first content-indexing slice

tests/test_content_indexing.py

@@ -0,0 +1,67 @@
+from repo_registry.content_indexing.extractor import ContentExtractor
+from repo_registry.core.models import ObservedFact
+
+
+def fact(id, kind, name, path="", line=None):
+    metadata = {}
+    if line is not None:
+        metadata["line"] = line
+    return ObservedFact(
+        id=id,
+        repository_id=1,
+        analysis_run_id=1,
+        snapshot_id=1,
+        kind=kind,
+        path=path,
+        name=name,
+        value="",
+        metadata=metadata,
+    )
+
+
+def test_content_extractor_chunks_docs_and_interface_line_ranges(tmp_path):
+    repo = tmp_path / "repo"
+    repo.mkdir()
+    (repo / "README.md").write_text(
+        "\n".join(f"readme line {number}" for number in range(1, 46)),
+        encoding="utf-8",
+    )
+    (repo / "app.py").write_text(
+        "\n".join(f"line {number}" for number in range(1, 21)),
+        encoding="utf-8",
+    )
+
+    chunks = ContentExtractor().extract(
+        repo,
+        [
+            fact(1, "documentation", "README", "README.md"),
+            fact(2, "interface", "python route decorator", "app.py", line=10),
+        ],
+    )
+
+    readme_chunks = [chunk for chunk in chunks if chunk.path == "README.md"]
+    interface_chunks = [chunk for chunk in chunks if chunk.path == "app.py"]
+    assert [(chunk.start_line, chunk.end_line) for chunk in readme_chunks] == [
+        (1, 40),
+        (41, 45),
+    ]
+    assert len(interface_chunks) == 1
+    assert interface_chunks[0].start_line == 5
+    assert interface_chunks[0].end_line == 20
+    assert "line 10" in interface_chunks[0].text
+
+
+def test_content_extractor_ignores_unindexed_and_missing_paths(tmp_path):
+    repo = tmp_path / "repo"
+    repo.mkdir()
+    (repo / "README.md").write_text("# ok\n", encoding="utf-8")
+
+    chunks = ContentExtractor().extract(
+        repo,
+        [
+            fact(1, "language", "Python"),
+            fact(2, "documentation", "missing", "missing.md"),
+        ],
+    )
+
+    assert chunks == []

tests/test_registry_service.py

@@ -343,6 +343,11 @@ def test_analyze_repository_records_snapshot_and_observed_facts(tmp_path):
     assert ("documentation", "README", "README.md") in fact_names
     assert ("framework", "FastAPI", "requirements.txt") in fact_names
     assert ("interface", "python route decorator", "app.py") in fact_names
+    chunks = service.list_content_chunks(repository.id, summary.analysis_run.id)
+    chunk_sources = {(chunk.kind, chunk.path) for chunk in chunks}
+    assert ("documentation", "README.md") in chunk_sources
+    assert ("manifest", "requirements.txt") in chunk_sources
+    assert ("interface", "app.py") in chunk_sources
 
     candidate_graph = service.candidate_graph(repository.id, summary.analysis_run.id)
     assert candidate_graph.repository.name == "Example"

tests/test_storage_migrations.py

@@ -25,9 +25,16 @@ def test_initialize_is_idempotent_and_applies_expected_columns(tmp_path):
         evidence_columns = {
             row[1] for row in connection.execute("PRAGMA table_info(approved_evidence)")
         }
+        tables = {
+            row[0]
+            for row in connection.execute(
+                "SELECT name FROM sqlite_master WHERE type = 'table'"
+            )
+        }
 
     assert "source_refs" in feature_columns
     assert "source_refs" in evidence_columns
+    assert "content_chunks" in tables
 
 
 def test_delete_repository_cascades_registry_and_review_rows(tmp_path):
@@ -72,6 +79,7 @@ def test_delete_repository_cascades_registry_and_review_rows(tmp_path):
             "approved_features",
             "approved_evidence",
             "analysis_runs",
+            "content_chunks",
             "review_decisions",
         ):
             count = connection.execute(f"SELECT COUNT(*) FROM {table}").fetchone()[0]

tests/test_web_api.py

@@ -320,6 +320,15 @@ def test_api_analysis_run_loop(tmp_path):
         assert ("documentation", "README", "README.md") in fact_names
         assert ("framework", "React", "package.json") in fact_names
         assert ("framework", "Vite", "package.json") in fact_names
+
+        chunks_response = client.get(
+            f"/repos/{repository_id}/analysis-runs/"
+            f"{run['analysis_run']['id']}/content-chunks"
+        )
+        assert chunks_response.status_code == 200
+        assert {
+            (chunk["kind"], chunk["path"]) for chunk in chunks_response.json()
+        } >= {("documentation", "README.md"), ("manifest", "package.json")}
     finally:
         app.dependency_overrides.clear()
 
@@ -392,6 +401,8 @@ def test_ui_register_analyze_and_approve_loop(tmp_path):
         run_detail = client.get(run_path)
         assert run_detail.status_code == 200
         assert "Candidate Graph" in run_detail.text
+        assert "Content Chunks" in run_detail.text
+        assert "README.md:1-1" in run_detail.text
         assert "ID " in run_detail.text
         assert "No review decisions yet." in run_detail.text