51 lines
2.6 KiB
Python
51 lines
2.6 KiB
Python
"""One-time export from an explicit historical Git revision, never a runtime seed."""
|
|
import argparse
|
|
import json
|
|
import os
|
|
from pathlib import Path
|
|
import re
|
|
import subprocess
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
BASELINE = 'cffca6942b1bc0005321e1685f38593fb0b853d5' # Integration snapshot before database migration.
|
|
RESEARCH_REVISION = '74af205b2959e1bb6a1fe9f567bc87069ac6d12c' # Final PR 14 update received during integration.
|
|
|
|
|
|
def export(ref):
|
|
commit = subprocess.check_output(['git', 'rev-parse', '--verify', ref + '^{commit}'], cwd=ROOT, text=True).strip()
|
|
|
|
def read(name, revision=commit):
|
|
return subprocess.check_output(['git', 'show', f'{revision}:{name}'], cwd=ROOT).decode()
|
|
|
|
catalog = json.loads(read('content/catalog.json'))
|
|
names = subprocess.check_output(['git', 'ls-tree', '-r', '--name-only', commit, '--', 'content/docs'], cwd=ROOT, text=True).splitlines()
|
|
documents = []
|
|
for name in sorted(n for n in names if n.endswith('.md')):
|
|
source = name.removeprefix('content/docs/').removesuffix('.md')
|
|
metadata = catalog['documents'][source]
|
|
collection = next(c for c in catalog['collections'] if not c['path'] or source.startswith(c['path'] + '/'))
|
|
revision = RESEARCH_REVISION if commit == BASELINE and source.startswith("ai-company-research/") else commit
|
|
content = read(name, revision)
|
|
title = re.search(r'^# (.+)$', content, re.M)
|
|
documents.append(dict(slug=metadata['slug'], sourceSlug=source, category=metadata['category'],
|
|
title=title[1].strip() if title else source, content=content,
|
|
group=metadata.get('group', collection['title']), collection=metadata.get('collection', collection['title']),
|
|
description=metadata.get('description', collection['description']),
|
|
draft=metadata.get('draft', False), featured=metadata.get('featured', False), revision=1))
|
|
if not documents:
|
|
raise ValueError('Refusing empty migration')
|
|
return dict(format='tabularium-documents-v1', documents=documents)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser(description=__doc__)
|
|
parser.add_argument('--ref', default=BASELINE)
|
|
parser.add_argument('--output', type=Path, required=True)
|
|
args = parser.parse_args()
|
|
payload = export(args.ref)
|
|
args.output.parent.mkdir(parents=True, exist_ok=True)
|
|
descriptor = os.open(args.output, os.O_WRONLY | os.O_CREAT | os.O_EXCL, 0o600)
|
|
with os.fdopen(descriptor, 'w') as output:
|
|
json.dump(payload, output, ensure_ascii=False)
|
|
print(f"Exported {len(payload['documents'])} documents; source is immutable Git history")
|