⚡️ Speed up method CodeCommitProvider._is_valid_codecommit_hostname by 68%

[codeflash-ai]

📄 68% (0.68x) speedup for CodeCommitProvider._is_valid_codecommit_hostname in pr_agent/git_providers/codecommit_provider.py

⏱️ Runtime : 861 microseconds → 514 microseconds (best of 164 runs)

📝 Explanation and details

The optimization pre-compiles the regex pattern into a module-level constant _CODECOMMIT_HOSTNAME_PATTERN instead of recompiling it on every function call. This eliminates the overhead of regex compilation that occurs each time _is_valid_codecommit_hostname is invoked.

Key changes:

• Added _CODECOMMIT_HOSTNAME_PATTERN = re.compile(r"^[a-z]{2}-(gov-)?[a-z]+-\d\.console\.aws\.amazon\.com$") at module level
• Replaced re.match(pattern, hostname) with _CODECOMMIT_HOSTNAME_PATTERN.match(hostname)

Why it's faster:
In Python, re.match() compiles the regex pattern every time it's called, which involves parsing the pattern string and building the finite state machine. By pre-compiling the pattern once at module import time, we eliminate this compilation overhead on each function call. The compiled pattern object's .match() method directly executes the pre-built state machine.

Performance characteristics:
The optimization shows consistent 47-72% speedups across all test cases, with particularly strong performance on:

• Large batch processing (59-72% faster on bulk hostname validation)
• Invalid hostname detection (68-73% faster, likely due to early regex failure detection)
• Edge cases with malformed inputs (68% faster)

This optimization is especially valuable for applications that validate many hostnames or call this function frequently, as the regex compilation cost is amortized across all calls.

✅ Correctness verification report:

Test	Status
⚙️ Existing Unit Tests	✅ 42 Passed
🌀 Generated Regression Tests	✅ 1862 Passed
⏪ Replay Tests	🔘 None Found
🔎 Concolic Coverage Tests	🔘 None Found
📊 Tests Coverage	100.0%

⚙️ Existing Unit Tests and Runtime

Test File::Test Function	Original ⏱️	Optimized ⏱️	Speedup
unittest/test_codecommit_provider.py::TestCodeCommitProvider.test_is_valid_codecommit_hostname	19.2μs	12.8μs	49.8%✅

🌀 Generated Regression Tests and Runtime

import re

# imports
import pytest  # used for our unit tests
from pr_agent.git_providers.codecommit_provider import CodeCommitProvider


def _is_valid_codecommit_hostname(hostname: str) -> bool:
    """
    Check if the provided hostname is a valid AWS CodeCommit hostname.

    This is not an exhaustive check of AWS region names,
    but instead uses a regex to check for matching AWS region patterns.

    Args:
    - hostname: the hostname to check

    Returns:
    - bool: True if the hostname is valid, False otherwise.
    """
    return re.match(r"^[a-z]{2}-(gov-)?[a-z]+-\d\.console\.aws\.amazon\.com$", hostname) is not None

# unit tests

# 1. Basic Test Cases














#------------------------------------------------
import re

# imports
import pytest  # used for our unit tests
from pr_agent.git_providers.codecommit_provider import CodeCommitProvider

# unit tests

# 1. Basic Test Cases

@pytest.mark.parametrize("hostname", [
    # Standard AWS regions
    "us-east-1.console.aws.amazon.com",
    "eu-west-3.console.aws.amazon.com",
    "ap-southeast-2.console.aws.amazon.com",
    "ca-central-1.console.aws.amazon.com",
    # GovCloud region
    "us-gov-west-1.console.aws.amazon.com",
    "us-gov-east-1.console.aws.amazon.com",
])
def test_valid_codecommit_hostnames_basic(hostname):
    """Test valid CodeCommit hostnames for standard and gov regions."""
    codeflash_output = CodeCommitProvider._is_valid_codecommit_hostname(hostname) # 12.2μs -> 8.25μs (48.2% faster)

@pytest.mark.parametrize("hostname", [
    # Invalid: missing region number
    "us-east.console.aws.amazon.com",
    # Invalid: region number not at end
    "us-east-1a.console.aws.amazon.com",
    # Invalid: wrong domain
    "us-east-1.console.aws.amazon.org",
    # Invalid: missing .console
    "us-east-1.aws.amazon.com",
    # Invalid: missing .amazon
    "us-east-1.console.aws.com",
    # Invalid: missing .com
    "us-east-1.console.aws.amazon",
    # Invalid: incomplete
    "us-east-1",
    "",
    # Invalid: extra text
    "us-east-1.console.aws.amazon.com.extra",
])
def test_invalid_codecommit_hostnames_basic(hostname):
    """Test clearly invalid CodeCommit hostnames."""
    codeflash_output = CodeCommitProvider._is_valid_codecommit_hostname(hostname) # 13.2μs -> 7.66μs (72.8% faster)

# 2. Edge Test Cases

@pytest.mark.parametrize("hostname", [
    # Uppercase letters (should be invalid)
    "US-EAST-1.console.aws.amazon.com",
    "Us-east-1.console.aws.amazon.com",
    # Leading/trailing whitespace
    " us-east-1.console.aws.amazon.com",
    "us-east-1.console.aws.amazon.com ",
    # Embedded whitespace
    "us- east-1.console.aws.amazon.com",
    # Special characters
    "us-east-1.console.aws.amazon!.com",
    # Invalid region pattern
    "usa-east-1.console.aws.amazon.com",
    "us-east.console.aws.amazon.com",
    # Numeric region name (should be invalid)
    "12-east-1.console.aws.amazon.com",
    # Extra hyphens
    "us--east-1.console.aws.amazon.com",
    # Too many segments
    "us-east-1-2.console.aws.amazon.com",
    # Only TLD
    "console.aws.amazon.com",
    # Just a dot
    ".",
    # None as input (should raise TypeError)
])
def test_invalid_codecommit_hostnames_edge(hostname):
    """Test edge cases that should be invalid."""
    codeflash_output = CodeCommitProvider._is_valid_codecommit_hostname(hostname) # 18.9μs -> 11.2μs (68.5% faster)

def test_none_input_raises_typeerror():
    """Test None input raises TypeError."""
    with pytest.raises(TypeError):
        CodeCommitProvider._is_valid_codecommit_hostname(None) # 2.24μs -> 1.51μs (48.2% faster)

@pytest.mark.parametrize("hostname", [
    # Valid with minimum region name length
    "eu-north-1.console.aws.amazon.com",
    "af-south-1.console.aws.amazon.com",
    # Valid with gov- in region
    "us-gov-east-1.console.aws.amazon.com",
])
def test_valid_codecommit_hostnames_edge(hostname):
    """Test edge valid hostnames with minimum/maximum region lengths."""
    codeflash_output = CodeCommitProvider._is_valid_codecommit_hostname(hostname) # 5.83μs -> 3.95μs (47.5% faster)

# 3. Large Scale Test Cases

def test_large_batch_valid_hostnames():
    """Test a large batch of syntactically valid hostnames."""
    base_regions = ["us-east", "us-west", "eu-west", "ap-southeast", "ap-northeast", "sa-east", "ca-central"]
    hostnames = [
        f"{region}-{i}.console.aws.amazon.com"
        for region in base_regions
        for i in range(1, 21)
    ]
    # Add gov- variants
    gov_hostnames = [
        f"{region.replace('us-', 'us-gov-')}-{i}.console.aws.amazon.com"
        for region in ["us-west", "us-east"]
        for i in range(1, 21)
    ]
    all_hostnames = hostnames + gov_hostnames
    for hostname in all_hostnames:
        codeflash_output = CodeCommitProvider._is_valid_codecommit_hostname(hostname) # 86.5μs -> 54.1μs (59.9% faster)

def test_large_batch_invalid_hostnames():
    """Test a large batch of syntactically invalid hostnames."""
    # Invalid: wrong TLD, missing .console, extra hyphens, bad region pattern, etc.
    invalid_hostnames = []
    for i in range(1, 51):
        invalid_hostnames.extend([
            f"us-east-{i}.console.aws.amazon.org",  # wrong TLD
            f"us-east-{i}.aws.amazon.com",         # missing .console
            f"us--east-{i}.console.aws.amazon.com", # double hyphen
            f"us-east-{i}console.aws.amazon.com",   # missing dot before console
            f"us-east-{i}.console.aws.amazon",      # missing .com
            f"us-east-{i}.console.aws.amazon.comm", # extra m
            f"us-east-{i}.console.aws.amazon.co",   # wrong TLD
            f"us-east-{i}.console.aws.amazoncom",   # missing dot
            f"us-east-{i}.console.aws.amazoncom.",  # trailing dot
            f"us-east-{i}.console.aws..amazon.com", # double dot
            f"us-east-{i}.console.aws.amazon..com", # double dot
            f"us-east-{i}.console.aws.amazon.com.", # trailing dot
            f"us-east-{i}.console.aws.amazon.com-extra", # extra suffix
        ])
    for hostname in invalid_hostnames:
        codeflash_output = CodeCommitProvider._is_valid_codecommit_hostname(hostname) # 277μs -> 164μs (68.6% faster)

def test_performance_large_scale():
    """Test performance does not degrade for large number of hostnames."""
    # Generate 1000 valid and 1000 invalid hostnames
    valid_hostnames = [f"us-east-{i}.console.aws.amazon.com" for i in range(1, 501)]
    invalid_hostnames = [f"us-east-{i}.console.aws.amazon.comm" for i in range(1, 501)]
    # All valid should return True
    for hostname in valid_hostnames:
        codeflash_output = CodeCommitProvider._is_valid_codecommit_hostname(hostname) # 215μs -> 126μs (69.5% faster)
    # All invalid should return False
    for hostname in invalid_hostnames:
        codeflash_output = CodeCommitProvider._is_valid_codecommit_hostname(hostname) # 210μs -> 122μs (71.7% faster)
# codeflash_output is used to check that the output of the original code is the same as that of the optimized code.

To edit these changes git checkout codeflash/optimize-CodeCommitProvider._is_valid_codecommit_hostname-mgzit9nq and push.