Add frontmatter mapped_pages URL validation with URI format checking (#1899)

* Initial plan

* Add frontmatter mapped_pages URL validation

- Added validation to ensure mapped_pages URLs start with https://www.elastic.co/guide
- Emits clear error messages with guidance on how to fix invalid URLs
- Added comprehensive test coverage for validation scenarios
- All existing tests continue to pass

Co-authored-by: reakaleek <[email protected]>

* Add URI well-formed validation to mapped_pages URLs

- Enhanced validation to include Uri.IsWellFormedUriString check
- Added test cases for malformed URIs, invalid characters, and non-absolute URIs
- URLs must now be both properly prefixed AND well-formed absolute URIs

Co-authored-by: cotti <[email protected]>

* Addressing PR comments

Co-authored-by: reakaleek <[email protected]>

* Restore global.json file to proper state

- Restored global.json content that was accidentally emptied in commit 05a6385
- Proper .NET 9.0.100 SDK configuration restored
- File now contains correct SDK version and rollForward settings

Co-authored-by: reakaleek <[email protected]>

* Run dotnet format

---------

Co-authored-by: copilot-swe-agent[bot] <[email protected]>
Co-authored-by: reakaleek <[email protected]>
Co-authored-by: Jan Calanog <[email protected]>
Co-authored-by: cotti <[email protected]>
Co-authored-by: Felipe Cotti <[email protected]>

Author: 3 people

src/Elastic.Markdown/IO/MarkdownFile.cs

@@ -363,6 +363,18 @@ private YamlFrontMatter ProcessYamlFrontMatter(MarkdownDocument document)
 				Collector.Emit(severity, FilePath, message);
 		}
 
+		// Validate mapped_pages URLs
+		if (fm.MappedPages is not null)
+		{
+			foreach (var url in fm.MappedPages)
+			{
+				if (!string.IsNullOrEmpty(url) && (!url.StartsWith("https://www.elastic.co/guide", StringComparison.OrdinalIgnoreCase) || !Uri.IsWellFormedUriString(url, UriKind.Absolute)))
+				{
+					Collector.EmitError(FilePath, $"Invalid mapped_pages URL: \"{url}\". All mapped_pages URLs must start with \"https://www.elastic.co/guide\". Please update the URL to reference content under the Elastic documentation guide.");
+				}
+			}
+		}
+
 		// TODO remove when migration tool and our demo content sets are updated
 		var deprecatedTitle = fm.Title;
 		if (!string.IsNullOrEmpty(deprecatedTitle))

tests/Elastic.Markdown.Tests/FrontMatter/YamlFrontMatterTests.cs

@@ -183,3 +183,156 @@ public void HasErrors()
 		Collector.Diagnostics.Should().Contain(d => d.Message.Contains("Invalid products frontmatter value: \"Product 'id' field is required."));
 	}
 }
+
+public class MappedPagesValidUrl(ITestOutputHelper output) : DirectiveTest(output,
+	"""
+	---
+	mapped_pages:
+	  - "https://www.elastic.co/guide/en/elasticsearch/reference/current/index.html"
+	---
+
+	# Test Page
+	"""
+)
+{
+	[Fact]
+	public void NoErrors()
+	{
+		Collector.Diagnostics.Should().BeEmpty();
+	}
+}
+
+public class MappedPagesInvalidUrl(ITestOutputHelper output) : DirectiveTest(output,
+	"""
+	---
+	mapped_pages:
+	  - "https://www.elastic.co/docs/get-started/deployment-options"
+	---
+
+	# Test Page
+	"""
+)
+{
+	[Fact]
+	public void HasErrors()
+	{
+		Collector.Diagnostics.Should().HaveCount(1);
+		Collector.Diagnostics.Should().Contain(d => d.Message.Contains("Invalid mapped_pages URL: \"https://www.elastic.co/docs/get-started/deployment-options\". All mapped_pages URLs must start with \"https://www.elastic.co/guide\". Please update the URL to reference content under the Elastic documentation guide."));
+	}
+}
+
+public class MappedPagesMixedUrls(ITestOutputHelper output) : DirectiveTest(output,
+	"""
+	---
+	mapped_pages:
+	  - "https://www.elastic.co/guide/en/elasticsearch/reference/current/index.html"
+	  - "https://www.elastic.co/docs/invalid-url"
+	  - "https://www.elastic.co/guide/en/kibana/current/index.html"
+	---
+
+	# Test Page
+	"""
+)
+{
+	[Fact]
+	public void HasErrorsForInvalidUrl()
+	{
+		Collector.Diagnostics.Should().HaveCount(1);
+		Collector.Diagnostics.Should().Contain(d => d.Message.Contains("Invalid mapped_pages URL: \"https://www.elastic.co/docs/invalid-url\". All mapped_pages URLs must start with \"https://www.elastic.co/guide\""));
+	}
+}
+
+public class MappedPagesEmptyUrl(ITestOutputHelper output) : DirectiveTest(output,
+	"""
+	---
+	mapped_pages:
+	  - ""
+	---
+
+	# Test Page
+	"""
+)
+{
+	[Fact]
+	public void NoErrorsForEmptyUrl()
+	{
+		// Empty URLs are ignored, no validation error should occur
+		Collector.Diagnostics.Should().BeEmpty();
+	}
+}
+
+public class MappedPagesExternalUrl(ITestOutputHelper output) : DirectiveTest(output,
+	"""
+	---
+	mapped_pages:
+	  - "https://github.com/elastic/docs-builder"
+	---
+
+	# Test Page
+	"""
+)
+{
+	[Fact]
+	public void HasErrorsForExternalUrl()
+	{
+		Collector.Diagnostics.Should().HaveCount(1);
+		Collector.Diagnostics.Should().Contain(d => d.Message.Contains("Invalid mapped_pages URL: \"https://github.com/elastic/docs-builder\". All mapped_pages URLs must start with \"https://www.elastic.co/guide\""));
+	}
+}
+
+public class MappedPagesMalformedUri(ITestOutputHelper output) : DirectiveTest(output,
+	"""
+	---
+	mapped_pages:
+	  - "https://www.elastic.co/guide/[invalid-characters]"
+	---
+
+	# Test Page
+	"""
+)
+{
+	[Fact]
+	public void HasErrorsForMalformedUri()
+	{
+		Collector.Diagnostics.Should().HaveCount(1);
+		Collector.Diagnostics.Should().Contain(d => d.Message.Contains("Invalid mapped_pages URL: \"https://www.elastic.co/guide/[invalid-characters]\". All mapped_pages URLs must start with \"https://www.elastic.co/guide\""));
+	}
+}
+
+public class MappedPagesInvalidScheme(ITestOutputHelper output) : DirectiveTest(output,
+	"""
+	---
+	mapped_pages:
+	  - "https://www.elastic.co/guide/invalid uri with spaces"
+	---
+
+	# Test Page
+	"""
+)
+{
+	[Fact]
+	public void HasErrorsForInvalidScheme()
+	{
+		Collector.Diagnostics.Should().HaveCount(1);
+		Collector.Diagnostics.Should().Contain(d => d.Message.Contains("Invalid mapped_pages URL: \"https://www.elastic.co/guide/invalid uri with spaces\". All mapped_pages URLs must start with \"https://www.elastic.co/guide\""));
+	}
+}
+
+public class MappedPagesNotAbsoluteUri(ITestOutputHelper output) : DirectiveTest(output,
+	"""
+	---
+	mapped_pages:
+	  - "not-a-uri-at-all"
+	---
+
+	# Test Page
+	"""
+)
+{
+	[Fact]
+	public void HasErrorsForNotAbsoluteUri()
+	{
+		Collector.Diagnostics.Should().HaveCount(1);
+		Collector.Diagnostics.Should().Contain(d => d.Message.Contains("Invalid mapped_pages URL: \"not-a-uri-at-all\". All mapped_pages URLs must start with \"https://www.elastic.co/guide\""));
+	}
+}