Query/page for open PRs

.github/workflows/main.yml

@@ -28,6 +28,7 @@ jobs:
           python update_dashboard.py ${{ secrets.GITHUB_TOKEN }} config/tracked_incubator.yaml html/incubator.html
           python update_dashboard.py ${{ secrets.GITHUB_TOKEN }} config/lsdb_workflows.yaml html/lsdb.html
           python src/lf_workflow_dash/lsdb_interrupts/external_issues.py ${{ secrets.GITHUB_TOKEN }} html/lsdb_issues.html
+          python src/lf_workflow_dash/lsdb_interrupts/open_prs.py ${{ secrets.GITHUB_TOKEN }}
       - name: Deploy to Github pages
         uses: JamesIves/github-pages-deploy-action@v4
         with:

src/lf_workflow_dash/lsdb_interrupts/external_issues.py

@@ -4,85 +4,22 @@
 organization, and writes them to HTML for human monitoring.
 """
 
-import re
 import sys
 from collections import defaultdict
 from datetime import datetime, timezone
 from typing import Dict, List, Set
 
-import human_readable
 import requests
 from jinja2 import Environment, FileSystemLoader
 
-GITHUB_API_BASE = "https://api.github.com"
-TEAM_MEMBERS = [
-    "delucchi-cmu",
-    "nevencaplar",
-    "hombit",
-    "smcguire-cmu",
-    "gitosaurus",
-    "dougbrn",
-    "olivialynn",
-    "camposandro",
-    "wilsonbb",
-    "mjuric",
-]
-
-
-def create_github_session(token) -> requests.Session:
-    """Create a requests session with GitHub authentication."""
-    session = requests.Session()
-    session.headers.update(
-        {
-            "Authorization": f"Bearer {token}",
-            "Accept": "application/vnd.github+json",
-        }
-    )
-    return session
-
-
-def paginate_github_api(session: requests.Session, url: str) -> List[Dict]:
-    """Paginate through GitHub API responses.
-
-    Follows the Link header for pagination as documented in:
-    https://docs.github.com/en/rest/guides/using-pagination-in-the-rest-api
-    """
-    results = []
-    while url:
-        response = session.get(url)
-        response.raise_for_status()
-        data = response.json()
-
-        # Handle both list and dict responses
-        if isinstance(data, list):
-            results.extend(data)
-        else:
-            results.append(data)
-
-        # Check for pagination using Link header (RFC 8288)
-        # Format: <https://api.github.com/...?page=2>; rel="next", <...>; rel="last"
-        link_header = response.headers.get("Link", "")
-        url = None
-        if link_header:
-            # Match URLs within angle brackets that have rel="next"
-            # Pattern: <URL>; rel="next"
-            match = re.search(r'<([^>]+)>;\s*rel="next"', link_header)
-            if match:
-                url = match.group(1)
-
-    return results
-
-
-def get_org_repos(org: str, token: str) -> List[str]:
-    """Get all repos in the org that are related to HATS or LSDB"""
-    print("Fetching org repositories...")
-    session = create_github_session(token)
-    url = f"{GITHUB_API_BASE}/orgs/{org}/repos?per_page=100"
-    repos_data = paginate_github_api(session, url)
-    repos = [repo["name"] for repo in repos_data]
-    repos = [repo for repo in repos if "hats" in repo or "lsdb" in repo]
-    print(f"Found {len(repos)} repositories.")
-    return repos
+from lf_workflow_dash.lsdb_interrupts.github_api import (
+    GITHUB_API_BASE,
+    TEAM_MEMBERS,
+    create_github_session,
+    get_humanized_updated_at,
+    get_lsdb_repos,
+    paginate_github_api,
+)
 
 
 def get_open_issues(org: str, repos: List[str], org_members: Set[str], token: str) -> List[Dict]:
@@ -142,15 +79,6 @@ def get_open_issues(org: str, repos: List[str], org_members: Set[str], token: st
     return all_issues
 
 
-def get_humanized_updated_at(iso_time: str, now: datetime) -> str:
-    """Convenience method to get a human readable duration, like '2 days ago'."""
-    try:
-        dt = datetime.strptime(iso_time, "%Y-%m-%dT%H:%M:%SZ").replace(tzinfo=timezone.utc)
-        return human_readable.date_time(dt, when=now)
-    except Exception:  # pylint: disable=broad-except
-        return iso_time
-
-
 def write_html_issues(external_issues: List[Dict], html_file: str):
     """Fill in the jinja template, using the external interest issues found"""
     print(f"Writing HTML output to {html_file} ...")
@@ -177,7 +105,7 @@ def write_html_issues(external_issues: List[Dict], html_file: str):
 
 def main(token, out_file):
     """Convenience method to do the work."""
-    repos = get_org_repos("astronomy-commons", token)
+    repos = get_lsdb_repos(token)
     external_issues = get_open_issues("astronomy-commons", repos, TEAM_MEMBERS, token)
     # Sort by most recent activity
     external_issues.sort(key=lambda x: x["updatedAt"], reverse=True)

src/lf_workflow_dash/lsdb_interrupts/github_api.py

@@ -0,0 +1,96 @@
+import re
+from datetime import datetime, timezone
+from typing import Dict, List
+
+import human_readable
+import requests
+
+GITHUB_API_BASE = "https://api.github.com"
+TEAM_MEMBERS = [
+    "delucchi-cmu",
+    "nevencaplar",
+    "hombit",
+    "smcguire-cmu",
+    "gitosaurus",
+    "dougbrn",
+    "olivialynn",
+    "camposandro",
+    "wilsonbb",
+    "mjuric",
+]
+
+
+def create_github_session(token) -> requests.Session:
+    """Create a requests session with GitHub authentication."""
+    session = requests.Session()
+    session.headers.update(
+        {
+            "Authorization": f"Bearer {token}",
+            "Accept": "application/vnd.github+json",
+        }
+    )
+    return session
+
+
+def paginate_github_api(session: requests.Session, url: str) -> List[Dict]:
+    """Paginate through GitHub API responses.
+
+    Follows the Link header for pagination as documented in:
+    https://docs.github.com/en/rest/guides/using-pagination-in-the-rest-api
+    """
+    results = []
+    while url:
+        response = session.get(url)
+        response.raise_for_status()
+        data = response.json()
+
+        # Handle both list and dict responses
+        if isinstance(data, list):
+            results.extend(data)
+        else:
+            results.append(data)
+
+        # Check for pagination using Link header (RFC 8288)
+        # Format: <https://api.github.com/...?page=2>; rel="next", <...>; rel="last"
+        link_header = response.headers.get("Link", "")
+        url = None
+        if link_header:
+            # Match URLs within angle brackets that have rel="next"
+            # Pattern: <URL>; rel="next"
+            match = re.search(r'<([^>]+)>;\s*rel="next"', link_header)
+            if match:
+                url = match.group(1)
+
+    return results
+
+
+def get_org_repos(org: str, token: str) -> List[str]:
+    """Get all repos in the org"""
+    print("Fetching org repositories...")
+    session = create_github_session(token)
+    url = f"{GITHUB_API_BASE}/orgs/{org}/repos?per_page=100"
+    repos_data = paginate_github_api(session, url)
+    repos = [repo["name"] for repo in repos_data if not repo["archived"]]
+    print(f"Found {len(repos)} repositories.")
+    return repos
+
+
+def get_lsdb_repos(token: str) -> List[str]:
+    """Get all repos that are related to HATS or LSDB"""
+    print("Fetching org repositories...")
+    session = create_github_session(token)
+    url = f"{GITHUB_API_BASE}/orgs/astronomy-commons/repos?per_page=100"
+    repos_data = paginate_github_api(session, url)
+    repos = [repo["name"] for repo in repos_data]
+    repos = [repo for repo in repos if "hats" in repo or "lsdb" in repo]
+    print(f"Found {len(repos)} repositories.")
+    return repos
+
+
+def get_humanized_updated_at(iso_time: str, now: datetime) -> str:
+    """Convenience method to get a human readable duration, like '2 days ago'."""
+    try:
+        dt = datetime.strptime(iso_time, "%Y-%m-%dT%H:%M:%SZ").replace(tzinfo=timezone.utc)
+        return human_readable.date_time(dt, when=now)
+    except Exception:  # pylint: disable=broad-except
+        return iso_time

src/lf_workflow_dash/lsdb_interrupts/open_prs.py

@@ -0,0 +1,92 @@
+import sys
+from datetime import datetime, timezone
+from typing import Dict, List
+
+import requests
+from jinja2 import Environment, FileSystemLoader
+
+from lf_workflow_dash.lsdb_interrupts.github_api import (
+    GITHUB_API_BASE,
+    create_github_session,
+    get_humanized_updated_at,
+    get_lsdb_repos,
+    get_org_repos,
+    paginate_github_api,
+)
+
+
+def get_open_prs(org: str, repos: List[str], token: str) -> List[Dict]:
+    """Find all OPEN PRs."""
+    print("Fetching open PRs for all repositories...")
+    session = create_github_session(token)
+    all_prs = []
+    for repo in repos:
+        print(f"  {repo}...")
+        try:
+            url = f"{GITHUB_API_BASE}/repos/{org}/{repo}/pulls?state=open&per_page=100"
+            pr_data = paginate_github_api(session, url)
+
+            prs = [
+                {
+                    "number": pr["number"],
+                    "title": pr["title"],
+                    "author": pr["user"],
+                    "updatedAt": pr["updated_at"],
+                    "url": pr["html_url"],
+                    "repo": repo,
+                    "is_draft": pr["draft"],
+                }
+                for pr in pr_data
+            ]
+            print(f"     Found {len(prs)} pull requests.")
+
+            all_prs.extend(prs)
+        except requests.exceptions.RequestException as e:
+            print(f"Error fetching prs for repo {repo}: {e}")
+    print(f"Collected {len(all_prs)} open prs.")
+    return all_prs
+
+
+def write_html_prs(prs: List[Dict], html_file: str):
+    """Fill in the jinja template, using the prs found"""
+    print(f"Writing HTML output to {html_file} ...")
+
+    now = datetime.now(timezone.utc)
+    pr_summaries = []
+    for pr in prs:
+        author = pr["author"]["login"] if pr["author"] else "unknown"
+        pr_summaries.append(
+            {
+                "updated_human": get_humanized_updated_at(pr["updatedAt"], now),
+                "author": author,
+                "title": pr["title"].replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;"),
+                "url": pr["url"],
+                "repo": pr["repo"],
+                "is_draft": "DRAFT" if pr["is_draft"] else "",
+                "is_bot": author in ["dependabot[bot]", "Copilot"],
+            }
+        )
+
+    environment = Environment(loader=FileSystemLoader("templates/"))
+    template = environment.get_template("pr_list.jinja")
+    with open(html_file, mode="w", encoding="utf-8") as results:
+        results.write(template.render({"all_prs": pr_summaries, "num_results": len(pr_summaries)}))
+    print(f"HTML output written to {html_file}")
+
+
+def main(token):
+    """Convenience method to do the work."""
+    repos = get_lsdb_repos(token)
+    prs = get_open_prs("astronomy-commons", repos, token)
+    prs.sort(key=lambda x: x["updatedAt"], reverse=True)
+    write_html_prs(prs, "html/lsdb_prs.html")
+
+    repos = get_org_repos("lincc-frameworks", token)
+    prs = get_open_prs("lincc-frameworks", repos, token)
+    prs.sort(key=lambda x: x["updatedAt"], reverse=True)
+    write_html_prs(prs, "html/lincc_prs.html")
+
+
+if __name__ == "__main__":
+    TOKEN = sys.argv[1]
+    main(TOKEN)

templates/pr_list.jinja

@@ -0,0 +1,43 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<title>Pull Requests</title>
+<style>
+body { font-family: sans-serif; margin: 2em; }
+table { border-collapse: collapse; width: 100%; }
+th, td { border: 1px solid #ccc; padding: 0.5em; text-align: left; }
+th { background: #eee; }
+tr:nth-child(even) { background: #f9f9f9; }
+a { color: #0366d6; text-decoration: none; }
+a:hover { text-decoration: underline; }
+td.bot {color: gray; font-style:italic}
+</style>
+</head>
+<body>
+<h2>Pull Requests ({{num_results}}) (most recent activity first)</h2>
+<table>
+<thead>
+<tr>
+<th>Last Activity</th>
+<th>Author</th>
+<th>Repo</th>
+<th>Draft?</th>
+<th>Title</th>
+</tr>
+</thead>
+<tbody>
+
+{% for pr in all_prs %}
+    <tr>
+        <td>{{pr.updated_human}}</td>
+        <td{% if pr.is_bot %} class="bot"{% endif %}>{{pr.author}}</td>
+        <td>{{pr.repo}}</td>
+        <td>{{pr.is_draft}}</td>
+        <td><a href="{{pr.url}}">{{pr.title}}</a></td>
+    </tr>
+{% endfor %}
+</tbody>
+</table>
+</body>
+</html>