Question

这是我目前的代码：

unsigned long charcount = 0;
unsigned long wordcount = 0;
unsigned long linecount = 0;
int n;

for (; (n = getchar()) != EOF; ++charcount) {
    if (n == '\n')
        ++linecount;
    if (n == ' ' || n == '\n' || n == '\t')
        ++wordcount;
    printf("%lu %lu %lu\n", charcount, wordcount, linecount);
}

我认为这个代码存在一个问题，如果我正在阅读的文本文件由段落组成，因为换行符将它们分开，它们将被视为单词。我不确定如何修复它以便它们不算作单词。

Answer 1

使用指示符来指定您是否正在阅读单词或空格：

int isWord = 0;
while ((n = getchar()) != EOF) {
    if (isspace(n)) {
        if (n == '\n') ++linecount;
        if (isWord) {
           ++wordcount;
           isWord = 0;
        }
    }
    else {
        isWord = 1;
    }
}
if (isWord)
    ++wordcount;

Answer 2

考虑使用这些定义：

行开头：当前字符是第一个或上一个是'\n' 单词开头：当前字符不是空格，也不是第一个或前一个字符是分隔符（空格）。

此方法检测行/单词的开头。

unsigned long charcount = 0;
unsigned long wordcount = 0;
unsigned long linecount = 0;
int previous = '\n';
int n;

while ((n = getchar()) != EOF) {
  ++charcount;
  if (isspace(previous)) {
    if (!issspace(n))  ++wordcount;    // Beginning of word detected
    if (previous == '\n') ++linecount; // Beginning of line detected
  }
  previous = n;
}
printf("%lu %lu %lu\n", charcount, wordcount, linecount);

这种方法运作良好，包括以下条件：

多个空格被视为单个空格（分隔符）。
以空格开头的文件，不会丢弃字数。
以空格或不以空格结尾的文件不会丢弃字数。
最后一行不必以'\n'结尾。
零长度文件不是问题。
调整EOF次数不需要line/word个帖子。
word/line/char以外的ULONG_MAX长度限制。

OP代码详情

for (; (n = getchar()) != EOF; ++charcount) {

    // This fails to count the last line of a file should it lack a \n
    if (n == '\n')
        ++linecount;

    // This counts separator (white-space) occurrence.
    // Multiple spaces count as 2 words: not good
    // Files like "Hello" will count as 0 words: not good
    // Files like " Hello " will count as 2 words: not good
    if (n == ' ' || n == '\n' || n == '\t')
        ++wordcount;

    // Using `unsigned long` is good, maybe even `unsigned long long`.
    printf("%lu %lu %lu\n", charcount, wordcount, linecount);
}

OP它没有得到足够的＆＃34;单词＆＃34;。我们假设非字母是有效的单词分隔符。

unsigned long charcount = 0;
unsigned long wordcount = 0;
unsigned long linecount = 0;
int previous = '\n';
int n;

while ((n = getchar()) != EOF) {
  ++charcount;
  if (!isalpha(previous)) {
    if (previous == '\n') ++linecount; // Beginning of line detected
    if (isalpha(n))  ++wordcount;    // Beginning of word detected
  }
  previous = n;
}
printf("%lu %lu %lu\n", charcount, wordcount, linecount);

Answer 3

尝试将前一个char存储在变量中并进行比较。

unsigned long int charcount = 0;
unsigned long int wordcount = 0;
unsigned long int linecount = 0;
int n;
int prev='\n';

while ((n = getchar()) != EOF){
    charcount++;
    if (n == '\n' && prev != '\n'){
        linecount++;
    }
    if (n == ' ' || n == '\n' || n == '\t')
        wordcount++;
    }
    prev=n
}
printf( "%lu %lu %lu\n", charcount, wordcount, linecount );

C字数 - 处理段落

3 个答案: