semantic-link-labs 0.8.2__py3-none-any.whl → 0.8.4__py3-none-any.whl

sempy_labs/tom/_model.py

@@ -6,6 +6,7 @@ from datetime import datetime
 from sempy_labs._helper_functions import (
     format_dax_object_name,
     generate_guid,
+    _make_list_unique,
 )
 from sempy_labs._list_functions import list_relationships
 from sempy_labs._refresh_semantic_model import refresh_semantic_model
@@ -15,6 +16,7 @@ from typing import List, Iterator, Optional, Union, TYPE_CHECKING
 from sempy._utils._log import log
 import sempy_labs._icons as icons
 from sempy.fabric.exceptions import FabricHTTPException
+import ast
 
 if TYPE_CHECKING:
     import Microsoft.AnalysisServices.Tabular
@@ -33,6 +35,8 @@ class TOMWrapper:
     _workspace: str
     _readonly: bool
     _tables_added: List[str]
+    _table_map = dict
+    _column_map = dict
 
     def __init__(self, dataset, workspace, readonly):
         self._dataset = dataset
@@ -45,6 +49,18 @@ class TOMWrapper:
         )
         self.model = self._tom_server.Databases.GetByName(dataset).Model
 
+        self._table_map = {}
+        self._column_map = {}
+        for t in self.model.Tables:
+            if len(t.LineageTag) == 0:
+                t.LineageTag = generate_guid()
+            self._table_map[t.LineageTag] = t.Name
+
+        for c in self.all_columns():
+            if len(c.LineageTag) == 0:
+                c.LineageTag = generate_guid()
+            self._column_map[c.LineageTag] = [c.Name, c.DataType]
+
     def all_columns(self):
         """
         Outputs a list of all columns within all tables in the semantic model.
@@ -291,8 +307,6 @@ class TOMWrapper:
             obj.LineageTag = generate_guid()
         if source_lineage_tag is not None:
             obj.SourceLineageTag = source_lineage_tag
-        else:
-            obj.SourceLineageTag = generate_guid()
         if detail_rows_expression is not None:
             drd = TOM.DetailRowsDefinition()
             drd.Expression = detail_rows_expression
@@ -388,8 +402,6 @@ class TOMWrapper:
             obj.LineageTag = generate_guid()
         if source_lineage_tag is not None:
             obj.SourceLineageTag = source_lineage_tag
-        else:
-            obj.SourceLineageTag = generate_guid()
         self.model.Tables[table_name].Columns.Add(obj)
 
     def add_data_column(
@@ -478,8 +490,6 @@ class TOMWrapper:
             obj.LineageTag = generate_guid()
         if source_lineage_tag is not None:
             obj.SourceLineageTag = source_lineage_tag
-        else:
-            obj.SourceLineagetTag = generate_guid()
         self.model.Tables[table_name].Columns.Add(obj)
 
     def add_calculated_column(
@@ -568,8 +578,6 @@ class TOMWrapper:
             obj.LineageTag = generate_guid()
         if source_lineage_tag is not None:
             obj.SourceLineageTag = source_lineage_tag
-        else:
-            obj.SourceLineagetTag = generate_guid()
         self.model.Tables[table_name].Columns.Add(obj)
 
     def add_calculation_item(
@@ -785,8 +793,6 @@ class TOMWrapper:
             obj.LineageTag = generate_guid()
         if source_lineage_tag is not None:
             obj.SourceLineageTag = source_lineage_tag
-        else:
-            obj.SourceLineagetTag = generate_guid()
         self.model.Tables[table_name].Hierarchies.Add(obj)
 
         for col in columns:
@@ -795,7 +801,6 @@ class TOMWrapper:
             lvl.Name = levels[columns.index(col)]
             lvl.Ordinal = columns.index(col)
             lvl.LineageTag = generate_guid()
-            lvl.SourceLineageTag = generate_guid()
             self.model.Tables[table_name].Hierarchies[hierarchy_name].Levels.Add(lvl)
 
     def add_relationship(
@@ -911,6 +916,7 @@ class TOMWrapper:
         part = TOM.Partition()
         part.Name = name
         part.Source = TOM.CalculationGroupSource()
+        part.Mode = TOM.ModeType.Import
         tbl.Partitions.Add(part)
 
         sortCol = "Ordinal"
@@ -969,8 +975,6 @@ class TOMWrapper:
             exp.LineageTag = generate_guid()
         if source_lineage_tag is not None:
             exp.SourceLineageTag = source_lineage_tag
-        else:
-            exp.SourceLineageTag = generate_guid()
         exp.Kind = TOM.ExpressionKind.M
         exp.Expression = expression
 
@@ -987,10 +991,13 @@ class TOMWrapper:
         """
         import Microsoft.AnalysisServices.Tabular as TOM
 
-        cul = TOM.Culture()
-        cul.Name = language
-
         if not any(c.Name == language for c in self.model.Cultures):
+            cul = TOM.Culture()
+            cul.Name = language
+            lm = TOM.LinguisticMetadata()
+            lm.ContentType = TOM.ContentType.Json
+            lm.Content = f'{{"Version": "1.0.0", "Language": "{language}"}}'
+            cul.LinguisticMetadata = lm
             self.model.Cultures.Add(cul)
 
     def add_perspective(self, perspective_name: str):
@@ -2108,7 +2115,9 @@ class TOMWrapper:
             if c.Parent.Name == table_name and c.Parent.DataCategory == "Time"
         )
 
-    def mark_as_date_table(self, table_name: str, column_name: str):
+    def mark_as_date_table(
+        self, table_name: str, column_name: str, validate: bool = False
+    ):
         """
         Marks a table as a `date table <https://learn.microsoft.com/power-bi/transform-model/desktop-date-tables>`_.
 
@@ -2118,6 +2127,8 @@ class TOMWrapper:
             Name of the table.
         column_name : str
             Name of the date column in the table.
+        validate : bool, default=False
+            If True, performs a validation on if the the date table is viable.
         """
         import Microsoft.AnalysisServices.Tabular as TOM
 
@@ -2128,31 +2139,32 @@ class TOMWrapper:
                 f"{icons.red_dot} The column specified in the 'column_name' parameter in this function must be of DateTime data type."
             )
 
-        daxQuery = f"""
-        define measure '{table_name}'[test] = 
-        var mn = MIN('{table_name}'[{column_name}])
-        var ma = MAX('{table_name}'[{column_name}])
-        var x = COUNTROWS(DISTINCT('{table_name}'[{column_name}]))
-        var y = DATEDIFF(mn, ma, DAY) + 1
-        return if(y = x, 1,0)
-
-        EVALUATE
-        SUMMARIZECOLUMNS(
-        "1",[test]
-        )
-        """
-        df = fabric.evaluate_dax(
-            dataset=self._dataset, workspace=self._workspace, dax_string=daxQuery
-        )
-        value = df["1"].iloc[0]
-        if value != "1":
-            raise ValueError(
-                f"{icons.red_dot} The '{column_name}' within the '{table_name}' table does not contain contiguous date values."
+        if validate:
+            dax_query = f"""
+            define measure '{table_name}'[test] = 
+            var mn = MIN('{table_name}'[{column_name}])
+            var ma = MAX('{table_name}'[{column_name}])
+            var x = COUNTROWS(DISTINCT('{table_name}'[{column_name}]))
+            var y = DATEDIFF(mn, ma, DAY) + 1
+            return if(y = x, 1,0)
+
+            EVALUATE
+            SUMMARIZECOLUMNS(
+            "1",[test]
             )
+            """
+            df = fabric.evaluate_dax(
+                dataset=self._dataset, workspace=self._workspace, dax_string=dax_query
+            )
+            value = df["[1]"].iloc[0]
+            if value != "1":
+                raise ValueError(
+                    f"{icons.red_dot} The '{column_name}' within the '{table_name}' table does not contain contiguous date values."
+                )
 
         # Mark as a date table
         t.DataCategory = "Time"
-        c.Columns[column_name].IsKey = True
+        c.IsKey = True
         print(
             f"{icons.green_dot} The '{table_name}' table has been marked as a date table using the '{column_name}' column as its primary date key."
         )
@@ -2654,8 +2666,6 @@ class TOMWrapper:
             t.LineageTag = generate_guid()
         if source_lineage_tag is not None:
             t.SourceLineageTag = source_lineage_tag
-        else:
-            t.SourceLineagetTag = generate_guid()
         t.Hidden = hidden
         self.model.Tables.Add(t)
 
@@ -2693,6 +2703,7 @@ class TOMWrapper:
 
         par = TOM.Partition()
         par.Name = name
+        par.Mode = TOM.ModeType.Import
 
         parSource = TOM.CalculatedPartitionSource()
         parSource.Expression = expression
@@ -2710,8 +2721,6 @@ class TOMWrapper:
             t.LineageTag = generate_guid()
         if source_lineage_tag is not None:
             t.SourceLineageTag = source_lineage_tag
-        else:
-            t.SourceLineagetTag = generate_guid()
         t.Hidden = hidden
         t.Partitions.Add(par)
         self.model.Tables.Add(t)
@@ -2952,6 +2961,8 @@ class TOMWrapper:
             runId = "1"
         self.set_annotation(object=self.model, name="Vertipaq_Run", value=runId)
 
+        icons.sll_tags.append("VertipaqAnnotations")
+
     def row_count(self, object: Union["TOM.Partition", "TOM.Table"]):
         """
         Obtains the row count of a table or partition within a semantic model.
@@ -4185,15 +4196,7 @@ class TOMWrapper:
             Name of the column to use for sorting. Must be of integer (Int64) data type.
         """
 
-        import Microsoft.AnalysisServices.Tabular as TOM
-
         sbc = self.model.Tables[table_name].Columns[sort_by_column]
-
-        if sbc.DataType != TOM.DataType.Int64:
-            raise ValueError(
-                f"{icons.red_dot} Invalid sort by column data type. The sort by column must be of 'Int64' data type."
-            )
-
         self.model.Tables[table_name].Columns[column_name].SortByColumn = sbc
 
     def remove_sort_by_column(self, table_name: str, column_name: str):
@@ -4281,41 +4284,67 @@ class TOMWrapper:
                             icons.default_schema
                         )
                     t.SourceLineageTag = f"[{schema_name}].[{entity_name}]"
-                else:
-                    t.SourceLineageTag = generate_guid()
         for c in self.all_columns():
             if len(c.LineageTag) == 0:
                 c.LineageTag = generate_guid()
-            if len(c.SourceLineageTag) == 0:
-                c.SourceLineageTag = generate_guid()
         for m in self.all_measures():
             if len(m.LineageTag) == 0:
                 m.LineageTag = generate_guid()
-            if len(m.SourceLineageTag) == 0:
-                m.SourceLineageTag = generate_guid()
         for h in self.all_hierarchies():
             if len(h.LineageTag) == 0:
                 h.LineageTag = generate_guid()
-            if len(h.SourceLineageTag) == 0:
-                h.SourceLineageTag = generate_guid()
         for lvl in self.all_levels():
             if len(lvl.LineageTag) == 0:
                 lvl.LineageTag = generate_guid()
-            if len(lvl.SourceLineageTag) == 0:
-                lvl.SourceLineageTag = generate_guid()
-        for e in self.model.Expressions():
+        for e in self.model.Expressions:
             if len(e.LineageTag) == 0:
                 e.LineageTag = generate_guid()
-            if len(e.SourceLineageTag) == 0:
-                e.SourceLineageTag = generate_guid()
+
+    def add_changed_property(self, object, property: str):
+        """
+        Adds a `ChangedProperty <https://learn.microsoft.com/dotnet/api/microsoft.analysisservices.tabular.changedproperty.property?view=analysisservices-dotnet#microsoft-analysisservices-tabular-changedproperty-property>`_ property to a semantic model object. Only adds the property if it does not already exist for the object.
+
+        Parameters
+        ----------
+        object : TOM Object
+            The TOM object within the semantic model.
+        property : str
+            The property to set (i.e. 'Name', 'DataType').
+        """
+
+        import Microsoft.AnalysisServices.Tabular as TOM
+
+        # Only add the property if it does not already exist for that object
+        if not any(c.Property == property for c in object.ChangedProperties):
+            cp = TOM.ChangedProperty()
+            cp.Property = property
+            object.ChangedProperties.Add(cp)
+
+    def remove_changed_property(self, object, property: str):
+        """
+        Removes a `ChangedProperty <https://learn.microsoft.com/dotnet/api/microsoft.analysisservices.tabular.changedproperty.property?view=analysisservices-dotnet#microsoft-analysisservices-tabular-changedproperty-property>`_ property to a semantic model object. Only adds the property if it does not already exist for the object.
+
+        Parameters
+        ----------
+        object : TOM Object
+            The TOM object within the semantic model.
+        property : str
+            The property to set (i.e. 'Name', 'DataType').
+        """
+
+        for cp in object.ChangedProperties:
+            if cp.Property == property:
+                object.ChangedProperties.Remove(cp)
 
     def generate_measure_descriptions(
         self,
         measure_name: Optional[str | List[str]] = None,
         max_batch_size: Optional[int] = 5,
-    ):
+    ) -> pd.DataFrame:
         """
-        Auto-generates descriptions for measures using an LLM.
+        Auto-generates descriptions for measures using an LLM. This function requires a paid F-sku (Fabric) of F64 or higher.
+        Setting the 'readonly' parameter in connect_semantic_model to True will allow you to see the auto-generated descriptions in a dataframe. Setting the 'readonly' parameter
+        to False will update the descriptions for the measures within the 'measure_name' parameter.
 
         Parameters
         ----------
@@ -4324,9 +4353,21 @@ class TOMWrapper:
             Defaults to None which generates descriptions for all measures in the semantic model.
         max_batch_size : int, default=5
             Sets the max batch size for each API call.
+
+        Returns
+        -------
+        pandas.DataFrame
+            A pandas dataframe showing the updated measure(s) and their new description(s).
         """
 
+        df = pd.DataFrame(
+            columns=["Table Name", "Measure Name", "Expression", "Description"]
+        )
+        data = []
+
         # import concurrent.futures
+        if measure_name is None:
+            measure_name = [m.Name for m in self.all_measures()]
 
         if isinstance(measure_name, str):
             measure_name = [measure_name]
@@ -4383,11 +4424,28 @@ class TOMWrapper:
                 if ms_name.startswith("urn: "):
                     ms_name = ms_name[5:]
                 desc = item.get("description")
-                table_name = next(
-                    m.Parent.Name for m in self.all_measures() if m.Name == ms_name
+                (table_name, expr) = next(
+                    (m.Parent.Name, m.Expression)
+                    for m in self.all_measures()
+                    if m.Name == ms_name
                 )
                 self.model.Tables[table_name].Measures[ms_name].Description = desc
 
+                # Collect new descriptions in a dataframe
+                new_data = {
+                    "Table Name": table_name,
+                    "Measure Name": ms_name,
+                    "Expression": expr,
+                    "Description": desc,
+                }
+
+                data.append(new_data)
+
+        if data:
+            df = pd.concat([df, pd.DataFrame(data)], ignore_index=True)
+
+        return df
+
         # def process_measure(m):
         #     table_name = m.Parent.Name
         #     m_name = m.Name
@@ -4424,7 +4482,55 @@ class TOMWrapper:
         #     executor.map(process_measure, self.all_measures())
 
     def close(self):
+
         if not self._readonly and self.model is not None:
+
+            import Microsoft.AnalysisServices.Tabular as TOM
+
+            # ChangedProperty logic
+            for t in self.model.Tables:
+                if any(
+                    p.SourceType == TOM.PartitionSourceType.Entity for p in t.Partitions
+                ):
+                    if t.LineageTag in list(self._table_map.keys()):
+                        if self._table_map.get(t.LineageTag) != t.Name:
+                            self.add_changed_property(object=t, property="Name")
+
+            for c in self.all_columns():
+                if c.LineageTag in list(self._column_map.keys()):
+                    if any(
+                        p.SourceType == TOM.PartitionSourceType.Entity
+                        for p in c.Parent.Partitions
+                    ):
+                        if self._column_map.get(c.LineageTag)[0] != c.Name:
+                            self.add_changed_property(object=c, property="Name")
+                    if self._column_map.get(c.LineageTag)[1] != c.DataType:
+                        self.add_changed_property(object=c, property="DataType")
+
+            tags = [f"{icons.sll_prefix}{a}" for a in icons.sll_tags]
+            tags.append("SLL")
+
+            if not any(a.Name == icons.sll_ann_name for a in self.model.Annotations):
+                ann_list = _make_list_unique(tags)
+                new_ann_value = str(ann_list).replace("'", '"')
+                self.set_annotation(
+                    object=self.model, name=icons.sll_ann_name, value=new_ann_value
+                )
+            else:
+                try:
+                    ann_value = self.get_annotation_value(
+                        object=self.model, name=icons.sll_ann_name
+                    )
+                    ann_list = ast.literal_eval(ann_value)
+                    ann_list += tags
+                    ann_list = _make_list_unique(ann_list)
+                    new_ann_value = str(ann_list).replace("'", '"')
+                    self.set_annotation(
+                        object=self.model, name=icons.sll_ann_name, value=new_ann_value
+                    )
+                except Exception:
+                    pass
+
             self.model.SaveChanges()
 
             if len(self._tables_added) > 0: