# 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 data enrichment pipeline."""
from enrichment import (
TECH_PATTERNS,
detect_tech_stack,
extract_company_info,
extract_social_profiles,
)
def test_detect_tech_wordpress() -> None:
html = ''
result = detect_tech_stack(html)
assert "wordpress" in result["detected"]
def test_detect_tech_shopify() -> None:
html = ''
result = detect_tech_stack(html)
assert "shopify" in result["detected"]
def test_detect_tech_nextjs() -> None:
html = ""
result = detect_tech_stack(html)
assert "nextjs" in result["detected"]
def test_detect_tech_cloudflare() -> None:
html = ""
result = detect_tech_stack(html, {"server": "cloudflare"})
assert "cloudflare" in result["detected"]
def test_detect_tech_empty() -> None:
result = detect_tech_stack("", {})
assert result["count"] == 0
def test_extract_social_twitter() -> None:
html = 'Follow us on Twitter'
result = extract_social_profiles(html)
assert "pry_scraper" in str(result["profiles"])
def test_extract_social_linkedin() -> None:
html = 'Connect on LinkedIn'
result = extract_social_profiles(html)
assert "pry-inc" in str(result["profiles"])
def test_extract_company_email() -> None:
html = "Contact us at info@example.com for inquiries"
result = extract_company_info(html)
assert len(result.get("emails", [])) >= 1
assert "info@example.com" in result["emails"]
def test_extract_company_founded() -> None:
html = "Founded in 2020, we have been growing ever since."
result = extract_company_info(html)
assert result.get("founded_year") == "2020"
def test_tech_patterns_exist() -> None:
assert "wordpress" in TECH_PATTERNS
assert "shopify" in TECH_PATTERNS
assert "nextjs" in TECH_PATTERNS
assert "cloudflare" in TECH_PATTERNS
assert "stripe" in TECH_PATTERNS