mirror of
https://github.com/semantica-agi/semantica.git
synced 2026-08-30 04:40:16 +00:00
KaifAhmad1
6391dcdf72
- Implemented provenance tracking across all 17 Semantica modules - Added W3C PROV-O compliant schemas (prov:Entity, prov:Activity, prov:Agent, prov:wasDerivedFrom) - Created ProvenanceManager with InMemory and SQLite storage backends - Implemented SHA-256 integrity verification for tamper detection - Added bridge axiom support for domain transformations (L1→L2→L3) - Created provenance-enabled versions of all modules (opt-in with provenance=True) - Added comprehensive test suite (237 tests covering edge cases and real scenarios) - Updated README with accurate claims and compliance disclaimers - Added complete documentation (usage guide and API reference) - Zero breaking changes - fully backward compatible
157 lines
4.6 KiB
Python
157 lines
4.6 KiB
Python
"""
|
|
Test Unified Provenance Manager
|
|
|
|
Tests for ProvenanceManager functionality including entity tracking,
|
|
chunk tracking, source tracking, and lineage tracing.
|
|
"""
|
|
|
|
import pytest
|
|
from semantica.provenance import ProvenanceManager, SourceReference
|
|
|
|
|
|
class TestProvenanceManager:
|
|
"""Test ProvenanceManager functionality."""
|
|
|
|
def test_initialization(self):
|
|
"""Test manager initialization."""
|
|
prov_mgr = ProvenanceManager()
|
|
|
|
assert prov_mgr is not None
|
|
assert prov_mgr.storage is not None
|
|
|
|
def test_track_entity(self):
|
|
"""Test tracking entity provenance."""
|
|
prov_mgr = ProvenanceManager()
|
|
|
|
entry = prov_mgr.track_entity(
|
|
entity_id="entity_1",
|
|
source="doc_1",
|
|
metadata={"confidence": 0.9}
|
|
)
|
|
|
|
assert entry is not None
|
|
assert entry.entity_id == "entity_1"
|
|
assert entry.source_document == "doc_1"
|
|
assert entry.checksum is not None
|
|
|
|
def test_track_relationship(self):
|
|
"""Test tracking relationship provenance."""
|
|
prov_mgr = ProvenanceManager()
|
|
|
|
entry = prov_mgr.track_relationship(
|
|
relationship_id="rel_1",
|
|
source="doc_1",
|
|
metadata={"type": "founded"}
|
|
)
|
|
|
|
assert entry is not None
|
|
assert entry.entity_id == "rel_1"
|
|
assert entry.entity_type == "relationship"
|
|
|
|
def test_track_chunk(self):
|
|
"""Test tracking chunk provenance."""
|
|
prov_mgr = ProvenanceManager()
|
|
|
|
entry = prov_mgr.track_chunk(
|
|
chunk_id="chunk_1",
|
|
source_document="doc_1",
|
|
source_path="/path/to/doc.pdf",
|
|
start_index=0,
|
|
end_index=500
|
|
)
|
|
|
|
assert entry is not None
|
|
assert entry.entity_id == "chunk_1"
|
|
assert entry.entity_type == "chunk"
|
|
assert entry.start_index == 0
|
|
assert entry.end_index == 500
|
|
|
|
def test_track_property_source(self):
|
|
"""Test tracking property source."""
|
|
prov_mgr = ProvenanceManager()
|
|
|
|
source = SourceReference(
|
|
document="DOI:10.1038/...",
|
|
page=4,
|
|
confidence=0.92
|
|
)
|
|
|
|
entry = prov_mgr.track_property_source(
|
|
entity_id="entity_1",
|
|
property_name="biomass_increase",
|
|
value="463%",
|
|
source=source
|
|
)
|
|
|
|
assert entry is not None
|
|
assert entry.entity_type == "property"
|
|
assert entry.metadata["property_name"] == "biomass_increase"
|
|
|
|
def test_get_lineage(self):
|
|
"""Test getting complete lineage."""
|
|
prov_mgr = ProvenanceManager()
|
|
|
|
# Create lineage chain
|
|
prov_mgr.track_entity("entity_1", "doc_1")
|
|
prov_mgr.track_chunk(
|
|
chunk_id="chunk_1",
|
|
source_document="doc_1",
|
|
parent_chunk_id="entity_1"
|
|
)
|
|
|
|
lineage = prov_mgr.get_lineage("chunk_1")
|
|
|
|
assert lineage is not None
|
|
assert "lineage_chain" in lineage
|
|
assert len(lineage["lineage_chain"]) > 0
|
|
|
|
def test_batch_entity_tracking(self):
|
|
"""Test batch entity tracking."""
|
|
prov_mgr = ProvenanceManager()
|
|
|
|
entities = [
|
|
{"id": "entity_1", "confidence": 0.9},
|
|
{"id": "entity_2", "confidence": 0.85}
|
|
]
|
|
|
|
count = prov_mgr.track_entities_batch(entities, "doc_1")
|
|
|
|
assert count == 2
|
|
|
|
def test_batch_chunk_tracking(self):
|
|
"""Test batch chunk tracking."""
|
|
prov_mgr = ProvenanceManager()
|
|
|
|
chunks = [
|
|
{"id": "chunk_1", "start_index": 0, "end_index": 100},
|
|
{"id": "chunk_2", "start_index": 100, "end_index": 200}
|
|
]
|
|
|
|
count = prov_mgr.track_chunks_batch(chunks, "doc_1")
|
|
|
|
assert count == 2
|
|
|
|
def test_get_statistics(self):
|
|
"""Test getting provenance statistics."""
|
|
prov_mgr = ProvenanceManager()
|
|
|
|
prov_mgr.track_entity("entity_1", "doc_1")
|
|
prov_mgr.track_chunk("chunk_1", "doc_1")
|
|
|
|
stats = prov_mgr.get_statistics()
|
|
|
|
assert stats["total_entries"] == 2
|
|
assert "entity_types" in stats
|
|
|
|
def test_clear(self):
|
|
"""Test clearing provenance data."""
|
|
prov_mgr = ProvenanceManager()
|
|
|
|
prov_mgr.track_entity("entity_1", "doc_1")
|
|
count = prov_mgr.clear()
|
|
|
|
assert count == 1
|
|
|
|
lineage = prov_mgr.get_lineage("entity_1")
|
|
assert lineage == {}
|