sarif-parsing

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
    │   ├── ruleIndex (index into tool.driver.rules[])
    │   ├── level (OPTIONAL, inherited from the rule when absent)
    │   ├── message.text
    │   ├── locations[]
    │   │   └── physicalLocation
    │   │       ├── artifactLocation.uri
    │   │       └── region (startLine, startColumn, etc.)
    │   ├── fingerprints{}
    │   └── partialFingerprints{}
    └── artifacts[] (scanned files metadata)

# Pretty print the file
jq '.' results.sarif

# Count total findings
jq '[.runs[].results[]] | length' results.sarif

# List all rule IDs triggered
jq '[.runs[].results[].ruleId] | unique' results.sarif

# Severity resolution, needed by every query below that filters on level.
# See resources/jq-queries.md for the annotated version.
LEVEL_FN='
  def rule($run):
    . as $r
    | ($run.tool.driver.rules // []) as $rules
    | (if ($r.ruleIndex | type) == "number" and $r.ruleIndex >= 0
       then $rules[$r.ruleIndex] else null end)
      // first($rules[] | select(.id == $r.ruleId))
      // null;
  def level($run):
    . as $r
    | if ($r.kind // "fail") != "fail" then "none"
      else ($r.level // rule($run).defaultConfiguration.level // "warning") end;
'

# Extract errors only
jq "$LEVEL_FN"'.runs[] as $run | $run.results[] | select(level($run) == "error")' results.sarif

# Get findings with file locations
jq '.runs[].results[] | {
  rule: .ruleId,
  message: .message.text,
  file: .locations[0].physicalLocation.artifactLocation.uri,
  line: .locations[0].physicalLocation.region.startLine
}' results.sarif

# Filter by severity and get count per rule
jq "$LEVEL_FN"'[.runs[] as $run | $run.results[] | select(level($run) == "error")] | group_by(.ruleId) | map({rule: .[0].ruleId, count: length})' results.sarif

# Extract findings for a specific file
jq --arg file "src/auth.py" '.runs[].results[] | select(.locations[].physicalLocation.artifactLocation.uri | contains($file))' results.sarif

from pysarif import load_from_file, save_to_file

# Load SARIF file
sarif = load_from_file("results.sarif")

# Iterate through runs and results
for run in sarif.runs:
    tool_name = run.tool.driver.name
    print(f"Tool: {tool_name}")

    for result in run.results:
        # pysarif fills a missing result.level with "warning", so .level here is NOT the
        # rule-inherited severity: a CodeQL error (no level on the result, severity on the
        # rule) reads as "warning". Gate severity with Strategy 1's level() or with
        # resolve_level() in resources/sarif_helpers.py, which resolve it from the rule.
        print(f"  {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}")

# Save modified SARIF
save_to_file(sarif, "modified.sarif")

from sarif import loader

# Load single file
sarif_data = loader.load_sarif_file("results.sarif")

# Or load multiple files
sarif_set = loader.load_sarif_files(["tool1.sarif", "tool2.sarif"])

# Get summary report
report = sarif_data.get_report()

# Get histogram by severity
errors = report.get_issue_type_histogram_for_severity("error")
warnings = report.get_issue_type_histogram_for_severity("warning")

# Filter by severity. sarif-tools hands back raw result dicts, and a result's level may
# live on its rule, so resolve it against the run instead of reading r["level"].
from sarif_helpers import extract_findings, filter_by_level, load_sarif

high_severity = filter_by_level(extract_findings(load_sarif("results.sarif")), "error")

# Summary of findings
sarif summary results.sarif

# List all results with details
sarif ls results.sarif

# Get results by severity
sarif ls --level error results.sarif

# Diff two SARIF files (find new/fixed issues)
sarif diff baseline.sarif current.sarif

# Convert to other formats
sarif csv results.sarif > results.csv
sarif html results.sarif > report.html

import json

from sarif_helpers import deduplicate, extract_findings

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

unique = deduplicate(extract_findings(aggregate_sarif_files(["tool1.sarif", "tool2.sarif"])))

from sarif_helpers import extract_findings, filter_by_level, load_sarif, sort_by_severity

findings = sort_by_severity(extract_findings(load_sarif("results.sarif")))
for f in filter_by_level(findings, "error"):
    print(f"{f.file_path}:{f.start_line} [{f.level}] {f.rule_id}: {f.message}")

def resolve_level(result: dict, run: dict) -> str:
    """Severity of a result: its own level, else its rule's default, else "warning"."""
    if result.get("kind", "fail") != "fail":
        return "none"
    if result.get("level"):
        return result["level"]

    rules = run.get("tool", {}).get("driver", {}).get("rules", [])
    index = result.get("ruleIndex")
    rule = rules[index] if isinstance(index, int) and 0 <= index < len(rules) else next(
        (r for r in rules if r.get("id") == result.get("ruleId")), {}
    )
    return rule.get("defaultConfiguration", {}).get("level") or "warning"

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  # run via: uv run --with 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

# Using ajv-cli
npm install -g ajv-cli
ajv validate -s sarif-schema-2.1.0.json -d results.sarif

# Using Python jsonschema
uv run --with jsonschema python your_script.py   # e.g. the function below

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: |
    # select(.level == "error") counts zero on CodeQL output, which records severity on
    # the rule instead. Resolve the level or the gate passes on a repo full of errors.
    HIGH_COUNT=$(jq '
      def rule($run):
        . as $r
        | ($run.tool.driver.rules // []) as $rules
        | (if ($r.ruleIndex | type) == "number" and $r.ruleIndex >= 0
           then $rules[$r.ruleIndex] else null end)
          // first($rules[] | select(.id == $r.ruleId))
          // null;
      def level($run):
        . as $r
        | if ($r.kind // "fail") != "fail" then "none"
          else ($r.level // rule($run).defaultConfiguration.level // "warning") end;
      [.runs[] as $run | $run.results[] | select(level($run) == "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)