Use subset name on task export (#8176)

<!-- Raise an issue to propose your change
(https://github.com/cvat-ai/cvat/issues).
It helps to avoid duplication of efforts from multiple independent
contributors.
Discuss your ideas with maintainers to be sure that changes will be
approved and merged.
Read the [Contribution guide](https://docs.cvat.ai/docs/contributing/).
-->

<!-- Provide a general summary of your changes in the Title above -->

### Motivation and context
<!-- Why is this change required? What problem does it solve? If it
fixes an open
issue, please link to the issue here. Describe your changes in detail,
add
screenshots. -->
Fixes #6451

### How has this been tested?
<!-- Please describe in detail how you tested your changes.
Include details of your testing environment, and the tests you ran to
see how your change affects other areas of the code, etc. -->

### Checklist
<!-- Go over all the following points, and put an `x` in all the boxes
that apply.
If an item isn't applicable for some reason, then ~~explicitly
strikethrough~~ the whole
line. If you don't do that, GitHub will show incorrect progress for the
pull request.
If you're unsure about any of these, don't hesitate to ask. We're here
to help! -->
- [ ] I submit my changes into the `develop` branch
- [ ] I have created a changelog fragment <!-- see top comment in
CHANGELOG.md -->
- [ ] I have updated the documentation accordingly
- [ ] I have added tests to cover my changes
- [ ] I have linked related issues (see [GitHub docs](

https://help.github.com/en/github/managing-your-work-on-github/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword))
- [ ] I have increased versions of npm packages if it is necessary

([cvat-canvas](https://github.com/cvat-ai/cvat/tree/develop/cvat-canvas#versioning),

[cvat-core](https://github.com/cvat-ai/cvat/tree/develop/cvat-core#versioning),

[cvat-data](https://github.com/cvat-ai/cvat/tree/develop/cvat-data#versioning)
and

[cvat-ui](https://github.com/cvat-ai/cvat/tree/develop/cvat-ui#versioning))

### License

- [ ] I submit _my code changes_ under the same [MIT License](
https://github.com/cvat-ai/cvat/blob/develop/LICENSE) that covers the
project.
  Feel free to contact the maintainers if that's a concern.


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

- **New Features**
- Enhanced task export functionality: Images are now organized into
folders based on subsets for better data organization.

- **Tests**
- Introduced new test methods and updated existing tests to validate the
new subset-based export functionality.
  - Added new data entries for improved test coverage and verification.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: Maxim Zhiltsov <zhiltsov.max35@gmail.com>

changelog.d/20240716_160243_dlavrukhin_apply_subset_name_on_task_export.md

@@ -0,0 +1,4 @@
+### Changed
+
+- On task export, put images to folders depending on subset
+  (<https://github.com/cvat-ai/cvat/pull/8176>)

cvat/apps/dataset_manager/bindings.py

@@ -200,7 +200,7 @@ class CommonData(InstanceLabelData):
     Tag = namedtuple('Tag', 'frame, label, attributes, source, group, id')
     Tag.__new__.__defaults__ = (0, None)
     Frame = namedtuple(
-        'Frame', 'idx, id, frame, name, width, height, labeled_shapes, tags, shapes, labels')
+        'Frame', 'idx, id, frame, name, width, height, labeled_shapes, tags, shapes, labels, subset')
     Label = namedtuple('Label', 'id, name, color, type')
 
     def __init__(self,
@@ -223,6 +223,7 @@ def __init__(self,
         self._db_data = db_task.data
         self._use_server_track_ids = use_server_track_ids
         self._required_frames = included_frames
+        self._db_subset = db_task.subset
 
         super().__init__(db_task)
 
@@ -268,6 +269,7 @@ def _init_frame_info(self):
                     "path": "frame_{:06d}".format(self.abs_frame_id(frame)),
                     "width": self._db_data.video.width,
                     "height": self._db_data.video.height,
+                    "subset": self._db_subset,
                 } for frame in self.rel_range
             }
         else:
@@ -278,6 +280,7 @@ def _init_frame_info(self):
                     "path": db_image.path,
                     "width": db_image.width,
                     "height": db_image.height,
+                    "subset": self._db_subset,
                 } for db_image in queryset
             }
 
@@ -409,6 +412,7 @@ def get_frame(idx):
                 frames[frame] = CommonData.Frame(
                     idx=idx,
                     id=frame_info.get("id", 0),
+                    subset=frame_info["subset"],
                     frame=frame,
                     name=frame_info["path"],
                     height=frame_info["height"],
@@ -1487,12 +1491,14 @@ def __init__(
         dimension: DimensionType = DimensionType.DIM_2D,
         **kwargs
     ):
+        instance_meta = instance_data.meta[instance_data.META_FIELD]
         dm.SourceExtractor.__init__(
-            self, media_type=dm.Image if dimension == DimensionType.DIM_2D else PointCloud
+            self,
+            media_type=dm.Image if dimension == DimensionType.DIM_2D else PointCloud,
+            subset=instance_meta['subset'],
         )
         CVATDataExtractorMixin.__init__(self, **kwargs)
 
-        instance_meta = instance_data.meta[instance_data.META_FIELD]
         self._categories = self._load_categories(instance_meta['labels'])
         self._user = self._load_user_info(instance_meta) if dimension == DimensionType.DIM_3D else {}
         self._dimension = dimension
@@ -1527,6 +1533,7 @@ def __init__(
                 dm_item = dm.DatasetItem(
                         id=osp.splitext(frame_data.name)[0],
                         annotations=dm_anno, media=dm_image,
+                        subset=frame_data.subset,
                         attributes={'frame': frame_data.frame
                     })
             elif dimension == DimensionType.DIM_3D:
@@ -1543,7 +1550,7 @@ def __init__(
                 dm_item = dm.DatasetItem(
                     id=osp.splitext(osp.split(frame_data.name)[-1])[0],
                     annotations=dm_anno, media=PointCloud(dm_image[0]), related_images=dm_image[1],
-                    attributes=attributes
+                    attributes=attributes, subset=frame_data.subset,
                 )
 
             dm_items.append(dm_item)

cvat/apps/quality_control/quality_reports.py

@@ -1701,7 +1701,7 @@ def _find_gt_conflicts(self):
         gt_job_dataset = self._gt_dataset
 
         for gt_item in gt_job_dataset:
-            ds_item = ds_job_dataset.get(gt_item.id)
+            ds_item = ds_job_dataset.get(id=gt_item.id, subset=gt_item.subset)
             if not ds_item:
                 continue  # we need to compare only intersecting frames
 

tests/python/rest_api/test_tasks.py

@@ -4,6 +4,7 @@
 # SPDX-License-Identifier: MIT
 
 import io
+import itertools
 import json
 import os
 import os.path as osp
@@ -13,6 +14,7 @@
 from http import HTTPStatus
 from itertools import chain, product
 from math import ceil
+from operator import itemgetter
 from pathlib import Path
 from tempfile import NamedTemporaryFile, TemporaryDirectory
 from time import sleep, time
@@ -807,6 +809,32 @@ def test_export_dataset_after_deleting_related_cloud_storage(self, admin_user, t
             response = export_dataset(api_client.tasks_api.retrieve_dataset_endpoint, id=task["id"])
             assert response.data
 
+    @pytest.mark.parametrize(
+        "export_format, default_subset_name, subset_path_template",
+        [
+            ("Datumaro 1.0", "", "images/{subset}"),
+            ("YOLO 1.1", "train", "obj_{subset}_data"),
+        ],
+    )
+    def test_uses_subset_name(
+        self, tasks, admin_user, export_format, default_subset_name, subset_path_template
+    ):
+        group_key_func = itemgetter("subset")
+        subsets_and_tasks = [
+            (subset, next(group))
+            for subset, group in itertools.groupby(
+                sorted(tasks, key=group_key_func),
+                key=group_key_func,
+            )
+        ]
+        for subset_name, task in subsets_and_tasks:
+            response = self._test_export_task(admin_user, tid=task["id"], format=export_format)
+            with zipfile.ZipFile(io.BytesIO(response.data)) as zip_file:
+                subset_path = subset_path_template.format(subset=subset_name or default_subset_name)
+                assert any(
+                    subset_path in path for path in zip_file.namelist()
+                ), f"No {subset_path} in {zip_file.namelist()}"
+
 
 @pytest.mark.usefixtures("restore_db_per_function")
 @pytest.mark.usefixtures("restore_cvat_data")