Segmentation fault在gcc -O中发生。

huangapple
go评论87阅读模式
英文:

Segmentation fault occurs in gcc -O

问题

我写了这段代码来返回.txt文件中出现频率最高的前n个单词：

  1. #include <stdio.h>
  2. #include <stdlib.h>
  3. #include <string.h>
  5. #define MAX_WORD_LENGTH 100
  6. #define MAX_LINE_LENGTH 1000
  8. struct WordFrequency {
  9.     char word[MAX_WORD_LENGTH];
  10.     int frequency;
  11. };
  13. char** find_frequent_words(const char* path, int32_t n) {
  14.     FILE* file = fopen(path, "r");
  15.     if (file == NULL) {
  16.         fprintf(stderr, "Failed to open file: %s\n", path);
  17.         return NULL;
  18.     }
  20.     // 创建哈希表来统计单词频率
  21.     struct WordFrequency* wordFrequencies = NULL;
  22.     int uniqueWordCount = 0;
  23.     int maxWordCount = 10000;
  25.     char line[MAX_LINE_LENGTH];
  26.     while (fgets(line, sizeof(line), file) != NULL) {
  27.         char* word = strtok(line, " \t\n");
  28.         while (word != NULL) {
  29.             int existingIndex = -1;
  30.             for (int i = 0; i < uniqueWordCount; i++) {
  31.                 if (strcmp(wordFrequencies[i].word, word) == 0) {
  32.                     existingIndex = i;
  33.                     break;
  34.                 }
  35.             }
  37.             if (existingIndex >= 0) {
  38.                 wordFrequencies[existingIndex].frequency++;
  39.             } else {
  40.                 if (uniqueWordCount == maxWordCount) {
  41.                     // 增加单词频率数组的大小
  42.                     maxWordCount *= 2;
  43.                     struct WordFrequency* newWordFrequencies = realloc(
  44.                         wordFrequencies, maxWordCount * sizeof(struct WordFrequency)
  45.                     );
  46.                     if (newWordFrequencies == NULL) {
  47.                         fprintf(stderr, "内存分配失败。\n");
  48.                         fclose(file);
  49.                         free(wordFrequencies);
  50.                         return NULL;
  51.                     }
  52.                     wordFrequencies = newWordFrequencies;
  53.                 }
  54.                 strncpy(wordFrequencies[uniqueWordCount].word, word, sizeof(wordFrequencies[uniqueWordCount].word) - 1);
  55.                 wordFrequencies[uniqueWordCount].word[sizeof(wordFrequencies[uniqueWordCount].word) - 1] = '\0';
  56.                 wordFrequencies[uniqueWordCount].frequency = 1;
  57.                 uniqueWordCount++;
  58.             }
  60.             word = strtok(NULL, " \t\n");
  61.         }
  62.     }
  64.     fclose(file);
  66.     // 按降序对单词频率进行排序
  67.     for (int i = 0; i < uniqueWordCount - 1; i++) {
  68.         for (int j = 0; j < uniqueWordCount - i - 1; j++) {
  69.             if (wordFrequencies[j].frequency < wordFrequencies[j + 1].frequency) {
  70.                 struct WordFrequency temp = wordFrequencies[j];
  71.                 wordFrequencies[j] = wordFrequencies[j + 1];
  72.                 wordFrequencies[j + 1] = temp;
  73.             }
  74.         }
  75.     }
  77.     // 创建包含最常见单词的结果数组
  78.     int resultCount = (n < uniqueWordCount) ? n : uniqueWordCount;
  79.     char** frequentWords = malloc((resultCount + 1) * sizeof(char*));
  80.     if (frequentWords == NULL) {
  81.         fprintf(stderr, "内存分配失败。\n");
  82.         free(wordFrequencies);
  83.         return NULL;
  84.     }
  86.     for (int i = 0; i < resultCount; i++) {
  87.         frequentWords[i] = strdup(wordFrequencies[i].word);
  88.         if (frequentWords[i] == NULL) {
  89.             fprintf(stderr, "内存分配失败。\n");
  90.             for (int j = 0; j < i; j++) {
  91.                 free(frequentWords[j]);
  92.             }
  93.             free(frequentWords);
  94.             free(wordFrequencies);
  95.             return NULL;
  96.         }
  97.     }
  98.     frequentWords[resultCount] = NULL;
  100.     free(wordFrequencies);
  102.     return frequentWords;
  103. }
  105. int main(int argc, char* argv[]) {
  106.     if (argc < 3) {
  107.         fprintf(stderr, "用法：%s <file_path> <n>\n", argv[0]);
  108.         return 1;
  109.     }
  111.     const char* path = argv[1];
  112.     int32_t n = atoi(argv[2]);
  113.     if (n <= 0) {
  114.         fprintf(stderr, "n的值无效：%s\n", argv[2]);
  115.         return 1;
  116.     }
  118.     char** frequentWords = find_frequent_words(path, n);
  119.     if (frequentWords == NULL) {
  120.         return 1;
  121.     }
  123.     printf("前%d个最常见的单词：\n", n);
  124.     for (int i = 0; frequentWords[i] != NULL; i++) {
  125.         printf("%s\n", frequentWords[i]);
  126.     }
  128.     // 释放为frequentWords数组及其元素分配的内存
  129.     for (int i = 0; frequentWords[i] != NULL; i++) {
  130.         free(frequentWords[i]);
  131.     }
  132.     free(frequentWords);
  134.     return 0;
  135. }

这是我如何编译和运行它的方式：

  1. gcc -o frequent_words frequent_words.c
  2. ./frequent_words tiny_shakespeare.txt 5

但是我得到了以下错误：

  1. Segmentation fault (core dumped)

我不知道哪一行引起了这个错误。我做错了什么？

英文:

I wrote this code to return the top n most frequent words in a .txt file:

  1. #include &lt;stdio.h&gt;
  2. #include &lt;stdlib.h&gt;
  3. #include &lt;string.h&gt;
  4. #define MAX_WORD_LENGTH 100
  5. #define MAX_LINE_LENGTH 1000
  6. struct WordFrequency {
  7. char word[MAX_WORD_LENGTH];
  8. int frequency;
  9. };
  10. char** find_frequent_words(const char* path, int32_t n) {
  11. FILE* file = fopen(path, &quot;r&quot;);
  12. if (file == NULL) {
  13. fprintf(stderr, &quot;Failed to open file: %s\n&quot;, path);
  14. return NULL;
  15. }
  16. // Create a hash table to count word frequencies
  17. struct WordFrequency* wordFrequencies = NULL;
  18. int uniqueWordCount = 0;
  19. int maxWordCount = 10000;
  20. char line[MAX_LINE_LENGTH];
  21. while (fgets(line, sizeof(line), file) != NULL) {
  22. char* word = strtok(line, &quot; \t\n&quot;);
  23. while (word != NULL) {
  24. int existingIndex = -1;
  25. for (int i = 0; i &lt; uniqueWordCount; i++) {
  26. if (strcmp(wordFrequencies[i].word, word) == 0) {
  27. existingIndex = i;
  28. break;
  29. }
  30. }
  31. if (existingIndex &gt;= 0) {
  32. wordFrequencies[existingIndex].frequency++;
  33. } else {
  34. if (uniqueWordCount == maxWordCount) {
  35. // Increase the size of the word frequencies array
  36. maxWordCount *= 2;
  37. struct WordFrequency* newWordFrequencies = realloc(
  38. wordFrequencies, maxWordCount * sizeof(struct WordFrequency)
  39. );
  40. if (newWordFrequencies == NULL) {
  41. fprintf(stderr, &quot;Memory allocation failed.\n&quot;);
  42. fclose(file);
  43. free(wordFrequencies);
  44. return NULL;
  45. }
  46. wordFrequencies = newWordFrequencies;
  47. }
  48. strncpy(wordFrequencies[uniqueWordCount].word, word, sizeof(wordFrequencies[uniqueWordCount].word) - 1);
  49. wordFrequencies[uniqueWordCount].word[sizeof(wordFrequencies[uniqueWordCount].word) - 1] = &#39;\0&#39;;
  50. wordFrequencies[uniqueWordCount].frequency = 1;
  51. uniqueWordCount++;
  52. }
  53. word = strtok(NULL, &quot; \t\n&quot;);
  54. }
  55. }
  56. fclose(file);
  57. // Sort word frequencies in descending order
  58. for (int i = 0; i &lt; uniqueWordCount - 1; i++) {
  59. for (int j = 0; j &lt; uniqueWordCount - i - 1; j++) {
  60. if (wordFrequencies[j].frequency &lt; wordFrequencies[j + 1].frequency) {
  61. struct WordFrequency temp = wordFrequencies[j];
  62. wordFrequencies[j] = wordFrequencies[j + 1];
  63. wordFrequencies[j + 1] = temp;
  64. }
  65. }
  66. }
  67. // Create the result array with the most frequent words
  68. int resultCount = (n &lt; uniqueWordCount) ? n : uniqueWordCount;
  69. char** frequentWords = malloc((resultCount + 1) * sizeof(char*));
  70. if (frequentWords == NULL) {
  71. fprintf(stderr, &quot;Memory allocation failed.\n&quot;);
  72. free(wordFrequencies);
  73. return NULL;
  74. }
  75. for (int i = 0; i &lt; resultCount; i++) {
  76. frequentWords[i] = strdup(wordFrequencies[i].word);
  77. if (frequentWords[i] == NULL) {
  78. fprintf(stderr, &quot;Memory allocation failed.\n&quot;);
  79. for (int j = 0; j &lt; i; j++) {
  80. free(frequentWords[j]);
  81. }
  82. free(frequentWords);
  83. free(wordFrequencies);
  84. return NULL;
  85. }
  86. }
  87. frequentWords[resultCount] = NULL;
  88. free(wordFrequencies);
  89. return frequentWords;
  90. }
  91. int main(int argc, char* argv[]) {
  92. if (argc &lt; 3) {
  93. fprintf(stderr, &quot;Usage: %s &lt;file_path&gt; &lt;n&gt;\n&quot;, argv[0]);
  94. return 1;
  95. }
  96. const char* path = argv[1];
  97. int32_t n = atoi(argv[2]);
  98. if (n &lt;= 0) {
  99. fprintf(stderr, &quot;Invalid value for n: %s\n&quot;, argv[2]);
  100. return 1;
  101. }
  102. char** frequentWords = find_frequent_words(path, n);
  103. if (frequentWords == NULL) {
  104. return 1;
  105. }
  106. printf(&quot;The %d most frequent words:\n&quot;, n);
  107. for (int i = 0; frequentWords[i] != NULL; i++) {
  108. printf(&quot;%s\n&quot;, frequentWords[i]);
  109. }
  110. // Free the memory allocated for the frequentWords array and its elements
  111. for (int i = 0; frequentWords[i] != NULL; i++) {
  112. free(frequentWords[i]);
  113. }
  114. free(frequentWords);
  115. return 0;
  116. }

And this is how I'm compiling and running it:

  1. gcc -o frequent_words frequent_words.c
  2. ./frequent_words tiny_shakespeare.txt 5

But this is the error I'm getting:

  1. Segmentation fault (core dumped)

I don't know what line is causing this. Where am I going wrong?

答案1

得分: 2

It segfaults on:

  1. strncpy(wordFrequencies[uniqueWordCount].word, word, sizeof(wordFrequencies[uniqueWordCount].word) - 1);

as wordFrequencies == NULL because you only allocate space in the array when uniqueWordCount == maxWordCount. I suggest you initialize maxWordCount to the correct capacity:

  1. #define INITIAL_WORD_COUNT 10000
  2. // ...
  3. int maxWordCount = 0;
  4. // ...
  5. if (uniqueWordCount == maxWordCount) {
  6.     // Increase the size of the word frequencies array
  7.     maxWordCount = maxWordCount ? 2 * maxWordCount : INITIAL_WORD_COUNT;

Consider eliminating the batch logic and just grow it one entry at a time. If it's a proven performance issue then reintroduce the batch logic.

英文:

It segfaults on:

  1.  strncpy(wordFrequencies[uniqueWordCount].word, word, sizeof(wordFrequencies[uniqueWor
  2. dCount].word) - 1);

as wordFrequencies == NULL because you only allocate space in the array when uniqueWordCount == maxWordCount. I suggest you initialize maxWordCount to the correct capacity:

  1. #define INITIAL_WORD_COUNT 10000
  2. // ...
  3. int maxWordCount = 0;
  4. // ...
  5. if (uniqueWordCount == maxWordCount) {
  6. // Increase the size of the word frequencies array
  7. maxWordCount = maxWordCount ? 2 * maxWordCount : INITIAL_WORD_COUNT;

Consider eliminating the batch logic and just grow it one entry at a time. If it's a proven performance issue then reintroduce the batch logic.

huangapple
  • 本文由 发表于 2023年5月25日 12:07:35
  • 转载请务必保留本文链接：https://go.coder-hub.com/76328865.html
  • c
  • gcc
  • segmentation-fault
匿名

发表评论

匿名网友

:?: :razz: :sad: :evil: :!: :smile: :oops: :grin: :eek: :shock: :???: :cool: :lol: :mad: :twisted: :roll: :wink: :idea: :arrow: :neutral: :cry: :mrgreen:

确定