magic-pdf 0.6.2b1__py3-none-any.whl → 0.7.0a1__py3-none-any.whl

magic_pdf/tools/cli_dev.py

@@ -0,0 +1,156 @@
+import os
+import json as json_parse
+import click
+from pathlib import Path
+from magic_pdf.libs.path_utils import (
+    parse_s3path,
+    parse_s3_range_params,
+    remove_non_official_s3_args,
+)
+from magic_pdf.libs.config_reader import (
+    get_s3_config,
+)
+from magic_pdf.rw.S3ReaderWriter import S3ReaderWriter
+from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
+from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
+import magic_pdf.model as model_config
+from magic_pdf.tools.common import parse_pdf_methods, do_parse
+from magic_pdf.libs.version import __version__
+
+
+def read_s3_path(s3path):
+    bucket, key = parse_s3path(s3path)
+
+    s3_ak, s3_sk, s3_endpoint = get_s3_config(bucket)
+    s3_rw = S3ReaderWriter(
+        s3_ak, s3_sk, s3_endpoint, "auto", remove_non_official_s3_args(s3path)
+    )
+    may_range_params = parse_s3_range_params(s3path)
+    if may_range_params is None or 2 != len(may_range_params):
+        byte_start, byte_end = 0, None
+    else:
+        byte_start, byte_end = int(may_range_params[0]), int(may_range_params[1])
+        byte_end += byte_start - 1
+    return s3_rw.read_jsonl(
+        remove_non_official_s3_args(s3path),
+        byte_start,
+        byte_end,
+        AbsReaderWriter.MODE_BIN,
+    )
+
+
+@click.group()
+@click.version_option(__version__, "--version", "-v", help="显示版本信息")
+def cli():
+    pass
+
+
+@cli.command()
+@click.option(
+    "-j",
+    "--jsonl",
+    "jsonl",
+    type=str,
+    help="输入 jsonl 路径，本地或者 s3 上的文件",
+    required=True,
+)
+@click.option(
+    "-m",
+    "--method",
+    "method",
+    type=parse_pdf_methods,
+    help="指定解析方法。txt: 文本型 pdf 解析方法， ocr: 光学识别解析 pdf, auto: 程序智能选择解析方法",
+    default="auto",
+)
+@click.option(
+    "-o",
+    "--output-dir",
+    "output_dir",
+    type=str,
+    help="输出到本地目录",
+    default="",
+)
+def jsonl(jsonl, method, output_dir):
+    print("haha")
+    model_config.__use_inside_model__ = False
+    full_jsonl_path = os.path.realpath(jsonl)
+    if output_dir == "":
+        output_dir = os.path.join(os.path.dirname(full_jsonl_path), "output")
+
+    if jsonl.startswith("s3://"):
+        jso = json_parse.loads(read_s3_path(jsonl).decode("utf-8"))
+    else:
+        with open(jsonl) as f:
+            jso = json_parse.loads(f.readline())
+    s3_file_path = jso.get("file_location")
+    if s3_file_path is None:
+        s3_file_path = jso.get("path")
+    pdf_file_name = Path(s3_file_path).stem
+    pdf_data = read_s3_path(s3_file_path)
+
+
+    print(pdf_file_name, jso, method)
+    do_parse(
+        output_dir,
+        pdf_file_name,
+        pdf_data,
+        jso["doc_layout_result"],
+        method,
+        f_dump_content_list=True,
+    )
+
+
+@cli.command()
+@click.option(
+    "-p",
+    "--pdf",
+    "pdf",
+    type=click.Path(exists=True),
+    required=True,
+    help="本地 PDF 文件",
+)
+@click.option(
+    "-j",
+    "--json",
+    "json_data",
+    type=click.Path(exists=True),
+    required=True,
+    help="本地模型推理出的 json 数据",
+)
+@click.option(
+    "-o", "--output-dir", "output_dir", type=str, help="本地输出目录", default=""
+)
+@click.option(
+    "-m",
+    "--method",
+    "method",
+    type=parse_pdf_methods,
+    help="指定解析方法。txt: 文本型 pdf 解析方法， ocr: 光学识别解析 pdf, auto: 程序智能选择解析方法",
+    default="auto",
+)
+def pdf(pdf, json_data, output_dir, method):
+    model_config.__use_inside_model__ = False
+    full_pdf_path = os.path.realpath(pdf)
+    if output_dir == "":
+        output_dir = os.path.join(os.path.dirname(full_pdf_path), "output")
+
+    def read_fn(path):
+        disk_rw = DiskReaderWriter(os.path.dirname(path))
+        return disk_rw.read(os.path.basename(path), AbsReaderWriter.MODE_BIN)
+
+    model_json_list = json_parse.loads(read_fn(json_data).decode("utf-8"))
+
+    file_name = str(Path(full_pdf_path).stem)
+    pdf_data = read_fn(full_pdf_path)
+    do_parse(
+        output_dir,
+        file_name,
+        pdf_data,
+        model_json_list,
+        method,
+        f_dump_content_list=True,
+    )
+
+
+if __name__ == "__main__":
+    cli()

magic_pdf/tools/common.py

@@ -0,0 +1,119 @@
+import os
+import json as json_parse
+import copy
+import click
+from loguru import logger
+from magic_pdf.libs.MakeContentConfig import DropMode, MakeMode
+from magic_pdf.libs.draw_bbox import draw_layout_bbox, draw_span_bbox
+from magic_pdf.pipe.UNIPipe import UNIPipe
+from magic_pdf.pipe.OCRPipe import OCRPipe
+from magic_pdf.pipe.TXTPipe import TXTPipe
+from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
+from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
+import magic_pdf.model as model_config
+
+
+def prepare_env(output_dir, pdf_file_name, method):
+    local_parent_dir = os.path.join(output_dir, pdf_file_name, method)
+
+    local_image_dir = os.path.join(str(local_parent_dir), "images")
+    local_md_dir = local_parent_dir
+    os.makedirs(local_image_dir, exist_ok=True)
+    os.makedirs(local_md_dir, exist_ok=True)
+    return local_image_dir, local_md_dir
+
+
+def do_parse(
+    output_dir,
+    pdf_file_name,
+    pdf_bytes,
+    model_list,
+    parse_method,
+    f_draw_span_bbox=True,
+    f_draw_layout_bbox=True,
+    f_dump_md=True,
+    f_dump_middle_json=True,
+    f_dump_model_json=True,
+    f_dump_orig_pdf=True,
+    f_dump_content_list=False,
+    f_make_md_mode=MakeMode.MM_MD,
+):
+    orig_model_list = copy.deepcopy(model_list)
+    local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
+
+    image_writer, md_writer = DiskReaderWriter(local_image_dir), DiskReaderWriter(
+        local_md_dir
+    )
+    image_dir = str(os.path.basename(local_image_dir))
+
+    if parse_method == "auto":
+        jso_useful_key = {"_pdf_type": "", "model_list": model_list}
+        pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer, is_debug=True)
+    elif parse_method == "txt":
+        pipe = TXTPipe(pdf_bytes, model_list, image_writer, is_debug=True)
+    elif parse_method == "ocr":
+        pipe = OCRPipe(pdf_bytes, model_list, image_writer, is_debug=True)
+    else:
+        logger.error("unknown parse method")
+        exit(1)
+
+    pipe.pipe_classify()
+
+    if len(model_list) == 0:
+        if model_config.__use_inside_model__:
+            pipe.pipe_analyze()
+            orig_model_list = copy.deepcopy(pipe.model_list)
+        else:
+            logger.error("need model list input")
+            exit(2)
+
+    pipe.pipe_parse()
+    pdf_info = pipe.pdf_mid_data["pdf_info"]
+    if f_draw_layout_bbox:
+        draw_layout_bbox(pdf_info, pdf_bytes, local_md_dir)
+    if f_draw_span_bbox:
+        draw_span_bbox(pdf_info, pdf_bytes, local_md_dir)
+
+    md_content = pipe.pipe_mk_markdown(
+        image_dir, drop_mode=DropMode.NONE, md_make_mode=f_make_md_mode
+    )
+    if f_dump_md:
+        md_writer.write(
+            content=md_content,
+            path=f"{pdf_file_name}.md",
+            mode=AbsReaderWriter.MODE_TXT,
+        )
+
+    if f_dump_middle_json:
+        md_writer.write(
+            content=json_parse.dumps(pipe.pdf_mid_data, ensure_ascii=False, indent=4),
+            path="middle.json",
+            mode=AbsReaderWriter.MODE_TXT,
+        )
+
+    if f_dump_model_json:
+        md_writer.write(
+            content=json_parse.dumps(orig_model_list, ensure_ascii=False, indent=4),
+            path="model.json",
+            mode=AbsReaderWriter.MODE_TXT,
+        )
+
+    if f_dump_orig_pdf:
+        md_writer.write(
+            content=pdf_bytes,
+            path="origin.pdf",
+            mode=AbsReaderWriter.MODE_BIN,
+        )
+
+    content_list = pipe.pipe_mk_uni_format(image_dir, drop_mode=DropMode.NONE)
+    if f_dump_content_list:
+        md_writer.write(
+            content=json_parse.dumps(content_list, ensure_ascii=False, indent=4),
+            path="content_list.json",
+            mode=AbsReaderWriter.MODE_TXT,
+        )
+
+    logger.info(f"local output dir is {local_md_dir}")
+
+
+parse_pdf_methods = click.Choice(["ocr", "txt", "auto"])

{magic_pdf-0.6.2b1.dist-info → magic_pdf-0.7.0a1.dist-info}/METADATA

@@ -1,33 +1,36 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 0.6.2b1
+Version: 0.7.0a1
 Summary: A practical tool for converting PDF to Markdown
 Home-page: https://github.com/opendatalab/MinerU
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: boto3 >=1.28.43
-Requires-Dist: Brotli >=1.1.0
-Requires-Dist: click >=8.1.7
-Requires-Dist: PyMuPDF >=1.24.9
-Requires-Dist: loguru >=0.6.0
-Requires-Dist: numpy <2.0.0,>=1.21.6
-Requires-Dist: fast-langdetect ==0.2.0
-Requires-Dist: wordninja >=2.0.0
-Requires-Dist: scikit-learn >=1.0.2
-Requires-Dist: pdfminer.six ==20231228
+Requires-Dist: boto3>=1.28.43
+Requires-Dist: Brotli>=1.1.0
+Requires-Dist: click>=8.1.7
+Requires-Dist: PyMuPDF>=1.24.9
+Requires-Dist: loguru>=0.6.0
+Requires-Dist: numpy<2.0.0,>=1.21.6
+Requires-Dist: fast-langdetect==0.2.0
+Requires-Dist: wordninja>=2.0.0
+Requires-Dist: scikit-learn>=1.0.2
+Requires-Dist: pdfminer.six==20231228
 Provides-Extra: full
-Requires-Dist: unimernet ==0.1.6 ; extra == 'full'
-Requires-Dist: matplotlib ; extra == 'full'
-Requires-Dist: ultralytics ; extra == 'full'
-Requires-Dist: paddleocr ==2.7.3 ; extra == 'full'
-Requires-Dist: detectron2 ; extra == 'full'
-Requires-Dist: paddlepaddle ==3.0.0b1 ; (platform_system == "Linux") and extra == 'full'
-Requires-Dist: paddlepaddle ==2.6.1 ; (platform_system == "Windows" or platform_system == "Darwin") and extra == 'full'
+Requires-Dist: unimernet==0.1.6; extra == "full"
+Requires-Dist: ultralytics; extra == "full"
+Requires-Dist: paddleocr==2.7.3; extra == "full"
+Requires-Dist: pypandoc; extra == "full"
+Requires-Dist: struct-eqtable==0.1.0; extra == "full"
+Requires-Dist: detectron2; extra == "full"
+Requires-Dist: paddlepaddle==3.0.0b1; platform_system == "Linux" and extra == "full"
+Requires-Dist: matplotlib; (platform_system == "Linux" or platform_system == "Darwin") and extra == "full"
+Requires-Dist: matplotlib<=3.9.0; platform_system == "Windows" and extra == "full"
+Requires-Dist: paddlepaddle==2.6.1; (platform_system == "Windows" or platform_system == "Darwin") and extra == "full"
 Provides-Extra: lite
-Requires-Dist: paddleocr ==2.7.3 ; extra == 'lite'
-Requires-Dist: paddlepaddle ==3.0.0b1 ; (platform_system == "Linux") and extra == 'lite'
-Requires-Dist: paddlepaddle ==2.6.1 ; (platform_system == "Windows" or platform_system == "Darwin") and extra == 'lite'
+Requires-Dist: paddleocr==2.7.3; extra == "lite"
+Requires-Dist: paddlepaddle==3.0.0b1; platform_system == "Linux" and extra == "lite"
+Requires-Dist: paddlepaddle==2.6.1; (platform_system == "Windows" or platform_system == "Darwin") and extra == "lite"
 
 <div id="top">
 
@@ -62,7 +65,7 @@ Requires-Dist: paddlepaddle ==2.6.1 ; (platform_system == "Windows" or platform_
 </p>
 
 <p align="center">
-    👋 join us on <a href="https://discord.gg/AsQMhuMN" target="_blank">Discord</a> and <a href="https://cdn.vansin.top/internlm/mineru.jpg" target="_blank">WeChat</a>
+    👋 join us on <a href="https://discord.gg/gPxmVeGC" target="_blank">Discord</a> and <a href="https://cdn.vansin.top/internlm/mineru.jpg" target="_blank">WeChat</a>
 </p>
 </div>
 
@@ -131,21 +134,30 @@ conda activate MinerU
 
 #### 1. Install Magic-PDF
 
-Install the full-feature package with pip:
->Note: The pip-installed package supports CPU-only and is ideal for quick tests.
->
->For CUDA/MPS acceleration in production, see [Acceleration Using CUDA or MPS](#4-Acceleration-Using-CUDA-or-MPS).
+**1.Install dependencies**
 
-```bash
-pip install magic-pdf[full-cpu]
-```
 The full-feature package depends on detectron2, which requires a compilation installation.   
 If you need to compile it yourself, please refer to https://github.com/facebookresearch/detectron2/issues/5114  
 Alternatively, you can directly use our precompiled whl package (limited to Python 3.10):
 
 ```bash
-pip install detectron2 --extra-index-url https://myhloli.github.io/wheels/
+pip install detectron2 --extra-index-url https://wheels.myhloli.com
+```
+
+**2.Install the full-feature package with pip**
+>Note: The pip-installed package supports CPU-only and is ideal for quick tests.
+>
+>For CUDA/MPS acceleration in production, see [Acceleration Using CUDA or MPS](#4-Acceleration-Using-CUDA-or-MPS).
+
+```bash
+pip install magic-pdf[full]==0.6.2b1
 ```
+> ❗️❗️❗️
+> We have pre-released the 0.6.2 beta version, addressing numerous issues mentioned in our logs. However, this build has not undergone full QA testing and does not represent the final release quality. Should you encounter any problems, please promptly report them to us via issues or revert to using version 0.6.1.
+> ```bash
+> pip install magic-pdf[full-cpu]==0.6.1
+> ```
+
 
 
 #### 2. Downloading model weights files
@@ -174,10 +186,16 @@ If you have an available Nvidia GPU or are using a Mac with Apple Silicon, you c
 ##### CUDA
 
 You need to install the corresponding PyTorch version according to your CUDA version.  
-This example installs the CUDA 11.8 version.More information https://pytorch.org/get-started/locally/  
+This example installs the CUDA 11.8 version.More information https://pytorch.org/get-started/locally/
 ```bash
 pip install --force-reinstall torch==2.3.1 torchvision==0.18.1 --index-url https://download.pytorch.org/whl/cu118
 ```
+> ❗ ️Make sure to specify version
+> ```bash
+> torch==2.3.1 torchvision==0.18.1
+> ```
+>  in the command, as these are the highest versions we support. Failing to specify the versions may result in automatically installing higher versions which can cause the program to fail.
+
 Also, you need to modify the value of "device-mode" in the configuration file magic-pdf.json.  
 ```json
 {

{magic_pdf-0.6.2b1.dist-info → magic_pdf-0.7.0a1.dist-info}/RECORD

@@ -1,14 +1,11 @@
 magic_pdf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/pdf_parse_by_ocr.py,sha256=IWnSWt1Z-d35xRqspzdLR2iUtma_SAu4W7K4kEk8SHc,638
 magic_pdf/pdf_parse_by_txt.py,sha256=KUSH7Gh83CZmdyWw59pqDskwyJ2Kg-jU-9fnQGJQEs4,537
-magic_pdf/pdf_parse_for_train.py,sha256=Oby61DMjJ716Jj_ri7lwXfv2Chus0pbBR2RPXrmBW08,28661
 magic_pdf/pdf_parse_union_core.py,sha256=jNly6l9pGcCf7wr6s6PgQhITJZ1m9PaI32Q26zxFngs,10620
 magic_pdf/user_api.py,sha256=CVQH-VSiZpz0bSkyMT4czk1epZriIPSJsLsPbluPa9Q,3054
-magic_pdf/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/cli/magicpdf.py,sha256=jzGSxLcx_tmjFiZfIKpomfU9rfvAwZDyMm4bmNGQmJw,13541
 magic_pdf/dict2md/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/dict2md/mkcontent.py,sha256=rWUY-2opd0jeowEUEVOV_uWcKum1Q7ng4nOoT6-ka_s,17459
-magic_pdf/dict2md/ocr_mkcontent.py,sha256=L5D6aLB3vSATfDmsXRI_Mnq79ijH6yPYdSxSJb5aFh8,15678
+magic_pdf/dict2md/ocr_mkcontent.py,sha256=mq6tACGkL383bdUla7xOkRXRTBBydRtdbgIHwkk_daM,16169
 magic_pdf/filter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/filter/pdf_classify_by_type.py,sha256=spmDO-f2ihAl1d6-EP-j271Yi50oyu6mw4X2kRd_m0s,42320
 magic_pdf/filter/pdf_meta_scan.py,sha256=5R2XDiBZw0xd4ugbDxuyk6fztGlT5jFsGN85hLvo-hQ,17390
@@ -25,7 +22,7 @@ magic_pdf/libs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/libs/boxbase.py,sha256=MvD0DypR4sTEF3T2RrI_yJ8mPDUBYHAqAaau2mnBSxY,15343
 magic_pdf/libs/calc_span_stats.py,sha256=5vnU27DcbkFDRSAoLqAmX0KQ3I9ehWkEgh_t9hxg_zI,10147
 magic_pdf/libs/commons.py,sha256=6Zu9-OyamyCNDY7qj0SxR-rux-ggj9im3CVPtC4ubB8,7108
-magic_pdf/libs/config_reader.py,sha256=Wlig8KRhKpz8fVNc7dlspxoccX5SnyT7FmwKj9i-gWE,2435
+magic_pdf/libs/config_reader.py,sha256=dPx6JJJuCw9AzNgKtrTG1elmfdeN6gDhgFK9r15-NsE,2505
 magic_pdf/libs/convert_utils.py,sha256=Ov-lsfCLBPz_15iSJXIslBNmrSf_E_1g_XDWJy8NgO8,143
 magic_pdf/libs/coordinate_transform.py,sha256=Bbop2cP2uz2ZG0U0gwd7J6EKkgABq5Rv03qf2LMPw80,429
 magic_pdf/libs/detect_language_from_model.py,sha256=Uln8F9qs8EJOw4EgI7KRlaU3lD_mK8KMTlADLFtz8fk,816
@@ -44,13 +41,13 @@ magic_pdf/libs/pdf_check.py,sha256=MAe8wzwT0qvPf_I72wEZG7k1g4haNHS7oUtLqkB5rlE,2
 magic_pdf/libs/pdf_image_tools.py,sha256=CAd01giTKr_UJz1_QtDOARG9G9z69GFpzRZwcWSfLtE,1282
 magic_pdf/libs/safe_filename.py,sha256=ckwcM_eqoysTb5id8czp-tXq2G9da0-l3pshZDCHQtE,236
 magic_pdf/libs/textbase.py,sha256=SC1Frhz3Fb7V7n2SFRBsl7Bmg0JZdlvZskq0lfW1vIk,732
-magic_pdf/libs/version.py,sha256=ZMr9EH74nzdVNg9PXVs5XLZcabTX-_J2XZD1VgXHRBE,24
+magic_pdf/libs/version.py,sha256=iEqOsQ5JUsdTQDAPqryKypkJMTOXXBl71cd4Drh5pDs,24
 magic_pdf/libs/vis_utils.py,sha256=hTOTEakKV0pGMbk0tbRkVI_tku7A3dGc96ynObZ4kwI,10207
 magic_pdf/model/__init__.py,sha256=1QcfMKET0xQhSaZMjNQHi_TjzSSDR6PI5mjkmaXHPe8,52
-magic_pdf/model/doc_analyze_by_custom_model.py,sha256=0YyZoDUQBFQIDiHDK59JEql9FKSkZMr8aGN0Tw1eL8k,4064
-magic_pdf/model/magic_model.py,sha256=tIGi-vtn6OUDqs3mtW2YLzoFvSPu4kkBiHJUv6o0Kic,25233
+magic_pdf/model/doc_analyze_by_custom_model.py,sha256=cSmh27RG1cvY0pd98T82rq0pANBwkYN0siZIN6oPNI8,4332
+magic_pdf/model/magic_model.py,sha256=xwKV9BrdjOJecJSzbErT54N6qeJu0tvFuJg2S1z_2kU,25413
 magic_pdf/model/model_list.py,sha256=AqxAtKGLDn7VVXWYwk0l9LnACxDLyU2jwOJ7vjPZj04,72
-magic_pdf/model/pdf_extract_kit.py,sha256=ecoTBn7ROmfU1KxFpFzu7yXw7aezmPV6xOht7PRmPHA,10692
+magic_pdf/model/pdf_extract_kit.py,sha256=I3pZBWQu8y5YVjURTUJnsIySjeSGK-Yefit9PiqN9VE,12952
 magic_pdf/model/pp_structure_v2.py,sha256=1sn8IJK0d5ZmqJ2XFt9FdaSdI0RQf-iwNAWBrVrIeuc,2872
 magic_pdf/model/pek_sub_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/model/pek_sub_modules/post_process.py,sha256=HzRxV2sVR3Qo8XKYEHhT6tae-bYTb6dnAfGP6gfVNaM,1135
@@ -75,6 +72,8 @@ magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/configur
 magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/modeling_layoutlmv3.py,sha256=mdo8tO-DrJcv0Lbk9Pp98n3NQXYOnFFyXQWjU7t35kA,54633
 magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3.py,sha256=diKlrfxYjKAmYrUgjYdx-FXLh-swShC3tl-EBX1b3oI,1197
 magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3_fast.py,sha256=0lxiG69_fGpSSBYA9CBLnDa_qqa1rInZ0pJpqBwZ0Yw,1372
+magic_pdf/model/pek_sub_modules/structeqtable/StructTableModel.py,sha256=BdrBZ_2B2jgF0vzn_ted8bE9Te-DC1Ea2UijqULNKjg,928
+magic_pdf/model/pek_sub_modules/structeqtable/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/para/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/para/block_continuation_processor.py,sha256=IkReB5hirjm0OAirNzQQpnWe2f2bdP3Hug3Ef8qTRDA,22749
 magic_pdf/para/block_termination_processor.py,sha256=YU3ZYqJy9e3OQmOuQYZrR6AUpmAlQ0mhj0PgZZPZ_fM,17957
@@ -128,23 +127,22 @@ magic_pdf/pre_proc/resolve_bbox_conflict.py,sha256=bJiegofPUeDyi--oZjfipQ5Q5RLm6
 magic_pdf/pre_proc/solve_line_alien.py,sha256=aNoQptPcC38Sm1I2ABhgw8jeH_5kjsRHx3VYlFFtm1g,853
 magic_pdf/pre_proc/statistics.py,sha256=_9jGlXq0iXd03UMxB92ZqCiu7cjNkG5vHvFlTF_9ytA,220
 magic_pdf/resources/fasttext-langdetect/lid.176.ftz,sha256=jzRyz-hzintgmejpmcPL-uDc0VaWqsfXc4qAOdtgPoM,938013
-magic_pdf/resources/model_config/model_configs.yaml,sha256=C_9UfFMlHOX-iSgcwCHjyHKazKKuwpy1RcGHeTQD1kY,139
+magic_pdf/resources/model_config/model_configs.yaml,sha256=2MxCOJ5yNUupQqvrAvEuJKlygjxxV_o1qE64K_4NWKA,235
 magic_pdf/resources/model_config/UniMERNet/demo.yaml,sha256=al9_--m3n2j9zEn9OjlmmpfQbqVBAYFakXc_hY4vDXo,807
 magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml,sha256=9aNAEYgpHTAWpcUrDvuPG2y4V-Qw8QdcJefi96y8yDU,6109
-magic_pdf/rw/AbsReaderWriter.py,sha256=1Hd6Xo2g12CaRAo5Sze-R_GSQA6GQ0rQwSmgQvw4V_c,1297
-magic_pdf/rw/DiskReaderWriter.py,sha256=0tt8lbRyqrOfFgGlhjt24YMdj2xN7QUIVysfhFIxPgo,2113
-magic_pdf/rw/S3ReaderWriter.py,sha256=O7Quf3CUqXBjMz4sIE7kNVI3TIQROeg5PuXneAacieY,4474
+magic_pdf/rw/AbsReaderWriter.py,sha256=2H5SDJfAAOX9kPfel06a8VRCHxD1Y8aPbWEkQDdn9JM,452
+magic_pdf/rw/DiskReaderWriter.py,sha256=7ZAekH8V6xlBo_1WeSZ6sNwAj2WGPtjNl50zq1CoMDY,2614
+magic_pdf/rw/S3ReaderWriter.py,sha256=_DmL45Ubio-_VsKD84KrqOQ-VNDUTzcXSrXfNMb5vww,5310
 magic_pdf/rw/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/spark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/spark/spark_api.py,sha256=eSLXTjMYW5Ya41VMIApRVfji1ZxEZXdH9ZdsL6fy5Kw,1131
-magic_pdf/train_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/train_utils/convert_to_train_format.py,sha256=ifo2FAoBMa_etCvz0O4v03xO6mHV8IPXYxHH7-OcHfk,2443
-magic_pdf/train_utils/extract_caption.py,sha256=gommEqIEWLplSDEJWD7_66daqlOBsWhpRBW1DHpkny4,1825
-magic_pdf/train_utils/remove_footer_header.py,sha256=pyeNNdJ-th3wl5Xwb10ZLYNaFN4-6BmahoMFE8VTNNs,5978
-magic_pdf/train_utils/vis_utils.py,sha256=MV9N9cT3ifJ35u7LFKGF9I_bOIQrtU1zcsxu2hj3aqM,10111
-magic_pdf-0.6.2b1.dist-info/LICENSE.md,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-magic_pdf-0.6.2b1.dist-info/METADATA,sha256=DVFHn5RBQilga9OZp87sGf4e4wAE-XT8QpB6KSVUgoo,11541
-magic_pdf-0.6.2b1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-magic_pdf-0.6.2b1.dist-info/entry_points.txt,sha256=NbSkSmE08UuTwdoJD8Uofq8iyufySA4x7jmIIk4YCzI,57
-magic_pdf-0.6.2b1.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
-magic_pdf-0.6.2b1.dist-info/RECORD,,
+magic_pdf/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/tools/cli.py,sha256=aVmurGAEyWT-MOv0MOaCRrfef1-jkRTpeVVWUsEVyeY,2157
+magic_pdf/tools/cli_dev.py,sha256=uDc4fDxVuOIrkaKRdjNAqyh9htyLd-fYDEfJBNFUYao,4149
+magic_pdf/tools/common.py,sha256=x4W-Tyo0A-TGsOjzlUGAhxiU2AisU3nBE3_2H_RLUO4,3801
+magic_pdf-0.7.0a1.dist-info/LICENSE.md,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+magic_pdf-0.7.0a1.dist-info/METADATA,sha256=NBLsixinI-5iHwdweKr13SM5qg6Jf-fWCwg5ihavlpY,12455
+magic_pdf-0.7.0a1.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+magic_pdf-0.7.0a1.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
+magic_pdf-0.7.0a1.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-0.7.0a1.dist-info/RECORD,,

{magic_pdf-0.6.2b1.dist-info → magic_pdf-0.7.0a1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: bdist_wheel (0.44.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

magic_pdf-0.7.0a1.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+magic-pdf = magic_pdf.tools.cli:cli
+magic-pdf-dev = magic_pdf.tools.cli_dev:cli