/** parse directory of files */ function parse_dir() { $ignore = array("..", '.', '.DS_STORE', "0"); $this->setCheckPoint('dataset'); $prefix = parent::getPrefix(); $bVersion = parent::getParameterValue('bio2rdf_release'); $date = date("Y-m-d\\TG:i:s\\Z"); $dataset_file = parent::getParameterValue("outdir") . parent::getBio2RDFReleaseFile(); $fp = fopen($dataset_file, "w"); if ($fp === FALSE) { trigger_error("Unable to open {$dataset_file}", E_USER_ERROR); return false; } $ids = explode(",", parent::getParameterValue('id_list')); $indir = parent::getParameterValue('indir'); echo "Processing {$indir}\n"; $outfile = "clinicaltrials." . parent::getParameterValue('output_format'); $gz = strstr(parent::getParameterValue('output_format'), ".gz") === FALSE ? false : true; parent::setWriteFile(parent::getParameterValue("outdir") . $outfile, $gz); $files = glob($indir . "NCT*"); foreach ($files as $i => $file) { if ($i % 10000 == 0) { parent::clear(); } $trial_id = basename($file, '.xml'); if (parent::getParameterValue('id_list') == '' || in_array($trial_id, $ids)) { if (filesize($file) != 0) { echo "Processing {$trial_id}" . PHP_EOL; $this->process_file($file); } else { echo "Processing {$trial_id} -> Empty!" . PHP_EOL; } } } echo "Finished." . PHP_EOL; parent::getWriteFile()->close(); // make the dataset description parent::setGraphURI(parent::getDatasetURI()); $rfile = "http://clinicaltrials.gov/ct2/show/NCT_ID?resultsxml=true"; $source_version = parent::getDatasetVersion(); // dataset description $source_file = (new DataResource($this))->setURI($rfile)->setTitle("Clinicaltrials")->setRetrievedDate(date("Y-m-d\\TG:i:s\\Z", filemtime($file)))->setFormat("application/xml")->setPublisher("http://clinicaltrials.gov/")->setHomepage("http://clinicaltrials.gov/")->setRights("use")->setRights("by-attribution")->setLicense("http://clinicaltrials.gov/ct2/about-site/terms-conditions")->setDataset("http://identifiers.org/clinicaltrials/"); parent::writeToReleaseFile($source_file->toRDF()); $output_file = (new DataResource($this))->setURI("http://download.bio2rdf.org/release/{$bVersion}/{$prefix}/{$outfile}")->setTitle("Bio2RDF v{$bVersion} RDF version of {$prefix} v{$source_version}")->setSource($source_file->getURI())->setCreator("https://github.com/bio2rdf/bio2rdf-scripts/blob/master/clinicaltrials/clinicaltrials.php")->setCreateDate($date)->setHomepage("http://download.bio2rdf.org/release/{$bVersion}/{$prefix}/{$prefix}.html")->setPublisher("http://bio2rdf.org")->setRights("use-share-modify")->setRights("by-attribution")->setRights("restricted-by-source-license")->setLicense("http://creativecommons.org/licenses/by/3.0/")->setDataset(parent::getDatasetURI()); $gz = strstr(parent::getParameterValue('output_format'), ".gz") === FALSE ? false : true; if ($gz) { $output_file->setFormat("application/gzip"); } if (strstr(parent::getParameterValue('output_format'), "nt")) { $output_file->setFormat("application/n-triples"); } else { $output_file->setFormat("application/n-quads"); } parent::writeToReleaseFile($output_file->toRDF()); parent::closeReleaseFile(); // write the dataset description file fclose($fp); }
function Run() { $indir = parent::getParameterValue('indir'); $outdir = parent::getParameterValue('outdir'); $download_url = parent::getParameterValue('download_url'); if (parent::getParameterValue('files') == 'all') { $files = explode("|", parent::getParameterList('files')); array_shift($files); } else { $files = explode("|", parent::getParameterValue('files')); } if (parent::getParameterValue("id_list")) { $this->id_list = array_flip(explode(",", parent::getParameterValue('id_list'))); } $dataset_description = ''; foreach ($files as $f) { if ($f == 'drugbank') { $file = 'drugbank.xml.zip'; $lname = 'drugbank'; } $fnx = 'parse_' . $f; $rfile = parent::getParameterValue('download_url') . $file; $lfile = parent::getParameterValue('indir') . $file; $cfile = $lname . "." . parent::getParameterValue('output_format'); // download if (!file_exists($lfile) || parent::getParameterValue('download') == true) { utils::downloadSingle($rfile, $lfile); } // setup the write $gz = strstr(parent::getParameterValue('output_format'), ".gz") === FALSE ? false : true; parent::setWriteFile($outdir . $cfile, $gz); echo $outdir . $cfile; if (file_exists($indir . $file)) { // call the parser echo "processing {$file} ..." . PHP_EOL; $this->{$fnx}($indir, $file); echo "done" . PHP_EOL; parent::clear(); } parent::getWriteFile()->close(); // dataset description $ouri = parent::getGraphURI(); parent::setGraphURI(parent::getDatasetURI()); $source_version = parent::getDatasetVersion(); $bVersion = parent::getParameterValue('bio2rdf_release'); $prefix = parent::getPrefix(); $date = date("Y-m-d\\TH:i:sP"); // dataset description $source_file = (new DataResource($this))->setURI($rfile)->setTitle("DrugBank ({$file})")->setRetrievedDate(date("Y-m-d\\TH:i:sP", filemtime($indir . $file)))->setFormat("application/xml")->setFormat("application/zip")->setPublisher("http://drugbank.ca")->setHomepage("http://drugbank.ca")->setRights("use")->setRights("by-attribution")->setRights("no-commercial")->setLicense("http://www.drugbank.ca/about")->setDataset("http://identifiers.org/drugbank/"); $output_file = (new DataResource($this))->setURI("http://download.bio2rdf.org/release/{$bVersion}/{$prefix}/{$cfile}")->setTitle("Bio2RDF v{$bVersion} RDF version of {$prefix} v{$source_version}")->setSource($source_file->getURI())->setCreator("https://github.com/bio2rdf/bio2rdf-scripts/blob/master/drugbank/drugbank.php")->setCreateDate($date)->setHomepage("http://download.bio2rdf.org/release/{$bVersion}/{$prefix}/{$prefix}.html")->setPublisher("http://bio2rdf.org")->setRights("use-share-modify")->setRights("by-attribution")->setRights("restricted-by-source-license")->setLicense("http://creativecommons.org/licenses/by/3.0/")->setDataset(parent::getDatasetURI()); $gz = strstr(parent::getParameterValue('output_format'), ".gz") === FALSE ? false : true; if ($gz) { $output_file->setFormat("application/gzip"); } if (strstr(parent::getParameterValue('output_format'), "nt")) { $output_file->setFormat("application/n-triples"); } else { $output_file->setFormat("application/n-quads"); } parent::writeToReleaseFile($source_file->toRDF() . $output_file->toRDF()); parent::setGraphURI($ouri); } parent::closeReleaseFile(); }