Merge pull request #1280 from icecraft/docs/tune_docs

Docs/tune docs

magic_pdf/pipe/operators.py

+import copy
 import json
 import os
 from typing import Callable
-import copy
 
 from magic_pdf.config.make_content_config import DropMode, MakeMode
 from magic_pdf.data.data_reader_writer import DataWriter
@@ -23,6 +23,26 @@ class PipeResult:
         self._pipe_res = pipe_res
         self._dataset = dataset
 
+    def get_markdown(self,
+                    img_dir_or_bucket_prefix: str,
+                    drop_mode=DropMode.WHOLE_PDF,
+                    md_make_mode=MakeMode.MM_MD) -> str:
+        """Get markdown content.
+
+        Args:
+            img_dir_or_bucket_prefix (str): The s3 bucket prefix or local file directory which used to store the figure
+            drop_mode (str, optional): Drop strategy when some page which is corrupted or inappropriate. Defaults to DropMode.WHOLE_PDF.
+            md_make_mode (str, optional): The content Type of Markdown be made. Defaults to MakeMode.MM_MD.
+
+        Returns:
+            str: return markdown content
+        """
+        pdf_info_list = self._pipe_res['pdf_info']
+        md_content = union_make(
+            pdf_info_list, md_make_mode, drop_mode, img_dir_or_bucket_prefix
+        )
+        return md_content
+
     def dump_md(
         self,
         writer: DataWriter,
@@ -40,14 +60,40 @@ class PipeResult:
             drop_mode (str, optional): Drop strategy when some page which is corrupted or inappropriate. Defaults to DropMode.WHOLE_PDF.
             md_make_mode (str, optional): The content Type of Markdown be made. Defaults to MakeMode.MM_MD.
         """
+
+        md_content = self.get_markdown(img_dir_or_bucket_prefix, drop_mode=drop_mode, md_make_mode=md_make_mode)
+        writer.write_string(file_path, md_content)
+
+    def get_content_list(self,
+                        image_dir_or_bucket_prefix: str,
+                        drop_mode=DropMode.NONE,
+                        md_make_mode=MakeMode.STANDARD_FORMAT) -> str:
+        """Get Content List.
+
+        Args:
+            image_dir_or_bucket_prefix (str): The s3 bucket prefix or local file directory which used to store the figure
+            drop_mode (str, optional): Drop strategy when some page which is corrupted or inappropriate. Defaults to DropMode.NONE.
+            md_make_mode (str, optional): The content Type of Markdown be made. Defaults to MakeMode.STANDARD_FORMAT.
+
+        Returns:
+            str: content list content
+        """
         pdf_info_list = self._pipe_res['pdf_info']
-        md_content = union_make(
-            pdf_info_list, md_make_mode, drop_mode, img_dir_or_bucket_prefix
+        content_list = union_make(
+            pdf_info_list,
+            md_make_mode,
+            drop_mode,
+            image_dir_or_bucket_prefix,
         )
-        writer.write_string(file_path, md_content)
+        return content_list
 
     def dump_content_list(
-        self, writer: DataWriter, file_path: str, image_dir_or_bucket_prefix: str
+        self,
+        writer: DataWriter,
+        file_path: str,
+        image_dir_or_bucket_prefix: str,
+        drop_mode=DropMode.NONE,
+        md_make_mode=MakeMode.STANDARD_FORMAT
     ):
         """Dump Content List.
 
@@ -55,14 +101,10 @@ class PipeResult:
             writer (DataWriter): File writer handle
             file_path (str): The file location of content list
             image_dir_or_bucket_prefix (str): The s3 bucket prefix or local file directory which used to store the figure
+            drop_mode (str, optional): Drop strategy when some page which is corrupted or inappropriate. Defaults to DropMode.NONE.
+            md_make_mode (str, optional): The content Type of Markdown be made. Defaults to MakeMode.STANDARD_FORMAT.
         """
-        pdf_info_list = self._pipe_res['pdf_info']
-        content_list = union_make(
-            pdf_info_list,
-            MakeMode.STANDARD_FORMAT,
-            DropMode.NONE,
-            image_dir_or_bucket_prefix,
-        )
+        content_list = self.get_content_list(image_dir_or_bucket_prefix, drop_mode=drop_mode, md_make_mode=md_make_mode)
         writer.write_string(
             file_path, json.dumps(content_list, ensure_ascii=False, indent=4)
         )
@@ -123,7 +165,7 @@ class PipeResult:
         Returns:
             str: compress the pipeline result and return
         """
-        return JsonCompressor.compress_json(self.pdf_mid_data)
+        return JsonCompressor.compress_json(self._pipe_res)
 
     def apply(self, proc: Callable, *args, **kwargs):
         """Apply callable method which.

next_docs/README.md

-<div align="center" xmlns="http://www.w3.org/1999/html">
-<!-- logo -->
-<p align="center">
-  <img src="docs/images/MinerU-logo.png" width="300px" style="vertical-align:middle;">
-</p>
-
-<!-- icon -->
-
-[![stars](https://img.shields.io/github/stars/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
-[![forks](https://img.shields.io/github/forks/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
-[![open issues](https://img.shields.io/github/issues-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
-[![issue resolution](https://img.shields.io/github/issues-closed-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
-[![PyPI version](https://badge.fury.io/py/magic-pdf.svg)](https://badge.fury.io/py/magic-pdf)
-[![Downloads](https://static.pepy.tech/badge/magic-pdf)](https://pepy.tech/project/magic-pdf)
-[![Downloads](https://static.pepy.tech/badge/magic-pdf/month)](https://pepy.tech/project/magic-pdf)
-
-[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
-[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
-[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
-[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/myhloli/3b3a00a4a0a61577b6c30f989092d20d/mineru_demo.ipynb)
-[![Paper](https://img.shields.io/badge/Paper-arXiv-green)](https://arxiv.org/abs/2409.18839)
-
-<a href="https://trendshift.io/repositories/11174" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11174" alt="opendatalab%2FMinerU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
-
-<!-- language -->
-
-[English](README.md) | [简体中文](README_zh-CN.md)
-
-<!-- hot link -->
-
-<p align="center">
-<a href="https://github.com/opendatalab/PDF-Extract-Kit">PDF-Extract-Kit: High-Quality PDF Extraction Toolkit</a>🔥🔥🔥
-</p>
-
-<!-- join us -->
-
-<p align="center">
-    👋 join us on <a href="https://discord.gg/Tdedn9GTXq" target="_blank">Discord</a> and <a href="https://cdn.vansin.top/internlm/mineru.jpg" target="_blank">WeChat</a>
-</p>
-
-
-<!-- read the docs -->
-<p align="center">
-    read more docs on  <a href="https://mineru.readthedocs.io/en/latest/"> Read The Docs </a>
-</p>
-
-</div>
-
-# Changelog
-- 2024/11/06 0.9.2 released. Integrated the [StructTable-InternVL2-1B](https://huggingface.co/U4R/StructTable-InternVL2-1B) model for table recognition functionality.
-- 2024/10/31 0.9.0 released. This is a major new version with extensive code refactoring, addressing numerous issues, improving performance, reducing hardware requirements, and enhancing usability:
-  - Refactored the sorting module code to use [layoutreader](https://github.com/ppaanngggg/layoutreader) for reading order sorting, ensuring high accuracy in various layouts.
-  - Refactored the paragraph concatenation module to achieve good results in cross-column, cross-page, cross-figure, and cross-table scenarios.
-  - Refactored the list and table of contents recognition functions, significantly improving the accuracy of list blocks and table of contents blocks, as well as the parsing of corresponding text paragraphs.
-  - Refactored the matching logic for figures, tables, and descriptive text, greatly enhancing the accuracy of matching captions and footnotes to figures and tables, and reducing the loss rate of descriptive text to near zero.
-  - Added multi-language support for OCR, supporting detection and recognition of 84 languages.For the list of supported languages, see [OCR Language Support List](https://paddlepaddle.github.io/PaddleOCR/latest/en/ppocr/blog/multi_languages.html#5-support-languages-and-abbreviations).
-  - Added memory recycling logic and other memory optimization measures, significantly reducing memory usage. The memory requirement for enabling all acceleration features except table acceleration (layout/formula/OCR) has been reduced from 16GB to 8GB, and the memory requirement for enabling all acceleration features has been reduced from 24GB to 10GB.
-  - Optimized configuration file feature switches, adding an independent formula detection switch to significantly improve speed and parsing results when formula detection is not needed.
-  - Integrated [PDF-Extract-Kit 1.0](https://github.com/opendatalab/PDF-Extract-Kit):
-    - Added the self-developed `doclayout_yolo` model, which speeds up processing by more than 10 times compared to the original solution while maintaining similar parsing effects, and can be freely switched with `layoutlmv3` via the configuration file.
-    - Upgraded formula parsing to `unimernet 0.2.1`, improving formula parsing accuracy while significantly reducing memory usage.
-    - Due to the repository change for `PDF-Extract-Kit 1.0`, you need to re-download the model. Please refer to [How to Download Models](docs/how_to_download_models_en.md) for detailed steps.
-- 2024/09/27 Version 0.8.1 released, Fixed some bugs, and providing a [localized deployment version](projects/web_demo/README.md) of the [online demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/) and the [front-end interface](projects/web/README.md).
-- 2024/09/09: Version 0.8.0 released, supporting fast deployment with Dockerfile, and launching demos on Huggingface and Modelscope.
-- 2024/08/30: Version 0.7.1 released, add paddle tablemaster table recognition option
-- 2024/08/09: Version 0.7.0b1 released, simplified installation process, added table recognition functionality
-- 2024/08/01: Version 0.6.2b1 released, optimized dependency conflict issues and installation documentation
-- 2024/07/05: Initial open-source release
-
-<!-- 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>
-            </ul>
-        </li>
-        <li><a href="#usage">Usage</a>
-            <ul>
-            <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="#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
-
-## Project Introduction
-
-MinerU is a tool that converts PDFs into machine-readable formats (e.g., markdown, JSON), allowing for easy extraction into any format.
-MinerU was born during the pre-training process of [InternLM](https://github.com/InternLM/InternLM). We focus on solving symbol conversion issues in scientific literature and hope to contribute to technological development in the era of large models.
-Compared to well-known commercial products, MinerU is still young. If you encounter any issues or if the results are not as expected, please submit an issue on [issue](https://github.com/opendatalab/MinerU/issues) and **attach the relevant PDF**.
-
-https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
-
-## Quick Start
-
-There are multiple different ways to experience MinerU:
-
-- [Online Demo (No Installation Required)](#online-demo)
-- [Quick CPU Demo (Windows, Linux, Mac)](#quick-cpu-demo)
-
-### Online Demo
-
-Stable Version (Stable version verified by QA):  
-[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
-
-Test Version (Synced with dev branch updates, testing new features):  
-[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
-[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
-
-### Quick CPU Demo
-
-#### 1. Install magic-pdf
-
-```bash
-conda create -n MinerU python=3.10
-conda activate MinerU
-pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
-```
-
-#### 2. Download model weight files
-
-Refer to [How to Download Model Files](docs/how_to_download_models_en.md) for detailed instructions.
-
-#### 3. Modify the Configuration File for Additional Configuration
-
-After completing the [2. Download model weight files](#2-download-model-weight-files) step, the script will automatically generate a `magic-pdf.json` file in the user directory and configure the default model path.
-You can find the `magic-pdf.json` file in your 【user directory】.
-
-> [!TIP]
-> The user directory for Windows is "C:\\Users\\username", for Linux it is "/home/username", and for macOS it is "/Users/username".
-
-You can modify certain configurations in this file to enable or disable features, such as table recognition:
-
-> [!NOTE]
-> If the following items are not present in the JSON, please manually add the required items and remove the comment content (standard JSON does not support comments).
-
-```json
-{
-    // other config
-    "layout-config": {
-        "model": "layoutlmv3" // Please change to "doclayout_yolo" when using doclayout_yolo.
-    },
-    "formula-config": {
-        "mfd_model": "yolo_v8_mfd",
-        "mfr_model": "unimernet_small",
-        "enable": true  // The formula recognition feature is enabled by default. If you need to disable it, please change the value here to "false".
-    },
-    "table-config": {
-        "model": "rapid_table",  // Default to using "rapid_table", can be switched to "tablemaster" or "struct_eqtable".
-        "enable": false, // The table recognition feature is disabled by default. If you need to enable it, please change the value here to "true".
-        "max_time": 400
-    }
-}
-```
-
-## Usage
-
-### API
-
-Processing files from local disk
-
-```python
-image_writer = DiskReaderWriter(local_image_dir)
-image_dir = str(os.path.basename(local_image_dir))
-jso_useful_key = {"_pdf_type": "", "model_list": []}
-pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
-pipe.pipe_classify()
-pipe.pipe_analyze()
-pipe.pipe_parse()
-md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
-```
-
-Processing files from object storage
-
-```python
-s3pdf_cli = S3ReaderWriter(pdf_ak, pdf_sk, pdf_endpoint)
-image_dir = "s3://img_bucket/"
-s3image_cli = S3ReaderWriter(img_ak, img_sk, img_endpoint, parent_path=image_dir)
-pdf_bytes = s3pdf_cli.read(s3_pdf_path, mode=s3pdf_cli.MODE_BIN)
-jso_useful_key = {"_pdf_type": "", "model_list": []}
-pipe = UNIPipe(pdf_bytes, jso_useful_key, s3image_cli)
-pipe.pipe_classify()
-pipe.pipe_analyze()
-pipe.pipe_parse()
-md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
-```
-
-For detailed implementation, refer to:
-
-- [demo.py Simplest Processing Method](demo/demo.py)
-- [magic_pdf_parse_main.py More Detailed Processing Workflow](demo/magic_pdf_parse_main.py)
-
-### Deploy Derived Projects
-
-Derived projects include secondary development projects based on MinerU by project developers and community developers,  
-such as application interfaces based on Gradio, RAG based on llama, web demos similar to the official website, lightweight multi-GPU load balancing client/server ends, etc.
-These projects may offer more features and a better user experience.  
-For specific deployment methods, please refer to the [Derived Project README](projects/README.md)
-
-
-### Development Guide
-
-TODO
-
-# TODO
-
-- [x] Reading order based on the model  
-- [x] Recognition of `index` and `list` in the main text  
-- [x] Table recognition
-- [ ] Code block recognition in the main text
-- [ ] [Chemical formula recognition](docs/chemical_knowledge_introduction/introduction.pdf)
-- [ ] Geometric shape recognition
-
-# All Thanks To Our Contributors
-
-<a href="https://github.com/opendatalab/MinerU/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
-</a>
-
-# License Information
-
-[LICENSE.md](LICENSE.md)
-
-This project currently uses PyMuPDF to achieve advanced functionality. However, since it adheres to the AGPL license, it may impose restrictions on certain usage scenarios. In future iterations, we plan to explore and replace it with a more permissive PDF processing library to enhance user-friendliness and flexibility.
-
-# Acknowledgments
-
-- [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
-- [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
-- [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
-- [RapidTable](https://github.com/RapidAI/RapidTable)
-- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
-- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
-- [layoutreader](https://github.com/ppaanngggg/layoutreader)
-- [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
-- [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
-
-# Citation
-
-```bibtex
-@misc{wang2024mineruopensourcesolutionprecise,
-      title={MinerU: An Open-Source Solution for Precise Document Content Extraction}, 
-      author={Bin Wang and Chao Xu and Xiaomeng Zhao and Linke Ouyang and Fan Wu and Zhiyuan Zhao and Rui Xu and Kaiwen Liu and Yuan Qu and Fukai Shang and Bo Zhang and Liqun Wei and Zhihao Sui and Wei Li and Botian Shi and Yu Qiao and Dahua Lin and Conghui He},
-      year={2024},
-      eprint={2409.18839},
-      archivePrefix={arXiv},
-      primaryClass={cs.CV},
-      url={https://arxiv.org/abs/2409.18839}, 
-}
-
-@article{he2024opendatalab,
-  title={Opendatalab: Empowering general artificial intelligence with open datasets},
-  author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
-  journal={arXiv preprint arXiv:2407.13773},
-  year={2024}
-}
-```
-
-# Star History
-
-<a>
- <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date&theme=dark" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
- </picture>
-</a>
-
-# Magic-doc
-
-[Magic-Doc](https://github.com/InternLM/magic-doc) Fast speed ppt/pptx/doc/docx/pdf extraction tool
-
-# Magic-html
-
-[Magic-HTML](https://github.com/opendatalab/magic-html) Mixed web page extraction tool
-
-# Links
-
-- [LabelU (A Lightweight Multi-modal Data Annotation Tool)](https://github.com/opendatalab/labelU)
-- [LabelLLM (An Open-source LLM Dialogue Annotation Platform)](https://github.com/opendatalab/LabelLLM)
-- [PDF-Extract-Kit (A Comprehensive Toolkit for High-Quality PDF Content Extraction)](https://github.com/opendatalab/PDF-Extract-Kit)

next_docs/README_zh-CN.md

-<div align="center" xmlns="http://www.w3.org/1999/html">
-<!-- logo -->
-<p align="center">
-  <img src="docs/images/MinerU-logo.png" width="300px" style="vertical-align:middle;">
-</p>
-
-<!-- icon -->
-
-[![stars](https://img.shields.io/github/stars/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
-[![forks](https://img.shields.io/github/forks/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
-[![open issues](https://img.shields.io/github/issues-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
-[![issue resolution](https://img.shields.io/github/issues-closed-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
-[![PyPI version](https://badge.fury.io/py/magic-pdf.svg)](https://badge.fury.io/py/magic-pdf)
-[![Downloads](https://static.pepy.tech/badge/magic-pdf)](https://pepy.tech/project/magic-pdf)
-[![Downloads](https://static.pepy.tech/badge/magic-pdf/month)](https://pepy.tech/project/magic-pdf)
-
-[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iMzAiIGhlaWdodD0iMzAiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgZmlsbD0ibm9uZSI+CiA8ZGVmcz4KICA8bGluZWFyR3JhZGllbnQgeTI9IjAuNTMzNjciIHgyPSIxLjAwMDQiIHkxPSIwLjI5MjE5IiB4MT0iLTAuMTEyNjgiIGlkPSJhIj4KICAgPHN0b3Agc3RvcC1jb2xvcj0iIzE1NDNGRSIvPgogICA8c3RvcCBzdG9wLWNvbG9yPSIjOEM0NkZGIiBvZmZzZXQ9IjEiLz4KICA8L2xpbmVhckdyYWRpZW50PgogIDxsaW5lYXJHcmFkaWVudCB5Mj0iMC41OTc1NyIgeDI9IjEuMDExMzciIHkxPSIwLjExMDIzIiB4MT0iLTAuMDg0NzQiIGlkPSJiIj4KICAgPHN0b3Agc3RvcC1jb2xvcj0iIzE1NDNGRSIvPgogICA8c3RvcCBzdG9wLWNvbG9yPSIjOEM0NkZGIiBvZmZzZXQ9IjEiLz4KICA8L2xpbmVhckdyYWRpZW50PgogPC9kZWZzPgogPGc+CiAgPHRpdGxlPkxheWVyIDE8L3RpdGxlPgogIDxwYXRoIGlkPSJzdmdfMSIgZmlsbD0idXJsKCNhKSIgZD0ibTEuNjIzLDEyLjA2N2EwLjQ4NCwwLjQ4NCAwIDAgMSAwLjA3LC0wLjM4NGw1LjMxLC03Ljg5NWMwLjA2OCwtMC4xIDAuMTcsLTAuMTcyIDAuMjg4LC0wLjJsMTQuMzc3LC0zLjQ3NGEwLjQ4NCwwLjQ4NCAwIDAgMSAwLjU4NCwwLjM1N2wzLjY2MiwxNS4xNTJjMS40NzcsNi4xMTQgLTIuMjgxLDEyLjI2NyAtOC4zOTQsMTMuNzQ1Yy02LjExNCwxLjQ3NyAtMTIuMjY3LC0yLjI4MSAtMTMuNzQ1LC04LjM5NWwtMi4xNTIsLTguOTA2eiIgb3BhY2l0eT0iMC40Ii8+CiAgPHBhdGggaWQ9InN2Z18yIiBmaWxsPSJ1cmwoI2IpIiBkPSJtNS44MjYsOC42NzNjMCwtMC4xMzYgMC4wNTcsLTAuMjY2IDAuMTU3LC0wLjM1OGw3LjAxNywtNi40MjVhMC40ODQsMC40ODQgMCAwIDEgMC4zMjcsLTAuMTI3bDE0Ljc5LDBjMC4yNjgsMCAwLjQ4NSwwLjIxNiAwLjQ4NSwwLjQ4NGwwLDE1LjU4OWMwLDYuMjkgLTUuMDk5LDExLjM4OCAtMTEuMzg4LDExLjM4OGMtNi4yOSwwIC0xMS4zODgsLTUuMDk5IC0xMS4zODgsLTExLjM4OGwwLC05LjE2M3oiLz4KICA8cGF0aCBpZD0ic3ZnXzMiIGZpbGw9IiM1RDc2RkYiIGQ9Im0xMi4zMzEsOC43NTNsLTYuMzgzLC0wLjM5OGw3LjEyMiwtNi41MmwwLjI5OSw1Ljg5MmEwLjk3OCwwLjk3OCAwIDAgMSAtMS4wMzgsMS4wMjZ6Ii8+CiAgPHBhdGggaWQ9InN2Z180IiBmaWxsPSIjMDAyOEZEIiBkPSJtMjAuNDE2LDE1LjAyMmwwLDEuNzExYTIuNDA0LDIuNDA0IDAgMCAxIC00LjgwOCwwbDAsLTQuMjc4bC0yLjgxLDBsMCw0LjY4NmE1LjIxNSw1LjIxNSAwIDEgMCAxMC40MywwbDAsLTQuNjg2bDAsMi41NjdsLTIuODEyLDB6IiBjbGlwLXJ1bGU9ImV2ZW5vZGQiIGZpbGwtcnVsZT0iZXZlbm9kZCIvPgogIDxwYXRoIGlkPSJzdmdfNSIgZmlsbD0iIzAwMjhGRCIgZD0ibTIzLjIyOCwxMy44ODFsMS4xNCwwbDAsMS4xNDFsLTEuMTQsMGwwLC0xLjE0bDAsLTAuMDAxem0tMi44MTIsLTAuNjkybDEuODM0LDBsMCwxLjgzM2wtMS44MzQsMGwwLC0xLjgzMmwwLC0wLjAwMXptMS44MzQsLTAuOTc5bDAuOTc4LDBsMCwwLjk3OWwtMC45NzgsMGwwLC0wLjk3OGwwLC0wLjAwMXptMS41NDgsLTEuNjI5bDAuNjExLDBsMCwwLjYxMWwtMC42MTEsMGwwLC0wLjYxMXoiLz4KICA8cGF0aCBpZD0ic3ZnXzYiIGZpbGw9IiNmZmYiIGQ9Im0yMC4wODYsMTQuOTEybDAsMS43MTFhMi40MDQsMi40MDQgMCAxIDEgLTQuODA3LDBsMCwtNC4yNzhsLTIuODEyLDBsMCw0LjY4NmE1LjIxNSw1LjIxNSAwIDAgMCAxMC40MywwbDAsLTQuNjg2bDAsMi41NjdsLTIuODEsMGwtMC4wMDEsMHoiIGNsaXAtcnVsZT0iZXZlbm9kZCIgZmlsbC1ydWxlPSJldmVub2RkIi8+CiAgPHBhdGggaWQ9InN2Z183IiBmaWxsPSIjZmZmIiBkPSJtMjIuODk4LDEzLjc3MWwxLjE0LDBsMCwxLjE0MWwtMS4xNCwwbDAsLTEuMTRsMCwtMC4wMDF6bS0yLjgxMiwtMC42OTJsMS44MzQsMGwwLDEuODMzbC0xLjgzNCwwbDAsLTEuODMybDAsLTAuMDAxem0xLjgzNCwtMC45NzlsMC45NzgsMGwwLDAuOTc5bC0wLjk3OCwwbDAsLTAuOTc5em0xLjU0OCwtMS42MjlsMC42MTEsMGwwLDAuNjExbC0wLjYxLDBsMCwtMC42MWwtMC4wMDEsLTAuMDAxeiIvPgogPC9nPgo8L3N2Zz4=&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
-[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
-[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
-[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/myhloli/3b3a00a4a0a61577b6c30f989092d20d/mineru_demo.ipynb)
-[![Paper](https://img.shields.io/badge/Paper-arXiv-green)](https://arxiv.org/abs/2409.18839)
-
-<a href="https://trendshift.io/repositories/11174" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11174" alt="opendatalab%2FMinerU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
-
-<!-- language -->
-
-[English](README.md) | [简体中文](README_zh-CN.md)
-
-<!-- hot link -->
-
-<p align="center">
-<a href="https://github.com/opendatalab/PDF-Extract-Kit">PDF-Extract-Kit: 高质量PDF解析工具箱</a>🔥🔥🔥
-</p>
-
-<!-- join us -->
-
-<p align="center">
-    👋 join us on <a href="https://discord.gg/Tdedn9GTXq" target="_blank">Discord</a> and <a href="https://cdn.vansin.top/internlm/mineru.jpg" target="_blank">WeChat</a>
-</p>
-
-<!-- read the docs -->
-<p align="center">
-    read more docs on <a href="https://mineru.readthedocs.io/zh-cn/latest/"> Read The Docs </a>
-</p>
-
-
-</div>
-
-# 更新记录
-
-- 2024/11/06 0.9.2发布，为表格识别功能接入了[StructTable-InternVL2-1B](https://huggingface.co/U4R/StructTable-InternVL2-1B)模型
-- 2024/10/31 0.9.0发布，这是我们进行了大量代码重构的全新版本，解决了众多问题，提升了性能，降低了硬件需求，并提供了更丰富的易用性：
-  - 重构排序模块代码，使用 [layoutreader](https://github.com/ppaanngggg/layoutreader) 进行阅读顺序排序，确保在各种排版下都能实现极高准确率
-  - 重构段落拼接模块，在跨栏、跨页、跨图、跨表情况下均能实现良好的段落拼接效果
-  - 重构列表和目录识别功能，极大提升列表块和目录块识别的准确率及对应文本段落的解析效果
-  - 重构图、表与描述性文本的匹配逻辑，大幅提升 caption 和 footnote 与图表的匹配准确率，并将描述性文本的丢失率降至接近0
-  - 增加 OCR 的多语言支持，支持 84 种语言的检测与识别，语言支持列表详见 [OCR 语言支持列表](https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5)
-  - 增加显存回收逻辑及其他显存优化措施，大幅降低显存使用需求。开启除表格加速外的全部加速功能(layout/公式/OCR)的显存需求从16GB降至8GB，开启全部加速功能的显存需求从24GB降至10GB
-  - 优化配置文件的功能开关，增加独立的公式检测开关，无需公式检测时可大幅提升速度和解析效果
-  - 集成 [PDF-Extract-Kit 1.0](https://github.com/opendatalab/PDF-Extract-Kit)
-    - 加入自研的 `doclayout_yolo` 模型，在相近解析效果情况下比原方案提速10倍以上，可通过配置文件与 `layoutlmv3` 自由切换
-    - 公式解析升级至 `unimernet 0.2.1`，在提升公式解析准确率的同时，大幅降低显存需求
-    - 因 `PDF-Extract-Kit 1.0` 更换仓库，需要重新下载模型，步骤详见 [如何下载模型](docs/how_to_download_models_zh_cn.md)
-- 2024/09/27 0.8.1发布，修复了一些bug，同时提供了[在线demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/)的[本地化部署版本](projects/web_demo/README_zh-CN.md)和[前端界面](projects/web/README_zh-CN.md)
-- 2024/09/09 0.8.0发布，支持Dockerfile快速部署，同时上线了huggingface、modelscope demo
-- 2024/08/30 0.7.1发布，集成了paddle tablemaster表格识别功能
-- 2024/08/09 0.7.0b1发布，简化安装步骤提升易用性，加入表格识别功能
-- 2024/08/01 0.6.2b1发布，优化了依赖冲突问题和安装文档
-- 2024/07/05 首次开源
-
-<!-- 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>
-            </ul>
-        </li>
-        <li><a href="#使用">使用方式</a>
-            <ul>
-            <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>
-
-# MinerU
-
-## 项目简介
-
-MinerU是一款将PDF转化为机器可读格式的工具（如markdown、json），可以很方便地抽取为任意格式。
-MinerU诞生于[书生-浦语](https://github.com/InternLM/InternLM)的预训练过程中，我们将会集中精力解决科技文献中的符号转化问题，希望在大模型时代为科技发展做出贡献。
-相比国内外知名商用产品MinerU还很年轻，如果遇到问题或者结果不及预期请到[issue](https://github.com/opendatalab/MinerU/issues)提交问题，同时**附上相关PDF**。
-
-https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
-
-
-## 快速开始
-
-有多种不同方式可以体验MinerU的效果：
-
-- [在线体验(无需任何安装)](#在线体验)
-- [使用CPU快速体验（Windows，Linux，Mac）](#使用cpu快速体验)
-
-### 在线体验
-稳定版(经过QA验证的稳定版本)：
-
-[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
-
-测试版(同步dev分支更新，测试新特性)：
-
-[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
-[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
-
-### 使用CPU快速体验
-
-#### 1. 安装magic-pdf
-
-> [!NOTE]
-> 最新版本国内镜像源同步可能会有延迟，请耐心等待
-
-```bash
-conda create -n MinerU python=3.10
-conda activate MinerU
-pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i https://mirrors.aliyun.com/pypi/simple
-```
-
-#### 2. 下载模型权重文件
-
-详细参考 [如何下载模型文件](docs/how_to_download_models_zh_cn.md)
-
-#### 3. 修改配置文件以进行额外配置
-
-完成[2. 下载模型权重文件](#2-下载模型权重文件)步骤后，脚本会自动生成用户目录下的magic-pdf.json文件，并自动配置默认模型路径。
-您可在【用户目录】下找到magic-pdf.json文件。
-
-> [!TIP]
-> windows的用户目录为 "C:\\Users\\用户名", linux用户目录为 "/home/用户名", macOS用户目录为 "/Users/用户名"
-
-您可修改该文件中的部分配置实现功能的开关，如表格识别功能：
-
-> [!NOTE]
->如json内没有如下项目，请手动添加需要的项目，并删除注释内容（标准json不支持注释）
-
-```json
-{
-    // other config
-    "layout-config": {
-        "model": "layoutlmv3" // 使用doclayout_yolo请修改为“doclayout_yolo"
-    },
-    "formula-config": {
-        "mfd_model": "yolo_v8_mfd",
-        "mfr_model": "unimernet_small",
-        "enable": true  // 公式识别功能默认是开启的，如果需要关闭请修改此处的值为"false"
-    },
-    "table-config": {
-        "model": "rapid_table",  // 默认使用"rapid_table",可以切换为"tablemaster"和"struct_eqtable"
-        "enable": false, // 表格识别功能默认是关闭的，如果需要开启请修改此处的值为"true"
-        "max_time": 400
-    }
-}
-```
-
-
-## 使用
-
-### API
-
-处理本地磁盘上的文件
-
-```python
-image_writer = DiskReaderWriter(local_image_dir)
-image_dir = str(os.path.basename(local_image_dir))
-jso_useful_key = {"_pdf_type": "", "model_list": []}
-pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
-pipe.pipe_classify()
-pipe.pipe_analyze()
-pipe.pipe_parse()
-md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
-```
-
-处理对象存储上的文件
-
-```python
-s3pdf_cli = S3ReaderWriter(pdf_ak, pdf_sk, pdf_endpoint)
-image_dir = "s3://img_bucket/"
-s3image_cli = S3ReaderWriter(img_ak, img_sk, img_endpoint, parent_path=image_dir)
-pdf_bytes = s3pdf_cli.read(s3_pdf_path, mode=s3pdf_cli.MODE_BIN)
-jso_useful_key = {"_pdf_type": "", "model_list": []}
-pipe = UNIPipe(pdf_bytes, jso_useful_key, s3image_cli)
-pipe.pipe_classify()
-pipe.pipe_analyze()
-pipe.pipe_parse()
-md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
-```
-
-详细实现可参考
-
-- [demo.py 最简单的处理方式](demo/demo.py)
-- [magic_pdf_parse_main.py 能够更清晰看到处理流程](demo/magic_pdf_parse_main.py)
-
-### 部署衍生项目
-
-衍生项目包含项目开发者和社群开发者们基于MinerU的二次开发项目，
-例如基于Gradio的应用界面、基于llama的RAG、官网同款web demo、轻量级的多卡负载均衡c/s端等，
-这些项目可能会提供更多的功能和更好的用户体验。
-具体部署方式请参考 [衍生项目readme](projects/README_zh-CN.md)
-
-
-### 二次开发
-
-TODO
-
-# TODO
-
-- [x] 基于模型的阅读顺序  
-- [x] 正文中目录、列表识别  
-- [x] 表格识别
-- [ ] 正文中代码块识别
-- [ ] [化学式识别](docs/chemical_knowledge_introduction/introduction.pdf)
-- [ ] 几何图形识别
-
-
-# All Thanks To Our Contributors
-
-<a href="https://github.com/opendatalab/MinerU/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
-</a>
-
-# License Information
-
-[LICENSE.md](LICENSE.md)
-
-本项目目前采用PyMuPDF以实现高级功能，但因其遵循AGPL协议，可能对某些使用场景构成限制。未来版本迭代中，我们计划探索并替换为许可条款更为宽松的PDF处理库，以提升用户友好度及灵活性。
-
-# Acknowledgments
-
-- [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
-- [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
-- [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
-- [RapidTable](https://github.com/RapidAI/RapidTable)
-- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
-- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
-- [layoutreader](https://github.com/ppaanngggg/layoutreader)
-- [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
-- [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
-
-# Citation
-
-```bibtex
-@misc{wang2024mineruopensourcesolutionprecise,
-      title={MinerU: An Open-Source Solution for Precise Document Content Extraction}, 
-      author={Bin Wang and Chao Xu and Xiaomeng Zhao and Linke Ouyang and Fan Wu and Zhiyuan Zhao and Rui Xu and Kaiwen Liu and Yuan Qu and Fukai Shang and Bo Zhang and Liqun Wei and Zhihao Sui and Wei Li and Botian Shi and Yu Qiao and Dahua Lin and Conghui He},
-      year={2024},
-      eprint={2409.18839},
-      archivePrefix={arXiv},
-      primaryClass={cs.CV},
-      url={https://arxiv.org/abs/2409.18839}, 
-}
-
-@article{he2024opendatalab,
-  title={Opendatalab: Empowering general artificial intelligence with open datasets},
-  author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
-  journal={arXiv preprint arXiv:2407.13773},
-  year={2024}
-}
-```
-
-# Star History
-
-<a>
- <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date&theme=dark" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
- </picture>
-</a>
-
-# Magic-doc
-
-[Magic-Doc](https://github.com/InternLM/magic-doc) Fast speed ppt/pptx/doc/docx/pdf extraction tool
-
-# Magic-html
-
-[Magic-HTML](https://github.com/opendatalab/magic-html) Mixed web page extraction tool
-
-# Links
-
-- [LabelU (A Lightweight Multi-modal Data Annotation Tool)](https://github.com/opendatalab/labelU)
-- [LabelLLM (An Open-source LLM Dialogue Annotation Platform)](https://github.com/opendatalab/LabelLLM)
-- [PDF-Extract-Kit (A Comprehensive Toolkit for High-Quality PDF Content Extraction)](https://github.com/opendatalab/PDF-Extract-Kit)

next_docs/en/user_guide/data/read_api.rst

@@ -83,7 +83,24 @@ Read images from path or directory
     datasets = read_local_images("tt.png")  # replace with real file path
 
     # read files from directory that endswith suffix in suffixes array 
-    datasets = read_local_images("images/", suffixes=["png", "jpg"])  # replace with real directory 
+    datasets = read_local_images("images/", suffixes=[".png", ".jpg"])  # replace with real directory 
+
+
+read_local_office
+^^^^^^^^^^^^^^^^^^^^
+Read MS-Office files from path or directory
+
+.. code:: python 
+
+    from magic_pdf.data.read_api import *
+
+    # read from image path 
+    datasets = read_local_office("tt.doc")  # replace with real file path
+
+    # read files from directory that endswith suffix in suffixes array 
+    datasets = read_local_office("docs/")  # replace with real directory 
+
+
 
 
 Check :doc:`../../api/read_api` for more details
\ No newline at end of file

next_docs/en/user_guide/install/config.rst

@@ -5,6 +5,14 @@ Config
 
 File **magic-pdf.json** is typically located in the **${HOME}** directory under a Linux system or in the **C:\Users\{username}** directory under a Windows system.
 
+.. admonition:: Tip 
+    :class: tip
+
+    You can override the default location of config file via the following command:
+    
+    export MINERU_TOOLS_CONFIG_JSON=new_magic_pdf.json
+
+
 
 magic-pdf.json
 ----------------

next_docs/en/user_guide/quick_start/convert_doc.rst

@@ -7,7 +7,7 @@ Convert Doc
     :class: tip
 
     When processing MS-Office files, we first use third-party software to convert the MS-Office files to PDF.
-    
+
     For certain MS-Office files, the quality of the converted PDF files may not be very high, which can affect the quality of the final output.
 
 
@@ -15,15 +15,15 @@ Convert Doc
 Command Line
 ^^^^^^^^^^^^^
 
-.. code:: python 
+.. code:: python
 
     # make sure the file have correct suffix
     magic-pdf -p a.doc -o output -m auto
 
 
-API 
+API
 ^^^^^^^^
-.. code:: python 
+.. code:: python
 
     import os
 
@@ -44,13 +44,16 @@ API
     # proc
     ## Create Dataset Instance
     input_file = "some_doc.doc"     # replace with real ms-office file
-    
+
     input_file_name = input_file.split(".")[0]
     ds = read_local_office(input_file)[0]
 
+    # ocr mode
     ds.apply(doc_analyze, ocr=True).pipe_ocr_mode(image_writer).dump_md(
         md_writer, f"{input_file_name}.md", image_dir
     )
 
-
-
+    # txt mode
+    ds.apply(doc_analyze, ocr=True).pipe_txt_mode(image_writer).dump_md(
+        md_writer, f"{input_file_name}.md", image_dir
+    )

next_docs/en/user_guide/quick_start/convert_docx.rst

@@ -6,23 +6,23 @@ Convert DocX
     :class: tip
 
     When processing MS-Office files, we first use third-party software to convert the MS-Office files to PDF.
-    
+
     For certain MS-Office files, the quality of the converted PDF files may not be very high, which can affect the quality of the final output.
 
 
 Command Line
 ^^^^^^^^^^^^^
 
-.. code:: python 
+.. code:: python
 
     # make sure the file have correct suffix
     magic-pdf -p a.docx -o output -m auto
 
 
-API 
+API
 ^^^^^
 
-.. code:: python 
+.. code:: python
 
     import os
 
@@ -43,11 +43,16 @@ API
     # proc
     ## Create Dataset Instance
     input_file = "some_docx.docx"     # replace with real ms-office file
-    
+
     input_file_name = input_file.split(".")[0]
     ds = read_local_office(input_file)[0]
 
+    # ocr mode
     ds.apply(doc_analyze, ocr=True).pipe_ocr_mode(image_writer).dump_md(
         md_writer, f"{input_file_name}.md", image_dir
     )
 
+    # txt mode
+    ds.apply(doc_analyze, ocr=True).pipe_txt_mode(image_writer).dump_md(
+        md_writer, f"{input_file_name}.md", image_dir
+    )

next_docs/en/user_guide/quick_start/convert_image.rst

@@ -7,13 +7,13 @@ Convert Image
 Command Line
 ^^^^^^^^^^^^^
 
-.. code:: python 
+.. code:: python
 
     # make sure the file have correct suffix
     magic-pdf -p a.png -o output -m auto
 
 
-API 
+API
 ^^^^^^
 
 .. code:: python
@@ -41,6 +41,12 @@ API
     input_file_name = input_file.split(".")[0]
     ds = read_local_images(input_file)[0]
 
+    # ocr mode
     ds.apply(doc_analyze, ocr=True).pipe_ocr_mode(image_writer).dump_md(
         md_writer, f"{input_file_name}.md", image_dir
     )
+
+    # txt mode
+    ds.apply(doc_analyze, ocr=True).pipe_txt_mode(image_writer).dump_md(
+        md_writer, f"{input_file_name}.md", image_dir
+    )

next_docs/en/user_guide/quick_start/convert_pdf.rst

 
 
-Convert PDF 
+Convert PDF
 ============
 
 Command Line
 ^^^^^^^^^^^^^
 
-.. code:: python 
+.. code:: python
 
     # make sure the file have correct suffix
     magic-pdf -p a.pdf -o output -m auto
@@ -44,6 +44,12 @@ API
     ## Create Dataset Instance
     ds = PymuDocDataset(pdf_bytes)
 
-    ds.apply(doc_analyze, ocr=True).pipe_ocr_mode(image_writer).dump_md(md_writer, f"{name_without_suff}.md", image_dir)
-
+    # ocr mode
+    ds.apply(doc_analyze, ocr=True).pipe_ocr_mode(image_writer).dump_md(
+        md_writer, f"{name_without_suff}.md", image_dir
+    )
 
+    # txt mode
+    ds.apply(doc_analyze, ocr=True).pipe_txt_mode(image_writer).dump_md(
+        md_writer, f"{name_without_suff}.md", image_dir
+    )

next_docs/en/user_guide/quick_start/convert_ppt.rst

 
 
-Convert PPT 
+Convert PPT
 ============
 
 .. admonition:: Warning
     :class: tip
 
     When processing MS-Office files, we first use third-party software to convert the MS-Office files to PDF.
-    
+
     For certain MS-Office files, the quality of the converted PDF files may not be very high, which can affect the quality of the final output.
 
 Command Line
 ^^^^^^^^^^^^^
 
-.. code:: python 
+.. code:: python
 
     # make sure the file have correct suffix
     magic-pdf -p a.ppt -o output -m auto
 
 
-API 
+API
 ^^^^^
 
-.. code:: python 
+.. code:: python
 
     import os
 
@@ -43,10 +43,16 @@ API
     # proc
     ## Create Dataset Instance
     input_file = "some_ppt.ppt"     # replace with real ms-office file
-    
+
     input_file_name = input_file.split(".")[0]
     ds = read_local_office(input_file)[0]
 
+    # ocr mode
     ds.apply(doc_analyze, ocr=True).pipe_ocr_mode(image_writer).dump_md(
         md_writer, f"{input_file_name}.md", image_dir
     )
+
+    # txt mode
+    ds.apply(doc_analyze, ocr=True).pipe_txt_mode(image_writer).dump_md(
+        md_writer, f"{input_file_name}.md", image_dir
+    )

next_docs/en/user_guide/quick_start/convert_pptx.rst

@@ -7,14 +7,14 @@ Convert PPTX
     :class: tip
 
     When processing MS-Office files, we first use third-party software to convert the MS-Office files to PDF.
-    
+
     For certain MS-Office files, the quality of the converted PDF files may not be very high, which can affect the quality of the final output.
 
 
 Command Line
 ^^^^^^^^^^^^^
 
-.. code:: python 
+.. code:: python
 
     # make sure the file have correct suffix
     magic-pdf -p a.pptx -o output -m auto
@@ -22,10 +22,10 @@ Command Line
 
 
 
-API 
+API
 ^^^^^^
 
-.. code:: python 
+.. code:: python
 
     import os
 
@@ -46,10 +46,16 @@ API
     # proc
     ## Create Dataset Instance
     input_file = "some_pptx.pptx"     # replace with real ms-office file
-    
+
     input_file_name = input_file.split(".")[0]
     ds = read_local_office(input_file)[0]
 
+    # ocr mode
     ds.apply(doc_analyze, ocr=True).pipe_ocr_mode(image_writer).dump_md(
         md_writer, f"{input_file_name}.md", image_dir
     )
+
+    # txt mode
+    ds.apply(doc_analyze, ocr=True).pipe_txt_mode(image_writer).dump_md(
+        md_writer, f"{input_file_name}.md", image_dir
+    )

next_docs/en/user_guide/usage/api.rst

 
-Api Usage 
+Api Usage
 ===========
 
 
@@ -16,6 +16,7 @@ Local File Example
     from magic_pdf.data.data_reader_writer import FileBasedDataWriter, FileBasedDataReader
     from magic_pdf.data.dataset import PymuDocDataset
     from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
+    from magic_pdf.config.enums import SupportedPdfParseMethod
 
     # args
     pdf_file_name = "abc.pdf"  # replace with the real pdf path
@@ -40,15 +41,22 @@ Local File Example
     ## Create Dataset Instance
     ds = PymuDocDataset(pdf_bytes)
 
-    ## inference 
-    infer_result = ds.apply(doc_analyze, ocr=True)
+    ## inference
+    if ds.classify() == SupportedPdfParseMethod.OCR:
+        infer_result = ds.apply(doc_analyze, ocr=True)
+
+        ## pipeline
+        pipe_result = infer_result.pipe_ocr_mode(image_writer)
+
+    else:
+        infer_result = ds.apply(doc_analyze, ocr=False)
+
+        ## pipeline
+        pipe_result = infer_result.pipe_txt_mode(image_writer)
 
     ### draw model result on each page
     infer_result.draw_model(os.path.join(local_md_dir, f"{name_without_suff}_model.pdf"))
 
-    ## pipeline
-    pipe_result = infer_result.pipe_ocr_mode(image_writer)
-
     ### draw layout result on each page
     pipe_result.draw_layout(os.path.join(local_md_dir, f"{name_without_suff}_layout.pdf"))
 
@@ -58,6 +66,9 @@ Local File Example
     ### dump markdown
     pipe_result.dump_md(md_writer, f"{name_without_suff}.md", image_dir)
 
+    ### dump content list
+    pipe_result.dump_content_list(md_writer, f"{name_without_suff}_content_list.json", image_dir)
+
 
 S3 File Example
 ^^^^^^^^^^^^^^^^
@@ -96,30 +107,39 @@ S3 File Example
     ## Create Dataset Instance
     ds = PymuDocDataset(pdf_bytes)
 
-    ## inference 
-    infer_result = ds.apply(doc_analyze, ocr=True)
+    ## inference
+    if ds.classify() == SupportedPdfParseMethod.OCR:
+        infer_result = ds.apply(doc_analyze, ocr=True)
 
-    ### draw model result on each page
-    infer_result.draw_model(os.path.join(local_dir, f'{name_without_suff}_model.pdf'))  # dump to local
+        ## pipeline
+        pipe_result = infer_result.pipe_ocr_mode(image_writer)
 
-    ## pipeline
-    pipe_result = infer_result.pipe_ocr_mode(image_writer)
+    else:
+        infer_result = ds.apply(doc_analyze, ocr=False)
+
+        ## pipeline
+        pipe_result = infer_result.pipe_txt_mode(image_writer)
+
+    ### draw model result on each page
+    infer_result.draw_model(os.path.join(local_md_dir, f"{name_without_suff}_model.pdf"))
 
     ### draw layout result on each page
-    pipe_result.draw_layout(os.path.join(local_dir, f'{name_without_suff}_layout.pdf'))  # dump to local
+    pipe_result.draw_layout(os.path.join(local_md_dir, f"{name_without_suff}_layout.pdf"))
 
     ### draw spans result on each page
-    pipe_result.draw_span(os.path.join(local_dir, f'{name_without_suff}_spans.pdf'))   # dump to local 
+    pipe_result.draw_span(os.path.join(local_md_dir, f"{name_without_suff}_spans.pdf"))
 
     ### dump markdown
-    pipe_result.dump_md(writer, f'{name_without_suff}.md', "unittest/tmp/images")    # dump to remote s3
+    pipe_result.dump_md(md_writer, f"{name_without_suff}.md", image_dir)
 
+    ### dump content list
+    pipe_result.dump_content_list(md_writer, f"{name_without_suff}_content_list.json", image_dir)
 
 
-MS-Office 
+MS-Office
 ----------
 
-.. code:: python 
+.. code:: python
 
     import os
 
@@ -144,7 +164,7 @@ MS-Office
     input_file_name = input_file.split(".")[0]
     ds = read_local_office(input_file)[0]
 
-    ds.apply(doc_analyze, ocr=True).pipe_ocr_mode(image_writer).dump_md(
+    ds.apply(doc_analyze, ocr=True).pipe_txt_mode(image_writer).dump_md(
         md_writer, f"{input_file_name}.md", image_dir
     )
 
@@ -154,7 +174,7 @@ This code snippet can be used to manipulate **ppt**, **pptx**, **doc**, **docx**
 Image
 ---------
 
-Single Image File 
+Single Image File
 ^^^^^^^^^^^^^^^^^^^
 
 .. code:: python
@@ -187,7 +207,7 @@ Single Image File
     )
 
 
-Directory That Contains Images 
+Directory That Contains Images
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 .. code:: python
@@ -213,7 +233,7 @@ Directory That Contains Images
     input_directory = "some_image_dir/"       # replace with real directory that contains images
 
 
-    dss = read_local_images(input_directory, suffixes=['.png', '.jpg'])[0]  
+    dss = read_local_images(input_directory, suffixes=['.png', '.jpg'])
 
     count = 0
     for ds in dss:

next_docs/requirements.txt

@@ -8,6 +8,7 @@ myst-parser
 Pillow==8.4.0
 pydantic>=2.7.2,<2.8.0
 PyMuPDF>=1.24.9
+pdfminer.six==20231228
 sphinx
 sphinx-argparse>=0.5.2
 sphinx-book-theme>=1.1.3

projects/web_api/app.py

@@ -9,10 +9,11 @@ from fastapi.responses import JSONResponse
 from loguru import logger
 
 import magic_pdf.model as model_config
+from magic_pdf.config.enums import SupportedPdfParseMethod
 from magic_pdf.data.data_reader_writer import FileBasedDataWriter
-from magic_pdf.pipe.OCRPipe import OCRPipe
-from magic_pdf.pipe.TXTPipe import TXTPipe
-from magic_pdf.pipe.UNIPipe import UNIPipe
+from magic_pdf.data.dataset import PymuDocDataset
+from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
+from magic_pdf.model.operators import InferenceResult
 
 model_config.__use_inside_model__ = True
 
@@ -20,14 +21,15 @@ app = FastAPI()
 
 
 def json_md_dump(
-    pipe,
+    model_json,
+    middle_json,
     md_writer,
     pdf_name,
     content_list,
     md_content,
 ):
     # Write model results to model.json
-    orig_model_list = copy.deepcopy(pipe.model_list)
+    orig_model_list = copy.deepcopy(model_json)
     md_writer.write_string(
         f'{pdf_name}_model.json',
         json.dumps(orig_model_list, ensure_ascii=False, indent=4),
@@ -36,7 +38,7 @@ def json_md_dump(
     # Write intermediate results to middle.json
     md_writer.write_string(
         f'{pdf_name}_middle.json',
-        json.dumps(pipe.pdf_mid_data, ensure_ascii=False, indent=4),
+        json.dumps(middle_json, ensure_ascii=False, indent=4),
     )
 
     # Write text content results to content_list.json
@@ -100,45 +102,49 @@ async def pdf_parse_main(
             output_image_path
         ), FileBasedDataWriter(output_path)
 
+        ds = PymuDocDataset(pdf_bytes)
         # Choose parsing method
         if parse_method == 'auto':
-            jso_useful_key = {'_pdf_type': '', 'model_list': model_json}
-            pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
-        elif parse_method == 'txt':
-            pipe = TXTPipe(pdf_bytes, model_json, image_writer)
-        elif parse_method == 'ocr':
-            pipe = OCRPipe(pdf_bytes, model_json, image_writer)
-        else:
+            if ds.classify() == SupportedPdfParseMethod.OCR:
+                parse_method = 'ocr'
+            else:
+                parse_method = 'txt'
+
+        if parse_method not in ['txt', 'ocr']:
             logger.error('Unknown parse method, only auto, ocr, txt allowed')
             return JSONResponse(
                 content={'error': 'Invalid parse method'}, status_code=400
             )
 
-        # Execute classification
-        pipe.pipe_classify()
-
-        # If no model data is provided, use built-in model for parsing
-        if not model_json:
-            if model_config.__use_inside_model__:
-                pipe.pipe_analyze()  # Parse
+        if len(model_json) == 0:
+            if parse_method == 'ocr':
+                infer_result = ds.apply(doc_analyze, ocr=True)
             else:
+                infer_result = ds.apply(doc_analyze, ocr=False)
+
+        else:
+            infer_result = InferenceResult(model_json, ds)
+
+        if len(model_json) == 0 and not model_config.__use_inside_model__:
                 logger.error('Need model list input')
                 return JSONResponse(
                     content={'error': 'Model list input required'}, status_code=400
                 )
+        if parse_method == 'ocr':
+            pipe_res = infer_result.pipe_ocr_mode(image_writer)
+        else:
+            pipe_res = infer_result.pipe_txt_mode(image_writer)
 
-        # Execute parsing
-        pipe.pipe_parse()
 
         # Save results in text and md format
-        content_list = pipe.pipe_mk_uni_format(image_path_parent, drop_mode='none')
-        md_content = pipe.pipe_mk_markdown(image_path_parent, drop_mode='none')
+        content_list = pipe_res.get_content_list(image_path_parent, drop_mode='none')
+        md_content = pipe_res.get_markdown(image_path_parent, drop_mode='none')
 
         if is_json_md_dump:
-            json_md_dump(pipe, md_writer, pdf_name, content_list, md_content)
+            json_md_dump(infer_result._infer_res, pipe_res._pipe_res, md_writer, pdf_name, content_list, md_content)
         data = {
-            'layout': copy.deepcopy(pipe.model_list),
-            'info': pipe.pdf_mid_data,
+            'layout': copy.deepcopy(infer_result._infer_res),
+            'info': pipe_res._pipe_res,
             'content_list': content_list,
             'md_content': md_content,
         }

projects/web_demo/web_demo/api/analysis/pdf_ext.py

@@ -11,9 +11,12 @@ from flask import current_app, url_for
 from loguru import logger
 
 import magic_pdf.model as model_config
+from magic_pdf.config.enums import SupportedPdfParseMethod
 from magic_pdf.data.data_reader_writer import FileBasedDataWriter
+from magic_pdf.data.dataset import PymuDocDataset
 from magic_pdf.libs.json_compressor import JsonCompressor
-from magic_pdf.pipe.UNIPipe import UNIPipe
+from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
+from magic_pdf.model.operators import InferenceResult
 
 from ..extentions import app, db
 from .ext import find_file
@@ -25,25 +28,28 @@ model_config.__use_inside_model__ = True
 def analysis_pdf(image_url_prefix, image_dir, pdf_bytes, is_ocr=False):
     try:
         model_json = []  # model_json传空list使用内置模型解析
+        image_writer = FileBasedDataWriter(image_dir)
         logger.info(f'is_ocr: {is_ocr}')
+        parse_method = 'ocr'
+        ds = PymuDocDataset(pdf_bytes)
+        # Choose parsing method
         if not is_ocr:
-            jso_useful_key = {'_pdf_type': '', 'model_list': model_json}
-            image_writer = FileBasedDataWriter(image_dir)
-            pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer, is_debug=True)
-            pipe.pipe_classify()
-        else:
-            jso_useful_key = {'_pdf_type': 'ocr', 'model_list': model_json}
-            image_writer = FileBasedDataWriter(image_dir)
-            pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer, is_debug=True)
-        """如果没有传入有效的模型数据，则使用内置model解析"""
-        if len(model_json) == 0:
-            if model_config.__use_inside_model__:
-                pipe.pipe_analyze()
+            if ds.classify() == SupportedPdfParseMethod.OCR:
+                parse_method = 'ocr'
             else:
-                logger.error('need model list input')
-                exit(1)
-        pipe.pipe_parse()
-        pdf_mid_data = JsonCompressor.decompress_json(pipe.get_compress_pdf_mid_data())
+                parse_method = 'txt'
+
+        if parse_method == 'ocr':
+            infer_result = ds.apply(doc_analyze, ocr=True)
+        else:
+            infer_result = ds.apply(doc_analyze, ocr=False)
+
+        if parse_method == 'ocr':
+            pipe_res = infer_result.pipe_ocr_mode(image_writer)
+        else:
+            pipe_res = infer_result.pipe_txt_mode(image_writer)
+
+        pdf_mid_data = pipe_res._pipe_res
         pdf_info_list = pdf_mid_data['pdf_info']
         md_content = json.dumps(ocr_mk_mm_markdown_with_para_and_pagination(pdf_info_list, image_url_prefix),
                                 ensure_ascii=False)
@@ -52,7 +58,6 @@ def analysis_pdf(image_url_prefix, image_dir, pdf_bytes, is_ocr=False):
     except Exception as e:  # noqa: F841
         logger.error(traceback.format_exc())
 
-
 def get_bbox_info(data):
     bbox_info = []
     for page in data: