query-orchestration/internal/database/migrations_collapsed/00000000000004_batch_uploads.up.sql

-- Migration 004: Batch Uploads
-- Batch upload tracking for ZIP file uploads
-- Merges original migrations 103 + 104

-- Create batch status ENUM type
CREATE TYPE batch_status AS ENUM (
    'processing',       -- Currently processing
    'completed',        -- All documents processed (may have individual failures)
    'failed',           -- Batch-level failure (ZIP corrupt, etc.)
    'cancelled'         -- Cancelled by user
);

-- Create batch uploads table with all columns
CREATE TABLE batch_uploads (
    id uuid PRIMARY KEY DEFAULT uuid_generate_v7(),
    client_id varchar(255) NOT NULL,
    original_filename text NOT NULL,

    -- Essential batch metrics
    total_documents integer NOT NULL,
    processed_documents integer NOT NULL DEFAULT 0,
    failed_documents integer NOT NULL DEFAULT 0,
    invalid_type_documents integer NOT NULL DEFAULT 0,

    -- Status and progress
    status batch_status NOT NULL DEFAULT 'processing',
    progress_percent integer NOT NULL DEFAULT 0,

    -- Failed document filenames (JSON array)
    failed_filenames jsonb DEFAULT '[]'::jsonb,

    -- Timestamps
    created_at timestamp NOT NULL DEFAULT NOW(),
    completed_at timestamp,

    -- Storage metadata (from migration 104)
    archive_bucket text,
    archive_key text,
    file_size_bytes bigint,

    FOREIGN KEY (client_id) REFERENCES clients(clientId),

    -- Constraint: storage metadata consistency
    CONSTRAINT batch_storage_consistent CHECK (
        (archive_bucket IS NULL AND archive_key IS NULL AND file_size_bytes IS NULL) OR
        (archive_bucket IS NOT NULL AND archive_key IS NOT NULL)
    )
);

-- Create indexes for efficient queries
CREATE INDEX idx_batch_uploads_client_id ON batch_uploads(client_id);
CREATE INDEX idx_batch_uploads_status ON batch_uploads(status);