synapse-sdk 1.0.0a81__tar.gz → 1.0.0a83__tar.gz

{synapse_sdk-1.0.0a81 → synapse_sdk-1.0.0a83}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: synapse-sdk
-Version: 1.0.0a81
+Version: 1.0.0a83
 Summary: synapse sdk
 Author-email: datamaker <developer@datamaker.io>
 License: MIT

{synapse_sdk-1.0.0a81 → synapse_sdk-1.0.0a83}/synapse_sdk/plugins/categories/pre_annotation/actions/to_task.py

@@ -1,7 +1,7 @@
 import json
 from datetime import datetime
 from enum import Enum
-from typing import Annotated, Any, Dict, List, Optional
+from typing import Annotated, Any, Dict, List, Optional, Tuple
 
 import requests
 from pydantic import AfterValidator, BaseModel, field_validator
@@ -381,14 +381,29 @@ class ToTaskAction(Action):
         files = data_unit.get('files', {})
         data_file = files.get(target_specification_name)
 
+        # Extract primary file URL from task data
+        primary_file_url, primary_file_original_name = self._extract_primary_file_url(task)
+        if not primary_file_url:
+            error_msg = 'Primary image URL not found in task data'
+            self.run.log_message(f'{error_msg} for task {task_id}')
+            self.run.log_annotate_task_data({'task_id': task_id, 'error': error_msg}, AnnotateTaskDataStatus.FAILED)
+            return {'success': False, 'error': error_msg}
+
         if not data_file:
             error_msg = 'File specification not found'
             self.run.log_message(f'{error_msg} for task {task_id}')
             self.run.log_annotate_task_data({'task_id': task_id, 'error': error_msg}, AnnotateTaskDataStatus.FAILED)
             return {'success': False, 'error': error_msg}
 
-        url = data_file.get('url')
-        if not url:
+        data_file_url = data_file.get('url')
+        data_file_original_name = data_file.get('file_name_original')
+        if not data_file_original_name:
+            error_msg = 'File original name not found'
+            self.run.log_message(f'{error_msg} for task {task_id}')
+            self.run.log_annotate_task_data({'task_id': task_id, 'error': error_msg}, AnnotateTaskDataStatus.FAILED)
+            return {'success': False, 'error': error_msg}
+
+        if not data_file_url:
             error_msg = 'URL not found'
             self.run.log_message(f'{error_msg} for task {task_id}')
             self.run.log_annotate_task_data({'task_id': task_id, 'error': error_msg}, AnnotateTaskDataStatus.FAILED)
@@ -396,32 +411,29 @@ class ToTaskAction(Action):
 
         # Fetch and process the data
         try:
-            response = requests.get(url)
-            response.raise_for_status()
-            data = json.loads(response.content)
-
             # Convert data to task object
             annotation_to_task = self.entrypoint(self.run)
-            converted_data = annotation_to_task.convert_data_from_file(data)
-
-            # Submit annotation data
-            client.annotate_task_data(task_id, data={'action': 'submit', 'data': converted_data})
-
-            # Log success
-            self.run.log_annotate_task_data({'task_id': task_id, 'url': url}, AnnotateTaskDataStatus.SUCCESS)
-            return {'success': True}
-
+            converted_data = annotation_to_task.convert_data_from_file(
+                primary_file_url, primary_file_original_name, data_file_url, data_file_original_name
+            )
         except requests.RequestException as e:
             error_msg = f'Failed to fetch data from URL: {str(e)}'
             self.run.log_message(f'{error_msg} for task {task_id}')
             self.run.log_annotate_task_data({'task_id': task_id, 'error': error_msg}, AnnotateTaskDataStatus.FAILED)
             return {'success': False, 'error': error_msg}
-        except json.JSONDecodeError as e:
-            error_msg = f'Failed to parse JSON data: {str(e)}'
+        except Exception as e:
+            error_msg = f'Failed to convert data to task object: {str(e)}'
             self.run.log_message(f'{error_msg} for task {task_id}')
             self.run.log_annotate_task_data({'task_id': task_id, 'error': error_msg}, AnnotateTaskDataStatus.FAILED)
             return {'success': False, 'error': error_msg}
 
+        # Submit annotation data
+        client.annotate_task_data(task_id, data={'action': 'submit', 'data': converted_data})
+
+        # Log success
+        self.run.log_annotate_task_data({'task_id': task_id}, AnnotateTaskDataStatus.SUCCESS)
+        return {'success': True}
+
     def _process_single_task_with_inference(
         self, client: BackendClient, task_id: int, task: Dict[str, Any]
     ) -> Dict[str, Any]:
@@ -464,7 +476,7 @@ class ToTaskAction(Action):
                 return pre_processor_status
 
             # Extract primary file URL from task data
-            primary_file_url = self._extract_primary_file_url(task)
+            primary_file_url, _ = self._extract_primary_file_url(task)
             if not primary_file_url:
                 error_msg = 'Primary image URL not found in task data'
                 self.run.log_message(f'{error_msg} for task {task_id}')
@@ -606,23 +618,23 @@ class ToTaskAction(Action):
         except Exception as e:
             return {'success': False, 'error': f'Failed to restart pre-processor: {str(e)}'}
 
-    def _extract_primary_file_url(self, task: Dict[str, Any]) -> Optional[str]:
+    def _extract_primary_file_url(self, task: Dict[str, Any]) -> Tuple[str, str]:
         """Extract the primary file URL from task data.
 
         Args:
             task (Dict[str, Any]): The task data.
 
         Returns:
-            Optional[str]: The primary file URL if found, None otherwise.
+            Tuple[str, str]: The primary file URL and original name.
         """
         data_unit = task.get('data_unit', {})
         files = data_unit.get('files', {})
 
         for file_info in files.values():
             if isinstance(file_info, dict) and file_info.get('is_primary') and file_info.get('url'):
-                return file_info['url']
+                return file_info['url'], file_info['file_name_original']
 
-        return None
+        return None, None
 
     def _run_inference(
         self, client: BackendClient, pre_processor_code: str, pre_processor_version: str, primary_file_url: str

synapse_sdk-1.0.0a83/synapse_sdk/plugins/categories/pre_annotation/templates/plugin/to_task.py

@@ -0,0 +1,40 @@
+class AnnotationToTask:
+    def __init__(self, run, *args, **kwargs):
+        """Initialize the plugin task pre annotation action class.
+
+        Args:
+            run: Plugin run object.
+        """
+        self.run = run
+
+    def convert_data_from_file(
+        self,
+        primary_file_url: str,
+        primary_file_original_name: str,
+        data_file_url: str,
+        data_file_original_name: str,
+    ) -> dict:
+        """Convert the data from a file to a task object.
+
+        Args:
+            primary_file_url (str): primary file url.
+            primary_file_original_name (str): primary file original name.
+            data_file_url (str): data file url.
+            data_file_original_name (str): data file original name.
+
+        Returns:
+            dict: The converted data.
+        """
+        converted_data = {}
+        return converted_data
+
+    def convert_data_from_inference(self, data: dict) -> dict:
+        """Convert the data from inference result to a task object.
+
+        Args:
+            data: Converted data.
+
+        Returns:
+            dict: The converted data.
+        """
+        return data

{synapse_sdk-1.0.0a81 → synapse_sdk-1.0.0a83}/synapse_sdk/utils/converters/coco/to_dm.py

@@ -116,12 +116,13 @@ class COCOToDMConverter(ToDMConverter):
             result[img_filename] = (dm_json, img_path)
         return result
 
-    def convert_single_file(self, data: Dict[str, Any], original_file: IO) -> Dict[str, Any]:
+    def convert_single_file(self, data: Dict[str, Any], original_file: IO, original_image_name: str) -> Dict[str, Any]:
         """Convert a single COCO annotation data and corresponding image to DM format.
 
         Args:
             data: COCO format data dictionary (JSON content)
             original_file: File object for the corresponding original image
+            original_image_name: Original image name
 
         Returns:
             Dictionary containing DM format data for the single file
@@ -147,7 +148,7 @@ class COCOToDMConverter(ToDMConverter):
         matched_img = None
         for img in images:
             for key in ['file_name', 'filename', 'name']:
-                if key in img and os.path.basename(img[key]) == img_basename:
+                if key in img and os.path.basename(img[key]) == original_image_name:
                     matched_img = img
                     break
             if matched_img:
@@ -157,7 +158,6 @@ class COCOToDMConverter(ToDMConverter):
             raise ValueError(f'No matching image found in COCO data for file: {img_basename}')
 
         img_id = matched_img['id']
-        print('img_id : ', img_id)
         cat_map = {cat['id']: cat for cat in categories}
         anns = [ann for ann in annotations if ann['image_id'] == img_id]
 

{synapse_sdk-1.0.0a81 → synapse_sdk-1.0.0a83}/synapse_sdk/utils/converters/pascal/to_dm.py

@@ -1,6 +1,6 @@
 import os
 import xml.etree.ElementTree as ET
-from typing import Any, Dict, IO, List, Optional, Tuple
+from typing import IO, Any, Dict, List, Optional, Tuple
 
 from PIL import Image
 

{synapse_sdk-1.0.0a81 → synapse_sdk-1.0.0a83}/synapse_sdk/utils/converters/yolo/to_dm.py

@@ -11,10 +11,29 @@ class YOLOToDMConverter(ToDMConverter):
     """Convert YOLO formatted datasets to DM format."""
 
     IMG_EXTENSIONS = ['.jpg', '.jpeg', '.png', '.bmp']
-
-    def __init__(self, root_dir: str = None, is_categorized_dataset: bool = False, is_single_conversion: bool = False):
+    CLASS_NAMES = []
+
+    def __init__(
+        self,
+        root_dir: str = None,
+        is_categorized_dataset: bool = False,
+        is_single_conversion: bool = False,
+        class_names: List[str] = None,
+    ):
         super().__init__(root_dir, is_categorized_dataset, is_single_conversion)
 
+        # Set class names
+        self.CLASS_NAMES = class_names
+
+        # Get class names from dataset.yaml if not provided
+        if not class_names:
+            dataset_yaml_path = os.path.join(self.root_dir, 'dataset.yaml')
+            if not os.path.exists(dataset_yaml_path):
+                raise FileNotFoundError(f'No dataset.yaml file found in {self.root_dir}.')
+            with open(dataset_yaml_path, 'r', encoding='utf-8') as f:
+                dataset_yaml = yaml.safe_load(f)
+                self.CLASS_NAMES = dataset_yaml.get('names', [])
+
     def convert(self):
         """Convert YOLO dataset to DM format."""
         if self.is_categorized_dataset:
@@ -122,15 +141,6 @@ class YOLOToDMConverter(ToDMConverter):
         if not os.path.isdir(labels_dir):
             raise FileNotFoundError(f"No labels directory found in {split_dir} (expected 'labels').")
 
-        # Load dataset.yaml
-
-        dataset_yaml_path = os.path.join(self.root_dir, 'dataset.yaml')
-        if not os.path.exists(dataset_yaml_path):
-            raise FileNotFoundError(f'No dataset.yaml file found in {split_dir}.')
-        with open(dataset_yaml_path, 'r', encoding='utf-8') as f:
-            dataset_yaml = yaml.safe_load(f)
-            class_names = dataset_yaml.get('names', [])
-
         # Build DM data
         result = {}
         for label_filename in os.listdir(labels_dir):
@@ -156,7 +166,7 @@ class YOLOToDMConverter(ToDMConverter):
             }
 
             for line in label_lines:
-                ann = self._parse_yolo_line(line, class_names, img_size)
+                ann = self._parse_yolo_line(line, self.CLASS_NAMES, img_size)
                 if ann is None:
                     continue
 
@@ -187,13 +197,12 @@ class YOLOToDMConverter(ToDMConverter):
             result[os.path.basename(img_path)] = (dm_json, img_path)
         return result
 
-    def convert_single_file(self, data: List[str], original_file: IO, class_names: List[str]) -> Dict[str, Any]:
+    def convert_single_file(self, data: List[str], original_file: IO) -> Dict[str, Any]:
         """Convert a single YOLO label data and corresponding image to DM format.
 
         Args:
             data: List of YOLO label lines (strings from .txt file content)
             original_file: File object for the corresponding original image
-            class_names: List of class names corresponding to indices in the label data
 
         Returns:
             Dictionary containing DM format data for the single file
@@ -206,7 +215,7 @@ class YOLOToDMConverter(ToDMConverter):
             raise ValueError('original_file must have a "name" attribute representing its path or filename.')
 
         if hasattr(self, '_get_image_size'):
-            img_size = self._get_image_size(original_file)
+            img_size = self._get_image_size(img_path)
         else:
             raise AttributeError('Converter missing _get_image_size method for file objects.')
 
@@ -223,7 +232,7 @@ class YOLOToDMConverter(ToDMConverter):
         }
 
         for line in label_lines:
-            ann = self._parse_yolo_line(line, class_names, img_size)
+            ann = self._parse_yolo_line(line, self.CLASS_NAMES, img_size)
             if ann is None:
                 continue
 

{synapse_sdk-1.0.0a81 → synapse_sdk-1.0.0a83}/synapse_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: synapse-sdk
-Version: 1.0.0a81
+Version: 1.0.0a83
 Summary: synapse sdk
 Author-email: datamaker <developer@datamaker.io>
 License: MIT

synapse_sdk-1.0.0a81/synapse_sdk/plugins/categories/pre_annotation/templates/plugin/to_task.py

@@ -1,24 +0,0 @@
-class AnnotationToTask:
-    def __init__(self, run, *args, **kwargs):
-        """Initialize the plugin task pre annotation action class.
-
-        Args:
-            run: Plugin run object.
-        """
-        self.run = run
-
-    def convert_data_from_file(self, data: dict):
-        """Convert the data from a file to a task object.
-
-        Args:
-            data: Converted data.
-        """
-        return data
-
-    def convert_data_from_inference(self, data: dict):
-        """Convert the data from inference result to a task object.
-
-        Args:
-            data: Converted data.
-        """
-        return data