|
| 1 | +from sempy_labs._helper_functions import ( |
| 2 | + resolve_workspace_name_and_id, |
| 3 | + _base_api, |
| 4 | + _create_dataframe, |
| 5 | + _update_dataframe_datatypes, |
| 6 | + delete_item, |
| 7 | + resolve_workspace_id, |
| 8 | +) |
| 9 | +import pandas as pd |
| 10 | +from typing import Optional |
| 11 | +import sempy_labs._icons as icons |
| 12 | +from uuid import UUID |
| 13 | +from sempy._utils._log import log |
| 14 | + |
| 15 | + |
| 16 | +@log |
| 17 | +def create_warehouse( |
| 18 | + warehouse: str, |
| 19 | + description: Optional[str] = None, |
| 20 | + case_insensitive_collation: bool = False, |
| 21 | + workspace: Optional[str | UUID] = None, |
| 22 | +) -> UUID: |
| 23 | + """ |
| 24 | + Creates a Fabric warehouse. |
| 25 | +
|
| 26 | + This is a wrapper function for the following API: `Items - Create Warehouse <https://learn.microsoft.com/rest/api/fabric/warehouse/items/create-warehouse>`_. |
| 27 | +
|
| 28 | + Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples). |
| 29 | +
|
| 30 | + Parameters |
| 31 | + ---------- |
| 32 | + warehouse: str |
| 33 | + Name of the warehouse. |
| 34 | + description : str, default=None |
| 35 | + A description of the warehouse. |
| 36 | + case_insensitive_collation: bool, default=False |
| 37 | + If True, creates the warehouse with case-insensitive collation. |
| 38 | + workspace : str | uuid.UUID, default=None |
| 39 | + The Fabric workspace name or ID. |
| 40 | + Defaults to None which resolves to the workspace of the attached lakehouse |
| 41 | + or if no lakehouse attached, resolves to the workspace of the notebook. |
| 42 | +
|
| 43 | + Returns |
| 44 | + ------- |
| 45 | + uuid.UUID |
| 46 | + The ID of the created warehouse. |
| 47 | + """ |
| 48 | + |
| 49 | + (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace) |
| 50 | + |
| 51 | + payload = {"displayName": warehouse} |
| 52 | + |
| 53 | + if description: |
| 54 | + payload["description"] = description |
| 55 | + if case_insensitive_collation: |
| 56 | + payload.setdefault("creationPayload", {}) |
| 57 | + payload["creationPayload"][ |
| 58 | + "defaultCollation" |
| 59 | + ] = "Latin1_General_100_CI_AS_KS_WS_SC_UTF8" |
| 60 | + |
| 61 | + result = _base_api( |
| 62 | + request=f"/v1/workspaces/{workspace_id}/warehouses", |
| 63 | + payload=payload, |
| 64 | + method="post", |
| 65 | + lro_return_json=True, |
| 66 | + status_codes=[201, 202], |
| 67 | + client="fabric_sp", |
| 68 | + ) |
| 69 | + |
| 70 | + print( |
| 71 | + f"{icons.green_dot} The '{warehouse}' warehouse has been created within the '{workspace_name}' workspace." |
| 72 | + ) |
| 73 | + |
| 74 | + return result.get("id") |
| 75 | + |
| 76 | + |
| 77 | +@log |
| 78 | +def list_warehouses(workspace: Optional[str | UUID] = None) -> pd.DataFrame: |
| 79 | + """ |
| 80 | + Shows the warehouses within a workspace. |
| 81 | +
|
| 82 | + This is a wrapper function for the following API: `Items - List Warehouses <https://learn.microsoft.com/rest/api/fabric/warehouse/items/list-warehouses>`_. |
| 83 | +
|
| 84 | + Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples). |
| 85 | +
|
| 86 | + Parameters |
| 87 | + ---------- |
| 88 | + workspace : str | uuid.UUID, default=None |
| 89 | + The Fabric workspace name or ID. |
| 90 | + Defaults to None which resolves to the workspace of the attached lakehouse |
| 91 | + or if no lakehouse attached, resolves to the workspace of the notebook. |
| 92 | +
|
| 93 | + Returns |
| 94 | + ------- |
| 95 | + pandas.DataFrame |
| 96 | + A pandas dataframe showing the warehouses within a workspace. |
| 97 | + """ |
| 98 | + |
| 99 | + columns = { |
| 100 | + "Warehouse Name": "string", |
| 101 | + "Warehouse Id": "string", |
| 102 | + "Description": "string", |
| 103 | + "Connection Info": "string", |
| 104 | + "Created Date": "datetime", |
| 105 | + "Last Updated Time": "datetime", |
| 106 | + } |
| 107 | + df = _create_dataframe(columns=columns) |
| 108 | + |
| 109 | + workspace_id = resolve_workspace_id(workspace) |
| 110 | + |
| 111 | + responses = _base_api( |
| 112 | + request=f"/v1/workspaces/{workspace_id}/warehouses", |
| 113 | + uses_pagination=True, |
| 114 | + client="fabric_sp", |
| 115 | + ) |
| 116 | + |
| 117 | + rows = [] |
| 118 | + for r in responses: |
| 119 | + for v in r.get("value", []): |
| 120 | + prop = v.get("properties", {}) |
| 121 | + |
| 122 | + rows.append( |
| 123 | + { |
| 124 | + "Warehouse Name": v.get("displayName"), |
| 125 | + "Warehouse Id": v.get("id"), |
| 126 | + "Description": v.get("description"), |
| 127 | + "Connection Info": prop.get("connectionInfo"), |
| 128 | + "Created Date": prop.get("createdDate"), |
| 129 | + "Last Updated Time": prop.get("lastUpdatedTime"), |
| 130 | + } |
| 131 | + ) |
| 132 | + |
| 133 | + if rows: |
| 134 | + df = pd.DataFrame(rows, columns=list(columns.keys())) |
| 135 | + _update_dataframe_datatypes(dataframe=df, column_map=columns) |
| 136 | + |
| 137 | + return df |
| 138 | + |
| 139 | + |
| 140 | +@log |
| 141 | +def delete_warehouse(name: str | UUID, workspace: Optional[str | UUID] = None): |
| 142 | + """ |
| 143 | + Deletes a Fabric warehouse. |
| 144 | +
|
| 145 | + This is a wrapper function for the following API: `Items - Delete Warehouse <https://learn.microsoft.com/rest/api/fabric/warehouse/items/delete-warehouse>`_. |
| 146 | +
|
| 147 | + Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples). |
| 148 | +
|
| 149 | + Parameters |
| 150 | + ---------- |
| 151 | + name: str | uuid.UUID |
| 152 | + Name or ID of the warehouse. |
| 153 | + workspace : str | uuid.UUID, default=None |
| 154 | + The Fabric workspace name or ID. |
| 155 | + Defaults to None which resolves to the workspace of the attached lakehouse |
| 156 | + or if no lakehouse attached, resolves to the workspace of the notebook. |
| 157 | + """ |
| 158 | + |
| 159 | + delete_item(item=name, type="Warehouse", workspace=workspace) |
| 160 | + |
| 161 | + |
| 162 | +@log |
| 163 | +def get_warehouse_tables( |
| 164 | + warehouse: str | UUID, workspace: Optional[str | UUID] = None |
| 165 | +) -> pd.DataFrame: |
| 166 | + """ |
| 167 | + Shows a list of the tables in the Fabric warehouse. This function is based on INFORMATION_SCHEMA.TABLES. |
| 168 | +
|
| 169 | + Parameters |
| 170 | + ---------- |
| 171 | + warehouse : str | uuid.UUID |
| 172 | + Name or ID of the Fabric warehouse. |
| 173 | + workspace : str | uuid.UUID, default=None |
| 174 | + The Fabric workspace name or ID. |
| 175 | + Defaults to None which resolves to the workspace of the attached lakehouse |
| 176 | + or if no lakehouse attached, resolves to the workspace of the notebook. |
| 177 | +
|
| 178 | + Returns |
| 179 | + ------- |
| 180 | + pandas.DataFrame |
| 181 | + A pandas dataframe showing a list of the tables in the Fabric warehouse. |
| 182 | + """ |
| 183 | + |
| 184 | + from sempy_labs._sql import ConnectWarehouse |
| 185 | + |
| 186 | + with ConnectWarehouse(warehouse=warehouse, workspace=workspace) as sql: |
| 187 | + df = sql.query( |
| 188 | + """ |
| 189 | + SELECT TABLE_SCHEMA AS [Schema], TABLE_NAME AS [Table Name], TABLE_TYPE AS [Table Type] |
| 190 | + FROM INFORMATION_SCHEMA.TABLES |
| 191 | + WHERE TABLE_TYPE = 'BASE TABLE' |
| 192 | + """ |
| 193 | + ) |
| 194 | + |
| 195 | + return df |
| 196 | + |
| 197 | + |
| 198 | +@log |
| 199 | +def get_warehouse_columns( |
| 200 | + warehouse: str | UUID, workspace: Optional[str | UUID] = None |
| 201 | +) -> pd.DataFrame: |
| 202 | + """ |
| 203 | + Shows a list of the columns in each table within the Fabric warehouse. This function is based on INFORMATION_SCHEMA.COLUMNS. |
| 204 | +
|
| 205 | + Parameters |
| 206 | + ---------- |
| 207 | + warehouse : str | uuid.UUID |
| 208 | + Name or ID of the Fabric warehouse. |
| 209 | + workspace : str | uuid.UUID, default=None |
| 210 | + The Fabric workspace name or ID. |
| 211 | + Defaults to None which resolves to the workspace of the attached lakehouse |
| 212 | + or if no lakehouse attached, resolves to the workspace of the notebook. |
| 213 | +
|
| 214 | + Returns |
| 215 | + ------- |
| 216 | + pandas.DataFrame |
| 217 | + A pandas dataframe showing a list of the columns in each table within the Fabric warehouse. |
| 218 | + """ |
| 219 | + |
| 220 | + from sempy_labs._sql import ConnectWarehouse |
| 221 | + |
| 222 | + with ConnectWarehouse(warehouse=warehouse, workspace=workspace) as sql: |
| 223 | + df = sql.query( |
| 224 | + """ |
| 225 | + SELECT t.TABLE_SCHEMA AS [Schema], t.TABLE_NAME AS [Table Name], c.COLUMN_NAME AS [Column Name], c.DATA_TYPE AS [Data Type], c.IS_NULLABLE AS [Is Nullable], c.CHARACTER_MAXIMUM_LENGTH AS [Character Max Length] |
| 226 | + FROM INFORMATION_SCHEMA.TABLES AS t |
| 227 | + LEFT JOIN INFORMATION_SCHEMA.COLUMNS AS c |
| 228 | + ON t.TABLE_NAME = c.TABLE_NAME |
| 229 | + AND t.TABLE_SCHEMA = c.TABLE_SCHEMA |
| 230 | + WHERE t.TABLE_TYPE = 'BASE TABLE' |
| 231 | + """ |
| 232 | + ) |
| 233 | + |
| 234 | + return df |
0 commit comments