Merge branch 'master' of https://github.com/myhloli/Magic-PDF

demo/ocr_demo.py

@@ -90,9 +90,10 @@ def ocr_parse_core(book_name, ocr_pdf_path, ocr_pdf_model_info, start_page_id=0,
 
 
 if __name__ == '__main__':
-    # pdf_path = r"/home/cxu/workspace/Magic-PDF/ocr_demo/j.1540-627x.2006.00176.x.pdf"
-    # json_file_path = r"/home/cxu/workspace/Magic-PDF/ocr_demo/j.1540-627x.2006.00176.x.json"
+    pdf_path = r"/home/cxu/workspace/Magic-PDF/ocr_demo/j.1540-627x.2006.00176.x.pdf"
+    json_file_path = r"/home/cxu/workspace/Magic-PDF/ocr_demo/j.1540-627x.2006.00176.x.json"
     # ocr_local_parse(pdf_path, json_file_path)
-    # book_name = "数学新星网/edu_00001236"
-    # ocr_online_parse(book_name)
+    book_name = "科数网/edu_00011318"
+    ocr_online_parse(book_name)
+    
     pass

magic_pdf/dict2md/ocr_mkcontent.py

@@ -72,18 +72,26 @@ def ocr_mk_mm_markdown_with_para(pdf_info_dict: dict):
     markdown = []
     for _, page_info in pdf_info_dict.items():
         paras_of_layout = page_info.get("para_blocks")
-        page_markdown = ocr_mk_mm_markdown_with_para_core(paras_of_layout)
+        page_markdown = ocr_mk_mm_markdown_with_para_core(paras_of_layout, "mm")
         markdown.extend(page_markdown)
     return '\n\n'.join(markdown)
 
 
+def ocr_mk_nlp_markdown_with_para(pdf_info_dict: dict):
+    markdown = []
+    for _, page_info in pdf_info_dict.items():
+        paras_of_layout = page_info.get("para_blocks")
+        page_markdown = ocr_mk_mm_markdown_with_para_core(paras_of_layout, "nlp")
+        markdown.extend(page_markdown)
+    return '\n\n'.join(markdown)
+
 def ocr_mk_mm_markdown_with_para_and_pagination(pdf_info_dict: dict):
     markdown_with_para_and_pagination = []
     for page_no, page_info in pdf_info_dict.items():
         paras_of_layout = page_info.get("para_blocks")
         if not paras_of_layout:
             continue
-        page_markdown = ocr_mk_mm_markdown_with_para_core(paras_of_layout)
+        page_markdown = ocr_mk_mm_markdown_with_para_core(paras_of_layout, "mm")
         markdown_with_para_and_pagination.append({
             'page_no': page_no,
             'md_content': '\n\n'.join(page_markdown)
@@ -91,7 +99,7 @@ def ocr_mk_mm_markdown_with_para_and_pagination(pdf_info_dict: dict):
     return markdown_with_para_and_pagination
 
 
-def ocr_mk_mm_markdown_with_para_core(paras_of_layout):
+def ocr_mk_mm_markdown_with_para_core(paras_of_layout, mode):
     page_markdown = []
     for paras in paras_of_layout:
         for para in paras:
@@ -99,6 +107,7 @@ def ocr_mk_mm_markdown_with_para_core(paras_of_layout):
             for line in para:
                 for span in line['spans']:
                     span_type = span.get('type')
+                    content = ''
                     if span_type == ContentType.Text:
                         content = split_long_words(span['content'])
                         # content = span['content']
@@ -107,9 +116,16 @@ def ocr_mk_mm_markdown_with_para_core(paras_of_layout):
                     elif span_type == ContentType.InterlineEquation:
                         content = f"\n$$\n{span['content']}\n$$\n"
                     elif span_type in [ContentType.Image, ContentType.Table]:
-                        content = f"\n![]({join_path(s3_image_save_path, span['image_path'])})\n"
-                    para_text += content + ' '
-            page_markdown.append(para_text.strip() + '  ')
+                        if mode == 'mm':
+                            content = f"\n![]({join_path(s3_image_save_path, span['image_path'])})\n"
+                        elif mode == 'nlp':
+                            pass
+                    if content != '':
+                        para_text += content + ' '
+            if para_text.strip() == '':
+                continue
+            else:
+                page_markdown.append(para_text.strip() + '  ')
     return page_markdown
 
 

magic_pdf/para/para_split.py

@@ -9,7 +9,7 @@ from magic_pdf.libs.ocr_content_type import ContentType
 LINE_STOP_FLAG = ['.', '!', '?', '。', '！', '？',"：", ":", ")", "）", ";"]
 INLINE_EQUATION = ContentType.InlineEquation
 INTERLINE_EQUATION = ContentType.InterlineEquation
-TEXT = "text"
+TEXT = ContentType.Text
 
 
 def __get_span_text(span):
@@ -20,7 +20,7 @@ def __get_span_text(span):
     return c
     
 
-def __detect_list_lines(lines, new_layout_bboxes, lang='en'):
+def __detect_list_lines(lines, new_layout_bboxes, lang):
     """
     探测是否包含了列表，并且把列表的行分开.
     这样的段落特点是，顶格字母大写/数字，紧跟着几行缩进的。缩进的行首字母含小写的。
@@ -315,11 +315,14 @@ def __split_para_in_layoutbox(lines_group, new_layout_bbox, lang="en", char_avg_
                     
     return layout_paras, list_info
 
-def __connect_list_inter_layout(layout_paras, new_layout_bbox, layout_list_info, page_num, lang="en"):
+def __connect_list_inter_layout(layout_paras, new_layout_bbox, layout_list_info, page_num, lang):
     """
-    如果上个layout的最后一个段落是列表，下一个layout的第一个段落也是列表，那么将他们连接起来。
+    如果上个layout的最后一个段落是列表，下一个layout的第一个段落也是列表，那么将他们连接起来。 TODO 因为没有区分列表和段落，所以这个方法暂时不实现。
     根据layout_list_info判断是不是列表。，下个layout的第一个段如果不是列表，那么看他们是否有几行都有相同的缩进。
     """
+    if len(layout_paras)==0 or len(layout_list_info)==0: # 0的时候最后的return 会出错
+        return layout_paras, [False, False]
+        
     for i in range(1, len(layout_paras)):
         pre_layout_list_info = layout_list_info[i-1]
         next_layout_list_info = layout_list_info[i]
@@ -345,7 +348,37 @@ def __connect_list_inter_layout(layout_paras, new_layout_bbox, layout_list_info,
                 pre_last_para.extend(may_list_lines)
                 layout_paras[i] = layout_paras[i][len(may_list_lines):]
                            
-    return layout_paras
+    return layout_paras, [layout_list_info[0][0], layout_list_info[-1][1]] # 同时还返回了这个页面级别的开头、结尾是不是列表的信息
+
+
+def __connect_list_inter_page(pre_page_paras, next_page_paras, pre_page_layout_bbox, next_page_layout_bbox,  pre_page_list_info, next_page_list_info, page_num, lang):
+    """
+    如果上个layout的最后一个段落是列表，下一个layout的第一个段落也是列表，那么将他们连接起来。 TODO 因为没有区分列表和段落，所以这个方法暂时不实现。
+    根据layout_list_info判断是不是列表。，下个layout的第一个段如果不是列表，那么看他们是否有几行都有相同的缩进。
+    """
+    if len(pre_page_paras)==0 or len(next_page_paras)==0: # 0的时候最后的return 会出错
+        return False
+    
+    if pre_page_list_info[1] and not next_page_list_info[0]: # 前一个是列表结尾，后一个是非列表开头，此时检测是否有相同的缩进
+        logger.info(f"连接page {page_num} 内的list")
+        # 向layout_paras[i] 寻找开头具有相同缩进的连续的行
+        may_list_lines = []
+        for j in range(len(next_page_paras[0])):
+            line = next_page_paras[0][j]
+            if len(line)==1: # 只可能是一行，多行情况再需要分析了
+                if line[0]['bbox'][0] > __find_layout_bbox_by_line(line[0]['bbox'], next_page_layout_bbox)[0]:
+                    may_list_lines.append(line[0])
+                else:
+                    break
+            else:
+                break
+        # 如果这些行的缩进是相等的，那么连到上一个layout的最后一个段落上。
+        if len(may_list_lines)>0 and len(set([x['bbox'][0] for x in may_list_lines]))==1:
+            pre_page_paras[-1].append(may_list_lines)
+            next_page_paras[0] = next_page_paras[0][len(may_list_lines):]
+            return True
+                       
+    return False
 
 
 def __find_layout_bbox_by_line(line_bbox, layout_bboxes):
@@ -358,7 +391,7 @@ def __find_layout_bbox_by_line(line_bbox, layout_bboxes):
     return None
 
 
-def __connect_para_inter_layoutbox(layout_paras, new_layout_bbox, lang="en"):
+def __connect_para_inter_layoutbox(layout_paras, new_layout_bbox, lang):
     """
     layout之间进行分段。
     主要是计算前一个layOut的最后一行和后一个layout的第一行是否可以连接。
@@ -368,10 +401,19 @@ def __connect_para_inter_layoutbox(layout_paras, new_layout_bbox, lang="en"):
 
     """
     connected_layout_paras = []
+    if len(layout_paras)==0:
+        return connected_layout_paras
+    
     connected_layout_paras.append(layout_paras[0])
     for i in range(1, len(layout_paras)):
-        pre_last_line = layout_paras[i-1][-1][-1]
-        next_first_line = layout_paras[i][0][0]
+        try:
+            if len(layout_paras[i])==0 or len(layout_paras[i-1])==0: #  TODO 考虑连接问题，
+                continue
+            pre_last_line = layout_paras[i-1][-1][-1]
+            next_first_line = layout_paras[i][0][0]
+        except Exception as e:
+            logger.error(f"page layout {i} has no line")
+            continue
         pre_last_line_text = ''.join([__get_span_text(span) for span in pre_last_line['spans']])
         pre_last_line_type = pre_last_line['spans'][-1]['type']
         next_first_line_text = ''.join([__get_span_text(span) for span in next_first_line['spans']])
@@ -400,7 +442,7 @@ def __connect_para_inter_layoutbox(layout_paras, new_layout_bbox, lang="en"):
     return connected_layout_paras
 
 
-def __connect_para_inter_page(pre_page_paras, next_page_paras, pre_page_layout_bbox, next_page_layout_bbox, lang):
+def __connect_para_inter_page(pre_page_paras, next_page_paras, pre_page_layout_bbox, next_page_layout_bbox, page_num, lang):
     """
     连接起来相邻两个页面的段落——前一个页面最后一个段落和后一个页面的第一个段落。
     是否可以连接的条件：
@@ -408,7 +450,7 @@ def __connect_para_inter_page(pre_page_paras, next_page_paras, pre_page_layout_b
     2. 后一个页面的第一个段落第一行没有空白开头。
     """
     # 有的页面可能压根没有文字
-    if len(pre_page_paras)==0 or len(next_page_paras)==0:
+    if len(pre_page_paras)==0 or len(next_page_paras)==0 or len(pre_page_paras[0])==0 or len(next_page_paras[0])==0: # TODO [[]]为什么出现在pre_page_paras里？
         return False
     pre_last_para = pre_page_paras[-1][-1]
     next_first_para = next_page_paras[0][0]
@@ -436,8 +478,85 @@ def __connect_para_inter_page(pre_page_paras, next_page_paras, pre_page_layout_b
     else:
         return False
 
+def find_consecutive_true_regions(input_array):
+    start_index = None  # 连续True区域的起始索引
+    regions = []  # 用于保存所有连续True区域的起始和结束索引
+
+    for i in range(len(input_array)):
+        # 如果我们找到了一个True值，并且当前并没有在连续True区域中
+        if input_array[i] and start_index is None:
+            start_index = i  # 记录连续True区域的起始索引
 
-def __do_split(blocks, layout_bboxes, new_layout_bbox, page_num, lang="en"):
+        # 如果我们找到了一个False值，并且当前在连续True区域中
+        elif not input_array[i] and start_index is not None:
+            # 如果连续True区域长度大于1，那么将其添加到结果列表中
+            if i - start_index > 1: 
+                regions.append((start_index, i-1)) 
+            start_index = None  # 重置起始索引
+
+    # 如果最后一个元素是True，那么需要将最后一个连续True区域加入到结果列表中
+    if start_index is not None and len(input_array) - start_index > 1:
+        regions.append((start_index, len(input_array)-1))
+
+    return regions
+
+
+def __connect_middle_align_text(page_paras, new_layout_bbox, page_num, lang, debug_mode):
+    """
+    找出来中间对齐的连续单行文本，如果连续行高度相同，那么合并为一个段落。
+    一个line居中的条件是：
+    1. 水平中心点跨越layout的中心点。
+    2. 左右两侧都有空白
+    """
+    
+    for layout_i, layout_para in enumerate(page_paras):
+        layout_box = new_layout_bbox[layout_i]
+        single_line_paras_tag = []
+        for i in range(len(layout_para)):
+            single_line_paras_tag.append(len(layout_para[i])==1 and layout_para[i][0]['spans'][0]['type']==TEXT)
+            
+        """找出来连续的单行文本，如果连续行高度相同，那么合并为一个段落。"""
+        consecutive_single_line_indices = find_consecutive_true_regions(single_line_paras_tag)
+        if len(consecutive_single_line_indices)>0:
+            index_offset = 0
+            """检查这些行是否是高度相同的，居中的"""
+            for start, end in consecutive_single_line_indices:
+                start += index_offset
+                end += index_offset
+                line_hi = np.array([line[0]['bbox'][3]-line[0]['bbox'][1] for line in layout_para[start:end+1]])
+                first_line_text = ''.join([__get_span_text(span) for span in layout_para[start][0]['spans']])
+                if "Table" in first_line_text or "Figure" in first_line_text:
+                    pass
+                if debug_mode:
+                    logger.info(line_hi.std())
+                
+                if line_hi.std()<2:
+                    """行高度相同，那么判断是否居中"""
+                    all_left_x0 = [line[0]['bbox'][0] for line in layout_para[start:end+1]]
+                    all_right_x1 = [line[0]['bbox'][2] for line in layout_para[start:end+1]]
+                    layout_center = (layout_box[0] + layout_box[2]) / 2
+                    if all([x0 < layout_center < x1 for x0, x1 in zip(all_left_x0, all_right_x1)]) \
+                    and not all([x0==layout_box[0] for x0 in all_left_x0]) \
+                    and not all([x1==layout_box[2] for x1 in all_right_x1]):
+                        merge_para = [l[0] for l in layout_para[start:end+1]]
+                        para_text = ''.join([__get_span_text(span) for line in merge_para for span in line['spans']])
+                        if debug_mode:
+                            logger.info(para_text)
+                        layout_para[start:end+1] = [merge_para]
+                        index_offset -= end-start
+                        
+    return
+            
+
+def __merge_signle_list_text(page_paras, new_layout_bbox, page_num, lang):
+    """
+    找出来连续的单行文本，如果首行顶格，接下来的几个单行段落缩进对齐，那么合并为一个段落。
+    """
+    
+    pass
+
+
+def __do_split_page(blocks, layout_bboxes, new_layout_bbox, page_num, lang):
     """
     根据line和layout情况进行分段
     先实现一个根据行末尾特征分段的简单方法。
@@ -451,35 +570,54 @@ def __do_split(blocks, layout_bboxes, new_layout_bbox, page_num, lang="en"):
     """
     lines_group = __group_line_by_layout(blocks, layout_bboxes, lang) # block内分段
     layout_paras, layout_list_info = __split_para_in_layoutbox(lines_group, new_layout_bbox, lang) # layout内分段
-    layout_paras2 = __connect_list_inter_layout(layout_paras, new_layout_bbox, layout_list_info, page_num, lang) # layout之间连接列表段落
+    layout_paras2, page_list_info = __connect_list_inter_layout(layout_paras, new_layout_bbox, layout_list_info, page_num, lang) # layout之间连接列表段落
     connected_layout_paras = __connect_para_inter_layoutbox(layout_paras2, new_layout_bbox, lang) # layout间链接段落
     
-    return connected_layout_paras
-    
     
-def para_split(pdf_info_dict, lang="en"):
+    return connected_layout_paras, page_list_info
+   
+
+def para_split(pdf_info_dict, debug_mode, lang="en"):
     """
     根据line和layout情况进行分段
     """
     new_layout_of_pages = [] # 数组的数组，每个元素是一个页面的layoutS
+    all_page_list_info = [] # 保存每个页面开头和结尾是否是列表
     for page_num, page in pdf_info_dict.items():
         blocks = page['preproc_blocks']
         layout_bboxes = page['layout_bboxes']
         new_layout_bbox = __common_pre_proc(blocks, layout_bboxes)
         new_layout_of_pages.append(new_layout_bbox)
-        splited_blocks = __do_split(blocks, layout_bboxes, new_layout_bbox, page_num, lang)
+        splited_blocks, page_list_info = __do_split_page(blocks, layout_bboxes, new_layout_bbox, page_num, lang)
+        all_page_list_info.append(page_list_info)
         page['para_blocks'] = splited_blocks
         
     """连接页面与页面之间的可能合并的段落"""
     pdf_infos = list(pdf_info_dict.values())
-    for i, page in enumerate(pdf_info_dict.values()):
-        if i==0:
+    for page_num, page in enumerate(pdf_info_dict.values()):
+        if page_num==0:
             continue
-        pre_page_paras = pdf_infos[i-1]['para_blocks']
-        next_page_paras = pdf_infos[i]['para_blocks']
-        pre_page_layout_bbox = new_layout_of_pages[i-1]
-        next_page_layout_bbox = new_layout_of_pages[i]
+        pre_page_paras = pdf_infos[page_num-1]['para_blocks']
+        next_page_paras = pdf_infos[page_num]['para_blocks']
+        pre_page_layout_bbox = new_layout_of_pages[page_num-1]
+        next_page_layout_bbox = new_layout_of_pages[page_num]
         
-        is_conn= __connect_para_inter_page(pre_page_paras, next_page_paras, pre_page_layout_bbox, next_page_layout_bbox, lang) 
-        if is_conn:
-            logger.info(f"连接了第{i-1}页和第{i}页的段落")
+        is_conn = __connect_para_inter_page(pre_page_paras, next_page_paras, pre_page_layout_bbox, next_page_layout_bbox, page_num, lang)
+        if debug_mode:
+            if is_conn:
+                logger.info(f"连接了第{page_num-1}页和第{page_num}页的段落")
+            
+        is_list_conn = __connect_list_inter_page(pre_page_paras, next_page_paras, pre_page_layout_bbox, next_page_layout_bbox, all_page_list_info[page_num-1], all_page_list_info[page_num], page_num, lang)
+        if debug_mode:
+            if is_list_conn:
+                logger.info(f"连接了第{page_num-1}页和第{page_num}页的列表段落")
+            
+    """接下来可能会漏掉一些特别的一些可以合并的内容，对他们进行段落连接
+    1. 正文中有时出现一个行顶格，接下来几行缩进的情况。
+    2. 居中的一些连续单行，如果高度相同，那么可能是一个段落。
+    """
+    for page_num, page in enumerate(pdf_info_dict.values()):
+        page_paras = page['para_blocks']
+        new_layout_bbox = new_layout_of_pages[page_num]
+        __connect_middle_align_text(page_paras, new_layout_bbox, page_num, lang, debug_mode=debug_mode)
+        __merge_signle_list_text(page_paras, new_layout_bbox, page_num, lang)

magic_pdf/pdf_parse_by_ocr.py

@@ -57,16 +57,16 @@ def construct_page_component(blocks, layout_bboxes, page_id, page_w, page_h, lay
 
 
 def parse_pdf_by_ocr(
-    pdf_path,
-    s3_pdf_profile,
-    pdf_model_output,
-    save_path,
-    book_name,
-    pdf_model_profile=None,
-    image_s3_config=None,
-    start_page_id=0,
-    end_page_id=None,
-    debug_mode=False,
+        pdf_path,
+        s3_pdf_profile,
+        pdf_model_output,
+        save_path,
+        book_name,
+        pdf_model_profile=None,
+        image_s3_config=None,
+        start_page_id=0,
+        end_page_id=None,
+        debug_mode=False,
 ):
     pdf_bytes = read_file(pdf_path, s3_pdf_profile)
     save_tmp_path = os.path.join(os.path.dirname(__file__), "../..", "tmp", "unittest")
@@ -95,7 +95,6 @@ def parse_pdf_by_ocr(
 
     start_time = time.time()
 
-
     end_page_id = end_page_id if end_page_id else len(pdf_docs) - 1
     for page_id in range(start_page_id, end_page_id + 1):
 
@@ -125,13 +124,6 @@ def parse_pdf_by_ocr(
             page_id, page, ocr_page_info, md_bookname_save_path, debug_mode=debug_mode
         )
 
-        # 构建需要remove的bbox列表
-        # need_remove_spans_bboxes = []
-        # need_remove_spans_bboxes.extend(page_no_bboxes)
-        # need_remove_spans_bboxes.extend(header_bboxes)
-        # need_remove_spans_bboxes.extend(footer_bboxes)
-        # need_remove_spans_bboxes.extend(footnote_bboxes)
-
         # 构建需要remove的bbox字典
         need_remove_spans_bboxes_dict = {
             DropTag.PAGE_NUMBER: page_no_bboxes,
@@ -199,50 +191,48 @@ def parse_pdf_by_ocr(
             else:
                 continue
 
-
-
-
-        # 删除重叠spans中较小的那些
+        '''删除重叠spans中较小的那些'''
         spans, dropped_spans_by_span_overlap = remove_overlaps_min_spans(spans)
 
-        # 删除remove_span_block_bboxes中的bbox
-        # spans = remove_spans_by_bboxes(spans, need_remove_spans_bboxes)
-        # 按qa要求，增加drop相关数据
+        '''
+        删除remove_span_block_bboxes中的bbox
+        并增加drop相关数据
+        '''
         spans, dropped_spans_by_removed_bboxes = remove_spans_by_bboxes_dict(spans, need_remove_spans_bboxes_dict)
 
-        # 对image和table截图
+        '''对image和table截图'''
         spans = cut_image_and_table(spans, page, page_id, book_name, save_path, img_s3_client)
 
-        # 行内公式调整, 高度调整至与同行文字高度一致(优先左侧, 其次右侧)
+        '''行内公式调整, 高度调整至与同行文字高度一致(优先左侧, 其次右侧)'''
         displayed_list = []
         text_inline_lines = []
         modify_y_axis(spans, displayed_list, text_inline_lines)
-        # 模型识别错误的行间公式, type类型转换成行内公式
+
+        '''模型识别错误的行间公式, type类型转换成行内公式'''
         spans = modify_inline_equation(spans, displayed_list, text_inline_lines)
 
-        # bbox去除粘连
+        '''bbox去除粘连'''
         spans = remove_overlap_between_bbox(spans)
 
-        # 对tpye=["interline_equation", "image", "table"]进行额外处理,如果左边有字的话,将该span的bbox中y0调整至不高于文字的y0
+        '''
+        对tpye=["interline_equation", "image", "table"]进行额外处理,
+        如果左边有字的话,将该span的bbox中y0调整至不高于文字的y0
+        '''
         spans = adjust_bbox_for_standalone_block(spans)
 
-
-        # 从ocr_page_info中解析layout信息(按自然阅读方向排序,并修复重叠和交错的bad case)
+        '''从ocr_page_info中解析layout信息(按自然阅读方向排序,并修复重叠和交错的bad case)'''
         layout_bboxes, layout_tree = layout_detect(ocr_page_info['subfield_dets'], page, ocr_page_info)
 
-        # 将spans合并成line(在layout内,从上到下,从左到右)
+        '''将spans合并成line(在layout内,从上到下,从左到右)'''
         lines, dropped_spans_by_layout = merge_spans_to_line_by_layout(spans, layout_bboxes)
 
-        # 将lines合并成block
+        '''将lines合并成block'''
         blocks = merge_lines_to_block(lines)
 
-        # 根据block合并段落
-        #para_blocks = para_split(blocks, layout_bboxes)
-        
-        # 获取QA需要外置的list
+        '''获取QA需要外置的list'''
         images, tables, interline_equations, inline_equations = get_qa_need_list(blocks)
 
-        # drop的span_list合并
+        '''drop的span_list合并'''
         dropped_spans = []
         dropped_spans.extend(dropped_spans_by_span_overlap)
         dropped_spans.extend(dropped_spans_by_removed_bboxes)
@@ -263,19 +253,18 @@ def parse_pdf_by_ocr(
             elif span['type'] in [ContentType.InlineEquation, ContentType.InterlineEquation]:
                 dropped_equation_block.append(span)
 
-
-
-        # 构造pdf_info_dict
+        '''构造pdf_info_dict'''
         page_info = construct_page_component(blocks, layout_bboxes, page_id, page_w, page_h, layout_tree,
                                              images, tables, interline_equations, inline_equations,
-                                             dropped_text_block, dropped_image_block, dropped_table_block, dropped_equation_block,
+                                             dropped_text_block, dropped_image_block, dropped_table_block,
+                                             dropped_equation_block,
                                              need_remove_spans_bboxes_dict)
         pdf_info_dict[f"page_{page_id}"] = page_info
 
     """分段"""
-    para_split(pdf_info_dict)
-    
-    # 在测试时,保存调试信息
+    para_split(pdf_info_dict, debug_mode=debug_mode)
+
+    '''在测试时,保存调试信息'''
     if debug_mode:
         params_file_save_path = join_path(
             save_tmp_path, "md", book_name, "preproc_out.json"

magic_pdf/pipeline.py

@@ -7,7 +7,7 @@ from magic_pdf.dict2md.ocr_mkcontent import (
     ocr_mk_nlp_markdown,
     ocr_mk_mm_markdown,
     ocr_mk_mm_standard_format,
-    ocr_mk_mm_markdown_with_para, ocr_mk_mm_markdown_with_para_and_pagination,
+    ocr_mk_mm_markdown_with_para, ocr_mk_mm_markdown_with_para_and_pagination, ocr_mk_nlp_markdown_with_para,
 )
 from magic_pdf.libs.commons import (
     read_file,
@@ -510,7 +510,8 @@ def ocr_pdf_intermediate_dict_to_markdown_with_para(jso: dict, debug_mode=False)
         pdf_intermediate_dict = jso["pdf_intermediate_dict"]
         # 将 pdf_intermediate_dict 解压
         pdf_intermediate_dict = JsonCompressor.decompress_json(pdf_intermediate_dict)
-        markdown_content = ocr_mk_mm_markdown_with_para(pdf_intermediate_dict)
+        # markdown_content = ocr_mk_mm_markdown_with_para(pdf_intermediate_dict)
+        markdown_content = ocr_mk_nlp_markdown_with_para(pdf_intermediate_dict)
         jso["content"] = markdown_content
         logger.info(
             f"book_name is:{get_data_source(jso)}/{jso['file_id']},markdown content length is {len(markdown_content)}",