import csv import io from datetime import UTC, datetime from unittest.mock import AsyncMock, MagicMock import pytest from fastapi import HTTPException from sqlalchemy.dialects import postgresql from app.api.v1.compute_intelligence import sample_query, selected_countries from app.services.collectors.epoch_ai import EpochAIGPUCollector from app.services.collectors.top500 import TOP500Collector from app.services.compute_history import compute_history def epoch_csv(**overrides): row = { "Name": "Cluster Alpha", "Country": "United States of America", "Status": "Existing", "First Operational Date": "2023-05-02", "16-bit OP/s (log)": "18", "Location": "3231 Riverport Rd, Memphis, TN 38109", "latitude": "35", "longitude": "-90", **overrides, } output = io.StringIO() writer = csv.DictWriter(output, fieldnames=list(row)) writer.writeheader() writer.writerow(row) return output.getvalue() def test_epoch_csv_preserves_precision_date_and_missing_values(): collector = EpochAIGPUCollector() row = collector.parse_response(epoch_csv())[0] assert row["value"] == 1e18 assert row["unit"] == "FLOP/s" assert row["metadata"]["precision"] == "FP16" assert row["metadata"]["location_precision"] == "precise" assert row["metadata"]["raw_country"] == "United States of America" assert row["reference_date"] == "2023-05-02" missing = collector.parse_response( epoch_csv(**{"16-bit OP/s (log)": "", "First Operational Date": ""}) )[0] assert missing["value"] is None assert missing["reference_date"] is None @pytest.mark.parametrize( ("location", "country", "expected"), [ ("United States of America", "United States of America", "country"), ("Japan", "Japan", "country"), ("Korea (Republic of)", "South Korea", "country"), ("Texas", "United States of America", "region"), ("Iowa, USA", "United States of America", "region"), ("Seoul", "South Korea", "city"), ("Paris, France", "France", "city"), ("Skolkovo Innovation Center\nMoscow Oblast\nRussia", "Russia", "site"), ("Cluster 2, Texas", "United States of America", "site"), ("Campus 7, Tokyo", "Japan", "site"), ("Building 240, Argonne", "United States of America", "site"), ("7", "United States of America", "unknown"), ("Jülich Supercomputing Centre\n52428 Jülich, Germany", "Germany", "precise"), ("35.380924,139.625008", "Japan", "precise"), ('33°24\'28.7"N 112°21\'54.3"W', "United States of America", "precise"), ("latitude: 35.0 longitude: 181.0", "United States of America", "unknown"), ('99°99\'00"N 200°00\'00"W', "United States of America", "unknown"), ("3231 Riverport Rd, Memphis, TN 38109", "United States of America", "precise"), ], ) def test_epoch_location_precision_follows_location_field(location, country, expected): row = EpochAIGPUCollector().parse_response( epoch_csv(Location=location, Country=country) )[0] assert row["metadata"]["location_precision"] == expected @pytest.mark.parametrize( ("location", "expected"), [ ({"lat": 35.0, "lng": 139.0}, "precise"), ({"latitude": 35.0, "longitude": 181.0}, "unknown"), ({"lat": 35.0}, "unknown"), ({"lng": 139.0}, "unknown"), ({"lat": "invalid", "lng": 139.0}, "unknown"), ], ) def test_epoch_coordinate_object_requires_complete_valid_pair(location, expected): from app.services.epoch_location import assess_epoch_location assert assess_epoch_location(location).precision == expected def test_epoch_anonymous_rows_are_not_geocoded(): row = EpochAIGPUCollector().parse_response(epoch_csv(Name="Anonymized 1", Country="China"))[0] assert row["latitude"] is None and row["longitude"] is None assert row["metadata"]["anonymous"] and row["metadata"]["rounded"] @pytest.mark.parametrize( "payload", ["blocked", "Name,Country\nA,US", epoch_csv(**{"16-bit OP/s (log)": "nan"})], ) def test_epoch_invalid_payload_fails_closed(payload): with pytest.raises(ValueError): EpochAIGPUCollector().parse_response(payload) def test_epoch_duplicate_identity_rejected(): payload = epoch_csv() with pytest.raises(ValueError, match="identity collision"): EpochAIGPUCollector().parse_response(payload + payload.splitlines()[1] + "\n") def test_anonymous_source_rows_preserve_multiplicity_without_claiming_identity(): payload = epoch_csv(Name="Anonymized Chinese System", Country="China") rows = EpochAIGPUCollector().parse_response(payload + payload.splitlines()[1] + "\n") assert len(rows) == 2 assert rows[0]["source_id"] != rows[1]["source_id"] assert all(row["metadata"]["identity_scope"] == "snapshot_record" for row in rows) def test_top500_units_and_stable_identity(): collector = TOP500Collector() html = '
RankSystemCoresRmax [TFlop/s]Rpeak [PFlop/s]Power
{rank}Test
Lab
USA
101,50021
' first = collector.parse_response( html.format(rank=1), "https://top500.org/lists/top500/2025/11/" )[0] second = collector.parse_response( html.format(rank=2), "https://top500.org/lists/top500/2026/06/" )[0] assert first["source_id"] == second["source_id"] == "top500_system_123" assert float(first["value"]) == 1.5e15 assert first["metadata"]["rpeak_flops"] == 2e15 assert first["reference_date"] == "2025-11-01" assert second["reference_date"] == "2026-06-01" with pytest.raises(ValueError, match="date missing"): collector.parse_response(html.format(rank=1)) @pytest.mark.asyncio async def test_large_source_loss_does_not_create_snapshot(): db = AsyncMock() db.scalar.return_value = 500 db.add = MagicMock() with pytest.raises(ValueError, match="40%"): await TOP500Collector()._create_snapshot(db, 1, [{}] * 2, datetime.now(UTC)) db.add.assert_not_called() db.commit.assert_not_awaited() def test_history_missing_years_and_denominators(): global_data = compute_history(["CN", "US"]) assert global_data["compute"][3]["values"] == {"CN": 31, "US": 41} assert global_data["compute"][-1]["values"] == {"CN": None, "US": None} bilateral = compute_history(["CN", "US"], "bilateral_share") assert sum(bilateral["compute"][3]["values"].values()) == 100 assert bilateral["denominator"] == "US+CN" absolute = compute_history(["US", "CN"], "absolute") assert absolute["compute"][3]["values"] == {"US": None, "CN": 435} assert global_data["innovation"][-2]["value"] == 17.95 assert global_data["innovation"][-1]["value"] is None assert global_data["evidence"]["innovation-2026"]["published_at"] == "2026-07-17" @pytest.mark.asyncio async def test_snapshot_query_uses_observation_cutoff_not_location(): query = await sample_query(AsyncMock(), ["CN"], 2023) sql = str(query.compile(dialect=postgresql.dialect(), compile_kwargs={"literal_binds": True})) assert "2024-01-01" in sql assert "row_number() OVER (PARTITION BY" in sql assert "compute_contract" in sql and "中国" in sql assert "latitude" not in sql and "longitude" not in sql def test_country_input_is_bounded_and_deduplicated(): assert selected_countries("CN,CN,US") == ["CN", "US"] assert selected_countries("CN,US,EUROPE,APAC,OTHER")[-1] == "OTHER" with pytest.raises(HTTPException): selected_countries("invalid") with pytest.raises(HTTPException, match="overlapping"): selected_countries("EUROPE,DE") def test_catalog_supports_global_participants_without_inventing_history(): from app.services.compute_catalog import ( CATALOG, COMPARISON_GROUPS, COUNTRIES, source_country_names, source_country_participants, ) assert {"CN", "US", "JP", "KR", "IN", "DE", "FR", "GB", "AU", "BR", "ZA"}.issubset( {entry["code"] for entry in CATALOG} ) assert not {"TW", "HK", "MO", "XK"}.intersection(entry["code"] for entry in CATALOG) owners = source_country_names(["CN"]) assert {"中国", "中国(台湾)", "中国(香港)", "中国(澳门)"}.issubset(owners) assert source_country_participants(["CN"])["中国(台湾)"] == "CN" assert [entry["code"] for entry in CATALOG[:5]] == ["CN", "US", "EUROPE", "APAC", "OTHER"] assert [entry["kind"] for entry in CATALOG[:5]] == [ "country", "country", "region", "region", "region", ] group_members = [ member for _code, _name, _name_en, members, _anchor in COMPARISON_GROUPS for member in members ] assert len(group_members) == len(set(group_members)) assert set(group_members) == set(COUNTRIES) data = compute_history(["JP", "KR"]) assert [row["values"]["JP"] for row in data["compute"][:4]] == [6, 5, 4, 4] assert all(row["values"]["KR"] is None for row in data["compute"]) assert all(row["value"] is None for row in data["innovation"]) assert len(data["catalog"]) > 30 def test_region_history_requires_complete_same_year_member_coverage(): data = compute_history(["CN", "US", "EUROPE", "APAC", "OTHER"]) row_2023 = next(row for row in data["compute"] if row["year"] == 2023) assert row_2023["values"]["CN"] == 31 assert row_2023["values"]["US"] == 41 assert row_2023["values"]["EUROPE"] is None assert row_2023["values"]["APAC"] is None assert row_2023["values"]["OTHER"] is None assert row_2023["coverage"]["EUROPE"]["status"] == "incomplete" assert "DE" in row_2023["coverage"]["EUROPE"]["missing_members"] assert data["default_participants"] == ["CN", "US", "EUROPE", "APAC", "OTHER"] def test_anonymous_records_never_enter_the_location_repair_queue(): from app.api.v1.visualization import convert_compute_centers_to_geojson from app.models.collected_data import CollectedData record = CollectedData( source="epoch_ai_gpu", source_id="anonymous", name="Anonymous", extra_data={"compute_contract": "v1", "anonymous": True}, ) result = convert_compute_centers_to_geojson([record]) assert result["features"] == [] assert result["unresolved"] == [] assert result["withheld_count"] == 1 def test_absolute_report_year_mapping_and_bilateral_denominator_ignore_other_countries(): absolute = compute_history(["CN"], "absolute") observed = {row["year"]: row for row in absolute["compute"]} assert observed[2022]["values"]["CN"] == 302 assert observed[2022]["evidence_id"] == "caict-2023" assert observed[2023]["evidence_id"] == "caict-2024" bilateral = compute_history(["CN", "US", "JP"], "bilateral_share") values = next(row["values"] for row in bilateral["compute"] if row["year"] == 2023) assert values == {"CN": 43.06, "US": 56.94, "JP": None} for row in absolute["compute"]: if row["evidence_id"]: report = absolute["evidence"][row["evidence_id"]] assert report["url"].startswith("https://www.caict.ac.cn/")