
StringBuilder rules = new StringBuilder(); // Holds rules from a <rules> ... </rules> block
int rulesFirstLine = 0; // Line number of the start of current <rules> block
int len = testString.Length;
for (charIdx = 0; charIdx < len;)
{
int c = testString.CodePointAt(charIdx);
charIdx++;
if (c == '\r' && charIdx < len && testString[charIdx] == '\n')
{
// treat CRLF as a unit
c = '\n';
charIdx++;
}
if (c == '\n' || c == '\r')
{
lineNum++;
colStart = charIdx;
}
column = charIdx - colStart + 1;
switch (parseState)
{
case PARSE_COMMENT:
if (c == 0x0a || c == 0x0d)
{
parseState = savedState;
}
break;
case PARSE_TAG:
{
if (c == '#')
{
parseState = PARSE_COMMENT;
savedState = PARSE_TAG;
break;
}
if (UCharacter.IsWhitespace(c))
{
break;
}
if (testString.StartsWith("<word>", charIdx - 1))
{
tp.bi = BreakIterator.GetWordInstance(tp.currentLocale);
charIdx += 5;
break;
}
if (testString.StartsWith("<char>", charIdx - 1))
{
tp.bi = BreakIterator.GetCharacterInstance(tp.currentLocale);
charIdx += 5;
break;
}
if (testString.StartsWith("<line>", charIdx - 1))
{
tp.bi = BreakIterator.GetLineInstance(tp.currentLocale);
charIdx += 5;
break;
}
if (testString.StartsWith("<sent>", charIdx - 1))
{
tp.bi = BreakIterator.GetSentenceInstance(tp.currentLocale);
charIdx += 5;
break;
}
if (testString.StartsWith("<title>", charIdx - 1))
{
tp.bi = BreakIterator.GetTitleInstance(tp.currentLocale);
charIdx += 6;
break;
}
if (testString.StartsWith("<rules>", charIdx - 1) ||
testString.StartsWith("<badrules>", charIdx - 1))
{
charIdx = testString.IndexOf('>', charIdx) + 1;
parseState = PARSE_RULES;
rules.Length = (0);
rulesFirstLine = lineNum;
break;
}
if (testString.StartsWith("<locale ", charIdx - 1))
{
int closeIndex = testString.IndexOf(">", charIdx);
if (closeIndex < 0)
{
Errln("line" + lineNum + ": missing close on <locale tag.");
break;
}
String localeName = testString.Substring(charIdx + 6, closeIndex - (charIdx + 6)); // ICU4N: Corrected 2nd parameter
localeName = localeName.Trim();
tp.currentLocale = new ULocale(localeName);
charIdx = closeIndex + 1;
break;
}
if (testString.StartsWith("<data>", charIdx - 1))
{
parseState = PARSE_DATA;
charIdx += 5;
tp.dataToBreak.Length = (0);
Arrays.Fill(tp.expectedBreaks, 0);
Arrays.Fill(tp.srcCol, 0);
Arrays.Fill(tp.srcLine, 0);
break;
}
Errln("line" + lineNum + ": Tag expected in test file.");
return;
//parseState = PARSE_COMMENT;
//savedState = PARSE_DATA;
}
case PARSE_RULES:
if (testString.StartsWith("</rules>", charIdx - 1))
{
charIdx += 7;
parseState = PARSE_TAG;
try
{
tp.bi = new RuleBasedBreakIterator(rules.ToString());
}
catch (ArgumentException e)
{
Errln(String.Format("rbbitst.txt:{0} Error creating break iterator from rules. {1}", lineNum, e));
}
}
else if (testString.StartsWith("</badrules>", charIdx - 1))
{
charIdx += 10;
parseState = PARSE_TAG;
bool goodRules = true;
try
{
new RuleBasedBreakIterator(rules.ToString());
}
catch (ArgumentException e)
{
goodRules = false;
}
if (goodRules)
{
Errln(String.Format(
"rbbitst.txt:{0} Expected, but did not get, a failure creating break iterator from rules.",
lineNum));
}
}
else
{
rules.AppendCodePoint(c);
}
break;
case PARSE_DATA:
if (c == '•')
{
int breakIdx = tp.dataToBreak.Length;
tp.expectedBreaks[breakIdx] = -1;
tp.srcLine[breakIdx] = lineNum;
tp.srcCol[breakIdx] = column;
break;
}
if (testString.StartsWith("</data>", charIdx - 1))
{
// Add final entry to mappings from break location to source file position.
// Need one extra because last break position returned is after the
// last char in the data, not at the last char.
int idx = tp.dataToBreak.Length;
tp.srcLine[idx] = lineNum;
tp.srcCol[idx] = column;
parseState = PARSE_TAG;
charIdx += 6;
// RUN THE TEST!
executeTest(tp);
break;
}
if (testString.StartsWith("\\N{", charIdx - 1))
{
int nameEndIdx = testString.IndexOf('}', charIdx);
if (nameEndIdx == -1)
{
Errln("Error in named character in test file at line " + lineNum +
", col " + column);
}
// Named character, e.g. \N{COMBINING GRAVE ACCENT}
// Get the code point from the name and insert it into the test data.
String charName = testString.Substring(charIdx + 2, nameEndIdx - (charIdx + 2)); // ICU4N: Corrected 2nd parameter
c = UCharacter.GetCharFromName(charName);
if (c == -1)
{
Errln("Error in named character in test file at line " + lineNum +
", col " + column);
}
else
{
// Named code point was recognized. Insert it
// into the test data.
tp.dataToBreak.AppendCodePoint(c);
for (i = tp.dataToBreak.Length - 1; i >= 0 && tp.srcLine[i] == 0; i--)
{
tp.srcLine[i] = lineNum;
tp.srcCol[i] = column;
}
}
if (nameEndIdx > charIdx)
{
charIdx = nameEndIdx + 1;
}
break;
}
if (testString.StartsWith("<>", charIdx - 1))
{
charIdx++;
int breakIdx = tp.dataToBreak.Length;
tp.expectedBreaks[breakIdx] = -1;
tp.srcLine[breakIdx] = lineNum;
tp.srcCol[breakIdx] = column;
break;
}
if (c == '<')
{
tagValue = 0;
parseState = PARSE_NUM;
break;
}
if (c == '#' && column == 3)
{ // TODO: why is column off so far?
parseState = PARSE_COMMENT;
savedState = PARSE_DATA;
break;
}
if (c == '\\')
{
// Check for \ at end of line, a line continuation.
// Advance over (discard) the newline
int cp = testString.CodePointAt(charIdx);
if (cp == '\r' && charIdx < len && testString.CodePointAt(charIdx + 1) == '\n')
{
// We have a CR LF
// Need an extra increment of the input ptr to move over both of them
charIdx++;
}
if (cp == '\n' || cp == '\r')
{
lineNum++;
column = 0;
charIdx++;
colStart = charIdx;
break;
}
// Let unescape handle the back slash.
int[] charIdxAr = new int[1];
charIdxAr[0] = charIdx;
cp = Utility.UnescapeAt(testString, charIdxAr);
if (cp != -1)
{
// Escape sequence was recognized. Insert the char
// into the test data.
charIdx = charIdxAr[0];
tp.dataToBreak.AppendCodePoint(cp);
for (i = tp.dataToBreak.Length - 1; i >= 0 && tp.srcLine[i] == 0; i--)
{
tp.srcLine[i] = lineNum;
tp.srcCol[i] = column;
}
break;
}
// Not a recognized backslash escape sequence.
// Take the next char as a literal.
// TODO: Should this be an error?
c = testString.CodePointAt(charIdx);
charIdx = testString.OffsetByCodePoints(charIdx, 1);
}
// Normal, non-escaped data char.
tp.dataToBreak.AppendCodePoint(c);
// Save the mapping from offset in the data to line/column numbers in
// the original input file. Will be used for better error messages only.
// If there's an expected break before this char, the slot in the mapping
// vector will already be set for this char; don't overwrite it.
for (i = tp.dataToBreak.Length - 1; i >= 0 && tp.srcLine[i] == 0; i--)
{
tp.srcLine[i] = lineNum;
tp.srcCol[i] = column;
}
break;
case PARSE_NUM:
// We are parsing an expected numeric tag value, like <1234>,
// within a chunk of data.
if (UCharacter.IsWhitespace(c))
{
break;
}
if (c == '>')
{
// Finished the number. Add the info to the expected break data,
// and switch parse state back to doing plain data.
parseState = PARSE_DATA;
if (tagValue == 0)
{
tagValue = -1;
}
int breakIdx = tp.dataToBreak.Length;
tp.expectedBreaks[breakIdx] = tagValue;
tp.srcLine[breakIdx] = lineNum;
tp.srcCol[breakIdx] = column;
break;
}
if (UCharacter.IsDigit(c))
{
tagValue = tagValue * 10 + UCharacter.Digit(c);
break;
}
Errln(String.Format("Syntax Error in rbbitst.txt at line {0}, col {1}", lineNum, column));
return;
}
}
// Reached end of test file. Raise an error if parseState indicates that we are
// within a block that should have been terminated.
if (parseState == PARSE_RULES)
{
Errln(String.Format("rbbitst.txt:{0} <rules> block beginning at line {1} is not closed.",
lineNum, rulesFirstLine));
}
if (parseState == PARSE_DATA)
{
Errln(String.Format("rbbitst.txt:{0} <data> block not closed.", lineNum));
}
}
public void TestRegUnreg()
{
CultureInfo thailand_locale = new CultureInfo("th-TH");
// ICU4N: Arbitrary locales are not allowed in .NET
//CultureInfo foo_locale = new CultureInfo("fu-FU");
BreakIterator jwbi = BreakIterator.GetWordInstance(new CultureInfo("ja"));
BreakIterator uwbi = BreakIterator.GetWordInstance(new CultureInfo("en-US"));
BreakIterator usbi = BreakIterator.GetSentenceInstance(new CultureInfo("en-US"));
BreakIterator twbi = BreakIterator.GetWordInstance(thailand_locale);
BreakIterator rwbi = BreakIterator.GetWordInstance(CultureInfo.InvariantCulture); // (new Locale("", "", ""));
BreakIterator sbi = (BreakIterator)usbi.Clone();
// todo: this will cause the test to fail, no way to set a breakiterator to null text so can't fix yet.
// String text = "This is some test, by golly. Boy, they don't make tests like they used to, do they? This here test ain't worth $2.50. Nope.";
// sbi.setText(text);
assertTrue(!BreakIterator.Unregister(""), "unregister before register"); // coverage
// ICU4N: Arbitrary locales are not allowed in .NET
//object key0 = BreakIterator.RegisterInstance((BreakIterator)twbi.Clone(), foo_locale, BreakIterator.KIND_WORD);
object key1 = BreakIterator.RegisterInstance(sbi, new CultureInfo("en-US"), BreakIterator.KIND_WORD);
object key2 = BreakIterator.RegisterInstance((BreakIterator)twbi.Clone(), new CultureInfo("en-US"), BreakIterator.KIND_WORD);
{
BreakIterator test0 = BreakIterator.GetWordInstance(new CultureInfo("ja"));
BreakIterator test1 = BreakIterator.GetWordInstance(new CultureInfo("en-US"));
BreakIterator test2 = BreakIterator.GetSentenceInstance(new CultureInfo("en-US"));
BreakIterator test3 = BreakIterator.GetWordInstance(thailand_locale);
// ICU4N: Arbitrary locales are not allowed in .NET
//BreakIterator test4 = BreakIterator.GetWordInstance(foo_locale);
assertEqual(test0, jwbi, "japan word == japan word");
assertEqual(test1, twbi, "us word == thai word");
assertEqual(test2, usbi, "us sentence == us sentence");
assertEqual(test3, twbi, "thai word == thai word");
// ICU4N: Arbitrary locales are not allowed in .NET
//assertEqual(test4, twbi, "foo word == thai word");
}
//Locale[] locales = BreakIterator.getAvailableLocales();
assertTrue(BreakIterator.Unregister(key2), "unregister us word (thai word)");
assertTrue(!BreakIterator.Unregister(key2), "unregister second time");
bool error = false;
try
{
BreakIterator.Unregister(null);
}
catch (ArgumentException e)
{
error = true;
}
assertTrue(error, "unregister null");
{
CharacterIterator sci = BreakIterator.GetWordInstance(new CultureInfo("en-US")).Text;
int len = sci.EndIndex - sci.BeginIndex;
assertEqual(len, 0, "us word text: " + getString(sci));
}
// ICU4N: Arbitrary locales are not allowed in .NET
//assertTrue((BreakIterator.GetAvailableLocales().ToList()).Contains(foo_locale), "foo_locale");
//assertTrue(BreakIterator.Unregister(key0), "unregister foo word (thai word)");
//assertTrue(!(BreakIterator.GetAvailableLocales().ToList()).Contains(foo_locale), "no foo_locale");
assertEqual(BreakIterator.GetWordInstance(new CultureInfo("en-US")), usbi, "us word == us sentence");
assertTrue(BreakIterator.Unregister(key1), "unregister us word (us sentence)");
{
BreakIterator test0 = BreakIterator.GetWordInstance(new CultureInfo("ja"));
BreakIterator test1 = BreakIterator.GetWordInstance(new CultureInfo("en-US"));
BreakIterator test2 = BreakIterator.GetSentenceInstance(new CultureInfo("en-US"));
BreakIterator test3 = BreakIterator.GetWordInstance(thailand_locale);
// ICU4N: Arbitrary locales are not allowed in .NET
//BreakIterator test4 = BreakIterator.GetWordInstance(foo_locale);
assertEqual(test0, jwbi, "japanese word break");
assertEqual(test1, uwbi, "us sentence-word break");
assertEqual(test2, usbi, "us sentence break");
assertEqual(test3, twbi, "thai word break");
// ICU4N: Arbitrary locales are not allowed in .NET
//assertEqual(test4, rwbi, "root word break");
CharacterIterator sci = test1.Text;
int len = sci.EndIndex - sci.BeginIndex;
assertEqual(len, 0, "us sentence-word break text: " + getString(sci));
}
}
public void TestLastPreviousPreceding()
{
int p, q;
String testString = "This is a word break. Isn't it? 2.25 dollars";
Logln("Testing last(),previous(), preceding() with custom rules");
Logln("testing word iteration for string \"" + testString + "\"");
RuleBasedBreakIterator wordIter1 = (RuleBasedBreakIterator)BreakIterator.GetWordInstance(new CultureInfo("en"));
wordIter1.SetText(testString);
p = wordIter1.Last();
if (p != testString.Length)
{
Errln("ERROR: last() returned" + p + "instead of" + testString.Length);
}
q = wordIter1.Previous();
doTest(testString, p, q, 37, "dollars");
p = q;
q = wordIter1.Previous();
doTest(testString, p, q, 36, " ");
q = wordIter1.Preceding(25);
doTest(testString, 25, q, 22, "Isn");
p = q;
q = wordIter1.Previous();
doTest(testString, p, q, 21, " ");
q = wordIter1.Preceding(20);
doTest(testString, 20, q, 15, "break");
p = wordIter1.Preceding(wordIter1.First());
if (p != BreakIterator.Done)
{
Errln("ERROR: preceding() at starting position returned #" + p + " instead of 0");
}
testString = "Hello! how are you? I'am fine. Thankyou. How are you doing? This costs $20,00,000.";
Logln("testing sentence iter - String:- \"" + testString + "\"");
RuleBasedBreakIterator sentIter1 = (RuleBasedBreakIterator)BreakIterator.GetSentenceInstance(CultureInfo.CurrentCulture);
sentIter1.SetText(testString);
p = sentIter1.Last();
if (p != testString.Length)
{
Errln("ERROR: last() returned" + p + "instead of " + testString.Length);
}
q = sentIter1.Previous();
doTest(testString, p, q, 60, "This costs $20,00,000.");
p = q;
q = sentIter1.Previous();
doTest(testString, p, q, 41, "How are you doing? ");
q = sentIter1.Preceding(40);
doTest(testString, 40, q, 31, "Thankyou.");
q = sentIter1.Preceding(25);
doTest(testString, 25, q, 20, "I'am ");
sentIter1.First();
p = sentIter1.Previous();
q = sentIter1.Preceding(sentIter1.First());
if (p != BreakIterator.Done || q != BreakIterator.Done)
{
Errln("ERROR: previous()/preceding() at starting position returned #"
+ p + " and " + q + " instead of 0\n");
}
testString = "Hello! how are you? I'am fine. Thankyou. How are you doing? This\n costs $20,00,000.";
Logln("testing line iter - String:- \"" + testString + "\"");
RuleBasedBreakIterator lineIter1 = (RuleBasedBreakIterator)BreakIterator.GetLineInstance(CultureInfo.CurrentCulture);
lineIter1.SetText(testString);
p = lineIter1.Last();
if (p != testString.Length)
{
Errln("ERROR: last() returned" + p + "instead of " + testString.Length);
}
q = lineIter1.Previous();
doTest(testString, p, q, 72, "$20,00,000.");
p = q;
q = lineIter1.Previous();
doTest(testString, p, q, 66, "costs ");
q = lineIter1.Preceding(40);
doTest(testString, 40, q, 31, "Thankyou.");
q = lineIter1.Preceding(25);
doTest(testString, 25, q, 20, "I'am ");
lineIter1.First();
p = lineIter1.Previous();
q = lineIter1.Preceding(sentIter1.First());
if (p != BreakIterator.Done || q != BreakIterator.Done)
{
Errln("ERROR: previous()/preceding() at starting position returned #"
+ p + " and " + q + " instead of 0\n");
}
}
public void TestFirstNextFollowing()
{
int p, q;
String testString = "This is a word break. Isn't it? 2.25";
Logln("Testing first() and next(), following() with custom rules");
Logln("testing word iterator - string :- \"" + testString + "\"\n");
RuleBasedBreakIterator wordIter1 = (RuleBasedBreakIterator)BreakIterator.GetWordInstance(CultureInfo.CurrentCulture);
wordIter1.SetText(testString);
p = wordIter1.First();
if (p != 0)
{
Errln("ERROR: first() returned" + p + "instead of 0");
}
q = wordIter1.Next(9);
doTest(testString, p, q, 20, "This is a word break");
p = q;
q = wordIter1.Next();
doTest(testString, p, q, 21, ".");
p = q;
q = wordIter1.Next(3);
doTest(testString, p, q, 28, " Isn't ");
p = q;
q = wordIter1.Next(2);
doTest(testString, p, q, 31, "it?");
q = wordIter1.Following(2);
doTest(testString, 2, q, 4, "is");
q = wordIter1.Following(22);
doTest(testString, 22, q, 27, "Isn't");
wordIter1.Last();
p = wordIter1.Next();
q = wordIter1.Following(wordIter1.Last());
if (p != BreakIterator.Done || q != BreakIterator.Done)
{
Errln("ERROR: next()/following() at last position returned #"
+ p + " and " + q + " instead of" + testString.Length + "\n");
}
RuleBasedBreakIterator charIter1 = (RuleBasedBreakIterator)BreakIterator.GetCharacterInstance(CultureInfo.CurrentCulture);
testString = "Write hindi here. ";
Logln("testing char iter - string:- \"" + testString + "\"");
charIter1.SetText(testString);
p = charIter1.First();
if (p != 0)
{
Errln("ERROR: first() returned" + p + "instead of 0");
}
q = charIter1.Next();
doTest(testString, p, q, 1, "W");
p = q;
q = charIter1.Next(4);
doTest(testString, p, q, 5, "rite");
p = q;
q = charIter1.Next(12);
doTest(testString, p, q, 17, " hindi here.");
p = q;
q = charIter1.Next(-6);
doTest(testString, p, q, 11, " here.");
p = q;
q = charIter1.Next(6);
doTest(testString, p, q, 17, " here.");
p = charIter1.Following(charIter1.Last());
q = charIter1.Next(charIter1.Last());
if (p != BreakIterator.Done || q != BreakIterator.Done)
{
Errln("ERROR: following()/next() at last position returned #"
+ p + " and " + q + " instead of" + testString.Length);
}
testString = "Hello! how are you? I'am fine. Thankyou. How are you doing? This costs $20,00,000.";
RuleBasedBreakIterator sentIter1 = (RuleBasedBreakIterator)BreakIterator.GetSentenceInstance(CultureInfo.CurrentCulture);
Logln("testing sentence iter - String:- \"" + testString + "\"");
sentIter1.SetText(testString);
p = sentIter1.First();
if (p != 0)
{
Errln("ERROR: first() returned" + p + "instead of 0");
}
q = sentIter1.Next();
doTest(testString, p, q, 7, "Hello! ");
p = q;
q = sentIter1.Next(2);
doTest(testString, p, q, 31, "how are you? I'am fine. ");
p = q;
q = sentIter1.Next(-2);
doTest(testString, p, q, 7, "how are you? I'am fine. ");
p = q;
q = sentIter1.Next(4);
doTest(testString, p, q, 60, "how are you? I'am fine. Thankyou. How are you doing? ");
p = q;
q = sentIter1.Next();
doTest(testString, p, q, 83, "This costs $20,00,000.");
q = sentIter1.Following(1);
doTest(testString, 1, q, 7, "ello! ");
q = sentIter1.Following(10);
doTest(testString, 10, q, 20, " are you? ");
q = sentIter1.Following(20);
doTest(testString, 20, q, 31, "I'am fine. ");
p = sentIter1.Following(sentIter1.Last());
q = sentIter1.Next(sentIter1.Last());
if (p != BreakIterator.Done || q != BreakIterator.Done)
{
Errln("ERROR: following()/next() at last position returned #"
+ p + " and " + q + " instead of" + testString.Length);
}
testString = "Hello! how\r\n (are)\r you? I'am fine- Thankyou. foo\u00a0bar How, are, you? This, costs $20,00,000.";
Logln("(UnicodeString)testing line iter - String:- \"" + testString + "\"");
RuleBasedBreakIterator lineIter1 = (RuleBasedBreakIterator)BreakIterator.GetLineInstance(CultureInfo.CurrentCulture);
lineIter1.SetText(testString);
p = lineIter1.First();
if (p != 0)
{
Errln("ERROR: first() returned" + p + "instead of 0");
}
q = lineIter1.Next();
doTest(testString, p, q, 7, "Hello! ");
p = q;
p = q;
q = lineIter1.Next(4);
doTest(testString, p, q, 20, "how\r\n (are)\r ");
p = q;
q = lineIter1.Next(-4);
doTest(testString, p, q, 7, "how\r\n (are)\r ");
p = q;
q = lineIter1.Next(6);
doTest(testString, p, q, 30, "how\r\n (are)\r you? I'am ");
p = q;
q = lineIter1.Next();
doTest(testString, p, q, 36, "fine- ");
p = q;
q = lineIter1.Next(2);
doTest(testString, p, q, 54, "Thankyou. foo\u00a0bar ");
q = lineIter1.Following(60);
doTest(testString, 60, q, 64, "re, ");
q = lineIter1.Following(1);
doTest(testString, 1, q, 7, "ello! ");
q = lineIter1.Following(10);
doTest(testString, 10, q, 12, "\r\n");
q = lineIter1.Following(20);
doTest(testString, 20, q, 25, "you? ");
p = lineIter1.Following(lineIter1.Last());
q = lineIter1.Next(lineIter1.Last());
if (p != BreakIterator.Done || q != BreakIterator.Done)
{
Errln("ERROR: following()/next() at last position returned #"
+ p + " and " + q + " instead of" + testString.Length);
}
}
private static BreakIterator LoadProto()
{
lock (syncLock)
return(BreakIterator.GetWordInstance(new CultureInfo("th")));
}
public void TestNullLocale()
{
CultureInfo loc = null;
ULocale uloc = null;
BreakIterator brk;
// Character
try
{
brk = BreakIterator.GetCharacterInstance(loc);
Errln("getCharacterInstance((Locale)null) did not throw NPE.");
}
catch (ArgumentNullException e) { /* OK */ }
try
{
brk = BreakIterator.GetCharacterInstance(uloc);
Errln("getCharacterInstance((ULocale)null) did not throw NPE.");
}
catch (ArgumentNullException e) { /* OK */ }
// Line
try
{
brk = BreakIterator.GetLineInstance(loc);
Errln("getLineInstance((Locale)null) did not throw NPE.");
}
catch (ArgumentNullException e) { /* OK */ }
try
{
brk = BreakIterator.GetLineInstance(uloc);
Errln("getLineInstance((ULocale)null) did not throw NPE.");
}
catch (ArgumentNullException e) { /* OK */ }
// Sentence
try
{
brk = BreakIterator.GetSentenceInstance(loc);
Errln("getSentenceInstance((Locale)null) did not throw NPE.");
}
catch (ArgumentNullException e) { /* OK */ }
try
{
brk = BreakIterator.GetSentenceInstance(uloc);
Errln("getSentenceInstance((ULocale)null) did not throw NPE.");
}
catch (ArgumentNullException e) { /* OK */ }
// Title
try
{
brk = BreakIterator.GetTitleInstance(loc);
Errln("getTitleInstance((Locale)null) did not throw NPE.");
}
catch (ArgumentNullException e) { /* OK */ }
try
{
brk = BreakIterator.GetTitleInstance(uloc);
Errln("getTitleInstance((ULocale)null) did not throw NPE.");
}
catch (ArgumentNullException e) { /* OK */ }
// Word
try
{
brk = BreakIterator.GetWordInstance(loc);
Errln("getWordInstance((Locale)null) did not throw NPE.");
}
catch (ArgumentNullException e) { /* OK */ }
try
{
brk = BreakIterator.GetWordInstance(uloc);
Errln("getWordInstance((ULocale)null) did not throw NPE.");
}
catch (ArgumentNullException e) { /* OK */ }
}
