feat: brain/index.go shebang; mail import is not a brain write (D14). (#12)
Commands live at bin/brain/{index,get,stats,eval,watch}.go and
bin/mail/import.go, bin/markdown/import.go, bin/postgres/query.go.
Python remains the Ladybug write worker. index_mail is a deprecation
shim that rebuilds via --with-mail.
This commit is contained in:
+11
-120
@@ -1,135 +1,26 @@
|
||||
#!/usr/bin/env python3
|
||||
"""mail/index_mail - rebuild the brain with every markdown under var/mail.
|
||||
"""mail/index_mail — deprecated. Use bin/brain/index.go --rebuild --with-mail.
|
||||
|
||||
Ladybug corrupts its WAL when brand-new leafs are bulk-inserted while the
|
||||
FTS/VECTOR indexes already exist, so indexing ALWAYS runs as a fresh rebuild
|
||||
(repo corpus + var/mail), matching the proven-safe `kb/index --rebuild` path.
|
||||
Conversion and indexing stay separate: conversion can crash in native docling
|
||||
and must not leave the brain DB mid-transaction.
|
||||
|
||||
bin/mail/index_mail rebuild the index incl. all mail
|
||||
bin/mail/index_mail --dry-run count without writing
|
||||
bin/mail/index_mail --limit N cap messages included
|
||||
bin/mail/index_mail --since D only messages dated >= D (YYYY-MM-DD)
|
||||
Ladybug corrupts its WAL on bulk-insert into an already-indexed DB, so this
|
||||
shim always rebuilds (repo corpus + var/mail). Conversion stays in mail/import.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[2]
|
||||
sys.path.insert(0, str(ROOT / "bin" / "tools"))
|
||||
|
||||
from kblib import DB_PATH, VAR, connect, ensure_indexes, init_schema, stats, upsert_leaf # noqa: E402
|
||||
from mdleaves import read_markdown, to_all, walk_markdown # noqa: E402
|
||||
|
||||
|
||||
def msg_date(md: Path) -> str:
|
||||
j = md.parent / "message.json"
|
||||
try:
|
||||
d = json.loads(j.read_text(encoding="utf-8"))
|
||||
return (d.get("receivedDate") or d.get("receivedAt") or "")[:10]
|
||||
except Exception:
|
||||
return ""
|
||||
|
||||
|
||||
def mail_leafs(limit: int, since: str, repo: str = "ooMail") -> list[dict]:
|
||||
root = ROOT / "var" / "mail"
|
||||
mds = sorted(root.rglob("message.md"))
|
||||
if since:
|
||||
mds = [m for m in mds if msg_date(m) >= since]
|
||||
if limit:
|
||||
mds = mds[:limit]
|
||||
leafs: list[dict] = []
|
||||
for md in mds:
|
||||
files = [md] + sorted((md.parent / "attachments").glob("*.md"))
|
||||
for f in files:
|
||||
if not f.exists():
|
||||
continue
|
||||
for lf in to_all(read_markdown(f), f, repo=repo):
|
||||
lf["source"] = f"ooMail:{md.parent.name}:{f.name}"
|
||||
lf["how"] = "mail/import"
|
||||
leafs.append(lf)
|
||||
return leafs
|
||||
|
||||
|
||||
def main(argv: list[str]) -> int:
|
||||
p = argparse.ArgumentParser(description="rebuild the brain incl. all mail")
|
||||
p.add_argument("--dry-run", action="store_true", help="count only, write nothing")
|
||||
p.add_argument("--limit", type=int, default=0, help="cap messages included")
|
||||
p.add_argument("--since", default="", help="only messages dated >= YYYY-MM-DD")
|
||||
p.add_argument("--json", action="store_true")
|
||||
a = p.parse_args(argv)
|
||||
|
||||
mail = mail_leafs(a.limit, a.since)
|
||||
if a.dry_run:
|
||||
print(f"mail/index_mail: {len(mail)} mail leafs would be indexed")
|
||||
return 0
|
||||
|
||||
# Fresh rebuild: delete DB, index repo corpus + mail, create indexes once
|
||||
# at the end. Never insert into an already-indexed DB (WAL corruption).
|
||||
VAR.mkdir(exist_ok=True)
|
||||
if DB_PATH.exists():
|
||||
DB_PATH.unlink()
|
||||
|
||||
corpus = _load_corpus()
|
||||
leafs = corpus + mail
|
||||
|
||||
db, conn = connect(DB_PATH, read_only=False)
|
||||
init_schema(conn)
|
||||
embed = _embedder()
|
||||
done, total = _index_leafs(conn, leafs, embed)
|
||||
ensure_indexes(conn)
|
||||
s = stats(conn)
|
||||
conn.close()
|
||||
db.close()
|
||||
|
||||
result = {"indexed": done, "corpus_total": total, "mail_leafs": len(mail),
|
||||
**{k: v for k, v in s.items() if k in ("total", "by_root")}}
|
||||
print(json.dumps(result, indent=2) if a.json else
|
||||
f"mail/index_mail: indexed {done}/{total} leafs (mail={len(mail)}); db total {s['total']}")
|
||||
return 0
|
||||
|
||||
|
||||
CORPUS_DEFAULTS = ["README.md", "PLAN.md", "AGENTS.md", "docs", "skills"]
|
||||
|
||||
|
||||
def _load_corpus() -> list[dict]:
|
||||
files: list[Path] = []
|
||||
for entry in CORPUS_DEFAULTS:
|
||||
p = ROOT / entry
|
||||
if p.is_file():
|
||||
files.append(p)
|
||||
elif p.is_dir():
|
||||
files.extend(walk_markdown(p))
|
||||
leafs: list[dict] = []
|
||||
for path in files:
|
||||
try:
|
||||
leafs.extend(to_all(read_markdown(path), path, repo="eSlider/2dph"))
|
||||
except OSError as e:
|
||||
print(f"mail/index_mail: skip {path}: {e}", file=sys.stderr)
|
||||
return leafs
|
||||
|
||||
|
||||
def _index_leafs(conn, leafs: list[dict], embed_fn) -> tuple[int, int]:
|
||||
count = 0
|
||||
for lf in leafs:
|
||||
query = f"{lf['heading']}\n\n{lf['text']}"
|
||||
emb = embed_fn(lf["text"]) if lf["text"] else None
|
||||
upsert_leaf(conn, text=query, root="info", confidence="confirmed",
|
||||
source=lf["source"], source_rev="mail" if lf.get("how") == "mail/import" else "working-tree",
|
||||
how=lf.get("how", "kb/index"), loc=lf["source"], type_=lf.get("type", "reference"),
|
||||
embedding=emb)
|
||||
count += 1
|
||||
return count, len(leafs)
|
||||
|
||||
|
||||
def _embedder():
|
||||
from model2vec import StaticModel
|
||||
model = StaticModel.from_pretrained("minishlab/potion-multilingual-128M")
|
||||
return lambda text: model.encode([text])[0].astype(float).tolist()
|
||||
print(
|
||||
"bin/mail/index_mail is deprecated; use bin/brain/index.go --rebuild --with-mail",
|
||||
file=sys.stderr,
|
||||
)
|
||||
index = ROOT / "bin" / "kb" / "index"
|
||||
os.execv(sys.executable, [sys.executable, str(index), "--rebuild", "--with-mail", *argv])
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user