function searchFromPeopleFinder($nameString, $mysqli_object)
{
//global $context;
//$returnVal = [];
//$baseURL = "https://webservices.doit.missouri.edu";
//if(empty($people_list)){
//return $returnVal;
//}
$qry = "SELECT LastName, FirstName, Department, Title, Email from MOSpacePeople where LastName = ? AND FirstName = ? ";
$parser = new HumanNameParser_Parser($nameString);
if (!($stmt = $mysqli_object->prepare($qry))) {
exit("statement prepared failed: (" . $mysqli_object->errno . ") " . $mysqli_object->error);
}
$bind_param_last_name = $parser->getLast();
$bind_param_first_name = $parser->getFirst();
if (!$stmt->bind_param("ss", $bind_param_last_name, $bind_param_first_name)) {
exit("bind parameter failed: (" . $stmt->errno . ")" . $stmt->error);
}
if (!$stmt->execute()) {
exit("Execute failed: (" . $stmt->errno . ")" . $stmt->error);
}
$stmt->store_result();
//echo $stmt->num_rows."\n";
if ($stmt->num_rows == 0) {
return false;
}
if ($stmt->num_rows > 0) {
$stmt->bind_result($last, $first, $dep, $title, $email);
$stmt->fetch();
return array("LastName" => $last, "FirstName" => $first, "Department" => $dep, "Title" => $title, "Email" => $email);
}
}
public function testSingleName()
{
$parser = new HumanNameParser_Parser("Björn");
$this->assertEquals("Björn", $parser->getName()->getStr());
$this->assertEquals(null, $parser->getFirst());
$this->assertEquals(null, $parser->getLast());
}
function addMOProperty($unifiedName, $client)
{
$mysqli = new mysqli(HOSTNAME, USERNAME, PASSWD, DATABASE);
if ($mysqli->connect_errno) {
die("error: " . $mysqli->connect_error);
}
$localTable = "MOSpacePeople";
$parser = new HumanNameParser_Parser($unifiedName);
$last = $parser->getLast();
$first = $parser->getFirst();
//@Debug
//echo "Checking ".$last.", ".$first.".....";
$q = "SELECT * from " . $localTable . " where firstname='" . $mysqli->real_escape_string($first) . "' and lastname='" . $mysqli->real_escape_string($last) . "'";
$fromMU = 0;
$isProfessor = 0;
if ($result = $mysqli->query($q)) {
if ($result->num_rows == 1) {
//@Debug
//echo "found in local database.....";
$fromMU = 1;
if ($resAssocArray = $result->fetch_assoc()) {
if (isset($resAssocArray['Title'])) {
$isProfessor = findIfProfessor($resAssocArray['Title']) == 1 ? 1 : 0;
//@Debug
//if($isProfessor == 1) echo "is a prof\n"; else echo "NOT a prof\n";
} else {
$isProfessor = 0;
//@Debu
//echo "NOT a prof\n";
}
} else {
die("fetch result from MOSpacePeople failed");
}
} else {
$peopleFinderURL = "https://webservices.doit.missouri.edu/peoplefinderWS/peoplefinderws.asmx/PeopleFinderXml?firstName=" . urlencode($first) . "&lastname=" . urlencode($last) . "&department=&phoneno=&email=";
$url_parser = new URLParser($peopleFinderURL);
$retArr = $url_parser->XMLToArray();
if (intval($retArr['@attributes']['found']) == 1) {
//@Debug
//echo "found in Peoplefinder...";
$fromMU = 1;
$title = array_key_exists("Title", $retArr['Person']) && !empty($retArr['Person']['Title']) ? $retArr['Person']['Title'] : "";
$isProfessor = findIfProfessor($title) == 1 ? 1 : 0;
//@Debug
//if($isProfessor == 1) echo "is a prof\n"; else echo "NOT a prof\n";
} else {
$isProfessor = 0;
//@Debug
//echo "NOT a prof\n";
}
}
} else {
die("query: " . $q . "\nFailed");
}
$q_str = "match (u:Person {name: \"" . $unifiedName . "\"}) set u.fromMU = " . $fromMU . ", u.isProfessor = " . $isProfessor;
$query = new Query($client, $q_str);
$client->executeCypherQuery($query);
}
function prepare_doc_for_citeproc(&$doc)
{
$authors = array();
foreach ($doc['authors'] as $author) {
$name = new HumanNameParser_Name($author);
$parser = new HumanNameParser_Parser($name);
$authors[] = array('given' => $parser->getFirst(), 'family' => $parser->getLast(), 'static-ordering' => false);
}
foreach (array('year', 'month', 'day') as $item) {
if (!$doc[$item]) {
$doc[$item] = '01';
}
}
$doc = array_filter(array('id' => $doc['id'], 'title' => $doc['title'], 'author' => $authors, 'publisher' => $doc['publisher'], 'volume' => $doc['volume'], 'issue' => $doc['issue'], 'page-range' => $doc['pages'], 'issued' => array('date-parts' => array(array($doc['year'], $doc['month'], $doc['day']))), 'type' => 'article'));
}
public function setFullname($fullname)
{
$name = new \HumanNameParser_Parser($fullname);
$this->customer->setName(new Name($name->getFirst(), $name->getLast(), $name->getMiddle()));
return $this;
}
}
$client = new Everyman\Neo4j\Client('localhost', 7474);
$client->getTransport()->setAuth('neo4j', 'muresearch');
$q = "match (u:Person) return u.name as name";
$query = new Query($client, $q);
$result = $query->getResultSet();
$mysqli = new mysqli(HOSTNAME, USERNAME, PASSWD, DATABASE);
if ($mysqli->connect_errno) {
die("error: " . $mysqli->connect_error);
}
$localTable = "MOSpacePeople";
$transaction = $client->beginTransaction();
foreach ($result as $r) {
$parser = new HumanNameParser_Parser($r['name']);
$last = $parser->getLast();
$first = $parser->getFirst();
//@Debug
echo "Checking " . $last . ", " . $first . ".....";
$q = "SELECT * from " . $localTable . " where firstname='" . $mysqli->real_escape_string($first) . "' and lastname='" . $mysqli->real_escape_string($last) . "'";
$fromMU = 0;
$isProfessor = 0;
if ($result = $mysqli->query($q)) {
if ($result->num_rows == 1) {
//@Debug
echo "found in local database.....";
$fromMU = 1;
if ($resAssocArray = $result->fetch_assoc()) {
if (isset($resAssocArray['Title'])) {
$isProfessor = findIfProfessor($resAssocArray['Title']) == 1 ? 1 : 0;
//@Debug
if ($isProfessor == 1) {
foreach ($people_array as $p) {
if (str_word_count($p) == 1) {
continue;
}
if (strpos("{$p}", ", ") !== false) {
$tmp = explode(",", $p);
if (in_array(trim($tmp[1]), array("Jr.")) && isset($tmp[2])) {
$p = $tmp[0] . ", " . $tmp[2];
} else {
$p = implode(",", array_slice($tmp, 0, 2));
}
}
//$p = implode(",", array_slice(explode(",", $p), 0, 2));
//echo $p."\n";
$parser = new HumanNameParser_Parser($p);
$searchURL = "/peoplefinderWS/peoplefinderws.asmx/PeopleFinderXml?firstName=" . urlencode($parser->getFirst()) . "&lastname=" . urlencode($parser->getLast()) . "&department=&phoneno=&email=";
$peopleInfoXML = file_get_contents($baseURL . $searchURL, false, $context) or die("The mospace server might failed\n");
//echo $baseURL.$searchURL;
$peopleInfoXMLObject = simplexml_load_string($peopleInfoXML, null, LIBXML_NOCDATA);
if ($peopleInfoXMLObject['found'] == 0 || $peopleInfoXMLObject['found'] >= 49) {
continue;
}
//echo "<pre>";
///print_r($peopleInfoXMLObject->Person);
//echo "</pre>";
$personObject = new Person();
$personObject->setLastName($parser->getLast());
$personObject->setFirstName($parser->getFirst());
//For test purpose only
//echo $personObject->getLastName().", ".$personObject->getFirstName()."; ";
$personObject->setDepartment($peopleInfoXMLObject->Person->Department);
public function crawlPubmed()
{
$search_url = $this->pubmed_search_url . "&term=" . urlencode($this->firstName . " " . $this->lastName . "[Author]" . " AND " . $this->affiliation . "[Affiliation]");
$search_url_parser = new URLParser($search_url);
$pubmedSearch_item_array = $search_url_parser->XMLToArray();
$returnVal = array();
if (array_key_exists('Count', $pubmedSearch_item_array) && $pubmedSearch_item_array['Count'] > 0) {
if ($pubmedSearch_item_array['Count'] == 1 || $pubmedSearch_item_array['RetMax'] == 1) {
$pubmedSearch_item_array['IdList']['Id'] = array($pubmedSearch_item_array['IdList']['Id']);
}
$pid_url = "";
foreach ($pubmedSearch_item_array['IdList']['Id'] as $ind => $pubid) {
$pid_url .= $pubid . ",";
}
$pid_url = rtrim($pid_url, ",");
$fetch_url = $this->pubmed_fetch_url . $pid_url;
$fetch_url_parser = new URLParser($fetch_url);
$pubmedFetchResultArray = $fetch_url_parser->XMLToArray();
if (!array_key_exists('PubmedArticle', $pubmedFetchResultArray)) {
trigger_error("PubmedArticle not set in pubmedFetchResultArray", E_USER_ERROR);
return null;
}
$pubmedFetchResultArray['PubmedArticle'] = isset($pubmedFetchResultArray['PubmedArticle'][0]) ? $pubmedFetchResultArray['PubmedArticle'] : array($pubmedFetchResultArray['PubmedArticle']);
foreach ($pubmedFetchResultArray['PubmedArticle'] as $record) {
if (!array_key_exists('MedlineCitation', $record)) {
trigger_error("MedlineCitation not set in one pubmed record", E_USER_ERROR);
continue;
}
$coauthorList = array();
$title = $record['MedlineCitation']['Article']['ArticleTitle'];
$url = 'http://www.ncbi.nlm.nih.gov/pubmed/' . $record['MedlineCitation']['PMID'];
if (array_key_exists('AuthorList', $record['MedlineCitation']['Article']) && array_key_exists('Author', $record['MedlineCitation']['Article']['AuthorList']) && !empty($record['MedlineCitation']['Article']['AuthorList'])) {
$authorList = $record['MedlineCitation']['Article']['AuthorList']['Author'];
} else {
trigger_error("authorlist/author not set or author is empty", E_USER_ERROR);
continue;
}
if (!isset($authorList[0])) {
continue;
}
if (count($authorList) > 20) {
continue;
}
foreach ($authorList as $a) {
//converting pubmed name to neo4j compatible format
$parser = new HumanNameParser_Parser($a['LastName'] . ", " . $a['ForeName']);
$first = $parser->getFirst();
$last = $parser->getLast();
if (array_key_exists('AffiliationInfo', $a)) {
if (array_key_exists('Affiliation', $a['AffiliationInfo'])) {
$affi = $a['AffiliationInfo']['Affiliation'];
} else {
if (array_key_exists(0, $a['AffiliationInfo']) && array_key_exists('Affiliation', $a['AffiliationInfo'][0])) {
$affi = $a['AffiliationInfo'][0]['Affiliation'];
}
}
} else {
$affi = "";
}
$coauthorList[] = array("firstName" => $first, "lastName" => $last, "affiliation" => $affi);
}
$returnVal[] = array("title" => $title, "url" => $url, "people" => $coauthorList);
}
}
return $returnVal;
}
exit("Binding parameters failed: (" . $stmt->errno . ")" . $stmt->error);
}
if (!$stmt->execute()) {
exit("Execute failed: (" . $stmt->errno . ") " . $stmt->error);
}
$stmt->store_result();
if ($stmt->num_rows == 0 || $stmt->num_rows >= 2) {
exit("Error: id not found or multiple result found");
}
$stmt->bind_result($userid, $lastname, $firstname, $middlename, $suffix, $title, $department, $phone, $email, $photoImageURL, $keywordImageURL, $socialKeywordURL, $description);
$stmt->fetch();
$registered = 1;
} else {
if (isset($name)) {
$bind_param_last_name = $parser->getLast();
$bind_param_first_name = $parser->getFirst();
$bind_param_middle_name = $parser->getMiddle();
$bind_param_suffix = $parser->getSuffix();
if (!$stmt->bind_param("ssss", $bind_param_last_name, $bind_param_first_name, $bind_param_middle_name, $bind_param_suffix)) {
exit("Binding parameters failed: (" . $stmt->errno . ")" . $stmt->error);
}
if (!$stmt->execute()) {
exit("Execute failed: (" . $stmt->errno . ") " . $stmt->error);
}
$stmt->store_result();
if ($stmt->num_rows == 1) {
$stmt->bind_result($theid, $lastname, $firstname, $middlename, $suffix, $title, $department, $phone, $email, $photoImageURL, $keywordImageURL, $socialKeywordURL, $description);
$stmt->fetch();
$registered = 1;
} else {
if ($stmt->num_rows > 1) {
if ($expected === '') {
$expected = "[empty]";
}
if ($actual === '') {
$actual = "[empty]";
}
if ($actual === $expected) {
$ret = "<span class='win'>{$expected} = {$actual}</span>";
} else {
$ret = "<span class='fail'>{$expected} ≠ {$actual}</span>";
}
return $ret;
}
$handle = fopen('./Tests/testNames.txt', 'r');
while ($nameArr = fgetcsv($handle, 1000, "|")) {
$parser = new HumanNameParser_Parser($nameArr[0]);
// check to see if the parser got each name-part correct
$ret = testEqual($nameArr[1], $parser->getleadingInit());
$ret .= testEqual($nameArr[2], $parser->getFirst());
$ret .= testEqual($nameArr[3], $parser->getNicknames());
$ret .= testEqual($nameArr[4], $parser->getMiddle());
$ret .= testEqual($nameArr[5], $parser->getLast());
$ret .= testEqual($nameArr[6], $parser->getSuffix());
$divClass = strpos($ret, "class='fail'") ? "fail" : "win";
// a hacky way to do this
echo "<div class='name {$divClass}'><h2 class='test-name'>{$nameArr[0]}</h2>{$ret}</div>";
}
?>
</body>
</html>