discourse/lib/onebox/engine/pubmed_onebox.rb
Arpit Jalan 283b08d45f
DEV: Absorb onebox gem into core (#12979)
* Move onebox gem in core library

* Update template file path

* Remove warning for onebox gem caching

* Remove onebox version file

* Remove onebox gem

* Add sanitize gem

* Require onebox library in lazy-yt plugin

* Remove onebox web specific code

This code was used in standalone onebox Sinatra application

* Merge Discourse specific AllowlistedGenericOnebox engine in core

* Fix onebox engine filenames to match class name casing

* Move onebox specs from gem into core

* DEV: Rename `response` helper to `onebox_response`

Fixes a naming collision.

* Require rails_helper

* Don't use `before/after(:all)`

* Whitespace

* Remove fakeweb

* Remove poor unit tests

* DEV: Re-add fakeweb, plugins are using it

* Move onebox helpers

* Stub Instagram API

* FIX: Follow additional redirect status codes (#476)

Don’t throw errors if we encounter 303, 307 or 308 HTTP status codes in responses

* Remove an empty file

* DEV: Update the license file

Using the copy from https://choosealicense.com/licenses/gpl-2.0/#

Hopefully this will enable GitHub to show the license UI?

* DEV: Update embedded copyrights

* DEV: Add Onebox copyright notice

* DEV: Add MIT license, convert COPYRIGHT.txt to md

* DEV: Remove an incorrect copyright claim

Co-authored-by: Jarek Radosz <jradosz@gmail.com>
Co-authored-by: jbrw <jamie@goatforce5.org>
2021-05-26 15:11:35 +05:30

61 lines
1.6 KiB
Ruby

# frozen_string_literal: true
module Onebox
module Engine
class PubmedOnebox
include Engine
include LayoutSupport
matches_regexp(/^https?:\/\/(?:(?:\w)+\.)?(www.ncbi.nlm.nih)\.gov(?:\/)?\/pubmed\/\d+/)
private
def xml
return @xml if defined?(@xml)
doc = Nokogiri::XML(URI.open(URI.join(@url, "?report=xml&format=text")))
pre = doc.xpath("//pre")
@xml = Nokogiri::XML("<root>" + pre.text + "</root>")
end
def authors
initials = xml.css("Initials").map { |x| x.content }
last_names = xml.css("LastName").map { |x| x.content }
author_list = (initials.zip(last_names)).map { |i, l| i + " " + l }
if author_list.length > 1 then
author_list[-2] = author_list[-2] + " and " + author_list[-1]
author_list.pop
end
author_list.join(", ")
end
def date
xml.css("PubDate")
.children
.map { |x| x.content }
.select { |s| !s.match(/^\s+$/) }
.map { |s| s.split }
.flatten
.sort
.reverse
.join(" ") # Reverse sort so month before year.
end
def data
{
title: xml.css("ArticleTitle").text,
authors: authors,
journal: xml.css("Title").text,
abstract: xml.css("AbstractText").text,
date: date,
link: @url,
pmid: match[:pmid]
}
end
def match
@match ||= @url.match(%r{www\.ncbi\.nlm\.nih\.gov/pubmed/(?<pmid>[0-9]+)})
end
end
end
end