date_time_parser (#25763)

Thank you for contributing to LangChain!

- [x] **PR title**: "langchain: Chains: query_constructor: add date time
parser"

- [x] **PR message**: 
- **Description:** add date time parser to langchain Chains
query_constructor
    - **Issue: https://github.com/langchain-ai/langchain/issues/25526


- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
This commit is contained in:
venkatram-dev 2024-08-27 10:18:52 -07:00 committed by GitHub
parent f359e6b0a5
commit 48b579f6b5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 60 additions and 0 deletions

View File

@ -35,6 +35,7 @@ GRAMMAR = r"""
?value: SIGNED_INT -> int
| SIGNED_FLOAT -> float
| DATE -> date
| DATETIME -> datetime
| list
| string
| ("false" | "False" | "FALSE") -> false
@ -42,6 +43,7 @@ GRAMMAR = r"""
args: expr ("," expr)*
DATE.2: /["']?(\d{4}-[01]\d-[0-3]\d)["']?/
DATETIME.2: /["']?\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d[Zz]?["']?/
string: /'[^']*'/ | ESCAPED_STRING
list: "[" [args] "]"
@ -61,6 +63,13 @@ class ISO8601Date(TypedDict):
type: Literal["date"]
class ISO8601DateTime(TypedDict):
"""A datetime in ISO 8601 format (YYYY-MM-DDTHH:MM:SS)."""
datetime: str
type: Literal["datetime"]
@v_args(inline=True)
class QueryTransformer(Transformer):
"""Transform a query string into an intermediate representation."""
@ -149,6 +158,20 @@ class QueryTransformer(Transformer):
)
return {"date": item, "type": "date"}
def datetime(self, item: Any) -> ISO8601DateTime:
item = str(item).strip("\"'")
try:
# Parse full ISO 8601 datetime format
datetime.datetime.strptime(item, "%Y-%m-%dT%H:%M:%S%z")
except ValueError:
try:
datetime.datetime.strptime(item, "%Y-%m-%dT%H:%M:%S")
except ValueError:
raise ValueError(
"Datetime values are expected to be in ISO 8601 format."
)
return {"datetime": item, "type": "datetime"}
def string(self, item: Any) -> str:
# Remove escaped quotes
return str(item).strip("\"'")

View File

@ -130,3 +130,40 @@ def test_parse_date_value(x: str) -> None:
parsed = cast(Comparison, DEFAULT_PARSER.parse(f'eq("x", {x})'))
actual = parsed.value["date"]
assert actual == x.strip("'\"")
@pytest.mark.parametrize(
"x, expected",
[
(
'"2021-01-01T00:00:00"',
{"datetime": "2021-01-01T00:00:00", "type": "datetime"},
),
(
'"2021-12-31T23:59:59Z"',
{"datetime": "2021-12-31T23:59:59Z", "type": "datetime"},
),
(
'"invalid-datetime"',
None, # Expecting failure or handling of invalid input
),
],
)
def test_parse_datetime_value(x: str, expected: dict) -> None:
"""Test parsing of datetime values with ISO 8601 format."""
try:
parsed = cast(Comparison, DEFAULT_PARSER.parse(f'eq("publishedAt", {x})'))
actual = parsed.value
assert actual == expected, f"Expected {expected}, got {actual}"
except ValueError as e:
# Handling the case where parsing should fail
if expected is None:
assert True # Correctly raised an error for invalid input
else:
pytest.fail(f"Unexpected error {e} for input {x}")
except Exception as e:
# If any other unexpected exception type is raised
if expected is None:
assert True # Correctly identified that input was invalid
else:
pytest.fail(f"Unhandled exception {e} for input {x}")