From ec9cbbc4f7ada2bb8dd82c8f1d9fdaa5e24b69ed Mon Sep 17 00:00:00 2001
From: HuangHai <10402852@qq.com>
Date: Thu, 26 Jun 2025 08:08:09 +0800
Subject: [PATCH] 'commit'

---
 .../{T2_DocxProcessor.py => T2_SplitTxt.py}   |  0
 dsRag/Tools/T3_ImportTxt.py                   | 33 ++++++++++---------
 2 files changed, 17 insertions(+), 16 deletions(-)
 rename dsRag/Tools/{T2_DocxProcessor.py => T2_SplitTxt.py} (100%)

diff --git a/dsRag/Tools/T2_DocxProcessor.py b/dsRag/Tools/T2_SplitTxt.py
similarity index 100%
rename from dsRag/Tools/T2_DocxProcessor.py
rename to dsRag/Tools/T2_SplitTxt.py
diff --git a/dsRag/Tools/T3_ImportTxt.py b/dsRag/Tools/T3_ImportTxt.py
index 54b07a07..3947bcce 100644
--- a/dsRag/Tools/T3_ImportTxt.py
+++ b/dsRag/Tools/T3_ImportTxt.py
@@ -47,25 +47,26 @@ def save_to_es(text):
 def process_directory(dir_path):
     """处理目录下所有文本文件"""
     total_paragraphs = 0
-    file_count = len([f for f in os.listdir(dir_path) if f.endswith('.txt')])
-    current_file = 0
+    
+    # 获取所有txt文件并按数字排序
+    files = [f for f in os.listdir(dir_path) if f.endswith('.txt')]
+    files.sort(key=lambda x: int(x.split('.')[0]))
+    file_count = len(files)
     
     print(f"共发现{file_count}个文本文件需要处理")
     
-    for filename in os.listdir(dir_path):
-        if filename.endswith('.txt'):
-            current_file += 1
-            print(f"正在处理第{current_file}/{file_count}个文件: {filename}")
-            
-            file_path = os.path.join(dir_path, filename)
-            with open(file_path, 'r', encoding='utf-8') as f:
-                content = f.read()
-            
-            paragraphs = split_paragraphs(content)
-            total_paragraphs += len(paragraphs)
-            
-            for paragraph in paragraphs:
-                save_to_es(paragraph)
+    for i, filename in enumerate(files, 1):
+        print(f"正在处理第{i}/{file_count}个文件: {filename}")
+        
+        file_path = os.path.join(dir_path, filename)
+        with open(file_path, 'r', encoding='utf-8') as f:
+            content = f.read()
+        
+        paragraphs = split_paragraphs(content)
+        total_paragraphs += len(paragraphs)
+        
+        for paragraph in paragraphs:
+            save_to_es(paragraph)
     
     print(f"\n处理完成，共处理{file_count}个文件，保存{total_paragraphs}个段落")