suzanne.soy/zotero
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add Chrome/Safari-compatible PubMed

Browse Source
This commit is contained in:
Simon Kornblith 2011-07-01 04:21:20 +00:00
parent 3b2cc93269
commit 3dcb45d6ac
1 changed files with 150 additions and 86 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

218
translators/NCBI PubMed.js
View File

@ -4,12 +4,13 @@
"label":"NCBI PubMed", "label":"NCBI PubMed",
"creator":"Simon Kornblith, Michael Berkowitz, Avram Lyon, and Rintze Zelle", "creator":"Simon Kornblith, Michael Berkowitz, Avram Lyon, and Rintze Zelle",
"target":"https?://[^/]*(www|preview)\\.ncbi\\.nlm\\.nih\\.gov[^/]*/(pubmed|sites/pubmed|sites/entrez|entrez/query\\.fcgi\\?.*db=PubMed)", "target":"https?://[^/]*(www|preview)\\.ncbi\\.nlm\\.nih\\.gov[^/]*/(pubmed|sites/pubmed|sites/entrez|entrez/query\\.fcgi\\?.*db=PubMed)",
"minVersion":"2.1b1", "minVersion":"2.1.9",
"maxVersion":"", "maxVersion":"",
"priority":100, "priority":100,
"browserSupport":"gcs",
"configOptions":{"dataMode":"block"}, "configOptions":{"dataMode":"block"},
"inRepository":true, "inRepository":true,
"lastUpdated":"2011-04-25 18:05:00" "lastUpdated":"2011-07-01 04:22:03"
} }
function detectWeb(doc, url) { function detectWeb(doc, url) {
@ -91,9 +92,6 @@ function detectImport() {
} }
function doImportFromText(text) { function doImportFromText(text) {
// Remove xml parse instruction and doctype
text = text.replace(/<!DOCTYPE[^>]*>/, "").replace(/<\?xml[^>]*\?>/, "");
if (!text.substr(0,1000).match(/<PubmedArticleSet>/)) { if (!text.substr(0,1000).match(/<PubmedArticleSet>/)) {
// Pubmed data in the wild, perhaps copied from the web site's search results, // Pubmed data in the wild, perhaps copied from the web site's search results,
// can be missing the <PubmedArticleSet> root tag. Let's add a pair! // can be missing the <PubmedArticleSet> root tag. Let's add a pair!
@ -101,28 +99,30 @@ function doImportFromText(text) {
text = "<PubmedArticleSet>" + text + "</PubmedArticleSet>"; text = "<PubmedArticleSet>" + text + "</PubmedArticleSet>";
} }
var xml = new XML(text); // parse XML with DOMParser
var parser = new DOMParser();
var doc = parser.parseFromString(text, "text/xml");
for(var i=0; i<xml.PubmedArticle.length(); i++) { var articles = ZU.xpath(doc, '/PubmedArticleSet/PubmedArticle');
for(var i in articles) {
var newItem = new Zotero.Item("journalArticle"); var newItem = new Zotero.Item("journalArticle");
var citation = xml.PubmedArticle[i].MedlineCitation; var citation = ZU.xpath(articles[i], 'MedlineCitation');
var PMID = ZU.xpathText(citation, 'PMID');
var PMID = citation.PMID.text().toString();
newItem.url = "http://www.ncbi.nlm.nih.gov/pubmed/" + PMID; newItem.url = "http://www.ncbi.nlm.nih.gov/pubmed/" + PMID;
newItem.extra = "PMID: "+PMID; newItem.extra = "PMID: "+PMID;
var article = citation.Article; var article = ZU.xpath(citation, 'Article');
if(article.ArticleTitle.length()) { var title = ZU.xpathText(article, 'ArticleTitle');
var title = article.ArticleTitle.text().toString(); if(title) {
if(title.substr(-1) == ".") { if(title.substr(-1) == ".") {
title = title.substring(0, title.length-1); title = title.substring(0, title.length-1);
} }
newItem.title = title; newItem.title = title;
} }
if (article.Pagination.MedlinePgn.length()){ var fullPageRange = ZU.xpathText(article, 'Pagination/MedlinePgn');
var fullPageRange = article.Pagination.MedlinePgn.text().toString(); if(fullPageRange) {
var pageRange = fullPageRange.match(/\d+-\d+/g); var pageRange = fullPageRange.match(/\d+-\d+/g);
for (var j in pageRange) { for (var j in pageRange) {
var pageRangeStart = pageRange[j].match(/^\d+/)[0]; var pageRangeStart = pageRange[j].match(/^\d+/)[0];
@ -135,75 +135,87 @@ function doImportFromText(text) {
newItem.pages = fullPageRange; newItem.pages = fullPageRange;
} }
if(article.Journal.length()) { var journal = ZU.xpath(article, 'Journal');
var issn = article.Journal.ISSN.text().toString(); if(journal.length) {
if(issn) { newItem.ISSN = ZU.xpathText(journal, 'ISSN');
newItem.ISSN = issn;
var abbreviation;
if((abbreviation = ZU.xpathText(journal, 'ISOAbbreviation'))) {
newItem.journalAbbreviation = abbreviation;
} else if((abbreviation = ZU.xpathText(journal, 'MedlineTA'))) {
newItem.journalAbbreviation = abbreviation;
} }
if(citation.Article.Journal.ISOAbbreviation.length()) { var title = ZU.xpathText(journal, 'Title');
newItem.journalAbbreviation = Zotero.Utilities.superCleanString(citation.Article.Journal.ISOAbbreviation.text().toString()); if(title) {
} else if(citation.MedlineJournalInfo.MedlineTA.length()) { newItem.publicationTitle = title;
newItem.journalAbbreviation = Zotero.Utilities.superCleanString(citation.MedlineJournalInfo.MedlineTA.text().toString()); } else if(newItem.journalAbbreviation) {
}
if(article.Journal.Title.length()) {
newItem.publicationTitle = Zotero.Utilities.superCleanString(article.Journal.Title.text().toString());
} else if(newItem.journalAbbreviation.length()) {
newItem.publicationTitle = newItem.journalAbbreviation; newItem.publicationTitle = newItem.journalAbbreviation;
} }
if(article.Journal.JournalIssue.length()) { var journalIssue = ZU.xpath(journal, 'JournalIssue');
newItem.volume = article.Journal.JournalIssue.Volume.text().toString(); if(journalIssue.length) {
newItem.issue = article.Journal.JournalIssue.Issue.text().toString(); newItem.volume = ZU.xpathText(journalIssue, 'Volume');
if(article.Journal.JournalIssue.PubDate.length()) { // try to get the date newItem.issue = ZU.xpathText(journalIssue, 'Issue');
if(article.Journal.JournalIssue.PubDate.Day.text().toString() != "") { var pubDate = ZU.xpath(journalIssue, 'PubDate');
newItem.date = article.Journal.JournalIssue.PubDate.Month.text().toString()+" "+article.Journal.JournalIssue.PubDate.Day.text().toString()+", "+article.Journal.JournalIssue.PubDate.Year.text().toString(); if(pubDate.length) { // try to get the date
} else if(article.Journal.JournalIssue.PubDate.Month.text().toString() != "") { var day = ZU.xpathText(pubDate, 'Day');
newItem.date = article.Journal.JournalIssue.PubDate.Month.text().toString()+" "+article.Journal.JournalIssue.PubDate.Year.text().toString(); var month = ZU.xpathText(pubDate, 'Month');
} else if(article.Journal.JournalIssue.PubDate.Year.text().toString() != "") { var year = ZU.xpathText(pubDate, 'Year');
newItem.date = article.Journal.JournalIssue.PubDate.Year.text().toString();
} else if(article.Journal.JournalIssue.PubDate.MedlineDate.text().toString() != "") { if(day) {
newItem.date = article.Journal.JournalIssue.PubDate.MedlineDate.text().toString(); newItem.date = month+" "+day+", "+year;
} else if(month) {
newItem.date = month+" "+year;
} else if(year) {
newItem.date = year;
} else {
newItem.date = ZU.xpathText(pubDate, 'MedlineDate');
} }
} }
} }
} }
if(article.AuthorList.length() && article.AuthorList.Author.length()) { var authors = ZU.xpath(article, 'AuthorList/Author');
var authors = article.AuthorList.Author; for(var j in authors) {
for(var j=0; j<authors.length(); j++) { var author = authors[j];
var lastName = authors[j].LastName.text().toString();
var firstName = authors[j].FirstName.text().toString(); var lastName = ZU.xpathText(author, 'LastName');
if(firstName == "") { var firstName = ZU.xpathText(author, 'FirstName');
firstName = authors[j].ForeName.text().toString(); if(!firstName) {
} firstName = ZU.xpathText(author, 'ForeName');
var suffix = authors[j].Suffix.text().toString(); }
if(suffix && firstName != "") { var suffix = ZU.xpathText(author, 'Suffix');
firstName += ", " + authors[j].Suffix.text().toString(); if(suffix && firstName) {
} firstName += ", " + suffix
if(firstName || lastName) { }
newItem.creators.push({lastName:lastName, firstName:firstName}); if(firstName || lastName) {
} newItem.creators.push({lastName:lastName, firstName:firstName});
} }
} }
if (citation.MeshHeadingList && citation.MeshHeadingList.MeshHeading) { var keywords = ZU.xpath(citation, 'MeshHeadingList/MeshHeading');
var keywords = citation.MeshHeadingList.MeshHeading; for(var k in keywords) {
for (var k = 0 ; k < keywords.length() ; k++) { newItem.tags.push(ZU.xpathText(keywords[k], 'DescriptorName'));
newItem.tags.push(keywords[k].DescriptorName.text().toString());
}
} }
// We use a regex to remove the section labels
// also, we have entities to clear up
newItem.abstractNote = Zotero.Utilities.unescapeHTML(
article.Abstract.AbstractText.toString()
.replace(/<\/?AbstractText\s*(?:Label=")?([^">]+)?[^>]*>/g, "$1\n")
);
newItem.DOI = xml.PubmedArticle[i].PubmedData.ArticleIdList.ArticleId.(@IdType == "doi" ).text().toString(); var abstractSections = ZU.xpath(article, 'Abstract/AbstractText');
newItem.publicationTitle = Zotero.Utilities.capitalizeTitle(newItem.publicationTitle); var abstractNote = [];
for(var j in abstractSections) {
var abstractSection = abstractSections[j];
if(abstractSection.hasAttribute("Label")) {
abstractNote.push(abstractSection.getAttribute("Label"));
}
abstractNote.push(abstractSection.textContent+"\n");
}
newItem.abstractNote = abstractNote.join("\n\n");
newItem.DOI = ZU.xpathText(articles[i], 'PubmedData/ArticleIdList/ArticleId[@IdType="doi"]');
// (do we want this?)
if(newItem.publicationTitle) {
newItem.publicationTitle = Zotero.Utilities.capitalizeTitle(newItem.publicationTitle);
}
newItem.complete(); newItem.complete();
} }
} }
@ -238,17 +250,17 @@ function doWeb(doc, url) {
items[uid.value] = article.textContent; items[uid.value] = article.textContent;
} }
items = Zotero.selectItems(items); Zotero.selectItems(items, function(items) {
if(!items) {
return true;
}
if(!items) { for(var i in items) {
return true; ids.push(i);
} }
for(var i in items) { lookupPMIDs(ids);
ids.push(i); });
}
lookupPMIDs(ids);
} else { } else {
ids.push(uid.value); ids.push(uid.value);
lookupPMIDs(ids, doc); lookupPMIDs(ids, doc);
@ -293,3 +305,55 @@ function doSearch(item) {
// pmid was defined earlier in detectSearch // pmid was defined earlier in detectSearch
lookupPMIDs([getPMID(item.contextObject)]); lookupPMIDs([getPMID(item.contextObject)]);
} }
/** BEGIN TEST CASES **/
var testCases = [
{
"type": "web",
"url": "http://www.ncbi.nlm.nih.gov/pubmed/20729678",
"items": [
{
"itemType": "journalArticle",
"creators": [
{
"lastName": "Coar",
"firstName": "Jaekea T"
},
{
"lastName": "Sewell",
"firstName": "Jeanne P"
}
],
"notes": [],
"tags": [
"Bibliography as Topic",
"Database Management Systems",
"Humans"
],
"seeAlso": [],
"attachments": [],
"url": "http://www.ncbi.nlm.nih.gov/pubmed/20729678",
"extra": "PMID: 20729678",
"title": "Zotero: harnessing the power of a personal bibliographic manager",
"pages": "205-207",
"ISSN": "1538-9855",
"journalAbbreviation": "Nurse Educ",
"publicationTitle": "Nurse Educator",
"volume": "35",
"issue": "5",
"date": "2010 Sep-Oct",
"abstractNote": "Zotero is a powerful free personal bibliographic manager (PBM) for writers. Use of a PBM allows the writer to focus on content, rather than the tedious details of formatting citations and references. Zotero 2.0 (http://www.zotero.org) has new features including the ability to synchronize citations with the off-site Zotero server and the ability to collaborate and share with others. An overview on how to use the software and discussion about the strengths and limitations are included.\u000a",
"DOI": "10.1097/NNE.0b013e3181ed81e4",
"libraryCatalog": "NCBI PubMed",
"shortTitle": "Zotero"
}
]
},
{
"type": "web",
"url": "http://www.ncbi.nlm.nih.gov/pubmed?term=zotero",
"items": "multiple"
}
]
/** END TEST CASES **/