Update app.py

app.py

@@ -1,83 +1,62 @@
 import gradio as gr
 import pandas as pd
 import re
-import json
 
-# 提取 JSON 格式中的文本部分
-def extract_text_from_json(text):
-    try:
-        data = json.loads(text)
-        if isinstance(data, dict):
-            if 'question' in data:
-                return data['question']['content']
-            if 'content' in data:
-                return data['content']
-    except json.JSONDecodeError:
-        return text
-    return text
-
-# 檢查 $ 符號前後是否有空格
+# 第一個檢查：檢查$符號前後是否有空格
 def check_spacing_around_dollar(df):
     errors = []
     for i, row in df.iterrows():
         for col in df.columns:
-            text = extract_text_from_json(str(row[col]))
-            matches = re.finditer(r'\$\S+|\S+\$', text)
+            text = str(row[col])
+            matches = list(re.finditer(r'(\s?\$\S*?\s?|\s?\S*?\$)', text))
             for match in matches:
-                if (match.start() > 0 and text[match.start() - 1] != ' ') or (match.end() < len(text) and text[match.end()] != ' '):
+                if not (text[match.start() - 1] == ' ' and text[match.end()] == ' '):
                     errors.append(f"行 {i+1} 列 '{col}': '{text}'")
     return errors
 
-# 檢查 $ 符號之間是否有空格
+# 第二個檢查：檢查$符號之間是否有空格
 def check_spacing_between_dollars(df):
     errors = []
     for i, row in df.iterrows():
         for col in df.columns:
-            text = extract_text_from_json(str(row[col]))
-            matches = re.finditer(r'\$\S+?(?=\$)', text)
+            text = str(row[col])
+            matches = list(re.finditer(r'\$\S+?(?=\$)', text))
             for match in matches:
                 if text[match.end()] != ' ' and text[match.start() - 1] != ' ':
                     errors.append(f"行 {i+1} 列 '{col}': '{text}'")
     return errors
 
-# 檢查數字前後是否有 $ 符號
+# 第三個檢查：檢查數字前後是否有$
 def check_numbers_surrounded_by_dollar(df):
     errors = []
     for i, row in df.iterrows():
         for col in df.columns:
-            text = extract_text_from_json(str(row[col]))
-            matches = re.finditer(r'\b\d+\b', text)
+            text = str(row[col])
+            matches = list(re.finditer(r'\b\d+\b', text))
             for match in matches:
-                if not (match.start() > 0 and text[match.start() - 1] == '$' and match.end() < len(text) and text[match.end()] == '$'):
+                if not (text[match.start() - 1] == '$' and text[match.end()] == '$'):
                     errors.append(f"行 {i+1} 列 '{col}': '{text}'")
     return errors
 
 # 處理檔案並執行檢查
 def process_file(file):
-    try:
-        if file.name.endswith('.csv'):
-            df = pd.read_csv(file.name)
-        elif file.name.endswith('.xlsx'):
-            df = pd.read_excel(file.name)
-        else:
-            return "只支持 CSV 和 XLSX 檔案"
-
-        # 打印 DataFrame 以檢查內容
-        print("讀取的 DataFrame：")
-        print(df.head())
-        
-        # 執行檢查
-        errors1 = check_spacing_around_dollar(df)
-        errors2 = check_spacing_between_dollars(df)
-        errors3 = check_numbers_surrounded_by_dollar(df)
-        
-        return {
-            "第一個檢查": errors1,
-            "第二個檢查": errors2,
-            "第三個檢查": errors3
-        }
-    except Exception as e:
-        return str(e)
+    if file.name.endswith('.csv'):
+        df = pd.read_csv(file.name)
+    elif file.name.endswith('.xlsx'):
+        df = pd.read_excel(file.name)
+    else:
+        return "只支持 CSV 和 XLSX 檔案"
+    
+    # 執行檢查
+    errors1 = check_spacing_around_dollar(df)
+    errors2 = check_spacing_between_dollars(df)
+    errors3 = check_numbers_surrounded_by_dollar(df)
+    
+    return {
+        "第一個檢查": errors1,
+        "第二個檢查": errors2,
+        "第三個檢查": errors3
+    }
 
 # Gradio 介面
 iface = gr.Interface(