⚡️ Speed up function parse_log_pytest_v2 by 145%

[codeflash-ai]

📄 145% (1.45x) speedup for parse_log_pytest_v2 in evaluation/benchmarks/testgeneval/log_parsers.py

⏱️ Runtime : 11.1 milliseconds → 4.53 milliseconds (best of 803 runs)

📝 Explanation and details

Key Optimizations.

1. Precompiled Regex Pattern: The regular expression is precompiled before the loop to avoid recompilation on each iteration, thereby improving efficiency.

2. Set Membership Checking: Utilizing sets for start_status_set and end_status_set allows for O(1) average-time complexity membership tests, instead of O(n) list checks.

3. Reduction in Split Operations: The number of split operations is minimized by performing them only when necessary and using more efficient methods like split(' ', 1) and rsplit(' ', 1) to manage line parsing.

These optimizations ensure faster execution and reduced overhead.

✅ Correctness verification report:

Test	Status
⚙️ Existing Unit Tests	🔘 None Found
🌀 Generated Regression Tests	✅ 24 Passed
⏪ Replay Tests	🔘 None Found
🔎 Concolic Coverage Tests	✅ 1 Passed
📊 Tests Coverage	100.0%

🌀 Generated Regression Tests Details

import re
from enum import Enum  # used to create the TestStatus enum for testing

# imports
import pytest  # used for our unit tests
from evaluation.benchmarks.testgeneval.log_parsers import parse_log_pytest_v2


# Mocking the TestStatus Enum for testing purposes
class TestStatus(Enum):
    PASSED = "PASSED"
    FAILED = "FAILED"
    SKIPPED = "SKIPPED"
from evaluation.benchmarks.testgeneval.log_parsers import parse_log_pytest_v2

# unit tests

def test_single_passed_case():
    """Test a simple log with one passed test case"""
    log = "PASSED test_case_1"
    expected = {"test_case_1": "PASSED"}
    codeflash_output = parse_log_pytest_v2(log)

def test_single_failed_case():
    """Test a simple log with one failed test case"""
    log = "FAILED test_case_2"
    expected = {"test_case_2": "FAILED"}
    codeflash_output = parse_log_pytest_v2(log)

def test_multiple_test_cases():
    """Test a log with multiple test cases"""
    log = "PASSED test_case_1\nFAILED test_case_2\nSKIPPED test_case_3"
    expected = {
        "test_case_1": "PASSED",
        "test_case_2": "FAILED",
        "test_case_3": "SKIPPED"
    }
    codeflash_output = parse_log_pytest_v2(log)

def test_empty_log():
    """Test an empty log"""
    log = ""
    expected = {}
    codeflash_output = parse_log_pytest_v2(log)

def test_log_with_escape_characters():
    """Test a log with only escape characters"""
    log = "\x01\x02\x03"
    expected = {}
    codeflash_output = parse_log_pytest_v2(log)

def test_log_with_ansi_codes():
    """Test a log with ANSI escape codes"""
    log = "[32mPASSED test_case_1[0m"
    expected = {"test_case_1": "PASSED"}
    codeflash_output = parse_log_pytest_v2(log)

def test_incomplete_information():
    """Test a log with incomplete information"""
    log = "PASSED"
    expected = {}
    codeflash_output = parse_log_pytest_v2(log)

def test_older_pytest_format():
    """Test a log with older pytest format"""
    log = "test_case_1 PASSED"
    expected = {"test_case_1": "PASSED"}
    codeflash_output = parse_log_pytest_v2(log)

def test_mixed_format_log():
    """Test a log with mixed format lines"""
    log = "PASSED test_case_1\nFAILED test_case_2\ntest_case_3 SKIPPED"
    expected = {
        "test_case_1": "PASSED",
        "test_case_2": "FAILED",
        "test_case_3": "SKIPPED"
    }
    codeflash_output = parse_log_pytest_v2(log)

def test_large_log():
    """Test a large log with many test cases"""
    log = "\n".join(f"PASSED test_case_{i}" if i % 2 == 0 else f"FAILED test_case_{i}" for i in range(1000))
    expected = {f"test_case_{i}": "PASSED" if i % 2 == 0 else "FAILED" for i in range(1000)}
    codeflash_output = parse_log_pytest_v2(log)

def test_special_characters_in_test_names():
    """Test a log with special characters in test names"""
    log = "PASSED test_case_1_special!@#\nFAILED test case with spaces"
    expected = {
        "test_case_1_special!@#": "PASSED",
        "test": "FAILED"  # Only the first part is considered as the test name
    }
    codeflash_output = parse_log_pytest_v2(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_v2


# Mocking the TestStatus enum for testing purposes
class TestStatus(Enum):
    PASSED = "PASSED"
    FAILED = "FAILED"
    SKIPPED = "SKIPPED"
from evaluation.benchmarks.testgeneval.log_parsers import parse_log_pytest_v2

# unit tests

def test_single_test_case_status_at_start():
    # Test single test case with status at the start
    log = "PASSED test_case_1"
    codeflash_output = parse_log_pytest_v2(log)

def test_single_test_case_status_at_end():
    # Test single test case with status at the end
    log = "test_case_1 PASSED"
    codeflash_output = parse_log_pytest_v2(log)

def test_empty_log():
    # Test empty log
    log = ""
    codeflash_output = parse_log_pytest_v2(log)

def test_log_with_only_control_characters():
    # Test log with only control characters
    log = "\x01\x02\x03"
    codeflash_output = parse_log_pytest_v2(log)

def test_log_with_only_ansi_escape_codes():
    # Test log with only ANSI escape codes
    log = "[32m"
    codeflash_output = parse_log_pytest_v2(log)

def test_mixed_content():
    # Test log with mixed content
    log = "Random text\nPASSED test_case_1\nFAILED test_case_2"
    codeflash_output = parse_log_pytest_v2(log)

def test_multiple_test_cases():
    # Test multiple test cases
    log = "PASSED test_case_1\nFAILED test_case_2\nSKIPPED test_case_3"
    codeflash_output = parse_log_pytest_v2(log)

def test_test_cases_with_similar_names():
    # Test cases with similar names
    log = "PASSED test_case_1\nFAILED test_case_1_variant"
    codeflash_output = parse_log_pytest_v2(log)

def test_malformed_lines():
    # Test malformed lines
    log = "test_case_1 - PASSED\nPASSED"
    codeflash_output = parse_log_pytest_v2(log)

def test_large_log_file():
    # Test large log file
    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_v2(log)

def test_mixed_large_log():
    # Test mixed large log
    log = "\n".join([f"PASSED test_case_{i}" if i % 2 == 0 else "Random text" for i in range(1000)])
    expected = {f"test_case_{i}": "PASSED" for i in range(0, 1000, 2)}
    codeflash_output = parse_log_pytest_v2(log)

def test_case_sensitivity():
    # Test case sensitivity
    log = "passed test_case_1"
    codeflash_output = parse_log_pytest_v2(log)

def test_whitespace_variations():
    # Test whitespace variations
    log = "  PASSED   test_case_1  "
    codeflash_output = parse_log_pytest_v2(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_v2

def test_parse_log_pytest_v2():
    parse_log_pytest_v2('')

To edit these changes git checkout codeflash/optimize-parse_log_pytest_v2-m8wz4pcj and push.