|
| 1 | +# Licensed to the Apache Software Foundation (ASF) under one |
| 2 | +# or more contributor license agreements. See the NOTICE file |
| 3 | +# distributed with this work for additional information |
| 4 | +# regarding copyright ownership. The ASF licenses this file |
| 5 | +# to you under the Apache License, Version 2.0 (the |
| 6 | +# "License"); you may not use this file except in compliance |
| 7 | +# with the License. You may obtain a copy of the License at |
| 8 | +# |
| 9 | +# http://www.apache.org/licenses/LICENSE-2.0 |
| 10 | +# |
| 11 | +# Unless required by applicable law or agreed to in writing, |
| 12 | +# software distributed under the License is distributed on an |
| 13 | +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| 14 | +# KIND, either express or implied. See the License for the |
| 15 | +# specific language governing permissions and limitations |
| 16 | +# under the License. |
| 17 | + |
| 18 | +""" |
| 19 | +Pydantic schemas for query history-related responses |
| 20 | +""" |
| 21 | + |
| 22 | +from __future__ import annotations |
| 23 | + |
| 24 | +from datetime import datetime |
| 25 | +from typing import Annotated, Any, Dict, List, Literal |
| 26 | + |
| 27 | +from pydantic import ( |
| 28 | + BaseModel, |
| 29 | + ConfigDict, |
| 30 | + Field, |
| 31 | + field_validator, |
| 32 | + model_serializer, |
| 33 | + model_validator, |
| 34 | + PositiveInt, |
| 35 | +) |
| 36 | + |
| 37 | +from superset.daos.base import ColumnOperator, ColumnOperatorEnum |
| 38 | +from superset.mcp_service.constants import MAX_PAGE_SIZE |
| 39 | +from superset.mcp_service.privacy import filter_user_directory_fields |
| 40 | +from superset.mcp_service.system.schemas import PaginationInfo |
| 41 | +from superset.mcp_service.utils.schema_utils import ( |
| 42 | + parse_json_or_list, |
| 43 | + parse_json_or_model_list, |
| 44 | +) |
| 45 | + |
| 46 | +DEFAULT_QUERY_COLUMNS = ["id", "sql", "status", "start_time", "database_id", "schema"] |
| 47 | +SORTABLE_QUERY_COLUMNS = [ |
| 48 | + "id", |
| 49 | + "start_time", |
| 50 | + "end_time", |
| 51 | + "status", |
| 52 | + "database_id", |
| 53 | +] |
| 54 | +ALL_QUERY_COLUMNS = [ |
| 55 | + "id", |
| 56 | + "sql", |
| 57 | + "status", |
| 58 | + "start_time", |
| 59 | + "end_time", |
| 60 | + "rows", |
| 61 | + "database_id", |
| 62 | + "schema", |
| 63 | + "tab_name", |
| 64 | + "error_message", |
| 65 | + "client_id", |
| 66 | + "limit", |
| 67 | + "progress", |
| 68 | + "changed_on", |
| 69 | +] |
| 70 | + |
| 71 | +DEFAULT_QUERY_PAGE_SIZE = 25 |
| 72 | + |
| 73 | + |
| 74 | +class QueryFilter(ColumnOperator): |
| 75 | + """ |
| 76 | + Filter object for query history listing. |
| 77 | + col: The column to filter on. Must be one of the allowed filter fields. |
| 78 | + opr: The operator to use. Must be one of the supported operators. |
| 79 | + value: The value to filter by (type depends on col and opr). |
| 80 | + """ |
| 81 | + |
| 82 | + col: Literal["status", "database_id", "schema"] = Field( |
| 83 | + ..., |
| 84 | + description="Column to filter on.", |
| 85 | + ) |
| 86 | + opr: ColumnOperatorEnum = Field( |
| 87 | + ..., |
| 88 | + description="Operator to use.", |
| 89 | + ) |
| 90 | + value: str | int | float | bool | List[str | int | float | bool] = Field( |
| 91 | + ..., description="Value to filter by (type depends on col and opr)" |
| 92 | + ) |
| 93 | + |
| 94 | + |
| 95 | +class QueryInfo(BaseModel): |
| 96 | + id: int | None = Field(None, description="Query ID") |
| 97 | + sql: str | None = Field(None, description="SQL query text") |
| 98 | + status: str | None = Field(None, description="Query execution status") |
| 99 | + start_time: float | None = Field( |
| 100 | + None, description="Query start time (seconds since epoch)" |
| 101 | + ) |
| 102 | + end_time: float | None = Field( |
| 103 | + None, description="Query end time (seconds since epoch)" |
| 104 | + ) |
| 105 | + rows: int | None = Field(None, description="Number of rows returned or affected") |
| 106 | + database_id: int | None = Field(None, description="Database connection ID") |
| 107 | + schema: str | None = Field(None, description="Database schema name") |
| 108 | + tab_name: str | None = Field(None, description="SQL Lab tab name") |
| 109 | + error_message: str | None = Field(None, description="Error message if query failed") |
| 110 | + client_id: str | None = Field(None, description="Client-assigned query identifier") |
| 111 | + limit: int | None = Field(None, description="Row limit applied to the query") |
| 112 | + progress: int | None = Field(None, description="Query execution progress (0-100)") |
| 113 | + changed_on: str | datetime | None = Field( |
| 114 | + None, description="Last modification timestamp" |
| 115 | + ) |
| 116 | + model_config = ConfigDict( |
| 117 | + from_attributes=True, |
| 118 | + ser_json_timedelta="iso8601", |
| 119 | + populate_by_name=True, |
| 120 | + ) |
| 121 | + |
| 122 | + @model_serializer(mode="wrap") |
| 123 | + def _filter_fields_by_context(self, serializer: Any, info: Any) -> Dict[str, Any]: |
| 124 | + data = filter_user_directory_fields(serializer(self)) |
| 125 | + |
| 126 | + if info.context and isinstance(info.context, dict): |
| 127 | + select_columns = info.context.get("select_columns") |
| 128 | + if select_columns: |
| 129 | + requested_fields = set(select_columns) |
| 130 | + return {k: v for k, v in data.items() if k in requested_fields} |
| 131 | + |
| 132 | + return data |
| 133 | + |
| 134 | + |
| 135 | +class QueryList(BaseModel): |
| 136 | + queries: List[QueryInfo] |
| 137 | + count: int |
| 138 | + total_count: int |
| 139 | + page: int |
| 140 | + page_size: int |
| 141 | + total_pages: int |
| 142 | + has_previous: bool |
| 143 | + has_next: bool |
| 144 | + columns_requested: List[str] = Field( |
| 145 | + default_factory=list, |
| 146 | + description="Requested columns for the response", |
| 147 | + ) |
| 148 | + columns_loaded: List[str] = Field( |
| 149 | + default_factory=list, |
| 150 | + description="Columns that were actually loaded for each query", |
| 151 | + ) |
| 152 | + columns_available: List[str] = Field( |
| 153 | + default_factory=list, |
| 154 | + description="All columns available for selection via select_columns parameter", |
| 155 | + ) |
| 156 | + sortable_columns: List[str] = Field( |
| 157 | + default_factory=list, |
| 158 | + description="Columns that can be used with order_column parameter", |
| 159 | + ) |
| 160 | + filters_applied: List[QueryFilter] = Field( |
| 161 | + default_factory=list, |
| 162 | + description="List of advanced filter dicts applied to the query.", |
| 163 | + ) |
| 164 | + pagination: PaginationInfo | None = None |
| 165 | + timestamp: datetime | None = None |
| 166 | + model_config = ConfigDict(ser_json_timedelta="iso8601") |
| 167 | + |
| 168 | + |
| 169 | +class ListQueriesRequest(BaseModel): |
| 170 | + """Request schema for list_queries.""" |
| 171 | + |
| 172 | + filters: Annotated[ |
| 173 | + List[QueryFilter], |
| 174 | + Field( |
| 175 | + default_factory=list, |
| 176 | + description="List of filter objects (column, operator, value). Each " |
| 177 | + "filter is an object with 'col', 'opr', and 'value' " |
| 178 | + "properties. Cannot be used together with 'search'.", |
| 179 | + ), |
| 180 | + ] |
| 181 | + select_columns: Annotated[ |
| 182 | + List[str], |
| 183 | + Field( |
| 184 | + default_factory=list, |
| 185 | + description="List of columns to select. Defaults to common columns if not " |
| 186 | + "specified.", |
| 187 | + ), |
| 188 | + ] |
| 189 | + search: Annotated[ |
| 190 | + str | None, |
| 191 | + Field( |
| 192 | + default=None, |
| 193 | + description="Text search string to match against query fields. " |
| 194 | + "Cannot be used together with 'filters'.", |
| 195 | + ), |
| 196 | + ] |
| 197 | + order_column: Annotated[ |
| 198 | + str | None, |
| 199 | + Field(default=None, description="Column to order results by"), |
| 200 | + ] |
| 201 | + order_direction: Annotated[ |
| 202 | + Literal["asc", "desc"], |
| 203 | + Field( |
| 204 | + default="desc", |
| 205 | + description="Direction to order results ('asc' or 'desc')", |
| 206 | + ), |
| 207 | + ] |
| 208 | + page: Annotated[ |
| 209 | + PositiveInt, |
| 210 | + Field(default=1, description="Page number for pagination (1-based)"), |
| 211 | + ] |
| 212 | + page_size: Annotated[ |
| 213 | + int, |
| 214 | + Field( |
| 215 | + default=DEFAULT_QUERY_PAGE_SIZE, |
| 216 | + gt=0, |
| 217 | + le=MAX_PAGE_SIZE, |
| 218 | + description=f"Number of items per page (max {MAX_PAGE_SIZE})", |
| 219 | + ), |
| 220 | + ] |
| 221 | + |
| 222 | + @field_validator("filters", mode="before") |
| 223 | + @classmethod |
| 224 | + def parse_filters(cls, v: Any) -> List[QueryFilter]: |
| 225 | + """Accept both JSON string and list of objects.""" |
| 226 | + return parse_json_or_model_list(v, QueryFilter, "filters") |
| 227 | + |
| 228 | + @field_validator("select_columns", mode="before") |
| 229 | + @classmethod |
| 230 | + def parse_columns(cls, v: Any) -> List[str]: |
| 231 | + """Accept JSON array, list, or comma-separated string.""" |
| 232 | + return parse_json_or_list(v, "select_columns") |
| 233 | + |
| 234 | + @model_validator(mode="after") |
| 235 | + def validate_search_and_filters(self) -> "ListQueriesRequest": |
| 236 | + """Prevent using both search and filters simultaneously.""" |
| 237 | + if self.search and self.filters: |
| 238 | + raise ValueError( |
| 239 | + "Cannot use both 'search' and 'filters' parameters simultaneously. " |
| 240 | + "Use either 'search' for text-based searching across multiple fields, " |
| 241 | + "or 'filters' for precise column-based filtering, but not both." |
| 242 | + ) |
| 243 | + return self |
| 244 | + |
| 245 | + |
| 246 | +class QueryError(BaseModel): |
| 247 | + error: str = Field(..., description="Error message") |
| 248 | + error_type: str = Field(..., description="Type of error") |
| 249 | + timestamp: str | datetime | None = Field(None, description="Error timestamp") |
| 250 | + model_config = ConfigDict(ser_json_timedelta="iso8601") |
| 251 | + |
| 252 | + @classmethod |
| 253 | + def create(cls, error: str, error_type: str) -> "QueryError": |
| 254 | + """Create a standardized QueryError with timestamp.""" |
| 255 | + from datetime import datetime, timezone |
| 256 | + |
| 257 | + return cls( |
| 258 | + error=error, error_type=error_type, timestamp=datetime.now(timezone.utc) |
| 259 | + ) |
| 260 | + |
| 261 | + |
| 262 | +class GetQueryInfoRequest(BaseModel): |
| 263 | + """Request schema for get_query_info with support for numeric ID only.""" |
| 264 | + |
| 265 | + identifier: Annotated[ |
| 266 | + int, |
| 267 | + Field(description="Query ID (numeric)"), |
| 268 | + ] |
| 269 | + |
| 270 | + |
| 271 | +def serialize_query_object(query: Any) -> QueryInfo | None: |
| 272 | + if not query: |
| 273 | + return None |
| 274 | + |
| 275 | + return QueryInfo( |
| 276 | + id=getattr(query, "id", None), |
| 277 | + sql=getattr(query, "sql", None), |
| 278 | + status=getattr(query, "status", None), |
| 279 | + start_time=getattr(query, "start_time", None), |
| 280 | + end_time=getattr(query, "end_time", None), |
| 281 | + rows=getattr(query, "rows", None), |
| 282 | + database_id=getattr(query, "database_id", None), |
| 283 | + schema=getattr(query, "schema", None), |
| 284 | + tab_name=getattr(query, "tab_name", None), |
| 285 | + error_message=getattr(query, "error_message", None), |
| 286 | + client_id=getattr(query, "client_id", None), |
| 287 | + limit=getattr(query, "limit", None), |
| 288 | + progress=getattr(query, "progress", None), |
| 289 | + changed_on=getattr(query, "changed_on", None), |
| 290 | + ) |
0 commit comments