Telethon/tests/telethon/extensions/test_html.py
2020-02-20 10:53:28 +01:00

66 lines
2.3 KiB
Python
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""
Tests for `telethon.extensions.html`.
"""
from telethon.extensions import html
from telethon.tl.types import MessageEntityBold, MessageEntityItalic, MessageEntityTextUrl
def test_entity_edges():
"""
Test that entities at the edges (start and end) don't crash.
"""
text = 'Hello, world'
entities = [MessageEntityBold(0, 5), MessageEntityBold(7, 5)]
result = html.unparse(text, entities)
assert result == '<strong>Hello</strong>, <strong>world</strong>'
def test_malformed_entities():
"""
Test that malformed entity offsets from bad clients
don't crash and produce the expected results.
"""
text = '🏆Telegram Official Android Challenge is over🏆.'
entities = [MessageEntityTextUrl(offset=2, length=43, url='https://example.com')]
result = html.unparse(text, entities)
assert result == '🏆<a href="https://example.com">Telegram Official Android Challenge is over</a>🏆.'
def test_trailing_malformed_entities():
"""
Similar to `test_malformed_entities`, but for the edge
case where the malformed entity offset is right at the end
(note the lack of a trailing dot in the text string).
"""
text = '🏆Telegram Official Android Challenge is over🏆'
entities = [MessageEntityTextUrl(offset=2, length=43, url='https://example.com')]
result = html.unparse(text, entities)
assert result == '🏆<a href="https://example.com">Telegram Official Android Challenge is over</a>🏆'
def test_entities_together():
"""
Test that an entity followed immediately by a different one behaves well.
"""
original = '<strong>⚙️</strong><em>Settings</em>'
stripped = 'Settings'
text, entities = html.parse(original)
assert text == stripped
assert entities == [MessageEntityBold(0, 2), MessageEntityItalic(2, 8)]
text = html.unparse(text, entities)
assert text == original
def test_offset_at_emoji():
"""
Tests that an entity starting at a emoji preserves the emoji.
"""
text = 'Hi\n👉 See example'
entities = [MessageEntityBold(0, 2), MessageEntityItalic(3, 2), MessageEntityBold(10, 7)]
parsed = '<strong>Hi</strong>\n<em>👉</em> See <strong>example</strong>'
assert html.parse(parsed) == (text, entities)
assert html.unparse(text, entities) == parsed