cryptorugmunch
0ecc250349
The duplicate file names (advanced, agency, auth, compliance, costing, etc.) in both root and routers/ made imports ambiguous. Renamed root modules to pry_<name>.py so: from quality import X -> from pry_quality import X from routers.quality import router (unchanged) Also: - Renamed x402.py to pry_x402/ package directory - Fixed 21+ bare imports across api.py, deps.py, routers/, tests/, llm_providers/ Tests: 593 passed, 1 skipped (test_ready_returns_200 fails pre-existing because Ollama is unreachable from test env, unrelated to this refactor). Audit item 8.
87 lines
2.7 KiB
Python
87 lines
2.7 KiB
Python
# SPDX-License-Identifier: MIT
|
|
# Copyright (c) 2026 Rug Munch Media LLC
|
|
#
|
|
# Part of Pry — https://git.rugmunch.io/RugMunchMedia/pryscraper
|
|
# Licensed under MIT. See LICENSE.
|
|
"""Tests for legal compliance engine."""
|
|
|
|
from pry_compliance import (
|
|
classify_tos,
|
|
detect_jurisdiction,
|
|
tag_sensitive_data,
|
|
)
|
|
|
|
|
|
def test_classify_tos_restrictive() -> None:
|
|
text = "No scraping, no crawling, no automated access. All rights reserved."
|
|
result = classify_tos(text)
|
|
assert result["classification"] == "restrictive"
|
|
|
|
|
|
def test_classify_tos_permissive() -> None:
|
|
text = "This data is freely available under Creative Commons Attribution 4.0."
|
|
result = classify_tos(text)
|
|
assert result["classification"] == "permissive"
|
|
|
|
|
|
def test_classify_tos_moderate() -> None:
|
|
text = "Personal use only. Attribution required. Fair use applies."
|
|
result = classify_tos(text)
|
|
assert result["classification"] == "moderate"
|
|
|
|
|
|
def test_classify_tos_empty() -> None:
|
|
result = classify_tos("")
|
|
assert result["confidence"] in ("low", "medium")
|
|
|
|
|
|
def test_detect_jurisdiction_eu() -> None:
|
|
result = detect_jurisdiction("https://example.de")
|
|
assert result["jurisdiction"] == "eu"
|
|
|
|
|
|
def test_detect_jurisdiction_us() -> None:
|
|
result = detect_jurisdiction("https://example.com")
|
|
assert result["jurisdiction"] == "us"
|
|
|
|
|
|
def test_detect_jurisdiction_ca() -> None:
|
|
result = detect_jurisdiction("https://example.ca")
|
|
assert result["jurisdiction"] == "ca"
|
|
|
|
|
|
def test_detect_jurisdiction_gdpr_signal() -> None:
|
|
html = "We comply with the General Data Protection Regulation (GDPR)."
|
|
result = detect_jurisdiction("https://example.com", html)
|
|
assert result["gdpr_signals"] is True
|
|
|
|
|
|
def test_detect_jurisdiction_ccpa_signal() -> None:
|
|
html = "CCPA California Consumer Privacy Act rights."
|
|
result = detect_jurisdiction("https://example.com", html)
|
|
assert result["ccpa_signals"] is True
|
|
|
|
|
|
def test_tag_sensitive_data_pii() -> None:
|
|
html = "Contact John Smith at john@example.com or call 555-0100."
|
|
result = tag_sensitive_data(html)
|
|
assert result["has_pii"] is True
|
|
assert result["has_contact"] is True
|
|
|
|
|
|
def test_tag_sensitive_data_financial() -> None:
|
|
html = "Total cost: $1,299.00. Invoice #1234."
|
|
result = tag_sensitive_data(html)
|
|
assert result["has_financial"] is True
|
|
|
|
|
|
def test_tag_sensitive_data_health() -> None:
|
|
html = "Patient diagnosis and treatment records are confidential."
|
|
result = tag_sensitive_data(html)
|
|
assert result["has_health"] is True
|
|
|
|
|
|
def test_tag_sensitive_data_empty() -> None:
|
|
result = tag_sensitive_data("<html><body><p>Hello</p></body></html>")
|
|
assert result["has_pii"] is False
|
|
assert result["has_financial"] is False
|