mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-11-09 10:39:41 -06:00
Vijay Janapa Reddi
f1ffe5b6fa
interviews/ held StaffML and nothing else, so the directory now carries the product's name. Three names inside it repeated that prefix, and now line up with vault/, vault-cli/, and paper/: interviews/staffml/ -> staffml/app/ interviews/staffml-vault-worker/ -> staffml/vault-worker/ interviews/staffml-vault-types/ -> staffml/vault-types/ Every repository path moved with it: workflow paths: triggers and variable fallbacks, pre-commit hooks, .gitignore, contributor tooling, vault-cli path joins, the app's tsconfig mapping to the shared types, and the docs. Left alone on purpose: - the published /interviews/ redirect to /staffml/ and the gh-pages subsite lists that protect it; those are URLs, not repository paths - package and worker names (staffml-vault-worker, @staffml/vault-types) and the vitest job name, which branch protection may key on - question YAMLs and generated track JSON, which are content-addressed. Three questions carry an older corruption, "recall @interviews/vault/ questions/...", that predates this change - the applied D1 migration 0001 and the vault CHANGELOG, which are history codegen-hashes.txt is re-recorded; the three pinned artifacts changed only in path strings. vault-cli: 97 passed, codegen --check clean. interviewer.py's __main__ loader was one parent short and pointed at a corpus.json that never existed; it now resolves staffml/app/src/data/ corpus.json. tools/validate_playbook.py and generate_interview_flashcard.py still expect per-track directories that no longer exist; they point at the new root but remain dead. The GitHub repository variables STAFFML_ROOT, VAULT_DIR, and VAULT_CLI_DIR still name the old paths and must change when this reaches origin.
68 lines
2.5 KiB
Python
68 lines
2.5 KiB
Python
#!/usr/bin/env python3
|
|
"""One-shot: normalize chain positions to contiguous [1..N] per chain.
|
|
|
|
The Phase-1 split preserved legacy ``chain_ids[0]`` as each question's chain
|
|
and took ``position + 1`` from the legacy 0-indexed value. Legacy corpus had
|
|
multi-chain membership: a single question could appear in up to 4 chains.
|
|
Our new single-chain schema kept only the first; the other chains are left
|
|
with gaps wherever their other members chose a different chain_ids[0].
|
|
|
|
This script re-numbers each chain's members to [1..N] sorted by their
|
|
current position, closing the gaps. Content-hash of affected questions
|
|
changes; re-run `vault build` afterward and update
|
|
``corpus-equivalence-hash.txt``.
|
|
|
|
Idempotent: running again with all chains already contiguous is a no-op.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from collections import defaultdict
|
|
from pathlib import Path
|
|
|
|
_REPO = Path(__file__).resolve().parents[3]
|
|
sys.path.insert(0, str(_REPO / "staffml" / "vault-cli" / "src"))
|
|
|
|
from vault_cli.loader import load_all # noqa: E402
|
|
from vault_cli.yaml_io import dump_str, load_file # noqa: E402
|
|
|
|
|
|
def main() -> int:
|
|
vault_dir = _REPO / "staffml" / "vault"
|
|
loaded, errors = load_all(vault_dir)
|
|
if errors:
|
|
sys.stderr.write(f"warning: {len(errors)} load errors — skipping those files\n")
|
|
|
|
# Group by chain_id; each entry is (original_position, LoadedQuestion).
|
|
chains: dict[str, list[tuple[int, object]]] = defaultdict(list)
|
|
for lq in loaded:
|
|
if lq.question.chain is not None:
|
|
chains[lq.question.chain.id].append((lq.question.chain.position, lq))
|
|
|
|
rewritten = 0
|
|
for _chain_id, members in chains.items():
|
|
members.sort(key=lambda t: t[0])
|
|
positions = [m[0] for m in members]
|
|
expected = list(range(1, len(members) + 1))
|
|
if positions == expected:
|
|
continue
|
|
|
|
# Rewrite each member's chain.position to its new index.
|
|
for new_pos, (_old_pos, lq) in enumerate(members, start=1):
|
|
# Load raw YAML (preserves untouched fields) then update.
|
|
data = load_file(lq.path)
|
|
if "chain" in data and isinstance(data["chain"], dict):
|
|
if data["chain"].get("position") == new_pos:
|
|
continue
|
|
data["chain"]["position"] = new_pos
|
|
lq.path.write_text(dump_str(data), encoding="utf-8")
|
|
rewritten += 1
|
|
|
|
print(f"normalized: {rewritten} questions rewritten across {len(chains)} chains")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|