def test_matched_query_text_tokenizer_works_with_spdx_ids(self):
text = u''' * SPDX-License-Identifier: GPL-2.0+ BSD-3-Clause
* SPDX-License-Identifier: (BSD-3-Clause OR EPL-1.0 OR Apache-2.0 OR MIT)
'''
result = list(matched_query_text_tokenizer(text))
expected = [(False, u' * '), (True, u'SPDX'), (False, u'-'),
(True, u'License'), (False, u'-'), (True, u'Identifier'),
(False, u': '),
(True, u'GPL'), (False, u'-'), (True, u'2'), (False, u'.'),
(True, u'0+'), (False, u' '), (True, u'BSD'),
(False, u'-'), (True, u'3'), (False, u'-'),
(True, u'Clause'), (False, u'\n * '),
(True, u'SPDX'), (False, u'-'), (True, u'License'),
(False, u'-'), (True, u'Identifier'), (False, u': ('),
(True, u'BSD'), (False, u'-'), (True, u'3'), (False, u'-'),
(True, u'Clause'), (False, u' '), (True, u'OR'),
(False, u' '), (True, u'EPL'), (False, u'-'), (True, u'1'),
(False, u'.'), (True, u'0'), (False, u' '), (True, u'OR'),
(False, u' '), (True, u'Apache'), (False, u'-'),
(True, u'2'), (False, u'.'), (True, u'0'), (False, u' '),
(True, u'OR'), (False, u' '), (True, u'MIT'),
(False, u')\n ')]
assert result == expected
result_as_text = u''.join(
itertools.chain.from_iterable(
[v for v in m.groupdict().values() if v]
for m in tokens_and_non_tokens(text)))
assert result_as_text == text
def test_tokens_and_non_tokens_yield_properly_all_texts(self):
text = u'''Redistribution+ ;and use in! + 2003 source and +binary forms,
()with or without modifi+cation, are permitted with İrəli .\t\n
\r'''
result = [m.groupdict() for m in tokens_and_non_tokens(text)]
expected = [
{'punct': None, 'token': 'Redistribution+'},
{'punct': ' ;', 'token': None},
{'punct': None, 'token': 'and'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'use'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'in'},
{'punct': '! + ', 'token': None},
{'punct': None, 'token': '2003'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'source'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'and'},
{'punct': ' +', 'token': None},
{'punct': None, 'token': 'binary'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'forms'},
{'punct': ',\n ()', 'token': None},
{'punct': None, 'token': 'with'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'or'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'without'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'modifi+cation'},
{'punct': ', ', 'token': None},
{'punct': None, 'token': 'are'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'permitted'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'with'},
{'punct': ' ', 'token': None},
{'punct': None, 'token': 'İrəli'},
{'punct': ' .\t\n\n \r', 'token': None}
]
assert result == expected
result_as_text = u''.join(itertools.chain.from_iterable(
[v for v in m.groupdict().values() if v] for m in tokens_and_non_tokens(text)))
assert result_as_text == text
def test_tokens_and_non_tokens_yield_properly_all_texts(self):
text = u'''Redistribution+ ;and use in! 2003 source and binary forms,
()with or without modification, are permitted.\t\n
\r'''
result = [m.groupdict() for m in tokens_and_non_tokens(text)]
expected = [
{u'punct': None, u'token': u'Redistribution+'},
{u'punct': u' ;', u'token': None},
{u'punct': None, u'token': u'and'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'use'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'in'},
{u'punct': u'! ', u'token': None},
{u'punct': None, u'token': u'2003'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'source'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'and'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'binary'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'forms'},
{u'punct': u', \n ()', u'token': None},
{u'punct': None, u'token': u'with'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'or'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'without'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'modification'},
{u'punct': u', ', u'token': None},
{u'punct': None, u'token': u'are'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'permitted'},
{u'punct': u'.\t\n\n \r', u'token': None}
]
assert expected == result
result_as_text = u''.join(itertools.chain.from_iterable([v for v in m.groupdict().values() if v] for m in tokens_and_non_tokens(text)))
assert text == result_as_text
def test_tokens_and_non_tokens_yield_properly_all_texts(self):
text = u'''Redistribution+ ;and use in! 2003 source and binary forms,
()with or without modification, are permitted.\t\n
\r'''
result = [m.groupdict() for m in tokens_and_non_tokens(text)]
expected = [
{u'punct': None, u'token': u'Redistribution+'},
{u'punct': u' ;', u'token': None},
{u'punct': None, u'token': u'and'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'use'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'in'},
{u'punct': u'! ', u'token': None},
{u'punct': None, u'token': u'2003'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'source'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'and'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'binary'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'forms'},
{u'punct': u', \n ()', u'token': None},
{u'punct': None, u'token': u'with'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'or'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'without'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'modification'},
{u'punct': u', ', u'token': None},
{u'punct': None, u'token': u'are'},
{u'punct': u' ', u'token': None},
{u'punct': None, u'token': u'permitted'},
{u'punct': u'.\t\n\n \r', u'token': None}
]
assert expected == result
result_as_text = u''.join(itertools.chain.from_iterable([v for v in m.groupdict().values() if v] for m in tokens_and_non_tokens(text)))
assert text == result_as_text
