magic-pdf 0.7.0a1__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

@@ -8,4 +8,33 @@ CROSS_PAGE = "cross_page"
 block维度自定义字段
 """
 # block中lines是否被删除
-LINES_DELETED = "lines_deleted"
+LINES_DELETED = "lines_deleted"
+
+# struct eqtable
+STRUCT_EQTABLE = "struct_eqtable"
+
+# table recognition max time default value
+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/draw_bbox.py

@@ -1,6 +1,7 @@
 from magic_pdf.libs.Constants import CROSS_PAGE
 from magic_pdf.libs.commons import fitz  # PyMuPDF
-from magic_pdf.libs.ocr_content_type import ContentType, BlockType
+from magic_pdf.libs.ocr_content_type import ContentType, BlockType, CategoryId
+from magic_pdf.model.magic_model import MagicModel
 
 
 def draw_bbox_without_number(i, bbox_list, page, rgb_config, fill_config):
@@ -225,3 +226,67 @@ def draw_span_bbox(pdf_info, pdf_bytes, out_path):
 
     # Save the PDF
     pdf_docs.save(f"{out_path}/spans.pdf")
+
+
+def drow_model_bbox(model_list: list, pdf_bytes, out_path):
+    dropped_bbox_list = []
+    tables_body_list, tables_caption_list, tables_footnote_list = [], [], []
+    imgs_body_list, imgs_caption_list = [], []
+    titles_list = []
+    texts_list = []
+    interequations_list = []
+    pdf_docs = fitz.open("pdf", pdf_bytes)
+    magic_model = MagicModel(model_list, pdf_docs)
+    for i in range(len(model_list)):
+        page_dropped_list = []
+        tables_body, tables_caption, tables_footnote = [], [], []
+        imgs_body, imgs_caption = [], []
+        titles = []
+        texts = []
+        interequations = []
+        page_info = magic_model.get_model_list(i)
+        layout_dets = page_info["layout_dets"]
+        for layout_det in layout_dets:
+            bbox = layout_det["bbox"]
+            if layout_det["category_id"] == CategoryId.Text:
+                texts.append(bbox)
+            elif layout_det["category_id"] == CategoryId.Title:
+                titles.append(bbox)
+            elif layout_det["category_id"] == CategoryId.TableBody:
+                tables_body.append(bbox)
+            elif layout_det["category_id"] == CategoryId.TableCaption:
+                tables_caption.append(bbox)
+            elif layout_det["category_id"] == CategoryId.TableFootnote:
+                tables_footnote.append(bbox)
+            elif layout_det["category_id"] == CategoryId.ImageBody:
+                imgs_body.append(bbox)
+            elif layout_det["category_id"] == CategoryId.ImageCaption:
+                imgs_caption.append(bbox)
+            elif layout_det["category_id"] == CategoryId.InterlineEquation_YOLO:
+                interequations.append(bbox)
+            elif layout_det["category_id"] == CategoryId.Abandon:
+                page_dropped_list.append(bbox)
+
+        tables_body_list.append(tables_body)
+        tables_caption_list.append(tables_caption)
+        tables_footnote_list.append(tables_footnote)
+        imgs_body_list.append(imgs_body)
+        imgs_caption_list.append(imgs_caption)
+        titles_list.append(titles)
+        texts_list.append(texts)
+        interequations_list.append(interequations)
+        dropped_bbox_list.append(page_dropped_list)
+
+    for i, page in enumerate(pdf_docs):
+        draw_bbox_with_number(i, dropped_bbox_list, page, [158, 158, 158], True) # color !
+        draw_bbox_with_number(i, tables_body_list, page, [204, 204, 0], True)
+        draw_bbox_with_number(i, tables_caption_list, page, [255, 255, 102], True)
+        draw_bbox_with_number(i, tables_footnote_list, page, [229, 255, 204], True)
+        draw_bbox_with_number(i, imgs_body_list, page, [153, 255, 51], True)
+        draw_bbox_with_number(i, imgs_caption_list, page, [102, 178, 255], True)
+        draw_bbox_with_number(i, titles_list, page, [102, 102, 255], True)
+        draw_bbox_with_number(i, texts_list, page, [153, 0, 76], True)
+        draw_bbox_with_number(i, interequations_list, page, [0, 255, 0], True)
+
+    # Save the PDF
+    pdf_docs.save(f"{out_path}/model.pdf")

magic_pdf/libs/ocr_content_type.py

@@ -19,3 +19,17 @@ class BlockType:
     Footnote = "footnote"
     Discarded = "discarded"
 
+
+class CategoryId:
+    Title = 0
+    Text = 1
+    Abandon = 2
+    ImageBody = 3
+    ImageCaption = 4
+    TableBody = 5
+    TableCaption = 6
+    TableFootnote = 7
+    InterlineEquation_Layout = 8
+    InlineEquation = 13
+    InterlineEquation_YOLO = 14
+    OcrText = 15

magic_pdf/libs/version.py

@@ -1 +1 @@
-__version__ = "0.7.0a1"
+__version__ = "0.7.1"

magic_pdf/model/doc_analyze_by_custom_model.py

@@ -37,8 +37,8 @@ def load_images_from_pdf(pdf_bytes: bytes, dpi=200) -> list:
             mat = fitz.Matrix(dpi / 72, dpi / 72)
             pm = page.get_pixmap(matrix=mat, alpha=False)
 
-            # if width or height > 3000 pixels, don't enlarge the image
-            if pm.width > 3000 or pm.height > 3000:
+            # If the width or height exceeds 9000 after scaling, do not scale further.
+            if pm.width > 9000 or pm.height > 9000:
                 pm = page.get_pixmap(matrix=fitz.Matrix(1, 1), alpha=False)
 
             img = Image.frombytes("RGB", (pm.width, pm.height), pm.samples)

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

@@ -2,6 +2,7 @@ from loguru import logger
 import os
 import time
 
+from magic_pdf.libs.Constants import *
 
 os.environ['NO_ALBUMENTATIONS_UPDATE'] = '1'  # 禁止albumentations检查更新
 try:
@@ -26,17 +27,25 @@ except ImportError as e:
     logger.exception(e)
     logger.error(
         'Required dependency not installed, please install by \n'
-        '"pip install magic-pdf[full] detectron2 --extra-index-url https://myhloli.github.io/wheels/"')
+        '"pip install magic-pdf[full] --extra-index-url https://myhloli.github.io/wheels/"')
     exit(1)
 
 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_)
+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
 
 
@@ -103,8 +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(
@@ -139,11 +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:
-            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)
+            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):
@@ -187,50 +199,56 @@ class CustomPEKModel:
             mfr_cost = round(time.time() - mfr_start, 2)
             logger.info(f"formula nums: {len(mf_image_list)}, mfr time: {mfr_cost}")
 
+        # Select regions for OCR / formula regions / table regions
+        ocr_res_list = []
+        table_res_list = []
+        single_page_mfdetrec_res = []
+        for res in layout_res:
+            if int(res['category_id']) in [13, 14]:
+                single_page_mfdetrec_res.append({
+                    "bbox": [int(res['poly'][0]), int(res['poly'][1]),
+                             int(res['poly'][4]), int(res['poly'][5])],
+                })
+            elif int(res['category_id']) in [0, 1, 2, 4, 6, 7]:
+                ocr_res_list.append(res)
+            elif int(res['category_id']) in [5]:
+                table_res_list.append(res)
+
+        #  Unified crop img logic
+        def crop_img(input_res, input_pil_img, crop_paste_x=0, crop_paste_y=0):
+            crop_xmin, crop_ymin = int(input_res['poly'][0]), int(input_res['poly'][1])
+            crop_xmax, crop_ymax = int(input_res['poly'][4]), int(input_res['poly'][5])
+            # Create a white background with an additional width and height of 50
+            crop_new_width = crop_xmax - crop_xmin + crop_paste_x * 2
+            crop_new_height = crop_ymax - crop_ymin + crop_paste_y * 2
+            return_image = Image.new('RGB', (crop_new_width, crop_new_height), 'white')
+
+            # Crop image
+            crop_box = (crop_xmin, crop_ymin, crop_xmax, crop_ymax)
+            cropped_img = input_pil_img.crop(crop_box)
+            return_image.paste(cropped_img, (crop_paste_x, crop_paste_y))
+            return_list = [crop_paste_x, crop_paste_y, crop_xmin, crop_ymin, crop_xmax, crop_ymax, crop_new_width, crop_new_height]
+            return return_image, return_list
+
+        pil_img = Image.fromarray(image)
+
         # ocr识别
         if self.apply_ocr:
             ocr_start = time.time()
-            pil_img = Image.fromarray(image)
-
-            # 筛选出需要OCR的区域和公式区域
-            ocr_res_list = []
-            single_page_mfdetrec_res = []
-            for res in layout_res:
-                if int(res['category_id']) in [13, 14]:
-                    single_page_mfdetrec_res.append({
-                        "bbox": [int(res['poly'][0]), int(res['poly'][1]),
-                                 int(res['poly'][4]), int(res['poly'][5])],
-                    })
-                elif int(res['category_id']) in [0, 1, 2, 4, 6, 7]:
-                    ocr_res_list.append(res)
-
-            # 对每一个需OCR处理的区域进行处理
+            # Process each area that requires OCR processing
             for res in ocr_res_list:
-                xmin, ymin = int(res['poly'][0]), int(res['poly'][1])
-                xmax, ymax = int(res['poly'][4]), int(res['poly'][5])
-
-                paste_x = 50
-                paste_y = 50
-                # 创建一个宽高各多50的白色背景
-                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_box = (xmin, ymin, xmax, ymax)
-                cropped_img = pil_img.crop(crop_box)
-                new_image.paste(cropped_img, (paste_x, paste_y))
-
-                # 调整公式区域坐标
+                new_image, useful_list = crop_img(res, pil_img, crop_paste_x=50, crop_paste_y=50)
+                paste_x, paste_y, xmin, ymin, xmax, ymax, new_width, new_height = useful_list
+                # Adjust the coordinates of the formula area
                 adjusted_mfdetrec_res = []
                 for mf_res in single_page_mfdetrec_res:
                     mf_xmin, mf_ymin, mf_xmax, mf_ymax = mf_res["bbox"]
-                    # 将公式区域坐标调整为相对于裁剪区域的坐标
+                    # Adjust the coordinates of the formula area to the coordinates relative to the cropping area
                     x0 = mf_xmin - xmin + paste_x
                     y0 = mf_ymin - ymin + paste_y
                     x1 = mf_xmax - xmin + paste_x
                     y1 = mf_ymax - ymin + paste_y
-                    # 过滤在图外的公式块
+                    # Filter formula blocks outside the graph
                     if any([x1 < 0, y1 < 0]) or any([x0 > new_width, y0 > new_height]):
                         continue
                     else:
@@ -238,17 +256,17 @@ class CustomPEKModel:
                             "bbox": [x0, y0, x1, y1],
                         })
 
-                # OCR识别
+                # OCR recognition
                 new_image = cv2.cvtColor(np.asarray(new_image), cv2.COLOR_RGB2BGR)
                 ocr_res = self.ocr_model.ocr(new_image, mfd_res=adjusted_mfdetrec_res)[0]
 
-                # 整合结果
+                # Integration results
                 if ocr_res:
                     for box_ocr_res in ocr_res:
                         p1, p2, p3, p4 = box_ocr_res[0]
                         text, score = box_ocr_res[1]
 
-                        # 将坐标转换回原图坐标系
+                        # Convert the coordinates back to the original coordinate system
                         p1 = [p1[0] - paste_x + xmin, p1[1] - paste_y + ymin]
                         p2 = [p2[0] - paste_x + xmin, p2[1] - paste_y + ymin]
                         p3 = [p3[0] - paste_x + xmin, p3[1] - paste_y + ymin]
@@ -266,30 +284,36 @@ class CustomPEKModel:
 
         # 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
+            table_start = time.time()
+            for res in table_res_list:
+                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():
+                    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
+
+                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)
+            logger.info(f"table cost: {table_cost}")
 
         return layout_res

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