def just_draw_columns(draw):
index = draw(index_strategy)
local_index_strategy = st.just(index)
data = OrderedDict((c.name, None) for c in rewritten_columns)
# Depending on how the columns are going to be generated we group
# them differently to get better shrinking. For columns with fill
# enabled, the elements can be shrunk independently of the size,
# so we can just shrink by shrinking the index then shrinking the
# length and are generally much more free to move data around.
# For columns with no filling the problem is harder, and drawing
# them like that would result in rows being very far apart from
# each other in the underlying data stream, which gets in the way
# of shrinking. So what we do is reorder and draw those columns
# row wise, so that the values of each row are next to each other.
# This makes life easier for the shrinker when deleting blocks of
# data.
columns_without_fill = [
c for c in rewritten_columns if c.fill.is_empty
]
if columns_without_fill:
for c in columns_without_fill:
data[c.name] = pandas.Series(np.zeros(shape=len(index),
dtype=c.dtype),
index=index)
seen = {
c.name: set()
for c in columns_without_fill if c.unique
}
for i in range(len(index)):
for c in columns_without_fill:
if c.unique:
for _ in range(5):
value = draw(c.elements)
if value not in seen[c.name]:
seen[c.name].add(value)
break
else:
reject()
else:
value = draw(c.elements)
data[c.name][i] = value
for c in rewritten_columns:
if not c.fill.is_empty:
data[c.name] = draw(
series(
index=local_index_strategy,
dtype=c.dtype,
elements=c.elements,
fill=c.fill,
unique=c.unique,
))
return pandas.DataFrame(data, index=index)
def urls() -> SearchStrategy[str]:
"""A strategy for :rfc:`3986`, generating http/https URLs."""
def url_encode(s):
return "".join(c if c in URL_SAFE_CHARACTERS else "%%%02X" % ord(c)
for c in s)
schemes = st.sampled_from(["http", "https"])
ports = st.integers(min_value=0, max_value=2**16 - 1).map(":{}".format)
paths = st.lists(st.text(string.printable).map(url_encode)).map("/".join)
return st.builds("{}://{}{}/{}".format, schemes, domains(),
st.just("") | ports, paths)
def dates(min_value: dt.date = dt.date.min,
max_value: dt.date = dt.date.max) -> SearchStrategy[dt.date]:
"""dates(min_value=datetime.date.min, max_value=datetime.date.max)
A strategy for dates between ``min_value`` and ``max_value``.
Examples from this strategy shrink towards January 1st 2000.
"""
check_type(dt.date, min_value, "min_value")
check_type(dt.date, max_value, "max_value")
check_valid_interval(min_value, max_value, "min_value", "max_value")
if min_value == max_value:
return just(min_value)
return DateStrategy(min_value, max_value)
def timedeltas(
min_value: dt.timedelta = dt.timedelta.min,
max_value: dt.timedelta = dt.timedelta.max,
) -> SearchStrategy[dt.timedelta]:
"""timedeltas(min_value=datetime.timedelta.min, max_value=datetime.timedelta.max)
A strategy for timedeltas between ``min_value`` and ``max_value``.
Examples from this strategy shrink towards zero.
"""
check_type(dt.timedelta, min_value, "min_value")
check_type(dt.timedelta, max_value, "max_value")
check_valid_interval(min_value, max_value, "min_value", "max_value")
if min_value == max_value:
return just(min_value)
return TimedeltaStrategy(min_value=min_value, max_value=max_value)
