计算文件中的单词出现次数 C
Counting word occurrences in a file C
欢迎大家。我是 Whosebug 的新手,我用 C 编写代码有一段时间了。
我在编写计算文本文件中单词出现次数的程序时遇到 运行 问题。我需要一个输出,告诉我哪个词出现了多少次。这是源代码:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int new_words=0;
int nwords=0;
typedef struct element{
char word[30];
int how_many;
} element;
int is_word_new(element ** dictionary, char * string)
{
for (int i =0; i<new_words; i++)
{
if (strcmp(string, dictionary[i]->word)==0)
return 0;
}
return 1;
}
int which_word(element ** dictionary, char * string)
{
for (int i =0; i<new_words; i++)
{
if (strcmp(string, dictionary[i]->word)==0)
return i;
}
return 0;
}
int main()
{
FILE * fp;
char word[30];
fp=fopen("input.txt", "r");
if (fp==NULL)
{
printf("FILE ERROR");
return 0;
}
while(!feof(fp))
{
fscanf(fp, "%s",word);
nwords++;
}
nwords--;
rewind(fp);
struct element * dictionary = (element*)malloc(sizeof(element)*nwords);
for (int i =0; i<nwords; i ++)
{
fscanf(fp, "%s", word);
if( is_word_new(&dictionary, word) )
{
strcpy(dictionary[new_words].word, word);
//dictionary[new_words].word= word;
dictionary[new_words].how_many=1;
new_words++;
}
else
dictionary[which_word(&dictionary, word)].how_many++;
word[0]='[=10=]';
}
printf("\n\nFinal dictionary\n with %d words", new_words);
for (int i =0; i<new_words; i++)
{
printf("%s %d \n", dictionary[i].word, dictionary[i].how_many);
}
free(dictionary);
fclose(fp);
return 0;
}
我的想法是首先计算文本中有多少个单词(不知何故总是比实际多一个)。函数 is_word_new 检查字典中是否已经有新读到的单词。 which_word()
告诉找到了哪个词
但是我得到一个分段错误 运行 这个程序。
当我使用注释为 // dictionary[i].word=word
的行时,程序表现得好像字典中只有 "word"。
请提示我哪里做错了
必读问题:Why is “while ( !feof (file) )” always wrong?感谢 Jonathan Leffler 的评论。
请在下面的代码中查看我的评论。当单词出现一次时,我为您准备好了。我把剩下的工作交给你,这样我们就可以分享乐趣,但你当然可以问。
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int new_words = 0;
int nwords = 0;
typedef struct element {
char word[30];
int how_many;
} element;
// no need to pass double pointer
int is_word_new(element* dictionary, char * string) {
int i;
for (i = 0; i < new_words; i++) {
printf("|%s|, |%s|\n", string, dictionary[i].word);
if (strcmp(string, dictionary[i].word) == 0)
return 0;
printf("i=%d\n",i);
}
return 1;
}
int which_word(element ** dictionary, char * string) {
int i;
for (i = 0; i < new_words; i++) {
if (strcmp(string, dictionary[i]->word) == 0)
return i;
}
return 0;
}
int main() {
FILE * fp;
char word[30];
fp = fopen("test.txt", "r");
if (fp == NULL) {
printf("FILE ERROR");
return 0;
}
printf("file read\n");
int read_counter;
while (!feof(fp)) {
read_counter = fscanf(fp, "%s", word);
// increment only if we really read something
if(read_counter >= 0)
nwords++;
}
// this is wrong, remove it
//nwords--;
rewind(fp);
printf("nwords = %d\n", nwords);
// do not cast what malloc returns. Also struct is not needed.
element * dictionary = malloc(sizeof (element) * nwords);
int i;
for (i = 0; i < nwords; i++) {
fscanf(fp, "%s", word);
printf("read |%s|\n", word);
if (is_word_new(dictionary, word)) {
strcpy(dictionary[new_words].word, word);
//dictionary[new_words].word= word;
dictionary[new_words].how_many = 1;
new_words++;
} else {
printf("bhka\n");
dictionary[which_word(&dictionary, word)].how_many++;
}
//word[0] = '[=10=]';
}
printf("\n\nFinal dictionary\n with %d words", new_words);
for (i = 0; i < new_words; i++) {
printf("%s %d \n", dictionary[i].word, dictionary[i].how_many);
}
free(dictionary);
fclose(fp);
return 0;
}
这是我使用的test.txt:
sam klouvi george dit epfl
ok
end
欢迎大家。我是 Whosebug 的新手,我用 C 编写代码有一段时间了。 我在编写计算文本文件中单词出现次数的程序时遇到 运行 问题。我需要一个输出,告诉我哪个词出现了多少次。这是源代码:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int new_words=0;
int nwords=0;
typedef struct element{
char word[30];
int how_many;
} element;
int is_word_new(element ** dictionary, char * string)
{
for (int i =0; i<new_words; i++)
{
if (strcmp(string, dictionary[i]->word)==0)
return 0;
}
return 1;
}
int which_word(element ** dictionary, char * string)
{
for (int i =0; i<new_words; i++)
{
if (strcmp(string, dictionary[i]->word)==0)
return i;
}
return 0;
}
int main()
{
FILE * fp;
char word[30];
fp=fopen("input.txt", "r");
if (fp==NULL)
{
printf("FILE ERROR");
return 0;
}
while(!feof(fp))
{
fscanf(fp, "%s",word);
nwords++;
}
nwords--;
rewind(fp);
struct element * dictionary = (element*)malloc(sizeof(element)*nwords);
for (int i =0; i<nwords; i ++)
{
fscanf(fp, "%s", word);
if( is_word_new(&dictionary, word) )
{
strcpy(dictionary[new_words].word, word);
//dictionary[new_words].word= word;
dictionary[new_words].how_many=1;
new_words++;
}
else
dictionary[which_word(&dictionary, word)].how_many++;
word[0]='[=10=]';
}
printf("\n\nFinal dictionary\n with %d words", new_words);
for (int i =0; i<new_words; i++)
{
printf("%s %d \n", dictionary[i].word, dictionary[i].how_many);
}
free(dictionary);
fclose(fp);
return 0;
}
我的想法是首先计算文本中有多少个单词(不知何故总是比实际多一个)。函数 is_word_new 检查字典中是否已经有新读到的单词。 which_word()
告诉找到了哪个词
但是我得到一个分段错误 运行 这个程序。
当我使用注释为 // dictionary[i].word=word
的行时,程序表现得好像字典中只有 "word"。
请提示我哪里做错了
必读问题:Why is “while ( !feof (file) )” always wrong?感谢 Jonathan Leffler 的评论。
请在下面的代码中查看我的评论。当单词出现一次时,我为您准备好了。我把剩下的工作交给你,这样我们就可以分享乐趣,但你当然可以问。
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int new_words = 0;
int nwords = 0;
typedef struct element {
char word[30];
int how_many;
} element;
// no need to pass double pointer
int is_word_new(element* dictionary, char * string) {
int i;
for (i = 0; i < new_words; i++) {
printf("|%s|, |%s|\n", string, dictionary[i].word);
if (strcmp(string, dictionary[i].word) == 0)
return 0;
printf("i=%d\n",i);
}
return 1;
}
int which_word(element ** dictionary, char * string) {
int i;
for (i = 0; i < new_words; i++) {
if (strcmp(string, dictionary[i]->word) == 0)
return i;
}
return 0;
}
int main() {
FILE * fp;
char word[30];
fp = fopen("test.txt", "r");
if (fp == NULL) {
printf("FILE ERROR");
return 0;
}
printf("file read\n");
int read_counter;
while (!feof(fp)) {
read_counter = fscanf(fp, "%s", word);
// increment only if we really read something
if(read_counter >= 0)
nwords++;
}
// this is wrong, remove it
//nwords--;
rewind(fp);
printf("nwords = %d\n", nwords);
// do not cast what malloc returns. Also struct is not needed.
element * dictionary = malloc(sizeof (element) * nwords);
int i;
for (i = 0; i < nwords; i++) {
fscanf(fp, "%s", word);
printf("read |%s|\n", word);
if (is_word_new(dictionary, word)) {
strcpy(dictionary[new_words].word, word);
//dictionary[new_words].word= word;
dictionary[new_words].how_many = 1;
new_words++;
} else {
printf("bhka\n");
dictionary[which_word(&dictionary, word)].how_many++;
}
//word[0] = '[=10=]';
}
printf("\n\nFinal dictionary\n with %d words", new_words);
for (i = 0; i < new_words; i++) {
printf("%s %d \n", dictionary[i].word, dictionary[i].how_many);
}
free(dictionary);
fclose(fp);
return 0;
}
这是我使用的test.txt:
sam klouvi george dit epfl
ok
end