Merge pull request #107 from RayLabsHQ/fix/issue-97-migration-duplicates

fix: resolve migration 0005 duplicate constraint failure (#97)

.github/workflows/docker-build.yml

@@ -10,6 +10,10 @@ on:
       - 'package.json'
       - 'bun.lock*'
       - '.github/workflows/docker-build.yml'
+      - 'docker-entrypoint.sh'
+      - 'drizzle/**'
+      - 'scripts/**'
+      - 'src/**'
   pull_request:
     paths:
       - 'Dockerfile'
@@ -17,6 +21,10 @@ on:
       - 'package.json'
       - 'bun.lock*'
       - '.github/workflows/docker-build.yml'
+      - 'docker-entrypoint.sh'
+      - 'drizzle/**'
+      - 'scripts/**'
+      - 'src/**'
   schedule:
     - cron: '0 0 * * 0'  # Weekly security scan on Sunday at midnight
 

docker-entrypoint.sh

@@ -120,161 +120,13 @@ fi
 # Dependencies are already installed during the Docker build process
 
 # Initialize the database if it doesn't exist
+# Note: Drizzle migrations will be run automatically when the app starts (see src/lib/db/index.ts)
 if [ ! -f "/app/data/gitea-mirror.db" ]; then
-  echo "Initializing database..."
-  if [ -f "dist/scripts/init-db.js" ]; then
-    bun dist/scripts/init-db.js
-  elif [ -f "dist/scripts/manage-db.js" ]; then
-    bun dist/scripts/manage-db.js init
-  elif [ -f "scripts/manage-db.ts" ]; then
-    bun scripts/manage-db.ts init
-  else
-    echo "Warning: Could not find database initialization scripts in dist/scripts."
-    echo "Creating and initializing database manually..."
-
-    # Create the database file
+  echo "Database not found. It will be created and initialized via Drizzle migrations on first app startup..."
+  # Create empty database file so migrations can run
   touch /app/data/gitea-mirror.db
-
-    # Initialize the database with required tables
-    sqlite3 /app/data/gitea-mirror.db <<EOF
-    CREATE TABLE IF NOT EXISTS users (
-      id TEXT PRIMARY KEY,
-      username TEXT NOT NULL,
-      password TEXT NOT NULL,
-      email TEXT NOT NULL,
-      created_at INTEGER NOT NULL,
-      updated_at INTEGER NOT NULL
-    );
-
-    CREATE TABLE IF NOT EXISTS configs (
-      id TEXT PRIMARY KEY,
-      user_id TEXT NOT NULL,
-      name TEXT NOT NULL,
-      is_active INTEGER NOT NULL DEFAULT 1,
-      github_config TEXT NOT NULL,
-      gitea_config TEXT NOT NULL,
-      include TEXT NOT NULL DEFAULT '["*"]',
-      exclude TEXT NOT NULL DEFAULT '[]',
-      schedule_config TEXT NOT NULL,
-      created_at INTEGER NOT NULL DEFAULT (strftime('%s','now')),
-      updated_at INTEGER NOT NULL DEFAULT (strftime('%s','now')),
-      FOREIGN KEY (user_id) REFERENCES users(id)
-    );
-
-    CREATE TABLE IF NOT EXISTS repositories (
-      id TEXT PRIMARY KEY,
-      user_id TEXT NOT NULL,
-      config_id TEXT NOT NULL,
-      name TEXT NOT NULL,
-      full_name TEXT NOT NULL,
-      url TEXT NOT NULL,
-      clone_url TEXT NOT NULL,
-      owner TEXT NOT NULL,
-      organization TEXT,
-      mirrored_location TEXT DEFAULT '',
-      destination_org TEXT,
-      is_private INTEGER NOT NULL DEFAULT 0,
-      is_fork INTEGER NOT NULL DEFAULT 0,
-      forked_from TEXT,
-      has_issues INTEGER NOT NULL DEFAULT 0,
-      is_starred INTEGER NOT NULL DEFAULT 0,
-      is_archived INTEGER NOT NULL DEFAULT 0,
-      size INTEGER NOT NULL DEFAULT 0,
-      has_lfs INTEGER NOT NULL DEFAULT 0,
-      has_submodules INTEGER NOT NULL DEFAULT 0,
-      language TEXT,
-      description TEXT,
-      default_branch TEXT NOT NULL,
-      visibility TEXT NOT NULL DEFAULT 'public',
-      status TEXT NOT NULL DEFAULT 'imported',
-      last_mirrored INTEGER,
-      error_message TEXT,
-      created_at INTEGER NOT NULL DEFAULT (strftime('%s','now')),
-      updated_at INTEGER NOT NULL DEFAULT (strftime('%s','now')),
-      FOREIGN KEY (user_id) REFERENCES users(id),
-      FOREIGN KEY (config_id) REFERENCES configs(id)
-    );
-
-    -- Uniqueness of (user_id, full_name) for repositories is enforced via drizzle migrations
-
-    CREATE TABLE IF NOT EXISTS organizations (
-      id TEXT PRIMARY KEY,
-      user_id TEXT NOT NULL,
-      config_id TEXT NOT NULL,
-      name TEXT NOT NULL,
-      avatar_url TEXT NOT NULL,
-      membership_role TEXT NOT NULL DEFAULT 'member',
-      is_included INTEGER NOT NULL DEFAULT 1,
-      status TEXT NOT NULL DEFAULT 'imported',
-      last_mirrored INTEGER,
-      error_message TEXT,
-      repository_count INTEGER NOT NULL DEFAULT 0,
-      created_at INTEGER NOT NULL DEFAULT (strftime('%s','now')),
-      updated_at INTEGER NOT NULL DEFAULT (strftime('%s','now')),
-      FOREIGN KEY (user_id) REFERENCES users(id),
-      FOREIGN KEY (config_id) REFERENCES configs(id)
-    );
-
-    CREATE TABLE IF NOT EXISTS mirror_jobs (
-      id TEXT PRIMARY KEY,
-      user_id TEXT NOT NULL,
-      repository_id TEXT,
-      repository_name TEXT,
-      organization_id TEXT,
-      organization_name TEXT,
-      details TEXT,
-      status TEXT NOT NULL DEFAULT 'imported',
-      message TEXT NOT NULL,
-      timestamp TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
-
-      -- New fields for job resilience
-      job_type TEXT NOT NULL DEFAULT 'mirror',
-      batch_id TEXT,
-      total_items INTEGER,
-      completed_items INTEGER DEFAULT 0,
-      item_ids TEXT, -- JSON array as text
-      completed_item_ids TEXT DEFAULT '[]', -- JSON array as text
-      in_progress INTEGER NOT NULL DEFAULT 0, -- Boolean as integer
-      started_at TIMESTAMP,
-      completed_at TIMESTAMP,
-      last_checkpoint TIMESTAMP,
-
-      FOREIGN KEY (user_id) REFERENCES users(id)
-    );
-
-    CREATE INDEX IF NOT EXISTS idx_mirror_jobs_user_id ON mirror_jobs(user_id);
-    CREATE INDEX IF NOT EXISTS idx_mirror_jobs_batch_id ON mirror_jobs(batch_id);
-    CREATE INDEX IF NOT EXISTS idx_mirror_jobs_in_progress ON mirror_jobs(in_progress);
-    CREATE INDEX IF NOT EXISTS idx_mirror_jobs_job_type ON mirror_jobs(job_type);
-    CREATE INDEX IF NOT EXISTS idx_mirror_jobs_timestamp ON mirror_jobs(timestamp);
-
-    CREATE TABLE IF NOT EXISTS events (
-      id TEXT PRIMARY KEY,
-      user_id TEXT NOT NULL,
-      channel TEXT NOT NULL,
-      payload TEXT NOT NULL,
-      read INTEGER NOT NULL DEFAULT 0,
-      created_at INTEGER NOT NULL DEFAULT (strftime('%s','now')),
-      FOREIGN KEY (user_id) REFERENCES users(id)
-    );
-
-    CREATE INDEX IF NOT EXISTS idx_events_user_channel ON events(user_id, channel);
-    CREATE INDEX IF NOT EXISTS idx_events_created_at ON events(created_at);
-    CREATE INDEX IF NOT EXISTS idx_events_read ON events(read);
-EOF
-    echo "Database initialized with required tables."
-  fi
 else
-  echo "Database already exists, checking for issues..."
-  if [ -f "dist/scripts/fix-db-issues.js" ]; then
-    bun dist/scripts/fix-db-issues.js
-  elif [ -f "dist/scripts/manage-db.js" ]; then
-    bun dist/scripts/manage-db.js fix
-  elif [ -f "scripts/manage-db.ts" ]; then
-    bun scripts/manage-db.ts fix
-  fi
-
-  echo "Database exists, checking integrity..."
+  echo "Database already exists, Drizzle will check for pending migrations on startup..."
 fi
 
 # Extract version from package.json and set as environment variable

drizzle/0005_polite_preak.sql

@@ -1 +1,11 @@
-CREATE UNIQUE INDEX `uniq_repositories_user_full_name` ON `repositories` (`user_id`,`full_name`);
+-- Step 1: Remove duplicate repositories, keeping the most recently updated one
+-- This handles cases where users have duplicate entries from before the unique constraint
+DELETE FROM repositories
+WHERE rowid NOT IN (
+  SELECT MAX(rowid)
+  FROM repositories
+  GROUP BY user_id, full_name
+);
+--> statement-breakpoint
+-- Step 2: Now create the unique index safely
+CREATE UNIQUE INDEX uniq_repositories_user_full_name ON repositories (user_id, full_name);