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

magic_pdf/dict2md/ocr_mkcontent.py

@@ -120,15 +120,20 @@ def ocr_mk_markdown_with_para_core_v2(paras_of_layout, mode, img_buket_path=""):
             if mode == 'nlp':
                 continue
             elif mode == 'mm':
+                table_caption = ''
                 for block in para_block['blocks']:  # 1st.拼table_caption
                     if block['type'] == BlockType.TableCaption:
-                        para_text += merge_para_with_text(block)
+                        table_caption = merge_para_with_text(block)
                 for block in para_block['blocks']:  # 2nd.拼table_body
                     if block['type'] == BlockType.TableBody:
                         for line in block['lines']:
                             for span in line['spans']:
                                 if span['type'] == ContentType.Table:
-                                    para_text += f"\n![]({join_path(img_buket_path, span['image_path'])})  \n"
+                                    # if processed by table model
+                                    if span.get('latex', ''):
+                                        para_text += f"\n\n$\n {span['latex']}\n$\n\n"
+                                    else:
+                                        para_text += f"\n![{table_caption}]({join_path(img_buket_path, span['image_path'])})  \n"
                 for block in para_block['blocks']:  # 3rd.拼table_footnote
                     if block['type'] == BlockType.TableFootnote:
                         para_text += merge_para_with_text(block)
@@ -163,7 +168,7 @@ def merge_para_with_text(para_block):
                 else:
                     content = ocr_escape_special_markdown_char(content)
             elif span_type == ContentType.InlineEquation:
-                content = f"${span['content']}$"
+                content = f" ${span['content']}$ "
             elif span_type == ContentType.InterlineEquation:
                 content = f"\n$$\n{span['content']}\n$$\n"
 
@@ -249,6 +254,8 @@ def para_to_standard_format_v2(para_block, img_buket_path, page_idx):
         }
         for block in para_block['blocks']:
             if block['type'] == BlockType.TableBody:
+                if block["lines"][0]["spans"][0].get('latex', ''):
+                    para_content['table_body'] = f"\n\n$\n {block['lines'][0]['spans'][0]['latex']}\n$\n\n"
                 para_content['img_path'] = join_path(img_buket_path, block["lines"][0]["spans"][0]['image_path'])
             if block['type'] == BlockType.TableCaption:
                 para_content['table_caption'] = merge_para_with_text(block)

magic_pdf/libs/config_reader.py

@@ -57,16 +57,6 @@ def get_bucket_name(path):
     return bucket
 
 
-def get_local_dir():
-    config = read_config()
-    local_dir = config.get("temp-output-dir")
-    if local_dir is None:
-        logger.warning(f"'temp-output-dir' not found in {CONFIG_FILE_NAME}, use '/tmp' as default")
-        return "/tmp"
-    else:
-        return local_dir
-
-
 def get_local_models_dir():
     config = read_config()
     models_dir = config.get("models-dir")
@@ -87,5 +77,15 @@ def get_device():
         return device
 
 
+def get_table_recog_config():
+    config = read_config()
+    table_config = config.get("table-config")
+    if table_config is None:
+        logger.warning(f"'table-config' not found in {CONFIG_FILE_NAME}, use 'False' as default")
+        return json.loads('{"is_table_recog_enable": false, "max_time": 400}')
+    else:
+        return table_config
+
+
 if __name__ == "__main__":
     ak, sk, endpoint = get_s3_config("llm-raw")

magic_pdf/libs/version.py

@@ -1 +1 @@
-__version__ = "0.6.2b1"
+__version__ = "0.7.0a1"

magic_pdf/model/doc_analyze_by_custom_model.py

@@ -4,7 +4,7 @@ import fitz
 import numpy as np
 from loguru import logger
 
-from magic_pdf.libs.config_reader import get_local_models_dir, get_device
+from magic_pdf.libs.config_reader import get_local_models_dir, get_device, get_table_recog_config
 from magic_pdf.model.model_list import MODEL
 import magic_pdf.model as model_config
 
@@ -84,7 +84,13 @@ def custom_model_init(ocr: bool = False, show_log: bool = False):
             # 从配置文件读取model-dir和device
             local_models_dir = get_local_models_dir()
             device = get_device()
-            custom_model = CustomPEKModel(ocr=ocr, show_log=show_log, models_dir=local_models_dir, device=device)
+            table_config = get_table_recog_config()
+            model_input = {"ocr": ocr,
+                           "show_log": show_log,
+                           "models_dir": local_models_dir,
+                           "device": device,
+                           "table_config": table_config}
+            custom_model = CustomPEKModel(**model_input)
         else:
             logger.error("Not allow model_name!")
             exit(1)

magic_pdf/model/magic_model.py

@@ -560,6 +560,10 @@ class MagicModel:
                 if category_id == 3:
                     span["type"] = ContentType.Image
                 elif category_id == 5:
+                    # 获取table模型结果
+                    latex = layout_det.get("latex", None)
+                    if latex:
+                        span["latex"] = latex
                     span["type"] = ContentType.Table
                 elif category_id == 13:
                     span["content"] = layout_det["latex"]

magic_pdf/model/pdf_extract_kit.py

@@ -2,6 +2,7 @@ from loguru import logger
 import os
 import time
 
+
 os.environ['NO_ALBUMENTATIONS_UPDATE'] = '1'  # 禁止albumentations检查更新
 try:
     import cv2
@@ -10,6 +11,7 @@ try:
     import numpy as np
     import torch
     import torchtext
+
     if torchtext.__version__ >= "0.18.0":
         torchtext.disable_torchtext_deprecation_warning()
     from PIL import Image
@@ -30,6 +32,12 @@ except ImportError as e:
 from magic_pdf.model.pek_sub_modules.layoutlmv3.model_init import Layoutlmv3_Predictor
 from magic_pdf.model.pek_sub_modules.post_process import get_croped_image, latex_rm_whitespace
 from magic_pdf.model.pek_sub_modules.self_modify import ModifiedPaddleOCR
+from magic_pdf.model.pek_sub_modules.structeqtable.StructTableModel import StructTableModel
+
+
+def table_model_init(model_path, max_time=400, _device_='cpu'):
+    table_model = StructTableModel(model_path, max_time=max_time, device=_device_)
+    return table_model
 
 
 def mfd_model_init(weight):
@@ -95,10 +103,12 @@ class CustomPEKModel:
         # 初始化解析配置
         self.apply_layout = kwargs.get("apply_layout", self.configs["config"]["layout"])
         self.apply_formula = kwargs.get("apply_formula", self.configs["config"]["formula"])
+        self.table_config = kwargs.get("table_config", self.configs["config"]["table_config"])
+        self.apply_table = self.table_config.get("is_table_recog_enable", False)
         self.apply_ocr = ocr
         logger.info(
-            "DocAnalysis init, this may take some times. apply_layout: {}, apply_formula: {}, apply_ocr: {}".format(
-                self.apply_layout, self.apply_formula, self.apply_ocr
+            "DocAnalysis init, this may take some times. apply_layout: {}, apply_formula: {}, apply_ocr: {}, apply_table: {}".format(
+                self.apply_layout, self.apply_formula, self.apply_ocr, self.apply_table
             )
         )
         assert self.apply_layout, "DocAnalysis must contain layout model."
@@ -129,6 +139,11 @@ class CustomPEKModel:
         if self.apply_ocr:
             self.ocr_model = ModifiedPaddleOCR(show_log=show_log)
 
+        # init structeqtable
+        if self.apply_table:
+            max_time = self.table_config.get("max_time", 400)
+            self.table_model = table_model_init(str(os.path.join(models_dir, self.configs["weights"]["table"])),
+                                                max_time=max_time, _device_=self.device)
         logger.info('DocAnalysis init done!')
 
     def __call__(self, image):
@@ -249,4 +264,32 @@ class CustomPEKModel:
             ocr_cost = round(time.time() - ocr_start, 2)
             logger.info(f"ocr cost: {ocr_cost}")
 
+        # 表格识别 table recognition
+        if self.apply_table:
+            pil_img = Image.fromarray(image)
+            for layout in layout_res:
+                if layout.get("category_id", -1) == 5:
+                    poly = layout["poly"]
+                    xmin, ymin = int(poly[0]), int(poly[1])
+                    xmax, ymax = int(poly[4]), int(poly[5])
+
+                    paste_x = 50
+                    paste_y = 50
+                    # 创建一个宽高各多50的白色背景 create a whiteboard with 50 larger width and length
+                    new_width = xmax - xmin + paste_x * 2
+                    new_height = ymax - ymin + paste_y * 2
+                    new_image = Image.new('RGB', (new_width, new_height), 'white')
+
+                    # 裁剪图像 crop image
+                    crop_box = (xmin, ymin, xmax, ymax)
+                    cropped_img = pil_img.crop(crop_box)
+                    new_image.paste(cropped_img, (paste_x, paste_y))
+                    start_time = time.time()
+                    logger.info("------------------table recognition processing begins-----------------")
+                    latex_code = self.table_model.image2latex(new_image)[0]
+                    end_time = time.time()
+                    run_time = end_time - start_time
+                    logger.info(f"------------table recognition processing ends within {run_time}s-----")
+                    layout["latex"] = latex_code
+
         return layout_res

magic_pdf/model/pek_sub_modules/structeqtable/StructTableModel.py

@@ -0,0 +1,22 @@
+from struct_eqtable.model import StructTable
+from pypandoc import convert_text
+class StructTableModel:
+    def __init__(self, model_path, max_new_tokens=2048, max_time=400, device = 'cpu'):
+        # init
+        self.model_path = model_path
+        self.max_new_tokens = max_new_tokens # maximum output tokens length
+        self.max_time = max_time # timeout for processing in seconds
+        if device == 'cuda':
+            self.model = StructTable(self.model_path, self.max_new_tokens, self.max_time).cuda()
+        else:
+            self.model = StructTable(self.model_path, self.max_new_tokens, self.max_time)
+
+    def image2latex(self, image) -> str:
+        #
+        table_latex = self.model.forward(image)
+        return table_latex
+
+    def image2html(self, image) -> str:
+        table_latex = self.image2latex(image)
+        table_html = convert_text(table_latex, 'html', format='latex')
+        return table_html

magic_pdf/resources/model_config/model_configs.yaml

@@ -2,8 +2,12 @@ config:
   device: cpu
   layout: True
   formula: True
+  table_config:
+    is_table_recog_enable: False
+    max_time: 400
 
 weights:
   layout: Layout/model_final.pth
   mfd: MFD/weights.pt
   mfr: MFR/UniMERNet
+  table: TabRec/StructEqTable

magic_pdf/rw/AbsReaderWriter.py

@@ -2,33 +2,16 @@ from abc import ABC, abstractmethod
 
 
 class AbsReaderWriter(ABC):
-    """
-    同时支持二进制和文本读写的抽象类
-    """
     MODE_TXT = "text"
     MODE_BIN = "binary"
-
-    def __init__(self, parent_path):
-        # 初始化代码可以在这里添加，如果需要的话
-        self.parent_path = parent_path # 对于本地目录是父目录，对于s3是会写到这个path下。
-
     @abstractmethod
     def read(self, path: str, mode=MODE_TXT):
-        """
-        无论对于本地还是s3的路径，检查如果path是绝对路径，那么就不再 拼接parent_path, 如果是相对路径就拼接parent_path
-        """
         raise NotImplementedError
 
     @abstractmethod
     def write(self, content: str, path: str, mode=MODE_TXT):
-        """
-        无论对于本地还是s3的路径，检查如果path是绝对路径，那么就不再 拼接parent_path, 如果是相对路径就拼接parent_path
-        """
         raise NotImplementedError
 
     @abstractmethod
-    def read_jsonl(self, path: str, byte_start=0, byte_end=None, encoding='utf-8'):
-        """
-        无论对于本地还是s3的路径，检查如果path是绝对路径，那么就不再 拼接parent_path, 如果是相对路径就拼接parent_path
-        """
+    def read_offset(self, path: str, offset=0, limit=None) -> bytes:
         raise NotImplementedError

magic_pdf/rw/DiskReaderWriter.py

@@ -3,34 +3,29 @@ from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
 from loguru import logger
 
 
-MODE_TXT = "text"
-MODE_BIN = "binary"
-
-
 class DiskReaderWriter(AbsReaderWriter):
-
     def __init__(self, parent_path, encoding="utf-8"):
         self.path = parent_path
         self.encoding = encoding
 
-    def read(self, path, mode=MODE_TXT):
+    def read(self, path, mode=AbsReaderWriter.MODE_TXT):
         if os.path.isabs(path):
             abspath = path
         else:
             abspath = os.path.join(self.path, path)
         if not os.path.exists(abspath):
-            logger.error(f"文件 {abspath} 不存在")
-            raise Exception(f"文件 {abspath} 不存在")
-        if mode == MODE_TXT:
+            logger.error(f"file {abspath} not exists")
+            raise Exception(f"file {abspath} no exists")
+        if mode == AbsReaderWriter.MODE_TXT:
             with open(abspath, "r", encoding=self.encoding) as f:
                 return f.read()
-        elif mode == MODE_BIN:
+        elif mode == AbsReaderWriter.MODE_BIN:
             with open(abspath, "rb") as f:
                 return f.read()
         else:
             raise ValueError("Invalid mode. Use 'text' or 'binary'.")
 
-    def write(self, content, path, mode=MODE_TXT):
+    def write(self, content, path, mode=AbsReaderWriter.MODE_TXT):
         if os.path.isabs(path):
             abspath = path
         else:
@@ -38,29 +33,42 @@ class DiskReaderWriter(AbsReaderWriter):
         directory_path = os.path.dirname(abspath)
         if not os.path.exists(directory_path):
             os.makedirs(directory_path)
-        if mode == MODE_TXT:
+        if mode == AbsReaderWriter.MODE_TXT:
             with open(abspath, "w", encoding=self.encoding, errors="replace") as f:
                 f.write(content)
 
-        elif mode == MODE_BIN:
+        elif mode == AbsReaderWriter.MODE_BIN:
             with open(abspath, "wb") as f:
                 f.write(content)
         else:
             raise ValueError("Invalid mode. Use 'text' or 'binary'.")
 
-    def read_jsonl(self, path: str, byte_start=0, byte_end=None, encoding="utf-8"):
-        return self.read(path)
+    def read_offset(self, path: str, offset=0, limit=None):
+        abspath = path
+        if not os.path.isabs(path):
+            abspath = os.path.join(self.path, path)
+        with open(abspath, "rb") as f:
+            f.seek(offset)
+            return f.read(limit)
 
 
-# 使用示例
 if __name__ == "__main__":
-    file_path = "io/test/example.txt"
-    drw = DiskReaderWriter("D:\projects\papayfork\Magic-PDF\magic_pdf")
+    if 0:
+        file_path = "io/test/example.txt"
+        drw = DiskReaderWriter("D:\projects\papayfork\Magic-PDF\magic_pdf")
+
+        # 写入内容到文件
+        drw.write(b"Hello, World!", path="io/test/example.txt", mode="binary")
+
+        # 从文件读取内容
+        content = drw.read(path=file_path)
+        if content:
+            logger.info(f"从 {file_path} 读取的内容: {content}")
+    if 1:
+        drw = DiskReaderWriter("/opt/data/pdf/resources/test/io/")
+        content_bin = drw.read_offset("1.txt")
+        assert content_bin == b"ABCD!"
 
-    # 写入内容到文件
-    drw.write(b"Hello, World!", path="io/test/example.txt", mode="binary")
+        content_bin = drw.read_offset("1.txt", offset=1, limit=2)
+        assert content_bin == b"BC"
 
-    # 从文件读取内容
-    content = drw.read(path=file_path)
-    if content:
-        logger.info(f"从 {file_path} 读取的内容: {content}")

magic_pdf/rw/S3ReaderWriter.py

@@ -2,16 +2,18 @@ from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
 from magic_pdf.libs.commons import parse_aws_param, parse_bucket_key, join_path
 import boto3
 from loguru import logger
-from boto3.s3.transfer import TransferConfig
 from botocore.config import Config
-import os
-
-MODE_TXT = "text"
-MODE_BIN = "binary"
 
 
 class S3ReaderWriter(AbsReaderWriter):
-    def __init__(self, ak: str, sk: str, endpoint_url: str, addressing_style: str = 'auto', parent_path: str = ''):
+    def __init__(
+        self,
+        ak: str,
+        sk: str,
+        endpoint_url: str,
+        addressing_style: str = "auto",
+        parent_path: str = "",
+    ):
         self.client = self._get_client(ak, sk, endpoint_url, addressing_style)
         self.path = parent_path
 
@@ -21,12 +23,14 @@ class S3ReaderWriter(AbsReaderWriter):
             aws_access_key_id=ak,
             aws_secret_access_key=sk,
             endpoint_url=endpoint_url,
-            config=Config(s3={"addressing_style": addressing_style},
-                          retries={'max_attempts': 5, 'mode': 'standard'}),
+            config=Config(
+                s3={"addressing_style": addressing_style},
+                retries={"max_attempts": 5, "mode": "standard"},
+            ),
         )
         return s3_client
 
-    def read(self, s3_relative_path, mode=MODE_TXT, encoding="utf-8"):
+    def read(self, s3_relative_path, mode=AbsReaderWriter.MODE_TXT, encoding="utf-8"):
         if s3_relative_path.startswith("s3://"):
             s3_path = s3_relative_path
         else:
@@ -34,22 +38,22 @@ class S3ReaderWriter(AbsReaderWriter):
         bucket_name, key = parse_bucket_key(s3_path)
         res = self.client.get_object(Bucket=bucket_name, Key=key)
         body = res["Body"].read()
-        if mode == MODE_TXT:
+        if mode == AbsReaderWriter.MODE_TXT:
             data = body.decode(encoding)  # Decode bytes to text
-        elif mode == MODE_BIN:
+        elif mode == AbsReaderWriter.MODE_BIN:
             data = body
         else:
             raise ValueError("Invalid mode. Use 'text' or 'binary'.")
         return data
 
-    def write(self, content, s3_relative_path, mode=MODE_TXT, encoding="utf-8"):
+    def write(self, content, s3_relative_path, mode=AbsReaderWriter.MODE_TXT, encoding="utf-8"):
         if s3_relative_path.startswith("s3://"):
             s3_path = s3_relative_path
         else:
             s3_path = join_path(self.path, s3_relative_path)
-        if mode == MODE_TXT:
+        if mode == AbsReaderWriter.MODE_TXT:
             body = content.encode(encoding)  # Encode text data as bytes
-        elif mode == MODE_BIN:
+        elif mode == AbsReaderWriter.MODE_BIN:
             body = content
         else:
             raise ValueError("Invalid mode. Use 'text' or 'binary'.")
@@ -57,51 +61,82 @@ class S3ReaderWriter(AbsReaderWriter):
         self.client.put_object(Body=body, Bucket=bucket_name, Key=key)
         logger.info(f"内容已写入 {s3_path} ")
 
-    def read_jsonl(self, path: str, byte_start=0, byte_end=None, mode=MODE_TXT, encoding='utf-8'):
+    def read_offset(self, path: str, offset=0, limit=None) -> bytes:
         if path.startswith("s3://"):
             s3_path = path
         else:
             s3_path = join_path(self.path, path)
         bucket_name, key = parse_bucket_key(s3_path)
 
-        range_header = f'bytes={byte_start}-{byte_end}' if byte_end else f'bytes={byte_start}-'
+        range_header = (
+            f"bytes={offset}-{offset+limit-1}" if limit else f"bytes={offset}-"
+        )
         res = self.client.get_object(Bucket=bucket_name, Key=key, Range=range_header)
-        body = res["Body"].read()
-        if mode == MODE_TXT:
-            data = body.decode(encoding)  # Decode bytes to text
-        elif mode == MODE_BIN:
-            data = body
-        else:
-            raise ValueError("Invalid mode. Use 'text' or 'binary'.")
-        return data
+        return res["Body"].read()
 
 
 if __name__ == "__main__":
-    # Config the connection info
-    ak = ""
-    sk = ""
-    endpoint_url = ""
-    addressing_style = "auto"
-    bucket_name = ""
-    # Create an S3ReaderWriter object
-    s3_reader_writer = S3ReaderWriter(ak, sk, endpoint_url, addressing_style, "s3://bucket_name/")
+    if 0:
+        # Config the connection info
+        ak = ""
+        sk = ""
+        endpoint_url = ""
+        addressing_style = "auto"
+        bucket_name = ""
+        # Create an S3ReaderWriter object
+        s3_reader_writer = S3ReaderWriter(
+            ak, sk, endpoint_url, addressing_style, "s3://bucket_name/"
+        )
 
-    # Write text data to S3
-    text_data = "This is some text data"
-    s3_reader_writer.write(data=text_data, s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json", mode=MODE_TXT)
+        # Write text data to S3
+        text_data = "This is some text data"
+        s3_reader_writer.write(
+            text_data,
+            s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json",
+            mode=AbsReaderWriter.MODE_TXT,
+        )
+
+        # Read text data from S3
+        text_data_read = s3_reader_writer.read(
+            s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json", mode=AbsReaderWriter.MODE_TXT
+        )
+        logger.info(f"Read text data from S3: {text_data_read}")
+        # Write binary data to S3
+        binary_data = b"This is some binary data"
+        s3_reader_writer.write(
+            text_data,
+            s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json",
+            mode=AbsReaderWriter.MODE_BIN,
+        )
 
-    # Read text data from S3
-    text_data_read = s3_reader_writer.read(s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json", mode=MODE_TXT)
-    logger.info(f"Read text data from S3: {text_data_read}")
-    # Write binary data to S3
-    binary_data = b"This is some binary data"
-    s3_reader_writer.write(data=text_data, s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json", mode=MODE_BIN)
+        # Read binary data from S3
+        binary_data_read = s3_reader_writer.read(
+            s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json", mode=AbsReaderWriter.MODE_BIN
+        )
+        logger.info(f"Read binary data from S3: {binary_data_read}")
+
+        # Range Read text data from S3
+        binary_data_read = s3_reader_writer.read_offset(
+            path=f"s3://{bucket_name}/ebook/test/test.json", offset=0, limit=10
+        )
+        logger.info(f"Read binary data from S3: {binary_data_read}")
+    if 1:
+        import os
+        import json
 
-    # Read binary data from S3
-    binary_data_read = s3_reader_writer.read(s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json", mode=MODE_BIN)
-    logger.info(f"Read binary data from S3: {binary_data_read}")
+        ak = os.getenv("AK", "")
+        sk = os.getenv("SK", "")
+        endpoint_url = os.getenv("ENDPOINT", "")
+        bucket = os.getenv("S3_BUCKET", "")
+        prefix = os.getenv("S3_PREFIX", "")
+        key_basename = os.getenv("S3_KEY_BASENAME", "")
+        s3_reader_writer = S3ReaderWriter(
+            ak, sk, endpoint_url, "auto", f"s3://{bucket}/{prefix}"
+        )
+        content_bin = s3_reader_writer.read_offset(key_basename)
+        assert content_bin[:10] == b'{"track_id'
+        assert content_bin[-10:] == b'r":null}}\n'
 
-    # Range Read text data from S3
-    binary_data_read = s3_reader_writer.read_jsonl(path=f"s3://{bucket_name}/ebook/test/test.json",
-                                                   byte_start=0, byte_end=10, mode=MODE_BIN)
-    logger.info(f"Read binary data from S3: {binary_data_read}")
+        content_bin = s3_reader_writer.read_offset(key_basename, offset=424, limit=426)
+        jso = json.dumps(content_bin.decode("utf-8"))
+        print(jso)

magic_pdf/tools/cli.py

@@ -0,0 +1,79 @@
+import os
+import click
+from loguru import logger
+from pathlib import Path
+
+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__
+
+
+@click.command()
+@click.version_option(__version__, "--version", "-v", help="display the version and exit")
+@click.option(
+    "-p",
+    "--path",
+    "path",
+    type=click.Path(exists=True),
+    required=True,
+    help="local pdf filepath or directory",
+)
+@click.option(
+    "-o",
+    "--output-dir",
+    "output_dir",
+    type=str,
+    help="output local directory",
+    default="",
+)
+@click.option(
+    "-m",
+    "--method",
+    "method",
+    type=parse_pdf_methods,
+    help="""the method for parsing pdf. 
+ocr: using ocr technique to extract information from pdf.
+txt: suitable for the text-based pdf only and outperform ocr.
+auto: automatically choose the best method for parsing pdf from ocr and txt.
+without method specified, auto will be used by default.""",
+    default="auto",
+)
+def cli(path, output_dir, method):
+    model_config.__use_inside_model__ = True
+    model_config.__model_mode__ = "full"
+    if output_dir == "":
+        if os.path.isdir(path):
+            output_dir = os.path.join(path, "output")
+        else:
+            output_dir = os.path.join(os.path.dirname(path), "output")
+
+    def read_fn(path):
+        disk_rw = DiskReaderWriter(os.path.dirname(path))
+        return disk_rw.read(os.path.basename(path), AbsReaderWriter.MODE_BIN)
+
+    def parse_doc(doc_path: str):
+        try:
+            file_name = str(Path(doc_path).stem)
+            pdf_data = read_fn(doc_path)
+            do_parse(
+                output_dir,
+                file_name,
+                pdf_data,
+                [],
+                method,
+            )
+
+        except Exception as e:
+            logger.exception(e)
+
+    if os.path.isdir(path):
+        for doc_path in Path(path).glob("*.pdf"):
+            parse_doc(doc_path)
+    else:
+        parse_doc(path)
+
+
+if __name__ == "__main__":
+    cli()