c_NlpCharGraph: 分析一篇文章,建立字与字的关系
c_NlpNgramGraph: 基于 n 个已经出现的词,预估后续可能出现的词 c_NlpLanguageModel: 如果有的词组合形式没有出现过,找到之前学习过最长类似的词句进行预测
This commit is contained in:
@@ -5,6 +5,14 @@
|
||||
#include <c_Base.h>
|
||||
#endif /*INCLUDED_C_BASE_H*/
|
||||
|
||||
/* ------------------------------------------------------------------------------------------------------------------ */
|
||||
/* */
|
||||
|
||||
#ifndef C_UNICODE_MAX
|
||||
#define C_UNICODE_MAX 0x10FFFFU
|
||||
#endif
|
||||
|
||||
|
||||
/* ------------------------------------------------------------------------------------------------------------------ */
|
||||
/* */
|
||||
|
||||
@@ -15,6 +23,14 @@ typedef uint16_t c_uint16_t;
|
||||
/* ------------------------------------------------------------------------------------------------------------------ */
|
||||
/* */
|
||||
|
||||
C_STATIC_FORCE_INLINE
|
||||
bool c_is_valid_unicode(uint32_t code) {
|
||||
// Unicode 码点不能超过 0x10FFFF,且必须排除 UTF-16 代理对范围 (0xD800 ~ 0xDFFF)
|
||||
if (code > C_UNICODE_MAX) return false;
|
||||
if (code >= 0xD800 && code <= 0xDFFF) return false;
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* @brief 获取一个 UTF-8 字符在当前指针位置所占用的实际字节数 (1 ~ 4 字节)
|
||||
*/
|
||||
|
||||
Reference in New Issue
Block a user