magic-pdf 1.3.10__py3-none-any.whl → 1.3.12__py3-none-any.whl

magic_pdf/data/utils.py

@@ -10,22 +10,22 @@ from loguru import logger
 
 
 
-def fitz_doc_to_image(doc, dpi=200) -> dict:
+def fitz_doc_to_image(page, dpi=200) -> dict:
     """Convert fitz.Document to image, Then convert the image to numpy array.
 
     Args:
-        doc (_type_): pymudoc page
+        page (_type_): pymudoc page
         dpi (int, optional): reset the dpi of dpi. Defaults to 200.
 
     Returns:
         dict:  {'img': numpy array, 'width': width, 'height': height }
     """
     mat = fitz.Matrix(dpi / 72, dpi / 72)
-    pm = doc.get_pixmap(matrix=mat, alpha=False)
+    pm = page.get_pixmap(matrix=mat, alpha=False)
 
     # If the width or height exceeds 4500 after scaling, do not scale further.
     if pm.width > 4500 or pm.height > 4500:
-        pm = doc.get_pixmap(matrix=fitz.Matrix(1, 1), alpha=False)
+        pm = page.get_pixmap(matrix=fitz.Matrix(1, 1), alpha=False)
 
     # Convert pixmap samples directly to numpy array
     img = np.frombuffer(pm.samples, dtype=np.uint8).reshape(pm.height, pm.width, 3)

magic_pdf/dict2md/ocr_mkcontent.py

@@ -70,19 +70,34 @@ def ocr_mk_markdown_with_para_core_v2(paras_of_layout,
             if mode == 'nlp':
                 continue
             elif mode == 'mm':
-                for block in para_block['blocks']:  # 1st.拼image_body
-                    if block['type'] == BlockType.ImageBody:
-                        for line in block['lines']:
-                            for span in line['spans']:
-                                if span['type'] == ContentType.Image:
-                                    if span.get('image_path', ''):
-                                        para_text += f"\n![]({join_path(img_buket_path, span['image_path'])})  \n"
-                for block in para_block['blocks']:  # 2nd.拼image_caption
-                    if block['type'] == BlockType.ImageCaption:
-                        para_text += merge_para_with_text(block) + '  \n'
-                for block in para_block['blocks']:  # 3rd.拼image_footnote
-                    if block['type'] == BlockType.ImageFootnote:
-                        para_text += merge_para_with_text(block) + '  \n'
+                # 检测是否存在图片脚注
+                has_image_footnote = any(block['type'] == BlockType.ImageFootnote for block in para_block['blocks'])
+                # 如果存在图片脚注，则将图片脚注拼接到图片正文后面
+                if has_image_footnote:
+                    for block in para_block['blocks']:  # 1st.拼image_caption
+                        if block['type'] == BlockType.ImageCaption:
+                            para_text += merge_para_with_text(block) + '  \n'
+                    for block in para_block['blocks']:  # 2nd.拼image_body
+                        if block['type'] == BlockType.ImageBody:
+                            for line in block['lines']:
+                                for span in line['spans']:
+                                    if span['type'] == ContentType.Image:
+                                        if span.get('image_path', ''):
+                                            para_text += f"![]({img_buket_path}/{span['image_path']})"
+                    for block in para_block['blocks']:  # 3rd.拼image_footnote
+                        if block['type'] == BlockType.ImageFootnote:
+                            para_text += '  \n' + merge_para_with_text(block)
+                else:
+                    for block in para_block['blocks']:  # 1st.拼image_body
+                        if block['type'] == BlockType.ImageBody:
+                            for line in block['lines']:
+                                for span in line['spans']:
+                                    if span['type'] == ContentType.Image:
+                                        if span.get('image_path', ''):
+                                            para_text += f"![]({img_buket_path}/{span['image_path']})"
+                    for block in para_block['blocks']:  # 2nd.拼image_caption
+                        if block['type'] == BlockType.ImageCaption:
+                            para_text += '  \n' + merge_para_with_text(block)
         elif para_type == BlockType.Table:
             if mode == 'nlp':
                 continue
@@ -96,20 +111,19 @@ def ocr_mk_markdown_with_para_core_v2(paras_of_layout,
                             for span in line['spans']:
                                 if span['type'] == ContentType.Table:
                                     # 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"
+                                    if span.get('html', ''):
+                                        para_text += f"\n{span['html']}\n"
                                     elif span.get('image_path', ''):
-                                        para_text += f"\n![]({join_path(img_buket_path, span['image_path'])})  \n"
+                                        para_text += f"![]({img_buket_path}/{span['image_path']})"
                 for block in para_block['blocks']:  # 3rd.拼table_footnote
                     if block['type'] == BlockType.TableFootnote:
-                        para_text += merge_para_with_text(block) + '  \n'
+                        para_text += '\n' + merge_para_with_text(block) + '  '
 
         if para_text.strip() == '':
             continue
         else:
-            page_markdown.append(para_text.strip() + '  ')
+            # page_markdown.append(para_text.strip() + '  ')
+            page_markdown.append(para_text.strip())
 
     return page_markdown
 
@@ -257,9 +271,9 @@ def para_to_standard_format_v2(para_block, img_buket_path, page_idx, drop_reason
                         if span['type'] == ContentType.Table:
 
                             if span.get('latex', ''):
-                                para_content['table_body'] = f"\n\n$\n {span['latex']}\n$\n\n"
+                                para_content['table_body'] = f"{span['latex']}"
                             elif span.get('html', ''):
-                                para_content['table_body'] = f"\n\n{span['html']}\n\n"
+                                para_content['table_body'] = f"{span['html']}"
 
                             if span.get('image_path', ''):
                                 para_content['img_path'] = join_path(img_buket_path, span['image_path'])

magic_pdf/libs/version.py

@@ -1 +1 @@
-__version__ = "1.3.10"
+__version__ = "1.3.12"

magic_pdf/model/batch_analyze.py

@@ -6,7 +6,7 @@ from tqdm import tqdm
 from magic_pdf.config.constants import MODEL_NAME
 from magic_pdf.model.sub_modules.model_init import AtomModelSingleton
 from magic_pdf.model.sub_modules.model_utils import (
-    clean_vram, crop_img, get_res_list_from_layout_res)
+    clean_vram, crop_img, get_res_list_from_layout_res, get_coords_and_area)
 from magic_pdf.model.sub_modules.ocr.paddleocr2pytorch.ocr_utils import (
     get_adjusted_mfdetrec_res, get_ocr_result_list)
 
@@ -148,6 +148,19 @@ class BatchAnalyze:
                 # Integration results
                 if ocr_res:
                     ocr_result_list = get_ocr_result_list(ocr_res, useful_list, ocr_res_list_dict['ocr_enable'], new_image, _lang)
+
+                    if res["category_id"] == 3:
+                        # ocr_result_list中所有bbox的面积之和
+                        ocr_res_area = sum(get_coords_and_area(ocr_res_item)[4] for ocr_res_item in ocr_result_list if 'poly' in ocr_res_item)
+                        # 求ocr_res_area和res的面积的比值
+                        res_area = get_coords_and_area(res)[4]
+                        if res_area > 0:
+                            ratio = ocr_res_area / res_area
+                            if ratio > 0.25:
+                                res["category_id"] = 1
+                            else:
+                                continue
+
                     ocr_res_list_dict['layout_res'].extend(ocr_result_list)
 
             # det_count += len(ocr_res_list_dict['ocr_res_list'])

magic_pdf/model/doc_analyze_by_custom_model.py

@@ -156,7 +156,10 @@ def doc_analyze(
         batch_images = [images_with_extra_info]
 
     results = []
-    for batch_image in batch_images:
+    processed_images_count = 0
+    for index, batch_image in enumerate(batch_images):
+        processed_images_count += len(batch_image)
+        logger.info(f'Batch {index + 1}/{len(batch_images)}: {processed_images_count} pages/{len(images_with_extra_info)} pages')
         result = may_batch_image_analyze(batch_image, ocr, show_log,layout_model, formula_enable, table_enable)
         results.extend(result)
 
@@ -186,7 +189,7 @@ def batch_doc_analyze(
     formula_enable=None,
     table_enable=None,
 ):
-    MIN_BATCH_INFERENCE_SIZE = int(os.environ.get('MINERU_MIN_BATCH_INFERENCE_SIZE', 200))
+    MIN_BATCH_INFERENCE_SIZE = int(os.environ.get('MINERU_MIN_BATCH_INFERENCE_SIZE', 100))
     batch_size = MIN_BATCH_INFERENCE_SIZE
     page_wh_list = []
 

magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/modeling_unimernet.py

@@ -66,9 +66,9 @@ LEFT_RIGHT_REMOVE_PATTERN = re.compile(r'\\left\.?|\\right\.?')
 
 def fix_latex_left_right(s):
     """
-    修复LaTeX中的\left和\right命令
+    修复LaTeX中的\\left和\\right命令
     1. 确保它们后面跟有效分隔符
-    2. 平衡\left和\right的数量
+    2. 平衡\\left和\\right的数量
     """
     # 白名单分隔符
     valid_delims_list = [r'(', r')', r'[', r']', r'{', r'}', r'/', r'|',
@@ -106,7 +106,7 @@ def fix_latex_left_right(s):
 
 def fix_left_right_pairs(latex_formula):
     """
-    检测并修复LaTeX公式中\left和\right不在同一组的情况
+    检测并修复LaTeX公式中\\left和\\right不在同一组的情况
 
     Args:
         latex_formula (str): 输入的LaTeX公式
@@ -308,9 +308,9 @@ ENV_FORMAT_PATTERNS = {env: re.compile(r'\\begin\{' + env + r'\}\{([^}]*)\}') fo
 
 def fix_latex_environments(s):
     """
-    检测LaTeX中环境（如array）的\begin和\end是否匹配
-    1. 如果缺少\begin标签则在开头添加
-    2. 如果缺少\end标签则在末尾添加
+    检测LaTeX中环境（如array）的\\begin和\\end是否匹配
+    1. 如果缺少\\begin标签则在开头添加
+    2. 如果缺少\\end标签则在末尾添加
     """
     for env in ENV_TYPES:
         begin_count = len(ENV_BEGIN_PATTERNS[env].findall(s))
@@ -334,7 +334,7 @@ def fix_latex_environments(s):
 
 UP_PATTERN = re.compile(r'\\up([a-zA-Z]+)')
 COMMANDS_TO_REMOVE_PATTERN = re.compile(
-    r'\\(?:lefteqn|boldmath|ensuremath|centering|textsubscript|sides|textsl|textcent|emph)')
+    r'\\(?:lefteqn|boldmath|ensuremath|centering|textsubscript|sides|textsl|textcent|emph|protect|null)')
 REPLACEMENTS_PATTERNS = {
     re.compile(r'\\underbar'): r'\\underline',
     re.compile(r'\\Bar'): r'\\hat',
@@ -346,6 +346,9 @@ REPLACEMENTS_PATTERNS = {
     re.compile(r'\\textunderscore'): r'\\_',
     re.compile(r'\\fint'): r'⨏',
     re.compile(r'\\up '): r'\\ ',
+    re.compile(r'\\vline = '): r'\\models ',
+    re.compile(r'\\vDash '): r'\\models ',
+    re.compile(r'\\sq \\sqcup '): r'\\square ',
 }
 QQUAD_PATTERN = re.compile(r'\\qquad(?!\s)')
 

magic_pdf/model/sub_modules/model_utils.py

@@ -31,10 +31,10 @@ def crop_img(input_res, input_np_img, crop_paste_x=0, crop_paste_y=0):
     return return_image, return_list
 
 
-def get_coords_and_area(table):
+def get_coords_and_area(block_with_poly):
     """Extract coordinates and area from a table."""
-    xmin, ymin = int(table['poly'][0]), int(table['poly'][1])
-    xmax, ymax = int(table['poly'][4]), int(table['poly'][5])
+    xmin, ymin = int(block_with_poly['poly'][0]), int(block_with_poly['poly'][1])
+    xmax, ymax = int(block_with_poly['poly'][4]), int(block_with_poly['poly'][5])
     area = (xmax - xmin) * (ymax - ymin)
     return xmin, ymin, xmax, ymax, area
 
@@ -243,7 +243,7 @@ def get_res_list_from_layout_res(layout_res, iou_threshold=0.7, overlap_threshol
                 "bbox": [int(res['poly'][0]), int(res['poly'][1]),
                          int(res['poly'][4]), int(res['poly'][5])],
             })
-        elif category_id in [0, 2, 4, 6, 7]:  # OCR regions
+        elif category_id in [0, 2, 4, 6, 7, 3]:  # OCR regions
             ocr_res_list.append(res)
         elif category_id == 5:  # Table regions
             table_res_list.append(res)

magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/__init__.py

@@ -35,7 +35,7 @@ def build_backbone(config, model_type):
         from .rec_mobilenet_v3 import MobileNetV3
         from .rec_svtrnet import SVTRNet
         from .rec_mv1_enhance import MobileNetV1Enhance
-
+        from .rec_pphgnetv2 import PPHGNetV2_B4
         support_dict = [
             "MobileNetV1Enhance",
             "MobileNetV3",
@@ -48,6 +48,7 @@ def build_backbone(config, model_type):
             "DenseNet",
             "PPLCNetV3",
             "PPHGNet_small",
+            "PPHGNetV2_B4",
         ]
     else:
         raise NotImplementedError