Add a new CLI command: datum format (#1570)

### Summary

- This PR resolves https://jira.devtools.intel.com/browse/CVS-144954 and
#1545
- Add a new CLI command: `datum format`. It displays a list of data
format names supported by Datumaro. It can be useful for quick reference
of data format name used for other CLI command such as `datum convert
-if <data-format> -f <data-format>`.

### How to test
Added unit tests as well.

### Checklist
<!-- Put an 'x' in all the boxes that apply -->
- [x] 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).​
- [x] I have updated the
[documentation](https://github.com/openvinotoolkit/datumaro/tree/develop/docs)
accordingly

### License

- [x] 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.
- [x] I have updated the license header for each file (see an example
below).

```python
# Copyright (C) 2024 Intel Corporation
#
# SPDX-License-Identifier: MIT
```

---------

Signed-off-by: Kim, Vinnam <vinnam.kim@intel.com>

CHANGELOG.md

@@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## \[unreleased\]
 ### New features
+- Add a new CLI command: datum format
+  (<https://github.com/openvinotoolkit/datumaro/pull/1570>)
 
 ### Enhancements
 

docs/source/docs/command-reference/helper/format.md

@@ -0,0 +1,22 @@
+# Format
+
+## List Supported Data Formats
+
+This command shows a list of supported import/export data formats in Datumaro.
+It is useful on a quick reference of data format name used for other CLI command such as [convert](../context_free/convert.md), [import](../context/sources.md#import-dataset), or [export](../context/export.md#export-datasets). For more detailed guides on each data format, please visit [our Data Formats section](../../data-formats/formats/index.rst).
+
+Usage:
+
+```console
+usage: datum format [-h] [-li | -le] [-d DELIMITER]
+```
+
+Parameters:
+- `-h, --help` - Print the help message and exit.
+- `-d DELIMITER, --delimiter DELIMITER` - Seperator used to list data format names (default: `\n`). For example, `datum format -d ','` command displays
+  ```console
+  Supported import formats:
+  ade20k2017,ade20k2020,align_celeba,...
+  ```
+- `-li, --list-import` - List all supported import data format names
+- `-le, --list-export` - List all supported export data format names

docs/source/docs/command-reference/helper/index.rst

@@ -0,0 +1,9 @@
+===============
+Helper Commands
+===============
+
+.. toctree::
+    :maxdepth: 1
+    :glob:
+
+    *

docs/source/docs/command-reference/overview.rst

@@ -2,8 +2,8 @@
 Overview
 ========
 
-The command line is split into the separate ``commands`` (:ref:`Context Commands`)
-and command ``contexts`` (:ref:`Context-free Commands`).
+The command line is split into three groups:
+``commands`` (:ref:`Context Commands`), command ``contexts`` (:ref:`Context-free Commands`), and ``helpers`` (:ref:`Helper Commands`).
 Contexts group multiple commands related to a specific topic, e.g.
 project operations, data source operations etc. Almost all the commands
 operate on projects, so the ``project`` context and commands without a context

docs/source/docs/explanation/command_line.dot

@@ -32,6 +32,11 @@ digraph command_line {
         "util";
     }
 
+    subgraph helper {
+        label = "Helper";
+        "format";
+    }
+
     subgraph cluster_model {
         label = "Model";
         "madd" [label = "add";];
@@ -70,7 +75,7 @@ digraph command_line {
         "split_video";
     }
 
-    "datum" -> {"convert" "detect" "compare" "dinfo" "download" "explain" "filter" "generate" "merge" "patch" "search" "stats" "transform" "validate"};
+    "datum" -> {"convert" "detect" "compare" "dinfo" "download" "explain" "filter" "generate" "merge" "patch" "search" "stats" "transform" "validate" "format"};
     "datum" -> {"model" "project" "source" "util"};
     "model" -> {"madd" "mremove" "run" "minfo"};
     "project" -> {"add" "create" "export" "import" "remove"};

docs/source/docs/index.rst

@@ -48,6 +48,7 @@ Docs
   command-reference/overview
   command-reference/context_free/index
   command-reference/context/index
+  command-reference/helper/index
 
 .. toctree::
   :maxdepth: 1

src/datumaro/cli/__main__.py

@@ -16,7 +16,7 @@
     send_command_success_info,
 )
 from ..version import __version__
-from . import contexts
+from . import contexts, helpers
 from .commands import get_non_project_commands, get_project_commands
 from .util import add_subparser, make_subcommands_help
 from .util.errors import CliException
@@ -80,9 +80,19 @@ def _get_known_contexts():
     ]
 
 
+def _get_helper_commands():
+    return [
+        (
+            "format",
+            helpers.format,
+            "List and show information about supported import/export data formats",
+        ),
+    ]
+
+
 def _get_sensitive_args():
     known_contexts = _get_known_contexts()
-    known_commands = get_project_commands() + get_non_project_commands()
+    known_commands = get_project_commands() + get_non_project_commands() + _get_helper_commands()
 
     res = {}
     for _, command, _ in known_contexts + known_commands:
@@ -104,6 +114,7 @@ def make_parser():
 
     known_contexts = _get_known_contexts()
     known_commands = get_non_project_commands()
+    known_helpers = _get_helper_commands()
 
     # Argparse doesn't support subparser groups:
     # https://stackoverflow.com/questions/32017020/grouping-argparse-subparser-arguments
@@ -118,6 +129,11 @@ def make_parser():
             subcommands_desc += "\n"
         subcommands_desc += "Context-free Commands:\n"
         subcommands_desc += make_subcommands_help(known_commands, help_line_start)
+    if known_helpers:
+        if subcommands_desc:
+            subcommands_desc += "\n"
+        subcommands_desc += "Helper Commands:\n"
+        subcommands_desc += make_subcommands_help(known_helpers, help_line_start)
     if subcommands_desc:
         subcommands_desc += (
             "\nRun '%s COMMAND --help' for more information on a command." % parser.prog
@@ -126,7 +142,7 @@ def make_parser():
     subcommands = parser.add_subparsers(
         title=subcommands_desc, description="", help=argparse.SUPPRESS
     )
-    for command_name, command, _ in known_contexts + known_commands:
+    for command_name, command, _ in known_contexts + known_commands + known_helpers:
         if command is not None:
             add_subparser(subcommands, command_name, command.build_parser)
 

src/datumaro/cli/helpers/__init__.py

@@ -0,0 +1,5 @@
+# Copyright (C) 2024 Intel Corporation
+#
+# SPDX-License-Identifier: MIT
+
+from . import format

src/datumaro/cli/helpers/format.py

@@ -0,0 +1,92 @@
+# Copyright (C) 2024 Intel Corporation
+#
+# SPDX-License-Identifier: MIT
+
+import argparse
+import os
+
+from datumaro.cli.util import MultilineFormatter
+
+
+def build_parser(parser_ctor=argparse.ArgumentParser):
+    parser = parser_ctor(
+        help="List supported import/export data formats",
+        description="""
+        List supported import/export data format names.
+        For more detailed guides on each data format,
+        please visit our documentation website:
+        https://openvinotoolkit.github.io/datumaro/stable/docs/data-formats/formats
+        |n
+        |n
+        Examples:|n
+        - List supported import/export data format names:|n
+        |s|s%(prog)s|n
+        |n
+        - List only supported import data format names:|n
+        |s|s%(prog)s --list-import|n
+        |n
+        - List only supported export data format names:|n
+        |s|s%(prog)s --list-export|n
+        |n
+        - List with comma delimiter:|n
+        |s|s%(prog)s --delimiter ','
+        """,
+        formatter_class=MultilineFormatter,
+    )
+
+    group = parser.add_argument_group()
+    exclusive_group = group.add_mutually_exclusive_group(required=False)
+
+    exclusive_group.add_argument(
+        "-li",
+        "--list-import",
+        action="store_true",
+        help="List all supported import data format names",
+    )
+    exclusive_group.add_argument(
+        "-le",
+        "--list-export",
+        action="store_true",
+        help="List all supported export data format names",
+    )
+    parser.add_argument(
+        "-d",
+        "--delimiter",
+        type=str,
+        default=os.linesep,
+        help="Seperator used to list data format names (default: \\n)",
+    )
+
+    parser.set_defaults(command=format_command)
+    return parser
+
+
+def get_sensitive_args():
+    return {
+        format_command: ["list", "show"],
+    }
+
+
+def format_command(args: argparse.Namespace) -> None:
+    from datumaro.components.environment import DEFAULT_ENVIRONMENT
+
+    delimiter = args.delimiter
+
+    if args.list_import:
+        builtin_readers = sorted(
+            set(DEFAULT_ENVIRONMENT.importers) | set(DEFAULT_ENVIRONMENT.extractors)
+        )
+        print(delimiter.join(builtin_readers))
+        return
+
+    if args.list_export:
+        builtin_writers = sorted(DEFAULT_ENVIRONMENT.exporters)
+        print(delimiter.join(builtin_writers))
+        return
+
+    builtin_readers = sorted(
+        set(DEFAULT_ENVIRONMENT.importers) | set(DEFAULT_ENVIRONMENT.extractors)
+    )
+    builtin_writers = sorted(DEFAULT_ENVIRONMENT.exporters)
+    print(f"Supported import formats:\n{delimiter.join(builtin_readers)}")
+    print(f"Supported export formats:\n{delimiter.join(builtin_writers)}")

tests/unit/cli/test_helper.py

@@ -0,0 +1,36 @@
+# Copyright (C) 2024 Intel Corporation
+#
+# SPDX-License-Identifier: MIT
+
+from argparse import ArgumentParser, Namespace
+
+import pytest
+
+from datumaro.cli.helpers.format import build_parser, format_command
+
+# from datumaro.cli.__main__ import make_parser
+
+
+class FormatTest:
+    def test_build_parser(self):
+        parser = build_parser(lambda help, **kwargs: ArgumentParser(**kwargs))
+        assert isinstance(parser, ArgumentParser)
+
+        args = parser.parse_args(["--list-import"])
+        assert args.list_import
+
+        args = parser.parse_args(["--list-export"])
+        assert args.list_export
+
+        args = parser.parse_args(["--delimiter", ","])
+        assert args.delimiter == ","
+
+    @pytest.mark.parametrize(
+        "list_import,list_export", [(True, False), (False, True), (False, False)]
+    )
+    def test_format_command(
+        self, list_import: bool, list_export: bool, capsys: pytest.CaptureFixture
+    ):
+        format_command(Namespace(delimiter="\n", list_import=list_import, list_export=list_export))
+        out, _ = capsys.readouterr()
+        assert "coco" in out