Question

我是C语言的初学者，所以我想看一段代码，该代码包含对给定文件中的字符，单词和行数进行计数。我在下面的代码中发现了问题，但我不明白为什么我们必须在while循环后增加最后一个单词的单词和行数：if (characters > 0)...

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

int main() {
    FILE *file;
    char path[100];
    char ch;
    int characters, words, lines;

    /* Input path of files to merge to third file */
    printf("Enter source file path: ");
    scanf("%s", path);

    /* Open source files in 'r' mode */
    file = fopen(path, "r");

    /* Check if file opened successfully */
    if (file == NULL) {
        printf("\nUnable to open file.\n");
        printf("Please check if file exists and you have read privilege.\n");
        exit(EXIT_FAILURE);
    }

    /*
     * Logic to count characters, words and lines.
     */
    characters = words = lines = 0;
    while ((ch = fgetc(file)) != EOF) {
        characters++;

        /* Check new line */
        if (ch == '\n' || ch == '\0')
            lines++;

        /* Check words */
        if (ch == ' ' || ch == '\t' || ch == '\n' || ch == '\0')
            words++;
    }

    /* Increment words and lines for last word */
    if (characters > 0) {
        words++;
        lines++;
    }

    /* Print file statistics */
    printf("\n");
    printf("Total characters = %d\n", characters);
    printf("Total words      = %d\n", words);
    printf("Total lines      = %d\n", lines);

    /* Close files to release resources */
    fclose(file);

    return 0;
}

Answer 1

该程序存在一些问题：

ch必须定义为int，才能正确检测到EOF。

scanf("%s", path);

超长输入将溢出path并导致未定义的行为。还要检查返回值以检测无效的输入或文件的提前结束
```
if (scanf("%99s", path) != 1)
    return 1;
```
测试ch == '\0'以计算行数是有争议的。标准的wc Unix实用程序不会将空字节用作行分隔符。
if (ch == ' ' || ch == '\t' || ch == '\n' || ch == '\0')也不是检测单词边界的标准方法。 if (isspace(ch))更惯用。
单词计数错误：多个空格将计为多个单词！相反，您应该检测边界，即空格字符后跟非空格字符。
最后一个测试是解决上述问题的a脚尝试，但这还不够。如果流不以换行符结尾，则确实需要进行额外的测试以计算流的最后一个。

这是更正的版本：

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

int main() {
    FILE *file;
    char path[1024];
    int ch, last;
    long long int characters, words, lines;

    /* Input path of files to merge to third file */
    printf("Enter source file path: ");
    if (scanf("%255s", path) != 1) {
        printf("Invalid input\n");
        return EXIT_FAILURE;
    }

    /* Open source files in 'r' mode */
    file = fopen(path, "r");

    /* Check if file opened successfully */
    if (file == NULL) {
        printf("Unable to open file %s\n", path);
        printf("Please check if file exists and you have read privilege.\n");
        return EXIT_FAILURE;
    }

    /*
     * Logic to count characters, words and lines.
     */
    characters = words = lines = 0;
    last = '\n';
    while ((ch = fgetc(file)) != EOF) {
        characters++;

        /* Check new line */
        if (ch == '\n')
            lines++;

        /* Check words */
        if (!isspace(ch) && isspace(last))
            words++;

        last = ch;
    }

    /* Increment words and lines for last word */
    if (last != '\n') {
        lines++;
    }

    /* Print file statistics */
    printf("\n");
    printf("Total characters = %lld\n", characters);
    printf("Total words      = %lld\n", words);
    printf("Total lines      = %lld\n", lines);

    /* Close file to release resources */
    fclose(file);

    return 0;
}

Answer 2

将需要根据输入的输入文件是否以漂亮的换行符（'\ n'）结尾来调整输出。

对于在所有行（包括最后一行）都以'\ n'结尾的普通sain文本文件，请在循环后删除这些增量。

但是对于这些特殊情况，似乎需要对程序进行一些调试，这取决于您的定义。但我强烈建议使用Linux / Unix命令wc作为参考和决胜局。

用C代码计算文件中字符，单词和行的数量

2 个答案: