quick

app.py

@@ -0,0 +1,76 @@
+# app.py
+import gradio as gr
+# Removed imports: pandas, openpyxl, datetime, timedelta, os, tempfile
+
+# Import the processing function from main.py
+from main import process_files
+
+def generate_report(file1_obj, file2_obj):
+    """
+    Gradio wrapper function to handle file uploads and call the main processing logic.
+
+    Args:
+        file1_obj: Gradio File object for the first input file.
+        file2_obj: Gradio File object for the second input file.
+
+    Returns:
+        str: Path to the generated output Excel file if successful.
+    Raises:
+        gr.Error: If file processing fails.
+    """
+    if file1_obj is None or file2_obj is None:
+        raise gr.Error("Please upload both required files.")
+
+    try:
+        # Gradio provides temporary paths for uploaded files
+        file1_path = file1_obj.name
+        file2_path = file2_obj.name
+
+        # Define the output filename (can be customized if needed)
+        output_filename = "generated_report.xlsx"
+
+        # Call the core processing logic from main.py
+        print(f"Processing files: {file1_path}, {file2_path}") # Log input paths
+        result_path = process_files(file1_path, file2_path, output_filename)
+        print(f"process_files returned: {result_path}") # Log result path
+
+        if result_path:
+            # Return the path of the generated file for Gradio to serve
+            return result_path
+        else:
+            # If process_files returned None, it means an error occurred
+            raise gr.Error("Failed to generate the report. Check logs or input files.")
+
+    except Exception as e:
+        # Catch any other unexpected errors during the wrapper execution
+        import traceback
+        print(f"Error in Gradio wrapper (generate_report): {e}")
+        print(traceback.format_exc())
+        raise gr.Error(f"An unexpected error occurred: {e}")
+
+
+# Create Gradio Interface
+inputs = [
+    gr.File(label="上传数据源文件 (类似 1.xls)"),
+    gr.File(label="上传模板文件 (类似 2.xlsx)")
+]
+outputs = gr.File(label="下载生成的报告")
+
+title = "Quality Inspection Report Generator" # Use English title
+description = "Upload the data source file and template file to generate the combined quality inspection report." # Use English description
+
+# Ensure interface runs on the default port 7860
+# share=False is default and recommended for custom deployments
+# server_name="0.0.0.0" makes it accessible within the container/network
+demo = gr.Interface(
+    fn=generate_report,
+    inputs=inputs,
+    outputs=outputs,
+    title=title,
+    description=description,
+    allow_flagging='never' # Disable flagging
+)
+
+if __name__ == "__main__":
+    # Launch the Gradio app
+    demo.launch(server_name="0.0.0.0") # Port defaults to 7860 

main.py

@@ -1,113 +1,183 @@
 import pandas as pd
 from openpyxl import load_workbook
 from datetime import datetime, timedelta
+import os # Added for path manipulation
 
-# 读取第一个文件
-file1 = '1.xls'
-header_df = pd.read_excel(file1, sheet_name='HEADER')
-
-# 读取Dimension表，跳过前12行，然后使用第13行作为列名
-dimension_df = pd.read_excel(file1, sheet_name='Dimension', skiprows=12)
-# 使用第一行作为列名
-dimension_df.columns = dimension_df.iloc[0]
-# 删除第一行（现在已经作为列名）并重置索引
-dimension_df = dimension_df.iloc[1:].reset_index(drop=True)
-
-# 读取Sand表的数据
-sand_df = pd.read_excel(file1, sheet_name='Sand', header=None)
-
-# 读取第二个文件
-file2 = '2.xlsx'
-wb = load_workbook(file2)
-wacker_sheet = wb['WACKER']
-
-# 获取Sales Order Quantity和Quality Assured By
-sales_order_quantity = header_df.iloc[5, 2]  # Sales Order Quantity位置
-quality_assured_by = header_df.iloc[3, 7]    # Quality Assured By在第4行最后一列
-
-# 定义元素和行号的对应关系
-element_row_mapping = {
-    'Al': 9,   # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_Al
-    'Ca': 10,  # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_Ca
-    'Cu': 11,  # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_Cu
-    'Fe': 12,  # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_Fe
-    'K': 13,   # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_K
-    'Li': 14,  # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_Li
-    'Mg': 15,  # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_Mg
-    'Mn': 16,  # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_Mn
-    'Na': 17,  # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_Na
-    'Ti': 18,  # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_Ti
-    'Zr': 19   # 硅柏_石英坩埚_QC530HS_201410_V3B-CN_Zr
-}
-
-# 定义元素在Sand表中的列索引
-element_col_mapping = {
-    'Al': 4,   # 第5列
-    'Ca': 5,   # 第6列
-    'Cu': 6,   # 第7列
-    'Fe': 7,   # 第8列
-    'K': 8,    # 第9列
-    'Li': 9,   # 第10列
-    'Mg': 10,  # 第11列
-    'Mn': 11,  # 第12列
-    'Na': 12,  # 第13列
-    'Ti': 13,  # 第14列
-    'Zr': 14   # 第15列
-}
-
-# 遍历Dimension表格中的每个Customer ID
-for index, row in dimension_df.iterrows():
-    customer_id = row['Customer ID']  # 现在这个列名应该是正确的了
-    inspection_date = pd.to_datetime(row['Inspection Date']).strftime('%Y-%m-%d')  # 格式化日期
-    
-    # 创建新的工作表
-    new_sheet = wb.create_sheet(title=str(customer_id))
-    
-    # 复制WACKER表格的内容到新工作表（这样会保持原有的客户名称）
-    for row_wacker in wacker_sheet.iter_rows(values_only=True):
-        new_sheet.append(row_wacker)
-    
-    # 填充数据（不再覆盖客户名称）
-    new_sheet['B3'] = str(sales_order_quantity) + ' PCS'  # Number+Unit/数量+单位
-    new_sheet['B4'] = customer_id  # Batch reference/批号
-    new_sheet['D4'] = inspection_date  # Date of issue/报告日期
-    new_sheet['B5'] = inspection_date  # Production date/生产日期
-    new_sheet['D5'] = (datetime.strptime(inspection_date, '%Y-%m-%d') + timedelta(days=730)).strftime('%Y-%m-%d')  # Expiring date/失效日期
-    
-    # 从sand表中获取当前customer_id的数据
-    sand_rows = sand_df[sand_df[2] == customer_id]  # 使用第3列（索引2）作为Crucible ID
-    if not sand_rows.empty:
-        sand_row = sand_rows.iloc[0]
+def process_files(file1_path, file2_path, output_filename="generated_report.xlsx"):
+    """
+    Processes two input Excel files and generates a combined report.
+
+    Args:
+        file1_path (str): Path to the first input Excel file (data source).
+        file2_path (str): Path to the second input Excel file (template).
+        output_filename (str): Desired name for the output report file.
+
+    Returns:
+        str: The path to the generated output Excel file.
+        Returns None if an error occurs during processing.
+    """
+    try:
+        # 读取第一个文件
+        header_df = pd.read_excel(file1_path, sheet_name='HEADER')
+        dimension_df = pd.read_excel(file1_path, sheet_name='Dimension', skiprows=12)
+        dimension_df.columns = dimension_df.iloc[0]
+        dimension_df = dimension_df.iloc[1:].reset_index(drop=True)
+        sand_df = pd.read_excel(file1_path, sheet_name='Sand', header=None)
+
+        # 读取第二个文件
+        wb = load_workbook(file2_path)
         
-        # 填充元素数据
-        for element, target_row in element_row_mapping.items():
-            source_col = element_col_mapping[element]
-            new_sheet[f'D{target_row}'] = sand_row[source_col]
-    
-    # 填充Analysis result/分析结果
-    # 保持原有的测试项目名称，只更新分析结果列
-    for i in range(20, 29):
-        if i == 20:
-            new_sheet[f'D{i}'] = row['OD1']  # 外径1
-        elif i == 21:
-            new_sheet[f'D{i}'] = row['OD2']  # 外径2
-        elif i == 22:
-            new_sheet[f'D{i}'] = row['OD3']  # 外径3
-        elif i == 23:
-            new_sheet[f'D{i}'] = row['Height']  # 高度
-        elif i == 24:
-            new_sheet[f'D{i}'] = row['Wall11']  # 壁厚11
-        elif i == 25:
-            new_sheet[f'D{i}'] = row['Wall12']  # 壁厚12
-        elif i == 26:
-            new_sheet[f'D{i}'] = row['Wall13']  # 壁厚13
-        elif i == 27:
-            new_sheet[f'D{i}'] = row['Wall2']  # 壁厚2
-        elif i == 28:
-            new_sheet[f'D{i}'] = row['Wall3']  # 壁厚3
-    
-    # 保持"批准人："文本，并在其后添加名字
-    new_sheet['D29'] = f"批准人：{quality_assured_by}"
-
-# 保存修改后的文件
-wb.save('2_updated.xlsx')
+        # Check if 'WACKER' sheet exists
+        if 'WACKER' not in wb.sheetnames:
+            print("Error: Template file must contain a sheet named 'WACKER'.")
+            return None # Indicate error
+        wacker_sheet = wb['WACKER']
+
+
+        # 获取Sales Order Quantity和Quality Assured By
+        sales_order_quantity = header_df.iloc[5, 2]
+        quality_assured_by = header_df.iloc[3, 7]
+
+        # 定义元素和行号的对应关系 (Copied from original script)
+        element_row_mapping = {
+            'Al': 9, 'Ca': 10, 'Cu': 11, 'Fe': 12, 'K': 13, 'Li': 14,
+            'Mg': 15, 'Mn': 16, 'Na': 17, 'Ti': 18, 'Zr': 19
+        }
+        element_col_mapping = {
+            'Al': 4, 'Ca': 5, 'Cu': 6, 'Fe': 7, 'K': 8, 'Li': 9,
+            'Mg': 10, 'Mn': 11, 'Na': 12, 'Ti': 13, 'Zr': 14
+        }
+
+
+        # 遍历Dimension表格中的每个Customer ID
+        for index, row in dimension_df.iterrows():
+            customer_id = row['Customer ID']
+            # Ensure customer_id is a valid sheet name (Excel has limitations)
+            safe_customer_id = str(customer_id).replace('/', '-').replace('\\', '-').replace('?', '').replace('*', '').replace('[', '').replace(']', '')
+            safe_customer_id = safe_customer_id[:31] # Max sheet name length
+
+            # Handle potential NaN or empty Customer ID
+            if pd.isna(customer_id) or not str(customer_id).strip():
+                print(f"Skipping row {index+14} due to missing or invalid Customer ID.") # +14 accounts for header rows skipped
+                continue
+
+            inspection_date_str = ""
+            inspection_date = None # Initialize inspection_date
+            try:
+                 # Check if inspection_date is already datetime or needs conversion
+                if isinstance(row['Inspection Date'], datetime):
+                    inspection_date = row['Inspection Date']
+                else:
+                    inspection_date = pd.to_datetime(row['Inspection Date'])
+                inspection_date_str = inspection_date.strftime('%Y-%m-%d')
+            except Exception as e:
+                print(f"Warning: Could not parse Inspection Date for Customer ID {customer_id}: {e}. Skipping date fields.")
+                # inspection_date remains None
+
+
+            new_sheet_title = safe_customer_id
+            # Avoid duplicate sheet names if safe_customer_id becomes the same for different original IDs
+            sheet_count = 1
+            while new_sheet_title in wb.sheetnames:
+                 suffix = f"_{sheet_count}"
+                 max_len = 31 - len(suffix)
+                 new_sheet_title = safe_customer_id[:max_len] + suffix
+                 sheet_count += 1
+
+            new_sheet = wb.create_sheet(title=new_sheet_title)
+
+            # 复制WACKER表格的内容到新工作表
+            for row_wacker in wacker_sheet.iter_rows(values_only=True):
+                new_sheet.append(row_wacker)
+
+            # 填充数据
+            new_sheet['B3'] = str(sales_order_quantity) + ' PCS'
+            new_sheet['B4'] = customer_id # Use original ID here
+            if inspection_date: # Only fill dates if parsing was successful
+                 new_sheet['D4'] = inspection_date_str
+                 new_sheet['B5'] = inspection_date_str
+                 new_sheet['D5'] = (inspection_date + timedelta(days=730)).strftime('%Y-%m-%d')
+
+
+            # 从sand表中获取当前customer_id的数据
+            sand_rows = sand_df[sand_df[2] == customer_id] # 使用第3列（索引2）作为Crucible ID
+            if not sand_rows.empty:
+                sand_row = sand_rows.iloc[0]
+                # 填充元素数据 (with added error handling)
+                for element, target_row in element_row_mapping.items():
+                    try:
+                        source_col = element_col_mapping[element]
+                        # Check if value exists and handle potential errors
+                        value = sand_row.get(source_col) # Use .get for safety
+                        if value is not None and not pd.isna(value):
+                             new_sheet[f'D{target_row}'] = value
+                        else:
+                             print(f"Warning: Missing or invalid sand data for {element}, Customer ID {customer_id}, Col Index {source_col}")
+                             # Optionally fill with a default value or leave blank
+                             # new_sheet[f'D{target_row}'] = "N/A"
+                    except KeyError:
+                         print(f"Warning: Column index {source_col} not found in sand_row for {element}, Customer ID {customer_id}")
+                    except Exception as e:
+                         print(f"Error filling element {element} for Customer ID {customer_id}: {e}")
+
+
+            # 填充Analysis result/分析结果 (with added error handling)
+            dim_mapping = {
+                20: 'OD1', 21: 'OD2', 22: 'OD3', 23: 'Height',
+                24: 'Wall11', 25: 'Wall12', 26: 'Wall13',
+                27: 'Wall2', 28: 'Wall3'
+            }
+            for target_row, source_col_name in dim_mapping.items():
+                 try:
+                     # Check if value exists and handle potential errors
+                     value = row.get(source_col_name) # Use .get for safety
+                     if value is not None and not pd.isna(value):
+                          new_sheet[f'D{target_row}'] = value
+                     else:
+                         print(f"Warning: Missing or invalid dimension data for {source_col_name}, Customer ID {customer_id}")
+                         # Optionally fill with a default value or leave blank
+                         # new_sheet[f'D{target_row}'] = "N/A"
+                 except KeyError:
+                     print(f"Warning: Column '{source_col_name}' not found in dimension_df for Customer ID {customer_id}")
+                 except Exception as e:
+                     print(f"Error filling dimension {source_col_name} for Customer ID {customer_id}: {e}")
+
+            # 保持"批准人："文本，并在其后添加名字
+            new_sheet['D29'] = f"批准人：{quality_assured_by}"
+
+        # Remove the original template sheet if it exists and wasn't intended to be kept
+        if 'WACKER' in wb.sheetnames:
+             del wb['WACKER'] # Remove template if no longer needed
+
+        # 保存修改后的文件
+        wb.save(output_filename)
+        return output_filename # Return the path of the saved file
+
+    except FileNotFoundError:
+        print(f"Error: Input file not found. Check paths: {file1_path}, {file2_path}")
+        return None
+    except KeyError as e:
+        print(f"Error: Missing expected column or sheet name: {e}. Check input file formats.")
+        return None
+    except Exception as e:
+        # Log other unexpected errors
+        import traceback
+        print(f"An unexpected error occurred in process_files: {e}")
+        print(traceback.format_exc())
+        return None
+
+
+# Keep the original script behavior if run directly (optional)
+if __name__ == "__main__":
+    # Define default input/output files for direct execution
+    default_file1 = '1.xls'
+    default_file2 = '2.xlsx'
+    default_output = '2_updated.xlsx'
+
+    print(f"Running script directly. Processing {default_file1} and {default_file2}...")
+    output_path = process_files(default_file1, default_file2, default_output)
+
+    if output_path:
+        print(f"Report generated successfully: {output_path}")
+    else:
+        print("Report generation failed.")

requirements.txt

@@ -1,2 +1,3 @@
 pandas>=1.3.0
-openpyxl>=3.0.0 
+openpyxl>=3.0.0
+gradio>=3.0