def convert_elements_to_legacy_format(elements_result):
"""
将 elements 格式转换为原有的 detail/pages 格式
Args:
elements_result: parse_mode 为 lite 或 vlm 时返回的 result 对象，包含 success_count 和 elements
Returns:
转换后的结果，包含 detail 和 pages 结构
"""
if not elements_result or 'elements' not in elements_result:
raise ValueError("输入结果不包含 elements 字段")
elements = elements_result.get('elements', [])
success_count = elements_result.get('success_count', 0)
# 按页码分组 elements
pages_dict = {}
detail_list = []
paragraph_id_counter = 0
# 用于生成 markdown：收集所有 text 和 is_continue 信息
markdown_parts = []
for idx, element in enumerate(elements):
if not element or 'metadata' not in element:
continue
metadata = element.get('metadata', {})
page_number = metadata.get('page_number', 1)
element_type = element.get('type', '')
text = element.get('text', '')
is_continue = metadata.get('is_continue', False)
coordinates = metadata.get('coordinates', [])
category_depth = metadata.get('category_depth', -1)
parent_id = metadata.get('parent_id', '')
sub_type = metadata.get('sub_type', '')
page_width = metadata.get('page_width', 0)
page_height = metadata.get('page_height', 0)
angle = metadata.get('angle', 0)
page_image_url = metadata.get('page_image_url', '')
original_image_url = metadata.get('original_image_url', '')
image_url = metadata.get('image_url', '')
image_base64 = metadata.get('image_base64', '')
# 初始化页面数据
if page_number not in pages_dict:
pages_dict[page_number] = {
'page_id': page_number,
'status': 'success',
'width': page_width,
'height': page_height,
'angle': angle,
'image_id': '',
'content': [],
'structured': [],
'durations': 0.0
}
page_data = pages_dict[page_number]
# 转换坐标：从归一化坐标转换为像素坐标
# coordinates 是归一化的 [x1, y1, x2, y2, x3, y3, x4, y4]
position = []
if len(coordinates) >= 8 and page_width > 0 and page_height > 0:
for i in range(0, 8, 2):
x = int(coordinates[i] * page_width)
y = int(coordinates[i + 1] * page_height)
position.extend([x, y])
else:
position = [0, 0, 0, 0, 0, 0, 0, 0]
# 创建 detail 条目
detail_item = {
'paragraph_id': paragraph_id_counter,
'page_id': page_number,
'outline_level': category_depth,
'text': text,
'position': position,
'type': '',
'sub_type': '',
'content': 0
}
# 根据 element type 映射到 detail 的 type 和 sub_type
type_mapping = {
'NarrativeText': ('paragraph', 'text'),
'Title': ('paragraph', 'text_title'),
'Table': ('table', 'bordered'),
'TableCaption': ('paragraph', 'table_title'),
'Image': ('image', sub_type if sub_type else ''),
'FigureCaption': ('paragraph', 'image_title'),
'Formula': ('paragraph', 'text'),
'Header': ('paragraph', 'header'),
'Footer': ('paragraph', 'footer'),
'CodeSnippet': ('paragraph', 'text'),
'PageNumber': ('paragraph', 'text'),
'UncategorizedText': ('paragraph', 'text')
}
detail_type, detail_sub_type = type_mapping.get(element_type, ('paragraph', 'text'))
detail_item['type'] = detail_type
detail_item['sub_type'] = detail_sub_type
# 处理图片相关字段
if element_type == 'Image' and image_url:
detail_item['image_url'] = image_url
if element_type == 'Image' and image_base64:
detail_item['image_base64'] = image_base64
detail_list.append(detail_item)
# 创建 content 条目（文本行）
content_id = len(page_data['content'])
content_item = {
'id': content_id,
'type': 'line',
'text': text,
'pos': position,
'angle': angle,
'score': 1.0
}
page_data['content'].append(content_item)
# 创建 structured 条目
structured_item = {
'type': 'textblock' if detail_type == 'paragraph' else detail_type,
'pos': position,
'content': [content_id],
'text': text,
'outline_level': category_depth
}
if detail_sub_type:
structured_item['sub_type'] = detail_sub_type
if detail_type == 'table':
structured_item['rows'] = 1
structured_item['cols'] = 1
structured_item['columns_width'] = [position[2] - position[0]] if len(position) >= 4 else [100]
structured_item['rows_height'] = [position[5] - position[1]] if len(position) >= 6 else [50]
structured_item['cells'] = []
if detail_type == 'image':
structured_item['lines'] = [content_id]
structured_item['content'] = [content_id]
page_data['structured'].append(structured_item)
# 收集 markdown 内容
markdown_parts.append({
'text': text,
'is_continue': is_continue
})
paragraph_id_counter += 1
# 生成 markdown：根据 is_continue 决定拼接方式
markdown_lines = []
for idx, part in enumerate(markdown_parts):
if idx == 0:
# 第一个元素直接添加
markdown_lines.append(part['text'])
else:
# 如果前一个元素 is_continue=True，直接拼接；否则用换行符拼接
prev_is_continue = markdown_parts[idx - 1]['is_continue']
if prev_is_continue:
# 直接拼接（追加到最后一个元素）
markdown_lines[-1] += part['text']
else:
# 用换行符拼接
markdown_lines.append(part['text'])
markdown = '\n'.join(markdown_lines)
# 构建最终结果
pages_list = [pages_dict[page_num] for page_num in sorted(pages_dict.keys())]
result = {
'markdown': markdown, # 由 elements 中的 text 拼接而成
'detail': detail_list,
'pages': pages_list,
'valid_page_number': success_count,
'total_page_number': len(pages_dict),
'success_count': success_count
}
return result
# 使用示例
if __name__ == "__main__":
# 示例：从 API 响应中提取 result
api_response = {
"code": 200,
"message": "success",
"result": {
"success_count": 1,
"elements": [
{
"element_id": "",
"type": "NarrativeText",
"text": "xParse 是一个端到端文档处理 AI 基础设施",
"metadata": {
"page_image_url": "https://web-api.textin.com/ocr_image/external/01a91572ca81092c.jpg",
"original_image_url": "",
"angle": 0,
"page_number": 1,
"page_width": 600,
"page_height": 800,
"coordinates": [0.182200, 0.231600, 0.671700, 0.231600, 0.671700, 0.273200, 0.182200, 0.273200],
"is_continue": False,
"category_depth": -1,
"parent_id": ""
}
}
]
}
}
# 转换格式
try:
converted_result = convert_elements_to_legacy_format(api_response['result'])
print("转换成功！")
print(f"Detail 条目数: {len(converted_result['detail'])}")
print(f"Pages 条目数: {len(converted_result['pages'])}")
except Exception as e:
print(f"转换失败: {e}")
