{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "title": "PDFtract Baseline Metrics Schema",
  "description": "Schema for baseline benchmark metrics stored in benches/baselines/",
  "type": "object",
  "required": ["commit_sha", "timestamp", "pdftract_geomean", "grep_1000_mean_ms"],
  "properties": {
    "commit_sha": {
      "type": "string",
      "description": "Git commit SHA (short or full) for the pdftract version used",
      "pattern": "^[a-fA-F0-9]{7,40}$|main$",
      "examples": ["abc1234", "deadbeef1234567890", "main"]
    },
    "timestamp": {
      "type": "string",
      "format": "date-time",
      "description": "ISO 8601 timestamp when the baseline was recorded",
      "examples": ["2024-01-01T00:00:00Z", "2024-07-06T10:30:45+00:00"]
    },
    "pdftract_geomean": {
      "type": "number",
      "minimum": 0,
      "description": "Geometric mean extraction time in seconds across all fixtures for pdftract",
      "unit": "seconds"
    },
    "pdfminer_geomean": {
      "type": "number",
      "minimum": 0,
      "description": "Geometric mean extraction time in seconds across all fixtures for pdfminer.six",
      "unit": "seconds"
    },
    "pypdf_geomean": {
      "type": "number",
      "minimum": 0,
      "description": "Geometric mean extraction time in seconds across all fixtures for pypdf",
      "unit": "seconds"
    },
    "pdfplumber_geomean": {
      "type": "number",
      "minimum": 0,
      "description": "Geometric mean extraction time in seconds across all fixtures for pdfplumber",
      "unit": "seconds"
    },
    "grep_1000_mean_ms": {
      "type": "number",
      "minimum": 0,
      "description": "Mean time in milliseconds for searching across 1000-PDF corpus",
      "unit": "milliseconds"
    },
    "throughput_mb_per_sec": {
      "type": "number",
      "minimum": 0,
      "description": "Aggregate throughput in megabytes per second for grep-corpus benchmark",
      "unit": "MB/s"
    },
    "files_per_sec": {
      "type": "number",
      "minimum": 0,
      "description": "Files processed per second in grep-corpus benchmark",
      "unit": "files/second"
    },
    "total_runtime_sec": {
      "type": "number",
      "minimum": 0,
      "description": "Total wall-clock runtime in seconds for the complete benchmark suite",
      "unit": "seconds"
    },
    "corpus_size": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of PDF files in the test corpus",
      "unit": "count"
    },
    "notes": {
      "type": "string",
      "description": "Free-form notes about this baseline (e.g., placeholder, experimental, environmental factors)"
    }
  },
  "additionalProperties": false,
  "examples": [
    {
      "commit_sha": "main",
      "timestamp": "2024-01-01T00:00:00Z",
      "pdftract_geomean": 10.0,
      "pdfminer_geomean": 100.0,
      "pypdf_geomean": 120.0,
      "pdfplumber_geomean": 150.0,
      "grep_1000_mean_ms": 50.0,
      "throughput_mb_per_sec": 78.5,
      "files_per_sec": 850.0,
      "total_runtime_sec": 1.18,
      "corpus_size": 1000,
      "notes": "Baseline for v0.1.0 release"
    }
  ]
}