ksanyok/TextHumanize v0.9.0

v0.9.0 — Kirchenbauer Watermark, HTML Diff, Quality Gate, Selective Humanization, Stylometric Anonymizer

on GitHub

What's New

Kirchenbauer Watermark Detector

Green-list z-test based on Kirchenbauer et al. 2023. Uses SHA-256 hash of previous token to partition vocabulary into green/red lists (γ=0.25), computes z-score and p-value. Flags AI watermark at z ≥ 4.0.

from texthumanize import detect_watermarks
report = detect_watermarks(text)
print(report.kirchenbauer_score, report.kirchenbauer_p_value)

HTML Diff Report

explain() now supports multiple output formats:

html = explain(result, fmt='html')      # self-contained HTML page
json_str = explain(result, fmt='json')  # RFC 6902 JSON Patch
diff = explain(result, fmt='diff')      # unified diff

Quality Gate

CLI + GitHub Action + pre-commit hook to check text for AI artifacts:

python -m texthumanize.quality_gate README.md docs/ --ai-threshold 25

Selective Humanization

Process only AI-flagged sentences, leaving human text untouched:

result = humanize(text, only_flagged=True)

Stylometric Anonymizer

Disguise authorship by transforming text toward a target style:

from texthumanize import anonymize_style
result = anonymize_style(text, target='blogger')

Stats

• 1,373 Python tests passing
• 40 new tests for v0.9.0 features
• Ruff lint clean
• 22 files changed, 1,637 additions