public static function get_all_taxa($resource_id)
{
$data = self::prepare_data();
$all_taxa = array();
$used_collection_ids = array();
$i = 0;
$total = count(array_keys($data));
foreach (array_keys($data) as $taxon) {
$i++;
print "\n{$i} of {$total} [{$taxon}]\n";
$taxon_record = $data[$taxon];
$taxon_record["name"] = $taxon;
$arr = self::get_BoldsImages_taxa($taxon_record, $used_collection_ids);
$page_taxa = $arr[0];
$used_collection_ids = $arr[1];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
}
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$resource_path = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
}
function get_all_taxa($resource_id)
{
$this->observers = self::get_observers();
$this->activities = self::get_activities();
self::get_associations();
self::get_general_descriptions();
self::prepare_common_names();
echo "\n total: " . count($GLOBALS['taxon']) . "\n";
$all_taxa = array();
$i = 0;
$total = count(array_keys($GLOBALS['taxon']));
foreach ($GLOBALS['taxon'] as $taxon_name => $record) {
$i++;
if ($i % 100 == 0) {
echo "\n{$i} of {$total} " . $taxon_name;
}
$record["taxon_name"] = $taxon_name;
$arr = self::get_visitors_taxa($record);
$page_taxa = $arr[0];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
}
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$resource_path = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
return $all_taxa;
//used for testing
}
function get_all_taxa($resource_id)
{
self::get_associations();
if ($this->debug_info) {
echo "\n\n total: " . count($GLOBALS['taxon']) . "\n";
}
$all_taxa = array();
$i = 0;
$total = count(array_keys($GLOBALS['taxon']));
foreach ($GLOBALS['taxon'] as $taxon_name => $record) {
$i++;
if ($this->debug_info) {
echo "\n{$i} of {$total} " . $taxon_name;
}
$record["taxon_name"] = $taxon_name;
$arr = self::get_plant_feeding_taxa($record);
$page_taxa = $arr[0];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
}
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$resource_path = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
return $all_taxa;
//used for testing
}
function get_videos_from_vimeo()
{
echo "\n -- start access to vimeo ";
$resource_id = "temp_vimeo_to_tamborine2";
require_library('connectors/VimeoAPI');
$taxa = VimeoAPI::get_all_taxa(array("user1632860"));
// Peter Kuttner's id
$xml = \SchemaDocument::get_taxon_xml($taxa);
$resource_path = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
echo " -- end.\n";
}
public function get_all_taxa_keys($resource_id)
{
require_library('connectors/DiscoverLifeAPIv2');
$func = new DiscoverLifeAPIv2();
$taxa_objects = self::process_keys_spreadsheet();
$all_taxa = array();
$used_collection_ids = array();
//initialize text file for DiscoverLife: save names without a page in EOL
self::initialize_text_file(DOC_ROOT . self::TEXT_FILE_FOR_DL . "_" . "id_keys" . ".txt");
$i = 0;
$save_count = 0;
$no_eol_page = 0;
foreach ($taxa_objects as $name => $fields) {
$i++;
//filter names. Process only those who already have a page in EOL. Report back to DiscoverLife names not found in EOL
if (!($taxon = $func->with_eol_page($name))) {
print "\n {$i} - no EOL page ({$name})";
$no_eol_page++;
self::store_name_to_text_file($name, "ID_Keys");
continue;
}
$taxon["keys"] = array();
foreach ($fields as $field) {
$taxon["keys"][] = $field;
}
print "\n {$i} -- " . $taxon['orig_sciname'];
//================================
$arr = self::get_discoverlife_taxa($taxon, $used_collection_ids);
$page_taxa = $arr[0];
$used_collection_ids = $arr[1];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
}
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$resource_path = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
$with_eol_page = $i - $no_eol_page;
print "\n\n total = {$i} \n With EOL page = {$with_eol_page} \n No EOL page = {$no_eol_page} \n\n";
}
function get_all_taxa($resource_id)
{
$xml = Functions::get_hashed_response(CONTENT_RESOURCE_LOCAL_PATH . "35.xml");
$all_taxa = array();
$i = 0;
$total = count($xml->taxon);
foreach ($xml->taxon as $t) {
$i++;
$t_dwc = $t->children("http://rs.tdwg.org/dwc/dwcore/");
$t_dc = $t->children("http://purl.org/dc/elements/1.1/");
print "\n {$i} of {$total} " . $t_dc->identifier;
$url = str_replace('xxx', str_replace('STRI-fish-', '', $t_dc->identifier), $this->map_url);
print " [{$url}] ";
if ($file = fopen($url, "r")) {
if (stripos(fgets($file), "no_website_found")) {
print " - no map";
} else {
print " - with map";
$taxon_record["taxon"] = array("sciname" => $t_dwc->ScientificName, "family" => $t_dwc->Family, "kingdom" => '', "phylum" => '', "class" => '', "order" => '', "id" => str_replace('STRI-fish-', '', $t_dc->identifier), "mediaURL" => $url, "source" => $this->taxon_page . str_replace('STRI-fish-', '', $t_dc->identifier));
$taxon_record["dataobjects"] = array();
$arr = self::get_stri_taxa($taxon_record);
$page_taxa = $arr[0];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
}
} else {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $url);
}
}
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$resource_path = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
}
public function get_all_taxa($resource_id)
{
// Delete temp files, possible remnants from interrupted runs
Functions::delete_temp_files($this->OBIS_DATA_PATH . "temp_obis_", "xml");
Functions::delete_temp_files($this->OBIS_DATA_PATH . "temp_", "csv");
//divide big file to a more consumable chunks
$file_count = self::divide_big_csv_file(40000);
//debug orig is 40000
if ($file_count === false) {
return false;
}
$all_taxa = array();
$used_collection_ids = array();
for ($i = 1; $i <= $file_count; $i++) {
echo "\nprocessing {$i} => \n";
$arr = self::get_obis_taxa($this->OBIS_DATA_PATH . "temp_" . $i . ".csv", $used_collection_ids);
$page_taxa = $arr[0];
$used_collection_ids = $arr[1];
$xml = \SchemaDocument::get_taxon_xml($page_taxa);
$resource_path = $this->OBIS_DATA_PATH . "temp_obis_" . $i . ".xml";
if (!($OUT = Functions::file_open($resource_path, "w"))) {
return;
}
fwrite($OUT, $xml);
fclose($OUT);
}
// Combine all XML files.
Functions::combine_all_eol_resource_xmls($resource_id, $this->OBIS_DATA_PATH . "temp_obis_*.xml");
// Set to force harvest
if (filesize(CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml")) {
$GLOBALS['db_connection']->update("UPDATE resources SET resource_status_id=" . ResourceStatus::force_harvest()->id . " WHERE id=" . $resource_id);
}
// Delete temp files
Functions::delete_temp_files($this->OBIS_DATA_PATH . "temp_obis_", "xml");
Functions::delete_temp_files($this->OBIS_DATA_PATH . "temp_", "csv");
}
$dc_source = $url_for_nematocysts;
$subject = "http://rs.tdwg.org/ontology/voc/SPMInfoItems#Biology";
$data_object_parameters = get_data_object("text", $taxon, "nematocyst", $dc_source, $agent_name, $agent_role, $html_nematocysts, $copyright, $image_url, $title, $subject);
$taxon_parameters["dataObjects"][] = new \SchemaDataObject($data_object_parameters);
}
//end
$used_taxa[$taxon] = $taxon_parameters;
}
//with photos
//end main loop
}
foreach ($used_taxa as $taxon_parameters) {
$schema_taxa[] = new \SchemaTaxon($taxon_parameters);
}
////////////////////// ---
$new_resource_xml = SchemaDocument::get_taxon_xml($schema_taxa);
$old_resource_path = CONTENT_RESOURCE_LOCAL_PATH . $resource->id . ".xml";
if (!($OUT = fopen($old_resource_path, "w+"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $old_resource_path);
return;
}
fwrite($OUT, $new_resource_xml);
fclose($OUT);
////////////////////// ---
$elapsed_time_sec = microtime(1) - $timestart;
echo "{$wrap}";
echo "elapsed time = {$elapsed_time_sec} sec \n";
echo "elapsed time = " . $elapsed_time_sec / 60 . " min \n";
echo "elapsed time = " . $elapsed_time_sec / 60 / 60 . " hr \n";
echo "{$wrap}{$wrap} Done processing.";
//######################################################################################################################
public function create_specialist_project_xml($taxon_info, $text_desc = NULL, $multimedia = NULL, $common_names = NULL, $synonyms = NULL, $do_details = NULL)
{
$schema_taxa = array();
$used_taxa = array();
$i = 0;
$references = $do_details['references'];
//formerly Scientific Name
foreach ($taxon_info["Scientific Name"] as $sciname) {
if (!trim($sciname)) {
$i++;
continue;
}
$taxon_identifier = self::format($sciname);
if (@$used_taxa[$taxon_identifier]) {
$taxon_parameters = $used_taxa[$taxon_identifier];
} else {
$taxon_parameters = array();
$taxon_parameters["identifier"] = self::format(@$taxon_info["ID"][$i]);
$taxon_parameters["kingdom"] = ucfirst(self::format(@$taxon_info["Kingdom"][$i]));
$taxon_parameters["phylum"] = ucfirst(self::format(@$taxon_info["Phylum"][$i]));
$taxon_parameters["class"] = ucfirst(self::format(@$taxon_info["Class"][$i]));
$taxon_parameters["order"] = ucfirst(self::format(@$taxon_info["Order"][$i]));
$taxon_parameters["family"] = ucfirst(self::format(@$taxon_info["Family"][$i]));
$taxon_parameters["genus"] = ucfirst(self::format(@$taxon_info["Genus"][$i]));
$taxon_parameters["scientificName"] = ucfirst(self::format(@$taxon_info["Scientific Name"][$i]));
$taxon_parameters["source"] = trim(self::format(@$taxon_info["Source URL"][$i]));
//start taxon reference
$taxon_parameters["references"] = array();
$refs = array();
$reference_code = self::format(@$taxon_info["Reference Code"][$i]);
$reference_code = str_ireplace(" ", "", $reference_code);
foreach (explode(",", $reference_code) as $ref_code) {
$referenceParameters = array();
$referenceParameters["fullReference"] = self::format(@$references[$ref_code]['Bibliographic Citation']);
if (@$references[$ref_code]['URL'] || @$references[$ref_code]['ISBN']) {
$referenceParameters["referenceIdentifiers"][] = new \SchemaReferenceIdentifier(array("label" => "url", "value" => self::format(@$references[$ref_code]['URL'])));
$referenceParameters["referenceIdentifiers"][] = new \SchemaReferenceIdentifier(array("label" => "isbn", "value" => self::format(@$references[$ref_code]['ISBN'])));
}
$refs[] = new \SchemaReference($referenceParameters);
}
$taxon_parameters["references"] = $refs;
//end taxon reference
//start preferred common names
$taxon_parameters["commonNames"] = array();
if (@$taxon_info["Preferred Common Name"][$i]) {
$taxon_parameters["commonNames"][] = new \SchemaCommonName(array("name" => self::format(@$taxon_info["Preferred Common Name"][$i]), "language" => self::format(@$taxon_info["Language of Common Name"][$i])));
}
//end preferred common names
//start common names
if (@$common_names[$taxon_identifier]) {
foreach (@$common_names[$taxon_identifier] as $rec) {
if ($rec) {
$taxon_parameters["commonNames"][] = new \SchemaCommonName(array("name" => self::format($rec['Common Name']), "language" => self::format($rec['Language'])));
}
}
}
//end common names
//start synonyms
$taxon_params["synonyms"] = array();
if (@$synonyms[$taxon_identifier]) {
foreach (@$synonyms[$taxon_identifier] as $rec) {
$taxon_parameters["synonyms"][] = new \SchemaSynonym(array("synonym" => self::format($rec['Synonym']), "relationship" => self::format($rec['Relationship'])));
}
}
//end synonyms
//start data objects
$dataObjects = array();
$text_desc_title = $text_desc[''];
/* to get the title e.g. 'Associations': $text_desc_title[0]['Associations'] */
$temp = self::prepare_text_dataObject(@$text_desc[$taxon_identifier], $do_details, $text_desc_title);
$dataObjects = array_merge($dataObjects, $temp);
$temp = self::prepare_media_dataObject(@$multimedia[$taxon_identifier], $do_details);
$dataObjects = array_merge($dataObjects, $temp);
foreach ($dataObjects as $object) {
$taxon_parameters["dataObjects"][] = new \SchemaDataObject($object);
unset($object);
}
//end data objects
@($used_taxa[$taxon_identifier] = $taxon_parameters);
}
@($used_taxa[$taxon_identifier] = $taxon_parameters);
$i++;
}
foreach ($used_taxa as $taxon_parameters) {
$schema_taxa[] = new \SchemaTaxon($taxon_parameters);
}
return \SchemaDocument::get_taxon_xml($schema_taxa);
}
}
}
if ($description) {
$dataObjects[] = get_data_object($amphibID . "_description", "Description", $description, "http://rs.tdwg.org/ontology/voc/SPMInfoItems#GeneralDescription", $refs, $agents, $pageURL);
}
/* we didn't get <comments>
if($comments) $dataObjects[] = get_data_object("Comments", $comments, "http://rs.tdwg.org/ontology/voc/SPMInfoItems#GeneralDescription", $refs, $agents, $pageURL);
*/
foreach ($dataObjects as $k => $v) {
$taxonParameters["dataObjects"][] = new \SchemaDataObject($v);
unset($v);
}
$taxa[] = new \SchemaTaxon($taxonParameters);
//if($i >= 5) break; //debug
}
$new_resource_xml = \SchemaDocument::get_taxon_xml($taxa);
$old_resource_path = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml";
if (!($OUT = Functions::file_open($old_resource_path, "w+"))) {
return;
}
fwrite($OUT, $new_resource_xml);
fclose($OUT);
Functions::set_resource_status_to_force_harvest($resource_id);
shell_exec("rm " . $new_resource_path);
//--------
// 0x73 0x20 0x68 0x61
$xml_path = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml";
if ($xml = Functions::lookup_with_cache($xml_path, array('timeout' => 1200, 'download_attempts' => 5, 'expire_seconds' => true))) {
// $xml = str_replace(chr(0x73)." ".chr(0x20)." ".chr(0x73)." ".chr(0x6B), " ", $xml);
// $xml = str_replace(array(chr(0x73), chr(0x20), chr(0x68), chr(0x61)), " ", $xml);
$xml = str_replace(array(0x73, 0x20, 0x73, 0x6b), " ", $xml);
function get_all_taxa($task, $temp_file_path)
{
$all_taxa = array();
$used_collection_ids = array();
$filename = $temp_file_path . $task . ".txt";
echo "\nfilename: [{$filename}]";
$i = 0;
foreach (new FileIterator($filename) as $line_number => $line) {
self::check_server_downtime();
if ($line) {
$i++;
echo "\n{$i} ";
$line = trim($line);
$fields = explode("\t", $line);
$taxon_id = trim($fields[0]);
$arr = self::get_tropicos_taxa($taxon_id, $used_collection_ids);
$page_taxa = $arr[0];
$used_collection_ids = $arr[1];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
} else {
echo "\n Task list: end-of-file";
}
}
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
// $xml = self::add_rating_to_image_object($xml, '1.0');
$resource_path = $temp_file_path . "temp_tropicos_" . $task . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
}
// .3 seconds wait time
include_once dirname(__FILE__) . "/../../config/environment.php";
$resource_id = 15;
if (!Functions::can_this_connector_run($resource_id)) {
return;
}
require_library('FlickrAPI');
$GLOBALS['ENV_DEBUG'] = false;
$auth_token = NULL;
if (FlickrAPI::valid_auth_token(FLICKR_AUTH_TOKEN)) {
$auth_token = FLICKR_AUTH_TOKEN;
}
// create new _temp file
if (!($resource_file = Functions::file_open(CONTENT_RESOURCE_LOCAL_PATH . $resource_id . "_temp.xml", "w+"))) {
return;
}
// start the resource file with the XML header
fwrite($resource_file, \SchemaDocument::xml_header());
// query Flickr and write results to file
FlickrAPI::get_all_eol_photos($auth_token, $resource_file);
// write the resource footer
fwrite($resource_file, \SchemaDocument::xml_footer());
fclose($resource_file);
// cache the previous version and make this new version the current version
@unlink(CONTENT_RESOURCE_LOCAL_PATH . $resource_id . "_previous.xml");
Functions::file_rename(CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml", CONTENT_RESOURCE_LOCAL_PATH . $resource_id . "_previous.xml");
Functions::file_rename(CONTENT_RESOURCE_LOCAL_PATH . $resource_id . "_temp.xml", CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml");
// set Flickr to force harvest
if (filesize(CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml") > 600) {
Functions::set_resource_status_to_force_harvest($resource_id);
}
function get_all_taxa($resource_id)
{
$data = self::prepare_data();
if ($data === false) {
return false;
}
$taxa = $data["taxon"];
$taxon_comnames = $data["taxon_comnames"];
$taxon_references = $data["taxon_references"];
$taxon_synonyms = $data["taxon_synonyms"];
$taxon_dataobject = $data["taxon_dataobject"];
$GLOBALS['taxon_dataobject_agent'] = $data["taxon_dataobject_agent"];
$GLOBALS['taxon_dataobject_reference'] = $data["taxon_dataobject_reference"];
$all_taxa = array();
$i = 0;
$total = count(array_keys($taxa));
$batch = 1000;
//debug orig 1000
$batch_count = 0;
foreach ($taxa as $taxon) {
// if($taxon["dc_identifier"] != "FB-47873") continue; // debug
$i++;
debug("\n{$i} of {$total} " . $taxon["dwc_ScientificName"]);
$taxon_record["taxon"] = $taxon;
$taxon_id = $taxon["int_id"];
$taxon_record["common_names"] = @$taxon_comnames[$taxon_id];
$taxon_record["references"] = @$taxon_references[$taxon_id];
$taxon_record["synonyms"] = @$taxon_synonyms[$taxon_id];
$taxon_record["dataobjects"] = @$taxon_dataobject[$taxon_id];
$arr = self::get_FishBase_taxa($taxon_record);
$page_taxa = $arr[0];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
if ($i % $batch == 0) {
$batch_count++;
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$resource_path = $this->TEMP_FILE_PATH . "FB_" . $batch_count . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
$all_taxa = array();
}
}
//last batch
$batch_count++;
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$resource_path = $this->TEMP_FILE_PATH . "FB_" . $batch_count . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
Functions::combine_all_eol_resource_xmls($resource_id, $this->TEMP_FILE_PATH . "FB_*.xml");
self::delete_temp_files($this->TEMP_FILE_PATH . "FB_*.xml");
// remove tmp dir
$this->TEMP_FILE_PATH = str_ireplace("/fishbase", "", $this->TEMP_FILE_PATH);
if ($this->TEMP_FILE_PATH) {
shell_exec("rm -fr {$this->TEMP_FILE_PATH}");
}
if ($this->test_run) {
return $all_taxa;
}
//used in testing
}
function get_all_taxa($task, $temp_file_path)
{
$all_taxa = array();
$used_collection_ids = array();
$filename = $temp_file_path . $task . ".txt";
$records = self::get_array_from_json_file($filename);
$num_rows = sizeof($records);
$i = 0;
foreach ($records as $rec) {
$i++;
echo "\n [{$i} of {$num_rows}] ";
echo $rec['taxonomy']['species']['taxon']['name'];
// if(trim($rec['taxonomy']['species']['taxon']['name']) != "Lumbricus centralis") continue; //debug
$arr = $this->get_boldsys_taxa($rec, $used_collection_ids);
$page_taxa = $arr[0];
$used_collection_ids = $arr[1];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
}
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$xml = str_replace("</mediaURL>", "</mediaURL><additionalInformation><subtype>map</subtype>\n</additionalInformation>\n", $xml);
$resource_path = $temp_file_path . $task . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
}
public function get_all_taxa($resource_id)
{
$all_taxa = array();
$this->used_collection_ids = array();
$urls = array(FWP_SPECIES_DOC_PATH);
// you can have multiple sources of the species.xls
$taxa_arr = self::compile_taxa($urls);
require_library('XLSParser');
$parser = new XLSParser();
$images = self::prepare_table($parser->convert_sheet_to_array(FWP_IMAGES_DOC_PATH), "multiple", "SId", "SId", "PictureId", "dbo_Picture_PictureNote", "PictureType", "IsLegal", "Location", "PicComments", "IsAvailable", "LifeStage", "CollectionName", "CollectionAcronym", "PictureSource", "Surname", "Firstname", "DisplayName", "FileName");
$comnames = self::prepare_table($parser->convert_sheet_to_array(FWP_COMNAMES_DOC_PATH), "multiple", "SId", "CommonName", "Language");
$synonyms = self::prepare_table($parser->convert_sheet_to_array(FWP_SYNONYMS_DOC_PATH), "multiple", "SId", "SynGenusSpecies", "SynStatus");
$i = 1;
$total = sizeof($taxa_arr);
$j = 0;
foreach ($taxa_arr as $taxon_arr) {
echo "\n {$i} of {$total} -- " . $taxon_arr['SId'];
$i++;
$taxon_id = $taxon_arr['SId'];
$page_taxa = self::get_fishwise_taxa($taxon_arr, @$images[$taxon_id], @$comnames[$taxon_id], @$synonyms[$taxon_id]);
$all_taxa = array_merge($all_taxa, $page_taxa);
if ($i % 10000 == 0) {
$j++;
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$j_str = Functions::format_number_with_leading_zeros($j, 3);
$resource_path = DOC_ROOT . "/update_resources/connectors/files/FishWisePro/" . $j_str . ".xml";
if (!($OUT = fopen($resource_path, "w+"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
$all_taxa = array();
}
}
if ($all_taxa) {
$j++;
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$j_str = Functions::format_number_with_leading_zeros($j, 3);
$resource_path = DOC_ROOT . "/update_resources/connectors/files/FishWisePro/" . $j_str . ".xml";
if (!($OUT = fopen($resource_path, "w+"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
}
Functions::combine_all_eol_resource_xmls($resource_id, DOC_ROOT . "/update_resources/connectors/files/FishWisePro/*.xml");
self::delete_files(DOC_ROOT . "/update_resources/connectors/files/FishWisePro/*.xml");
return;
}
private function get_all_taxa($task)
{
require_library('CheckIfNameHasAnEOLPage');
$func = new CheckIfNameHasAnEOLPage();
$all_taxa = array();
$used_collection_ids = array();
//initialize text file for DiscoverLife: save names without a page in EOL
self::initialize_text_file(self::$TEXT_FILE_FOR_DL);
$filename = self::$TEMP_FILE_PATH . $task . ".txt";
if (!($FILE = fopen($filename, "r"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $filename);
return;
}
$i = 0;
$save_count = 0;
$no_eol_page = 0;
while (!feof($FILE)) {
if ($line = fgets($FILE)) {
sleep(1);
$name = trim($line);
$i++;
//Filter names. Process only those who already have a page in EOL. Report back to DiscoverLife names not found in EOL
$arr = $func->check_if_name_has_EOL_page($name);
$if_name_has_page_in_EOL = $arr[0];
$xml_from_api = $arr[1];
if (!$if_name_has_page_in_EOL) {
print "\n - no EOL page ({$name})";
$no_eol_page++;
self::store_name_to_text_file($name, $task);
continue;
}
$taxon = array();
$taxon = $func->get_taxon_simple_stat($name, $xml_from_api);
$taxon["map"] = 1;
if (trim($name) == trim(Functions::canonical_form(trim($taxon['sciname'])))) {
$taxon["call_back"] = "taxon_concept_id";
} else {
$taxon["call_back"] = "scientific_name";
}
print "\n {$i} -- " . $taxon['sciname'] . "\n";
$arr = self::get_discoverlife_taxa($taxon, $used_collection_ids);
$page_taxa = $arr[0];
$used_collection_ids = $arr[1];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
}
}
fclose($FILE);
$xml = SchemaDocument::get_taxon_xml($all_taxa);
$resource_path = CONTENT_RESOURCE_LOCAL_PATH . "DiscoverLife/temp_DiscoverLife_" . $task . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
$with_eol_page = $i - $no_eol_page;
print "\n\n total = {$i} \n With EOL page = {$with_eol_page} \n No EOL page = {$no_eol_page} \n\n ";
}
function start($resource_id)
{
$new_resource_path = DOC_ROOT . "temp/" . $resource_id . ".xml";
// $file = 'http://localhost/cp/Amphibiaweb/amphib_dump.xml';
$file = 'http://amphibiaweb.org/amphib_dump.xml';
if (!($new_resource_xml = Functions::lookup_with_cache($file, array('timeout' => 1200, 'download_attempts' => 5, 'expire_seconds' => 86400)))) {
echo "\n\n Content partner's server is down, connector will now terminate.\n";
} else {
// These may look like the same wrong characters - but they are several different wrong characters
$new_resource_xml = str_replace("", "\"", $new_resource_xml);
$new_resource_xml = str_replace("", "\"", $new_resource_xml);
$new_resource_xml = str_replace("", "-", $new_resource_xml);
if (!($OUT = Functions::file_open($new_resource_path, "w+"))) {
return;
}
fwrite($OUT, $new_resource_xml);
fclose($OUT);
unset($new_resource_xml);
$taxa = array();
$xml = simplexml_load_file($new_resource_path);
$total = count($xml->species);
$i = 0;
foreach (@$xml->species as $species) {
$i++;
if ($i % 1000 == 0) {
echo "\n {$i} of {$total} ";
}
$amphibID = (int) trim($species->amphib_id);
$genus = format_utf8((string) trim($species->genus));
$speciesName = format_utf8((string) trim($species->species));
$order = format_utf8((string) trim($species->ordr));
$family = format_utf8((string) trim($species->family));
$commonNames = format_utf8((string) trim($species->common_name));
$commonNames = explode(",", $commonNames);
$submittedBy = format_utf8((string) trim($species->submittedby));
$editedBy = format_utf8((string) trim($species->editedby));
$description = format_utf8((string) trim($species->description));
$distribution = format_utf8((string) trim($species->distribution));
$life_history = format_utf8((string) trim($species->life_history));
$trends_and_threats = format_utf8((string) trim($species->trends_and_threats));
$relation_to_humans = format_utf8((string) trim($species->relation_to_humans));
$comments = format_utf8((string) trim($species->comments));
$ref = format_utf8((string) trim($species->refs));
$separator = "<p>";
$separator = "<p>";
$ref = explode($separator, $ref);
$refs = array();
foreach ($ref as $r) {
$refs[] = array("fullReference" => trim($r));
}
$description = fix_article($description);
$distribution = fix_article($distribution);
$life_history = fix_article($life_history);
$trends_and_threats = fix_article($trends_and_threats);
$relation_to_humans = fix_article($relation_to_humans);
$comments = fix_article($comments);
$pageURL = "http://amphibiaweb.org/cgi/amphib_query?where-genus=" . $genus . "&where-species=" . $speciesName . "&account=amphibiaweb";
if (!$submittedBy) {
continue;
}
$agents = array();
if ($submittedBy) {
$parts = preg_split("/(,| and )/", $submittedBy);
while (list($key, $val) = each($parts)) {
$val = trim($val);
if (!$val) {
continue;
}
$agentParameters = array();
$agentParameters["role"] = "author";
$agentParameters["fullName"] = $val;
$agents[] = new \SchemaAgent($agentParameters);
}
}
$nameString = trim($genus . " " . $speciesName);
$taxonParameters = array();
$taxonParameters["identifier"] = $amphibID;
$taxonParameters["source"] = $pageURL;
$taxonParameters["kingdom"] = "Animalia";
$taxonParameters["phylum"] = "Chordata";
$taxonParameters["class"] = "Amphibia";
$taxonParameters["order"] = $order;
$taxonParameters["family"] = $family;
$taxonParameters["scientificName"] = $nameString;
foreach ($commonNames as $common_name) {
$taxonParameters['commonNames'][] = new \SchemaCommonName(array("name" => $common_name, "language" => "en"));
}
$taxonParameters["dataObjects"] = array();
$dataObjects = array();
if ($distribution) {
$dataObjects[] = get_data_object($amphibID . "_distribution", "Distribution and Habitat", $distribution, "http://rs.tdwg.org/ontology/voc/SPMInfoItems#Distribution", $refs, $agents, $pageURL);
}
if ($life_history) {
$dataObjects[] = get_data_object($amphibID . "_life_history", "Life History, Abundance, Activity, and Special Behaviors", $life_history, "http://rs.tdwg.org/ontology/voc/SPMInfoItems#Trends", $refs, $agents, $pageURL);
}
if ($trends_and_threats) {
$dataObjects[] = get_data_object($amphibID . "_trends_threats", "Life History, Abundance, Activity, and Special Behaviors", $trends_and_threats, "http://rs.tdwg.org/ontology/voc/SPMInfoItems#Threats", $refs, $agents, $pageURL);
}
if ($relation_to_humans) {
$dataObjects[] = get_data_object($amphibID . "_relation_to_humans", "Relation to Humans", $relation_to_humans, "http://rs.tdwg.org/ontology/voc/SPMInfoItems#RiskStatement", $refs, $agents, $pageURL);
}
if ($description != "") {
if ($comments != "") {
$description .= $comments;
} else {
if ($comments != "") {
$description = $comments;
}
}
}
if ($description) {
$dataObjects[] = get_data_object($amphibID . "_description", "Description", $description, "http://rs.tdwg.org/ontology/voc/SPMInfoItems#GeneralDescription", $refs, $agents, $pageURL);
}
/* we didn't get <comments>
if($comments) $dataObjects[] = get_data_object("Comments", $comments, "http://rs.tdwg.org/ontology/voc/SPMInfoItems#GeneralDescription", $refs, $agents, $pageURL);
*/
foreach ($dataObjects as $k => $v) {
$taxonParameters["dataObjects"][] = new \SchemaDataObject($v);
unset($v);
}
$taxa[] = new \SchemaTaxon($taxonParameters);
//if($i >= 5) break; //debug
}
$new_resource_xml = \SchemaDocument::get_taxon_xml($taxa);
$old_resource_path = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml";
if (!($OUT = Functions::file_open($old_resource_path, "w+"))) {
return;
}
fwrite($OUT, $new_resource_xml);
fclose($OUT);
// Functions::set_resource_status_to_force_harvest($resource_id);
shell_exec("rm " . $new_resource_path);
// Functions::gzip_resource_xml($resource_id);
// $elapsed_time_sec = microtime(1)-$timestart;
// echo "\n";
// echo "elapsed time = $elapsed_time_sec sec \n";
// echo "elapsed time = " . $elapsed_time_sec/60 . " minutes \n";
// echo "elapsed time = " . $elapsed_time_sec/60/60 . " hours \n";
// echo "\n\n Done processing.";
}
}
function prepare_resource()
{
if (!($resource_file = fopen(CONTENT_RESOURCE_LOCAL_PATH . $this->resource_id . "_temp.xml", "w+"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . CONTENT_RESOURCE_LOCAL_PATH . $this->resource_id . "_temp.xml");
return;
}
fwrite($resource_file, \SchemaDocument::xml_header());
$language_iso_codes = self::language_iso_codes();
$avibaseids_added = array();
foreach ($this->names_in_families as $taxon_name => $metadata) {
$taxon_parameters = array();
$taxon_parameters['identifier'] = $metadata['avibaseid'];
if (isset($avibaseids_added[$metadata['avibaseid']])) {
continue;
}
$avibaseids_added[$metadata['avibaseid']] = 1;
$taxon_parameters['kingdom'] = "Animalia";
$taxon_parameters['phylum'] = "Chordata";
$taxon_parameters['class'] = "Aves";
$taxon_parameters['order'] = @$this->family_orders[$metadata['family']];
$taxon_parameters['family'] = @$metadata['family'];
$taxon_parameters['scientificName'] = $metadata['taxon_name'];
$taxon_parameters['source'] = self::AVIBASE_SOURCE_URL . $metadata['avibaseid'];
if (preg_match("/^([a-z][^ ]+) /i", $metadata['taxon_name'], $arr)) {
$taxon_parameters['genus'] = $arr[1];
}
if (!$taxon_parameters['scientificName']) {
continue;
}
$taxon_parameters['common_names'] = array();
if (isset($metadata['common_names'])) {
foreach ($metadata['common_names'] as $language => $common_names) {
if ($language_iso_code = @$language_iso_codes[$language]) {
foreach ($common_names as $common_name => $value) {
$taxon_parameters['commonNames'][] = new \SchemaCommonName(array("name" => $common_name, "language" => $language_iso_code));
}
} else {
debug("No iso code for: {$language} \n");
}
}
}
$taxon_parameters['synonyms'] = array();
if (isset($metadata['synonyms'])) {
foreach ($metadata['synonyms'] as $synonym => $value) {
if ($synonym == $metadata['taxon_name']) {
continue;
}
$taxon_parameters['synonyms'][] = new \SchemaSynonym(array("synonym" => $synonym, "relationship" => 'synonym'));
}
}
$taxon = new \SchemaTaxon($taxon_parameters);
fwrite($resource_file, $taxon->__toXML());
}
fwrite($resource_file, \SchemaDocument::xml_footer());
fclose($resource_file);
// cache the previous version and make this new version the current version
@unlink(CONTENT_RESOURCE_LOCAL_PATH . $this->resource_id . "_previous.xml");
@rename(CONTENT_RESOURCE_LOCAL_PATH . $this->resource_id . ".xml", CONTENT_RESOURCE_LOCAL_PATH . $this->resource_id . "_previous.xml");
rename(CONTENT_RESOURCE_LOCAL_PATH . $this->resource_id . "_temp.xml", CONTENT_RESOURCE_LOCAL_PATH . $this->resource_id . ".xml");
// returning the last taxon
return $taxon;
}
function get_all_taxa($task)
{
$all_taxa = array();
$used_collection_ids = array();
//initialize text file for DiscoverLife: save names without a page in EOL
self::initialize_text_file($this->TEXT_FILE_FOR_DL);
$filename = $this->TEMP_FILE_PATH . $task . ".txt";
$i = 0;
$save_count = 0;
$no_eol_page = 0;
foreach (new FileIterator($filename) as $line_number => $line) {
if ($line) {
$name = trim($line);
$i++;
//Filter names. Process only those who already have a page in EOL. Report back to DiscoverLife names not found in EOL
if (!($taxon = self::with_eol_page($name))) {
print "\n {$i} -- no EOL page ({$name})";
$no_eol_page++;
self::store_name_to_text_file($name, $task);
continue;
}
print "\n {$i} -- " . $taxon['orig_sciname'] . "\n";
$arr = self::get_discoverlife_taxa($taxon, $used_collection_ids);
$page_taxa = $arr[0];
$used_collection_ids = $arr[1];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
}
}
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$xml = str_replace("</dataObject>", "<additionalInformation><subtype>map</subtype></additionalInformation></dataObject>", $xml);
$resource_path = $this->TEMP_FILE_PATH . "temp_DiscoverLife_" . $task . ".xml";
if (!($OUT = Functions::file_open($resource_path, "w"))) {
return;
}
fwrite($OUT, $xml);
fclose($OUT);
$with_eol_page = $i - $no_eol_page;
print "\n\n total = {$i} \n With EOL page = {$with_eol_page} \n No EOL page = {$no_eol_page} \n\n ";
}
public static function get_all_taxa_keys($resource_id)
{
require_library('CheckIfNameHasAnEOLPage');
$func = new CheckIfNameHasAnEOLPage();
$GLOBALS['animal_plant_list'] = self::prepare_animal_plant_list();
$temp = self::prepare_taxa_list();
$taxa_objects = $temp[0];
$synonymy = $temp[1];
$names_to_be_added = $temp[2];
$all_taxa = array();
$used_collection_ids = array();
//initialize text file for USFWS
self::initialize_text_file(DOC_ROOT . self::TEXT_FILE_FOR_PARTNER);
$i = 0;
$no_eol_page = 0;
foreach ($taxa_objects as $name => $taxon) {
$i++;
if (@$synonymy[$name]) {
$name = trim($synonymy[$name]['EOL NAME']);
$taxon['NAME'] = $name;
} elseif (@$names_to_be_added[$name]) {
} else {
//filter names. Process only those who already have a page in EOL. Report back to USFWS names not found in EOL
$name = str_replace(".", "", $name);
if (!self::name_in_eol($name, $func)) {
self::store_name_to_text_file($name);
$name_canonical = Functions::canonical_form($name);
// try the canonical form
if ($name == $name_canonical) {
$no_eol_page++;
continue;
}
if (!self::name_in_eol($name_canonical, $func)) {
$name_without_parenthesis = self::remove_parenthesis($name);
// try name without parenthesis
if ($name == $name_without_parenthesis) {
$no_eol_page++;
continue;
}
if (!self::name_in_eol($name_without_parenthesis, $func)) {
$no_eol_page++;
continue;
} else {
echo "\n OK name without parenthesis in EOL: [{$name_without_parenthesis}]\n";
$taxon['NAME'] = $name_without_parenthesis;
self::store_name_to_text_file($name . " - name without parenthesis found in EOL: {$name_without_parenthesis}");
}
} else {
echo "\n OK canonical name in EOL: [{$name_canonical}]\n";
$taxon['NAME'] = $name_canonical;
self::store_name_to_text_file($name . " - canonical form of the name found in EOL: {$name_canonical}");
}
}
}
echo "\n {$i} -- ";
echo $taxon['NAME'] . " -- ";
$arr = self::get_usfws_taxa($taxon, $used_collection_ids);
$page_taxa = $arr[0];
$used_collection_ids = $arr[1];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
}
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$resource_path = CONTENT_RESOURCE_LOCAL_PATH . $resource_id . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
$with_eol_page = $i - $no_eol_page;
echo "\n\n total = {$i} \n With EOL page = {$with_eol_page} \n No EOL page = {$no_eol_page} \n\n";
}
<?php
namespace php_active_record;
/* connector for Photosynth
estimated execution time: 29 secs.
This connector will use an un-official service to search the Photosynth server.
It also scrapes the Photosynth site to get the tags entered by owners as the tags where not included in the service.
*/
$timestart = microtime(1);
include_once dirname(__FILE__) . "/../../config/environment.php";
require_library('connectors/PhotosynthAPI');
$GLOBALS['ENV_DEBUG'] = false;
$taxa = PhotosynthAPI::get_all_taxa();
$xml = \SchemaDocument::get_taxon_xml($taxa);
$resource_path = CONTENT_RESOURCE_LOCAL_PATH . "119.xml";
if (!($OUT = fopen($resource_path, "w+"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
$elapsed_time_sec = microtime(1) - $timestart;
echo "\n";
echo "elapsed time = {$elapsed_time_sec} sec \n";
echo "elapsed time = " . $elapsed_time_sec / 60 . " min \n";
echo "elapsed time = " . $elapsed_time_sec / 60 / 60 . " hr \n";
echo "\n\n Done processing.";
function get_all_taxa($task, $temp_path = null, $info = array())
{
$all_taxa = array();
$used_collection_ids = array();
$filename = $this->TEMP_FILE_PATH . $task . ".txt";
$i = 0;
$save_count = 0;
$no_eol_page = 0;
$total = Functions::count_rows_from_text_file($filename);
foreach (new FileIterator($filename) as $line_number => $line) {
$split = explode("\t", trim($line));
if (!@$split[0]) {
continue;
}
$taxon = array("sciname" => $split[1], "id" => $split[0], "rank" => @$split[2]);
$i++;
echo "\n {$info['1']} of {$info['0']}";
echo "\n {$i} of {$total} -- " . $taxon['sciname'] . " {$taxon['id']} \n";
$arr = self::get_Bolds_taxa($taxon, $used_collection_ids);
$page_taxa = $arr[0];
$used_collection_ids = $arr[1];
if ($page_taxa) {
$all_taxa = array_merge($all_taxa, $page_taxa);
}
unset($page_taxa);
// if($i >= 2) break; //debug
}
$xml = \SchemaDocument::get_taxon_xml($all_taxa);
$xml = str_replace("</mediaURL>", "</mediaURL><additionalInformation><subtype>map</subtype>\n</additionalInformation>\n", $xml);
$resource_path = $this->TEMP_FILE_PATH . "temp_Bolds_" . $task . ".xml";
if (!($OUT = fopen($resource_path, "w"))) {
debug(__CLASS__ . ":" . __LINE__ . ": Couldn't open file: " . $resource_path);
return;
}
fwrite($OUT, $xml);
fclose($OUT);
echo "\n\n total = {$i} \n\n";
// remove temp dir
recursive_rmdir($this->TEMP_DIR);
// debug - uncomment in real operation
echo "\n temporary directory removed: " . $this->TEMP_DIR;
}
