C程序词频统计异常求助：文本与关键词对比并降序输出

需求与预期输出 #

需实现功能：读取用户指定的文本文件，与keyword.txt中的关键词对比，统计每个关键词的出现频率，并按降序输出。

预期输出格式：

euery 8
common 8
gaue 7
thankes 5
vnkle 4
growes 3
wag 3
seal 3
day 3
soft 3

当前代码 #

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#define MAX_FILENAME_LENGTH 256
#define MAX_TEXT_LENGTH 100000
#define MAX_KEYWORDS 100

// Structure to store keyword frequencies
typedef struct KeywordFrequency {
    char keyword[50];
    int frequency;
} KeywordFrequency;

// Compare function for sorting keyword frequencies
int compareKeywords(const void *a, const void *b) {
    return ((KeywordFrequency *)b)->frequency - ((KeywordFrequency *)a)->frequency;
}

int main() {
    char filename[MAX_FILENAME_LENGTH];
    char text[MAX_TEXT_LENGTH];
    KeywordFrequency keywords[MAX_KEYWORDS];
    int totalKeywords = 0;

    // Ask the user for the name of the text file
    printf("Enter the name of the text file: ");
    scanf("%s", filename);

    // Open and read the text file
    FILE *textFile = fopen(filename, "r");
    if (textFile == NULL) {
        printf("Error opening %s\n", filename);
        return 1;
    }

    // Read the content of the text file
    fread(text, 1, sizeof(text), textFile);
    fclose(textFile);

    // Open and read the keyword file
    FILE *keywordFile = fopen("keyword.txt", "r");
    if (keywordFile == NULL) {
        printf("Error opening keyword.txt\n");
        return 1;
    }

    // Initialize keyword frequencies
    while (fscanf(keywordFile, "%s", keywords[totalKeywords].keyword) != EOF) {
        keywords[totalKeywords].frequency = 0;
        totalKeywords++;
    }
    fclose(keywordFile);

    // Tokenize and compare the text with keywords
    char *token = strtok(text, " ");
    while (token != NULL) {
        for (int i = 0; i < totalKeywords; i++) {
            if (strcmp(token, keywords[i].keyword) == 0) {
                keywords[i].frequency++;
            }
        }
        token = strtok(NULL, " ");
    }

    // Sort keyword frequencies in descending order
    qsort(keywords, totalKeywords, sizeof(KeywordFrequency), compareKeywords);

    // Print the results in a table format
    printf("Keyword\tFrequency\n");
    for (int i = 0; i < totalKeywords; i++) {
        printf("%s\t%d\n", keywords[i].keyword, keywords[i].frequency);
    }

    return 0;
}

关键问题与修复方案 #

• 文本读取未添加字符串终止符：fread不会自动在读取的文本末尾添加\0，导致strtok无法正确识别字符串边界，引发错误分词或内存越界。修复代码：

  // 读取文本时预留1字节存放终止符
  size_t bytesRead = fread(text, 1, sizeof(text)-1, textFile);
  text[bytesRead] = '\0';
  

• 分词分隔符不完整：仅用空格作为分隔符，无法处理文本中的标点（如逗号、句号、换行），导致关键词与标点粘连（如euery.），无法匹配关键词。修复分隔符集合：

  char *token = strtok(text, " \n\t.,!?;:\"'");
  

• 关键词数组越界风险：未限制totalKeywords不超过MAX_KEYWORDS，若keyword.txt中关键词数量超过100，会导致数组越界。修复读取逻辑：

  while (totalKeywords < MAX_KEYWORDS && fscanf(keywordFile, "%s", keywords[totalKeywords].keyword) != EOF) {
      keywords[totalKeywords].frequency = 0;
      totalKeywords++;
  }
  

• 输出格式不符合预期：当前输出包含表头且用制表符分隔，与预期的“关键词+空格+频率”格式不符。修改输出代码：

  for (int i = 0; i < totalKeywords; i++) {
      printf("%s %d\n", keywords[i].keyword, keywords[i].frequency);
  }
  

内容的提问来源于stack exchange，提问作者kristian williams