🔒 Fix: Use strict UTF-8 string conversion for database password

[bashandbone]

🔒 Fix: Use strict UTF-8 string conversion for database password

🎯 What: The from_utf8_lossy conversion function was replaced with String::from_utf8 during PostgreSQL password retrieval. Now, if the configuration provides invalid UTF-8 bytes for a password, an explicit StorageError::Backend is returned.
⚠️ Risk: from_utf8_lossy masks incorrectly encoded characters by substituting them with a replacement character (U+FFFD). If a password legitimately contained non-UTF-8 bytes or was corrupted in transmission, this allowed it to silently morph into a different incorrect password string. This silent mutation risks obfuscating authentication failures and causes unpredictability in password verifications.
🛡️ Solution: By enforcing strict UTF-8 compliance, passwords either correctly materialize as configured, or the initialization explicitly returns an actionable StorageError::Backend error detailing that the password contained invalid UTF-8 strings. This fails fast and avoids unexplainable downstream connection rejections.

I also fixed an unused variable compile error in crates/language/src/lib.rs that appeared when compiling the workspace.

---

PR created automatically by Jules for task 13212919964801170405 started by @bashandbone

Summary by Sourcery

Enforce strict UTF-8 handling for PostgreSQL passwords and fix a minor compile-time warning.

Bug Fixes:

• Return a backend storage error when the PostgreSQL password contains invalid UTF-8 instead of silently converting it with lossy decoding.
• Resolve an unused variable compilation warning in the language crate by correctly referencing the placeholder variable.

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Enforces strict UTF-8 handling when reading the PostgreSQL password so invalid encodings cause a clear backend error instead of silent lossy conversion, and fixes an unused variable compile warning in the language crate.

Sequence diagram for strict UTF-8 PostgreSQL password retrieval

sequenceDiagram
    actor App
    participant PostgresIncrementalBackend
    participant PgConfig

    App->>PostgresIncrementalBackend: initialize_from_pg_config(pg_config)
    PostgresIncrementalBackend->>PgConfig: get_password()
    PgConfig-->>PostgresIncrementalBackend: Option<password_bytes>
    alt password is Some
        PostgresIncrementalBackend->>PostgresIncrementalBackend: String::from_utf8(password_bytes.to_vec())
        alt valid UTF8
            PostgresIncrementalBackend->>PostgresIncrementalBackend: cfg.password = Some(pwd_str)
            PostgresIncrementalBackend-->>App: Ok(backend)
        else invalid UTF8
            PostgresIncrementalBackend-->>App: Err(StorageError::Backend("Invalid UTF-8 in password: ..."))
        end
    else password is None
        PostgresIncrementalBackend-->>App: Ok(backend_without_password)
    end

Loading

Class diagram for PostgresIncrementalBackend password handling and StorageError

classDiagram
    class PostgresIncrementalBackend {
        +cfg: PostgresConfig
        +from_pg_config(pg_config: PgConfig) Result<PostgresIncrementalBackend, StorageError>
    }

    class PgConfig {
        +get_user() Option<&str>
        +get_password() Option<&[u8]>
        +get_dbname() Option<&str>
    }

    class PostgresConfig {
        +user: Option<String>
        +password: Option<String>
        +dbname: Option<String>
    }

    class StorageError {
        +Backend(message: String)
    }

    PostgresIncrementalBackend o--> PostgresConfig
    PostgresIncrementalBackend ..> PgConfig : reads_from
    PostgresIncrementalBackend ..> StorageError : returns

    PgConfig ..> PostgresConfig : populates

Loading

File-Level Changes

Change	Details	Files
Enforce strict UTF-8 decoding for PostgreSQL password and surface invalid encodings as backend errors.	Replace lossy UTF-8 conversion of the password bytes with String::from_utf8 on a cloned buffer. Map UTF-8 decoding failures into StorageError::Backend with a descriptive error message. Assign the successfully decoded password string directly to the PostgreSQL config password field.	crates/flow/src/incremental/backends/postgres.rs
Fix unused variable warning in language crate to keep workspace compiling cleanly.	Update dummy assignment to reference _file_name instead of file_name so the correct variable is marked as used when certain features are disabled.	crates/language/src/lib.rs

---

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.

[sourcery-ai]

Hey - I've left some high level feedback:

• The change from let _ = file_name; to let _ = _file_name; in crates/language/src/lib.rs looks like a typo and will fail to compile because _file_name is not defined; it should likely remain file_name (or define _file_name).
• When converting the password, you can avoid an extra allocation by using String::from_utf8(password.to_owned()) instead of password.to_vec(), since to_owned is a bit more idiomatic on slices.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The change from `let _ = file_name;` to `let _ = _file_name;` in `crates/language/src/lib.rs` looks like a typo and will fail to compile because `_file_name` is not defined; it should likely remain `file_name` (or define `_file_name`).
- When converting the password, you can avoid an extra allocation by using `String::from_utf8(password.to_owned())` instead of `password.to_vec()`, since `to_owned` is a bit more idiomatic on slices.

---

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.}

[Copilot]

Pull request overview

Enforces strict UTF-8 decoding for PostgreSQL passwords (fail-fast on invalid bytes) and adjusts a variable usage in the language crate to fix a compilation issue.

Changes:

• Replace from_utf8_lossy with strict UTF-8 conversion when reading the PostgreSQL password, returning a StorageError::Backend on invalid UTF-8.
• Update unused-variable silencing logic in crates/language/src/lib.rs.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
crates/language/src/lib.rs	Tweaks unused-variable handling in extension detection logic.
crates/flow/src/incremental/backends/postgres.rs	Switches password decoding to strict UTF-8 with explicit error on invalid bytes.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

_file_name is referenced here, but the surrounding context indicates the variable is named file_name (per the removed line). Unless the variable was renamed elsewhere in this function, this will not compile. To silence the unused-variable warning, either revert to let _ = file_name; or rename the original binding to _file_name and remove this line entirely (a leading underscore on the binding already suppresses warnings).

[Copilot]

This adds an unconditional allocation/copy via password.to_vec() just to validate UTF-8. Since get_password() already yields bytes as a slice, prefer std::str::from_utf8(password) and then .to_owned() to avoid the extra allocation. This keeps the same strict UTF-8 behavior with less overhead.

Suggested change

	let pwd_str = String::from_utf8(password.to_vec())
	.map_err(|e| StorageError::Backend(format!("Invalid UTF-8 in password: {e}")))?;
	cfg.password = Some(pwd_str);
	let pwd_str = std::str::from_utf8(password)
	.map_err(|e| StorageError::Backend(format!("Invalid UTF-8 in password: {e}")))?;
	cfg.password = Some(pwd_str.to_owned());