microformats2 2.9.0 → 3.0.0

data/lib/microformats2/time_property_parser.rb

@@ -0,0 +1,161 @@
+module Microformats2
+  class TimePropertyParser < ParserCore
+
+    def parse(element, base: nil, element_type: , format_class_array: [], backcompat:  nil)
+      @base = base
+      @duration_value = nil
+      @date_value = nil
+      @time_value = nil
+
+      @property_type = element_type
+
+      @fmt_classes = format_class_array
+      @mode_backcompat = backcompat
+
+      parse_value_class_pattern(element)
+
+      if @duration_value.nil?  and @time_value.nil? and @date_value.nil?
+
+        value = nil
+        if ['time', 'ins', 'del'].include? element.name and not element.attribute('datetime').nil?
+          value = element.attribute('datetime').value.strip
+        elsif element.name == 'abbr' and not element.attribute('title').nil?
+          value = element.attribute('title').value.strip
+        elsif (element.name == 'data' or element.name == 'input') and not element.attribute('value').nil?
+          value = element.attribute('value').value.strip
+        else
+          value = element.text.strip
+        end
+
+        parse_dt(value)
+
+      end
+
+      if not  @duration_value.nil?
+        @duration_value
+      elsif not @time_value.nil? and not @date_value.nil?
+        @date_value + ' ' + @time_value
+      elsif not @time_value.nil?
+        @time_value
+      elsif not @date_value.nil?
+        @date_value
+      else
+        nil
+      end
+    end
+
+    def parse_value_class_pattern(element)
+      parse_node(element.children)
+    end
+
+    def parse_element(element)
+
+      if @duration_value.nil? or (@time_value.nil? and @date_value.nil?)
+        if value_title_classes(element).length >= 1
+          value =  element.attribute('title').value.strip
+        elsif value_classes(element).length >= 1
+          if element.name == 'img' or element.name == 'area' and not element.attribute('alt').nil?
+            value = element.attribute('alt').value.strip
+          elsif element.name == 'data' and not element.attribute('value').nil?
+            value = element.attribute('value').value.strip
+          elsif element.name == 'abbr' and not element.attribute('title').nil?
+            value = element.attribute('title').value.strip
+          elsif ['time', 'ins', 'del'].include? element.name and not element.attribute('datetime').nil?
+            value = element.attribute('datetime').value.strip
+          else
+            value = element.text.strip
+          end
+        end
+        parse_dt(value, normalize: true) 
+
+        p_classes = property_classes(element)
+        p_classes = backcompat_property_classes(element) if @mode_backcompat
+        if p_classes.length == 0 and format_classes(element).length == 0
+          parse_node(element.children)
+        end
+      end
+
+    end
+
+    def parse_dt(data, normalize: false)
+      # currently the value-class-pattern page lists to normalize  and remove :'s but not regular parsing, seems very odd
+      # https://github.com/microformats/tests/issues/29
+      #
+      #TODO this still allows a lot of non correct values such as 39th day of the month, etc
+      begin
+        case data.strip
+        when /^(\d{4}-[01]\d-[0-3]\d)[tT ]([0-2]\d:[0-5]\d(:[0-5]\d)?([zZ]|[-+][01]?\d:?[0-5]\d)?)$/
+          @date_value = $1 if @date_value.nil?
+          @time_value = $2.gsub(/z/, 'Z') if @time_value.nil?
+        when /^(\d{4}-[01]\d-[0-3]\d)[tT ]([0-2]\d:[0-5]\d(:[0-5]\d)? ?[-+]\d\d)$/
+          @date_value = $1 if @date_value.nil?
+          @time_value = $2 if @time_value.nil?
+        when /^(\d{4}-[01]\d-[0-3]\d)[tT ]([0-2]\d:[0-5]\d:[0-5]\d ?[-+]\d\d):?(\d\d)$/
+          @date_value = $1 if @date_value.nil?
+          if normalize
+            @time_value = $2 + $3 if @time_value.nil?
+          else
+            @time_value = $2 + ':' + $3 if @time_value.nil?
+          end
+        when /^(\d{4}-[01]\d-[0-3]\d)[tT ]([0-2]\d:[0-5]\d)( ?[-+]\d\d:?\d\d)$/
+          @date_value = $1 if @date_value.nil?
+          if normalize
+            @time_value = $2 + $3.gsub(/:/,'') if @time_value.nil?
+          else
+            @time_value = $2 + $3 if @time_value.nil?
+          end
+        when /^P\d*W$/
+          @duration_value = data if @duration_value.nil?
+
+        when /^P(\d+Y)?(\d+M)?(\d+D)?(T(\d+H)?(\d+M)?(\d+S)?)?$/
+          @duration_value = data if @duration_value.nil?
+
+        when /^(\d{4})-([01]?\d)-([0-3]?\d)$/
+          @date_value = DateTime.new($1.to_i, $2.to_i, $3.to_i).strftime('%F') if @date_value.nil?
+
+        when /^(\d{4})-([0-3]\d{2})$/
+          @date_value = data if @date_value.nil?
+
+        when /^(\d{4})-([01]?\d)$/
+          @date_value = data if @date_value.nil?
+
+        when /^[0-2]\d:[0-5]\d(:[0-5]\d)?([zZ]|[-+][01]\d:?\d\d)?$/
+          if normalize
+            @time_value = data.gsub(/z/, 'Z').gsub(/([+-]\d\d):(\d\d)/, '\1\2') if @time_value.nil?
+          else
+            @time_value = data.gsub(/z/, 'Z') if @time_value.nil?
+          end
+
+        when /^[0-2]\d:[0-5]\d[zZ]?$/
+          @time_value = Time.parse(data).strftime('%H:%M') if @time_value.nil?
+        when /^([0-2]\d:[0-5]\d:[0-5]\d[-+][01]\d:?[0-5]\d)$/
+          Time.parse(data).strftime('%T') #to make sure this time doesn't throw an error
+          @time_value = $1 if @time_value.nil?
+
+        when /^([0-2][0-0]:[0-5]\d[-+][01]\d:?[0-5]\d)$/
+          Time.parse(data).strftime('%H:%M') #to make sure this time doesn't throw an error
+          @time_value = $1 if @time_value.nil?
+
+        when /^([01]?\d):?([0-5]\d)?p\.?m\.?$/i
+          @time_value = ($1.to_i + 12).to_s + ':' + $2.to_s.rjust(2,'0') if @time_value.nil?
+        when /^([01]?\d):?([0-5]\d)?a\.?m\.?$/i
+          @time_value = $1.to_s.rjust(2,'0') + ':' + $2.to_s.rjust(2,'0') if @time_value.nil?
+        when /^([01]?\d):([0-5]\d):([0-5]\d)?p\.?m\.?$/i
+          @time_value = ($1.to_i + 12).to_s + ':' + $2.to_s.rjust(2,'0') + ':'+ $3.to_s.rjust(2,'0') if @time_value.nil?
+        when /^([01]?\d):([0-5]\d):([0-5]\d)?a\.?m\.?$/i
+          @time_value = $1.to_s.rjust(2,'0') + ':' + $2.to_s.rjust(2,'0') + ':'+ $3.to_s.rjust(2,'0') if @time_value.nil?
+
+        else
+          t = Time.parse(data)
+          @time_value = t.strftime('%T') if @time_value.nil?
+          @date_value = t.strftime('%F') if @date_value.nil?
+        end
+
+      rescue
+        nil
+      end
+
+    end
+
+  end
+end

data/lib/microformats2/version.rb

@@ -1,3 +1,3 @@
 module Microformats2
-  VERSION = "2.9.0"
+  VERSION = "3.0.0"
 end

data/microformats2.gemspec

@@ -17,9 +17,10 @@ Gem::Specification.new do |gem|
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
   gem.require_paths = ["lib"]
 
+  gem.required_ruby_version = ">= 2.0"
+
   gem.add_runtime_dependency "nokogiri"
   gem.add_runtime_dependency "json"
-  gem.add_runtime_dependency "activesupport"
 
   gem.add_development_dependency "rake"
   gem.add_development_dependency "rspec"

data/spec/lib/microformats2/absolute_uri_spec.rb

@@ -3,7 +3,7 @@ require "microformats2/absolute_uri"
 
 describe Microformats2::AbsoluteUri do
   describe "#absolutize" do
-    subject { Microformats2::AbsoluteUri.new(base, relative).absolutize }
+    subject { Microformats2::AbsoluteUri.new(relative, base: base).absolutize }
     let(:base) { nil }
 
     context "when relative is nil" do
@@ -18,7 +18,7 @@ describe Microformats2::AbsoluteUri do
 
     context "when relative is a valid absolute URI" do
       let(:relative) { "http://google.com" }
-      it { should eq("http://google.com/") }
+      it { should eq("http://google.com") }
     end
 
     context "when relative is a valid non-absolute URI" do

data/spec/lib/microformats2/parser_spec.rb

@@ -6,7 +6,7 @@ describe Microformats2::Parser do
 
   describe "#http_headers" do
     it "starts as a blank hash" do
-      parser.http_headers.should eq({})
+      expect(parser.http_headers).to eq({})
     end
 
     describe "open file" do
@@ -15,10 +15,10 @@ describe Microformats2::Parser do
       end
 
       it "doesn't save #http_headers" do
-        parser.http_headers.should eq({})
+        expect(parser.http_headers).to eq({})
       end
       it "saves #http_body" do
-        parser.http_body.should include "<!DOCTYPE html>"
+        expect(parser.http_body).to include "<!DOCTYPE html>"
       end
     end
 
@@ -31,11 +31,42 @@ describe Microformats2::Parser do
       end
 
       it "saves #http_headers" do
-        parser.http_headers.should eq({"content-length" => "3"})
+        expect(parser.http_headers).to eq({"content-length" => "3"})
       end
       it "saves #http_body" do
-        parser.http_body.should eq("abc")
+        expect(parser.http_body).to eq("abc")
       end
     end
   end
+
+  describe "microformat-tests/tests" do
+    cases_dir = "vendor/tests/tests/*" 
+    #cases_dir = "vendor/tests/tests/microformats-mixed"
+    #cases_dir = "vendor/tests/tests/microformats-v1"
+    #cases_dir = "vendor/tests/tests/microformats-working"
+    #cases_dir = "vendor/tests/tests/microformats-v2" #limit to only v2 for now
+    Dir[File.join(cases_dir, "*")].each do |page_dir|
+    describe page_dir.split("/")[-2..-1].join("/") do
+        Dir[File.join(page_dir, "*")].keep_if { |f| f =~ /([.]json$)/ }.each do |json_file|
+          it "#{json_file.split("/").last}" do
+
+            if  json_file =~ /\/includes\//
+              pending "include-pattern are not yet implemented"
+            elsif json_file =~ /\/h-entry\/urlincontent/
+              pending "known issue / this is an aspect of nokogiri / won't fix"
+            elsif json_file =~ /\/hcard\/email/
+              pending "believed issue with the test suite, test needs to be fixed"
+            end
+            #pending "These are dynamic tests that are not yet passing so commenting out for now"
+            html_file = json_file.gsub(/([.]json$)/, ".html")
+            html = open(html_file).read
+            json = open(json_file).read
+            
+            expect(JSON.parse(Microformats2.parse(html, base: 'http://example.com').to_json)).to eq(JSON.parse(json))
+          end
+        end
+      end
+    end
+  end
+
 end

data/spec/lib/microformats2_spec.rb

@@ -9,25 +9,25 @@ describe Microformats2 do
   end
 
   describe "::parse" do
-    it "returns a collection" do
-      Microformats2.parse(@html).should be_kind_of Microformats2::Collection
+    it "returns ParserResult" do
+      expect(Microformats2.parse(@html)).to be_kind_of Microformats2::Collection
     end
   end
 
   describe "::read_html" do
     it "can be a string of html" do
-      Microformats2.read_html(@html).should include @html
+      expect(Microformats2.read_html(@html)).to include @html
     end
     it "can be a file path to html" do
       html = "spec/support/lib/microformats2/simple.html"
-      Microformats2.read_html(html).should include "<div class=\"h-card\">"
+      expect(Microformats2.read_html(html)).to include "<div class=\"h-card\">"
     end
     it "can be a url to html" do
       stub_request(:get, "http://google.com/").
                with(:headers => {'Accept'=>'*/*', 'User-Agent'=>'Ruby'}).
                to_return(:status => 200, :body => "google", :headers => {})
       html = "http://google.com"
-      Microformats2.read_html(html).should include "google"
+      expect(Microformats2.read_html(html)).to include "google"
     end
   end
 end

data/spec/spec_helper.rb

@@ -3,7 +3,6 @@ SimpleCov.start
 
 require 'rubygems'
 require 'rspec'
-require 'rspec/autorun'
 require 'webmock/rspec'
 
 RSpec.configure do |config|

data/vendor/tests/.gitignore

@@ -0,0 +1,25 @@
+
+lib-cov
+*.seed
+*.log
+*.csv
+*.dat
+*.out
+*.pid
+*.gz
+
+pids
+logs
+results
+
+node_modules
+lib
+oldhtml
+templates/change-log.html
+
+npm-debug.log
+_site
+.DS_Store
+*.svn-base
+
+

data/vendor/tests/LICENSE.md

@@ -0,0 +1,36 @@
+# Creative Commons Legal Code
+
+## CC0 1.0 Universal
+
+http://creativecommons.org/publicdomain/zero/1.0
+
+Official translations of this legal tool are available> CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED HEREUNDER.
+
+### _Statement of Purpose_
+
+The laws of most jurisdictions throughout the world automatically confer exclusive Copyright and Related Rights (defined below) upon the creator and subsequent owner(s) (each and all, an "owner") of an original work of authorship and/or a database (each, a "Work").
+
+Certain owners wish to permanently relinquish those rights to a Work for the purpose of contributing to a commons of creative, cultural and scientific works ("Commons") that the public can reliably and without fear of later claims of infringement build upon, modify, incorporate in other works, reuse and redistribute as freely as possible in any form whatsoever and for any purposes, including without limitation commercial purposes. These owners may contribute to the Commons to promote the ideal of a free culture and the further production of creative, cultural and scientific works, or to gain reputation or greater distribution for their Work in part through the use and efforts of others.
+
+For these and/or other purposes and motivations, and without any expectation of additional consideration or compensation, the person associating CC0 with a Work (the "Affirmer"), to the extent that he or she is an owner of Copyright and Related Rights in the Work, voluntarily elects to apply CC0 to the Work and publicly distribute the Work under its terms, with knowledge of his or her Copyright and Related Rights in the Work and the meaning and intended legal effect of CC0 on those rights.
+
+**1. Copyright and Related Rights.** A Work made available under CC0 may be protected by copyright and related or neighboring rights ("Copyright and Related Rights"). Copyright and Related Rights include, but are not limited to, the following:
+
+1.  the right to reproduce, adapt, distribute, perform, display, communicate, and translate a Work;
+2.  moral rights retained by the original author(s) and/or performer(s);
+3.  publicity and privacy rights pertaining to a person's image or likeness depicted in a Work;
+4.  rights protecting against unfair competition in regards to a Work, subject to the limitations in paragraph 4(a), below;
+5.  rights protecting the extraction, dissemination, use and reuse of data in a Work;
+6.  database rights (such as those arising under Directive 96/9/EC of the European Parliament and of the Council of 11 March 1996 on the legal protection of databases, and under any national implementation thereof, including any amended or successor version of such directive); and
+7.  other similar, equivalent or corresponding rights throughout the world based on applicable law or treaty, and any national implementations thereof.
+
+**2. Waiver.** To the greatest extent permitted by, but not in contravention of, applicable law, Affirmer hereby overtly, fully, permanently, irrevocably and unconditionally waives, abandons, and surrenders all of Affirmer's Copyright and Related Rights and associated claims and causes of action, whether now known or unknown (including existing as well as future claims and causes of action), in the Work (i) in all territories worldwide, (ii) for the maximum duration provided by applicable law or treaty (including future time extensions), (iii) in any current or future medium and for any number of copies, and (iv) for any purpose whatsoever, including without limitation commercial, advertising or promotional purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each member of the public at large and to the detriment of Affirmer's heirs and successors, fully intending that such Waiver shall not be subject to revocation, rescission, cancellation, termination, or any other legal or equitable action to disrupt the quiet enjoyment of the Work by the public as contemplated by Affirmer's express Statement of Purpose.
+
+**3. Public License Fallback.** Should any part of the Waiver for any reason be judged legally invalid or ineffective under applicable law, then the Waiver shall be preserved to the maximum extent permitted taking into account Affirmer's express Statement of Purpose. In addition, to the extent the Waiver is so judged Affirmer hereby grants to each affected person a royalty-free, non transferable, non sublicensable, non exclusive, irrevocable and unconditional license to exercise Affirmer's Copyright and Related Rights in the Work (i) in all territories worldwide, (ii) for the maximum duration provided by applicable law or treaty (including future time extensions), (iii) in any current or future medium and for any number of copies, and (iv) for any purpose whatsoever, including without limitation commercial, advertising or promotional purposes (the "License"). The License shall be deemed effective as of the date CC0 was applied by Affirmer to the Work. Should any part of the License for any reason be judged legally invalid or ineffective under applicable law, such partial invalidity or ineffectiveness shall not invalidate the remainder of the License, and in such case Affirmer hereby affirms that he or she will not (i) exercise any of his or her remaining Copyright and Related Rights in the Work or (ii) assert any associated claims and causes of action with respect to the Work, in either case contrary to Affirmer's express Statement of Purpose.
+
+**4. Limitations and Disclaimers.**
+
+1.  No trademark or patent rights held by Affirmer are waived, abandoned, surrendered, licensed or otherwise affected by this document.
+2.  Affirmer offers the Work as-is and makes no representations or warranties of any kind concerning the Work, express, implied, statutory or otherwise, including without limitation warranties of title, merchantability, fitness for a particular purpose, non infringement, or the absence of latent or other defects, accuracy, or the present or absence of errors, whether or not discoverable, all to the greatest extent permissible under applicable law.
+3.  Affirmer disclaims responsibility for clearing rights of other persons that may apply to the Work or any use thereof, including without limitation any person's Copyright and Related Rights in the Work. Further, Affirmer disclaims responsibility for obtaining any necessary consents, permissions or other rights required for any use of the Work.
+4.  Affirmer understands and acknowledges that Creative Commons is not a party to this document and has no duty or obligation with respect to this CC0 or use of the Work.

data/vendor/tests/README.md

@@ -0,0 +1,48 @@
+# Microformats test suite
+
+This group of tests was built to test microformats parsers. The individual tests are files containing fragments of HTML.  There is also a second a corresponding JSON file, which contains the expected output. 
+
+The tests are broken into sets within the tests directory of this project. They are first grouped by version. Some parsers only support a single version of microformats. They are then subdivided by the type of microformat i.e. h-card.
+
+
+## NPM
+
+The test have been added to npm (Node Package Manager) and the latest version can be add to a project using the following command:
+
+    npm i microformat-tests --save
+
+
+## Contributing new tests or updating tests
+
+This set of test belongs to the microformats community. If you find any errors in the current test or new patterns you believe should be in the test suite please feel free to send a pull request. 
+
+Notes on creating a new test
+
+A test is built in two parts a HTML file, which contains a fragment of HTML to parse, and JSON file with the expected output from a parser.
+
+1. Within the “test” directory of this project select the correct directory for the version of microformats the test belongs to. If you are creating a test for a new microformats feature or exploring an issue please add these tests to the “experimental” directory.
+
+2. Within the correct directory add your new test to subdirecory with either the name of it format i.e. `h-card` or the name of the new feature.
+
+3. Create the HTML file. Add the smallest and clearest example of the markup you can. There is no need to add head or body tags etc.
+
+4. Create a JSON file with the same name as your HTML file. The JSON should be the expected output from a parser.
+
+5. Once you have created the test please update the change-log.html Add a `h-entry` with details of the test . At the bottom of the page please add yourself as a contributor on the authors list
+
+
+## Date format for testing purposes
+
+Within the tests datetime formats are based on the [HTML5 profile](http://www.w3.org/TR/html5/infrastructure.html#dates-and-times) which is a subset of ISO8601 and allows a space to separate the date and time. To allow us to compare dates please provide a way for your parser to output dates/times with the follwing rules:
+
+* Date and time are separated by a spaces ie `2015-04-29 15:34`
+* Date and time keeps the authored level of specificity  ie `15:34` does NOT become `15:34:00`
+* Times and timezones always use the `:` separator ie `+01:30` NOT `+0130`
+* If used the zulu is always uppercase ie `2015-04-29 15:34Z`
+
+
+## License
+
+**Microformats test suite** is dedicated to the public domain using Creative Commons -- CC0 1.0 Universal.
+
+http://creativecommons.org/publicdomain/zero/1.0

data/vendor/tests/app.js

@@ -0,0 +1,84 @@
+'use strict';
+// This file create a small node server so 
+// you view the files over http://localhost:3009/
+// enter in commandline - $ node app
+// Glenn Jones
+
+
+var Hapi            = require('hapi'),
+    Blipp           = require('blipp'),
+    Pack            = require('./package');
+    
+    
+var routes = [{
+	method: 'GET',
+	path: '/{path*}',
+	handler: {
+		directory: {
+			path: '/tests',
+			listing: true,
+			index: false
+		}
+	}
+},{
+	method: 'GET',
+	path: '/css/{path*}',
+	handler: {
+		directory: {
+			path: './css',
+			listing: true,
+			index: true
+		}
+	}
+},{
+	method: 'GET',
+	path: '/javascript/{path*}',
+	handler: {
+		directory: {
+			path: './javascript',
+			listing: true,
+			index: true
+		}
+	}
+}];    
+    
+
+
+// Create a server with a host and port
+var server = new Hapi.Server();
+
+server.connection({ 
+    host: (process.env.PORT)? '0.0.0.0' : 'localhost', 
+    port: parseInt(process.env.PORT, 10) || 3008
+});
+
+
+// hapi server settings
+server.route(routes);
+
+
+var goodOptions = {
+    opsInterval: 1000,
+    reporters: [{
+        reporter: require('good-console'),
+        events: { log: '*', response: '*' }
+    }]
+};
+
+
+
+// Register plug-in and start
+server.register([{
+    register: require('good'), 
+    options: goodOptions
+  },{
+    register: require('blipp'), 
+  }], function (err) {
+      if (err) {
+          console.error(err);
+      }else {
+          server.start(function () {
+              console.info('Server started at ' + server.info.uri);
+          });
+      }
+  });