wgit 0.10.7 → 0.11.0

data/lib/wgit/document.rb

@@ -3,7 +3,6 @@ require_relative 'utils'
 require_relative 'assertable'
 require 'nokogiri'
 require 'json'
-require 'set'
 
 module Wgit
   # Class modeling/serialising a HTML web document, although other MIME types
@@ -18,9 +17,9 @@ module Wgit
     include Assertable
 
     # Regex for the allowed var names when defining an extractor.
-    REGEX_EXTRACTOR_NAME = /[a-z0-9_]+/.freeze
+    REGEX_EXTRACTOR_NAME = /[a-z0-9_]+/
 
-    # Set of text elements used to build Document#text.
+    # Set of text elements used to build the xpath for Document#text.
     @text_elements = Set.new(%i[
       a abbr address article aside b bdi bdo blockquote button caption cite
       code data dd del details dfn div dl dt em figcaption figure footer h1 h2
@@ -29,6 +28,13 @@ module Wgit
       summary sup td textarea th time u ul var wbr
     ])
 
+    # Instance vars to be ignored by Document#to_h and in turn Model.document.
+    @to_h_ignore_vars = [
+      '@parser',      # Always ignore the Nokogiri object.
+      '@meta_robots', # Used by #no_index?, ignore.
+      '@meta_wgit'    # Used by #no_index?, ignore.
+    ]
+
     # Set of Symbols representing the defined Document extractors.
     @extractors = Set.new
 
@@ -38,6 +44,12 @@ module Wgit
       # README.md for how to add to this Set dynamically.
       attr_reader :text_elements
 
+      # Array of instance vars to ignore when Document#to_h and in turn
+      # Model.document methods are called. Append your own defined extractor
+      # vars to omit them from the model (database object) when indexing.
+      # Each var should be a String starting with an '@' char e.g. "@data" etc.
+      attr_reader :to_h_ignore_vars
+
       # Set of Symbols representing the defined Document extractors. Is
       # read-only. Use Wgit::Document.define_extractor for a new extractor.
       attr_reader :extractors
@@ -76,9 +88,9 @@ module Wgit
     #   false if the Document content is an image etc.
     def initialize(url_or_obj, html = '', encode: true)
       if url_or_obj.is_a?(String)
-        init_from_strings(url_or_obj, html, encode: encode)
+        init_from_strings(url_or_obj, html, encode:)
       else
-        init_from_object(url_or_obj, encode: encode)
+        init_from_object(url_or_obj, encode:)
       end
     end
 
@@ -89,9 +101,9 @@ module Wgit
     #
     # @return [String] An xpath String to obtain a webpage's text elements.
     def self.text_elements_xpath
-      Wgit::Document.text_elements.each_with_index.reduce('') do |xpath, (el, i)|
+      @text_elements.each_with_index.reduce('') do |xpath, (el, i)|
         xpath += ' | ' unless i.zero?
-        xpath += format('//%s/text()', el)
+        xpath + format('//%s/text()', el)
       end
     end
 
@@ -192,13 +204,27 @@ module Wgit
       Document.send(:remove_method, "init_#{var}_from_object")
 
       @extractors.delete(var.to_sym)
+
       true
     rescue NameError
       false
     end
 
+    # Removes all default and defined extractors by calling
+    # `Document.remove_extractor` underneath. See its documentation.
+    def self.remove_extractors
+      @extractors.each { |var| remove_extractor(var) }
+    end
+
     ### Document Instance Methods ###
 
+    # Overrides String#inspect to shorten the printed output of a Document.
+    #
+    # @return [String] A short textual representation of this Document.
+    def inspect
+      "#<Wgit::Document url=\"#{@url}\" html_size=#{size}>"
+    end
+
     # Determines if both the url and html match. Use
     # doc.object_id == other.object_id for exact object comparison.
     #
@@ -227,10 +253,10 @@ module Wgit
     # Provide the `link:` parameter to get the correct base URL for that type
     # of link. For example, a link of `#top` would always return @url because
     # it applies to that page, not a different one. Query strings work in the
-    # same way. Use this parameter if manually concatting Url's e.g.
+    # same way. Use this parameter if manually joining Url's e.g.
     #
     #   relative_link = Wgit::Url.new('?q=hello')
-    #   absolute_link = doc.base_url(link: relative_link).concat(relative_link)
+    #   absolute_link = doc.base_url(link: relative_link).join(relative_link)
     #
     # This is similar to how Wgit::Document#internal_absolute_links works.
     #
@@ -250,7 +276,7 @@ module Wgit
 be relative"
       end
 
-      get_base = -> { @base.relative? ? @url.to_origin.concat(@base) : @base }
+      get_base = -> { @base.relative? ? @url.to_origin.join(@base) : @base }
 
       if link
         link = Wgit::Url.new(link)
@@ -274,11 +300,11 @@ be relative"
     #   returned Hash.
     # @return [Hash] Containing self's instance vars.
     def to_h(include_html: false, include_score: true)
-      ignore = include_html ? [] : ['@html']
+      ignore = Wgit::Document.to_h_ignore_vars.dup
+      ignore << '@html' unless include_html
       ignore << '@score' unless include_score
-      ignore << '@parser' # Always ignore the Nokogiri object.
 
-      Wgit::Utils.to_h(self, ignore: ignore)
+      Wgit::Utils.to_h(self, ignore:)
     end
 
     # Converts this Document's #to_h return value to a JSON String.
@@ -287,7 +313,7 @@ be relative"
     #   returned JSON String.
     # @return [String] This Document represented as a JSON String.
     def to_json(include_html: false)
-      h = to_h(include_html: include_html)
+      h = to_h(include_html:)
       JSON.generate(h)
     end
 
@@ -309,7 +335,7 @@ be relative"
         else
           next unless instance_variable_get(var).respond_to?(:length)
 
-          hash[var[1..-1].to_sym] = instance_variable_get(var).send(:length)
+          hash[var[1..].to_sym] = instance_variable_get(var).send(:length)
         end
       end
 
@@ -417,7 +443,6 @@ be relative"
                 end
               end
               .reject { |link| link.relative?(host: @url.to_origin) }
-              .map(&:omit_trailing_slash)
 
       Wgit::Utils.sanitize(links)
     end
@@ -493,10 +518,7 @@ be relative"
       query, case_sensitive: false, whole_sentence: true, sentence_limit: 80
     )
       orig_text = @text
-      @text = search(
-        query, case_sensitive: case_sensitive,
-               whole_sentence: whole_sentence, sentence_limit: sentence_limit
-      )
+      @text = search(query, case_sensitive:, whole_sentence:, sentence_limit:)
 
       orig_text
     end
@@ -519,11 +541,17 @@ be relative"
     # @return [String, Object] The value found in the html or the default value
     #   (singleton ? nil : []).
     def extract(xpath, singleton: true, text_content_only: true, &block)
-      send(
-        :extract_from_html, xpath,
-        singleton: singleton, text_content_only: text_content_only,
-        &block
-      )
+      send(:extract_from_html, xpath, singleton:, text_content_only:, &block)
+    end
+
+    # Works with the default extractors to extract and check the HTML meta tags
+    # instructing Wgit not to index this document (save it to a Database). If
+    # the default extractors are removed, this method will always return false.
+    #
+    # @return [Boolean] True if this document shouldn't be saved to a Database,
+    #   false otherwise.
+    def no_index?
+      [@meta_robots, @meta_wgit].include?('noindex')
     end
 
     protected
@@ -567,7 +595,7 @@ be relative"
         result = singleton ? result.content : result.map(&:content)
       end
 
-      Wgit::Utils.sanitize(result)
+      result = Wgit::Utils.sanitize(result)
       result = yield(result, self, :document) if block_given?
       result
     end
@@ -594,7 +622,7 @@ be relative"
       default = singleton ? nil : []
       result  = obj.fetch(key.to_s, default)
 
-      Wgit::Utils.sanitize(result)
+      result = Wgit::Utils.sanitize(result)
       result = yield(result, obj, :object) if block_given?
       result
     end
@@ -614,13 +642,13 @@ be relative"
       @parser = init_nokogiri
       @score  = 0.0
 
-      Wgit::Utils.sanitize(@html, encode: encode)
+      @html = Wgit::Utils.sanitize(@html, encode:)
 
       # Dynamically run the init_*_from_html methods.
       Document.private_instance_methods(false).each do |method|
         if method.to_s.start_with?('init_') &&
-           method.to_s.end_with?('_from_html')
-          send(method) unless method == __method__
+           method.to_s.end_with?('_from_html') && method != __method__
+          send(method)
         end
       end
     end
@@ -635,13 +663,13 @@ be relative"
       @parser = init_nokogiri
       @score  = obj.fetch('score', 0.0)
 
-      Wgit::Utils.sanitize(@html, encode: encode)
+      @html = Wgit::Utils.sanitize(@html, encode:)
 
       # Dynamically run the init_*_from_object methods.
       Document.private_instance_methods(false).each do |method|
         if method.to_s.start_with?('init_') &&
-           method.to_s.end_with?('_from_object')
-          send(method, obj) unless method == __method__
+           method.to_s.end_with?('_from_object') && method != __method__
+          send(method, obj)
         end
       end
     end
@@ -654,7 +682,7 @@ be relative"
     def init_var(var, value)
       # instance_var_name starts with @, var_name doesn't.
       var = var.to_s
-      var_name = (var.start_with?('@') ? var[1..-1] : var).to_sym
+      var_name = (var.start_with?('@') ? var[1..] : var).to_sym
       instance_var_name = "@#{var_name}".to_sym
 
       instance_variable_set(instance_var_name, value)
@@ -663,10 +691,10 @@ be relative"
       var_name
     end
 
-    alias content                html
-    alias statistics             stats
-    alias internal_urls          internal_links
-    alias internal_absolute_urls internal_absolute_links
-    alias external_urls          external_links
+    alias_method :content,                :html
+    alias_method :statistics,             :stats
+    alias_method :internal_urls,          :internal_links
+    alias_method :internal_absolute_urls, :internal_absolute_links
+    alias_method :external_urls,          :external_links
   end
 end

data/lib/wgit/document_extractors.rb

@@ -2,6 +2,20 @@
 
 ### Default Document Extractors ###
 
+# No index.
+Wgit::Document.define_extractor(
+  :meta_robots,
+  '//meta[@name="robots"]/@content',
+  singleton: true,
+  text_content_only: true
+)
+Wgit::Document.define_extractor(
+  :meta_wgit,
+  '//meta[@name="wgit"]/@content',
+  singleton: true,
+  text_content_only: true
+)
+
 # Base.
 Wgit::Document.define_extractor(
   :base,
@@ -45,7 +59,7 @@ Wgit::Document.define_extractor(
 ) do |keywords, _source, type|
   if keywords && (type == :document)
     keywords = keywords.split(',')
-    Wgit::Utils.sanitize(keywords)
+    keywords = Wgit::Utils.sanitize(keywords)
   end
   keywords
 end

data/lib/wgit/dsl.rb

@@ -101,7 +101,7 @@ the 'start' function".freeze
       raise DSL_ERROR__NO_START_URL if urls.empty?
 
       urls.map! { |url| Wgit::Url.parse(url) }
-      crawler.crawl_urls(*urls, follow_redirects: follow_redirects, &block)
+      crawler.crawl_urls(*urls, follow_redirects:, &block)
     end
 
     # Crawls an entire site using `Wgit::Crawler#crawl_site` underneath. If no
@@ -135,9 +135,7 @@ the 'start' function".freeze
       raise DSL_ERROR__NO_START_URL if urls.empty?
 
       xpath = follow || :default
-      opts  = {
-        follow: xpath, allow_paths: allow_paths, disallow_paths: disallow_paths
-      }
+      opts  = { follow: xpath, allow_paths:, disallow_paths: }
 
       urls.reduce([]) do |externals, url|
         externals + crawler.crawl_site(Wgit::Url.parse(url), **opts, &block)
@@ -189,7 +187,7 @@ the 'start' function".freeze
       db      = Wgit::Database.new(connection_string)
       indexer = Wgit::Indexer.new(db, crawler)
 
-      indexer.index_www(max_sites: max_sites, max_data: max_data)
+      indexer.index_www(max_sites:, max_data:)
     end
 
     # Indexes a single website using `Wgit::Indexer#index_site` underneath.
@@ -226,8 +224,7 @@ the 'start' function".freeze
       indexer    = Wgit::Indexer.new(db, crawler)
       xpath      = follow || :default
       crawl_opts = {
-        insert_externals: insert_externals, follow: xpath,
-        allow_paths: allow_paths, disallow_paths: disallow_paths
+        insert_externals:, follow: xpath, allow_paths:, disallow_paths:
       }
 
       urls.reduce(0) do |total, url|
@@ -261,9 +258,11 @@ the 'start' function".freeze
       indexer = Wgit::Indexer.new(db, crawler)
 
       urls.map! { |url| Wgit::Url.parse(url) }
-      indexer.index_urls(*urls, insert_externals: insert_externals, &block)
+      indexer.index_urls(*urls, insert_externals:, &block)
     end
 
+    ### DATABASE METHODS ###
+
     # Performs a search of the database's indexed documents and pretty prints
     # the results in a search engine-esque format. See `Wgit::Database#search!`
     # and `Wgit::Document#search!` for details of how the search works.
@@ -285,7 +284,7 @@ the 'start' function".freeze
     #   database containing only its matching `#text`.
     # @return [Array<Wgit::Document>] The search results with matching text.
     def search(
-      query, connection_string: @dsl_conn_str, stream: STDOUT,
+      query, connection_string: @dsl_conn_str, stream: $stdout,
       case_sensitive: false, whole_sentence: true,
       limit: 10, skip: 0, sentence_limit: 80, &block
     )
@@ -294,15 +293,12 @@ the 'start' function".freeze
 
       results = db.search!(
         query,
-        case_sensitive: case_sensitive,
-        whole_sentence: whole_sentence,
-        limit: limit,
-        skip: skip,
-        sentence_limit: sentence_limit,
-        &block
+        case_sensitive:, whole_sentence:,
+        limit:, skip:,
+        sentence_limit:, &block
       )
 
-      Wgit::Utils.printf_search_results(results, stream: stream)
+      Wgit::Utils.pprint_search_results(results, stream:)
 
       results
     end
@@ -317,9 +313,9 @@ the 'start' function".freeze
       db.clear_db
     end
 
-    alias crawl_url  crawl
-    alias crawl_r    crawl_site
-    alias index_r    index_site
-    alias start_urls start
+    alias_method :crawl_url,  :crawl
+    alias_method :crawl_r,    :crawl_site
+    alias_method :index_r,    :index_site
+    alias_method :start_urls, :start
   end
 end