Delete paddleocr/whl/det/ch/ch_PP-OCRv4_det_infer/inference.pdiparams

.gitattributes

@@ -32,4 +32,19 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.8.0a1-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.8.0a2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.8.0a3-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+paddleocr/whl/cls/ch_ppocr_mobile_v2.0_cls_infer/inference.pdmodel filter=lfs diff=lfs merge=lfs -text
+paddleocr/whl/det/ch/ch_PP-OCRv4_det_infer/inference.pdiparams filter=lfs diff=lfs merge=lfs -text
+paddleocr/whl/rec/ch/ch_PP-OCRv4_rec_infer/inference.pdiparams filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.9.0a1-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.9.0a2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.9.0a3-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.9.0a4-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.9.0a5-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.9.0a6-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.9.0a7-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.9.0a8-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+magic_pdf-0.9.0a9-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,20 +1,16 @@
 ---
-title: MinerU OCR
+title: MinerU
 emoji: 📚
 colorFrom: purple
 colorTo: blue
 sdk: gradio
-sdk_version: 6.8.0
+sdk_version: 5.7.1
 app_file: app.py
-pinned: true
+pinned: false
 license: agpl-3.0
-python_version: 3.12
 models:
 - opendatalab/PDF-Extract-Kit-1.0
-- opendatalab/MinerU2.5-2509-1.2B
-thumbnail: >-
-  https://cdn-uploads.huggingface.co/production/uploads/668f77a3b3991ac0c308a441/dsQTqtqf8SiM5oDe1FKFY.png
-short_description: A data extraction tool to convert PDF to Markdown and JSON
+- hantian/layoutreader
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,40 +1,238 @@
 # Copyright (c) Opendatalab. All rights reserved.
 
+import base64
 import os
-import json
+import time
+import zipfile
+from pathlib import Path
+import re
+import uuid
+import pymupdf
+
+# os.system('pip install -U magic-pdf==0.10.5')
+os.system('pip uninstall -y magic-pdf')
+os.system('pip install git+https://github.com/opendatalab/MinerU.git@dev')
+
+os.system('wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py')
+os.system('python download_models_hf.py')
+os.system("sed -i 's|cpu|cuda|g' /home/user/magic-pdf.json")
+
+os.system('cp -r paddleocr /home/user/.paddleocr')
+os.system("pip install gradio-pdf==0.0.19")
+from gradio_pdf import PDF
+
+import gradio as gr
 from loguru import logger
 
+from magic_pdf.libs.hash_utils import compute_sha256
+from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
+from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
+from magic_pdf.tools.common import do_parse, prepare_env
+
+
+def read_fn(path):
+    disk_rw = DiskReaderWriter(os.path.dirname(path))
+    return disk_rw.read(os.path.basename(path), AbsReaderWriter.MODE_BIN)
+
+
+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:
+        file_name = f"{str(Path(doc_path).stem)}_{time.time()}"
+        pdf_data = read_fn(doc_path)
+        if is_ocr:
+            parse_method = "ocr"
+        else:
+            parse_method = "auto"
+        local_image_dir, local_md_dir = prepare_env(output_dir, file_name, parse_method)
+        do_parse(
+            output_dir,
+            file_name,
+            pdf_data,
+            [],
+            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:
+        logger.exception(e)
+
+
+def compress_directory_to_zip(directory_path, output_zip_path):
+    """
+    压缩指定目录到一个 ZIP 文件。
 
-if __name__ == '__main__':
-    os.system('pip uninstall -y mineru')
-    os.system('pip install git+https://github.com/myhloli/Magic-PDF.git@dev')
-    os.system('pip install -U mineru_vl_utils')
-    os.system('mineru-models-download -s huggingface -m all')
-    # os.system('mineru-models-download -s modelscope -m all')
-    os.environ['MINERU_MODEL_SOURCE'] = "local"
-    os.environ['GRADIO_SSR_MODE'] = "false"
-    os.environ['MINERU_PDF_RENDER_TIMEOUT'] = "10"
+    :param directory_path: 要压缩的目录路径
+    :param output_zip_path: 输出的 ZIP 文件路径
+    """
     try:
-        home_dir = os.path.expanduser('~')
-        config_file = os.path.join(home_dir, 'mineru.json')
-        with open(config_file, 'r+') as file:
-            config = json.load(file)
-            
-            delimiters = {
-                'display': {'left': '\\[', 'right': '\\]'},
-                'inline': {'left': '\\(', 'right': '\\)'}
-            }
-            
-            config['latex-delimiter-config'] = delimiters
-            
-            if os.getenv('apikey'):
-                config['llm-aided-config']['title_aided']['api_key'] = os.getenv('apikey')
-                config['llm-aided-config']['title_aided']['enable'] = True
-                config['llm-aided-config']['title_aided']['model'] = "qwen3-next-80b-a3b-instruct"
-            
-            file.seek(0)  # 将文件指针移回文件开始位置
-            file.truncate()  # 截断文件，清除原有内容
-            json.dump(config, file, indent=4)  # 写入新内容
+        with zipfile.ZipFile(output_zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
+
+            # 遍历目录中的所有文件和子目录
+            for root, dirs, files in os.walk(directory_path):
+                for file in files:
+                    # 构建完整的文件路径
+                    file_path = os.path.join(root, file)
+                    # 计算相对路径
+                    arcname = os.path.relpath(file_path, directory_path)
+                    # 添加文件到 ZIP 文件
+                    zipf.write(file_path, arcname)
+        return 0
     except Exception as e:
         logger.exception(e)
-    os.system('mineru-gradio --enable-api false --max-convert-pages 20 --latex-delimiters-type b --gpu-memory-utilization 0.5')
+        return -1
+
+
+def image_to_base64(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode('utf-8')
+
+
+def replace_image_with_base64(markdown_text, image_dir_path):
+    # 匹配Markdown中的图片标签
+    pattern = r'\!\[(?:[^\]]*)\]\(([^)]+)\)'
+
+    # 替换图片链接
+    def replace(match):
+        relative_path = match.group(1)
+        full_path = os.path.join(image_dir_path, relative_path)
+        base64_image = image_to_base64(full_path)
+        return f"![{relative_path}](data:image/jpeg;base64,{base64_image})"
+
+    # 应用替换
+    return re.sub(pattern, replace, markdown_text)
+
+
+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,
+                                        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:
+        logger.info("压缩成功")
+    else:
+        logger.error("压缩失败")
+    md_path = os.path.join(local_md_dir, file_name + ".md")
+    with open(md_path, 'r', encoding='utf-8') as f:
+        txt_content = f.read()
+    md_content = replace_image_with_base64(txt_content, local_md_dir)
+    # 返回转换后的PDF路径
+    new_pdf_path = os.path.join(local_md_dir, file_name + "_layout.pdf")
+
+    return md_content, txt_content, archive_zip_path, new_pdf_path
+
+
+latex_delimiters = [{"left": "$$", "right": "$$", "display": True},
+                    {"left": '$', "right": '$', "display": False}]
+
+
+def init_model():
+    from magic_pdf.model.doc_analyze_by_custom_model import ModelSingleton
+    try:
+        model_manager = ModelSingleton()
+        txt_model = model_manager.get_model(False, False)
+        logger.info(f"txt_model init final")
+        ocr_model = model_manager.get_model(True, False)
+        logger.info(f"ocr_model init final")
+        return 0
+    except Exception as e:
+        logger.exception(e)
+        return -1
+
+
+model_init = init_model()
+logger.info(f"model_init: {model_init}")
+
+
+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):
+                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():
+                    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(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
+                    )
+
+            with gr.Column(variant='panel', scale=5):
+                output_file = gr.File(label="convert result", interactive=False)
+                with gr.Tabs():
+                    with gr.Tab("Markdown rendering"):
+                        md = gr.Markdown(label="Markdown rendering", height=900, show_copy_button=True,
+                                         latex_delimiters=latex_delimiters, line_breaks=True)
+                    with gr.Tab("Markdown text"):
+                        md_text = gr.TextArea(lines=45, show_copy_button=True)
+        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], api_name=False, concurrency_limit=4)
+        clear_bu.add([file, md, pdf_show, md_text, output_file, is_ocr, table_enable, language])
+
+    demo.launch(ssr_mode=False)

header.html

@@ -0,0 +1,122 @@
+<html>
+  <head>
+  <!-- <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bulma@0.9.3/css/bulma.min.css"> -->
+  <link rel="stylesheet" href="https://use.fontawesome.com/releases/v5.15.4/css/all.css">
+<style>
+  .link-block {
+    border: 1px solid transparent;
+    border-radius: 24px;
+    background-color: rgba(54, 54, 54, 1);
+    cursor: pointer !important;
+  }
+  .link-block:hover {
+    background-color: rgba(54, 54, 54, 0.75) !important;
+    cursor: pointer !important;
+  }
+  .external-link {
+    display: inline-flex;
+    align-items: center;
+    height: 36px;
+    line-height: 36px;
+    padding: 0 16px;
+    cursor: pointer !important;
+  }
+  .external-link,
+  .external-link:hover {
+    cursor: pointer !important;
+  }
+  a {
+    text-decoration: none;
+  }
+</style>
+  </head>
+
+<body>
+  <div style="
+      display: flex;
+      flex-direction: column;
+      justify-content: center;
+      align-items: center;
+      text-align: center;
+      background: linear-gradient(45deg, #007bff 0%, #0056b3 100%);
+      padding: 24px;
+      gap: 24px;
+      border-radius: 8px;
+    ">
+    <div style="
+        display: flex;
+        flex-direction: column;
+        align-items: center;
+        gap: 16px;
+      ">
+      <div style="display: flex; flex-direction: column; gap: 8px">
+        <h1 style="
+            font-size: 48px;
+            color: #fafafa;
+            margin: 0;
+            font-family: 'Trebuchet MS', 'Lucida Sans Unicode',
+              'Lucida Grande', 'Lucida Sans', Arial, sans-serif;
+          ">
+          MinerU: PDF Extraction Demo
+        </h1>
+      </div>
+    </div>
+
+    <p style="
+        margin: 0;
+        line-height: 1.6rem;
+        font-size: 16px;
+        color: #fafafa;
+        opacity: 0.8;
+      ">
+      A one-stop, open-source, high-quality data extraction tool, supports
+      PDF/webpage/e-book extraction.<br>
+    </p>
+    <style>
+      .link-block {
+        display: inline-block;
+      }
+      .link-block + .link-block {
+        margin-left: 20px;
+      }
+    </style>
+
+    <div class="column has-text-centered">
+      <div class="publication-links">
+        <!-- Code Link. -->
+        <span class="link-block">
+          <a href="https://github.com/opendatalab/MinerU" class="external-link button is-normal is-rounded is-dark" style="text-decoration: none; cursor: pointer">
+            <span class="icon" style="margin-right: 4px">
+              <i class="fab fa-github" style="color: white; margin-right: 4px"></i>
+            </span>
+            <span style="color: white">Code</span>
+          </a>
+        </span>
+
+        <!-- arXiv Link. -->
+        <span class="link-block">
+          <a href="https://arxiv.org/abs/2409.18839" class="external-link button is-normal is-rounded is-dark" style="text-decoration: none; cursor: pointer">
+            <span class="icon" style="margin-right: 8px">
+              <i class="fas fa-file" style="color: white"></i>
+            </span>
+            <span style="color: white">Paper</span>
+          </a>
+        </span>
+
+        <!-- Homepage Link. -->
+        <span class="link-block">
+          <a href="https://opendatalab.com/" class="external-link button is-normal is-rounded is-dark" style="text-decoration: none; cursor: pointer">
+            <span class="icon" style="margin-right: 8px">
+              <i class="fas fa-globe" style="color: white"></i>
+            </span>
+            <span style="color: white">Homepage</span>
+          </a>
+        </span>
+      </div>
+    </div>
+
+    <!-- New Demo Links -->
+  </div>
+
+
+</body></html>

packages.txt

@@ -1,2 +0,0 @@
-fonts-noto-core
-fonts-noto-cjk

requirements.txt

@@ -1,2 +1,23 @@
-mineru[pipeline,vlm,api,vllm]>=2.7.6
-gradio-pdf>=0.0.22
+boto3>=1.28.43
+Brotli>=1.1.0
+click>=8.1.7
+PyMuPDF>=1.24.9
+loguru>=0.6.0
+numpy>=1.21.6,<2.0.0
+fast-langdetect==0.2.0
+scikit-learn>=1.0.2
+unimernet==0.2.1
+doclayout_yolo==0.0.2
+matplotlib
+ultralytics
+paddleocr==2.7.3
+paddlepaddle-gpu @ https://paddle-whl.bj.bcebos.com/stable/cu118/paddlepaddle-gpu/paddlepaddle_gpu-3.0.0b1-cp310-cp310-linux_x86_64.whl
+pypandoc
+struct-eqtable==0.3.2
+detectron2 @ https://wheels-1251341229.cos.ap-shanghai.myqcloud.com/assets/whl/detectron2/detectron2-0.6-cp310-cp310-linux_x86_64.whl
+magic-pdf>=0.9.2
+rapid-table
+rapidocr-paddle
+gradio
+huggingface_hub
+gradio-pdf