[AI-01] Adding OCR and complementary changes.

.gitignore

@@ -14,6 +14,9 @@ aws/
 *.md
 !**/README.md
 
+# Generated snapshots (regenerate as needed)
+p1_integration_snapshot.md
+
 # Frontend build outputs and dependencies
 client/node_modules/
 client/dist/

Dockerfile

@@ -1,6 +1,7 @@
 # ============================================
 # Stage 1: Build the Spring Boot application
 # ============================================
+# Pin Gradle and JDK versions to prevent unexpected upgrades
 FROM gradle:8.8-jdk21-alpine AS build
 
 WORKDIR /src
@@ -19,17 +20,30 @@ COPY src ./src
 RUN ./gradlew --no-daemon clean bootJar
 
 # ============================================
-# Stage 2: Runtime image
+# Stage 2: Runtime image (Ubuntu Jammy for Tesseract)
 # ============================================
-FROM amazoncorretto:21-alpine
+# Pin specific JRE version for reproducible builds
+# Format: eclipse-temurin:{java_version}_{build_version}-jre-jammy
+FROM eclipse-temurin:21.0.5_11-jre-jammy
 
 WORKDIR /app
 
+# Pin Datadog Java agent version
 ARG DD_JAVA_AGENT_VERSION=1.52.1
 
-# Install runtime dependencies (curl for healthchecks, su-exec for privilege dropping)
-RUN apk add --no-cache curl su-exec && \
-    adduser -D -u 10001 -s /bin/sh appuser
+# Install runtime dependencies including Tesseract OCR
+# Note: Ubuntu 22.04 (Jammy) ships with Tesseract 4.1.1
+# Tess4J 5.16.0 is compatible with Tesseract 4.x and 5.x
+RUN apt-get update && apt-get install -y --no-install-recommends \
+      curl \
+      gosu \
+      tesseract-ocr \
+      tesseract-ocr-eng && \
+    rm -rf /var/lib/apt/lists/* && \
+    useradd -u 10001 -m -s /bin/sh appuser
+
+# Verify Tesseract is installed and working (4.x or 5.x)
+RUN tesseract --version 2>&1 | head -1
 
 # Copy the boot JAR from build stage
 COPY --from=build /src/build/libs/app.jar /app/app.jar
@@ -48,11 +62,16 @@ RUN set -eux; \
       awk '{print $1"  /app/dd-java-agent.jar"}' /tmp/dd.jar.sha512 | sha512sum -c -; \
     fi || echo "Datadog agent download failed, continuing without it"
 
+# Environment variables for Tesseract
+ENV OMP_THREAD_LIMIT=1
+ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata
+
 # Free-tier friendly memory settings (prevents OOM on t3.micro/small)
-ENV JAVA_TOOL_OPTIONS="-XX:MaxRAMPercentage=65.0 -XX:+UseSerialGC"
+ENV JAVA_TOOL_OPTIONS="-javaagent:/app/dd-java-agent.jar -XX:MaxRAMPercentage=75.0 -XX:+UseSerialGC"
 ENV HOME=/tmp
 
 EXPOSE 8080
 
 # Start as root to read secrets, then drop privileges in entrypoint
 ENTRYPOINT ["/app/load-secrets.sh"]
+

build.gradle.kts

@@ -25,7 +25,7 @@ dependencies {
 
     runtimeOnly("io.jsonwebtoken:jjwt-impl:0.12.6")
     runtimeOnly("io.jsonwebtoken:jjwt-jackson:0.12.6")
-    runtimeOnly("org.postgresql:postgresql")
+    implementation("org.postgresql:postgresql")
 
     compileOnly("org.projectlombok:lombok")
 
@@ -46,6 +46,12 @@ dependencies {
     implementation("com.bucket4j:bucket4j-core:8.10.1")
     implementation("com.github.ben-manes.caffeine:caffeine:3.2.2")
     implementation("org.springdoc:springdoc-openapi-starter-webmvc-ui:2.8.13")
+
+    // OCR and PDF processing
+    implementation("net.sourceforge.tess4j:tess4j:5.16.0")
+    implementation("org.apache.pdfbox:pdfbox:3.0.6")
+    implementation("net.java.dev.jna:jna:5.18.1")
+
     annotationProcessor("org.projectlombok:lombok")
     annotationProcessor("org.springframework.boot:spring-boot-configuration-processor")
     testImplementation("org.springframework.boot:spring-boot-starter-test")

client/package.json

@@ -24,6 +24,7 @@
   },
   "dependencies": {
     "@tanstack/react-query": "^5.60.0",
+    "dompurify": "^3.3.0",
     "lucide-react": "^0.453.0",
     "react": "^19.2.0",
     "react-dom": "^19.2.0",

client/src/App.tsx

@@ -11,6 +11,7 @@ import {UploadPanel} from '@/components/files/UploadPanel';
 import {LoginPage} from '@/pages/LoginPage';
 import {RegisterPage} from '@/pages/RegisterPage';
 import {FilesPage} from '@/pages/FilesPage';
+import {SearchPage} from '@/pages/SearchPage';
 
 const queryClient = new QueryClient({
     defaultOptions: {
@@ -42,6 +43,16 @@ export function App() {
                                         </AuthGuard>
                                     }
                                 />
+                                <Route
+                                    path="/search"
+                                    element={
+                                        <AuthGuard>
+                                            <AppShell>
+                                                <SearchPage/>
+                                            </AppShell>
+                                        </AuthGuard>
+                                    }
+                                />
                                 <Route path="*" element={<Navigate to="/" replace/>}/>
                             </Routes>
                         </BrowserRouter>

client/src/api/client.ts

@@ -143,6 +143,14 @@ export async function apiRequest<T>(endpoint: string, options?: RequestInit): Pr
 
 export const api = {
     get: <T>(url: string) => apiRequest<T>(url, {method: 'GET'}),
+    head: (url: string) => fetch(url, {
+        method: 'HEAD',
+        headers: {
+            ...(localStorage.getItem('auth_token') && {
+                Authorization: `Bearer ${localStorage.getItem('auth_token')}`
+            }),
+        },
+    }),
     post: <T>(url: string, data?: unknown) =>
         apiRequest<T>(url, {
             method: 'POST',

client/src/components/files/OcrStatusBadge.tsx

@@ -0,0 +1,63 @@
+import { useHasText } from '../../hooks/useSearch';
+import { FileText, Loader2, CheckCircle } from 'lucide-react';
+
+interface OcrStatusBadgeProps {
+  fileId: number;
+}
+
+/**
+ * Badge showing OCR text availability status for a file
+ * Uses HEAD request for efficient checking (no body transfer)
+ * 
+ * Example usage:
+ * ```tsx
+ * <OcrStatusBadge fileId={file.id} />
+ * ```
+ */
+export function OcrStatusBadge({ fileId }: OcrStatusBadgeProps) {
+  const { data, isLoading, error } = useHasText(fileId);
+
+  if (isLoading) {
+    return (
+      <div className="flex items-center gap-1 text-gray-500 text-sm">
+        <Loader2 size={16} className="animate-spin" />
+        <span>Checking...</span>
+      </div>
+    );
+  }
+
+  if (error) {
+    return (
+      <div className="flex items-center gap-1 text-gray-400 text-sm">
+        <FileText size={16} />
+        <span>Unknown</span>
+      </div>
+    );
+  }
+
+  if (!data?.hasText) {
+    return (
+      <div className="flex items-center gap-1 text-gray-400 text-sm">
+        <FileText size={16} />
+        <span>No text</span>
+      </div>
+    );
+  }
+
+  return (
+    <div className="flex items-center gap-1 text-green-600 text-sm">
+      <CheckCircle size={16} />
+      <span>Text available ({formatTextLength(data.textLength)})</span>
+    </div>
+  );
+}
+
+function formatTextLength(chars: number): string {
+  if (chars === 0) return '0 chars';
+  if (chars < 1000) return `${chars} char${chars !== 1 ? 's' : ''}`;
+  if (chars < 10000) return `${(chars / 1000).toFixed(1)}K`;
+  return `${Math.round(chars / 1000)}K`;
+}
+
+
+