LEXIO-37880 Adds support for group by all (#2)

* all

* version

* Version bumped to 0.3.0

Co-authored-by: ns-circle-ci <devops-team+circleci@narrativescience.com>

Author: jdrake

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 default_stages: [commit]
 
 default_language_version:
-  python: python3
+  python: python3.9
 
 exclude: "examples/.*$"
 
@@ -74,7 +74,7 @@ repos:
         entry: mypy -p pysaql
         language: python
         types: [ file, python ]
-        additional_dependencies: [ mypy==0.910 ]
+        additional_dependencies: [ mypy==0.940 ]
         pass_filenames: false
 
       - id: flake8

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pysaql"
-version = "0.2.0"
+version = "0.3.0"
 description = "Python SAQL query builder"
 authors = ["Jonathan Drake <jon.drake@salesforce.com>"]
 license = "BSD-3-Clause"

pysaql/__init__.py

@@ -1,3 +1,3 @@
 """Python SAQL query builder"""
 
-__version__ = "0.2.0"
+__version__ = "0.3.0"

pysaql/saql/aggregation.py pysaql/aggregation.pypysaql/saql/aggregation.py renamed to pysaql/aggregation.py

@@ -1,8 +1,8 @@
 """Contains aggregation function definitions"""
 
-from typing import Optional, Sequence, Tuple, Union
+from __future__ import annotations
 
-from typing_extensions import Self
+from typing import Optional, Sequence, Tuple, Union
 
 from .enums import Order
 from .function import Function, NullaryFunction
@@ -34,7 +34,7 @@ def over(
         row_range: Tuple[Optional[int], Optional[int]],
         reset_groups: Union[str, Sequence[Scalar]],
         order_by: Sequence[Union[Scalar, Tuple[Scalar, Order]]],
-    ) -> Self:
+    ) -> WindowFunction:
         """Set the windowing function parameters
 
         Args:

pysaql/saql/date_.py pysaql/date_.pypysaql/saql/date_.py renamed to pysaql/date_.py

@@ -329,6 +329,6 @@ def __str__(self) -> str:
             end = ",".join(str(arg) for arg in self.end_date._args)
             return f"[dateRange([{start}], [{end}])]"
         else:
-            start = self.start_date or ""
-            end = self.end_date or ""
+            start = str(self.start_date) if self.start_date else ""
+            end = str(self.end_date) if self.end_date else ""
             return f"[{start}..{end}]"

pysaql/saql/enums.py pysaql/enums.pypysaql/saql/enums.py renamed to pysaql/enums.py

@@ -1,14 +1,14 @@
 """Contains core function definitions"""
 
-from typing import Any, List, Optional
+from typing import Any, Optional, Sequence
 
 from .scalar import Scalar
 
 
 class Function(Scalar):
     """Base function definition"""
 
-    _args: List[Any]
+    _args: Sequence[Any]
     _name: Optional[str] = None
 
     def __init__(self, *args: Any) -> None:

pysaql/saql/expression.py pysaql/expression.pypysaql/saql/expression.py renamed to pysaql/expression.py

@@ -1,11 +1,11 @@
 """Contains definition of a scalar"""
 
+from __future__ import annotations
+
 from abc import ABC, abstractmethod
 import operator
 from typing import Any, Callable, Optional, Sequence, Union
 
-from typing_extensions import Self
-
 from .expression import Expression
 from .util import escape_identifier, stringify
 
@@ -43,7 +43,7 @@ class Operation:
 class BooleanOperation(Operation):
     """Mixin that defines boolean comparison methods"""
 
-    def __and__(self, obj: Any) -> "BinaryOperation":
+    def __and__(self, obj: Any) -> BinaryOperation:
         """Creates a binary operation using the `and` operator
 
         Args:
@@ -55,7 +55,7 @@ def __and__(self, obj: Any) -> "BinaryOperation":
         """
         return BinaryOperation(operator.and_, self, obj)
 
-    def __or__(self, obj: Any) -> "BinaryOperation":
+    def __or__(self, obj: Any) -> BinaryOperation:
         """Creates a binary operation using the `or` operator
 
         Args:
@@ -67,7 +67,7 @@ def __or__(self, obj: Any) -> "BinaryOperation":
         """
         return BinaryOperation(operator.or_, self, obj, wrap=True)
 
-    def __invert__(self) -> "BinaryOperation":
+    def __invert__(self) -> UnaryOperation:
         """Creates a unary operation using the `inv` operator
 
         Returns:
@@ -134,7 +134,7 @@ class Scalar(Expression, BooleanOperation, ABC):
 
     _alias: Optional[str] = None
 
-    def alias(self, name: str) -> Self:
+    def alias(self, name: str) -> Scalar:
         """Set the alias name for a scalar expression
 
         Args:
@@ -165,7 +165,7 @@ def __str__(self) -> str:
 
         return s
 
-    def __eq__(self, obj: Any) -> BinaryOperation:
+    def __eq__(self, obj: Any) -> BinaryOperation:  # type: ignore[override]
         """Creates a binary operation using the `eq` or `is` operator
 
         Args:
@@ -178,7 +178,7 @@ def __eq__(self, obj: Any) -> BinaryOperation:
         op = operator.is_ if obj is None else operator.eq
         return BinaryOperation(op, self, obj)
 
-    def __ne__(self, obj: Any) -> BinaryOperation:
+    def __ne__(self, obj: Any) -> BinaryOperation:  # type: ignore[override]
         """Creates a binary operation using the `ne` or `is_not` operator
 
         Args:

pysaql/saql/function.py pysaql/function.pypysaql/saql/function.py renamed to pysaql/function.py

@@ -1,12 +1,12 @@
 """Contains stream expressions and statements"""
 
+from __future__ import annotations
+
 from abc import ABC
 import functools
 import operator
 from typing import List, Optional, Sequence, Tuple, Union
 
-from typing_extensions import Self
-
 from .enums import FillDateTypeString, JoinType, Order
 from .expression import Expression
 from .scalar import BinaryOperation, field, Scalar
@@ -83,7 +83,7 @@ def add_statement(self, statement: StreamStatement) -> None:
         """
         self._statements.append(statement)
 
-    def foreach(self, *fields: Scalar) -> Self:
+    def foreach(self, *fields: Scalar) -> Stream:
         """Applies a set of expressions to every row in a dataset.
 
         This action is often referred to as projection
@@ -98,14 +98,15 @@ def foreach(self, *fields: Scalar) -> Self:
         self._statements.append(ProjectionStatement(self, fields))
         return self
 
-    def group(self, *fields: Scalar) -> Self:
+    def group(self, *fields: Scalar) -> Stream:
         """Organizes the rows returned from a query into groups
 
         Within each group, you can apply an aggregate function, such as count() or sum()
         to get the number of items or sum, respectively.
 
         Args:
-            fields: One or more fields to group by
+            fields: One or more fields to group by. If no fields are provided,
+                "group by all" is assumed.
 
         Returns:
             self
@@ -114,7 +115,7 @@ def group(self, *fields: Scalar) -> Self:
         self._statements.append(GroupStatement(self, fields))
         return self
 
-    def filter(self, *filters: BinaryOperation) -> Self:
+    def filter(self, *filters: BinaryOperation) -> Stream:
         """Selects rows from a dataset based on a filter predicate
 
         Args:
@@ -128,7 +129,7 @@ def filter(self, *filters: BinaryOperation) -> Self:
         self._statements.append(FilterStatement(self, filters))
         return self
 
-    def order(self, *fields: Union[Scalar, Tuple[Scalar, Order]]) -> Self:
+    def order(self, *fields: Union[Scalar, Tuple[Scalar, Order]]) -> Stream:
         """Sorts in ascending or descending order on one or more fields.
 
         Args:
@@ -141,7 +142,7 @@ def order(self, *fields: Union[Scalar, Tuple[Scalar, Order]]) -> Self:
         self._statements.append(OrderStatement(self, fields))
         return self
 
-    def limit(self, limit: int) -> Self:
+    def limit(self, limit: int) -> Stream:
         """Limits the number of rows returned.
 
         Args:
@@ -159,7 +160,7 @@ def fill(
         date_cols: Sequence[field],
         date_type_string: FillDateTypeString,
         partition: Optional[field] = None,
-    ) -> Self:
+    ) -> Stream:
         """Fills missing date values by adding rows in data stream
 
         Args:
@@ -202,7 +203,7 @@ def __str__(self) -> str:
 class ProjectionStatement(StreamStatement):
     """Statement to project columns from a stream"""
 
-    def __init__(self, stream: Stream, fields: List[Scalar]) -> None:
+    def __init__(self, stream: Stream, fields: Sequence[Scalar]) -> None:
         """Initializer
 
         Args:
@@ -228,7 +229,7 @@ class OrderStatement(StreamStatement):
     def __init__(
         self,
         stream: Stream,
-        fields: Union[Scalar, List[Scalar], List[Tuple[Scalar, Order]]],
+        fields: Sequence[Union[Scalar, Tuple[Scalar, Order]]],
     ) -> None:
         """Initializer
 
@@ -284,30 +285,29 @@ def __str__(self) -> str:
 class GroupStatement(StreamStatement):
     """Statement to group rows in a stream"""
 
-    def __init__(self, stream: Stream, fields: List[Scalar]):
+    def __init__(self, stream: Stream, fields: Sequence[Scalar]):
         """Initializer
 
         Args:
             stream: Stream containing this statement
-            fields: One or more fields to group by
+            fields: One or more fields to group by. If no fields are provided,
+                "group by all" is assumed.
 
         """
         super().__init__()
         self.stream = stream
-        if not fields:
-            raise ValueError("At least one field is required")
         self.fields = fields
 
     def __str__(self) -> str:
         """Cast this group statement to a string"""
-        fields = ", ".join(str(f) for f in self.fields)
+        fields = stringify_list(self.fields) if self.fields else "all"
         return f"{self.stream.ref} = group {self.stream.ref} by {fields};"
 
 
 class FilterStatement(StreamStatement):
     """Statement to filter rows in a stream"""
 
-    def __init__(self, stream: Stream, filters: List[BinaryOperation]) -> None:
+    def __init__(self, stream: Stream, filters: Sequence[BinaryOperation]) -> None:
         """Initializer
 
         Args:
@@ -336,7 +336,7 @@ class CogroupStatement(StreamStatement):
     def __init__(
         self,
         stream: Stream,
-        streams: List[Tuple[Stream, Scalar]],
+        streams: Sequence[Tuple[Stream, Scalar]],
         join_type: JoinType = JoinType.inner,
     ) -> None:
         """Initializer