~srushe/indieweb-authorship: Support encoded emails within the h-card.

7 files changed, 77 insertions(+), 8 deletions(-)

M CHANGELOG.md
M Gemfile.lock
M indieweb-authorship.gemspec
M lib/indieweb/authorship.rb
M lib/indieweb/authorship/version.rb
A spec/examples/h-entry-author-email-is-escaped
A spec/h-entry-author-email-is-escaped_spec.rb

M CHANGELOG.md => CHANGELOG.md +14 -0

@@ 6,6 6,20 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 ## [Unreleased]
 
+## [0.2.2] - 2021-04-03
+
+### Added
+
+- Support encoded emails within the h-card.
+
+### Changed
+
+- Update microformats gem to a minimum of 4.2.1 (to remove Ruby 2.7 deprecation warning).
+
+### Security
+
+- Update nokogiri from 1.10.10 to 1.11.2
+
 ## [0.2.1] - 2020-08-02
 
 ### Changed

M Gemfile.lock => Gemfile.lock +4 -4

@@ 1,15 1,15 @@
 PATH
   remote: .
   specs:
-    indieweb-authorship (0.2.1)
-      microformats (~> 4.0, >= 4.1.0)
+    indieweb-authorship (0.2.2)
+      microformats (~> 4.0, >= 4.2.1)
 
 GEM
   remote: https://rubygems.org/
   specs:
     diff-lcs (1.3)
-    json (2.3.1)
-    microformats (4.2.0)
+    json (2.5.1)
+    microformats (4.2.1)
       json (~> 2.2)
       nokogiri (~> 1.10)
     mini_portile2 (2.5.0)

M indieweb-authorship.gemspec => indieweb-authorship.gemspec +1 -1

@@ 28,7 28,7 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
-  spec.add_runtime_dependency "microformats", "~> 4.0", ">= 4.1.0"
+  spec.add_runtime_dependency "microformats", "~> 4.0", ">= 4.2.1"
 
   spec.add_development_dependency "bundler", "~> 1.16"
   spec.add_development_dependency "rake", "~> 13.0"

M lib/indieweb/authorship.rb => lib/indieweb/authorship.rb +9 -2

@@ 3,11 3,12 @@
 require 'indieweb/authorship/version'
 require 'microformats'
 require 'net/http'
+require 'cgi'
 
 module Indieweb
   module Authorship
     def self.identify(url, html = nil)
-      collection = microformats_from(html: html, url: url)
+      collection = microformats_from(html: unescaped_html_for(html), url: url)
 
       # 1. start with a particular h-entry to determine authorship for, and
       #    no author. if no h-entry, then there's no post to find authorship


@@ 64,7 65,7 @@ module Indieweb
 
     def self.microformats_from(html: nil, url:)
       html ||= Net::HTTP.get(URI(url))
-      ::Microformats.parse(html, base: url)
+      ::Microformats.parse(unescaped_html_for(html), base: url)
     end
     private_class_method :microformats_from
 


@@ 182,5 183,11 @@ module Indieweb
                      hcard['properties']['name'][0],
                      hcard['properties']['photo'][0])
     end
+
+    def self.unescaped_html_for(html)
+      return if html.nil?
+      CGI.unescape(html)
+    end
+    private_class_method :unescaped_html_for
   end
 end

M lib/indieweb/authorship/version.rb => lib/indieweb/authorship/version.rb +1 -1

@@ 1,5 1,5 @@
 module Indieweb
   module Authorship
-    VERSION = "0.2.1"
+    VERSION = "0.2.2"
   end
 end

A spec/examples/h-entry-author-email-is-escaped => spec/examples/h-entry-author-email-is-escaped +24 -0

@@ 0,0 1,24 @@
+HTTP/1.1 200 OK
+Server: Apache
+Date: Wed, 09 Dec 2015 03:29:14 GMT
+Content-Type: text/html; charset=utf-8
+
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <title>busybee</title>
+</head>
+
+<body>
+  <article class="entry h-entry">
+    <span class="h-card p-author hidden">
+      <a class="p-name u-url" rel="author me" href="/">fluffy</a>
+      <a class="u-email" href="mailto:fluffy%40beesbuzz%2ebiz">fluffy at beesbuzz dot biz</a>
+      <a class="u-photo" href="/static/headshot.jpg"></a>
+      <time class="dt-bday" datetime="1978-06-14"></time>
+      <span class="p-note">A Seattle-based programmer/musician who makes games, comics, and bad decisions.</span>
+      <span class="p-pronouns"><span class="p-pronoun-nominative">she</span>/<span class="p-pronoun-oblique">her</span> or <span class="p-pronoun-nominative">they</span>/<span class="p-pronoun-oblique">them</span></span>
+    </span>
+  </article>
+</body>
+</html><
\ No newline at end of file

A spec/h-entry-author-email-is-escaped_spec.rb => spec/h-entry-author-email-is-escaped_spec.rb +24 -0

@@ 0,0 1,24 @@
+RSpec.describe Indieweb::Authorship do
+  let(:page) { 'h-entry-author-email-is-escaped' }
+  let(:url) { "https://beesbuzz.biz/" }
+  let(:html) { html_for(page) }
+  let(:expected_data) do
+    {
+      'url' => url,
+      'name' => 'fluffy',
+      'photo' => 'https://beesbuzz.biz/static/headshot.jpg'
+    }
+  end
+
+  before do
+    allow(Net::HTTP).to receive(:get).with(URI(url)) { html }
+  end
+
+  context 'when given just a URL' do
+    it { expect(described_class.identify(url)).to eq expected_data }
+  end
+
+  context 'when given both a URL and HTML' do
+    it { expect(described_class.identify(url, html)).to eq expected_data }
+  end
+end