com.ibm.icu.text.FilteredNormalizer2 Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of virtdata-lib-realer Show documentation
With inspiration from other libraries
There is a newer version: 2.12.15
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
/*
*******************************************************************************
*   Copyright (C) 2009-2014, International Business Machines
*   Corporation and others.  All Rights Reserved.
*******************************************************************************
*/
package com.ibm.icu.text;

import java.io.IOException;

import com.ibm.icu.util.ICUUncheckedIOException;

/**
 * Normalization filtered by a UnicodeSet.
 * Normalizes portions of the text contained in the filter set and leaves
 * portions not contained in the filter set unchanged.
 * Filtering is done via UnicodeSet.span(..., UnicodeSet.SpanCondition.SIMPLE).
 * Not-in-the-filter text is treated as "is normalized" and "quick check yes".
 * This class implements all of (and only) the Normalizer2 API.
 * An instance of this class is unmodifiable/immutable.
 * @stable ICU 4.4
 * @author Markus W. Scherer
 */
public class FilteredNormalizer2 extends Normalizer2 {
    /**
     * Constructs a filtered normalizer wrapping any Normalizer2 instance
     * and a filter set.
     * Both are aliased and must not be modified or deleted while this object
     * is used.
     * The filter set should be frozen; otherwise the performance will suffer greatly.
     * @param n2 wrapped Normalizer2 instance
     * @param filterSet UnicodeSet which determines the characters to be normalized
     * @stable ICU 4.4
     */
    public FilteredNormalizer2(Normalizer2 n2, UnicodeSet filterSet) {
        norm2=n2;
        set=filterSet;
    }

    /**
     * {@inheritDoc}
     * @stable ICU 4.4
     */
    @Override
    public StringBuilder normalize(CharSequence src, StringBuilder dest) {
        if(dest==src) {
            throw new IllegalArgumentException();
        }
        dest.setLength(0);
        normalize(src, dest, UnicodeSet.SpanCondition.SIMPLE);
        return dest;
    }
    /**
     * {@inheritDoc}
     * @stable ICU 4.6
     */
    @Override
    public Appendable normalize(CharSequence src, Appendable dest) {
        if(dest==src) {
            throw new IllegalArgumentException();
        }
        return normalize(src, dest, UnicodeSet.SpanCondition.SIMPLE);
    }

    /**
     * {@inheritDoc}
     * @stable ICU 4.4
     */
    @Override
    public StringBuilder normalizeSecondAndAppend(
            StringBuilder first, CharSequence second) {
        return normalizeSecondAndAppend(first, second, true);
    }
    /**
     * {@inheritDoc}
     * @stable ICU 4.4
     */
    @Override
    public StringBuilder append(StringBuilder first, CharSequence second) {
        return normalizeSecondAndAppend(first, second, false);
    }

    /**
     * {@inheritDoc}
     * @stable ICU 4.6
     */
    @Override
    public String getDecomposition(int c) {
        return set.contains(c) ? norm2.getDecomposition(c) : null;
    }

    /**
     * {@inheritDoc}
     * @stable ICU 49
     */
    @Override
    public String getRawDecomposition(int c) {
        return set.contains(c) ? norm2.getRawDecomposition(c) : null;
    }

    /**
     * {@inheritDoc}
     * @stable ICU 49
     */
    @Override
    public int composePair(int a, int b) {
        return (set.contains(a) && set.contains(b)) ? norm2.composePair(a, b) : -1;
    }

    /**
     * {@inheritDoc}
     * @stable ICU 49
     */
    @Override
    public int getCombiningClass(int c) {
        return set.contains(c) ? norm2.getCombiningClass(c) : 0;
    }

    /**
     * {@inheritDoc}
     * @stable ICU 4.4
     */
    @Override
    public boolean isNormalized(CharSequence s) {
        UnicodeSet.SpanCondition spanCondition=UnicodeSet.SpanCondition.SIMPLE;
        for(int prevSpanLimit=0; prevSpanLimit