refactor: move translation logic to mylib/translate_utils.py and add DEBUG mode

mylib/translate_utils.py

@@ -0,0 +1,70 @@
+import os
+import logging
+from typing import List
+from mylib.pdfzh_translator import OpenAITranslator
+
+logger = logging.getLogger(__name__)
+
+def insert_empty_columns(data: List[List[str]], column_indices: List[int]) -> List[List[str]]:
+    """在指定列之后插入空列"""
+    try:
+        # 按从大到小排序，防止插入影响后续索引
+        column_indices.sort(reverse=True)
+        for row in data:
+            for index in column_indices:
+                row.insert(index + 1, '')
+        return data
+    except Exception as e:
+        logger.error(f"Error inserting empty columns: {e}")
+        raise
+
+def process_batch_translations(data: List[List[str]], search_term_index: int, category_indices: List[int]) -> List[List[str]]:
+    """批量处理翻译"""
+    try:
+        # 初始化翻译器
+        translator = OpenAITranslator("openai", "zh-CN", "en", "gpt-3.5-turbo")
+        
+        # 收集所有需要翻译的文本
+        translation_batches = {
+            'search_terms': [row[search_term_index] for row in data[2:]],  # 从第三行开始
+            'categories': []
+        }
+        
+        # 收集类别翻译
+        for index in category_indices:
+            translation_batches['categories'].extend([row[index] for row in data[2:]])  # 从第三行开始
+        
+        # 批量翻译
+        logger.info("Starting batch translations...")
+        
+        if os.getenv('DEBUG', '').lower() in ('true', '1', 't'):
+            # DEBUG模式：使用模拟翻译
+            search_translations = [f"{text} 翻译测试" for text in translation_batches['search_terms']]
+            category_translations = [f"{text} 翻译测试" for text in translation_batches['categories']]
+        else:
+            # 正常模式：调用真实翻译
+            search_translations = translator.translate(translation_batches['search_terms'])
+            category_translations = translator.translate(translation_batches['categories'])
+        
+        logger.info("Batch translations completed")
+        
+        # 更新数据
+        for i, row in enumerate(data[2:], start=2):  # 从第三行开始处理
+            try:
+                # 更新搜索词翻译列
+                row[search_term_index + 1] = search_translations[i-2]
+                
+                # 更新类别翻译
+                category_trans_index = (i-2) * len(category_indices)
+                for cat_index in category_indices:
+                    row[cat_index + 1] = category_translations[category_trans_index]
+                    category_trans_index += 1
+                
+            except Exception as e:
+                logger.error(f"Error processing row {i}: {e}")
+                raise
+                
+        return data
+    except Exception as e:
+        logger.error(f"Error in batch translation: {e}")
+        raise

process_data.py

@@ -3,7 +3,7 @@ import chardet
 import sys
 import logging
 from pathlib import Path
-from mylib.pdfzh_translator import OpenAITranslator
+from mylib.translate_utils import insert_empty_columns, process_batch_translations
 from brand_add_url_link import create_hyperlink, create_asin_link
 from mylib.logging_config import setup_logging
 
@@ -43,66 +43,6 @@ def read_csv(file_path):
     logger.error("Failed to read file with all attempted encodings")
     sys.exit(1)
 
-def insert_empty_columns(data, column_indices):
-    """在指定列之后插入空列"""
-    try:
-        # 按从大到小排序，防止插入影响后续索引
-        column_indices.sort(reverse=True)
-        for row in data:
-            for index in column_indices:
-                row.insert(index + 1, '')
-        return data
-    except Exception as e:
-        logger.error(f"Error inserting empty columns: {e}")
-        sys.exit(1)
-
-def process_batch_translations(data, search_term_index, category_indices):
-    """批量处理翻译"""
-    try:
-        # 初始化翻译器
-        translator = OpenAITranslator("openai", "zh-CN", "en", "gpt-3.5-turbo")
-        
-        # 收集所有需要翻译的文本
-        translation_batches = {
-            'search_terms': [row[search_term_index] for row in data[2:]],  # 从第三行开始
-            'categories': []
-        }
-        
-        # 收集类别翻译
-        for index in category_indices:
-            translation_batches['categories'].extend([row[index] for row in data[2:]])  # 从第三行开始
-        
-        # 批量翻译
-        logger.info("Starting batch translations...")
-        search_translations = translator.translate(translation_batches['search_terms'])
-        category_translations = translator.translate(translation_batches['categories'])
-        logger.info("Batch translations completed")
-        
-        # 更新数据
-        for i, row in enumerate(data[2:], start=2):  # 从第三行开始处理
-            try:
-                # 更新搜索词翻译列
-                row[search_term_index + 1] = search_translations[i-2]
-                
-                # 添加亚马逊搜索链接（跳过标题行）
-                amazon_url = f"https://www.amazon.co.jp/s?k={row[search_term_index]}"
-                row[search_term_index] = create_hyperlink(row[search_term_index], amazon_url)
-                
-                # 更新类别翻译
-                category_trans_index = (i-2) * len(category_indices)
-                for cat_index in category_indices:
-                    row[cat_index + 1] = category_translations[category_trans_index]
-                    category_trans_index += 1
-                
-            except Exception as e:
-                logger.error(f"Error processing row {i}: {e}")
-                sys.exit(1)
-                
-        return data
-    except Exception as e:
-        logger.error(f"Error in batch translation: {e}")
-        sys.exit(1)
-
 def add_brand_asin_links(data, brand_indices, asin_indices):
     """为品牌和ASIN列添加链接"""
     try: