mirror of
https://github.com/safishamsi/graphify.git
synced 2026-07-13 10:57:13 +00:00
Safi
63 lines
2.6 KiB
Python
63 lines
2.6 KiB
Python
import json
|
|
from pathlib import Path
|
|
from graphify.build import build_from_json, build
|
|
|
|
FIXTURES = Path(__file__).parent / "fixtures"
|
|
|
|
def load_extraction():
|
|
return json.loads((FIXTURES / "extraction.json").read_text())
|
|
|
|
def test_build_from_json_node_count():
|
|
G = build_from_json(load_extraction())
|
|
assert G.number_of_nodes() == 4
|
|
|
|
def test_build_from_json_edge_count():
|
|
G = build_from_json(load_extraction())
|
|
assert G.number_of_edges() == 4
|
|
|
|
def test_nodes_have_label():
|
|
G = build_from_json(load_extraction())
|
|
assert G.nodes["n_transformer"]["label"] == "Transformer"
|
|
|
|
def test_edges_have_confidence():
|
|
G = build_from_json(load_extraction())
|
|
data = G.edges["n_attention", "n_concept_attn"]
|
|
assert data["confidence"] == "INFERRED"
|
|
|
|
def test_ambiguous_edge_preserved():
|
|
G = build_from_json(load_extraction())
|
|
data = G.edges["n_layernorm", "n_concept_attn"]
|
|
assert data["confidence"] == "AMBIGUOUS"
|
|
|
|
def test_legacy_node_source_canonicalized():
|
|
"""Legacy 'source' key on nodes is renamed to 'source_file' before graph build."""
|
|
ext = {"nodes": [{"id": "n1", "label": "A", "file_type": "code", "source": "a.py"}],
|
|
"edges": [], "input_tokens": 0, "output_tokens": 0}
|
|
G = build_from_json(ext)
|
|
assert "source_file" in G.nodes["n1"]
|
|
assert G.nodes["n1"]["source_file"] == "a.py"
|
|
assert "source" not in G.nodes["n1"]
|
|
|
|
|
|
def test_legacy_edge_from_to_canonicalized():
|
|
"""Legacy 'from'/'to' keys on edges are accepted alongside 'source'/'target'."""
|
|
ext = {"nodes": [{"id": "n1", "label": "A", "file_type": "code", "source_file": "a.py"},
|
|
{"id": "n2", "label": "B", "file_type": "code", "source_file": "b.py"}],
|
|
"edges": [{"from": "n1", "to": "n2", "relation": "calls",
|
|
"confidence": "EXTRACTED", "source_file": "a.py", "weight": 1.0}],
|
|
"input_tokens": 0, "output_tokens": 0}
|
|
G = build_from_json(ext)
|
|
assert G.number_of_edges() == 1
|
|
|
|
|
|
def test_build_merges_multiple_extractions():
|
|
ext1 = {"nodes": [{"id": "n1", "label": "A", "file_type": "code", "source_file": "a.py"}],
|
|
"edges": [], "input_tokens": 0, "output_tokens": 0}
|
|
ext2 = {"nodes": [{"id": "n2", "label": "B", "file_type": "document", "source_file": "b.md"}],
|
|
"edges": [{"source": "n1", "target": "n2", "relation": "references",
|
|
"confidence": "INFERRED", "source_file": "b.md", "weight": 1.0}],
|
|
"input_tokens": 0, "output_tokens": 0}
|
|
G = build([ext1, ext2])
|
|
assert G.number_of_nodes() == 2
|
|
assert G.number_of_edges() == 1
|