magic-pdf 0.7.0b1__py3-none-any.whl → 0.7.1__py3-none-any.whl

magic_pdf/dict2md/ocr_mkcontent.py

@@ -132,6 +132,8 @@ def ocr_mk_markdown_with_para_core_v2(paras_of_layout, mode, img_buket_path=""):
                                     # if processed by table model
                                     if span.get('latex', ''):
                                         para_text += f"\n\n$\n {span['latex']}\n$\n\n"
+                                    elif span.get('html', ''):
+                                        para_text += f"\n\n{span['html']}\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
@@ -256,6 +258,8 @@ def para_to_standard_format_v2(para_block, img_buket_path, page_idx):
             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"
+                elif block["lines"][0]["spans"][0].get('html', ''):
+                    para_content['table_body'] = f"\n\n{block['lines'][0]['spans'][0]['html']}\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/Constants.py

@@ -10,5 +10,31 @@ block维度自定义字段
 # block中lines是否被删除
 LINES_DELETED = "lines_deleted"
 
+# struct eqtable
+STRUCT_EQTABLE = "struct_eqtable"
+
 # table recognition max time default value
-TABLE_MAX_TIME_VALUE = 400
+TABLE_MAX_TIME_VALUE = 400
+
+# pp_table_result_max_length
+TABLE_MAX_LEN = 480
+
+# pp table structure algorithm
+TABLE_MASTER = "TableMaster"
+
+# table master structure dict
+TABLE_MASTER_DICT = "table_master_structure_dict.txt"
+
+# table master dir
+TABLE_MASTER_DIR = "table_structure_tablemaster_infer/"
+
+# pp detect model dir
+DETECT_MODEL_DIR = "ch_PP-OCRv3_det_infer"
+
+# pp rec model dir
+REC_MODEL_DIR = "ch_PP-OCRv3_rec_infer"
+
+# pp rec char dict path
+REC_CHAR_DICT = "ppocr_keys_v1.txt"
+
+

magic_pdf/libs/version.py

@@ -1 +1 @@
-__version__ = "0.7.0b1"
+__version__ = "0.7.1"

magic_pdf/model/magic_model.py

@@ -562,8 +562,11 @@ class MagicModel:
                 elif category_id == 5:
                     # 获取table模型结果
                     latex = layout_det.get("latex", None)
+                    html = layout_det.get("html", None)
                     if latex:
                         span["latex"] = latex
+                    elif html:
+                        span["html"] = html
                     span["type"] = ContentType.Table
                 elif category_id == 13:
                     span["content"] = layout_det["latex"]

magic_pdf/model/pdf_extract_kit.py

@@ -2,7 +2,7 @@ from loguru import logger
 import os
 import time
 
-from magic_pdf.libs.Constants import TABLE_MAX_TIME_VALUE
+from magic_pdf.libs.Constants import *
 
 os.environ['NO_ALBUMENTATIONS_UPDATE'] = '1'  # 禁止albumentations检查更新
 try:
@@ -34,10 +34,18 @@ from magic_pdf.model.pek_sub_modules.layoutlmv3.model_init import Layoutlmv3_Pre
 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, _device_='cpu'):
-    table_model = StructTableModel(model_path, max_time=max_time, device=_device_)
+from magic_pdf.model.ppTableModel import ppTableModel
+
+
+def table_model_init(table_model_type, model_path, max_time, _device_='cpu'):
+    if table_model_type == STRUCT_EQTABLE:
+        table_model = StructTableModel(model_path, max_time=max_time, device=_device_)
+    else:
+        config = {
+            "model_dir": model_path,
+            "device": _device_
+        }
+        table_model = ppTableModel(config)
     return table_model
 
 
@@ -104,9 +112,11 @@ 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"])
+        # table config
         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.table_max_time = self.table_config.get("max_time", TABLE_MAX_TIME_VALUE)
+        self.table_model_type = self.table_config.get("model", TABLE_MASTER)
         self.apply_ocr = ocr
         logger.info(
             "DocAnalysis init, this may take some times. apply_layout: {}, apply_formula: {}, apply_ocr: {}, apply_table: {}".format(
@@ -141,10 +151,11 @@ class CustomPEKModel:
         if self.apply_ocr:
             self.ocr_model = ModifiedPaddleOCR(show_log=show_log)
 
-        # init structeqtable
+        # init table model
         if self.apply_table:
-            self.table_model = table_model_init(str(os.path.join(models_dir, self.configs["weights"]["table"])),
-                                                max_time = self.table_max_time, _device_=self.device)
+            table_model_dir = self.configs["weights"][self.table_model_type]
+            self.table_model = table_model_init(self.table_model_type, str(os.path.join(models_dir, table_model_dir)),
+                                                max_time=self.table_max_time, _device_=self.device)
         logger.info('DocAnalysis init done!')
 
     def __call__(self, image):
@@ -278,16 +289,28 @@ class CustomPEKModel:
                 new_image, _ = crop_img(res, pil_img)
                 single_table_start_time = time.time()
                 logger.info("------------------table recognition processing begins-----------------")
+                latex_code = None
+                html_code = None
                 with torch.no_grad():
-                    latex_code = self.table_model.image2latex(new_image)[0]
+                    if self.table_model_type == STRUCT_EQTABLE:
+                        latex_code = self.table_model.image2latex(new_image)[0]
+                    else:
+                        html_code = self.table_model.img2html(new_image)
                 run_time = time.time() - single_table_start_time
                 logger.info(f"------------table recognition processing ends within {run_time}s-----")
                 if run_time > self.table_max_time:
                     logger.warning(f"------------table recognition processing exceeds max time {self.table_max_time}s----------")
                 # 判断是否返回正常
-                expected_ending = latex_code.strip().endswith('end{tabular}') or latex_code.strip().endswith('end{table}')
-                if latex_code and expected_ending:
-                    res["latex"] = latex_code
+
+                if latex_code:
+                    expected_ending = latex_code.strip().endswith('end{tabular}') or latex_code.strip().endswith(
+                        'end{table}')
+                    if expected_ending:
+                        res["latex"] = latex_code
+                    else:
+                        logger.warning(f"------------table recognition processing fails----------")
+                elif html_code:
+                    res["html"] = html_code
                 else:
                     logger.warning(f"------------table recognition processing fails----------")
             table_cost = round(time.time() - table_start, 2)

magic_pdf/model/pek_sub_modules/structeqtable/StructTableModel.py

@@ -12,7 +12,6 @@ class StructTableModel:
             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
 

magic_pdf/model/ppTableModel.py

@@ -0,0 +1,67 @@
+from paddleocr.ppstructure.table.predict_table import TableSystem
+from paddleocr.ppstructure.utility import init_args
+from magic_pdf.libs.Constants import *
+import os
+from PIL import Image
+import numpy as np
+
+
+class ppTableModel(object):
+    """
+        This class is responsible for converting image of table into HTML format using a pre-trained model.
+
+        Attributes:
+        - table_sys: An instance of TableSystem initialized with parsed arguments.
+
+        Methods:
+        - __init__(config): Initializes the model with configuration parameters.
+        - img2html(image): Converts a PIL Image or NumPy array to HTML string.
+        - parse_args(**kwargs): Parses configuration arguments.
+    """
+
+    def __init__(self, config):
+        """
+        Parameters:
+        - config (dict): Configuration dictionary containing model_dir and device.
+        """
+        args = self.parse_args(**config)
+        self.table_sys = TableSystem(args)
+
+    def img2html(self, image):
+        """
+        Parameters:
+        - image (PIL.Image or np.ndarray): The image of the table to be converted.
+
+        Return:
+        - HTML (str): A string representing the HTML structure with content of the table.
+        """
+        if isinstance(image, Image.Image):
+            image = np.array(image)
+        pred_res, _ = self.table_sys(image)
+        pred_html = pred_res["html"]
+        res = '<td><table  border="1">' + pred_html.replace("<html><body><table>", "").replace("</table></body></html>",
+                                                                                               "") + "</table></td>\n"
+        return res
+
+    def parse_args(self, **kwargs):
+        parser = init_args()
+        model_dir = kwargs.get("model_dir")
+        table_model_dir = os.path.join(model_dir, TABLE_MASTER_DIR)
+        table_char_dict_path = os.path.join(model_dir, TABLE_MASTER_DICT)
+        det_model_dir = os.path.join(model_dir, DETECT_MODEL_DIR)
+        rec_model_dir = os.path.join(model_dir, REC_MODEL_DIR)
+        rec_char_dict_path = os.path.join(model_dir, REC_CHAR_DICT)
+        device = kwargs.get("device", "cpu")
+        use_gpu = True if device == "cuda" else False
+        config = {
+            "use_gpu": use_gpu,
+            "table_max_len": kwargs.get("table_max_len", TABLE_MAX_LEN),
+            "table_algorithm": TABLE_MASTER,
+            "table_model_dir": table_model_dir,
+            "table_char_dict_path": table_char_dict_path,
+            "det_model_dir": det_model_dir,
+            "rec_model_dir": rec_model_dir,
+            "rec_char_dict_path": rec_char_dict_path,
+        }
+        parser.set_defaults(**config)
+        return parser.parse_args([])

magic_pdf/para/para_split_v2.py

@@ -100,59 +100,62 @@ def __detect_list_lines(lines, new_layout_bboxes, lang):
 
     if lang != 'en':
         return lines, None
-    else:
-        total_lines = len(lines)
-        line_fea_encode = []
-        """
-        对每一行进行特征编码，编码规则如下：
-        1. 如果行顶格，且大写字母开头或者数字开头，编码为1
-        2. 如果顶格，其他非大写开头编码为4
-        3. 如果非顶格，首字符大写，编码为2
-        4. 如果非顶格，首字符非大写编码为3
-        """
-        if len(lines) > 0:
-            x_map_tag_dict, min_x_tag = cluster_line_x(lines)
-        for l in lines:
-            span_text = __get_span_text(l['spans'][0])
-            first_char = span_text[0]
-            layout = __find_layout_bbox_by_line(l['bbox'], new_layout_bboxes)
-            if not layout:
-                line_fea_encode.append(0)
+
+    total_lines = len(lines)
+    line_fea_encode = []
+    """
+    对每一行进行特征编码，编码规则如下：
+    1. 如果行顶格，且大写字母开头或者数字开头，编码为1
+    2. 如果顶格，其他非大写开头编码为4
+    3. 如果非顶格，首字符大写，编码为2
+    4. 如果非顶格，首字符非大写编码为3
+    """
+    if len(lines) > 0:
+        x_map_tag_dict, min_x_tag = cluster_line_x(lines)
+    for l in lines:
+        span_text = __get_span_text(l['spans'][0])
+        if not span_text:
+            line_fea_encode.append(0)
+            continue
+        first_char = span_text[0]
+        layout = __find_layout_bbox_by_line(l['bbox'], new_layout_bboxes)
+        if not layout:
+            line_fea_encode.append(0)
+        else:
+            #
+            if x_map_tag_dict[round(l['bbox'][0])] == min_x_tag:
+                # if first_char.isupper() or first_char.isdigit() or not first_char.isalnum():
+                if not first_char.isalnum() or if_match_reference_list(span_text):
+                    line_fea_encode.append(1)
+                else:
+                    line_fea_encode.append(4)
             else:
-                #
-                if x_map_tag_dict[round(l['bbox'][0])] == min_x_tag:
-                    # if first_char.isupper() or first_char.isdigit() or not first_char.isalnum():
-                    if not first_char.isalnum() or if_match_reference_list(span_text):
-                        line_fea_encode.append(1)
-                    else:
-                        line_fea_encode.append(4)
+                if first_char.isupper():
+                    line_fea_encode.append(2)
                 else:
-                    if first_char.isupper():
-                        line_fea_encode.append(2)
-                    else:
-                        line_fea_encode.append(3)
+                    line_fea_encode.append(3)
 
-        # 然后根据编码进行分段, 选出来 1,2,3连续出现至少2次的行，认为是列表。
+    # 然后根据编码进行分段, 选出来 1,2,3连续出现至少2次的行，认为是列表。
 
-        list_indice, list_start_idx = find_repeating_patterns2(line_fea_encode)
-        if len(list_indice) > 0:
+    list_indice, list_start_idx = find_repeating_patterns2(line_fea_encode)
+    if len(list_indice) > 0:
+        if debug_able:
+            logger.info(f"发现了列表，列表行数：{list_indice}， {list_start_idx}")
+
+    # TODO check一下这个特列表里缩进的行左侧是不是对齐的。
+    segments = []
+    for start, end in list_indice:
+        for i in range(start, end + 1):
+            if i > 0:
+                if line_fea_encode[i] == 4:
+                    if debug_able:
+                        logger.info(f"列表行的第{i}行不是顶格的")
+                    break
+        else:
             if debug_able:
-                logger.info(f"发现了列表，列表行数：{list_indice}， {list_start_idx}")
-
-        # TODO check一下这个特列表里缩进的行左侧是不是对齐的。
-        segments = []
-        for start, end in list_indice:
-            for i in range(start, end + 1):
-                if i > 0:
-                    if line_fea_encode[i] == 4:
-                        if debug_able:
-                            logger.info(f"列表行的第{i}行不是顶格的")
-                        break
-            else:
-                if debug_able:
-                    logger.info(f"列表行的第{start}到第{end}行是列表")
+                logger.info(f"列表行的第{start}到第{end}行是列表")
 
-        return split_indices(total_lines, list_indice), list_start_idx
+    return split_indices(total_lines, list_indice), list_start_idx
 
 
 def cluster_line_x(lines: list) -> dict:

magic_pdf/resources/model_config/model_configs.yaml

@@ -3,6 +3,7 @@ config:
   layout: True
   formula: True
   table_config:
+    model: TableMaster
     is_table_recog_enable: False
     max_time: 400
 
@@ -10,4 +11,5 @@ weights:
   layout: Layout/model_final.pth
   mfd: MFD/weights.pt
   mfr: MFR/UniMERNet
-  table: TabRec/StructEqTable
+  struct_eqtable: TabRec/StructEqTable
+  TableMaster: TabRec/TableMaster

{magic_pdf-0.7.0b1.dist-info → magic_pdf-0.7.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 0.7.0b1
+Version: 0.7.1
 Summary: A practical tool for converting PDF to Markdown
 Home-page: https://github.com/opendatalab/MinerU
 Requires-Python: >=3.9
@@ -64,6 +64,7 @@ Requires-Dist: paddlepaddle==2.6.1; (platform_system == "Windows" or platform_sy
 </div>
 
 # Changelog
+- 2024/08/30: Version 0.7.1 released, add paddle tablemaster table recognition option
 - 2024/08/09: Version 0.7.0b1 released, simplified installation process, added table recognition functionality
 - 2024/08/01: Version 0.6.2b1 released, optimized dependency conflict issues and installation documentation
 - 2024/07/05: Initial open-source release
@@ -205,7 +206,7 @@ In non-mainline environments, due to the diversity of hardware and software conf
 ```bash
 conda create -n MinerU python=3.10
 conda activate MinerU
-pip install magic-pdf[full]==0.7.0b1 --extra-index-url https://wheels.myhloli.com
+pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
 ```
 #### 2. Download model weight files
 
@@ -234,6 +235,7 @@ Find the `magic-pdf.json` file in your user directory and configure the "models-
   // other config
   "models-dir": "D:/models",
   "table-config": {
+        "model": "TableMaster", // Another option of this value is 'struct_eqtable'
         "is_table_recog_enable": false, // Table recognition is disabled by default, modify this value to enable it
         "max_time": 400
     }
@@ -345,13 +347,7 @@ TODO
 - Comic books, art books, elementary school textbooks, and exercise books are not well-parsed yet
 - Enabling OCR may produce better results in PDFs with a high density of formulas
 - If you are processing PDFs with a large number of formulas, it is strongly recommended to enable the OCR function. When using PyMuPDF to extract text, overlapping text lines can occur, leading to inaccurate formula insertion positions.
-- **Table Recognition** is currently in the testing phase; recognition speed is slow, and accuracy needs improvement. Below are some performance test results in an Ubuntu 22.04 LTS + Intel(R) Xeon(R) Platinum 8352V CPU @ 2.10GHz + NVIDIA GeForce RTX 4090 environment for reference.
 
-| Table Size     | Parsing Time        | 
-|---------------|----------------------------| 
-| 6\*5 55kb     | 37s                   | 
-| 16\*12 284kb  | 3m18s                 | 
-| 44\*7 559kb   | 4m12s                 | 
 
 # FAQ
 [FAQ in Chinese](docs/FAQ_zh_cn.md)

{magic_pdf-0.7.0b1.dist-info → magic_pdf-0.7.1.dist-info}/RECORD

@@ -5,7 +5,7 @@ magic_pdf/pdf_parse_union_core.py,sha256=jNly6l9pGcCf7wr6s6PgQhITJZ1m9PaI32Q26zx
 magic_pdf/user_api.py,sha256=CVQH-VSiZpz0bSkyMT4czk1epZriIPSJsLsPbluPa9Q,3054
 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=mq6tACGkL383bdUla7xOkRXRTBBydRtdbgIHwkk_daM,16169
+magic_pdf/dict2md/ocr_mkcontent.py,sha256=jg_v2Bj62xBObg0LDayvqUVX_O9DrIBli5Z9_i7Qduw,16479
 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
@@ -15,7 +15,7 @@ magic_pdf/layout/layout_det_utils.py,sha256=NCYBTvsrULE3Cue53aMD1MfXTmOL9Xy0nivl
 magic_pdf/layout/layout_sort.py,sha256=ovqRX1xcRA7E7s8VvsI7ZNbaNSElJe07bApCh5hxwIE,33533
 magic_pdf/layout/layout_spiler_recog.py,sha256=QjBSgB-a7J2yjUR1eaCs9ZD7URtiRnV6W934hpAeuC4,3067
 magic_pdf/layout/mcol_sort.py,sha256=ADnLisBJBHXDKYChcf2lzTb_TC_vZ4q89_CSN8mwEJc,11331
-magic_pdf/libs/Constants.py,sha256=aKdTHeK75qkVvxvE_2EA5LYis6Z6HLmiuk9o8ESOnNg,260
+magic_pdf/libs/Constants.py,sha256=rdJVadmgN0UlIB-xcMQ9j7Qk9q1Qahxt3KEY-vL7hSU,774
 magic_pdf/libs/MakeContentConfig.py,sha256=UDZPpsv8q4DqTy8h0vRtrT2kHqWiVI205VnVhlUEQc0,206
 magic_pdf/libs/ModelBlockTypeEnum.py,sha256=kalXPbo5ya6hKhhBHPGlHl1yjWOURoXZWQM3rVUyPsY,164
 magic_pdf/libs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -41,13 +41,14 @@ 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=95eHzU5LYX2l3ASu7OvUb95xo-2kfuwh1uUYnY54K90,24
+magic_pdf/libs/version.py,sha256=2KJZDSMOG7KS82AxYOrZ4ZihYxX0wjfUjDsIZh3L024,22
 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=SoT21VHy6ICXoRfC9V3XS6BMiX8EZI6zaqSNgoE17oo,4347
-magic_pdf/model/magic_model.py,sha256=xwKV9BrdjOJecJSzbErT54N6qeJu0tvFuJg2S1z_2kU,25413
+magic_pdf/model/magic_model.py,sha256=3eAfmglKFkmIVPoz3TG8xAzkNK2g_VLI5rRMQAb_cK4,25544
 magic_pdf/model/model_list.py,sha256=AqxAtKGLDn7VVXWYwk0l9LnACxDLyU2jwOJ7vjPZj04,72
-magic_pdf/model/pdf_extract_kit.py,sha256=21vBy8p6pI5a0b6V45ul52yE8zD1R0xrjv4Tx8r9gaw,13620
+magic_pdf/model/pdf_extract_kit.py,sha256=WO54IoxX8XYXLGrjPts--84qRO1FQZm9f_yVyfpPi0s,14539
+magic_pdf/model/ppTableModel.py,sha256=wWiui9VOjkKYlNX-viPqsWpzgkNJ-9_S2Se-j4oyLqU,2687
 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
@@ -72,7 +73,7 @@ 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/StructTableModel.py,sha256=C9WluPhwaqsFg154WsNxN2HlhFXVkAAw0prR7t8r5J4,918
 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
@@ -84,7 +85,7 @@ magic_pdf/para/exceptions.py,sha256=kpjGxrSZ-drNmoKlmuQ0asTjI8cKKKWsdDDBoDHQP9M,
 magic_pdf/para/layout_match_processor.py,sha256=yr4FEO7GJ502udShqGRqIJQ_FQxoa0aG_mhmWd8nLwI,1554
 magic_pdf/para/para_pipeline.py,sha256=zLaCHI9jLi1UPzh0lHP44mUjpKVTHS0gE_5YrkjVqEY,11796
 magic_pdf/para/para_split.py,sha256=-UJM2jREW_2h3ZlJAU7dRD8bK3CMGKuhJrfgqv3Auvk,31310
-magic_pdf/para/para_split_v2.py,sha256=jGOhsubdh_CEgSv9WMNmp1loq1YNlpcAj3yh3g0gPhw,37027
+magic_pdf/para/para_split_v2.py,sha256=jJnn8numhxVgojGwKGCqBNIIYn2AYsucO-q-eQgsPb4,36911
 magic_pdf/para/raw_processor.py,sha256=mHxD9FrdOSXH7NqM41s55URyCyuyACvm9kKtowkIb3k,6317
 magic_pdf/para/stats.py,sha256=-6Pf9Y8jkP1uJOYWiHUjw9Lb-Fb9GY7MHr_ok7x2GX0,9731
 magic_pdf/para/title_processor.py,sha256=pYZv9vEkIjAtCz8jIUtl9AVUy_ib5SdAZmMVoZtsMRI,38593
@@ -127,7 +128,7 @@ 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=2MxCOJ5yNUupQqvrAvEuJKlygjxxV_o1qE64K_4NWKA,235
+magic_pdf/resources/model_config/model_configs.yaml,sha256=_gOSxK9jxe1bFwtH_uwovsyZnRi1sEVNYb1OAexDmF4,301
 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=2H5SDJfAAOX9kPfel06a8VRCHxD1Y8aPbWEkQDdn9JM,452
@@ -140,9 +141,9 @@ 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=w-J4OixDzHjknnUuRW44PXsUlUqyiD4nPbBSSk9WkXM,4160
 magic_pdf/tools/common.py,sha256=XoSs19DD-4ubbjrDFQer83T9O6O_MmgEO61NbjlP_2M,3939
-magic_pdf-0.7.0b1.dist-info/LICENSE.md,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-magic_pdf-0.7.0b1.dist-info/METADATA,sha256=47QGAd2iGc0i1osA_jbBS1QT_Jrfmofoyetsrh9KRy8,18571
-magic_pdf-0.7.0b1.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-magic_pdf-0.7.0b1.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
-magic_pdf-0.7.0b1.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
-magic_pdf-0.7.0b1.dist-info/RECORD,,
+magic_pdf-0.7.1.dist-info/LICENSE.md,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+magic_pdf-0.7.1.dist-info/METADATA,sha256=SD5oVg3vUEuFg7IyAbwncQ_mtgXljhKiJCOwRCTSOVo,18232
+magic_pdf-0.7.1.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+magic_pdf-0.7.1.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
+magic_pdf-0.7.1.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-0.7.1.dist-info/RECORD,,