/// \brief TODOCUMENT
bool options_block::is_acceptable_executable(const path &arg_output_file ///< TODOCUMENT
) {
if (arg_output_file.filename() == ".." || arg_output_file.filename() == ".") {
// cerr << "Here0" << endl;
return false;
}
if (arg_output_file.has_root_directory() || arg_output_file.has_root_name()) {
// cerr << "Here1" << endl;
if (!exists(arg_output_file) && !is_regular_file(arg_output_file)) {
// cerr << "Here2" << endl;
return false;
}
}
return true;
}
LandmarkCollection DefaultNamedLandmarkSource::get(const path& imagePath) {
// Todo: .at throws an out_of_range exception when the element is not found.
// [] inserts a new, empty element if not found. Think about what we want.
// there is also find, which returns an iterator
// and we may want to use an unordered_map because of O(1) access
Logger logger = Loggers->getLogger("imageio");
LandmarkCollection landmarks;
try { // Todo: We should probably change this unreadable try-catch code to find()
landmarks = landmarkCollections.at(imagePath);
} catch (std::out_of_range& e) {
try {
landmarks = landmarkCollections.at(imagePath.filename());
} catch (std::out_of_range& e) {
try {
landmarks = landmarkCollections.at(imagePath.stem());
}
catch (std::out_of_range& e) {
logger.warn("Landmarks for the given image could not be found, returning an empty LandmarkCollection. Is this expected?");
}
}
// we succeeded using the basename
}
return landmarks; // empty if element not found
}
/// \brief TODOCUMENT
///
/// \relates score_classn_value_results_set
void cath::score::write_to_svm_light_data_files(const score_classn_value_results_set &arg_results_set, ///< TODOCUMENT
const path &arg_output_file_stem, ///< TODOCUMENT
const size_t &arg_num_repeats, ///< TODOCUMENT
mt19937 &arg_rng, ///< TODOCUMENT
const double &arg_fraction_train ///< TODOCUMENT
) {
const auto num_instances = get_num_instances ( arg_results_set );
const auto names = get_names ( arg_results_set );
const auto instance_labels = get_instance_labels ( arg_results_set );
const auto scalings = get_value_list_scalings( arg_results_set );
// Get a data structure in which all lists are sorted in the same way
const auto results = transform_build<score_classn_value_vec_vec>(
names,
[&] (const string &x) {
const auto &results_list = arg_results_set.get_score_classn_value_list_of_name( x );
return get_score_classn_values_of_instance_labels( results_list, instance_labels );
}
);
for (const size_t &repeat_ctr : irange( 1_z, arg_num_repeats + 1 ) ) {
const auto repeat_ctr_str = lexical_cast<string>( repeat_ctr );
const path train_file = arg_output_file_stem.parent_path() / ( path( arg_output_file_stem.filename() ).string() + "." + repeat_ctr_str + ".train" );
const path test_file = arg_output_file_stem.parent_path() / ( path( arg_output_file_stem.filename() ).string() + "." + repeat_ctr_str + ".test" );
const size_vec_size_vec_pair split_indices = random_split( arg_rng, num_instances, arg_fraction_train );
write_to_svm_light_data_files_impl( results, scalings, train_file, split_indices.first );
write_to_svm_light_data_files_impl( results, scalings, test_file, split_indices.second );
}
}
node_tuple readFile(path currentFile)
{
regex rx("(^|\\s)#include\\s[\"<](.*?)[\">]");
string fileName = currentFile.filename();
transform(fileName.begin(), fileName.end(), fileName.begin(), tolower);
string fileFolder = currentFile.parent_path();
transform(fileFolder.begin(), fileFolder.end(), fileFolder.begin(), tolower);
vector<string> includes;
ifstream sourceFile(currentFile);
stringstream buffer;
buffer << sourceFile.rdbuf();
sourceFile.close();
string sourceFileContent(buffer.str());
sregex_iterator rit(sourceFileContent.begin(), sourceFileContent.end(), rx);
sregex_iterator riend;
smatch res;
string res2;
while (rit != riend) {
res = *rit;
res2 = res[2];
transform(res2.begin(), res2.end(), res2.begin(), tolower);
includes.push_back(res2);
++rit;
}
return make_tuple(fileName, fileFolder, includes);
}
void file_manager::safe_add_file(path & file, suffix_array_builder & sa_builder)
{
boost::lock_guard<boost::mutex> locker(lock_);
size_t file_number = files_.size();
std::string file_name = file.filename().string();
files_.push_back(file.string());
sa_builder.add_suffixes(file_name, file_number);
}
HUEFile::HUEFile(const path p)
{
//TODO: name = p.filename().string(); for Boost >1.46
name = p.filename().string();
ppath = p.string();
size = file_size(p);
column = 4;
sslimit = 10;
}
static void add_resource_dir(const char* a_class, const path& p)
{
const path xml_file = p / (p.filename().replace_extension(".xml"));
if (!exists(xml_file))
warn() << "Missing resource XML file: " << xml_file;
else
add_resource(a_class, IResourcePtr(new FilesystemResource(p)));
}
filetype analyse_file(path file){
if(!is_regular_file(file)){
return OTHER;
}
string filename=file.filename().string();
string filename_extension=cut(filename,".").back();
if(in(filename_extension,settings::header_endings)){
return HEADER;
}
else if(in(filename_extension,settings::implementation_endings)){
return IMPL;
}
else return OTHER;
}
InquiryProcessor (ThreadPool & _threadPool, std::string _saver): threadPool(_threadPool), saverPath(_saver) {
std::ifstream ifs(saverPath);
std::string textsPath;
getline(ifs, textsPath);
curPath = path(textsPath);
std::string text;
int words = 0;
std::string str;
int counter = 0;
std::vector<double> newText;
while (getline(ifs, str)) {
while(str.find(" ") != std::string::npos) {
text = str.substr(0, str.find(" "));
str = str.substr(str.find(" ") + 1);
newText.push_back(atof(text.c_str()));
}
matrix.push_back(newText);
CPoint kdTreePoint(newText, counter);
counter++;
KDTreeBase.push_back(kdTreePoint);
newText.clear();
}
ifs.close();
directory_iterator end_iter;
try {
if (exists(curPath)) {
if (is_regular_file(curPath)) {
docs = 1;
docNames.push_back(curPath.filename().generic_string());
}
docs = 0;
if (is_directory(curPath)) {
for (directory_iterator p(curPath); p != end_iter; ++p) {
docNames.push_back(p->path().filename().generic_string());
docs++;
}
}
}
} catch (const filesystem_error& ex) {
std::cout << ex.what() << std::endl;
}
for (int i = 0; i < docs; ++i) {
docID.push_back(i);
}
// build для одного, потом выкидываем точку из кдтри бэйз и снова строим вектор рутов
root = BuildKDTree(KDTreeBase);
}
int SortIt::isCorrectFile(path file) {
string fileName = file.filename().string();
// EXISTS = -1
if (!exists(file)) {
return -1;
}
// DUPLICATE = 1
if (boost::starts_with(fileName, DUPLICATE_FILE_TAG)) {
return 1;
}
// FILE OK = 0
return 0;
}
uint32_t wallet::import_electrum_wallet(
const path& wallet_dat,
const string& wallet_dat_passphrase,
const string& account_name
)
{ try {
if( NOT is_open() ) FC_CAPTURE_AND_THROW( wallet_closed );
if( NOT is_unlocked() ) FC_CAPTURE_AND_THROW( wallet_locked );
uint32_t count = 0;
auto keys = bitcoin::import_electrum_wallet( wallet_dat, wallet_dat_passphrase );
for( const auto& key : keys )
count += friendly_import_private_key( key, account_name );
start_scan( 0, 1 );
ulog( "Successfully imported ${x} keys from ${file}", ("x",keys.size())("file",wallet_dat.filename()) );
return count;
} FC_CAPTURE_AND_RETHROW( (wallet_dat)(account_name) ) }
void KeyManager::prefixKeyFile(const path& pKeyFileFName, const std::string& pPrefix) const {
BOOST_LOG_NAMED_SCOPE("KeyManager::renameMallformedKeyFile");
path myNewFName;
try {
if (exists(pKeyFileFName)) {
path myPath = pKeyFileFName.parent_path();
path myFName = pKeyFileFName.filename();
myNewFName = myPath / (path(pPrefix+"-") += myFName);
BOOST_LOG_TRIVIAL(debug)<<"Going to rename "<< pKeyFileFName << " into " << myNewFName << ".";
rename(pKeyFileFName, myNewFName);
} else {
BOOST_LOG_TRIVIAL(debug)<<"File "<< pKeyFileFName << " does not exist.";
}
} catch (const std::exception& myExc) {
BOOST_LOG_TRIVIAL(error)<<"Failed to rename "<< pKeyFileFName << " into " << myNewFName << "because - " << myExc.what();
} catch(...) {
BOOST_LOG_TRIVIAL(error)<<"Failed to rename "<< pKeyFileFName << " into " << myNewFName << ".";
}
}
void GenerateStdAfxMaker::set_include( const path& include )
{
for ( size_t i = 0; i < m_includes.size(); ++i )
{
const path& p = m_includes[i].first;
if ( p == include )
{
m_includes[i].second = true;
break;
}
else if ( p.has_parent_path() )
{
if ( p.filename() == include.filename() )
{
m_includes[i].second = true;
break;
}
}
}
}
size_t inline Epub::compute_epub_hash(const path & _absolute_path)
{
unsigned int size = file_size(_absolute_path);
time_t lmtime = last_write_time(_absolute_path);
string timestring = lexical_cast<std::string>(lmtime);
#ifdef DEBUG
cout << "File Exists" << endl;
cout << "\t Name: " << _absolute_path.filename().string() << endl;
cout << "\t Absolute path: " << _absolute_path.string() << endl;
cout << "\t Size: " << size << endl;
cout << "\t Last Modified: " << timestring << endl;
#endif
//Calculate the hash.
size_t filehash = 0;
hash_combine<string>(filehash, _absolute_path.string());
hash_combine<unsigned int>(filehash, size);
hash_combine<string>(filehash, timestring);
return filehash;
}
int main(int argc, char* argv[])
{
using std::cout;
using std::cerr;
using boost::filesystem::directory_iterator;
using boost::filesystem::ifstream;
using boost::iostreams::filtering_istream;
using boost::iostreams::gzip_decompressor;
const directory_iterator dir_iter;
ptr_vector<genome> genomes(20);
string line;
for (directory_iterator di0(argv[1]); di0 != dir_iter; ++di0)
{
const path genome_path = di0->path();
if (!is_directory(genome_path)) continue;
cout << "Reading " << genome_path.filename() << '\n';
// Parse README
ifstream readme(genome_path / "README");
for (auto i = 0; i < 21; ++i) getline(readme, line);
size_t idx;
while (getline(readme, line) && ((idx = line.find("taxid=", 51)) == string::npos));
const auto taxid = line.substr(idx + 6, line.size() - idx - 7);
readme.close();
// Parse README_CURRENT_BUILD
ifstream build(genome_path / "README_CURRENT_BUILD");
getline(build, line); // ======================================================================
getline(build, line); // Organism: Apis mellifera (honey bee)
const auto organism = line.substr(10, line.size() - 11);
getline(build, line); // NCBI Build Number: 5
const auto ncbiBuild = line.substr(19, line.size() - 20);
getline(build, line); // Version: 1
const auto version = line.substr(9, line.size() - 10);
getline(build, line); // Release date: 29 April 2011
const auto releaseDate = line.substr(14, line.size() - 15);
build.close();
// Construct a genome.
genomes.push_back(new genome(taxid, organism, ncbiBuild, version, releaseDate));
auto& g = genomes.back();
// Sort *.fa.gz
ptr_vector<string> files(20);
for (directory_iterator di(genome_path); di != dir_iter; ++di)
{
const auto p = di->path();
if (p.extension().string() != ".gz") continue;
files.push_back(new string(p.filename().string()));
}
files.sort();
// Parse *.fa.gz in the previously sorted order
g.files.reserve(files.size());
for (const auto& f : files)
{
ifstream in(genome_path / f);
filtering_istream fis;
fis.push(gzip_decompressor());
fis.push(in);
getline(fis, line); // Header line
const auto header = line;
size_t nucleotides = 0;
while (getline(fis, line))
{
if (line.front() == '>')
{
cerr << "Multiple header lines in " << f << '\n';
}
if (line.size() > 70)
{
cerr << "Line longer than 70 characters in " << f << '\n';
}
nucleotides += line.size();
}
g.files.push_back(file_t(f, header, nucleotides));
}
// Compute the overall nucleotides
for (const auto& f : g.files) g.nucleotides += f.nucleotides;
}
// Sort genomes in the descending order of nucleotides
genomes.sort();
// Output genome construction code in javascript
cout << " var genomes = [";
for (auto i = 0; i < genomes.size(); ++i)
{
const auto& g = genomes[i];
if (i) cout << ", ";
cout << "{\n"
<< " taxid: " << g.taxid << ",\n"
<< " name: '" << g.organism << "',\n"
<< " ncbiBuild: " << g.ncbiBuild << ",\n"
<< " version: " << g.version << ",\n"
<< " releaseDate: '" << g.releaseDate << "',\n"
<< " nucleotides: " << g.nucleotides << ",\n"
<< " files: [";
for (auto j = 0; j < g.files.size(); ++j)
{
const auto& f = g.files[j];
if (j) cout << ", ";
cout << "{\n"
<< " file: '" << f.file << "',\n"
<< " header: '" << f.header << "',\n"
<< " nucleotides: " << f.nucleotides << "\n"
<< " }";
}
cout << "]\n"
<< " }";
}
cout << "];\n";
}
bool HasExtension(path const& p, std::string const& ext) {
auto filename = p.filename().string();
if (filename.size() < ext.size() + 1) return false;
if (filename[filename.size() - ext.size() - 1] != '.') return false;
return boost::iends_with(filename, ext);
}
void decrypt(path &filePlace, path &keyPlace) {
std::ifstream fileToDecode(filePlace.string(), std::ios::binary);
std::ifstream fileWithKey(keyPlace.string(), std::ios::binary);
if (!fileToDecode.is_open()) {
std::cout << "Cannot open file to decode: " << filePlace.filename().string();
exit(0);
}
if (!fileWithKey.is_open()) {
std::cout << "Cannot open file with key: " << keyPlace.filename().string();
exit(0);
}
DES_cblock key;
fileWithKey.read((char *)key, file_size(keyPlace));
DES_key_schedule key_schedule;
DES_set_key_checked(&key, &key_schedule);
DES_cblock ivec;
memset((char*)&ivec, 0, sizeof(ivec));
char *inputData = new char[file_size(filePlace)];
char *outputData = new char[file_size(filePlace)];
memset(inputData, 0, file_size(filePlace));
memset(outputData, 0, file_size(filePlace));
fileToDecode.read(inputData, file_size(filePlace));
DES_ncbc_encrypt((unsigned char *)inputData, (unsigned char *)outputData,
file_size(filePlace), &key_schedule, &ivec, DES_DECRYPT);
std::stringstream outputDataStream(outputData);
std::string newFileName;
std::string size;
//Loop for file data
while (std::getline(outputDataStream, newFileName)) {
std::getline(outputDataStream, size);
int fileSize = std::stoi(size);
std::string newData;
newData.resize(fileSize + 1);
outputDataStream.read(&newData[0], fileSize);
std::ofstream outputFile;
//if on Linux
if (filePlace.parent_path().string()[0] == '/') {
outputFile.open(filePlace.parent_path().string() + "/" + newFileName,
std::ofstream::out | std::ofstream::trunc | std::ofstream::binary);
}
else {
outputFile.open(filePlace.parent_path().string() + "\\" + newFileName,
std::ofstream::out | std::ofstream::trunc | std::ofstream::binary);
}
if (!outputFile.is_open()) {
std::cout << "Cannot create new file: " << newFileName;
exit(0);
}
//If it`s an image then decode back
path p(newFileName);
if (p.extension() != ".txt") {
char *decoded_image = new char[fileSize + 1];
bn::decode_b16(newData.begin(), newData.end(), decoded_image);
outputFile.write(decoded_image, fileSize);
}
else {
outputFile.write(&newData[0], fileSize);
}
outputFile.close();
}
fileToDecode.close();
fileWithKey.close();
delete[] inputData;
delete[] outputData;
}
void __copy(const path& from, const path& to, copy_options options,
std::error_code *ec)
{
const bool sym_status = bool(options &
(copy_options::create_symlinks | copy_options::skip_symlinks));
const bool sym_status2 = bool(options &
copy_options::copy_symlinks);
std::error_code m_ec;
struct ::stat f_st = {};
const file_status f = sym_status || sym_status2
? detail::posix_lstat(from, f_st, &m_ec)
: detail::posix_stat(from, f_st, &m_ec);
if (m_ec)
return set_or_throw(m_ec, ec, "copy", from, to);
struct ::stat t_st = {};
const file_status t = sym_status ? detail::posix_lstat(to, t_st, &m_ec)
: detail::posix_stat(to, t_st, &m_ec);
if (not status_known(t))
return set_or_throw(m_ec, ec, "copy", from, to);
if (!exists(f) || is_other(f) || is_other(t)
|| (is_directory(f) && is_regular_file(t))
|| detail::stat_equivalent(f_st, t_st))
{
return set_or_throw(make_error_code(errc::function_not_supported),
ec, "copy", from, to);
}
if (ec) ec->clear();
if (is_symlink(f)) {
if (bool(copy_options::skip_symlinks & options)) {
// do nothing
} else if (not exists(t)) {
__copy_symlink(from, to, ec);
} else {
set_or_throw(make_error_code(errc::file_exists),
ec, "copy", from, to);
}
return;
}
else if (is_regular_file(f)) {
if (bool(copy_options::directories_only & options)) {
// do nothing
}
else if (bool(copy_options::create_symlinks & options)) {
__create_symlink(from, to, ec);
}
else if (bool(copy_options::create_hard_links & options)) {
__create_hard_link(from, to, ec);
}
else if (is_directory(t)) {
__copy_file(from, to / from.filename(), options, ec);
} else {
__copy_file(from, to, options, ec);
}
return;
}
else if (is_directory(f) && bool(copy_options::create_symlinks & options)) {
return set_or_throw(make_error_code(errc::is_a_directory), ec, "copy");
}
else if (is_directory(f) && (bool(copy_options::recursive & options) ||
copy_options::none == options)) {
if (!exists(t)) {
// create directory to with attributes from 'from'.
__create_directory(to, from, ec);
if (ec && *ec) { return; }
}
directory_iterator it = ec ? directory_iterator(from, *ec)
: directory_iterator(from);
if (ec && *ec) { return; }
std::error_code m_ec;
for (; it != directory_iterator(); it.increment(m_ec)) {
if (m_ec) return set_or_throw(m_ec, ec, "copy", from, to);
__copy(it->path(), to / it->path().filename(),
options | copy_options::__in_recursive_copy, ec);
if (ec && *ec) { return; }
}
}
}
void process_file(const options *adbr_opt, path &fpath)
{
long fdate = last_write_time(fpath);
ulong fsize = file_size(fpath);
uint fid = 0;
char ed2k[33];
adbr_attr attrib;
bool hash_req = false,
ident_req = true;
if(adbr_opt->use_repository)
{
printf("\tSearching repository...\t\t");
adbr_entry e;
if((adbr_opt->use_dates && repos->search_hash(fsize, fdate, &e)) ||
(repos->search_hash(fsize, &e)))
{
strcpy(ed2k, e.ed2k);
fid = e.fileid;
printf("Found (%s|%lu)\n", ed2k, fsize);
}
else
{
hash_req = true;
printf("Failed\n");
}
}
if((!adbr_opt->use_repository && !adbr_opt->rename &&
!adbr_opt->add_mylist && !adbr_opt->move) ||
(fid && !adbr_opt->rename && !adbr_opt->move))
{
ident_req = false;
}
if(hash_req)
{
printf("\tHashing...\t\t\t");
ed2k_hash(fpath.string().c_str(), ed2k);
printf("Done (%s)\n", ed2k);
if(adbr_opt->use_repository)
{
repos->insert_hash(fsize, ed2k, fdate);
}
}
if(ident_req)
{
printf("\tIdentifying file...\t\t");
if((fid && adbc->file(attrib, fid)) ||
(!fid && adbc->file(attrib, ed2k, fsize)))
{
if(adbr_opt->romaji)
attrib["PREFERRED_NAME"] = attrib["ANIME_ROMAJI"];
else
attrib["PREFERRED_NAME"] = attrib["ANIME_ENGLISH"];
sscanf(attrib["FID"].c_str(), "%u", &fid);
if(adbr_opt->use_repository)
repos->update_hash(fsize, fdate, fid);
printf("Done (%u)\n", fid);
}
else
{
printf("Failed\n");
return;
}
}
if(adbr_opt->rename || adbr_opt->move)
{
printf("\tRenaming file...\t\t");
string str;
if(adbr_opt->rename)
{
str = adbr_opt->format;
if(!attrib["ANIME_TYPE"].compare("Film"))
{
if(attrib["EPISODE_NAME"].find("0123456789") == string::npos)
{
str = adbr_opt->format_yn;
}
else
{
str = adbr_opt->format_y;
}
}
else if(!attrib["ANIME_TYPE"].compare("OVA") ||
!attrib["ANIME_TYPE"].compare("TV Special"))
{
if(!attrib["EPISODE_TOTAL"].compare("1"))
{
if(attrib["EPISODE_NAME"].find("OVA") == string::npos)
{
str = adbr_opt->format_ye;
}
else
{
str = adbr_opt->format_y;
}
}
}
for(size_t i = 0; i < str.length(); i++)
{
size_t st;
if(str.at(i) == '%')
{
st = i;
while(++i < str.length())
{
if(str.at(i) != '%')
{
continue;
}
else
{
string at = str.substr(st+1, i-st-1);
if(attrib.count(at.c_str()))
{
string r = attrib[at.c_str()];
str.replace(st, i-st+1, r);
i = st+r.length();
// printf("after: %s (<- %s)\n", str->c_str(), at.c_str());
}
else
{
printf("|%s| is not a valid token\n", at.c_str());
}
}
break;
}
}
}
boost::algorithm::trim(str);
}
else
{
str = fpath.filename();
}
path fnew = fpath.parent_path();
if(adbr_opt->move)
{
fnew = adbr_opt->animeroot;
if(adbr_opt->wstatus)
{
size_t viewdate = 0;
adbr_attr file_att;
if(adbc->myfile(file_att, fid))
{
sscanf(file_att["VIEWDATE"].c_str(), "%u", &viewdate);
}
if(viewdate)
{
fnew /= "watched";
}
else
{
fnew /= "unwatched";
}
}
fnew /= attrib["PREFERRED_NAME"];
if(!exists(fnew))
{
if(!create_directories(fnew))
{
printf("Failed to create parent (%s) | ", fnew.file_string().c_str());
}
}
fnew /= str;
}
else
{
fnew = fpath.parent_path() / str;
}
if(exists(fnew))
{
printf("Already exists (%s)\n", fnew.file_string().c_str());
}
else
{
rename(fpath, fnew);
if(exists(fnew))
{
printf("Done (%s)\n", fnew.filename().c_str());
}
else
{
printf("Failed (%s)\n", fnew.file_string().c_str());
}
}
}
if(adbr_opt->add_mylist)
{
printf("\tAdding to mylist...\t\t");
if((fid && adbc->mylistadd(fid, adbr_opt)) ||
(!fid && adbc->mylistadd(ed2k, fsize, adbr_opt)))
{
printf("Done\n");
}
else
{
printf("Failed\n");
}
}
}
path canonical_parent(const path& pth, const path& base) {
return canonical(pth.parent_path(), base) / pth.filename();
}
void get_files_in_dir(const std::string &dir,
std::vector<std::string>* files,
std::vector<std::string>* dirs,
file_name_option mode,
file_filter_option filter,
file_reorder_option reorder,
file_tree_checksum* checksum) {
if(path(dir).is_relative() && !game_config::path.empty()) {
path absolute_dir(game_config::path);
absolute_dir /= dir;
if(is_directory_internal(absolute_dir)) {
get_files_in_dir(absolute_dir.string(), files, dirs, mode, filter, reorder, checksum);
return;
}
}
const path dirpath(dir);
if (reorder == DO_REORDER) {
LOG_FS << "searching for _main.cfg in directory " << dir << '\n';
const path maincfg = dirpath / maincfg_filename;
if (file_exists(maincfg)) {
LOG_FS << "_main.cfg found : " << maincfg << '\n';
push_if_exists(files, maincfg, mode == ENTIRE_FILE_PATH);
return;
}
}
error_code ec;
bfs::directory_iterator di(dirpath, ec);
bfs::directory_iterator end;
if (ec) {
// Probably not a directory, let the caller deal with it.
return;
}
for(; di != end; ++di) {
bfs::file_status st = di->status(ec);
if (ec) {
LOG_FS << "Failed to get file status of " << di->path().string() << ": " << ec.message() << '\n';
continue;
}
if (st.type() == bfs::regular_file) {
{
std::string basename = di->path().filename().string();
if (filter == SKIP_PBL_FILES && looks_like_pbl(basename))
continue;
if(!basename.empty() && basename[0] == '.' )
continue;
}
push_if_exists(files, di->path(), mode == ENTIRE_FILE_PATH);
if (checksum != NULL) {
std::time_t mtime = bfs::last_write_time(di->path(), ec);
if (ec) {
LOG_FS << "Failed to read modification time of " << di->path().string() << ": " << ec.message() << '\n';
} else if (mtime > checksum->modified) {
checksum->modified = mtime;
}
uintmax_t size = bfs::file_size(di->path(), ec);
if (ec) {
LOG_FS << "Failed to read filesize of " << di->path().string() << ": " << ec.message() << '\n';
} else {
checksum->sum_size += size;
}
checksum->nfiles++;
}
} else if (st.type() == bfs::directory_file) {
std::string basename = di->path().filename().string();
if(!basename.empty() && basename[0] == '.' )
continue;
if (filter == SKIP_MEDIA_DIR
&& (basename == "images" || basename == "sounds"))
continue;
const path inner_main(di->path() / maincfg_filename);
bfs::file_status main_st = bfs::status(inner_main, ec);
if (error_except_not_found(ec)) {
LOG_FS << "Failed to get file status of " << inner_main.string() << ": " << ec.message() << '\n';
} else if (reorder == DO_REORDER && main_st.type() == bfs::regular_file) {
LOG_FS << "_main.cfg found : " << (mode == ENTIRE_FILE_PATH ? inner_main.string() : inner_main.filename().string()) << '\n';
push_if_exists(files, inner_main, mode == ENTIRE_FILE_PATH);
} else {
push_if_exists(dirs, di->path(), mode == ENTIRE_FILE_PATH);
}
}
}
if (files != NULL)
std::sort(files->begin(),files->end());
if (dirs != NULL)
std::sort(dirs->begin(),dirs->end());
if (files != NULL && reorder == DO_REORDER) {
// move finalcfg_filename, if present, to the end of the vector
for (unsigned int i = 0; i < files->size(); i++) {
if (ends_with((*files)[i], "/" + finalcfg_filename)) {
files->push_back((*files)[i]);
files->erase(files->begin()+i);
break;
}
}
// move initialcfg_filename, if present, to the beginning of the vector
int foundit = -1;
for (unsigned int i = 0; i < files->size(); i++)
if (ends_with((*files)[i], "/" + initialcfg_filename)) {
foundit = i;
break;
}
if (foundit > 0) {
std::string initialcfg = (*files)[foundit];
for (unsigned int i = foundit; i > 0; i--)
(*files)[i] = (*files)[i-1];
(*files)[0] = initialcfg;
}
}
}
int main(int argc, char* argv[])
{
if (argc != 5)
{
std::cout << "combinelog slices_folder prefix 16_prop_350.xls out.csv\n";
return 1;
}
const path slices = argv[1];
const string prefix = argv[2];
const path prop = argv[3];
const path output_csv = argv[4];
string line;
line.reserve(600);
std::cout << "Reading log.csv's." << std::endl;
vector<record> records;
records.reserve(80000);
const directory_iterator end_dir_iter;
for (directory_iterator dir_iter(slices); dir_iter != end_dir_iter; ++dir_iter)
{
if (!is_directory(dir_iter->status())) continue; // Find example directories.
const path slice_path = dir_iter->path();
const string fullslice = slice_path.filename().string();
if (!starts_with(fullslice, prefix)) continue;
std::cout << fullslice << '\n';
const string slice = fullslice.substr(6);
ifstream log(slice_path / "log.csv");
getline(log, line); // Filter out header line.
while (getline(log, line))
{
records.push_back(record(static_cast<string&&>(line), slice));
}
}
const size_t num_records = records.size();
std::cout << "Sorting " << num_records << " records." << std::endl;
std::sort(records.begin(), records.end());
std::cout << "Reading property xls file " << prop << '.' << std::endl;
vector<property> properties;
properties.reserve(7220928); // Number of molecules in 16_prop_350.xls
ifstream xls(prop);
getline(xls, line); // Filter out header line.
while (getline(xls, line))
{
properties.push_back(property(static_cast<string&&>(line)));
}
xls.close();
std::cout << properties.size() << " records in prop xls file." << std::endl;
std::cout << "Writing combined csv to " << output_csv << std::endl;
ofstream csv(output_csv);
csv << "Slice,Ligand,Conf,FE1,HB1,FE2,HB2,FE3,HB3,FE4,HB4,FE5,HB5,FE6,HB6,FE7,HB7,FE8,HB8,FE9,HB9,HA,MWT,LogP,Desolv_apolar,Desolv_polar,HBD,HBA,tPSA,Charge,NRB,SMILES\n";
size_t s, e, num_not_found = 0;
for (size_t i = 0; i < num_records; ++i)
{
const record& r = records[i];
const string id = r.line.substr(4, 8);
csv << r.slice << ',' << id << ',' << r.line.substr(r.comma + 1);
const property& p = properties[binary(properties, id)];
if (id != p.id)
{
//std::cerr << id << ' ' << p.id;
++num_not_found;
csv << ",,,,,,,,,,,,,,,,,,,\n";
continue;
}
s = 13;
for (size_t j = 0; j < 10; ++j) // 9 properties, i.e. HA,MWT,LogP,Desolv_apolar,Desolv_polar,HBD,HBA,tPSA,Charge,NRB
{
e = p.line.find_first_of('\t', s + 1);
csv << ',' << p.line.substr(s, e - s);
s = e + 1;
}
csv << ',' << p.line.substr(s) << '\n'; // SMILES
}
csv.close();
std::cout << num_not_found << " records in log.csv's but not in prop xls file." << std::endl;
return 0;
}
