Merge branch 'dev' into dev-table-model-update

next_docs/en/api/dataset.rst

+Dataset Api
+------------------
+
+.. autoclass:: magic_pdf.data.dataset.PageableData
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.dataset.Dataset
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.dataset.ImageDataset
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.dataset.PymuDocDataset
+   :members:
+   :inherited-members:
+
+.. autoclass:: magic_pdf.data.dataset.Doc
+   :members:
+   :inherited-members:

next_docs/en/api/read_api.rst

+read_api Api
+------------------
+
+.. automodule:: magic_pdf.data.read_api
+   :members:
+   :inherited-members:

next_docs/en/api/utils.rst

+

docs/en/index.rst → next_docs/en/index.rst

@@ -24,3 +24,15 @@ Welcome to the MinerU Documentation
    <a class="github-button" href="https://github.com/opendatalab/MinerU/subscription" data-icon="octicon-eye" data-size="large" aria-label="Watch">Watch</a>
    <a class="github-button" href="https://github.com/opendatalab/MinerU/fork" data-icon="octicon-repo-forked" data-size="large" aria-label="Fork">Fork</a>
    </p>
+
+
+API Reference
+-------------
+
+If you are looking for information on a specific function, class or
+method, this part of the documentation is for you.
+
+.. toctree::
+   :maxdepth: 2
+
+   api

docs/requirements.txt → next_docs/requirements.txt

+boto3>=1.28.43
+loguru>=0.6.0
 myst-parser
+Pillow==8.4.0
+pydantic>=2.7.2,<2.8.0
+PyMuPDF>=1.24.9
 sphinx
 sphinx-argparse
 sphinx-book-theme

projects/README.md

@@ -6,5 +6,4 @@
 - [gradio_app](./gradio_app/README.md): Build a web app based on gradio
 - [web_demo](./web_demo/README.md): MinerU online [demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/) localized deployment version
 - [web_api](./web_api/README.md): Web API Based on FastAPI
-
-
+- [multi_gpu](./multi_gpu/README.md): Multi-GPU parallel processing based on LitServe

projects/README_zh-CN.md

@@ -6,4 +6,4 @@
 - [gradio_app](./gradio_app/README_zh-CN.md): 基于 Gradio 的 Web 应用
 - [web_demo](./web_demo/README_zh-CN.md): MinerU在线[demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/)本地化部署版本
 - [web_api](./web_api/README.md): 基于 FastAPI 的 Web API
-
+- [multi_gpu](./multi_gpu/README.md): 基于 LitServe 的多 GPU 并行处理

projects/gradio_app/app.py

@@ -3,10 +3,12 @@
 import base64
 import os
 import time
+import uuid
 import zipfile
 from pathlib import Path
 import re
 
+import pymupdf
 from loguru import logger
 
 from magic_pdf.libs.hash_utils import compute_sha256
@@ -23,7 +25,7 @@ def read_fn(path):
     return disk_rw.read(os.path.basename(path), AbsReaderWriter.MODE_BIN)
 
 
-def parse_pdf(doc_path, output_dir, end_page_id, is_ocr):
+def parse_pdf(doc_path, output_dir, end_page_id, is_ocr, layout_mode, formula_enable, table_enable, language):
     os.makedirs(output_dir, exist_ok=True)
 
     try:
@@ -42,6 +44,10 @@ def parse_pdf(doc_path, output_dir, end_page_id, is_ocr):
             parse_method,
             False,
             end_page_id=end_page_id,
+            layout_model=layout_mode,
+            formula_enable=formula_enable,
+            table_enable=table_enable,
+            lang=language,
         )
         return local_md_dir, file_name
     except Exception as e:
@@ -93,9 +99,10 @@ def replace_image_with_base64(markdown_text, image_dir_path):
     return re.sub(pattern, replace, markdown_text)
 
 
-def to_markdown(file_path, end_pages, is_ocr):
+def to_markdown(file_path, end_pages, is_ocr, layout_mode, formula_enable, table_enable, language):
     # 获取识别的md文件以及压缩包文件路径
-    local_md_dir, file_name = parse_pdf(file_path, './output', end_pages - 1, is_ocr)
+    local_md_dir, file_name = parse_pdf(file_path, './output', end_pages - 1, is_ocr,
+                                        layout_mode, formula_enable, table_enable, language)
     archive_zip_path = os.path.join("./output", compute_sha256(local_md_dir) + ".zip")
     zip_archive_success = compress_directory_to_zip(local_md_dir, archive_zip_path)
     if zip_archive_success == 0:
@@ -138,24 +145,71 @@ with open("header.html", "r") as file:
     header = file.read()
 
 
+latin_lang = [
+        'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga', 'hr',
+        'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms', 'mt', 'nl',
+        'no', 'oc', 'pi', 'pl', 'pt', 'ro', 'rs_latin', 'sk', 'sl', 'sq', 'sv',
+        'sw', 'tl', 'tr', 'uz', 'vi', 'french', 'german'
+]
+arabic_lang = ['ar', 'fa', 'ug', 'ur']
+cyrillic_lang = [
+        'ru', 'rs_cyrillic', 'be', 'bg', 'uk', 'mn', 'abq', 'ady', 'kbd', 'ava',
+        'dar', 'inh', 'che', 'lbe', 'lez', 'tab'
+]
+devanagari_lang = [
+        'hi', 'mr', 'ne', 'bh', 'mai', 'ang', 'bho', 'mah', 'sck', 'new', 'gom',
+        'sa', 'bgc'
+]
+other_lang = ['ch', 'en', 'korean', 'japan', 'chinese_cht', 'ta', 'te', 'ka']
+
+all_lang = [""]
+all_lang.extend([*other_lang, *latin_lang, *arabic_lang, *cyrillic_lang, *devanagari_lang])
+
+
+def to_pdf(file_path):
+    with pymupdf.open(file_path) as f:
+        if f.is_pdf:
+            return file_path
+        else:
+            pdf_bytes = f.convert_to_pdf()
+            # 将pdfbytes 写入到uuid.pdf中
+            # 生成唯一的文件名
+            unique_filename = f"{uuid.uuid4()}.pdf"
+
+            # 构建完整的文件路径
+            tmp_file_path = os.path.join(os.path.dirname(file_path), unique_filename)
+
+            # 将字节数据写入文件
+            with open(tmp_file_path, 'wb') as tmp_pdf_file:
+                tmp_pdf_file.write(pdf_bytes)
+
+            return tmp_file_path
+
+
 if __name__ == "__main__":
     with gr.Blocks() as demo:
         gr.HTML(header)
         with gr.Row():
             with gr.Column(variant='panel', scale=5):
-                pdf_show = gr.Markdown()
+                file = gr.File(label="Please upload a PDF or image", file_types=[".pdf", ".png", ".jpeg", "jpg"])
                 max_pages = gr.Slider(1, 10, 5, step=1, label="Max convert pages")
-                with gr.Row() as bu_flow:
-                    is_ocr = gr.Checkbox(label="Force enable OCR")
+                with gr.Row():
+                    layout_mode = gr.Dropdown(["layoutlmv3", "doclayout_yolo"], label="Layout model", value="layoutlmv3")
+                    language = gr.Dropdown(all_lang, label="Language", value="")
+                with gr.Row():
+                    formula_enable = gr.Checkbox(label="Enable formula recognition", value=True)
+                    is_ocr = gr.Checkbox(label="Force enable OCR", value=False)
+                    table_enable = gr.Checkbox(label="Enable table recognition(test)", value=False)
+                with gr.Row():
                     change_bu = gr.Button("Convert")
-                    clear_bu = gr.ClearButton([pdf_show], value="Clear")
-                pdf_show = PDF(label="Please upload pdf", interactive=True, height=800)
+                    clear_bu = gr.ClearButton(value="Clear")
+                pdf_show = PDF(label="PDF preview", interactive=True, height=800)
                 with gr.Accordion("Examples:"):
                     example_root = os.path.join(os.path.dirname(__file__), "examples")
                     gr.Examples(
                         examples=[os.path.join(example_root, _) for _ in os.listdir(example_root) if
                                   _.endswith("pdf")],
-                        inputs=pdf_show,
+                        inputs=pdf_show
                     )
 
             with gr.Column(variant='panel', scale=5):
@@ -166,7 +220,9 @@ if __name__ == "__main__":
                                          latex_delimiters=latex_delimiters, line_breaks=True)
                     with gr.Tab("Markdown text"):
                         md_text = gr.TextArea(lines=45, show_copy_button=True)
-        change_bu.click(fn=to_markdown, inputs=[pdf_show, max_pages, is_ocr], outputs=[md, md_text, output_file, pdf_show])
-        clear_bu.add([md, pdf_show, md_text, output_file, is_ocr])
+        file.upload(fn=to_pdf, inputs=file, outputs=pdf_show)
+        change_bu.click(fn=to_markdown, inputs=[pdf_show, max_pages, is_ocr, layout_mode, formula_enable, table_enable, language],
+                        outputs=[md, md_text, output_file, pdf_show])
+        clear_bu.add([file, md, pdf_show, md_text, output_file, is_ocr, table_enable, language])
 
-    demo.launch()
\ No newline at end of file
+    demo.launch(server_name="0.0.0.0")
\ No newline at end of file