Example usage for org.apache.lucene.analysis.cn.smart WordType NUMBER

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.cn.smart WordType NUMBER.

Prototype

int NUMBER

To view the source code for org.apache.lucene.analysis.cn.smart WordType NUMBER.

Click Source Link

Document

ASCII Alphanumeric

Usage

From source file:com.churvey.graduate.chinese.WordSegmenter.java

License:Apache License

/**
 * Process a {@link SegToken} so that it is ready for indexing.
 * //from   ww  w.  j av  a 2s .co m
 * This method calculates offsets and normalizes the token with {@link SegTokenFilter}.
 * 
 * @param st input {@link SegToken}
 * @param sentence associated Sentence
 * @param sentenceStartOffset offset into sentence
 * @return Lucene {@link SegToken}
 */
public SegToken convertSegToken(SegToken st, String sentence, int sentenceStartOffset) {

    switch (st.wordType) {
    case WordType.STRING:
    case WordType.NUMBER:
    case WordType.FULLWIDTH_NUMBER:
    case WordType.FULLWIDTH_STRING:
        st.charArray = sentence.substring(st.startOffset, st.endOffset).toCharArray();
        break;
    default:
        break;
    }

    st = tokenFilter.filter(st);
    st.startOffset += sentenceStartOffset;
    st.endOffset += sentenceStartOffset;
    return st;
}

---