Spaces:
Running
Running
File size: 11,767 Bytes
09801ca | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 | # MCP SQL Executor Module
"""
SQL execution tools for MCP integration using DuckDB.
Features:
- In-memory SQL execution
- DataFrame to table conversion
- Query result formatting
- Aggregation support
"""
from typing import Dict, List, Optional, Any
import json
# Global DuckDB connection
_connection = None
def _get_connection():
"""Get or create DuckDB connection"""
global _connection
if _connection is None:
try:
import duckdb
_connection = duckdb.connect(':memory:')
except ImportError:
return None
return _connection
def execute_sql(
query: str,
data: Optional[Dict[str, Any]] = None
) -> Dict:
"""
Execute SQL query on data.
Args:
query: SQL query string
data: Dict mapping table names to DataFrames
Returns:
Query results
"""
try:
conn = _get_connection()
if conn is None:
# Fallback to pandas-based execution
return _execute_sql_pandas(query, data)
import duckdb
# Register DataFrames as tables
if data:
for table_name, df_data in data.items():
import pandas as pd
if isinstance(df_data, pd.DataFrame):
df = df_data
elif isinstance(df_data, list):
df = pd.DataFrame(df_data)
elif isinstance(df_data, dict):
df = pd.DataFrame(df_data)
else:
continue
conn.register(table_name, df)
# Execute query
result = conn.execute(query)
# Get column names
columns = [desc[0] for desc in result.description] if result.description else []
# Fetch results
rows = result.fetchall()
# Convert to list of dicts
records = []
for row in rows:
record = {}
for i, col in enumerate(columns):
val = row[i]
# Convert to JSON-serializable types
if hasattr(val, 'item'): # numpy types
val = val.item()
record[col] = val
records.append(record)
return {
"success": True,
"columns": columns,
"data": records,
"row_count": len(records)
}
except Exception as e:
return {
"success": False,
"error": str(e),
"data": []
}
def _execute_sql_pandas(query: str, data: Optional[Dict] = None) -> Dict:
"""Fallback SQL execution using pandas and sqlite"""
try:
import pandas as pd
import sqlite3
# Create in-memory SQLite connection
conn = sqlite3.connect(':memory:')
# Load DataFrames as tables
if data:
for table_name, df_data in data.items():
if isinstance(df_data, pd.DataFrame):
df = df_data
elif isinstance(df_data, list):
df = pd.DataFrame(df_data)
elif isinstance(df_data, dict):
df = pd.DataFrame(df_data)
else:
continue
df.to_sql(table_name, conn, index=False, if_exists='replace')
# Execute query
result_df = pd.read_sql_query(query, conn)
conn.close()
return {
"success": True,
"columns": list(result_df.columns),
"data": result_df.to_dict(orient='records'),
"row_count": len(result_df)
}
except Exception as e:
return {
"success": False,
"error": str(e),
"data": []
}
def create_table_from_df(
name: str,
df: Any,
replace: bool = True
) -> Dict:
"""
Create virtual table from DataFrame.
Args:
name: Table name
df: DataFrame to register
replace: Whether to replace existing table
Returns:
Table creation result
"""
try:
conn = _get_connection()
if conn is None:
return {
"success": False,
"error": "DuckDB not available",
"table_name": None
}
import pandas as pd
if not isinstance(df, pd.DataFrame):
if isinstance(df, list):
df = pd.DataFrame(df)
elif isinstance(df, dict):
df = pd.DataFrame(df)
else:
return {
"success": False,
"error": "Invalid data type",
"table_name": None
}
conn.register(name, df)
return {
"success": True,
"table_name": name,
"columns": list(df.columns),
"row_count": len(df)
}
except Exception as e:
return {
"success": False,
"error": str(e),
"table_name": None
}
def query_to_dataframe(query: str) -> Dict:
"""
Execute query and return DataFrame result.
Args:
query: SQL query string
Returns:
Query result as DataFrame dict
"""
try:
conn = _get_connection()
if conn is None:
return {
"success": False,
"error": "DuckDB not available",
"dataframe": None
}
import pandas as pd
result_df = conn.execute(query).fetchdf()
return {
"success": True,
"dataframe": result_df.to_dict(orient='records'),
"columns": list(result_df.columns),
"row_count": len(result_df)
}
except Exception as e:
return {
"success": False,
"error": str(e),
"dataframe": None
}
def aggregate_data(
table_or_df: Any,
group_by: List[str],
aggregations: Dict[str, str]
) -> Dict:
"""
Perform aggregation on data.
Args:
table_or_df: Table name (str) or DataFrame
group_by: Columns to group by
aggregations: Dict of {column: agg_function}
agg_function: "sum", "avg", "count", "min", "max"
Returns:
Aggregated results
"""
try:
import pandas as pd
if isinstance(table_or_df, str):
# It's a table name, query it
conn = _get_connection()
if conn is None:
return {
"success": False,
"error": "DuckDB not available",
"data": None
}
df = conn.execute(f"SELECT * FROM {table_or_df}").fetchdf()
elif isinstance(table_or_df, pd.DataFrame):
df = table_or_df
else:
df = pd.DataFrame(table_or_df)
# Build aggregation dict for pandas
agg_map = {
"sum": "sum",
"avg": "mean",
"count": "count",
"min": "min",
"max": "max",
"mean": "mean"
}
pandas_agg = {}
for col, func in aggregations.items():
if col in df.columns:
pandas_agg[col] = agg_map.get(func.lower(), func)
# Perform aggregation
if group_by:
result = df.groupby(group_by).agg(pandas_agg).reset_index()
else:
result = df.agg(pandas_agg).to_frame().T
return {
"success": True,
"data": result.to_dict(orient='records'),
"columns": list(result.columns),
"row_count": len(result)
}
except Exception as e:
return {
"success": False,
"error": str(e),
"data": None
}
def join_tables(
left_table: Any,
right_table: Any,
left_on: str,
right_on: str,
how: str = "inner"
) -> Dict:
"""
Join two tables.
Args:
left_table: Left table name or DataFrame
right_table: Right table name or DataFrame
left_on: Left join column
right_on: Right join column
how: Join type ("inner", "left", "right", "outer")
Returns:
Joined table
"""
try:
import pandas as pd
# Convert to DataFrames
if isinstance(left_table, str):
conn = _get_connection()
left_df = conn.execute(f"SELECT * FROM {left_table}").fetchdf()
else:
left_df = pd.DataFrame(left_table)
if isinstance(right_table, str):
conn = _get_connection()
right_df = conn.execute(f"SELECT * FROM {right_table}").fetchdf()
else:
right_df = pd.DataFrame(right_table)
# Perform join
result = pd.merge(left_df, right_df, left_on=left_on, right_on=right_on, how=how)
return {
"success": True,
"data": result.to_dict(orient='records'),
"columns": list(result.columns),
"row_count": len(result)
}
except Exception as e:
return {
"success": False,
"error": str(e),
"data": None
}
def filter_data(
table_or_df: Any,
conditions: List[Dict]
) -> Dict:
"""
Filter data based on conditions.
Args:
table_or_df: Table name or DataFrame
conditions: List of {column, operator, value}
operator: "=", "!=", ">", "<", ">=", "<=", "in", "like"
Returns:
Filtered data
"""
try:
import pandas as pd
if isinstance(table_or_df, str):
conn = _get_connection()
df = conn.execute(f"SELECT * FROM {table_or_df}").fetchdf()
else:
df = pd.DataFrame(table_or_df)
result = df.copy()
for cond in conditions:
col = cond.get("column")
op = cond.get("operator", "=")
val = cond.get("value")
if col not in result.columns:
continue
if op == "=" or op == "==":
result = result[result[col] == val]
elif op == "!=":
result = result[result[col] != val]
elif op == ">":
result = result[result[col] > val]
elif op == "<":
result = result[result[col] < val]
elif op == ">=":
result = result[result[col] >= val]
elif op == "<=":
result = result[result[col] <= val]
elif op == "in":
result = result[result[col].isin(val)]
elif op == "like":
result = result[result[col].str.contains(val, case=False, na=False)]
return {
"success": True,
"data": result.to_dict(orient='records'),
"columns": list(result.columns),
"row_count": len(result),
"original_count": len(df)
}
except Exception as e:
return {
"success": False,
"error": str(e),
"data": None
}
def reset_connection():
"""Reset the DuckDB connection"""
global _connection
_connection = None
return {"success": True, "message": "Connection reset"}
|