refactor: 重构项目配置管理，统一使用.env配置

- 新增config.py统一读取.env配置，移除硬编码路径和参数
- 重构collect_jrxml.py支持命令行参数和环境变量配置源目录
- 新增.env.example示例配置文件，整理所有可配置项
- 重构down_embedding_model.py、import_to_chroma.py等所有脚本使用统一配置
- 新增Windows一键部署脚本setup.bat
- 修正jrxml_banch_chunker.py的文件名拼写错误

jrxml_banch_chunker.py

@@ -11,9 +11,10 @@ from pathlib import Path
 from datetime import datetime
 from collections import defaultdict
 from jrxml_chunker import JRXMLSemanticChunker, save_chunks_to_json, print_chunk_summary
+from config import JRXML_SOURCE_DIR, CHUNKER_OUTPUT_DIR, MAX_CHUNK_SIZE
 
 
-def batch_chunk_with_report(input_dir: str, output_dir: str = None, max_chunk_size: int = 2000):
+def batch_chunk_with_report(input_dir: str = None, output_dir: str = None, max_chunk_size: int = None):
     """
     批量分块并生成详细报告
     
@@ -22,6 +23,8 @@ def batch_chunk_with_report(input_dir: str, output_dir: str = None, max_chunk_si
         output_dir: 输出目录，默认为 input_dir/../chunked_output
         max_chunk_size: 单个chunk最大字节数
     """
+    if input_dir is None:
+        input_dir = str(JRXML_SOURCE_DIR)
     input_path = Path(input_dir).resolve()
     
     if not input_path.exists():
@@ -32,11 +35,13 @@ def batch_chunk_with_report(input_dir: str, output_dir: str = None, max_chunk_si
         print(f"❌ 不是目录: {input_path}")
         return None
     
-    # 设置输出目录
     if output_dir is None:
-        output_dir = input_path.parent / f"{input_path.name}_chunked_{datetime.now().strftime('%Y%m%d_%H%M%S')}"
+        output_dir = str(CHUNKER_OUTPUT_DIR)
     output_path = Path(output_dir)
     output_path.mkdir(parents=True, exist_ok=True)
+
+    if max_chunk_size is None:
+        max_chunk_size = MAX_CHUNK_SIZE
     
     print(f"\n{'='*60}")
     print(f"JRXML 语义分块 v3.0 - 批量处理")
@@ -214,21 +219,24 @@ if __name__ == "__main__":
         print("=" * 60)
         print("JRXML Semantic Chunking v3.0 - 批量处理工具")
         print("=" * 60)
+        print(f"\n默认输入目录: {JRXML_SOURCE_DIR}")
+        print(f"默认输出目录: {CHUNKER_OUTPUT_DIR}")
         print("\n用法:")
-        print("  python batch_chunker.py <目录路径>")
-        print("  python batch_chunker.py <文件路径>")
+        print("  python jrxml_banch_chunker.py <目录路径>")
+        print("  python jrxml_banch_chunker.py <文件路径>")
+        print("  python jrxml_banch_chunker.py                  (使用默认配置)")
         print("\n参数:")
-        print("  <路径>       JRXML文件所在目录 或 单个JRXML文件路径")
+        print("  <路径>            JRXML文件所在目录 或 单个JRXML文件路径")
         print("  --output <目录>   指定输出目录 (可选)")
         print("\n示例:")
-        print("  python batch_chunker.py ./jasper_reports")
-        print("  python batch_chunker.py ./jasper_reports --output ./chunks")
-        print("  python batch_chunker.py report.jrxml")
+        print("  python jrxml_banch_chunker.py")
+        print("  python jrxml_banch_chunker.py ./jasper_reports")
+        print("  python jrxml_banch_chunker.py ./jasper_reports --output ./chunks")
+        print("  python jrxml_banch_chunker.py report.jrxml")
         sys.exit(0)
     
     input_path = sys.argv[1]
     
-    # 解析--output参数
     output_dir = None
     if "--output" in sys.argv:
         idx = sys.argv.index("--output")
@@ -236,10 +244,8 @@ if __name__ == "__main__":
             output_dir = sys.argv[idx + 1]
     
     if os.path.isdir(input_path):
-        # 批量处理目录
         batch_chunk_with_report(input_path, output_dir)
     elif os.path.isfile(input_path):
-        # 处理单个文件
         chunk_single_file_with_report(input_path, output_dir)
     else:
         print(f"❌ 路径无效: {input_path}")