Add markdown benchmark harness

[PrzemyslawKlys]

Summary

• add a dedicated OfficeIMO.Markdown.Benchmarks project using BenchmarkDotNet
• benchmark representative parse and HTML render workloads for OfficeIMO default, OfficeIMO portable profile, and the internal comparison baseline
• wire the benchmark project into the solution and document how to run it

Validation

• dotnet build OfficeIMO.Markdown.Benchmarks/OfficeIMO.Markdown.Benchmarks.csproj -c Release
• dotnet run -c Release --project OfficeIMO.Markdown.Benchmarks/OfficeIMO.Markdown.Benchmarks.csproj -- --list flat

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, add credits to your account and enable them for code reviews in your settings.

[claude]

Claude finished @PrzemyslawKlys's task —— View job

---

PR Review: Add markdown benchmark harness

Review Progress

• Read and analyze all changed files
• Review code quality and structure
• Check for potential bugs and issues
• Evaluate performance considerations
• Assess security concerns
• Review test coverage and documentation
• Provide comprehensive feedback

---

🔍 Overall Assessment

This is a well-structured addition that introduces proper benchmarking infrastructure for the OfficeIMO.Markdown library. The implementation follows BenchmarkDotNet best practices and provides meaningful comparison metrics.

✅ Strengths

1. Proper Benchmarking Setup: Uses BenchmarkDotNet with appropriate configurations ([MemoryDiagnoser], [SimpleJob(RuntimeMoniker.Net80)])

2. Meaningful Comparisons: Benchmarks both parsing and HTML rendering against:

   • OfficeIMO default profile
   • OfficeIMO portable profile
   • Markdig baseline (industry standard)

3. Realistic Test Data: The corpus includes diverse markdown scenarios:

   • README-style documentation (PortableReadme)
   • Conversational transcript format (Transcript)
   • Technical documentation with advanced features (TechnicalDoc)

4. Good Project Structure: Clean separation with dedicated benchmark project that's properly excluded from packaging (<IsPackable>false</IsPackable>)

⚠️ Areas for Improvement

Code Quality & Best Practices

1. Null-forgiving Operators: Lines MarkdownBenchmarks.cs:10,40 use null! initialization

   private MarkdownReaderOptions _portableOptions = null!;

   Consider using nullable reference types properly or lazy initialization.

2. Static Pipeline Reuse: Good practice in MarkdownBenchmarks.cs:37 with static Markdig pipeline, but could be applied consistently.

Performance Considerations

1. Memory Efficiency: The corpus generation using string.Concat(Enumerable.Repeat(...)) creates large strings in memory. For very large benchmarks, consider:

   • Lazy evaluation
   • Streaming approaches for larger corpora
   • Memory usage validation

2. Baseline Selection: Using OfficeIMO default as baseline ([Benchmark(Baseline = true)]) is reasonable, but consider if Markdig might be a more neutral baseline for broader comparisons.

Configuration & Documentation

1. Target Frameworks: OfficeIMO.Markdown.Benchmarks.csproj:5 targets both net8.0 and net10.0. Consider:

   • Verifying .NET 10.0 availability in CI/CD
   • Adding framework-specific performance notes

2. Corpus Size Documentation: The README doesn't mention corpus sizes or expected benchmark duration. Consider adding:

   • Approximate corpus sizes
   • Expected benchmark execution time
   • Memory requirements

3. Markdig Version: OfficeIMO.Markdown.Benchmarks.csproj:14 uses Markdig 1.1.1. Verify this is the intended comparison version or if it should match a current stable release.

Security Considerations

✅ No security concerns identified:

• No external data sources
• No user input processing
• Contained within benchmark context
• Appropriate access modifiers used

Test Coverage

📋 Benchmark Coverage Assessment:

• ✅ Parse operations covered
• ✅ HTML rendering covered
• ✅ Multiple reader profiles tested
• ⚠️ Consider adding benchmarks for:
  • Document queries/traversal
  • Large document scenarios
  • Memory stress testing

💡 Recommendations

1. Short-term:

   • Add expected execution times to README
   • Consider nullable reference type cleanup
   • Validate .NET 10.0 requirement

2. Future Enhancements:

   • Add corpus size metrics to benchmark output
   • Consider parameterized corpus sizes
   • Add CI integration guidelines

🎯 Verdict

✅ APPROVE - This is a solid implementation that adds valuable benchmarking infrastructure. The identified improvements are minor and don't block the core functionality. The benchmark setup follows industry best practices and provides meaningful performance insights.

---

| Branch: codex/markdown-benchmarks