def synthesis(prepare_res, params):
dw_passed, _ = prepare_res
# Using set_slice on a dataset that was written in analysis is not
# actually supported, but since it currently works (as long as that
# particular slice wasn't written in analysis) let's test it.
dw_passed.set_slice(0)
dw_passed.write(**{k: v[0] for k, v in test_data.data.items()})
dw_synthesis_split = DatasetWriter(name="synthesis_split", hashlabel="a")
dw_synthesis_split.add("a", "int32")
dw_synthesis_split.add("b", "unicode")
dw_synthesis_split.get_split_write()(1, "a")
dw_synthesis_split.get_split_write_list()([2, "b"])
dw_synthesis_split.get_split_write_dict()({"a": 3, "b": "c"})
dw_synthesis_manual = DatasetWriter(name="synthesis_manual",
columns={"sliceno": "int32"})
dw_nonetest = DatasetWriter(name="nonetest",
columns={t: t
for t in test_data.data})
for sliceno in range(params.slices):
dw_synthesis_manual.set_slice(sliceno)
dw_synthesis_manual.write(sliceno)
dw_nonetest.set_slice(sliceno)
dw_nonetest.write(
**{
k: v[0] if k in test_data.not_none_capable else None
for k, v in test_data.data.items()
})
def _verify(name, types, data, coltype, want, default, want_fail, kw):
if callable(want):
check = want
else:
def check(got, fromstr, filtered=False):
want1 = want if isinstance(want, list) else want[typ]
if filtered:
want1 = want1[::2]
assert got == want1, 'Expected %r, got %r from %s.' % (
want1,
got,
fromstr,
)
dw = DatasetWriter(name=name, columns={'data': coltype, 'extra': 'bytes'})
dw.set_slice(0)
for ix, v in enumerate(data):
dw.write(v, b'1' if ix % 2 == 0 else b'skip')
for sliceno in range(1, g.SLICES):
dw.set_slice(sliceno)
bytes_ds = dw.finish()
for typ in types:
opts = dict(column2type=dict(data=typ))
opts.update(kw)
if default is not no_default:
opts['defaults'] = {'data': default}
try:
jid = subjobs.build('dataset_type',
datasets=dict(source=bytes_ds),
options=opts)
except JobError:
if want_fail:
continue
raise Exception('Typing %r as %s failed.' % (
bytes_ds,
typ,
))
assert not want_fail, "Typing %r as %s should have failed, but didn't (%s)." % (
bytes_ds, typ, jid)
typed_ds = Dataset(jid)
got = list(typed_ds.iterate(0, 'data'))
check(got, '%s (typed as %s from %r)' % (
typed_ds,
typ,
bytes_ds,
))
if 'filter_bad' not in opts and not callable(want):
opts['filter_bad'] = True
opts['column2type']['extra'] = 'int32_10'
jid = subjobs.build('dataset_type',
datasets=dict(source=bytes_ds),
options=opts)
typed_ds = Dataset(jid)
got = list(typed_ds.iterate(0, 'data'))
check(
got,
'%s (typed as %s from %r with every other line skipped from filter_bad)'
% (
typed_ds,
typ,
bytes_ds,
), True)
used_type(typ)
def test_filter_bad_across_types():
columns = {
'bytes': 'bytes',
'float64': 'bytes',
'int32_10': 'ascii',
'json': 'unicode',
'number:int': 'unicode',
'unicode:utf-8': 'bytes',
}
# all_good, *values
# Make sure all those types (except bytes) can filter other lines,
# and be filtered by other lines. And that several filtering values
# is not a problem (line 11).
data = [
(
True,
b'first',
b'1.1',
'1',
'"a"',
'001',
b'ett',
),
(
True,
b'second',
b'2.2',
'2',
'"b"',
'02',
b'tv\xc3\xa5',
),
(
True,
b'third',
b'3.3',
'3',
'["c"]',
'3.0',
b'tre',
),
(
False,
b'fourth',
b'4.4',
'4',
'"d"',
'4.4',
b'fyra',
), # number:int bad
(
False,
b'fifth',
b'5.5',
'-',
'"e"',
'5',
b'fem',
), # int32_10 bad
(
False,
b'sixth',
b'6.b',
'6',
'"f"',
'6',
b'sex',
), # float64 bad
[
False,
b'seventh',
b'7.7',
'7',
'{"g"}',
'7',
b'sju',
], # json bad
(
False,
b'eigth',
b'8.8',
'8',
'"h"',
'8',
b'\xa5\xc3tta',
), # unicode:utf-8 bad
(
True,
b'ninth',
b'9.9',
'9',
'"i"',
'9',
b'nio',
),
(
True,
b'tenth',
b'10',
'10',
'"j"',
'10',
b'tio',
),
(
False,
b'eleventh',
b'11a',
'1-',
'"k",',
'1,',
b'elva',
), # float64, int32_10 and number:int bad
(
True,
b'twelfth',
b'12',
'12',
'"l"',
'12',
b'tolv',
),
]
dw = DatasetWriter(name="filter bad across types", columns=columns)
dw.set_slice(0)
want = []
def add_want(v):
want.append((
int(v[3]),
v[1],
json.loads(v[4]),
v[6].decode('utf-8'),
))
for v in data:
if v[0]:
add_want(v)
dw.write(*v[1:])
for sliceno in range(1, g.SLICES):
dw.set_slice(sliceno)
source_ds = dw.finish()
# Once with just filter_bad, once with some defaults too.
defaults = {}
for _ in range(2):
jid = subjobs.build(
'dataset_type',
datasets=dict(source=source_ds),
options=dict(column2type={t: t
for t in columns},
filter_bad=True,
defaults=defaults),
)
typed_ds = Dataset(jid)
got = list(
typed_ds.iterate(0,
['int32_10', 'bytes', 'json', 'unicode:utf-8']))
assert got == want, "Exptected %r, got %r from %s (from %r%s)" % (
want, got, typed_ds, source_ds,
' with defaults' if defaults else '')
# make more lines "ok" for the second lap
defaults = {'number:int': '0', 'float64': '0', 'json': '"replacement"'}
add_want(data[3])
add_want(data[5])
data[6][4] = '"replacement"'
add_want(data[6])
want.sort() # adding them out of order, int32_10 sorts correctly.
def do_one(params, name, data):
dw = DatasetWriter(name=name, columns=columns)
dw.set_slice(0)
for v in data:
if v is None:
d = dict(
ascii_new=None,
ascii_old=None,
bytes_new=None,
bytes_old=None,
unicode_new=None,
unicode_old=None,
)
else:
d = dict(
ascii_new=v,
ascii_old=v,
bytes_new=uni(v).encode("ascii"),
bytes_old=uni(v).encode("ascii"),
unicode_new=uni(v),
unicode_old=uni(v),
)
dw.write_dict(d)
# We don't really want the other slices, but write one thing to
# each, to make sure it doesn't show up in slice 0.
# (Small slice merging will put it in the same file, so this is
# a real risk.)
for sliceno in range(1, params.slices):
dw.set_slice(sliceno)
dw.write_dict(d)
dw.finish()
# verify we got what we asked for
me_ds = Dataset(params.jobid, name)
for colname, coltype in columns.items():
col = me_ds.columns[colname]
assert col.type == coltype.split("_")[-1], colname
assert col.backing_type == coltype, colname
for want, got in zip(data, me_ds.iterate(0, colname)):
if want is not None:
if PY2 and "unicode" in coltype:
want = uni(want)
if PY3 and "bytes" in coltype:
want = want.encode("ascii")
assert want == got, "%s in %s did not contain the expected value. Wanted %r but got %r." % (colname, me_ds, want, got)
# check that both types of bytes filter correctly through typing
jid = subjobs.build("dataset_type", datasets=dict(source=me_ds), options=dict(
column2type=dict(
ascii_new="bytes",
ascii_old="number", # fails on the string, so that gets filtered out everywhere
bytes_new="bytes",
bytes_old="bytes",
),
filter_bad=True,
))
ds = Dataset(jid)
# verify the number first
data_it = iter(raw_data)
next(data_it) # skip the filtered out string
for got in ds.iterate(0, "ascii_old"):
want = next(data_it)
if want is None:
# Becomes 0 because the typer (unfortunately) sees it as an empty string
want = 0
assert want == got, "ascii_old in %s did not type correctly as number. Wanted %r but got %r." % (ds, want, got)
# now verify all the bytes ones are ok, no longer containing the string.
for colname in ("ascii_new", "bytes_new", "bytes_old",):
data_it = iter(data)
next(data_it) # skip the filtered out string
for got in ds.iterate(0, colname):
want = next(data_it)
if want is not None:
want = want.encode("ascii")
assert want == got, "%s in %s did not roundtrip correctly as bytes. Wanted %r but got %r." % (colname, ds, want, got)
# and now check that the Nones are ok after making bytes from ascii and unicode from bytes.
jid = subjobs.build("dataset_type", datasets=dict(source=me_ds), options=dict(
column2type=dict(
ascii_new="bytes",
ascii_old="bytes",
bytes_new="unicode:ascii",
bytes_old="unicode:ascii",
),
))
ds = Dataset(jid)
for colname in ("ascii_new", "ascii_old", "bytes_new", "bytes_old",):
for want, got in ds.iterate(0, ["unicode_new", colname]):
assert uni(want) == uni(got), "%s in %s did not roundtrip correctly as bytes. Wanted %r but got %r." % (colname, ds, want, got)