Script to summarize all ShiftLeft Scan SAST reports

summary.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

from pathlib import Path
import json

# pip install jinja2
from jinja2 import Template


def agg_summary(summary, metrics):
    if not summary:
        summary = {"total": 0, "critical": 0, "high": 0, "medium": 0, "low": 0}
    if metrics:
        summary["total"] += metrics["total"]
        summary["critical"] += metrics["critical"]
        summary["high"] += metrics["high"]
        summary["medium"] += metrics["medium"]
        summary["low"] += metrics["low"]
    return summary


def get_sast_summary(jsonfile):
    with open(jsonfile, mode="r") as fp:
        json_data = fp.read()
        summary = None
        for line in json_data.split("\n"):
            if not line.strip():
                continue
            try:
                sarif_data = json.loads(line)
                metrics = sarif_data.get("properties", {}).get("metrics", {})
                summary = agg_summary(summary, metrics)
            except:
                print(line)
        return summary


def to_html(repo_summary, grand_summary):
    SUMMARY_HTML = Template(
        """
    <h2>Summary {% if repo %}for {{ repo }} {%- endif %}</h2>
    <table class="table">
        <thead>
            <tr>
                <th>Severity</th>
                <th>Count</th>
            </tr>
        </thead>
        <tbody>
        {% for sev in ["critical", "high", "medium", "low", "total"] -%}
            <tr>
                <td>{{ sev|upper }}</span></td>
                <td>{{ metrics.get(sev)|default('NA') }}</td>
            </tr>
            {%- endfor %}
        </tbody>
    </table>
    """
    )
    print(SUMMARY_HTML.render(repo=None, metrics=grand_summary))
    for k, v in repo_summary.items():
        print(SUMMARY_HTML.render(repo=k, metrics=v))


def main():
    # This file should be placed outside reports_dir
    reports_dir = Path(__file__).parent / "reports_dir"
    full_reports = [p.as_posix() for p in reports_dir.rglob("scan-full-report.json")]
    # This is a dict with repo name as the key and summary count as value
    repo_summary = {d.split("/")[1]: get_sast_summary(d) for d in full_reports}
    # This dict would have a grand summary for all repositories
    grand_summary = None
    for k, v in repo_summary.items():
        grand_summary = agg_summary(grand_summary, v)
    print(repo_summary)
    print(grand_summary)
    to_html(repo_summary, grand_summary)


if __name__ == "__main__":
    main()