entity relationship model

tests/test_semantics.py

@@ -0,0 +1,221 @@
+import json
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+import pytest
+
+from infospace_bench import InfospaceError, add_artifact, create_infospace
+from infospace_bench.semantics import (
+    list_entities,
+    list_relations,
+    parse_entity_artifact,
+    parse_relation_artifact,
+)
+
+
+ENTITY = """# Division of Labour
+
+## Definition
+
+Increasing productivity by splitting work into specialized tasks.
+
+## Source Chapter
+
+Book I, Chapter 1
+
+## Context
+
+Smith introduces the pin factory as an example of this mechanism.
+
+## Economic Domain
+
+Production
+
+## Original Wording
+
+The greatest improvement in the productive powers of labour.
+
+## Modern Interpretation
+
+Specialization improves throughput by reducing switching costs.
+"""
+
+
+INVALID_ENTITY = """# Thin Entity
+
+## Context
+
+This artifact is missing its definition.
+"""
+
+
+RELATION = """# Division of Labour enables Market Extent
+
+## Subject
+
+Division of Labour
+
+## Predicate
+
+is limited by
+
+## Object
+
+Market Extent
+
+## Relation Type
+
+constrains
+
+## VSM Channel
+
+S1 -> S4
+
+## Evidence
+
+Book I, Chapter 3 connects specialization to market size.
+
+## Feedback Role
+
+Part of the market expansion loop.
+"""
+
+
+def cli_env() -> dict[str, str]:
+    env = os.environ.copy()
+    env["PYTHONPATH"] = "src:/home/worsch/markitect-tool/src"
+    return env
+
+
+def test_parse_entity_artifact_extracts_legacy_sections(tmp_path: Path) -> None:
+    path = tmp_path / "division.md"
+    path.write_text(ENTITY, encoding="utf-8")
+
+    entity = parse_entity_artifact("entity/division.md", path)
+
+    assert entity.artifact_id == "entity/division.md"
+    assert entity.slug == "division-of-labour"
+    assert entity.title == "Division of Labour"
+    assert entity.definition_word_count == 8
+    assert entity.domain == "Production"
+    assert entity.has_original_wording is True
+    assert entity.section_slugs == [
+        "definition",
+        "source-chapter",
+        "context",
+        "economic-domain",
+        "original-wording",
+        "modern-interpretation",
+    ]
+
+
+def test_parse_entity_artifact_reports_missing_required_sections(tmp_path: Path) -> None:
+    path = tmp_path / "thin.md"
+    path.write_text(INVALID_ENTITY, encoding="utf-8")
+
+    with pytest.raises(InfospaceError) as raised:
+        parse_entity_artifact("entity/thin.md", path)
+
+    assert raised.value.code == "invalid_entity_artifact"
+    assert raised.value.detail["missing_sections"] == ["definition"]
+
+
+def test_parse_relation_artifact_links_entity_endpoints(tmp_path: Path) -> None:
+    path = tmp_path / "relation.md"
+    path.write_text(RELATION, encoding="utf-8")
+    entity_ids = {
+        "division-of-labour": "entity/division.md",
+        "market-extent": "entity/market.md",
+    }
+
+    relation = parse_relation_artifact("relation/division-market.md", path, entity_ids)
+
+    assert relation.slug == "division-of-labour-enables-market-extent"
+    assert relation.subject_slug == "division-of-labour"
+    assert relation.object_slug == "market-extent"
+    assert relation.subject_entity_id == "entity/division.md"
+    assert relation.object_entity_id == "entity/market.md"
+    assert relation.is_feedback_member is True
+
+
+def test_parse_relation_artifact_reports_unresolved_endpoint(tmp_path: Path) -> None:
+    path = tmp_path / "relation.md"
+    path.write_text(RELATION, encoding="utf-8")
+
+    with pytest.raises(InfospaceError) as raised:
+        parse_relation_artifact("relation/division-market.md", path, {})
+
+    assert raised.value.code == "unresolved_relation_endpoint"
+    assert raised.value.detail["missing_slugs"] == [
+        "division-of-labour",
+        "market-extent",
+    ]
+
+
+def test_list_entities_and_relations_from_manifest(tmp_path: Path) -> None:
+    infospace = create_infospace(tmp_path, "pilot", name="Pilot")
+    division = tmp_path / "division.md"
+    division.write_text(ENTITY, encoding="utf-8")
+    market = tmp_path / "market.md"
+    market.write_text(
+        ENTITY.replace("Division of Labour", "Market Extent").replace(
+            "Production", "Exchange"
+        ),
+        encoding="utf-8",
+    )
+    relation = tmp_path / "relation.md"
+    relation.write_text(RELATION, encoding="utf-8")
+
+    add_artifact(infospace.root, division, kind="entity", title="Division")
+    add_artifact(infospace.root, market, kind="entity", title="Market")
+    add_artifact(infospace.root, relation, kind="relation", title="Relation")
+
+    assert [entity.slug for entity in list_entities(infospace.root)] == [
+        "division-of-labour",
+        "market-extent",
+    ]
+    assert [item.relation_type for item in list_relations(infospace.root)] == [
+        "constrains"
+    ]
+
+
+def test_cli_entities_and_relations_output_json(tmp_path: Path) -> None:
+    infospace = create_infospace(tmp_path, "pilot", name="Pilot")
+    division = tmp_path / "division.md"
+    division.write_text(ENTITY, encoding="utf-8")
+    market = tmp_path / "market.md"
+    market.write_text(
+        ENTITY.replace("Division of Labour", "Market Extent").replace(
+            "Production", "Exchange"
+        ),
+        encoding="utf-8",
+    )
+    relation = tmp_path / "relation.md"
+    relation.write_text(RELATION, encoding="utf-8")
+    add_artifact(infospace.root, division, kind="entity", title="Division")
+    add_artifact(infospace.root, market, kind="entity", title="Market")
+    add_artifact(infospace.root, relation, kind="relation", title="Relation")
+
+    entities = subprocess.run(
+        [sys.executable, "-m", "infospace_bench", "entities", str(infospace.root)],
+        check=False,
+        env=cli_env(),
+        text=True,
+        capture_output=True,
+    )
+    relations = subprocess.run(
+        [sys.executable, "-m", "infospace_bench", "relations", str(infospace.root)],
+        check=False,
+        env=cli_env(),
+        text=True,
+        capture_output=True,
+    )
+
+    assert entities.returncode == 0, entities.stderr
+    assert relations.returncode == 0, relations.stderr
+    assert json.loads(entities.stdout)["entities"][0]["slug"] == "division-of-labour"
+    assert json.loads(relations.stdout)["relations"][0]["subject_entity_id"] == (
+        "entity/division.md"
+    )