github/OpenHands
1
1
Fork 0
mirror of https://github.com/All-Hands-AI/OpenHands.git synced 2026-01-09 14:57:59 -05:00
Code Issues Packages Projects Releases Wiki Activity

chore(lint): Apply comprehensive linting and formatting fixes (#10287)

Browse Source 
Co-authored-by: openhands <openhands@all-hands.dev>
This commit is contained in:
Xingyao Wang
2025-08-13 15:13:19 -04:00
committed by GitHub
parent e39bf80239
commit c2f46200c0
164 changed files with 526 additions and 1023 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
evaluation/benchmarks/testgeneval/compute_readability.py
View File

@@ -181,9 +181,7 @@ def distinct_methods_stats(tree, num_lines):
def loops_stats(tree, num_lines):
"""
Calculate the average number of loops.
"""
"""Calculate the average number of loops."""
total_loops = 0
def traverse(node):
@@ -199,9 +197,7 @@ def loops_stats(tree, num_lines):
def branches_stats(tree, num_lines):
"""
Calculate the average number of branches (conditional statements).
"""
"""Calculate the average number of branches (conditional statements)."""
total_branches = 0
def traverse(node):

9
evaluation/benchmarks/testgeneval/eval_infer.py
View File

@@ -192,8 +192,7 @@ def run_mutation_testing(
def grade_test_output(
test_suite: str, instance: pd.Series, test_output: str, test_spec: TestSpec, runtime
):
"""
Two-pass test grading with short-circuiting:
"""Two-pass test grading with short-circuiting:
1. Run all tests to identify passing/failing tests
2. If no failing tests, evaluate coverage immediately
3. Otherwise, run only passing tests for coverage analysis
@@ -280,8 +279,7 @@ def process_instance(
reset_logger: bool = True,
log_dir: str | None = None,
) -> EvalOutput:
"""
Evaluate agent performance on a TestGenEval problem instance.
"""Evaluate agent performance on a TestGenEval problem instance.
Note that this signature differs from the expected input to `run_evaluation`. Use
`functools.partial` to provide optional arguments before passing to the evaluation harness.
@@ -453,8 +451,7 @@ def process_instance(
def count_and_log_fields(evaluated_predictions, fields, key):
"""
Count and log the sum of specified fields in the evaluated predictions,
"""Count and log the sum of specified fields in the evaluated predictions,
ignoring fields with a value of -1. If all values for a field are -1,
return -1.

21
evaluation/benchmarks/testgeneval/log_parsers.py
View File

@@ -4,8 +4,7 @@ from evaluation.benchmarks.testgeneval.constants import TestStatus
def parse_log_pytest(log: str) -> dict[str, str]:
"""
Parser for test logs generated with PyTest framework
"""Parser for test logs generated with PyTest framework
Args:
log (str): log content
@@ -26,8 +25,7 @@ def parse_log_pytest(log: str) -> dict[str, str]:
def parse_log_pytest_options(log: str) -> dict[str, str]:
"""
Parser for test logs generated with PyTest framework with options
"""Parser for test logs generated with PyTest framework with options
Args:
log (str): log content
@@ -61,8 +59,7 @@ def parse_log_pytest_options(log: str) -> dict[str, str]:
def parse_log_django(log: str) -> dict[str, str]:
"""
Parser for test logs generated with Django tester framework
"""Parser for test logs generated with Django tester framework
Args:
log (str): log content
@@ -141,8 +138,7 @@ def parse_log_django(log: str) -> dict[str, str]:
def parse_log_pytest_v2(log: str) -> dict[str, str]:
"""
Parser for test logs generated with PyTest framework (Later Version)
"""Parser for test logs generated with PyTest framework (Later Version)
Args:
log (str): log content
@@ -170,8 +166,7 @@ def parse_log_pytest_v2(log: str) -> dict[str, str]:
def parse_log_seaborn(log: str) -> dict[str, str]:
"""
Parser for test logs generated with seaborn testing framework
"""Parser for test logs generated with seaborn testing framework
Args:
log (str): log content
@@ -196,8 +191,7 @@ def parse_log_seaborn(log: str) -> dict[str, str]:
def parse_log_sympy(log: str) -> dict[str, str]:
"""
Parser for test logs generated with Sympy framework
"""Parser for test logs generated with Sympy framework
Args:
log (str): log content
@@ -229,8 +223,7 @@ def parse_log_sympy(log: str) -> dict[str, str]:
def parse_log_matplotlib(log: str) -> dict[str, str]:
"""
Parser for test logs generated with PyTest framework
"""Parser for test logs generated with PyTest framework
Args:
log (str): log content

45
evaluation/benchmarks/testgeneval/metrics.py
View File

@@ -12,8 +12,7 @@ if sys.getrecursionlimit() < 10_000:
def bleu(gold: list[str], pred: list[str]) -> float:
"""
Calculate BLEU score, using smoothing method 2 with auto reweighting, in the range of 0~100.
"""Calculate BLEU score, using smoothing method 2 with auto reweighting, in the range of 0~100.
:param gold: list of gold tokens
:param pred: list of predicted tokens
@@ -30,8 +29,7 @@ def bleu(gold: list[str], pred: list[str]) -> float:
def batch_bleu(golds: list[list[str]], preds: list[list[str]]) -> list[float]:
"""
Calculate BLEU score for a batch of sentences.
"""Calculate BLEU score for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@@ -43,8 +41,7 @@ def batch_bleu(golds: list[list[str]], preds: list[list[str]]) -> list[float]:
def corpus_bleu(golds: list[list[str]], preds: list[list[str]]) -> float:
"""
Calculate corpus-level BLEU score for a batch of sentences.
"""Calculate corpus-level BLEU score for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@@ -63,8 +60,7 @@ def corpus_bleu(golds: list[list[str]], preds: list[list[str]]) -> float:
def edit_sim(
gold: Union[str, list[str]], pred: Union[str, list[str]], sep: str = ' '
) -> float:
"""
Calculate char-level edit similarity, in the range of 0~100.
"""Calculate char-level edit similarity, in the range of 0~100.
:param gold: gold sentence or list of gold tokens
:param pred: predicted sentence or list of predicted tokens
@@ -85,8 +81,7 @@ def batch_edit_sim(
preds: list[Union[str, list[str]]],
sep: str = ' ',
) -> list[float]:
"""
Calculate char-level edit similarity for a batch of sentences.
"""Calculate char-level edit similarity for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@@ -102,8 +97,7 @@ T = TypeVar('T')
def exact_match(gold: T, pred: T) -> float:
"""
Calculate exact match accuracy, in the range of {0, 100}.
"""Calculate exact match accuracy, in the range of {0, 100}.
:param gold: gold sentence or list of gold tokens
:param pred: predicted sentence or list of predicted tokens
@@ -115,8 +109,7 @@ def exact_match(gold: T, pred: T) -> float:
def batch_exact_match(golds: list[T], preds: list[T]) -> list[float]:
"""
Calculate exact match accuracy for a batch of sentences.
"""Calculate exact match accuracy for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@@ -130,8 +123,7 @@ def batch_exact_match(golds: list[T], preds: list[T]) -> list[float]:
def rouge_l(
gold: Union[str, list[str]], pred: Union[str, list[str]], sep: str = ' '
) -> dict[str, float]:
"""
Calculate ROUGE-L F1, precision, and recall scores, in the range of 0~100.
"""Calculate ROUGE-L F1, precision, and recall scores, in the range of 0~100.
:param gold: gold sentence or list of gold tokens
:param pred: predicted sentence or list of predicted tokens
@@ -156,8 +148,7 @@ def batch_rouge_l(
preds: list[Union[str, list[str]]],
sep: str = ' ',
) -> dict[str, list[float]]:
"""
Calculate ROUGE-L F1, precision, and recall scores for a batch of sentences.
"""Calculate ROUGE-L F1, precision, and recall scores for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@@ -175,8 +166,7 @@ def accuracy(
pred: list[str],
ignore: Optional[Sequence[str]] = None,
) -> float:
"""
Calculate token-level accuracy, in the range of 0~100.
"""Calculate token-level accuracy, in the range of 0~100.
If gold and pred are not the same length, the longer one would be truncated.
:param gold: list of gold tokens
@@ -210,8 +200,7 @@ def batch_accuracy(
preds: list[list[str]],
ignore: Optional[Sequence[str]] = None,
) -> list[float]:
"""
Calculate token-level accuracy for a batch of sentences.
"""Calculate token-level accuracy for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@@ -226,8 +215,7 @@ def batch_accuracy(
def first_match_to_topk(
first_match_list: list[int], k_values: list[int]
) -> dict[int, list[float]]:
"""
Calculate top-k accuracy with the first match ranks (1-indexed).
"""Calculate top-k accuracy with the first match ranks (1-indexed).
:param first_match: first match ranks (1-indexed)
:param k_values: k values to consider
@@ -237,8 +225,7 @@ def first_match_to_topk(
def pass_at_k(n: int, c: int, k: int) -> float:
"""
Sample pass@k metric according to the Codex paper, but in the scale of 0~100.
"""Sample pass@k metric according to the Codex paper, but in the scale of 0~100.
:param n: total number of samples
:param c: number of correct samples
:param k: k in pass@$k$
@@ -251,8 +238,7 @@ def pass_at_k(n: int, c: int, k: int) -> float:
def self_bleu(samples: list[list[str]]) -> float:
"""
Calculate self-BLEU among the samples.
"""Calculate self-BLEU among the samples.
:param samples: the chosen m samples
:return: self-BLEU
"""
@@ -274,8 +260,7 @@ def self_bleu(samples: list[list[str]]) -> float:
def self_edit_distance(samples: list[Union[str, list[str]]], sep=' ') -> float:
"""
Calculate self-edit-distance among the samples.
"""Calculate self-edit-distance among the samples.
:param samples: the chosen m samples
:param sep: the separator between tokens
:return: self-edit-distance

6
evaluation/benchmarks/testgeneval/report_utils.py
View File

@@ -30,8 +30,7 @@ def check_mutation(mutation_output):
def count_methods(code_str):
"""
Counts the number of methods/functions in a given string of code.
"""Counts the number of methods/functions in a given string of code.
Args:
code_str (str): A string containing code.
@@ -46,8 +45,7 @@ def count_methods(code_str):
def get_lines_of_code(code_str):
"""
Extracts lines of code from a given string.
"""Extracts lines of code from a given string.
Args:
code_str (str): A string containing code.

6
evaluation/benchmarks/testgeneval/scripts/eval/build_outputs_ablation.py
View File

@@ -7,8 +7,7 @@ import traceback
def insert_line_in_string(input_string, new_str, insert_line):
"""
Inserts a new line into a string at the specified line number.
"""Inserts a new line into a string at the specified line number.
:param input_string: The original string.
:param new_str: The string to insert.
@@ -29,8 +28,7 @@ def insert_line_in_string(input_string, new_str, insert_line):
def print_string_diff(original, modified):
"""
Prints the differences between two strings line by line.
"""Prints the differences between two strings line by line.
:param original: The original string.
:param modified: The modified string.

10
evaluation/benchmarks/testgeneval/test_filter.py
View File

@@ -37,8 +37,7 @@ def extract_preamble_classes_and_functions(code):
current_position = 0
def extract_class_body(code: str, start_index: int) -> tuple[str, int]:
"""
Extracts the body of a class from the given code starting from the specified index.
"""Extracts the body of a class from the given code starting from the specified index.
Returns the class body and the end index of the class body.
"""
if not code or start_index < 0 or start_index >= len(code):
@@ -168,8 +167,8 @@ def extract_preamble_classes_and_functions(code):
def filter_passing_tests(
test_content: str, test_output: str, repo: str
) -> tuple[str, list[str], list[str]]:
"""
Filter tests based on their execution results.
"""Filter tests based on their execution results.
Returns:
Tuple containing:
- Modified test content with only passing tests
@@ -246,8 +245,7 @@ def filter_passing_tests(
def filter_tests(
test_content: str, test_output: str, repo: str
) -> tuple[str, list[str], list[str]]:
"""
Filter tests using AST parsing to remove failing test functions from the test file.
"""Filter tests using AST parsing to remove failing test functions from the test file.
Non-test functions (e.g. setup or helper methods) and classes (even if all test methods are failing)
are preserved.

14
evaluation/benchmarks/testgeneval/test_spec.py
View File

@@ -20,9 +20,7 @@ DIFF_MODIFIED_FILE_REGEX = r'--- a/(.*)'
@dataclass
class TestSpec:
"""
A dataclass that represents a test specification for a single instance of SWE-bench.
"""
"""A dataclass that represents a test specification for a single instance of SWE-bench."""
instance_id: str
id: str
@@ -86,10 +84,7 @@ def make_test_setup(specs, env_name, repo_directory, includes_tox=False):
def make_test_script_list(test_cmd, specs, env_name, repo_directory):
"""
Runs the tests.
"""
"""Runs the tests."""
includes_tox = 'tox' in test_cmd
eval_commands = make_test_setup(specs, env_name, repo_directory, includes_tox)
eval_commands += [
@@ -104,10 +99,7 @@ def make_test_script_list(test_cmd, specs, env_name, repo_directory):
def make_mutation_script_list(specs, env_name, repo_directory, mutation_timeout):
"""
Runs the tests.
"""
"""Runs the tests."""
eval_commands = make_test_setup(specs, env_name, repo_directory)
eval_commands += [
'cosmic-ray init mutation.toml mutation.sqlite',

7
evaluation/benchmarks/testgeneval/utils.py
View File

@@ -11,8 +11,7 @@ from evaluation.benchmarks.testgeneval.constants import (
def get_test_directives(instance: TestGenEvalInstance) -> list:
"""
Get test directives from the test_patch of a task instance
"""Get test directives from the test_patch of a task instance
Args:
instance (dict): task instance
@@ -43,9 +42,7 @@ def get_test_directives(instance: TestGenEvalInstance) -> list:
def load_testgeneval_dataset(
name='kjain14/testgeneval', split='test', ids=None
) -> list[TestGenEvalInstance]:
"""
Load SWE-bench dataset from Hugging Face Datasets or local .json/.jsonl file
"""
"""Load SWE-bench dataset from Hugging Face Datasets or local .json/.jsonl file"""
# check that all instance IDs are in the dataset
if ids:
ids = set(ids)