Skip to content
Open
Show file tree
Hide file tree
Changes from all 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
Original file line number Diff line number Diff line change
Expand Up @@ -275,6 +275,71 @@ def find_nearest(
stages.FindNearest(field, vector, distance_measure, options)
)

def literals(self, *documents: Selectable | dict) -> "_BasePipeline":
"""
Returns documents from a fixed set of predefined document objects.

This stage is commonly used for testing other stages in isolation,
though it can also be used as inputs to join conditions.

Example:
>>> from google.cloud.firestore_v1.pipeline_expressions import Constant
>>> documents = [
... {"name": "joe", "age": 10},
... {"name": "bob", "age": 30},
... {"name": "alice", "age": 40}
... ]
>>> pipeline = client.pipeline()
... .literals(Constant.of(documents))
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looking at the code, it seems like:

  1. Constant isn't a Selectable
  2. Constant doesn't seem like it supports dict types. (We do have a Map, which serves that purpose, but it doesn't seem Selectable either)

... .where(field("age").lessThan(35))

Output documents:
```json
[
{"name": "joe", "age": 10},
{"name": "bob", "age": 30}
]
```

Behavior:
The `literals(...)` stage can only be used as the first stage in a pipeline (or
sub-pipeline). The order of documents returned from the `literals` matches the
order in which they are defined.

While literal values are the most common, it is also possible to pass in
expressions, which will be evaluated and returned, making it possible to test
out different query / expression behavior without first needing to create some
test data.

For example, the following shows how to quickly test out the `length(...)`
function on some constant test sets:

Example:
>>> from google.cloud.firestore_v1.pipeline_expressions import Constant
>>> documents = [
... {"x": Constant.of("foo-bar-baz").char_length()},
... {"x": Constant.of("bar").char_length()}
... ]
>>> pipeline = client.pipeline().literals(Constant.of(documents))

Output documents:
```json
[
{"x": 11},
{"x": 3}
]
```

Args:
documents: A `str` or `Selectable` expression. If a `str`, it's
treated as a field path to an array of documents.
If a `Selectable`, it's usually a `Constant`
containing an array of documents (as dictionaries).
Comment on lines +334 to +337
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The Args section of the docstring is misleading. It describes a single argument, but the method accepts *documents. It also incorrectly states that a str is treated as a field path; the implementation treats it as a string literal. To use a field path, field() should be used explicitly.

Suggested change
documents: A `str` or `Selectable` expression. If a `str`, it's
treated as a field path to an array of documents.
If a `Selectable`, it's usually a `Constant`
containing an array of documents (as dictionaries).
documents: One or more documents to be returned by this stage.
Each can be a `dict`, a `str` literal, or a
`Selectable` expression (e.g. `field("path")` or
`Constant.of(...)`).

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

+1. Usually I'd put the * in here too: *documents:

Returns:
A new Pipeline object with this stage appended to the stage list.
"""
return self._append(stages.Literals(*documents))

def replace_with(
self,
field: Selectable,
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -342,6 +342,23 @@ def _pb_args(self):
return [Value(integer_value=self.limit)]


class Literals(Stage):
"""Returns documents from a fixed set of predefined document objects."""

def __init__(self, *documents: Selectable | dict):
super().__init__("literals")
self.documents = documents

def _pb_args(self):
args = []
for doc in self.documents:
if hasattr(doc, "_to_pb"):
args.append(doc._to_pb())
else:
args.append(encode_value(doc))
return args


class Offset(Stage):
"""Skips a specified number of documents."""

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -684,4 +684,23 @@ tests:
- args:
- fieldReferenceValue: awards
- stringValue: full_replace
name: replace_with
name: replace_with
- description: literals
pipeline:
- Literals:
- title: "The Hitchhiker's Guide to the Galaxy"
author: "Douglas Adams"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe it's been a while since I looked at this, but this doesn't seem like the right syntax to me. Isn't this essentially sending Literals({"title": ""The Hitchhiker's Guide to the Galaxy", "author", "Douglas Adams"})? That doesn't seem to match the str | Selectable

Does the test pass?

assert_results:
- title: "The Hitchhiker's Guide to the Galaxy"
author: "Douglas Adams"
assert_proto:
pipeline:
stages:
- args:
- mapValue:
fields:
author:
stringValue: "Douglas Adams"
title:
stringValue: "The Hitchhiker's Guide to the Galaxy"
name: literals
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We should also have tests here that cover the different input types we support

Original file line number Diff line number Diff line change
Expand Up @@ -417,6 +417,7 @@ def test_pipeline_execute_stream_equivalence():
("aggregate", (Field.of("n").as_("alias"),), stages.Aggregate),
("distinct", ("field_name",), stages.Distinct),
("distinct", (Field.of("n"), "second"), stages.Distinct),
("literals", (Field.of("a"),), stages.Literals),
],
)
def test_pipeline_methods(method, args, result_cls):
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -517,6 +517,35 @@ def test_to_pb(self):
assert len(result.options) == 0


class TestLiterals:
def _make_one(self, *args, **kwargs):
return stages.Literals(*args, **kwargs)

def test_ctor(self):
val1 = Constant.of({"a": 1})
val2 = {"b": 2}
instance = self._make_one(val1, val2)
assert instance.documents == (val1, val2)
assert instance.name == "literals"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We should have tests that cover all supported input types. I don't see anything using str (and looking at go, I'm not sure if we should be supporting str?)


def test_repr(self):
val1 = Constant.of({"a": 1})
instance = self._make_one(val1, {"b": 2})
repr_str = repr(instance)
assert repr_str == "Literals(documents=(Constant.of({'a': 1}), {'b': 2}))"

def test_to_pb(self):
val1 = Constant.of({"a": 1})
val2 = {"b": 2}
instance = self._make_one(val1, val2)
result = instance._to_pb()
assert result.name == "literals"
assert len(result.args) == 2
assert result.args[0].map_value.fields["a"].integer_value == 1
assert result.args[1].map_value.fields["b"].integer_value == 2
assert len(result.options) == 0


class TestOffset:
def _make_one(self, *args, **kwargs):
return stages.Offset(*args, **kwargs)
Expand Down
Loading