增加标准格式的拼装逻辑

demo/ocr_demo.py

@@ -4,7 +4,7 @@ import os
 from loguru import logger
 from pathlib import Path
 
-from magic_pdf.dict2md.ocr_mkcontent import mk_mm_markdown2, mk_nlp_markdown, mk_mm_markdown
+from magic_pdf.dict2md.ocr_mkcontent import ocr_mk_mm_markdown_with_para, ocr_mk_nlp_markdown, ocr_mk_mm_markdown, ocr_mk_mm_standard_format
 from magic_pdf.libs.commons import join_path
 from magic_pdf.pdf_parse_by_ocr import parse_pdf_by_ocr
 
@@ -35,8 +35,8 @@ if __name__ == '__main__':
     # ocr_pdf_path = r"D:\project\20231108code-clean\ocr\new\双栏\j.1540-627x.2006.00176.x.pdf"
     # ocr_json_file_path = r"D:\project\20231108code-clean\ocr\new\双栏\j.1540-627x.2006.00176.x.json"
     
-    ocr_pdf_path = r"/home/cxu/workspace/Magic-PDF/ocr_demo/j.1540-627x.2006.00176.x.pdf"
-    ocr_json_file_path = r"/home/cxu/workspace/Magic-PDF/ocr_demo/j.1540-627x.2006.00176.x.json"
+    # ocr_pdf_path = r"/home/cxu/workspace/Magic-PDF/ocr_demo/j.1540-627x.2006.00176.x.pdf"
+    # ocr_json_file_path = r"/home/cxu/workspace/Magic-PDF/ocr_demo/j.1540-627x.2006.00176.x.json"
     try:
         ocr_pdf_model_info = read_json_file(ocr_json_file_path)
         pth = Path(ocr_json_file_path)
@@ -58,11 +58,16 @@ if __name__ == '__main__':
             os.makedirs(parent_dir)
 
         # markdown_content = mk_nlp_markdown(pdf_info_dict)
-        markdown_content = mk_mm_markdown2(pdf_info_dict)
+        markdown_content = ocr_mk_mm_markdown_with_para(pdf_info_dict)
 
         with open(text_content_save_path, "w", encoding="utf-8") as f:
             f.write(markdown_content)
 
+        standard_format = ocr_mk_mm_standard_format(pdf_info_dict)
+        standard_format_save_path = f"{save_path_with_bookname}/standard_format.txt"
+        with open(standard_format_save_path, "w", encoding="utf-8") as f:
+            f.write(str(standard_format))
+
         # logger.info(markdown_content)
         # save_markdown(markdown_text, ocr_json_file_path)
     except Exception as e:

magic_pdf/dict2md/ocr_mkcontent.py

@@ -28,7 +28,6 @@ def ocr_mk_nlp_markdown(pdf_info_dict: dict):
 
 
 def ocr_mk_mm_markdown(pdf_info_dict: dict):
-
     markdown = []
 
     for _, page_info in pdf_info_dict.items():
@@ -56,7 +55,7 @@ def ocr_mk_mm_markdown(pdf_info_dict: dict):
     return '\n'.join(markdown)
 
 
-def mk_mm_markdown2(pdf_info_dict:dict):
+def ocr_mk_mm_markdown_with_para(pdf_info_dict: dict):
     markdown = []
     for _, page_info in pdf_info_dict.items():
         paras = page_info.get("para_blocks")
@@ -80,10 +79,64 @@ def mk_mm_markdown2(pdf_info_dict:dict):
     return '\n\n'.join(markdown)
 
 
-def ocr_mk_mm_standard_format():
+def line_to_standard_format(line):
+    line_text = ""
+    inline_equation_num = 0
+    for span in line['spans']:
+        if not span.get('content'):
+            if not span.get('image_path'):
+                continue
+            else:
+                if span['type'] == ContentType.Image:
+                    content = {
+                        'type': 'image',
+                        'img_path': join_path(s3_image_save_path, span['image_path'])
+                    }
+                    return content
+                elif span['type'] == ContentType.Table:
+                    content = {
+                        'type': 'table',
+                        'img_path': join_path(s3_image_save_path, span['image_path'])
+                    }
+                    return content
+        else:
+            if span['type'] == ContentType.InterlineEquation:
+                interline_equation = ocr_escape_special_markdown_char(span['content'])  # 转义特殊符号
+                content = {
+                    'type': 'equation',
+                    'latex': f"$$\n{interline_equation}\n$$"
+                }
+                return content
+            elif span['type'] == ContentType.InlineEquation:
+                inline_equation = ocr_escape_special_markdown_char(span['content'])  # 转义特殊符号
+                line_text += f"${inline_equation}$"
+                inline_equation_num += 1
+            elif span['type'] == ContentType.Text:
+                line_text += span['content']
+    content = {
+        'type': 'text',
+        'text': line_text,
+        'inline_equation_num': inline_equation_num
+    }
+    return content
+
+
+def ocr_mk_mm_standard_format(pdf_info_dict: dict):
     '''
     content_list
-    type string image/text/table/equation(行间的单独拿出来，行内的和text合并)
-
+    type         string      image/text/table/equation(行间的单独拿出来，行内的和text合并)
+    latex        string      latex文本字段。
+    text         string      纯文本格式的文本数据。
+    md           string      markdown格式的文本数据。
+    img_path     string      s3://full/path/to/img.jpg
     '''
-    pass
+    content_list = []
+    for _, page_info in pdf_info_dict.items():
+        blocks = page_info.get("preproc_blocks")
+        if not blocks:
+            continue
+        for block in blocks:
+            for line in block['lines']:
+                content = line_to_standard_format(line)
+                content_list.append(content)
+    return content_list

magic_pdf/pipeline.py

@@ -3,7 +3,7 @@ import sys
 import time
 from urllib.parse import quote
 
-from magic_pdf.dict2md.ocr_mkcontent import ocr_mk_nlp_markdown, ocr_mk_mm_markdown
+from magic_pdf.dict2md.ocr_mkcontent import ocr_mk_nlp_markdown, ocr_mk_mm_markdown, ocr_mk_mm_standard_format
 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
@@ -387,5 +387,31 @@ def ocr_pdf_intermediate_dict_to_markdown(jso: dict, debug_mode=False) -> dict:
     return jso
 
 
+def ocr_pdf_intermediate_dict_to_standard_format(jso: dict, debug_mode=False) -> dict:
+
+    if debug_mode:
+        pass
+    else:  # 如果debug没开，则检测是否有needdrop字段
+        if jso.get('need_drop', False):
+            book_name = join_path(get_data_source(jso), jso['file_id'])
+            logger.info(f"book_name is:{book_name} need drop", file=sys.stderr)
+            jso["dropped"] = True
+            return jso
+    try:
+        pdf_intermediate_dict = jso['pdf_intermediate_dict']
+        # 将 pdf_intermediate_dict 解压
+        pdf_intermediate_dict = JsonCompressor.decompress_json(pdf_intermediate_dict)
+        standard_format = ocr_mk_mm_standard_format(pdf_intermediate_dict)
+        jso["content_list"] = standard_format
+        logger.info(f"book_name is:{get_data_source(jso)}/{jso['file_id']},content_list length is {len(standard_format)}", file=sys.stderr)
+        # 把无用的信息清空
+        jso["doc_layout_result"] = ""
+        jso["pdf_intermediate_dict"] = ""
+        jso["pdf_meta"] = ""
+    except Exception as e:
+        jso = exception_handler(jso, e)
+    return jso
+
+
 if __name__ == "__main__":
     pass

requirements.txt

@@ -11,5 +11,6 @@ pycld2>=0.41
 regex>=2023.12.25
 spacy>=3.7.4
 termcolor>=2.4.0
+scikit-learn>=1.4.1.post1
 en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl
 zh_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/zh_core_web_sm-3.7.0/zh_core_web_sm-3.7.0-py3-none-any.whl