⚡️ Speed up function parse_log_pytest_options by 230%

[codeflash-ai]

📄 230% (2.30x) speedup for parse_log_pytest_options in evaluation/benchmarks/testgeneval/log_parsers.py

⏱️ Runtime : 7.10 milliseconds → 2.15 milliseconds (best of 941 runs)

📝 Explanation and details

Modifications and Optimizations.

1. Set for TestStatus Check: I used a set comprehension to generate test_status_values which allows O(1) lookup times for line_status checks, instead of iterating through the TestStatus Enum on each iteration.

2. Regex Direct Match: Directly used match instead of search to ensure we are checking only at the start of the test case string. This is slightly more optimal when we know the starting position.

3. Conditional Logic Simplification: Simplified the condition to modify option string when it's necessary, avoiding redundant checks inside the loop.

These changes should improve the runtime efficiency while preserving the original functionality and output, especially when parsing large log files.

✅ Correctness verification report:

Test	Status
⚙️ Existing Unit Tests	🔘 None Found
🌀 Generated Regression Tests	✅ 26 Passed
⏪ Replay Tests	🔘 None Found
🔎 Concolic Coverage Tests	✅ 2 Passed
📊 Tests Coverage	100.0%

🌀 Generated Regression Tests Details

import re
from enum import Enum

# imports
import pytest  # used for our unit tests
from evaluation.benchmarks.testgeneval.log_parsers import \
    parse_log_pytest_options


# Mocking TestStatus for testing purposes
class TestStatus(Enum):
    PASSED = "PASSED"
    FAILED = "FAILED"
    SKIPPED = "SKIPPED"
from evaluation.benchmarks.testgeneval.log_parsers import \
    parse_log_pytest_options


# unit tests
def test_single_test_case_without_options():
    log = "PASSED test_case_1"
    expected = {"test_case_1": "PASSED"}
    codeflash_output = parse_log_pytest_options(log)

def test_single_test_case_with_options():
    log = "PASSED test_case_1[option1]"
    expected = {"test_case_1[option1]": "PASSED"}
    codeflash_output = parse_log_pytest_options(log)

def test_multiple_test_cases_without_options():
    log = "PASSED test_case_1\nFAILED test_case_2"
    expected = {"test_case_1": "PASSED", "test_case_2": "FAILED"}
    codeflash_output = parse_log_pytest_options(log)

def test_multiple_test_cases_with_mixed_options():
    log = "PASSED test_case_1[option1]\nFAILED test_case_2"
    expected = {"test_case_1[option1]": "PASSED", "test_case_2": "FAILED"}
    codeflash_output = parse_log_pytest_options(log)

def test_empty_log():
    log = ""
    expected = {}
    codeflash_output = parse_log_pytest_options(log)

def test_malformed_log_lines():
    log = "UNKNOWN test_case_1"
    expected = {}
    codeflash_output = parse_log_pytest_options(log)

def test_test_case_without_status():
    log = "test_case_1"
    expected = {}
    codeflash_output = parse_log_pytest_options(log)

def test_options_with_leading_slashes():
    log = "PASSED test_case_1[/option1]"
    expected = {"test_case_1[/option1]": "PASSED"}
    codeflash_output = parse_log_pytest_options(log)

def test_options_with_asterisks():
    log = "PASSED test_case_1[opt*ion]"
    expected = {"test_case_1[opt*ion]": "PASSED"}
    codeflash_output = parse_log_pytest_options(log)

def test_failed_test_case_formatting():
    log = "FAILED - test_case_1"
    expected = {"test_case_1": "FAILED"}
    codeflash_output = parse_log_pytest_options(log)

def test_large_number_of_test_cases():
    log = "\n".join(f"PASSED test_case_{i}" for i in range(1000))
    expected = {f"test_case_{i}": "PASSED" for i in range(1000)}
    codeflash_output = parse_log_pytest_options(log)

def test_duplicate_test_names():
    log = "PASSED test_case_1\nFAILED test_case_1"
    expected = {"test_case_1": "FAILED"}
    codeflash_output = parse_log_pytest_options(log)

def test_non_standard_statuses():
    log = "SKIPPED test_case_1"
    expected = {"test_case_1": "SKIPPED"}
    codeflash_output = parse_log_pytest_options(log)

def test_different_line_endings():
    log = "PASSED test_case_1\r\nFAILED test_case_2"
    expected = {"test_case_1": "PASSED", "test_case_2": "FAILED"}
    codeflash_output = parse_log_pytest_options(log)
# codeflash_output is used to check that the output of the original code is the same as that of the optimized code.

import re
from enum import Enum

# imports
import pytest  # used for our unit tests
from evaluation.benchmarks.testgeneval.log_parsers import \
    parse_log_pytest_options


# Mocking TestStatus Enum for testing purposes
class TestStatus(Enum):
    PASSED = "PASSED"
    FAILED = "FAILED"
    SKIPPED = "SKIPPED"
from evaluation.benchmarks.testgeneval.log_parsers import \
    parse_log_pytest_options

# unit tests

def test_single_test_case_with_status():
    # Basic test with a single test case
    log = "PASSED test_case_1"
    expected = {"test_case_1": "PASSED"}
    codeflash_output = parse_log_pytest_options(log)

def test_test_case_with_simple_option():
    # Test with a test case that includes a simple option
    log = "PASSED test_case_2[option1]"
    expected = {"test_case_2[option1]": "PASSED"}
    codeflash_output = parse_log_pytest_options(log)

def test_test_case_with_complex_option():
    # Test with a test case that includes a complex option
    log = "FAILED test_case_3[/path/to/option2]"
    expected = {"test_case_3[/option2]": "FAILED"}
    codeflash_output = parse_log_pytest_options(log)

def test_failed_test_case_with_dash():
    # Test with a failed test case that includes a dash
    log = "FAILED - test_case_4"
    expected = {"test_case_4": "FAILED"}
    codeflash_output = parse_log_pytest_options(log)

def test_empty_log():
    # Test with an empty log
    log = ""
    expected = {}
    codeflash_output = parse_log_pytest_options(log)

def test_log_with_only_status():
    # Test with a log line that only contains a status
    log = "PASSED"
    expected = {}
    codeflash_output = parse_log_pytest_options(log)

def test_multiple_test_cases():
    # Test with multiple test cases in a single log
    log = "PASSED test_case_5\nFAILED test_case_6[option3]"
    expected = {"test_case_5": "PASSED", "test_case_6[option3]": "FAILED"}
    codeflash_output = parse_log_pytest_options(log)

def test_malformed_test_case_line():
    # Test with a malformed test case line
    log = "UNKNOWN test_case_7"
    expected = {}
    codeflash_output = parse_log_pytest_options(log)

def test_test_case_with_nested_options():
    # Test with a test case that includes nested options
    log = "PASSED test_case_8[option4[inner_option]]"
    expected = {"test_case_8[option4[inner_option]]": "PASSED"}
    codeflash_output = parse_log_pytest_options(log)

def test_large_log():
    # Large scale test with many entries
    log = "\n".join([f"PASSED test_case_{i}" for i in range(1000)])
    expected = {f"test_case_{i}": "PASSED" for i in range(1000)}
    codeflash_output = parse_log_pytest_options(log)

def test_special_characters_in_test_names():
    # Test with special characters in test names or options
    log = "PASSED test_case_9[opt!on5]"
    expected = {"test_case_9[opt!on5]": "PASSED"}
    codeflash_output = parse_log_pytest_options(log)

def test_stress_test_with_large_input():
    # Stress test with a very large input
    log = "\n".join([f"PASSED test_case_{i}[option]" for i in range(1000)])
    expected = {f"test_case_{i}[option]": "PASSED" for i in range(1000)}
    codeflash_output = parse_log_pytest_options(log)
# codeflash_output is used to check that the output of the original code is the same as that of the optimized code.

from evaluation.benchmarks.testgeneval.log_parsers import parse_log_pytest_options

def test_parse_log_pytest_options():
    parse_log_pytest_options('FAILED - \x00\x00\n')

def test_parse_log_pytest_options_2():
    parse_log_pytest_options('XFAIL')

To edit these changes git checkout codeflash/optimize-parse_log_pytest_options-m8wywa7j and push.