Example usage for org.apache.lucene.analysis.util StemmerUtil delete

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.util StemmerUtil delete.

Prototype

public static int delete(char s[], int pos, int len) 

Source Link

Document

Delete a character in-place

Usage

From source file:com.romeikat.datamessie.core.processing.service.stemming.text.KeywordAwareGermanNormalizationFilter.java

License:Open Source License

@Override
public boolean incrementToken() throws IOException {
    if (input.incrementToken()) {
        if (keywordAttr.isKeyword()) {
            return true;
        }/*from  w  w  w .  j ava2s. com*/

        int state = N;
        char buffer[] = termAtt.buffer();
        int length = termAtt.length();
        for (int i = 0; i < length; i++) {
            final char c = buffer[i];
            switch (c) {
            case 'a':
            case 'o':
                state = U;
                break;
            case 'u':
                state = (state == N) ? U : V;
                break;
            case 'e':
                if (state == U) {
                    length = StemmerUtil.delete(buffer, i--, length);
                }
                state = V;
                break;
            case 'i':
            case 'q':
            case 'y':
                state = V;
                break;
            case '\u00e4':
                buffer[i] = 'a';
                state = V;
                break;
            case '\u00f6':
                buffer[i] = 'o';
                state = V;
                break;
            case '\u00fc':
                buffer[i] = 'u';
                state = V;
                break;
            case '\u00df':
                buffer[i++] = 's';
                buffer = termAtt.resizeBuffer(1 + length);
                if (i < length) {
                    System.arraycopy(buffer, i, buffer, i + 1, (length - i));
                }
                buffer[i] = 's';
                length++;
                state = N;
                break;
            default:
                state = N;
            }
        }
        termAtt.setLength(length);
        return true;
    } else {
        return false;
    }
}

---

From source file:jp.ameba.elasticsearch.analysis.japanese.tiny.CJKWidthFilter.java

License:Apache License

public boolean incrementToken() throws IOException {
    if (input.incrementToken()) {
        char text[] = termAtt.buffer();
        int length = termAtt.length();
        for (int i = 0; i < length; i++) {
            final char ch = text[i];
            if (ch >= 0xFF01 && ch <= 0xFF5E) {
                // Fullwidth ASCII variants
                text[i] -= 0xFEE0;//from w  ww  .ja  va  2  s  . co m
            } else if (ch >= 0xFF65 && ch <= 0xFF9F) {
                // Halfwidth Katakana variants
                if ((ch == 0xFF9E || ch == 0xFF9F) && i > 0 && combine(text, i, length, ch)) {
                    length = StemmerUtil.delete(text, i--, length);
                } else {
                    text[i] = KANA_NORM[ch - 0xFF65];
                }
            }
        }
        termAtt.setLength(length);
        return true;
    } else {
        return false;
    }
}

---