Merge pull request #2644 from myhloli/dev

fix: update configure_model to use environment variable for config file name

README.md

@@ -347,48 +347,38 @@ 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
@@ -717,6 +707,7 @@ 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

@@ -336,49 +336,38 @@
   <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>
 
 
@@ -710,6 +699,7 @@ 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.

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/version.py

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

signatures/version1/cla.json

@@ -263,6 +263,46 @@
       "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
     }
   ]
 }