Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

allow datetime object to be provided for temporal queries #451

Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 27 additions & 20 deletions earthaccess/search.py
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
import datetime as dt
from inspect import getmembers, ismethod
from typing import Any, Dict, List, Optional, Tuple, Type
from typing import Any, Dict, List, Optional, Tuple, Type, Union

import dateutil.parser as parser # type: ignore
from cmr import CollectionQuery, GranuleQuery # type: ignore
Expand Down Expand Up @@ -262,31 +262,36 @@ def get(self, limit: int = 2000) -> list:
return results

def temporal(
self, date_from: str, date_to: str, exclude_boundary: bool = False
self,
date_from: Optional[Union[str, dt.datetime]] = None,
date_to: Optional[Union[str, dt.datetime]] = None,
exclude_boundary: bool = False,
) -> Type[CollectionQuery]:
"""Filter by an open or closed date range. Dates can be provided as datetime objects
or ISO 8601 formatted strings. Multiple ranges can be provided by successive calls.
to this method before calling execute().

Parameters:
date_from (String): earliest date of temporal range
date_to (string): latest date of temporal range
date_from (String or Datetime object): earliest date of temporal range
date_to (String or Datetime object): latest date of temporal range
exclude_boundary (Boolean): whether or not to exclude the date_from/to in the matched range
"""
DEFAULT = dt.datetime(1979, 1, 1)
if date_from is not None:
if date_from is not None and not isinstance(date_from, dt.datetime):
try:
parsed_from = parser.parse(date_from, default=DEFAULT).isoformat() + "Z"
date_from = parser.parse(date_from, default=DEFAULT).isoformat() + "Z"
except Exception:
print("The provided start date was not recognized")
parsed_from = ""
if date_to is not None:
date_from = ""

if date_to is not None and not isinstance(date_to, dt.datetime):
try:
parsed_to = parser.parse(date_to, default=DEFAULT).isoformat() + "Z"
date_to = parser.parse(date_to, default=DEFAULT).isoformat() + "Z"
except Exception:
print("The provided end date was not recognized")
parsed_to = ""
super().temporal(parsed_from, parsed_to, exclude_boundary)
date_to = ""

super().temporal(date_from, date_to, exclude_boundary)
return self


Expand Down Expand Up @@ -614,8 +619,8 @@ def debug(self, debug: bool = True) -> Type[GranuleQuery]:

def temporal(
self,
date_from: Optional[str] = None,
date_to: Optional[str] = None,
date_from: Optional[Union[str, dt.datetime]] = None,
date_to: Optional[Union[str, dt.datetime]] = None,
exclude_boundary: bool = False,
) -> Type[GranuleQuery]:
"""Filter by an open or closed date range.
Expand All @@ -628,19 +633,21 @@ def temporal(
exclude_boundary (Boolean): whether or not to exclude the date_from/to in the matched range
"""
DEFAULT = dt.datetime(1979, 1, 1)
if date_from is not None:
if date_from is not None and not isinstance(date_from, dt.datetime):
try:
parsed_from = parser.parse(date_from, default=DEFAULT).isoformat() + "Z"
date_from = parser.parse(date_from, default=DEFAULT).isoformat() + "Z"
except Exception:
print("The provided start date was not recognized")
parsed_from = ""
if date_to is not None:
date_from = ""

if date_to is not None and not isinstance(date_to, dt.datetime):
try:
parsed_to = parser.parse(date_to, default=DEFAULT).isoformat() + "Z"
date_to = parser.parse(date_to, default=DEFAULT).isoformat() + "Z"
except Exception:
print("The provided end date was not recognized")
parsed_to = ""
super().temporal(parsed_from, parsed_to, exclude_boundary)
date_to = ""

super().temporal(date_from, date_to, exclude_boundary)
return self

def version(self, version: str = "") -> Type[GranuleQuery]:
Expand Down
36 changes: 36 additions & 0 deletions tests/unit/test_collection_queries.py
Original file line number Diff line number Diff line change
@@ -1,6 +1,26 @@
# package imports
import datetime as dt

import pytest
from earthaccess.search import DataCollections

valid_single_dates = [
("2001-12-12", "2001-12-21", "2001-12-12T00:00:00Z,2001-12-21T00:00:00Z"),
("2021-02-01", "", "2021-02-01T00:00:00Z,"),
("1999-02-01 06:00", "2009-01-01", "1999-02-01T06:00:00Z,2009-01-01T00:00:00Z"),
(
dt.datetime(2021, 2, 1),
betolink marked this conversation as resolved.
Show resolved Hide resolved
dt.datetime(2021, 2, 2),
"2021-02-01T00:00:00Z,2021-02-02T00:00:00Z",
),
]

invalid_single_dates = [
("2001-12-45", "2001-12-21", None),
("2021w1", "", None),
("2999-02-01", "2009-01-01", None),
]


def test_query_can_find_cloud_provider():
query = DataCollections().daac("PODAAC").cloud_hosted(True)
Expand All @@ -18,3 +38,19 @@ def test_querybuilder_can_handle_doi():
assert query.params["doi"] == doi
query = DataCollections().cloud_hosted(True).daac("PODAAC").doi(doi)
assert query.params["doi"] == doi


@pytest.mark.parametrize("start,end,expected", valid_single_dates)
def test_query_can_parse_single_dates(start, end, expected):
query = DataCollections().temporal(start, end)
assert query.params["temporal"][0] == expected


@pytest.mark.parametrize("start,end,expected", invalid_single_dates)
def test_query_can_handle_invalid_dates(start, end, expected):
query = DataCollections()
try:
query = query.temporal(start, end)
except Exception as e:
assert isinstance(e, ValueError)
assert "temporal" not in query.params
7 changes: 7 additions & 0 deletions tests/unit/test_granule_queries.py
Original file line number Diff line number Diff line change
@@ -1,11 +1,18 @@
# package imports
import datetime as dt

import pytest
from earthaccess.search import DataGranules

valid_single_dates = [
("2001-12-12", "2001-12-21", "2001-12-12T00:00:00Z,2001-12-21T00:00:00Z"),
("2021-02-01", "", "2021-02-01T00:00:00Z,"),
("1999-02-01 06:00", "2009-01-01", "1999-02-01T06:00:00Z,2009-01-01T00:00:00Z"),
(
dt.datetime(2021, 2, 1),
dt.datetime(2021, 2, 2),
"2021-02-01T00:00:00Z,2021-02-02T00:00:00Z",
),
]

invalid_single_dates = [
Expand Down