infoboxer 0.2.2 → 0.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 69ee012f6cd8bb3e923289a4a921e81798ffd2aa
-  data.tar.gz: 42686bced509c310051ba7bc895c68d26a96bd2f
+  metadata.gz: fcf940ddedd92a04eb2e555bc16c5ef765a3e8d3
+  data.tar.gz: c8e8c4976ea2e8e023c79c26bd221ff5f22b5a32
 SHA512:
-  metadata.gz: cc237b46fe0f59a2ba04d3b53da4a7361cd974e50e1d18f688a077093da664a7d205dd363ddc2622a9af4c1a6f1168315d90fb6867e65c0a61bd60e5e453e81a
-  data.tar.gz: d844446421cffd8e7f6a8fe885f0f1918c772f9e2e7c1d289a1e90b544fde9b3c2b41c8956df7338aab9ad2ae5ca7f5ec9d67fb2d3f16da34367ed5b96a5aa22
+  metadata.gz: d2e54fe4fe9d1a7714f6aa5b0d47b2957a0b0a00b1d65ca9ea4f925efa2dafb364d354235f3c19990f812293ee6bfe6e86602b019fb71eff4b6a67b96d6bf82a
+  data.tar.gz: d3ea47fcedb10473abc5083b750b4c3804532f8f6d0278a51a2d270913a899f3897c35fee9099a5aa08bf1dea8dfaa7292fc5b06cc350671cbde24625936d956

data/CHANGELOG.md

@@ -1,5 +1,21 @@
 # Infoboxer's change log
 
+## 0.2.3 (2016-03-02)
+
+New and enchanced features:
+* more useful templates (quick-n-dirty sometimes, but prettier output for
+  typical cases);
+* Caching of wikiobjects, so for several calls to `Infoboxer.wp` it would
+  be only one API call for wiki metainformation;
+* `MediaWiki#get` now preserves order of pages (page list would be in
+  the same order as requested titles);
+* `MediaWiki#get_h` to receive hash of `title => page object` (useful
+  to know which titles have been no pages for and better control on
+  redirects).
+
+Fixes:
+* `Image` node equality fixed.
+
 ## 0.2.2 (2016-01-03)
 
 Fixes:
@@ -22,7 +38,7 @@ Fixes:
   50 in previous versions);
 * `bin/infoboxer` console added for quick experimenting;
 * `Template#to_h` added for quick information extraction;
-* many small bugfixes and echancements. 
+* many small bugfixes and enchancements. 
 
 ## 0.1.2.1 (2015-12-04)
 

data/Parsing.md

@@ -19,7 +19,7 @@ Here's what I've came with:
   * Long formatting like templates can span several lines, so we continue
     scan through next lines, till template end (it means we are still in
     same paragraph!), it's "normal inline scan", or just "inline scan"
-  * Some __inline__ formatting (like <ref>'s) and special formatting,
+  * Some __inline__ formatting (like `<ref>`'s) and special formatting,
     like table cells, can have other paragraphs inside! (But it's still
     "inline" formatting, because when <ref> is ended, the same paragraph
     is continued -- while showing it in Wikipedia, ref will leave a small

data/README.md

@@ -147,10 +147,6 @@ they may still work for you.
 
 * [Wiki](https://github.com/molybdenum-99/infoboxer/wiki)
 * [API Docs](http://www.rubydoc.info/gems/infoboxer)
-  * **NB**: ↑ this is "current version" link, but RubyDoc.info unfortunately
-    sometimes fails to update it to really _current_; in case you feel
-    something seriously underdocumented, please-please look at
-    [0.2.0 docs](http://www.rubydoc.info/gems/infoboxer/0.2.0).
 * [Contributing](https://github.com/molybdenum-99/infoboxer/wiki/Contributing)
 * [Roadmap](https://github.com/molybdenum-99/infoboxer/wiki/Roadmap)
 

data/bin/infoboxer

@@ -9,7 +9,7 @@ require 'optparse'
 wiki_url = nil
 
 OptionParser.new do |opts|
-  opts.banner = "Usage: bin/infoboxer [-w wiki_api_url]"
+  opts.banner = "Usage: infoboxer [-w wiki_api_url]"
 
   opts.on("-w", "--wiki WIKI_API_URL",
               "Make wiki by WIKI_API_URL a default wiki, and use it with just get('Pagename')") do |w|

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

@@ -335,6 +335,26 @@ module Infoboxer
         end
       end
 
+      # Prononciation/lang templates - are frequent in article abstracts
+      # Doint it dirty, but useful, for now:
+      template 'Lang', match: /^lang-(\w{2,3})$/i do
+        def children
+          fetch('1')
+        end
+      end
+
+      template 'IPAc', match: /^IPAc[12]?-(\w{2,3})$/i do
+        def text
+          unnamed_variables.text
+        end
+      end
+
+      template 'IPA', match: /^IPA-(\w{2,3})$/i do
+        def text
+          fetch('1').text
+        end
+      end
+
       # TODO: extremely popular:
       # Str left - https://en.wikipedia.org/wiki/Category:String_manipulation_templates
       # Rnd - https://en.wikipedia.org/wiki/Category:Mathematical_function_templates

data/lib/infoboxer/media_wiki/mediawiktory_patch.rb

@@ -0,0 +1,25 @@
+require 'mediawiktory'
+
+# FIXME: looks like pretty "core" functionality and should moved to mediawiktory itself
+
+class MediaWiktory::Page
+  attr_writer :queried_title
+
+  def queried_title
+    @queried_title || title
+  end
+end
+
+class MediaWiktory::Query::Response
+  alias_method :old_initialize, :initialize
+  def initialize(*arg)
+    old_initialize(*arg)
+    
+    if raw.query.redirects
+      raw.query.redirects.each do |redirect|
+        pg = @pages.detect{|p| p.title == redirect.to} or next
+        pg.queried_title = redirect.from
+      end
+    end
+  end
+end

data/lib/infoboxer/media_wiki.rb

@@ -4,6 +4,7 @@
 require 'mediawiktory'
 require 'addressable/uri'
 
+require_relative 'media_wiki/mediawiktory_patch'
 require_relative 'media_wiki/traits'
 require_relative 'media_wiki/page'
 
@@ -65,7 +66,8 @@ module Infoboxer
           prop(revisions: {prop: :content}, info: {prop: :url}).
           redirects(true). # FIXME: should be done transparently by MediaWiktory?
           perform.pages
-      }.inject(:concat) # somehow flatten(1) fails!
+      }.inject(:concat). # somehow flatten(1) fails!
+      sort_by{|page| titles.index(page.queried_title) || 1_000}
     end
 
     # Receive list of parsed MediaWiki pages for list of titles provided.
@@ -104,6 +106,27 @@ module Infoboxer
       titles.count == 1 ? pages.first : Tree::Nodes[*pages]
     end
 
+    # Same as {#get}, but returns hash of {requested title => page}.
+    #
+    # Useful quirks:
+    # * when requested page not existing, key will be still present in
+    #   resulting hash (value will be `nil`);
+    # * when requested page redirects to another, key will still be the
+    #   requested title. For ex., `get_h('Einstein')` will return hash
+    #   with key 'Einstein' and page titled 'Albert Einstein'.
+    #
+    # This allows you to be in full control of what pages of large list
+    # you've received.
+    #
+    # @return [Hash<String, Page>]
+    #
+    def get_h(*titles)
+      pages = [*get(*titles)]
+      titles.map{|t|
+        [t, pages.detect{|p| p.source.queried_title == t}]
+      }.to_h
+    end
+
     # Receive list of parsed MediaWiki pages from specified category.
     #
     # **NB**: currently, this API **always** fetches all pages from

data/lib/infoboxer/navigation/sections.rb

@@ -151,9 +151,10 @@ module Infoboxer
       # See {Sections parent module} documentation for details.
       class Section < Tree::Compound
         def initialize(heading, children = Tree::Nodes[])
-          # no super: we don't wont to rewriter children's parent
+          # no super: we don't wont to rewrite children's parent
           @children = Tree::Nodes[*children]
           @heading = heading
+          @params = {level: heading.level, heading: heading.text.strip}
         end
 
         # Section's heading.
@@ -173,6 +174,12 @@ module Infoboxer
         end
 
         include Container
+
+        private
+
+        #def show_params
+          #super(level: heading.level, heading: heading.text)
+        #end
       end
     end
   end

data/lib/infoboxer/tree/image.rb

@@ -48,6 +48,12 @@ module Infoboxer
             ''
           end
       end
+
+      private
+
+      def _eq(other)
+        path == other.path
+      end
     end
 
     # Represents image caption.

data/lib/infoboxer/tree/node.rb

@@ -134,7 +134,8 @@ module Infoboxer
       MAX_CHARS = 30
 
       def shorten_text
-        text_.length > MAX_CHARS ? text_[0..MAX_CHARS] + '...' : text_
+        txt = text_.sub(/^([^\n]+)\n.+$/m, '\1...')
+        txt.length > MAX_CHARS ? txt[0..MAX_CHARS] + '...' : txt
       end
 
       def clean_class
@@ -158,7 +159,7 @@ module Infoboxer
       end
 
       def _eq(other)
-        fail(NotImplementedError, "#_eq should be defined in subclasses")
+        fail(NotImplementedError, "#_eq should be defined in subclasses (called for #{self.class})")
       end
 
       def decode(str)

data/lib/infoboxer/version.rb

@@ -2,6 +2,6 @@
 module Infoboxer
   MAJOR = 0
   MINOR = 2
-  PATCH = 2
+  PATCH = 3
   VERSION = [MAJOR, MINOR, PATCH].join('.')
 end

data/lib/infoboxer.rb

@@ -69,11 +69,13 @@ module Infoboxer
     species: 'species.wikimedia.org',
   }
 
+  WIKIS = {}
+
   public
   
   # Includeable version of {Infoboxer.wiki}
   def wiki(api_url, options = {})
-    MediaWiki.new(api_url, options || {})
+    WIKIS[api_url] ||= MediaWiki.new(api_url, options || {})
   end
 
   class << self

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: infoboxer
 version: !ruby/object:Gem::Version
-  version: 0.2.2
+  version: 0.2.3
 platform: ruby
 authors:
 - Victor Shepelev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-01-02 00:00:00.000000000 Z
+date: 2016-03-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities
@@ -121,6 +121,7 @@ files:
 - lib/infoboxer/core_ext.rb
 - lib/infoboxer/definitions/en.wikipedia.org.rb
 - lib/infoboxer/media_wiki.rb
+- lib/infoboxer/media_wiki/mediawiktory_patch.rb
 - lib/infoboxer/media_wiki/page.rb
 - lib/infoboxer/media_wiki/traits.rb
 - lib/infoboxer/navigation.rb