Merged in feature/download-pdf (pull request #216)

retrieve document by id and tests

* working

* missing files

scripts/manual_tests/test_zip_upload.sh

@@ -27,6 +27,8 @@
 # - GET /client/{CLIENT_ID}/document/batch                - List all batches for client with pagination
 # - POST /client/{CLIENT_ID}/document/batch (invalid)     - Test error handling with non-ZIP file
 # - DELETE /client/{CLIENT_ID}/document/batch/{BATCH_ID}  - Cancel/delete batch processing
+# - GET /document/{DOCUMENT_ID}/download                  - Download a processed document
+# - GET /document/{FAKE_ID}/download                      - Verify 404 for non-existent document
 
 set -e  # Exit on any error
 
@@ -257,6 +259,124 @@ test_invalid_file() {
     fi
 }
 
+# Wait for at least one document in the batch to have a document_id assigned.
+# Polls the batch status endpoint until a document_id appears or timeout is reached.
+wait_for_document_id() {
+    log_info "Waiting for documents to be processed (up to 60s)..."
+
+    local max_wait=60
+    local elapsed=0
+    local interval=3
+
+    while [ $elapsed -lt $max_wait ]; do
+        response=$(curl -s "$BASE_URL/client/$CLIENT_ID/document/batch/$BATCH_ID" 2>/dev/null)
+
+        # Extract first non-null document_id from document_outcomes array
+        DOCUMENT_ID=$(echo "$response" | python3 -c "
+import sys, json
+data = json.load(sys.stdin)
+for outcome in data.get('document_outcomes', []):
+    doc_id = outcome.get('document_id')
+    if doc_id:
+        print(doc_id)
+        sys.exit(0)
+sys.exit(1)
+" 2>/dev/null)
+
+        if [ $? -eq 0 ] && [ -n "$DOCUMENT_ID" ]; then
+            log_info "Document ready for download: $DOCUMENT_ID"
+            return 0
+        fi
+
+        sleep $interval
+        elapsed=$((elapsed + interval))
+        log_info "Still waiting... ($elapsed/${max_wait}s)"
+    done
+
+    log_error "Timed out waiting for documents to be processed"
+    return 1
+}
+
+# Test downloading a document via GET /document/{id}/download.
+# Verifies HTTP 200, Content-Disposition header, Content-Type, non-empty body, and PDF magic bytes.
+test_document_download() {
+    log_info "Testing document download: GET /document/$DOCUMENT_ID/download"
+
+    local output_file="downloaded_document.pdf"
+
+    # Download with headers captured
+    curl -s -D headers.txt -o "$output_file" \
+        "$BASE_URL/document/$DOCUMENT_ID/download" 2>/dev/null
+
+    http_code=$(grep -m1 "^HTTP/" headers.txt | awk '{print $2}')
+
+    if [ "$http_code" != "200" ]; then
+        log_error "Download failed (HTTP $http_code)"
+        cat headers.txt 2>/dev/null
+        rm -f "$output_file" headers.txt
+        return 1
+    fi
+
+    log_info "Download returned HTTP 200"
+
+    # Verify Content-Disposition header is present
+    if grep -qi "Content-Disposition" headers.txt; then
+        disposition=$(grep -i "Content-Disposition" headers.txt | tr -d '\r')
+        log_info "$disposition"
+    else
+        log_error "Missing Content-Disposition header"
+        rm -f "$output_file" headers.txt
+        return 1
+    fi
+
+    # Log Content-Type
+    content_type=$(grep -i "Content-Type" headers.txt | head -1 | tr -d '\r')
+    log_info "$content_type"
+
+    # Verify file is non-empty
+    file_size=$(stat -f%z "$output_file" 2>/dev/null || stat -c%s "$output_file" 2>/dev/null || echo "0")
+    if [ "$file_size" -eq 0 ]; then
+        log_error "Downloaded file is empty"
+        rm -f "$output_file" headers.txt
+        return 1
+    fi
+    log_info "Downloaded file size: $file_size bytes"
+
+    # Verify file starts with PDF magic bytes (%PDF)
+    file_header=$(head -c 4 "$output_file")
+    if [ "$file_header" = "%PDF" ]; then
+        log_info "File is a valid PDF (starts with %%PDF header)"
+    else
+        log_warn "File does not start with %%PDF header (got: $file_header)"
+    fi
+
+    # Cleanup
+    rm -f "$output_file" headers.txt
+
+    log_info "Document download test PASSED"
+    return 0
+}
+
+# Test that downloading a non-existent document returns 404.
+test_download_not_found() {
+    log_info "Testing download of non-existent document (should return 404)..."
+
+    local fake_id="00000000-0000-0000-0000-000000000000"
+
+    response=$(curl -s -w "\n%{http_code}" \
+        "$BASE_URL/document/$fake_id/download" 2>/dev/null)
+
+    http_code=$(echo "$response" | tail -n1)
+
+    if [ "$http_code" = "404" ]; then
+        log_info "Non-existent document correctly returned 404"
+        return 0
+    else
+        log_warn "Expected HTTP 404 for non-existent document, got HTTP $http_code"
+        return 1
+    fi
+}
+
 # Cancel batch
 cancel_batch() {
     log_info "Canceling batch..."
@@ -280,7 +400,7 @@ cancel_batch() {
 # Cleanup function
 cleanup() {
     log_info "Cleaning up..."
-    rm -f "$ZIP_FILE" invalid.txt
+    rm -f "$ZIP_FILE" invalid.txt downloaded_document.pdf headers.txt
     rm -rf temp_zip_structure
     log_info "Cleanup complete"
 }
@@ -303,6 +423,15 @@ main() {
         sleep 1  # Brief pause to let the system process
         get_batch_status
         list_batches
+
+        # Document download tests -- must run before cancel_batch
+        if wait_for_document_id; then
+            test_document_download
+            test_download_not_found
+        else
+            log_warn "Skipping download tests - no documents were processed in time"
+        fi
+
         test_invalid_file
         cancel_batch