Merge pull request #2648 from myhloli/dev

Dev

README.md

@@ -51,6 +51,10 @@ Easier to use: Just grab MinerU Desktop. No coding, no login, just a simple inte
 </div>
 
 # Changelog
+- 2025/06/15 2.0.2 released
+  - Fixed a configuration file key-value update error that occurred when downloading model type was set to `all`
+  - Fixed an issue where formula and table feature toggle parameters in the command line interface could not be effectively disabled
+  - Updated Dockerfile and installation documentation for deploying the full version of MinerU in sglang environment
 - 2025/06/13 2.0.0 Released
   - MinerU 2.0 represents a comprehensive reconstruction and upgrade from architecture to functionality, delivering a more streamlined design, enhanced performance, and more flexible user experience.
     - **New Architecture**: MinerU 2.0 has been deeply restructured in code organization and interaction methods, significantly improving system usability, maintainability, and extensibility.
@@ -347,48 +351,38 @@ Easier to use: Just grab MinerU Desktop. No coding, no login, just a simple inte
   <details>
   <summary>2024/07/05 Initial open-source release</summary>
   </details>
+</details>
+
+<!-- TABLE OF CONTENT -->
   
-  <!-- TABLE OF CONTENT -->
-  
-  <details open="open">
-    <summary><h2 style="display: inline-block">Table of Contents</h2></summary>
-    <ol>
-      <li>
-        <a href="#mineru">MinerU</a>
-        <ul>
-          <li><a href="#project-introduction">Project Introduction</a></li>
-          <li><a href="#key-features">Key Features</a></li>
-          <li><a href="#quick-start">Quick Start</a>
-              <ul>
-              <li><a href="#online-demo">Online Demo</a></li>
-              <li><a href="#quick-cpu-demo">Quick CPU Demo</a></li>
-              <li><a href="#using-gpu">Using GPU</a></li>
-              <li><a href="#using-npu">Using NPU</a></li>
-              </ul>
-          </li>
-          <li><a href="#usage">Usage</a>
-              <ul>
-              <li><a href="#command-line">Command Line</a></li>
-              <li><a href="#api">API</a></li>
-              <li><a href="#deploy-derived-projects">Deploy Derived Projects</a></li>
-              <li><a href="#development-guide">Development Guide</a></li>
-              </ul>
-          </li>
-        </ul>
-      </li>
-      <li><a href="#todo">TODO</a></li>
-      <li><a href="#known-issues">Known Issues</a></li>
-      <li><a href="#faq">FAQ</a></li>
-      <li><a href="#all-thanks-to-our-contributors">All Thanks To Our Contributors</a></li>
-      <li><a href="#license-information">License Information</a></li>
-      <li><a href="#acknowledgments">Acknowledgments</a></li>
-      <li><a href="#citation">Citation</a></li>
-      <li><a href="#star-history">Star History</a></li>
-      <li><a href="#magic-doc">Magic-doc</a></li>
-      <li><a href="#magic-html">Magic-html</a></li>
-      <li><a href="#links">Links</a></li>
-    </ol>
-  </details>
+<details open="open">
+  <summary><h2 style="display: inline-block">Table of Contents</h2></summary>
+  <ol>
+    <li>
+      <a href="#mineru">MinerU</a>
+      <ul>
+        <li><a href="#project-introduction">Project Introduction</a></li>
+        <li><a href="#key-features">Key Features</a></li>
+        <li><a href="#quick-start">Quick Start</a>
+            <ul>
+            <li><a href="#online-demo">Online Demo</a></li>
+            <li><a href="#quick-cpu-demo">Local Deployment</a></li>
+            </ul>
+        </li>
+      </ul>
+    </li>
+    <li><a href="#todo">TODO</a></li>
+    <li><a href="#known-issues">Known Issues</a></li>
+    <li><a href="#faq">FAQ</a></li>
+    <li><a href="#all-thanks-to-our-contributors">All Thanks To Our Contributors</a></li>
+    <li><a href="#license-information">License Information</a></li>
+    <li><a href="#acknowledgments">Acknowledgments</a></li>
+    <li><a href="#citation">Citation</a></li>
+    <li><a href="#star-history">Star History</a></li>
+    <li><a href="#magic-doc">Magic-doc</a></li>
+    <li><a href="#magic-html">Magic-html</a></li>
+    <li><a href="#links">Links</a></li>
+  </ol>
 </details>
 
 # MinerU
@@ -492,7 +486,7 @@ There are three different ways to experience MinerU:
 ```bash
 pip install --upgrade pip
 pip install uv
-uv pip install "mineru[core]>=2.0.0"
+uv pip install -U "mineru[core]"
 ```
 
 #### 1.2 Install from source
@@ -503,19 +497,40 @@ cd MinerU
 uv pip install -e .[core]
 ```
 
-#### 1.3 Install full version (with sglang acceleration)
+#### 1.3 Install the Full Version (Supports sglang Acceleration)
 
-To use **sglang acceleration for VLM model inference**, install the full version:
+If you need to use **sglang to accelerate VLM model inference**, you can choose any of the following methods to install the full version:
 
-```bash
-uv pip install "mineru[all]>=2.0.0"
-```
-
-Or install from source:
-
-```bash
-uv pip install -e .[all]
-```
+- Install using uv or pip:
+  ```bash
+  uv pip install -U "mineru[all]"
+  ```
+- Install from source:
+  ```bash
+  uv pip install -e .[all]
+  ```
+- Build image using Dockerfile:
+  ```bash
+  wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/global/Dockerfile
+  docker build -t mineru-sglang:latest -f Dockerfile .
+  ```
+  Start Docker container:
+  ```bash
+  docker run --gpus all \
+    --shm-size 32g \
+    -p 30000:30000 \
+    --ipc=host \
+    mineru-sglang:latest \
+    mineru-sglang-server --host 0.0.0.0 --port 30000
+  ```
+  Or start using Docker Compose:
+  ```bash
+    wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
+    docker compose -f compose.yaml up -d
+  ```
+  
+> [!TIP]
+> The Dockerfile uses `lmsysorg/sglang:v0.4.7-cu124` as the default base image. If necessary, you can modify it to another platform version.
 
 ---
 
@@ -639,7 +654,8 @@ mineru-sglang-server --port 30000
 mineru -p <input_path> -o <output_path> -b vlm-sglang-client -u http://127.0.0.1:30000
 ```
 
-> 💡 For more information about output files, please refer to [Output File Documentation](docs/output_file_en_us.md)
+> [!TIP]
+> For more information about output files, please refer to [Output File Documentation](docs/output_file_en_us.md)
 
 ---
 
@@ -717,6 +733,7 @@ Currently, some models in this project are trained based on YOLO. However, since
 - [xy-cut](https://github.com/Sanster/xy-cut)
 - [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
 - [pypdfium2](https://github.com/pypdfium2-team/pypdfium2)
+- [pdftext](https://github.com/datalab-to/pdftext)
 - [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
 - [pypdf](https://github.com/py-pdf/pypdf)
 

README_zh-CN.md

@@ -50,6 +50,10 @@
 </div>
 
 # 更新记录
+- 2025/06/15 2.0.2发布
+  - 修复了当下载模型类型设置为`all`时，配置文件出现键值更新错误的问题
+  - 修复了命令行接口中公式和表格功能的开关参数实际无法关闭的问题
+  - 更新了sglang环境下部署完整版MinerU的Dockerfile和相关安装文档
 - 2025/06/13 2.0.0发布
   - MinerU 2.0 是一次从架构到功能的全面重构与升级，带来了更简洁的设计、更强的性能以及更灵活的使用体验。
     - **全新架构**：MinerU 2.0 在代码结构和交互方式上进行了深度重构，显著提升了系统的易用性、可维护性与扩展能力。
@@ -336,49 +340,38 @@
   <details>
   <summary>2024/07/05 首次开源</summary>
   </details>
-  
-  
-  <!-- TABLE OF CONTENT -->
-  
-  <details open="open">
-    <summary><h2 style="display: inline-block">文档目录</h2></summary>
-    <ol>
-      <li>
-        <a href="#mineru">MinerU</a>
-        <ul>
-          <li><a href="#项目简介">项目简介</a></li>
-          <li><a href="#主要功能">主要功能</a></li>
-          <li><a href="#快速开始">快速开始</a>
-              <ul>
-              <li><a href="#在线体验">在线体验</a></li>
-              <li><a href="#使用CPU快速体验">使用CPU快速体验</a></li>
-              <li><a href="#使用GPU">使用GPU</a></li>
-              <li><a href="#使用NPU">使用NPU</a></li>
-              </ul>
-          </li>
-          <li><a href="#使用">使用方式</a>
-              <ul>
-              <li><a href="#命令行">命令行</a></li>
-              <li><a href="#api">API</a></li>
-              <li><a href="#部署衍生项目">部署衍生项目</a></li>
-              <li><a href="#二次开发">二次开发</a></li>
-              </ul>
-          </li>
-        </ul>
-      </li>
-      <li><a href="#todo">TODO</a></li>
-      <li><a href="#known-issues">Known Issues</a></li>
-      <li><a href="#faq">FAQ</a></li>
-      <li><a href="#all-thanks-to-our-contributors">Contributors</a></li>
-      <li><a href="#license-information">License Information</a></li>
-      <li><a href="#acknowledgments">Acknowledgements</a></li>
-      <li><a href="#citation">Citation</a></li>
-      <li><a href="#star-history">Star History</a></li>
-      <li><a href="#magic-doc">magic-doc快速提取PPT/DOC/PDF</a></li>
-      <li><a href="#magic-html">magic-html提取混合网页内容</a></li>
-      <li><a href="#links">Links</a></li>
-    </ol>
-  </details>
+</details>
+
+
+<!-- TABLE OF CONTENT -->
+
+<details open="open">
+  <summary><h2 style="display: inline-block">文档目录</h2></summary>
+  <ol>
+    <li>
+      <a href="#mineru">MinerU</a>
+      <ul>
+        <li><a href="#项目简介">项目简介</a></li>
+        <li><a href="#主要功能">主要功能</a></li>
+        <li><a href="#快速开始">快速开始</a>
+            <ul>
+            <li><a href="#在线体验">在线体验</a></li>
+            <li><a href="#本地部署">本地部署</a></li>
+            </ul>
+      </ul>
+    </li>
+    <li><a href="#todo">TODO</a></li>
+    <li><a href="#known-issues">Known Issues</a></li>
+    <li><a href="#faq">FAQ</a></li>
+    <li><a href="#all-thanks-to-our-contributors">Contributors</a></li>
+    <li><a href="#license-information">License Information</a></li>
+    <li><a href="#acknowledgments">Acknowledgements</a></li>
+    <li><a href="#citation">Citation</a></li>
+    <li><a href="#star-history">Star History</a></li>
+    <li><a href="#magic-doc">magic-doc快速提取PPT/DOC/PDF</a></li>
+    <li><a href="#magic-html">magic-html提取混合网页内容</a></li>
+    <li><a href="#links">Links</a></li>
+  </ol>
 </details>
 
 
@@ -483,7 +476,7 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
 ```bash
 pip install --upgrade pip -i https://mirrors.aliyun.com/pypi/simple
 pip install uv -i https://mirrors.aliyun.com/pypi/simple
-uv pip install "mineru[core]>=2.0.0" -i https://mirrors.aliyun.com/pypi/simple 
+uv pip install -U "mineru[core]" -i https://mirrors.aliyun.com/pypi/simple 
 ```
 
 #### 1.2 源码安装
@@ -496,17 +489,38 @@ uv pip install -e .[core] -i https://mirrors.aliyun.com/pypi/simple
 
 #### 1.3 安装完整版（支持 sglang 加速）
 
-如需使用 **sglang 加速 VLM 模型推理**，请安装完整版本：
+如需使用 **sglang 加速 VLM 模型推理**，请选择合适的方式安装完整版本：
 
-```bash
-uv pip install "mineru[all]>=2.0.0" -i https://mirrors.aliyun.com/pypi/simple
-```
-
-或从源码安装：
-
-```bash
-uv pip install -e .[all] -i https://mirrors.aliyun.com/pypi/simple
-```
+- 使用uv或pip安装
+  ```bash
+  uv pip install -U "mineru[all]" -i https://mirrors.aliyun.com/pypi/simple
+  ```
+- 从源码安装：
+  ```bash
+  uv pip install -e .[all] -i https://mirrors.aliyun.com/pypi/simple
+  ```
+- 使用 Dockerfile 构建镜像：
+  ```bash
+  wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/china/Dockerfile
+  docker build -t mineru-sglang:latest -f Dockerfile .
+  ```
+  启动 Docker 容器：
+  ```bash
+  docker run --gpus all \
+    --shm-size 32g \
+    -p 30000:30000 \
+    --ipc=host \
+    mineru-sglang:latest \
+    mineru-sglang-server --host 0.0.0.0 --port 30000
+  ```
+  或使用 Docker Compose 启动：
+  ```bash
+    wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
+    docker compose -f compose.yaml up -d
+  ```
+  
+> [!TIP]
+> Dockerfile默认使用`lmsysorg/sglang:v0.4.7-cu124`作为基础镜像，如有需要，您可以自行修改为其他平台版本。
 
 ---
 
@@ -630,7 +644,8 @@ mineru-sglang-server --port 30000
 mineru -p <input_path> -o <output_path> -b vlm-sglang-client -u http://127.0.0.1:30000
 ```
 
-> 💡 更多关于输出文件的信息，请参考 [输出文件说明](docs/output_file_zh_cn.md)
+> [!TIP]
+> 更多关于输出文件的信息，请参考 [输出文件说明](docs/output_file_zh_cn.md)
 
 ---
 
@@ -710,6 +725,7 @@ mineru -p <input_path> -o <output_path> -b vlm-sglang-client -u http://127.0.0.1
 - [xy-cut](https://github.com/Sanster/xy-cut)
 - [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
 - [pypdfium2](https://github.com/pypdfium2-team/pypdfium2)
+- [pdftext](https://github.com/datalab-to/pdftext)
 - [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
 - [pypdf](https://github.com/py-pdf/pypdf)
 

SECURITY.md

@@ -0,0 +1,31 @@
+# Security Policy
+
+## Supported Versions
+
+latest
+
+## Reporting a Vulnerability
+
+Please do not report security vulnerabilities through public GitHub issues.
+
+Instead, please report them at https://github.com/opendatalab/MinerU/security.
+
+Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
+
+  * Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
+  * Full paths of source file(s) related to the manifestation of the issue
+  * The location of the affected source code (tag/branch/commit or direct URL)
+  * Any special configuration required to reproduce the issue
+  * Step-by-step instructions to reproduce the issue
+  * Proof-of-concept or exploit code (if possible)
+  * Impact of the issue, including how an attacker might exploit the issue
+
+This information will help us triage your report more quickly.
+
+## Preferred Languages
+
+We prefer all communications to be in English and Chinese.
+
+## Policy
+
+We will fix security issues in the project's own code as quickly as possible. Before the project completes the fix, you must not disclose the vulnerability information to any public platform.

docker/china/Dockerfile

@@ -1,33 +1,8 @@
-# Use the official Ubuntu base image
-FROM ubuntu:22.04
-
-# Set environment variables to non-interactive to avoid prompts during installation
-ENV DEBIAN_FRONTEND=noninteractive
-
-# Update the package list and install necessary packages
-RUN apt-get update && \
-    apt-get install -y \
-        software-properties-common && \
-    add-apt-repository ppa:deadsnakes/ppa && \
-    apt-get update && \
-    apt-get install -y \
-        python3.10 \
-        python3.10-venv \
-        python3.10-distutils \
-        python3-pip \
-        wget \
-        git \
-        libgl1 \
-        libglib2.0-0 \
-        && rm -rf /var/lib/apt/lists/*
-
-# Set Python 3.10 as the default python3
-RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
+# Use the official sglang image
+FROM lmsysorg/sglang:v0.4.7-cu124
 
 # install mineru latest
-RUN /bin/bash -c "pip3 install --upgrade pip -i https://mirrors.aliyun.com/pypi/simple && \
-    pip3 install uv -i https://mirrors.aliyun.com/pypi/simple && \
-    uv pip install 'mineru[all]>=2.0.0' -i https://mirrors.aliyun.com/pypi/simple"
+RUN python3 -m pip install -U 'mineru[core]' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages
 
 # Download models and update the configuration file
 RUN /bin/bash -c "mineru-models-download -s modelscope -m all"

docker/compose.yaml

@@ -0,0 +1,26 @@
+services:
+  mineru-sglang:
+    image: mineru-sglang:latest
+    container_name: mineru-sglang
+    restart: always
+    ports:
+      - 30000:30000
+    environment:
+      MINERU_MODEL_SOURCE: local
+    entrypoint: mineru-sglang-server
+    command:
+      --host 0.0.0.0
+      --port 30000
+    ulimits:
+      memlock: -1
+      stack: 67108864
+    ipc: host
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: ["0"]
+              capabilities: [gpu]

docker/global/Dockerfile

@@ -1,33 +1,8 @@
-# Use the official Ubuntu base image
-FROM ubuntu:22.04
-
-# Set environment variables to non-interactive to avoid prompts during installation
-ENV DEBIAN_FRONTEND=noninteractive
-
-# Update the package list and install necessary packages
-RUN apt-get update && \
-    apt-get install -y \
-        software-properties-common && \
-    add-apt-repository ppa:deadsnakes/ppa && \
-    apt-get update && \
-    apt-get install -y \
-        python3.10 \
-        python3.10-venv \
-        python3.10-distutils \
-        python3-pip \
-        wget \
-        git \
-        libgl1 \
-        libglib2.0-0 \
-        && rm -rf /var/lib/apt/lists/*
-
-# Set Python 3.10 as the default python3
-RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
+# Use the official sglang image
+FROM lmsysorg/sglang:v0.4.7-cu124
 
 # install mineru latest
-RUN /bin/bash -c "pip3 install --upgrade pip && \
-    pip3 install uv && \
-    uv pip install 'mineru[all]>=2.0.0'"
+RUN python3 -m pip install -U 'mineru[core]' --break-system-packages
 
 # Download models and update the configuration file
 RUN /bin/bash -c "mineru-models-download -s huggingface -m all"

mineru/backend/pipeline/batch_analyze.py

@@ -5,6 +5,7 @@ from collections import defaultdict
 import numpy as np
 
 from .model_init import AtomModelSingleton
+from ...utils.config_reader import get_formula_enable, get_table_enable
 from ...utils.model_utils import crop_img, get_res_list_from_layout_res
 from ...utils.ocr_utils import get_adjusted_mfdetrec_res, get_ocr_result_list, OcrConfidence
 
@@ -16,8 +17,8 @@ MFR_BASE_BATCH_SIZE = 16
 class BatchAnalyze:
     def __init__(self, model_manager, batch_ratio: int, formula_enable, table_enable, enable_ocr_det_batch: bool = True):
         self.batch_ratio = batch_ratio
-        self.formula_enable = formula_enable
-        self.table_enable = table_enable
+        self.formula_enable = get_formula_enable(formula_enable)
+        self.table_enable = get_table_enable(table_enable)
         self.model_manager = model_manager
         self.enable_ocr_det_batch = enable_ocr_det_batch
 

mineru/backend/pipeline/model_json_to_middle_json.py

@@ -4,7 +4,7 @@ import time
 from loguru import logger
 from tqdm import tqdm
 
-from mineru.utils.config_reader import get_device, get_llm_aided_config
+from mineru.utils.config_reader import get_device, get_llm_aided_config, get_formula_enable
 from mineru.backend.pipeline.model_init import AtomModelSingleton
 from mineru.backend.pipeline.para_split import para_split
 from mineru.utils.block_pre_proc import prepare_block_bboxes, process_groups
@@ -165,6 +165,7 @@ def page_model_info_to_page_info(page_model_info, image_dict, page, image_writer
 
 def result_to_middle_json(model_list, images_list, pdf_doc, image_writer, lang=None, ocr_enable=False, formula_enabled=True):
     middle_json = {"pdf_info": [], "_backend":"pipeline", "_version_name": __version__}
+    formula_enabled = get_formula_enable(formula_enabled)
     for page_index, page_model_info in tqdm(enumerate(model_list), total=len(model_list), desc="Processing pages"):
         page = pdf_doc[page_index]
         image_dict = images_list[page_index]

mineru/backend/pipeline/pipeline_analyze.py

@@ -5,7 +5,7 @@ import PIL.Image
 import torch
 
 from .model_init import MineruPipelineModel
-from mineru.utils.config_reader import get_device, get_formula_config, get_table_recog_config
+from mineru.utils.config_reader import get_device
 from ...utils.pdf_classify import classify
 from ...utils.pdf_image_tools import load_images_from_pdf
 
@@ -44,20 +44,15 @@ class ModelSingleton:
 
 def custom_model_init(
     lang=None,
-    formula_enable=None,
-    table_enable=None,
+    formula_enable=True,
+    table_enable=True,
 ):
     model_init_start = time.time()
     # 从配置文件读取model-dir和device
     device = get_device()
 
-    formula_config = get_formula_config()
-    if formula_enable is not None:
-        formula_config['enable'] = formula_enable
-
-    table_config = get_table_recog_config()
-    if table_enable is not None:
-        table_config['enable'] = table_enable
+    formula_config = {"enable": formula_enable}
+    table_config = {"enable": table_enable}
 
     model_input = {
         'device': device,
@@ -78,8 +73,8 @@ def doc_analyze(
         pdf_bytes_list,
         lang_list,
         parse_method: str = 'auto',
-        formula_enable=None,
-        table_enable=None,
+        formula_enable=True,
+        table_enable=True,
 ):
     MIN_BATCH_INFERENCE_SIZE = int(os.environ.get('MINERU_MIN_BATCH_INFERENCE_SIZE', 100))
 
@@ -152,8 +147,8 @@ def doc_analyze(
 
 def batch_image_analyze(
         images_with_extra_info: List[Tuple[PIL.Image.Image, bool, str]],
-        formula_enable=None,
-        table_enable=None):
+        formula_enable=True,
+        table_enable=True):
     # os.environ['CUDA_VISIBLE_DEVICES'] = str(idx)
 
     from .batch_analyze import BatchAnalyze

mineru/cli/client.py

@@ -2,7 +2,6 @@
 import os
 import click
 from pathlib import Path
-import torch
 from loguru import logger
 
 from mineru.utils.config_reader import get_device
@@ -140,10 +139,6 @@ from .common import do_parse, read_fn, pdf_suffixes, image_suffixes
 
 def main(input_path, output_dir, method, backend, lang, server_url, start_page_id, end_page_id, formula_enable, table_enable, device_mode, virtual_vram, model_source):
 
-    if os.getenv('MINERU_FORMULA_ENABLE', None) is None:
-        os.environ['MINERU_FORMULA_ENABLE'] = str(formula_enable).lower()
-    if os.getenv('MINERU_TABLE_ENABLE', None) is None:
-        os.environ['MINERU_TABLE_ENABLE'] = str(table_enable).lower()
     def get_device_mode() -> str:
         if device_mode is not None:
             return device_mode
@@ -184,6 +179,8 @@ def main(input_path, output_dir, method, backend, lang, server_url, start_page_i
                 p_lang_list=lang_list,
                 backend=backend,
                 parse_method=method,
+                p_formula_enable=formula_enable,
+                p_table_enable=table_enable,
                 server_url=server_url,
                 start_page_id=start_page_id,
                 end_page_id=end_page_id

mineru/cli/common.py

@@ -115,6 +115,7 @@ def do_parse(
             pdf_doc = all_pdf_docs[idx]
             _lang = lang_list[idx]
             _ocr_enable = ocr_enabled_list[idx]
+
             middle_json = pipeline_result_to_middle_json(model_list, images_list, pdf_doc, image_writer, _lang, _ocr_enable, p_formula_enable)
 
             pdf_info = middle_json["pdf_info"]

mineru/cli/models_download.py

@@ -42,9 +42,8 @@ def download_and_modify_json(url, local_filename, modifications):
 
 def configure_model(model_dir, model_type):
     """配置模型"""
-    # json_url = 'https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/mineru.template.json'
-    json_url = 'https://gcore.jsdelivr.net/gh/myhloli/Magic-PDF@dev/mineru.template.json'
-    config_file_name = 'mineru.json'
+    json_url = 'https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/mineru.template.json'
+    config_file_name = os.getenv('MINERU_TOOLS_CONFIG_JSON', 'mineru.json')
     home_dir = os.path.expanduser('~')
     config_file = os.path.join(home_dir, config_file_name)
 
@@ -120,13 +119,13 @@ def download_models(model_source, model_type):
             click.echo(f"Downloading model: {model_path}")
             download_finish_path = auto_download_and_get_model_root_path(model_path, repo_mode='pipeline')
         click.echo(f"Pipeline models downloaded successfully to: {download_finish_path}")
-        configure_model(download_finish_path, model_type)
+        configure_model(download_finish_path, "pipeline")
 
     def download_vlm_models():
         """下载VLM模型"""
         download_finish_path = auto_download_and_get_model_root_path("/", repo_mode='vlm')
         click.echo(f"VLM models downloaded successfully to: {download_finish_path}")
-        configure_model(download_finish_path, model_type)
+        configure_model(download_finish_path, "vlm")
 
     try:
         if model_type == 'pipeline':

mineru/model/mfr/unimernet/unimernet_hf/modeling_unimernet.py

@@ -349,6 +349,7 @@ REPLACEMENTS_PATTERNS = {
     re.compile(r'\\vline = '): r'\\models ',
     re.compile(r'\\vDash '): r'\\models ',
     re.compile(r'\\sq \\sqcup '): r'\\square ',
+    re.compile(r'\\copyright'): r'©',
 }
 QQUAD_PATTERN = re.compile(r'\\qquad(?!\s)')
 

mineru/utils/config_reader.py

@@ -86,22 +86,16 @@ def get_device():
         return "cpu"
 
 
-def get_table_recog_config():
-    table_enable = os.getenv('MINERU_TABLE_ENABLE', None)
-    if table_enable is not None:
-        return json.loads(f'{{"enable": {table_enable}}}')
-    else:
-        # logger.warning(f"not found 'MINERU_TABLE_ENABLE' in environment variable, use 'true' as default.")
-        return json.loads(f'{{"enable": true}}')
+def get_formula_enable(formula_enable):
+    formula_enable_env = os.getenv('MINERU_FORMULA_ENABLE')
+    formula_enable = formula_enable if formula_enable_env is None else formula_enable_env.lower() == 'true'
+    return formula_enable
 
 
-def get_formula_config():
-    formula_enable = os.getenv('MINERU_FORMULA_ENABLE', None)
-    if formula_enable is not None:
-        return json.loads(f'{{"enable": {formula_enable}}}')
-    else:
-        # logger.warning(f"not found 'MINERU_FORMULA_ENABLE' in environment variable, use 'true' as default.")
-        return json.loads(f'{{"enable": true}}')
+def get_table_enable(table_enable):
+    table_enable_env = os.getenv('MINERU_TABLE_ENABLE')
+    table_enable = table_enable if table_enable_env is None else table_enable_env.lower() == 'true'
+    return table_enable
 
 
 def get_latex_delimiter_config():

mineru/version.py

@@ -1 +1 @@
-__version__ = "2.0.0"
+__version__ = "2.0.1"

signatures/version1/cla.json

@@ -263,6 +263,54 @@
       "created_at": "2025-04-30T09:25:31Z",
       "repoId": 765083837,
       "pullRequestNo": 2411
+    },
+    {
+      "name": "seedclaimer",
+      "id": 86753366,
+      "comment_id": 2916194375,
+      "created_at": "2025-05-28T12:50:25Z",
+      "repoId": 765083837,
+      "pullRequestNo": 2536
+    },
+    {
+      "name": "liuzhenghua",
+      "id": 11787325,
+      "comment_id": 2921092605,
+      "created_at": "2025-05-30T02:57:07Z",
+      "repoId": 765083837,
+      "pullRequestNo": 2550
+    },
+    {
+      "name": "PairZhu",
+      "id": 47098840,
+      "comment_id": 2938149702,
+      "created_at": "2025-06-04T02:39:39Z",
+      "repoId": 765083837,
+      "pullRequestNo": 2566
+    },
+    {
+      "name": "AdrianWangs",
+      "id": 72337244,
+      "comment_id": 2943818300,
+      "created_at": "2025-06-05T11:30:42Z",
+      "repoId": 765083837,
+      "pullRequestNo": 2578
+    },
+    {
+      "name": "YanzhenHuang",
+      "id": 86364920,
+      "comment_id": 2968974232,
+      "created_at": "2025-06-13T04:17:08Z",
+      "repoId": 765083837,
+      "pullRequestNo": 2620
+    },
+    {
+      "name": "Ar-Hyk",
+      "id": 55748412,
+      "comment_id": 2970512136,
+      "created_at": "2025-06-13T14:02:16Z",
+      "repoId": 765083837,
+      "pullRequestNo": 2634
     }
   ]
 }