Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Extract DOI from the current web page URL #1799

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Extract DOI from the current web page URL #1799

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1b6deda
Extract DOI from the current web page URL
mrtcode Dec 14, 2018
92f8713
Fix regular expression, decode DOI
mrtcode Dec 17, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 21 additions & 8 deletions DOI.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@
"inRepository": true,
"translatorType": 4,
"browserSupport": "gcsv",
"lastUpdated": "2016-11-05 10:57:01"
"lastUpdated": "2018-12-14 20:57:01"
}

// The variables items and selectArray will be filled during the first
Expand All @@ -20,7 +20,18 @@ var selectArray = {};


// builds a list of DOIs
function getDOIs(doc) {
function getDOIs(doc, url) {
var dois = [], m, DOI;

// Extract DOIs from the current URL
var re = /10.[0-9]{4,}?\/[^\s&?#,]*[^\s&?#\/.,]/g;
while (m = re.exec(url)) {
DOI = decodeURIComponent(m[0]);
if (!dois.includes(DOI)) {
dois.push(DOI);
}
}

// TODO Detect DOIs more correctly.
// The actual rules for DOIs are very lax-- but we're more strict.
// Specifically, we should allow space characters, and all Unicode
Expand All @@ -36,10 +47,7 @@ function getDOIs(doc) {
const DOIre = /\b10\.[0-9]{4,}\/[^\s&"']*[^\s&"'.,]/g;
const DOIXPath = "//text()[contains(., '10.')]\
[not(parent::script or parent::style)]";

var dois = [];

var node, m, DOI;
var node;
var results = doc.evaluate(DOIXPath, doc, null, XPathResult.ANY_TYPE, null);
while (node = results.iterateNext()) {
//Z.debug(node.nodeValue)
Expand Down Expand Up @@ -69,7 +77,7 @@ function detectWeb(doc, url) {
const blacklistRe = /^https?:\/\/[^/]*(?:google\.com|sciencedirect\.com\/science\/advertisement\/)/i;

if (!blacklistRe.test(url)) {
var DOIs = getDOIs(doc);
var DOIs = getDOIs(doc, url);
if (DOIs.length) {
return "multiple";
}
Expand Down Expand Up @@ -151,7 +159,7 @@ function retrieveDOIs(dois, doc, providers) {
}

function doWeb(doc, url) {
var dois = getDOIs(doc);
var dois = getDOIs(doc, url);
Z.debug(dois);
var providers = [
{
Expand Down Expand Up @@ -191,6 +199,11 @@ var testCases = [
"type": "web",
"url": "https://en.wikipedia.org/wiki/Template_talk:Doi",
"items": "multiple"
},
{
"type": "web",
"url": "https://zotero.org/?d=10.7208/chicago/9780226924632.001.0001",
"items": "multiple"
}
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you also add https://onlinelibrary.wiley.com/doi/abs/10.1002/(SICI)1099-1360(199711)6:6%3C320::AID-MCDA164%3E3.0.CO;2-2 as a test case?

]
/** END TEST CASES **/