function get_all_taxa()
{
require_library('connectors/INBioAPI');
$func = new INBioAPI();
$paths = $func->extract_archive_file($this->dwca_file, "meta.xml");
$archive_path = $paths['archive_path'];
$temp_dir = $paths['temp_dir'];
$harvester = new ContentArchiveReader(NULL, $archive_path);
$tables = $harvester->tables;
if (!($this->fields["taxa"] = $tables["http://rs.tdwg.org/dwc/terms/taxon"][0]->fields)) {
debug("Invalid archive file. Program will terminate.");
return false;
}
self::build_taxa_rank_array($harvester->process_row_type('http://rs.tdwg.org/dwc/terms/Taxon'));
self::create_instances_from_taxon_object($harvester->process_row_type('http://rs.tdwg.org/dwc/terms/Taxon'));
self::get_objects($harvester->process_row_type('http://eol.org/schema/media/Document'));
self::get_references($harvester->process_row_type('http://rs.gbif.org/terms/1.0/Reference'));
self::get_agents($harvester->process_row_type('http://eol.org/schema/agent/Agent'));
self::get_vernaculars($harvester->process_row_type('http://rs.gbif.org/terms/1.0/VernacularName'));
$this->archive_builder->finalize(TRUE);
// remove temp dir
recursive_rmdir($temp_dir);
echo "\n temporary directory removed: " . $temp_dir;
print_r($this->debug);
}
function get_all_taxa($taxa_list_text_file = NULL)
{
$this->TEMP_FILE_PATH = create_temp_dir() . "/";
if ($taxa_list_text_file) {
if ($contents = Functions::lookup_with_cache($taxa_list_text_file, $this->download_options)) {
self::save_to_taxa_text_file($contents);
}
} else {
self::generate_taxa_list();
}
/* debug: stop operation here if you only want to generate taxa list */
//return;
self::save_data_to_text();
/* debug: stop operation here if you only want to generate processed text files */
//return;
if ($taxa_list_text_file) {
echo "\n\n finished processing: [{$taxa_list_text_file}]\n\n";
return;
// you need to consolidate the processed text files before proceeding.
}
self::process_text_file();
$this->archive_builder->finalize(true);
// remove temp dir
recursive_rmdir($this->TEMP_FILE_PATH);
echo "\n temporary directory removed: " . $this->TEMP_FILE_PATH;
}
function recursive_rmdir($directory, $empty = false)
{
$directory = preg_replace('@[\\/]$@', '', $directory);
if (!file_exists($directory) || !is_dir($directory)) {
return false;
} elseif (!is_readable($directory)) {
return false;
} else {
$handle = opendir($directory);
while (false !== ($item = readdir($handle))) {
if ($item != '.' && $item != '..') {
$path = $directory . DIRECTORY_SEPARATOR . $item;
if (is_dir($path)) {
recursive_rmdir($path);
} elseif (unlink($path)) {
echo $path . "\n";
}
}
}
closedir($handle);
if ($empty == false) {
if (rmdir($directory)) {
echo $directory . "\n";
} else {
return false;
}
}
return true;
}
}
function get_all_taxa()
{
$this->institution_uris = self::get_institution_uris();
self::load_zip_contents();
print_r($this->text_path);
require_library('connectors/FishBaseAPI');
$func = new FishBaseAPI();
$fields = array("lngSpeciesSenior_ID", "lngSpecies_ID", "lngRepository_ID", "strCatNr", "lngPrepMeth_ID", "lngPersPrep_ID", "lngPersID2_ID", "lngPersID3_ID", "bytCountPrep", "lngDocuTypeSpecimen", "lngPrep_ID", "txtPrepNotes", "lngSpecimen_ID", "strTypeStat", "lngLoc_ID", "strLocName", "txtLocDescr", "sngElevation", "sngLatitudeWGS84", "sngLongitudeWGS84", "lngMacrohabitat_ID", "lngPermanency_ID", "strDepth", "lngGeology_ID", "lngSpecLocal_ID");
$records_specimen = $func->make_array($this->text_path["sd_specimen"], $fields, "", array());
array_shift($records_specimen);
$fields = array("lngPersIdent_ID", "lngSpecimen_ID");
$records_specimen_identifier = $func->make_array($this->text_path["sd_specimen_identifier"], $fields, "", array());
array_shift($records_specimen_identifier);
$fields = array("lngSpeciesSenior_ID", "lngMacroMicro_ID", "lngSpecies_ID");
$records_habitat = $func->make_array($this->text_path["sd_macro_locality"], $fields, "", array());
array_shift($records_habitat);
/*
$fields = array("lngLoc_ID", "strLocName", "txtLocDescr", "sngElevation", "sngLatitudeWGS84", "sngLongitudeWGS84", "lngMacrohabitat_ID", "lngPermanency_ID", "strDepth", "lngGeology_ID", "lngSpecLocal_ID", "lngSpecimen_ID", "lngSpeciesSenior_ID", "lngSpecies_ID");
$records_locality = $func->make_array($this->text_path["sd_locality"], $fields, "", array());
array_shift($records_locality);
*/
$this->assemble_identified_by($records_specimen_identifier);
$this->create_instances_from_taxon_object($records_specimen, "specimen");
// $this->create_instances_from_taxon_object($records_locality, "locality");
$this->create_instances_from_taxon_object($records_habitat, "habitat");
$this->create_archive();
// remove temp dir
$path = $this->text_path["sd_specimen"];
$parts = pathinfo($path);
$parts["dirname"] = str_ireplace("/type_specimen", "", $parts["dirname"]);
recursive_rmdir($parts["dirname"]);
debug("\n temporary directory removed: " . $parts["dirname"]);
}
function get_all_taxa()
{
/*
$id = "100001";
$arr = array("distribution", "chromosome", "taxon_name", "taxonomy", "synonyms", "taxon_ref", "images");
foreach($arr as $type)
{
if($type == "taxon_name") $url = TROPICOS_API_SERVICE . $id . "?format=json&apikey=" . TROPICOS_API_KEY;
elseif($type == "taxonomy") $url = TROPICOS_API_SERVICE . $id . "/HigherTaxa?format=xml&apikey=" . TROPICOS_API_KEY;
elseif($type == "synonyms") $url = TROPICOS_API_SERVICE . $id . "/Synonyms?format=xml&apikey=" . TROPICOS_API_KEY;
elseif($type == "taxon_ref") $url = TROPICOS_API_SERVICE . $id . "/References?format=xml&apikey=" . TROPICOS_API_KEY;
elseif($type == "distribution") $url = TROPICOS_API_SERVICE . $id . "/Distributions?format=xml&apikey=" . TROPICOS_API_KEY;
elseif($type == "images") $url = TROPICOS_API_SERVICE . $id . "/Images?format=xml&apikey=" . TROPICOS_API_KEY;
elseif($type == "chromosome") $url = TROPICOS_API_SERVICE . $id . "/ChromosomeCounts?format=xml&apikey=" . TROPICOS_API_KEY;
echo "\n $type: [$url]";
}
exit;
*/
self::assemble_id_list();
exit;
self::process_taxa();
$this->archive_builder->finalize(TRUE);
// remove temp dir
recursive_rmdir($this->TEMP_DIR);
echo "\n temporary directory removed: " . $this->TEMP_DIR;
}
function export_gbif_to_eol($params)
{
require_library('connectors/INBioAPI');
$func = new INBioAPI();
$paths = $func->extract_archive_file($params["dwca_file"], "meta.xml");
$archive_path = $paths['archive_path'];
$temp_dir = $paths['temp_dir'];
$harvester = new ContentArchiveReader(NULL, $archive_path);
$tables = $harvester->tables;
if (!($this->fields["occurrence"] = $tables["http://rs.tdwg.org/dwc/terms/occurrence"][0]->fields)) {
debug("Invalid archive file. Program will terminate.");
return false;
}
/*
$harvester->process_row_type() - this will convert rows into array.
*/
// $r = $harvester->process_row_type('http://rs.tdwg.org/dwc/terms/occurrence');
// $r = $harvester->process_row_type('http://rs.gbif.org/terms/1.0/Multimedia');
// print_r($r); exit;
self::create_instances_from_taxon_object($harvester->process_row_type('http://rs.tdwg.org/dwc/terms/occurrence'));
self::get_media_objects($harvester->process_row_type('http://rs.gbif.org/terms/1.0/Multimedia'));
// self::get_objects($harvester->process_row_type('http://eol.org/schema/media/Document'));
// self::get_references($harvester->process_row_type('http://rs.gbif.org/terms/1.0/Reference'));
// self::get_agents($harvester->process_row_type('http://eol.org/schema/agent/Agent'));
// self::get_vernaculars($harvester->process_row_type('http://rs.gbif.org/terms/1.0/VernacularName'));
$this->archive_builder->finalize(TRUE);
// remove temp dir
recursive_rmdir($temp_dir);
echo "\n temporary directory removed: " . $temp_dir;
}
function get_all_taxa()
{
self::initialize_dump_file();
$this->agent_ids = self::get_object_agents($this->agents);
// /* normal operation
$this->save_data_to_text();
$this->access_dump_file(false, "synonyms");
$this->access_dump_file(false, "objects");
$this->process_taxa();
// */
/* use this if the dump file has already been created - works okay!
$dump_file = DOC_ROOT . "tmp/turbellarian_dump/turbellarian_dump.txt";
$this->access_dump_file($dump_file, "synonyms");
$this->access_dump_file($dump_file, "objects");
$this->process_taxa($dump_file);
*/
/* manually adding Bilateria */
$rec = array();
$rec["sciname"] = "Bilateria";
$rec["taxon_id"] = "Bilateria";
$rec["authorship"] = "";
$rec["parent_id"] = "";
$rec["status"] = "";
$this->create_instances_from_taxon_object($rec);
$this->create_archive();
/* remove temp dir */
recursive_rmdir($this->TEMP_DIR);
echo "\n temporary directory removed: " . $this->TEMP_DIR;
}
function generate_EnvEOL_data()
{
require_library('connectors/IUCNRedlistDataConnector');
$func = new IUCNRedlistDataConnector();
$basenames = array("eol_env_annotations_noParentTerms");
// list of needed basenames
$options = $this->download_options;
$options['expire_seconds'] = 2592000 * 3;
// 3 months before cache expires
$text_path = $func->load_zip_contents($this->species_list_export, $options, $basenames, ".tsv");
print_r($text_path);
self::csv_to_array($text_path[$basenames[0]]);
$this->archive_builder->finalize(TRUE);
// remove temp dir
$parts = pathinfo($text_path[$basenames[0]]);
recursive_rmdir($parts["dirname"]);
debug("\n temporary directory removed: " . $parts["dirname"]);
recursive_rmdir($this->TEMP_DIR);
// comment this if u want to check "need_to_check_tc_id.txt"
/* run problematic tc_ids with cache=0 --- a utility
$tc_ids = self::get_dump();
foreach($tc_ids as $tc_id)
{
$rec['taxon_id'] = $tc_id;
self::prepare_taxon($rec);
}
exit("\n-exit-\n");
*/
}
function load_xml_string()
{
$file_contents = "";
debug("Please wait, downloading resource document...");
if (preg_match("/^(.*)\\.(gz|gzip)\$/", $this->xml_path, $arr)) {
$path_parts = pathinfo($this->xml_path);
$filename = $path_parts['basename'];
$temp_dir = create_temp_dir() . "/";
debug("temp file path: " . $temp_dir);
if ($file_contents = Functions::get_remote_file($this->xml_path, array('timeout' => 172800))) {
$temp_file_path = $temp_dir . "/" . $filename;
$TMP = fopen($temp_file_path, "w");
fwrite($TMP, $file_contents);
fclose($TMP);
shell_exec("gunzip -f {$temp_file_path}");
$this->xml_path = $temp_dir . str_ireplace(".gz", "", $filename);
debug("xml path: " . $this->xml_path);
} else {
debug("Connector terminated. Remote files are not ready.");
return false;
}
echo "\n {$temp_dir} \n";
$file_contents = Functions::get_remote_file($this->xml_path, array('timeout' => 172800));
recursive_rmdir($temp_dir);
// remove temp dir
echo "\n temporary directory removed: [{$temp_dir}]\n";
}
return $file_contents;
}
function export_gbif_to_eol($params)
{
$this->uris = self::get_uris($params);
require_library('connectors/INBioAPI');
$func = new INBioAPI();
$paths = $func->extract_archive_file($params["dwca_file"], "meta.xml", array("timeout" => 7200, "expire_seconds" => false));
// "expire_seconds" -- false => won't expire; 0 => expires now
$archive_path = $paths['archive_path'];
$temp_dir = $paths['temp_dir'];
$this->harvester = new ContentArchiveReader(NULL, $archive_path);
if (!@$this->harvester->tables["http://rs.tdwg.org/dwc/terms/occurrence"][0]->fields) {
debug("Invalid archive file. Program will terminate.");
return false;
}
if ($params["dataset"] == "NMNH") {
self::process_row_type($params);
} elseif ($params["dataset"] == "NHM") {
self::process_row_type_from_NHM($temp_dir . "/" . $params['location']);
}
$this->archive_builder->finalize(TRUE);
// remove temp dir
recursive_rmdir($temp_dir);
echo "\n temporary directory removed: " . $temp_dir;
print_r($this->debug);
}
public function uninstall()
{
recursive_rmdir(DATA_DIR . '/Base_Theme/templates/default/images');
Variable::delete('default_theme');
Variable::delete('preload_image_cache_default');
Variable::delete('preload_image_cache_selected');
return true;
}
function get_all_taxa()
{
if (self::process_text_files()) {
$this->create_archive();
// remove temp dir
$parts = pathinfo($this->text_path["1"]);
recursive_rmdir($parts["dirname"]);
debug("\n temporary directory removed: " . $parts["dirname"]);
}
}
function get_all_taxa()
{
self::process_text_files();
// remove temp dir
$path = $this->text_path["species"];
$parts = pathinfo($path);
$parts["dirname"] = str_ireplace("/rotifers", "", $parts["dirname"]);
recursive_rmdir($parts["dirname"]);
debug("\n temporary directory removed: " . $parts["dirname"]);
}
function export_lifedesk_to_eol($params)
{
require_library('connectors/LifeDeskToScratchpadAPI');
$func = new LifeDeskToScratchpadAPI();
if ($this->text_path = $func->load_zip_contents($params["lifedesk"])) {
self::update_eol_xml("LD_" . $params["name"]);
}
// remove temp dir
$parts = pathinfo($this->text_path["eol_xml"]);
recursive_rmdir($parts["dirname"]);
debug("\n temporary directory removed: " . $parts["dirname"]);
}
function get_all_taxa()
{
$this->stored_offline_urls = $this->get_rows_from_dump_file($this->stored_offline_urls_dump_file);
$this->create_reference();
$urls = self::get_urls_to_process();
$this->process_urls($urls);
$this->manuall_add_taxon();
$this->archive_builder->finalize(TRUE);
recursive_rmdir($this->TEMP_DIR);
// comment this line to check offline_urls.txt
debug("\n temporary directory removed: " . $this->TEMP_DIR);
}
public function begin()
{
$this->path_to_archive_directory = CONTENT_RESOURCE_LOCAL_PATH . '/' . $this->resource_id . '_working/';
$this->archive_builder = new \eol_schema\ContentArchiveBuilder(array('directory_path' => $this->path_to_archive_directory));
$this->prepare_files();
$this->process_export();
$this->archive_builder->finalize(true);
//remove temp dir
$parts = pathinfo($this->source_file_path);
recursive_rmdir($parts["dirname"]);
debug("\n temporary directory removed: " . $parts["dirname"]);
}
function get_all_taxa($resource_id)
{
$this->uris = self::get_uris();
// print_r($this->uris); exit;
/*
$str = "bathydemersal; marine; depth range 549 - 1202 m (Ref. 97189)";
$str = "benthopelagic; potamodromous (Ref. 51243); freshwater; brackish; pH range: 7.0 - 7.5; dH range: 15; depth range 1 - ? m (Ref. 9696)";
$str = "depth range 220 - 457 m, usually 274 - 402 m";
$str = "reef-associated; non-migratory; marine; depth range 6 - 80 m (Ref. 9334), usually 6 - 20 m (Ref. 6852)";
$str = "demersal; freshwater; pH range: 6.6 - 36,751.0; depth range 0 - 1 m (Ref. 58018)";
$parts = self::get_description_parts($str, false);
print_r($parts);
$a = self::process_habitat_data($parts);
print_r($a);
exit;
*/
/*
$str = "33.7 cm SL (male/unsexed; (Ref. 93606)); max. reported age: 33 years (Ref. 93630)";
$str = "69.0 cm TL (male/unsexed; (Ref. 5578))";
$str = "4.7 cm SL (male/unsexed; (Ref. 4696)); 3.9 cm SL (female); max. reported age: 1 years (Ref. 232)";
$str = "61.0 cm TL (male/unsexed; (Ref. 58426));
42.9 cm SL (female);
max. published weight: 9,500 g (Ref. 4701);
max. published weight: 5,000.0 g;
max. reported age: 13 years (Ref. 54207)";
$str = "50.0 cm TL (male/unsexed; (Ref. 3506));
133 cm TL (female);
max. published weight: 6,599 g (Ref. 39903);
max. published weight: 2,850.0 g;
max. reported age: 88 years (Ref. 72468)";
$str = str_ireplace("unsexed;", "unsexed", $str);
$parts = self::get_description_parts($str, false);
print_r($parts);
$a = self::process_size_data($parts);
print_r($a);
exit;
*/
self::prepare_data();
// remove tmp dir
$this->TEMP_FILE_PATH = str_ireplace("/fishbase", "", $this->TEMP_FILE_PATH);
// if($this->TEMP_FILE_PATH) shell_exec("rm -fr $this->TEMP_FILE_PATH");
recursive_rmdir($this->TEMP_FILE_PATH);
// debug uncomment in real operation
echo "\n temporary directory removed: " . $this->TEMP_FILE_PATH;
if ($this->test_run) {
return $all_taxa;
}
//used in testing
}
public function __construct()
{
$this->mysqli =& $GLOBALS['db_connection'];
if ($GLOBALS['ENV_NAME'] == 'production' && environment_defined('slave')) {
$this->mysqli_slave = load_mysql_environment('slave');
} else {
$this->mysqli_slave =& $this->mysqli;
}
$this->output_directory = DOC_ROOT . "temp/eol_names_and_ranks_to_family_archive/";
recursive_rmdir($this->output_directory);
$this->archive_builder = new \eol_schema\ContentArchiveBuilder(array('directory_path' => $this->output_directory));
$this->load_all_ranks();
$this->load_all_hierarchies();
}
public function build_archive()
{
$this->path_to_archive_directory = CONTENT_RESOURCE_LOCAL_PATH . "/{$this->resource_id}/";
$this->archive_builder = new \eol_schema\ContentArchiveBuilder(array('directory_path' => $this->path_to_archive_directory));
if ($download_directory = ContentManager::download_temp_file_and_assign_extension(self::DUMP_URL)) {
if (is_dir($download_directory) && file_exists($download_directory . "/names.dmp")) {
$this->download_directory = $download_directory;
$this->get_names();
$this->get_nodes();
recursive_rmdir($download_directory);
}
}
$this->archive_builder->finalize(true);
}
function process_xml($params)
{
$all_taxa = self::get_taxa_list_from_biogeodb();
$this->taxa_id_list = array_merge($all_taxa, self::get_taxa_list_from_myspecies());
require_library('connectors/INBioAPI');
$func = new INBioAPI();
$paths = $func->extract_archive_file($params["eol_xml_file"], $params["filename"], array("timeout" => 7200, "expire_seconds" => false));
print_r($paths);
$params["path"] = $paths["temp_dir"];
$xml = self::update_xml($params);
recursive_rmdir($paths["temp_dir"]);
// remove temp dir
return $xml;
}
function generate_IUCN_data()
{
$basename = $this->export_basename;
$text_path = self::load_zip_contents($this->species_list_export, $this->download_options, array($basename), ".csv");
print_r($text_path);
self::csv_to_array($text_path[$basename]);
$this->archive_builder->finalize(TRUE);
// remove temp dir
$path = $text_path[$basename];
$parts = pathinfo($path);
$parts["dirname"] = str_ireplace($basename, "", $parts["dirname"]);
recursive_rmdir($parts["dirname"]);
debug("\n temporary directory removed: " . $parts["dirname"]);
print_r($this->debug);
}
function get_all_taxa()
{
require_library('connectors/INBioAPI');
$func = new INBioAPI();
$paths = $func->extract_archive_file($this->dwca_file, "meta.xml");
$archive_path = $paths['archive_path'];
$harvester = new ContentArchiveReader(NULL, $archive_path);
$tables = $harvester->tables;
if (!($this->fields["taxa"] = $tables["http://rs.tdwg.org/dwc/terms/taxon"][0]->fields)) {
debug("Invalid archive file. Program will terminate.");
return false;
}
if ($records = $harvester->process_row_type('http://rs.gbif.org/terms/1.0/Reference')) {
self::get_references($records);
}
if ($records = $harvester->process_row_type('http://rs.tdwg.org/dwc/terms/Taxon')) {
$taxa_id_list = self::get_taxa_id_list($records);
self::create_instances_from_taxon_object($records, $taxa_id_list);
}
if ($this->params["process occurrence"]) {
echo "\nProcessed OCCURRENCE\n";
if ($records = $harvester->process_row_type('http://rs.tdwg.org/dwc/terms/Occurrence')) {
$this->uris = self::get_uris();
self::get_occurrences($records);
}
}
if ($records = $harvester->process_row_type('http://rs.gbif.org/terms/1.0/Distribution')) {
self::get_distributions($records);
}
if ($records = $harvester->process_row_type('http://rs.gbif.org/terms/1.0/Image')) {
self::get_images($records);
}
//http://eol.org/content_partners/159/resources/345
if ($records = $harvester->process_row_type('http://rs.gbif.org/terms/1.0/Description')) {
self::get_descriptions($records);
}
//http://eol.org/content_partners/159/resources/332
if ($records = $harvester->process_row_type('http://rs.gbif.org/terms/1.0/VernacularName')) {
self::get_vernaculars($records);
}
$this->archive_builder->finalize(TRUE);
// remove temp dir
recursive_rmdir($paths['temp_dir']);
echo "\n temporary directory removed: " . $paths['temp_dir'];
print_r($this->debug);
}
function generate_traits_for_taxa($params)
{
$this->temp_dir = create_temp_dir() . "/";
$taxa = self::access_spreadsheet($params, 0);
$this->traits = self::access_spreadsheet($params, 1);
self::process_taxa($taxa, "get_measurement_fields");
self::initialize_text_files();
self::process_taxa($taxa, "process_taxa");
self::delete_blank_text_files();
// compress text files, delete temp dir
$trait_request_dir_path = DOC_ROOT . "/public/tmp/trait_request/";
if (!is_dir($trait_request_dir_path)) {
mkdir($trait_request_dir_path);
}
$command_line = "tar -czf " . $trait_request_dir_path . $params["name"] . ".tar.gz --directory=" . $this->temp_dir . " .";
$output = shell_exec($command_line);
recursive_rmdir($this->temp_dir);
}
function get_all_taxa($resource_id)
{
$this->uris = self::get_uris();
$this->bibliographic_citation = self::get_fishbase_remote_citation();
/*
$str = "Circumglobal in coastal warm temperate and tropical seas (Ref. 13562). Western Atlantic: North Carolina, USA to Uruguay, including the Gulf of Mexico and Caribbean. Eastern Atlantic: Mediterranean and Morocco to Senegal. Indo-Pacific: throughout the Indian Ocean; Ryukyu Islands to New Caledonia and French Polynesia. Eastern Pacific: southern Baja California, Mexico to Peru. Highly migratory species, Annex I of the 1982 Convention on the Law of the Sea (Ref. 26139).";
$str = "Western Atlantic: o River basin (Ref. 3498, 40587, 81627), but also in Ogowe River, Kouilou-Niari River and Loeme River (Ref. 3498, 40587, 81627, Ref. 2)Panama to southern Brazil and Uruguay (Ref. 58839) (Ref. 5663, 89864) bvhgbhghty hbgj nh b hgv (Ref. 2921, Ref. 3515).";
$texts = self::process_distribution_text($str);
print_r($texts); exit;
*/
/*
$str = "bathydemersal; marine; depth range 549 - 1202 m (Ref. 97189)";
$str = "benthopelagic; potamodromous (Ref. 51243); freshwater; brackish; pH range: 7.0 - 7.5; dH range: 15; depth range 1 - ? m (Ref. 9696)";
$str = "depth range 220 - 457 m, usually 274 - 402 m";
$str = "reef-associated; non-migratory; marine; depth range 6 - 80 m (Ref. 9334), usually 6 - 20 m (Ref. 6852)";
$str = "non-migratory; freshwater; anadromous; pH range: 6.6 - 36,751.0; depth range 0 - 1 m (Ref. 58018)";
$str = "pH range: 6.6; depth range 220 - 457 m, usually 274 - 402 m";
$str = "depth range 220 - 457 m; benthopelagic; freshwater, usually ? - 10 m (Ref. 5595)";
$str = "demersal; amphidromous? (Ref. 51243); freshwater; brackish; marine; depth range ? - 5 m (Ref. 6733)";
$parts = self::get_description_parts($str, false); print_r($parts);
$a = self::process_habitat_data($parts); print_r($a); exit;
*/
/*
$str = "33.7 cm SL (male/unsexed; (Ref. 93606)); max. reported age: 33 years (Ref. 93630)";
$str = "69.0 cm TL (male/unsexed; (Ref. 5578))";
$str = "4.7 cm SL (male/unsexed; (Ref. 4696)); 3.9 cm SL (female); max. reported age: 1 years (Ref. 232)";
$str = "61.0 cm TL (male/unsexed; (Ref. 58426)); 42.9 cm SL (female); max. published weight: 9,500 g (Ref. 4701); max. published weight: 5,000.0 g; max. reported age: 13 years (Ref. 54207)";
$str = "50.0 cm TL (male/unsexed; (Ref. 3506)); 133 cm TL (female); max. published weight: 6,599 g (Ref. 39903); max. published weight: 2,850.0 g; max. reported age: 88 years (Ref. 72468)";
$str = str_ireplace("unsexed;", "unsexed", $str);
$parts = self::get_description_parts($str, false); print_r($parts);
$a = self::process_size_data($parts); print_r($a); exit;
*/
self::prepare_data();
// remove tmp dir
$this->TEMP_FILE_PATH = str_ireplace("/fishbase", "", $this->TEMP_FILE_PATH);
// if($this->TEMP_FILE_PATH) shell_exec("rm -fr $this->TEMP_FILE_PATH");
recursive_rmdir($this->TEMP_FILE_PATH);
// debug uncomment in real operation
echo "\n temporary directory removed: " . $this->TEMP_FILE_PATH;
if ($this->test_run) {
return $all_taxa;
}
//used in testing
}
function generate_FEIS_data()
{
$basenames = array_keys($this->export_basenames);
$text_path = self::load_zip_contents($this->species_list_export, array('timeout' => 3600, 'download_attempts' => 1, 'delay_in_minutes' => 1), $basenames, ".csv");
foreach ($this->export_basenames as $type => $uri) {
self::csv_to_array($text_path[$type], $type, $uri);
}
$this->archive_builder->finalize(TRUE);
// remove temp dir
$basename = $basenames[0];
$path = $text_path[$basename];
$parts = pathinfo($path);
$parts["dirname"] = str_ireplace($basename, "", $parts["dirname"]);
recursive_rmdir($parts["dirname"]);
debug("\n temporary directory removed: " . $parts["dirname"]);
if ($val = $this->debug) {
print_r($val);
}
}
function get_all_taxa()
{
if (!self::load_zip_contents()) {
return FALSE;
}
self::assign_name_and_id();
self::process_files("species");
self::process_genera_files();
self::add_higher_level_taxa_to_archive();
$this->create_archive();
// remove temp dir
recursive_rmdir($this->TEMP_FILE_PATH);
echo "\n temporary directory removed: " . $this->TEMP_FILE_PATH;
// some stats
echo "\n count not numeric: " . $this->not_numeric_id;
echo "\n synonyms count: " . $this->syn_count;
echo "\n wrong data: " . $this->no_rank;
// print_r($this->debug); //to list the unique habitat values
}
function clean_media_extension($resource_id, $dwca_file)
{
require_library('connectors/INBioAPI');
$func = new INBioAPI();
if ($paths = $func->extract_archive_file($dwca_file, "meta.xml")) {
print_r($paths);
if ($contents = Functions::get_remote_file($paths['archive_path'] . "media.txt", array('timeout' => 172800))) {
$contents = str_ireplace('<a title=""', '<a title="', $contents);
$contents = str_ireplace('"" href=""', '" href="', $contents);
$contents = str_ireplace('"">', '">', $contents);
//saving new media.txt
if (!($WRITE = fopen($paths['archive_path'] . "media.txt", "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $paths['archive_path'] . "media.txt");
return;
}
fwrite($WRITE, $contents);
fclose($WRITE);
// remove the archive file e.g. plazi.zip
$info = pathinfo($dwca_file);
unlink($paths['archive_path'] . $info["basename"]);
// creating the archive file
$command_line = "tar -czf " . CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".tar.gz --directory=" . $paths['archive_path'] . " .";
$output = shell_exec($command_line);
// moving files to /resources/
recursive_rmdir(CONTENT_RESOURCE_LOCAL_PATH . $resource_id);
if (!file_exists(CONTENT_RESOURCE_LOCAL_PATH . $resource_id)) {
mkdir(CONTENT_RESOURCE_LOCAL_PATH . $resource_id);
}
$src = $paths['archive_path'];
$dst = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . "/";
$files = glob($paths['archive_path'] . "*.*");
foreach ($files as $file) {
$file_to_go = str_replace($src, $dst, $file);
copy($file, $file_to_go);
}
}
// remove temp dir
recursive_rmdir($paths['archive_path']);
echo "\n temporary directory removed: " . $paths['archive_path'];
}
}
public function __construct()
{
$this->mysqli =& $GLOBALS['db_connection'];
if ($GLOBALS['ENV_NAME'] == 'production' && environment_defined('slave')) {
$this->mysqli_slave = load_mysql_environment('slave');
} else {
$this->mysqli_slave =& $this->mysqli;
}
$this->output_directory = DOC_ROOT . "temp/eol_archive_objects/";
recursive_rmdir($this->output_directory);
$this->archive_builder = new \eol_schema\ContentArchiveBuilder(array('directory_path' => $this->output_directory));
$this->load_all_ranks();
$this->load_all_hierarchies();
$this->load_all_data_types();
$this->load_all_mime_types();
$this->load_all_languages();
$this->load_all_licenses();
$this->load_all_curated_object_associations();
$this->load_all_user_object_associations();
$this->load_all_resources();
$this->initital_object_associations = array_merge($this->curated_data_objects_taxa, $this->user_data_objects_taxa);
}
function export_gbif_to_eol($params)
{
$this->uris = self::get_uris($params, $params["uri_file"]);
$params["uri_type"] = "citation";
if ($file = @$params["citation_file"]) {
$this->citations = self::get_uris($params, $file);
}
require_library('connectors/INBioAPI');
$func = new INBioAPI();
$paths = $func->extract_archive_file($params["dwca_file"], "meta.xml", array("timeout" => 7200, "expire_seconds" => 0));
$archive_path = $paths['archive_path'];
$temp_dir = $paths['temp_dir'];
$this->harvester = new ContentArchiveReader(NULL, $archive_path);
if (!@$this->harvester->tables["http://rs.tdwg.org/dwc/terms/occurrence"][0]->fields) {
echo "\nInvalid archive file. Program will terminate.\n";
return false;
}
if ($params["dataset"] == "GBIF") {
$params["row_type"] = "http://rs.tdwg.org/dwc/terms/occurrence";
$params["location"] = "occurrence.txt";
self::process_row_type($params);
} elseif ($params["dataset"] == "iDigBio") {
$params["row_type"] = "http://rs.tdwg.org/dwc/terms/occurrence";
$params["location"] = "occurrence.txt";
self::process_row_type($params);
}
/* old ways
self::process_row_type(array("row_type" => 'http://rs.gbif.org/terms/1.0/Multimedia', "location" => "multimedia.txt"));
self::create_instances_from_taxon_object($harvester->process_row_type('http://rs.tdwg.org/dwc/terms/occurrence'));
self::get_media_objects($harvester->process_row_type('http://rs.gbif.org/terms/1.0/Multimedia'));
self::get_objects($harvester->process_row_type('http://eol.org/schema/media/Document'));
self::get_references($harvester->process_row_type('http://rs.gbif.org/terms/1.0/Reference'));
*/
$this->archive_builder->finalize(TRUE);
recursive_rmdir($temp_dir);
// remove temp dir
print_r($this->debug);
}
function export_xml_to_archive($params, $xml_file_YN = false)
{
if (!$xml_file_YN) {
require_library('connectors/INBioAPI');
$func = new INBioAPI();
$paths = $func->extract_archive_file($params["eol_xml_file"], $params["filename"], array("timeout" => 7200, "expire_seconds" => 0));
// "expire_seconds" -- false => won't expire; 0 => expires now //debug
print_r($paths);
$params["path"] = $paths["temp_dir"];
self::convert_xml($params);
$this->archive_builder->finalize(TRUE);
recursive_rmdir($paths["temp_dir"]);
// remove temp dir
} else {
$params['path'] = DOC_ROOT . "tmp/";
$local_xml_file = Functions::save_remote_file_to_local($params['eol_xml_file'], array('file_extension' => "xml", 'cache' => 0, "timeout" => 7200, "download_attempts" => 2, "delay_in_minutes" => 2));
//debug - cache should be 0 zero in normal operation
$params['filename'] = pathinfo($local_xml_file, PATHINFO_BASENAME);
self::convert_xml($params);
$this->archive_builder->finalize(TRUE);
unlink($local_xml_file);
}
}
