Skip to content

GitLab

Unverified Commit 4bb54393 authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #1427 from opendatalab/release-1.0.0 

Release 1.0.0
parents 04f084ac 1c9f9942
Hide whitespace changes
Inline Side-by-side
Showing with 250 additions and 1031 deletions
magic_pdf/post_proc/llm_aided.py 0 → 100644
View file @ 4bb54393
# Copyright (c) Opendatalab. All rights reserved.
import json
from loguru import logger
from magic_pdf.dict2md.ocr_mkcontent import merge_para_with_text
from openai import OpenAI
#@todo: 有的公式以"\"结尾，这样会导致尾部拼接的"$"被转义，也需要修复
formula_optimize_prompt = """请根据以下指南修正LaTeX公式的错误，确保公式能够渲染且符合原始内容：
1. 修正渲染或编译错误：
- Some syntax errors such as mismatched/missing/extra tokens. Your task is to fix these syntax errors and make sure corrected results conform to latex math syntax principles.
- 包含KaTeX不支持的关键词等原因导致的无法编译或渲染的错误
2. 保留原始信息：
- 保留原始公式中的所有重要信息
- 不要添加任何原始公式中没有的新信息
IMPORTANT:请仅返回修正后的公式，不要包含任何介绍、解释或元数据。
LaTeX recognition result:
$FORMULA
Your corrected result:
"""
text_optimize_prompt = f"""请根据以下指南修正OCR引起的错误，确保文本连贯并符合原始内容：
1. 修正OCR引起的拼写错误和错误：
- 修正常见的OCR错误（例如，'rn' 被误读为 'm'）
- 使用上下文和常识进行修正
- 只修正明显的错误，不要不必要的修改内容
- 不要添加额外的句号或其他不必要的标点符号
2. 保持原始结构：
- 保留所有标题和子标题
3. 保留原始内容：
- 保留原始文本中的所有重要信息
- 不要添加任何原始文本中没有的新信息
- 保留段落之间的换行符
4. 保持连贯性：
- 确保内容与前文顺畅连接
- 适当处理在句子中间开始或结束的文本
5. 修正行内公式：
- 去除行内公式前后多余的空格
- 修正公式中的OCR错误
- 确保公式能够通过KaTeX渲染
6. 修正全角字符
- 修正全角标点符号为半角标点符号
- 修正全角字母为半角字母
- 修正全角数字为半角数字
IMPORTANT:请仅返回修正后的文本，保留所有原始格式，包括换行符。不要包含任何介绍、解释或元数据。
Previous context:
Current chunk to process:
Corrected text:
"""
def llm_aided_formula(pdf_info_dict, formula_aided_config):
pass
def llm_aided_text(pdf_info_dict, text_aided_config):
pass
def llm_aided_title(pdf_info_dict, title_aided_config):
client = OpenAI(
api_key=title_aided_config["api_key"],
base_url=title_aided_config["base_url"],
)
title_dict = {}
origin_title_list = []
i = 0
for page_num, page in pdf_info_dict.items():
blocks = page["para_blocks"]
for block in blocks:
if block["type"] == "title":
origin_title_list.append(block)
title_text = merge_para_with_text(block)
title_dict[f"{i}"] = title_text
i += 1
# logger.info(f"Title list: {title_dict}")
title_optimize_prompt = f"""输入的内容是一篇文档中所有标题组成的字典，请根据以下指南优化标题的结果，使结果符合正常文档的层次结构：
1. 保留原始内容：
- 输入的字典中所有元素都是有效的，不能删除字典中的任何元素
- 请务必保证输出的字典中元素的数量和输入的数量一致
2. 保持字典内key-value的对应关系不变
3. 优化层次结构：
- 为每个标题元素添加适当的层次结构
- 标题层级应具有连续性，不能跳过某一层级
- 标题层级最多为4级，不要添加过多的层级
- 优化后的标题为一个整数，代表该标题的层级
IMPORTANT:
请直接返回优化过的由标题层级组成的json，返回的json不需要格式化。
Input title list:
{title_dict}
Corrected title list:
"""
completion = client.chat.completions.create(
model=title_aided_config["model"],
messages=[
{'role': 'user', 'content': title_optimize_prompt}],
temperature=0.7,
)
json_completion = json.loads(completion.choices[0].message.content)
# logger.info(f"Title completion: {json_completion}")
# logger.info(f"len(json_completion): {len(json_completion)}, len(title_dict): {len(title_dict)}")
if len(json_completion) == len(title_dict):
try:
for i, origin_title_block in enumerate(origin_title_list):
origin_title_block["level"] = int(json_completion[str(i)])
except Exception as e:
logger.exception(e)
else:
logger.error("The number of titles in the optimized result is not equal to the number of titles in the input.")
magic_pdf/pre_proc/ocr_span_list_modify.py
View file @ 4bb54393
...@@ -33,6 +33,14 @@ def remove_overlaps_low_confidence_spans(spans): ...@@ -33,6 +33,14 @@ def remove_overlaps_low_confidence_spans(spans):
return spans, dropped_spans return spans, dropped_spans
def check_chars_is_overlap_in_span(chars):
for i in range(len(chars)):
for j in range(i + 1, len(chars)):
if calculate_iou(chars[i]['bbox'], chars[j]['bbox']) > 0.9:
return True
return False
def remove_overlaps_min_spans(spans): def remove_overlaps_min_spans(spans):
dropped_spans = [] dropped_spans = []
# 删除重叠spans中较小的那些 # 删除重叠spans中较小的那些
......
magic_pdf/pre_proc/remove_bbox_overlap.py
View file @ 4bb54393
...@@ -70,7 +70,7 @@ def _remove_overlap_between_bboxes(arr): ...@@ -70,7 +70,7 @@ def _remove_overlap_between_bboxes(arr):
res[i] = None res[i] = None
else: else:
keeps[idx] = False keeps[idx] = False
drop_reasons.append(drop_reasons) drop_reasons.append(drop_reason)
if keeps[idx]: if keeps[idx]:
res[idx] = v res[idx] = v
return res, drop_reasons return res, drop_reasons
......
magic_pdf/rw/AbsReaderWriter.py deleted 100644 → 0
View file @ 04f084ac
from abc import ABC, abstractmethod
class AbsReaderWriter(ABC):
MODE_TXT = "text"
MODE_BIN = "binary"
@abstractmethod
def read(self, path: str, mode=MODE_TXT):
raise NotImplementedError
@abstractmethod
def write(self, content: str, path: str, mode=MODE_TXT):
raise NotImplementedError
@abstractmethod
def read_offset(self, path: str, offset=0, limit=None) -> bytes:
raise NotImplementedError
magic_pdf/rw/DiskReaderWriter.py deleted 100644 → 0
View file @ 04f084ac
import os
from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
from loguru import logger
class DiskReaderWriter(AbsReaderWriter):
def __init__(self, parent_path, encoding="utf-8"):
self.path = parent_path
self.encoding = encoding
def read(self, path, mode=AbsReaderWriter.MODE_TXT):
if os.path.isabs(path):
abspath = path
else:
abspath = os.path.join(self.path, path)
if not os.path.exists(abspath):
logger.error(f"file {abspath} not exists")
raise Exception(f"file {abspath} no exists")
if mode == AbsReaderWriter.MODE_TXT:
with open(abspath, "r", encoding=self.encoding) as f:
return f.read()
elif mode == AbsReaderWriter.MODE_BIN:
with open(abspath, "rb") as f:
return f.read()
else:
raise ValueError("Invalid mode. Use 'text' or 'binary'.")
def write(self, content, path, mode=AbsReaderWriter.MODE_TXT):
if os.path.isabs(path):
abspath = path
else:
abspath = os.path.join(self.path, path)
directory_path = os.path.dirname(abspath)
if not os.path.exists(directory_path):
os.makedirs(directory_path)
if mode == AbsReaderWriter.MODE_TXT:
with open(abspath, "w", encoding=self.encoding, errors="replace") as f:
f.write(content)
elif mode == AbsReaderWriter.MODE_BIN:
with open(abspath, "wb") as f:
f.write(content)
else:
raise ValueError("Invalid mode. Use 'text' or 'binary'.")
def read_offset(self, path: str, offset=0, limit=None):
abspath = path
if not os.path.isabs(path):
abspath = os.path.join(self.path, path)
with open(abspath, "rb") as f:
f.seek(offset)
return f.read(limit)
if __name__ == "__main__":
if 0:
file_path = "io/test/example.txt"
drw = DiskReaderWriter("D:\projects\papayfork\Magic-PDF\magic_pdf")
# 写入内容到文件
drw.write(b"Hello, World!", path="io/test/example.txt", mode="binary")
# 从文件读取内容
content = drw.read(path=file_path)
if content:
logger.info(f"从 {file_path} 读取的内容: {content}")
if 1:
drw = DiskReaderWriter("/opt/data/pdf/resources/test/io/")
content_bin = drw.read_offset("1.txt")
assert content_bin == b"ABCD!"
content_bin = drw.read_offset("1.txt", offset=1, limit=2)
assert content_bin == b"BC"
magic_pdf/rw/S3ReaderWriter.py deleted 100644 → 0
View file @ 04f084ac
from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
from magic_pdf.libs.commons import parse_bucket_key, join_path
import boto3
from loguru import logger
from botocore.config import Config
class S3ReaderWriter(AbsReaderWriter):
def __init__(
self,
ak: str,
sk: str,
endpoint_url: str,
addressing_style: str = "auto",
parent_path: str = "",
):
self.client = self._get_client(ak, sk, endpoint_url, addressing_style)
self.path = parent_path
def _get_client(self, ak: str, sk: str, endpoint_url: str, addressing_style: str):
s3_client = boto3.client(
service_name="s3",
aws_access_key_id=ak,
aws_secret_access_key=sk,
endpoint_url=endpoint_url,
config=Config(
s3={"addressing_style": addressing_style},
retries={"max_attempts": 5, "mode": "standard"},
),
)
return s3_client
def read(self, s3_relative_path, mode=AbsReaderWriter.MODE_TXT, encoding="utf-8"):
if s3_relative_path.startswith("s3://"):
s3_path = s3_relative_path
else:
s3_path = join_path(self.path, s3_relative_path)
bucket_name, key = parse_bucket_key(s3_path)
res = self.client.get_object(Bucket=bucket_name, Key=key)
body = res["Body"].read()
if mode == AbsReaderWriter.MODE_TXT:
data = body.decode(encoding) # Decode bytes to text
elif mode == AbsReaderWriter.MODE_BIN:
data = body
else:
raise ValueError("Invalid mode. Use 'text' or 'binary'.")
return data
def write(self, content, s3_relative_path, mode=AbsReaderWriter.MODE_TXT, encoding="utf-8"):
if s3_relative_path.startswith("s3://"):
s3_path = s3_relative_path
else:
s3_path = join_path(self.path, s3_relative_path)
if mode == AbsReaderWriter.MODE_TXT:
body = content.encode(encoding) # Encode text data as bytes
elif mode == AbsReaderWriter.MODE_BIN:
body = content
else:
raise ValueError("Invalid mode. Use 'text' or 'binary'.")
bucket_name, key = parse_bucket_key(s3_path)
self.client.put_object(Body=body, Bucket=bucket_name, Key=key)
logger.info(f"内容已写入 {s3_path} ")
def read_offset(self, path: str, offset=0, limit=None) -> bytes:
if path.startswith("s3://"):
s3_path = path
else:
s3_path = join_path(self.path, path)
bucket_name, key = parse_bucket_key(s3_path)
range_header = (
f"bytes={offset}-{offset+limit-1}" if limit else f"bytes={offset}-"
)
res = self.client.get_object(Bucket=bucket_name, Key=key, Range=range_header)
return res["Body"].read()
if __name__ == "__main__":
if 0:
# Config the connection info
ak = ""
sk = ""
endpoint_url = ""
addressing_style = "auto"
bucket_name = ""
# Create an S3ReaderWriter object
s3_reader_writer = S3ReaderWriter(
ak, sk, endpoint_url, addressing_style, "s3://bucket_name/"
)
# Write text data to S3
text_data = "This is some text data"
s3_reader_writer.write(
text_data,
s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json",
mode=AbsReaderWriter.MODE_TXT,
)
# Read text data from S3
text_data_read = s3_reader_writer.read(
s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json", mode=AbsReaderWriter.MODE_TXT
)
logger.info(f"Read text data from S3: {text_data_read}")
# Write binary data to S3
binary_data = b"This is some binary data"
s3_reader_writer.write(
text_data,
s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json",
mode=AbsReaderWriter.MODE_BIN,
)
# Read binary data from S3
binary_data_read = s3_reader_writer.read(
s3_relative_path=f"s3://{bucket_name}/ebook/test/test.json", mode=AbsReaderWriter.MODE_BIN
)
logger.info(f"Read binary data from S3: {binary_data_read}")
# Range Read text data from S3
binary_data_read = s3_reader_writer.read_offset(
path=f"s3://{bucket_name}/ebook/test/test.json", offset=0, limit=10
)
logger.info(f"Read binary data from S3: {binary_data_read}")
if 1:
import os
import json
ak = os.getenv("AK", "")
sk = os.getenv("SK", "")
endpoint_url = os.getenv("ENDPOINT", "")
bucket = os.getenv("S3_BUCKET", "")
prefix = os.getenv("S3_PREFIX", "")
key_basename = os.getenv("S3_KEY_BASENAME", "")
s3_reader_writer = S3ReaderWriter(
ak, sk, endpoint_url, "auto", f"s3://{bucket}/{prefix}"
)
content_bin = s3_reader_writer.read_offset(key_basename)
assert content_bin[:10] == b'{"track_id'
assert content_bin[-10:] == b'r":null}}\n'
content_bin = s3_reader_writer.read_offset(key_basename, offset=424, limit=426)
jso = json.dumps(content_bin.decode("utf-8"))
print(jso)
magic_pdf/tools/cli.py
View file @ 4bb54393
import os import os
from pathlib import Path import shutil
import tempfile
import click import click
import fitz
from loguru import logger from loguru import logger
from pathlib import Path
import magic_pdf.model as model_config import magic_pdf.model as model_config
from magic_pdf.data.data_reader_writer import FileBasedDataReader from magic_pdf.data.data_reader_writer import FileBasedDataReader
from magic_pdf.libs.version import __version__ from magic_pdf.libs.version import __version__
from magic_pdf.tools.common import do_parse, parse_pdf_methods from magic_pdf.tools.common import do_parse, parse_pdf_methods
from magic_pdf.utils.office_to_pdf import convert_file_to_pdf
pdf_suffixes = ['.pdf']
ms_office_suffixes = ['.ppt', '.pptx', '.doc', '.docx']
image_suffixes = ['.png', '.jpeg', '.jpg']
@click.command() @click.command()
...@@ -21,7 +28,7 @@ from magic_pdf.tools.common import do_parse, parse_pdf_methods ...@@ -21,7 +28,7 @@ from magic_pdf.tools.common import do_parse, parse_pdf_methods
'path', 'path',
type=click.Path(exists=True), type=click.Path(exists=True),
required=True, required=True,
help='local pdf filepath or directory', help='local filepath or directory. support PDF, PPT, PPTX, DOC, DOCX, PNG, JPG files',
) )
@click.option( @click.option(
'-o', '-o',
...@@ -83,12 +90,27 @@ def cli(path, output_dir, method, lang, debug_able, start_page_id, end_page_id): ...@@ -83,12 +90,27 @@ def cli(path, output_dir, method, lang, debug_able, start_page_id, end_page_id):
model_config.__use_inside_model__ = True model_config.__use_inside_model__ = True
model_config.__model_mode__ = 'full' model_config.__model_mode__ = 'full'
os.makedirs(output_dir, exist_ok=True) os.makedirs(output_dir, exist_ok=True)
temp_dir = tempfile.mkdtemp()
def read_fn(path: Path):
if path.suffix in ms_office_suffixes:
convert_file_to_pdf(str(path), temp_dir)
fn = os.path.join(temp_dir, f"{path.stem}.pdf")
elif path.suffix in image_suffixes:
with open(str(path), 'rb') as f:
bits = f.read()
pdf_bytes = fitz.open(stream=bits).convert_to_pdf()
fn = os.path.join(temp_dir, f"{path.stem}.pdf")
with open(fn, 'wb') as f:
f.write(pdf_bytes)
elif path.suffix in pdf_suffixes:
fn = str(path)
else:
raise Exception(f"Unknown file suffix: {path.suffix}")
disk_rw = FileBasedDataReader(os.path.dirname(fn))
return disk_rw.read(os.path.basename(fn))
def read_fn(path): def parse_doc(doc_path: Path):
disk_rw = FileBasedDataReader(os.path.dirname(path))
return disk_rw.read(os.path.basename(path))
def parse_doc(doc_path: str):
try: try:
file_name = str(Path(doc_path).stem) file_name = str(Path(doc_path).stem)
pdf_data = read_fn(doc_path) pdf_data = read_fn(doc_path)
...@@ -108,10 +130,13 @@ def cli(path, output_dir, method, lang, debug_able, start_page_id, end_page_id): ...@@ -108,10 +130,13 @@ def cli(path, output_dir, method, lang, debug_able, start_page_id, end_page_id):
logger.exception(e) logger.exception(e)
if os.path.isdir(path): if os.path.isdir(path):
for doc_path in Path(path).glob('*.pdf'): for doc_path in Path(path).glob('*'):
parse_doc(doc_path) if doc_path.suffix in pdf_suffixes + image_suffixes + ms_office_suffixes:
parse_doc(doc_path)
else: else:
parse_doc(path) parse_doc(Path(path))
shutil.rmtree(temp_dir)
if __name__ == '__main__': if __name__ == '__main__':
......
magic_pdf/tools/common.py
View file @ 4bb54393
...@@ -9,8 +9,9 @@ from magic_pdf.config.enums import SupportedPdfParseMethod ...@@ -9,8 +9,9 @@ from magic_pdf.config.enums import SupportedPdfParseMethod
from magic_pdf.config.make_content_config import DropMode, MakeMode from magic_pdf.config.make_content_config import DropMode, MakeMode
from magic_pdf.data.data_reader_writer import FileBasedDataWriter from magic_pdf.data.data_reader_writer import FileBasedDataWriter
from magic_pdf.data.dataset import PymuDocDataset from magic_pdf.data.dataset import PymuDocDataset
from magic_pdf.libs.draw_bbox import draw_char_bbox
from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
from magic_pdf.model.operators import InferenceResult from magic_pdf.operators.models import InferenceResult
# from io import BytesIO # from io import BytesIO
# from pypdf import PdfReader, PdfWriter # from pypdf import PdfReader, PdfWriter
...@@ -83,6 +84,7 @@ def do_parse( ...@@ -83,6 +84,7 @@ def do_parse(
f_make_md_mode=MakeMode.MM_MD, f_make_md_mode=MakeMode.MM_MD,
f_draw_model_bbox=False, f_draw_model_bbox=False,
f_draw_line_sort_bbox=False, f_draw_line_sort_bbox=False,
f_draw_char_bbox=False,
start_page_id=0, start_page_id=0,
end_page_id=None, end_page_id=None,
lang=None, lang=None,
...@@ -94,9 +96,7 @@ def do_parse( ...@@ -94,9 +96,7 @@ def do_parse(
logger.warning('debug mode is on') logger.warning('debug mode is on')
f_draw_model_bbox = True f_draw_model_bbox = True
f_draw_line_sort_bbox = True f_draw_line_sort_bbox = True
# f_draw_char_bbox = True
if lang == '':
lang = None
pdf_bytes = convert_pdf_bytes_to_bytes_by_pymupdf( pdf_bytes = convert_pdf_bytes_to_bytes_by_pymupdf(
pdf_bytes, start_page_id, end_page_id pdf_bytes, start_page_id, end_page_id
...@@ -109,7 +109,7 @@ def do_parse( ...@@ -109,7 +109,7 @@ def do_parse(
) )
image_dir = str(os.path.basename(local_image_dir)) image_dir = str(os.path.basename(local_image_dir))
ds = PymuDocDataset(pdf_bytes) ds = PymuDocDataset(pdf_bytes, lang=lang)
if len(model_list) == 0: if len(model_list) == 0:
if model_config.__use_inside_model__: if model_config.__use_inside_model__:
...@@ -118,50 +118,50 @@ def do_parse( ...@@ -118,50 +118,50 @@ def do_parse(
infer_result = ds.apply( infer_result = ds.apply(
doc_analyze, doc_analyze,
ocr=False, ocr=False,
lang=lang, lang=ds._lang,
layout_model=layout_model, layout_model=layout_model,
formula_enable=formula_enable, formula_enable=formula_enable,
table_enable=table_enable, table_enable=table_enable,
) )
pipe_result = infer_result.pipe_txt_mode( pipe_result = infer_result.pipe_txt_mode(
image_writer, debug_mode=True, lang=lang image_writer, debug_mode=True, lang=ds._lang
) )
else: else:
infer_result = ds.apply( infer_result = ds.apply(
doc_analyze, doc_analyze,
ocr=True, ocr=True,
lang=lang, lang=ds._lang,
layout_model=layout_model, layout_model=layout_model,
formula_enable=formula_enable, formula_enable=formula_enable,
table_enable=table_enable, table_enable=table_enable,
) )
pipe_result = infer_result.pipe_ocr_mode( pipe_result = infer_result.pipe_ocr_mode(
image_writer, debug_mode=True, lang=lang image_writer, debug_mode=True, lang=ds._lang
) )
elif parse_method == 'txt': elif parse_method == 'txt':
infer_result = ds.apply( infer_result = ds.apply(
doc_analyze, doc_analyze,
ocr=False, ocr=False,
lang=lang, lang=ds._lang,
layout_model=layout_model, layout_model=layout_model,
formula_enable=formula_enable, formula_enable=formula_enable,
table_enable=table_enable, table_enable=table_enable,
) )
pipe_result = infer_result.pipe_txt_mode( pipe_result = infer_result.pipe_txt_mode(
image_writer, debug_mode=True, lang=lang image_writer, debug_mode=True, lang=ds._lang
) )
elif parse_method == 'ocr': elif parse_method == 'ocr':
infer_result = ds.apply( infer_result = ds.apply(
doc_analyze, doc_analyze,
ocr=True, ocr=True,
lang=lang, lang=ds._lang,
layout_model=layout_model, layout_model=layout_model,
formula_enable=formula_enable, formula_enable=formula_enable,
table_enable=table_enable, table_enable=table_enable,
) )
pipe_result = infer_result.pipe_ocr_mode( pipe_result = infer_result.pipe_ocr_mode(
image_writer, debug_mode=True, lang=lang image_writer, debug_mode=True, lang=ds._lang
) )
else: else:
logger.error('unknown parse method') logger.error('unknown parse method')
...@@ -170,19 +170,26 @@ def do_parse( ...@@ -170,19 +170,26 @@ def do_parse(
logger.error('need model list input') logger.error('need model list input')
exit(2) exit(2)
else: else:
infer_result = InferenceResult(model_list, ds) infer_result = InferenceResult(model_list, ds)
if parse_method == 'ocr': if parse_method == 'ocr':
pipe_result = infer_result.pipe_ocr_mode( pipe_result = infer_result.pipe_ocr_mode(
image_writer, debug_mode=True, lang=lang image_writer, debug_mode=True, lang=ds._lang
) )
elif parse_method == 'txt': elif parse_method == 'txt':
pipe_result = infer_result.pipe_txt_mode( pipe_result = infer_result.pipe_txt_mode(
image_writer, debug_mode=True, lang=lang image_writer, debug_mode=True, lang=ds._lang
) )
else: else:
pipe_result = infer_result.pipe_auto_mode( if ds.classify() == SupportedPdfParseMethod.TXT:
image_writer, debug_mode=True, lang=lang pipe_result = infer_result.pipe_txt_mode(
) image_writer, debug_mode=True, lang=ds._lang
)
else:
pipe_result = infer_result.pipe_ocr_mode(
image_writer, debug_mode=True, lang=ds._lang
)
if f_draw_model_bbox: if f_draw_model_bbox:
infer_result.draw_model( infer_result.draw_model(
...@@ -201,6 +208,9 @@ def do_parse( ...@@ -201,6 +208,9 @@ def do_parse(
os.path.join(local_md_dir, f'{pdf_file_name}_line_sort.pdf') os.path.join(local_md_dir, f'{pdf_file_name}_line_sort.pdf')
) )
if f_draw_char_bbox:
draw_char_bbox(pdf_bytes, local_md_dir, f'{pdf_file_name}_char_bbox.pdf')
if f_dump_md: if f_dump_md:
pipe_result.dump_md( pipe_result.dump_md(
md_writer, md_writer,
......
magic_pdf/user_api.py deleted 100644 → 0
View file @ 04f084ac
"""用户输入： model数组，每个元素代表一个页面 pdf在s3的路径 截图保存的s3位置.
然后：
1）根据s3路径，调用spark集群的api,拿到ak,sk,endpoint，构造出s3PDFReader
2）根据用户输入的s3地址，调用spark集群的api,拿到ak,sk,endpoint，构造出s3ImageWriter
其余部分至于构造s3cli, 获取ak,sk都在code-clean里写代码完成。不要反向依赖！！！
"""
from loguru import logger
from magic_pdf.data.data_reader_writer import DataWriter
from magic_pdf.data.dataset import Dataset
from magic_pdf.libs.version import __version__
from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
from magic_pdf.pdf_parse_by_ocr import parse_pdf_by_ocr
from magic_pdf.pdf_parse_by_txt import parse_pdf_by_txt
from magic_pdf.config.constants import PARSE_TYPE_TXT, PARSE_TYPE_OCR
def parse_txt_pdf(
dataset: Dataset,
model_list: list,
imageWriter: DataWriter,
is_debug=False,
start_page_id=0,
end_page_id=None,
lang=None,
*args,
**kwargs
):
"""解析文本类pdf."""
pdf_info_dict = parse_pdf_by_txt(
dataset,
model_list,
imageWriter,
start_page_id=start_page_id,
end_page_id=end_page_id,
debug_mode=is_debug,
lang=lang,
)
pdf_info_dict['_parse_type'] = PARSE_TYPE_TXT
pdf_info_dict['_version_name'] = __version__
if lang is not None:
pdf_info_dict['_lang'] = lang
return pdf_info_dict
def parse_ocr_pdf(
dataset: Dataset,
model_list: list,
imageWriter: DataWriter,
is_debug=False,
start_page_id=0,
end_page_id=None,
lang=None,
*args,
**kwargs
):
"""解析ocr类pdf."""
pdf_info_dict = parse_pdf_by_ocr(
dataset,
model_list,
imageWriter,
start_page_id=start_page_id,
end_page_id=end_page_id,
debug_mode=is_debug,
lang=lang,
)
pdf_info_dict['_parse_type'] = PARSE_TYPE_OCR
pdf_info_dict['_version_name'] = __version__
if lang is not None:
pdf_info_dict['_lang'] = lang
return pdf_info_dict
def parse_union_pdf(
dataset: Dataset,
model_list: list,
imageWriter: DataWriter,
is_debug=False,
start_page_id=0,
end_page_id=None,
lang=None,
*args,
**kwargs
):
"""ocr和文本混合的pdf，全部解析出来."""
def parse_pdf(method):
try:
return method(
dataset,
model_list,
imageWriter,
start_page_id=start_page_id,
end_page_id=end_page_id,
debug_mode=is_debug,
lang=lang,
)
except Exception as e:
logger.exception(e)
return None
pdf_info_dict = parse_pdf(parse_pdf_by_txt)
if pdf_info_dict is None or pdf_info_dict.get('_need_drop', False):
logger.warning('parse_pdf_by_txt drop or error, switch to parse_pdf_by_ocr')
if len(model_list) == 0:
layout_model = kwargs.get('layout_model', None)
formula_enable = kwargs.get('formula_enable', None)
table_enable = kwargs.get('table_enable', None)
infer_res = doc_analyze(
dataset,
ocr=True,
start_page_id=start_page_id,
end_page_id=end_page_id,
lang=lang,
layout_model=layout_model,
formula_enable=formula_enable,
table_enable=table_enable,
)
model_list = infer_res.get_infer_res()
pdf_info_dict = parse_pdf(parse_pdf_by_ocr)
if pdf_info_dict is None:
raise Exception('Both parse_pdf_by_txt and parse_pdf_by_ocr failed.')
else:
pdf_info_dict['_parse_type'] = PARSE_TYPE_OCR
else:
pdf_info_dict['_parse_type'] = PARSE_TYPE_TXT
pdf_info_dict['_version_name'] = __version__
if lang is not None:
pdf_info_dict['_lang'] = lang
return pdf_info_dict
magic_pdf/utils/office_to_pdf.py 0 → 100644
View file @ 4bb54393
import os
import subprocess
from pathlib import Path
class ConvertToPdfError(Exception):
def __init__(self, msg):
self.msg = msg
super().__init__(self.msg)
def convert_file_to_pdf(input_path, output_dir):
if not os.path.isfile(input_path):
raise FileNotFoundError(f"The input file {input_path} does not exist.")
os.makedirs(output_dir, exist_ok=True)
cmd = [
'soffice',
'--headless',
'--convert-to', 'pdf',
'--outdir', str(output_dir),
str(input_path)
]
process = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
if process.returncode != 0:
raise ConvertToPdfError(process.stderr.decode())
next_docs/README.md deleted 100644 → 0
View file @ 04f084ac
<div align="center" xmlns="http://www.w3.org/1999/html">
<!-- logo -->
<p align="center">
<img src="docs/images/MinerU-logo.png" width="300px" style="vertical-align:middle;">
</p>
<!-- icon -->
[![stars](https://img.shields.io/github/stars/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
[![forks](https://img.shields.io/github/forks/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
[![open issues](https://img.shields.io/github/issues-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
[![issue resolution](https://img.shields.io/github/issues-closed-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
[![PyPI version](https://badge.fury.io/py/magic-pdf.svg)](https://badge.fury.io/py/magic-pdf)
[![Downloads](https://static.pepy.tech/badge/magic-pdf)](https://pepy.tech/project/magic-pdf)
[![Downloads](https://static.pepy.tech/badge/magic-pdf/month)](https://pepy.tech/project/magic-pdf)
[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/myhloli/3b3a00a4a0a61577b6c30f989092d20d/mineru_demo.ipynb)
[![Paper](https://img.shields.io/badge/Paper-arXiv-green)](https://arxiv.org/abs/2409.18839)
<a href="https://trendshift.io/repositories/11174" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11174" alt="opendatalab%2FMinerU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
<!-- language -->
[English](README.md) | [简体中文](README_zh-CN.md)
<!-- hot link -->
<p align="center">
<a href="https://github.com/opendatalab/PDF-Extract-Kit">PDF-Extract-Kit: High-Quality PDF Extraction Toolkit</a>🔥🔥🔥
</p>
<!-- join us -->
<p align="center">
👋 join us on <a href="https://discord.gg/Tdedn9GTXq" target="_blank">Discord</a> and <a href="https://cdn.vansin.top/internlm/mineru.jpg" target="_blank">WeChat</a>
</p>
<!-- read the docs -->
<p align="center">
read more docs on <a href="https://mineru.readthedocs.io/en/latest/"> Read The Docs </a>
</p>
</div>
# Changelog
- 2024/11/06 0.9.2 released. Integrated the [StructTable-InternVL2-1B](https://huggingface.co/U4R/StructTable-InternVL2-1B) model for table recognition functionality.
- 2024/10/31 0.9.0 released. This is a major new version with extensive code refactoring, addressing numerous issues, improving performance, reducing hardware requirements, and enhancing usability:
- Refactored the sorting module code to use [layoutreader](https://github.com/ppaanngggg/layoutreader) for reading order sorting, ensuring high accuracy in various layouts.
- Refactored the paragraph concatenation module to achieve good results in cross-column, cross-page, cross-figure, and cross-table scenarios.
- Refactored the list and table of contents recognition functions, significantly improving the accuracy of list blocks and table of contents blocks, as well as the parsing of corresponding text paragraphs.
- Refactored the matching logic for figures, tables, and descriptive text, greatly enhancing the accuracy of matching captions and footnotes to figures and tables, and reducing the loss rate of descriptive text to near zero.
- Added multi-language support for OCR, supporting detection and recognition of 84 languages.For the list of supported languages, see [OCR Language Support List](https://paddlepaddle.github.io/PaddleOCR/latest/en/ppocr/blog/multi_languages.html#5-support-languages-and-abbreviations).
- Added memory recycling logic and other memory optimization measures, significantly reducing memory usage. The memory requirement for enabling all acceleration features except table acceleration (layout/formula/OCR) has been reduced from 16GB to 8GB, and the memory requirement for enabling all acceleration features has been reduced from 24GB to 10GB.
- Optimized configuration file feature switches, adding an independent formula detection switch to significantly improve speed and parsing results when formula detection is not needed.
- Integrated [PDF-Extract-Kit 1.0](https://github.com/opendatalab/PDF-Extract-Kit):
- Added the self-developed `doclayout_yolo` model, which speeds up processing by more than 10 times compared to the original solution while maintaining similar parsing effects, and can be freely switched with `layoutlmv3` via the configuration file.
- Upgraded formula parsing to `unimernet 0.2.1`, improving formula parsing accuracy while significantly reducing memory usage.
- Due to the repository change for `PDF-Extract-Kit 1.0`, you need to re-download the model. Please refer to [How to Download Models](docs/how_to_download_models_en.md) for detailed steps.
- 2024/09/27 Version 0.8.1 released, Fixed some bugs, and providing a [localized deployment version](projects/web_demo/README.md) of the [online demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/) and the [front-end interface](projects/web/README.md).
- 2024/09/09: Version 0.8.0 released, supporting fast deployment with Dockerfile, and launching demos on Huggingface and Modelscope.
- 2024/08/30: Version 0.7.1 released, add paddle tablemaster table recognition option
- 2024/08/09: Version 0.7.0b1 released, simplified installation process, added table recognition functionality
- 2024/08/01: Version 0.6.2b1 released, optimized dependency conflict issues and installation documentation
- 2024/07/05: Initial open-source release
<!-- TABLE OF CONTENT -->
<details open="open">
<summary><h2 style="display: inline-block">Table of Contents</h2></summary>
<ol>
<li>
<a href="#mineru">MinerU</a>
<ul>
<li><a href="#project-introduction">Project Introduction</a></li>
<li><a href="#key-features">Key Features</a></li>
<li><a href="#quick-start">Quick Start</a>
<ul>
<li><a href="#online-demo">Online Demo</a></li>
<li><a href="#quick-cpu-demo">Quick CPU Demo</a></li>
</ul>
</li>
<li><a href="#usage">Usage</a>
<ul>
<li><a href="#api">API</a></li>
<li><a href="#deploy-derived-projects">Deploy Derived Projects</a></li>
<li><a href="#development-guide">Development Guide</a></li>
</ul>
</li>
</ul>
</li>
<li><a href="#todo">TODO</a></li>
<li><a href="#all-thanks-to-our-contributors">All Thanks To Our Contributors</a></li>
<li><a href="#license-information">License Information</a></li>
<li><a href="#acknowledgments">Acknowledgments</a></li>
<li><a href="#citation">Citation</a></li>
<li><a href="#star-history">Star History</a></li>
<li><a href="#magic-doc">Magic-doc</a></li>
<li><a href="#magic-html">Magic-html</a></li>
<li><a href="#links">Links</a></li>
</ol>
</details>
# MinerU
## Project Introduction
MinerU is a tool that converts PDFs into machine-readable formats (e.g., markdown, JSON), allowing for easy extraction into any format.
MinerU was born during the pre-training process of [InternLM](https://github.com/InternLM/InternLM). We focus on solving symbol conversion issues in scientific literature and hope to contribute to technological development in the era of large models.
Compared to well-known commercial products, MinerU is still young. If you encounter any issues or if the results are not as expected, please submit an issue on [issue](https://github.com/opendatalab/MinerU/issues) and **attach the relevant PDF**.
https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
## Quick Start
There are multiple different ways to experience MinerU:
- [Online Demo (No Installation Required)](#online-demo)
- [Quick CPU Demo (Windows, Linux, Mac)](#quick-cpu-demo)
### Online Demo
Stable Version (Stable version verified by QA):
[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
Test Version (Synced with dev branch updates, testing new features):
[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAF8AAABYCAMAAACkl9t/AAAAk1BMVEVHcEz/nQv/nQv/nQr/nQv/nQr/nQv/nQv/nQr/wRf/txT/pg7/yRr/rBD/zRz/ngv/oAz/zhz/nwv/txT/ngv/0B3+zBz/nQv/0h7/wxn/vRb/thXkuiT/rxH/pxD/ogzcqyf/nQvTlSz/czCxky7/SjifdjT/Mj3+Mj3wMj15aTnDNz+DSD9RTUBsP0FRO0Q6O0WyIxEIAAAAGHRSTlMADB8zSWF3krDDw8TJ1NbX5efv8ff9/fxKDJ9uAAAGKklEQVR42u2Z63qjOAyGC4RwCOfB2JAGqrSb2WnTw/1f3UaWcSGYNKTdf/P+mOkTrE+yJBulvfvLT2A5ruenaVHyIks33npl/6C4s/ZLAM45SOi/1FtZPyFur1OYofBX3w7d54Bxm+E8db+nDr12ttmESZ4zludJEG5S7TO72YPlKZFyE+YCYUJTBZsMiNS5Sd7NlDmKM2Eg2JQg8awbglfqgbhArjxkS7dgp2RH6hc9AMLdZYUtZN5DJr4molC8BfKrEkPKEnEVjLbgW1fLy77ZVOJagoIcLIl+IxaQZGjiX597HopF5CkaXVMDO9Pyix3AFV3kw4lQLCbHuMovz8FallbcQIJ5Ta0vks9RnolbCK84BtjKRS5uA43hYoZcOBGIG2Epbv6CvFVQ8m8loh66WNySsnN7htL58LNp+NXT8/PhXiBXPMjLSxtwp8W9f/1AngRierBkA+kk/IpUSOeKByzn8y3kAAAfh//0oXgV4roHm/kz4E2z//zRc3/lgwBzbM2mJxQEa5pqgX7d1L0htrhx7LKxOZlKbwcAWyEOWqYSI8YPtgDQVjpB5nvaHaSnBaQSD6hweDi8PosxD6/PT09YY3xQA7LTCTKfYX+QHpA0GCcqmEHvr/cyfKQTEuwgbs2kPxJEB0iNjfJcCTPyocx+A0griHSmADiC91oNGVwJ69RudYe65vJmoqfpul0lrqXadW0jFKH5BKwAeCq+Den7s+3zfRJzA61/Uj/9H/VzLKTx9jFPPdXeeP+L7WEvDLAKAIoF8bPTKT0+TM7W8ePj3Rz/Yn3kOAp2f1Kf0Weony7pn/cPydvhQYV+eFOfmOu7VB/ViPe34/EN3RFHY/yRuT8ddCtMPH/McBAT5s+vRde/gf2c/sPsjLK+m5IBQF5tO+h2tTlBGnP6693JdsvofjOPnnEHkh2TnV/X1fBl9S5zrwuwF8NFrAVJVwCAPTe8gaJlomqlp0pv4Pjn98tJ/t/fL++6unpR1YGC2n/KCoa0tTLoKiEeUPDl94nj+5/Tv3/eT5vBQ60X1S0oZr+IWRR8Ldhu7AlLjPISlJcO9vrFotky9SpzDequlwEir5beYAc0R7D9KS1DXva0jhYRDXoExPdc6yw5GShkZXe9QdO/uOvHofxjrV/TNS6iMJS+4TcSTgk9n5agJdBQbB//IfF/HpvPt3Tbi7b6I6K0R72p6ajryEJrENW2bbeVUGjfgoals4L443c7BEE4mJO2SpbRngxQrAKRudRzGQ8jVOL2qDVjjI8K1gc3TIJ5KiFZ1q+gdsARPB4NQS4AjwVSt72DSoXNyOWUrU5mQ9nRYyjp89Xo7oRI6Bga9QNT1mQ/ptaJq5T/7WcgAZywR/XlPGAUDdet3LE+qS0TI+g+aJU8MIqjo0Kx8Ly+maxLjJmjQ18rA0YCkxLQbUZP1WqdmyQGJLUm7VnQFqodmXSqmRrdVpqdzk5LvmvgtEcW8PMGdaS23EOWyDVbACZzUJPaqMbjDxpA3Qrgl0AikimGDbqmyT8P8NOYiqrldF8rX+YN7TopX4UoHuSCYY7cgX4gHwclQKl1zhx0THf+tCAUValzjI7Wg9EhptrkIcfIJjA94evOn8B2eHaVzvBrnl2ig0So6hvPaz0IGcOvTHvUIlE2+prqAxLSQxZlU2stql1NqCCLdIiIN/i1DBEHUoElM9dBravbiAnKqgpi4IBkw+utSPIoBijDXJipSVV7MpOEJUAc5Qmm3BnUN+w3hteEieYKfRZSIUcXKMVf0u5wD4EwsUNVvZOtUT7A2GkffHjByWpHqvRBYrTV72a6j8zZ6W0DTE86Hn04bmyWX3Ri9WH7ZU6Q7h+ZHo0nHUAcsQvVhXRDZHChwiyi/hnPuOsSEF6Exk3o6Y9DT1eZ+6cASXk2Y9k+6EOQMDGm6WBK10wOQJCBwren86cPPWUcRAnTVjGcU1LBgs9FURiX/e6479yZcLwCBmTxiawEwrOcleuu12t3tbLv/N4RLYIBhYexm7Fcn4OJcn0+zc+s8/VfPeddZHAGN6TT8eGczHdR/Gts1/MzDkThr23zqrVfAMFT33Nx1RJsx1k5zuWILLnG/vsH+Fv5D4NTVcp1Gzo8AAAAAElFTkSuQmCC&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
### Quick CPU Demo
#### 1. Install magic-pdf
```bash
conda create -n MinerU python=3.10
conda activate MinerU
pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
```
#### 2. Download model weight files
Refer to [How to Download Model Files](docs/how_to_download_models_en.md) for detailed instructions.
#### 3. Modify the Configuration File for Additional Configuration
After completing the [2. Download model weight files](#2-download-model-weight-files) step, the script will automatically generate a `magic-pdf.json` file in the user directory and configure the default model path.
You can find the `magic-pdf.json` file in your 【user directory】.
> [!TIP]
> The user directory for Windows is "C:\\Users\\username", for Linux it is "/home/username", and for macOS it is "/Users/username".
You can modify certain configurations in this file to enable or disable features, such as table recognition:
> [!NOTE]
> If the following items are not present in the JSON, please manually add the required items and remove the comment content (standard JSON does not support comments).
```json
{
// other config
"layout-config": {
"model": "layoutlmv3" // Please change to "doclayout_yolo" when using doclayout_yolo.
},
"formula-config": {
"mfd_model": "yolo_v8_mfd",
"mfr_model": "unimernet_small",
"enable": true // The formula recognition feature is enabled by default. If you need to disable it, please change the value here to "false".
},
"table-config": {
"model": "rapid_table", // Default to using "rapid_table", can be switched to "tablemaster" or "struct_eqtable".
"enable": false, // The table recognition feature is disabled by default. If you need to enable it, please change the value here to "true".
"max_time": 400
}
}
```
## Usage
### API
Processing files from local disk
```python
image_writer = DiskReaderWriter(local_image_dir)
image_dir = str(os.path.basename(local_image_dir))
jso_useful_key = {"_pdf_type": "", "model_list": []}
pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
pipe.pipe_classify()
pipe.pipe_analyze()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
```
Processing files from object storage
```python
s3pdf_cli = S3ReaderWriter(pdf_ak, pdf_sk, pdf_endpoint)
image_dir = "s3://img_bucket/"
s3image_cli = S3ReaderWriter(img_ak, img_sk, img_endpoint, parent_path=image_dir)
pdf_bytes = s3pdf_cli.read(s3_pdf_path, mode=s3pdf_cli.MODE_BIN)
jso_useful_key = {"_pdf_type": "", "model_list": []}
pipe = UNIPipe(pdf_bytes, jso_useful_key, s3image_cli)
pipe.pipe_classify()
pipe.pipe_analyze()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
```
For detailed implementation, refer to:
- [demo.py Simplest Processing Method](demo/demo.py)
- [magic_pdf_parse_main.py More Detailed Processing Workflow](demo/magic_pdf_parse_main.py)
### Deploy Derived Projects
Derived projects include secondary development projects based on MinerU by project developers and community developers,
such as application interfaces based on Gradio, RAG based on llama, web demos similar to the official website, lightweight multi-GPU load balancing client/server ends, etc.
These projects may offer more features and a better user experience.
For specific deployment methods, please refer to the [Derived Project README](projects/README.md)
### Development Guide
TODO
# TODO
- [x] Reading order based on the model
- [x] Recognition of `index` and `list` in the main text
- [x] Table recognition
- [ ] Code block recognition in the main text
- [ ] [Chemical formula recognition](docs/chemical_knowledge_introduction/introduction.pdf)
- [ ] Geometric shape recognition
# All Thanks To Our Contributors
<a href="https://github.com/opendatalab/MinerU/graphs/contributors">
<img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
</a>
# License Information
[LICENSE.md](LICENSE.md)
This project currently uses PyMuPDF to achieve advanced functionality. However, since it adheres to the AGPL license, it may impose restrictions on certain usage scenarios. In future iterations, we plan to explore and replace it with a more permissive PDF processing library to enhance user-friendliness and flexibility.
# Acknowledgments
- [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
- [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
- [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
- [RapidTable](https://github.com/RapidAI/RapidTable)
- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
- [layoutreader](https://github.com/ppaanngggg/layoutreader)
- [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
- [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
# Citation
```bibtex
@misc{wang2024mineruopensourcesolutionprecise,
title={MinerU: An Open-Source Solution for Precise Document Content Extraction},
author={Bin Wang and Chao Xu and Xiaomeng Zhao and Linke Ouyang and Fan Wu and Zhiyuan Zhao and Rui Xu and Kaiwen Liu and Yuan Qu and Fukai Shang and Bo Zhang and Liqun Wei and Zhihao Sui and Wei Li and Botian Shi and Yu Qiao and Dahua Lin and Conghui He},
year={2024},
eprint={2409.18839},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2409.18839},
}
@article{he2024opendatalab,
title={Opendatalab: Empowering general artificial intelligence with open datasets},
author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
journal={arXiv preprint arXiv:2407.13773},
year={2024}
}
```
# Star History
<a>
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date&theme=dark" />
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
<img alt="Star History Chart" src="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
</picture>
</a>
# Magic-doc
[Magic-Doc](https://github.com/InternLM/magic-doc) Fast speed ppt/pptx/doc/docx/pdf extraction tool
# Magic-html
[Magic-HTML](https://github.com/opendatalab/magic-html) Mixed web page extraction tool
# Links
- [LabelU (A Lightweight Multi-modal Data Annotation Tool)](https://github.com/opendatalab/labelU)
- [LabelLLM (An Open-source LLM Dialogue Annotation Platform)](https://github.com/opendatalab/LabelLLM)
- [PDF-Extract-Kit (A Comprehensive Toolkit for High-Quality PDF Content Extraction)](https://github.com/opendatalab/PDF-Extract-Kit)
next_docs/README_zh-CN.md deleted 100644 → 0
View file @ 04f084ac
<div align="center" xmlns="http://www.w3.org/1999/html">
<!-- logo -->
<p align="center">
<img src="docs/images/MinerU-logo.png" width="300px" style="vertical-align:middle;">
</p>
<!-- icon -->
[![stars](https://img.shields.io/github/stars/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
[![forks](https://img.shields.io/github/forks/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
[![open issues](https://img.shields.io/github/issues-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
[![issue resolution](https://img.shields.io/github/issues-closed-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
[![PyPI version](https://badge.fury.io/py/magic-pdf.svg)](https://badge.fury.io/py/magic-pdf)
[![Downloads](https://static.pepy.tech/badge/magic-pdf)](https://pepy.tech/project/magic-pdf)
[![Downloads](https://static.pepy.tech/badge/magic-pdf/month)](https://pepy.tech/project/magic-pdf)
[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/myhloli/3b3a00a4a0a61577b6c30f989092d20d/mineru_demo.ipynb)
[![Paper](https://img.shields.io/badge/Paper-arXiv-green)](https://arxiv.org/abs/2409.18839)
<a href="https://trendshift.io/repositories/11174" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11174" alt="opendatalab%2FMinerU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
<!-- language -->
[English](README.md) | [简体中文](README_zh-CN.md)
<!-- hot link -->
<p align="center">
<a href="https://github.com/opendatalab/PDF-Extract-Kit">PDF-Extract-Kit: 高质量PDF解析工具箱</a>🔥🔥🔥
</p>
<!-- join us -->
<p align="center">
👋 join us on <a href="https://discord.gg/Tdedn9GTXq" target="_blank">Discord</a> and <a href="https://cdn.vansin.top/internlm/mineru.jpg" target="_blank">WeChat</a>
</p>
<!-- read the docs -->
<p align="center">
read more docs on <a href="https://mineru.readthedocs.io/zh-cn/latest/"> Read The Docs </a>
</p>
</div>
# 更新记录
- 2024/11/06 0.9.2发布，为表格识别功能接入了[StructTable-InternVL2-1B](https://huggingface.co/U4R/StructTable-InternVL2-1B)模型
- 2024/10/31 0.9.0发布，这是我们进行了大量代码重构的全新版本，解决了众多问题，提升了性能，降低了硬件需求，并提供了更丰富的易用性：
- 重构排序模块代码，使用 [layoutreader](https://github.com/ppaanngggg/layoutreader) 进行阅读顺序排序，确保在各种排版下都能实现极高准确率
- 重构段落拼接模块，在跨栏、跨页、跨图、跨表情况下均能实现良好的段落拼接效果
- 重构列表和目录识别功能，极大提升列表块和目录块识别的准确率及对应文本段落的解析效果
- 重构图、表与描述性文本的匹配逻辑，大幅提升 caption 和 footnote 与图表的匹配准确率，并将描述性文本的丢失率降至接近0
- 增加 OCR 的多语言支持，支持 84 种语言的检测与识别，语言支持列表详见 [OCR 语言支持列表](https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5)
- 增加显存回收逻辑及其他显存优化措施，大幅降低显存使用需求。开启除表格加速外的全部加速功能(layout/公式/OCR)的显存需求从16GB降至8GB，开启全部加速功能的显存需求从24GB降至10GB
- 优化配置文件的功能开关，增加独立的公式检测开关，无需公式检测时可大幅提升速度和解析效果
- 集成 [PDF-Extract-Kit 1.0](https://github.com/opendatalab/PDF-Extract-Kit)
- 加入自研的 `doclayout_yolo` 模型，在相近解析效果情况下比原方案提速10倍以上，可通过配置文件与 `layoutlmv3` 自由切换
- 公式解析升级至 `unimernet 0.2.1`，在提升公式解析准确率的同时，大幅降低显存需求
- 因 `PDF-Extract-Kit 1.0` 更换仓库，需要重新下载模型，步骤详见 [如何下载模型](docs/how_to_download_models_zh_cn.md)
- 2024/09/27 0.8.1发布，修复了一些bug，同时提供了[在线demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/)的[本地化部署版本](projects/web_demo/README_zh-CN.md)和[前端界面](projects/web/README_zh-CN.md)
- 2024/09/09 0.8.0发布，支持Dockerfile快速部署，同时上线了huggingface、modelscope demo
- 2024/08/30 0.7.1发布，集成了paddle tablemaster表格识别功能
- 2024/08/09 0.7.0b1发布，简化安装步骤提升易用性，加入表格识别功能
- 2024/08/01 0.6.2b1发布，优化了依赖冲突问题和安装文档
- 2024/07/05 首次开源
<!-- TABLE OF CONTENT -->
<details open="open">
<summary><h2 style="display: inline-block">文档目录</h2></summary>
<ol>
<li>
<a href="#mineru">MinerU</a>
<ul>
<li><a href="#项目简介">项目简介</a></li>
<li><a href="#主要功能">主要功能</a></li>
<li><a href="#快速开始">快速开始</a>
<ul>
<li><a href="#在线体验">在线体验</a></li>
<li><a href="#使用CPU快速体验">使用CPU快速体验</a></li>
</ul>
</li>
<li><a href="#使用">使用方式</a>
<ul>
<li><a href="#api">API</a></li>
<li><a href="#部署衍生项目">部署衍生项目</a></li>
<li><a href="#二次开发">二次开发</a></li>
</ul>
</li>
</ul>
</li>
<li><a href="#todo">TODO</a></li>
<li><a href="#known-issues">Known Issues</a></li>
<li><a href="#faq">FAQ</a></li>
<li><a href="#all-thanks-to-our-contributors">Contributors</a></li>
<li><a href="#license-information">License Information</a></li>
<li><a href="#acknowledgments">Acknowledgements</a></li>
<li><a href="#citation">Citation</a></li>
<li><a href="#star-history">Star History</a></li>
<li><a href="#magic-doc">magic-doc快速提取PPT/DOC/PDF</a></li>
<li><a href="#magic-html">magic-html提取混合网页内容</a></li>
<li><a href="#links">Links</a></li>
</ol>
</details>
# MinerU
## 项目简介
MinerU是一款将PDF转化为机器可读格式的工具（如markdown、json），可以很方便地抽取为任意格式。
MinerU诞生于[书生-浦语](https://github.com/InternLM/InternLM)的预训练过程中，我们将会集中精力解决科技文献中的符号转化问题，希望在大模型时代为科技发展做出贡献。
相比国内外知名商用产品MinerU还很年轻，如果遇到问题或者结果不及预期请到[issue](https://github.com/opendatalab/MinerU/issues)提交问题，同时**附上相关PDF**。
https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
## 快速开始
有多种不同方式可以体验MinerU的效果：
- [在线体验(无需任何安装)](#在线体验)
- [使用CPU快速体验（Windows，Linux，Mac）](#使用cpu快速体验)
### 在线体验
稳定版(经过QA验证的稳定版本)：
[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
测试版(同步dev分支更新，测试新特性)：
[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
### 使用CPU快速体验
#### 1. 安装magic-pdf
> [!NOTE]
> 最新版本国内镜像源同步可能会有延迟，请耐心等待
```bash
conda create -n MinerU python=3.10
conda activate MinerU
pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i https://mirrors.aliyun.com/pypi/simple
```
#### 2. 下载模型权重文件
详细参考 [如何下载模型文件](docs/how_to_download_models_zh_cn.md)
#### 3. 修改配置文件以进行额外配置
完成[2. 下载模型权重文件](#2-下载模型权重文件)步骤后，脚本会自动生成用户目录下的magic-pdf.json文件，并自动配置默认模型路径。
您可在【用户目录】下找到magic-pdf.json文件。
> [!TIP]
> windows的用户目录为 "C:\\Users\\用户名", linux用户目录为 "/home/用户名", macOS用户目录为 "/Users/用户名"
您可修改该文件中的部分配置实现功能的开关，如表格识别功能：
> [!NOTE]
>如json内没有如下项目，请手动添加需要的项目，并删除注释内容（标准json不支持注释）
```json
{
// other config
"layout-config": {
"model": "layoutlmv3" // 使用doclayout_yolo请修改为“doclayout_yolo"
},
"formula-config": {
"mfd_model": "yolo_v8_mfd",
"mfr_model": "unimernet_small",
"enable": true // 公式识别功能默认是开启的，如果需要关闭请修改此处的值为"false"
},
"table-config": {
"model": "rapid_table", // 默认使用"rapid_table",可以切换为"tablemaster"和"struct_eqtable"
"enable": false, // 表格识别功能默认是关闭的，如果需要开启请修改此处的值为"true"
"max_time": 400
}
}
```
## 使用
### API
处理本地磁盘上的文件
```python
image_writer = DiskReaderWriter(local_image_dir)
image_dir = str(os.path.basename(local_image_dir))
jso_useful_key = {"_pdf_type": "", "model_list": []}
pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
pipe.pipe_classify()
pipe.pipe_analyze()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
```
处理对象存储上的文件
```python
s3pdf_cli = S3ReaderWriter(pdf_ak, pdf_sk, pdf_endpoint)
image_dir = "s3://img_bucket/"
s3image_cli = S3ReaderWriter(img_ak, img_sk, img_endpoint, parent_path=image_dir)
pdf_bytes = s3pdf_cli.read(s3_pdf_path, mode=s3pdf_cli.MODE_BIN)
jso_useful_key = {"_pdf_type": "", "model_list": []}
pipe = UNIPipe(pdf_bytes, jso_useful_key, s3image_cli)
pipe.pipe_classify()
pipe.pipe_analyze()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
```
详细实现可参考
- [demo.py 最简单的处理方式](demo/demo.py)
- [magic_pdf_parse_main.py 能够更清晰看到处理流程](demo/magic_pdf_parse_main.py)
### 部署衍生项目
衍生项目包含项目开发者和社群开发者们基于MinerU的二次开发项目，
例如基于Gradio的应用界面、基于llama的RAG、官网同款web demo、轻量级的多卡负载均衡c/s端等，
这些项目可能会提供更多的功能和更好的用户体验。
具体部署方式请参考 [衍生项目readme](projects/README_zh-CN.md)
### 二次开发
TODO
# TODO
- [x] 基于模型的阅读顺序
- [x] 正文中目录、列表识别
- [x] 表格识别
- [ ] 正文中代码块识别
- [ ] [化学式识别](docs/chemical_knowledge_introduction/introduction.pdf)
- [ ] 几何图形识别
# All Thanks To Our Contributors
<a href="https://github.com/opendatalab/MinerU/graphs/contributors">
<img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
</a>
# License Information
[LICENSE.md](LICENSE.md)
本项目目前采用PyMuPDF以实现高级功能，但因其遵循AGPL协议，可能对某些使用场景构成限制。未来版本迭代中，我们计划探索并替换为许可条款更为宽松的PDF处理库，以提升用户友好度及灵活性。
# Acknowledgments
- [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
- [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
- [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
- [RapidTable](https://github.com/RapidAI/RapidTable)
- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
- [layoutreader](https://github.com/ppaanngggg/layoutreader)
- [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
- [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
# Citation
```bibtex
@misc{wang2024mineruopensourcesolutionprecise,
title={MinerU: An Open-Source Solution for Precise Document Content Extraction},
author={Bin Wang and Chao Xu and Xiaomeng Zhao and Linke Ouyang and Fan Wu and Zhiyuan Zhao and Rui Xu and Kaiwen Liu and Yuan Qu and Fukai Shang and Bo Zhang and Liqun Wei and Zhihao Sui and Wei Li and Botian Shi and Yu Qiao and Dahua Lin and Conghui He},
year={2024},
eprint={2409.18839},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2409.18839},
}
@article{he2024opendatalab,
title={Opendatalab: Empowering general artificial intelligence with open datasets},
author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
journal={arXiv preprint arXiv:2407.13773},
year={2024}
}
```
# Star History
<a>
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date&theme=dark" />
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
<img alt="Star History Chart" src="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
</picture>
</a>
# Magic-doc
[Magic-Doc](https://github.com/InternLM/magic-doc) Fast speed ppt/pptx/doc/docx/pdf extraction tool
# Magic-html
[Magic-HTML](https://github.com/opendatalab/magic-html) Mixed web page extraction tool
# Links
- [LabelU (A Lightweight Multi-modal Data Annotation Tool)](https://github.com/opendatalab/labelU)
- [LabelLLM (An Open-source LLM Dialogue Annotation Platform)](https://github.com/opendatalab/LabelLLM)
- [PDF-Extract-Kit (A Comprehensive Toolkit for High-Quality PDF Content Extraction)](https://github.com/opendatalab/PDF-Extract-Kit)
next_docs/en/additional_notes/glossary.rst
View file @ 4bb54393
...@@ -4,8 +4,11 @@ Glossary ...@@ -4,8 +4,11 @@ Glossary
=========== ===========
1. jsonl 1. jsonl
TODO: add description Newline-delimited (\n), and each line must be a valid, independent JSON object.
Currently, All the function shipped with **MinerU** assume that json object must contain one field named with either **path** or **file_location**
2. magic-pdf.json
TODO
2. magic-pdf.json
TODO: add description
next_docs/en/api/model_operators.rst
View file @ 4bb54393
...@@ -2,7 +2,7 @@ ...@@ -2,7 +2,7 @@
Model Api Model Api
========== ==========
.. autoclass:: magic_pdf.model.InferenceResultBase .. autoclass:: magic_pdf.operators.InferenceResultBase
:members: :members:
:inherited-members: :inherited-members:
:show-inheritance: :show-inheritance:
next_docs/en/api/pipe_operators.rst
View file @ 4bb54393
...@@ -3,7 +3,7 @@ ...@@ -3,7 +3,7 @@
Pipeline Api Pipeline Api
============= =============
.. autoclass:: magic_pdf.pipe.operators.PipeResult .. autoclass:: magic_pdf.operators.pipes.PipeResult
:members: :members:
:inherited-members: :inherited-members:
:show-inheritance: :show-inheritance:
\ No newline at end of file
next_docs/en/index.rst
View file @ 4bb54393
...@@ -70,6 +70,12 @@ Key Features ...@@ -70,6 +70,12 @@ Key Features
- Supports both CPU and GPU environments. - Supports both CPU and GPU environments.
- Compatible with Windows, Linux, and Mac platforms. - Compatible with Windows, Linux, and Mac platforms.
.. tip::
Get started with MinerU by trying the `online demo <https://www.modelscope.cn/studios/OpenDataLab/MinerU>`_ or :doc:`installing it locally <user_guide/install/install>`.
User Guide User Guide
------------- -------------
.. toctree:: .. toctree::
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment