Java中的字符串的中英文处理

最新推荐文章于 2023-03-07 14:50:09 发布

Ghost_war

最新推荐文章于 2023-03-07 14:50:09 发布

阅读量917

点赞数

分类专栏： Java 文章标签： java string

本文链接：https://blog.youkuaiyun.com/Ghost_war/article/details/52672711

版权

Java 专栏收录该内容

9 篇文章

订阅专栏

本文介绍了一种去除字符串中数字的方法，并展示了如何将汉字与英文进行分离的技术细节。通过对字符串进行字符数组处理，实现了去除数字、提取中文标题以及分离中文与英文的功能。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

/**
     * 除去数字
     * 
     * @param title
     * @return
     */
    private static String parseTitle(String title) {

        char[] charArray = title.toCharArray();
        char[] chars = null;// 除去数字后的数组
        for (int i = 0; i < charArray.length; i++) {
            char c = charArray[i];
            if (isChinese(c) || Character.isLetter(c)) {
                chars = new char[charArray.length - i];
                System.arraycopy(charArray, i, chars, 0, charArray.length - i);
                break;
            }
        }
        return new String(chars);
    }

    /**
     * 汉字在前，英文在后
     * @param title
     * @return
     */
    public static String getCNTitle(String title) {

        char[] chars = title.toCharArray();
        char[] result = null;
        int length = chars.length;

        for (int i = length - 1; i >= 0; i--) {
            char c = chars[i];
            if (isChinese(c)) {
                char cc = chars[i + 1];
                if (Character.isDigit(cc)) {
                    result = new char[i + 2];
                    System.arraycopy(chars, 0, result, 0, i + 2);
                    break;
                } else {
                    result = new char[i + 1];
                    System.arraycopy(chars, 0, result, 0, i + 1);
                    break;
                }
            }
        }
        String s = new String(result);
        return replaceBlank(s);

    }

    public static String getENTitle(String title) {
        char[] chars = title.toCharArray();
        char[] result = null;
        int length = chars.length;

        for (int i = length - 1; i >= 0; i--) {
            char c = chars[i];
            if (isChinese(c)) {
                char cc = chars[i + 1];
                if (Character.isDigit(cc)) {
                    result = new char[length - i - 2];
                    System.arraycopy(chars, i + 2, result, 0, length - i - 2);
                    break;
                } else {
                    result = new char[length - i - 1];
                    System.arraycopy(chars, i + 1, result, 0, length - i - 1);
                    break;
                }
            }
        }
        String s = new String(result);
        return replaceBlank(s);
    }

    private static String replaceBlank(String s) {
        Pattern p = Pattern.compile("\\s*|\t|\r|\n");
        Matcher m = p.matcher(s);
        String after = m.replaceAll("");
        return after;
    }

    private 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.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B
                || ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
                || ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS
                || ub == Character.UnicodeBlock.GENERAL_PUNCTUATION) {
            return true;
        }
        return false;
    }