pyr0ball
aa80f307fe
Renames the app/ingest/ package to app/glean/ and updates all references across Python modules, shell scripts, Vue components, tests, and documentation. Intentionally preserved: - SQLite column name ingest_time (avoids schema migration) - RetrievedEntry.ingest_time field (maps to the column above) - Any public-facing JSON keys that reference ingest_time Changes by category: - app/ingest/ → app/glean/ (full package move, all parsers) - app/tasks/ingest_scheduler.py → app/tasks/glean_scheduler.py - scripts/ingest_corpus.py → scripts/glean_corpus.py - tests/test_ingest_*.py → tests/test_glean_*.py - Docstrings, log messages, comments: ingest → glean - Env var: TURNSTONE_INGEST_INTERVAL → TURNSTONE_GLEAN_INTERVAL - Shell scripts: glean.log, glean_corpus.py references - README.md: multi-source ingest → multi-source glean - .env.example: updated env var name - patterns/: new diagnostic patterns from 2026-05-20 SSH incident (service_crash_loop, pkg_daemon_restart, ssh_forward_conflict) - SourcesView.vue: pipeline label updated - All test import paths updated to app.glean.* 285 tests passing.
43 lines
1.3 KiB
Python
43 lines
1.3 KiB
Python
"""Upload adapter: processes file bytes and writes to context store — MIT licensed."""
|
|
from __future__ import annotations
|
|
|
|
import sqlite3
|
|
import uuid
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
from app.context.chunker import process_upload
|
|
from app.context.store import add_document, add_fact
|
|
|
|
|
|
def glean_upload(db_path: Path, filename: str, content: bytes) -> dict[str, Any]:
|
|
"""Process an uploaded file and write to context store. Returns result summary."""
|
|
doc_type, facts, chunks = process_upload(filename, content)
|
|
|
|
doc = add_document(
|
|
db_path,
|
|
filename=filename,
|
|
doc_type=doc_type,
|
|
full_text=content.decode("utf-8", errors="replace"),
|
|
file_size=len(content),
|
|
)
|
|
|
|
for fact in facts:
|
|
add_fact(db_path, fact.category, fact.key, fact.value, source="upload")
|
|
|
|
conn = sqlite3.connect(str(db_path))
|
|
conn.execute("PRAGMA journal_mode=WAL")
|
|
for i, chunk_text in enumerate(chunks):
|
|
conn.execute(
|
|
"INSERT INTO context_chunks(id, document_id, chunk_index, text) VALUES (?,?,?,?)",
|
|
(str(uuid.uuid4()), doc.id, i, chunk_text),
|
|
)
|
|
conn.commit()
|
|
conn.close()
|
|
|
|
return {
|
|
"document_id": doc.id,
|
|
"doc_type": doc_type,
|
|
"facts_written": len(facts),
|
|
"chunks_written": len(chunks),
|
|
}
|