def test_write_database(tmp_path, mini_testsuite, empty_alt_testsuite):
tmp_ts = tmp_path.joinpath('test_write_database')
db = tsdb.Database(mini_testsuite)
tsdb.write_database(db, str(tmp_ts))
assert tmp_ts.is_dir()
assert tmp_ts.joinpath('relations').is_file()
assert tmp_ts.joinpath('item').is_file()
assert tmp_ts.joinpath('parse').is_file()
assert tmp_ts.joinpath('result').is_file()
assert tmp_ts.joinpath('parse').read_text() == (
'10@10@1\n'
'20@20@0\n'
'30@30@1\n')
tsdb.write_database(db, str(tmp_ts), names=['item'])
assert tmp_ts.joinpath('item').is_file()
assert not tmp_ts.joinpath('parse').is_file()
assert not tmp_ts.joinpath('result').is_file()
# alt_schema drops i-wf field from mini_testsuite's schema
alt_schema = tsdb.read_schema(empty_alt_testsuite)
tsdb.write_database(db, str(tmp_ts), names=['item'], schema=alt_schema)
alt_db = tsdb.Database(str(tmp_ts))
assert len(db.schema['item']) == 4
assert len(alt_db.schema['item']) == 3
assert tmp_ts.joinpath('item').read_text() == (
'10@It rained.@1-feb-2018 15:00\n'
'20@Rained.@01-02-18 15:00:00\n'
'30@It snowed.@2018-2-1 (15:00:00)\n')
def test_init(self, tmp_path, mini_testsuite):
with pytest.raises(TypeError):
tsdb.Database()
with pytest.raises(tsdb.TSDBError):
dir = tmp_path.joinpath('not_a_testsuite')
dir.mkdir()
tsdb.Database(str(dir))
tsdb.Database(mini_testsuite)
def test__getitem__(self, mini_testsuite, empty_testsuite):
db = tsdb.Database(mini_testsuite)
assert list(db['item']) == [
('10', 'It rained.', '1', '1-feb-2018 15:00'),
('20', 'Rained.', '0', '01-02-18 15:00:00'),
('30', 'It snowed.', '1', '2018-2-1 (15:00:00)'),
]
# with autocast
db.autocast = True
assert list(db['item']) == [
(10, 'It rained.', 1, datetime(2018, 2, 1, 15, 0)),
(20, 'Rained.', 0, datetime(2018, 2, 1, 15, 0)),
(30, 'It snowed.', 1, datetime(2018, 2, 1, 15, 0)),
]
# relation undefined
with pytest.raises(tsdb.TSDBError):
db['not_a_relation']
# relation defined by file missing
db = tsdb.Database(empty_testsuite)
with pytest.raises(tsdb.TSDBError):
db['item']
def test_bad_date_issue_279(tmp_path, empty_alt_testsuite):
tmp_ts = tmp_path.joinpath('test_bad_date_issue_279')
tmp_ts.mkdir()
schema = tsdb.read_schema(empty_alt_testsuite)
fields = schema['item']
tsdb.write_schema(tmp_ts, schema)
tsdb.write(tmp_ts, 'item', [(0, 'The cat meows.', datetime(1999, 9, 8))],
fields)
db = tsdb.Database(tmp_ts)
assert list(db['item']) == [('0', 'The cat meows.', '8-sep-1999')]
tsdb.write(tmp_ts, 'item', [(0, 'The cat meows.', 'September 8, 1999')],
fields)
assert list(db['item']) == [('0', 'The cat meows.', 'September 8, 1999')]
def select(query: str, path: util.PathLike, record_class=None):
"""
Select data from [incr tsdb()] test suites.
Args:
query (str): TSQL select query (e.g., `'i-id i-input mrs'` or
`'* from item where readings > 0'`)
path: path to a TSDB test suite
record_class: alternative class for records in the selection
Yields:
selected data from the test suite
"""
db = tsdb.Database(path, autocast=True)
return tsql.select(query, db, record_class=record_class)
def update_test(args):
"""
Use the current test profile to the gold.
"""
tests = list(_discover(args))
if len(tests) != 1:
raise RegressionTestError('only 1 test may be updated at a time')
name, idx, chc, txt, skel, prof, gold = tests[0]
try:
db = tsdb.Database(prof)
tsdb.write_database(db, gold)
except tsdb.TSDBError as exc:
raise RegressionTestError('Failed to update gold.') from exc
def _read(path, source_codec, select, kwargs):
if hasattr(path, 'read'):
xs = list(source_codec.load(path, **kwargs))
else:
path = Path(path).expanduser()
if path.is_dir():
db = tsdb.Database(path)
# ts = itsdb.TestSuite(path)
xs = [
next(iter(source_codec.loads(r[0], **kwargs)), None)
for r in tsql.select(select, db)
]
else:
xs = list(source_codec.load(path, **kwargs))
yield from xs
def test_select_from(self, mini_testsuite):
db = tsdb.Database(mini_testsuite)
fields = ('i-id', 'i-date')
assert list(db.select_from('item', fields)) == [
('10', '1-feb-2018 15:00'),
('20', '01-02-18 15:00:00'),
('30', '2018-2-1 (15:00:00)'),
]
assert list(db.select_from('item', fields, cast=True)) == [
(10, datetime(2018, 2, 1, 15, 0)),
(20, datetime(2018, 2, 1, 15, 0)),
(30, datetime(2018, 2, 1, 15, 0)),
]
db.autocast = True
assert list(db.select_from('item', fields)) == [
(10, datetime(2018, 2, 1, 15, 0)),
(20, datetime(2018, 2, 1, 15, 0)),
(30, datetime(2018, 2, 1, 15, 0)),
]
assert list(db.select_from('item', fields, cast=True)) == [
(10, datetime(2018, 2, 1, 15, 0)),
(20, datetime(2018, 2, 1, 15, 0)),
(30, datetime(2018, 2, 1, 15, 0)),
]
def test_path(self, mini_testsuite):
db = tsdb.Database(mini_testsuite)
assert db.path == pathlib.Path(mini_testsuite)
def mkprof(destination, source=None, schema=None, where=None, delimiter=None,
refresh=False, skeleton=False, full=False, gzip=False, quiet=False):
"""
Create [incr tsdb()] profiles or skeletons.
Data for the testsuite may come from an existing testsuite or from
a list of sentences. There are four main usage patterns:
- `source="testsuite/"` -- read data from `testsuite/`
- `source=None, refresh=True` -- read data from *destination*
- `source=None, refresh=False` -- read sentences from stdin
- `source="sents.txt"` -- read sentences from `sents.txt`
The latter two require the *schema* parameter.
Args:
destination (str): path of the new testsuite
source (str): path to a source testsuite or a file containing
sentences; if not given and *refresh* is `False`, sentences
are read from stdin
schema (str): path to a relations file to use for the created
testsuite; if `None` and *source* is a test suite, the
schema of *source* is used
where (str): TSQL condition to filter records by; ignored if
*source* is not a testsuite
delimiter (str): if given, split lines from *source* or stdin
on the character *delimiter*; if *delimiter* is `"@"`,
split using :func:`delphin.tsdb.split`; a header line
with field names is required; ignored when the data source
is not text lines
refresh (bool): if `True`, rewrite the data at *destination*;
implies *full* is `True`; ignored if *source* is not
`None`, best combined with *schema* or *gzip* (default:
`False`)
skeleton (bool): if `True`, only write tsdb-core files
(default: `False`)
full (bool): if `True`, copy all data from the source
testsuite; ignored if the data source is not a testsuite
or if *skeleton* is `True` (default: `False`)
gzip (bool): if `True`, non-empty tables will be compressed
with gzip
quiet (bool): if `True`, don't print summary information
"""
destination = Path(destination).expanduser()
if source is not None:
source = Path(source).expanduser()
if schema is not None:
schema = tsdb.read_schema(schema)
old_relation_files = []
# work in-place on destination test suite
if source is None and refresh:
db = tsdb.Database(destination)
old_relation_files = list(db.schema)
tsdb.write_database(db, db.path, schema=schema, gzip=gzip)
# input is sentences on stdin or a file of sentences
elif source is None and not refresh:
_mkprof_from_lines(
destination, sys.stdin, schema, delimiter, gzip)
elif source.is_file():
with source.open() as fh:
_mkprof_from_lines(
destination, fh, schema, delimiter, gzip)
# input is source testsuite
elif source.is_dir():
db = tsdb.Database(source)
old_relation_files = list(db.schema)
_mkprof_from_database(
destination, db, schema, where, full, gzip)
else:
raise CommandError(f'invalid source for mkprof: {source!s}')
_mkprof_cleanup(destination, skeleton, old_relation_files)
if not quiet:
_mkprof_summarize(destination, tsdb.read_schema(destination))
