feat(transformers): Add MR transformer and polymorphic discussion support

Introduces NormalizedMergeRequest transformer and updates discussion
normalization to handle both issue and MR discussions polymorphically.

New transformers:
- NormalizedMergeRequest: Transforms API MergeRequest to database row,
  extracting labels/assignees/reviewers into separate collections for
  junction table insertion. Handles draft detection, detailed_merge_status
  preference over deprecated merge_status, and merge_user over merged_by.

Discussion transformer updates:
- NormalizedDiscussion now takes noteable_type ("Issue" | "MergeRequest")
  and noteable_id for polymorphic FK binding
- normalize_discussions_for_issue(): Convenience wrapper for issues
- normalize_discussions_for_mr(): Convenience wrapper for MRs
- DiffNote position fields (type, line_range, SHA triplet) now extracted
  from API position object for code review context

Design decisions:
- Transformer returns (normalized_item, labels, assignees, reviewers)
  tuple for efficient batch insertion without re-querying
- Timestamps converted to ms epoch for SQLite storage consistency
- Optional fields use map() chains for clean null handling

The polymorphic discussion approach allows reusing the same discussions
and notes tables for both issues and MRs, with noteable_type + FK
determining the parent relationship.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Taylor Eernisse
2026-01-26 22:45:29 -05:00
parent cc8c489fd2
commit d33f24c91b
4 changed files with 340 additions and 9 deletions

View File

@@ -0,0 +1,155 @@
//! Merge request transformer: converts GitLabMergeRequest to local schema.
use chrono::DateTime;
use std::time::{SystemTime, UNIX_EPOCH};
use crate::gitlab::types::GitLabMergeRequest;
/// Get current time in milliseconds since Unix epoch.
fn now_ms() -> i64 {
SystemTime::now()
.duration_since(UNIX_EPOCH)
.expect("Time went backwards")
.as_millis() as i64
}
/// Parse ISO 8601 timestamp to milliseconds since Unix epoch.
fn iso_to_ms(ts: &str) -> Result<i64, String> {
DateTime::parse_from_rfc3339(ts)
.map(|dt| dt.timestamp_millis())
.map_err(|e| format!("Failed to parse timestamp '{}': {}", ts, e))
}
/// Parse optional ISO 8601 timestamp to optional milliseconds since Unix epoch.
fn iso_to_ms_opt(ts: &Option<String>) -> Result<Option<i64>, String> {
match ts {
Some(s) => iso_to_ms(s).map(Some),
None => Ok(None),
}
}
/// Local schema representation of a merge request row.
#[derive(Debug, Clone)]
pub struct NormalizedMergeRequest {
pub gitlab_id: i64,
pub project_id: i64,
pub iid: i64,
pub title: String,
pub description: Option<String>,
pub state: String,
pub draft: bool,
pub author_username: String,
pub source_branch: String,
pub target_branch: String,
pub head_sha: Option<String>,
pub references_short: Option<String>,
pub references_full: Option<String>,
pub detailed_merge_status: Option<String>,
pub merge_user_username: Option<String>,
pub created_at: i64, // ms epoch UTC
pub updated_at: i64, // ms epoch UTC
pub merged_at: Option<i64>, // ms epoch UTC
pub closed_at: Option<i64>, // ms epoch UTC
pub last_seen_at: i64, // ms epoch UTC
pub web_url: String,
}
/// Merge request bundled with extracted metadata.
#[derive(Debug, Clone)]
pub struct MergeRequestWithMetadata {
pub merge_request: NormalizedMergeRequest,
pub label_names: Vec<String>,
pub assignee_usernames: Vec<String>,
pub reviewer_usernames: Vec<String>,
}
/// Transform a GitLab merge request into local schema format.
///
/// # Arguments
/// * `gitlab_mr` - The GitLab MR API response
/// * `local_project_id` - The local database project ID (not GitLab's project_id)
///
/// # Returns
/// * `Ok(MergeRequestWithMetadata)` - Transformed MR with extracted metadata
/// * `Err(String)` - Error message if transformation fails (e.g., invalid timestamps)
pub fn transform_merge_request(
gitlab_mr: &GitLabMergeRequest,
local_project_id: i64,
) -> Result<MergeRequestWithMetadata, String> {
// Parse required timestamps
let created_at = iso_to_ms(&gitlab_mr.created_at)?;
let updated_at = iso_to_ms(&gitlab_mr.updated_at)?;
// Parse optional timestamps
let merged_at = iso_to_ms_opt(&gitlab_mr.merged_at)?;
let closed_at = iso_to_ms_opt(&gitlab_mr.closed_at)?;
// Draft: prefer draft, fallback to work_in_progress
let is_draft = gitlab_mr.draft || gitlab_mr.work_in_progress;
// Merge status: prefer detailed_merge_status over legacy
let detailed_merge_status = gitlab_mr
.detailed_merge_status
.clone()
.or_else(|| gitlab_mr.merge_status_legacy.clone());
// Merge user: prefer merge_user over merged_by
let merge_user_username = gitlab_mr
.merge_user
.as_ref()
.map(|u| u.username.clone())
.or_else(|| gitlab_mr.merged_by.as_ref().map(|u| u.username.clone()));
// References extraction
let (references_short, references_full) = gitlab_mr
.references
.as_ref()
.map(|r| (Some(r.short.clone()), Some(r.full.clone())))
.unwrap_or((None, None));
// Head SHA
let head_sha = gitlab_mr.sha.clone();
// Extract assignee usernames
let assignee_usernames: Vec<String> = gitlab_mr
.assignees
.iter()
.map(|a| a.username.clone())
.collect();
// Extract reviewer usernames
let reviewer_usernames: Vec<String> = gitlab_mr
.reviewers
.iter()
.map(|r| r.username.clone())
.collect();
Ok(MergeRequestWithMetadata {
merge_request: NormalizedMergeRequest {
gitlab_id: gitlab_mr.id,
project_id: local_project_id,
iid: gitlab_mr.iid,
title: gitlab_mr.title.clone(),
description: gitlab_mr.description.clone(),
state: gitlab_mr.state.clone(),
draft: is_draft,
author_username: gitlab_mr.author.username.clone(),
source_branch: gitlab_mr.source_branch.clone(),
target_branch: gitlab_mr.target_branch.clone(),
head_sha,
references_short,
references_full,
detailed_merge_status,
merge_user_username,
created_at,
updated_at,
merged_at,
closed_at,
last_seen_at: now_ms(),
web_url: gitlab_mr.web_url.clone(),
},
label_names: gitlab_mr.labels.clone(),
assignee_usernames,
reviewer_usernames,
})
}