Improve the backport missing script (#14723)

distribution/asf-release-process-guide.md

@@ -258,7 +258,7 @@ It is also the release managers responsibility for correctly assigning all PRs m
 | [get-milestone-contributors](bin/get-milestone-contributors.py) | lists github users who contributed to a milestone |
 | [get-milestone-prs](bin/get-milestone-prs.py) | lists PRs between tags or commits and the milestone associated with them. |
 | [tag-missing-milestones](bin/tag-missing-milestones.py) | Find pull requests which the milestone is missing and tag them properly. |
-| [find-missing-backports](bin/find-missing-backports.py) | Find PRs which have been back-ported to one release branch but not another. Useful if a bug fix release based on the previous release is required during a release cycle. |
+| [find-missing-backports](bin/find-missing-backports.py) | Find PRs which have been back-ported to one release branch but not another. Useful if a bug fix release based on the previous release is required during a release cycle. Make sure to fetch remote commits before running this command. |
 | [make-linkable-release-notes](bin/make-linkable-release-notes.py) | given input of a version, input markdown file path, and output markdown file path, will rewrite markdown headers of the input file to have embedded links in the release notes style. |
 
 

distribution/bin/find-missing-backports.py

@@ -22,37 +22,34 @@ import subprocess
 import sys
 
 
+pr_number_pattern = r'\(#(\d+)\)'
+backport_pattern = r'\[Backport[^\]]*\]'
+
 def extract_pr_title_from_commit_message(commit_msg):
     # Extract commit message except the pr number
+    commit_msg = re.sub(backport_pattern, '', commit_msg)
     pr_num_pos = commit_msg.find("(#")
     if pr_num_pos < 0:
         pr_num_pos = len(commit_msg)
-    backport_pos = commit_msg.find("[Backport]")
-    if backport_pos < 0:
-        backport_pos = 0
-    else:
-        backport_pos = backport_pos + len("[Backport]")
-    return commit_msg[backport_pos:pr_num_pos].strip()
+    return commit_msg[:pr_num_pos].strip()
 
+def extract_pr_numbers_from_commit_message(commit_msg):
+    extracted_numbers = re.findall(pr_number_pattern, commit_msg)
+    return extracted_numbers
 
-def extract_pr_title(pr_json):
-    commit_url = pr_json['commits_url']
-    resp = requests.get(commit_url, auth=(github_username, os.environ["GIT_TOKEN"]))
-    title_candidates = [extract_pr_title_from_commit_message(pr_json['title'])]
-    if len(resp.json()) == 1:
-        title_candidates.append(extract_pr_title_from_commit_message(resp.json()[0]['commit']['message']))
-    return title_candidates
-
-
-def find_missing_backports(pr_jsons, release_pr_subjects):
+def find_missing_backports(pr_jsons, release_pr_subjects, release_pr_numbers):
     for pr in pr_jsons:
-        if pr['milestone'] is not None:
-            if pr['milestone']['number'] == milestone_number:
-                for pr_title_candidate in extract_pr_title(pr):
-                    if pr_title_candidate in release_pr_subjects:
-                        return
-                print("Missing backport found for PR {}, url: {}".format(pr['number'], pr['html_url']))
-
+      backport_found = False
+      for label in pr['labels']:
+        if label['name'] == 'Backport':
+          backport_found = True
+      pr_title_candidate = extract_pr_title_from_commit_message(pr['title'])
+      if pr_title_candidate in release_pr_subjects:
+        backport_found = True
+      if str(pr['number']) in release_pr_numbers:
+        backport_found = True
+      if backport_found == False: 
+        print("Missing backport found for PR {}, url: {}".format(pr['number'], pr['html_url']))
 
 def find_next_url(links):
     for link in links:
@@ -95,15 +92,33 @@ command = "git log --pretty=tformat:%s {}..{}".format(previous_branch_first_comm
 all_release_commits = subprocess.check_output(command, shell=True).decode('UTF-8')
 
 release_pr_subjects = set()
+release_pr_numbers = set()
 for commit_msg in all_release_commits.splitlines():
     title = extract_pr_title_from_commit_message(commit_msg)
+    pr_numbers = extract_pr_numbers_from_commit_message(commit_msg)
     release_pr_subjects.add(title)
+    release_pr_numbers.update(pr_numbers)
 
+print("Number of release PR subjects: {}".format(len(release_pr_subjects)))
 # Get all closed PRs and filter out with milestone
-next_url = "https://api.github.com/repos/apache/druid/pulls?state=closed"
-
-while next_url is not None:
-    resp = requests.get(next_url, auth=(github_username, os.environ["GIT_TOKEN"]))
-    find_missing_backports(resp.json(), release_pr_subjects)
-    links = resp.headers['Link'].split(',')
-    next_url = find_next_url(links)
+milestone_url = "https://api.github.com/repos/apache/druid/milestones/{}".format(milestone_number)
+resp = requests.get(milestone_url, auth=(github_username, os.environ["GIT_TOKEN"])).json()
+milestone_title = resp['title']
+pr_items = []
+page = 0
+while True:
+  page = page + 1
+  pr_url = "https://api.github.com/search/issues?per_page=50&page={}&q=milestone:{}+type:pr+is:merged+is:closed+repo:apache/druid".format(page,milestone_title)
+  pr_resp = requests.get(pr_url, auth=(github_username, os.environ["GIT_TOKEN"])).json()
+  if pr_resp['incomplete_results']:
+    sys.stderr.write('This script cannot handle incomplete results')
+    sys.exit(1)
+  pr_items.extend(pr_resp['items'])
+  if len(pr_resp['items']) < 50:
+    print("Total PRs for current milestone: {}".format(len(pr_items)))
+    print("Total expected count: {}".format(pr_resp['total_count']))
+    if pr_resp['total_count'] != len(pr_items):
+      sys.stderr.write('Expected PR count does not match with number of PRs fetched')
+      sys.exit(1)
+    break
+find_missing_backports(pr_items, release_pr_subjects, release_pr_numbers)