mirror of
https://github.com/soxoj/maigret.git
synced 2026-08-17 19:25:41 +02:00
Sanjay SanthanamandGitHub
e08310da87
extract_ids_from_page() has the same bug #2907 fixed in checking.py::parse_usernames(). "username" is itself in SUPPORTED_IDS, so the `if k in SUPPORTED_IDS` loop stores a bare `username` value directly, bypassing the is_plausible_username() guard that extract_usernames() applies in its own separate pass. A URL or email returned by socid_extractor under a bare `username` key therefore becomes a recursive search target via `maigret --parse-url`, reproducing the #1403 false-error cascade. Skip keys containing "username" in the SUPPORTED_IDS loop; those are already owned (and validated) by extract_usernames(). Every other SUPPORTED_ID (gaia_id, vk_id, orcid, ...) is unaffected since none of those keys contain "username". Add regression tests for the bare `username` key with a URL value and for the unchanged handling of other supported IDs. Closes #2911
119 lines
2.8 KiB
Python
119 lines
2.8 KiB
Python
"""
|
|
Unit tests for username extraction helpers.
|
|
"""
|
|
|
|
from maigret.utils import extract_usernames
|
|
from maigret.maigret import extract_ids_from_page
|
|
|
|
from unittest.mock import Mock, patch
|
|
|
|
|
|
def test_extract_username():
|
|
logger = Mock()
|
|
|
|
result = extract_usernames(
|
|
{"profile_username": "emily"},
|
|
logger,
|
|
)
|
|
|
|
assert result == ["emily"]
|
|
|
|
|
|
def test_extract_list_usernames():
|
|
logger = Mock()
|
|
|
|
result = extract_usernames(
|
|
{"profile_usernames": "['emily','ashton']"},
|
|
logger,
|
|
)
|
|
|
|
assert set(result) == {"emily", "ashton"}
|
|
|
|
|
|
def test_reject_invalid_username():
|
|
logger = Mock()
|
|
|
|
result = extract_usernames(
|
|
{"profile_username": "https.example.com/au"},
|
|
logger,
|
|
)
|
|
|
|
assert result == []
|
|
|
|
|
|
def test_ignore_invalid_username_list():
|
|
logger = Mock()
|
|
|
|
result = extract_usernames(
|
|
{"profile_usernames": "not-a-list"},
|
|
logger,
|
|
)
|
|
|
|
assert result == []
|
|
assert logger.warning.called
|
|
|
|
def test_extract_ids_from_page_username_contract():
|
|
logger = Mock()
|
|
|
|
with patch("maigret.maigret.parse") as mock_parse, \
|
|
patch("maigret.maigret.extract") as mock_extract, \
|
|
patch("maigret.maigret.extract_usernames") as mock_usernames:
|
|
|
|
# fake page fetch
|
|
mock_parse.return_value = ("<html></html>", {})
|
|
|
|
# no structured IDs
|
|
mock_extract.return_value = {}
|
|
|
|
# username detection
|
|
mock_usernames.return_value = ["emily"]
|
|
|
|
result = extract_ids_from_page(
|
|
"https://example.com/profile",
|
|
logger,
|
|
timeout=5,
|
|
)
|
|
|
|
assert result == {"emily": "username"}
|
|
|
|
|
|
def test_extract_ids_from_page_rejects_bare_username_url():
|
|
logger = Mock()
|
|
|
|
with patch("maigret.maigret.parse") as mock_parse, \
|
|
patch("maigret.maigret.extract") as mock_extract:
|
|
|
|
mock_parse.return_value = ("<html></html>", {})
|
|
|
|
# socid_extractor returned a URL under the bare `username` key
|
|
mock_extract.return_value = {"username": "https://instagram.com/zuck"}
|
|
|
|
result = extract_ids_from_page(
|
|
"https://example.com/profile",
|
|
logger,
|
|
timeout=5,
|
|
)
|
|
|
|
assert result == {}
|
|
|
|
|
|
def test_extract_ids_from_page_keeps_other_supported_ids():
|
|
logger = Mock()
|
|
|
|
with patch("maigret.maigret.parse") as mock_parse, \
|
|
patch("maigret.maigret.extract") as mock_extract:
|
|
|
|
mock_parse.return_value = ("<html></html>", {})
|
|
mock_extract.return_value = {
|
|
"gaia_id": "123456789",
|
|
"profile_username": "emily",
|
|
}
|
|
|
|
result = extract_ids_from_page(
|
|
"https://example.com/profile",
|
|
logger,
|
|
timeout=5,
|
|
)
|
|
|
|
assert result == {"123456789": "gaia_id", "emily": "username"}
|