ca66d31f0a
Adds documents-ingest-paperless: paginated GET /api/documents/, maps each doc to a source='paperless' envelope per plan §4.2-4.3, reusing kb_mail.Envelope/insert_envelope unchanged (packages/kb-mail not touched). Cross-source link (source_mail entity) is a deterministic join of original_file_name against the phase-1 registry.json consume_name index — no heuristics, no correspondent guessing (plan decision 4). Stats always balance (fetched = already_in_db + inserted + errors) and main() now also exits non-zero on imbalance, not just on errors>0, matching the exit-code convention already established in gmail-bulk-import. Verified live on PIHA (rsync to /tmp, ~/kb/venv, PIHA checkout untouched): dry-run then --apply inserted 186/186 paperless envelopes (0 errors, 180 source_mail links), a second --apply reported inserted=0/already_in_db=186 (idempotent), gmail rows stayed at 225030 and document_chunk stayed empty. Rotated the kb-ingest Paperless API token after it was accidentally partially echoed during recon (old token now dead). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
26 lines
528 B
TOML
26 lines
528 B
TOML
[build-system]
|
|
requires = ["setuptools>=68"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "documents-ingest"
|
|
version = "0.1.0"
|
|
requires-python = ">=3.11"
|
|
dependencies = [
|
|
"asyncpg>=0.29",
|
|
"structlog>=24.1",
|
|
"aiohttp>=3.9",
|
|
"kb-mail",
|
|
]
|
|
|
|
[project.scripts]
|
|
documents-ingest = "documents_ingest.extractor:main"
|
|
documents-ingest-paperless = "documents_ingest.paperless_adapter:main"
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["src"]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
testpaths = ["tests"]
|