semantic-link-labs 0.5.0__py3-none-any.whl → 0.7.0__py3-none-any.whl

sempy_labs/migration/_migrate_calctables_to_semantic_model.py

@@ -1,8 +1,12 @@
-import sempy
 import sempy.fabric as fabric
-import re, datetime, time
+import re
+import datetime
 from sempy_labs.lakehouse._get_lakehouse_tables import get_lakehouse_tables
-from sempy_labs._helper_functions import resolve_lakehouse_name
+from sempy_labs._helper_functions import (
+    resolve_lakehouse_name,
+    format_dax_object_name,
+    retry,
+)
 from sempy_labs.tom import connect_semantic_model
 from typing import Optional
 from sempy._utils._log import log
@@ -66,7 +70,7 @@ def migrate_calc_tables_to_semantic_model(
     dfC_filt = dfC[
         (dfC["Table Name"].isin(dfP_filt["Table Name"]))
     ]  # & (dfC['Type'] == 'CalculatedTableColumn')]
-    # dfA = list_annotations(new_dataset, new_dataset_workspace)
+    # dfA = fabric.list_annotations(new_dataset, new_dataset_workspace)
     # dfA_filt = dfA[(dfA['Object Type'] == 'Model') & ~ (dfA['Annotation Value'].str.contains('NAMEOF'))]
 
     if len(dfP_filt) == 0:
@@ -75,76 +79,73 @@ def migrate_calc_tables_to_semantic_model(
         )
         return
 
-    start_time = datetime.datetime.now()
-    timeout = datetime.timedelta(minutes=1)
-    success = False
-
-    while not success:
-        try:
-            with connect_semantic_model(
-                dataset=new_dataset, readonly=False, workspace=new_dataset_workspace
-            ) as tom:
-                success = True
-                for tName in dfC_filt["Table Name"].unique():
-                    if tName.lower() in lc["Table Name"].values:
-
-                        try:
-                            tom.model.Tables[tName]
-                        except:
-                            tom.add_table(name=tName)
-                            tom.add_entity_partition(
-                                table_name=tName,
-                                entity_name=tName.replace(" ", "_").lower(),
-                            )
-
-                    columns_in_table = dfC_filt.loc[
-                        dfC_filt["Table Name"] == tName, "Column Name"
-                    ].unique()
-
-                    for cName in columns_in_table:
-                        scName = dfC.loc[
-                            (dfC["Table Name"] == tName)
-                            & (dfC["Column Name"] == cName),
-                            "Source",
-                        ].iloc[0]
-                        cDataType = dfC.loc[
-                            (dfC["Table Name"] == tName)
-                            & (dfC["Column Name"] == cName),
-                            "Data Type",
-                        ].iloc[0]
-                        cType = dfC.loc[
-                            (dfC["Table Name"] == tName)
-                            & (dfC["Column Name"] == cName),
-                            "Type",
-                        ].iloc[0]
-
-                        # av = tom.get_annotation_value(object = tom.model, name = tName)
-
-                        # if cType == 'CalculatedTableColumn':
-                        # lakeColumn = scName.replace(' ','_')
-                        # elif cType == 'Calculated':
-                        pattern = r"\[([^]]+)\]"
-
-                        matches = re.findall(pattern, scName)
-                        lakeColumn = matches[0].replace(" ", "")
-                        try:
-                            tom.model.Tables[tName].Columns[cName]
-                        except:
-                            tom.add_data_column(
-                                table_name=tName,
-                                column_name=cName,
-                                source_column=lakeColumn,
-                                data_type=cDataType,
-                            )
-                            print(
-                                f"{icons.green_dot} The '{tName}'[{cName}] column has been added."
-                            )
-
-                print(
-                    f"\n{icons.green_dot} All viable calculated tables have been added to the model."
-                )
-
-        except Exception as e:
-            if datetime.datetime.now() - start_time > timeout:
-                break
-            time.sleep(1)
+    @retry(
+        sleep_time=1,
+        timeout_error_message=f"{icons.red_dot} Function timed out after 1 minute",
+    )
+    def dyn_connect():
+        with connect_semantic_model(
+            dataset=new_dataset, readonly=True, workspace=new_dataset_workspace
+        ) as tom:
+
+            tom.model
+
+    dyn_connect()
+
+    with connect_semantic_model(
+        dataset=new_dataset, readonly=False, workspace=new_dataset_workspace
+    ) as tom:
+        for tName in dfC_filt["Table Name"].unique():
+            if tName.lower() in lc["Table Name"].values:
+                if not any(t.Name == tName for t in tom.model.Tables):
+                    tom.add_table(name=tName)
+                    tom.add_entity_partition(
+                        table_name=tName,
+                        entity_name=tName.replace(" ", "_").lower(),
+                    )
+
+            columns_in_table = dfC_filt.loc[
+                dfC_filt["Table Name"] == tName, "Column Name"
+            ].unique()
+
+            for cName in columns_in_table:
+                scName = dfC.loc[
+                    (dfC["Table Name"] == tName) & (dfC["Column Name"] == cName),
+                    "Source",
+                ].iloc[0]
+                cDataType = dfC.loc[
+                    (dfC["Table Name"] == tName) & (dfC["Column Name"] == cName),
+                    "Data Type",
+                ].iloc[0]
+                # cType = dfC.loc[
+                #    (dfC["Table Name"] == tName)
+                #    & (dfC["Column Name"] == cName),
+                #    "Type",
+                # ].iloc[0]
+
+                # av = tom.get_annotation_value(object = tom.model, name = tName)
+
+                # if cType == 'CalculatedTableColumn':
+                # lakeColumn = scName.replace(' ','_')
+                # elif cType == 'Calculated':
+                pattern = r"\[([^]]+)\]"
+
+                matches = re.findall(pattern, scName)
+                lakeColumn = matches[0].replace(" ", "")
+                if not any(
+                    c.Name == cName and c.Parent.Name == tName
+                    for c in tom.all_columns()
+                ):
+                    tom.add_data_column(
+                        table_name=tName,
+                        column_name=cName,
+                        source_column=lakeColumn,
+                        data_type=cDataType,
+                    )
+                    print(
+                        f"{icons.green_dot} The {format_dax_object_name(tName,cName)} column has been added."
+                    )
+
+        print(
+            f"\n{icons.green_dot} All viable calculated tables have been added to the model."
+        )