1
我正在編寫一個C程序,以便找到某個字符串中最頻繁的n-gram。無法找到n-gram算法的泄漏
的n-gram中的是n項從文本的給定序列的
連續序列
然而,我有一個分段錯誤在功能most_freq_ngram
。
的參數,依次爲:
- 從中我要計算的n-gram
- 字符的文本
- 我想了n元語法的大小數字的文本計算
- 一個指向字符串最頻繁的n元
這裏是我的代碼:
#include <stdlib.h>
#include <ctype.h>
#include <stdio.h>
#include <stdarg.h>
#include <errno.h>
typedef struct nodo_t{
char* gram;
int count;
struct nodo_t * next;
} nodo_t;
typedef struct linked_list{
nodo_t * head;
} linked_list;
int compare_arrays(char * igram, char * list_gram, size_t ngram_len){
int i;
for(i=0;i<ngram_len;i++){
if(tolower(list_gram[i]) != tolower(igram[i])) return 0;
}
return 1;
}
void copy_array(char * igram, char * list_gram, size_t ngram_len){
int i;
for(i=0;i<ngram_len;i++)
list_gram[i] = tolower(igram[i]);
}
void add_gram(char * igram, linked_list * list, size_t ngram_len){
if(list == NULL){
list = malloc(sizeof(linked_list));
nodo_t* head = malloc(sizeof(nodo_t));
head->count = 1;
head->next = NULL;
head->gram = malloc(ngram_len * sizeof(char));
int i;
for(i=0;i<ngram_len;i++)
head->gram[i] = igram[i];
list->head = head;
}else{
nodo_t * sent = list->head;
int found = 0;
while(sent->next != NULL && !found){
//Check every element, otherwise add to que
int same = compare_arrays(igram, sent->gram, ngram_len);
if(same){
sent->count++;
found = 1;
}
sent = sent->next;
}
if(!found){
sent->next = malloc(sizeof(nodo_t));
sent = sent->next;
sent->next = NULL;
sent->count = 1;
copy_array(igram, sent->gram, ngram_len);
}
}
}
void most_freq_ngram(const char* text, size_t text_len, size_t ngram_len, char** ngram){
int i;
linked_list * list = NULL;
for(i=0;i<text_len - ngram_len +1;i++){
char igram[ngram_len+1];
int j;
int temp_i = i;
for(j=0;j<ngram_len;j++){
igram[j] = text[temp_i];
temp_i++;
}
igram[ngram_len] = '\0';
add_gram(igram, list, ngram_len);
}
//Check list for most frequent element
char * most_frequent = malloc(ngram_len * sizeof(char));
int frequency = 0;
nodo_t * sent = list->head;
if(sent == NULL){
int i;
for(i=0;i<ngram_len;i++)
most_frequent[i] = '\0';
return;
}
while(sent->next != NULL){
if(sent->count > frequency){
copy_array(sent->gram, most_frequent, ngram_len);
frequency = sent->count;
}
}
*ngram = most_frequent;
return ;
}
int main(){
size_t ngram_len = 2;
char *ngram = malloc((ngram_len+1) * sizeof(char));
size_t text_len = 5;
const char text[6] = {'a','a','a','a','a', '\0'};
most_freq_ngram(text, text_len, ngram_len, &ngram);
return 0;
}
你的問題標題是指「泄漏」,而你的問題的文本抱怨分段錯誤。無論如何,除了發生段錯誤的函數的名稱之外,您不會從調試會話中提供有用的信息。 – rici
'{'a','a','a','a','a','\ 0'}'是'「aaaaa」'。 – DyZ