/*
 * [TestUTF8Diff.java]
 *
 * Summary: Discover how a UTF-8 and ISO_8859-1 differ in the encoding of char x0000..0xffff.
 *
 * Copyright: (c) 2009-2017 Roedy Green, Canadian Mind Products, http://mindprod.com
 *
 * Licence: This software may be copied and used freely for any purpose but military.
 *          http://mindprod.com/contact/nonmil.html
 *
 * Requires: JDK 1.8+
 *
 * Created with: JetBrains IntelliJ IDEA IDE http://www.jetbrains.com/idea/
 *
 * Version History:
 *  1.0 2011-01-14
 */
package com.mindprod.test;

import com.mindprod.common18.EIO;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.nio.charset.Charset;

/**
 * Discover how a UTF-8 and ISO_8859-1 differ in the encoding of char x0000..0xffff.
 *
 * @author Roedy Green, Canadian Mind Products
 * @version 1.0 2011-01-14
 * @since 2011-01-14
 */
public final class TestUTF8Diff
    {
    /**
     * encoding for iso-8859-1
     */
    public static final Charset ISO88591Charset = Charset.forName( "ISO-8859-1" );

    /**
     * Write a sample file in the given encoding
     *
     * @throws java.io.IOException on I/O failure.
     */
    private static void writeSampleFile( String filename, Charset encoding ) throws IOException
        {
        // O P E N for write
        FileOutputStream fos = new FileOutputStream( new File( filename ), false/* no append */ );
        OutputStreamWriter osw = new OutputStreamWriter( fos, encoding );
        // W R I T E
        for ( char c = 0; c < 4096; c++ )
            {
            if ( c % 64 == 0 )
                {
                osw.write( '\n' );
                }
            osw.write( c );
            }
        // C L O S E
        osw.close();
        }

    /**
     * Discover how a UTF-8 and ISO_8859-1 differ in the encoding of char x0000..0xffff.
     *
     * @param args not used
     *
     * @throws java.io.IOException on I/O failure
     */
    public static void main( String[] args ) throws IOException
        {
        writeSampleFile( "C:/temp/temputf8.txt", EIO.UTF8 );
        writeSampleFile( "C:/temp/tempiso88591", ISO88591Charset );
        // If you compare the output files, you see UTF-8 and ISO-8859-1 encode 7 bit characters identically,
        // 0x00 .. 0x7f,
        // but after than that are quite different.
        }
    }