app.py

import json
from github import Github
# Authentication is defined via github.Auth
from github import Auth
import os
from dotenv import load_dotenv
load_dotenv()
auth = Auth.Token(os.getenv('GITHUB_TOKEN'))
g = Github(auth=auth)



class Issue:
    def __init__(self, url, repository_url, labels_url, comments_url, events_url, html_url, id, node_id, number, title, user, labels, state, locked, assignee, assignees, milestone, comments, created_at, updated_at, closed_at, author_association, active_lock_reason, body, closed_by, reactions, timeline_url, performed_via_github_app, state_reason):
        self.url = url
        self.repository_url = repository_url
        self.labels_url = labels_url
        self.comments_url = comments_url
        self.events_url = events_url
        self.html_url = html_url
        self.id = id
        self.node_id = node_id
        self.number = number
        self.title = title
        self.user = user
        self.labels = labels
        self.state = state
        self.locked = locked
        self.assignee = assignee
        self.assignees = assignees
        self.milestone = milestone
        self.comments = comments
        self.created_at = created_at
        self.updated_at = updated_at
        self.closed_at = closed_at
        self.author_association = author_association
        self.active_lock_reason = active_lock_reason
        self.body = body
        self.closed_by = closed_by
        self.reactions = reactions
        self.timeline_url = timeline_url
        self.performed_via_github_app = performed_via_github_app
        self.state_reason = state_reason

    def __repr__(self):
        return f"Issue(id={self.id}, title={self.title}, state={self.state}, created_at={self.created_at}, updated_at={self.updated_at})"
    
    def fetch_issue_comments(self):
        repo_org = self.repository_url.split('/')[4]
        repo_name = self.repository_url.split('/')[5]
        repo = g.get_repo(f"{repo_org}/{repo_name}")
        issue = repo.get_issue(self.number)
        comments = issue.get_comments()
        return comments
    
    def get_repo_org(self):
        repo_org = self.repository_url.split('/')[4]
        repo_name = self.repository_url.split('/')[5]
        return f"{repo_org}-{repo_name}#issue-{self.number}"

    def fetch_associated_prs(self):
        repo_org = self.repository_url.split('/')[4]
        repo_name = self.repository_url.split('/')[5]
        repo = g.get_repo(f"{repo_org}/{repo_name}")

        # Search for PRs that mention the issue number in their body or title
        prs = repo.get_pulls(state='all')
        associated_prs = []
        issue_ref = f"{self.number}"  # Reference to the issue number

        for pr in prs:
            # Ensure pr.body and pr.title are not None before checking
            # Check if issue_ref is in pr.body
            if pr.body is not None and issue_ref in pr.body:
                print(f"PR {pr.number} mentions issue {self.number} in body")
                associated_prs.append(pr)

        return associated_prs
    
    def fetch_comments_from_prs(self):
        prs = self.fetch_associated_prs()
        pr_comments = []
        for pr in prs:
            temp = pr.get_comments() # Fetch comments from PRs
            temp_list = list(temp)  # Convert PaginatedList to a list
            for comment in temp_list:
                pr_comments.append(comment)
        return pr_comments
    
    def fetch_all_comments_related(self):
        # Convert PaginatedList to a list for issue comments
        issue_comments = list(self.fetch_issue_comments())  # Convert PaginatedList to a list
        pr_comments = self.fetch_comments_from_prs()  # PR comments is already a list
        new_com = []
        for x in issue_comments:
            new_com.append({"issue_node_id": x.node_id, "comment": x.body})
        for x in pr_comments:
            new_com.append({"pr_node_id": x.raw_data["node_id"], "comment": x.body})
        return new_com 
def import_json():
    with open('devpool-issues.json') as f:
        data = json.load(f)
    return data

def get_issues():
    data = import_json()
    issues = []
    for issue in data:
        issues.append(Issue(
            url=issue['url'], repository_url=issue['repository_url'], labels_url=issue['labels_url'],
            comments_url=issue['comments_url'], events_url=issue['events_url'], html_url=issue['html_url'],
            id=issue['id'], node_id=issue['node_id'], number=issue['number'], title=issue['title'], 
            user=issue['user'], labels=issue['labels'], state=issue['state'], locked=issue['locked'],
            assignee=issue['assignee'], assignees=issue['assignees'], milestone=issue['milestone'], 
            comments=issue['comments'], created_at=issue['created_at'], updated_at=issue['updated_at'], 
            closed_at=issue['closed_at'], author_association=issue['author_association'], 
            active_lock_reason=issue['active_lock_reason'], body=issue['body'], closed_by=issue['closed_by'], 
            reactions=issue['reactions'], timeline_url=issue['timeline_url'], performed_via_github_app=issue['performed_via_github_app'], 
            state_reason=issue['state_reason']
        ))
    tot_text = 0
    for issue in issues:
        comments = issue.fetch_all_comments_related()
        #pr_comments = issue.fetch_comments_from_prs()
        #comments.extend(pr_comments)
        print(f"Number of comments for issue {issue.number}: {len(comments)}")
        tot_text += len(comments)
        #Dump to json
        with open(f"comments/{issue.get_repo_org()}.json", 'w') as f:
            json.dump(comments, f)
    print(f"Total number of comments: {tot_text}")

    return data

if __name__ == '__main__':
    get_issues()