Add progress reporters for Datumaro, COCO, VOC, YOLO (#1100)

<!-- Contributing guide:
https://github.com/openvinotoolkit/datumaro/blob/develop/CONTRIBUTING.md
-->

### Summary

<!--
Resolves #111 and #222.
Depends on #1000 (for series of dependent commits).

This PR introduces this capability to make the project better in this
and that.

- Added this feature
- Removed that feature
- Fixed the problem #1234
-->

### How to test
<!-- Describe the testing procedure for reviewers, if changes are
not fully covered by unit tests or manual testing can be complicated.
-->

### Checklist
<!-- Put an 'x' in all the boxes that apply -->
- [ ] I have added unit tests to cover my changes.​
- [ ] I have added integration tests to cover my changes.​
- [x] I have added the description of my changes into
[CHANGELOG](https://github.com/openvinotoolkit/datumaro/blob/develop/CHANGELOG.md).​
- [ ] I have updated the
[documentation](https://github.com/openvinotoolkit/datumaro/tree/develop/docs)
accordingly

### License

- [ ] I submit _my code changes_ under the same [MIT
License](https://github.com/openvinotoolkit/datumaro/blob/develop/LICENSE)
that covers the project.
  Feel free to contact the maintainers if that's a concern.
- [ ] I have updated the license header for each file (see an example
below).

```python
# Copyright (C) 2023 Intel Corporation
#
# SPDX-License-Identifier: MIT
```

CHANGELOG.md

@@ -15,6 +15,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Enhancements
 - Give notice that the deprecation works will be done in datumaro==1.5.0
   (<https://github.com/openvinotoolkit/datumaro/pull/1085>)
+- Unify COCO, Datumaro, VOC, YOLO importer/exporter progress reporter descriptions
+  (<https://github.com/openvinotoolkit/datumaro/pull/1100>)
 
 ### Bug fixes
 - Create cache dir under only writable filesystem

src/datumaro/plugins/data_formats/coco/base.py

@@ -266,7 +266,7 @@ def _stream_items(self) -> Iterator[DatasetItem]:
 
         for img_info, ann_infos in pbars.iter(
             self._page_mapper,
-            desc=f"Parsing image info in '{osp.basename(self._path)}'",
+            desc=f"Importing '{self._subset}'",
         ):
             parsed = self._parse_item(img_info)
             if parsed is None:
@@ -289,7 +289,7 @@ def _parse_anns(self, img_info, ann_info, item):
             self._load_panoptic_ann(ann_info, parsed_annotations=item.annotations)
 
     def _load_items(self, json_data):
-        pbars = self._ctx.progress_reporter.split(2)
+        pbar = self._ctx.progress_reporter
 
         def _gen_ann(info_lists):
             while info_lists:
@@ -298,11 +298,7 @@ def _gen_ann(info_lists):
         items = {}
         img_infos = {}
         img_lists = self._parse_field(json_data, "images", list)
-        for img_info in pbars[0].iter(
-            _gen_ann(img_lists),
-            desc=f"Parsing image info in '{osp.basename(self._path)}'",
-            total=len(img_lists),
-        ):
+        for img_info in _gen_ann(img_lists):
             parsed = self._parse_item(img_info)
             if parsed is None:
                 continue
@@ -315,9 +311,9 @@ def _gen_ann(info_lists):
 
         ann_lists = self._parse_field(json_data, "annotations", list)
 
-        for ann_info in pbars[1].iter(
+        for ann_info in pbar.iter(
             _gen_ann(ann_lists),
-            desc=f"Parsing annotations in '{osp.basename(self._path)}'",
+            desc=f"Importing '{self._subset}'",
             total=len(ann_lists),
         ):
             try:

src/datumaro/plugins/data_formats/coco/exporter.py

@@ -731,7 +731,7 @@ def _apply_impl(self):
             if CocoTask.panoptic in task_converters:
                 self._make_segmentation_dir(subset_name)
 
-            for item in pbar.iter(subset, desc=f"Exporting {subset_name}"):
+            for item in pbar.iter(subset, desc=f"Exporting '{subset_name}'"):
                 try:
                     if self._save_media:
                         if item.media:

src/datumaro/plugins/data_formats/datumaro/base.py

@@ -111,16 +111,17 @@ def _load_categories(parsed) -> Dict:
         return categories
 
     def _load_items(self, parsed) -> List:
-        items = []
-
         item_descs = parsed["items"]
         pbar = self._ctx.progress_reporter
 
         def _gen():
             while item_descs:
                 yield item_descs.pop()
 
-        for item_desc in pbar.iter(_gen(), total=len(item_descs)):
+        items = []
+        for item_desc in pbar.iter(
+            _gen(), desc=f"Importing '{self._subset}'", total=len(item_descs)
+        ):
             item = self._parse_item(item_desc)
             items.append(item)
 

src/datumaro/plugins/data_formats/datumaro/exporter.py

@@ -33,7 +33,7 @@
     _Shape,
 )
 from datumaro.components.crypter import NULL_CRYPTER
-from datumaro.components.dataset_base import DEFAULT_SUBSET_NAME, DatasetItem
+from datumaro.components.dataset_base import DatasetItem
 from datumaro.components.dataset_item_storage import ItemStatus
 from datumaro.components.exporter import ExportContextComponent, Exporter
 from datumaro.components.media import Image, MediaElement, PointCloud
@@ -419,11 +419,12 @@ def _apply_impl(self, pool: Optional[Pool] = None, *args, **kwargs):
             writer.add_infos(self._extractor.infos())
             writer.add_categories(self._extractor.categories())
 
-        for item in self._extractor:
-            subset = item.subset or DEFAULT_SUBSET_NAME
-            writers[subset].add_item(item, pool)
+        pbar = self._ctx.progress_reporter
+        for subset_name, subset in self._extractor.subsets().items():
+            for item in pbar.iter(subset, desc=f"Exporting '{subset_name}'"):
+                writers[subset_name].add_item(item, pool)
 
-            self._check_hash_key_existence(item)
+                self._check_hash_key_existence(item)
 
         for subset, writer in writers.items():
             if self._patch and subset in self._patch.updated_subsets and writer.is_empty():

src/datumaro/plugins/data_formats/voc/base.py

@@ -155,7 +155,7 @@ def __iter__(self):
         )
 
         for item_id in self._ctx.progress_reporter.iter(
-            self._items, desc=f"Parsing boxes in '{self._subset}'"
+            self._items, desc=f"Importing '{self._subset}'"
         ):
             log.debug("Reading item '%s'" % item_id)
             size = None

src/datumaro/plugins/data_formats/yolo/base.py

@@ -285,7 +285,7 @@ def __iter__(self) -> Iterator[DatasetItem]:
         subsets = self._subsets
         pbars = self._ctx.progress_reporter.split(len(subsets))
         for pbar, (subset_name, subset) in zip(pbars, subsets.items()):
-            for item in pbar.iter(subset, desc=f"Parsing '{subset_name}'"):
+            for item in pbar.iter(subset, desc=f"Importing '{subset_name}'"):
                 yield item
 
     def __len__(self):
@@ -332,7 +332,8 @@ def __iter__(self) -> Iterator[DatasetItem]:
         if label_categories is None:
             raise DatasetImportError("label_categories should be not None.")
 
-        for url in self._urls:
+        pbar = self._ctx.progress_reporter
+        for url in pbar.iter(self._urls, desc=f"Importing '{self._subset}'"):
             try:
                 fname = self._get_fname(url)
                 img = Image.from_file(path=self._img_files[fname])