kg 修改

src/plugins/__init__.py

@@ -1,2 +1,2 @@
-from oneke import *
-from pdf2txt import *
+from plugins.oneke import *
+from plugins.pdf2txt import *

src/plugins/oneke.py

@@ -117,12 +117,9 @@ class OneKE:
         return outputs
 
     def processing_text_to_kg(self, text_or_path, output_path):
-        if os.path.isfile(text_or_path):
-            with open(text_or_path, 'r', encoding='utf-8') as f:
-                text = f.read()
-        else:
-            text = text_or_path
+        for chunk in read_and_process_chars(text_or_path):
 
+            text = chunk
             schema = [
                 {
                     "entity_type": "食品",
@@ -136,14 +133,25 @@ class OneKE:
                     }
                 }
             ]
-
             task = "KG"
             output = self.predict(text=text, schema=schema, task=task, language="zh")
             formatted_output = parse_and_format_output(output=output, task_type=task)
+            if os.path.exists(output_path):
+                with open(output_path, 'r', encoding='utf-8') as f:
+                    existing_data = json.load(f)
+            else:
+                existing_data = []
 
-        with open(output_path, 'a+', encoding='utf-8') as f:
-            for entry in formatted_output:
-                f.write(json.dumps(entry, ensure_ascii=False) + '\n')
+            # 将新的数据添加到现有数据之后
+            existing_data.extend(formatted_output)
+
+            # 将合并后的数据写回 JSON 文件
+            with open(output_path, 'w', encoding='utf-8') as f:
+                json.dump(existing_data, f, ensure_ascii=False, indent=4)
+
+            # with open(output_path, 'a+', encoding='utf-8') as f:
+            #     for entry in formatted_output:
+            #         f.write(json.dumps(entry, ensure_ascii=False) + '\n')
 
         print(f"预测结果已添加到 {output_path} 文件中。")
         return output_path

src/utils/__init__.py

@@ -1,6 +1,6 @@
 import fitz
 
-from logging_config import setup_logger, logger
+from utils.logging_config import setup_logger, logger
 
 def is_text_pdf(pdf_path):
     doc = fitz.open(pdf_path)