Update app.py

app.py

@@ -4,33 +4,33 @@ from PIL import Image
 import numpy as np
 import re
 
-# 初始化OCR模型
+# Initialize OCR model
 ocr = PaddleOCR(use_angle_cls=True, lang="en")
 
 def ocr_recognition(image):
     try:
-        # 确保使用PIL
+        # Ensure using PIL
         if isinstance(image, np.ndarray):
             image = Image.fromarray(image)
         if not isinstance(image, Image.Image):
             return "Invalid image format"
             
-        # 转换为numpy数组
+        # Convert to numpy array
         image_np = np.array(image)
         
-        # 执行OCR识别
+        # Perform OCR recognition
         result = ocr.ocr(image_np, cls=True)
         
         if not result or len(result) == 0 or result[0] is None:
             return "No text recognized"
             
-        # 提取文本
+        # Extract text
         texts = [line[1][0] for line in result[0] if line]
         
         if not texts:
             return "No text recognized"
             
-        # 解析文本以提取结构化信息
+        # Parse text to extract structured information
         structured_info = parse_text_to_structure(texts)
         return structured_info
         
@@ -38,7 +38,7 @@ def ocr_recognition(image):
         return f"Error processing image: {str(e)}"
 
 def parse_text_to_structure(texts):
-    # 初始化结构化字段
+    # Initialize structured fields
     structured_data = {
         "Event": "",
         "Location": "",
@@ -48,11 +48,11 @@ def parse_text_to_structure(texts):
         "Date": ""
     }
     
-    # 合并所有文本
+    # Merge all text
     full_text = " ".join(texts)
     
-    # 尝试使用正则表达式匹配各个字段
-    # 这些模式需要根据您的实际文档格式进行调整
+    # Try to match each field using regex
+    # These patterns should be adjusted according to your actual document format
     event_pattern = re.search(r"(?:Event|Title):\s*(.+?)(?=\s*(?:Location|Venue|Date|Start|End|Duration)|$)", full_text, re.I)
     if event_pattern:
         structured_data["Event"] = event_pattern.group(1).strip()
@@ -77,29 +77,29 @@ def parse_text_to_structure(texts):
     if duration_pattern:
         structured_data["Duration"] = duration_pattern.group(1).strip()
     
-    # 如果没有找到明确的持续时间，但有开始和结束时间，可以尝试计算
+    # If no explicit duration is found but we have start and end times, we could calculate it
     if structured_data["Duration"] == "" and structured_data["Start Time"] and structured_data["End Time"]:
-        # 这里需要更复杂的时间计算逻辑，简单起见暂时略过
+        # More complex time calculation logic would be needed here
         pass
     
-    # 格式化输出
+    # Format output
     output = "\n".join([f"{key}: {value}" for key, value in structured_data.items() if value])
     
-    # 如果没有提取到任何结构化信息，返回原始文本
+    # If no structured information was extracted, return the original text
     if not output:
-        return "未能提取结构化信息。原始文本:\n" + "\n".join(texts)
+        return "\n".join(texts)
         
     return output
 
-# 创建Gradio界面
+# Create Gradio interface
 interface = gr.Interface(
     fn=ocr_recognition,
-    inputs=gr.Image(type="pil"),  # 明确指定使用PIL
+    inputs=gr.Image(type="pil"),  # Explicitly specify using PIL
     outputs="text",
-    title="结构化OCR识别",
-    description="上传图片进行文本识别，并提取事件、地点、时间等结构化信息"
+    title="Structured OCR Recognition",
+    description="Upload an image for text recognition and extraction of structured information"
 )
 
-# 启动服务
+# Launch the service
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch()