wiki-api 0.0.2 → 0.1.2

data/lib/wiki/api/page_block.rb

@@ -1,25 +1,28 @@
+# frozen_string_literal: true
+
 module Wiki
   module Api
-
+    # Collection of elements for segmented per headline
     class PageBlock
+      attr_accessor :elements, :parent
 
-      attr_accessor :elements
-
-      def initialize options={}
+      def initialize(options = {})
+        self.parent = options[:parent] if options.include?(:parent)
         self.elements = []
       end
 
-      def << value
-        self.elements << value
+      def <<(value)
+        # value.first.previous.name
+        elements << value
       end
 
       def to_texts
-        # TODO: perhaps we should wrap the elements with objects??
         texts = []
-        self.elements.flatten.each do |element|
-          text = Wiki::Api::Util.element_to_text element if element.is_a? Nokogiri::XML::Element
+        elements.flatten.each do |element|
+          text = Wiki::Api::Util.element_to_text(element) if element.is_a?(Nokogiri::XML::Element)
           next if text.nil?
           next if text.empty?
+
           texts << text
         end
         texts
@@ -27,27 +30,25 @@ module Wiki
 
       def list_items
         # TODO: perhaps we should wrap the elements with objects, and request a li per element??
-        self.search("li").map do |list_item|
-          PageListItem.new element: list_item
+        search('li').map do |list_item|
+          PageListItem.new(parent: self, element: list_item)
         end
       end
 
       def links
         # TODO: perhaps we should wrap the elements with objects, and request a li per element??
-        self.search("a").map do |a|
-          PageLink.new element: a
+        search('a').map do |a|
+          PageLink.new(parent: self, element: a)
         end
       end
 
       protected
 
       def search *paths
-        self.elements.flatten.flat_map do |element|
+        elements.flatten.flat_map do |element|
           element.search(*paths)
-        end.reject{|t| t.nil?}
+        end.reject(&:nil?)
       end
-
     end
-
   end
-end
+end

data/lib/wiki/api/page_headline.rb

@@ -1,22 +1,118 @@
+# frozen_string_literal: true
+
 module Wiki
   module Api
-
+    # Headline for a page (class="mw-healine")
     class PageHeadline
+      require 'json'
+
+      LEVEL = %w[text h1 h2 h3 h4 h5 h6].freeze
+
+      attr_accessor :name, :block, :parent, :headlines, :level
+
+      def initialize(options = {})
+        self.name = options[:name] if options.include?(:name)
+        self.parent = options[:parent] if options.include?(:parent)
+        self.level = options[:level] if options.include?(:level)
+        options[:headlines] ||= []
+        self.headlines ||= {}
+
+        # store elements in a block
+        self.block = PageBlock.new(parent: self)
+        if options[:headlines].include?(name)
+          options[:headlines][name].each do |element|
+            block << element
+          end
+        end
 
-      attr_accessor :name, :block
+        # collect nested headlines
+        headlines = options[:headlines]
+        # remove self from list
+        headlines.delete(name)
+        nested_headlines = self.nested_headlines(headlines, name, level)
 
-      def initialize options={}
-        self.name = options[:name] if options.include? :name
-        self.block = PageBlock.new
+        # iterate nested headlines, and call recursive
+        nested_headlines.each do |headline_name, value|
+          level = LEVEL.index(value.first.first.previous.name)
+          self.headlines[headline_name] =
+            PageHeadline.new(parent: self, name: headline_name, headlines:, level:)
+        end
       end
 
       def elements
-        self.block.elements
+        block.elements
       end
 
+      def type
+        block.elements.first.first.previous.name
+      end
 
+      # get headline by name
+      def headline(name)
+        name = name.downcase.gsub(' ', '_')
+        self.headlines.select do |k, _v|
+          k.downcase.start_with?(name)
+        end.values
+      end
 
-    end
+      def headline_in_depth(name, depth = 1)
+        name = name.downcase.gsub(' ', '_')
+        ret = []
+
+        self.headlines.each do |k, v|
+          ret << v if k.downcase.start_with?(name)
+          next if v.headlines.empty?
+
+          if depth.positive?
+            q = v.headline_in_depth(name, (depth - 1))
+            ret.concat(q)
+          end
+        end
+        ret
+      end
+
+      # headline exists for current headline
+      def has_headline?(name)
+        name = name.downcase.gsub(' ', '_')
+        self.headlines.each_key do |k|
+          return true if k.downcase.start_with?(name)
+        end
+        false
+      end
 
+      def to_hash
+        ret = { name:, headlines: [], type: }
+        self.headlines.each_value do |headline|
+          ret[:headlines] << headline.to_hash
+        end
+        ret
+      end
+
+      def to_pretty_json
+        JSON.pretty_generate(to_hash)
+      end
+
+      protected
+
+      # filter nested headlines (elements) from a parent headline (by name)
+      def nested_headlines(headlines, _name, original_level)
+        ret = {}
+        init_level = nil
+        # iterate headlines, skip already done onces
+        # headlines.drop(headline_index + 1).each do |headline|
+        headlines.to_a.each do |name, value|
+          level = LEVEL.index(value.first.first.previous.name)
+          init_level ||= level
+          # lower level indicate nest end
+          break if level <= original_level
+          break if level < init_level
+          # higher level indicates nested items, these will be processed recursive
+          next if init_level != level
+
+          ret[name] = value
+        end
+        ret
+      end
+    end
   end
-end
+end

data/lib/wiki/api/page_link.rb

@@ -1,33 +1,37 @@
+# frozen_string_literal: true
+
 module Wiki
   module Api
-
+    # Link on a wiki page (a href=xxx)
     class PageLink
+      attr_accessor :element, :parent
 
-      attr_accessor :element
-
-      def initialize options={}
-        self.element = options[:element] if options.include? :element
+      def initialize(options = {})
+        self.element = options[:element] if options.include?(:element)
+        self.parent = options[:parent] if options.include?(:parent)
       end
 
       def to_text
-        Wiki::Api::Util.element_to_text self.element
+        Wiki::Api::Util.element_to_text(element)
       end
 
       def uri
-        host = Wiki::Api::Connect.config[:uri]
-        element_value = self.element.attributes["href"].value
-        URI.parse "#{host}#{element_value}"
+        # lookup the root parent, and get connector info
+        host = Wiki::Api::Util.parent_root(self).connect.uri
+        href_value = element.attributes['href'].value
+        URI.parse("#{host}#{href_value}")
       end
 
       def title
-        self.element.attributes["title"].value
+        # skip links with no title
+        return '' if element.attributes['title'].nil?
+
+        element.attributes['title'].value
       end
 
       def html
-        "<a href=\"#{self.uri}\" alt=\"#{self.title}\">#{self.title}</a>"
+        "<a href=\"#{uri}\" alt=\"#{title}\">#{title}</a>"
       end
-
     end
-
   end
-end
+end

data/lib/wiki/api/page_list_item.rb

@@ -1,32 +1,31 @@
+# frozen_string_literal: true
+
 module Wiki
   module Api
-
+    # List Items on a Page (li=xxx)
     class PageListItem
+      attr_accessor :element, :parent
 
-      attr_accessor :element
-
-      def initialize options={}
-        self.element = options[:element] if options.include? :element
+      def initialize(options = {})
+        self.parent = options[:parent] if options.include?(:parent)
+        self.element = options[:element] if options.include?(:element)
       end
 
       def to_text
-        Wiki::Api::Util.element_to_text self.element
+        Wiki::Api::Util.element_to_text(element)
       end
 
       def links
-        self.search("a").map do |a|
-          PageLink.new element: a
+        search('a').map do |a|
+          PageLink.new(parent: self, element: a)
         end
       end
 
       protected
 
       def search *paths
-        self.element.search(*paths)
+        element.search(*paths)
       end
-
-
     end
-
   end
-end
+end

data/lib/wiki/api/util.rb

@@ -1,35 +1,44 @@
+# frozen_string_literal: true
+
 module Wiki
   module Api
-
     class Util
-
       class << self
+        def element_to_text(element)
+          raise('not an element') unless element.is_a?(Nokogiri::XML::Element)
 
-        def element_to_text element
-          raise "not an element" unless element.is_a? Nokogiri::XML::Element
-          self.clean_text element.text
+          clean_text(element.text)
         end
 
-        def element_filter_lists element
-          raise "not an element" unless element.is_a? Nokogiri::XML::Element
+        def element_filter_lists(element)
+          raise('not an element') unless element.is_a?(Nokogiri::XML::Element)
+
           result = {}
-          element.search("li").each_with_index do |li, i|
+          element.search('li').each_with_index do |li, i|
             li.children.each do |child|
               result[i] ||= []
-              result[i] << self.clean_text(child.text)
+              result[i] << clean_text(child.text)
             end
           end
-          result.map{|k,v| v.join("")}
+          result.map { |_k, v| v.join('') }
         end
 
+        def parent_root(current_object)
+          current = current_object
+          loop do
+            break if current.parent.nil?
 
-        protected
-        def clean_text text
-          text.gsub(/\n/, " ").squeeze(" ").gsub(/\s(\W)/, '\1').gsub(/(\W)\s/, '\1 ').strip
+            current = current.parent
+          end
+          current
         end
 
-      end
+        protected
 
+        def clean_text(text)
+          text.gsub(/\n/, ' ').squeeze(' ').gsub(/\s(\W)/, '\1').gsub(/(\W)\s/, '\1 ').strip
+        end
+      end
     end
   end
-end
+end

data/lib/wiki/api/version.rb

@@ -1,5 +1,7 @@
+# frozen_string_literal: true
+
 module Wiki
   module Api
-    VERSION = "0.0.2"
+    VERSION = '0.1.2'
   end
 end

data/lib/wiki/api.rb

@@ -1,12 +1,13 @@
-require File.expand_path(File.dirname(__FILE__) + "/api/version")
-require File.expand_path(File.dirname(__FILE__) + "/api/connect")
-require File.expand_path(File.dirname(__FILE__) + "/api/page")
-require File.expand_path(File.dirname(__FILE__) + "/api/page_headline")
-require File.expand_path(File.dirname(__FILE__) + "/api/page_block")
-require File.expand_path(File.dirname(__FILE__) + "/api/page_list_item")
-require File.expand_path(File.dirname(__FILE__) + "/api/page_link")
-require File.expand_path(File.dirname(__FILE__) + "/api/util")
+# frozen_string_literal: true
 
+require File.expand_path("#{File.dirname(__FILE__)}/api/version")
+require File.expand_path("#{File.dirname(__FILE__)}/api/connect")
+require File.expand_path("#{File.dirname(__FILE__)}/api/page")
+require File.expand_path("#{File.dirname(__FILE__)}/api/page_headline")
+require File.expand_path("#{File.dirname(__FILE__)}/api/page_block")
+require File.expand_path("#{File.dirname(__FILE__)}/api/page_list_item")
+require File.expand_path("#{File.dirname(__FILE__)}/api/page_link")
+require File.expand_path("#{File.dirname(__FILE__)}/api/util")
 
 module Wiki
   module Api

data/test/test_helper.rb

@@ -1,8 +1,5 @@
+# frozen_string_literal: true
 
-class ActiveSupport::TestCase
-  setup :global_setup
-
-  def global_setup
-  end
-end
-
+require 'rubygems'
+require 'test/unit'
+require File.expand_path("#{File.dirname(__FILE__)}/../lib/wiki/api")