Merge pull request #1372 from MasterEnoc/pandas

Update Pandas to 1.1.4

assets/javascripts/templates/pages/about_tmpl.coffee

@@ -573,7 +573,7 @@ credits = [
     'https://raw.githubusercontent.com/padrino/padrino-framework/master/padrino/LICENSE.txt'
   ], [
     'pandas',
-    '2008-2012, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team',
+    '2008-2020, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team',
     'BSD',
     'https://raw.githubusercontent.com/pydata/pandas/master/LICENSE'
   ], [

lib/docs/filters/pandas/clean_html.rb

@@ -2,17 +2,34 @@ module Docs
   class Pandas
     class CleanHtmlFilter < Filter
       def call
-        @doc = at_css('.body')
 
         if root_page?
-          css('a[href$=".zip"]', 'a[href$=".pdf"]', '.toctree-wrapper').remove
-          at_css('h1').content = 'pandas'
+          css('img').remove
         end
 
-        css('h2 > a.reference', 'h3 > a.reference').each do |node|
-          node.before(node.children).remove
+        css('#navbar-main').remove
+
+        css('form').remove
+
+        # add ':' to '.classifier' clases
+        css('.classifier').each do |node|
+          text = node.content
+          node.content = ':' + text
+          node.content = node.content.gsub(/::/, ' : ')
         end
 
+        # sidebar
+        css('ul.nav.bd-sidenav').remove
+
+        # title side symbol
+        css('.headerlink').remove
+
+        # next and previous section buttons
+        css('next-link').remove
+        css('prev-link').remove
+
+        css('footer').remove
+
         doc
       end
     end

lib/docs/filters/pandas/clean_html_old.rb

@@ -0,0 +1,20 @@
+module Docs
+  class Pandas
+    class CleanHtmlOldFilter < Filter
+      def call
+        @doc = at_css('.body')
+
+        if root_page?
+          css('a[href$=".zip"]', 'a[href$=".pdf"]', '.toctree-wrapper').remove
+          at_css('h1').content = 'pandas'
+        end
+
+        css('h2 > a.reference', 'h3 > a.reference').each do |node|
+          node.before(node.children).remove
+        end
+
+        doc
+      end
+    end
+  end
+end

lib/docs/filters/pandas/entries.rb

@@ -1,29 +1,29 @@
 module Docs
   class Pandas
     class EntriesFilter < Docs::EntriesFilter
+
       def get_name
-        if subpath.start_with?('generated') || (subpath.include?('reference') && !subpath.include?('reference/index'))
-          name_node = at_css('dt')
-          name_node = at_css('h1') if name_node.nil?
-          name = name_node.content.strip
-          name.sub! %r{\(.*}, '()'
-          name.remove! %r{\s=.*}
-          name.remove! %r{\A(class(method)?) (pandas\.)?}
-        else
-          name = at_css('h1').content.strip
-          name.prepend "#{css('.toctree-l1 > a:not([href^="http"])').to_a.index(at_css('.toctree-l1.current > a')) + 1}. "
-        end
-        name.remove! "\u{00B6}"
-        name
+        at_css('h1').content
       end
 
       def get_type
-        if subpath.start_with?('generated') || (subpath.include?('reference') && !subpath.include?('reference/index'))
-          css('.toctree-l2.current > a').last.content.remove(/\s\(.+?\)/)
-        else
-          'Manual'
-        end
+        return 'Manual' if slug.include?('user_guide')
+        return 'General utility functions' if slug.match?('option|assert|errors|types|show_versions')
+        return 'Extensions' if slug.match?(/extensions|check_array/)
+        return 'Style' if slug.match?(/style/)
+        return 'Input/output' if slug.match?(/read|io|HDFStore/)
+        return 'Series' if slug.match?(/Series/)
+        return 'GroupBy' if slug.match?(/groupby|Grouper/)
+        return 'DataFrame' if slug.match?(/DataFrame|frame/)
+        return 'Window' if slug.match?(/window|indexers/)
+        return 'Index Objects' if slug.match?(/Index|indexing/)
+        return 'Data offsets' if slug.match?(/offsets?/)
+        return 'Resampling' if slug.match?(/resample/)
+        return 'Plotting' if slug.match?(/plotting/)
+        return 'Pandas arrays' if slug.match?(/arrays?|Timestamp|Datetime|Timedelta|Period|Interval|Categorical|Dtype/)
+        'General functions'
       end
+
     end
   end
 end

lib/docs/filters/pandas/entries_old.rb

@@ -0,0 +1,29 @@
+module Docs
+  class Pandas
+    class EntriesOldFilter < Docs::EntriesFilter
+      def get_name
+        if subpath.start_with?('generated') || (subpath.include?('reference') && !subpath.include?('reference/index'))
+          name_node = at_css('dt')
+          name_node = at_css('h1') if name_node.nil?
+          name = name_node.content.strip
+          name.sub! %r{\(.*}, '()'
+          name.remove! %r{\s=.*}
+          name.remove! %r{\A(class(method)?) (pandas\.)?}
+        else
+          name = at_css('h1').content.strip
+          name.prepend "#{css('.toctree-l1 > a:not([href^="http"])').to_a.index(at_css('.toctree-l1.current > a')) + 1}. "
+        end
+        name.remove! "\u{00B6}"
+        name
+      end
+
+      def get_type
+        if subpath.start_with?('generated') || (subpath.include?('reference') && !subpath.include?('reference/index'))
+          css('.toctree-l2.current > a').last.content.remove(/\s\(.+?\)/)
+        else
+          'Manual'
+        end
+      end
+    end
+  end
+end

lib/docs/scrapers/pandas.rb

@@ -4,61 +4,117 @@ module Docs
     self.type = 'sphinx'
     self.root_path = 'index.html'
     self.links = {
-      home: 'http://pandas.pydata.org/',
+      home: 'https://pandas.pydata.org/',
       code: 'https://github.com/pydata/pandas'
     }
 
-    html_filters.push 'pandas/entries', 'pandas/clean_html', 'sphinx/clean_html'
-
-    # Cannot take only the body, as the sidebar gives info about the type.
-    options[:container] = '.document'
+    html_filters.push 'pandas/clean_html', 'pandas/entries'
 
     options[:skip] = %w(internals.html release.html contributing.html whatsnew.html)
     options[:skip_patterns] = [/whatsnew\//]
 
     options[:attribution] = <<-HTML
-      &copy; 2008&ndash;2012, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team<br>
+      &copy; 2008&ndash;2020, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team<br>
       Licensed under the 3-clause BSD License.
     HTML
 
+    version '1' do
+      self.release = '1.1.4'
+      self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+
+      html_filters.push 'pandas/clean_html', 'pandas/entries'
+
+      options[:skip_patterns] = [
+        /development/,
+        /getting_started/,
+        /whatsnew/
+      ]
+
+      options[:skip] = [
+        'panel.html',
+        'pandas.pdf',
+        'pandas.zip',
+        'ecosystem.html'
+      ]
+
+    end
+
     version '0.25' do
       self.release = '0.25.0'
       self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+
+      html_filters.push 'pandas/entries_old', 'pandas/clean_html_old', 'sphinx/clean_html'
+
+      options[:container] = '.document'
+
     end
 
     version '0.24' do
       self.release = '0.24.2'
       self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+
+      html_filters.push 'pandas/entries_old', 'pandas/clean_html_old', 'sphinx/clean_html'
+      options[:container] = '.document'
+
     end
 
     version '0.23' do
       self.release = '0.23.4'
       self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+
+      html_filters.push 'pandas/entries_old', 'pandas/clean_html_old', 'sphinx/clean_html'
+      options[:container] = '.document'
+
     end
 
     version '0.22' do
       self.release = '0.22.0'
       self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+
+      html_filters.push 'pandas/entries_old', 'pandas/clean_html_old', 'sphinx/clean_html'
+
+      options[:container] = '.document'
+
     end
 
     version '0.21' do
       self.release = '0.21.1'
       self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+
+      html_filters.push 'pandas/entries_old', 'pandas/clean_html_old', 'sphinx/clean_html'
+
+      options[:container] = '.document'
+
     end
 
     version '0.20' do
       self.release = '0.20.3'
       self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+
+      html_filters.push 'pandas/entries_old', 'pandas/clean_html_old', 'sphinx/clean_html'
+
+      options[:container] = '.document'
+
     end
 
     version '0.19' do
       self.release = '0.19.2'
       self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+
+      html_filters.push 'pandas/entries_old', 'pandas/clean_html_old', 'sphinx/clean_html'
+
+      options[:container] = '.document'
+
     end
 
     version '0.18' do
       self.release = '0.18.1'
       self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+
+      html_filters.push 'pandas/entries_old', 'pandas/clean_html_old', 'sphinx/clean_html'
+
+      options[:container] = '.document'
+
     end
 
     def get_latest_version(opts)

public/icons/docs/pandas/SOURCE

@@ -1 +1 @@
-http://pandas.pydata.org/_static/pandas_logo.png
+https://commons.wikimedia.org/wiki/File:Pandas_mark.svg