Add Polars documentation

Add a scraper for the Polars Python API reference
(https://docs.pola.rs/api/python/stable/reference/), pinned to the
stable 1.41.0 release.

The site uses the pydata-sphinx-theme, so the scraper reuses the shared
sphinx/clean_html filter alongside Polars-specific filters:

- clean_html removes the theme chrome (sidebars, in-page TOC, prev/next
  navigation, footer) and tags code blocks for Python highlighting.
- entries names each page from its heading and groups entries into types
  (DataFrame, LazyFrame, Series, Expressions, Functions, Data Types,
  Input/output, etc.). Top-level members are stored flat under api/ and
  are classified by their member name.

Latest-version detection uses the most recent GitHub release and strips
the py- prefix, since the repo also tags Rust (rs-) releases.

Author: mcagriardic

lib/docs/filters/polars/clean_html.rb

@@ -0,0 +1,32 @@
+module Docs
+  class Polars
+    class CleanHtmlFilter < Filter
+      def call
+        # Remove pydata-sphinx-theme chrome that survives the container extraction
+        # or sits inside the article (sidebars, in-page TOC, prev/next nav, footer).
+        css(
+          '.bd-sidebar-primary',
+          '.bd-sidebar-secondary',
+          '.bd-toc',
+          '.bd-header-article',
+          '.prev-next-area',
+          '.prev-next-footer',
+          '.bd-footer',
+          '.headerlink',
+          'form'
+        ).remove
+
+        # Drop banner/logo imagery on the landing page.
+        css('img').remove if root_page?
+
+        # Make sure every code block is tagged so Prism highlights it as Python.
+        css('.highlight pre').each do |node|
+          node.content = node.content
+          node['data-language'] = 'python'
+        end
+
+        doc
+      end
+    end
+  end
+end

lib/docs/filters/polars/entries.rb

@@ -0,0 +1,64 @@
+module Docs
+  class Polars
+    class EntriesFilter < Docs::EntriesFilter
+      # Map the leading path segment of a reference page to a human readable
+      # type. The Polars reference is laid out as <section>/... under the base
+      # url (e.g. dataframe/api/polars.DataFrame.count.html). Top-level members
+      # (plain functions, datatypes, IO, config, ...) instead live flat under
+      # api/ and are classified by name in #classify_api.
+      SECTION_TYPES = {
+        'dataframe'      => 'DataFrame',
+        'lazyframe'      => 'LazyFrame',
+        'series'         => 'Series',
+        'expressions'    => 'Expressions',
+        'functions'      => 'Functions',
+        'selectors'      => 'Selectors',
+        'datatypes'      => 'Data Types',
+        'datatype_expr'  => 'Data Types',
+        'config'         => 'Config',
+        'io'             => 'Input/output',
+        'sql'            => 'SQL',
+        'exceptions'     => 'Exceptions',
+        'testing'        => 'Testing',
+        'catalog'        => 'Catalog',
+        'metadata'       => 'Metadata',
+        'schema'         => 'Schema',
+        'plugins'        => 'Plugins'
+      }.freeze
+
+      def get_name
+        name = at_css('h1').content.strip
+        # This runs before clean_html removes the headerlink, so strip its
+        # anchor character off the heading.
+        name.sub! %r{\s*[#\u{00B6}]+\s*\z}, ''
+        name
+      end
+
+      def get_type
+        return 'Manual' if root_page?
+        segment = slug.split('/').first
+        return classify_api(get_name) if segment == 'api'
+        SECTION_TYPES[segment] || 'Manual'
+      end
+
+      private
+
+      # Members stored flat under api/ (top-level polars.* objects).
+      def classify_api(name)
+        case name
+        when %r{\Apolars\.datatypes\.}       then 'Data Types'
+        when %r{\Apolars\.Config\b}          then 'Config'
+        when %r{\Apolars\.exceptions\.}      then 'Exceptions'
+        when %r{\Apolars\.testing\.}         then 'Testing'
+        when %r{\Apolars\.(api|plugins)\.}   then 'Plugins'
+        when %r{\Apolars\.io\.}              then 'Input/output'
+        when %r{\Apolars\.DataFrame\.}       then 'DataFrame'
+        when %r{\Apolars\.LazyFrame\.}       then 'LazyFrame'
+        when %r{\Apolars\.(read_|scan_|write_|from_)}, %r{\Apolars\.json_normalize\b}
+          'Input/output'
+        else 'Functions'
+        end
+      end
+    end
+  end
+end

lib/docs/scrapers/polars.rb

@@ -0,0 +1,34 @@
+module Docs
+  class Polars < UrlScraper
+    self.name = 'Polars'
+    self.type = 'sphinx'
+    self.release = '1.41.0'
+    self.base_url = 'https://docs.pola.rs/api/python/stable/reference/'
+    self.root_path = 'index.html'
+    self.links = {
+      home: 'https://pola.rs/',
+      code: 'https://github.com/pola-rs/polars'
+    }
+
+    html_filters.push 'polars/entries', 'sphinx/clean_html', 'polars/clean_html'
+
+    # pydata-sphinx-theme keeps the page content in the article body.
+    options[:container] = 'article.bd-article'
+
+    options[:skip_patterns] = [/_changelog/, /whatsnew/]
+
+    # https://github.com/pola-rs/polars/blob/main/LICENSE
+    options[:attribution] = <<-HTML
+      &copy; 2020 Ritchie Vink<br>
+      &copy; 2022 Polars contributors<br>
+      Licensed under the MIT License.
+    HTML
+
+    # Polars tags both Rust (rs-*) and Python (py-*) releases in the same repo.
+    # The tags API only lists recent Rust ones, but the latest GitHub release is
+    # always the Python one, so use that and drop the py- prefix.
+    def get_latest_version(opts)
+      get_latest_github_release('pola-rs', 'polars', opts).sub(/\Apy-/, '')
+    end
+  end
+end

public/icons/docs/polars/16.png

@@ -0,0 +1 @@
+https://raw.githubusercontent.com/pola-rs/polars-static/master/icons/favicon-32x32.png