cim_summary/backend/sql/complete_database_setup.sql

-- Complete Database Setup for CIM Summarizer
-- Run this in Supabase SQL Editor to create all necessary tables

-- 1. Create users table
CREATE TABLE IF NOT EXISTS users (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    firebase_uid VARCHAR(255) UNIQUE NOT NULL,
    email VARCHAR(255) UNIQUE NOT NULL,
    display_name VARCHAR(255),
    photo_url VARCHAR(1000),
    created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
    updated_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
    last_login_at TIMESTAMP WITH TIME ZONE
);

CREATE INDEX IF NOT EXISTS idx_users_firebase_uid ON users(firebase_uid);
CREATE INDEX IF NOT EXISTS idx_users_email ON users(email);

-- 2. Create update_updated_at_column function (needed for triggers)
CREATE OR REPLACE FUNCTION update_updated_at_column()
RETURNS TRIGGER AS $$
BEGIN
    NEW.updated_at = CURRENT_TIMESTAMP;
    RETURN NEW;
END;
$$ language 'plpgsql';

-- 3. Create documents table
CREATE TABLE IF NOT EXISTS documents (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    user_id VARCHAR(255) NOT NULL, -- Changed from UUID to VARCHAR to match Firebase UID
    original_file_name VARCHAR(500) NOT NULL,
    file_path VARCHAR(1000) NOT NULL,
    file_size BIGINT NOT NULL CHECK (file_size > 0),
    uploaded_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
    status VARCHAR(50) NOT NULL DEFAULT 'uploaded' CHECK (status IN ('uploading', 'uploaded', 'extracting_text', 'processing_llm', 'generating_pdf', 'completed', 'failed')),
    extracted_text TEXT,
    generated_summary TEXT,
    summary_markdown_path VARCHAR(1000),
    summary_pdf_path VARCHAR(1000),
    processing_started_at TIMESTAMP WITH TIME ZONE,
    processing_completed_at TIMESTAMP WITH TIME ZONE,
    error_message TEXT,
    analysis_data JSONB, -- Added for storing analysis results
    created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
    updated_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP
);

CREATE INDEX IF NOT EXISTS idx_documents_user_id ON documents(user_id);
CREATE INDEX IF NOT EXISTS idx_documents_status ON documents(status);
CREATE INDEX IF NOT EXISTS idx_documents_uploaded_at ON documents(uploaded_at);
CREATE INDEX IF NOT EXISTS idx_documents_processing_completed_at ON documents(processing_completed_at);
CREATE INDEX IF NOT EXISTS idx_documents_user_status ON documents(user_id, status);

CREATE TRIGGER update_documents_updated_at
    BEFORE UPDATE ON documents
    FOR EACH ROW
    EXECUTE FUNCTION update_updated_at_column();

-- 4. Create processing_jobs table
CREATE TABLE IF NOT EXISTS processing_jobs (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    document_id UUID NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
    user_id VARCHAR(255) NOT NULL,
    status VARCHAR(50) NOT NULL DEFAULT 'pending' CHECK (status IN ('pending', 'processing', 'completed', 'failed', 'retrying')),
    attempts INTEGER NOT NULL DEFAULT 0,
    max_attempts INTEGER NOT NULL DEFAULT 3,
    options JSONB,
    created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
    started_at TIMESTAMP WITH TIME ZONE,
    completed_at TIMESTAMP WITH TIME ZONE,
    updated_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
    error TEXT,
    last_error_at TIMESTAMP WITH TIME ZONE,
    result JSONB
);

CREATE INDEX IF NOT EXISTS idx_processing_jobs_status ON processing_jobs(status);
CREATE INDEX IF NOT EXISTS idx_processing_jobs_created_at ON processing_jobs(created_at);
CREATE INDEX IF NOT EXISTS idx_processing_jobs_document_id ON processing_jobs(document_id);
CREATE INDEX IF NOT EXISTS idx_processing_jobs_user_id ON processing_jobs(user_id);
CREATE INDEX IF NOT EXISTS idx_processing_jobs_pending ON processing_jobs(status, created_at) WHERE status = 'pending';
CREATE INDEX IF NOT EXISTS idx_processing_jobs_last_error_at ON processing_jobs(last_error_at) WHERE status = 'retrying';
CREATE INDEX IF NOT EXISTS idx_processing_jobs_attempts ON processing_jobs(attempts);

CREATE TRIGGER update_processing_jobs_updated_at
    BEFORE UPDATE ON processing_jobs
    FOR EACH ROW
    EXECUTE FUNCTION update_updated_at_column();

-- Verify all tables were created
SELECT table_name
FROM information_schema.tables
WHERE table_schema = 'public'
AND table_name IN ('users', 'documents', 'processing_jobs')
ORDER BY table_name;