geointel/backend/tests/test_sprint18_change_detection.py

from __future__ import annotations

from datetime import datetime, timezone
from uuid import uuid4

from fastapi.testclient import TestClient
from geoalchemy2.shape import from_shape
from shapely.geometry import box

from app.db.session import get_db
from app.main import app
from app.models import Dataset, Job, VectorFeature
from app.schemas.analysis import ChangeDetectionSummary
from app.services.change_detection_service import ChangeDetectionService


class FakeQuery:
    def __init__(self, rows):
        self.rows = list(rows)

    def filter(self, *criteria):
        for criterion in criteria:
            left = getattr(criterion, "left", None)
            right = getattr(criterion, "right", None)
            operator = getattr(criterion, "operator", None)
            name = getattr(left, "name", None)
            value = getattr(right, "value", right)
            if name and operator and operator.__name__ == "eq":
                self.rows = [row for row in self.rows if getattr(row, name) == value]
        return self

    def all(self):
        return list(self.rows)


class FakeSession:
    def __init__(self, objects=None, query_rows=None) -> None:
        self.objects = objects or {}
        self.query_rows = query_rows or {}
        self.added = []
        self.commits = 0
        self.refreshes = []

    def get(self, model, item_id):
        return self.objects.get((model, item_id))

    def query(self, model):
        return FakeQuery(self.query_rows.get(model, []))

    def add(self, item) -> None:
        self.added.append(item)
        if getattr(item, "id", None) is not None:
            self.objects[(item.__class__, item.id)] = item

    def commit(self) -> None:
        self.commits += 1

    def refresh(self, item) -> None:
        self.refreshes.append(item)


def _dataset(dataset_id, project_id, name):
    return Dataset(
        id=dataset_id,
        project_id=project_id,
        name=name,
        dataset_type="vector",
        source="manual",
        dataset_role="source",
    )


def _feature(dataset_id, source_feature_id, geometry):
    return VectorFeature(
        id=uuid4(),
        dataset_id=dataset_id,
        source_feature_id=source_feature_id,
        geometry=from_shape(geometry, srid=4326),
        properties_json={"source_feature_id": source_feature_id},
    )


def test_change_detection_compares_persisted_vector_features() -> None:
    project_id = uuid4()
    source_dataset_id = uuid4()
    target_dataset_id = uuid4()
    source_dataset = _dataset(source_dataset_id, project_id, "before.geojson")
    target_dataset = _dataset(target_dataset_id, project_id, "after.geojson")
    rows = [
        _feature(source_dataset_id, "source-unchanged", box(0, 0, 1, 1)),
        _feature(source_dataset_id, "source-removed", box(10, 10, 11, 11)),
        _feature(target_dataset_id, "target-unchanged", box(0, 0, 1, 1)),
        _feature(target_dataset_id, "target-added", box(20, 20, 21, 21)),
    ]
    db = FakeSession(
        objects={(Dataset, source_dataset_id): source_dataset, (Dataset, target_dataset_id): target_dataset},
        query_rows={VectorFeature: rows},
    )

    result = ChangeDetectionService.compare_vector_datasets(
        db=db,
        project_id=project_id,
        source_dataset_id=source_dataset_id,
        target_dataset_id=target_dataset_id,
        iou_threshold=0.8,
    )

    change_types = [feature["properties"]["change_type"] for feature in result.geojson["features"]]
    assert result.source_feature_count == 2
    assert result.target_feature_count == 2
    assert result.added_count == 1
    assert result.removed_count == 1
    assert result.unchanged_count == 1
    assert sorted(change_types) == ["added", "removed", "unchanged"]
    assert result.warnings == []


def test_change_detection_endpoint_returns_canonical_envelope(monkeypatch) -> None:
    project_id = uuid4()
    source_dataset_id = uuid4()
    target_dataset_id = uuid4()
    source_dataset = _dataset(source_dataset_id, project_id, "before.geojson")
    target_dataset = _dataset(target_dataset_id, project_id, "after.geojson")
    db = FakeSession(objects={(Dataset, source_dataset_id): source_dataset, (Dataset, target_dataset_id): target_dataset})
    summary = ChangeDetectionSummary(
        source_dataset_id=source_dataset_id,
        target_dataset_id=target_dataset_id,
        source_feature_count=1,
        target_feature_count=1,
        added_count=0,
        removed_count=0,
        unchanged_count=1,
        iou_threshold=0.8,
        warnings=[],
        generated_at=datetime.now(timezone.utc),
        geojson={"type": "FeatureCollection", "features": []},
    )

    monkeypatch.setattr(
        "app.api.routes.analysis.ChangeDetectionService.compare_vector_datasets",
        lambda **_kwargs: summary,
    )
    app.dependency_overrides[get_db] = lambda: db
    try:
        response = TestClient(app).post(
            "/api/v1/analysis/change-detection",
            json={
                "source_dataset_id": str(source_dataset_id),
                "target_dataset_id": str(target_dataset_id),
                "iou_threshold": 0.8,
                "include_unchanged": True,
            },
        )
    finally:
        app.dependency_overrides.pop(get_db, None)

    assert response.status_code == 200
    payload = response.json()
    assert set(payload) == {"data"}
    assert payload["data"]["job_type"] == "analysis.change-detection"
    assert payload["data"]["status"] == "success"
    assert payload["data"]["result_json"]["unchanged_count"] == 1
    assert any(isinstance(item, Job) for item in db.added)