Merged in feature/preserve-folder-paths (pull request #179)

support folder paths

* support folder paths

* s3 storage docs

scripts/manual_tests/test_zip_upload.sh

@@ -65,9 +65,9 @@ check_service() {
     log_info "Service is running"
 }
 
-# Create test ZIP file with real PDFs from test.pdf.batch directory
+# Create test ZIP file with real PDFs from test.pdf.batch directory, each in its own subfolder
 create_test_zip() {
-    log_info "Creating test ZIP file with real PDFs from ./test.pdf.batch..."
+    log_info "Creating test ZIP file with real PDFs from ./test.pdf.batch, each in its own subfolder..."
 
     # Remove existing file if it exists
     rm -f "$ZIP_FILE"
@@ -86,14 +86,34 @@ create_test_zip() {
         exit 1
     fi
 
-    # Create ZIP file with all PDFs from the batch directory
+    # Create temporary directory structure
+    temp_dir="temp_zip_structure"
+    rm -rf "$temp_dir"
+    mkdir -p "$temp_dir"
+
+    # Copy each PDF to its own subfolder
+    folder_num=1
+    for pdf_file in "$pdf_dir"/*.pdf; do
+        if [ -f "$pdf_file" ]; then
+            folder_name="folder$folder_num"
+            mkdir -p "$temp_dir/$folder_name"
+            cp "$pdf_file" "$temp_dir/$folder_name/"
+            log_info "Placed $(basename "$pdf_file") in $folder_name/"
+            folder_num=$((folder_num + 1))
+        fi
+    done
+
+    # Create ZIP file with the folder structure
     current_dir=$(pwd)
-    cd "$pdf_dir"
-    zip -q "$current_dir/$ZIP_FILE" *.pdf
+    cd "$temp_dir"
+    zip -q -r "$current_dir/$ZIP_FILE" .
     cd "$current_dir"
 
+    # Cleanup temporary directory
+    rm -rf "$temp_dir"
+
     file_size=$(stat -f%z "$ZIP_FILE" 2>/dev/null || stat -c%s "$ZIP_FILE" 2>/dev/null || echo "unknown")
-    log_info "Created $ZIP_FILE with $pdf_count real PDFs ($file_size bytes)"
+    log_info "Created $ZIP_FILE with $pdf_count real PDFs in separate subfolders ($file_size bytes)"
 }
 
 # Create client (idempotent)
@@ -261,6 +281,7 @@ cancel_batch() {
 cleanup() {
     log_info "Cleaning up..."
     rm -f "$ZIP_FILE" invalid.txt
+    rm -rf temp_zip_structure
     log_info "Cleanup complete"
 }
 

scripts/manual_tests/upload_single_document.sh

@@ -30,14 +30,38 @@ fi
 
 echo -e "${GREEN}API is running${NC}"
 
-# Verify client exists by trying to get its details
+# Function to create client
+create_client() {
+    echo "Creating client with ID '$CLIENT_ID'..."
+    CREATE_RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "$API_URL/client" \
+        -H "Content-Type: application/json" \
+        -d "{\"id\":\"$CLIENT_ID\",\"name\":\"Test Client $CLIENT_ID\"}")
+    
+    CREATE_HTTP_CODE=$(echo "$CREATE_RESPONSE" | tail -n1)
+    CREATE_RESPONSE_BODY=$(echo "$CREATE_RESPONSE" | sed '$d')
+    
+    if [ "$CREATE_HTTP_CODE" = "201" ] || [ "$CREATE_HTTP_CODE" = "200" ]; then
+        echo -e "${GREEN}Client '$CLIENT_ID' created successfully${NC}"
+        return 0
+    elif [ "$CREATE_HTTP_CODE" = "409" ] || [ "$CREATE_HTTP_CODE" = "400" ]; then
+        echo -e "${GREEN}Client '$CLIENT_ID' already exists${NC}"
+        return 0
+    else
+        echo -e "${RED}Error: Failed to create client (HTTP $CREATE_HTTP_CODE)${NC}"
+        echo "Response: $CREATE_RESPONSE_BODY"
+        return 1
+    fi
+}
+
+# Verify client exists or create it
 echo "Verifying client with ID '$CLIENT_ID' exists..."
 CLIENT_CHECK=$(curl -s -o /dev/null -w "%{http_code}" "$API_URL/client/$CLIENT_ID")
 
 if [ "$CLIENT_CHECK" != "200" ]; then
-    echo -e "${RED}Error: Client with ID '$CLIENT_ID' not found${NC}"
-    echo "Please ensure the client exists in the database"
-    exit 1
+    echo "Client '$CLIENT_ID' not found, attempting to create it..."
+    if ! create_client; then
+        exit 1
+    fi
 else
     echo -e "${GREEN}Client '$CLIENT_ID' verified${NC}"
 fi