chore(dependencies): 更新mineru依赖为mineru[core]，简化文档解析逻辑

docker/mineru.Dockerfile

@@ -1,10 +1,24 @@
 # Lastest version: wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/china/Dockerfile
 
 # Use the official sglang image
-FROM lmsysorg/sglang:v0.4.7-cu124
+FROM lmsysorg/sglang:v0.4.9.post3-cu126
+# For blackwell GPU, use the following line instead:
+# FROM lmsysorg/sglang:v0.4.9.post3-cu128-b200
 
-# install mineru latest
+# Install libgl for opencv support & Noto fonts for Chinese characters
-RUN python3 -m pip install -U 'mineru[core]' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages
+RUN apt-get update && \
+    apt-get install -y \
+        fonts-noto-core \
+        fonts-noto-cjk \
+        fontconfig \
+        libgl1 && \
+    fc-cache -fv && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install mineru latest
+RUN python3 -m pip install -U 'mineru[core]' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages && \
+    python3 -m pip cache purge
 
 # Download models and update the configuration file
 RUN /bin/bash -c "mineru-models-download -s modelscope -m all"

pyproject.toml

@@ -51,7 +51,7 @@ dependencies = [
     "tqdm>=4.66.4",
     "rich>=13.7.1",
     "typer>=0.16.0",
-    "mineru>=2.1.6",
+    "mineru[core]>=2.1.6",
 ]
 [tool.ruff]
 line-length = 210  # 代码最大行宽

src/plugins/mineru.py

@@ -206,33 +206,29 @@ def parse_doc(
             Adapted only for the case where the backend is set to "pipeline".
         server_url: When the backend is `sglang-client`, you need to specify the server_url, for example:`http://127.0.0.1:30000`
     """
-    try:
+    file_name_list = []
-        file_name_list = []
+    pdf_bytes_list = []
-        pdf_bytes_list = []
+    lang_list = []
-        lang_list = []
+    for path in tqdm(path_list, desc="Parsing documents"):
-        for path in tqdm(path_list, desc="Parsing documents"):
+        file_name = str(Path(path).stem)
-            file_name = str(Path(path).stem)
+        pdf_bytes = read_fn(path)
-            pdf_bytes = read_fn(path)
+        file_name_list.append(file_name)
-            file_name_list.append(file_name)
+        pdf_bytes_list.append(pdf_bytes)
-            pdf_bytes_list.append(pdf_bytes)
+        lang_list.append(lang)
-            lang_list.append(lang)
 
-        result = do_parse(
+    result = do_parse(
-            output_dir=output_dir,
+        output_dir=output_dir,
-            pdf_file_names=file_name_list,
+        pdf_file_names=file_name_list,
-            pdf_bytes_list=pdf_bytes_list,
+        pdf_bytes_list=pdf_bytes_list,
-            p_lang_list=lang_list,
+        p_lang_list=lang_list,
-            backend=backend,
+        backend=backend,
-            parse_method=method,
+        parse_method=method,
-            server_url=server_url,
+        server_url=server_url,
-            start_page_id=start_page_id,
+        start_page_id=start_page_id,
-            end_page_id=end_page_id
+        end_page_id=end_page_id
-        )
+    )
-        return result if result else [""]
+    return result if result else [""]
 
-    except Exception as e:
-        logger.exception(e)
-        return [""]
 
 if __name__ == "__main__":