lang之Charater

最新推荐文章于 2024-07-18 11:02:34 发布

ahcen001

最新推荐文章于 2024-07-18 11:02:34 发布

阅读量584

点赞数

分类专栏：专题技术--语言学习文章标签： c

本文链接：https://blog.csdn.net/ahcen001/article/details/769061

版权

专题技术--语言学习专栏收录该内容

6 篇文章 0 订阅

订阅专栏

1,Character.Subset 和Character.UnicodeBlock ，其中Character.Subset类用于描述Unicode编码的一个子集，而Character.UnicodeBlock类中包含了Unicode 2.0编码的字符块。

static int codePointAt(CharSequence seq, int index)

public static final char MIN_HIGH_SURROGATE = '/uD800';

public static final char MIN_LOW_SURROGATE = '/uDC00';

public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;

public static int toCodePoint(char high, char low) {
        return ((high - MIN_HIGH_SURROGATE) << 10)
            + (low - MIN_LOW_SURROGATE) + MIN_SUPPLEMENTARY_CODE_POINT;
    }

public static int codePointAt(CharSequence seq, int index) {
        char c1 = seq.charAt(index++);
        if (isHighSurrogate(c1)) {
            if (index < seq.length()) {
                char c2 = seq.charAt(index);
                if (isLowSurrogate(c2)) {
                    return toCodePoint(c1, c2);
                }
            }
        }
        return c1;
    }