indexmap 0.4.2 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9b0f3c8b9175d0c18c39e52b61b3934129dfa8b8b637d06ad3d0d9adc30eb995
-  data.tar.gz: 3baf06c566ce17d63e189aabfdd7f3e7b4047d5908fc6a58f3e017da5ecef1de
+  metadata.gz: 38fa952c31358e79a900d348041a2475d5f597d19652837b50d27713f2004250
+  data.tar.gz: 6889768f6be1e01b6de1938687a757b050a52f7f9dbf2af58d1818cca2fdc977
 SHA512:
-  metadata.gz: 700e0cd5485cd433ceaa520a2d634eb4e5ccf93d4d8993224fae61acdf7dacd73c91029e24ff750cc58ce8704a5b00bb4ed66eff113d0693c46df75fc5aea4df
-  data.tar.gz: aa51396dad778e50b18a53606d316d5f9008ed358cecb7b75c0f7dc72f24d47a3959750102fdddafe50fbb31688256e16b07ec9c9c0ae53cb9431148593bb250
+  metadata.gz: 612858ebdac07d01107af653411182685e161b1e501670e569d84265e1dbcd455dbb6a7e55615f802d112037875d9eb15d94c11747a2c15e6cbd1b9f63b804de
+  data.tar.gz: 512df6e55dbad711516e9558cda07b0b90b65f7f950441e36699fe696965296690c52a478247b707ff9e15801b49b73a5d3428cea92dd1e0b49e9861c14580d2

data/CHANGELOG.md

@@ -5,12 +5,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.4.2] - 2026-04-23
+## [0.5.0] - 2026-04-24
 
 
 ### Fixed
 
-- harden sitemap pinging and indexnow key handling (#7)
+- namespace rake tasks and harden sitemap validation (#8)
 
 
 

data/README.md

@@ -80,12 +80,12 @@ end
 Then run:
 
 ```bash
-bin/rails sitemap:create
-bin/rails sitemap:format
-bin/rails sitemap:validate
+bin/rails indexmap:sitemap:create
+bin/rails indexmap:sitemap:format
+bin/rails indexmap:sitemap:validate
 ```
 
-`sitemap:create` is the main task. It writes sitemap files, formats them, and validates the result.
+`indexmap:sitemap:create` is the main task. It writes sitemap files, formats them, and validates the result.
 
 ### Default Index Mode
 
@@ -129,8 +129,15 @@ Indexmap::Validator.new.validate!
 The built-in validator checks for:
 
 - missing sitemap files
+- malformed sitemap XML
+- empty sitemap files
+- missing or duplicate child sitemap references
 - duplicate sitemap URLs
 - parameterized URLs in sitemap entries
+- fragment URLs in sitemap entries
+- non-HTTP or relative URLs
+- URLs outside the configured `base_url`
+- invalid `lastmod` values
 
 ## Search Engine Ping
 
@@ -139,11 +146,11 @@ The built-in validator checks for:
 Available rake tasks:
 
 ```bash
-bin/rails sitemap:validate
-bin/rails sitemap:google:ping
-bin/rails sitemap:index_now:ping
-bin/rails sitemap:index_now:write_key
-bin/rails sitemap:ping
+bin/rails indexmap:sitemap:validate
+bin/rails indexmap:google:ping
+bin/rails indexmap:index_now:ping
+bin/rails indexmap:index_now:write_key
+bin/rails indexmap:ping
 ```
 
 ### Google Search Console
@@ -156,7 +163,7 @@ Indexmap.configure do |config|
 end
 ```
 
-If `config.google.credentials` is blank, `sitemap:google:ping` skips Google submission.
+If `config.google.credentials` is blank, `indexmap:google:ping` skips Google submission.
 
 You can optionally override the Search Console property identifier:
 
@@ -184,21 +191,21 @@ Indexmap.configure do |config|
 end
 ```
 
-If `config.index_now.key` is set, `sitemap:create` also writes the matching `public/<key>.txt` verification file automatically.
+If `config.index_now.key` is set, `indexmap:sitemap:create` also writes the matching `public/<key>.txt` verification file automatically.
 
 If you prefer the file-based flow, run:
 
 ```bash
-bin/rails sitemap:index_now:write_key
+bin/rails indexmap:index_now:write_key
 ```
 
 That task:
 
 - reuses an existing valid key file when present
 - otherwise generates a new key in `public/<key>.txt`
-- makes that key available to `sitemap:index_now:ping` without adding `config.index_now.key`
+- makes that key available to `indexmap:index_now:ping` without adding `config.index_now.key`
 
-If neither a configured key nor a valid key file is present, `sitemap:index_now:ping` skips IndexNow submission.
+If neither a configured key nor a valid key file is present, `indexmap:index_now:ping` skips IndexNow submission.
 
 ## Development
 

data/lib/indexmap/validator.rb

@@ -1,5 +1,10 @@
 # frozen_string_literal: true
 
+require "nokogiri"
+require "date"
+require "time"
+require "uri"
+
 module Indexmap
   class Validator
     def initialize(configuration: Indexmap.configuration, path: nil)
@@ -14,9 +19,15 @@ module Indexmap
       )
       raise ValidationError, "Missing sitemap file: #{sitemap_path}" unless File.exist?(sitemap_path)
 
+      validate_sitemap_file!(sitemap_path)
       entries = Parser.new(path: sitemap_path).entries
+      validate_presence!(entries)
       validate_duplicates!(entries)
       validate_parameterized_urls!(entries)
+      validate_fragment_urls!(entries)
+      validate_absolute_http_urls!(entries)
+      validate_same_host_urls!(entries)
+      validate_lastmods!(entries)
       true
     end
 
@@ -24,6 +35,65 @@ module Indexmap
 
     attr_reader :configuration, :path
 
+    def validate_sitemap_file!(sitemap_path)
+      document = read_xml_document(sitemap_path)
+      root_name = document.root&.name
+
+      case root_name
+      when "urlset"
+        validate_urlset_document!(document, sitemap_path)
+      when "sitemapindex"
+        validate_sitemap_index_document!(document, sitemap_path)
+      else
+        raise ValidationError, "Invalid sitemap root element in #{sitemap_path}: #{root_name || "none"}"
+      end
+    end
+
+    def read_xml_document(file_path)
+      document = Nokogiri::XML(File.read(file_path, encoding: "UTF-8")) { |config| config.strict }
+      document.remove_namespaces!
+      document
+    rescue Nokogiri::XML::SyntaxError => error
+      raise ValidationError, "Invalid sitemap XML in #{file_path}: #{error.message.lines.first.strip}"
+    end
+
+    def validate_urlset_document!(document, sitemap_path)
+      return if document.xpath("/urlset/url/loc").any?
+
+      raise ValidationError, "Sitemap has no URLs: #{sitemap_path}"
+    end
+
+    def validate_sitemap_index_document!(document, sitemap_path)
+      child_locations = document.xpath("/sitemapindex/sitemap/loc").map { |node| node.text.to_s.strip }.reject(&:empty?)
+      raise ValidationError, "Sitemap index has no child sitemap URLs: #{sitemap_path}" if child_locations.empty?
+
+      duplicate_children = child_locations.group_by(&:itself).select { |_loc, values| values.size > 1 }.keys
+      unless duplicate_children.empty?
+        raise ValidationError, "Duplicate child sitemap URLs detected: #{duplicate_children.first(5).join(", ")}"
+      end
+
+      child_locations.each do |location|
+        child_path = local_child_path(sitemap_path, location)
+        raise ValidationError, "Missing child sitemap file: #{child_path}" unless File.exist?(child_path)
+
+        validate_sitemap_file!(child_path)
+      end
+    end
+
+    def local_child_path(sitemap_path, location)
+      uri = URI.parse(location)
+      filename = (uri.absolute? || location.start_with?("/")) ? File.basename(uri.path) : location
+      File.expand_path(filename, File.dirname(sitemap_path))
+    rescue URI::InvalidURIError
+      File.expand_path(location, File.dirname(sitemap_path))
+    end
+
+    def validate_presence!(entries)
+      return unless entries.empty?
+
+      raise ValidationError, "Sitemap has no URLs"
+    end
+
     def validate_duplicates!(entries)
       duplicates = entries.map(&:loc).group_by(&:itself).select { |_url, values| values.size > 1 }.keys
       return if duplicates.empty?
@@ -37,5 +107,55 @@ module Indexmap
 
       raise ValidationError, "Parameterized sitemap URLs detected: #{param_urls.first(5).join(", ")}"
     end
+
+    def validate_fragment_urls!(entries)
+      fragment_urls = entries.map(&:loc).select { |url| parse_uri(url)&.fragment }
+      return if fragment_urls.empty?
+
+      raise ValidationError, "Fragment sitemap URLs detected: #{fragment_urls.first(5).join(", ")}"
+    end
+
+    def validate_absolute_http_urls!(entries)
+      invalid_urls = entries.map(&:loc).reject do |url|
+        uri = parse_uri(url)
+        uri&.absolute? && %w[http https].include?(uri.scheme)
+      end
+      return if invalid_urls.empty?
+
+      raise ValidationError, "Invalid sitemap URLs detected: #{invalid_urls.first(5).join(", ")}"
+    end
+
+    def validate_same_host_urls!(entries)
+      base_uri = parse_uri(configuration.base_url)
+      return unless base_uri&.host
+
+      invalid_urls = entries.map(&:loc).reject do |url|
+        uri = parse_uri(url)
+        uri&.host == base_uri.host && uri&.scheme == base_uri.scheme && uri&.port == base_uri.port
+      end
+      return if invalid_urls.empty?
+
+      raise ValidationError, "Sitemap URLs outside configured base URL detected: #{invalid_urls.first(5).join(", ")}"
+    end
+
+    def validate_lastmods!(entries)
+      invalid_entries = entries.select do |entry|
+        next false if entry.lastmod.nil?
+
+        Date.iso8601(entry.lastmod)
+        false
+      rescue ArgumentError
+        true
+      end
+      return if invalid_entries.empty?
+
+      raise ValidationError, "Invalid sitemap lastmod values detected: #{invalid_entries.first(5).map(&:loc).join(", ")}"
+    end
+
+    def parse_uri(url)
+      URI.parse(url.to_s)
+    rescue URI::InvalidURIError
+      nil
+    end
   end
 end

data/lib/indexmap/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Indexmap
-  VERSION = "0.4.2"
+  VERSION = "0.5.0"
 end

data/lib/tasks/indexmap_tasks.rake

@@ -1,35 +1,37 @@
-namespace :sitemap do
-  desc "Create sitemap files"
-  task create: :environment do
-    runner = Indexmap::TaskRunner.new
-    create_result = runner.create
-    runner.format
-    validated_files = runner.validate
-
-    puts "Created, formatted, and validated #{file_count(validated_files)} in #{public_directory(runner)}."
-    puts "IndexNow key file: #{create_result[:index_now_key_path]}" if create_result[:index_now_key_path]
-  end
+namespace :indexmap do
+  namespace :sitemap do
+    desc "Create sitemap files"
+    task create: :environment do
+      runner = Indexmap::TaskRunner.new
+      create_result = runner.create
+      runner.format
+      validated_files = runner.validate
+
+      puts "Created, formatted, and validated #{file_count(validated_files)} in #{public_directory(runner)}."
+      puts "IndexNow key file: #{create_result[:index_now_key_path]}" if create_result[:index_now_key_path]
+    end
 
-  desc "Format sitemap files for better readability"
-  task format: :environment do
-    runner = Indexmap::TaskRunner.new
-    formatted_files = runner.format
+    desc "Format sitemap files for better readability"
+    task format: :environment do
+      runner = Indexmap::TaskRunner.new
+      formatted_files = runner.format
 
-    puts "Formatted #{file_count(formatted_files)} in #{public_directory(runner)}."
-  end
+      puts "Formatted #{file_count(formatted_files)} in #{public_directory(runner)}."
+    end
 
-  desc "Validate sitemap shape and URL hygiene"
-  task validate: :environment do
-    runner = Indexmap::TaskRunner.new
-    validated_files = runner.validate
+    desc "Validate sitemap shape and URL hygiene"
+    task validate: :environment do
+      runner = Indexmap::TaskRunner.new
+      validated_files = runner.validate
 
-    puts "Validated #{file_count(validated_files)} for sitemap shape and URL hygiene."
+      puts "Validated #{file_count(validated_files)} for sitemap shape and URL hygiene."
+    end
   end
 
   desc "Ping all configured search engines"
   task ping: :environment do
-    Rake::Task["sitemap:index_now:ping"].invoke
-    Rake::Task["sitemap:google:ping"].invoke
+    Rake::Task["indexmap:index_now:ping"].invoke
+    Rake::Task["indexmap:google:ping"].invoke
   end
 
   namespace :google do

data/test/indexmap/configuration_test.rb

@@ -8,30 +8,41 @@ class IndexmapConfigurationTest < Minitest::Test
   end
 
   def test_writer_builds_from_configured_callables
-    Indexmap.configure do |config|
-      config.base_url = -> { "https://example.com" }
-      config.public_path = -> { Pathname("tmp/public") }
-      config.sections = -> do
-        [Indexmap::Section.new(filename: "sitemap-pages.xml", entries: [Indexmap::Entry.new(loc: "https://example.com/")])]
+    Dir.mktmpdir do |dir|
+      public_path = Pathname(dir)
+
+      Indexmap.configure do |config|
+        config.base_url = -> { "https://example.com" }
+        config.public_path = -> { public_path }
+        config.sections = -> do
+          [Indexmap::Section.new(filename: "sitemap-pages.xml", entries: [Indexmap::Entry.new(loc: "https://example.com/")])]
+        end
       end
-    end
 
-    writer = Indexmap.configuration.writer
+      Indexmap.configuration.writer.write
 
-    assert_equal Pathname("tmp/public"), writer.instance_variable_get(:@public_path)
+      assert_includes public_path.join("sitemap.xml").read, "<loc>https://example.com/sitemap-pages.xml</loc>"
+      assert_includes public_path.join("sitemap-pages.xml").read, "<loc>https://example.com/</loc>"
+    end
   end
 
   def test_writer_builds_single_file_writer_from_configured_entries
-    Indexmap.configure do |config|
-      config.base_url = "https://example.com"
-      config.format = :single_file
-      config.entries = -> { [Indexmap::Entry.new(loc: "https://example.com/")] }
-    end
+    Dir.mktmpdir do |dir|
+      public_path = Pathname(dir)
+
+      Indexmap.configure do |config|
+        config.base_url = "https://example.com"
+        config.public_path = public_path
+        config.format = :single_file
+        config.entries = -> { [Indexmap::Entry.new(loc: "https://example.com/")] }
+      end
 
-    writer = Indexmap.configuration.writer
+      Indexmap.configuration.writer.write
 
-    assert_equal :single_file, writer.instance_variable_get(:@format)
-    assert_equal [Indexmap::Entry.new(loc: "https://example.com/")], writer.instance_variable_get(:@entries)
+      assert_includes public_path.join("sitemap.xml").read, "<urlset"
+      assert_includes public_path.join("sitemap.xml").read, "<loc>https://example.com/</loc>"
+      refute public_path.join("sitemap-pages.xml").exist?
+    end
   end
 
   def test_writer_raises_without_base_url

data/test/indexmap/validator_test.rb

@@ -52,6 +52,120 @@ class IndexmapValidatorTest < Minitest::Test
     end
   end
 
+  def test_validate_raises_for_fragment_urls
+    Dir.mktmpdir do |directory|
+      path = Pathname(directory).join("sitemap.xml")
+      path.write(<<~XML)
+        <?xml version="1.0" encoding="UTF-8"?>
+        <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
+          <url><loc>https://example.com/about#team</loc></url>
+        </urlset>
+      XML
+
+      error = assert_raises(Indexmap::ValidationError) do
+        Indexmap::Validator.new(path: path).validate!
+      end
+
+      assert_equal "Fragment sitemap URLs detected: https://example.com/about#team", error.message
+    end
+  end
+
+  def test_validate_raises_for_relative_urls
+    Dir.mktmpdir do |directory|
+      path = Pathname(directory).join("sitemap.xml")
+      path.write(<<~XML)
+        <?xml version="1.0" encoding="UTF-8"?>
+        <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
+          <url><loc>/about</loc></url>
+        </urlset>
+      XML
+
+      error = assert_raises(Indexmap::ValidationError) do
+        Indexmap::Validator.new(path: path).validate!
+      end
+
+      assert_equal "Invalid sitemap URLs detected: /about", error.message
+    end
+  end
+
+  def test_validate_raises_for_urls_outside_configured_base_url
+    Dir.mktmpdir do |directory|
+      path = Pathname(directory).join("sitemap.xml")
+      path.write(<<~XML)
+        <?xml version="1.0" encoding="UTF-8"?>
+        <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
+          <url><loc>https://other.example.com/about</loc></url>
+        </urlset>
+      XML
+
+      configuration = Indexmap::Configuration.new
+      configuration.base_url = "https://example.com"
+
+      error = assert_raises(Indexmap::ValidationError) do
+        Indexmap::Validator.new(configuration: configuration, path: path).validate!
+      end
+
+      assert_equal "Sitemap URLs outside configured base URL detected: https://other.example.com/about", error.message
+    end
+  end
+
+  def test_validate_raises_for_invalid_lastmod_values
+    Dir.mktmpdir do |directory|
+      path = Pathname(directory).join("sitemap.xml")
+      path.write(<<~XML)
+        <?xml version="1.0" encoding="UTF-8"?>
+        <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
+          <url>
+            <loc>https://example.com/about</loc>
+            <lastmod>not-a-date</lastmod>
+          </url>
+        </urlset>
+      XML
+
+      error = assert_raises(Indexmap::ValidationError) do
+        Indexmap::Validator.new(path: path).validate!
+      end
+
+      assert_equal "Invalid sitemap lastmod values detected: https://example.com/about", error.message
+    end
+  end
+
+  def test_validate_raises_for_empty_sitemaps
+    Dir.mktmpdir do |directory|
+      path = Pathname(directory).join("sitemap.xml")
+      path.write(<<~XML)
+        <?xml version="1.0" encoding="UTF-8"?>
+        <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
+        </urlset>
+      XML
+
+      error = assert_raises(Indexmap::ValidationError) do
+        Indexmap::Validator.new(path: path).validate!
+      end
+
+      assert_equal "Sitemap has no URLs: #{path}", error.message
+    end
+  end
+
+  def test_validate_raises_for_missing_child_sitemap_files
+    Dir.mktmpdir do |directory|
+      path = Pathname(directory).join("sitemap.xml")
+      child_path = Pathname(directory).join("sitemap-pages.xml")
+      path.write(<<~XML)
+        <?xml version="1.0" encoding="UTF-8"?>
+        <sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
+          <sitemap><loc>https://example.com/sitemap-pages.xml</loc></sitemap>
+        </sitemapindex>
+      XML
+
+      error = assert_raises(Indexmap::ValidationError) do
+        Indexmap::Validator.new(path: path).validate!
+      end
+
+      assert_equal "Missing child sitemap file: #{child_path}", error.message
+    end
+  end
+
   def test_validate_passes_for_valid_sitemap
     Dir.mktmpdir do |directory|
       path = Pathname(directory).join("sitemap.xml")

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: indexmap
 version: !ruby/object:Gem::Version
-  version: 0.4.2
+  version: 0.5.0
 platform: ruby
 authors:
 - Paulo Fidalgo