sarifLog
├── version: "2.1.0"
├── $schema: (optional, enables IDE validation)
└── runs[] (array of analysis runs)
    ├── tool
    │   ├── driver
    │   │   ├── name (required)
    │   │   ├── version
    │   │   └── rules[] (rule definitions)
    │   └── extensions[] (plugins)
    ├── results[] (findings)
    │   ├── ruleId
    │   ├── level (error/warning/note)
    │   ├── message.text
    │   ├── locations[]
    │   │   └── physicalLocation
    │   │       ├── artifactLocation.uri
    │   │       └── region (startLine, startColumn, etc.)
    │   ├── fingerprints{}
    │   └── partialFingerprints{}
    └── artifacts[] (scanned files metadata)

undefined

undefined

from pysarif import load_from_file, save_to_file

for result in run.results:
    print(f"  [{result.level}] {result.rule_id}: {result.message.text}")

    if result.locations:
        loc = result.locations[0].physical_location
        if loc and loc.artifact_location:
            print(f"    File: {loc.artifact_location.uri}")
            if loc.region:
                print(f"    Line: {loc.region.start_line}")

undefined

from sarif import loader

**sarif-tools CLI commands:**

```bash

undefined

import json
from pathlib import Path

def aggregate_sarif_files(sarif_paths: list[str]) -> dict:
    """Combine multiple SARIF files into one."""
    aggregated = {
        "version": "2.1.0",
        "$schema": "https://json.schemastore.org/sarif-2.1.0.json",
        "runs": []
    }

    for path in sarif_paths:
        with open(path) as f:
            sarif = json.load(f)
            aggregated["runs"].extend(sarif.get("runs", []))

    return aggregated

def deduplicate_results(sarif: dict) -> dict:
    """Remove duplicate findings based on fingerprints."""
    seen_fingerprints = set()

    for run in sarif["runs"]:
        unique_results = []
        for result in run.get("results", []):
            # Use partialFingerprints or create key from location
            fp = None
            if result.get("partialFingerprints"):
                fp = tuple(sorted(result["partialFingerprints"].items()))
            elif result.get("fingerprints"):
                fp = tuple(sorted(result["fingerprints"].items()))
            else:
                # Fallback: create fingerprint from rule + location
                loc = result.get("locations", [{}])[0]
                phys = loc.get("physicalLocation", {})
                fp = (
                    result.get("ruleId"),
                    phys.get("artifactLocation", {}).get("uri"),
                    phys.get("region", {}).get("startLine")
                )

            if fp not in seen_fingerprints:
                seen_fingerprints.add(fp)
                unique_results.append(result)

        run["results"] = unique_results

    return sarif

import json
from dataclasses import dataclass
from typing import Optional

@dataclass
class Finding:
    rule_id: str
    level: str
    message: str
    file_path: Optional[str]
    start_line: Optional[int]
    end_line: Optional[int]
    fingerprint: Optional[str]

def extract_findings(sarif_path: str) -> list[Finding]:
    """Extract structured findings from SARIF file."""
    with open(sarif_path) as f:
        sarif = json.load(f)

    findings = []
    for run in sarif.get("runs", []):
        for result in run.get("results", []):
            loc = result.get("locations", [{}])[0]
            phys = loc.get("physicalLocation", {})
            region = phys.get("region", {})

            findings.append(Finding(
                rule_id=result.get("ruleId", "unknown"),
                level=result.get("level", "warning"),
                message=result.get("message", {}).get("text", ""),
                file_path=phys.get("artifactLocation", {}).get("uri"),
                start_line=region.get("startLine"),
                end_line=region.get("endLine"),
                fingerprint=next(iter(result.get("partialFingerprints", {}).values()), None)
            ))

    return findings

undefined

from urllib.parse import unquote
from pathlib import Path

def normalize_path(uri: str, base_path: str = "") -> str:
    """Normalize SARIF artifact URI to consistent path."""
    # Remove file:// prefix if present
    if uri.startswith("file://"):
        uri = uri[7:]

    # URL decode
    uri = unquote(uri)

    # Handle relative paths
    if not Path(uri).is_absolute() and base_path:
        uri = str(Path(base_path) / uri)

    # Normalize separators
    return str(Path(uri))

def compute_stable_fingerprint(result: dict, file_content: str = None) -> str:
    """Compute environment-independent fingerprint."""
    import hashlib

    components = [
        result.get("ruleId", ""),
        result.get("message", {}).get("text", "")[:100],  # First 100 chars
    ]

    # Add code snippet if available
    if file_content and result.get("locations"):
        region = result["locations"][0].get("physicalLocation", {}).get("region", {})
        if region.get("startLine"):
            lines = file_content.split("\n")
            line_idx = region["startLine"] - 1
            if 0 <= line_idx < len(lines):
                # Normalize whitespace
                components.append(lines[line_idx].strip())

    return hashlib.sha256("".join(components).encode()).hexdigest()[:16]

def safe_get_location(result: dict) -> tuple[str, int]:
    """Safely extract file and line from result."""
    try:
        loc = result.get("locations", [{}])[0]
        phys = loc.get("physicalLocation", {})
        file_path = phys.get("artifactLocation", {}).get("uri", "unknown")
        line = phys.get("region", {}).get("startLine", 0)
        return file_path, line
    except (IndexError, KeyError, TypeError):
        return "unknown", 0

import ijson  # pip install ijson

def stream_results(sarif_path: str):
    """Stream results without loading entire file."""
    with open(sarif_path, "rb") as f:
        # Stream through results arrays
        for result in ijson.items(f, "runs.item.results.item"):
            yield result

undefined

```python
from jsonschema import validate, ValidationError
import json

def validate_sarif(sarif_path: str, schema_path: str) -> bool:
    """Validate SARIF file against schema."""
    with open(sarif_path) as f:
        sarif = json.load(f)
    with open(schema_path) as f:
        schema = json.load(f)

    try:
        validate(sarif, schema)
        return True
    except ValidationError as e:
        print(f"Validation error: {e.message}")
        return False

- name: Upload SARIF
  uses: github/codeql-action/upload-sarif@v3
  with:
    sarif_file: results.sarif

- name: Check for high severity
  run: |
    HIGH_COUNT=$(jq '[.runs[].results[] | select(.level == "error")] | length' results.sarif)
    if [ "$HIGH_COUNT" -gt 0 ]; then
      echo "Found $HIGH_COUNT high severity issues"
      exit 1
    fi

from sarif import loader

def check_for_regressions(baseline: str, current: str) -> int:
    """Return count of new issues not in baseline."""
    baseline_data = loader.load_sarif_file(baseline)
    current_data = loader.load_sarif_file(current)

    baseline_fps = {get_fingerprint(r) for r in baseline_data.get_results()}
    new_issues = [r for r in current_data.get_results()
                  if get_fingerprint(r) not in baseline_fps]

    return len(new_issues)