Esempio n. 1
0
 private void  Init(int bufferSize)
 {
     this.done = false;
     termAtt   = (TermAttribute)AddAttribute(typeof(TermAttribute));
     offsetAtt = (OffsetAttribute)AddAttribute(typeof(OffsetAttribute));
     termAtt.ResizeTermBuffer(bufferSize);
 }
Esempio n. 2
0
 public override bool IncrementToken()
 {
     if (!done)
     {
         ClearAttributes();
         done = true;
         int    upto   = 0;
         char[] buffer = termAtt.TermBuffer();
         while (true)
         {
             int length = input.Read(buffer, upto, buffer.Length - upto);
             if (length == 0)
             {
                 break;
             }
             upto += length;
             if (upto == buffer.Length)
             {
                 buffer = termAtt.ResizeTermBuffer(1 + buffer.Length);
             }
         }
         termAtt.SetTermLength(upto);
         finalOffset = CorrectOffset(upto);
         offsetAtt.SetOffset(CorrectOffset(0), finalOffset);
         return(true);
     }
     return(false);
 }
Esempio n. 3
0
		private void  Init(int bufferSize)
		{
			this.done = false;
			termAtt = (TermAttribute) AddAttribute(typeof(TermAttribute));
			offsetAtt = (OffsetAttribute) AddAttribute(typeof(OffsetAttribute));
			termAtt.ResizeTermBuffer(bufferSize);
		}
Esempio n. 4
0
        public override bool IncrementToken()
        {
            ClearAttributes();
            int length = 0;
            int start  = bufferIndex;

            char[] buffer = termAtt.TermBuffer();
            while (true)
            {
                if (bufferIndex >= dataLen)
                {
                    offset += dataLen;
                    dataLen = input.Read((System.Char[])ioBuffer, 0, ioBuffer.Length);
                    if (dataLen <= 0)
                    {
                        dataLen = 0;                         // so next offset += dataLen won't decrement offset
                        if (length > 0)
                        {
                            break;
                        }
                        else
                        {
                            return(false);
                        }
                    }
                    bufferIndex = 0;
                }

                char c = ioBuffer[bufferIndex++];

                if (IsTokenChar(c))
                {
                    // if it's a token char

                    if (length == 0)
                    {
                        // start of token
                        start = offset + bufferIndex - 1;
                    }
                    else if (length == buffer.Length)
                    {
                        buffer = termAtt.ResizeTermBuffer(1 + length);
                    }

                    buffer[length++] = Normalize(c);                     // buffer it, normalized

                    if (length == MAX_WORD_LEN)
                    {
                        // buffer overflow!
                        break;
                    }
                }
                else if (length > 0)
                {
                    // at non-Letter w/ chars
                    break;                     // return 'em
                }
            }

            termAtt.SetTermLength(length);
            offsetAtt.SetOffset(CorrectOffset(start), CorrectOffset(start + length));
            return(true);
        }