feat(reports): store and browse report artifacts

tests/test_report_backfill.py

@@ -0,0 +1,114 @@
+#!/usr/bin/env python3
+"""Tests for legacy report artifact backfill."""
+
+from __future__ import annotations
+
+import os
+import tempfile
+import unittest
+from pathlib import Path
+
+from app.db import connect
+from app.db.backfill import backfill_report_artifacts
+from app.db import repositories as repo
+
+
+class ReportBackfillTest(unittest.TestCase):
+    def setUp(self):
+        self.temp_dir = tempfile.TemporaryDirectory()
+        self.root = Path(self.temp_dir.name)
+        self.conn = connect(str(self.root / "test.db"))
+        self.roots = {
+            "copyparty": str(self.root / "copyparty"),
+            "npm": str(self.root / "npm"),
+            "app": str(self.root / "app"),
+            "mikrotik": str(self.root / "mikrotik"),
+        }
+        for path in self.roots.values():
+            Path(path).mkdir(parents=True)
+
+    def tearDown(self):
+        self.conn.close()
+        self.temp_dir.cleanup()
+
+    def test_dry_run_and_import_are_idempotent(self):
+        Path(self.roots["copyparty"], "2026-11-06-11-30-10.txt").write_text(
+            "copyparty summary\n", encoding="utf-8")
+        Path(self.roots["npm"], "2026-11-06.csv").write_text(
+            "ip,count\n192.0.2.1,3\n", encoding="utf-8")
+        Path(self.roots["app"], "2026-11-06.json").write_text(
+            '{"summary":{"blocked":1}}', encoding="utf-8")
+        Path(self.roots["app"], "data").mkdir()
+        Path(self.roots["app"], "data", "requests.csv").write_text(
+            "ip\n192.0.2.2\n", encoding="utf-8")
+
+        preview = backfill_report_artifacts(
+            self.conn, dry_run=True, roots=self.roots)["reports"]
+        self.assertEqual(preview["would_import"], 3)
+        self.assertEqual(preview["skipped_canonical"], [
+            {"source": "app", "path": "data/requests.csv"}])
+        self.assertEqual(preview["by_source"]["copyparty"]["would_import"], 1)
+        self.assertEqual(preview["by_format"]["csv"]["would_import"], 1)
+        self.assertEqual(repo.list_report_artifacts(self.conn)["items"], [])
+
+        imported = backfill_report_artifacts(
+            self.conn, roots=self.roots)["reports"]
+        self.assertEqual(imported["imported"], 3)
+        self.assertEqual(imported["unmapped"], [])
+
+        repeated = backfill_report_artifacts(
+            self.conn, roots=self.roots)["reports"]
+        self.assertEqual(repeated["imported"], 0)
+        self.assertEqual(repeated["already_imported"], 3)
+
+        items = repo.list_report_artifacts(
+            self.conn, source="copyparty")["items"]
+        self.assertEqual(items[0]["original_path"],
+                         "copyparty/2026-11-06-11-30-10.txt")
+        self.assertEqual(items[0]["generated_at"],
+                         "2026-11-06T11:30:10+00:00")
+
+    def test_malformed_json_is_preserved_with_parse_error(self):
+        Path(self.roots["app"], "2026-11-06.json").write_text(
+            '{"incomplete":', encoding="utf-8")
+
+        result = backfill_report_artifacts(
+            self.conn, roots=self.roots)["reports"]
+        self.assertEqual(result["imported"], 1)
+        artifact = repo.list_report_artifacts(
+            self.conn, source="app")["items"][0]
+        detail = repo.get_report_artifact(self.conn, artifact["id"])
+        self.assertEqual(detail["payload"]["content"], '{"incomplete":')
+        self.assertIn("parse_error", detail["payload"])
+
+    def test_artifacts_survive_sqlite_backup_and_restore(self):
+        artifact_id = repo.insert_report_artifact(
+            self.conn, source="app", report_type="summary",
+            generated_at="2026-11-06T00:00:00+00:00",
+            payload={"summary": {"count": 4}},
+            original_path="app/2026-11-06.json", content_sha256="c" * 64,
+        )
+        restored = connect(str(self.root / "restored.db"))
+        try:
+            self.conn.backup(restored)
+            artifact = repo.get_report_artifact(restored, artifact_id)
+            self.assertEqual(artifact["payload"], {"summary": {"count": 4}})
+        finally:
+            restored.close()
+
+    def test_oversized_file_is_reported_without_deleting_source(self):
+        source = Path(self.roots["npm"], "large.txt")
+        source.write_text("keep", encoding="utf-8")
+        from unittest.mock import patch
+
+        with patch("app.db.backfill.MAX_REPORT_ARTIFACT_BYTES", 1):
+            result = backfill_report_artifacts(
+                self.conn, roots=self.roots)["reports"]
+
+        self.assertEqual(len(result["unmapped"]), 1)
+        self.assertTrue(source.exists())
+        self.assertEqual(result["unmapped"][0]["path"], "large.txt")
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_report_persistence.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+"""Tests for dual-writing generated reports to SQLite."""
+
+from __future__ import annotations
+
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+import app.scan
+from app.analyzer import Analyzer
+from app.db import connect
+from app.db import repositories as repo
+from app.utils.blocklist_history import write_blocklist_report
+
+
+class ReportPersistenceTest(unittest.TestCase):
+    def setUp(self):
+        self.temp_dir = tempfile.TemporaryDirectory()
+        self.root = Path(self.temp_dir.name)
+        self.conn = connect(str(self.root / "test.db"))
+        self.connection_patch = patch("app.db.get_connection",
+                                      return_value=self.conn)
+        self.connection_patch.start()
+
+    def tearDown(self):
+        self.connection_patch.stop()
+        self.conn.close()
+        self.temp_dir.cleanup()
+
+    def test_analyzer_summary_is_stored_with_file_provenance(self):
+        report_dir = self.root / "copyparty"
+        report_dir.mkdir()
+        path = report_dir / "2026-11-06-11-30-10.txt"
+        path.write_text("summary body", encoding="utf-8")
+        analyzer = Analyzer("logs", str(report_dir), quiet=True)
+
+        analyzer.persist_report_artifact(str(path), scan_id=14)
+
+        item = repo.list_report_artifacts(
+            self.conn, source="ids")["items"][0]
+        detail = repo.get_report_artifact(self.conn, item["id"])
+        self.assertEqual(item["original_path"], "ids/2026-11-06-11-30-10.txt")
+        self.assertEqual(detail["scan_id"], 14)
+        self.assertEqual(detail["payload"]["content"], "summary body")
+
+    def test_blocklist_report_is_stored_as_structured_artifact(self):
+        path = write_blocklist_report(
+            str(self.root / "reports"), history_v4=set(), history_v6=set(),
+            prev_v4=set(), prev_v6=set(),
+            complete_v4={"192.0.2.1/32"}, complete_v6=set(),
+            firewall_changes={"added_ipv4": ["192.0.2.1/32"]},
+            dry_run=True, scan_id=22,
+        )
+
+        items = repo.list_report_artifacts(
+            self.conn, source="app", report_type="blocklist_change")["items"]
+        self.assertEqual(len(items), 1)
+        detail = repo.get_report_artifact(self.conn, items[0]["id"])
+        self.assertEqual(detail["scan_id"], 22)
+        self.assertEqual(detail["payload"]["blocked_ipv4"], ["192.0.2.1/32"])
+        self.assertTrue(Path(path).exists())
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_report_routes.py

@@ -0,0 +1,71 @@
+#!/usr/bin/env python3
+"""Tests for database-backed report API routes."""
+
+from __future__ import annotations
+
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+from app.db import connect
+from app.db import repositories as repo
+from app.web import create_app
+
+
+class ReportRoutesTest(unittest.TestCase):
+    def setUp(self):
+        self.temp_dir = tempfile.TemporaryDirectory()
+        self.conn = connect(str(Path(self.temp_dir.name) / "test.db"))
+        self.app = create_app()
+        self.app.config["TESTING"] = True
+        self.client = self.app.test_client()
+        self.connection_patch = patch("app.db.get_connection",
+                                      return_value=self.conn)
+        self.connection_patch.start()
+        self.artifact_id = repo.insert_report_artifact(
+            self.conn, source="copyparty", report_type="text_report",
+            generated_at="2026-11-06T10:00:00+00:00",
+            payload={"format": "text", "content": "summary"},
+            original_path="copyparty/2026-11-06.txt",
+            content_sha256="b" * 64,
+        )
+
+    def tearDown(self):
+        self.connection_patch.stop()
+        self.conn.close()
+        self.temp_dir.cleanup()
+
+    def test_list_detail_and_text_export(self):
+        listed = self.client.get("/api/reports?source=copyparty&limit=1")
+        self.assertEqual(listed.status_code, 200)
+        self.assertEqual(listed.json["items"][0]["id"], self.artifact_id)
+
+        detail = self.client.get(
+            f"/api/report-artifacts/{self.artifact_id}")
+        self.assertEqual(detail.status_code, 200)
+        self.assertEqual(detail.json["payload"]["content"], "summary")
+
+        exported = self.client.get(
+            f"/api/report-artifacts/{self.artifact_id}/export?format=txt")
+        self.assertEqual(exported.status_code, 200)
+        self.assertEqual(exported.data.decode(), "summary")
+        self.assertIn("attachment", exported.headers["Content-Disposition"])
+        self.assertNotIn(".txt.txt", exported.headers["Content-Disposition"])
+
+    def test_invalid_source_cursor_and_missing_id(self):
+        self.assertEqual(
+            self.client.get("/api/reports?source=unknown").status_code, 400)
+        self.assertEqual(
+            self.client.get("/api/reports?cursor=invalid").status_code, 400)
+        self.assertEqual(
+            self.client.get("/api/report-artifacts/9999").status_code, 404)
+
+    def test_legacy_file_routes_remain_registered(self):
+        response = self.client.get("/api/reports/copyparty")
+        self.assertEqual(response.status_code, 200)
+        self.assertIn("files", response.json)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_repositories.py

@@ -47,7 +47,7 @@ class SchemaTest(unittest.TestCase):
                   "blocklist_reasons", "whitelist_entries",
                   "whitelist_sources", "firewall_snapshots",
                   "firewall_address_list_entries", "firewall_rule_entries",
-                  "whois_info", "log_sources"):
+                  "whois_info", "log_sources", "report_artifacts"):
             self.assertIn(t, tables, f"missing table {t}")
         conn.close()
 
@@ -195,5 +195,54 @@ class FirewallTest(unittest.TestCase):
             "SELECT COUNT(*) FROM firewall_rule_entries").fetchone()[0], 1)
 
 
+class ReportArtifactTest(unittest.TestCase):
+    def setUp(self):
+        self.conn = _new_conn()
+
+    def tearDown(self):
+        self.conn.close()
+
+    def test_artifact_insert_is_idempotent_and_detail_decodes_payload(self):
+        kwargs = {
+            "source": "copyparty", "report_type": "analyzer_summary",
+            "generated_at": "2026-11-01T10:00:00+00:00",
+            "payload": {"summary": {"requests": 12}},
+            "original_path": "reports/copyparty/2026-11-01.txt",
+            "content_sha256": "a" * 64,
+        }
+        first_id = repo.insert_report_artifact(self.conn, **kwargs)
+        duplicate_id = repo.insert_report_artifact(self.conn, **kwargs)
+
+        self.assertEqual(first_id, duplicate_id)
+        self.assertEqual(self.conn.execute(
+            "SELECT COUNT(*) FROM report_artifacts").fetchone()[0], 1)
+        self.assertEqual(repo.get_report_artifact(self.conn, first_id)["payload"],
+                         kwargs["payload"])
+
+    def test_artifact_cursor_orders_stably_and_filters_source(self):
+        for day, source in (("01", "npm"), ("02", "copyparty"),
+                            ("03", "npm")):
+            repo.insert_report_artifact(
+                self.conn, source=source, report_type="summary",
+                generated_at=f"2026-11-{day}T00:00:00+00:00",
+                payload={"day": day}, original_path=f"reports/{day}.txt",
+                content_sha256=day * 64,
+            )
+
+        first = repo.list_report_artifacts(self.conn, source="npm", limit=1)
+        self.assertEqual(len(first["items"]), 1)
+        self.assertIsNotNone(first["next_cursor"])
+        second = repo.list_report_artifacts(
+            self.conn, source="npm", limit=1, cursor=first["next_cursor"])
+        self.assertEqual(len(second["items"]), 1)
+        self.assertIsNone(second["next_cursor"])
+        self.assertGreater(first["items"][0]["generated_at"],
+                           second["items"][0]["generated_at"])
+
+    def test_artifact_cursor_rejects_invalid_token(self):
+        with self.assertRaises(ValueError):
+            repo.list_report_artifacts(self.conn, cursor="invalid")
+
+
 if __name__ == "__main__":
     unittest.main()