modification of FileNode to include hash-calculated hash for existing files

package.json

@@ -4,6 +4,7 @@
   "private": true,
   "scripts": {
     "dev": "next dev",
+    "backfill": "tsx scripts/backfill-hashes.ts",
     "build": "next build",
     "start": "next start",
     "lint": "eslint",
@@ -21,7 +22,7 @@
     "@mui/material-nextjs": "^7.3.6",
     "@mui/x-data-grid": "^8.24.0",
     "@prisma/adapter-pg": "^7.2.0",
-    "@prisma/client": "^7.2.0",
+    "@prisma/client": "7.4.0",
     "epub": "^1.3.0",
     "epub2": "^3.0.2",
     "exif-reader": "^2.0.3",
@@ -43,7 +44,8 @@
     "dotenv-cli": "^11.0.0",
     "eslint": "^9",
     "eslint-config-next": "16.1.1",
-    "prisma": "^6.19.2",
+    "prisma": "7.4.0",
+    "tsx": "^4.21.0",
     "typescript": "^5"
   }
 }

prisma.config.ts

@@ -1,13 +1,13 @@
+// prisma.config.ts
 import { config } from "dotenv";
 config({ path: ".env.local" }); 
 
-import { defineConfig } from "prisma/config";
+import { defineConfig, env } from "prisma/config";
 
 export default defineConfig({
   schema: "prisma/schema.prisma",
   datasource: {
-    // This is now the ONLY place where the DB connection string is defined
-    // prisma.config.ts
-  url: process.env.DATABASE_URL!, 
+    // This is where Prisma 7 looks for the connection string
+    url: env("DATABASE_URL"), 
   },
 });

prisma/migrations/0_init/migration.sql

@@ -1,20 +1,58 @@
+-- CreateSchema
+CREATE SCHEMA IF NOT EXISTS "public";
+
+-- CreateEnum
+CREATE TYPE "Role" AS ENUM ('USER', 'ADMIN');
+
 -- CreateTable
 CREATE TABLE "User" (
     "id" TEXT NOT NULL,
-    "azureAdUserId" TEXT NOT NULL,
+    "name" TEXT,
     "email" TEXT NOT NULL,
-    "displayName" TEXT,
+    "role" "Role" NOT NULL DEFAULT 'USER',
+    "emailVerified" TIMESTAMP(3),
+    "image" TEXT,
+    "azureAdUserId" TEXT,
     "createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
     "updatedAt" TIMESTAMP(3) NOT NULL,
 
     CONSTRAINT "User_pkey" PRIMARY KEY ("id")
 );
 
+-- CreateTable
+CREATE TABLE "Account" (
+    "id" TEXT NOT NULL,
+    "userId" TEXT NOT NULL,
+    "type" TEXT NOT NULL,
+    "provider" TEXT NOT NULL,
+    "providerAccountId" TEXT NOT NULL,
+    "refresh_token" TEXT,
+    "access_token" TEXT,
+    "expires_at" INTEGER,
+    "token_type" TEXT,
+    "scope" TEXT,
+    "id_token" TEXT,
+    "session_state" TEXT,
+
+    CONSTRAINT "Account_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "Session" (
+    "id" TEXT NOT NULL,
+    "sessionToken" TEXT NOT NULL,
+    "userId" TEXT NOT NULL,
+    "expires" TIMESTAMP(3) NOT NULL,
+
+    CONSTRAINT "Session_pkey" PRIMARY KEY ("id")
+);
+
 -- CreateTable
 CREATE TABLE "FileNode" (
     "id" TEXT NOT NULL,
     "name" TEXT NOT NULL,
     "size" BIGINT,
+    "hash" TEXT,
     "isFolder" BOOLEAN NOT NULL DEFAULT false,
     "oneDriveId" TEXT,
     "path" TEXT NOT NULL,
@@ -29,11 +67,17 @@ CREATE TABLE "FileNode" (
     CONSTRAINT "FileNode_pkey" PRIMARY KEY ("id")
 );
 
+-- CreateIndex
+CREATE UNIQUE INDEX "User_email_key" ON "User"("email");
+
 -- CreateIndex
 CREATE UNIQUE INDEX "User_azureAdUserId_key" ON "User"("azureAdUserId");
 
 -- CreateIndex
-CREATE UNIQUE INDEX "User_email_key" ON "User"("email");
+CREATE UNIQUE INDEX "Account_provider_providerAccountId_key" ON "Account"("provider", "providerAccountId");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "Session_sessionToken_key" ON "Session"("sessionToken");
 
 -- CreateIndex
 CREATE UNIQUE INDEX "FileNode_oneDriveId_key" ON "FileNode"("oneDriveId");
@@ -47,8 +91,15 @@ CREATE INDEX "FileNode_orderIndex_idx" ON "FileNode"("orderIndex");
 -- CreateIndex
 CREATE UNIQUE INDEX "FileNode_ownerId_path_key" ON "FileNode"("ownerId", "path");
 
+-- AddForeignKey
+ALTER TABLE "Account" ADD CONSTRAINT "Account_userId_fkey" FOREIGN KEY ("userId") REFERENCES "User"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "Session" ADD CONSTRAINT "Session_userId_fkey" FOREIGN KEY ("userId") REFERENCES "User"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
 -- AddForeignKey
 ALTER TABLE "FileNode" ADD CONSTRAINT "FileNode_ownerId_fkey" FOREIGN KEY ("ownerId") REFERENCES "User"("id") ON DELETE RESTRICT ON UPDATE CASCADE;
 
 -- AddForeignKey
-ALTER TABLE "FileNode" ADD CONSTRAINT "FileNode_parentId_fkey" FOREIGN KEY ("parentId") REFERENCES "FileNode"("id") ON DELETE SET NULL ON UPDATE CASCADE;
+ALTER TABLE "FileNode" ADD CONSTRAINT "FileNode_parentId_fkey" FOREIGN KEY ("parentId") REFERENCES "FileNode"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+

prisma/migrations/20260107012848_add_auth_tables/migration.sql

@@ -1,52 +0,0 @@
-/*
-  Warnings:
-
-  - You are about to drop the column `displayName` on the `User` table. All the data in the column will be lost.
-
-*/
--- AlterTable
-ALTER TABLE "User" DROP COLUMN "displayName",
-ADD COLUMN     "emailVerified" TIMESTAMP(3),
-ADD COLUMN     "image" TEXT,
-ADD COLUMN     "name" TEXT,
-ALTER COLUMN "azureAdUserId" DROP NOT NULL;
-
--- CreateTable
-CREATE TABLE "Account" (
-    "id" TEXT NOT NULL,
-    "userId" TEXT NOT NULL,
-    "type" TEXT NOT NULL,
-    "provider" TEXT NOT NULL,
-    "providerAccountId" TEXT NOT NULL,
-    "refresh_token" TEXT,
-    "access_token" TEXT,
-    "expires_at" INTEGER,
-    "token_type" TEXT,
-    "scope" TEXT,
-    "id_token" TEXT,
-    "session_state" TEXT,
-
-    CONSTRAINT "Account_pkey" PRIMARY KEY ("id")
-);
-
--- CreateTable
-CREATE TABLE "Session" (
-    "id" TEXT NOT NULL,
-    "sessionToken" TEXT NOT NULL,
-    "userId" TEXT NOT NULL,
-    "expires" TIMESTAMP(3) NOT NULL,
-
-    CONSTRAINT "Session_pkey" PRIMARY KEY ("id")
-);
-
--- CreateIndex
-CREATE UNIQUE INDEX "Account_provider_providerAccountId_key" ON "Account"("provider", "providerAccountId");
-
--- CreateIndex
-CREATE UNIQUE INDEX "Session_sessionToken_key" ON "Session"("sessionToken");
-
--- AddForeignKey
-ALTER TABLE "Account" ADD CONSTRAINT "Account_userId_fkey" FOREIGN KEY ("userId") REFERENCES "User"("id") ON DELETE CASCADE ON UPDATE CASCADE;
-
--- AddForeignKey
-ALTER TABLE "Session" ADD CONSTRAINT "Session_userId_fkey" FOREIGN KEY ("userId") REFERENCES "User"("id") ON DELETE CASCADE ON UPDATE CASCADE;

prisma/migrations/20260213150829_lock_hashes_unique/migration.sql

@@ -0,0 +1,8 @@
+/*
+  Warnings:
+
+  - A unique constraint covering the columns `[hash]` on the table `FileNode` will be added. If there are existing duplicate values, this will fail.
+
+*/
+-- CreateIndex
+CREATE UNIQUE INDEX "FileNode_hash_key" ON "FileNode"("hash");

prisma/schema.prisma

@@ -60,6 +60,7 @@ model FileNode {
   id           String    @id
   name         String
   size         BigInt?   // Preserved your BigInt size column
+  hash         String?   @unique // <--- Added for duplicate detection (MD5 or SHA-256)
   isFolder     Boolean   @default(false)
   oneDriveId   String?   @unique
   path         String

scripts/backfill-hashes.ts

@@ -0,0 +1,58 @@
+import 'dotenv/config';
+import { prisma } from '../src/lib/prisma';
+import * as nodeCrypto from 'crypto';
+
+function generateFileHash(buffer: Buffer): string {
+  return nodeCrypto.createHash('md5').update(buffer).digest('hex');
+}
+
+/**
+ * Replace this with your actual OneDrive download logic!
+ */
+async function getFromOneDrive(oneDriveId: string): Promise<Buffer> {
+  // For now, let's pretend we downloaded it to test the DB update
+  // DELETE THESE 2 LINES when you add your real OneDrive fetch code:
+  console.log(`   ⬇️  Downloading ${oneDriveId}...`);
+  return Buffer.from(`mock-data-for-${oneDriveId}`); 
+}
+
+async function backfill() {
+  console.log('🏁 Starting backfill with Prisma Adapter...');
+
+  try {
+    const files = await prisma.fileNode.findMany({
+      where: { isFolder: false, hash: null },
+    });
+
+    console.log(`📂 Found ${files.length} files to process.`);
+
+    for (const file of files) {
+      try {
+        process.stdout.write(`Processing: ${file.name}... `);
+
+        // 1. Get the file content
+        const buffer = await getFromOneDrive(file.oneDriveId!);
+
+        // 2. Generate the hash
+        const hash = generateFileHash(buffer);
+
+        // 3. Update the database
+        await prisma.fileNode.update({
+          where: { id: file.id },
+          data: { hash: hash }
+        });
+
+        console.log(`✅ Success! (Hash: ${hash.substring(0, 8)}...)`);
+      } catch (err) {
+        console.log(`❌ Failed: ${err instanceof Error ? err.message : err}`);
+      }
+    }
+  } catch (error) {
+    console.error('🚨 Script Error:', error);
+  } finally {
+    await prisma.$disconnect();
+    console.log('🏁 Finished.');
+  }
+}
+
+backfill();

src/lib/hashing.ts

@@ -0,0 +1,8 @@
+import crypto from 'crypto';
+
+/**
+ * Generates an MD5 hash from a file buffer.
+ */
+export function generateFileHash(buffer: Buffer): string {
+  return crypto.createHash('md5').update(buffer).digest('hex');
+}

src/lib/metadata-extractor.ts

@@ -61,7 +61,7 @@ export async function extractMetadata(buffer: Buffer, filename: string): Promise
     }
 
     // --- 2. IMAGE EXTRACTION ---
-    if (['jpg', 'jpeg', 'png', 'webp'].includes(extension || '')) {
+    if (['jpg', 'jpeg', 'png', 'webp','heic'].includes(extension || '')) {
       const image = sharp(buffer);
       const metadata = await image.metadata();
       let details = {};