[AL-5942] Moving tests around to the designated folders (#1203)

Author: yamini-labelbox

tests/integration/export_v2/test_export_data_rows.py

@@ -14,11 +14,24 @@ def test_export_data_rows(client, data_row, wait_for_data_row_processing):
         "project_details": True,
         "data_row_details": True
     }
+
     task = DataRow.export_v2(client=client, data_rows=[data_row])
     task.wait_till_done()
     assert task.status == "COMPLETE"
     assert task.errors is None
     assert len(task.result) == 1
-    assert task.result[0]["data_row"]["id"] == data_row.uid
-    assert task.result[0]["data_row"]["external_id"] == data_row.external_id
-    assert task.result[0]["data_row"]["row_data"] == data_row.row_data
+    assert task.result[0]['data_row']['id'] == data_row.uid
+
+    task = DataRow.export_v2(client=client, data_rows=[data_row.uid])
+    task.wait_till_done()
+    assert task.status == "COMPLETE"
+    assert task.errors is None
+    assert len(task.result) == 1
+    assert task.result[0]['data_row']['id'] == data_row.uid
+
+    task = DataRow.export_v2(client=client, global_keys=[data_row.global_key])
+    task.wait_till_done()
+    assert task.status == "COMPLETE"
+    assert task.errors is None
+    assert len(task.result) == 1
+    assert task.result[0]['data_row']['id'] == data_row.uid

tests/integration/export_v2/test_export_dataset.py

@@ -1,7 +1,7 @@
 import pytest
 
 
-@pytest.mark.parametrize('data_rows', [2], indirect=True)
+@pytest.mark.parametrize('data_rows', [3], indirect=True)
 def test_dataset_export_v2(export_v2_test_helpers, dataset, data_rows):
     data_row_ids = [dr.uid for dr in data_rows]
     params = {"performance_details": False, "label_details": False}
@@ -11,10 +11,7 @@ def test_dataset_export_v2(export_v2_test_helpers, dataset, data_rows):
     assert set([dr['data_row']['id'] for dr in task_results
                ]) == set(data_row_ids)
 
-
-@pytest.mark.parametrize('data_rows', [3], indirect=True)
-def test_dataset_export_v2_datarow_list(export_v2_test_helpers, dataset,
-                                        data_rows):
+    # testing with a datarow ids filter
     datarow_filter_size = 2
     data_row_ids = [dr.uid for dr in data_rows]
 
@@ -29,3 +26,19 @@ def test_dataset_export_v2_datarow_list(export_v2_test_helpers, dataset,
     # only filtered datarows should be exported
     assert set([dr['data_row']['id'] for dr in task_results
                ]) == set(data_row_ids[:datarow_filter_size])
+
+    # testing with a global key and a datarow id filter
+    datarow_filter_size = 2
+    global_keys = [dr.global_key for dr in data_rows]
+
+    params = {"performance_details": False, "label_details": False}
+    filters = {"global_keys": global_keys[:datarow_filter_size]}
+
+    task_results = export_v2_test_helpers.run_dataset_export_v2_task(
+        dataset, filters=filters, params=params)
+
+    # only 2 datarows should be exported
+    assert len(task_results) == datarow_filter_size
+    # only filtered datarows should be exported
+    assert set([dr['data_row']['global_key'] for dr in task_results
+               ]) == set(global_keys[:datarow_filter_size])

tests/integration/export_v2/test_export_project.py

@@ -1,8 +1,13 @@
 from datetime import datetime, timezone, timedelta
 
 import pytest
+import uuid
+from typing import Tuple
 
 from labelbox.schema.media_type import MediaType
+from labelbox import Project, Dataset
+from labelbox.schema.data_row import DataRow
+from labelbox.schema.label import Label
 
 IMAGE_URL = "https://storage.googleapis.com/lb-artifacts-testing-public/sdk_integration_test/potato.jpeg"
 
@@ -86,17 +91,25 @@ def test_project_export_v2_date_filters(client, export_v2_test_helpers,
 
     filters = {
         "last_activity_at": ["2000-01-01 00:00:00", "2050-01-01 00:00:00"],
-        "label_created_at": ["2000-01-01 00:00:00", "2050-01-01 00:00:00"]
+        "label_created_at": ["2000-01-01 00:00:00", "2050-01-01 00:00:00"],
+        "task_queue_status": "InReview"
     }
 
     # TODO: Right now we don't have a way to test this
     include_performance_details = True
     params = {
-        "include_performance_details": include_performance_details,
+        "performance_details": include_performance_details,
         "include_labels": True,
+        "project_details": True,
         "media_type_override": MediaType.Image
     }
 
+    task_queues = project.task_queues()
+
+    review_queue = next(
+        tq for tq in task_queues if tq.queue_type == "MANUAL_REVIEW_QUEUE")
+    project.move_data_rows_to_task_queue([data_row.uid], review_queue.uid)
+
     task_results = export_v2_test_helpers.run_project_export_v2_task(
         project, task_name=task_name, filters=filters, params=params)
 
@@ -105,6 +118,7 @@ def test_project_export_v2_date_filters(client, export_v2_test_helpers,
         task_project_label_ids_set = set(
             map(lambda prediction: prediction['id'], task_project['labels']))
         assert label_id in task_project_label_ids_set
+        assert task_project['project_details']['workflow_status'] == 'IN_REVIEW'
 
         # TODO: Add back in when we have a way to test this
         # if include_performance_details:
@@ -156,7 +170,7 @@ def test_project_export_v2_with_iso_date_filters(client, export_v2_test_helpers,
 
 
 @pytest.mark.parametrize("data_rows", [3], indirect=True)
-def test_project_export_v2_datarow_filter(
+def test_project_export_v2_datarows_filter(
         export_v2_test_helpers,
         configured_batch_project_with_multiple_datarows):
     project, _, data_rows = configured_batch_project_with_multiple_datarows
@@ -178,3 +192,56 @@ def test_project_export_v2_datarow_filter(
     # only filtered datarows should be exported
     assert set([dr['data_row']['id'] for dr in task_results
                ]) == set(data_row_ids[:datarow_filter_size])
+
+    global_keys = [dr.global_key for dr in data_rows]
+    filters = {
+        "last_activity_at": ["2000-01-01 00:00:00", "2050-01-01 00:00:00"],
+        "label_created_at": ["2000-01-01 00:00:00", "2050-01-01 00:00:00"],
+        "global_keys": global_keys[:datarow_filter_size]
+    }
+    params = {"data_row_details": True, "media_type_override": MediaType.Image}
+    task_results = export_v2_test_helpers.run_project_export_v2_task(
+        project, filters=filters, params=params)
+
+    # only 2 datarows should be exported
+    assert len(task_results) == datarow_filter_size
+    # only filtered datarows should be exported
+    assert set([dr['data_row']['global_key'] for dr in task_results
+               ]) == set(global_keys[:datarow_filter_size])
+
+
+def test_batch_project_export_v2(
+        configured_batch_project_with_label: Tuple[Project, Dataset, DataRow,
+                                                   Label],
+        export_v2_test_helpers, dataset: Dataset, image_url: str):
+    project, dataset, *_ = configured_batch_project_with_label
+
+    batch = list(project.batches())[0]
+    filters = {
+        "last_activity_at": ["2000-01-01 00:00:00", "2050-01-01 00:00:00"],
+        "label_created_at": ["2000-01-01 00:00:00", "2050-01-01 00:00:00"],
+        "batch_ids": [batch.uid],
+    }
+    params = {
+        "include_performance_details": True,
+        "include_labels": True,
+        "media_type_override": MediaType.Image
+    }
+    task_name = "test_batch_export_v2"
+    task = dataset.create_data_rows([
+        {
+            "row_data": image_url,
+            "external_id": "my-image"
+        },
+    ] * 2)
+    task.wait_till_done()
+    data_rows = [dr.uid for dr in list(dataset.export_data_rows())]
+    batch_one = f'batch one {uuid.uuid4()}'
+
+    # This test creates two batches, only one batch should be exporter
+    # Creatin second batch that will not be used in the export due to the filter: batch_id
+    project.create_batch(batch_one, data_rows)
+
+    task_results = export_v2_test_helpers.run_project_export_v2_task(
+        project, task_name=task_name, filters=filters, params=params)
+    assert (batch.size == len(task_results))

tests/integration/export_v2/test__export_slice.py renamed to tests/integration/export_v2/test_export_slice.py

@@ -220,7 +220,7 @@ def test_issues_export(project):
 
 
 def test_dataset_export(dataset, image_url):
-    n_data_rows = 5
+    n_data_rows = 2
     ids = set()
     for _ in range(n_data_rows):
         ids.add(dataset.create_data_row(row_data=image_url))

tests/integration/export_v2/test_legacy_export.py

@@ -9,7 +9,6 @@
 
 from labelbox import DataRow
 from labelbox.exceptions import MalformedQueryException
-from labelbox.schema.export_filters import DatarowExportFilters
 from labelbox.schema.task import Task
 from labelbox.schema.data_row_metadata import DataRowMetadataField, DataRowMetadataKind
 import labelbox.exceptions
@@ -1037,30 +1036,3 @@ def test_create_data_row_with_media_type(dataset, image_url, is_adv_enabled):
             exc.value)
 
     dataset.create_data_row(row_data=image_url, media_type="IMAGE")
-
-
-def test_export_data_rows(client, data_row, wait_for_data_row_processing):
-    # Ensure created data rows are indexed
-    data_row = wait_for_data_row_processing(client, data_row)
-    time.sleep(7)  # temp fix for ES indexing delay
-
-    task = DataRow.export_v2(client=client, data_rows=[data_row])
-    task.wait_till_done()
-    assert task.status == "COMPLETE"
-    assert task.errors is None
-    assert len(task.result) == 1
-    assert task.result[0]['data_row']['id'] == data_row.uid
-
-    task = DataRow.export_v2(client=client, data_rows=[data_row.uid])
-    task.wait_till_done()
-    assert task.status == "COMPLETE"
-    assert task.errors is None
-    assert len(task.result) == 1
-    assert task.result[0]['data_row']['id'] == data_row.uid
-
-    task = DataRow.export_v2(client=client, global_keys=[data_row.global_key])
-    task.wait_till_done()
-    assert task.status == "COMPLETE"
-    assert task.errors is None
-    assert len(task.result) == 1
-    assert task.result[0]['data_row']['id'] == data_row.uid

tests/integration/test_data_rows.py

@@ -144,59 +144,6 @@ def test_bulk_conversation(dataset, sample_bulk_conversation: list) -> None:
     assert len(list(dataset.data_rows())) == len(sample_bulk_conversation)
 
 
-def test_data_row_export(dataset, image_url):
-    n_data_rows = 2
-    ids = set()
-    for _ in range(n_data_rows):
-        ids.add(dataset.create_data_row(row_data=image_url))
-    result = list(dataset.export_data_rows())
-    assert len(result) == n_data_rows
-    assert set(result) == ids
-
-
-@pytest.mark.parametrize('data_rows', [3], indirect=True)
-def test_dataset_export_v2(export_v2_test_helpers, dataset, data_rows):
-    data_row_ids = [dr.uid for dr in data_rows]
-    params = {"performance_details": False, "label_details": False}
-    task_results = export_v2_test_helpers.run_dataset_export_v2_task(
-        dataset, params=params)
-    assert len(task_results) == 3
-    assert set([dr['data_row']['id'] for dr in task_results
-               ]) == set(data_row_ids)
-
-    # testing with a datarow ids filter
-    datarow_filter_size = 2
-    data_row_ids = [dr.uid for dr in data_rows]
-
-    params = {"performance_details": False, "label_details": False}
-    filters = {"data_row_ids": data_row_ids[:datarow_filter_size]}
-
-    task_results = export_v2_test_helpers.run_dataset_export_v2_task(
-        dataset, filters=filters, params=params)
-
-    # only 2 datarows should be exported
-    assert len(task_results) == datarow_filter_size
-    # only filtered datarows should be exported
-    assert set([dr['data_row']['id'] for dr in task_results
-               ]) == set(data_row_ids[:datarow_filter_size])
-
-    # testing with a global key and a datarow id filter
-    datarow_filter_size = 2
-    global_keys = [dr.global_key for dr in data_rows]
-
-    params = {"performance_details": False, "label_details": False}
-    filters = {"global_keys": global_keys[:datarow_filter_size]}
-
-    task_results = export_v2_test_helpers.run_dataset_export_v2_task(
-        dataset, filters=filters, params=params)
-
-    # only 2 datarows should be exported
-    assert len(task_results) == datarow_filter_size
-    # only filtered datarows should be exported
-    assert set([dr['data_row']['global_key'] for dr in task_results
-               ]) == set(global_keys[:datarow_filter_size])
-
-
 def test_create_descriptor_file(dataset):
     import unittest.mock as mock
     with mock.patch.object(dataset.client,