Fix release notes parser to handle bot-generated content

[yhwang]

The regex pattern was greedy and incorrectly captured bot-generated 'Summary by Sourcery' content within release notes sections. This caused the parser to fail with 'expect section header' errors.

Changes:

• Changed regex from greedy to reluctant quantifier (.*?)
• Replaced negative lookahead with positive lookahead for clarity
• Added \s* to handle optional whitespace before 'Summary by'
• Pattern now stops before any bot-generated content

The fix maintains backward compatibility with all existing test cases while correctly handling PRs with bot-generated summaries.

Test coverage:

• Added test case for Sourcery bot content
• All 36 TestCheckReleaseNotesTask tests pass
• All TestGenerateReleaseNotesTask tests pass
• No regressions detected

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Adjusts the release-notes regex to stop before bot-generated "Summary by" footers and adds a targeted test to ensure PRs with Sourcery bot content are parsed correctly without regressing existing behavior.

Sequence diagram for release notes parsing with bot-generated Summary by content

sequenceDiagram
    participant CiJob
    participant GenerateReleaseNotesTask
    participant ReleaseNotesParser
    participant ReleaseNotePattern

    CiJob->>GenerateReleaseNotesTask: run()
    GenerateReleaseNotesTask->>ReleaseNotesParser: parse(prBody)
    ReleaseNotesParser->>ReleaseNotePattern: match("== release notes ==...Summary by Sourcery...")
    Note over ReleaseNotePattern: Pattern: == release note(s)? ==\w*\n?(.*?)(?=\s*Summary by|\z)
    ReleaseNotePattern-->>ReleaseNotesParser: match groups
    Note over ReleaseNotesParser: Group 2 contains only release notes section
    ReleaseNotesParser-->>GenerateReleaseNotesTask: ReleaseNotes
    GenerateReleaseNotesTask-->>CiJob: success (no "expect section header" error)

Loading

File-Level Changes

Change	Details	Files
Update release-notes extraction regex to be non-greedy and explicitly stop before bot-generated "Summary by" sections.	Switch main capture group from a tempered-dot pattern with negative lookahead to a reluctant quantifier to avoid over-capturing content Replace the negative lookahead construction with a trailing positive lookahead that matches either optional whitespace plus "Summary by" or end-of-string Allow optional whitespace before the "Summary by" marker so bot footers with varying spacing are handled consistently	presto-release-tools/src/main/java/com/facebook/presto/release/tasks/GenerateReleaseNotesTask.java
Broaden test coverage to include release notes with Sourcery bot-generated summaries.	Register a new release-notes fixture containing Sourcery bot content in the map of valid release-notes samples Add a corresponding text fixture file under test resources to exercise parsing when a bot-generated "Summary by" footer is present	presto-release-tools/src/test/java/com/facebook/presto/release/tasks/TestCheckReleaseNotesTask.java presto-release-tools/src/test/resources/release-notes-test/pr/release_notes_with_sourcery_bot.txt

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[yhwang]

cc @unidevel

[sourcery-ai]

Hey - I've found 1 issue, and left some high level feedback:

• The updated pattern stops on any Summary by preceded by optional whitespace anywhere in the text, which may prematurely terminate content if Summary by appears in the middle of a sentence; consider tightening the lookahead to something like (?=\n\s*Summary by|\z) so it only triggers at the start of a line.
• The comment above RELEASE_NOTE_PATTERN still refers to stopping before a "\nSummary by" footer, but the regex now uses \s*Summary by; either align the implementation with the comment or update the comment to reflect the broader matching behavior.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The updated pattern stops on any `Summary by` preceded by optional whitespace anywhere in the text, which may prematurely terminate content if `Summary by` appears in the middle of a sentence; consider tightening the lookahead to something like `(?=\n\s*Summary by|\z)` so it only triggers at the start of a line.
- The comment above `RELEASE_NOTE_PATTERN` still refers to stopping before a "\nSummary by" footer, but the regex now uses `\s*Summary by`; either align the implementation with the comment or update the comment to reflect the broader matching behavior.

## Individual Comments

### Comment 1
<location path="presto-release-tools/src/main/java/com/facebook/presto/release/tasks/GenerateReleaseNotesTask.java" line_range="88-91" />
<code_context>
     // Pattern: "== release note(s)? ==" followed by optional whitespace and newline, then captures content
     // until it encounters "\nSummary by" or reaches end of string
-    protected static final Pattern RELEASE_NOTE_PATTERN = Pattern.compile("== release note(s)? ==\\w*\\n?((?:(?!\\nSummary by).)*)", CASE_INSENSITIVE + MULTILINE + DOTALL);
+    protected static final Pattern RELEASE_NOTE_PATTERN = Pattern.compile("== release note(s)? ==\\w*\\n?(.*?)(?=\\s*Summary by|\\z)", CASE_INSENSITIVE + MULTILINE + DOTALL);
     protected static final Pattern HEADER_PATTERN = Pattern.compile("(.*) change(s)$", CASE_INSENSITIVE);
     public static final List<Pattern> VALID_SECTION_HEADERS = ImmutableList.of(
</code_context>
<issue_to_address>
**suggestion (bug_risk):** The `Summary by` lookahead should likely be anchored to the start of a line to avoid truncating notes that mention it in the middle of text.

With `MULTILINE + DOTALL`, `(?=\s*Summary by|\z)` will end the match on any `Summary by` preceded by whitespace anywhere in the body, not only on footer lines. A note like `... as summarized in Summary by XYZ ...` would be truncated. If this is meant to target only footer-style lines, anchor to line start, e.g. `(?=^\s*Summary by|\z)` (keeping `MULTILINE`).

```suggestion
    // Matches release notes section and stops capturing before "Summary by" footer (added by bots like Sourcery)
    // Pattern: "== release note(s)? ==" followed by optional whitespace and newline, then captures content
    // until it encounters a line starting with "Summary by" or reaches end of string
    protected static final Pattern RELEASE_NOTE_PATTERN = Pattern.compile("== release note(s)? ==\\w*\\n?(.*?)(?=^\\s*Summary by|\\z)", CASE_INSENSITIVE + MULTILINE + DOTALL);
```
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[sourcery-ai]

suggestion (bug_risk): The Summary by lookahead should likely be anchored to the start of a line to avoid truncating notes that mention it in the middle of text.

With MULTILINE + DOTALL, (?=\s*Summary by|\z) will end the match on any Summary by preceded by whitespace anywhere in the body, not only on footer lines. A note like ... as summarized in Summary by XYZ ... would be truncated. If this is meant to target only footer-style lines, anchor to line start, e.g. (?=^\s*Summary by|\z) (keeping MULTILINE).

Suggested change

	// Matches release notes section and stops capturing before "Summary by" footer (added by bots like Sourcery)
	// Pattern: "== release note(s)? ==" followed by optional whitespace and newline, then captures content
	// until it encounters "\nSummary by" or reaches end of string
	protected static final Pattern RELEASE_NOTE_PATTERN = Pattern.compile("== release note(s)? ==\\w*\\n?((?:(?!\\nSummary by).)*)", CASE_INSENSITIVE + MULTILINE + DOTALL);
	protected static final Pattern RELEASE_NOTE_PATTERN = Pattern.compile("== release note(s)? ==\\w*\\n?(.*?)(?=\\s*Summary by|\\z)", CASE_INSENSITIVE + MULTILINE + DOTALL);
	// Matches release notes section and stops capturing before "Summary by" footer (added by bots like Sourcery)
	// Pattern: "== release note(s)? ==" followed by optional whitespace and newline, then captures content
	// until it encounters a line starting with "Summary by" or reaches end of string
	protected static final Pattern RELEASE_NOTE_PATTERN = Pattern.compile("== release note(s)? ==\\w*\\n?(.*?)(?=^\\s*Summary by|\\z)", CASE_INSENSITIVE + MULTILINE + DOTALL);