Logging de DataStore

from pathlib import Path
Path("data.csv").write_text("""\
name,age,city,salary,department
Alice,25,NYC,55000,Engineering
Bob,30,LA,65000,Product
Charlie,35,NYC,80000,Engineering
Diana,28,SF,70000,Design
Eve,42,NYC,95000,Product
""")

from chdb import datastore as pd
from chdb.datastore.config import config

# Habilitar el logging de depuración
config.enable_debug()

# Ahora todas las operaciones registrarán detalles
ds = pd.read_csv("data.csv")
result = ds.filter(ds['age'] > 25).to_df()

import logging
from chdb.datastore.config import config

# Usando niveles de registro estándar
config.set_log_level(logging.DEBUG)
config.set_log_level(logging.INFO)
config.set_log_level(logging.WARNING)  # Predeterminado
config.set_log_level(logging.ERROR)

# Usando configuración rápida
config.enable_debug()  # Establece el nivel DEBUG + formato detallado

DEBUG - Creating DataStore from file 'data.csv'
DEBUG - SQL: SELECT * FROM file('data.csv', 'CSVWithNames') WHERE age > 25
DEBUG - Using engine: chdb
DEBUG - Execution time: 0.089s
DEBUG - Cache: Storing result (key: abc123)

INFO - Loaded 1,000,000 rows from data.csv
INFO - Execution engine set to: chdb
INFO - Connected to MySQL: localhost:3306/mydb

WARNING - Large result set (>1M rows) may cause memory issues
WARNING - Cache TTL exceeded, re-executing query
WARNING - Column 'date' has mixed types, using string

ERROR - Failed to execute SQL: syntax error near 'FORM'
ERROR - Connection to MySQL failed: timeout
ERROR - Cannot convert column 'price' to float

import logging

# Configurar el root logger
logging.basicConfig(
    level=logging.DEBUG,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
    handlers=[
        logging.FileHandler('datastore.log'),
        logging.StreamHandler()
    ]
)

# Obtener el logger de DataStore
ds_logger = logging.getLogger('chdb.datastore')
ds_logger.setLevel(logging.DEBUG)

import logging

# Crear manejador de archivo
file_handler = logging.FileHandler('datastore_debug.log')
file_handler.setLevel(logging.DEBUG)
file_handler.setFormatter(logging.Formatter(
    '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
))

# Agregar al logger de DataStore
ds_logger = logging.getLogger('chdb.datastore')
ds_logger.addHandler(file_handler)

import logging

# Suprimir todos los logs de DataStore
logging.getLogger('chdb.datastore').setLevel(logging.CRITICAL)

# O usando config
config.set_log_level(logging.CRITICAL)

config.enable_debug()

ds = pd.read_csv("data.csv")
result = ds.filter(ds['age'] > 25).groupby('city').sum()

DEBUG - Creating DataStore from file 'data.csv'
DEBUG - Building filter: age > 25
DEBUG - Building groupby: city
DEBUG - Building aggregation: sum
DEBUG - Generated SQL:
        SELECT city, SUM(*) 
        FROM file('data.csv', 'CSVWithNames')
        WHERE age > 25
        GROUP BY city

config.enable_debug()

result = ds.filter(ds['x'] > 10).apply(custom_func)

DEBUG - filter: selecting engine (eligible: chdb, pandas)
DEBUG - filter: using chdb (SQL-compatible)
DEBUG - apply: selecting engine (eligible: pandas)
DEBUG - apply: using pandas (custom function)

config.enable_debug()

# Primera ejecución
result1 = ds.filter(ds['age'] > 25).to_df()
# DEBUG - Fallo de caché para el hash de consulta abc123
# DEBUG - Ejecutando consulta...
# DEBUG - Almacenando resultado en caché (key: abc123, size: 1.2MB)

# Segunda ejecución (misma consulta)
result2 = ds.filter(ds['age'] > 25).to_df()
# DEBUG - Acierto de caché para el hash de consulta abc123
# DEBUG - Devolviendo resultado en caché

config.enable_debug()
config.enable_profiling()

# Los registros mostrarán el tiempo de cada operación
result = (ds
    .filter(ds['amount'] > 100)
    .groupby('region')
    .agg({'amount': 'sum'})
    .to_df()
)

DEBUG - filter: 0.002ms
DEBUG - groupby: 0.001ms
DEBUG - agg: 0.003ms
DEBUG - SQL generation: 0.012ms
DEBUG - SQL execution: 89.456ms  <- Aquí es donde se concentra el tiempo
DEBUG - Result conversion: 2.345ms

import logging
from chdb.datastore.config import config

# Producción: logging mínimo
config.set_log_level(logging.WARNING)
config.set_log_format("simple")
config.set_profiling_enabled(False)

import logging
from logging.handlers import RotatingFileHandler

# Crear manejador de archivo rotativo
handler = RotatingFileHandler(
    'datastore.log',
    maxBytes=10*1024*1024,  # 10MB
    backupCount=5
)
handler.setLevel(logging.WARNING)

# Agregar al logger de DataStore
logging.getLogger('chdb.datastore').addHandler(handler)

# Establecer el nivel de log
export CHDB_LOG_LEVEL=DEBUG

# Establecer el formato de log
export CHDB_LOG_FORMAT=verbose

import os
import logging

# Leer desde el entorno
log_level = os.environ.get('CHDB_LOG_LEVEL', 'WARNING')
config.set_log_level(getattr(logging, log_level))