|
public static GetInstance ( Lucene.Net.Util.Version matchVersion ) : |
||
| matchVersion | Lucene.Net.Util.Version | /// a version instance |
| return | ||
public virtual void TestCodePointAtCharSequenceInt()
{
#pragma warning disable 612, 618
var java4 = CharacterUtils.GetInstance(LuceneVersion.LUCENE_30);
#pragma warning restore 612, 618
var cpAt3 = "Abc\ud801\udc1c";
var highSurrogateAt3 = "Abc\ud801";
assertEquals((int)'A', java4.CodePointAt(cpAt3, 0));
assertEquals((int)'\ud801', java4.CodePointAt(cpAt3, 3));
assertEquals((int)'\ud801', java4.CodePointAt(highSurrogateAt3, 3));
try
{
java4.CodePointAt(highSurrogateAt3, 4);
fail("string index out of bounds");
}
catch (Exception e) when(e.IsIndexOutOfBoundsException())
{
}
var java5 = CharacterUtils.GetInstance(TEST_VERSION_CURRENT);
assertEquals((int)'A', java5.CodePointAt(cpAt3, 0));
assertEquals(Character.ToCodePoint('\ud801', '\udc1c'), java5.CodePointAt(cpAt3, 3));
assertEquals((int)'\ud801', java5.CodePointAt(highSurrogateAt3, 3));
try
{
java5.CodePointAt(highSurrogateAt3, 4);
fail("string index out of bounds");
}
catch (Exception e) when(e.IsIndexOutOfBoundsException())
{
}
}
public virtual void TestCodePointAtCharSequenceInt()
{
var java4 = CharacterUtils.GetInstance(LuceneVersion.LUCENE_30);
var cpAt3 = "Abc\ud801\udc1c";
var highSurrogateAt3 = "Abc\ud801";
assertEquals((int)'A', java4.CodePointAt(cpAt3, 0));
assertEquals((int)'\ud801', java4.CodePointAt(cpAt3, 3));
assertEquals((int)'\ud801', java4.CodePointAt(highSurrogateAt3, 3));
try
{
java4.CodePointAt(highSurrogateAt3, 4);
fail("string index out of bounds");
}
catch (IndexOutOfRangeException)
{
}
var java5 = CharacterUtils.GetInstance(TEST_VERSION_CURRENT);
assertEquals((int)'A', java5.CodePointAt(cpAt3, 0));
assertEquals(Character.CodePointAt('\ud801', '\udc1c'), java5.CodePointAt(cpAt3, 3));
assertEquals((int)'\ud801', java5.CodePointAt(highSurrogateAt3, 3));
try
{
java5.CodePointAt(highSurrogateAt3, 4);
fail("string index out of bounds");
}
catch (System.IndexOutOfRangeException)
{
}
}
/// <summary>
/// Creates a new <seealso cref="CharTokenizer"/> instance
/// </summary>
/// <param name="matchVersion">
/// Lucene version to match </param>
/// <param name="input">
/// the input to split up into tokens </param>
protected CharTokenizer(LuceneVersion matchVersion, TextReader input)
: base(input)
{
termAtt = AddAttribute <ICharTermAttribute>();
offsetAtt = AddAttribute <IOffsetAttribute>();
charUtils = CharacterUtils.GetInstance(matchVersion);
}
public virtual void TestConversions()
{
var java4 = CharacterUtils.GetJava4Instance(TEST_VERSION_CURRENT);
var java5 = CharacterUtils.GetInstance(TEST_VERSION_CURRENT);
TestConversions(java4);
TestConversions(java5);
}
public virtual void TestCodePointCount()
{
var java4 = CharacterUtils.GetJava4Instance(TEST_VERSION_CURRENT);
var java5 = CharacterUtils.GetInstance(TEST_VERSION_CURRENT);
var s = TestUtil.RandomUnicodeString(Random);
assertEquals(s.Length, java4.CodePointCount(s));
assertEquals(Character.CodePointCount(s, 0, s.Length), java5.CodePointCount(s));
}
internal V[] values; // package private because used in CharArraySet's non Set-conform CharArraySetIterator
/// <summary>
/// Create map with enough capacity to hold startSize terms
/// </summary>
/// <param name="matchVersion">
/// compatibility match version see <a href="#version">Version
/// note</a> above for details. </param>
/// <param name="startSize">
/// the initial capacity </param>
/// <param name="ignoreCase">
/// <code>false</code> if and only if the set should be case sensitive
/// otherwise <code>true</code>. </param>
public CharArrayMap(LuceneVersion matchVersion, int startSize, bool ignoreCase)
{
this.ignoreCase = ignoreCase;
int size = INIT_SIZE;
while (startSize + (startSize >> 2) > size)
{
size <<= 1;
}
keys = new char[size][];
values = new V[size];
this.charUtils = CharacterUtils.GetInstance(matchVersion);
this.matchVersion = matchVersion;
}
internal V[] values; // package private because used in CharArraySet's non Set-conform CharArraySetIterator
/// <summary>
/// Create map with enough capacity to hold startSize terms
/// </summary>
/// <param name="matchVersion">
/// compatibility match version see <a href="#version">Version
/// note</a> above for details. </param>
/// <param name="startSize">
/// the initial capacity </param>
/// <param name="ignoreCase">
/// <code>false</code> if and only if the set should be case sensitive
/// otherwise <code>true</code>. </param>
public CharArrayMap(Lucene.Net.Util.LuceneVersion matchVersion, int startSize, bool ignoreCase)
{
this.ignoreCase = ignoreCase;
int size_Renamed = INIT_SIZE;
while (startSize + (startSize >> 2) > size_Renamed)
{
size_Renamed <<= 1;
}
keys = new char[size_Renamed][];
values = (V[])new object[size_Renamed];
this.charUtils = CharacterUtils.GetInstance(matchVersion);
this.matchVersion = matchVersion;
}
public virtual void TestCodePointAtCharArrayIntInt()
{
#pragma warning disable 612, 618
var java4 = CharacterUtils.GetInstance(LuceneVersion.LUCENE_30);
#pragma warning restore 612, 618
var cpAt3 = "Abc\ud801\udc1c".ToCharArray();
var highSurrogateAt3 = "Abc\ud801".ToCharArray();
assertEquals((int)'A', java4.CodePointAt(cpAt3, 0, 2));
assertEquals((int)'\ud801', java4.CodePointAt(cpAt3, 3, 5));
assertEquals((int)'\ud801', java4.CodePointAt(highSurrogateAt3, 3, 4));
var java5 = CharacterUtils.GetInstance(TEST_VERSION_CURRENT);
assertEquals((int)'A', java5.CodePointAt(cpAt3, 0, 2));
assertEquals(Character.ToCodePoint('\ud801', '\udc1c'), java5.CodePointAt(cpAt3, 3, 5));
assertEquals((int)'\ud801', java5.CodePointAt(highSurrogateAt3, 3, 4));
}
public virtual void TestOffsetByCodePoint()
{
var java4 = CharacterUtils.GetJava4Instance(TEST_VERSION_CURRENT);
var java5 = CharacterUtils.GetInstance(TEST_VERSION_CURRENT);
for (int i = 0; i < 10; ++i)
{
var s = TestUtil.RandomUnicodeString(Random).toCharArray();
var index = TestUtil.NextInt32(Random, 0, s.Length);
var offset = Random.Next(7) - 3;
try
{
var to = java4.OffsetByCodePoints(s, 0, s.Length, index, offset);
assertEquals(to, index + offset);
}
catch (Exception e) when(e.IsIndexOutOfBoundsException())
{
assertTrue((index + offset) < 0 || (index + offset) > s.Length);
}
int o;
try
{
o = java5.OffsetByCodePoints(s, 0, s.Length, index, offset);
}
catch (Exception e) when(e.IsIndexOutOfBoundsException())
{
try
{
Character.OffsetByCodePoints(s, 0, s.Length, index, offset);
fail();
}
catch (Exception e2) when(e2.IsIndexOutOfBoundsException())
{
// OK
}
o = -1;
}
if (o >= 0)
{
assertEquals(Character.OffsetByCodePoints(s, 0, s.Length, index, offset), o);
}
}
}
public virtual void TestFillJava14()
{
var input = "1234\ud801\udc1c789123\ud801\ud801\udc1c\ud801";
var instance = CharacterUtils.GetInstance(LuceneVersion.LUCENE_30);
var reader = new StringReader(input);
var buffer = CharacterUtils.NewCharacterBuffer(5);
assertTrue(instance.Fill(buffer, reader));
assertEquals(5, buffer.Length);
assertEquals("1234\ud801", new string(buffer.Buffer, buffer.Offset, buffer.Length));
assertTrue(instance.Fill(buffer, reader));
assertEquals(5, buffer.Length);
assertEquals("\udc1c7891", new string(buffer.Buffer));
buffer = CharacterUtils.NewCharacterBuffer(6);
assertTrue(instance.Fill(buffer, reader));
assertEquals(6, buffer.Length);
assertEquals("23\ud801\ud801\udc1c\ud801", new string(buffer.Buffer, buffer.Offset, buffer.Length));
assertFalse(instance.Fill(buffer, reader));
}
public virtual void TestFillNoHighSurrogate()
{
var versions = new LuceneVersion[] { LuceneVersion.LUCENE_30, TEST_VERSION_CURRENT };
foreach (var version in versions)
{
var instance = CharacterUtils.GetInstance(version);
var reader = new StringReader("helloworld");
var buffer = CharacterUtils.NewCharacterBuffer(6);
assertTrue(instance.Fill(buffer, reader));
assertEquals(0, buffer.Offset);
assertEquals(6, buffer.Length);
assertEquals("hellow", new string(buffer.Buffer));
assertFalse(instance.Fill(buffer, reader));
assertEquals(4, buffer.Length);
assertEquals(0, buffer.Offset);
assertEquals("orld", new string(buffer.Buffer, buffer.Offset, buffer.Length));
assertFalse(instance.Fill(buffer, reader));
}
}
public virtual void TestFillJava15()
{
const string input = "1234\ud801\udc1c789123\ud801\ud801\udc1c\ud801";
var instance = CharacterUtils.GetInstance(TEST_VERSION_CURRENT);
var reader = new StringReader(input);
var buffer = CharacterUtils.NewCharacterBuffer(5);
assertTrue(instance.Fill(buffer, reader));
assertEquals(4, buffer.Length);
assertEquals("1234", new string(buffer.Buffer, buffer.Offset, buffer.Length));
assertTrue(instance.Fill(buffer, reader));
assertEquals(5, buffer.Length);
assertEquals("\ud801\udc1c789", new string(buffer.Buffer));
assertTrue(instance.Fill(buffer, reader));
assertEquals(4, buffer.Length);
assertEquals("123\ud801", new string(buffer.Buffer, buffer.Offset, buffer.Length));
assertFalse(instance.Fill(buffer, reader));
assertEquals(3, buffer.Length);
assertEquals("\ud801\udc1c\ud801", new string(buffer.Buffer, buffer.Offset, buffer.Length));
assertFalse(instance.Fill(buffer, reader));
assertEquals(0, buffer.Length);
}
/// <summary>
/// LUCENENET specific - Added in the .NET version to assist with setting the attributes
/// from multiple constructors.
/// </summary>
/// <param name="matchVersion"></param>
private void Init(LuceneVersion matchVersion)
{
charUtils = CharacterUtils.GetInstance(matchVersion);
termAtt = AddAttribute <ICharTermAttribute>();
offsetAtt = AddAttribute <IOffsetAttribute>();
}
/// <summary>
/// Creates a new <seealso cref="CharTokenizer"/> instance
/// </summary>
/// <param name="matchVersion">
/// Lucene version to match </param>
/// <param name="factory">
/// the attribute factory to use for this <seealso cref="Tokenizer"/> </param>
/// <param name="input">
/// the input to split up into tokens </param>
protected CharTokenizer(LuceneVersion matchVersion, AttributeFactory factory, TextReader input)
: base(factory, input)
{
_input = input;
charUtils = CharacterUtils.GetInstance(matchVersion);
}
