Add tokenization benchmarks comparing Links Notation with JSON, YAML, XML

.github/workflows/benchmarks.yml

@@ -0,0 +1,208 @@
+name: benchmarks
+
+on:
+  push:
+    branches: main
+    paths:
+      - 'benchmarks/**'
+      - 'rust/links-notation-benchmark/**'
+      - '.github/workflows/benchmarks.yml'
+  pull_request:
+    paths:
+      - 'benchmarks/**'
+      - 'rust/links-notation-benchmark/**'
+      - '.github/workflows/benchmarks.yml'
+  workflow_dispatch:
+
+env:
+  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+jobs:
+  findChangedBenchmarkFiles:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    outputs:
+      isBenchmarkFilesChanged: ${{ steps.setIsBenchmarkFilesChangedOutput.outputs.isBenchmarkFilesChanged }}
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+      - name: Get changed files using defaults
+        id: changed-files
+        uses: tj-actions/changed-files@v47
+      - name: Set output isBenchmarkFilesChanged
+        id: setIsBenchmarkFilesChangedOutput
+        run: |
+          isBenchmarkFilesChanged='false'
+          echo "Changed files: ${{ steps.changed-files.outputs.all_changed_files }}"
+          for changedFile in ${{ steps.changed-files.outputs.all_changed_files }}; do
+            if [[ $changedFile == benchmarks/* ]] || [[ $changedFile == rust/links-notation-benchmark/* ]] || [[ $changedFile == .github/workflows/benchmarks.yml ]]; then
+              echo "isBenchmarkFilesChanged='true'"
+              isBenchmarkFilesChanged='true'
+              break
+            fi
+          done
+          echo "isBenchmarkFilesChanged=${isBenchmarkFilesChanged}" >> $GITHUB_OUTPUT
+          echo "isBenchmarkFilesChanged: ${isBenchmarkFilesChanged}"
+
+  run-benchmark:
+    needs: [findChangedBenchmarkFiles]
+    if: ${{ needs.findChangedBenchmarkFiles.outputs.isBenchmarkFilesChanged == 'true' }}
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: true
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Setup Rust
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Cache Cargo registry
+        uses: actions/cache@v5
+        with:
+          path: ~/.cargo/registry
+          key: ${{ runner.os }}-cargo-registry-${{ hashFiles('**/Cargo.lock') }}
+
+      - name: Cache Cargo index
+        uses: actions/cache@v5
+        with:
+          path: ~/.cargo/git
+          key: ${{ runner.os }}-cargo-index-${{ hashFiles('**/Cargo.lock') }}
+
+      - name: Cache Cargo build
+        uses: actions/cache@v5
+        with:
+          path: rust/target
+          key: ${{ runner.os }}-cargo-build-target-benchmark-${{ hashFiles('**/Cargo.lock') }}
+
+      - name: Build benchmark
+        working-directory: rust
+        run: cargo build -p links-notation-benchmark --release
+
+      - name: Run benchmark tests
+        working-directory: rust
+        run: cargo test -p links-notation-benchmark
+
+      - name: Run benchmark and generate report
+        working-directory: rust
+        run: cargo run -p links-notation-benchmark --release
+
+      - name: Check for changes in benchmark results
+        id: check-changes
+        run: |
+          if git diff --quiet benchmarks/BENCHMARK_RESULTS.md benchmarks/benchmark_results.json; then
+            echo "No changes in benchmark results"
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          else
+            echo "Benchmark results have changed"
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Commit updated benchmark results
+        if: ${{ steps.check-changes.outputs.has_changes == 'true' && github.event_name == 'push' && github.ref == 'refs/heads/main' }}
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+          git add benchmarks/BENCHMARK_RESULTS.md benchmarks/benchmark_results.json
+          git diff --staged --quiet || git commit -m "Update benchmark results [skip ci]"
+          git push
+
+  validate-all-benchmarks:
+    needs: [run-benchmark]
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: true
+
+      # Rust benchmark (already tested in run-benchmark job)
+      - name: Setup Rust
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Cache Cargo
+        uses: actions/cache@v5
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            rust/target
+          key: ${{ runner.os }}-cargo-validate-${{ hashFiles('**/Cargo.lock') }}
+
+      - name: Validate Rust benchmark
+        working-directory: rust
+        run: |
+          cargo build -p links-notation-benchmark --release
+          cargo run -p links-notation-benchmark --release
+          echo "Rust benchmark: PASSED"
+
+      # JavaScript benchmark
+      - name: Setup Node.js
+        uses: actions/setup-node@v6
+        with:
+          node-version: '20'
+
+      - name: Validate JavaScript benchmark
+        run: |
+          node benchmarks/js/benchmark.mjs
+          echo "JavaScript benchmark: PASSED"
+
+      # Python benchmark
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Validate Python benchmark
+        run: |
+          python3 benchmarks/python/benchmark.py
+          echo "Python benchmark: PASSED"
+
+      # C# benchmark
+      - name: Setup .NET
+        uses: actions/setup-dotnet@v4
+        with:
+          dotnet-version: '8.0.x'
+
+      - name: Validate C# benchmark
+        run: |
+          dotnet run --project benchmarks/csharp/Benchmark.csproj
+          echo "C# benchmark: PASSED"
+
+      # Go benchmark
+      - name: Setup Go
+        uses: actions/setup-go@v5
+        with:
+          go-version: '1.21'
+
+      - name: Validate Go benchmark
+        working-directory: benchmarks/go
+        run: |
+          go run benchmark.go
+          echo "Go benchmark: PASSED"
+
+      # Java benchmark
+      - name: Setup Java
+        uses: actions/setup-java@v4
+        with:
+          distribution: 'temurin'
+          java-version: '17'
+          cache: 'maven'
+
+      - name: Validate Java benchmark
+        working-directory: benchmarks/java
+        run: |
+          mvn compile exec:java -q
+          echo "Java benchmark: PASSED"
+
+      - name: Summary
+        run: |
+          echo "=== All benchmarks validated successfully ==="
+          echo "- Rust: PASSED"
+          echo "- JavaScript: PASSED"
+          echo "- Python: PASSED"
+          echo "- C#: PASSED"
+          echo "- Go: PASSED"
+          echo "- Java: PASSED"

benchmarks/BENCHMARK_RESULTS.md

@@ -0,0 +1,96 @@
+# Links Notation Character Count Benchmark
+
+This benchmark compares the UTF-8 character count of Links Notation (lino) against JSON, YAML, and XML.
+
+## Summary
+
+| Format | Total Characters | vs Lino |
+|--------|------------------|----------|
+| **Lino** | **734** | - |
+| JSON | 1332 | +81.5% |
+| YAML | 920 | +25.3% |
+| XML | 1882 | +156.4% |
+
+## Average Savings with Lino
+
+- **vs JSON**: 47.9% fewer characters
+- **vs YAML**: 21.5% fewer characters
+- **vs XML**: 61.5% fewer characters
+
+## Detailed Results
+
+| Test Case | Description | Lino | JSON | YAML | XML | Lino vs JSON | Lino vs YAML | Lino vs XML |
+|-----------|-------------|------|------|------|-----|--------------|--------------|-------------|
+| employees | Employee records with nested structure | 177 | 251 | 142 | 302 | 29.5% | -24.6% | 41.4% |
+| simple_doublets | Simple doublet links (2-tuples) | 62 | 155 | 112 | 215 | 60.0% | 44.6% | 71.2% |
+| triplets | Triplet relations (3-tuples) | 54 | 229 | 183 | 371 | 76.4% | 70.5% | 85.4% |
+| nested_structure | Deeply nested company structure | 254 | 400 | 282 | 615 | 36.5% | 9.9% | 58.7% |
+| config | Application configuration | 187 | 297 | 201 | 379 | 37.0% | 7.0% | 50.7% |
+
+## Test Cases
+
+### employees
+
+Employee records with nested structure
+
+| Format | Characters |
+|--------|------------|
+| Lino | 177 |
+| JSON | 251 |
+| YAML | 142 |
+| XML | 302 |
+
+### simple_doublets
+
+Simple doublet links (2-tuples)
+
+| Format | Characters |
+|--------|------------|
+| Lino | 62 |
+| JSON | 155 |
+| YAML | 112 |
+| XML | 215 |
+
+### triplets
+
+Triplet relations (3-tuples)
+
+| Format | Characters |
+|--------|------------|
+| Lino | 54 |
+| JSON | 229 |
+| YAML | 183 |
+| XML | 371 |
+
+### nested_structure
+
+Deeply nested company structure
+
+| Format | Characters |
+|--------|------------|
+| Lino | 254 |
+| JSON | 400 |
+| YAML | 282 |
+| XML | 615 |
+
+### config
+
+Application configuration
+
+| Format | Characters |
+|--------|------------|
+| Lino | 187 |
+| JSON | 297 |
+| YAML | 201 |
+| XML | 379 |
+
+## Methodology
+
+This benchmark counts UTF-8 characters (not bytes) in equivalent data representations across all formats.
+The "savings" percentage indicates how much smaller the Lino representation is compared to each format.
+
+A positive savings percentage means Lino uses fewer characters.
+
+---
+
+*Generated automatically by links-notation-benchmark*