1 void traverseFileandCount(char* path, struct alphaArray* dictionary)
 2 {
 3     DIR *pDir; //定义一个DIR类的指针
 4     struct dirent *ent=NULL; //定义一个结构体 dirent的指针，dirent结构体见上
 5     int i = 0;
 6     char childpath[512]; //定义一个字符数组，用来存放读取的路径
 7     pDir = opendir(path); // opendir方法打开path目录，并将地址付给pDir指针
 8     memset(childpath, 0, sizeof(childpath)); //将字符数组childpath的数组元素全部置零
 9     while ((ent = readdir(pDir)) != NULL)
10         //读取pDir打开的目录，并赋值给ent, 同时判断是否目录为空，不为空则执行循环体
11     {
12         if (ent->d_type&DT_DIR)
13             /*读取 打开目录的文件类型 并与 DT_DIR进行位与运算操作，即如果读取的d_type类型为DT_DIR
14             (=4 表示读取的为目录)*/
15         {
16             if (strcmp(ent->d_name, ".") == 0 || strcmp(ent->d_name, "..") == 0)
17                 //如果读取的d_name为 . 或者.. 表示读取的是当前目录符和上一目录符,
18                 //则用contiue跳过，不进行下面的输出
19                 continue;
20             sprintf(childpath, "%s/%s", path, ent->d_name);
21             //如果非. ..则将 路径 和 文件名d_name 付给childpath, 并在下一行prinf输出
22             //printf("path:%s\n",childpath);原文链接这里是要打印出文件夹的地址
23             traverseFileandCount(childpath, dictionary);
24             //递归读取下层的字目录内容， 因为是递归，所以从外往里逐次输出所有目录（路径+目录名），
25             //然后才在else中由内往外逐次输出所有文件名
26         }
27         else
28             //如果读取的d_type类型不是 DT_DIR, 即读取的不是目录，而是文件，
29             //则直接输出 d_name, 即输出文件名
30         {
31             //cout<<ent->d_name<<endl; 输出文件名
32             //cout<<childpath<<"/"<<ent->d_name<<endl; 输出带有目录的文件名
33             sprintf(childpath, "%s/%s", path, ent->d_name);
34             //你可以唯一注意的地方是下一行
35             //目前childpath就是你要读入的文件的path了，可以作为你的读入文件的函数的参数
36             count(childpath, dictionary);//这里就是你的处理文件的接口！，
37         }
38     }
39 }

#define childPathLength 512//tranverse file recursively
void traverseFileandCount(char* path, struct alphaArray* dictionary)
{DIR *filePoint;struct dirent *fileInfo = BULL;char childPath[childPathLength];filePoint = opendir(path);memset(childPath,0,childPathLength);//init the childPath array with 0while((fileInfo=readdir(filePoint)) != NULL){if(isDirectory(fileInfo)){if(isPresentOrPriorDirectory(fileInfo))continue;sprintf(childpath, "%s/%s", path, ent->d_name);//create new path
            traverseFileandCount(childpath, dictionary);}else{sprintf(childpath, "%s/%s", path, ent->d_name);//create new path
            count(childpath, dictionary);}}
}bool isDirectory(struct dirent *fileInfo)
{return fileInfo->d_type&DT_DIR;
}bool isPresentOrPriorDirectory(struct dirent *fileInfo)
{return strcmp(ent->d_name, ".") == 0 || strcmp(ent->d_name, "..") == 0;
}

View Code

int main()
{char filePath[filePathLength];struct alphaArray dictionary[alphabet];struct wordStatisticsResult topFrequencyWord[topFrequencyWordNum];struct phaseStatisticsResult topFrequencyPhase[topFrequencyPhaseNum];dictionaryInit(dictionary);getFilePath(filePath);traverseFileandCount(filePath, dictionary);outputResult(dictionary);topFrequencyWordStatistics(dictionary, topFrequencyWord);topFrequencyPhaseStatistics(dictionary, topFrequencyPhase);outputToFile(filePath,topFrequencyWord, topFrequencyPhase);dictionaryDestroy(dictionary);return 0;
}

View Code

(page->wordArray + hash)->wordStr = (char*)realloc((page->wordArray + hash)->wordStr, sizeof(char)*((page->wordArray + hash)->strlength) * 2);

View Code