/*
 * [IniCharCategory.java]
 *
 * Summary: top level enum to define the categories of character for the CSVTokenizer.
 *
 * Copyright: (c) 2004-2017 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:
 *  3.1 2009-04-12 shorter style names, improved highlighting.
 */
package com.mindprod.jprep;

/**
 * top level enum to define the categories of character for the CSVTokenizer.
 *
 * @author Roedy Green, Canadian Mind Products
 * @version 3.1 2009-04-12 shorter style names, improved highlighting.
 * @since 2004-05-15
 */
@SuppressWarnings( { "EnumeratedConstantNamingConvention" } )
public enum IniCharCategory
    {
        /**
         * ]
         */
        BRACKET_CLOSE,
        /**
         * [
         */
        BRACKET_OPEN,
        /**
         * End of line character
         */
        EOL,
        /**
         * equals
         */
        EQUALS,
        /**
         * ignore control chars
         */
        IGNORE,
        /**
         * ordinary chars, including punct, ", space, high ascii, unicode
         */
        ORDINARY,
        /**
         * "
         */
        QUOTE,
        /**
         * ; comment start , sometimes #
         */
        START_COMMENT,;

    /**
     * char that introduces a comment. EOL terminates it.  ';' or '#'
     */
    private static char commentChar = ';';

    /**
     * Categorise one character
     *
     * @param theChar character to categorise
     *
     * @return category code, e.g. PLAIN QUOTE
     */
    static IniCharCategory categorise( char theChar )
        {
        switch ( theChar )
            {
            case ']':
                return BRACKET_CLOSE;
            case '[':
                return BRACKET_OPEN;
            case '\n':
                return EOL;
            case '=':
                return EQUALS;
            case '\r':
            case 127:
            case 0xfeff: /* bom */
            case 0xfffd: /* replaced bom */
                return IGNORE;
            case ' ':
            case 0xa0://  
                return ORDINARY;
            case '\"':
                return QUOTE;
            default:
                if ( 0 <= theChar && theChar <= 31 )
                    {
                    return IGNORE;
                    }
                else
                    {
                    return theChar == commentChar ? START_COMMENT : ORDINARY;
                    }
            } // end switch
        } // end categorise

    /**
     * set comment introducer
     *
     * @param commentChar, either ';' or '#'
     */
    static void setCommentChar( char commentChar )
        {
        IniCharCategory.commentChar = commentChar;
        }
    } // end IniCharCategory