kumoai 2.14.0.dev202512211732__cp313-cp313-win_amd64.whl → 2.15.0.dev202601151732__cp313-cp313-win_amd64.whl

kumoai/experimental/rfm/backend/snow/table.py

@@ -1,4 +1,5 @@
 import re
+from collections import Counter
 from collections.abc import Sequence
 from typing import cast
 
@@ -8,28 +9,27 @@ from kumoapi.typing import Dtype
 
 from kumoai.experimental.rfm.backend.snow import Connection
 from kumoai.experimental.rfm.base import (
-    ColumnExpressionSpec,
-    ColumnExpressionType,
+    ColumnSpec,
+    ColumnSpecType,
     DataBackend,
     SourceColumn,
     SourceForeignKey,
-    SQLTable,
+    Table,
 )
 from kumoai.utils import quote_ident
 
 
-class SnowTable(SQLTable):
+class SnowTable(Table):
     r"""A table backed by a :class:`sqlite` database.
 
     Args:
         connection: The connection to a :class:`snowflake` database.
-        name: The logical name of this table.
-        source_name: The physical name of this table in the database. If set to
-            ``None``, ``name`` is being used.
+        name: The name of this table.
+        source_name: The source name of this table. If set to ``None``,
+            ``name`` is being used.
         database: The database.
         schema: The schema.
-        columns: The selected physical columns of this table.
-        column_expressions: The logical columns of this table.
+        columns: The selected columns of this table.
         primary_key: The name of the primary key of this table, if it exists.
         time_column: The name of the time column of this table, if it exists.
         end_time_column: The name of the end time column of this table, if it
@@ -42,14 +42,21 @@ class SnowTable(SQLTable):
         source_name: str | None = None,
         database: str | None = None,
         schema: str | None = None,
-        columns: Sequence[str] | None = None,
-        column_expressions: Sequence[ColumnExpressionType] | None = None,
+        columns: Sequence[ColumnSpecType] | None = None,
         primary_key: MissingType | str | None = MissingType.VALUE,
         time_column: str | None = None,
         end_time_column: str | None = None,
     ) -> None:
 
-        if database is not None and schema is None:
+        if database is None or schema is None:
+            with connection.cursor() as cursor:
+                cursor.execute("SELECT CURRENT_DATABASE(), CURRENT_SCHEMA()")
+                result = cursor.fetchone()
+                database = database or result[0]
+                assert database is not None
+                schema = schema or result[1]
+
+        if schema is None:
             raise ValueError(f"Unspecified 'schema' for table "
                              f"'{source_name or name}' in database "
                              f"'{database}'")
@@ -62,70 +69,41 @@ class SnowTable(SQLTable):
             name=name,
             source_name=source_name,
             columns=columns,
-            column_expressions=column_expressions,
             primary_key=primary_key,
             time_column=time_column,
             end_time_column=end_time_column,
         )
 
-    @staticmethod
-    def to_dtype(snowflake_dtype: str | None) -> Dtype | None:
-        if snowflake_dtype is None:
-            return None
-        snowflake_dtype = snowflake_dtype.strip().upper()
-        # TODO 'NUMBER(...)' is not always an integer!
-        if snowflake_dtype.startswith('NUMBER'):
-            return Dtype.int
-        elif snowflake_dtype.startswith('VARCHAR'):
-            return Dtype.string
-        elif snowflake_dtype == 'FLOAT':
-            return Dtype.float
-        elif snowflake_dtype == 'BOOLEAN':
-            return Dtype.bool
-        elif re.search('DATE|TIMESTAMP', snowflake_dtype):
-            return Dtype.date
-        return None
+    @property
+    def source_name(self) -> str:
+        names = [self._database, self._schema, self._source_name]
+        return '.'.join(names)
 
     @property
-    def backend(self) -> DataBackend:
-        return cast(DataBackend, DataBackend.SNOWFLAKE)
+    def _quoted_source_name(self) -> str:
+        names = [self._database, self._schema, self._source_name]
+        return '.'.join([quote_ident(name) for name in names])
 
     @property
-    def fqn(self) -> str:
-        r"""The fully-qualified quoted table name."""
-        names: list[str] = []
-        if self._database is not None:
-            names.append(quote_ident(self._database))
-        if self._schema is not None:
-            names.append(quote_ident(self._schema))
-        return '.'.join(names + [quote_ident(self._source_name)])
+    def backend(self) -> DataBackend:
+        return cast(DataBackend, DataBackend.SNOWFLAKE)
 
     def _get_source_columns(self) -> list[SourceColumn]:
         source_columns: list[SourceColumn] = []
         with self._connection.cursor() as cursor:
             try:
-                sql = f"DESCRIBE TABLE {self.fqn}"
+                sql = f"DESCRIBE TABLE {self._quoted_source_name}"
                 cursor.execute(sql)
             except Exception as e:
-                names: list[str] = []
-                if self._database is not None:
-                    names.append(self._database)
-                if self._schema is not None:
-                    names.append(self._schema)
-                source_name = '.'.join(names + [self._source_name])
-                raise ValueError(f"Table '{source_name}' does not exist in "
-                                 f"the remote data backend") from e
+                raise ValueError(f"Table '{self.source_name}' does not exist "
+                                 f"in the remote data backend") from e
 
             for row in cursor.fetchall():
-                column, type, _, null, _, is_pkey, is_unique, *_ = row
-
-                dtype = self.to_dtype(type)
-                if dtype is None:
-                    continue
+                column, dtype, _, null, _, is_pkey, is_unique, *_ = row
 
                 source_column = SourceColumn(
                     name=column,
-                    dtype=dtype,
+                    dtype=self._to_dtype(dtype),
                     is_primary_key=is_pkey.strip().upper() == 'Y',
                     is_unique_key=is_unique.strip().upper() == 'Y',
                     is_nullable=null.strip().upper() == 'Y',
@@ -135,35 +113,133 @@ class SnowTable(SQLTable):
         return source_columns
 
     def _get_source_foreign_keys(self) -> list[SourceForeignKey]:
-        source_fkeys: list[SourceForeignKey] = []
+        source_foreign_keys: list[SourceForeignKey] = []
         with self._connection.cursor() as cursor:
-            sql = f"SHOW IMPORTED KEYS IN TABLE {self.fqn}"
+            sql = f"SHOW IMPORTED KEYS IN TABLE {self._quoted_source_name}"
             cursor.execute(sql)
-            for row in cursor.fetchall():
-                _, _, _, dst_table, pkey, _, _, _, fkey, *_ = row
-                source_fkeys.append(SourceForeignKey(fkey, dst_table, pkey))
-        return source_fkeys
+            rows = cursor.fetchall()
+            counts = Counter(row[13] for row in rows)
+            for row in rows:
+                if counts[row[13]] == 1:
+                    source_foreign_key = SourceForeignKey(
+                        name=row[8],
+                        dst_table=f'{row[1]}.{row[2]}.{row[3]}',
+                        primary_key=row[4],
+                    )
+                    source_foreign_keys.append(source_foreign_key)
+        return source_foreign_keys
 
     def _get_source_sample_df(self) -> pd.DataFrame:
         with self._connection.cursor() as cursor:
             columns = [quote_ident(col) for col in self._source_column_dict]
-            sql = f"SELECT {', '.join(columns)} FROM {self.fqn} LIMIT 1000"
+            sql = (f"SELECT {', '.join(columns)} "
+                   f"FROM {self._quoted_source_name} "
+                   f"LIMIT {self._NUM_SAMPLE_ROWS}")
             cursor.execute(sql)
             table = cursor.fetch_arrow_all()
-            return table.to_pandas(types_mapper=pd.ArrowDtype)
+
+        if table is None:
+            raise RuntimeError(f"Table '{self.source_name}' is empty")
+
+        return self._sanitize(
+            df=table.to_pandas(types_mapper=pd.ArrowDtype),
+            dtype_dict={
+                column.name: column.dtype
+                for column in self._source_column_dict.values()
+            },
+            stype_dict=None,
+        )
 
     def _get_num_rows(self) -> int | None:
-        return None
+        with self._connection.cursor() as cursor:
+            quoted_source_name = quote_ident(self._source_name, char="'")
+            sql = (f"SHOW TABLES LIKE {quoted_source_name} "
+                   f"IN SCHEMA {quote_ident(self._database)}."
+                   f"{quote_ident(self._schema)}")
+            cursor.execute(sql)
+            num_rows = cursor.fetchone()[7]
+
+        if num_rows == 0:
+            raise RuntimeError("Table '{self.source_name}' is empty")
 
-    def _get_expression_sample_df(
+        return num_rows
+
+    def _get_expr_sample_df(
         self,
-        specs: Sequence[ColumnExpressionSpec],
+        columns: Sequence[ColumnSpec],
     ) -> pd.DataFrame:
         with self._connection.cursor() as cursor:
-            columns = [
-                f"{spec.expr} AS {quote_ident(spec.name)}" for spec in specs
+            projections = [
+                f"{column.expr} AS {quote_ident(column.name)}"
+                for column in columns
             ]
-            sql = f"SELECT {', '.join(columns)} FROM {self.fqn} LIMIT 1000"
+            sql = (f"SELECT {', '.join(projections)} "
+                   f"FROM {self._quoted_source_name} "
+                   f"LIMIT {self._NUM_SAMPLE_ROWS}")
             cursor.execute(sql)
             table = cursor.fetch_arrow_all()
-            return table.to_pandas(types_mapper=pd.ArrowDtype)
+
+        if table is None:
+            raise RuntimeError(f"Table '{self.source_name}' is empty")
+
+        return self._sanitize(
+            df=table.to_pandas(types_mapper=pd.ArrowDtype),
+            dtype_dict={column.name: column.dtype
+                        for column in columns},
+            stype_dict=None,
+        )
+
+    @staticmethod
+    def _to_dtype(dtype: str | None) -> Dtype | None:
+        if dtype is None:
+            return None
+        dtype = dtype.strip().upper()
+        if dtype.startswith('NUMBER'):
+            try:  # Parse `scale` from 'NUMBER(precision, scale)':
+                scale = int(dtype.split(',')[-1].split(')')[0])
+                return Dtype.int if scale == 0 else Dtype.float
+            except Exception:
+                return Dtype.float
+        if dtype == 'FLOAT':
+            return Dtype.float
+        if dtype.startswith('VARCHAR'):
+            return Dtype.string
+        if dtype.startswith('BINARY'):
+            return Dtype.binary
+        if dtype == 'BOOLEAN':
+            return Dtype.bool
+        if dtype.startswith('DATE') or dtype.startswith('TIMESTAMP'):
+            return Dtype.date
+        if dtype.startswith('TIME'):
+            return Dtype.time
+        if dtype.startswith('VECTOR'):
+            try:  # Parse element data type from 'VECTOR(dtype, dimension)':
+                dtype = dtype.split(',')[0].split('(')[1].strip()
+                if dtype == 'INT':
+                    return Dtype.intlist
+                elif dtype == 'FLOAT':
+                    return Dtype.floatlist
+            except Exception:
+                pass
+            return Dtype.unsupported
+        if dtype.startswith('ARRAY'):
+            try:  # Parse element data type from 'ARRAY(dtype)':
+                dtype = dtype.split('(', maxsplit=1)[1]
+                dtype = dtype.rsplit(')', maxsplit=1)[0]
+                _dtype = SnowTable._to_dtype(dtype)
+                if _dtype is not None and _dtype.is_int():
+                    return Dtype.intlist
+                elif _dtype is not None and _dtype.is_float():
+                    return Dtype.floatlist
+                elif _dtype is not None and _dtype.is_string():
+                    return Dtype.stringlist
+            except Exception:
+                pass
+            return Dtype.unsupported
+        # Unsupported data types:
+        if re.search(
+                'DECFLOAT|VARIANT|OBJECT|MAP|FILE|GEOGRAPHY|GEOMETRY',
+                dtype,
+        ):
+            return Dtype.unsupported
+        return None