Hugo 删文后旧页面还在：用 Python 对比全新构建与残留 HTML

hugo version
python3 --version
mkdir hugo-stale-demo
cd hugo-stale-demo
mkdir -p content layouts/_default static
cat > hugo.toml <<'TOML'
baseURL = 'https://example.org/'
title = 'Stale output demo'
disableKinds = ['taxonomy', 'term', 'RSS', 'sitemap']
TOML
cat > layouts/_default/single.html <<'HTML'
<!doctype html><html><head><title>{{ .Title }}</title></head>
<body><h1>{{ .Title }}</h1>{{ .Content }}</body></html>
HTML
cat > layouts/_default/list.html <<'HTML'
<!doctype html><html><head><title>{{ .Title }}</title></head>
<body>{{ range .Pages }}<a href="{{ .RelPermalink }}">{{ .Title }}</a>{{ end }}</body></html>
HTML
cat > content/old.md <<'MARKDOWN'
+++
title = 'Old page'
+++
Only a disposable demo page.
MARKDOWN

hugo --quiet --destination out-existing
test -f out-existing/old/index.html
python3 - <<'PY_DELETE'
from pathlib import Path
Path("content/old.md").unlink()
PY_DELETE
hugo --quiet --destination out-existing
test -f out-existing/old/index.html && printf 'STALE: old/index.html\n'

python3 - <<'PY_COPY'
import shutil
shutil.copytree("out-existing", "out-cleaned")
PY_COPY
hugo --quiet --cleanDestinationDir --destination out-cleaned
test ! -f out-cleaned/old/index.html && printf 'CLEAN: old/index.html absent\n'

"""Compare HTML path inventories, without modifying either tree. Python 3.10+."""
import argparse
import json
import os
from pathlib import Path
import stat
import sys


def scan_error(error):
    raise error


def html_paths(root):
    result = set()
    for folder, dirs, files in os.walk(root, onerror=scan_error, followlinks=False):
        for name in dirs + files:
            if (Path(folder) / name).is_symlink():
                raise ValueError(f"symbolic link not allowed: {Path(folder) / name}")
        for name in files:
            path = Path(folder) / name
            if path.suffix.lower() != ".html":
                continue
            if not stat.S_ISREG(path.stat().st_mode):
                raise ValueError(f"not a regular HTML file: {path}")
            result.add(path.relative_to(root).as_posix())
    return result


def directory(value):
    path = Path(value)
    if path.is_symlink():
        raise ValueError(f"symbolic link not allowed: {path}")
    path = path.resolve(strict=True)
    if not path.is_dir():
        raise ValueError(f"not a directory: {path}")
    return path


def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--existing", required=True)
    parser.add_argument("--fresh", required=True)
    args = parser.parse_args()
    try:
        existing = directory(args.existing)
        fresh = directory(args.fresh)
        if existing == fresh or existing in fresh.parents or fresh in existing.parents:
            raise ValueError("directories must be separate and non-nested")
        old_paths, new_paths = html_paths(existing), html_paths(fresh)
        if not new_paths:
            raise ValueError("fresh build has no HTML files")
        extra = sorted(old_paths - new_paths)
        missing = sorted(new_paths - old_paths)
        print(json.dumps({"extra_html": extra, "missing_html": missing},
                         ensure_ascii=True, sort_keys=True))
        return 1 if extra or missing else 0
    except (OSError, ValueError) as error:
        print(f"ERROR: {error}", file=sys.stderr)
        return 2


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

python3 audit_output.py --help
if python3 audit_output.py --existing out-existing --fresh out-cleaned; then
    status=0
else
    status=$?
fi
printf 'exit=%s\n' "$status"

{"extra_html": ["old/index.html"], "missing_html": []}
exit=1

"""Build into a fresh temporary directory, then audit an existing output."""
import argparse
from pathlib import Path
import subprocess
import sys
from tempfile import TemporaryDirectory

parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--existing", default="public")
parser.add_argument("--config", default="hugo.toml")
args = parser.parse_args()

workspace = Path("/tmp/codex-work")
workspace.mkdir(parents=True, exist_ok=True)
with TemporaryDirectory(prefix="hugo-output-", dir=workspace) as temporary:
    preview = Path(temporary) / "site"
    subprocess.run(
        ["hugo", "--quiet", "--config", args.config,
         "--destination", str(preview)],
        check=True, timeout=120,
    )
    result = subprocess.run(
        [sys.executable, "audit_output.py", "--existing", args.existing,
         "--fresh", str(preview)],
        check=False, timeout=120,
    )
    raise SystemExit(result.returncode)

python3 preview_check.py --existing out-cleaned
if python3 preview_check.py --existing out-existing; then
    status=0
else
    status=$?
fi
printf 'exit=%s\n' "$status"