Files
arc53--docsgpt/tests/parser/file/test_html_parser.py
T
wehub-resource-sync fed8b2eed7
Backend release / release (push) Waiting to run
Bandit Security Scan / bandit_scan (push) Waiting to run
Build and push multi-arch DocsGPT Docker image / build (linux/amd64, ubuntu-latest, amd64) (push) Waiting to run
Build and push multi-arch DocsGPT Docker image / build (linux/arm64, ubuntu-24.04-arm, arm64) (push) Waiting to run
Build and push multi-arch DocsGPT Docker image / manifest (push) Blocked by required conditions
Build and push DocsGPT FE Docker image for development / build (linux/amd64, ubuntu-latest, amd64) (push) Waiting to run
Build and push DocsGPT FE Docker image for development / build (linux/arm64, ubuntu-24.04-arm, arm64) (push) Waiting to run
Build and push DocsGPT FE Docker image for development / manifest (push) Blocked by required conditions
Python linting / ruff (push) Waiting to run
Run python tests with pytest / Run tests and count coverage (3.12) (push) Waiting to run
React Widget Build / build (push) Waiting to run
chore: import upstream snapshot with attribution
2026-07-13 13:28:29 +08:00

44 lines
1.2 KiB
Python

import pytest
from pathlib import Path
from unittest.mock import patch, MagicMock
import sys
import types
from application.parser.file.html_parser import HTMLParser
@pytest.fixture
def html_parser():
return HTMLParser()
def test_html_init_parser():
parser = HTMLParser()
assert isinstance(parser._init_parser(), dict)
assert not parser.parser_config_set
parser.init_parser()
assert parser.parser_config_set
def test_html_parser_parse_file():
parser = HTMLParser()
mock_doc = MagicMock()
mock_doc.page_content = "Extracted HTML content"
mock_doc.metadata = {"source": "test.html"}
fake_lc = types.ModuleType("langchain_community")
fake_dl = types.ModuleType("langchain_community.document_loaders")
bshtml_mock = MagicMock(return_value=MagicMock(load=MagicMock(return_value=[mock_doc])))
fake_dl.BSHTMLLoader = bshtml_mock
fake_lc.document_loaders = fake_dl
with patch.dict(sys.modules, {
"langchain_community": fake_lc,
"langchain_community.document_loaders": fake_dl,
}):
result = parser.parse_file(Path("test.html"))
assert result == [mock_doc]
bshtml_mock.assert_called_once_with(Path("test.html"))