def execute(cls, options):
options = cls.handle_options(options)
try:
if options.extract:
MySQLExtractor(options).extract()
if options.load:
MediawikiLoader(options).load()
finally:
if not options.keep_dumps:
shutil.rmtree(options.dump_dir)
def setUp(self):
setup_basic_test()
self.options = mock.Mock()
self.options.dump_dir = os.path.join(g.tmpdir, 'w2m_test')
# monkey-patch MySQLExtractor for test
def pages(self):
yield {'page_id': 1, 'title': 'Test title'}
yield {'page_id': 2, 'title': 'Main_Page'}
yield {'page_id': 3, 'title': 'Test'}
def history(self, page_id):
data = {
1: [{
'timestamp': 1,
'text': "Test",
'username': '******'
}, {
'timestamp': 2,
'text': "Test Text",
'username': '******'
}],
2: [{
'timestamp': 1,
'text': "Main_Page",
'username': '******'
}, {
'timestamp': 2,
'text': "Main_Page text",
'username': '******'
}],
3: [{
'timestamp': 1,
'text': "Some test text",
'username': ''
}, {
'timestamp': 2,
'text': "",
'username': ''
}]
}
revisions = data[page_id]
for rev in revisions:
yield rev
def talk(self, page_title):
return {
'text': 'Talk for page %s.' % page_title,
'timestamp': 1,
'username': '******'
}
def attachments(self, *args, **kwargs):
# make 'empty' iterator
if False:
yield
MySQLExtractor._pages = pages
MySQLExtractor._history = history
MySQLExtractor._talk = talk
MySQLExtractor._attachments = attachments
self.extractor = MySQLExtractor(self.options)
