24 lines
616 B
Python
24 lines
616 B
Python
"""tmkit: PDF 数据脱敏工具库（最小可用版）。
|
||
|
||
模块：
|
||
- splitter: PDF 分流（native / scanned 页检测）
|
||
- extractor: 原生页文字 + bbox 抽取
|
||
- detector: PII 正则识别引擎（支持自定义规则）
|
||
- redactor: bbox 坐标回写，输出脱敏后 PDF
|
||
"""
|
||
|
||
from .splitter import classify_pages
|
||
from .extractor import extract_page_words
|
||
from .detector import PIIDetector, Rule, default_detector
|
||
from .redactor import redact_pdf
|
||
|
||
__all__ = [
|
||
"classify_pages",
|
||
"extract_page_words",
|
||
"PIIDetector",
|
||
"Rule",
|
||
"default_detector",
|
||
"redact_pdf",
|
||
]
|
||
__version__ = "0.1.0"
|