Created
October 13, 2010 13:57
-
-
Save chrisrichards/624076 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using System.IO; | |
using Lucene.Net.Analysis; | |
namespace LuceneTest | |
{ | |
public class PartNumberAnalyzer : Analyzer | |
{ | |
private const string SkipCharacters = " -/\\"; | |
#region Overrides of Analyzer | |
public override TokenStream TokenStream(string fieldName, TextReader reader) | |
{ | |
TokenStream result = new SkipCharTokenizer(reader, SkipCharacters); | |
result = new LowerCaseFilter(result); | |
return result; | |
} | |
#endregion | |
} | |
} |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using Lucene.Net.Analysis; | |
namespace LuceneTest | |
{ | |
public class SkipCharTokenizer : Tokenizer | |
{ | |
private int _offset, _bufferIndex, _dataLen; | |
private const int MaxWordLen = 255; | |
private const int IoBufferSize = 1024; | |
private readonly char[] _ioBuffer = new char[IoBufferSize]; | |
private readonly string _skipCharacters; | |
public SkipCharTokenizer(System.IO.TextReader input, string skipCharacters) | |
: base(input) | |
{ | |
_skipCharacters = skipCharacters; | |
} | |
public override Token Next(Token token) | |
{ | |
token.Clear(); | |
var length = 0; | |
var start = _bufferIndex; | |
var buffer = token.TermBuffer(); | |
while (true) { | |
if (_bufferIndex >= _dataLen) { | |
_offset += _dataLen; | |
_dataLen = input.Read(_ioBuffer, 0, _ioBuffer.Length); | |
if (_dataLen <= 0) { | |
if (length > 0) { | |
break; | |
} | |
return null; | |
} | |
_bufferIndex = 0; | |
} | |
var c = _ioBuffer[_bufferIndex++]; | |
if (_skipCharacters.IndexOf(c) != -1) { | |
continue; | |
} | |
if (length == 0) { | |
start = _offset + _bufferIndex - 1; | |
} | |
else if (length == buffer.Length) { | |
buffer = token.ResizeTermBuffer(1 + length); | |
} | |
buffer[length++] = c; | |
if (length == MaxWordLen) { | |
break; | |
} | |
} | |
token.SetTermLength(length); | |
token.SetStartOffset(start); | |
token.SetEndOffset(start + length); | |
return token; | |
} | |
public override void Reset(System.IO.TextReader reader) | |
{ | |
base.Reset(reader); | |
_bufferIndex = 0; | |
_offset = 0; | |
_dataLen = 0; | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment