Improve progress bar with per-step success/failure tracking, marquee animation, and tooltips

.github/workflows/js-tests.yml

@@ -0,0 +1,31 @@
+name: Run JS Tests
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - '**/*.js'
+      - '**/*.mjs'
+  pull_request:
+    branches:
+      - main
+    paths:
+      - '**/*.js'
+      - '**/*.mjs'
+
+jobs:
+  run-js-tests:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 'latest'
+
+      - name: Run JS tests
+        run: npm run test:js

docker-compose.test.yml

@@ -41,6 +41,7 @@ services:
       - ./detection_service:/tests/tests/detection_service
       - ./web_service:/tests/tests/web_service
       - ./ocr_service:/tests/tests/ocr_service
+      - ./file_naming_service:/tests/tests/file_naming_service
 
   redis:
     image: redis:latest

file_naming_service/main.py

@@ -17,7 +17,22 @@
 RABBITQUEUE = "file_naming_queue"
 
 
+def get_latest_file_naming_status(item: ProcessItem):
+    status_name = execute_query(
+        "SELECT file_naming_status FROM file_naming_jobs WHERE id = ?",
+        (item.file_naming_db_id,),
+        return_scalar=True
+    )
+    if status_name:
+        try:
+            return FileNamingStatus[status_name]
+        except KeyError:
+            logger.warning(f"Unknown file naming status '{status_name}' for item {item.filename}")
+    return item.file_naming_status
+
+
 def callback(ch, method, properties, body):
+    item = None
     try:
         item: ProcessItem = pickle.loads(body)
 
@@ -42,6 +57,7 @@ def callback(ch, method, properties, body):
 
         if not openai_enabled and not ollama_enabled:
             logger.error("Neither OpenAI nor Ollama is enabled. Please enable one of them in the settings.")
+        item.file_naming_status = FileNamingStatus.PROCESSING
         execute_query('UPDATE file_naming_jobs SET file_naming_status = ? WHERE id = ?', (FileNamingStatus.PROCESSING.name, item.file_naming_db_id))
 
         method_setting = settings.file_naming.method
@@ -65,7 +81,12 @@ def callback(ch, method, properties, body):
         execute_query("UPDATE file_naming_jobs SET file_naming_status = ?, error_description = ?, finished = DATETIME('now', 'localtime') WHERE id = ?", (FileNamingStatus.FAILED.name, "OCR file does not exist", item.file_naming_db_id))
     except TypeError as e:
         logger.error(f"Received object is not a ProcessItem: {e}. Skipping.")
-        execute_query("UPDATE file_naming_jobs SET file_naming_status = ?, error_description = ?, finished = DATETIME('now', 'localtime') WHERE id = ?", (FileNamingStatus.FAILED.name, str(e), item.file_naming_db_id))
+        item_file_naming_db_id = getattr(item, "file_naming_db_id", None)
+        if item_file_naming_db_id:
+            execute_query(
+                "UPDATE file_naming_jobs SET file_naming_status = ?, error_description = ?, finished = DATETIME('now', 'localtime') WHERE id = ?",
+                (FileNamingStatus.FAILED.name, str(e), item_file_naming_db_id)
+            )
         return
     except Exception as e:
         logger.exception(f"Failed processing {item.filename}.")
@@ -77,7 +98,10 @@ def callback(ch, method, properties, body):
             logger.error("Connection lost while acknowledging message. Reconnecting...")
             connection, channel = connect_rabbitmq([RABBITQUEUE], heartbeat=120)
             channel.basic_ack(delivery_tag=method.delivery_tag)
-        if item:
+        if isinstance(item, ProcessItem):
+            item_file_naming_db_id = getattr(item, "file_naming_db_id", None)
+            if item_file_naming_db_id:
+                item.file_naming_status = get_latest_file_naming_status(item)
             item.status = ProcessStatus.SYNC_PENDING
             update_scanneddata_database(item, {"file_status": item.status.value})
             forward_to_rabbitmq("upload_queue", item)
@@ -101,5 +125,6 @@ def start_consuming_with_reconnect():
             time.sleep(5)
 
 
-# Start the consumer with reconnect logic
-start_consuming_with_reconnect()
+if __name__ == "__main__":
+    # Start the consumer with reconnect logic
+    start_consuming_with_reconnect()

ocr_service/main.py

@@ -1,6 +1,6 @@
 from scansynclib.logging import logger
 from scansynclib.ProcessItem import ProcessItem, ProcessStatus, OCRStatus
-from scansynclib.sqlite_wrapper import update_scanneddata_database
+from scansynclib.sqlite_wrapper import execute_query, update_scanneddata_database
 from scansynclib.helpers import connect_rabbitmq, forward_to_rabbitmq, extract_text
 import pickle
 import ocrmypdf
@@ -30,53 +30,77 @@ def callback(ch, method, properties, body):
 
 def start_processing(item: ProcessItem):
     item.status = ProcessStatus.OCR
+    item.ocr_status = OCRStatus.PROCESSING
+    item.ocr_db_id = execute_query(
+        'INSERT INTO ocr_jobs (scanneddata_id, ocr_status) VALUES (?, ?)',
+        (item.db_id, OCRStatus.PROCESSING.name),
+        return_last_id=True
+    )
     update_scanneddata_database(item, {"file_status": item.status.value})
     item.time_ocr_started = datetime.now()
 
     logger.info(f"Processing file with OCR: {item.filename}")
+    ocr_error = None
+    result = None
 
     try:
         result = ocrmypdf.ocr(item.local_file_path, item.ocr_file, output_type='pdfa', skip_text=True, rotate_pages=True, jpg_quality=80, png_quality=80, optimize=2, language=["eng", "deu"], tesseract_timeout=120)
         logger.debug(f"OCR exited with code {result}")
-        
+
         if result != 0:
             logger.error(f"OCR exited with code {result}")
             item.ocr_status = OCRStatus.FAILED
+            ocr_error = f"OCR exited with code {result}"
         else:
             logger.info(f"OCR processing completed: {item.filename}")
-            
+
             # Verify that the OCR file actually contains text
             if os.path.exists(item.ocr_file):
-                extracted_text = (extract_text(item.ocr_file, max_pages=2, max_chars=2048) or "").strip()
+                extracted_text = (extract_text(item.ocr_file, max_pages=5, max_chars=2048) or "").strip()
                 if extracted_text:
                     logger.info(f"OCR verification successful: extracted {len(extracted_text)} characters from {item.filename}")
                     item.ocr_status = OCRStatus.COMPLETED
                 else:
                     logger.warning(f"OCR verification failed: no text found in OCR output file {item.ocr_file}")
-                    item.ocr_status = OCRStatus.FAILED
+                    item.ocr_status = OCRStatus.NO_TEXT
             else:
                 logger.error(f"OCR output file not found: {item.ocr_file}")
                 item.ocr_status = OCRStatus.OUTPUT_ERROR
     except ocrmypdf.UnsupportedImageFormatError:
         logger.error(f"Unsupported image format: {item.local_file_path}")
         item.ocr_status = OCRStatus.UNSUPPORTED
+        ocr_error = "Unsupported image format"
     except ocrmypdf.DpiError as dpiex:
         logger.error(f"DPI error: {item.local_file_path} {dpiex}")
         item.ocr_status = OCRStatus.DPI_ERROR
+        ocr_error = str(dpiex)
     except ocrmypdf.InputFileError as inex:
         logger.error(f"Input error: {item.local_file_path} {inex}")
         item.ocr_status = OCRStatus.INPUT_ERROR
+        ocr_error = str(inex)
     except ocrmypdf.OutputFileAccessError as outex:
         logger.error(f"Output error: {item.local_file_path} {outex}")
         item.ocr_status = OCRStatus.OUTPUT_ERROR
+        ocr_error = str(outex)
     except ocrmypdf.MissingDependencyError:
         logger.exception("Cannot process with OCR due to missing dependencies.")
         item.ocr_status = OCRStatus.FAILED
+        ocr_error = "Missing OCR dependency"
     except Exception as ex:
         logger.exception(f"Failed processing {item.local_file_path} with OCR: {ex}")
         item.ocr_status = OCRStatus.FAILED
+        ocr_error = str(ex)
     finally:
         item.time_ocr_finished = datetime.now()
+        if result is not None and result != 0:
+            item.ocr_status = OCRStatus.FAILED
+            if not ocr_error:
+                ocr_error = f"OCR exited with code {result}"
+        if item.ocr_db_id:
+            execute_query(
+                "UPDATE ocr_jobs SET ocr_status = ?, ocr_error = ?, finished = DATETIME('now', 'localtime') WHERE id = ?",
+                (item.ocr_status.name, ocr_error, item.ocr_db_id)
+            )
         item.status = ProcessStatus.SYNC_PENDING
 
         try:

package.json

@@ -8,7 +8,8 @@
     "test": "tests"
   },
   "scripts": {
-    "test": "echo \"Error: no test specified\" && exit 1"
+    "test": "echo \"Error: no test specified\" && exit 1",
+    "test:js": "node --test \"tests/js/**/*.test.mjs\""
   },
   "repository": {
     "type": "git",

run-tests.sh

@@ -5,6 +5,9 @@ set -e
 COMPOSE_FILE="docker-compose.test.yml"
 TEST_SERVICE_NAME="test_service"
 
+echo "🧪 Running JS tests..."
+npm run test:js
+
 echo "🧪 Starting tests with Docker Compose..."
 
 docker compose -f $COMPOSE_FILE up --build --abort-on-container-exit --exit-code-from $TEST_SERVICE_NAME

scansynclib/scansynclib/ProcessItem.py

@@ -69,6 +69,7 @@ class OCRStatus(Enum):
     DPI_ERROR: Image DPI is too low for accurate OCR.
     INPUT_ERROR: Error reading input image/PDF.
     OUTPUT_ERROR: Error writing OCR output file.
+    NO_TEXT: OCR completed but the output file contained no extractable text.
     """
     UNKNOWN = 0
     PENDING = 1
@@ -80,6 +81,7 @@ class OCRStatus(Enum):
     DPI_ERROR = -4
     INPUT_ERROR = -5
     OUTPUT_ERROR = -6
+    NO_TEXT = -7
 
 
 class FileNamingStatus(Enum):