mirror of
https://github.com/opendatalab/MinerU.git
synced 2026-08-28 11:12:05 +08:00
feat: add copyright notice to multiple files
This commit is contained in:
@@ -1 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import time
|
||||
from collections import defaultdict
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import copy
|
||||
import re
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
import os
|
||||
import time
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import re
|
||||
from collections import defaultdict
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import re
|
||||
from typing import Literal
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import re
|
||||
import unicodedata
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import base64
|
||||
import html
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import threading
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
class AtomicModel:
|
||||
Layout = "layout"
|
||||
MFD = "mfd"
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import copy
|
||||
from loguru import logger
|
||||
from mineru.utils.enum_class import ContentType, BlockType, SplitFlag
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import time
|
||||
from typing import List, Tuple
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from mineru.backend.pipeline.para_split import ListLineTag
|
||||
from mineru.backend.pipeline.pipeline_middle_json_mkcontent import _merge_para_text
|
||||
from mineru.utils.boxbase import (
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import re
|
||||
from html import unescape
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import base64
|
||||
import re
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from PIL import Image, ImageDraw, ImageFont
|
||||
from loguru import logger
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import copy
|
||||
|
||||
from mineru.utils.enum_class import BlockType, SplitFlag
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import time
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import time
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
|
||||
from loguru import logger
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import re
|
||||
|
||||
from loguru import logger
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import re
|
||||
from html import escape, unescape
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import asyncio
|
||||
import atexit
|
||||
import json
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
API_PROTOCOL_VERSION = 1
|
||||
DEFAULT_MAX_CONCURRENT_REQUESTS = 3
|
||||
DEFAULT_PROCESSING_WINDOW_SIZE = 64
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import asyncio
|
||||
import mimetypes
|
||||
import multiprocessing
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from contextlib import contextmanager
|
||||
import json
|
||||
import os
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import asyncio
|
||||
import json
|
||||
import os
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import json
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from collections.abc import Mapping, Sequence
|
||||
from typing import Any
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import click
|
||||
import sys
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from .base import DataReader, DataWriter
|
||||
from .dummy import DummyDataWriter
|
||||
from .filebase import FileBasedDataReader, FileBasedDataWriter
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from .base import DataWriter
|
||||
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
|
||||
from .base import DataReader, DataWriter
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
from ..utils.exceptions import InvalidConfig, InvalidParams
|
||||
from .base import DataReader, DataWriter
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from .multi_bucket_s3 import MultiBucketS3DataReader, MultiBucketS3DataWriter
|
||||
from ..utils.schemas import S3Config
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
from .base import IOReader, IOWriter
|
||||
from .http import HttpReader, HttpWriter
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from abc import ABC, abstractmethod
|
||||
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
import io
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import boto3
|
||||
from botocore.config import Config
|
||||
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from typing import BinaryIO
|
||||
|
||||
from mineru.model.docx.docx_converter import DocxConverter
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
"""
|
||||
Adapted from https://github.com/xiilei/dwml/blob/master/dwml/latex_dict.py
|
||||
On 23/01/2025
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
"""
|
||||
Office Math Markup Language (OMML)
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import xml.dom.minidom
|
||||
|
||||
from mammoth.docx.xmlparser import XmlText, XmlElement
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import argparse
|
||||
import colorsys
|
||||
import hashlib
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import math
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import json
|
||||
import numpy as np
|
||||
import cv2
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import math
|
||||
|
||||
import torch
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from .unimer_swin import UnimerSwinConfig, UnimerSwinModel, UnimerSwinImageProcessor
|
||||
from .unimer_mbart import UnimerMBartConfig, UnimerMBartModel, UnimerMBartForCausalLM
|
||||
from .modeling_unimernet import UnimernetModel
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import warnings
|
||||
from typing import Optional
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from .configuration_unimer_mbart import UnimerMBartConfig
|
||||
from .modeling_unimer_mbart import UnimerMBartModel, UnimerMBartForCausalLM
|
||||
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from .configuration_unimer_swin import UnimerSwinConfig
|
||||
from .modeling_unimer_swin import UnimerSwinModel
|
||||
from .image_processing_unimer_swin import UnimerSwinImageProcessor
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from PIL import Image, ImageOps
|
||||
from transformers.image_processing_utils import BaseImageProcessor
|
||||
import numpy as np
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import re
|
||||
|
||||
LEFT_PATTERN = re.compile(r'(\\left)(\S*)')
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from typing import BinaryIO
|
||||
|
||||
from mineru.model.pptx.pptx_converter import PptxConverter
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from dataclasses import dataclass
|
||||
from typing import Any, Final, Sequence
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
|
||||
from PIL import Image
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import copy
|
||||
import time
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
# copyright (c) 2022 PaddlePaddle Authors. All Rights Reserve.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
# copyright (c) 2022 PaddlePaddle Authors. All Rights Reserve.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import html
|
||||
import logging
|
||||
import os
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from typing import Dict, List, Tuple
|
||||
|
||||
import numpy as np
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import copy
|
||||
import math
|
||||
from typing import Optional, Dict, Any, Tuple
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import traceback
|
||||
from enum import Enum
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import math
|
||||
|
||||
import cv2
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from typing import Any, Dict, List, Union, Tuple
|
||||
|
||||
import numpy as np
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os
|
||||
import torch
|
||||
from .modeling.architectures.base_model import BaseModel
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from torch import nn
|
||||
|
||||
from ..backbones import build_backbone
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from torch import nn
|
||||
|
||||
from ..common import Activation
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import collections.abc
|
||||
from collections import OrderedDict
|
||||
import math
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
# copyright (c) 2021 PaddlePaddle Authors. All Rights Reserve.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from torch import nn
|
||||
|
||||
from .det_mobilenet_v3 import ConvBNLayer, ResidualUnit, make_divisible
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import os, sys
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import math
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from torch import nn
|
||||
|
||||
from ..necks.rnn import Im2Seq, SequenceEncoder
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
# copyright (c) 2024 PaddlePaddle Authors. All Rights Reserve.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import copy
|
||||
import math
|
||||
import re
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
from torch import nn
|
||||
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# Copyright (c) Opendatalab. All rights reserved.
|
||||
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user