infoboxer 0.3.1 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 67bb7aed02bc7048e3508902a5b921be691b8bac
-  data.tar.gz: 0c1b8de5e72f824f29802d5a1e202e914ad3c241
+  metadata.gz: d1eca6a2e6e025b77b1eeed915629b24338380a8
+  data.tar.gz: a852e3d6cefa55b04b2a8ffe530478e8199a884f
 SHA512:
-  metadata.gz: ee0babd55c7fe433dc3b55aa6988abf17ddee81424f56bd83b31dcb076dcdcfd22c966b50a26b979e5a917e096847bdaf9390063807694133734671201cb5003
-  data.tar.gz: b70854401485cb7981110c3da6a5f7d4b4623545b3b1af4b05c4b541514efa9727818a09c25d89dbe55b31a79c2e772adedf06f2b1211386f17242ddb11cde1a
+  metadata.gz: 0cb20f539dcb4fecaf1f3c57a842d407481e37a2763ee35018bd436b058e704382493fd0a0a6a008101a70e9d9c283cc9fa3b7dbd8f48deef894e8d857ea7c42
+  data.tar.gz: b4f9ab8d39bc3c5fca6f7f247fd8c7f54bf76de8b5ed878a9fb935c6ccf3d99f7ed768c16cd1b1529ba56742a0bb1b6a09dafd0fc2900c12f2c0a39264d938fb

data/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Infoboxer's change log
 
+## 0.3.2 (2018-02-09)
+
+* Updated MediaWiktory to finally turn on gzip encoding of responses;
+* Utility methods to expose some internals (`MediaWiki#api`, `Infoboxer#url_for(:wikipedia)`,
+  `Page#namespaces`, `Template#named_variables` and so on);
+* Fix parsing of lowercase `file:` links in `<gallery>`.
+
 ## 0.3.1 (2017-12-04)
 
 * (Experimental) new representation of templates, much more readable;

data/infoboxer.gemspec

@@ -32,7 +32,7 @@ Gem::Specification.new do |s|
   s.executables << 'infoboxer'
 
   s.add_dependency 'htmlentities'
-  s.add_dependency 'mediawiktory', '= 0.1.2'
+  s.add_dependency 'mediawiktory', '= 0.1.3'
   s.add_dependency 'addressable'
   s.add_dependency 'terminal-table'
 end

data/lib/infoboxer.rb

@@ -47,7 +47,6 @@ module Infoboxer
   # @private
   WIKIA_API_URL = 'http://%s.wikia.com/api.php'.freeze
 
-  # @private
   WIKIMEDIA_PROJECTS = {
     wikipedia: 'wikipedia.org',
     wikivoyage: 'wikivoyage.org',
@@ -59,7 +58,6 @@ module Infoboxer
     wikisource: 'wikisource.org'
   }.freeze
 
-  # @private
   WIKIMEDIA_COMMONS = {
     commons: 'commons.wikimedia.org',
     species: 'species.wikimedia.org',
@@ -181,6 +179,20 @@ module Infoboxer
     end
   end
 
+  # Returns URL of API entry-point for a well-known Wiki-project (wikipedia, wikivoyage etc.)
+  # by project's name.
+  #
+  # @param symbol [Symbol] One of {WIKIMEDIA_PROJECTS} or {WIKIMEDIA_COMMONS} keys.
+  # @param lang [String, Symbol] Language of the project, if applicable.
+  # @return [String]
+  def url_for(symbol, lang = 'en')
+    if (domain = WIKIMEDIA_PROJECTS[symbol])
+      "https://#{lang}.#{domain}/w/api.php"
+    elsif (domain = WIKIMEDIA_COMMONS[symbol])
+      "https://#{domain}/w/api.php"
+    end
+  end
+
   # @!method wikipedia(lang = 'en', options = {})
   # Includeable version of {Infoboxer.wikipedia}
 

data/lib/infoboxer/definitions/en.wikipedia.org.rb

@@ -1,3 +1,4 @@
+# rubocop:disable Layout/EmptyLinesAroundArguments
 module Infoboxer
   MediaWiki::Traits.for('en.wikipedia.org') do
     templates do
@@ -370,3 +371,4 @@ module Infoboxer
     end
   end
 end
+# rubocop:enable Layout/EmptyLinesAroundArguments

data/lib/infoboxer/media_wiki.rb

@@ -41,6 +41,9 @@ module Infoboxer
     # @private
     attr_reader :api_base_url, :traits
 
+    # @return [MediaWiktory::Wikipedia::Client]
+    attr_reader :api
+
     # Creating new MediaWiki client. {Infoboxer.wiki} provides shortcut
     # for it, as well as shortcuts for some well-known wikis, like
     # {Infoboxer.wikipedia}.
@@ -51,7 +54,7 @@ module Infoboxer
     # @param user_agent [String] (also aliased as `:ua`) Custom User-Agent header.
     def initialize(api_base_url, ua: nil, user_agent: ua)
       @api_base_url = Addressable::URI.parse(api_base_url)
-      @client = MediaWiktory::Wikipedia::Api.new(api_base_url, user_agent: user_agent(user_agent))
+      @api = MediaWiktory::Wikipedia::Api.new(api_base_url, user_agent: user_agent(user_agent))
       @traits = Traits.get(@api_base_url.host, siteinfo)
     end
 
@@ -72,7 +75,7 @@ module Infoboxer
       return {} if titles.empty?
 
       titles.each_slice(50).map do |part|
-        request = prepare_request(@client.query.titles(*part), &processor)
+        request = prepare_request(@api.query.titles(*part), &processor)
         response = request.response
 
         # If additional props are required, there may be additional pages, even despite each_slice(50)
@@ -173,7 +176,7 @@ module Infoboxer
     def category(title, limit: 'max', &processor)
       title = normalize_category_title(title)
 
-      list(@client.query.generator(:categorymembers).title(title), limit, &processor)
+      list(@api.query.generator(:categorymembers).title(title), limit, &processor)
     end
 
     # Receive list of parsed MediaWiki pages for provided search query.
@@ -193,7 +196,7 @@ module Infoboxer
     # @return [Tree::Nodes<Page>] array of parsed pages.
     #
     def search(query, limit: 'max', &processor)
-      list(@client.query.generator(:search).search(query), limit, &processor)
+      list(@api.query.generator(:search).search(query), limit, &processor)
     end
 
     # Receive list of parsed MediaWiki pages with titles startin from prefix.
@@ -210,7 +213,7 @@ module Infoboxer
     # @return [Tree::Nodes<Page>] array of parsed pages.
     #
     def prefixsearch(prefix, limit: 'max', &processor)
-      list(@client.query.generator(:prefixsearch).search(prefix), limit, &processor)
+      list(@api.query.generator(:prefixsearch).search(prefix), limit, &processor)
     end
 
     # @return [String]
@@ -260,7 +263,7 @@ module Infoboxer
     end
 
     def siteinfo
-      @siteinfo ||= @client.query.meta(:siteinfo).prop(:namespaces, :namespacealiases, :interwikimap).response.to_h
+      @siteinfo ||= @api.query.meta(:siteinfo).prop(:namespaces, :namespacealiases, :interwikimap).response.to_h
     end
 
     def interwikis(prefix)

data/lib/infoboxer/media_wiki/page.rb

@@ -33,6 +33,15 @@ module Infoboxer
         client.traits
       end
 
+      # FIXME: take from siteinfo!
+      def namespace
+        Traits::STANDARD_NAMESPACES[source.fetch('ns') + 2] # Media = -2, Specia = -1, Main = 0
+      end
+
+      def category?
+        namespace == 'Category'
+      end
+
       private
 
       PARAMS_TO_INSPECT = %i[url title].freeze

data/lib/infoboxer/navigation.rb

@@ -94,5 +94,11 @@ module Infoboxer
     class Tree::Document
       include Navigation::Sections::Container
     end
+
+    module Helpers
+      def W(*arg, &block) # rubocop:disable Naming/MethodName
+        Lookup::Selector.new(*arg, &block)
+      end
+    end
   end
 end

data/lib/infoboxer/parser/inline.rb

@@ -16,7 +16,7 @@ module Infoboxer
 
           if @context.eof?
             break unless until_pattern
-            @context.fail!("#{until_pattern} not found, starting from #{start}")
+            @context.fail!("#{until_pattern.source} not found, starting from #{start}")
           end
 
           if @context.eol?
@@ -64,7 +64,7 @@ module Infoboxer
 
           if @context.eof?
             break unless until_pattern
-            @context.fail!("#{until_pattern} not found")
+            @context.fail!("#{until_pattern.source} not found")
           end
 
           if @context.eol?
@@ -178,7 +178,8 @@ module Infoboxer
           path = @context.scan_until(%r{</gallery>|\||$})
           attrs = @context.matched == '|' ? gallery_image_attrs : {}
           unless path.empty?
-            images << Tree::Image.new(path.sub(/^#{re.file_namespace}/, ''), attrs)
+            # FIXME: what if path NOT matches the namespace?
+            images << Tree::Image.new(path.sub(/^#{re.file_namespace.source}/i, ''), attrs)
           end
           break if @context.matched == '</gallery>'
         end

data/lib/infoboxer/tree/list.rb

@@ -13,9 +13,8 @@ module Infoboxer
       # Internal, used by {Parser}
       def merge!(other)
         ochildren = other.children.dup
-        if children.last && children.last.can_merge?(ochildren.first)
-          children.last.merge!(ochildren.shift)
-        end
+        children.last.merge!(ochildren.shift) \
+          if children.last && children.last.can_merge?(ochildren.first)
         push_children(*ochildren)
       end
 

data/lib/infoboxer/tree/template.rb

@@ -149,6 +149,10 @@ module Infoboxer
         variables.reject(&:named?)
       end
 
+      def named_variables
+        variables.select(&:named?)
+      end
+
       # Fetches template variable(s) by name(s) or patterns.
       #
       # Usage:

data/lib/infoboxer/version.rb

@@ -1,7 +1,7 @@
 module Infoboxer
   MAJOR = 0
   MINOR = 3
-  PATCH = 1
+  PATCH = 2
   PRE = nil
   VERSION = [MAJOR, MINOR, PATCH, PRE].compact.join('.')
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: infoboxer
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.3.2
 platform: ruby
 authors:
 - Victor Shepelev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-12-04 00:00:00.000000000 Z
+date: 2018-02-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities
@@ -30,14 +30,14 @@ dependencies:
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.1.2
+        version: 0.1.3
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.1.2
+        version: 0.1.3
 - !ruby/object:Gem::Dependency
   name: addressable
   requirement: !ruby/object:Gem::Requirement
@@ -171,7 +171,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.10
+rubygems_version: 2.6.14
 signing_key: 
 specification_version: 4
 summary: MediaWiki client and parser, targeting information extraction.