Skip to content

feat(optimizer)!: type annotation for databricks REGR_SXX, REGR_SXY, REGR_SYY #7851

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.

Sign up for GitHub

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

Open
fivetran-amrutabhimsenayachit wants to merge 3 commits into
base: main
Choose a base branch
from
Open

feat(optimizer)!: type annotation for databricks REGR_SXX, REGR_SXY, REGR_SYY #7851

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
251f8b7
feat(typing): add databricks type inference for REGR_SXX, REGR_SXY, R…
fivetran-amrutabhimsenayachit Jul 9, 2026
0433f73
fix(typing): correct DISTINCT arg semantics for REGR_SXX and REGR_SYY…
fivetran-amrutabhimsenayachit Jul 10, 2026
38b23a1
refactor(typing): extract shared _regr_sql helper in DatabricksGenerator
fivetran-amrutabhimsenayachit Jul 10, 2026
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
2 changes: 1 addition & 1 deletion sqlglot-integration-tests
Open in desktop
Submodule sqlglot-integration-tests updated from 8d9d5e to bfd6be
16 changes: 16 additions & 0 deletions sqlglot/generators/databricks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,6 +117,22 @@ def regravgx_sql(self, expression: exp.RegrAvgx) -> str:
)
return self.func("REGR_AVGX", expression.this, x)

def regrsxx_sql(self, expression: exp.RegrSxx) -> str:
x = expression.expression
if isinstance(x, exp.Distinct):
return self.func(
"REGR_SXX", exp.Distinct(expressions=[expression.this]), *x.expressions
)
return self.func("REGR_SXX", expression.this, x)

def regrsyy_sql(self, expression: exp.RegrSyy) -> str:
x = expression.expression
if isinstance(x, exp.Distinct):
return self.func(
"REGR_SYY", exp.Distinct(expressions=[expression.this]), *x.expressions
)
return self.func("REGR_SYY", expression.this, x)

@geooo109 geooo109 Jul 10, 2026 •
edited
Loading

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Let's refactor here:

    def _regr_sql(self, expression: exp.RegrAvgx  | exp.RegrSxx | exp.RegrSyy) -> str:
        name = expression.sql_name()
        x = expression.expression
        if isinstance(x, exp.Distinct):
            return self.func(name, exp.Distinct(expressions=[expression.this]), *x.expressions)
       
        return self.func(name, expression.this, x)

Then we can resue this ^ for all the 3 cases.


def clusterproperty_sql(self, expression):
this = self.sql(expression, "this") or f"({self.expressions(expression, flat=True)})"
return f"CLUSTER BY {this}"
3 changes: 3 additions & 0 deletions sqlglot/parsers/databricks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,9 @@ class DatabricksParser(SparkParser):
**SparkParser.FUNCTION_PARSERS,
"REGR_AVGX": lambda self: self._parse_distinct_arg_function(exp.RegrAvgx, distinct_index=1),
"REGR_AVGY": lambda self: self._parse_distinct_arg_function(exp.RegrAvgy),
"REGR_SXX": lambda self: self._parse_distinct_arg_function(exp.RegrSxx, distinct_index=1),
"REGR_SXY": lambda self: self._parse_distinct_arg_function(exp.RegrSxy),
"REGR_SYY": lambda self: self._parse_distinct_arg_function(exp.RegrSyy, distinct_index=1),
}

FACTOR = {
Expand Down
3 changes: 3 additions & 0 deletions sqlglot/typing/databricks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,9 @@
exp.RegrIntercept,
exp.RegrR2,
exp.RegrSlope,
exp.RegrSxx,
exp.RegrSxy,
exp.RegrSyy,
}
},
**{
Expand Down
60 changes: 60 additions & 0 deletions tests/fixtures/optimizer/annotate_functions.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4439,6 +4439,66 @@ DOUBLE;
REGR_SYY(tbl.decfloat_col, tbl.decfloat_col);
DECFLOAT;

# dialect: databricks
REGR_SXX(tbl.double_col, tbl.double_col);
DOUBLE;

# dialect: databricks
REGR_SXX(tbl.int_col, tbl.int_col);
DOUBLE;

# dialect: databricks
REGR_SXX(ALL tbl.double_col, tbl.double_col);
DOUBLE;

# dialect: databricks
REGR_SXX(DISTINCT tbl.double_col, tbl.double_col);
DOUBLE;

# dialect: databricks
REGR_SXX(tbl.double_col, tbl.double_col) OVER (PARTITION BY 1);
DOUBLE;

# dialect: databricks
REGR_SXY(tbl.double_col, tbl.double_col);
DOUBLE;

# dialect: databricks
REGR_SXY(tbl.int_col, tbl.int_col);
DOUBLE;

# dialect: databricks
REGR_SXY(ALL tbl.double_col, tbl.double_col);
DOUBLE;

# dialect: databricks
REGR_SXY(DISTINCT tbl.double_col, tbl.double_col);
DOUBLE;

# dialect: databricks
REGR_SXY(tbl.double_col, tbl.double_col) OVER (PARTITION BY 1);
DOUBLE;

# dialect: databricks
REGR_SYY(tbl.double_col, tbl.double_col);
DOUBLE;

# dialect: databricks
REGR_SYY(tbl.int_col, tbl.int_col);
DOUBLE;

# dialect: databricks
REGR_SYY(ALL tbl.double_col, tbl.double_col);
DOUBLE;

# dialect: databricks
REGR_SYY(DISTINCT tbl.double_col, tbl.double_col);
DOUBLE;

# dialect: databricks
REGR_SYY(tbl.double_col, tbl.double_col) OVER (PARTITION BY 1);
DOUBLE;

# dialect: snowflake
REGR_SLOPE(tbl.double_col, tbl.double_col);
DOUBLE;
Expand Down
Loading