public virtual void TestMixedStringArray()
{
Token t = new Token("hello", 0, 5);
Assert.AreEqual(t.TermLength(), 5);
Assert.AreEqual(t.Term, "hello");
t.SetTermBuffer("hello2");
Assert.AreEqual(t.TermLength(), 6);
Assert.AreEqual(t.Term, "hello2");
t.SetTermBuffer("hello3".ToCharArray(), 0, 6);
Assert.AreEqual(t.Term, "hello3");
char[] buffer = t.TermBuffer();
buffer[1] = 'o';
Assert.AreEqual(t.Term, "hollo3");
}
public override Token Next(/* in */ Token reusableToken)
{
System.Diagnostics.Debug.Assert(reusableToken != null);
Token nextToken = input.Next(reusableToken);
if (nextToken != null)
{
char[] buffer = nextToken.TermBuffer();
int length = nextToken.TermLength();
// If no characters actually require rewriting then we
// just return token as-is:
for (int i = 0; i < length; i++)
{
char c = buffer[i];
if (c >= '\u00c0' && c <= '\ufb06')
{
RemoveAccents(buffer, length);
nextToken.SetTermBuffer(output, 0, outputPos);
break;
}
}
return(nextToken);
}
else
{
return(null);
}
}
public override Token Next(Token result)
{
result = input.Next(result);
if (result != null)
{
char[] buffer = result.TermBuffer();
int length = result.TermLength();
// If no characters actually require rewriting then we
// just return token as-is:
for (int i = 0; i < length; i++)
{
char c = buffer[i];
if (c >= '\u00c0' && c <= '\u0178')
{
RemoveAccents(buffer, length);
result.SetTermBuffer(output, 0, outputPos);
break;
}
}
return(result);
}
else
{
return(null);
}
}
public virtual void TestMixedStringArray()
{
Token t = new Token("hello", 0, 5);
Assert.AreEqual(t.TermText(), "hello");
Assert.AreEqual(t.TermLength(), 5);
Assert.AreEqual(new System.String(t.TermBuffer(), 0, 5), "hello");
t.SetTermText("hello2");
Assert.AreEqual(t.TermLength(), 6);
Assert.AreEqual(new System.String(t.TermBuffer(), 0, 6), "hello2");
t.SetTermBuffer("hello3".ToCharArray(), 0, 6);
Assert.AreEqual(t.TermText(), "hello3");
// Make sure if we get the buffer and change a character
// that termText() reflects the change
char[] buffer = t.TermBuffer();
buffer[1] = 'o';
Assert.AreEqual(t.TermText(), "hollo3");
}
public virtual void TestMixedStringArray()
{
Token t = new Token("hello", 0, 5);
Assert.AreEqual(t.TermText(), "hello");
Assert.AreEqual(t.TermLength(), 5);
Assert.AreEqual(t.Term(), "hello");
t.SetTermText("hello2");
Assert.AreEqual(t.TermLength(), 6);
Assert.AreEqual(t.Term(), "hello2");
t.SetTermBuffer("hello3".ToCharArray(), 0, 6);
Assert.AreEqual(t.TermText(), "hello3");
// Make sure if we get the buffer and change a character
// that termText() reflects the change
char[] buffer = t.TermBuffer();
buffer[1] = 'o';
Assert.AreEqual(t.TermText(), "hollo3");
}
/// <summary> Returns the next input Token whose term() is the right len</summary>
public override Token Next(/* in */ Token reusableToken)
{
System.Diagnostics.Debug.Assert(reusableToken != null);
// return the first non-stop word found
for (Token nextToken = input.Next(reusableToken); nextToken != null; nextToken = input.Next(reusableToken))
{
int len = nextToken.TermLength();
if (len >= min && len <= max)
{
return(nextToken);
}
// note: else we ignore it but should we index each part of it?
}
// reached EOS -- return null
return(null);
}
public override Token Next(/* in */ Token reusableToken)
{
System.Diagnostics.Debug.Assert(reusableToken != null);
Token nextToken = input.Next(reusableToken);
if (nextToken == null)
{
return(null);
}
if (stemmer.Stem(nextToken.TermBuffer(), 0, nextToken.TermLength()))
{
nextToken.SetTermBuffer(stemmer.GetResultBuffer(), 0, stemmer.GetResultLength());
}
return(nextToken);
}
public override Token Next(Token reusableToken)
{
Token nextToken = input.Next(reusableToken);
if (nextToken != null)
{
char[] buffer = nextToken.TermBuffer();
int length = nextToken.TermLength();
for (int i = 0; i < length; i++)
{
buffer[i] = System.Char.ToLower(buffer[i]);
}
return(nextToken);
}
else
{
return(null);
}
}
/// <summary> Returns the next input Token whose term() is not a stop word.</summary>
public override Token Next(/* in */ Token reusableToken)
{
System.Diagnostics.Debug.Assert(reusableToken != null);
// return the first non-stop word found
int skippedPositions = 0;
for (Token nextToken = input.Next(reusableToken); nextToken != null; nextToken = input.Next(reusableToken))
{
if (!stopWords.Contains(nextToken.TermBuffer(), 0, nextToken.TermLength()))
{
if (enablePositionIncrements)
{
nextToken.SetPositionIncrement(nextToken.GetPositionIncrement() + skippedPositions);
}
return(nextToken);
}
skippedPositions += nextToken.GetPositionIncrement();
}
// reached EOS -- return null
return(null);
}
public override Token Next(Token result)
{
result = input.Next(result);
if (result != null)
{
char[] buffer = result.TermBuffer();
int length = result.TermLength();
// If no characters actually require rewriting then we
// just return token as-is:
for (int i = 0; i < length; i++)
{
char c = buffer[i];
if (c >= '\u00c0' && c <= '\u0178')
{
RemoveAccents(buffer, length);
result.SetTermBuffer(output, 0, outputPos);
break;
}
}
return result;
}
else
return null;
}
public virtual void TestGrow()
{
Token t = new Token();
System.Text.StringBuilder buf = new System.Text.StringBuilder("ab");
for (int i = 0; i < 20; i++)
{
char[] content = buf.ToString().ToCharArray();
t.SetTermBuffer(content, 0, content.Length);
Assert.AreEqual(buf.Length, t.TermLength());
Assert.AreEqual(buf.ToString(), t.Term);
buf.Append(buf.ToString());
}
Assert.AreEqual(1048576, t.TermLength());
Assert.AreEqual(1048576, t.TermBuffer().Length);
// now as a string, first variant
t = new Token();
buf = new System.Text.StringBuilder("ab");
for (int i = 0; i < 20; i++)
{
System.String content = buf.ToString();
t.SetTermBuffer(content, 0, content.Length);
Assert.AreEqual(content.Length, t.TermLength());
Assert.AreEqual(content, t.Term);
buf.Append(content);
}
Assert.AreEqual(1048576, t.TermLength());
Assert.AreEqual(1048576, t.TermBuffer().Length);
// now as a string, second variant
t = new Token();
buf = new System.Text.StringBuilder("ab");
for (int i = 0; i < 20; i++)
{
System.String content = buf.ToString();
t.SetTermBuffer(content);
Assert.AreEqual(content.Length, t.TermLength());
Assert.AreEqual(content, t.Term);
buf.Append(content);
}
Assert.AreEqual(1048576, t.TermLength());
Assert.AreEqual(1048576, t.TermBuffer().Length);
// Test for slow growth to a long term
t = new Token();
buf = new System.Text.StringBuilder("a");
for (int i = 0; i < 20000; i++)
{
System.String content = buf.ToString();
t.SetTermBuffer(content);
Assert.AreEqual(content.Length, t.TermLength());
Assert.AreEqual(content, t.Term);
buf.Append("a");
}
Assert.AreEqual(20000, t.TermLength());
Assert.AreEqual(32768, t.TermBuffer().Length);
// Test for slow growth to a long term
t = new Token();
buf = new System.Text.StringBuilder("a");
for (int i = 0; i < 20000; i++)
{
System.String content = buf.ToString();
t.SetTermBuffer(content);
Assert.AreEqual(content.Length, t.TermLength());
Assert.AreEqual(content, t.Term);
buf.Append("a");
}
Assert.AreEqual(20000, t.TermLength());
Assert.AreEqual(32768, t.TermBuffer().Length);
}
public int TermLength()
{
return(delegate_Renamed.TermLength());
}
public virtual void TestGrow()
{
Token t = new Token();
System.Text.StringBuilder buf = new System.Text.StringBuilder("ab");
for (int i = 0; i < 20; i++)
{
char[] content = buf.ToString().ToCharArray();
t.SetTermBuffer(content, 0, content.Length);
Assert.AreEqual(buf.Length, t.TermLength());
Assert.AreEqual(buf.ToString(), t.Term);
buf.Append(buf.ToString());
}
Assert.AreEqual(1048576, t.TermLength());
Assert.AreEqual(1179654, t.TermBuffer().Length);
// now as a string, first variant
t = new Token();
buf = new System.Text.StringBuilder("ab");
for (int i = 0; i < 20; i++)
{
System.String content = buf.ToString();
t.SetTermBuffer(content, 0, content.Length);
Assert.AreEqual(content.Length, t.TermLength());
Assert.AreEqual(content, t.Term);
buf.Append(content);
}
Assert.AreEqual(1048576, t.TermLength());
Assert.AreEqual(1179654, t.TermBuffer().Length);
// now as a string, second variant
t = new Token();
buf = new System.Text.StringBuilder("ab");
for (int i = 0; i < 20; i++)
{
System.String content = buf.ToString();
t.SetTermBuffer(content);
Assert.AreEqual(content.Length, t.TermLength());
Assert.AreEqual(content, t.Term);
buf.Append(content);
}
Assert.AreEqual(1048576, t.TermLength());
Assert.AreEqual(1179654, t.TermBuffer().Length);
// Test for slow growth to a long term
t = new Token();
buf = new System.Text.StringBuilder("a");
for (int i = 0; i < 20000; i++)
{
System.String content = buf.ToString();
t.SetTermBuffer(content);
Assert.AreEqual(content.Length, t.TermLength());
Assert.AreEqual(content, t.Term);
buf.Append("a");
}
Assert.AreEqual(20000, t.TermLength());
Assert.AreEqual(20167, t.TermBuffer().Length);
// Test for slow growth to a long term
t = new Token();
buf = new System.Text.StringBuilder("a");
for (int i = 0; i < 20000; i++)
{
System.String content = buf.ToString();
t.SetTermBuffer(content);
Assert.AreEqual(content.Length, t.TermLength());
Assert.AreEqual(content, t.Term);
buf.Append("a");
}
Assert.AreEqual(20000, t.TermLength());
Assert.AreEqual(20167, t.TermBuffer().Length);
}
public virtual void TestMixedStringArray()
{
Token t = new Token("hello", 0, 5);
Assert.AreEqual(t.TermLength(), 5);
Assert.AreEqual(t.Term, "hello");
t.SetTermBuffer("hello2");
Assert.AreEqual(t.TermLength(), 6);
Assert.AreEqual(t.Term, "hello2");
t.SetTermBuffer("hello3".ToCharArray(), 0, 6);
Assert.AreEqual(t.Term, "hello3");
char[] buffer = t.TermBuffer();
buffer[1] = 'o';
Assert.AreEqual(t.Term, "hollo3");
}
private void SetCurrentToken(Token token)
{
if (token == null) return;
ClearAttributes();
_termAtt.SetTermBuffer(token.TermBuffer(), 0, token.TermLength());
_posIncrAtt.SetPositionIncrement(token.GetPositionIncrement());
_flagsAtt.SetFlags(token.GetFlags());
_offsetAtt.SetOffset(token.StartOffset(), token.EndOffset());
_typeAtt.SetType(token.Type());
_payloadAtt.SetPayload(token.GetPayload());
}