Merge pull request #2641 from publicarray/main

Add PowerShell docs

Author: simon04

assets/javascripts/news.json

@@ -1,4 +1,8 @@
 [
+  [
+    "2026-06-02",
+    "New documentation: <a href=\"/powershell/\">PowerShell</a>"
+  ],
   [
     "2026-05-26",
     "New documentations: <a href=\"/opentofu/\">OpenTofu</a>, <a href=\"/cyclejs/\">Cycle.js</a>, <a href=\"/polars/\">Polars</a>"

docs/file-scrapers.md

@@ -320,3 +320,9 @@ mv three.js-r${VERSION}/docs/* docs/threejs~${VERSION}/
 rm -rf three.js-r${VERSION}/
 rm threejs.tar.gz
 ```
+
+## PowerShell
+
+```sh
+curl -L 'https://github.com/MicrosoftDocs/PowerShell-Docs/archive/refs/heads/main.zip' | bsdtar --extract --file - --directory=docs/powershell/ --strip-components=2
+```

lib/docs/filters/core/normalize_paths.rb

@@ -51,6 +51,8 @@ def normalize_path(path)
         "#{path}index"
       elsif path.end_with? '.html'
         path[0..-6]
+      elsif path.end_with? '.md'
+        path[0..-4]
       else
         path
       end

lib/docs/filters/powershell/attribution.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module Docs
+  class Powershell
+    class AttributionFilter < Docs::AttributionFilter
+      def attribution_link
+        url = current_url.to_s.downcase
+        base = self.version == 'Scripting' ? 'scripting' : 'module'
+        url.sub! 'http://localhost/', "https://learn.microsoft.com/en-us/powershell/#{base}/"
+        url.remove! %r{\.md$}
+        url << "?view=powershell-" + self.version
+        %(<a href="#{url}" class="_attribution-link">#{url}</a>)
+      end
+    end
+  end
+end

lib/docs/filters/powershell/clean_html.rb

@@ -0,0 +1,23 @@
+module Docs
+  class Powershell
+    class CleanHtmlFilter < Filter
+      def call
+        # web
+        css('header').remove
+        css('#ms--content-header').remove
+        css('#article-header').remove
+        css('.left-container').remove
+        css('.layout-body-aside').remove
+        css('#site-user-feedback-footer').remove
+        css('footer').remove
+        # markdown-folder-to-html
+        css('#menuLink').remove
+        css('#menu').remove
+        css('script').remove
+        css('style').remove
+        css('.heading-anchor-permalink').remove
+        doc
+      end
+    end
+  end
+end

lib/docs/filters/powershell/entries.rb

@@ -0,0 +1,14 @@
+module Docs
+  class Powershell
+    class EntriesFilter < Docs::EntriesFilter
+      def get_name
+        at_css('h1').content.strip
+      end
+
+      def get_type
+        parts = slug.split('/')
+        parts.length > 1 ? parts.first : 'Overview'
+      end
+    end
+  end
+end

lib/docs/scrapers/powershell.rb

@@ -0,0 +1,86 @@
+module Docs
+  class Powershell < FileScraper
+    self.name = 'PowerShell'
+    self.type = 'simple'
+    self.root_path = 'Microsoft.PowerShell.Core/Get-Help.html'
+    self.links = {
+      home: 'https://learn.microsoft.com/powershell',
+      code: 'https://github.com/MicrosoftDocs/PowerShell-Docs'
+    }
+    html_filters.push 'powershell/clean_html', 'powershell/entries'
+    text_filters.replace 'attribution', 'powershell/attribution'
+
+    # https://github.com/MicrosoftDocs/PowerShell-Docs/blob/main/LICENSE-CODE.md
+    # https://github.com/MicrosoftDocs/PowerShell-Docs/blob/main/LICENSE.md
+    options[:attribution] = <<-HTML
+    &copy; Microsoft Corporation
+    Code licensed under an MIT-style License. Documentation licensed under CC BY 4.0.
+    HTML
+
+    version '7.7' do
+      self.release = '7.7'
+    end
+
+    version '7.6' do
+      self.release = '7.6'
+    end
+
+    version '7.5' do
+      self.release = '7.5'
+    end
+
+    version '7.4' do
+      self.release = '7.4'
+    end
+
+    version '5.1' do
+      self.release = '5.1'
+    end
+
+    version 'Scripting' do
+      self.root_path = 'discover-powershell.html'
+
+      def source_directory
+        @source_directory ||= File.join(Docs::FileScraper::SOURCE_DIRECTORY, 'powershell', 'docs-conceptual')
+      end
+    end
+
+    def source_directory
+      @source_directory ||= File.join(Docs::FileScraper::SOURCE_DIRECTORY, 'powershell', self.class.version)
+    end
+
+    def get_latest_version(opts)
+      # Stable PowerShell releases are tagged like "v7.5.2"; the docs are
+      # versioned by major.minor (e.g. "7.5"), so drop the patch component.
+      get_latest_github_release('PowerShell', 'PowerShell', opts).split('.')[0..1].join('.')
+    end
+
+    # No index page, enumerate all HTML files
+    def request_all(urls)
+      assert_source_directory_exists
+      Dir.glob(File.join(source_directory, '**', '*.md')).sort.each do |path|
+        url = File.join(base_url.to_s, path.sub("#{source_directory}/", ''))
+        yield request_one(url)
+      end
+    end
+
+    private
+
+    def parse(response)
+      body = response.body.sub(/\A---\s*\n.*?\n---\s*\n/m, '')
+      html = markdown_renderer.render(body)
+      [Parser.new("<html></head><body>#{html}</body></html>").html, ""]
+    end
+
+    def markdown_renderer
+      require 'redcarpet'
+      @markdown_renderer ||= Redcarpet::Markdown.new(
+        Redcarpet::Render::HTML.new(with_toc_data: true),
+        autolink: true,
+        fenced_code_blocks: true,
+        no_intra_emphasis: true,
+        tables: true
+      )
+    end
+  end
+end

public/icons/docs/powershell/16.png

@@ -0,0 +1 @@
+https://learn.microsoft.com/en-us/powershell/media/index/ps_black_128.svg