Character.UnicodeBlock中cjk的说明

本文转载自:http://blog.csdn.net/imduan/article/details/54907998

CJK的意思是“Chinese，Japanese，Korea”的简写 ，实际上就是指中日韩三国的象形文字的Unicode编码

枚举说明

Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS ： 4E00-9FBF：CJK 统一表意符号

Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS ：F900-FAFF：CJK 兼容象形文字 Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A ：3400-4DBF：CJK 统一表意符号扩展 A

Character.UnicodeBlock.GENERAL_PUNCTUATION ：2000-206F：常用标点 Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION ：3000-303F：CJK 符号和标点 Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS ：FF00-FFEF：半角及全角形式

常用函数

/**
     * 校验一个字符是否是汉字
     * 
     * @param c
     *            被校验的字符
     * @return true代表是汉字
     */
    public static boolean isChineseChar(char c) {
        try {
            return String.valueOf(c).getBytes("UTF-8").length > 1;
        } catch (UnsupportedEncodingException e) {
            e.printStackTrace();
            return false;
        }
    }

    /**
     * 验证字符串内容是否包含下列非法字符

     * `~!#%^&*=+\\|{};:'\",<>/?○●★☆☉♀♂※¤╬の〆
     * 
     * @param content
     *            字符串内容
     * @return 't'代表不包含非法字符，otherwise代表包含非法字符。
     */
    public static char validateLegalString(String content) {
        String illegal = "`~!#%^&*=+\\|{};:'\",<>/?○●★☆☉♀♂※¤╬の〆";
        char isLegalChar = 't';
        L1: for (int i = 0; i < content.length(); i++) {
            for (int j = 0; j < illegal.length(); j++) {
                if (content.charAt(i) == illegal.charAt(j)) {
                    isLegalChar = content.charAt(i);
                    break L1;
                }
            }
        }
        return isLegalChar;
    }

    /**
     * 验证是否是汉字或者0-9、a-z、A-Z
     * 
     * @param c
     *            被验证的char
     * @return true代表符合条件
     */
    public static boolean isRightChar(char c) {
        return isChinese(c) || isWord(c);
    }

    /**
     * 校验某个字符是否是a-z、A-Z、_、0-9
     * 
     * @param c
     *            被校验的字符
     * @return true代表符合条件
     */
    public static boolean isWord(char c) {
        String regEx = "[\\w]";
        Pattern p = Pattern.compile(regEx);
        Matcher m = p.matcher("" + c);
        return m.matches();
    }

    /**
     * 判定输入的是否是汉字
     * 
     * @param c
     *            被校验的字符
     * @return true代表是汉字
     */
    public static boolean isChinese(char c) {
        Character.UnicodeBlock ub = Character.UnicodeBlock.of(c);
        if (ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
                || ub == Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS
                || ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A
                || ub == Character.UnicodeBlock.GENERAL_PUNCTUATION
                || ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
                || ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
            return true;
        }
        return false;
    }

    /**
     * 校验String是否全是中文
     * 
     * @param name
     *            被校验的字符串
     * @return true代表全是汉字
     */
    public static boolean checkNameChese(String name) {
        boolean res = true;
        char[] cTemp = name.toCharArray();
        for (int i = 0; i < name.length(); i++) {
            if (!isChinese(cTemp[i])) {
                res = false;
                break;
            }
        }
        return res;
    }