xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-02 11:50:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

improve and combine regex

Browse Source
This commit is contained in:
Hussam.lawen
2024-10-14 10:30:07 +03:00
parent eb804d0b34
commit 3a52122677
1 changed files with 13 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
pr_agent/tools/ticket_pr_compliance_check.py
View File

@ -6,7 +6,9 @@ from pr_agent.git_providers import GithubProvider
from pr_agent.log import get_logger from pr_agent.log import get_logger
# Compile the regex pattern once, outside the function # Compile the regex pattern once, outside the function
GITHUB_TICKET_PATTERN = re.compile(r'(https://github[^/]+/[^/]+/[^/]+/issues/\d+)|(\b(\w+)/(\w+)#(\d+)\b)') GITHUB_TICKET_PATTERN = re.compile(
r'(https://github[^/]+/[^/]+/[^/]+/issues/\d+)|(\b(\w+)/(\w+)#(\d+)\b)|(#\d+)'
)
def find_jira_tickets(text): def find_jira_tickets(text):
@ -35,32 +37,26 @@ def extract_ticket_links_from_pr_description(pr_description, repo_path):
""" """
Extract all ticket links from PR description Extract all ticket links from PR description
""" """
github_tickets = [] github_tickets = set()
try: try:
# Pattern to match full GitHub issue URLs and shorthand notations like owner/repo#issue_number or https://github.com/owner/repo/issues/issue_number # Use the updated pattern to find matches
matches = GITHUB_TICKET_PATTERN.findall(pr_description) matches = GITHUB_TICKET_PATTERN.findall(pr_description)
for match in matches: for match in matches:
if match[0]: # Full URL match if match[0]: # Full URL match
github_tickets.append(match[0]) github_tickets.add(match[0])
else: # Shorthand notation match elif match[1]: # Shorthand notation match: owner/repo#issue_number
owner, repo, issue_number = match[2], match[3], match[4] owner, repo, issue_number = match[2], match[3], match[4]
github_tickets.append(f'https://github.com/{owner}/{repo}/issues/{issue_number}') github_tickets.add(f'https://github.com/{owner}/{repo}/issues/{issue_number}')
if not github_tickets: else: # #123 format
# Search for #123 format within the same repo issue_number = match[5][1:] # remove #
issue_number_pattern = r'#\d+'
issue_numbers = re.findall(issue_number_pattern, pr_description)
for issue_number in issue_numbers:
issue_number = issue_number[1:] # remove #
if issue_number.isdigit() and len(issue_number) < 5: if issue_number.isdigit() and len(issue_number) < 5:
issue_url = f'https://github.com/{repo_path}/issues/{issue_number}' github_tickets.add(f'https://github.com/{repo_path}/issues/{issue_number}')
if issue_url not in github_tickets:
github_tickets.append(issue_url)
except Exception as e: except Exception as e:
get_logger().error(f"Error extracting tickets error= {e}", get_logger().error(f"Error extracting tickets error= {e}",
artifact={"traceback": traceback.format_exc()}) artifact={"traceback": traceback.format_exc()})
return github_tickets return list(github_tickets)
async def extract_tickets(git_provider): async def extract_tickets(git_provider):