170 lines
6.3 KiB
Python
170 lines
6.3 KiB
Python
"""FU-1: unified ingest pipeline tests (offline, all I/O monkeypatched).
|
|
|
|
Proves both intake types flow through services.ingest.ingest_document and that
|
|
the canonical pipeline is symmetric: BOTH metadata and halacha extraction are
|
|
queued for BOTH types (GAP-02 regression), enum validation applies to both
|
|
(GAP-04), multimodal is gated by flag+PDF not by intake type (GAP-05), and the
|
|
external citation guard is preserved.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
from pathlib import Path
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
|
|
from legal_mcp import config
|
|
from legal_mcp.services import db, embeddings, chunker, extractor
|
|
from legal_mcp.services import ingest, precedent_library, internal_decisions
|
|
|
|
|
|
def _run(coro):
|
|
return asyncio.run(coro)
|
|
|
|
|
|
class _Chunk:
|
|
def __init__(self, i):
|
|
self.chunk_index = i
|
|
self.content = f"chunk-{i}"
|
|
self.section_type = "body"
|
|
self.page_number = 1
|
|
self.role = "child"
|
|
self.local_id = f"c{i}"
|
|
self.parent_local_id = None
|
|
|
|
|
|
@pytest.fixture()
|
|
def patched(monkeypatch, tmp_path):
|
|
"""Patch every I/O boundary. Record queue + create calls."""
|
|
calls = {"metadata": [], "halacha": [], "create": [], "chunks": [], "pages": []}
|
|
|
|
async def _extract_text(path):
|
|
return ("full decision text", 2, [0, 100])
|
|
|
|
def _strip(text):
|
|
return text
|
|
|
|
def _chunk(text, page_offsets=None):
|
|
return [_Chunk(0), _Chunk(1)]
|
|
|
|
async def _embed(texts, input_type="document"):
|
|
return [[0.0] * 8 for _ in texts]
|
|
|
|
async def _store_chunks(cid, dicts):
|
|
calls["chunks"].append((cid, len(dicts)))
|
|
return len(dicts)
|
|
|
|
async def _create_external(**kw):
|
|
calls["create"].append(("external", kw))
|
|
return {"id": uuid4()}
|
|
|
|
async def _create_internal(**kw):
|
|
calls["create"].append(("internal", kw))
|
|
return {"id": uuid4()}
|
|
|
|
async def _req_meta(cid):
|
|
calls["metadata"].append(cid)
|
|
|
|
async def _req_hal(cid):
|
|
calls["halacha"].append(cid)
|
|
|
|
async def _set_status(cid, status):
|
|
return None
|
|
|
|
monkeypatch.setattr(extractor, "extract_text", _extract_text)
|
|
monkeypatch.setattr(extractor, "strip_nevo_preamble", _strip)
|
|
monkeypatch.setattr(chunker, "chunk_document", _chunk)
|
|
monkeypatch.setattr(embeddings, "embed_texts", _embed)
|
|
monkeypatch.setattr(db, "store_precedent_chunks", _store_chunks)
|
|
monkeypatch.setattr(db, "create_external_case_law", _create_external)
|
|
monkeypatch.setattr(db, "create_internal_committee_decision", _create_internal)
|
|
monkeypatch.setattr(db, "request_metadata_extraction", _req_meta)
|
|
monkeypatch.setattr(db, "request_halacha_extraction", _req_hal)
|
|
monkeypatch.setattr(db, "set_case_law_extraction_status", _set_status)
|
|
monkeypatch.setattr(db, "set_case_law_halacha_status", _set_status)
|
|
# Force flat chunking + multimodal OFF unless a test flips it.
|
|
monkeypatch.setattr(config, "PARENT_DOC_RETRIEVAL_ENABLED", False)
|
|
monkeypatch.setattr(config, "MULTIMODAL_ENABLED", False)
|
|
return calls
|
|
|
|
|
|
def _make_pdf(tmp_path) -> str:
|
|
p = tmp_path / "decision.pdf"
|
|
p.write_bytes(b"%PDF-1.4 fake")
|
|
return str(p)
|
|
|
|
|
|
def test_internal_queues_BOTH_metadata_and_halacha(patched, tmp_path):
|
|
"""GAP-02 regression: the internal path must queue metadata too."""
|
|
_run(internal_decisions.ingest_internal_decision(
|
|
case_number="8046/24", text="decision text", chair_name="דפנה תמיר",
|
|
district="ירושלים", practice_area="betterment_levy",
|
|
))
|
|
assert len(patched["metadata"]) == 1, "internal path must queue metadata (GAP-02)"
|
|
assert len(patched["halacha"]) == 1
|
|
|
|
|
|
def test_external_queues_both(patched, tmp_path):
|
|
_run(precedent_library.ingest_precedent(
|
|
file_path=_make_pdf(tmp_path), citation="עע\"מ 1234/20",
|
|
practice_area="rishuy_uvniya", source_type="court_ruling",
|
|
))
|
|
assert len(patched["metadata"]) == 1
|
|
assert len(patched["halacha"]) == 1
|
|
|
|
|
|
def test_both_types_go_through_ingest_document(patched, tmp_path, monkeypatch):
|
|
seen = []
|
|
real = ingest.ingest_document
|
|
|
|
async def _spy(spec, **kw):
|
|
seen.append(spec.source_kind)
|
|
return await real(spec, **kw)
|
|
|
|
monkeypatch.setattr(ingest, "ingest_document", _spy)
|
|
_run(internal_decisions.ingest_internal_decision(
|
|
case_number="8046/24", text="t", chair_name="דפנה תמיר", practice_area="betterment_levy"))
|
|
_run(precedent_library.ingest_precedent(
|
|
file_path=_make_pdf(tmp_path), citation="עע\"מ 1/20", practice_area="rishuy_uvniya"))
|
|
assert seen == ["internal_committee", "external_upload"]
|
|
|
|
|
|
def test_enum_validation_rejects_bad_practice_area_internal(patched, tmp_path):
|
|
"""GAP-04: internal path must validate enums like the external one."""
|
|
with pytest.raises(ValueError, match="practice_area"):
|
|
_run(internal_decisions.ingest_internal_decision(
|
|
case_number="8046/24", text="t", chair_name="x", practice_area="bogus"))
|
|
|
|
|
|
def test_enum_validation_rejects_bad_practice_area_external(patched, tmp_path):
|
|
with pytest.raises(ValueError, match="practice_area"):
|
|
_run(precedent_library.ingest_precedent(
|
|
file_path=_make_pdf(tmp_path), citation="עע\"מ 1/20", practice_area="bogus"))
|
|
|
|
|
|
def test_external_citation_guard_still_blocks_arar(patched, tmp_path):
|
|
with pytest.raises(ValueError, match="ערר"):
|
|
_run(precedent_library.ingest_precedent(
|
|
file_path=_make_pdf(tmp_path), citation="ערר 1234/24"))
|
|
|
|
|
|
def test_internal_text_path_works_without_file(patched):
|
|
out = _run(internal_decisions.ingest_internal_decision(
|
|
case_number="8046/24", text="t", chair_name="x", practice_area="betterment_levy"))
|
|
assert out["status"] == "completed"
|
|
assert out["case_law_id"]
|
|
|
|
|
|
def test_internal_requires_file_or_text(patched):
|
|
with pytest.raises(ValueError, match="file_path or text"):
|
|
_run(internal_decisions.ingest_internal_decision(
|
|
case_number="8046/24", chair_name="x", practice_area="betterment_levy"))
|
|
|
|
|
|
def test_display_name_fallback_uses_canonical_id(patched, tmp_path):
|
|
_run(internal_decisions.ingest_internal_decision(
|
|
case_number="8046/24", text="t", chair_name="x", practice_area="betterment_levy"))
|
|
kind, kw = patched["create"][0]
|
|
assert kw["case_name"] == "8046/24", "missing case_name falls back to canonical id"
|