将ocr解析模块独立出来

ocr/config.py

@@ -0,0 +1,42 @@
+#
+#  Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+"""
+OCR 模块配置文件
+"""
+import os
+import logging
+
+# 并行设备数量（GPU数量，0表示使用CPU）
+PARALLEL_DEVICES = 0
+try:
+    import torch.cuda
+    PARALLEL_DEVICES = torch.cuda.device_count()
+    logging.info(f"found {PARALLEL_DEVICES} gpus")
+except Exception:
+    logging.info("can't import package 'torch', using CPU mode")
+
+# 模型目录
+# 可以从环境变量获取，或使用默认路径
+MODEL_DIR = os.getenv("OCR_MODEL_DIR", None)
+if MODEL_DIR is None:
+    # 默认模型目录：当前项目根目录下的 models/deepdoc 目录
+    # 如果不存在，将在 OCR 类初始化时尝试从 HuggingFace 下载
+    _base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+    MODEL_DIR = os.path.join(_base_dir, "models", "deepdoc")
+    # 如果目录不存在，设置为 None，让 OCR 类处理下载逻辑
+    if not os.path.exists(MODEL_DIR):
+        MODEL_DIR = None
+