Switch to internal dependency, and fix linter errors

Author: jaredoconnell

pyproject.toml

@@ -56,7 +56,6 @@ dependencies = [
     "pyyaml>=6.0.0",
     "rich",
     "transformers",
-    "click-default-group~=1.2.4"
 ]
 
 [project.optional-dependencies]

src/guidellm/__main__.py

@@ -2,22 +2,21 @@
 import codecs
 from pathlib import Path
 from typing import get_args
-from click_default_group import DefaultGroup
 
 import click
 from pydantic import ValidationError
 
 from guidellm.backend import BackendType
 from guidellm.benchmark import (
     ProfileType,
-    benchmark_generative_text,
     reimport_benchmarks_report,
 )
 from guidellm.benchmark.entrypoints import benchmark_with_scenario
 from guidellm.benchmark.scenario import GenerativeTextScenario, get_builtin_scenarios
 from guidellm.config import print_config
 from guidellm.preprocess.dataset import ShortPromptStrategy, process_dataset
 from guidellm.scheduler import StrategyType
+from guidellm.utils import DefaultGroupHandler
 from guidellm.utils import cli as cli_tools
 
 STRATEGY_PROFILE_CHOICES = set(
@@ -29,11 +28,11 @@
 def cli():
     pass
 
+
 @cli.group(
     help="Commands to run a new benchmark or load a prior one.",
-    cls=DefaultGroup,
+    cls=DefaultGroupHandler,
     default="run",
-    default_if_no_args=True,
 )
 def benchmark():
     pass
@@ -334,15 +333,15 @@ def run(
     is_flag=False,
     flag_value=Path.cwd() / "benchmarks_reexported.json",
     help=(
-        "Allows re-exporting the benchmarks to another format."
+        "Allows re-exporting the benchmarks to another format. "
         "The path to save the output to. If it is a directory, "
         "it will save benchmarks.json under it. "
         "Otherwise, json, yaml, or csv files are supported for output types "
-        "which will be read from the extension for the file path."
-        "Optional. If the output path flag is not provided, the benchmarks "
-        "will not be reexported. If the flag is present but no value is "
-        "specified, it will default to the current directory with the file "
-        "name benchmarks_reexported.json."
+        "which will be read from the extension for the file path. "
+        "This input is optional. If the output path flag is not provided, "
+        "the benchmarks will not be reexported. If the flag is present but "
+        "no value is specified, it will default to the current directory "
+        "with the file name `benchmarks_reexported.json`."
     ),
 )
 def from_file(path, output_path):
@@ -368,7 +367,7 @@ def decode_escaped_str(_ctx, _param, value):
     help=(
         "Print out the available configuration settings that can be set "
         "through environment variables."
-    )
+    ),
 )
 def config():
     print_config()

src/guidellm/benchmark/entrypoints.py

@@ -147,6 +147,7 @@ async def benchmark_generative_text(
 
     return report, saved_path
 
+
 def reimport_benchmarks_report(file: Path, output_path: Optional[Path]) -> None:
     """
     The command-line entry point for re-importing and displaying an

src/guidellm/benchmark/output.py

@@ -242,7 +242,10 @@ def _file_setup(
         if path_suffix in [".csv"]:
             return path, "csv"
 
-        raise ValueError(f"Unsupported file extension: {path_suffix} for {path}; expected json, yaml, or csv.")
+        raise ValueError(
+            f"Unsupported file extension: {path_suffix} for {path}; "
+            "expected json, yaml, or csv."
+        )
 
     @staticmethod
     def _benchmark_desc_headers_and_values(

src/guidellm/utils/__init__.py

@@ -1,4 +1,5 @@
 from .colors import Colors
+from .default_group import DefaultGroupHandler
 from .hf_datasets import (
     SUPPORTED_TYPES,
     save_dataset_to_file,
@@ -20,6 +21,7 @@
 __all__ = [
     "SUPPORTED_TYPES",
     "Colors",
+    "DefaultGroupHandler",
     "EndlessTextCreator",
     "IntegerRangeSampler",
     "check_load_processor",

src/guidellm/utils/default_group.py

@@ -0,0 +1,103 @@
+"""
+File uses code adapted from code with the following license:
+
+Copyright (c) 2015-2023, Heungsub Lee
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification,
+are permitted provided that the following conditions are met:
+
+  Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+  Redistributions in binary form must reproduce the above copyright notice, this
+  list of conditions and the following disclaimer in the documentation and/or
+  other materials provided with the distribution.
+
+  Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+"""
+
+__all__ = ["DefaultGroupHandler"]
+
+import click
+
+
+class DefaultGroupHandler(click.Group):
+    """
+    Allows the migration to a new sub-command by allowing the group to run
+    one of its sub-commands as the no-args default command.
+    """
+
+    def __init__(self, *args, **kwargs):
+        # To resolve as the default command.
+        if not kwargs.get('ignore_unknown_options', True):
+            raise ValueError('Default group accepts unknown options')
+        self.ignore_unknown_options = True
+        self.default_cmd_name = kwargs.pop('default', None)
+        self.default_if_no_args = kwargs.pop('default_if_no_args', False)
+        super(DefaultGroupHandler, self).__init__(*args, **kwargs)
+
+    def parse_args(self, ctx, args):
+        if not args and self.default_if_no_args:
+            args.insert(0, self.default_cmd_name)
+        return super(DefaultGroupHandler, self).parse_args(ctx, args)
+
+    def get_command(self, ctx, cmd_name):
+        if cmd_name not in self.commands:
+            # If it doesn't match an existing command, use the default command name.
+            ctx.arg0 = cmd_name
+            cmd_name = self.default_cmd_name
+        return super(DefaultGroupHandler, self).get_command(ctx, cmd_name)
+
+    def resolve_command(self, ctx, args):
+        base = super(DefaultGroupHandler, self)
+        cmd_name, cmd, args = base.resolve_command(ctx, args)
+        if hasattr(ctx, 'arg0'):
+            args.insert(0, ctx.arg0)
+            cmd_name = cmd.name
+        return cmd_name, cmd, args
+
+    def format_commands(self, ctx, formatter):
+        """
+        Used to wrap the default formatter to clarify which command is the default.
+        """
+        formatter = DefaultCommandFormatter(self, formatter, mark=' (default)')
+        return super(DefaultGroupHandler, self).format_commands(ctx, formatter)
+
+
+class DefaultCommandFormatter(object):
+    """
+    Wraps a formatter to edit the line for the default command to mark it
+    with the specified mark string.
+    """
+
+    def __init__(self, group, formatter, mark='*'):
+        self.group = group
+        self.formatter = formatter
+        self.mark = mark
+        super().__init__()
+
+    def __getattr__(self, attr):
+        return getattr(self.formatter, attr)
+
+    def write_dl(self, rows, *args, **kwargs):
+        rows_ = []
+        for cmd_name, help_msg in rows:
+            if cmd_name == self.group.default_cmd_name:
+                rows_.insert(0, (cmd_name + self.mark, help_msg))
+            else:
+                rows_.append((cmd_name, help_msg))
+        return self.formatter.write_dl(rows_, *args, **kwargs)

tests/unit/entrypoints/test_benchmark_from_file_entrypoint.py

@@ -1,9 +1,9 @@
+import filecmp
 import os
 import unittest
 from pathlib import Path
 
 import pytest
-import filecmp
 
 from guidellm.benchmark import reimport_benchmarks_report
 
@@ -18,13 +18,14 @@ def _() -> Path:
 
     return _
 
+
 @pytest.fixture
 def cleanup():
-    to_delete = []
+    to_delete: list[Path] = []
     yield to_delete
     for item in to_delete:
-        if os.path.exists(item):
-            os.remove(item)
+        if item.exists():
+            item.unlink()  # Deletes the file
 
 
 def test_display_entrypoint_json(capfd, get_test_asset_dir):
@@ -58,14 +59,16 @@ def generic_test_display_entrypoint(filename, capfd, get_test_asset_dir):
             expected_output = file.read()
         assert out == expected_output
 
+
 def test_reexporting_benchmark(get_test_asset_dir, cleanup):
     asset_dir = get_test_asset_dir()
     source_file = asset_dir / "benchmarks_stripped.json"
     exported_file = asset_dir / "benchmarks_reexported.json"
-    # If you need to inspect the output to see why it failed, comment out the following statement.
+    # If you need to inspect the output to see why it failed, comment out
+    # the cleanup statement.
     cleanup.append(exported_file)
     if exported_file.exists():
-        os.remove(exported_file)
+        exported_file.unlink()
     reimport_benchmarks_report(source_file, exported_file)
     # The reexported file should exist and be identical to the source.
     assert exported_file.exists()