function Retrieve()
{
if ($this->id != 0) {
$this->object = db_retrieve_reference($this->id);
}
return $this->object;
}
function find_reference($journal, $volume, $page, $year = '')
{
global $db;
$references = array();
$hits = array();
if ($journal == '' || $volume == '' || $page == '') {
//echo "journal=$journal\n";
return $hits;
}
$series = '';
$issn = '';
$oclc = 0;
if (preg_match('/^(?<journal>.*),\\s+ser\\.\\s+(?<series>.*)$/', $journal, $m)) {
$journal = $m['journal'];
$series = $m['series'];
}
if (preg_match('/^(?<journal>.*),\\s+(ns|n.s.)$/', $journal, $m)) {
$journal = $m['journal'];
//$series = $m['series'];
}
if (preg_match('/^(?<page>\\d+),(.*)$/', $page, $m)) {
$page = $m['page'];
}
$issn = issn_from_title($journal);
if ($issn == '') {
$oclc = oclc_for_title($journal);
}
//echo $issn;
//echo $oclc;
$sql = '';
if ($issn != '') {
$sql = 'SELECT * FROM rdmp_reference WHERE issn=' . $db->qstr($issn) . ' AND volume=' . $db->qstr($volume) . ' AND ' . $page . ' BETWEEN spage AND epage';
}
if ($oclc != '') {
$sql = 'SELECT * FROM rdmp_reference WHERE oclc=' . $db->qstr($oclc) . ' AND volume=' . $db->qstr($volume) . ' AND ' . $page . ' BETWEEN spage AND epage';
}
if ($sql != '') {
if ($series != '') {
$sql .= ' AND series=' . $db->qstr($series);
}
if ($year != '') {
$sql .= ' AND year=' . $db->qstr($year);
}
$result = $db->Execute($sql);
if ($result == false) {
die("failed [" . __FILE__ . ":" . __LINE__ . "]: " . $sql);
}
while (!$result->EOF) {
$references[] = $result->fields['reference_id'];
$result->MoveNext();
}
}
foreach ($references as $reference_id) {
$hits[] = reference_to_bibjson(db_retrieve_reference($reference_id));
}
return $hits;
}
function articles_for_item($ItemID)
{
global $db;
$obj = new stdclass();
$sql = 'SELECT * FROM bhl_title INNER JOIN bhl_item USING(TitleID) WHERE ItemID=' . $ItemID . ' LIMIT 1';
$result = $db->Execute($sql);
if ($result == false) {
die("failed [" . __FILE__ . ":" . __LINE__ . "]: " . $sql);
}
if ($result->NumRows() == 1) {
$obj->ItemID = $result->fields['ItemID'];
$obj->FullTitle = $result->fields['FullTitle'];
$obj->VolumeInfo = $result->fields['VolumeInfo'];
} else {
}
if (isset($obj->ItemID)) {
$ids = array();
$sql = 'SELECT DISTINCT rdmp_reference.reference_id, page.SequenceOrder
FROM rdmp_reference_page_joiner
INNER JOIN page USING(PageID)
INNER JOIN rdmp_reference USING(PageID)
WHERE ItemID=' . $obj->ItemID . '
ORDER BY CAST(page.SequenceOrder AS SIGNED)';
$result = $db->Execute($sql);
if ($result == false) {
die("failed [" . __FILE__ . ":" . __LINE__ . "]: " . $sql);
}
while (!$result->EOF) {
$ids[] = $result->fields['reference_id'];
$result->MoveNext();
}
$obj->articles = array();
foreach ($ids as $reference_id) {
$reference = db_retrieve_reference($reference_id);
if (isset($reference->oclc)) {
if ($reference->oclc == 0) {
unset($reference->oclc);
}
}
if (isset($reference->sici)) {
unset($reference->sici);
}
if (isset($reference->reference_cluster_id)) {
unset($reference->reference_cluster_id);
}
// get pages
$pages = bhl_retrieve_reference_pages($reference_id);
foreach ($pages as $page) {
$reference->bhl_pages[] = (int) $page->PageID;
}
$obj->articles[] = $reference;
}
}
//print_r($obj);
return $obj;
}
$exhibit->items = array();
$id = 0;
if (isset($_GET['id'])) {
$id = $_GET['id'];
}
if ($id != 0) {
$refs = db_retrieve_authored_references($id);
$coauthors = db_retrieve_coauthors($id);
$c = array();
foreach ($coauthors->coauthors as $co) {
$c[] = $co->id;
}
$journal_names = array();
foreach ($refs as $reference_id) {
global $config;
$reference = db_retrieve_reference($reference_id);
$item = new stdclass();
$item->uri = $config['web_root'] . 'reference/' . $reference_id;
$item->type = $reference->genre;
$item->label = $reference->title;
// Group journals
if (!isset($journal_names[$reference->issn])) {
$journal_names[$reference->issn] = $reference->secondary_title;
}
$item->journal = $journal_names[$reference->issn];
$item->citation = reference_authors_to_text_string($reference) . ' (' . $reference->year . ') ' . reference_to_citation_text_string($reference);
$item->year = $reference->year;
if ($reference->PageID != 0) {
$image = bhl_fetch_page_image($reference->PageID);
$item->imageURL = $image->thumbnail->url;
} else {
function DisplayHtmlContent()
{
global $config;
echo html_page_header(true, '', 'name');
echo '<div style="float:right;background-color:rgb(230,242,250);padding:6px">' . "\n";
if ($this->issn != '') {
echo '<h2>Identifiers</h2>' . "\n";
echo '<ul class="guid-list">' . "\n";
echo '<li class="permalink"><a href="' . $config['web_root'] . 'issn/' . $this->issn . '" title="Permalink">' . $config['web_root'] . 'issn/' . $this->issn . '</a></li>' . "\n";
echo '<li class="worldcat"><a href="http://www.worldcat.org/issn/' . $this->issn . '" title="ISSN">' . $this->issn . '</a></li>' . "\n";
echo '<h2>Export</h2>' . "\n";
echo '<ul class="export-list">' . "\n";
echo '<li class="xml"><a href="' . $config['web_root'] . 'issn/' . $this->issn . '.xml" title="Endnote XML">Endnote XML</a></li>';
echo '<li class="ris"><a href="' . $config['web_root'] . 'issn/' . $this->issn . '.ris" title="RIS">Reference manager</a></li>';
echo '<li class="bibtex"><a href="' . $config['web_root'] . 'issn/' . $this->issn . '.bib" title="BibTex">BibTex</a></li>';
echo '<li class="text"><a href="' . $config['web_root'] . 'issn/' . $this->issn . '.text" title="text">Text</a></li>';
echo '</ul>' . "\n";
}
if ($this->oclc != '') {
echo '<h2>Identifiers</h2>' . "\n";
echo '<ul class="guid-list">' . "\n";
echo '<li class="permalink"><a href="' . $config['web_root'] . 'oclc/' . $this->oclc . '" title="Permalink">' . $config['web_root'] . 'oclc/' . $this->oclc . '</a></li>' . "\n";
echo '<li class="worldcat"><a href="http://www.worldcat.org/oclc/' . $this->oclc . '" title="OCLC">' . $this->oclc . '</a></li>' . "\n";
echo '<h2>Export</h2>' . "\n";
echo '<ul class="export-list">' . "\n";
echo '<li class="xml"><a href="' . $config['web_root'] . 'oclc/' . $this->oclc . '.xml" title="Endnote XML">Endnote XML</a></li>';
echo '<li class="ris"><a href="' . $config['web_root'] . 'oclc/' . $this->oclc . '.ris" title="RIS">Reference manager</a></li>';
echo '<li class="bibtex"><a href="' . $config['web_root'] . 'oclc/' . $this->oclc . '.bib" title="BibTex">BibTex</a></li>';
echo '<li class="text"><a href="' . $config['web_root'] . 'oclc/' . $this->oclc . '.text" title="text">Text</a></li>';
echo '</ul>' . "\n";
}
echo '</div>' . "\n";
echo '<h1>' . $this->GetTitle() . '</h1>';
// Image
if (isset($this->issn)) {
echo '<div>';
echo '<img src="http://bioguid.info/issn/image.php?issn=' . $this->issn . '" alt="cover" style="border:1px solid rgb(228,228,228);height:100px;" />';
echo '</div>';
}
// Stats
/* echo '<div>';
echo '<img src="' . sparkline_articles_added_for_issn($this->issn) . '" alt="sparkline" />';
echo '</div>';*/
echo '<a href="http://twitter.com/share" class="twitter-share-button" data-count="vertical" data-via="rdmpage" data-related="biostor_org">Tweet</a><script type="text/javascript" src="http://platform.twitter.com/widgets.js"></script>';
echo '<h2>Coverage</h2>' . "\n";
echo '<p>';
if ($this->issn != '') {
echo bhl_articles_for_issn($this->issn);
}
if ($this->oclc != '') {
echo bhl_articles_for_oclc($this->oclc);
}
echo ' articles in database.</p>' . "\n";
echo '<h3>Distribution of identified articles over time</h3>' . "\n";
echo '<div>' . "\n";
echo ' <img src="' . sparkline_references($this->issn, $this->oclc, 360, 100) . '" alt="sparkline" />' . "\n";
echo '</div>' . "\n";
$titles = array();
if ($this->issn != '') {
$titles = bhl_titles_for_issn($this->issn);
}
if ($this->oclc != '') {
$titles = bhl_titles_for_oclc($this->oclc);
}
if (count($titles) > 0) {
echo '<h3>Distribution of identified articles across BHL items</h3>' . "\n";
echo '<div>';
echo '<div style="display:inline;background-color:rgb(230,242,250);width:20px;height:20px;"> </div>';
echo ' Scanned pages ';
echo '<div style="display:inline;background-color:rgb(0,119,204);width:10px;height:10px;"> </div>';
echo ' Articles ';
echo '</div>';
echo '<p></p>';
$items = array();
$volumes = array();
items_from_titles($titles, $items, $volumes);
$html = '<div style="height:400px;border:1px solid rgb(192,192,192);overflow:auto;">' . "\n";
$html .= '<table>' . "\n";
$html .= '<tbody style="font-size:10px;">' . "\n";
foreach ($volumes as $volume) {
$item = $items[$volume];
// How many pages in this item?
$num_pages = bhl_num_pages_in_item($item->ItemID);
// Coverage
$coverage = bhl_item_page_coverage($item->ItemID);
$row_height = 10;
// Draw as DIV
$html .= '<tr>' . "\n";
$html .= '<td>';
$html .= '<a href="http://www.biodiversitylibrary.org/item/' . $item->ItemID . '" target="_new">';
$html .= $item->VolumeInfo;
$html .= '</a>';
$html .= '</td>' . "\n";
$html .= '<td>' . "\n";
$html .= '<div style="position:relative">' . "\n";
$html .= ' <div style="background-color:rgb(230,242,250);border-bottom:1px solid rgb(192,192,192);border-right:1px solid rgb(192,192,192);position:absolute;left:0px;top:0px;width:' . $num_pages . 'px;height:' . $row_height . 'px;">' . "\n";
foreach ($coverage as $c) {
$html .= ' <div style="background-color:rgb(0,119,204);position:absolute;left:' . $c->start . 'px;top:0px;width:' . ($c->end - $c->start) . 'px;height:' . $row_height . 'px;">' . "\n";
$html .= ' </div>' . "\n";
}
$html .= ' </div>' . "\n";
$html .= '</div>' . "\n";
$html .= '</td>' . "\n";
$html .= '</tr>' . "\n";
}
$html .= '</tbody>' . "\n";
$html .= '</table>' . "\n";
$html .= '</div>' . "\n";
echo $html;
}
$institutions = institutions_from_titles($titles);
if (count($institutions) != 0) {
echo '<h3>BHL source(s)</h3>' . "\n";
echo '<table>' . "\n";
foreach ($institutions as $k => $v) {
echo '<tr>' . "\n";
echo '<td>' . "\n";
switch ($k) {
case 'American Museum of Natural History Library':
echo '<img src="' . $config['web_root'] . 'images/institutions/' . 'AMNH_logo_--_blue_rectangle.jpg' . '" width="48" />';
break;
case 'Harvard University, MCZ, Ernst Mayr Library':
echo '<br /><img src="' . $config['web_root'] . 'images/institutions/' . 'Mod_Color_Harvard_Shield_small_bigger.jpg' . '" width="48" />';
break;
case 'Missouri Botanical Garden':
echo '<br /><img src="' . $config['web_root'] . 'images/institutions/' . 'twitter_icon_MBG.jpg' . '" width="48" />';
break;
case 'New York Botanical Garden':
echo '<br /><img src="' . $config['web_root'] . 'images/institutions/' . 'NYBGDOMEHEADERWEB.jpg' . '" />';
break;
case 'Smithsonian Institution Libraries':
echo '<br /><img src="' . $config['web_root'] . 'images/institutions/' . 'SILCatesbyMagnolia.jpg' . '" width="48" />';
break;
case 'The Field Museum':
echo '<br /><img src="' . $config['web_root'] . 'images/institutions/' . 'field.jpg' . '" width="48" />';
break;
case 'BHL-Europe':
echo '<br /><div style="background-color:green;width:120px;text-align:center"><img src="' . $config['web_root'] . 'images/institutions/' . 'BHL_logo_wg.png' . '" height="48" /></div>';
break;
case 'Boston Public Library':
echo '<br /><img src="' . $config['web_root'] . 'images/institutions/' . 'BPLcards.jpg' . '" width="48" />';
break;
case 'Harvard University Herbarium':
echo '<br /><img src="' . $config['web_root'] . 'images/institutions/' . 'huh_logo_bw_100.png' . '" width="48" />';
break;
case 'MBLWHOI Library':
echo '<br /><img src="' . $config['web_root'] . 'images/institutions/' . 'library_logo2_bigger.jpg' . '" width="48" />';
break;
case 'Natural History Museum, London':
echo '<br /><img src="' . $config['web_root'] . 'images/institutions/' . 'natural_history_museum-01.jpg' . '" width="48" />';
break;
case 'University of Illinois Urbana Champaign':
echo '<br /><img src="' . $config['web_root'] . 'images/institutions/' . 'ilogo_horz_bold.gif' . '" height="48" />';
break;
default:
break;
}
echo '</td>' . "\n";
echo '<td>' . "\n";
echo $k . '<br />' . $v . ' items';
echo '</td>' . "\n";
echo '</tr>' . "\n";
}
echo '</table>' . "\n";
}
// How does journal relate to BHL Titles and Items?
$titles = array();
if ($this->issn != '') {
$titles = db_retrieve_journal_names_from_issn($this->issn);
}
if ($this->oclc != '') {
$titles = db_retrieve_journal_names_from_oclc($this->oclc);
}
if (count($titles) > 1) {
echo '<h2>Alternative titles</h2>';
echo '<ul>';
foreach ($titles as $title) {
echo '<li>' . $title . '</li>';
}
echo '</ul>';
}
echo '<h2>Articles</h2>';
if ($this->issn == '0374-5481') {
// Special treatment for Ann mag Nat Hist
echo '<ul>';
for ($series = 1; $series <= 9; $series++) {
echo '<li><a href="' . $config['web_root'] . 'issn/' . $this->issn . '#series' . $series . '">Series ' . $series . '</a></li>';
}
echo '</ul>';
for ($series = 1; $series <= 9; $series++) {
echo '<h3><a name="series' . $series . '"></a>Series ' . $series . '</h3>' . "\n";
$articles = db_retrieve_articles_from_journal_series($this->issn, $series == 1 ? '' : $series);
echo '<ul>';
foreach ($articles as $k => $v) {
echo '<li style="display:block;border-top:1px solid #EEE; ">' . $k;
echo '<ul>';
if (is_array($v)) {
foreach ($v as $ref) {
echo '<li><a href="' . $config['web_root'] . 'reference/' . $ref->id . '">' . $ref->title . '</a></li>';
}
}
echo '</ul>';
echo '</li>';
}
echo '</ul>';
}
} else {
$articles = db_retrieve_articles_from_journal($this->issn, $this->oclc);
//print_r($articles);
echo '<ul>';
foreach ($articles as $k => $v) {
echo '<li style="display:block;border-top:1px solid #EEE; ">' . $k;
echo '<ul>';
if (is_array($v)) {
foreach ($v as $ref) {
if (0) {
// fast
echo '<li><a href="' . $config['web_root'] . 'reference/' . $ref->id . '">' . $ref->title . '</a></li>';
} else {
// slower, but useful for debugging
$reference = db_retrieve_reference($ref->id);
echo '<li style="border-bottom:1px dotted rgb(128,128,128);padding:4px;">';
echo '<a href="' . $config['web_root'] . 'reference/' . $ref->id . '">' . $reference->title . '</a><br/>';
echo '<span style="color:green;">' . reference_authors_to_text_string($reference);
if (isset($reference->year)) {
echo ' (' . $reference->year . ')';
}
echo ' ' . reference_to_citation_text_string($reference) . '</span>';
echo ' ' . reference_to_coins($reference);
// Thumbail, useful for debugging
if (0) {
echo '<div>';
$pages = bhl_retrieve_reference_pages($ref->id);
$image = bhl_fetch_page_image($pages[0]->PageID);
echo '<a href="' . $config['web_root'] . 'reference/' . $ref->id . '">';
echo '<img style="padding:2px;border:1px solid blue;margin:2px;" id="thumbnail_image_' . $page->PageID . '" src="' . $image->thumbnail->url . '" width="' . $image->thumbnail->width . '" height="' . $image->thumbnail->height . '" alt="thumbnail"/>';
echo '</a>';
echo '</div>';
}
echo '</li>';
}
}
} else {
// Article lacks volume
if (isset($v->id)) {
$reference = db_retrieve_reference($v->id);
echo '<li style="border-bottom:1px dotted rgb(128,128,128);padding:4px;">';
echo '<a href="' . $config['web_root'] . 'reference/' . $v->id . '">' . $reference->title . '</a><br/>';
echo '<span style="color:green;">' . reference_authors_to_text_string($reference);
if (isset($reference->year)) {
echo ' (' . $reference->year . ')';
}
echo ' ' . reference_to_citation_text_string($reference) . '</span>';
echo ' ' . reference_to_coins($reference);
}
}
echo '</ul>';
echo '</li>';
}
echo '</ul>';
}
}
function db_find_article($article, $allow_non_bhl = false)
{
global $db;
$id = 0;
// Ensure we have enough info
// Otherwise tools like the Google Bot may cause spurious records to be added
if (!isset($article->volume) || !isset($article->spage) || !(isset($article->secondary_title) || isset($article->issn))) {
// handle case where OpenURL has DOI but not enough other details
if (!isset($article->doi)) {
return $id;
}
}
// Does a reference exist?
$sql = '';
$hits = array();
// Unset things we don't have
foreach ($article as $k => $v) {
if ($v == '') {
unset($article->{${k}});
}
}
// Check first for identifiers
if (isset($article->doi) && $article->doi != '') {
$id = db_retrieve_reference_from_doi($article->doi);
if ($id != 0) {
return $id;
}
}
if (isset($article->hdl) && $article->hdl != '') {
$id = db_retrieve_reference_from_handle($article->hdl);
if ($id != 0) {
return $id;
}
}
// Metadata lookup
if (isset($article->issn) && $article->issn != '' && isset($article->volume) && isset($article->spage)) {
$sql = 'SELECT * FROM rdmp_reference
WHERE (issn = ' . $db->Quote($article->issn) . ')
AND (volume = ' . $db->Quote($article->volume) . ')
AND (spage = ' . $db->Quote($article->spage) . ')';
} elseif (isset($article->oclc) && $article->oclc != '' && isset($article->volume) && isset($article->spage)) {
// OCLC
$sql = 'SELECT * FROM rdmp_reference
WHERE (oclc = ' . $db->Quote($article->oclc) . ')
AND (volume = ' . $db->Quote($article->volume) . ')
AND (spage = ' . $db->Quote($article->spage) . ')';
} else {
// No ISSN so try and match on journal title
$sql = 'SELECT * FROM rdmp_reference
WHERE (secondary_title = ' . $db->Quote($article->secondary_title) . ')
AND (volume = ' . $db->Quote($article->volume) . ')
AND (spage = ' . $db->Quote($article->spage) . ')';
}
if ($allow_non_bhl) {
} else {
$sql .= ' AND (PageID <> 0)';
}
//echo $sql;
// Do we have this?
$result = $db->Execute($sql);
if ($result == false) {
die("failed [" . __FILE__ . ":" . __LINE__ . "]: " . $sql);
}
while (!$result->EOF) {
$hits[] = $result->fields['reference_id'];
$result->MoveNext();
}
//print_r($hits);
//print_r($article);
$matches = array();
if (count($hits) > 0) {
// We have a potential match, but if journal pagination is with respect to issue,
// not journal, then we may have a problem as different articles may start with the
// same page number
foreach ($hits as $hit) {
$ref = db_retrieve_reference($hit);
//print_r($ref);
$matched = 0;
// Does ending page match?
if (isset($article->epage) && isset($ref->epage)) {
if ($article->epage == $ref->epage) {
$matched++;
}
} else {
// no epage, accept hit by default
$matched++;
}
// Do issue numbers match?
if (isset($article->issue) && isset($ref->issue)) {
if ($article->issue != '' && $article->issue == $ref->issue) {
$matched++;
}
}
switch ($matched) {
case 0:
// Unlikely to be same thing, unless mistake in pagination, but allow for missing epage
break;
case 1:
case 2:
default:
// gotta be this one
$matches[] = $hit;
break;
}
}
}
if (count($matches) == 1) {
$id = $matches[0];
}
/* // Basic triple
if (
(isset($article->issn) && ($article->issn != ''))
&& isset($article->volume)
&& isset($article->spage)
)
{
$sql = 'SELECT * FROM rdmp_reference
WHERE (issn = ' . $db->Quote($article->issn) . ')
AND (volume = ' . $db->Quote($article->volume) . ')
AND (spage = ' . $db->Quote($article->spage) . ')
LIMIT 1';
}
else
{
// No ISSN so try and match on journal title
$sql = 'SELECT * FROM rdmp_reference
WHERE (secondary_title = ' . $db->Quote($article->secondary_title) . ')
AND (volume = ' . $db->Quote($article->volume) . ')
AND (spage = ' . $db->Quote($article->spage) . ')
LIMIT 1';
}
$result = $db->Execute($sql);
if ($result == false) die("failed [" . __FILE__ . ":" . __LINE__ . "]: " . $sql);
if ($result->NumRows() == 1)
{
$id = $result->fields['reference_id'];
}
*/
return $id;
}
<?php
require_once '../config.inc.php';
require_once '../db.php';
$ids = array(113472);
//foreach ($ids as $reference_id)
for ($reference_id = 113472; $reference_id <= 113472; $reference_id++) {
echo "-- {$reference_id}\n";
$article = db_retrieve_reference($reference_id);
$pages = bhl_retrieve_reference_pages($reference_id);
//print_r($pages);
foreach ($pages as $page) {
$url = 'http://www.biodiversitylibrary.org/api2/httpquery.ashx?op=GetPageNames&pageid=' . $page->PageID . '&apikey=' . '0d4f0303-712e-49e0-92c5-2113a5959159' . '&format=json';
$json = get($url);
$obj = json_decode($json);
//print_r($obj);
if ($obj->Status == 'ok') {
foreach ($obj->Result as $name) {
$sql = "DELETE FROM bhl_page_name WHERE NameConfirmed='" . addslashes($name->NameFound) . "' AND PageID=" . $page->PageID . ";";
echo $sql . "\n";
$sql = "INSERT INTO bhl_page_name(NameBankID,PageID,NameConfirmed) VALUES (";
if ($name->NameBankID != null) {
$sql .= $name->NameBankID;
} else {
$sql .= '0';
}
$sql .= ',' . $page->PageID;
$sql .= ",'" . addslashes($name->NameFound) . "'";
$sql .= ');';
echo $sql . "\n";
}
/**
* @brief Handle OpenURL request
*
* We may have more than one parameter with same name, so need to access QUERY_STRING, not _GET
* http://stackoverflow.com/questions/353379/how-to-get-multiple-parameters-with-same-name-from-a-url-in-php
*
*/
function main()
{
global $config;
global $debug;
global $format;
$id = 0;
$callback = '';
// If no query parameters
if (count($_GET) == 0) {
display_form();
exit(0);
}
if (isset($_GET['format'])) {
switch ($_GET['format']) {
case 'html':
$format = 'html';
break;
case 'json':
$format = 'json';
break;
default:
$format = 'html';
break;
}
}
if (isset($_GET['callback'])) {
$callback = $_GET['callback'];
}
$debug = false;
if (isset($_GET['debug'])) {
$debug = true;
}
// Handle query and display results.
$query = explode('&', html_entity_decode($_SERVER['QUERY_STRING']));
$params = array();
foreach ($query as $param) {
list($key, $value) = explode('=', $param);
$key = preg_replace('/^\\?/', '', urldecode($key));
$params[$key][] = trim(urldecode($value));
}
if ($debug) {
echo '<h1>Params</h1>';
echo '<pre>';
print_r($params);
echo '</pre>';
}
// This is what we got from user
$referent = new stdclass();
parse_openurl($params, $referent);
// Flesh it out
// If we are looking for an article we need an ISSN, or at least an OCLC
// Ask whether have this in our database (assumes we have ISSN)
if (!isset($referent->issn)) {
// Try and get ISSN from bioGUID
$issn = issn_from_title($referent->secondary_title);
if ($issn != '') {
$referent->issn = $issn;
} else {
// No luck with ISSN, look for OCLC
if (!isset($referent->oclc)) {
$oclc = oclc_for_title($referent->secondary_title);
if ($oclc != 0) {
$referent->oclc = $oclc;
}
}
}
}
if ($debug) {
echo '<h1>Referent</h1>';
echo '<pre>';
print_r($referent);
echo '</pre>';
}
// Handle identifiers
if (isset($referent->url)) {
// BHL URL, for example if we have already mapped article to BHL
// in Zotero,
if (preg_match('/^http:\\/\\/(www\\.)?biodiversitylibrary.org\\/page\\/(?<pageid>[0-9]+)/', $referent->url, $matches)) {
//print_r($matches);
$PageID = $matches['pageid'];
$references = bhl_reference_from_pageid($PageID);
//print_r($references);
if (count($references) == 0) {
// We don't have an article for this PageID
$search_hit = bhl_score_page($PageID, $referent->title);
// Store
$id = db_store_article($referent, $PageID);
} else {
// Have a reference with this PageID already
// Will need to handle case where > 1 article on same page, e.g.
// http://www.biodiversitylibrary.org/page/3336598
$id = $references[0];
}
// Did we get a hit?
if ($id != 0) {
// We have this reference in our database
switch ($format) {
case 'json':
// Display object
$reference = db_retrieve_reference($id);
header("Content-type: text/plain; charset=utf-8\n\n");
if ($callback != '') {
echo $callback . '(';
}
echo json_format(json_encode($reference));
if ($callback != '') {
echo ')';
}
break;
case 'html':
default:
// Redirect to reference display
header('Location: ' . $config['web_root'] . 'reference/' . $id . "\n\n");
break;
}
exit;
}
}
}
// OK, we're not forcing a match to BHL, so do we have this article?
$id = db_find_article($referent);
//echo "<b>id=$id</b><br/>";
if ($id != 0) {
// We have this reference in our database
switch ($format) {
case 'json':
// Display object
$reference = db_retrieve_reference($id);
header("Content-type: text/plain; charset=utf-8\n\n");
if ($callback != '') {
echo $callback . '(';
}
echo json_format(json_encode($reference));
if ($callback != '') {
echo ')';
}
break;
case 'html':
default:
// Twitter as log
if ($config['twitter']) {
$tweet_this = false;
$tweet_this = isset($_GET['rfr_id']);
if ($tweet_this) {
$url = $config['web_root'] . 'reference/' . $id . ' ';
// . '#openurl'; // url + hashtag
$url = $id;
$url_len = strlen($url);
$status = '';
//$text = $_GET['rfr_id'];
$text = '#openurl ' . $_SERVER["HTTP_REFERER"];
//$text .= ' @rdmpage';
if (isset($article->title)) {
}
$status = $text;
$status_len = strlen($status);
$extra = 140 - $status_len - $url_len - 1;
if ($extra < 0) {
$status_len += $extra;
$status_len -= 1;
$status = substr($status, 0, $status_len);
$status .= '…';
}
$status .= ' ' . $url;
tweet($status);
}
}
// Redirect to reference display
header('Location: reference/' . $id . "\n\n");
break;
}
exit;
}
// OK, not found, so let's go look for it...
// Search BHL
$atitle = '';
if (isset($referent->title)) {
$atitle = $referent->title;
}
$search_hits = bhl_find_article($atitle, $referent->secondary_title, $referent->volume, isset($referent->spage) ? $referent->spage : $referent->pages, isset($referent->series) ? $referent->series : '', isset($referent->date) ? $referent->date : '', isset($referent->issn) ? $referent->issn : '');
if (count($search_hits) == 0) {
// try alternative way of searching using article title
$search_hits = bhl_find_article_from_article_title($referent->title, $referent->secondary_title, $referent->volume, isset($referent->spage) ? $referent->spage : $referent->pages, isset($referent->series) ? $referent->series : '', isset($referent->issn) ? $referent->issn : '');
}
// At this point if we haven't found it in BHL we could go elsewhere, e.g. bioGUID,
// in which case we'd need to take this into account when displaying HTML and JSON
if ($debug) {
echo '<h3>Search hits</h3>';
echo '<pre>';
print_r($search_hits);
echo '</pre>';
}
if (1) {
// Check whether we already have an article that starts on this
foreach ($search_hits as $hit) {
$references = bhl_reference_from_pageid($hit->PageID);
//print_r($references);
if (count($references) != 0) {
// We have this reference in our database
switch ($format) {
case 'json':
// Display object
$reference = db_retrieve_reference($references[0]);
header("Content-type: text/plain; charset=utf-8\n\n");
if ($callback != '') {
echo $callback . '(';
}
echo json_format(json_encode($reference));
if ($callback != '') {
echo ')';
}
break;
case 'html':
default:
// Redirect to reference display
header('Location: reference/' . $references[0] . "\n\n");
break;
}
exit;
}
}
}
// Output search results in various formats...
switch ($format) {
case 'json':
display_bhl_result_json($referent, $search_hits, $callback);
break;
case 'html':
default:
display_bhl_result_html($referent, $search_hits);
break;
}
}
function DisplayHtmlContent()
{
global $config;
echo html_page_header(true, '', 'name');
echo '<h1>' . $this->GetTitle() . '</h1>';
if (count($this->object->specimens) == 0) {
echo '<p>No specimens with this code</p>';
} else {
// What articles have this specimen?
echo '<h2>References in BioStor with this specimen</h2>';
$refs = specimens_references_with_code($this->code);
//print_r($refs);
foreach ($refs as $occurrenceID => $ref_list) {
if ($occurrenceID != 0) {
echo '<p>GBIF occurrence <a class="gbif" href="http://data.gbif.org/occurrences/' . $occurrenceID . '/" target="_new">' . $occurrenceID . '</a>';
$datasetID = specimens_dataset_from_occurrence($occurrenceID);
$dataset = specimens_dataset($datasetID);
echo ' from dataset <a href="gbif_dataset.php?datasetID=' . $dataset->datasetID . '">' . $dataset->dataResourceName . ' (' . $dataset->providerName . ')' . '</a>';
echo '</p>';
$occurrence = specimens_from_occurrenceID($occurrenceID);
echo '<p>' . $occurrence->scientificName . ' (' . join(':', $occurrence->lineage) . ')' . '</p>';
} else {
echo '<p>(specimen not known in GBIF)</p>';
}
echo '<table cellspacing="0" cellpadding="2" width="100%">';
foreach ($ref_list as $reference_id) {
$reference = db_retrieve_reference($reference_id);
echo '<tr';
if (in_array($reference_id, $act_refs)) {
echo ' style="background-color:#D8F3C9;"';
}
echo '>';
if ($reference->PageID != 0) {
$image = bhl_fetch_page_image($reference->PageID);
$imageURL = $image->thumbnail->url;
} else {
// if it's an article we could use journal image
$imageURL = 'http://bioguid.info/issn/image.php?issn=' . $reference->issn;
}
echo '<td valign="top"><img style="border:1px solid rgb(192,192,192);" src="' . $imageURL . '" width="40" />';
echo '</td>';
echo '<td valign="top">';
echo '<a href="' . $config['web_root'] . 'reference/' . $reference_id . '">' . $reference->title . '</a><br/>';
echo '<span>' . reference_authors_to_text_string($reference);
if (isset($reference->year)) {
echo ' (' . $reference->year . ')';
}
echo ' ' . reference_to_citation_text_string($reference) . '</span>';
echo ' ' . reference_to_coins($reference);
if (0) {
echo '<div>';
echo bhl_pages_with_name_thumbnails($reference_id, $this->object->NameBankID);
echo '</div>';
}
echo '</td>';
echo '</tr>';
}
echo '</table>';
}
}
}
// fetch names if we haven't got them...
require_once dirname(__FILE__) . '/db.php';
require_once dirname(__FILE__) . '/lib.php';
require_once dirname(__FILE__) . '/bhl_names.php';
$ids = array(126311);
$ids = array(105416, 105402, 125890, 59343, 107177);
$ids = array(110878);
$ids = array(99906, 108144, 100200, 100656, 107955, 107963, 107976, 83078, 66142, 87244, 87255, 105412, 87185, 87103, 65960, 66503, 87120, 105406, 86522, 105403, 126315, 107177, 95592, 97207, 105415, 87635, 97899, 65958, 48993, 59343, 14562, 125890, 103534, 109586, 891, 97484, 889, 105414, 1312, 104732, 84533, 113895, 105402, 85290, 114597, 126311, 102399);
$ids = array(54668, 14790, 54677, 99677, 127560, 60044, 127575, 127574, 99512, 107049, 106157, 105730, 125900, 127561, 105962, 61688, 58301, 105714, 58630, 14789, 98326, 14787, 106156, 97776, 99962, 98307, 14781, 97871, 4435, 844, 97482, 832, 97490, 101826, 106132);
$ids = array(127609);
$ids = array(120824);
$ids = array(116847);
$ids = array(127997);
foreach ($ids as $reference_id) {
echo $reference_id . "\n";
if (db_retrieve_reference($reference_id) != null) {
$nm = bhl_names_in_reference_by_page($reference_id);
if (isset($nm->names) && count($nm->names) == 0) {
// fetch names
$pages = bhl_retrieve_reference_pages($reference_id);
$page_ids = array();
foreach ($pages as $p) {
echo $p->PageID;
$parameters = array('op' => 'GetPageMetadata', 'pageid' => $p->PageID, 'ocr' => 'f', 'names' => 't', 'apikey' => '0d4f0303-712e-49e0-92c5-2113a5959159', 'format' => 'json');
$url = 'http://www.biodiversitylibrary.org/api2/httpquery.ashx?' . http_build_query($parameters);
$json = get($url);
//echo $json;
if ($json != '') {
$response = json_decode($json);
foreach ($response->Result->Names as $Name) {
echo '.';
}
/*
echo '<pre>';
print_r($page2biostor);
echo '</pre>';
*/
$count = 0;
foreach ($r as $row) {
if (is_array($row)) {
if (isset($row['Url'])) {
$PageID = str_replace('http://www.biodiversitylibrary.org/page/', '', $row['Url']);
//echo $PageID . '<br/>';
if (isset($page2biostor[$PageID])) {
if (!isset($hits[$page2biostor[$PageID]])) {
$reference = db_retrieve_reference($page2biostor[$PageID]);
$hit = reference_to_bibjson($reference);
$hit->PageID = $reference->PageID;
$hit->biostor = $page2biostor[$PageID];
$hits[$page2biostor[$PageID]] = $hit;
}
} else {
/* $ItemID = bhl_retrieve_ItemID_from_PageID($PageID);
if ($ItemID == 0)
{
$id = $count;
$count++;
}
else
{
function DisplayJson()
{
$act_refs = array();
$refs = bhl_references_with_namestring($this->GetTitle());
// Merge with references from nomenclators
$refs = array_merge($refs, $act_refs);
$refs = array_unique($refs);
$obj = new stdclass();
$obj->references = array();
foreach ($refs as $reference_id) {
$obj->references[] = db_retrieve_reference($reference_id);
}
header("Content-type: text/plain; charset=utf-8\n\n");
if ($this->callback != '') {
echo $this->callback . '(';
}
echo json_format(json_encode($obj));
if ($this->callback != '') {
echo ')';
}
}
function Retrieve()
{
if ($this->id != 0) {
$this->object = db_retrieve_reference($this->id);
$this->in_bhl = db_reference_from_bhl($this->id);
}
// Geocoding?
if ($this->in_bhl) {
if (!bhl_has_been_geocoded($this->id)) {
bhl_geocode_reference($this->id);
}
$this->localities = bhl_localities_for_reference($this->id);
}
// Specimens?
if ($this->in_bhl) {
if (!specimens_has_been_parsed($this->id)) {
specimens_from_reference($this->id);
}
$this->specimens = specimens_from_db($this->id);
}
return $this->object;
}
/**
* @brief Create PDF for a reference
*
* We create a simple cover page for the PDF. This page contains basic bibliographic metadata
* for the PDF, in order for Mendeley to process the PDF correctly. In response to my discovery
* that Mendeley doesn't accept all XMP (Ticket#2010040110000015) support@mendeley.com replied that
* they have some heuristic tests to see if the metadata is valid, such as whether the information
* about the title and authors occurs on the first of the PDF.
*
*
* @param reference_id Reference id
* @param pdf_filename Full path of PDF file to create
*
*/
function pdf_create($reference_id, $pdf_filename)
{
global $config;
// Get reference
$reference = db_retrieve_reference($reference_id);
// Get tags
$tags = pdf_tags($reference->reference_id, 10);
// Paper size
// A4 = 210 x 297
$paper_width = 210;
// mm
$paper_height = 297;
// mm
$margin = 10;
//----------------------------------------------------------------------------------------------
// PDF
$pdf = new FPDF('P', 'mm', 'A4');
//$pdf = PDF_Rotate('P', 'mm', 'A4');
//----------------------------------------------------------------------------------------------
// Basic metadata (e.g., that displayed by Mac OS X Preview)
$pdf->SetTitle($reference->title, true);
// true means use UTF-8
$pdf->SetAuthor(reference_authors_to_text_string($reference), true);
// true means use UTF-8
if (count($tags) > 0) {
$pdf->SetKeywords(join(", ", $tags), true);
}
//----------------------------------------------------------------------------------------------
// Cover page (partly to ensure Mendeley accepts XMP metadata)
$pdf->AddPage();
// Title
$pdf->SetFont('Arial', '', 24);
$pdf->SetXY($margin, $margin);
$pdf->Write(10, utf8_decode($reference->title));
// Authors
$y = $pdf->GetY();
$pdf->SetXY($margin, $y + 16);
$pdf->SetFont('Arial', 'B', 16);
$pdf->Write(6, utf8_decode(reference_authors_to_text_string($reference)));
// Citation
$y = $pdf->GetY();
$pdf->SetXY($margin, $y + 10);
$pdf->SetFont('Arial', 'I', 12);
$pdf->Write(6, utf8_decode($reference->secondary_title));
$pdf->SetFont('Arial', '', 12);
$pdf->Write(6, ' ' . $reference->volume);
if (isset($reference->issue)) {
$pdf->Write(6, '(' . $reference->issue . ')');
}
$pdf->Write(6, ':' . $reference->spage);
if (isset($reference->epage)) {
$pdf->Write(6, '-' . $reference->epage);
}
$pdf->Write(6, ' (' . $reference->year . ')');
// URL
$url = $config['web_root'] . 'reference/' . $reference->reference_id;
$pdf->Write(6, ' ');
$pdf->SetTextColor(0, 0, 255);
$pdf->SetFont('', 'U');
$pdf->Write(6, $url, $url);
$pdf->SetFont('', '');
$pdf->SetTextColor(0, 0, 0);
//----------------------------------------------------------------------------------------------
// If we add taxon names as keywords
if (count($tags) > 0) {
$keywords = "Keywords: " . join("; ", $tags);
$y = $pdf->GetY();
$pdf->SetXY($margin, $y + 10);
$pdf->Write(6, $keywords);
}
//----------------------------------------------------------------------------------------------
// Footer giving credit to BHL
$y = $paper_height;
$y -= $margin;
$y -= 40;
$pdf->Image($config['web_dir'] . '/images/cc/cc.png', 10, $y, 10);
$pdf->Image($config['web_dir'] . '/images/cc/by.png', 20, $y, 10);
$pdf->Image($config['web_dir'] . '/images/cc/nc.png', 30, $y, 10);
$pdf->SetXY(10, $y + 10);
$pdf->SetFont('Arial', '', 10);
$pdf->SetTextColor(0, 0, 0);
$pdf->Write(6, 'Page images from the Biodiversity Heritage Library, ');
//Then put a blue underlined link
$pdf->SetTextColor(0, 0, 255);
$pdf->SetFont('', 'U');
$pdf->Write(6, 'http://www.biodiversitylibrary.org/', 'http://www.biodiversitylibrary.org/');
$pdf->SetFont('', '');
$pdf->SetTextColor(0, 0, 0);
$pdf->Write(6, ', made available under a Creative Commons Attribution-Noncommercial License ');
$pdf->SetTextColor(0, 0, 255);
$pdf->SetFont('', 'U');
$pdf->Write(6, 'http://creativecommons.org/licenses/by-nc/2.5/', 'http://creativecommons.org/licenses/by-nc/2.5/');
//----------------------------------------------------------------------------------------------
// Add BHL page scans
$pages = bhl_retrieve_reference_pages($reference_id);
foreach ($pages as $page) {
$image = bhl_fetch_page_image($page->PageID);
$page_width = $paper_width;
$page_height = $paper_height;
$page_width -= 2 * $margin;
$page_height -= 2 * $margin;
// Fit to page
$img_height = $image->height;
$img_width = $image->width;
$w_scale = $page_width / $img_width;
$h_scale = $page_height / $img_height;
$scale = min($w_scale, $h_scale);
$img_height *= $scale;
$img_width *= $scale;
$pdf->AddPage();
$x_offset = ($paper_width - $img_width) / 2.0;
$y_offset = ($paper_height - $img_height) / 2.0;
$pdf->Image($image->file_name, $x_offset, $y_offset, $img_width);
}
$pdf->Output($pdf_filename, 'F');
pdf_add_xmp($reference, $pdf_filename, $tags);
}