"""Measure the pinned OKF corpus against the CURRENT parser. No src/ changes."""
import os, sys, collections
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "src"))
from llm_ingestion_guard import okf

ROOT = os.path.join(os.path.dirname(__file__), "corpus", "okf", "bundles")

def docs():
    out = []
    for dirpath, _dirnames, filenames in os.walk(ROOT):
        for fn in sorted(filenames):
            if not fn.endswith(".md"):
                continue
            if fn in ("index.md", "log.md"):
                continue
            out.append(os.path.join(dirpath, fn))
    return sorted(out)

def main():
    paths = docs()
    ok, fail = [], []
    reasons = collections.Counter()
    for p in paths:
        with open(p, encoding="utf-8") as fh:
            text = fh.read()
        try:
            okf.parse_frontmatter(text)
            ok.append(p)
        except okf.OKFFrontmatterError as exc:
            fail.append((p, str(exc)))
            reasons[str(exc).split(":")[0]] += 1
    print("denominator: %d documents" % len(paths))
    print("parse OK   : %d" % len(ok))
    print("parse FAIL : %d" % len(fail))
    print("--- failure classes ---")
    for r, c in reasons.most_common():
        print("%4d  %s" % (c, r))
    print("--- passing documents (positive control) ---")
    for p in ok:
        print("  " + os.path.relpath(p, ROOT))
    print("--- first 8 failures verbatim ---")
    for p, e in fail[:8]:
        print("  %s\n      %s" % (os.path.relpath(p, ROOT), e))

main()