uk.org.retep.util.string.Sentence Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of strings Show documentation
The newest version!
/*
 * Copyright (c) 1998-2010, Peter T Mount

 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 
 *   Redistributions of source code must retain the above copyright
 *   notice, this list of conditions and the following disclaimer.
 *
 *   Redistributions in binary form must reproduce the above copyright
 *   notice, this list of conditions and the following disclaimer in the
 *   documentation and/or other materials provided with the distribution.
 *
 *   Neither the name of the retep.org.uk nor the names of its contributors
 *   may be used to endorse or promote products derived from this software
 *   without specific prior written permission.
 *
 * 
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 * A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER
 * OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
package uk.org.retep.util.string;

import java.util.Arrays;
import javax.annotation.concurrent.NotThreadSafe;

/**
 *
 * @author peter
 */
@NotThreadSafe
public class Sentence
{

    private String original;
    private Integer mappings[];
    private String normalized;
    private String splitted[];

    /**
     *
     * @param original
     */
    public Sentence( String original )
    {
        this( original, null, null );
    }

    /**
     *
     * @param original
     * @param mappings
     * @param normalized
     */
    public Sentence( String original, Integer mappings[], String normalized )
    {
        setOriginal( original );
        setMappings( mappings );
        setNormalized( normalized );
    }

    /**
     *
     * @param obj
     * @return
     */
    @Override
    public boolean equals( Object obj )
    {
        if( obj == null || !(obj instanceof Sentence) )
        {
            return false;
        }
        Sentence compared = (Sentence) obj;
        return original.equals( compared.original ) &&
                Arrays.equals( mappings, compared.mappings ) &&
                normalized.equals( compared.normalized );
    }

    @Override
    public int hashCode()
    {
        return original.hashCode() ^ Arrays.hashCode( mappings ) ^ normalized.hashCode();
    }

    /**
     * Gets the number of individual words contained by the Sentence.
     * @return
     */
    public int length()
    {
        return splitted.length;
    }

    /**
     * Returns the normalized as an array of String words.
     * @return
     */
    public String[] normalized()
    {
        return splitted;
    }

    /**
     * Returns the normalised word at a specified position
     * @param index Word index
     * @return the word at the specified index
     */
    public String getWord( int index )
    {
        return splitted[index];
    }

    /**
     * Returns the normalised word at a specified position in uppercase
     * @param index Word index
     * @return the word at the specified index
     */
    public String getWordUppercase( int index )
    {
        String word = getWord( index );
        return word == null ? null : word.toUpperCase();
    }

    /**
     * Gets the (index)th word of the Sentence, in its normalized form.
     * @param index
     * @return
     */
    public String normalized( int index )
    {
        return splitted[index];
    }

    /**
     *
     * @param beginIndex
     * @param endIndex
     * @return
     */
    public String original( int beginIndex, int endIndex )
    {
//        beginIndex = Math.max( -1, Math.min( beginIndex, mappings.length-1 ) );
//        endIndex = Math.max( 0, Math.min( endIndex, mappings.length-1 ) );

        if( beginIndex < 0 )
        {
            throw new ArrayIndexOutOfBoundsException( beginIndex );
        }

        while( beginIndex >= 0 && mappings[beginIndex] == null )
        {
            beginIndex--;
        }

        int n = mappings.length;
        while( endIndex < n && mappings[endIndex] == null )
        {
            endIndex++;
        }

        if( endIndex >= n )
        {
            endIndex = n - 1;
        }

        return StringUtils.removeNonAlphaNumeric( original.substring(
                mappings[beginIndex], mappings[endIndex] + 1 ) );
    }

    /**
     * Returns a string representation of the Sentence. This is useful for printing the state of Sentence objects during tests.
     *
     * @return A string formed of three bracket-separated sections: the original sentence string, the normalized-to-original word mapping array, and the normalized string.
     */
    @Override
    public String toString()
    {
        return "[" + original + "]" + Arrays.toString( mappings ) + "[" + normalized + "]";
    }

    /**
     * Returns a trimmed version of the original Sentence string.
     *
     * @return A trimmed version of the original Sentence string.
     */
    public String trimOriginal()
    {
        return original.trim();
    }

    /**
     *
     * @return
     */
    public Integer[] getMappings()
    {
        return mappings;
    }

    /**
     *
     * @param mappings
     */
    public void setMappings( Integer[] mappings )
    {
        this.mappings = mappings;
    }

    /**
     * Gets the Sentence in its normalized form.
     * @return
     */
    public String getNormalised()
    {
        return normalized;
    }

    /**
     *
     * @param normalized
     */
    public void setNormalized( String normalized )
    {
        this.normalized = normalized;
        if( normalized != null )
        {
            splitted = normalized.trim().split( " " );
        }
    }

    /**
     * Gets the Sentence, in its original, unformatted form.
     * @return
     */
    public String getOriginal()
    {
        return original;
    }

    /**
     *
     * @param original
     */
    public void setOriginal( String original )
    {
        this.original = original;
    }
}