697 lines
26 KiB
Python
697 lines
26 KiB
Python
|
# Copyright (c) Opendatalab. All rights reserved.
|
|||
|
|
import io
|
|||
|
|
import json
|
|||
|
|
import os
|
|||
|
|
import copy
|
|||
|
|
from pathlib import Path
|
|||
|
|
|
|||
|
|
from loguru import logger
|
|||
|
|
import pypdfium2 as pdfium
|
|||
|
|
|
|||
|
|
from mineru.data.data_reader_writer import FileBasedDataWriter
|
|||
|
|
from mineru.utils.draw_bbox import draw_layout_bbox, draw_span_bbox, draw_line_sort_bbox
|
|||
|
|
from mineru.utils.engine_utils import get_vlm_engine
|
|||
|
|
from mineru.utils.enum_class import MakeMode
|
|||
|
|
from mineru.utils.guess_suffix_or_lang import guess_suffix_by_bytes
|
|||
|
|
from mineru.utils.pdf_image_tools import images_bytes_to_pdf_bytes
|
|||
|
|
from mineru.backend.vlm.vlm_middle_json_mkcontent import union_make as vlm_union_make
|
|||
|
|
from mineru.backend.vlm.vlm_analyze import doc_analyze as vlm_doc_analyze
|
|||
|
|
from mineru.backend.vlm.vlm_analyze import aio_doc_analyze as aio_vlm_doc_analyze
|
|||
|
|
from mineru.utils.pdf_page_id import get_end_page_id
|
|||
|
|
|
|||
|
|
if os.getenv("MINERU_LMDEPLOY_DEVICE", "") == "maca":
|
|||
|
|
import torch
|
|||
|
|
torch.backends.cudnn.enabled = False
|
|||
|
|
|
|||
|
|
|
|||
|
|
pdf_suffixes = ["pdf"]
|
|||
|
|
image_suffixes = ["png", "jpeg", "jp2", "webp", "gif", "bmp", "jpg", "tiff"]
|
|||
|
|
word_suffixes = ["docx", "doc"]
|
|||
|
|
|
|||
|
|
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
|||
|
|
|
|||
|
|
def read_fn(path):
|
|||
|
|
if not isinstance(path, Path):
|
|||
|
|
path = Path(path)
|
|||
|
|
with open(str(path), "rb") as input_file:
|
|||
|
|
file_bytes = input_file.read()
|
|||
|
|
file_suffix = guess_suffix_by_bytes(file_bytes, path)
|
|||
|
|
if file_suffix in image_suffixes:
|
|||
|
|
return images_bytes_to_pdf_bytes(file_bytes)
|
|||
|
|
elif file_suffix in pdf_suffixes:
|
|||
|
|
return file_bytes
|
|||
|
|
elif file_suffix in word_suffixes:
|
|||
|
|
# 处理 Word 文件，转换为 PDF（保持原格式）
|
|||
|
|
from io import BytesIO
|
|||
|
|
import tempfile
|
|||
|
|
import os
|
|||
|
|
|
|||
|
|
try:
|
|||
|
|
# 方法 1: 使用 LibreOffice 进行高质量转换（推荐）
|
|||
|
|
# 创建临时文件
|
|||
|
|
with tempfile.NamedTemporaryFile(suffix=f'.{file_suffix}', delete=False) as temp_word:
|
|||
|
|
temp_word.write(file_bytes)
|
|||
|
|
temp_word_path = temp_word.name
|
|||
|
|
|
|||
|
|
pdf_fd, pdf_path = tempfile.mkstemp(suffix='.pdf')
|
|||
|
|
os.close(pdf_fd)
|
|||
|
|
|
|||
|
|
try:
|
|||
|
|
# 使用 LibreOffice 进行转换（保持原格式，包括图片、表格等）
|
|||
|
|
import subprocess
|
|||
|
|
result = subprocess.run(
|
|||
|
|
[
|
|||
|
|
'libreoffice', '--headless', '--convert-to', 'pdf',
|
|||
|
|
'--outdir', os.path.dirname(pdf_path),
|
|||
|
|
temp_word_path
|
|||
|
|
],
|
|||
|
|
capture_output=True,
|
|||
|
|
timeout=120
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
if result.returncode == 0:
|
|||
|
|
# LibreOffice 会在同目录下生成 PDF
|
|||
|
|
base_name = os.path.basename(temp_word_path).rsplit('.', 1)[0]
|
|||
|
|
generated_pdf = os.path.join(os.path.dirname(temp_word_path), f"{base_name}.pdf")
|
|||
|
|
|
|||
|
|
if os.path.exists(generated_pdf):
|
|||
|
|
with open(generated_pdf, 'rb') as f:
|
|||
|
|
pdf_bytes_result = f.read()
|
|||
|
|
os.remove(generated_pdf)
|
|||
|
|
os.remove(temp_word_path)
|
|||
|
|
return pdf_bytes_result
|
|||
|
|
|
|||
|
|
logger.warning(f"LibreOffice conversion failed: {result.stderr}")
|
|||
|
|
|
|||
|
|
except (subprocess.TimeoutExpired, FileNotFoundError) as libreoffice_error:
|
|||
|
|
logger.warning(f"LibreOffice not available or failed: {libreoffice_error}")
|
|||
|
|
|
|||
|
|
finally:
|
|||
|
|
# 清理临时文件
|
|||
|
|
if os.path.exists(temp_word_path):
|
|||
|
|
os.remove(temp_word_path)
|
|||
|
|
if os.path.exists(pdf_path):
|
|||
|
|
os.remove(pdf_path)
|
|||
|
|
|
|||
|
|
# 方法 2: 如果 LibreOffice 不可用，使用 python-docx + reportlab 作为备选
|
|||
|
|
if file_suffix == "docx":
|
|||
|
|
from docx import Document
|
|||
|
|
from reportlab.lib.pagesizes import letter
|
|||
|
|
from reportlab.pdfgen import canvas
|
|||
|
|
|
|||
|
|
# 读取 Word 文件
|
|||
|
|
doc = Document(BytesIO(file_bytes))
|
|||
|
|
|
|||
|
|
# 创建 PDF（简单文本转换，不保留复杂格式）
|
|||
|
|
output = BytesIO()
|
|||
|
|
c = canvas.Canvas(output, pagesize=letter)
|
|||
|
|
width, height = letter
|
|||
|
|
|
|||
|
|
y = height - 50
|
|||
|
|
for para in doc.paragraphs:
|
|||
|
|
text = para.text
|
|||
|
|
if text:
|
|||
|
|
# 处理长文本自动换行
|
|||
|
|
max_width = width - 100
|
|||
|
|
words = text.split(' ')
|
|||
|
|
line = ''
|
|||
|
|
for word in words:
|
|||
|
|
test_line = f"{line} {word}".strip()
|
|||
|
|
if c.stringWidth(test_line, 'Helvetica', 12) < max_width:
|
|||
|
|
line = test_line
|
|||
|
|
else:
|
|||
|
|
if y < 50:
|
|||
|
|
c.showPage()
|
|||
|
|
y = height - 50
|
|||
|
|
c.drawString(50, y, line)
|
|||
|
|
y -= 15
|
|||
|
|
line = word
|
|||
|
|
|
|||
|
|
# 写入最后一行
|
|||
|
|
if y < 50:
|
|||
|
|
c.showPage()
|
|||
|
|
y = height - 50
|
|||
|
|
c.drawString(50, y, line)
|
|||
|
|
y -= 15
|
|||
|
|
|
|||
|
|
c.save()
|
|||
|
|
output.seek(0)
|
|||
|
|
return output.read()
|
|||
|
|
|
|||
|
|
raise Exception("Word to PDF conversion failed with all methods")
|
|||
|
|
|
|||
|
|
except Exception as e:
|
|||
|
|
logger.exception(f"Error converting Word file to PDF: {e}")
|
|||
|
|
raise Exception(f"Failed to convert Word file to PDF: {str(e)}. Please install LibreOffice for better conversion: sudo apt-get install libreoffice")
|
|||
|
|
else:
|
|||
|
|
raise Exception(f"Unknown file suffix: {file_suffix}")
|
|||
|
|
|
|||
|
|
|
|||
|
|
def prepare_env(output_dir, pdf_file_name, parse_method):
|
|||
|
|
local_md_dir = str(os.path.join(output_dir, pdf_file_name, parse_method))
|
|||
|
|
local_image_dir = os.path.join(str(local_md_dir), "images")
|
|||
|
|
os.makedirs(local_image_dir, exist_ok=True)
|
|||
|
|
os.makedirs(local_md_dir, exist_ok=True)
|
|||
|
|
return local_image_dir, local_md_dir
|
|||
|
|
|
|||
|
|
|
|||
|
|
def convert_pdf_bytes_to_bytes_by_pypdfium2(pdf_bytes, start_page_id=0, end_page_id=None):
|
|||
|
|
pdf = pdfium.PdfDocument(pdf_bytes)
|
|||
|
|
output_pdf = pdfium.PdfDocument.new()
|
|||
|
|
try:
|
|||
|
|
end_page_id = get_end_page_id(end_page_id, len(pdf))
|
|||
|
|
|
|||
|
|
# 逐页导入,失败则跳过
|
|||
|
|
output_index = 0
|
|||
|
|
for page_index in range(start_page_id, end_page_id + 1):
|
|||
|
|
try:
|
|||
|
|
output_pdf.import_pages(pdf, pages=[page_index])
|
|||
|
|
output_index += 1
|
|||
|
|
except Exception as page_error:
|
|||
|
|
output_pdf.del_page(output_index)
|
|||
|
|
logger.warning(f"Failed to import page {page_index}: {page_error}, skipping this page.")
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
# 将新PDF保存到内存缓冲区
|
|||
|
|
output_buffer = io.BytesIO()
|
|||
|
|
output_pdf.save(output_buffer)
|
|||
|
|
|
|||
|
|
# 获取字节数据
|
|||
|
|
output_bytes = output_buffer.getvalue()
|
|||
|
|
except Exception as e:
|
|||
|
|
logger.warning(f"Error in converting PDF bytes: {e}, Using original PDF bytes.")
|
|||
|
|
output_bytes = pdf_bytes
|
|||
|
|
pdf.close()
|
|||
|
|
output_pdf.close()
|
|||
|
|
return output_bytes
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _prepare_pdf_bytes(pdf_bytes_list, start_page_id, end_page_id):
|
|||
|
|
"""准备处理PDF字节数据"""
|
|||
|
|
result = []
|
|||
|
|
for pdf_bytes in pdf_bytes_list:
|
|||
|
|
new_pdf_bytes = convert_pdf_bytes_to_bytes_by_pypdfium2(pdf_bytes, start_page_id, end_page_id)
|
|||
|
|
result.append(new_pdf_bytes)
|
|||
|
|
return result
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _process_output(
|
|||
|
|
pdf_info,
|
|||
|
|
pdf_bytes,
|
|||
|
|
pdf_file_name,
|
|||
|
|
local_md_dir,
|
|||
|
|
local_image_dir,
|
|||
|
|
md_writer,
|
|||
|
|
f_draw_layout_bbox,
|
|||
|
|
f_draw_span_bbox,
|
|||
|
|
f_dump_orig_pdf,
|
|||
|
|
f_dump_md,
|
|||
|
|
f_dump_content_list,
|
|||
|
|
f_dump_middle_json,
|
|||
|
|
f_dump_model_output,
|
|||
|
|
f_make_md_mode,
|
|||
|
|
middle_json,
|
|||
|
|
model_output=None,
|
|||
|
|
is_pipeline=True
|
|||
|
|
):
|
|||
|
|
f_draw_line_sort_bbox = False
|
|||
|
|
from mineru.backend.pipeline.pipeline_middle_json_mkcontent import union_make as pipeline_union_make
|
|||
|
|
"""处理输出文件"""
|
|||
|
|
if f_draw_layout_bbox:
|
|||
|
|
draw_layout_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_layout.pdf")
|
|||
|
|
|
|||
|
|
if f_draw_span_bbox:
|
|||
|
|
draw_span_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_span.pdf")
|
|||
|
|
|
|||
|
|
if f_dump_orig_pdf:
|
|||
|
|
md_writer.write(
|
|||
|
|
f"{pdf_file_name}_origin.pdf",
|
|||
|
|
pdf_bytes,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
if f_draw_line_sort_bbox:
|
|||
|
|
draw_line_sort_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_line_sort.pdf")
|
|||
|
|
|
|||
|
|
image_dir = str(os.path.basename(local_image_dir))
|
|||
|
|
|
|||
|
|
if f_dump_md:
|
|||
|
|
make_func = pipeline_union_make if is_pipeline else vlm_union_make
|
|||
|
|
md_content_str = make_func(pdf_info, f_make_md_mode, image_dir)
|
|||
|
|
md_writer.write_string(
|
|||
|
|
f"{pdf_file_name}.md",
|
|||
|
|
md_content_str,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
if f_dump_content_list:
|
|||
|
|
make_func = pipeline_union_make if is_pipeline else vlm_union_make
|
|||
|
|
content_list = make_func(pdf_info, MakeMode.CONTENT_LIST, image_dir)
|
|||
|
|
md_writer.write_string(
|
|||
|
|
f"{pdf_file_name}_content_list.json",
|
|||
|
|
json.dumps(content_list, ensure_ascii=False, indent=4),
|
|||
|
|
)
|
|||
|
|
if not is_pipeline:
|
|||
|
|
content_list_v2 = make_func(pdf_info, MakeMode.CONTENT_LIST_V2, image_dir)
|
|||
|
|
md_writer.write_string(
|
|||
|
|
f"{pdf_file_name}_content_list_v2.json",
|
|||
|
|
json.dumps(content_list_v2, ensure_ascii=False, indent=4),
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
if f_dump_middle_json:
|
|||
|
|
md_writer.write_string(
|
|||
|
|
f"{pdf_file_name}_middle.json",
|
|||
|
|
json.dumps(middle_json, ensure_ascii=False, indent=4),
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
if f_dump_model_output:
|
|||
|
|
md_writer.write_string(
|
|||
|
|
f"{pdf_file_name}_model.json",
|
|||
|
|
json.dumps(model_output, ensure_ascii=False, indent=4),
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
logger.info(f"local output dir is {local_md_dir}")
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _process_pipeline(
|
|||
|
|
output_dir,
|
|||
|
|
pdf_file_names,
|
|||
|
|
pdf_bytes_list,
|
|||
|
|
p_lang_list,
|
|||
|
|
parse_method,
|
|||
|
|
p_formula_enable,
|
|||
|
|
p_table_enable,
|
|||
|
|
f_draw_layout_bbox,
|
|||
|
|
f_draw_span_bbox,
|
|||
|
|
f_dump_md,
|
|||
|
|
f_dump_middle_json,
|
|||
|
|
f_dump_model_output,
|
|||
|
|
f_dump_orig_pdf,
|
|||
|
|
f_dump_content_list,
|
|||
|
|
f_make_md_mode,
|
|||
|
|
):
|
|||
|
|
"""处理pipeline后端逻辑"""
|
|||
|
|
from mineru.backend.pipeline.model_json_to_middle_json import result_to_middle_json as pipeline_result_to_middle_json
|
|||
|
|
from mineru.backend.pipeline.pipeline_analyze import doc_analyze as pipeline_doc_analyze
|
|||
|
|
|
|||
|
|
infer_results, all_image_lists, all_pdf_docs, lang_list, ocr_enabled_list = (
|
|||
|
|
pipeline_doc_analyze(
|
|||
|
|
pdf_bytes_list, p_lang_list, parse_method=parse_method,
|
|||
|
|
formula_enable=p_formula_enable, table_enable=p_table_enable
|
|||
|
|
)
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
for idx, model_list in enumerate(infer_results):
|
|||
|
|
model_json = copy.deepcopy(model_list)
|
|||
|
|
pdf_file_name = pdf_file_names[idx]
|
|||
|
|
local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
|
|||
|
|
image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
|
|||
|
|
|
|||
|
|
images_list = all_image_lists[idx]
|
|||
|
|
pdf_doc = all_pdf_docs[idx]
|
|||
|
|
_lang = lang_list[idx]
|
|||
|
|
_ocr_enable = ocr_enabled_list[idx]
|
|||
|
|
|
|||
|
|
middle_json = pipeline_result_to_middle_json(
|
|||
|
|
model_list, images_list, pdf_doc, image_writer,
|
|||
|
|
_lang, _ocr_enable, p_formula_enable
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
pdf_info = middle_json["pdf_info"]
|
|||
|
|
pdf_bytes = pdf_bytes_list[idx]
|
|||
|
|
|
|||
|
|
_process_output(
|
|||
|
|
pdf_info, pdf_bytes, pdf_file_name, local_md_dir, local_image_dir,
|
|||
|
|
md_writer, f_draw_layout_bbox, f_draw_span_bbox, f_dump_orig_pdf,
|
|||
|
|
f_dump_md, f_dump_content_list, f_dump_middle_json, f_dump_model_output,
|
|||
|
|
f_make_md_mode, middle_json, model_json, is_pipeline=True
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
async def _async_process_vlm(
|
|||
|
|
output_dir,
|
|||
|
|
pdf_file_names,
|
|||
|
|
pdf_bytes_list,
|
|||
|
|
backend,
|
|||
|
|
f_draw_layout_bbox,
|
|||
|
|
f_draw_span_bbox,
|
|||
|
|
f_dump_md,
|
|||
|
|
f_dump_middle_json,
|
|||
|
|
f_dump_model_output,
|
|||
|
|
f_dump_orig_pdf,
|
|||
|
|
f_dump_content_list,
|
|||
|
|
f_make_md_mode,
|
|||
|
|
server_url=None,
|
|||
|
|
progress_callback=None,
|
|||
|
|
**kwargs,
|
|||
|
|
):
|
|||
|
|
"""异步处理VLM后端逻辑"""
|
|||
|
|
parse_method = "vlm"
|
|||
|
|
f_draw_span_bbox = False
|
|||
|
|
if not backend.endswith("client"):
|
|||
|
|
server_url = None
|
|||
|
|
|
|||
|
|
total_files = len(pdf_bytes_list)
|
|||
|
|
for idx, pdf_bytes in enumerate(pdf_bytes_list):
|
|||
|
|
pdf_file_name = pdf_file_names[idx]
|
|||
|
|
local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
|
|||
|
|
image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
|
|||
|
|
|
|||
|
|
# 更新进度
|
|||
|
|
if progress_callback:
|
|||
|
|
progress_callback((idx / total_files) * 50, f"处理文件 {idx+1}/{total_files}")
|
|||
|
|
|
|||
|
|
middle_json, infer_result = await aio_vlm_doc_analyze(
|
|||
|
|
pdf_bytes, image_writer=image_writer, backend=backend, server_url=server_url, **kwargs,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
# 更新进度
|
|||
|
|
if progress_callback:
|
|||
|
|
progress_callback(((idx + 1) / total_files) * 100, f"完成文件 {idx+1}/{total_files}")
|
|||
|
|
|
|||
|
|
pdf_info = middle_json["pdf_info"]
|
|||
|
|
|
|||
|
|
_process_output(
|
|||
|
|
pdf_info, pdf_bytes, pdf_file_name, local_md_dir, local_image_dir,
|
|||
|
|
md_writer, f_draw_layout_bbox, f_draw_span_bbox, f_dump_orig_pdf,
|
|||
|
|
f_dump_md, f_dump_content_list, f_dump_middle_json, f_dump_model_output,
|
|||
|
|
f_make_md_mode, middle_json, infer_result, is_pipeline=False
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _process_vlm(
|
|||
|
|
output_dir,
|
|||
|
|
pdf_file_names,
|
|||
|
|
pdf_bytes_list,
|
|||
|
|
backend,
|
|||
|
|
f_draw_layout_bbox,
|
|||
|
|
f_draw_span_bbox,
|
|||
|
|
f_dump_md,
|
|||
|
|
f_dump_middle_json,
|
|||
|
|
f_dump_model_output,
|
|||
|
|
f_dump_orig_pdf,
|
|||
|
|
f_dump_content_list,
|
|||
|
|
f_make_md_mode,
|
|||
|
|
server_url=None,
|
|||
|
|
**kwargs,
|
|||
|
|
):
|
|||
|
|
"""同步处理VLM后端逻辑"""
|
|||
|
|
parse_method = "vlm"
|
|||
|
|
f_draw_span_bbox = False
|
|||
|
|
if not backend.endswith("client"):
|
|||
|
|
server_url = None
|
|||
|
|
|
|||
|
|
for idx, pdf_bytes in enumerate(pdf_bytes_list):
|
|||
|
|
pdf_file_name = pdf_file_names[idx]
|
|||
|
|
local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
|
|||
|
|
image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
|
|||
|
|
|
|||
|
|
middle_json, infer_result = vlm_doc_analyze(
|
|||
|
|
pdf_bytes, image_writer=image_writer, backend=backend, server_url=server_url, **kwargs,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
pdf_info = middle_json["pdf_info"]
|
|||
|
|
|
|||
|
|
_process_output(
|
|||
|
|
pdf_info, pdf_bytes, pdf_file_name, local_md_dir, local_image_dir,
|
|||
|
|
md_writer, f_draw_layout_bbox, f_draw_span_bbox, f_dump_orig_pdf,
|
|||
|
|
f_dump_md, f_dump_content_list, f_dump_middle_json, f_dump_model_output,
|
|||
|
|
f_make_md_mode, middle_json, infer_result, is_pipeline=False
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _process_hybrid(
|
|||
|
|
output_dir,
|
|||
|
|
pdf_file_names,
|
|||
|
|
pdf_bytes_list,
|
|||
|
|
h_lang_list,
|
|||
|
|
parse_method,
|
|||
|
|
inline_formula_enable,
|
|||
|
|
backend,
|
|||
|
|
f_draw_layout_bbox,
|
|||
|
|
f_draw_span_bbox,
|
|||
|
|
f_dump_md,
|
|||
|
|
f_dump_middle_json,
|
|||
|
|
f_dump_model_output,
|
|||
|
|
f_dump_orig_pdf,
|
|||
|
|
f_dump_content_list,
|
|||
|
|
f_make_md_mode,
|
|||
|
|
server_url=None,
|
|||
|
|
**kwargs,
|
|||
|
|
):
|
|||
|
|
from mineru.backend.hybrid.hybrid_analyze import doc_analyze as hybrid_doc_analyze
|
|||
|
|
"""同步处理hybrid后端逻辑"""
|
|||
|
|
if not backend.endswith("client"):
|
|||
|
|
server_url = None
|
|||
|
|
|
|||
|
|
for idx, (pdf_bytes, lang) in enumerate(zip(pdf_bytes_list, h_lang_list)):
|
|||
|
|
pdf_file_name = pdf_file_names[idx]
|
|||
|
|
local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, f"hybrid_{parse_method}")
|
|||
|
|
image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
|
|||
|
|
|
|||
|
|
middle_json, infer_result, _vlm_ocr_enable = hybrid_doc_analyze(
|
|||
|
|
pdf_bytes,
|
|||
|
|
image_writer=image_writer,
|
|||
|
|
backend=backend,
|
|||
|
|
parse_method=parse_method,
|
|||
|
|
language=lang,
|
|||
|
|
inline_formula_enable=inline_formula_enable,
|
|||
|
|
server_url=server_url,
|
|||
|
|
**kwargs,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
pdf_info = middle_json["pdf_info"]
|
|||
|
|
|
|||
|
|
# f_draw_span_bbox = not _vlm_ocr_enable
|
|||
|
|
f_draw_span_bbox = False
|
|||
|
|
|
|||
|
|
_process_output(
|
|||
|
|
pdf_info, pdf_bytes, pdf_file_name, local_md_dir, local_image_dir,
|
|||
|
|
md_writer, f_draw_layout_bbox, f_draw_span_bbox, f_dump_orig_pdf,
|
|||
|
|
f_dump_md, f_dump_content_list, f_dump_middle_json, f_dump_model_output,
|
|||
|
|
f_make_md_mode, middle_json, infer_result, is_pipeline=False
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
async def _async_process_hybrid(
|
|||
|
|
output_dir,
|
|||
|
|
pdf_file_names,
|
|||
|
|
pdf_bytes_list,
|
|||
|
|
h_lang_list,
|
|||
|
|
parse_method,
|
|||
|
|
inline_formula_enable,
|
|||
|
|
backend,
|
|||
|
|
f_draw_layout_bbox,
|
|||
|
|
f_draw_span_bbox,
|
|||
|
|
f_dump_md,
|
|||
|
|
f_dump_middle_json,
|
|||
|
|
f_dump_model_output,
|
|||
|
|
f_dump_orig_pdf,
|
|||
|
|
f_dump_content_list,
|
|||
|
|
f_make_md_mode,
|
|||
|
|
server_url=None,
|
|||
|
|
progress_callback=None,
|
|||
|
|
**kwargs,
|
|||
|
|
):
|
|||
|
|
from mineru.backend.hybrid.hybrid_analyze import aio_doc_analyze as aio_hybrid_doc_analyze
|
|||
|
|
"""异步处理hybrid后端逻辑"""
|
|||
|
|
if not backend.endswith("client"):
|
|||
|
|
server_url = None
|
|||
|
|
|
|||
|
|
total_files = len(pdf_bytes_list)
|
|||
|
|
for idx, (pdf_bytes, lang) in enumerate(zip(pdf_bytes_list, h_lang_list)):
|
|||
|
|
pdf_file_name = pdf_file_names[idx]
|
|||
|
|
local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, f"hybrid_{parse_method}")
|
|||
|
|
image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
|
|||
|
|
|
|||
|
|
# 更新进度
|
|||
|
|
if progress_callback:
|
|||
|
|
progress_callback((idx / total_files) * 50, f"处理文件 {idx+1}/{total_files}")
|
|||
|
|
|
|||
|
|
middle_json, infer_result, _vlm_ocr_enable = await aio_hybrid_doc_analyze(
|
|||
|
|
pdf_bytes,
|
|||
|
|
image_writer=image_writer,
|
|||
|
|
backend=backend,
|
|||
|
|
parse_method=parse_method,
|
|||
|
|
language=lang,
|
|||
|
|
inline_formula_enable=inline_formula_enable,
|
|||
|
|
server_url=server_url,
|
|||
|
|
**kwargs,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
# 更新进度
|
|||
|
|
if progress_callback:
|
|||
|
|
progress_callback(((idx + 1) / total_files) * 100, f"完成文件 {idx+1}/{total_files}")
|
|||
|
|
|
|||
|
|
pdf_info = middle_json["pdf_info"]
|
|||
|
|
|
|||
|
|
# f_draw_span_bbox = not _vlm_ocr_enable
|
|||
|
|
f_draw_span_bbox = False
|
|||
|
|
|
|||
|
|
_process_output(
|
|||
|
|
pdf_info, pdf_bytes, pdf_file_name, local_md_dir, local_image_dir,
|
|||
|
|
md_writer, f_draw_layout_bbox, f_draw_span_bbox, f_dump_orig_pdf,
|
|||
|
|
f_dump_md, f_dump_content_list, f_dump_middle_json, f_dump_model_output,
|
|||
|
|
f_make_md_mode, middle_json, infer_result, is_pipeline=False
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def do_parse(
|
|||
|
|
output_dir,
|
|||
|
|
pdf_file_names: list[str],
|
|||
|
|
pdf_bytes_list: list[bytes],
|
|||
|
|
p_lang_list: list[str],
|
|||
|
|
backend="pipeline",
|
|||
|
|
parse_method="auto",
|
|||
|
|
formula_enable=True,
|
|||
|
|
table_enable=True,
|
|||
|
|
server_url=None,
|
|||
|
|
f_draw_layout_bbox=True,
|
|||
|
|
f_draw_span_bbox=True,
|
|||
|
|
f_dump_md=True,
|
|||
|
|
f_dump_middle_json=True,
|
|||
|
|
f_dump_model_output=True,
|
|||
|
|
f_dump_orig_pdf=True,
|
|||
|
|
f_dump_content_list=True,
|
|||
|
|
f_make_md_mode=MakeMode.MM_MD,
|
|||
|
|
start_page_id=0,
|
|||
|
|
end_page_id=None,
|
|||
|
|
**kwargs,
|
|||
|
|
):
|
|||
|
|
# 预处理PDF字节数据
|
|||
|
|
pdf_bytes_list = _prepare_pdf_bytes(pdf_bytes_list, start_page_id, end_page_id)
|
|||
|
|
|
|||
|
|
if backend == "pipeline":
|
|||
|
|
_process_pipeline(
|
|||
|
|
output_dir, pdf_file_names, pdf_bytes_list, p_lang_list,
|
|||
|
|
parse_method, formula_enable, table_enable,
|
|||
|
|
f_draw_layout_bbox, f_draw_span_bbox, f_dump_md, f_dump_middle_json,
|
|||
|
|
f_dump_model_output, f_dump_orig_pdf, f_dump_content_list, f_make_md_mode
|
|||
|
|
)
|
|||
|
|
else:
|
|||
|
|
if backend.startswith("vlm-"):
|
|||
|
|
backend = backend[4:]
|
|||
|
|
|
|||
|
|
if backend == "vllm-async-engine":
|
|||
|
|
raise Exception("vlm-vllm-async-engine backend is not supported in sync mode, please use vlm-vllm-engine backend")
|
|||
|
|
|
|||
|
|
if backend == "auto-engine":
|
|||
|
|
backend = get_vlm_engine(inference_engine='auto', is_async=False)
|
|||
|
|
|
|||
|
|
os.environ['MINERU_VLM_FORMULA_ENABLE'] = str(formula_enable)
|
|||
|
|
os.environ['MINERU_VLM_TABLE_ENABLE'] = str(table_enable)
|
|||
|
|
|
|||
|
|
_process_vlm(
|
|||
|
|
output_dir, pdf_file_names, pdf_bytes_list, backend,
|
|||
|
|
f_draw_layout_bbox, f_draw_span_bbox, f_dump_md, f_dump_middle_json,
|
|||
|
|
f_dump_model_output, f_dump_orig_pdf, f_dump_content_list, f_make_md_mode,
|
|||
|
|
server_url, **kwargs,
|
|||
|
|
)
|
|||
|
|
elif backend.startswith("hybrid-"):
|
|||
|
|
backend = backend[7:]
|
|||
|
|
|
|||
|
|
if backend == "vllm-async-engine":
|
|||
|
|
raise Exception(
|
|||
|
|
"hybrid-vllm-async-engine backend is not supported in sync mode, please use hybrid-vllm-engine backend")
|
|||
|
|
|
|||
|
|
if backend == "auto-engine":
|
|||
|
|
backend = get_vlm_engine(inference_engine='auto', is_async=False)
|
|||
|
|
|
|||
|
|
os.environ['MINERU_VLM_TABLE_ENABLE'] = str(table_enable)
|
|||
|
|
os.environ['MINERU_VLM_FORMULA_ENABLE'] = "true"
|
|||
|
|
|
|||
|
|
_process_hybrid(
|
|||
|
|
output_dir, pdf_file_names, pdf_bytes_list, p_lang_list, parse_method, formula_enable, backend,
|
|||
|
|
f_draw_layout_bbox, f_draw_span_bbox, f_dump_md, f_dump_middle_json,
|
|||
|
|
f_dump_model_output, f_dump_orig_pdf, f_dump_content_list, f_make_md_mode,
|
|||
|
|
server_url, **kwargs,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
async def aio_do_parse(
|
|||
|
|
output_dir,
|
|||
|
|
pdf_file_names: list[str],
|
|||
|
|
pdf_bytes_list: list[bytes],
|
|||
|
|
p_lang_list: list[str],
|
|||
|
|
backend="pipeline",
|
|||
|
|
parse_method="auto",
|
|||
|
|
formula_enable=True,
|
|||
|
|
table_enable=True,
|
|||
|
|
server_url=None,
|
|||
|
|
f_draw_layout_bbox=True,
|
|||
|
|
f_draw_span_bbox=True,
|
|||
|
|
f_dump_md=True,
|
|||
|
|
f_dump_middle_json=True,
|
|||
|
|
f_dump_model_output=True,
|
|||
|
|
f_dump_orig_pdf=True,
|
|||
|
|
f_dump_content_list=True,
|
|||
|
|
f_make_md_mode=MakeMode.MM_MD,
|
|||
|
|
start_page_id=0,
|
|||
|
|
end_page_id=None,
|
|||
|
|
progress_callback=None,
|
|||
|
|
**kwargs,
|
|||
|
|
):
|
|||
|
|
# 预处理PDF字节数据
|
|||
|
|
pdf_bytes_list = _prepare_pdf_bytes(pdf_bytes_list, start_page_id, end_page_id)
|
|||
|
|
|
|||
|
|
if backend == "pipeline":
|
|||
|
|
# pipeline模式暂不支持异步，使用同步处理方式
|
|||
|
|
_process_pipeline(
|
|||
|
|
output_dir, pdf_file_names, pdf_bytes_list, p_lang_list,
|
|||
|
|
parse_method, formula_enable, table_enable,
|
|||
|
|
f_draw_layout_bbox, f_draw_span_bbox, f_dump_md, f_dump_middle_json,
|
|||
|
|
f_dump_model_output, f_dump_orig_pdf, f_dump_content_list, f_make_md_mode
|
|||
|
|
)
|
|||
|
|
else:
|
|||
|
|
if backend.startswith("vlm-"):
|
|||
|
|
backend = backend[4:]
|
|||
|
|
|
|||
|
|
if backend == "vllm-engine":
|
|||
|
|
raise Exception("vlm-vllm-engine backend is not supported in async mode, please use vlm-vllm-async-engine backend")
|
|||
|
|
|
|||
|
|
if backend == "auto-engine":
|
|||
|
|
backend = get_vlm_engine(inference_engine='auto', is_async=True)
|
|||
|
|
|
|||
|
|
os.environ['MINERU_VLM_FORMULA_ENABLE'] = str(formula_enable)
|
|||
|
|
os.environ['MINERU_VLM_TABLE_ENABLE'] = str(table_enable)
|
|||
|
|
|
|||
|
|
# 传递进度回调
|
|||
|
|
await _async_process_vlm(
|
|||
|
|
output_dir, pdf_file_names, pdf_bytes_list, backend,
|
|||
|
|
f_draw_layout_bbox, f_draw_span_bbox, f_dump_md, f_dump_middle_json,
|
|||
|
|
f_dump_model_output, f_dump_orig_pdf, f_dump_content_list, f_make_md_mode,
|
|||
|
|
server_url, progress_callback=progress_callback, **kwargs,
|
|||
|
|
)
|
|||
|
|
elif backend.startswith("hybrid-"):
|
|||
|
|
backend = backend[7:]
|
|||
|
|
|
|||
|
|
if backend == "vllm-engine":
|
|||
|
|
raise Exception("hybrid-vllm-engine backend is not supported in async mode, please use hybrid-vllm-async-engine backend")
|
|||
|
|
|
|||
|
|
if backend == "auto-engine":
|
|||
|
|
backend = get_vlm_engine(inference_engine='auto', is_async=True)
|
|||
|
|
|
|||
|
|
os.environ['MINERU_VLM_TABLE_ENABLE'] = str(table_enable)
|
|||
|
|
os.environ['MINERU_VLM_FORMULA_ENABLE'] = "true"
|
|||
|
|
|
|||
|
|
# 传递进度回调
|
|||
|
|
await _async_process_hybrid(
|
|||
|
|
output_dir, pdf_file_names, pdf_bytes_list, p_lang_list, parse_method, formula_enable, backend,
|
|||
|
|
f_draw_layout_bbox, f_draw_span_bbox, f_dump_md, f_dump_middle_json,
|
|||
|
|
f_dump_model_output, f_dump_orig_pdf, f_dump_content_list, f_make_md_mode,
|
|||
|
|
server_url, progress_callback=progress_callback, **kwargs,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
# pdf_path = "../../demo/pdfs/demo3.pdf"
|
|||
|
|
pdf_path = "C:/Users/zhaoxiaomeng/Downloads/4546d0e2-ba60-40a5-a17e-b68555cec741.pdf"
|
|||
|
|
|
|||
|
|
try:
|
|||
|
|
do_parse("./output", [Path(pdf_path).stem], [read_fn(Path(pdf_path))],["ch"],
|
|||
|
|
end_page_id=10,
|
|||
|
|
backend='vlm-huggingface'
|
|||
|
|
# backend = 'pipeline'
|
|||
|
|
)
|
|||
|
|
except Exception as e:
|
|||
|
|
logger.exception(e)
|