# -*- coding: utf-8 -*-
"""REUSE.md refs check — staleness defense for the per-repo reuse maps.

Usage:  python scripts/reuse_refs_check.py <repo-root> [<repo-root> ...]

For each repo root given, parses <root>/REUSE.md, extracts every cited file path
(*.go, *.py, *.html, *.css, *.yml, *.yaml, *.sh) and verifies the file exists in
the tree. Only slash-containing (repo-relative) tokens are checked — bare filenames
are conventions, not citations. Prints offending lines; exits non-zero if any cited
path is missing. Symbols are NOT checked here — those are spot-verified by the
reviewer at file:line.
"""
import io, os, re, sys

# path-looking tokens ending in a checked extension; globs (*) are conventions, not refs
PATH_RE = re.compile(r'[A-Za-z0-9_][A-Za-z0-9_./\-]*/[A-Za-z0-9_./\-]*\.(?:go|py|html|css|yml|yaml|sh)\b')

fails = 0


def check_repo(root):
    global fails
    root = os.path.abspath(root)
    reuse = os.path.join(root, "REUSE.md")
    name = os.path.basename(root)
    if not os.path.isfile(reuse):
        print("FAIL [%s]: no REUSE.md at %s" % (name, reuse))
        fails += 1
        return
    seen, missing = set(), 0
    with io.open(reuse, encoding="utf-8") as f:
        for lineno, line in enumerate(f, 1):
            for m in PATH_RE.finditer(line):
                p = m.group(0)
                if "*" in line[max(0, m.start() - 2):m.end() + 2]:
                    continue  # glob like scripts/*.py — a convention, not a file ref
                if p in seen:
                    continue
                seen.add(p)
                if not os.path.isfile(os.path.join(root, p)):
                    print("FAIL [%s] line %d: cited path missing: %s" % (name, lineno, p))
                    missing += 1
    if missing:
        fails += missing
    else:
        print("OK   [%s]: %d cited paths, all exist" % (name, len(seen)))


if len(sys.argv) < 2:
    print(__doc__)
    sys.exit(2)
for r in sys.argv[1:]:
    check_repo(r)
sys.exit(1 if fails else 0)