ocr_platform/ocr_utils/__init__.py

"""
OCR 工具包

整合了文档处理相关的工具函数，包括：
- PDF 处理工具
- JSON/Markdown/HTML 格式化工具
- 文件处理工具
- 数字标准化工具
"""

from .pdf_utils import PDFUtils
from .json_formatters import JSONFormatters
from .markdown_generator import MarkdownGenerator
from .html_generator import HTMLGenerator
from .visualization_utils import VisualizationUtils
from .output_formatter_v2 import OutputFormatterV2, save_mineru_format
from .pdf_extractor import extract_pdf_pages
from .normalize_financial_numbers import (
    normalize_financial_numbers,
    normalize_json_table,
    normalize_markdown_table,
    normalize_json_file
)
from .file_utils import (
    get_input_files,
    collect_pid_files,
    get_image_files_from_dir,
    get_image_files_from_list,
    get_image_files_from_csv,
    convert_pdf_to_images,
    split_files,
    create_temp_file_list
)
from .log_utils import setup_logging

__all__ = [
    # PDF 工具
    'PDFUtils',
    'extract_pdf_pages',
    # JSON 格式化
    'JSONFormatters',
    # Markdown 生成
    'MarkdownGenerator',
    # HTML 生成
    'HTMLGenerator',
    # 可视化
    'VisualizationUtils',
    # 输出格式化
    'OutputFormatterV2',
    'save_mineru_format',
    # 数字标准化
    'normalize_financial_numbers',
    'normalize_json_table',
    'normalize_markdown_table',
    'normalize_json_file',
    # 文件工具
    'get_input_files',
    'collect_pid_files',
    'get_image_files_from_dir',
    'get_image_files_from_list',
    'get_image_files_from_csv',
    'convert_pdf_to_images',
    'split_files',
    'create_temp_file_list',
    # 日志工具
    'setup_logging',
]

__version__ = "1.0.0"
__author__ = "zhch158"