egutierrez
47fac22230
- .claude/CLAUDE.md - .claude/commands/subagentes.md - .claude/rules/INDEX.md - .mcp.json - bash/functions/cybersecurity/analyze_dns.md - bash/functions/cybersecurity/audit_http_headers.md - bash/functions/cybersecurity/audit_ssh_config.md - bash/functions/cybersecurity/check_firewall.md - bash/functions/cybersecurity/detect_suspicious_users.md - bash/functions/cybersecurity/encrypt_file.md - ... Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
70 lines
2.3 KiB
Markdown
70 lines
2.3 KiB
Markdown
---
|
|
name: bq_query
|
|
kind: function
|
|
lang: py
|
|
domain: infra
|
|
version: "1.0.0"
|
|
purity: impure
|
|
signature: "def bq_query(client: BQClient, sql: str, params: list[dict] | None = None, dry_run: bool = False) -> dict"
|
|
description: "Ejecuta una query SQL en BigQuery con soporte para parametros tipados y modo dry-run para estimacion de costos."
|
|
tags: [bigquery, gcp, query, sql, google-cloud, python, pendiente-usar]
|
|
uses_functions: []
|
|
uses_types: []
|
|
returns: []
|
|
returns_optional: false
|
|
error_type: "error_go_core"
|
|
imports: [google-cloud-bigquery]
|
|
params:
|
|
- name: client
|
|
desc: "cliente BQClient autenticado contra el proyecto GCP"
|
|
- name: sql
|
|
desc: "query SQL a ejecutar; usar @nombre para referencias a parametros tipados"
|
|
- name: params
|
|
desc: "lista de parametros tipados, cada uno con {name, type, value}; tipos: STRING, INT64, FLOAT64, BOOL, DATE, TIMESTAMP"
|
|
- name: dry_run
|
|
desc: "si True, estima bytes procesados/facturados sin ejecutar la query"
|
|
output: "si dry_run=True: {total_bytes_processed, total_bytes_billed}; si False: {columns, rows, total_rows, bytes_processed, cache_hit}"
|
|
tested: false
|
|
tests: []
|
|
test_file_path: ""
|
|
file_path: "python/functions/bigquery/queries.py"
|
|
---
|
|
|
|
## Ejemplo
|
|
|
|
```python
|
|
from bigquery.client import bq_auth
|
|
from bigquery.queries import bq_query
|
|
|
|
client = bq_auth("my-project")
|
|
|
|
# Query simple
|
|
result = bq_query(client, "SELECT COUNT(*) as n FROM `my_project.dataset.table`")
|
|
print(result["columns"]) # ["n"]
|
|
print(result["rows"]) # [[12345]]
|
|
|
|
# Con parametros
|
|
result = bq_query(
|
|
client,
|
|
"SELECT * FROM `dataset.users` WHERE status = @s AND age > @a",
|
|
params=[
|
|
{"name": "s", "type": "STRING", "value": "active"},
|
|
{"name": "a", "type": "INT64", "value": 18},
|
|
],
|
|
)
|
|
|
|
# Dry-run para estimar costo
|
|
est = bq_query(client, "SELECT * FROM `dataset.big_table`", dry_run=True)
|
|
print(f"Procesaria {est['total_bytes_processed'] / 1e9:.2f} GB")
|
|
```
|
|
|
|
## Notas
|
|
|
|
Usa `bigquery.ScalarQueryParameter` para parametros — solo soporta escalares. Para arrays
|
|
usar `bigquery.ArrayQueryParameter` directamente si se necesita.
|
|
|
|
En dry_run=True el job se crea pero no se ejecuta; `job.result()` no se llama. BigQuery
|
|
retorna la estimacion de bytes sin cargo.
|
|
|
|
`cache_hit=True` indica que el resultado provino de la cache de BigQuery (sin costo).
|