#!/usr/bin/env python3
"""Reads a CycloneDX JSON file (and optionally the jar it came from). Standard library only.

  analyse.py inspect  SBOM
  analyse.py compare  SBOM JAR
  analyse.py licences SBOM
  analyse.py scan     SBOM          (calls https://api.osv.dev)
"""
import collections, json, sys, urllib.request, zipfile

def load(p):
    return json.load(open(p))

def purl(c):
    return c.get("purl") or c["bom-ref"]

def inspect(p):
    d = load(p)
    m = d["metadata"]
    print(f"format {d['bomFormat']} {d['specVersion']}, serial {d['serialNumber'][:13]}...")
    print(f"lifecycle phase: {m['lifecycles'][0]['phase']}")
    t = m["tools"]["components"][0]
    print(f"generated by: {t['group']}:{t['name']} {t['version']}")
    a = m["component"]
    print(f"describes: {a['type']} {a['group']}:{a['name']}:{a['version']}")
    c = d["components"]
    print(f"components: {len(c)}")
    print("by scope: " + ", ".join(f"{k} {v}" for k, v in sorted(collections.Counter(x.get('scope', '?') for x in c).items())))
    print("with a hash: %d of %d" % (sum(1 for x in c if x.get("hashes")), len(c)))
    print("hash algorithms on the first component: " + ", ".join(h["alg"] for h in c[0]["hashes"]))
    print("with a licence: %d of %d" % (sum(1 for x in c if x.get("licenses")), len(c)))
    deps = d["dependencies"]
    print(f"dependency entries: {len(deps)}")
    root = [x for x in deps if x["ref"] == a["bom-ref"]][0]
    print(f"direct dependencies of the application: {len(root['dependsOn'])}")
    for r in root["dependsOn"]:
        print("  " + r.split("/", 1)[1].split("?")[0])
    print("first three components:")
    for x in c[:3]:
        print("  " + purl(x).split("?")[0])

def compare(p, jar):
    d = load(p)
    sb = {f"{c['name']}-{c['version']}.jar": c for c in d["components"]}
    z = zipfile.ZipFile(jar)
    lib = {n.rsplit("/", 1)[1] for n in z.namelist() if n.startswith("BOOT-INF/lib/") and n.endswith(".jar")}
    print(f"components in the SBOM: {len(sb)}")
    print(f"jars in BOOT-INF/lib:   {len(lib)}")
    print(f"in both:                {len(set(sb) & lib)}")
    print("in the SBOM but not in the jar:")
    for n in sorted(set(sb) - lib):
        print("  " + n)
    print("in the jar but not in the SBOM:")
    for n in sorted(lib - set(sb)):
        print("  " + n)

COPYLEFT = ("GPL", "LGPL", "AGPL", "MPL", "EPL", "CDDL")
def licences(p):
    d = load(p)
    c = collections.Counter()
    rows = []
    for x in d["components"]:
        ids = [l["license"].get("id") or l["license"].get("name") for l in x.get("licenses", [])]
        for i in ids:
            c[i] += 1
        rows.append((x["name"], ids))
    print("licence entries (a component with two licences counts once under each):")
    for k, v in c.most_common():
        print(f"  {k:36s} {v}")
    print()
    naive = [n for n, ids in rows if any(any(k in i for k in ("GPL",)) for i in ids)]
    print(f"naive rule 'fail on any GPL or LGPL entry' flags {len(naive)}: {', '.join(naive)}")
    strict = [n for n, ids in rows if ids and all(any(k in i for k in ("GPL",)) for i in ids)]
    print(f"rule 'fail only when every listed licence is GPL or LGPL' flags {len(strict)}")
    print("no licence listed: " + (", ".join(n for n, ids in rows if not ids) or "none"))
    print("dual-licensed components (more than one entry):")
    for n, ids in rows:
        if len(ids) > 1:
            print(f"  {n}: {' / '.join(ids)}")

def post(url, body):
    r = urllib.request.Request(url, json.dumps(body).encode(), {"Content-Type": "application/json"})
    return json.load(urllib.request.urlopen(r, timeout=30))

def get(url):
    return json.load(urllib.request.urlopen(url, timeout=30))

def scan(p):
    d = load(p)
    comps = d["components"]
    res = post("https://api.osv.dev/v1/querybatch",
               {"queries": [{"package": {"purl": purl(x).split("?")[0]}} for x in comps]})["results"]
    hits = [(x, r["vulns"]) for x, r in zip(comps, res) if r.get("vulns")]
    print(f"queried {len(comps)} components against api.osv.dev")
    print(f"components with at least one advisory: {len(hits)}")
    for x, vs in hits:
        print(f"{x['group']}:{x['name']}:{x['version']} - {len(vs)} advisories")
        for v in sorted(vs, key=lambda v: v["id"]):
            full = get("https://api.osv.dev/v1/vulns/" + v["id"])
            cves = [a for a in full.get("aliases", []) if a.startswith("CVE-")]
            fixed = sorted({e["fixed"] for a in full.get("affected", []) for r in a.get("ranges", [])
                            for e in r.get("events", []) if "fixed" in e})
            print(f"  {v['id']} {','.join(cves) or '-'} fixed in {','.join(fixed) or '?'}: {full.get('summary', '')[:70]}")

if __name__ == "__main__":
    {"inspect": lambda: inspect(sys.argv[2]), "compare": lambda: compare(sys.argv[2], sys.argv[3]),
     "licences": lambda: licences(sys.argv[2]), "scan": lambda: scan(sys.argv[2])}[sys.argv[1]]()