按照统一格式组合文本型pdf的解析结果

demo/demo_test.py

@@ -5,6 +5,7 @@ from pathlib import Path
 
 import click
 
+from magic_pdf.dict2md.mkcontent import mk_mm_markdown
 from magic_pdf.pipeline import (
     meta_scan,
     classify_by_type,
@@ -55,14 +56,19 @@ def demo_parse_pdf(book_name=None, start_page_id=0, debug_mode=True):
     write_json_to_local(jso, book_name)
 
     jso_md = pdf_intermediate_dict_to_markdown(jso, debug_mode=debug_mode)
-    md_content = jso_md.get("content")
+    content = jso_md.get("content_list")
+    markdown_content = mk_mm_markdown(content)
     if book_name is not None:
-        save_tmp_path = os.path.join(os.path.dirname(__file__), "../..", "tmp", "unittest")
-        markdown_save_path = join_path(save_tmp_path, "md", book_name + ".md")
+        save_tmp_path = os.path.join(os.path.dirname(__file__), "../..", "tmp", "unittest", "md", book_name)
+        uni_format_save_path = join_path(save_tmp_path,  "book" + ".json")
+        markdown_save_path = join_path(save_tmp_path,  "book" + ".md")
+        with open(uni_format_save_path, "w", encoding="utf-8") as f:
+            f.write(json.dumps(content, ensure_ascii=False, indent=4))
         with open(markdown_save_path, "w", encoding="utf-8") as f:
-            f.write(md_content)
+            f.write(markdown_content)
+            
     else:
-        logger.info(md_content)
+        logger.info(json.dumps(content, ensure_ascii=False))
 
 
 def demo_save_tables(book_name=None, start_page_id=0, debug_mode=True):

magic_pdf/dict2md/mkcontent.py

@@ -2,9 +2,15 @@ import math
 from loguru import logger
 
 from magic_pdf.libs.boxbase import find_bottom_nearest_text_bbox, find_top_nearest_text_bbox
+from magic_pdf.libs.ocr_content_type import ContentType
 
+TYPE_INLINE_EQUATION = ContentType.InlineEquation
+TYPE_INTERLINE_EQUATION = ContentType.InterlineEquation
+UNI_FORMAT_TEXT_TYPE = ['text', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6']
 
-def mk_nlp_markdown(para_dict: dict):
+
+@DeprecationWarning
+def mk_nlp_markdown_1(para_dict: dict):
     """
     对排序后的bboxes拼接内容
     """
@@ -69,14 +75,14 @@ def __insert_before(content, image_content, target):
     return content
 
 
-
-def mk_mm_markdown(para_dict: dict):
+@DeprecationWarning
+def mk_mm_markdown_1(para_dict: dict):
     """拼装多模态markdown"""
     content_lst = []
     for _, page_info in para_dict.items():
         page_lst = [] # 一个page内的段落列表
         para_blocks = page_info.get("para_blocks")
-        pymu_raw_blocks = page_info.get("preproc_blocks")  
+        pymu_raw_blocks = page_info.get("preproc_blocks")
         
         all_page_images = []
         all_page_images.extend(page_info.get("images",[]))
@@ -137,7 +143,7 @@ def mk_mm_markdown(para_dict: dict):
                                 else:
                                     page_md = __insert_before(page_md, img_content, line_txt)
                             else:
-                                logger.error(f"Can't find the location of image {img['image_path']} in the markdown file")
+                                logger.error(f"Can't find the location of image {img['image_path']} in the markdown file #1")
                 else:# 应当在两个block之间
                     # 找到上方最近的block，如果上方没有就找大下方最近的block
                     top_txt_block = find_top_nearest_text_bbox(pymu_raw_blocks, imgbox)
@@ -150,7 +156,7 @@ def mk_mm_markdown(para_dict: dict):
                             line_txt = "".join([s['text'] for s in bottom_txt_block['lines'][0]['spans']])
                             page_md = __insert_before(page_md, img_content, line_txt)
                         else:
-                            logger.error(f"Can't find the location of image {img['image_path']} in the markdown file")
+                            logger.error(f"Can't find the location of image {img['image_path']} in the markdown file #2")
                     
         content_lst.append(page_md)
                     
@@ -158,92 +164,186 @@ def mk_mm_markdown(para_dict: dict):
     content_text = "\n\n".join(content_lst)
 
     return content_text
-    
-    
-@DeprecationWarning
-def mk_mm_markdown_1(para_dict: dict):
+
+
+def __insert_after_para(text, image_path, content_list):
     """
-    得到images和tables变量
+    在content_list中找到text，将image_path作为一个新的node插入到text后面
     """
-    image_all_list = []
+    for i, c in enumerate(content_list):
+        content_type = c.get("type")
+        if content_type in UNI_FORMAT_TEXT_TYPE and text in c.get("text", ''):
+            img_node = {
+                "type": "image",
+                "img_path": image_path,
+                "img_alt":"",
+                "img_title":"",
+                "img_caption":""
+            }
+            content_list.insert(i+1, img_node)
+            break
+    else:
+        logger.error(f"Can't find the location of image {image_path} in the markdown file, search target is {text}")
     
+
+
+def __insert_before_para(text, image_path, content_list):
+    """
+    在content_list中找到text，将image_path作为一个新的node插入到text前面
+    """
+    for i, c in enumerate(content_list):
+        content_type = c.get("type")
+        if content_type in  UNI_FORMAT_TEXT_TYPE and text in c.get("text", ''):
+            img_node = {
+                "type": "image",
+                "img_path": image_path,
+                "img_alt":"",
+                "img_title":"",
+                "img_caption":""
+            }
+            content_list.insert(i, img_node)
+            break
+    else:
+        logger.error(f"Can't find the location of image {image_path} in the markdown file, search target is {text}")
+         
+
+def mk_universal_format(para_dict: dict):
+    """
+    构造统一格式 https://aicarrier.feishu.cn/wiki/FqmMwcH69iIdCWkkyjvcDwNUnTY
+    """
+    content_lst = []
     for _, page_info in para_dict.items():
-        images = page_info.get("images",[])
-        tables = page_info.get("tables",[])
-        image_backup = page_info.get("image_backup", [])  
-        table_backup = page_info.get("table_backup",[]) 
+        page_lst = [] # 一个page内的段落列表
+        para_blocks = page_info.get("para_blocks")
+        pymu_raw_blocks = page_info.get("preproc_blocks")
+        
         all_page_images = []
-        all_page_images.extend(images)
-        all_page_images.extend(image_backup)
-        all_page_images.extend(tables)
-        all_page_images.extend(table_backup)
+        all_page_images.extend(page_info.get("images",[]))
+        all_page_images.extend(page_info.get("image_backup", []) )
+        all_page_images.extend(page_info.get("tables",[]))
+        all_page_images.extend(page_info.get("table_backup",[]) )
         
-        pymu_raw_blocks = page_info.get("pymu_raw_blocks")  
-
-        # 提取每个图片所在位置
-        for image_info in all_page_images:
-            x0_image, y0_image, x1_image, y1_image = image_info['bbox'][:4]
-            image_path = image_info['image_path']
-            
-            # 判断图片处于原始PDF中哪个模块之间
-            image_internal_dict = {}
-            image_external_dict = {}
-            between_dict = {}
+        if not para_blocks or not pymu_raw_blocks: # 只有图片的拼接的场景
+            for img in all_page_images:
+                content_node = {
+                    "type": "image",
+                    "img_path": img['image_path'],
+                    "img_alt":"",
+                    "img_title":"",
+                    "img_caption":""
+                }
+                page_lst.append(content_node) # TODO 图片顺序
+        else:
+            for block in para_blocks:
+                item = block["paras"]
+                for _, p in item.items():
+                    font_type = p['para_font_type']# 对于文本来说，要么是普通文本，要么是个行间公式
+                    if font_type == TYPE_INTERLINE_EQUATION:
+                        content_node = {
+                            "type": "equation",
+                            "latex": p["para_text"]
+                        }
+                        page_lst.append(content_node)
+                    else:
+                        para_text = p["para_text"]
+                        is_title = p["is_para_title"]
+                        title_level = p['para_title_level']
+                        
+                        if is_title:
+                            content_node = {
+                                "type": f"h{title_level}",
+                                "text": para_text
+                            }
+                            page_lst.append(content_node)
+                        else:
+                            content_node = {
+                                "type": "text",
+                                "text": para_text
+                            }
+                            page_lst.append(content_node)
+                            
+        content_lst.extend(page_lst)
+        
+        """插入图片"""
+        for img in all_page_images:
+            imgbox = img['bbox']
+            img_content = f"{img['image_path']}"
+            # 先看在哪个block内
             for block in pymu_raw_blocks:
-                x0, y0, x1, y1 = block['bbox'][:4]
-
-                # 在某个模块内部
-                if x0 <= x0_image < x1 and y0 <= y0_image < y1:
-                    image_internal_dict['bbox'] = [x0_image, y0_image, x1_image, y1_image]
-                    image_internal_dict['path'] = image_path
-                    
-                    # 确定图片在哪句文本之前
-                    y_pre = 0
-                    for line in block['lines']:
-                        x0, y0, x1, y1 = line['spans'][0]['bbox']
-                        if x0 <= x0_image < x1 and y_pre <= y0_image < y0: 
-                            text = line['spans']['text']
-                            image_internal_dict['text'] = text
-                            image_internal_dict['markdown_image'] = f'![image_path]({image_path})'
+                bbox = block['bbox']
+                if bbox[0]-1 <= imgbox[0] < bbox[2]+1 and bbox[1]-1 <= imgbox[1] < bbox[3]+1:# 确定在这个大的block内，然后进入逐行比较距离
+                    for l in block['lines']:
+                        line_box = l['bbox']
+                        if line_box[0]-1 <= imgbox[0] < line_box[2]+1 and line_box[1]-1 <= imgbox[1] < line_box[3]+1: # 在line内的，插入line前面
+                            line_txt = "".join([s['text'] for s in l['spans']])
+                            __insert_before_para(line_txt, img_content, content_lst)
+                            break
+                        break
+                    else:# 在行与行之间
+                        # 找到图片x0,y0与line的x0,y0最近的line
+                        min_distance = 100000
+                        min_line = None
+                        for l in block['lines']:
+                            line_box = l['bbox']
+                            distance = math.sqrt((line_box[0] - imgbox[0])**2 + (line_box[1] - imgbox[1])**2)
+                            if distance < min_distance:
+                                min_distance = distance
+                                min_line = l
+                        if min_line:
+                            line_txt = "".join([s['text'] for s in min_line['spans']])
+                            img_h = imgbox[3] - imgbox[1]
+                            if min_distance<img_h: # 文字在图片前面
+                                __insert_after_para(line_txt, img_content, content_lst)
+                            else:
+                                __insert_before_para(line_txt, img_content, content_lst) 
                             break
                         else:
-                            y_pre = y0
-                # 在某两个模块之间
-                elif x0 <= x0_image < x1:
-                    distance = math.sqrt((x1_image - x0)**2 + (y1_image - y0)**2)
-                    between_dict[block['number']] = distance
-            
-            # 找到与定位点距离最小的文本block
-            if between_dict:
-                min_key = min(between_dict, key=between_dict.get)
-                spans_list = []
-                for span in pymu_raw_blocks[min_key]['lines']: 
-                    for text_piece in span['spans']:
-                        # 防止索引定位文本内容过多
-                        if len(spans_list) < 60:
-                            spans_list.append(text_piece['text'])
-                text1 = ''.join(spans_list)
-                
-                image_external_dict['bbox'] = [x0_image, y0_image, x1_image, y1_image]
-                image_external_dict['path'] = image_path 
-                image_external_dict['text'] = text1
-                image_external_dict['markdown_image'] = f'![image_path]({image_path})'
-
-            # 将内部图片或外部图片存入当页所有图片的列表
-            if len(image_internal_dict) != 0:
-                image_all_list.append(image_internal_dict)
-            elif len(image_external_dict) != 0:
-                image_all_list.append(image_external_dict)
-            else:
-                logger.error(f"Can't find the location of image {image_path} in the markdown file")
-
-    content_text = mk_nlp_markdown(para_dict)
-
-    for image_info_extract in image_all_list:
-        loc = __find_index(content_text, image_info_extract['text'])
-        if loc is not None:
-            content_text = __insert_string(content_text, image_info_extract['markdown_image'], loc)
-        else:
-            logger.error(f"Can't find the location of image {image_info_extract['path']} in the markdown file")
+                            logger.error(f"Can't find the location of image {img['image_path']} in the markdown file #1")
+            else:# 应当在两个block之间
+                # 找到上方最近的block，如果上方没有就找大下方最近的block
+                top_txt_block = find_top_nearest_text_bbox(pymu_raw_blocks, imgbox)
+                if top_txt_block:
+                    line_txt = "".join([s['text'] for s in top_txt_block['lines'][-1]['spans']])
+                    __insert_after_para(line_txt, img_content, content_lst) 
+                else:
+                    bottom_txt_block = find_bottom_nearest_text_bbox(pymu_raw_blocks, imgbox)
+                    if bottom_txt_block:
+                        line_txt = "".join([s['text'] for s in bottom_txt_block['lines'][0]['spans']])
+                        __insert_before_para(line_txt, img_content, content_lst) 
+                    else: # TODO ，图片可能独占一列，这种情况上下是没有图片的
+                        logger.error(f"Can't find the location of image {img['image_path']} in the markdown file #2")
+    # end for
+    return content_lst
 
-    return content_text
+
+def mk_mm_markdown(content_list):
+    """
+    基于同一格式的内容列表，构造markdown，含图片
+    """
+    content_md = []
+    for c in content_list:
+        content_type = c.get("type")
+        if content_type == "text":
+            content_md.append(c.get("text"))
+        elif content_type == "equation":
+            content_md.append(f"$$\n{c.get('latex')}\n$$")
+        elif content_type in UNI_FORMAT_TEXT_TYPE:
+            content_md.append(f"{'#'*int(content_type[1])} {c.get('text')}")
+        elif content_type == "image":
+            content_md.append(f"![]({c.get('img_path')})")
+    return "\n\n".join(content_md)
+
+def mk_nlp_markdown(content_list):
+    """
+    基于同一格式的内容列表，构造markdown，不含图片
+    """
+    content_md = []
+    for c in content_list:
+        content_type = c.get("type")
+        if content_type == "text":
+            content_md.append(c.get("text"))
+        elif content_type == "equation":
+            content_md.append(f"$$\n{c.get('latex')}\n$$")
+        elif content_type in UNI_FORMAT_TEXT_TYPE:
+            content_md.append(f"{'#'*int(content_type[1])} {c.get('text')}")
+    return "\n\n".join(content_md)

magic_pdf/libs/drop_tag.py

@@ -1,2 +1,9 @@
 
-COLOR_BG_HEADER_TXT_BLOCK = "color_background_header_txt_block"
+COLOR_BG_HEADER_TXT_BLOCK = "color_background_header_txt_block"
+PAGE_NO = "page-no" # 页码
+CONTENT_IN_FOOT_OR_HEADER = 'in-foot-header-area' # 页眉页脚内的文本
+VERTICAL_TEXT = 'vertical-text' # 垂直文本
+ROTATE_TEXT = 'rotate-text' # 旋转文本
+EMPTY_SIDE_BLOCK = 'empty-side-block' # 边缘上的空白没有任何内容的block
+ON_IMAGE_TEXT = 'on-image-text' # 文本在图片上
+ON_TABLE_TEXT = 'on-table-text' # 文本在表格上

magic_pdf/pipeline.py

@@ -7,7 +7,7 @@ from magic_pdf.dict2md.ocr_mkcontent import ocr_mk_nlp_markdown, ocr_mk_mm_markd
 from magic_pdf.libs.commons import read_file, join_path, parse_bucket_key, formatted_time, s3_image_save_path
 from magic_pdf.libs.drop_reason import DropReason
 from magic_pdf.libs.json_compressor import JsonCompressor
-from magic_pdf.dict2md.mkcontent import mk_nlp_markdown
+from magic_pdf.dict2md.mkcontent import mk_nlp_markdown, mk_universal_format
 from magic_pdf.pdf_parse_by_model import parse_pdf_by_model
 from magic_pdf.filter.pdf_classify_by_type import classify
 from magic_pdf.filter.pdf_meta_scan import pdf_meta_scan
@@ -237,9 +237,10 @@ def pdf_intermediate_dict_to_markdown(jso: dict, debug_mode=False) -> dict:
         pdf_intermediate_dict = jso['pdf_intermediate_dict']
         # 将 pdf_intermediate_dict 解压
         pdf_intermediate_dict = JsonCompressor.decompress_json(pdf_intermediate_dict)
-        markdown_content = mk_nlp_markdown(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)}", file=sys.stderr)
+        #markdown_content = mk_nlp_markdown(pdf_intermediate_dict)
+        jso['content_list'] = mk_universal_format(pdf_intermediate_dict)
+        #jso["content"] = markdown_content
+        logger.info(f"book_name is:{get_data_source(jso)}/{jso['file_id']}")
         # 把无用的信息清空
         jso["doc_layout_result"] = ""
         jso["pdf_intermediate_dict"] = ""

magic_pdf/pre_proc/equations_replace.py

@@ -6,9 +6,10 @@ import json
 import os
 from pathlib import Path
 from loguru import logger
+from magic_pdf.libs.ocr_content_type import ContentType
 
-TYPE_INLINE_EQUATION = "inline-equation"
-TYPE_INTERLINE_EQUATION = "interline-equation"
+TYPE_INLINE_EQUATION = ContentType.InlineEquation
+TYPE_INTERLINE_EQUATION = ContentType.InterlineEquation
 
 
 def combine_chars_to_pymudict(block_dict, char_dict):

magic_pdf/pre_proc/remove_footer_header.py

@@ -1,6 +1,7 @@
 import re
 
 from magic_pdf.libs.boxbase import _is_in_or_part_overlap
+from magic_pdf.libs.drop_tag import CONTENT_IN_FOOT_OR_HEADER, PAGE_NO
 
 
 def remove_headder_footer_one_page(text_raw_blocks, image_bboxes, table_bboxes, header_bboxs, footer_bboxs,
@@ -67,7 +68,7 @@ def remove_headder_footer_one_page(text_raw_blocks, image_bboxes, table_bboxes,
                 blk['lines'].remove(line)
         else:
             # if not blk['lines']:
-            blk['tag'] = 'in-foot-header-area'
+            blk['tag'] = CONTENT_IN_FOOT_OR_HEADER
             text_block_to_remove.append(blk)
 
     """有的时候由于pageNo太小了，总是会有一点和content_boundry重叠一点，被放入正文，因此对于pageNo，进行span粒度的删除"""
@@ -80,7 +81,7 @@ def remove_headder_footer_one_page(text_raw_blocks, image_bboxes, table_bboxes,
                         for span in line['spans']:
                             if _is_in_or_part_overlap(pagenobox, span['bbox']):
                                 # span['text'] = ''
-                                span['tag'] = "page-no"
+                                span['tag'] = PAGE_NO
                                 # 检查这个block是否只有这一个span，如果是，那么就把这个block也删除
                                 if len(line['spans']) == 1 and len(block['lines']) == 1:
                                     page_no_block_2_remove.append(block)
@@ -96,7 +97,7 @@ def remove_headder_footer_one_page(text_raw_blocks, image_bboxes, table_bboxes,
                     if last_span['text'].strip() and not re.search('[a-zA-Z]', last_span['text']) and re.search('[0-9]',
                                                                                                                 last_span[
                                                                                                                     'text']):
-                        last_span['tag'] = "page-no"
+                        last_span['tag'] = PAGE_NO
                         page_no_block_2_remove.append(last_block)
 
     for b in page_no_block_2_remove:

magic_pdf/pre_proc/remove_rotate_bbox.py

@@ -1,6 +1,7 @@
 import math
 
 from magic_pdf.libs.boxbase import is_vbox_on_side
+from magic_pdf.libs.drop_tag import EMPTY_SIDE_BLOCK, ROTATE_TEXT, VERTICAL_TEXT
 
 
 def detect_non_horizontal_texts(result_dict):
@@ -134,13 +135,13 @@ def remove_rotate_side_textblock(pymu_text_block, page_width, page_height):
             is_box_valign = (len(set([int(line['spans'][0]['bbox'][0] ) for line in lines if len(line['spans'])>0]))==1) and (len([int(line['spans'][0]['bbox'][0] ) for line in lines if len(line['spans'])>0])>1)  # 测试bbox在垂直方向是不是x0都相等，也就是在垂直方向排列.同时必须大于等于2个字
             
             if is_box_valign:
-                block['tag'] = "vertical-text"
+                block['tag'] = VERTICAL_TEXT
                 removed_text_block.append(block)
                 continue
         
         for line in lines:
             if line['dir']!=(1,0):
-                block['tag'] = "rotate"
+                block['tag'] = ROTATE_TEXT
                 removed_text_block.append(block) # 只要有一个line不是dir=(1,0)，就把整个block都删掉
                 break
         
@@ -177,7 +178,7 @@ def remove_side_blank_block(pymu_text_block, page_width, page_height):
            continue
             
         if __is_empty_side_box(block):
-            block['tag'] = "empty-side-block"
+            block['tag'] = EMPTY_SIDE_BLOCK
             removed_text_block.append(block)
             continue
         

magic_pdf/pre_proc/resolve_bbox_conflict.py

@@ -6,6 +6,7 @@
 """
 
 from magic_pdf.libs.boxbase import _is_in, _is_in_or_part_overlap, _is_left_overlap
+from magic_pdf.libs.drop_tag import ON_IMAGE_TEXT, ON_TABLE_TEXT
 
 
 def resolve_bbox_overlap_conflict(images:list, tables:list, interline_equations:list, inline_equations:list, text_raw_blocks:list):
@@ -27,14 +28,14 @@ def resolve_bbox_overlap_conflict(images:list, tables:list, interline_equations:
         for text_block in text_raw_blocks:
             text_bbox = text_block["bbox"]
             if _is_in(text_bbox, image_box):
-                text_block['tag'] = "on-image"
+                text_block['tag'] = ON_IMAGE_TEXT
                 text_block_removed.append(text_block)
     # 去掉table上的文字block
     for table_box in tables:
         for text_block in text_raw_blocks:
             text_bbox = text_block["bbox"]
             if _is_in(text_bbox, table_box):
-                text_block['tag'] = "on-table"
+                text_block['tag'] = ON_TABLE_TEXT
                 text_block_removed.append(text_block)
                 
     for text_block in text_block_removed: