#!/usr/bin/env python3 """Walk Google's whole Discovery directory and report what the engine cannot do. python3 src/google/discovery/tools/check_discovery_directory.py [--cache DIR] [--no-fetch] [--json FILE] [--max-rejected N] [--workers N] 1. Fetches https://discovery.googleapis.com/discovery/v1/apis and the document of every preferred API into --cache (default build/google/discovery-cache). Fetch failures are listed as UNREACHABLE: Google lists them but does not serve them (not an engine fault). 2. Builds build/google/discovery-audit (src/google/discovery/tools/audit_main.cc) against libgoogle.a and runs it on the saved files, so the verdict comes from the engine's own classification, never from a second implementation. 3. Prints totals, a reason table and the APIs with rejected or limited methods. Exit 1 when a fetched document does not parse, or when rejected methods exceed --max-rejected (default: no ceiling). python3 standard library only. """ import argparse import concurrent.futures as cf import json import os import subprocess import sys import urllib.request ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", "..", "..")) DIRECTORY = "https://discovery.googleapis.com/discovery/v1/apis" AUDIT_SRC = os.path.join(ROOT, "src/google/discovery/tools/audit_main.cc") AUDIT_BIN = os.path.join(ROOT, "build/google/discovery-audit") LIBS = ["build/google/libgoogle.a", "build/clients/libclients.a", "build/liboperability.a"] def get(url, tries=3): last = None for _ in range(tries): try: with urllib.request.urlopen(url, timeout=90) as r: return r.read() except Exception as e: # noqa: BLE001 - report whatever the network said last = e raise last def fetch_all(cache, workers): os.makedirs(cache, exist_ok=True) raw = get(DIRECTORY) with open(os.path.join(cache, "directory.json"), "wb") as f: f.write(raw) items = [i for i in json.loads(raw)["items"] if i.get("preferred")] unreachable = [] def one(item): path = os.path.join(cache, "%s_%s.json" % (item["name"], item["version"])) try: data = get(item["discoveryRestUrl"]) with open(path, "wb") as f: f.write(data) return None except Exception as e: # noqa: BLE001 if os.path.exists(path): os.remove(path) return (item["id"], str(e)) with cf.ThreadPoolExecutor(workers) as ex: for r in ex.map(one, items): if r: unreachable.append(r) return len(items), unreachable def build_audit(): subprocess.run(["make", "-s", "-j8", "google", "build/clients/libclients.a", "build/liboperability.a"], cwd=ROOT, check=True) cmd = ["g++", "-std=c++23", "-Wall", "-Wextra", "-Werror", "-DMOLO_HAS_WOLFSSL", "-I" + os.path.join(ROOT, "src"), AUDIT_SRC] + [os.path.join(ROOT, l) for l in LIBS] + \ ["-lwolfssl", "-o", AUDIT_BIN] subprocess.run(cmd, cwd=ROOT, check=True) def main(): ap = argparse.ArgumentParser() ap.add_argument("--cache", default=os.path.join(ROOT, "build/google/discovery-cache")) ap.add_argument("--no-fetch", action="store_true", help="reuse the files already in --cache") ap.add_argument("--json", help="write the full audit report here") ap.add_argument("--max-rejected", type=int, default=None) ap.add_argument("--workers", type=int, default=16) ap.add_argument("--list", type=int, default=40, help="APIs to list with problems") args = ap.parse_args() unreachable = [] listed = None if not args.no_fetch: listed, unreachable = fetch_all(args.cache, args.workers) build_audit() out = subprocess.run([AUDIT_BIN, args.cache], capture_output=True, text=True) if out.returncode != 0: print(out.stderr, file=sys.stderr) return 1 rep = json.loads(out.stdout) if args.json: with open(args.json, "w") as f: json.dump(rep, f, indent=1) unreach_ids = {u[0] for u in unreachable} parse_failures = [f for f in rep["failed"] if f["api"] not in unreach_ids] gone = [f for f in rep["failed"] if f["api"] in unreach_ids or "NOT_FOUND" in f["why"]] print("preferred APIs in the directory : %d" % rep["preferred"]) print("documents loaded by the engine : %d" % rep["loaded"]) print("UNREACHABLE at the source : %d" % len(gone)) for f in gone: print(" %-40s %s" % (f["api"], f["why"][:90])) parse_failures = [f for f in parse_failures if f not in gone] print("documents the engine REJECTS : %d" % len(parse_failures)) for f in parse_failures: print(" %-40s %s" % (f["api"], f["why"][:160])) print("methods : %d" % rep["methods"]) print(" full / limited / rejected : %d / %d / %d" % (rep["full"], rep["limited"], rep["rejected"])) print(" pageable (pageToken) : %d" % rep["pageable"]) print(" long-running replies : %d (%d in APIs with no operations.get)" % (rep["longRunning"], rep["longRunningWithoutGetter"])) print("dry plans (required params only): %d planned, %d skipped (synthetic value vs exotic pattern), %d FAILED" % (rep["planned"], rep["planSkippedPattern"], rep["planFailed"])) for f in rep["planFailures"][:20]: print(" %s: %s" % (f["method"], f["why"][:140])) print("APIs with regional endpoints : %d" % rep["apisWithRegionalEndpoints"]) print("APIs declaring a batchPath : %d (batch endpoints are not used)" % rep["apisDeclaringBatchPath"]) print("\nreasons (methods):") for k, v in sorted(rep["reasons"].items(), key=lambda kv: -kv[1]): print(" %6d %s" % (v, k)) bad = [a for a in rep["apis"] if a["rejected"] or a["limited"]] bad.sort(key=lambda a: -(a["rejected"] * 1000 + a["limited"])) print("\nAPIs with rejected or limited methods: %d of %d" % (len(bad), len(rep["apis"]))) for a in bad[:args.list]: sample = a["problems"][0] print(" %-34s rejected %-3d limited %-3d e.g. %s: %s" % (a["api"], a["rejected"], a["limited"], sample["method"], sample["notes"][0][:70])) if len(bad) > args.list: print(" ... %d more (use --json)" % (len(bad) - args.list)) code = 0 if parse_failures or rep["planFailed"]: code = 1 if args.max_rejected is not None and rep["rejected"] > args.max_rejected: print("FAIL: %d rejected methods exceed --max-rejected %d" % (rep["rejected"], args.max_rejected)) code = 1 return code if __name__ == "__main__": sys.exit(main())