int main(int argc, char** argv)
{
printf("hi");
if (!indexerValidateArgs(argc, argv))
{
DICTIONARY* index = buildIndexFromDirectory(argv[1]);
printf("directory: %s \n", argv[1]);
printf("filename: %s \n", argv[2]);
saveIndexToFile(index, argv[2]);
cleanIndex(index);
if (argc == 5)
{
// filename= argv[2];
//newFile = argv[argc -1];
//sprintf(path, "%s/%s", targetDir, filename);
index = rebuild(argv[3]);
saveIndexToFile(index, argv[4]);
cleanIndex(index);
}
return 0;
}
return 1;
}
/// Distributes correlation counts over all points that are possible for a given
/// d-value.
void PoldiResidualCorrelationCore::distributeCorrelationCounts(
const std::vector<double> &correctedCorrelatedIntensities,
const std::vector<double> &dValues) const {
const std::vector<double> chopperSlits(m_chopper->slitTimes());
PARALLEL_FOR_NO_WSP_CHECK()
for (int k = 0; k < static_cast<int>(m_indices.size()); ++k) {
for (size_t i = 0; i < dValues.size(); ++i) {
double d = dValues[dValues.size() - i - 1];
double dInt = correctedCorrelatedIntensities[i];
double deltaForD =
-dInt / m_weightsForD[i] / static_cast<double>(chopperSlits.size());
for (double chopperSlit : chopperSlits) {
CountLocator locator = getCountLocator(d, chopperSlit, m_indices[k]);
int indexDifference = locator.icmax - locator.icmin;
switch (indexDifference) {
case 0:
addToCountData(locator.detectorElement, locator.iicmin,
deltaForD * locator.arrivalWindowWidth);
break;
case 2: {
int middleIndex = cleanIndex((locator.icmin + 1), m_timeBinCount);
if (middleIndex < 0) {
m_logger.warning()
<< "Inconsistency foun while calculating distribute "
"correlation counts for d-value with index "
<< std::to_string(k)
<< ", got middle index: " << std::to_string(middleIndex)
<< ", ignoring it.\n";
break;
}
addToCountData(locator.detectorElement, middleIndex, deltaForD);
}
case 1: {
addToCountData(locator.detectorElement, locator.iicmin,
deltaForD * (static_cast<double>(locator.icmin) -
locator.cmin + 1.0));
addToCountData(
locator.detectorElement, locator.iicmax,
deltaForD * (locator.cmax - static_cast<double>(locator.icmax)));
break;
}
default:
break;
}
}
}
}
}
int main(int argc, char *argv[])
{
// INPUT VARIABLES
char* program;
char* target_dir;
char* output_file_name;
char* input_file_name;
char* rewritten_file_name;
// determines which mode the program is running in
int indexer_test_flag;
// overall data structure
INVERTED_INDEX* index;
// these variables handle the scandir results and pulling information from files
int numfiles = 0;
struct dirent **files;
char* file_name;
char* file_contents;
// this variable is used for parsing the HTML
int file_pos;
// variables used for WordNode (word == key) and DocumentNode (doc_id)
char* word;
int doc_id;
indexer_test_flag = 0; // default is basic funcitonality
program = argv[0];
// if incorrect number of arguments
if(argc != 3 && argc != 5)
{
fprintf(stderr, "%s: The indexer requires either 2 (a target directory and output file name) or 4 (a target directory, output file name, input file name, and a rewritten file name\n", program);
return 1;
}
target_dir = argv[1];
output_file_name = argv[2];
// if 5 arguments --> TESTING MODE
if(argc == 5)
{
indexer_test_flag = 1;
input_file_name = argv[3];
rewritten_file_name = argv[4];
}
// if the target directory doesn't exist
if(!directoryExists(target_dir))
{
fprintf(stderr, "%s: Invalid target directory %s\n", program, target_dir);
return 1;
}
numfiles = getFileList(target_dir, &files);
chdir(target_dir);
// if there are no files in the target directory
if(numfiles <= 0)
{
fprintf(stderr, "%s: Error with target directory %s'n", program, target_dir);
return 1;
}
index = initializeDict();
// this for loop goes through each file in "files", pulls each word out of the HTML, and updates the index data structure
for(int i=0; i < numfiles; i++)
{
file_name = files[i]->d_name;
// if it's a regular file (to avoid . and .. files)
if(regularFile(file_name))
{
file_contents = NULL;
file_contents = readFile(file_name);
file_pos = 0;
doc_id = atoi(file_name);
// just in case a 404 wasn't caught by the crawler
if(file_contents != NULL)
{
word = NULL;
word = malloc(500*sizeof(char));
MALLOC_CHECK(word);
BZERO(word, 500*sizeof(char));
// GetNextWord returns the index in file_contents where it stopped parsing, while assigning a new word to the "word"
while((file_pos = parseHTML(file_contents, word, file_pos)) != -1)
{
updateIndex(word, doc_id, index);
free(word);
//word = NULL;
word = malloc(500*sizeof(char));
MALLOC_CHECK(word);
BZERO(word, 500*sizeof(char));
}
free(word);
}
free(file_contents);
}
free(files[i]);
}
free(files);
// outputs to a file
saveFile(index, output_file_name);
cleanIndex(index);
// if it's in testing mode
if(indexer_test_flag)
{
INVERTED_INDEX* newindex;
newindex = readIndex(input_file_name);
saveFile(newindex, rewritten_file_name);
cleanIndex(newindex);
}
}
