Phil Skentelbery
074f74002c
Implements complete domain verification flow with: - rel=me link verification service - HTML fetching with security controls - Rate limiting to prevent abuse - Email validation utilities - Authorization and verification API endpoints - User-facing templates for authorization and verification flows This completes Phase 2: Domain Verification as designed. Tests: - All Phase 2 unit tests passing - Coverage: 85% overall - Migration tests updated 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
182 lines
5.3 KiB
Python
182 lines
5.3 KiB
Python
"""Tests for rel=me parser service."""
|
|
import pytest
|
|
|
|
from gondulf.services.relme_parser import RelMeParser
|
|
|
|
|
|
class TestRelMeParser:
|
|
"""Tests for RelMeParser."""
|
|
|
|
def test_parse_relme_links_basic(self):
|
|
"""Test parsing basic rel=me links."""
|
|
html = """
|
|
<html>
|
|
<body>
|
|
<a rel="me" href="https://github.com/user">GitHub</a>
|
|
<a rel="me" href="mailto:user@example.com">Email</a>
|
|
</body>
|
|
</html>
|
|
"""
|
|
parser = RelMeParser()
|
|
links = parser.parse_relme_links(html)
|
|
|
|
assert len(links) == 2
|
|
assert "https://github.com/user" in links
|
|
assert "mailto:user@example.com" in links
|
|
|
|
def test_parse_relme_links_link_tag(self):
|
|
"""Test parsing rel=me from <link> tags."""
|
|
html = """
|
|
<html>
|
|
<head>
|
|
<link rel="me" href="https://twitter.com/user">
|
|
</head>
|
|
</html>
|
|
"""
|
|
parser = RelMeParser()
|
|
links = parser.parse_relme_links(html)
|
|
|
|
assert len(links) == 1
|
|
assert "https://twitter.com/user" in links
|
|
|
|
def test_parse_relme_links_no_rel_me(self):
|
|
"""Test parsing HTML with no rel=me links."""
|
|
html = """
|
|
<html>
|
|
<body>
|
|
<a href="https://example.com">Link</a>
|
|
</body>
|
|
</html>
|
|
"""
|
|
parser = RelMeParser()
|
|
links = parser.parse_relme_links(html)
|
|
|
|
assert len(links) == 0
|
|
|
|
def test_parse_relme_links_no_href(self):
|
|
"""Test parsing rel=me link without href."""
|
|
html = """
|
|
<html>
|
|
<body>
|
|
<a rel="me">No href</a>
|
|
</body>
|
|
</html>
|
|
"""
|
|
parser = RelMeParser()
|
|
links = parser.parse_relme_links(html)
|
|
|
|
assert len(links) == 0
|
|
|
|
def test_parse_relme_links_malformed_html(self):
|
|
"""Test parsing malformed HTML returns empty list."""
|
|
html = "<html><body><<>>broken"
|
|
parser = RelMeParser()
|
|
links = parser.parse_relme_links(html)
|
|
|
|
# Should not crash, returns what it can parse
|
|
assert isinstance(links, list)
|
|
|
|
def test_extract_mailto_email_basic(self):
|
|
"""Test extracting email from mailto: link."""
|
|
links = ["mailto:user@example.com"]
|
|
parser = RelMeParser()
|
|
email = parser.extract_mailto_email(links)
|
|
|
|
assert email == "user@example.com"
|
|
|
|
def test_extract_mailto_email_with_query(self):
|
|
"""Test extracting email from mailto: link with query parameters."""
|
|
links = ["mailto:user@example.com?subject=Hello"]
|
|
parser = RelMeParser()
|
|
email = parser.extract_mailto_email(links)
|
|
|
|
assert email == "user@example.com"
|
|
|
|
def test_extract_mailto_email_multiple_links(self):
|
|
"""Test extracting email from multiple links (returns first mailto:)."""
|
|
links = [
|
|
"https://github.com/user",
|
|
"mailto:user@example.com",
|
|
"mailto:other@example.com"
|
|
]
|
|
parser = RelMeParser()
|
|
email = parser.extract_mailto_email(links)
|
|
|
|
assert email == "user@example.com"
|
|
|
|
def test_extract_mailto_email_no_mailto(self):
|
|
"""Test extracting email when no mailto: links present."""
|
|
links = ["https://github.com/user", "https://twitter.com/user"]
|
|
parser = RelMeParser()
|
|
email = parser.extract_mailto_email(links)
|
|
|
|
assert email is None
|
|
|
|
def test_extract_mailto_email_invalid_format(self):
|
|
"""Test extracting email from malformed mailto: link."""
|
|
links = ["mailto:notanemail"]
|
|
parser = RelMeParser()
|
|
email = parser.extract_mailto_email(links)
|
|
|
|
# Should return None for invalid email format
|
|
assert email is None
|
|
|
|
def test_extract_mailto_email_empty_list(self):
|
|
"""Test extracting email from empty list."""
|
|
parser = RelMeParser()
|
|
email = parser.extract_mailto_email([])
|
|
|
|
assert email is None
|
|
|
|
def test_find_email_success(self):
|
|
"""Test find_email combining parse and extract."""
|
|
html = """
|
|
<html>
|
|
<body>
|
|
<a rel="me" href="https://github.com/user">GitHub</a>
|
|
<a rel="me" href="mailto:user@example.com">Email</a>
|
|
</body>
|
|
</html>
|
|
"""
|
|
parser = RelMeParser()
|
|
email = parser.find_email(html)
|
|
|
|
assert email == "user@example.com"
|
|
|
|
def test_find_email_no_email(self):
|
|
"""Test find_email when no email present."""
|
|
html = """
|
|
<html>
|
|
<body>
|
|
<a rel="me" href="https://github.com/user">GitHub</a>
|
|
</body>
|
|
</html>
|
|
"""
|
|
parser = RelMeParser()
|
|
email = parser.find_email(html)
|
|
|
|
assert email is None
|
|
|
|
def test_find_email_malformed_html(self):
|
|
"""Test find_email with malformed HTML."""
|
|
html = "<html><<broken>>"
|
|
parser = RelMeParser()
|
|
email = parser.find_email(html)
|
|
|
|
assert email is None
|
|
|
|
def test_parse_relme_multiple_rel_values(self):
|
|
"""Test parsing link with multiple rel values including 'me'."""
|
|
html = """
|
|
<html>
|
|
<body>
|
|
<a rel="me nofollow" href="https://example.com">Link</a>
|
|
</body>
|
|
</html>
|
|
"""
|
|
parser = RelMeParser()
|
|
links = parser.parse_relme_links(html)
|
|
|
|
assert len(links) == 1
|
|
assert "https://example.com" in links
|