// $xml = str_replace(array(chr(0x73), chr(0x20), chr(0x68), chr(0x61)), " ", $xml);
$xml = str_replace(array(0x73, 0x20, 0x73, 0x6b), " ", $xml);
$xml = str_replace(array(0x32, 0x35, 0x2e, 0x35), " ", $xml);
$xml = str_replace(array(0x32, 0x33, 0x20, 0x6d), " ", $xml);
$xml = str_replace(chr(0x32) . " " . chr(0x33) . " " . chr(0x20) . " " . chr(0x6d), " ", $xml);
$xml = str_replace(array(0x20, 0x4e, 0x61, 0x74), " ", $xml);
$xml = str_replace(array(0x73, 0x20, 0x68, 0x6f), " ", $xml);
$xml = str_replace(chr(0x73) . " " . chr(0x20) . " " . chr(0x68) . " " . chr(0x6f), " ", $xml);
$xml = str_replace(array(0x77, 0x65, 0x72, 0x65), " ", $xml);
$xml = str_replace(array(0xe2, 0x80, 0xc2, 0xa6), " ", $xml);
$xml = str_replace(array(0x6e, 0x20, 0x32, 0x30), " ", $xml);
$xml = str_replace(array(0x67, 0x75, 0x65, 0x7a), " ", $xml);
$xml = str_replace(array(0x73, 0x20, 0x61, 0x6e), " ", $xml);
$xml = str_replace(array(0x74, 0x7a, 0x3c, 0x2f), " ", $xml);
// 0x74 0x7A 0x20 0x77
$xml = format_utf8($xml);
$xml = mb_convert_encoding($xml, "UTF-8", mb_detect_encoding($xml, "UTF-8, ISO-8859-1, ISO-8859-15", true));
//
$xml = str_replace(array(0x74, 0x7a, 0x3c, 0x2f), " ", $xml);
$xml = str_replace(array(0x74, 0x7a, 0x20, 0x77), " ", $xml);
// 0x73 0x20 0x68 0x6F
if (!($OUT = Functions::file_open($xml_path, "w"))) {
return;
}
fwrite($OUT, $xml);
fclose($OUT);
echo "\nSaved [{$xml_path}]...\n";
}
//--------
Functions::gzip_resource_xml($resource_id);
$elapsed_time_sec = microtime(1) - $timestart;
function start($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.";
}
}
