CLOUDP-295785 - Calculate next version and release notes script

requirements.txt

@@ -33,6 +33,7 @@ pytest-mock==3.14.1
 wrapt==1.17.2
 botocore==1.38.33
 boto3==1.38.33
+python-frontmatter==1.1.0
 
 # from kubeobject
 freezegun==1.5.2

scripts/release/__init__.py

@@ -0,0 +1 @@
+# Makes 'release' a Python package.

scripts/release/calculate_next_version.py

@@ -0,0 +1,60 @@
+import argparse
+import pathlib
+
+from git import Repo
+
+from scripts.release.changelog import (
+    DEFAULT_CHANGELOG_PATH,
+    DEFAULT_INITIAL_GIT_TAG_VERSION,
+)
+from scripts.release.release_notes import calculate_next_version_with_changelog
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Calculate the next version based on the changes since the previous version tag.",
+        formatter_class=argparse.RawTextHelpFormatter,
+    )
+    parser.add_argument(
+        "-p",
+        "--path",
+        default=".",
+        metavar="",
+        action="store",
+        type=pathlib.Path,
+        help="Path to the Git repository. Default is the current directory '.'",
+    )
+    parser.add_argument(
+        "-c",
+        "--changelog-path",
+        default=DEFAULT_CHANGELOG_PATH,
+        metavar="",
+        action="store",
+        type=str,
+        help=f"Path to the changelog directory relative to the repository root. Default is '{DEFAULT_CHANGELOG_PATH}'",
+    )
+    parser.add_argument(
+        "-s",
+        "--initial-commit-sha",
+        metavar="",
+        action="store",
+        type=str,
+        help="SHA of the initial commit to start from if no previous version tag is found.",
+    )
+    parser.add_argument(
+        "-v",
+        "--initial-version",
+        default=DEFAULT_INITIAL_GIT_TAG_VERSION,
+        metavar="",
+        action="store",
+        type=str,
+        help=f"Version to use if no previous version tag is found. Default is '{DEFAULT_INITIAL_GIT_TAG_VERSION}'",
+    )
+    args = parser.parse_args()
+
+    repo = Repo(args.path)
+
+    version, _ = calculate_next_version_with_changelog(
+        repo, args.changelog_path, args.initial_commit_sha, args.initial_version
+    )
+
+    print(version)

scripts/release/changelog.py

@@ -0,0 +1,160 @@
+import datetime
+import os
+import re
+from enum import StrEnum
+
+import frontmatter
+from git import Commit, Repo
+
+DEFAULT_CHANGELOG_PATH = "changelog/"
+DEFAULT_INITIAL_GIT_TAG_VERSION = "1.0.0"
+FILENAME_DATE_FORMAT = "%Y%m%d"
+FRONTMATTER_DATE_FORMAT = "%Y-%m-%d"
+MAX_TITLE_LENGTH = 50
+
+PRELUDE_ENTRIES = ["prelude"]
+BREAKING_CHANGE_ENTRIES = ["breaking", "major"]
+FEATURE_ENTRIES = ["feat", "feature"]
+BUGFIX_ENTRIES = ["fix", "bugfix", "hotfix", "patch"]
+
+
+class ChangeKind(StrEnum):
+    PRELUDE = "prelude"
+    BREAKING = "breaking"
+    FEATURE = "feature"
+    FIX = "fix"
+    OTHER = "other"
+
+
+class ChangeEntry:
+    def __init__(self, date: datetime, kind: ChangeKind, title: str, contents: str):
+        self.date = date
+        self.kind = kind
+        self.title = title
+        self.contents = contents
+
+
+def get_changelog_entries(
+    base_commit: Commit,
+    repo: Repo,
+    changelog_sub_path: str,
+) -> list[ChangeEntry]:
+    changelog = []
+
+    # Compare base commit with current working tree
+    diff_index = base_commit.diff(other=repo.head.commit, paths=changelog_sub_path)
+
+    # No changes since the previous version
+    if not diff_index:
+        return changelog
+
+    # Traverse added Diff objects only (change type 'A' for added files)
+    for diff_item in diff_index.iter_change_type("A"):
+        file_path = diff_item.b_path
+
+        change_entry = extract_changelog_entry(repo.working_dir, file_path)
+        changelog.append(change_entry)
+
+    return changelog
+
+
+def extract_changelog_entry(working_dir: str, file_path: str) -> ChangeEntry:
+    file_name = os.path.basename(file_path)
+    date, kind = extract_date_and_kind_from_file_name(file_name)
+
+    abs_file_path = os.path.join(working_dir, file_path)
+    with open(abs_file_path, "r") as file:
+        file_content = file.read()
+
+    change_entry = extract_changelog_entry_from_contents(file_content)
+
+    if change_entry.date != date:
+        raise Exception(
+            f"{file_name} - date in front matter '{change_entry.date}' does not match date extracted from file name '{date}'"
+        )
+
+    if change_entry.kind != kind:
+        raise Exception(
+            f"{file_name} - kind in front matter '{change_entry.kind}' does not match kind extracted from file name '{kind}'"
+        )
+
+    return change_entry
+
+
+def extract_date_and_kind_from_file_name(file_name: str) -> (datetime, ChangeKind):
+    match = re.match(r"(\d{8})_([a-zA-Z]+)_(.+)\.md", file_name)
+    if not match:
+        raise Exception(f"{file_name} - doesn't match expected pattern")
+
+    date_str, kind_str, _ = match.groups()
+    try:
+        date = parse_change_date(date_str, FILENAME_DATE_FORMAT)
+    except Exception as e:
+        raise Exception(f"{file_name} - {e}")
+
+    kind = get_change_kind(kind_str)
+
+    return date, kind
+
+
+def parse_change_date(date_str: str, date_format: str) -> datetime:
+    try:
+        date = datetime.datetime.strptime(date_str, date_format).date()
+    except Exception:
+        raise Exception(f"date '{date_str}' is not in the expected format {date_format}")
+
+    return date
+
+
+def get_change_kind(kind_str: str) -> ChangeKind:
+    if kind_str.lower() in PRELUDE_ENTRIES:
+        return ChangeKind.PRELUDE
+    if kind_str.lower() in BREAKING_CHANGE_ENTRIES:
+        return ChangeKind.BREAKING
+    elif kind_str.lower() in FEATURE_ENTRIES:
+        return ChangeKind.FEATURE
+    elif kind_str.lower() in BUGFIX_ENTRIES:
+        return ChangeKind.FIX
+    else:
+        return ChangeKind.OTHER
+
+
+def extract_changelog_entry_from_contents(file_contents: str) -> ChangeEntry:
+    data = frontmatter.loads(file_contents)
+
+    kind = get_change_kind(str(data["kind"]))
+    date = parse_change_date(str(data["date"]), FRONTMATTER_DATE_FORMAT)
+    ## Add newline to contents so the Markdown file also contains a newline at the end
+    contents = data.content + "\n"
+
+    return ChangeEntry(date=date, title=str(data["title"]), kind=kind, contents=contents)
+
+
+def get_changelog_filename(title: str, kind: ChangeKind, date: datetime) -> str:
+    sanitized_title = sanitize_title(title)
+    filename_date = datetime.datetime.strftime(date, FILENAME_DATE_FORMAT)
+
+    return f"{filename_date}_{kind}_{sanitized_title}.md"
+
+
+def sanitize_title(title: str) -> str:
+    # Only keep alphanumeric characters, dashes, underscores and spaces
+    regex = re.compile("[^a-zA-Z0-9-_ ]+")
+    title = regex.sub("", title)
+
+    # Replace multiple dashes, underscores and spaces with underscores
+    regex_underscore = re.compile("[-_ ]+")
+    title = regex_underscore.sub(" ", title).strip()
+
+    # Lowercase and split by space
+    words = [word.lower() for word in title.split(" ")]
+
+    result = words[0]
+
+    for word in words[1:]:
+        if len(result) + len("_") + len(word) <= MAX_TITLE_LENGTH:
+            result = result + "_" + word
+        else:
+            break
+
+    return result

scripts/release/changelog_test.py

@@ -0,0 +1,138 @@
+import datetime
+import unittest
+
+from scripts.release.changelog import (
+    MAX_TITLE_LENGTH,
+    ChangeKind,
+    extract_changelog_entry_from_contents,
+    extract_date_and_kind_from_file_name,
+    sanitize_title,
+)
+
+
+class TestExtractChangelogDataFromFileName(unittest.TestCase):
+    def test_prelude(self):
+        date, kind = extract_date_and_kind_from_file_name("20250502_prelude_release_notes.md")
+        self.assertEqual(date, datetime.date(2025, 5, 2))
+        self.assertEqual(kind, ChangeKind.PRELUDE)
+
+    def test_breaking_changes(self):
+        date, kind = extract_date_and_kind_from_file_name("20250101_breaking_api_update.md")
+        self.assertEqual(date, datetime.date(2025, 1, 1))
+        self.assertEqual(kind, ChangeKind.BREAKING)
+
+        date, kind = extract_date_and_kind_from_file_name("20250508_breaking_remove_deprecated.md")
+        self.assertEqual(date, datetime.date(2025, 5, 8))
+        self.assertEqual(kind, ChangeKind.BREAKING)
+
+        date, kind = extract_date_and_kind_from_file_name("20250509_major_schema_change.md")
+        self.assertEqual(date, datetime.date(2025, 5, 9))
+        self.assertEqual(kind, ChangeKind.BREAKING)
+
+    def test_features(self):
+        date, kind = extract_date_and_kind_from_file_name("20250509_feature_new_dashboard.md")
+        self.assertEqual(date, datetime.date(2025, 5, 9))
+        self.assertEqual(kind, ChangeKind.FEATURE)
+
+        date, kind = extract_date_and_kind_from_file_name("20250511_feat_add_metrics.md")
+        self.assertEqual(date, datetime.date(2025, 5, 11))
+        self.assertEqual(kind, ChangeKind.FEATURE)
+
+    def test_fixes(self):
+        date, kind = extract_date_and_kind_from_file_name("20251210_fix_olm_missing_images.md")
+        self.assertEqual(date, datetime.date(2025, 12, 10))
+        self.assertEqual(kind, ChangeKind.FIX)
+
+        date, kind = extract_date_and_kind_from_file_name("20251010_bugfix_memory_leak.md")
+        self.assertEqual(date, datetime.date(2025, 10, 10))
+        self.assertEqual(kind, ChangeKind.FIX)
+
+        date, kind = extract_date_and_kind_from_file_name("20250302_hotfix_security_issue.md")
+        self.assertEqual(date, datetime.date(2025, 3, 2))
+        self.assertEqual(kind, ChangeKind.FIX)
+
+        date, kind = extract_date_and_kind_from_file_name("20250301_patch_typo_correction.md")
+        self.assertEqual(date, datetime.date(2025, 3, 1))
+        self.assertEqual(kind, ChangeKind.FIX)
+
+    def test_other(self):
+        date, kind = extract_date_and_kind_from_file_name("20250520_docs_update_readme.md")
+        self.assertEqual(date, datetime.date(2025, 5, 20))
+        self.assertEqual(kind, ChangeKind.OTHER)
+
+        date, kind = extract_date_and_kind_from_file_name("20250610_refactor_codebase.md")
+        self.assertEqual(date, datetime.date(2025, 6, 10))
+        self.assertEqual(kind, ChangeKind.OTHER)
+
+    def test_invalid_date(self):
+        with self.assertRaises(Exception) as context:
+            extract_date_and_kind_from_file_name("20250640_refactor_codebase.md")
+        self.assertEqual(
+            str(context.exception),
+            "20250640_refactor_codebase.md - date '20250640' is not in the expected format %Y%m%d",
+        )
+
+    def test_wrong_file_name_format_date(self):
+        with self.assertRaises(Exception) as context:
+            extract_date_and_kind_from_file_name("202yas_refactor_codebase.md")
+        self.assertEqual(str(context.exception), "202yas_refactor_codebase.md - doesn't match expected pattern")
+
+    def test_wrong_file_name_format_missing_title(self):
+        with self.assertRaises(Exception) as context:
+            extract_date_and_kind_from_file_name("20250620_change.md")
+        self.assertEqual(str(context.exception), "20250620_change.md - doesn't match expected pattern")
+
+
+def test_strip_changelog_entry_frontmatter():
+    file_contents = """
+---
+title: This is my change
+kind: feature
+date: 2025-07-10
+---
+
+* **MongoDB**: public search preview release of MongoDB Search (Community Edition) is now available.
+  * Added new property [spec.search](https://www.mongodb.com/docs/kubernetes/current/mongodb/specification/#spec-search) to enable MongoDB Search.
+"""
+
+    change_entry = extract_changelog_entry_from_contents(file_contents)
+
+    assert change_entry.title == "This is my change"
+    assert change_entry.kind == ChangeKind.FEATURE
+    assert change_entry.date == datetime.date(2025, 7, 10)
+    assert (
+        change_entry.contents
+        == """* **MongoDB**: public search preview release of MongoDB Search (Community Edition) is now available.
+  * Added new property [spec.search](https://www.mongodb.com/docs/kubernetes/current/mongodb/specification/#spec-search) to enable MongoDB Search.
+"""
+    )
+
+
+class TestSanitizeTitle(unittest.TestCase):
+    def test_basic_case(self):
+        self.assertEqual(sanitize_title("Simple Title"), "simple_title")
+
+    def test_non_alphabetic_chars(self):
+        self.assertEqual(sanitize_title("Title tha@t-_ contain's strange char&s!"), "title_that_contains_strange_chars")
+
+    def test_with_numbers_and_dashes(self):
+        self.assertEqual(sanitize_title("Title with 123 numbers to-go!"), "title_with_123_numbers_to_go")
+
+    def test_mixed_case(self):
+        self.assertEqual(sanitize_title("MiXeD CaSe TiTlE"), "mixed_case_title")
+
+    def test_length_limit(self):
+        long_title = "This is a very long title that should be truncated because it exceeds the maximum length"
+        sanitized_title = sanitize_title(long_title)
+        self.assertTrue(len(sanitized_title) <= MAX_TITLE_LENGTH)
+        self.assertEqual(sanitized_title, "this_is_a_very_long_title_that_should_be_truncated")
+
+    def test_leading_trailing_spaces(self):
+        sanitized_title = sanitize_title("  Title with spaces  ")
+        self.assertEqual(sanitized_title, "title_with_spaces")
+
+    def test_empty_title(self):
+        self.assertEqual(sanitize_title(""), "")
+
+    def test_only_non_alphabetic(self):
+        self.assertEqual(sanitize_title("!@#"), "")