fix: solve conflicts

LICENSE.md

@@ -660,6 +660,3 @@ if any, to sign a "copyright disclaimer" for the program, if necessary.
 For more information on this, and how to apply and follow the GNU AGPL, see
 <https://www.gnu.org/licenses/>.
 
-
-
-$^1$

app.py

@@ -1,167 +0,0 @@
-# Copyright (c) Opendatalab. All rights reserved.
-
-import base64
-import os
-import time
-import zipfile
-from pathlib import Path
-import re
-
-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
-
-os.system("pip install gradio")
-os.system("pip install gradio-pdf")
-import gradio as gr
-from gradio_pdf import PDF
-
-
-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):
-    os.makedirs(output_dir, exist_ok=True)
-
-    try:
-        file_name = f"{str(Path(doc_path).stem)}_{time.time()}"
-        pdf_data = read_fn(doc_path)
-        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,
-        )
-        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。
-
-    :param directory_path: 要压缩的目录路径
-    :param output_zip_path: 输出的 ZIP 文件路径
-    """
-    try:
-        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)
-        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):
-    # 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)
-    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
-
-
-# def show_pdf(file_path):
-#     with open(file_path, "rb") as f:
-#         base64_pdf = base64.b64encode(f.read()).decode('utf-8')
-#     pdf_display = f'<embed src="data:application/pdf;base64,{base64_pdf}" ' \
-#                   f'width="100%" height="1000" type="application/pdf">'
-#     return pdf_display
-
-
-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}")
-
-
-if __name__ == "__main__":
-    with gr.Blocks() as demo:
-        with gr.Row():
-            with gr.Column(variant='panel', scale=5):
-                pdf_show = gr.Markdown()
-                max_pages = gr.Slider(1, 10, 5, step=1, label="Max convert pages")
-                with gr.Row() as bu_flow:
-                    change_bu = gr.Button("Convert")
-                    clear_bu = gr.ClearButton([pdf_show], value="Clear")
-                pdf_show = PDF(label="Please upload pdf", interactive=True, height=800)
-
-            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)
-        change_bu.click(fn=to_markdown, inputs=[pdf_show, max_pages], outputs=[md, md_text, output_file, pdf_show])
-        clear_bu.add([md, pdf_show, md_text, output_file])
-
-    demo.launch()
-

magic_pdf/libs/version.py

@@ -1,5 +1 @@
-<<<<<<< HEAD
-__version__ = "0.7.1"
-=======
 __version__ = "0.8.0"
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999

magic_pdf/model/doc_analyze_by_custom_model.py

@@ -106,11 +106,7 @@ def custom_model_init(ocr: bool = False, show_log: bool = False, lang=None):
 
 
 def doc_analyze(pdf_bytes: bytes, ocr: bool = False, show_log: bool = False,
-<<<<<<< HEAD
                 start_page_id=0, end_page_id=None, lang=None):
-=======
-                start_page_id=0, end_page_id=None):
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 
     model_manager = ModelSingleton()
     custom_model = model_manager.get_model(ocr, show_log, lang)

magic_pdf/model/pdf_extract_kit.py

@@ -74,16 +74,11 @@ def layout_model_init(weight, config_file, device):
     return model
 
 
-<<<<<<< HEAD
 def ocr_model_init(show_log: bool = False, det_db_box_thresh=0.3, lang=None):
     if lang is not None:
         model = ModifiedPaddleOCR(show_log=show_log, det_db_box_thresh=det_db_box_thresh, lang=lang)
     else:
         model = ModifiedPaddleOCR(show_log=show_log, det_db_box_thresh=det_db_box_thresh)
-=======
-def ocr_model_init(show_log: bool = False, det_db_box_thresh=0.3):
-    model = ModifiedPaddleOCR(show_log=show_log, det_db_box_thresh=det_db_box_thresh)
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
     return model
 
 
@@ -142,12 +137,8 @@ def atom_model_init(model_name: str, **kwargs):
     elif model_name == AtomicModel.OCR:
         atom_model = ocr_model_init(
             kwargs.get("ocr_show_log"),
-<<<<<<< HEAD
             kwargs.get("det_db_box_thresh"),
             kwargs.get("lang")
-=======
-            kwargs.get("det_db_box_thresh")
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
         )
     elif model_name == AtomicModel.Table:
         atom_model = table_model_init(
@@ -244,12 +235,8 @@ class CustomPEKModel:
             self.ocr_model = atom_model_manager.get_atom_model(
                 atom_model_name=AtomicModel.OCR,
                 ocr_show_log=show_log,
-<<<<<<< HEAD
                 det_db_box_thresh=0.3,
                 lang=self.lang
-=======
-                det_db_box_thresh=0.3
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
             )
         # init table model
         if self.apply_table:

magic_pdf/pipe/AbsPipe.py

@@ -17,11 +17,7 @@ class AbsPipe(ABC):
     PIP_TXT = "txt"
 
     def __init__(self, pdf_bytes: bytes, model_list: list, image_writer: AbsReaderWriter, is_debug: bool = False,
-<<<<<<< HEAD
                  start_page_id=0, end_page_id=None, lang=None):
-=======
-                 start_page_id=0, end_page_id=None):
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
         self.pdf_bytes = pdf_bytes
         self.model_list = model_list
         self.image_writer = image_writer
@@ -29,10 +25,7 @@ class AbsPipe(ABC):
         self.is_debug = is_debug
         self.start_page_id = start_page_id
         self.end_page_id = end_page_id
-<<<<<<< HEAD
         self.lang = lang
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
     
     def get_compress_pdf_mid_data(self):
         return JsonCompressor.compress_json(self.pdf_mid_data)

magic_pdf/pipe/OCRPipe.py

@@ -10,25 +10,16 @@ from magic_pdf.user_api import parse_ocr_pdf
 class OCRPipe(AbsPipe):
 
     def __init__(self, pdf_bytes: bytes, model_list: list, image_writer: AbsReaderWriter, is_debug: bool = False,
-<<<<<<< HEAD
                  start_page_id=0, end_page_id=None, lang=None):
         super().__init__(pdf_bytes, model_list, image_writer, is_debug, start_page_id, end_page_id, lang)
-=======
-                 start_page_id=0, end_page_id=None):
-        super().__init__(pdf_bytes, model_list, image_writer, is_debug, start_page_id, end_page_id)
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 
     def pipe_classify(self):
         pass
 
     def pipe_analyze(self):
         self.model_list = doc_analyze(self.pdf_bytes, ocr=True,
-<<<<<<< HEAD
                                       start_page_id=self.start_page_id, end_page_id=self.end_page_id,
                                       lang=self.lang)
-=======
-                                      start_page_id=self.start_page_id, end_page_id=self.end_page_id)
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 
     def pipe_parse(self):
         self.pdf_mid_data = parse_ocr_pdf(self.pdf_bytes, self.model_list, self.image_writer, is_debug=self.is_debug,

magic_pdf/pipe/TXTPipe.py

@@ -11,25 +11,16 @@ from magic_pdf.user_api import parse_txt_pdf
 class TXTPipe(AbsPipe):
 
     def __init__(self, pdf_bytes: bytes, model_list: list, image_writer: AbsReaderWriter, is_debug: bool = False,
-<<<<<<< HEAD
                  start_page_id=0, end_page_id=None, lang=None):
         super().__init__(pdf_bytes, model_list, image_writer, is_debug, start_page_id, end_page_id, lang)
-=======
-                 start_page_id=0, end_page_id=None):
-        super().__init__(pdf_bytes, model_list, image_writer, is_debug, start_page_id, end_page_id)
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 
     def pipe_classify(self):
         pass
 
     def pipe_analyze(self):
         self.model_list = doc_analyze(self.pdf_bytes, ocr=False,
-<<<<<<< HEAD
                                       start_page_id=self.start_page_id, end_page_id=self.end_page_id,
                                       lang=self.lang)
-=======
-                                      start_page_id=self.start_page_id, end_page_id=self.end_page_id)
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 
     def pipe_parse(self):
         self.pdf_mid_data = parse_txt_pdf(self.pdf_bytes, self.model_list, self.image_writer, is_debug=self.is_debug,

magic_pdf/pipe/UNIPipe.py

@@ -14,15 +14,9 @@ from magic_pdf.user_api import parse_union_pdf, parse_ocr_pdf
 class UNIPipe(AbsPipe):
 
     def __init__(self, pdf_bytes: bytes, jso_useful_key: dict, image_writer: AbsReaderWriter, is_debug: bool = False,
-<<<<<<< HEAD
                  start_page_id=0, end_page_id=None, lang=None):
         self.pdf_type = jso_useful_key["_pdf_type"]
         super().__init__(pdf_bytes, jso_useful_key["model_list"], image_writer, is_debug, start_page_id, end_page_id, lang)
-=======
-                 start_page_id=0, end_page_id=None):
-        self.pdf_type = jso_useful_key["_pdf_type"]
-        super().__init__(pdf_bytes, jso_useful_key["model_list"], image_writer, is_debug, start_page_id, end_page_id)
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
         if len(self.model_list) == 0:
             self.input_model_is_empty = True
         else:
@@ -34,30 +28,19 @@ class UNIPipe(AbsPipe):
     def pipe_analyze(self):
         if self.pdf_type == self.PIP_TXT:
             self.model_list = doc_analyze(self.pdf_bytes, ocr=False,
-<<<<<<< HEAD
                                           start_page_id=self.start_page_id, end_page_id=self.end_page_id,
                                           lang=self.lang)
         elif self.pdf_type == self.PIP_OCR:
             self.model_list = doc_analyze(self.pdf_bytes, ocr=True,
                                           start_page_id=self.start_page_id, end_page_id=self.end_page_id,
                                           lang=self.lang)
-=======
-                                          start_page_id=self.start_page_id, end_page_id=self.end_page_id)
-        elif self.pdf_type == self.PIP_OCR:
-            self.model_list = doc_analyze(self.pdf_bytes, ocr=True,
-                                          start_page_id=self.start_page_id, end_page_id=self.end_page_id)
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 
     def pipe_parse(self):
         if self.pdf_type == self.PIP_TXT:
             self.pdf_mid_data = parse_union_pdf(self.pdf_bytes, self.model_list, self.image_writer,
                                                 is_debug=self.is_debug, input_model_is_empty=self.input_model_is_empty,
-<<<<<<< HEAD
                                                 start_page_id=self.start_page_id, end_page_id=self.end_page_id,
                                                 lang=self.lang)
-=======
-                                                start_page_id=self.start_page_id, end_page_id=self.end_page_id)
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
         elif self.pdf_type == self.PIP_OCR:
             self.pdf_mid_data = parse_ocr_pdf(self.pdf_bytes, self.model_list, self.image_writer,
                                               is_debug=self.is_debug,

magic_pdf/resources/model_config/model_configs.yaml

@@ -10,10 +10,6 @@ config:
 weights:
   layout: Layout/model_final.pth
   mfd: MFD/weights.pt
-<<<<<<< HEAD
   mfr: MFR/unimernet_base
-=======
-  mfr: MFR/UniMERNet
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
   struct_eqtable: TabRec/StructEqTable
   TableMaster: TabRec/TableMaster

magic_pdf/tools/cli.py

@@ -45,7 +45,6 @@ without method specified, auto will be used by default.""",
     default='auto',
 )
 @click.option(
-<<<<<<< HEAD
     '-l',
     '--lang',
     'lang',
@@ -58,8 +57,6 @@ without method specified, auto will be used by default.""",
     default=None,
 )
 @click.option(
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
     '-d',
     '--debug',
     'debug_able',
@@ -83,11 +80,7 @@ without method specified, auto will be used by default.""",
     help='The ending page for PDF parsing, beginning from 0.',
     default=None,
 )
-<<<<<<< HEAD
 def cli(path, output_dir, method, lang, debug_able, start_page_id, end_page_id):
-=======
-def cli(path, output_dir, method, debug_able, start_page_id, end_page_id):
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
     model_config.__use_inside_model__ = True
     model_config.__model_mode__ = 'full'
     os.makedirs(output_dir, exist_ok=True)
@@ -109,10 +102,7 @@ def cli(path, output_dir, method, debug_able, start_page_id, end_page_id):
                 debug_able,
                 start_page_id=start_page_id,
                 end_page_id=end_page_id,
-<<<<<<< HEAD
                 lang=lang
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
             )
 
         except Exception as e:

magic_pdf/user_api.py

@@ -71,11 +71,7 @@ def parse_ocr_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWrit
 
 def parse_union_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWriter, is_debug=False,
                     input_model_is_empty: bool = False,
-<<<<<<< HEAD
                     start_page_id=0, end_page_id=None, lang=None,
-=======
-                    start_page_id=0, end_page_id=None,
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
                     *args, **kwargs):
     """
     ocr和文本混合的pdf，全部解析出来
@@ -99,17 +95,11 @@ def parse_union_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWr
     if pdf_info_dict is None or pdf_info_dict.get("_need_drop", False):
         logger.warning(f"parse_pdf_by_txt drop or error, switch to parse_pdf_by_ocr")
         if input_model_is_empty:
-<<<<<<< HEAD
             pdf_models = doc_analyze(pdf_bytes,
                                      ocr=True,
                                      start_page_id=start_page_id,
                                      end_page_id=end_page_id,
                                      lang=lang)
-=======
-            pdf_models = doc_analyze(pdf_bytes, ocr=True,
-                                     start_page_id=start_page_id,
-                                     end_page_id=end_page_id)
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
         pdf_info_dict = parse_pdf(parse_pdf_by_ocr)
         if pdf_info_dict is None:
             raise Exception("Both parse_pdf_by_txt and parse_pdf_by_ocr failed.")

mv_pdf.py

@@ -1,26 +0,0 @@
-import os
-import shutil
-
-def move_pdfs(root_folder, destination_folder):
-    # 遍历根目录及其子目录中的所有文件
-    for root, dirs, files in os.walk(root_folder):
-        for file in files:
-            if file.endswith('.pdf'):
-                # 构建完整的文件路径
-                src_path = os.path.join(root, file)
-                # 构建目标路径
-                dst_path = os.path.join(destination_folder, file)
-                
-                # 移动文件
-                shutil.move(src_path, dst_path)
-                print(f'Moved {file} to {destination_folder}')
-
-# 使用方法
-root_folder = r'D:\mineru\datasets\datasets'  # 源文件夹路径
-destination_folder = r'D:\mineru\datasets\pdf'  # 目标文件夹路径
-
-# 创建目标文件夹如果不存在
-if not os.path.exists(destination_folder):
-    os.makedirs(destination_folder)
-
-move_pdfs(root_folder, destination_folder)

projects/README.md

@@ -3,9 +3,6 @@
 ## Project List
 
 - [llama_index_rag](./llama_index_rag/README.md): Build a lightweight RAG system based on llama_index
-<<<<<<< HEAD
 - [gradio_app](./gradio_app/README.md): Build a web app based on gradio
 
 
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999

projects/README_zh-CN.md

@@ -3,8 +3,5 @@
 ## 项目列表
 
 - [llama_index_rag](./llama_index_rag/README_zh-CN.md): 基于 llama_index 构建轻量级 RAG 系统
-<<<<<<< HEAD
 - [gradio_app](./gradio_app/README_zh-CN.md): 基于 Gradio 的 Web 应用
 
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999

projects/llama_index_rag/README_zh-CN.md

@@ -59,10 +59,6 @@ Server: Docker Engine - Community
 ```bash
 # install
 pip install modelscope==1.14.0
-<<<<<<< HEAD
-
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 pip install llama-index-vector-stores-elasticsearch==0.2.0
 pip install llama-index-embeddings-dashscope==0.2.0
 pip install llama-index-core==0.10.68
@@ -74,19 +70,12 @@ pip install accelerate==0.33.0
 pip uninstall transformer-engine
 ```
 
-<<<<<<< HEAD
 
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 ## 示例
 
 ````bash
 cd  projects/llama_index_rag
 
-<<<<<<< HEAD
-
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 docker compose up -d
 
 or
@@ -94,20 +83,14 @@ or
 docker-compose up -d
 
 
-<<<<<<< HEAD
 # 配置环境变量
 
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 export ES_USER=elastic
 export ES_PASSWORD=llama_index
 export ES_URL=http://127.0.0.1:9200
 export DASHSCOPE_API_KEY={some_key}
 
-<<<<<<< HEAD
 
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 DASHSCOPE_API_KEY 开通参考[文档](https://help.aliyun.com/zh/dashscope/opening-service)
 
 # 未导入数据，查询问题。返回通义千问默认答案
@@ -135,10 +118,7 @@ python data_ingestion.py -p example/data/declaration_of_the_rights_of_man_1789.p
 
 
 # 导入数据后，查询问题。通义千问模型会根据 RAG 系统的检索结果，结合上下文，给出答案。
-<<<<<<< HEAD
 
-=======
->>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
 python query.py -q 'how about the rights of men'
 
 ## outputs