52 lines
2.3 KiB
C
52 lines
2.3 KiB
C
|
#ifndef INCLUDED_C_NLPNGRAMGRAPH_H
|
||
|
|
#define INCLUDED_C_NLPNGRAMGRAPH_H
|
||
|
|
|
||
|
|
#ifndef INCLUDED_C_UTF8_H
|
||
|
|
#include <c_utf8.h>
|
||
|
|
#endif /*INCLUDED_C_UTF8_H*/
|
||
|
|
|
||
|
|
/* ------------------------------------------------------------------------------------------------------------------ */
|
||
|
|
/* */
|
||
|
|
|
||
|
|
|
||
|
|
/* --- 1. N-gram 預測邊（記錄後續可能出現的單個字及頻次） --- */
|
||
|
|
typedef struct c_NgramEdge_t {
|
||
|
|
c_ucs4_t target_cp; /* 後續預測出的第 N 個字 */
|
||
|
|
c_size_t co_count; /* 該字在當前上下文後出現的次數 */
|
||
|
|
struct c_NgramEdge_t* next; /* 鄰接邊哈希衝突拉鏈 */
|
||
|
|
} c_NgramEdge_t;
|
||
|
|
|
||
|
|
/* --- 2. N-gram 上下文節點（代表長度為 N-1 的歷史狀態） --- */
|
||
|
|
typedef struct c_NgramNode_t {
|
||
|
|
c_ucs4_t* context; /* 歷史上下文陣列，長度為 N-1 */
|
||
|
|
c_size_t frequency; /* 該上下文總出現次數 */
|
||
|
|
|
||
|
|
c_NgramEdge_t** next_chars; /* 後續字哈希桶（動態分配） */
|
||
|
|
c_size_t relation_capacity; /* 邊哈希桶容量 */
|
||
|
|
|
||
|
|
struct c_NgramNode_t* next; /* 主哈希表衝突拉鏈指针（解決主桶碰撞） */
|
||
|
|
} c_NgramNode_t;
|
||
|
|
|
||
|
|
/* --- 3. 多元馬爾可夫鏈模型主控結構体 --- */
|
||
|
|
typedef struct {
|
||
|
|
c_NgramNode_t** buckets; /* 主哈希表（儲存所有不重複的歷史上下文狀態） */
|
||
|
|
c_size_t bucket_count; /* 主哈希桶大小 */
|
||
|
|
c_size_t n_value; /* 模型階數 N (例如：3 代表 Trigram 模型) */
|
||
|
|
c_size_t relation_default_capacity; /* 子節點邊哈希桶默認容量 */
|
||
|
|
c_size_t total_states; /* 記錄圖中唯一存在的歷史狀態總數 */
|
||
|
|
} c_NlpNgramGraph_t;
|
||
|
|
|
||
|
|
/* ------------------------------------------------------------------------------------------------------------------ */
|
||
|
|
/* */
|
||
|
|
|
||
|
|
c_err_t c_NlpNgramGraph_Init(c_NlpNgramGraph_t* self, c_size_t n_value, c_size_t bucket_count, c_size_t relation_default_capacity);
|
||
|
|
|
||
|
|
void c_NlpNgramGraph_Destroy(c_NlpNgramGraph_t* self);
|
||
|
|
|
||
|
|
c_err_t c_NlpNgramGraph_Process(c_NlpNgramGraph_t* self, const c_ucs4_t* unicode_array, c_size_t length);
|
||
|
|
|
||
|
|
c_err_t c_NlpNgramGraph_PredictNext(c_NlpNgramGraph_t* self, const c_ucs4_t* history_context,
|
||
|
|
c_ucs4_t* out_next_char, double* out_confidence);
|
||
|
|
|
||
|
|
#endif /*INCLUDED_C_NLPNGRAMGRAPH_H*/
|