Add release notes processing script and unit tests

.github/scripts/release-notes/process_release_notes.py

@@ -0,0 +1,160 @@
+import re
+import sys
+import subprocess
+import json
+from typing import List, Tuple
+
+def get_linked_issues(owner: str, repo: str, pr_number: int) -> List[int]:
+    """Call GitHub API to get linked issue numbers for a PR.
+
+    Args:
+        owner: Repository owner
+        repo: Repository name
+        pr_number: Pull request number
+
+    Returns:
+        List of linked issue numbers
+    """
+
+
+    query = """
+    query ($owner: String!, $repo: String!, $pr: Int!) {
+        repository(owner: $owner, name: $repo) {
+            pullRequest(number: $pr) {
+                closingIssuesReferences(first: 100) {
+                    nodes {
+                        number
+                    }
+                }
+            }
+        }
+    }
+    """
+
+    try:
+        result = subprocess.run([
+            'gh', 'api', 'graphql',
+            '-F', f'owner={owner}',
+            '-F', f'repo={repo}',
+            '-F', f'pr={pr_number}',
+            '-f', f'query={query}',
+            '--jq', '.data.repository.pullRequest.closingIssuesReferences.nodes[].number'
+        ], capture_output=True, text=True, check=True)
+
+        # Split output into lines and convert to integers
+        if result.stdout.strip():
+            return [int(num) for num in result.stdout.strip().split('\n')]
+        return []
+
+    except subprocess.CalledProcessError:
+        print(f"Error fetching linked issues for PR #{pr_number}")
+        return []
+
+
+
+def extract_jira_tickets(line: str) -> List[str]:
+    # Find all Jira tickets in format ABC-123 (with any prefix/suffix)
+    return re.findall(r'[A-Z]+-\d+', line)
+
+def extract_pr_numbers(line: str) -> List[str]:
+    # Match PR numbers from GitHub format (#123)
+    return re.findall(r'#(\d+)', line)
+
+def process_line(line: str) -> str:
+    """Process a single line from release notes by removing Jira tickets, conventional commit prefixes and other common patterns.
+
+    Args:
+        line: A single line from release notes
+
+    Returns:
+        Processed line with tickets and prefixes removed
+
+    Example:
+        >>> process_line("[ABC-123] feat(ui): Add new button")
+        "Add new button"
+    """
+    original = line
+
+    # Remove Jira ticket patterns:
+    # line = re.sub(r'\[[A-Z]+-\d+\]', '', line) # [ABC-123] -> ""
+    # line = re.sub(r'[A-Z]+-\d+:\s', '', line) # ABC-123: -> ""
+    # line = re.sub(r'[A-Z]+-\d+\s-\s', '', line) # ABC-123 - -> ""
+
+    # Remove keywords and their variations
+    patterns = [
+        r'BACKPORT',              # BACKPORT -> ""
+        r'[deps]:',               # [deps]: -> ""
+        r'feat(?:\([^)]*\))?:',   # feat: or feat(ui): -> ""
+        r'bug(?:\([^)]*\))?:',    # bug: or bug(core): -> ""
+        r'ci(?:\([^)]*\))?:'      # ci: or ci(workflow): -> ""
+    ]
+    for pattern in patterns:
+        line = re.sub(pattern, '', line)
+
+    cleaned = line.strip()
+    if cleaned != original.strip():
+        print(f"Processed: {original.strip()} -> {cleaned}")
+    return cleaned
+
+def process_file(input_file: str) -> Tuple[List[str], List[str], List[str]]:
+    jira_tickets: List[str] = []
+    pr_numbers: List[str] = []
+    processed_lines: List[str] = []
+
+    print("Processing file: ", input_file)
+
+    with open(input_file, 'r') as f:
+        for line in f:
+            line = line.strip()
+            should_process = line and not line.endswith(':')
+
+            if should_process:
+                tickets = extract_jira_tickets(line)
+                jira_tickets.extend(tickets)
+
+                prs = extract_pr_numbers(line)
+                pr_numbers.extend(prs)
+                processed_lines.append(process_line(line))
+            else:
+                processed_lines.append(line)
+
+
+    # Remove duplicates while preserving order
+    jira_tickets = list(dict.fromkeys(jira_tickets))
+    pr_numbers = list(dict.fromkeys(pr_numbers))
+
+    print("Jira tickets:", ",".join(jira_tickets))
+    print("PR numbers:", ",".join(pr_numbers))
+    print("Finished processing file: ", input_file)
+    return jira_tickets, pr_numbers, processed_lines
+
+def save_results(jira_tickets: List[str], pr_numbers: List[str], processed_lines: List[str],
+                jira_file: str = 'jira_tickets.txt',
+                pr_file: str = 'pr_numbers.txt',
+                processed_file: str = 'processed_notes.txt') -> None:
+    with open(jira_file, 'w') as f:
+        f.write('\n'.join(jira_tickets))
+
+    with open(pr_file, 'w') as f:
+        f.write('\n'.join(pr_numbers))
+
+    with open(processed_file, 'w') as f:
+        f.write('\n'.join(processed_lines))
+
+if __name__ == '__main__':
+    input_file = 'release_notes.txt'
+    jira_file = 'jira_tickets.txt'
+    pr_file = 'pr_numbers.txt'
+    processed_file = 'processed_notes.txt'
+
+    if len(sys.argv) >= 2:
+        input_file = sys.argv[1]
+    if len(sys.argv) >= 3:
+        jira_file = sys.argv[2]
+    if len(sys.argv) >= 4:
+        pr_file = sys.argv[3]
+    if len(sys.argv) >= 5:
+        processed_file = sys.argv[4]
+
+    jira_tickets, pr_numbers, processed_lines = process_file(input_file)
+    save_results(jira_tickets, pr_numbers, processed_lines, jira_file, pr_file, processed_file)

.github/scripts/release-notes/test_process_release_notes.py

@@ -0,0 +1,95 @@
+import unittest
+import tempfile
+import os
+from process_release_notes import extract_jira_tickets, extract_pr_numbers, process_line, process_file, get_linked_issues
+
+class TestProcessReleaseNotes(unittest.TestCase):
+    def setUp(self):
+        self.test_file = tempfile.NamedTemporaryFile(delete=False)
+
+    def tearDown(self):
+        os.unlink(self.test_file.name)
+
+    def test_extract_jira_tickets(self):
+        test_cases = [
+            ("[ABC-123] Some text", ["ABC-123"]),
+            ("DEF-456: Some text", ["DEF-456"]),
+            ("GHI-789 - Some text", ["GHI-789"]),
+            ("Multiple [ABC-123] and DEF-456: tickets", ["ABC-123", "DEF-456"]),
+            ("No tickets here", []),
+            ("Mixed formats ABC-123 [DEF-456] GHI-789:", ["ABC-123", "DEF-456", "GHI-789"])
+        ]
+        for input_text, expected in test_cases:
+            with self.subTest(input_text=input_text):
+                result = extract_jira_tickets(input_text)
+                self.assertEqual(result, expected)
+
+    def test_extract_pr_numbers(self):
+        test_cases = [
+            ("PR #123 text", ["123"]),
+            ("Multiple PRs #456 and #789", ["456", "789"]),
+            ("No PR numbers", [])
+        ]
+        for input_text, expected in test_cases:
+            with self.subTest(input_text=input_text):
+                result = extract_pr_numbers(input_text)
+                self.assertEqual(result, expected)
+
+    def test_process_line(self):
+        test_cases = [
+            ("[ABC-123] BACKPORT Some text", "Some text"),
+            ("DEF-456: feat(component): Some text", "Some text"),
+            ("GHI-789 - bug(fix): Some text", "Some text"),
+            ("ci: Some text", "Some text"),
+            ("ci(workflow): Some text", "Some text"),
+            ("feat: Direct feature", "Direct feature"),
+            ("bug: Simple bugfix", "Simple bugfix"),
+            ("Normal text", "Normal text")
+        ]
+        for input_text, expected in test_cases:
+            with self.subTest(input_text=input_text):
+                result = process_line(input_text)
+                self.assertEqual(result, expected)
+
+    def test_process_file(self):
+        content = """
+### Features:
+[ABC-123] feat(comp): Feature 1 #123
+DEF-456: bug(fix): Bug fix #456
+GHI-789 - BACKPORT Some text #789
+
+### Bug Fixes:
+Another line without changes
+"""
+        with open(self.test_file.name, 'w') as f:
+            f.write(content)
+
+        jira_tickets, pr_numbers, processed_lines = process_file(self.test_file.name)
+
+        self.assertEqual(jira_tickets, ["ABC-123", "DEF-456", "GHI-789"])
+        self.assertEqual(pr_numbers, ["123", "456", "789"])
+        self.assertEqual(processed_lines, [
+            '',
+            '### Features:',
+            'Feature 1 #123',
+            'Bug fix #456',
+            'Some text #789',
+            '',
+            '### Bug Fixes:',
+            'Another line without changes'
+        ])
+
+    def test_get_linked_issues(self):
+        test_cases = [
+            ("bitwarden", "android", 4696, [4659]),
+            ("bitwarden", "android", 4809, [])
+        ]
+
+        for owner, repo, pr_id, expected_linked_issues in test_cases:
+            with self.subTest(msg=f"Testing PR #{pr_id} for {owner}/{repo}"):
+                result = get_linked_issues(owner, repo, pr_id)
+                self.assertEqual(sorted(result), sorted(expected_linked_issues))
+
+
+if __name__ == '__main__':
+    unittest.main()