Merge pull request #30 from myhloli/master

重构parse_by_ocr_v2

magic_pdf/cli/magicpdf.py

@@ -144,7 +144,7 @@ def pdf_command(pdf, model, method):
         model = pdf.replace(".pdf", ".json")
         if not os.path.exists(model):
             print(f"make sure json file existed and place under {os.dirname(pdf)}")
-            os.eixt(1)
+            os.exit(1)
 
     def read_fn(path):
         disk_rw = DiskReaderWriter(os.path.dirname(path))

magic_pdf/model/magic_model.py

@@ -6,6 +6,7 @@ from loguru import logger
 
 from magic_pdf.libs.commons import join_path
 from magic_pdf.libs.coordinate_transform import get_scale_ratio
+from magic_pdf.libs.ocr_content_type import ContentType
 from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
 from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
 from magic_pdf.libs.math import float_gt
@@ -19,6 +20,7 @@ class MagicModel:
     """
 
     def __fix_axis(self):
+        need_remove_list = []
         for model_page_info in self.__model_list:
             page_no = model_page_info["page_info"]["page_no"]
             horizontal_scale_ratio, vertical_scale_ratio = get_scale_ratio(
@@ -34,6 +36,12 @@ class MagicModel:
                     int(y1 / vertical_scale_ratio),
                 ]
                 layout_det["bbox"] = bbox
+                # 删除高度或者宽度为0的spans
+                if bbox[2] - bbox[0] == 0 or bbox[3] - bbox[1] == 0:
+                    need_remove_list.append(layout_det)
+            for need_remove in need_remove_list:
+                layout_dets.remove(need_remove)
+
 
     def __init__(self, model_list: list, docs: fitz.Document):
         self.__model_list = model_list
@@ -175,10 +183,12 @@ class MagicModel:
                         if l in (j, k) or l in used or l in seen:
                             continue
 
+
                         if not float_gt(dis[l][k], dis[j][k]):
                             is_nearest = False
                             break
 
+
                     if is_nearest:
                         tmp.append(k)
                         seen.add(k)
@@ -349,10 +359,58 @@ class MagicModel:
         pass  # @凯文
 
     def get_ocr_text(self, page_no: int) -> list:  # paddle 搞的，有字也有坐标
-        pass  # @小蒙
-
-    def get_ocr_spans(self, page_no: int) -> list:
-        pass  # @小蒙
+        text_spans = []
+        model_page_info = self.__model_list[page_no]
+        layout_dets = model_page_info["layout_dets"]
+        for layout_det in layout_dets:
+            if layout_det["category_id"] == "15":
+                span = {
+                    "bbox": layout_det['bbox'],
+                    "content": layout_det["text"],
+                }
+                text_spans.append(span)
+        return text_spans
+
+    def get_all_spans(self, page_no: int) -> list:
+        all_spans = []
+        model_page_info = self.__model_list[page_no]
+        layout_dets = model_page_info["layout_dets"]
+        allow_category_id_list = [3, 5, 13, 14, 15]
+        """当成span拼接的"""
+        #  3: 'image', # 图片
+        #  4: 'table',       # 表格
+        #  13: 'inline_equation',     # 行内公式
+        #  14: 'interline_equation',      # 行间公式
+        #  15: 'text',      # ocr识别文本
+        for layout_det in layout_dets:
+            category_id = layout_det["category_id"]
+            if category_id in allow_category_id_list:
+                span = {
+                    "bbox": layout_det['bbox']
+                }
+                if category_id == 3:
+                    span["type"] = ContentType.Image
+                elif category_id == 5:
+                    span["type"] = ContentType.Table
+                elif category_id == 13:
+                    span["content"] = layout_det["latex"]
+                    span["type"] = ContentType.InlineEquation
+                elif category_id == 14:
+                    span["content"] = layout_det["latex"]
+                    span["type"] = ContentType.InterlineEquation
+                elif category_id == 15:
+                    span["content"] = layout_det["text"]
+                    span["type"] = ContentType.Text
+                all_spans.append(span)
+        return all_spans
+
+    def get_page_size(self, page_no: int):  # 获取页面宽高
+        # 获取当前页的page对象
+        page = self.__docs[page_no]
+        # 获取当前页的宽高
+        page_w = page.rect.width
+        page_h = page.rect.height
+        return page_w, page_h
 
 
 if __name__ == "__main__":

magic_pdf/parse_by_ocr_v2.py

@@ -0,0 +1,63 @@
+from magic_pdf.layout.layout_sort import get_bboxes_layout
+from magic_pdf.libs.hash_utils import compute_md5
+from magic_pdf.libs.commons import fitz
+from magic_pdf.model.magic_model import MagicModel
+from magic_pdf.pre_proc.cut_image import ocr_cut_image_and_table
+from magic_pdf.pre_proc.ocr_detect_all_bboxes import ocr_prepare_bboxes_for_layout_split
+from magic_pdf.pre_proc.ocr_dict_merge import sort_blocks_by_layout, fill_spans_in_blocks, fix_block_spans
+from magic_pdf.pre_proc.ocr_span_list_modify import remove_overlaps_min_spans
+
+
+def parse_pdf_by_ocr(pdf_bytes,
+                     model_list,
+                     imageWriter,
+                     start_page_id=0,
+                     end_page_id=None,
+                     debug_mode=False,
+                     ):
+
+    pdf_bytes_md5 = compute_md5(pdf_bytes)
+    pdf_docs = fitz.open("pdf", pdf_bytes)
+
+    '''用model_list和docs对象初始化magic_model'''
+    magic_model = MagicModel(model_list, pdf_docs)
+
+    '''根据输入的起始范围解析pdf'''
+    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):
+
+        '''从magic_model对象中获取后面会用到的区块信息'''
+        img_blocks = magic_model.get_imgs(page_id)
+        table_blocks = magic_model.get_tables(page_id)
+        discarded_blocks = magic_model.get_discarded(page_id)
+        text_blocks = magic_model.get_text_blocks(page_id)
+        title_blocks = magic_model.get_title_blocks(page_id)
+        inline_equations, interline_equations, interline_equation_blocks = magic_model.get_equations(page_id)
+
+        page_w, page_h = magic_model.get_page_size(page_id)
+
+        '''将所有区块的bbox整理到一起'''
+        all_bboxes = ocr_prepare_bboxes_for_layout_split(
+            img_blocks, table_blocks, discarded_blocks, text_blocks, title_blocks,
+            interline_equation_blocks, page_w, page_h)
+
+        '''根据区块信息计算layout'''
+        page_boundry = [0, 0, page_w, page_h]
+        layout_bboxes, layout_tree = get_bboxes_layout(all_bboxes, page_boundry, page_id)
+
+        '''根据layout顺序，对当前页面所有需要留下的block进行排序'''
+        sorted_blocks = sort_blocks_by_layout(all_bboxes, layout_bboxes)
+
+        '''获取所有需要拼接的span资源'''
+        spans = magic_model.get_all_spans(page_id)
+        '''删除重叠spans中较小的那些'''
+        spans, dropped_spans_by_span_overlap = remove_overlaps_min_spans(spans)
+        '''对image和table截图'''
+        spans = ocr_cut_image_and_table(spans, pdf_docs[page_id], page_id, pdf_bytes_md5, imageWriter)
+
+        '''将span填入排好序的blocks中'''
+        block_with_spans = fill_spans_in_blocks(sorted_blocks, spans)
+
+        '''对block进行fix操作'''
+        fix_blocks = fix_block_spans(block_with_spans, img_blocks, table_blocks)
+

magic_pdf/pdf_parse_by_ocr.py

@@ -160,9 +160,6 @@ def parse_pdf_by_ocr(
         '''bbox去除粘连'''
         spans = remove_overlap_between_bbox(spans)
 
-        '''用现有的bbox计算layout'''
-
-
         '''
         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

magic_pdf/pipe/UNIPipe.py

@@ -1,21 +1,17 @@
 import json
 
 from loguru import logger
-from magic_pdf.dict2md.mkcontent import mk_universal_format, mk_mm_markdown
-from magic_pdf.dict2md.ocr_mkcontent import make_standard_format_with_para, ocr_mk_mm_markdown_with_para
-from magic_pdf.filter.pdf_classify_by_type import classify
-from magic_pdf.filter.pdf_meta_scan import pdf_meta_scan
 from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
 from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
 from magic_pdf.libs.commons import join_path
-from magic_pdf.libs.json_compressor import JsonCompressor
 from magic_pdf.pipe.AbsPipe import AbsPipe
 from magic_pdf.user_api import parse_union_pdf, parse_ocr_pdf
 
 
 class UNIPipe(AbsPipe):
 
-    def __init__(self, pdf_bytes: bytes, model_list: list, image_writer: AbsReaderWriter, img_parent_path: str, is_debug: bool = False):
+    def __init__(self, pdf_bytes: bytes, model_list: list, image_writer: AbsReaderWriter, img_parent_path: str,
+                 is_debug: bool = False):
         self.pdf_type = self.PIP_OCR
         super().__init__(pdf_bytes, model_list, image_writer, img_parent_path, is_debug)
 
@@ -24,9 +20,11 @@ class UNIPipe(AbsPipe):
 
     def pipe_parse(self):
         if self.pdf_type == self.PIP_TXT:
-            self.pdf_mid_data = parse_union_pdf(self.pdf_bytes, self.model_list, self.image_writer, is_debug=self.is_debug)
+            self.pdf_mid_data = parse_union_pdf(self.pdf_bytes, self.model_list, self.image_writer,
+                                                is_debug=self.is_debug)
         elif self.pdf_type == self.PIP_OCR:
-            self.pdf_mid_data = parse_ocr_pdf(self.pdf_bytes, self.model_list, self.image_writer, is_debug=self.is_debug)
+            self.pdf_mid_data = parse_ocr_pdf(self.pdf_bytes, self.model_list, self.image_writer,
+                                              is_debug=self.is_debug)
 
     def pipe_mk_uni_format(self):
         content_list = AbsPipe.mk_uni_format(self.get_compress_pdf_mid_data(), self.img_parent_path)
@@ -36,6 +34,7 @@ class UNIPipe(AbsPipe):
         markdown_content = AbsPipe.mk_markdown(self.get_compress_pdf_mid_data(), self.img_parent_path)
         return markdown_content
 
+
 if __name__ == '__main__':
     # 测试
     drw = DiskReaderWriter(r"D:/project/20231108code-clean")
@@ -60,5 +59,6 @@ if __name__ == '__main__':
 
     md_writer = DiskReaderWriter(write_path)
     md_writer.write(md_content, "19983-00.md", AbsReaderWriter.MODE_TXT)
-    md_writer.write(json.dumps(pipe.pdf_mid_data, ensure_ascii=False, indent=4), "19983-00.json", AbsReaderWriter.MODE_TXT)
+    md_writer.write(json.dumps(pipe.pdf_mid_data, ensure_ascii=False, indent=4), "19983-00.json",
+                    AbsReaderWriter.MODE_TXT)
     md_writer.write(str(content_list), "19983-00.txt", AbsReaderWriter.MODE_TXT)

magic_pdf/pre_proc/ocr_detect_all_bboxes.py

@@ -0,0 +1,32 @@
+def ocr_prepare_bboxes_for_layout_split(img_blocks, table_blocks, discarded_blocks, text_blocks,
+                                        title_blocks, interline_equation_blocks, page_w, page_h):
+    all_bboxes = []
+
+    for image in img_blocks:
+        x0, y0, x1, y1 = image['bbox']
+        all_bboxes.append([x0, y0, x1, y1, None, None, None, 'image_block', None, None, None, None])
+
+    for table in table_blocks:
+        x0, y0, x1, y1 = table['bbox']
+        all_bboxes.append([x0, y0, x1, y1, None, None, None, 'table_block', None, None, None, None])
+
+    for text in text_blocks:
+        x0, y0, x1, y1 = text['bbox']
+        all_bboxes.append([x0, y0, x1, y1, None, None, None, 'text_block', None, None, None, None])
+
+    for title in title_blocks:
+        x0, y0, x1, y1 = title['bbox']
+        all_bboxes.append([x0, y0, x1, y1, None, None, None, 'title_block', None, None, None, None])
+
+    for interline_equation in interline_equation_blocks:
+        x0, y0, x1, y1 = interline_equation['bbox']
+        all_bboxes.append([x0, y0, x1, y1, None, None, None, 'interline_equation_block', None, None, None, None])
+
+    '''discarded_blocks中只保留宽度超过1/3页面宽度的，高度超过10的，处于页面下半50%区域的（限定footnote）'''
+    for discarded in discarded_blocks:
+        x0, y0, x1, y1 = discarded['bbox']
+        if (x1 - x0) > (page_w / 3) and (y1 - y0) > 10 and y0 > (page_h / 2):
+            all_bboxes.append([x0, y0, x1, y1, None, None, None, 'footnote', None, None, None, None])
+
+    return all_bboxes
+

magic_pdf/pre_proc/ocr_dict_merge.py

@@ -4,6 +4,7 @@ from magic_pdf.libs.boxbase import __is_overlaps_y_exceeds_threshold, get_minbox
     calculate_overlap_area_in_bbox1_area_ratio
 from magic_pdf.libs.drop_tag import DropTag
 from magic_pdf.libs.ocr_content_type import ContentType
+from magic_pdf.pre_proc.ocr_fix_block_logic import fix_image_block, fix_table_block
 
 
 # 将每一个line中的span从左到右排序
@@ -24,6 +25,7 @@ def line_sort_spans_by_left_to_right(lines):
         })
     return line_objects
 
+
 def merge_spans_to_line(spans):
     if len(spans) == 0:
         return []
@@ -37,7 +39,8 @@ def merge_spans_to_line(spans):
             # 如果当前的span类型为"interline_equation" 或者 当前行中已经有"interline_equation"
             # image和table类型，同上
             if span['type'] in [ContentType.InterlineEquation, ContentType.Image, ContentType.Table] or any(
-                    s['type'] in [ContentType.InterlineEquation, ContentType.Image, ContentType.Table] for s in current_line):
+                    s['type'] in [ContentType.InterlineEquation, ContentType.Image, ContentType.Table] for s in
+                    current_line):
                 # 则开始新行
                 lines.append(current_line)
                 current_line = [span]
@@ -57,6 +60,7 @@ def merge_spans_to_line(spans):
 
         return lines
 
+
 def merge_spans_to_line_by_layout(spans, layout_bboxes):
     lines = []
     new_spans = []
@@ -103,7 +107,80 @@ def merge_lines_to_block(lines):
     return blocks
 
 
+def sort_blocks_by_layout(all_bboxes, layout_bboxes):
+    new_blocks = []
+    sort_blocks = []
+    for item in layout_bboxes:
+        layout_bbox = item['layout_bbox']
 
+        # 遍历blocks,将每个blocks放入对应的layout中
+        layout_blocks = []
+        for block in all_bboxes:
+            # 如果是footnote则跳过
+            if block[7] == 'footnote':
+                continue
+            block_bbox = [block[0], block[1], block[2], block[3]]
+            if calculate_overlap_area_in_bbox1_area_ratio(block_bbox, layout_bbox) > 0.8:
+                layout_blocks.append(block)
 
-
-
+        # 如果layout_blocks不为空，则放入new_blocks中
+        if len(layout_blocks) > 0:
+            new_blocks.append(layout_blocks)
+            # 从spans删除已经放入layout_sapns中的span
+            for layout_block in layout_blocks:
+                all_bboxes.remove(layout_block)
+
+    # 如果new_blocks不为空，则对new_blocks中每个block进行排序
+    if len(new_blocks) > 0:
+        for bboxes_in_layout_block in new_blocks:
+            bboxes_in_layout_block.sort(key=lambda x: x[1])  # 一个layout内部的box，按照y0自上而下排序
+            sort_blocks.extend(bboxes_in_layout_block)
+
+    # sort_blocks中已经包含了当前页面所有最终留下的block，且已经排好了顺序
+    return sort_blocks
+
+
+def fill_spans_in_blocks(blocks, spans):
+    block_with_spans = []
+    for block in blocks:
+        block_type = block[7]
+        block_bbox = block[0:4]
+        block_dict = {
+            'block_type': block_type,
+            'bbox': block_bbox,
+        }
+        block_spans = []
+        for span in spans:
+            span_bbox = span['bbox']
+            if calculate_overlap_area_in_bbox1_area_ratio(span_bbox, block_bbox) > 0.8:
+                block_spans.append(span)
+        block_dict['spans'] = block_spans
+        block_with_spans.append(block_dict)
+
+        # 从spans删除已经放入block_spans中的span
+        if len(block_spans) > 0:
+            for span in block_spans:
+                spans.remove(span)
+
+    return block_with_spans
+
+
+def fix_block_spans(block_with_spans, img_blocks, table_blocks):
+    fix_blocks = []
+    for block in block_with_spans:
+        block_type = block['block_type']
+        # 只有type为image_block和table_block才需要处理
+        if block_type == 'image_block':
+            block = fix_image_block(block, img_blocks)
+        elif block_type == 'table_block':
+            block = fix_table_block(block, table_blocks)
+        elif block_type == 'text_block':
+            pass
+        elif block_type == 'title_block':
+            pass
+        elif block_type == 'interline_equation_block':
+            pass
+        else:
+            continue
+        fix_blocks.append(block)
+    return fix_blocks

magic_pdf/pre_proc/ocr_fix_block_logic.py

@@ -0,0 +1,101 @@
+from magic_pdf.libs.boxbase import calculate_overlap_area_in_bbox1_area_ratio
+from magic_pdf.libs.ocr_content_type import ContentType
+from magic_pdf.pre_proc.ocr_dict_merge import merge_spans_to_line, line_sort_spans_by_left_to_right
+
+def merge_spans_to_block(spans: list, block_bbox: list, block_type: str):
+    block_spans = []
+    # 如果有img_caption，则将img_block中的text_spans放入img_caption_block中
+    for span in spans:
+        if calculate_overlap_area_in_bbox1_area_ratio(span['bbox'], block_bbox) > 0.8:
+            block_spans.append(span)
+    block_lines = merge_spans_to_line(block_spans)
+    # 对line中的span进行排序
+    sort_block_lines = line_sort_spans_by_left_to_right(block_lines)
+    block = {
+        'bbox': block_bbox,
+        'block_type': block_type,
+        'lines': sort_block_lines
+    }
+    return block, block_spans
+
+def make_body_block(span: dict, block_bbox: list, block_type: str):
+    # 创建body_block
+    body_line = {
+        'bbox': block_bbox,
+        'spans': [span],
+    }
+    body_block = {
+        'bbox': block_bbox,
+        'block_type': block_type,
+        'lines': [body_line]
+    }
+    return body_block
+
+
+def fix_image_block(block, img_blocks):
+    block['blocks'] = []
+    # 遍历img_blocks,找到与当前block匹配的img_block
+    for img_block in img_blocks:
+        if img_block['bbox'] == block['bbox']:
+            # 创建img_body_block
+            for span in block['spans']:
+                if span['type'] == ContentType.Image and span['bbox'] == img_block['img_body_bbox']:
+                    # 创建img_body_block
+                    img_body_block = make_body_block(span, img_block['img_body_bbox'], 'img_body_block')
+                    block['blocks'].append(img_body_block)
+
+                    # 从spans中移除img_body_block中已经放入的span
+                    block['spans'].remove(span)
+                    break
+
+            # 根据list长度，判断img_block中是否有img_caption
+            if len(img_block['img_caption_bbox']) > 0:
+                img_caption_block, img_caption_spans = merge_spans_to_block(
+                    block['spans'], img_block['img_caption_bbox'], 'img_caption_block'
+                )
+                block['blocks'].append(img_caption_block)
+
+            break
+    del block['spans']
+    return block
+
+
+def fix_table_block(block, table_blocks):
+    block['blocks'] = []
+    # 遍历table_blocks,找到与当前block匹配的table_block
+    for table_block in table_blocks:
+        if table_block['bbox'] == block['bbox']:
+            # 创建table_body_block
+            for span in block['spans']:
+                if span['type'] == ContentType.Table and span['bbox'] == table_block['table_body_bbox']:
+                    # 创建table_body_block
+                    table_body_block = make_body_block(span, table_block['table_body_bbox'], 'table_body_block')
+                    block['blocks'].append(table_body_block)
+
+                    # 从spans中移除img_body_block中已经放入的span
+                    block['spans'].remove(span)
+                    break
+
+            # 根据list长度，判断table_block中是否有caption
+            if len(table_block['table_caption_bbox']) > 0:
+                table_caption_block, table_caption_spans = merge_spans_to_block(
+                    block['spans'], table_block['table_caption_bbox'], 'table_caption_block'
+                )
+                block['blocks'].append(table_caption_block)
+
+                # 如果table_caption_block_spans不为空
+                if len(table_caption_spans) > 0:
+                    #  一些span已经放入了caption_block中，需要从block['spans']中删除
+                    for span in table_caption_spans:
+                        block['spans'].remove(span)
+
+            # 根据list长度，判断table_block中是否有table_note
+            if len(table_block['table_footnote_bbox']) > 0:
+                table_footnote_block, table_footnote_spans = merge_spans_to_block(
+                    block['spans'], table_block['table_footnote_bbox'], 'table_footnote_block'
+                )
+                block['blocks'].append(table_footnote_block)
+
+            break
+    del block['spans']
+    return block