data_drain 0.5.0 → 0.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c92c85e6232344565dc090539d3d58aa47904ca1e454b696ba4eba12e2648881
-  data.tar.gz: 1b3332ac50288dfd6793aed0c51ab8fa49d8dc309f7bc8dd4a642ecffd97e3cd
+  metadata.gz: 036367c9d2512c4a9a2785bbef6efeaaf9ee013ee31c013e1527001f91f22d65
+  data.tar.gz: c7dc050b51c3024ad9e2e62ae57e28bb549fee9a0341aea5ee524d4b55a07da5
 SHA512:
-  metadata.gz: d0cecb3d168ad96943b9cc70eb936e9b95e92d03dc0bd08ed5996ac1967ef627191802892097abf3b094d5b59515c150ca8edc4ffcefe13be8b4a2d7721a180a
-  data.tar.gz: 45018ca7e4287bf055cb7060e5720f83da318bd7c9ad44a30d8e832972feb1eb99d29286a9813128d4f84171d4c032e12f9a4f4dd7cc0022b36e44a3098d91c8
+  metadata.gz: 9ed7fb071a8d1f0c103c44c402279b9b575b535944a21db6f260b5d2aa4da2675f56095a9d79d1054c8e4c48ac578a955673befde82a84ca030ee508adf11e8e
+  data.tar.gz: f4c3665f97d5f4c287f70a715bd4fc36264bae977f868bb5f062bade177527cb6bfb10dbaf6c83fb6280ab2fce4787bf8abc1789fa9fb5893ac99f3a0a2b1ee0

data/CHANGELOG.md

@@ -1,5 +1,12 @@
 ## [Unreleased]
 
+## [0.5.1] - 2026-04-15
+
+### Docs
+
+- `skill/references/eventos-telemetria.md`: nuevos eventos `script_uploaded` y `script_upload_error`.
+- `README.md`: ejemplos de `script_path` en GlueRunner y observabilidad.
+
 ## [0.5.0] - 2026-04-15
 
 ### Features

data/README.md

@@ -115,11 +115,13 @@ DataDrain::GlueRunner.job_exists?("my-glue-export-job")
 job = DataDrain::GlueRunner.get_job("my-glue-export-job")
 # => Aws::Glue::Types::Job (Name, Command, DefaultArguments, etc.)
 
-# Crear un job
+# Crear un job con script local (v0.5.0+)
 job = DataDrain::GlueRunner.create_job(
   "my-glue-export-job",
   role_arn: "arn:aws:iam::123:role/GlueServiceRole",
-  script_location: "s3://my-bucket/scripts/export.py",
+  script_path: "scripts/glue/export.py",  # local → S3 automático
+  script_bucket: "my-bucket",
+  script_folder: "scripts",
   default_arguments: { "--extra-files" => "s3://my-bucket/scripts/udf.py" },
   timeout: 1440,
   max_retries: 2
@@ -129,8 +131,9 @@ job = DataDrain::GlueRunner.create_job(
 job = DataDrain::GlueRunner.ensure_job(
   "my-glue-export-job",
   role_arn: "arn:aws:iam::123:role/GlueServiceRole",
-  script_location: "s3://my-bucket/scripts/export.py",
-  timeout: 1440
+  script_path: "scripts/glue/export.py",
+  script_bucket: "my-bucket",
+  script_folder: "scripts"
 )
 
 # Eliminar un job
@@ -198,6 +201,7 @@ ArchivedVersion.destroy_all(year: 2024, month: 3)    # un mes globalmente
 ```
 component=data_drain event=engine.complete table=versions duration_s=12.4 export_duration_s=8.1 purge_duration_s=3.9 count=150000
 component=data_drain event=engine.purge_heartbeat table=versions batches_processed_count=100 rows_deleted_count=500000
+component=data_drain event=glue_runner.script_uploaded local_path=scripts/glue/export.py s3_path=s3://my-bucket/scripts/export.py bytes=4521
 component=data_drain event=glue_runner.failed job=my-export-job run_id=jr_abc123 status=FAILED duration_s=301.0
 ```
 

data/lib/data_drain/version.rb

@@ -2,5 +2,5 @@
 
 module DataDrain
   # @return [String] versión semver de la gema
-  VERSION = "0.5.0"
+  VERSION = "0.5.1"
 end

data/skill/SKILL.md

@@ -70,7 +70,7 @@ DataDrain resuelve el ciclo de vida de datos históricos en bases relacionales c
 
 - Ruby `>= 3.2.0`
 - Runtime: `activemodel >= 6.0`, `duckdb ~> 1.4`, `pg >= 1.2`, `aws-sdk-s3 ~> 1.114`, `aws-sdk-glue ~> 1.0`
-- Versión actual: `0.5.0`
+- Versión actual: `0.5.1`
 
 ## API Pública (resumen)
 

data/skill/references/eventos-telemetria.md

@@ -115,6 +115,15 @@ Catálogo completo de eventos KV emitidos por DataDrain. Formato Wispro-Observab
 **Nivel:** INFO. Emite antes de `start_job_run`.
 **Campos:** `job`.
 
+### `glue_runner.script_uploaded`
+**Nivel:** INFO. Emite tras subir un script a S3 (v0.5.0+).
+**Campos:** `local_path`, `s3_path`, `bytes`.
+
+### `glue_runner.script_upload_error`
+**Nivel:** ERROR. Emite si el upload a S3 falla (v0.5.0+).
+**Campos:** `local_path`, `bucket`, `error_class`, `error_message`.
+**Consecuencia:** propaga el `Aws::S3::Errors::ServiceError`.
+
 ### `glue_runner.job_exists`
 **Nivel:** INFO. Emite en `ensure_job` cuando el job ya existe y se actualiza.
 **Campos:** `job`.

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: data_drain
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.5.1
 platform: ruby
 authors:
 - Gabriel
@@ -104,11 +104,11 @@ files:
 - docs/execution/archive/v0.3.0.md
 - docs/execution/archive/v0.3.1-OBSERVACIONES.md
 - docs/execution/archive/v0.3.1.md
+- docs/execution/archives/v0.5.0-OBSERVACIONES.md
+- docs/execution/archives/v0.5.0.md
 - docs/execution/v0.2.2.md
 - docs/execution/v0.4.0-OBSERVACIONES.md
 - docs/execution/v0.4.0.md
-- docs/execution/v0.5.0-OBSERVACIONES.md
-- docs/execution/v0.5.0.md
 - docs/glue-jobs-lifecycle.md
 - docs/glue_pyspark_example.py
 - lib/data_drain.rb