extern void testEtagsInvocation (void)
{
char* const execName = eStrdup (getExecutableName ());
char* const etags = eStrdup (ETAGS);
#ifdef CASE_INSENSITIVE_FILENAMES
toLowerString (execName);
toLowerString (etags);
#endif
if (strstr (execName, etags) != NULL)
{
verbose ("Running in etags mode\n");
setEtagsMode ();
}
}
// cleanWord()
// Requires: std::string reference
// Returns: None
// Trims end of line characters, leading spaces, and trailing spaces
// from the passed string reference. After that, it transforms the
// word to lower case for consistent matching.
void cleanWord(std::string &s) {
// Small chance of getting empty string, so don't check here every time.
trimEndOfLine(s);
trimLeadingWhitespace(s);
trimTrailingWhitespace(s);
toLowerString(s);
}
bool compareStringWildcard(std::string source, std::string mod, bool ignCase)
{
for (auto iter = mod.begin(); iter != mod.end();)
{
auto next = iter + 1;
if (*iter == '*' && next != mod.end() && *next == '*')
{
iter = mod.erase(iter);
continue;
}
iter++;
}
if (ignCase)
{
mod = toLowerString(mod);
source = toLowerString(source);
}
std::vector<std::pair<std::string::size_type, std::string::size_type>> stk;
stk.reserve(10);
stk.push_back(std::make_pair(0, 0));
return compareStringWildcard(stk, source, mod) != 0;
}
string Util::get_file_signature(string file_path)
{
int fd;
long file_size = 0;
char file_size_char[FILESIZE_CHARLEN]; // 文件大小
struct stat file_info;
const char* file_path_char = file_path.c_str();
string file_signature;
char md5_result[MD5SUM_CHARLEN];
char buf[READ_BLOCK];
if( stat(file_path_char, &file_info) != -1)
{
/**
S_ISREG是否是一个常规文件.
S_ISLNK(st_mode):是否是一个连接.
S_ISDIR是否是一个目录.
S_ISCHR是否是一个字符设备.
S_ISBLK是否是一个块设备.
S_ISFIFO是否是一个FIFO文件.
S_ISSOCK是否是一个SOCKET文件.
*/
if(S_ISREG(file_info.st_mode))
{
file_size = (long)file_info.st_size;
sprintf(file_size_char, "%ld ", file_size);
}
else
{
file_signature = file_path;
file_signature.append(" is not a regular file");
return file_signature;
}
}
else
{
return strerror(errno);
}
fd = open(file_path_char, O_RDONLY);
if(file_size <= SMALL_FILE)
{
get_md5sum(fd, file_size, md5_result, buf);
strncat(md5_result, "_", 2);
file_signature = md5_result;
file_signature.append(file_size_char);
}
else
{
get_md5sum(fd, FILE_BLOCK, md5_result, buf);
strncat(md5_result, "_", 2);
file_signature = md5_result;
lseek(fd, file_size / 2, SEEK_SET);
get_md5sum(fd, FILE_BLOCK, md5_result, buf);
strncat(md5_result, "_", 2);
file_signature.append(md5_result);
lseek(fd, -FILE_BLOCK , SEEK_END);
get_md5sum(fd, FILE_BLOCK, md5_result, buf);
strncat(md5_result, "_", 2);
file_signature.append(md5_result);
file_signature.append(file_size_char);
}
close(fd);
toLowerString(file_signature);
return file_signature;
}
int main(int argc, char *argv[])
{
if (argc != 2) {
std::cout << "Please specify exactly one parameter, the filename, if necessary with the full path." << std::endl;
system("PAUSE");
return 1;
}
std::string curFilePath = argv[1]; // kompletter Dateiname mit Pfad
std::string curFileName = curFilePath.substr( curFilePath.find_last_of("\\") + 1 ); // nur Dateiname
std::cout << "Working real hard ..." << std::endl << std::endl;
#ifdef WIN32
// für die Perfomancemessung
long long frequency, startTime, stopTime;
double timeTaken, timeScale;
bool counterAvailable = false;
// falls vorhanden den richtig schnellen timer
if ( QueryPerformanceFrequency( (LARGE_INTEGER*) &frequency) ) {
counterAvailable = true;
timeScale = 1.0/frequency;
QueryPerformanceCounter( (LARGE_INTEGER*) &startTime);
} else {
// sonst den "langsamen" (auflösung 1ms)
startTime = GetTickCount();
timeScale = 0.001;
}
#endif
cWoerterbuch *myWoerterbuch = new cWoerterbuch();
cIndexer *myIndexer = new cIndexer(myWoerterbuch);
int myLoadResult = myIndexer->loadFile(argv[1]);
#ifdef WIN32
if (counterAvailable) {
QueryPerformanceCounter( (LARGE_INTEGER*) &stopTime);
} else {
stopTime = GetTickCount();
}
timeTaken = ( stopTime - startTime ) * timeScale;
#else
double timeTaken = 0;
#endif
if (myLoadResult < 0) return -1;
std::cout << "It took " << timeTaken << " seconds to index " << curFileName << std::endl;
std::cout << "I found " << myWoerterbuch->wordCount << " unique Words in a total of "
<< myIndexer->totalwords << " Words." << std::endl;
std::cout << "I had " << myWoerterbuch->collisions << " Collisions." << std::endl;
while (true) {
std::cout << std::endl;
std::cout << "The following commands are available:" << std::endl <<
"\"getCount WORD\" to view how many times i found WORD" << std::endl <<
"\"printit\" to print the entire hashtable in format $HASH : $WORD." << std::endl <<
"\"exit\" to quit the program (this will discard the index!)" << std::endl << std::endl;
std::cout << "my master? > ";
std::string inString;
char inBuffer[255];
std::cin.getline(inBuffer,256);
inString = inBuffer;
toLowerString(inString);
std::string command = inString.substr( 0, inString.find_first_of(' ') );
std::string commandParam = inString.substr( inString.find_first_of(' ')+1,inString.length() );
if (command == "exit") {
break;
}
if (command == "getcount") {
std::cout << std::endl << "I found \"" << commandParam << "\" " << myWoerterbuch->getCount(commandParam) << " Times." << std::endl;
continue;
}
if (command == "printit") {
myWoerterbuch->printall();
continue;
}
std::cout << "Sorry, i couldn't understand that command" << std::endl;
}
delete(myWoerterbuch);
delete(myIndexer);
return 0;
}
