#!/usr/bin/env python3
"""Exports nothing imports, and assets nothing renders.

## Why

Dead code is not merely clutter. It is read, maintained, and trusted: somebody
eventually changes it, and nothing happens. On the repository this was written
against, two issues had already been filed by hand for exactly this — four
progress components exported and imported nowhere, and a 1.1 MB image shipping
in every container while being rendered by nothing. Both are the kind of thing a
person finds by accident and a script finds every time.

## What it checks

**Exports.** A symbol exported from a module and referenced nowhere but its own
declaration. Framework entry points are excluded by name, because a Next.js
`page.tsx` exporting `metadata` or a route exporting `GET` is *called by the
framework* and referencing it would be wrong.

**Assets.** A file under the asset roots whose name appears in no source file.

## Tuned for near-silence

`GUARDS.md` rule 5: a check that is wrong six times in ten is one people learn
to skip. So the reference scan covers **tests as well as source** — the first
draft of this scanned only `src/` and reported every test-only helper as dead,
which is the mistake that makes a tool untrustworthy on its first run.

It still cannot see a symbol referenced only by string name, by a build step, or
from outside the repository. Treat findings as candidates, and delete only what
you have confirmed.

    python3 scripts/dead-code.py
    python3 scripts/dead-code.py --src src --refs src tests --assets public
    python3 scripts/dead-code.py --exports-only

Exit codes: 0 nothing found. 1 candidates found. 2 nothing was scanned.
"""

from __future__ import annotations

import argparse
import os
import re
import sys
from collections import Counter

SKIP_DIRS = {"node_modules", ".next", ".git", "dist", "build", "__pycache__"}
CODE_EXTS = (".ts", ".tsx", ".js", ".jsx", ".mjs")

# An asset is referenced from prose and configuration as often as from code — a
# README embeds a screenshot, a manifest names an icon, a stylesheet loads a
# font. Scanning only code reported twelve screenshots as dead when the README
# renders every one of them, which is exactly the first-run noise that ends a
# tool's credibility.
PROSE_EXTS = CODE_EXTS + (".md", ".mdx", ".json", ".yml", ".yaml", ".html", ".css", ".webmanifest")

EXPORT = re.compile(
    r"^export\s+(?:async\s+)?(?:function|const|let|class|type|interface|enum)\s+(\w+)"
)

# `export default function FaqPage()` is called by the framework, and the name
# is incidental — it exists so a stack trace reads well. Matching it reported
# every page and layout in the application as dead, which is the kind of first
# run that ends a tool's credibility.
DEFAULT_EXPORT = re.compile(r"^export\s+default\b")

# Called by the framework, never imported. Reporting these would be worse than
# reporting nothing: it teaches the reader that the tool does not understand the
# project, and everything after it gets skipped too.
FRAMEWORK = {
    "default", "metadata", "generateMetadata", "generateStaticParams",
    "dynamic", "revalidate", "runtime", "fetchCache", "preferredRegion",
    "maxDuration", "viewport", "GET", "POST", "PUT", "PATCH", "DELETE",
    "HEAD", "OPTIONS", "middleware", "config", "loader", "action",
}


def walk(roots: list[str], exts: tuple[str, ...]) -> list[str]:
    found: list[str] = []

    for root in roots:
        if os.path.isfile(root):
            found.append(root)
            continue

        for base, dirs, names in os.walk(root):
            dirs[:] = [d for d in dirs if d not in SKIP_DIRS]
            found.extend(
                os.path.join(base, n) for n in names if not exts or n.endswith(exts)
            )

    return found


def main() -> int:
    parser = argparse.ArgumentParser(description=__doc__.split("\n")[0])
    parser.add_argument("--src", nargs="+", default=["src"], help="where exports live")
    parser.add_argument(
        "--refs", nargs="+", default=["src", "tests", "app", "scripts", "notices"],
        help="where references may appear — include tests, or every helper reads as dead",
    )
    parser.add_argument("--assets", nargs="+", default=["public"], help="asset roots")
    parser.add_argument("--exports-only", action="store_true")
    parser.add_argument("--assets-only", action="store_true")
    args = parser.parse_args()

    sources = walk(args.src, CODE_EXTS)
    references = walk([r for r in args.refs if os.path.exists(r)], CODE_EXTS)

    if not sources and not args.assets_only:
        print("dead-code: nothing to scan.", file=sys.stderr)
        return 2

    # One pass over every referencing file, counting every identifier and
    # remembering the raw text for asset lookups.
    counts: Counter[str] = Counter()
    corpus: list[str] = []

    for path in references:
        try:
            with open(path, encoding="utf8", errors="ignore") as handle:
                body = handle.read()
        except OSError:
            continue

        corpus.append(body)
        counts.update(re.findall(r"\b\w+\b", body))

    findings = 0

    if not args.assets_only:
        exported: dict[str, str] = {}

        for path in sources:
            try:
                with open(path, encoding="utf8", errors="ignore") as handle:
                    for line in handle:
                        if DEFAULT_EXPORT.match(line):
                            continue

                        match = EXPORT.match(line)

                        if match and match.group(1) not in FRAMEWORK:
                            exported.setdefault(match.group(1), path)
            except OSError:
                continue

        # Exactly one occurrence is the declaration itself and nothing else.
        dead = sorted((name, path) for name, path in exported.items() if counts[name] <= 1)

        if dead:
            print("exported and referenced nowhere:")

            for name, path in dead:
                print(f"  {name:<32} {path}")

            findings += len(dead)

    if not args.exports_only:
        # A wider net than the export scan uses, for the reason above.
        asset_refs = walk([r for r in args.refs if os.path.exists(r)], PROSE_EXTS)
        asset_refs += [p for p in walk(["."], (".md",)) if p.count(os.sep) <= 1]

        text = "\n".join(corpus)

        for path in set(asset_refs):
            try:
                with open(path, encoding="utf8", errors="ignore") as handle:
                    text += "\n" + handle.read()
            except OSError:
                continue

        assets = walk([a for a in args.assets if os.path.exists(a)], ())
        orphans = []

        for path in assets:
            name = os.path.basename(path)

            # By basename and by path — a reference is written either way, and
            # missing one direction is how a false positive gets in.
            if name in text or path in text or path.split(os.sep, 1)[-1] in text:
                continue

            try:
                size = os.path.getsize(path)
            except OSError:
                size = 0

            orphans.append((size, path))

        if orphans:
            print("\nasset files nothing references:" if findings else "asset files nothing references:")

            for size, path in sorted(orphans, reverse=True):
                print(f"  {size / 1024:9.1f} KB  {path}")

            findings += len(orphans)

    if not findings:
        print(
            f"dead-code: nothing unreferenced across {len(sources)} source "
            f"and {len(references)} referencing file(s).",
            file=sys.stderr,
        )
        return 0

    print(
        f"\ndead-code: {findings} candidate(s). A symbol referenced only by "
        "string name, or from outside this repository, will appear here and is "
        "not dead — confirm before deleting.",
        file=sys.stderr,
    )

    return 1


if __name__ == "__main__":
    raise SystemExit(main())