sparrow-parse 0.4.0__py3-none-any.whl → 0.4.2__py3-none-any.whl

sparrow_parse/__init__.py

@@ -1 +1 @@
-__version__ = '0.4.0'
+__version__ = '0.4.2'

sparrow_parse/extractors/vllm_extractor.py

@@ -54,7 +54,7 @@ class VLLMExtractor(object):
         """
         file_path = input_data[0]["file_path"]
         if tables_only:
-            return [self._extract_tables(model_inference_instance, file_path, input_data, debug, debug_dir)], 1
+            return self._extract_tables(model_inference_instance, file_path, input_data, debug, debug_dir), 1
         else:
             input_data[0]["file_path"] = [file_path]
             results = model_inference_instance.inference(input_data)
@@ -85,7 +85,8 @@ class VLLMExtractor(object):
                 tables_result = self._extract_tables(
                     model_inference_instance, file_path, input_data, debug, debug_dir, page_index=i
                 )
-                results_array.append(tables_result)
+                # Since _extract_tables returns a list with one JSON string, unpack it
+                results_array.extend(tables_result)  # Unpack the single JSON string
         else:
             if debug:
                 print(f"Processing {len(output_files)} pages for inference at once.")
@@ -115,11 +116,18 @@ class VLLMExtractor(object):
 
             input_data[0]["file_path"] = [output_filename]
             result = self._run_model_inference(model_inference_instance, input_data)
-            result = self.add_table_info_to_data(result, "table_nr", i + 1)
             results_array.append(result)
 
         shutil.rmtree(temp_dir, ignore_errors=True)
-        return json.dumps(results_array, indent=4)
+
+        # Merge results_array elements into a single JSON structure
+        merged_results = {"page_tables": results_array}
+
+        # Format the merged results as a JSON string with indentation
+        formatted_results = json.dumps(merged_results, indent=4)
+
+        # Return the formatted JSON string wrapped in a list
+        return [formatted_results]
 
 
     @staticmethod
@@ -140,35 +148,6 @@ class VLLMExtractor(object):
         return file_path.lower().endswith('.pdf')
 
 
-    @staticmethod
-    def add_table_info_to_data(data: Union[Dict, List], key: str, message: Any) -> Dict:
-        """
-        Add a key-value pair to a dictionary or wrap a list in a dictionary.
-        If a 'table' key exists, add or update the key-value pair inside it.
-
-        Args:
-            data (Union[Dict, List]): The input data (either a dictionary or list).
-            key (str): The key to add.
-            message (Any): The value to associate with the key.
-
-        Returns:
-            Dict: The modified data.
-        """
-        if isinstance(data, dict):
-            if "table" in data and isinstance(data["table"], list):
-                # Add or update the key-value pair in the existing structure
-                data[key] = message
-            else:
-                # Wrap the dictionary inside a `table` key and include the additional key-value pair
-                data = {"table": [data], key: message}
-        elif isinstance(data, list):
-            # Wrap the list in a dictionary with the additional key-value pair
-            data = {"table": data, key: message}
-        else:
-            raise TypeError("Data must be a dictionary or a list.")
-        return data
-
-
 if __name__ == "__main__":
     # run locally: python -m sparrow_parse.extractors.vllm_extractor
 
@@ -196,7 +175,7 @@ if __name__ == "__main__":
     # ]
     #
     # # Now you can run inference without knowing which implementation is used
-    # results_array, num_pages = extractor.run_inference(model_inference_instance, input_data, tables_only=False,
+    # results_array, num_pages = extractor.run_inference(model_inference_instance, input_data, tables_only=True,
     #                                                    generic_query=False,
     #                                                    debug_dir="/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/",
     #                                                    debug=True,

{sparrow_parse-0.4.0.dist-info → sparrow_parse-0.4.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.4.0
+Version: 0.4.2
 Summary: Sparrow Parse is a Python package (part of Sparrow) for parsing and extracting information from documents.
 Home-page: https://github.com/katanaml/sparrow/tree/main/sparrow-data/parse
 Author: Andrej Baranovskij

{sparrow_parse-0.4.0.dist-info → sparrow_parse-0.4.2.dist-info}/RECORD

@@ -1,7 +1,7 @@
-sparrow_parse/__init__.py,sha256=DObMj8zITWgJRRICOQXNFEgLDtZ9uQZUVwbNAU-P3oc,21
+sparrow_parse/__init__.py,sha256=ZQn_AcWYegaUtOl4-txMtrEFR2pE4wBpoPlmrITggnY,21
 sparrow_parse/__main__.py,sha256=Xs1bpJV0n08KWOoQE34FBYn6EBXZA9HIYJKrE4ZdG78,153
 sparrow_parse/extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sparrow_parse/extractors/vllm_extractor.py,sha256=SCqxdr8V_cm0COfs0TelTcBXapVcz2WffhESJ1fry0g,8716
+sparrow_parse/extractors/vllm_extractor.py,sha256=ybWpRpDH0YHoYpHkjIJtm7DQoHJBKNsirK2YIAlMvGo,7863
 sparrow_parse/helpers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sparrow_parse/helpers/pdf_optimizer.py,sha256=GIqQYWtixFeZGCRFXL0lQfQByapCDuQzzRHAkzcPwLE,3302
 sparrow_parse/processors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -12,8 +12,8 @@ sparrow_parse/vllm/inference_base.py,sha256=4mwGoAY63MB4cHZpV0czTkJWEzimmiTzqqzK
 sparrow_parse/vllm/inference_factory.py,sha256=FTM65O-dW2WZchHOrNN7_Q3-FlVoAc65iSptuuUuClM,1166
 sparrow_parse/vllm/local_gpu_inference.py,sha256=aHoJTejb5xrXjWDIGu5RBQWEyRCOBCB04sMvO2Wyvg8,628
 sparrow_parse/vllm/mlx_inference.py,sha256=xR40qwjIR0HvrN8x58oOq6F4r1hEANRB-9kcokUQHHU,4748
-sparrow_parse-0.4.0.dist-info/METADATA,sha256=IQqfUUKnpA0ystjBmrrpSWw4b1hDYnLO4sqKdoNYEHk,6432
-sparrow_parse-0.4.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-sparrow_parse-0.4.0.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
-sparrow_parse-0.4.0.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
-sparrow_parse-0.4.0.dist-info/RECORD,,
+sparrow_parse-0.4.2.dist-info/METADATA,sha256=JTSkKdB2X5o3tXovyjnLSEANrPnkvJLtTfeYH7PZRDw,6432
+sparrow_parse-0.4.2.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+sparrow_parse-0.4.2.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
+sparrow_parse-0.4.2.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
+sparrow_parse-0.4.2.dist-info/RECORD,,