From c16c374d1c378b3167b9f9fd78e75963dbb7864e Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 13:04:35 +0000
Subject: [PATCH 01/24] first commit

---
 README.md | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 README.md

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..33bb4f1
--- /dev/null
+++ b/README.md
@@ -0,0 +1 @@
+# repositorio-teste

From 0f6d71f1e198e63110b5a5aa18adaa2940309c25 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 13:08:07 +0000
Subject: [PATCH 02/24] first commit

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 33bb4f1..cd0bd6c 100644
--- a/README.md
+++ b/README.md
@@ -1 +1 @@
-# repositorio-teste
+# repositorio-teste - 

From 5e326f317e737b76ef7ee91a4a1871668ad62fac Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 13:14:30 +0000
Subject: [PATCH 03/24] Removendo dab_test do GitHub mas mantendo localmente

---
 dab_test | 1 -
 1 file changed, 1 deletion(-)
 delete mode 160000 dab_test

diff --git a/dab_test b/dab_test
deleted file mode 160000
index 2850ef9..0000000
--- a/dab_test
+++ /dev/null
@@ -1 +0,0 @@
-Subproject commit 2850ef9a66e0c9446329cbf7c384c69139185c2e

From 2191879b0a5d3d9a54b50e308d32d8020eb62cf7 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 13:15:37 +0000
Subject: [PATCH 04/24] first commit

---
 README.md                                     |   2 +-
 dab_test/.vscode/__builtins__.pyi             |   3 +
 dab_test/.vscode/extensions.json              |   7 +
 dab_test/.vscode/settings.json                |  39 +++++
 dab_test/AGENTS.md                            |  25 +++
 dab_test/CLAUDE.md                            |   6 +
 dab_test/README.md                            |  71 +++++++++
 dab_test/databricks.yml                       |  48 ++++++
 dab_test/fixtures/.gitkeep                    |   9 ++
 dab_test/pyproject.toml                       |  31 ++++
 dab_test/resources/dab_test_job.yml           |  36 +++++
 dab_test/src/dab_test/__init__.py             |   0
 dab_test/src/dab_test/main.py                 |  14 ++
 dab_test/src/dab_test_etl/README.md           |  20 +++
 .../explorations/sample_exploration.ipynb     |  63 ++++++++
 .../transformations/sample_trips_dab_test.py  |  12 ++
 .../transformations/sample_zones_dab_test.py  |  17 ++
 dab_test/src/notebooks/demo_notebooks.py      |  30 ++++
 dab_test/src/sample_notebook.ipynb            | 149 ++++++++++++++++++
 dab_test/tests/job_config_test.py             |  51 ++++++
 dab_test/tests/main_test.py                   |   6 +
 21 files changed, 638 insertions(+), 1 deletion(-)
 create mode 100644 dab_test/.vscode/__builtins__.pyi
 create mode 100644 dab_test/.vscode/extensions.json
 create mode 100644 dab_test/.vscode/settings.json
 create mode 100644 dab_test/AGENTS.md
 create mode 100644 dab_test/CLAUDE.md
 create mode 100644 dab_test/README.md
 create mode 100644 dab_test/databricks.yml
 create mode 100644 dab_test/fixtures/.gitkeep
 create mode 100644 dab_test/pyproject.toml
 create mode 100644 dab_test/resources/dab_test_job.yml
 create mode 100644 dab_test/src/dab_test/__init__.py
 create mode 100644 dab_test/src/dab_test/main.py
 create mode 100644 dab_test/src/dab_test_etl/README.md
 create mode 100644 dab_test/src/dab_test_etl/explorations/sample_exploration.ipynb
 create mode 100644 dab_test/src/dab_test_etl/transformations/sample_trips_dab_test.py
 create mode 100644 dab_test/src/dab_test_etl/transformations/sample_zones_dab_test.py
 create mode 100644 dab_test/src/notebooks/demo_notebooks.py
 create mode 100644 dab_test/src/sample_notebook.ipynb
 create mode 100644 dab_test/tests/job_config_test.py
 create mode 100644 dab_test/tests/main_test.py

diff --git a/README.md b/README.md
index cd0bd6c..146bb9e 100644
--- a/README.md
+++ b/README.md
@@ -1 +1 @@
-# repositorio-teste - 
+# repositorio-teste 
diff --git a/dab_test/.vscode/__builtins__.pyi b/dab_test/.vscode/__builtins__.pyi
new file mode 100644
index 0000000..0edd518
--- /dev/null
+++ b/dab_test/.vscode/__builtins__.pyi
@@ -0,0 +1,3 @@
+# Typings for Pylance in Visual Studio Code
+# see https://github.com/microsoft/pyright/blob/main/docs/builtins.md
+from databricks.sdk.runtime import *
diff --git a/dab_test/.vscode/extensions.json b/dab_test/.vscode/extensions.json
new file mode 100644
index 0000000..b958aac
--- /dev/null
+++ b/dab_test/.vscode/extensions.json
@@ -0,0 +1,7 @@
+{
+    "recommendations": [
+        "charliermarsh.ruff",
+        "databricks.databricks",
+        "redhat.vscode-yaml"
+    ]
+}
diff --git a/dab_test/.vscode/settings.json b/dab_test/.vscode/settings.json
new file mode 100644
index 0000000..d73c73b
--- /dev/null
+++ b/dab_test/.vscode/settings.json
@@ -0,0 +1,39 @@
+{
+    "jupyter.interactiveWindow.cellMarker.codeRegex": "^# COMMAND ----------|^# Databricks notebook source|^(#\\s*%%|#\\s*\\<codecell\\>|#\\s*In\\[\\d*?\\]|#\\s*In\\[ \\])",
+    "jupyter.interactiveWindow.cellMarker.default": "# COMMAND ----------",
+    "python.testing.pytestArgs": [
+        "."
+    ],
+    "files.exclude": {
+        "**/*.egg-info": true,
+        "**/__pycache__": true,
+        ".pytest_cache": true,
+        "dist": true,
+    },
+    "files.associations": {
+        "**/.gitkeep": "markdown"
+    },
+
+    // Pylance settings (VS Code)
+    // Set typeCheckingMode to "basic" to enable type checking!
+    "python.analysis.typeCheckingMode": "off",
+    "python.analysis.extraPaths": ["src", "lib", "resources"],
+    "python.analysis.diagnosticMode": "workspace",
+    "python.analysis.stubPath": ".vscode",
+
+    // Pyright settings (Cursor)
+    // Set typeCheckingMode to "basic" to enable type checking!
+    "cursorpyright.analysis.typeCheckingMode": "off",
+    "cursorpyright.analysis.extraPaths": ["src", "lib", "resources"],
+    "cursorpyright.analysis.diagnosticMode": "workspace",
+    "cursorpyright.analysis.stubPath": ".vscode",
+
+    // General Python settings
+    "python.defaultInterpreterPath": "./.venv/bin/python",
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "[python]": {
+        "editor.defaultFormatter": "charliermarsh.ruff",
+        "editor.formatOnSave": true,
+    },
+}
diff --git a/dab_test/AGENTS.md b/dab_test/AGENTS.md
new file mode 100644
index 0000000..fdcca98
--- /dev/null
+++ b/dab_test/AGENTS.md
@@ -0,0 +1,25 @@
+# Declarative Automation Bundles Project
+
+This project uses Declarative Automation Bundles (DABs) for deployment. Add project-specific instructions below.
+
+## For AI Agents: Use Databricks AI Tools
+
+**BEFORE any other action, read the `databricks-core` skill.**
+
+It sets you up to work with this project reliably: CLI authentication, profile
+selection, data discovery, and the bundle deployment workflow. Without it,
+results are often slower and less accurate.
+
+If this skill is not available (Databricks AI Tools are not installed), you can install them for your coding agent in seconds:
+
+```bash
+databricks aitools install
+```
+
+If the CLI is not installed, see: https://docs.databricks.com/dev-tools/cli/install
+
+---
+
+## Project Instructions
+
+<!-- Add your project-specific instructions, coding conventions, or notes here -->
diff --git a/dab_test/CLAUDE.md b/dab_test/CLAUDE.md
new file mode 100644
index 0000000..5612c9b
--- /dev/null
+++ b/dab_test/CLAUDE.md
@@ -0,0 +1,6 @@
+# CLAUDE.md
+
+Project guidance for AI agents lives in AGENTS.md.
+Claude Code loads it via the import below.
+
+@AGENTS.md
diff --git a/dab_test/README.md b/dab_test/README.md
new file mode 100644
index 0000000..bdf9c44
--- /dev/null
+++ b/dab_test/README.md
@@ -0,0 +1,71 @@
+# dab_test
+
+The 'dab_test' project was generated by using the default-python template.
+
+* `src/`: Python source code for this project.
+  * `src/dab_test/`: Shared Python code that can be used by jobs and pipelines.
+* `resources/`:  Resource configurations (jobs, pipelines, etc.)
+* `tests/`: Unit tests for the shared Python code.
+* `fixtures/`: Fixtures for data sets (primarily used for testing).
+
+
+## Getting started
+
+Choose how you want to work on this project:
+
+(a) Directly in your Databricks workspace, see
+    https://docs.databricks.com/dev-tools/bundles/workspace.
+
+(b) Locally with an IDE like Cursor or VS Code, see
+    https://docs.databricks.com/dev-tools/vscode-ext.html.
+
+(c) With command line tools, see https://docs.databricks.com/dev-tools/cli/databricks-cli.html
+
+If you're developing with an IDE, dependencies for this project should be installed using uv:
+
+*  Make sure you have the UV package manager installed.
+   It's an alternative to tools like pip: https://docs.astral.sh/uv/getting-started/installation/.
+*  Run `uv sync --dev` to install the project's dependencies.
+
+
+# Using this project using the CLI
+
+The Databricks workspace and IDE extensions provide a graphical interface for working
+with this project. It's also possible to interact with it directly using the CLI:
+
+1. Authenticate to your Databricks workspace, if you have not done so already:
+    ```
+    $ databricks configure
+    ```
+
+2. To deploy a development copy of this project, type:
+    ```
+    $ databricks bundle deploy --target dev
+    ```
+    (Note that "dev" is the default target, so the `--target` parameter
+    is optional here.)
+
+    This deploys everything that's defined for this project.
+    For example, the default template would deploy a pipeline called
+    `[dev yourname] dab_test_etl` to your workspace.
+    You can find that resource by opening your workpace and clicking on **Jobs & Pipelines**.
+
+3. Similarly, to deploy a production copy, type:
+   ```
+   $ databricks bundle deploy --target prod
+   ```
+   Note the default template has a includes a job that runs the pipeline every day
+   (defined in resources/sample_job.job.yml). The schedule
+   is paused when deploying in development mode (see
+   https://docs.databricks.com/dev-tools/bundles/deployment-modes.html).
+
+4. To run a job or pipeline, use the "run" command:
+   ```
+   $ databricks bundle run
+   ```
+
+5. Finally, to run tests locally, use `pytest`:
+   ```
+   $ uv run pytest
+   ```
+video 01
diff --git a/dab_test/databricks.yml b/dab_test/databricks.yml
new file mode 100644
index 0000000..ad36d9e
--- /dev/null
+++ b/dab_test/databricks.yml
@@ -0,0 +1,48 @@
+# This is a Declarative Automation Bundle definition for dab_test.
+# See https://docs.databricks.com/dev-tools/bundles/index.html for documentation.
+bundle:
+  name: dab_test
+  uuid: 348afa13-f395-4806-9fcf-f5fc52935756
+
+include:
+  - resources/jobs/*.yml
+  - resources/pipelines/*.yml
+  - resources/schemas/*.yml
+
+artifacts:
+  python_artifact:
+    type: whl
+    build: uv build --wheel
+  
+# Variable declarations. These variables are assigned in the dev/prod targets below.
+variables:
+  catalog:
+    description: The catalog to use
+  schema:
+    description: The schema to use
+
+targets:
+  dev:
+    # The default target uses 'mode: development' to create a development copy.
+    # - Deployed resources get prefixed with '[dev my_user_name]'
+    # - Any job schedules and triggers are paused by default.
+    # See also https://docs.databricks.com/dev-tools/bundles/deployment-modes.html.
+    mode: development
+    default: true
+    workspace:
+      host: https://dbc-39ee3252-8e93.cloud.databricks.com
+    variables:
+      catalog: dev
+      schema: dev
+  prod:
+    mode: production
+    workspace:
+      host: https://dbc-39ee3252-8e93.cloud.databricks.com
+      # We explicitly deploy to /Workspace/Users/rubencruzh@gmail.com to make sure we only have a single copy.
+      root_path: /Workspace/Users/rubencruzh@gmail.com/.bundle/${bundle.name}/${bundle.target}
+    variables:
+      catalog: dev
+      schema: prod
+    permissions:
+      - user_name: rubencruzh@gmail.com
+        level: CAN_MANAGE
diff --git a/dab_test/fixtures/.gitkeep b/dab_test/fixtures/.gitkeep
new file mode 100644
index 0000000..77a9066
--- /dev/null
+++ b/dab_test/fixtures/.gitkeep
@@ -0,0 +1,9 @@
+# Test fixtures directory
+
+Add JSON or CSV files here. In tests, use them with `load_fixture()`:
+
+```
+def test_using_fixture(load_fixture):
+    data = load_fixture("my_data.json")
+    assert len(data) >= 1
+```
diff --git a/dab_test/pyproject.toml b/dab_test/pyproject.toml
new file mode 100644
index 0000000..8fee306
--- /dev/null
+++ b/dab_test/pyproject.toml
@@ -0,0 +1,31 @@
+[project]
+name = "dab_test"
+version = "0.0.1"
+authors = [{ name = "rubencruzh@gmail.com" }]
+requires-python = ">=3.10,<3.13"
+dependencies = [
+    # Any dependencies for jobs and pipelines in this project can be added here
+    # See also https://docs.databricks.com/dev-tools/bundles/library-dependencies
+    #
+    # LIMITATION: for pipelines, dependencies are cached during development;
+    # add dependencies to the 'environment' section of your pipeline.yml file instead
+]
+
+[dependency-groups]
+dev = [
+    "pytest",
+    "ruff",
+    "databricks-dlt",
+    "databricks-connect>=15.4,<15.5",
+    "ipykernel",
+]
+
+[project.scripts]
+main = "dab_test.main:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.ruff]
+line-length = 120
diff --git a/dab_test/resources/dab_test_job.yml b/dab_test/resources/dab_test_job.yml
new file mode 100644
index 0000000..209811c
--- /dev/null
+++ b/dab_test/resources/dab_test_job.yml
@@ -0,0 +1,36 @@
+# Job do treinamento para executar o notebook demo.
+resources:
+  jobs:
+    dab_test_job:
+      name: dab_test_job
+      tags:
+        treinamento: dab
+        ambiente: dev
+        area: engenharia
+      description: Job de treinamento que ingere usuários de exemplo com parâmetros dinâmicos.
+      parameters:
+        - name: catalog_name
+          default: ${var.catalog_name}
+        - name: user_id
+          default: "3"
+        - name: user_name
+          default: "Anselmo"
+      email_notifications:
+        on_failure:
+          - anselmoborges@gmail.com
+      timeout_seconds: 900
+      schedule:
+        quartz_cron_expression: "0 0 8 ? * TUE *"
+        timezone_id: America/Sao_Paulo
+      tasks:
+        - task_key: ingestao_usuarios
+          description: Ingestão de usuários de exemplo via notebook.
+          notebook_task:
+            notebook_path: ../../src/notebooks/demo_notebook.py
+            base_parameters:
+              catalog_name: "{{job.parameters.catalog_name}}"
+              user_id: "{{job.parameters.user_id}}"
+              user_name: "{{job.parameters.user_name}}"
+      queue:
+        enabled: true
+      performance_target: ${var.performance_target}
\ No newline at end of file
diff --git a/dab_test/src/dab_test/__init__.py b/dab_test/src/dab_test/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/dab_test/src/dab_test/main.py b/dab_test/src/dab_test/main.py
new file mode 100644
index 0000000..aadae50
--- /dev/null
+++ b/dab_test/src/dab_test/main.py
@@ -0,0 +1,14 @@
+from databricks.sdk.runtime import spark
+from pyspark.sql import DataFrame
+
+
+def find_all_taxis() -> DataFrame:
+    return spark.read.table("samples.nyctaxi.trips")
+
+
+def main():
+    find_all_taxis().show(5)
+
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file
diff --git a/dab_test/src/dab_test_etl/README.md b/dab_test/src/dab_test_etl/README.md
new file mode 100644
index 0000000..30f31d3
--- /dev/null
+++ b/dab_test/src/dab_test_etl/README.md
@@ -0,0 +1,20 @@
+# dab_test
+
+This folder defines all source code for the dab_test pipeline:
+
+- `explorations/`: Ad-hoc notebooks used to explore the data processed by this pipeline.
+- `transformations/`: All dataset definitions and transformations.
+- `utilities/` (optional): Utility functions and Python modules used in this pipeline.
+- `data_sources/` (optional): View definitions describing the source data for this pipeline.
+
+## Getting Started
+
+To get started, go to the `transformations` folder -- most of the relevant source code lives there:
+
+* By convention, every dataset under `transformations` is in a separate file.
+* Take a look at the sample called "sample_trips_dab_test.py" to get familiar with the syntax.
+  Read more about the syntax at https://docs.databricks.com/dlt/python-ref.html.
+* If you're using the workspace UI, use `Run file` to run and preview a single transformation.
+* If you're using the CLI, use `databricks bundle run dab_test_etl --refresh sample_trips_dab_test` to run a single transformation.
+
+For more tutorials and reference material, see https://docs.databricks.com/dlt.
diff --git a/dab_test/src/dab_test_etl/explorations/sample_exploration.ipynb b/dab_test/src/dab_test_etl/explorations/sample_exploration.ipynb
new file mode 100644
index 0000000..6b3bc19
--- /dev/null
+++ b/dab_test/src/dab_test_etl/explorations/sample_exploration.ipynb
@@ -0,0 +1,63 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {},
+     "inputWidgets": {},
+     "nuid": "19a992e9-55e0-49e4-abc7-8c92c420dd5b",
+     "showTitle": false,
+     "tableResultSettingsMap": {},
+     "title": ""
+    }
+   },
+   "source": [
+    "### Example Exploratory Notebook\n",
+    "\n",
+    "Use this notebook to explore the data generated by the pipeline in your preferred programming language.\n",
+    "\n",
+    "**Note**: This notebook is not executed as part of the pipeline."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {},
+     "inputWidgets": {},
+     "nuid": "1b0a82fa-3c6a-4f29-bb43-ded1c4fd77c6",
+     "showTitle": false,
+     "tableResultSettingsMap": {},
+     "title": ""
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# !!! Before performing any data analysis, make sure to run the pipeline to materialize the sample datasets. The tables referenced in this notebook depend on that step.\n",
+    "\n",
+    "display(spark.sql(\"SELECT * FROM dev.rubencruzh.sample_trips_dab_test\"))"
+   ]
+  }
+ ],
+ "metadata": {
+  "application/vnd.databricks.v1+notebook": {
+   "computePreferences": null,
+   "dashboards": [],
+   "environmentMetadata": null,
+   "inputWidgetPreferences": null,
+   "language": "python",
+   "notebookMetadata": {
+    "pythonIndentUnit": 2
+   },
+   "notebookName": "sample_exploration",
+   "widgets": {}
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/dab_test/src/dab_test_etl/transformations/sample_trips_dab_test.py b/dab_test/src/dab_test_etl/transformations/sample_trips_dab_test.py
new file mode 100644
index 0000000..c739b02
--- /dev/null
+++ b/dab_test/src/dab_test_etl/transformations/sample_trips_dab_test.py
@@ -0,0 +1,12 @@
+from pyspark import pipelines as dp
+from pyspark.sql.functions import col
+
+
+# This file defines a sample transformation.
+# Edit the sample below or add new transformations
+# using "+ Add" in the file browser.
+
+
+@dp.table
+def sample_trips_dab_test():
+    return spark.read.table("samples.nyctaxi.trips")
diff --git a/dab_test/src/dab_test_etl/transformations/sample_zones_dab_test.py b/dab_test/src/dab_test_etl/transformations/sample_zones_dab_test.py
new file mode 100644
index 0000000..a8c936e
--- /dev/null
+++ b/dab_test/src/dab_test_etl/transformations/sample_zones_dab_test.py
@@ -0,0 +1,17 @@
+from pyspark import pipelines as dp
+from pyspark.sql.functions import col, sum
+
+
+# This file defines a sample transformation.
+# Edit the sample below or add new transformations
+# using "+ Add" in the file browser.
+
+
+@dp.table
+def sample_zones_dab_test():
+    # Read from the "sample_trips" table, then sum all the fares
+    return (
+        spark.read.table(f"sample_trips_dab_test")
+        .groupBy(col("pickup_zip"))
+        .agg(sum("fare_amount").alias("total_fare"))
+    )
diff --git a/dab_test/src/notebooks/demo_notebooks.py b/dab_test/src/notebooks/demo_notebooks.py
new file mode 100644
index 0000000..a56304d
--- /dev/null
+++ b/dab_test/src/notebooks/demo_notebooks.py
@@ -0,0 +1,30 @@
+# Databricks notebook source
+# DBTITLE 1,Configura widgets de entrada
+dbutils.widgets.text("catalog", "dev", "Catalog Name")
+dbutils.widgets.text("user_id", "3", "User ID")
+dbutils.widgets.text("user_name", "Anselmo", "User Name")
+
+# COMMAND ----------
+# DBTITLE 1,Obtém valores informados
+catalog_name = dbutils.widgets.get("catalog")
+user_id = int(dbutils.widgets.get("user_id"))
+user_name = dbutils.widgets.get("user_name")
+print(f"Using Catalog: {catalog_name}")
+print(f"Inserting user_id={user_id}, user_name={user_name}")
+
+# COMMAND ----------
+# DBTITLE 1,Cria tabela e insere dados de exemplo + parâmetro
+spark.sql(
+    f"CREATE TABLE IF NOT EXISTS {catalog_name}.rescue_b.users (id INT, name STRING)"
+)
+spark.sql(
+    f"INSERT OVERWRITE {catalog_name}.rescue_b.users VALUES (1, 'Alice'), (2, 'Bob')"
+)
+spark.sql(
+    f"INSERT INTO {catalog_name}.rescue_b.users VALUES ({user_id}, '{user_name}')"
+)
+
+# COMMAND ----------
+# DBTITLE 1,Lê os dados inseridos
+result_df = spark.sql(f"SELECT * FROM {catalog_name}.rescue_b.users ORDER BY id")
+display(result_df)
\ No newline at end of file
diff --git a/dab_test/src/sample_notebook.ipynb b/dab_test/src/sample_notebook.ipynb
new file mode 100644
index 0000000..1f32293
--- /dev/null
+++ b/dab_test/src/sample_notebook.ipynb
@@ -0,0 +1,149 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {},
+     "inputWidgets": {},
+     "nuid": "ee353e42-ff58-4955-9608-12865bd0950e",
+     "showTitle": false,
+     "title": ""
+    }
+   },
+   "source": [
+    "# Default notebook\n",
+    "\n",
+    "This default notebook is executed using a Lakeflow job as defined in resources/sample_job.job.yml."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {},
+     "inputWidgets": {},
+     "nuid": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
+     "showTitle": false,
+     "title": ""
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Set default catalog and schema\n",
+    "catalog = dbutils.widgets.get(\"catalog\")\n",
+    "schema = dbutils.widgets.get(\"schema\")\n",
+    "spark.sql(f\"USE CATALOG {catalog}\")\n",
+    "spark.sql(f\"USE SCHEMA {schema}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "6bca260b-13d1-448f-8082-30b60a85c9ae",
+     "showTitle": false,
+     "title": ""
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "\n",
+    "sys.path.append(\"../src\")\n",
+    "from dab_test import taxis\n",
+    "\n",
+    "taxis.find_all_taxis().show(10)"
+   ]
+  }
+ ],
+ "metadata": {
+  "application/vnd.databricks.v1+notebook": {
+   "dashboards": [],
+   "environmentMetadata": {
+    "base_environment": "",
+    "dependencies": [
+     "--editable .."
+    ],
+    "environment_version": "4"
+   },
+   "language": "python",
+   "notebookMetadata": {
+    "pythonIndentUnit": 2
+   },
+   "notebookName": "notebook",
+   "widgets": {
+    "catalog": {
+     "currentValue": "dev",
+     "nuid": "c4t4l0g-w1dg-3t12-3456-789012345678",
+     "typedWidgetInfo": {
+      "autoCreated": false,
+      "defaultValue": "dev",
+      "label": "Catalog",
+      "name": "catalog",
+      "options": {
+       "validationRegex": null,
+       "widgetDisplayType": "Text"
+      },
+      "parameterDataType": "String"
+     },
+     "widgetInfo": {
+      "defaultValue": "dev",
+      "label": "Catalog",
+      "name": "catalog",
+      "options": {
+       "autoCreated": false,
+       "validationRegex": null,
+       "widgetType": "text"
+      },
+      "widgetType": "text"
+     }
+    },
+    "schema": {
+     "currentValue": "rubencruzh",
+     "nuid": "5ch3m4-w1dg-3t98-7654-321098765432",
+     "typedWidgetInfo": {
+      "autoCreated": false,
+      "defaultValue": "default",
+      "label": "Schema",
+      "name": "schema",
+      "options": {
+       "validationRegex": null,
+       "widgetDisplayType": "Text"
+      },
+      "parameterDataType": "String"
+     },
+     "widgetInfo": {
+      "defaultValue": "default",
+      "label": "Schema",
+      "name": "schema",
+      "options": {
+       "autoCreated": false,
+       "validationRegex": null,
+       "widgetType": "text"
+      },
+      "widgetType": "text"
+     }
+    }
+   }
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/dab_test/tests/job_config_test.py b/dab_test/tests/job_config_test.py
new file mode 100644
index 0000000..921bf3a
--- /dev/null
+++ b/dab_test/tests/job_config_test.py
@@ -0,0 +1,51 @@
+from pathlib import Path
+import yaml
+
+ROOT = Path(__file__).resolve().parents[1]
+JOB_FILE = ROOT / "resources" / "jobs" / "dab_treinamento.job.yml"
+
+
+def _load_job():
+    data = yaml.safe_load(JOB_FILE.read_text())
+    job = data["resources"]["jobs"]["dab_treinamento_job"]
+    return job
+
+
+def test_job_has_description_and_tags():
+    job = _load_job()
+    print("Validando descrição do job...")
+    assert job.get("description"), "Job description must be set"
+    print("Descrição OK!")
+    tags = job.get("tags", {})
+    print(f"Validando tags obrigatórias: {list(tags.keys())}")
+    for tag_key in ("treinamento", "ambiente", "area"):
+        assert tag_key in tags, f"Tag '{tag_key}' está ausente"
+    print("Tags obrigatórias OK!")
+
+
+def test_job_has_schedule_and_timeout():
+    job = _load_job()
+    print("Validando agendamento e timeout...")
+    schedule = job.get("schedule")
+    assert schedule, "Job schedule deve estar configurado"
+    print(f"Agendamento encontrado: {schedule['quartz_cron_expression']} ({schedule['timezone_id']})")
+    assert schedule["quartz_cron_expression"].lower() == "0 0 8 ? * tue *"
+    assert schedule["timezone_id"] == "America/Sao_Paulo"
+    assert job.get("timeout_seconds") == 900
+    print("Agendamento e timeout OK!")
+
+
+def test_job_parameters_exposed():
+    job = _load_job()
+    params = {p["name"]: p["default"] for p in job.get("parameters", [])}
+    print(f"Validando parâmetros expostos: {list(params.keys())}")
+    for expected in ("catalog_name", "user_id", "user_name"):
+        assert expected in params, f"Parâmetro '{expected}' não configurado"
+    print("Parâmetros obrigatórios OK!")
+
+
+def test_job_uses_variable_for_performance_target():
+    job = _load_job()
+    print("Validando uso da variável performance_target...")
+    assert job.get("performance_target") == "${var.performance_target}"
+    print("performance_target OK!")
\ No newline at end of file
diff --git a/dab_test/tests/main_test.py b/dab_test/tests/main_test.py
new file mode 100644
index 0000000..240f1d9
--- /dev/null
+++ b/dab_test/tests/main_test.py
@@ -0,0 +1,6 @@
+from dab_test import main
+
+
+def test_find_all_taxis():
+    taxis = main.find_all_taxis()
+    assert taxis.count() > 5
\ No newline at end of file

From e73a4fda1178819e8b2eb1dd6a64d32b39d1273e Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 13:50:15 +0000
Subject: [PATCH 05/24] update resource

---
 dab_test/src/dab_test/__init__.py             |  0
 dab_test/src/dab_test/main.py                 | 14 -----
 dab_test/src/dab_test_etl/README.md           | 20 ------
 .../explorations/sample_exploration.ipynb     | 63 -------------------
 .../transformations/sample_trips_dab_test.py  | 12 ----
 .../transformations/sample_zones_dab_test.py  | 17 -----
 6 files changed, 126 deletions(-)
 delete mode 100644 dab_test/src/dab_test/__init__.py
 delete mode 100644 dab_test/src/dab_test/main.py
 delete mode 100644 dab_test/src/dab_test_etl/README.md
 delete mode 100644 dab_test/src/dab_test_etl/explorations/sample_exploration.ipynb
 delete mode 100644 dab_test/src/dab_test_etl/transformations/sample_trips_dab_test.py
 delete mode 100644 dab_test/src/dab_test_etl/transformations/sample_zones_dab_test.py

diff --git a/dab_test/src/dab_test/__init__.py b/dab_test/src/dab_test/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/dab_test/src/dab_test/main.py b/dab_test/src/dab_test/main.py
deleted file mode 100644
index aadae50..0000000
--- a/dab_test/src/dab_test/main.py
+++ /dev/null
@@ -1,14 +0,0 @@
-from databricks.sdk.runtime import spark
-from pyspark.sql import DataFrame
-
-
-def find_all_taxis() -> DataFrame:
-    return spark.read.table("samples.nyctaxi.trips")
-
-
-def main():
-    find_all_taxis().show(5)
-
-
-if __name__ == "__main__":
-    main()
\ No newline at end of file
diff --git a/dab_test/src/dab_test_etl/README.md b/dab_test/src/dab_test_etl/README.md
deleted file mode 100644
index 30f31d3..0000000
--- a/dab_test/src/dab_test_etl/README.md
+++ /dev/null
@@ -1,20 +0,0 @@
-# dab_test
-
-This folder defines all source code for the dab_test pipeline:
-
-- `explorations/`: Ad-hoc notebooks used to explore the data processed by this pipeline.
-- `transformations/`: All dataset definitions and transformations.
-- `utilities/` (optional): Utility functions and Python modules used in this pipeline.
-- `data_sources/` (optional): View definitions describing the source data for this pipeline.
-
-## Getting Started
-
-To get started, go to the `transformations` folder -- most of the relevant source code lives there:
-
-* By convention, every dataset under `transformations` is in a separate file.
-* Take a look at the sample called "sample_trips_dab_test.py" to get familiar with the syntax.
-  Read more about the syntax at https://docs.databricks.com/dlt/python-ref.html.
-* If you're using the workspace UI, use `Run file` to run and preview a single transformation.
-* If you're using the CLI, use `databricks bundle run dab_test_etl --refresh sample_trips_dab_test` to run a single transformation.
-
-For more tutorials and reference material, see https://docs.databricks.com/dlt.
diff --git a/dab_test/src/dab_test_etl/explorations/sample_exploration.ipynb b/dab_test/src/dab_test_etl/explorations/sample_exploration.ipynb
deleted file mode 100644
index 6b3bc19..0000000
--- a/dab_test/src/dab_test_etl/explorations/sample_exploration.ipynb
+++ /dev/null
@@ -1,63 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
-     "inputWidgets": {},
-     "nuid": "19a992e9-55e0-49e4-abc7-8c92c420dd5b",
-     "showTitle": false,
-     "tableResultSettingsMap": {},
-     "title": ""
-    }
-   },
-   "source": [
-    "### Example Exploratory Notebook\n",
-    "\n",
-    "Use this notebook to explore the data generated by the pipeline in your preferred programming language.\n",
-    "\n",
-    "**Note**: This notebook is not executed as part of the pipeline."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 0,
-   "metadata": {
-    "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
-     "inputWidgets": {},
-     "nuid": "1b0a82fa-3c6a-4f29-bb43-ded1c4fd77c6",
-     "showTitle": false,
-     "tableResultSettingsMap": {},
-     "title": ""
-    }
-   },
-   "outputs": [],
-   "source": [
-    "# !!! Before performing any data analysis, make sure to run the pipeline to materialize the sample datasets. The tables referenced in this notebook depend on that step.\n",
-    "\n",
-    "display(spark.sql(\"SELECT * FROM dev.rubencruzh.sample_trips_dab_test\"))"
-   ]
-  }
- ],
- "metadata": {
-  "application/vnd.databricks.v1+notebook": {
-   "computePreferences": null,
-   "dashboards": [],
-   "environmentMetadata": null,
-   "inputWidgetPreferences": null,
-   "language": "python",
-   "notebookMetadata": {
-    "pythonIndentUnit": 2
-   },
-   "notebookName": "sample_exploration",
-   "widgets": {}
-  },
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 0
-}
diff --git a/dab_test/src/dab_test_etl/transformations/sample_trips_dab_test.py b/dab_test/src/dab_test_etl/transformations/sample_trips_dab_test.py
deleted file mode 100644
index c739b02..0000000
--- a/dab_test/src/dab_test_etl/transformations/sample_trips_dab_test.py
+++ /dev/null
@@ -1,12 +0,0 @@
-from pyspark import pipelines as dp
-from pyspark.sql.functions import col
-
-
-# This file defines a sample transformation.
-# Edit the sample below or add new transformations
-# using "+ Add" in the file browser.
-
-
-@dp.table
-def sample_trips_dab_test():
-    return spark.read.table("samples.nyctaxi.trips")
diff --git a/dab_test/src/dab_test_etl/transformations/sample_zones_dab_test.py b/dab_test/src/dab_test_etl/transformations/sample_zones_dab_test.py
deleted file mode 100644
index a8c936e..0000000
--- a/dab_test/src/dab_test_etl/transformations/sample_zones_dab_test.py
+++ /dev/null
@@ -1,17 +0,0 @@
-from pyspark import pipelines as dp
-from pyspark.sql.functions import col, sum
-
-
-# This file defines a sample transformation.
-# Edit the sample below or add new transformations
-# using "+ Add" in the file browser.
-
-
-@dp.table
-def sample_zones_dab_test():
-    # Read from the "sample_trips" table, then sum all the fares
-    return (
-        spark.read.table(f"sample_trips_dab_test")
-        .groupBy(col("pickup_zip"))
-        .agg(sum("fare_amount").alias("total_fare"))
-    )

From d218c40ee1f9f02ce04d87ec47bb6a9d1ca7bb71 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 13:52:59 +0000
Subject: [PATCH 06/24] update resource

---
 dab_test/resources/dab_test_job.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/dab_test/resources/dab_test_job.yml b/dab_test/resources/dab_test_job.yml
index 209811c..4b3191f 100644
--- a/dab_test/resources/dab_test_job.yml
+++ b/dab_test/resources/dab_test_job.yml
@@ -17,7 +17,7 @@ resources:
           default: "Anselmo"
       email_notifications:
         on_failure:
-          - anselmoborges@gmail.com
+          - rubencruzh@gmail.com
       timeout_seconds: 900
       schedule:
         quartz_cron_expression: "0 0 8 ? * TUE *"

From 1ceacfd645870503d5b45c9cc514307fdab95a65 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 14:05:44 +0000
Subject: [PATCH 07/24] update notebooks

---
 dab_test/src/sample_notebook.ipynb | 149 -----------------------------
 1 file changed, 149 deletions(-)
 delete mode 100644 dab_test/src/sample_notebook.ipynb

diff --git a/dab_test/src/sample_notebook.ipynb b/dab_test/src/sample_notebook.ipynb
deleted file mode 100644
index 1f32293..0000000
--- a/dab_test/src/sample_notebook.ipynb
+++ /dev/null
@@ -1,149 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
-     "inputWidgets": {},
-     "nuid": "ee353e42-ff58-4955-9608-12865bd0950e",
-     "showTitle": false,
-     "title": ""
-    }
-   },
-   "source": [
-    "# Default notebook\n",
-    "\n",
-    "This default notebook is executed using a Lakeflow job as defined in resources/sample_job.job.yml."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 0,
-   "metadata": {
-    "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
-     "inputWidgets": {},
-     "nuid": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
-     "showTitle": false,
-     "title": ""
-    }
-   },
-   "outputs": [],
-   "source": [
-    "# Set default catalog and schema\n",
-    "catalog = dbutils.widgets.get(\"catalog\")\n",
-    "schema = dbutils.widgets.get(\"schema\")\n",
-    "spark.sql(f\"USE CATALOG {catalog}\")\n",
-    "spark.sql(f\"USE SCHEMA {schema}\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 0,
-   "metadata": {
-    "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {
-      "byteLimit": 2048000,
-      "rowLimit": 10000
-     },
-     "inputWidgets": {},
-     "nuid": "6bca260b-13d1-448f-8082-30b60a85c9ae",
-     "showTitle": false,
-     "title": ""
-    }
-   },
-   "outputs": [],
-   "source": [
-    "import sys\n",
-    "\n",
-    "sys.path.append(\"../src\")\n",
-    "from dab_test import taxis\n",
-    "\n",
-    "taxis.find_all_taxis().show(10)"
-   ]
-  }
- ],
- "metadata": {
-  "application/vnd.databricks.v1+notebook": {
-   "dashboards": [],
-   "environmentMetadata": {
-    "base_environment": "",
-    "dependencies": [
-     "--editable .."
-    ],
-    "environment_version": "4"
-   },
-   "language": "python",
-   "notebookMetadata": {
-    "pythonIndentUnit": 2
-   },
-   "notebookName": "notebook",
-   "widgets": {
-    "catalog": {
-     "currentValue": "dev",
-     "nuid": "c4t4l0g-w1dg-3t12-3456-789012345678",
-     "typedWidgetInfo": {
-      "autoCreated": false,
-      "defaultValue": "dev",
-      "label": "Catalog",
-      "name": "catalog",
-      "options": {
-       "validationRegex": null,
-       "widgetDisplayType": "Text"
-      },
-      "parameterDataType": "String"
-     },
-     "widgetInfo": {
-      "defaultValue": "dev",
-      "label": "Catalog",
-      "name": "catalog",
-      "options": {
-       "autoCreated": false,
-       "validationRegex": null,
-       "widgetType": "text"
-      },
-      "widgetType": "text"
-     }
-    },
-    "schema": {
-     "currentValue": "rubencruzh",
-     "nuid": "5ch3m4-w1dg-3t98-7654-321098765432",
-     "typedWidgetInfo": {
-      "autoCreated": false,
-      "defaultValue": "default",
-      "label": "Schema",
-      "name": "schema",
-      "options": {
-       "validationRegex": null,
-       "widgetDisplayType": "Text"
-      },
-      "parameterDataType": "String"
-     },
-     "widgetInfo": {
-      "defaultValue": "default",
-      "label": "Schema",
-      "name": "schema",
-      "options": {
-       "autoCreated": false,
-       "validationRegex": null,
-       "widgetType": "text"
-      },
-      "widgetType": "text"
-     }
-    }
-   }
-  },
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "name": "python",
-   "version": "3.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 0
-}

From bae918b754e8950d1d71a44256b0d5316f57e985 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 14:17:18 +0000
Subject: [PATCH 08/24] update readme.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 146bb9e..9d6bd3c 100644
--- a/README.md
+++ b/README.md
@@ -1 +1 @@
-# repositorio-teste 
+# repositorio-teste video -

From a8746b8652c259552b607efe096d86e619909d33 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 14:51:28 +0000
Subject: [PATCH 09/24] update main

---
 dab_test/pyproject.toml           |  4 +++
 dab_test/src/dab_test/__init__.py |  0
 dab_test/src/dab_test/main.py     | 57 +++++++++++++++++++++++++++++++
 3 files changed, 61 insertions(+)
 create mode 100644 dab_test/src/dab_test/__init__.py
 create mode 100644 dab_test/src/dab_test/main.py

diff --git a/dab_test/pyproject.toml b/dab_test/pyproject.toml
index 8fee306..1cbaedc 100644
--- a/dab_test/pyproject.toml
+++ b/dab_test/pyproject.toml
@@ -15,6 +15,7 @@ dependencies = [
 dev = [
     "pytest",
     "ruff",
+    "pyyaml",
     "databricks-dlt",
     "databricks-connect>=15.4,<15.5",
     "ipykernel",
@@ -27,5 +28,8 @@ main = "dab_test.main:main"
 requires = ["hatchling"]
 build-backend = "hatchling.build"
 
+[tool.hatch.build.targets.wheel]
+packages = ["dab_test"]
+
 [tool.ruff]
 line-length = 120
diff --git a/dab_test/src/dab_test/__init__.py b/dab_test/src/dab_test/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/dab_test/src/dab_test/main.py b/dab_test/src/dab_test/main.py
new file mode 100644
index 0000000..cdcd27a
--- /dev/null
+++ b/dab_test/src/dab_test/main.py
@@ -0,0 +1,57 @@
+"""This file configures pytest."""
+
+import os, sys, pathlib
+from contextlib import contextmanager
+
+
+try:
+    from databricks.connect import DatabricksSession
+    from databricks.sdk import WorkspaceClient
+    from pyspark.sql import SparkSession
+    import pytest
+except ImportError:
+    raise ImportError("Test dependencies not found.\n\nRun tests using 'uv run pytest'. See http://docs.astral.sh/uv to learn more about uv.")
+
+
+def enable_fallback_compute():
+    """Enable serverless compute if no compute is specified."""
+    conf = WorkspaceClient().config
+    if conf.serverless_compute_id or conf.cluster_id or os.environ.get("SPARK_REMOTE"):
+        return
+
+    url = "https://docs.databricks.com/dev-tools/databricks-connect/cluster-config"
+    print("☁️ no compute specified, falling back to serverless compute", file=sys.stderr)
+    print(f"  see {url} for manual configuration", file=sys.stderr)
+
+    os.environ["DATABRICKS_SERVERLESS_COMPUTE_ID"] = "auto"
+
+
+@contextmanager
+def allow_stderr_output(config: pytest.Config):
+    """Temporarily disable pytest output capture."""
+    capman = config.pluginmanager.get_plugin("capturemanager")
+    if capman:
+        with capman.global_and_fixture_disabled():
+            yield
+    else:
+        yield
+
+
+def pytest_configure(config: pytest.Config):
+    """Configure pytest session."""
+    with allow_stderr_output(config):
+        enable_fallback_compute()
+
+        # Initialize Spark session eagerly, so it is available even when
+        # SparkSession.builder.getOrCreate() is used. For DB Connect 15+,
+        # we validate version compatibility with the remote cluster.
+        if hasattr(DatabricksSession.builder, "validateSession"):
+            DatabricksSession.builder.validateSession().getOrCreate()
+        else:
+            DatabricksSession.builder.getOrCreate()
+
+
+@pytest.fixture(scope="session")
+def spark() -> SparkSession:
+    """Provide a SparkSession fixture for tests."""
+    return DatabricksSession.builder.getOrCreate()
\ No newline at end of file

From e00d32dc434c24e7a3f525d23601cb27d61b9563 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 15:53:19 +0000
Subject: [PATCH 10/24] =?UTF-8?q?feat:=20salvando=20altera=C3=A7=C3=B5es?=
 =?UTF-8?q?=20antes=20de=20sincronizar=20com=20dev?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 dab_test/pyproject.toml                       |  3 +-
 dab_test/resources/{ => job}/dab_test_job.yml |  0
 .../dab_test/{__init__.py => ____init__.py}   |  0
 dab_test/src/dab_test/main.py                 | 59 +++----------------
 dab_test/tests/job_config_test.py             |  2 +-
 5 files changed, 11 insertions(+), 53 deletions(-)
 rename dab_test/resources/{ => job}/dab_test_job.yml (100%)
 rename dab_test/src/dab_test/{__init__.py => ____init__.py} (100%)

diff --git a/dab_test/pyproject.toml b/dab_test/pyproject.toml
index 1cbaedc..24abc54 100644
--- a/dab_test/pyproject.toml
+++ b/dab_test/pyproject.toml
@@ -28,8 +28,9 @@ main = "dab_test.main:main"
 requires = ["hatchling"]
 build-backend = "hatchling.build"
 
+
 [tool.hatch.build.targets.wheel]
-packages = ["dab_test"]
+packages = ["src/dab_test"]
 
 [tool.ruff]
 line-length = 120
diff --git a/dab_test/resources/dab_test_job.yml b/dab_test/resources/job/dab_test_job.yml
similarity index 100%
rename from dab_test/resources/dab_test_job.yml
rename to dab_test/resources/job/dab_test_job.yml
diff --git a/dab_test/src/dab_test/__init__.py b/dab_test/src/dab_test/____init__.py
similarity index 100%
rename from dab_test/src/dab_test/__init__.py
rename to dab_test/src/dab_test/____init__.py
diff --git a/dab_test/src/dab_test/main.py b/dab_test/src/dab_test/main.py
index cdcd27a..aadae50 100644
--- a/dab_test/src/dab_test/main.py
+++ b/dab_test/src/dab_test/main.py
@@ -1,57 +1,14 @@
-"""This file configures pytest."""
+from databricks.sdk.runtime import spark
+from pyspark.sql import DataFrame
 
-import os, sys, pathlib
-from contextlib import contextmanager
 
+def find_all_taxis() -> DataFrame:
+    return spark.read.table("samples.nyctaxi.trips")
 
-try:
-    from databricks.connect import DatabricksSession
-    from databricks.sdk import WorkspaceClient
-    from pyspark.sql import SparkSession
-    import pytest
-except ImportError:
-    raise ImportError("Test dependencies not found.\n\nRun tests using 'uv run pytest'. See http://docs.astral.sh/uv to learn more about uv.")
 
+def main():
+    find_all_taxis().show(5)
 
-def enable_fallback_compute():
-    """Enable serverless compute if no compute is specified."""
-    conf = WorkspaceClient().config
-    if conf.serverless_compute_id or conf.cluster_id or os.environ.get("SPARK_REMOTE"):
-        return
 
-    url = "https://docs.databricks.com/dev-tools/databricks-connect/cluster-config"
-    print("☁️ no compute specified, falling back to serverless compute", file=sys.stderr)
-    print(f"  see {url} for manual configuration", file=sys.stderr)
-
-    os.environ["DATABRICKS_SERVERLESS_COMPUTE_ID"] = "auto"
-
-
-@contextmanager
-def allow_stderr_output(config: pytest.Config):
-    """Temporarily disable pytest output capture."""
-    capman = config.pluginmanager.get_plugin("capturemanager")
-    if capman:
-        with capman.global_and_fixture_disabled():
-            yield
-    else:
-        yield
-
-
-def pytest_configure(config: pytest.Config):
-    """Configure pytest session."""
-    with allow_stderr_output(config):
-        enable_fallback_compute()
-
-        # Initialize Spark session eagerly, so it is available even when
-        # SparkSession.builder.getOrCreate() is used. For DB Connect 15+,
-        # we validate version compatibility with the remote cluster.
-        if hasattr(DatabricksSession.builder, "validateSession"):
-            DatabricksSession.builder.validateSession().getOrCreate()
-        else:
-            DatabricksSession.builder.getOrCreate()
-
-
-@pytest.fixture(scope="session")
-def spark() -> SparkSession:
-    """Provide a SparkSession fixture for tests."""
-    return DatabricksSession.builder.getOrCreate()
\ No newline at end of file
+if __name__ == "__main__":
+    main()
\ No newline at end of file
diff --git a/dab_test/tests/job_config_test.py b/dab_test/tests/job_config_test.py
index 921bf3a..9e30f35 100644
--- a/dab_test/tests/job_config_test.py
+++ b/dab_test/tests/job_config_test.py
@@ -2,7 +2,7 @@
 import yaml
 
 ROOT = Path(__file__).resolve().parents[1]
-JOB_FILE = ROOT / "resources" / "jobs" / "dab_treinamento.job.yml"
+JOB_FILE = ROOT / "resources" / "jobs" / "dab_treinamento_job.yml"
 
 
 def _load_job():

From b2085c1d6818f0343ea9a7907f74520114e54d8c Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 16:25:43 +0000
Subject: [PATCH 11/24] update

---
 README.md                         | 2 +-
 dab_test/tests/job_config_test.py | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 9d6bd3c..9fb08b5 100644
--- a/README.md
+++ b/README.md
@@ -1 +1 @@
-# repositorio-teste video -
+# repositorio-teste video 
diff --git a/dab_test/tests/job_config_test.py b/dab_test/tests/job_config_test.py
index 9e30f35..fd9becf 100644
--- a/dab_test/tests/job_config_test.py
+++ b/dab_test/tests/job_config_test.py
@@ -2,12 +2,12 @@
 import yaml
 
 ROOT = Path(__file__).resolve().parents[1]
-JOB_FILE = ROOT / "resources" / "jobs" / "dab_treinamento_job.yml"
+JOB_FILE = ROOT / "resources" / "jobs" / "dab_test_job.yml"
 
 
 def _load_job():
     data = yaml.safe_load(JOB_FILE.read_text())
-    job = data["resources"]["jobs"]["dab_treinamento_job"]
+    job = data["resources"]["jobs"]["dab_test_job"]
     return job
 
 

From 0a847df2b9b070c43c24688af6c51806fd8f9106 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 16:30:41 +0000
Subject: [PATCH 12/24] update jobs

---
 dab_test/resources/{job => jobs}/dab_test_job.yml | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename dab_test/resources/{job => jobs}/dab_test_job.yml (100%)

diff --git a/dab_test/resources/job/dab_test_job.yml b/dab_test/resources/jobs/dab_test_job.yml
similarity index 100%
rename from dab_test/resources/job/dab_test_job.yml
rename to dab_test/resources/jobs/dab_test_job.yml

From 5ea721a64f695796ae37fbc52d2bbc909b370475 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 17:09:59 +0000
Subject: [PATCH 13/24] update main

---
 dab_test/tests/main_test.py | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/dab_test/tests/main_test.py b/dab_test/tests/main_test.py
index 240f1d9..38ed1b0 100644
--- a/dab_test/tests/main_test.py
+++ b/dab_test/tests/main_test.py
@@ -1,6 +1,18 @@
+from unittest.mock import MagicMock, patch
+
 from dab_test import main
 
 
 def test_find_all_taxis():
-    taxis = main.find_all_taxis()
-    assert taxis.count() > 5
\ No newline at end of file
+    mock_df = MagicMock()
+    mock_reader = MagicMock()
+    mock_spark = MagicMock()
+
+    mock_spark.read = mock_reader
+    mock_reader.table.return_value = mock_df
+
+    with patch.object(main, "spark", mock_spark):
+        taxis = main.find_all_taxis()
+
+    mock_reader.table.assert_called_once_with("samples.nyctaxi.trips")
+    assert taxis == mock_df
\ No newline at end of file

From a120ad935ddaba7fd1900973c442b135074e0d5e Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 17:26:05 +0000
Subject: [PATCH 14/24] update main

---
 dab_test/databricks.yml           | 3 +++
 dab_test/tests/job_config_test.py | 5 ++++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/dab_test/databricks.yml b/dab_test/databricks.yml
index ad36d9e..be7a0a5 100644
--- a/dab_test/databricks.yml
+++ b/dab_test/databricks.yml
@@ -20,6 +20,9 @@ variables:
     description: The catalog to use
   schema:
     description: The schema to use
+  catalog_name:
+    description: "Catalog used by the job"
+    default: dev
 
 targets:
   dev:
diff --git a/dab_test/tests/job_config_test.py b/dab_test/tests/job_config_test.py
index fd9becf..3421ea0 100644
--- a/dab_test/tests/job_config_test.py
+++ b/dab_test/tests/job_config_test.py
@@ -48,4 +48,7 @@ def test_job_uses_variable_for_performance_target():
     job = _load_job()
     print("Validando uso da variável performance_target...")
     assert job.get("performance_target") == "${var.performance_target}"
-    print("performance_target OK!")
\ No newline at end of file
+    print("performance_target OK!")
+
+spark = None
+

From 241d3f628256f0f3d8250394dca39a26e0c05c7d Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 17:37:26 +0000
Subject: [PATCH 15/24] update

---
 README.md               | 2 +-
 dab_test/databricks.yml | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 9fb08b5..9d6bd3c 100644
--- a/README.md
+++ b/README.md
@@ -1 +1 @@
-# repositorio-teste video 
+# repositorio-teste video -
diff --git a/dab_test/databricks.yml b/dab_test/databricks.yml
index be7a0a5..5048f15 100644
--- a/dab_test/databricks.yml
+++ b/dab_test/databricks.yml
@@ -23,7 +23,9 @@ variables:
   catalog_name:
     description: "Catalog used by the job"
     default: dev
-
+  performance_target:
+    description: "Performance target for the job"
+    default: "10"
 targets:
   dev:
     # The default target uses 'mode: development' to create a development copy.

From 6f45c522e898180a702827abcc6a18b4fc631a15 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 17:46:01 +0000
Subject: [PATCH 16/24] update

---
 dab_test/databricks.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/dab_test/databricks.yml b/dab_test/databricks.yml
index 5048f15..104975f 100644
--- a/dab_test/databricks.yml
+++ b/dab_test/databricks.yml
@@ -25,7 +25,7 @@ variables:
     default: dev
   performance_target:
     description: "Performance target for the job"
-    default: "10"
+    default: "STANDARD"
 targets:
   dev:
     # The default target uses 'mode: development' to create a development copy.

From f3215e258907a6ad2210194da25c9b4f53732455 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 18:00:22 +0000
Subject: [PATCH 17/24] update

---
 dab_test/src/notebooks/{demo_notebooks.py => demo_notebook.py} | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename dab_test/src/notebooks/{demo_notebooks.py => demo_notebook.py} (100%)

diff --git a/dab_test/src/notebooks/demo_notebooks.py b/dab_test/src/notebooks/demo_notebook.py
similarity index 100%
rename from dab_test/src/notebooks/demo_notebooks.py
rename to dab_test/src/notebooks/demo_notebook.py

From 52edfd1ce71ebfc2050ba65e5e24839ef6cfdcd2 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 22:25:01 +0000
Subject: [PATCH 18/24] update video

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 9d6bd3c..4aada1d 100644
--- a/README.md
+++ b/README.md
@@ -1 +1 @@
-# repositorio-teste video -
+# repositorio-teste video - p

From 8bbeb40086e854b2023f913b15a2d8141e6454aa Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 22:36:46 +0000
Subject: [PATCH 19/24] update

---
 .github/workflows/deploy_prd.yml | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/deploy_prd.yml b/.github/workflows/deploy_prd.yml
index edee33e..51d2b35 100644
--- a/.github/workflows/deploy_prd.yml
+++ b/.github/workflows/deploy_prd.yml
@@ -37,19 +37,19 @@ jobs:
         env:
           DATABRICKS_CONFIG_PROFILE: PRD
         run: |
-          cd dab_treinamento
+          cd dab_test
           databricks bundle validate --target prd
 
       - name: Deploy bundle Databricks
         env:
           DATABRICKS_CONFIG_PROFILE: PRD
         run: |
-          cd dab_treinamento
+          cd dab_test
           databricks bundle deploy --target prd
 
       - name: Executar job Databricks
         env:
           DATABRICKS_CONFIG_PROFILE: PRD
         run: |
-          cd dab_treinamento
-          databricks bundle run dab_treinamento_job --target prd
\ No newline at end of file
+          cd dab_test
+          databricks bundle run dab_test_job --target prd
\ No newline at end of file

From 7419a23b970fdcdef7ed81f9438345359c7f48f6 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 22:42:37 +0000
Subject: [PATCH 20/24] update dev

---
 .github/workflows/deploy_prd.yml | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/.github/workflows/deploy_prd.yml b/.github/workflows/deploy_prd.yml
index 51d2b35..8ba25f0 100644
--- a/.github/workflows/deploy_prd.yml
+++ b/.github/workflows/deploy_prd.yml
@@ -4,7 +4,7 @@ on:
   workflow_dispatch:
   push:
     branches:
-      - main
+      - prod
 
 jobs:
   deploy-prd:
@@ -35,21 +35,21 @@ jobs:
 
       - name: Validar bundle Databricks
         env:
-          DATABRICKS_CONFIG_PROFILE: PRD
+          DATABRICKS_CONFIG_PROFILE: PROD
         run: |
           cd dab_test
-          databricks bundle validate --target prd
+          databricks bundle validate --target prod
 
       - name: Deploy bundle Databricks
         env:
-          DATABRICKS_CONFIG_PROFILE: PRD
+          DATABRICKS_CONFIG_PROFILE: PROD
         run: |
           cd dab_test
-          databricks bundle deploy --target prd
+          databricks bundle deploy --target prod
 
       - name: Executar job Databricks
         env:
-          DATABRICKS_CONFIG_PROFILE: PRD
+          DATABRICKS_CONFIG_PROFILE: PROD
         run: |
           cd dab_test
-          databricks bundle run dab_test_job --target prd
\ No newline at end of file
+          databricks bundle run dab_test_job --target prod
\ No newline at end of file

From 5148dfb510d4daee1d435ba257c281fbdb4ad08b Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 22:55:40 +0000
Subject: [PATCH 21/24] update dev

---
 .github/workflows/deploy_prd.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/deploy_prd.yml b/.github/workflows/deploy_prd.yml
index 8ba25f0..1945ced 100644
--- a/.github/workflows/deploy_prd.yml
+++ b/.github/workflows/deploy_prd.yml
@@ -1,4 +1,4 @@
-name: Deploy Databricks Bundle PRD
+name: Deploy Databricks Bundle PROD
 
 on:
   workflow_dispatch:

From 3dee5a8574f6968e1b4790370fa35039bc8399b1 Mon Sep 17 00:00:00 2001
From: "rubencruzh@gmail.com" <rubencruzh@gmail.com>
Date: Tue, 11 Aug 2026 23:08:52 +0000
Subject: [PATCH 22/24] update dev

---
 dab_test/databricks.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/dab_test/databricks.yml b/dab_test/databricks.yml
index 104975f..8cb2b66 100644
--- a/dab_test/databricks.yml
+++ b/dab_test/databricks.yml
@@ -46,7 +46,7 @@ targets:
       # We explicitly deploy to /Workspace/Users/rubencruzh@gmail.com to make sure we only have a single copy.
       root_path: /Workspace/Users/rubencruzh@gmail.com/.bundle/${bundle.name}/${bundle.target}
     variables:
-      catalog: dev
+      catalog: prod
       schema: prod
     permissions:
       - user_name: rubencruzh@gmail.com

From 3a7ebf40465edeb66ea570fa7933b1ceea5eb7fb Mon Sep 17 00:00:00 2001
From: "Ruben Cruz H." <rubencruzh@gmail.com>
Date: Wed, 12 Aug 2026 10:45:55 -0300
Subject: [PATCH 23/24] Revise README for Databricks Asset Bundle project

Updated project title and detailed project overview, architecture, technology stack, repository structure, and deployment workflows for Databricks Asset Bundle.
---
 README.md | 974 +++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 973 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 4aada1d..e7ae401 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,973 @@
-# repositorio-teste video - p
+# Databricks Asset Bundle — Python Data Engineering
+
+A practical Databricks Data Engineering project demonstrating how to develop, test, package, deploy, and execute Python workloads using **Databricks Asset Bundles (DAB)** and **GitHub Actions CI/CD**.
+
+The project implements separate **DEV and PROD environments**, Python Wheel packaging, automated testing, parameterized Databricks Jobs, OAuth Service Principal authentication, and a reproducible development environment using VS Code Dev Containers.
+
+---
+
+## Architecture
+
+```text
+                         GitHub Repository
+                                │
+                    ┌───────────┴───────────┐
+                    │                       │
+                   dev                    prod
+                    │                       │
+                    ▼                       ▼
+             deploy_dev.yml          deploy_prd.yml
+                    │                       │
+                    ▼                       ▼
+             GitHub Actions           GitHub Actions
+                    │                       │
+              ┌─────┴─────┐           ┌─────┴─────┐
+              │           │           │           │
+            Tests       Validate     Validate    Deploy
+              │           │           │           │
+              └─────┬─────┘           └─────┬─────┘
+                    │                       │
+                    ▼                       ▼
+              DAB Bundle              DAB Bundle
+                    │                       │
+                    ▼                       ▼
+             Databricks DEV          Databricks PROD
+                    │                       │
+                    └───────────┬───────────┘
+                                │
+                                ▼
+                         dab_test_job
+                                │
+                                ▼
+                     demo_notebook.py
+                                │
+                                ▼
+                         Unity Catalog
+                     catalog.schema.users
+```
+
+---
+
+# Project Overview
+
+This project is based on the **Databricks Asset Bundle default Python project structure** and has been extended to demonstrate a more complete Data Engineering deployment workflow.
+
+The main workload demonstrates:
+
+1. Python application development.
+2. Databricks notebook execution.
+3. Parameterized Databricks Jobs.
+4. Python Wheel packaging.
+5. Databricks Asset Bundle configuration.
+6. DEV and PROD environments.
+7. Automated testing.
+8. GitHub Actions CI/CD.
+9. OAuth Service Principal authentication.
+10. Containerized local development.
+
+---
+
+# Technology Stack
+
+| Technology               | Purpose                                     |
+| ------------------------ | ------------------------------------------- |
+| Python 3.10–3.12         | Application development                     |
+| PySpark                  | Distributed data processing                 |
+| Databricks               | Data Engineering platform                   |
+| Databricks Asset Bundles | Deployment and resource management          |
+| Databricks CLI           | Bundle validation, deployment and execution |
+| Unity Catalog            | Catalog/schema/table organization           |
+| uv                       | Python dependency management and build      |
+| Hatchling                | Python Wheel build backend                  |
+| Pytest                   | Automated testing                           |
+| Ruff                     | Python linting                              |
+| GitHub Actions           | CI/CD                                       |
+| Docker                   | Development environment                     |
+| VS Code Dev Containers   | Reproducible development environment        |
+| YAML                     | Databricks and CI/CD configuration          |
+| TOML                     | Python project configuration                |
+
+---
+
+# Repository Structure
+
+```text
+.
+├── .devcontainer/
+│   ├── .env
+│   ├── Dockerfile
+│   ├── devcontainer.json
+│   └── requirements.txt
+│
+├── .github/
+│   └── workflows/
+│       ├── deploy_dev.yml
+│       └── deploy_prd.yml
+│
+├── dab_test/
+│   ├── .vscode/
+│   │
+│   ├── fixtures/
+│   │
+│   ├── resources/
+│   │   └── jobs/
+│   │       └── dab_test_job.yml
+│   │
+│   ├── src/
+│   │   ├── dab_test/
+│   │   │   ├── __init__.py
+│   │   │   └── main.py
+│   │   │
+│   │   └── notebooks/
+│   │       └── demo_notebook.py
+│   │
+│   ├── tests/
+│   │   ├── job_config_test.py
+│   │   └── main_test.py
+│   │
+│   ├── AGENTS.md
+│   ├── CLAUDE.md
+│   ├── README.md
+│   ├── databricks.yml
+│   └── pyproject.toml
+│
+└── README.md
+```
+
+---
+
+# Databricks Asset Bundle
+
+The core of the project is the `databricks.yml` file.
+
+The Bundle is named:
+
+```yaml
+bundle:
+  name: dab_test
+```
+
+The configuration includes resource definitions from:
+
+```text
+resources/jobs/*.yml
+resources/pipelines/*.yml
+resources/schemas/*.yml
+```
+
+It also defines a Python Wheel artifact:
+
+```yaml
+artifacts:
+  python_artifact:
+    type: whl
+    build: uv build --wheel
+```
+
+This means the deployment process can build the Python application into a `.whl` package and make it available to the Databricks workload.
+
+---
+
+# Environments
+
+The project defines two Databricks Bundle targets.
+
+## DEV
+
+The `dev` target uses:
+
+```yaml
+mode: development
+```
+
+and is the default Bundle target.
+
+It uses the following configuration:
+
+```text
+Catalog: dev
+Schema: rescue_b
+```
+
+The DEV workflow is intended for development, testing, validation, deployment, and execution.
+
+---
+
+## PROD
+
+The `prod` target uses:
+
+```yaml
+mode: production
+```
+
+with:
+
+```text
+Catalog: prod
+Schema: rescue_b
+```
+
+The production deployment is associated with the `prod` Git branch.
+
+The production workflow can be triggered by:
+
+* a push to the `prod` branch;
+* manual GitHub Actions execution.
+
+---
+
+# Python Application
+
+The main Python package is located under:
+
+```text
+dab_test/src/dab_test/
+```
+
+The main application contains a simple Spark workload that reads the Databricks sample NYC Taxi dataset:
+
+```python
+def find_all_taxis() -> DataFrame:
+    return spark.read.table("samples.nyctaxi.trips")
+```
+
+The `main()` function displays the first five records.
+
+The project therefore provides a minimal Python/Spark workload that can be packaged and executed through the Databricks environment.
+
+---
+
+# Demo Notebook
+
+The project also contains:
+
+```text
+dab_test/src/notebooks/demo_notebook.py
+```
+
+The notebook demonstrates parameterized Databricks execution using widgets:
+
+```text
+catalog
+user_id
+user_name
+```
+
+The notebook:
+
+1. Receives runtime parameters.
+2. Creates a `users` table if it does not exist.
+3. Inserts sample users.
+4. Inserts the parameterized user.
+5. Reads the resulting table.
+6. Displays the resulting DataFrame.
+
+The target table follows the pattern:
+
+```text
+<catalog>.rescue_b.users
+```
+
+For example:
+
+```text
+dev.rescue_b.users
+prod.rescue_b.users
+```
+
+---
+
+# Databricks Job
+
+The Job is defined in:
+
+```text
+dab_test/resources/jobs/dab_test_job.yml
+```
+
+The Job is called:
+
+```text
+dab_test_job
+```
+
+It contains a task named:
+
+```text
+ingestao_usuarios
+```
+
+which executes:
+
+```text
+src/notebooks/demo_notebook.py
+```
+
+The Job exposes parameters including:
+
+```text
+catalog_name
+user_id
+user_name
+```
+
+This allows the same notebook to be reused with different runtime values instead of hard-coding the input data.
+
+---
+
+# Job Schedule
+
+The Job configuration defines a Quartz cron schedule:
+
+```text
+Every Tuesday at 08:00
+Timezone: America/Sao_Paulo
+```
+
+The Job also has a timeout of:
+
+```text
+900 seconds
+```
+
+Failure notifications are configured through Databricks Job email notifications.
+
+---
+
+# Dynamic Parameters
+
+One of the main concepts demonstrated by this project is the separation between:
+
+### Bundle variables
+
+Defined in:
+
+```text
+databricks.yml
+```
+
+Example:
+
+```text
+catalog
+schema
+catalog_name
+performance_target
+```
+
+and:
+
+### Job parameters
+
+Defined in:
+
+```text
+resources/jobs/dab_test_job.yml
+```
+
+Example:
+
+```text
+catalog_name
+user_id
+user_name
+```
+
+The values can flow through the deployment configuration into the notebook at runtime.
+
+Conceptually:
+
+```text
+databricks.yml
+      │
+      │ ${var.catalog_name}
+      ▼
+Databricks Job
+      │
+      │ {{job.parameters.catalog_name}}
+      ▼
+demo_notebook.py
+      │
+      ▼
+Unity Catalog
+```
+
+---
+
+# Python Packaging
+
+The Python project is configured through:
+
+```text
+dab_test/pyproject.toml
+```
+
+The project supports:
+
+```text
+Python >= 3.10
+Python < 3.13
+```
+
+The build system uses:
+
+```text
+Hatchling
+```
+
+The Wheel package is built using:
+
+```bash
+uv build --wheel
+```
+
+The resulting package can be used by the Databricks deployment.
+
+---
+
+# Development Dependencies
+
+The project includes development dependencies for:
+
+* Pytest
+* Ruff
+* PyYAML
+* Databricks DLT
+* Databricks Connect
+* IPython Kernel
+
+Install the development dependencies using:
+
+```bash
+uv sync --dev
+```
+
+---
+
+# Testing
+
+Tests are located under:
+
+```text
+dab_test/tests/
+```
+
+Current test modules include:
+
+```text
+main_test.py
+job_config_test.py
+```
+
+Run the tests locally with:
+
+```bash
+uv run pytest
+```
+
+The DEV CI/CD workflow also executes:
+
+```bash
+uv run pytest -s
+```
+
+before Bundle validation and deployment.
+
+---
+
+# CI/CD
+
+The repository contains two GitHub Actions workflows:
+
+```text
+.github/workflows/
+├── deploy_dev.yml
+└── deploy_prd.yml
+```
+
+## DEV Pipeline
+
+The DEV workflow is triggered by pushes to:
+
+```text
+dev
+```
+
+It performs:
+
+```text
+Checkout
+   │
+   ▼
+Install Databricks CLI
+   │
+   ▼
+Install uv
+   │
+   ▼
+Configure Databricks OAuth
+   │
+   ▼
+Run Pytest
+   │
+   ▼
+Validate Bundle
+   │
+   ▼
+Deploy Bundle
+   │
+   ▼
+Run Databricks Job
+```
+
+---
+
+# PROD Pipeline
+
+The production workflow is triggered by:
+
+```text
+push to prod
+```
+
+or manually through:
+
+```text
+workflow_dispatch
+```
+
+The production workflow performs:
+
+```text
+Checkout
+   │
+   ▼
+Install Databricks CLI
+   │
+   ▼
+Install uv
+   │
+   ▼
+Configure PROD OAuth Service Principal
+   │
+   ▼
+Validate Bundle
+   │
+   ▼
+Deploy Bundle
+   │
+   ▼
+Run Databricks Job
+```
+
+The PROD workflow deploys using:
+
+```bash
+databricks bundle deploy --target prod
+```
+
+and executes:
+
+```bash
+databricks bundle run dab_test_job --target prod
+```
+
+---
+
+# Authentication
+
+GitHub Actions authenticates to Databricks using an **OAuth Service Principal**.
+
+The workflows obtain the following values from GitHub Secrets:
+
+```text
+DATABRICKS_HOST
+DATABRICKS_CLIENT_ID
+DATABRICKS_CLIENT_SECRET
+```
+
+Environment-specific secrets are used for DEV and PROD.
+
+For example:
+
+```text
+DATABRICKS_HOST_DEV
+DATABRICKS_CLIENT_ID_DEV
+DATABRICKS_CLIENT_SECRET_DEV
+```
+
+and:
+
+```text
+DATABRICKS_HOST_PRD
+DATABRICKS_CLIENT_ID_PRD
+DATABRICKS_CLIENT_SECRET_PRD
+```
+
+No credentials should be committed to the repository.
+
+---
+
+# Local Development
+
+## Prerequisites
+
+Recommended tools:
+
+* Git
+* Docker
+* Visual Studio Code
+* VS Code Dev Containers extension
+* Python 3.10–3.12
+* uv
+* Databricks CLI
+
+---
+
+## Dev Container
+
+The project provides a development container under:
+
+```text
+.devcontainer/
+```
+
+with:
+
+```text
+Dockerfile
+devcontainer.json
+requirements.txt
+.env
+```
+
+Open the repository in VS Code and select:
+
+```text
+Dev Containers: Reopen in Container
+```
+
+This provides a reproducible development environment.
+
+> Never commit production credentials, access tokens, client secrets, or other sensitive information to `.env` or the repository.
+
+---
+
+# Databricks CLI
+
+Authenticate to Databricks using your preferred authentication method.
+
+For a local profile:
+
+```bash
+databricks configure
+```
+
+Verify the CLI:
+
+```bash
+databricks --version
+```
+
+---
+
+# Validate the Bundle
+
+From the project directory:
+
+```bash
+cd dab_test
+```
+
+Validate DEV:
+
+```bash
+databricks bundle validate --target dev
+```
+
+Validate PROD:
+
+```bash
+databricks bundle validate --target prod
+```
+
+Validation should be performed before deployment.
+
+---
+
+# Deploy to DEV
+
+```bash
+cd dab_test
+
+databricks bundle deploy --target dev
+```
+
+After deployment, execute the Job:
+
+```bash
+databricks bundle run dab_test_job --target dev
+```
+
+---
+
+# Deploy to PROD
+
+Production deployment should preferably occur through the GitHub Actions workflow.
+
+The equivalent CLI commands are:
+
+```bash
+cd dab_test
+
+databricks bundle validate --target prod
+
+databricks bundle deploy --target prod
+
+databricks bundle run dab_test_job --target prod
+```
+
+---
+
+# End-to-End Deployment Flow
+
+The complete workflow is:
+
+```text
+Developer
+    │
+    │ git push
+    ▼
+GitHub
+    │
+    ├───────────────┐
+    │               │
+   dev             prod
+    │               │
+    ▼               ▼
+DEV Workflow    PROD Workflow
+    │               │
+    ▼               ▼
+Pytest          Validation
+    │               │
+    ▼               ▼
+Validation      Deployment
+    │               │
+    ▼               ▼
+Deployment      Job Execution
+    │               │
+    ▼               ▼
+Databricks DEV  Databricks PROD
+```
+
+---
+
+# Configuration Files
+
+## `databricks.yml`
+
+Defines the Databricks Asset Bundle.
+
+Responsible for:
+
+* Bundle name
+* Resources
+* Variables
+* Artifacts
+* DEV target
+* PROD target
+* Workspace configuration
+
+---
+
+## `pyproject.toml`
+
+Defines the Python project.
+
+Responsible for:
+
+* Python version
+* Project metadata
+* Dependencies
+* Development dependencies
+* Entry point
+* Build system
+* Wheel packaging
+* Ruff configuration
+
+---
+
+## `resources/jobs/dab_test_job.yml`
+
+Defines the Databricks Job.
+
+Responsible for:
+
+* Job name
+* Job parameters
+* Schedule
+* Timeout
+* Notifications
+* Notebook task
+* Runtime parameters
+* Performance configuration
+
+---
+
+## `.github/workflows/deploy_dev.yml`
+
+Defines the DEV CI/CD pipeline.
+
+Responsible for:
+
+* Installing tooling
+* Authentication
+* Running tests
+* Bundle validation
+* Deployment
+* Job execution
+
+---
+
+## `.github/workflows/deploy_prd.yml`
+
+Defines the PROD CI/CD pipeline.
+
+Responsible for:
+
+* Installing tooling
+* PROD authentication
+* Bundle validation
+* Production deployment
+* Job execution
+
+---
+
+# Key Engineering Concepts
+
+This project demonstrates the following Data Engineering and DevOps practices:
+
+### Infrastructure as Code
+
+Databricks resources are defined as code rather than being created manually through the Databricks UI.
+
+### Environment Separation
+
+The same Bundle supports:
+
+```text
+DEV
+PROD
+```
+
+using different targets.
+
+### Python Packaging
+
+The application is packaged as a Python Wheel before deployment.
+
+### Automated Testing
+
+Pytest is integrated into the DEV deployment pipeline.
+
+### CI/CD
+
+GitHub Actions automates the deployment lifecycle.
+
+### Parameterized Workloads
+
+The Databricks Job passes runtime parameters into the notebook.
+
+### Service Principal Authentication
+
+CI/CD uses OAuth-based Service Principal authentication rather than personal credentials.
+
+### Reproducible Development
+
+The Dev Container provides a consistent development environment.
+
+---
+
+# Project Status
+
+Current implementation:
+
+* [x] Databricks Asset Bundle
+* [x] Python project structure
+* [x] PySpark application
+* [x] Databricks notebook
+* [x] Parameterized Databricks Job
+* [x] Unity Catalog catalog/schema configuration
+* [x] DEV target
+* [x] PROD target
+* [x] Python Wheel packaging
+* [x] uv dependency management
+* [x] Hatchling build system
+* [x] Pytest tests
+* [x] Ruff configuration
+* [x] VS Code Dev Container
+* [x] GitHub Actions DEV pipeline
+* [x] GitHub Actions PROD pipeline
+* [x] Databricks OAuth Service Principal authentication
+* [x] Automated Databricks Job execution
+
+---
+
+# Future Improvements
+
+Potential extensions include:
+
+* [ ] Add Delta Lake ingestion and transformation layers
+* [ ] Add Bronze/Silver/Gold architecture
+* [ ] Add data quality validation
+* [ ] Add integration tests against Databricks
+* [ ] Add structured logging
+* [ ] Add monitoring and alerting
+* [ ] Add Unity Catalog permissions management
+* [ ] Add CI quality gates for Ruff
+* [ ] Add pull-request validation
+* [ ] Add deployment approval gates for PROD
+* [ ] Add infrastructure documentation
+* [ ] Add job run monitoring
+* [ ] Add data lineage documentation
+
+---
+
+# Learning Objectives
+
+This project was created to demonstrate practical knowledge of:
+
+```text
+Python
+  │
+  ├── Packaging
+  ├── Testing
+  └── PySpark
+        │
+        ▼
+   Databricks
+        │
+        ├── Asset Bundles
+        ├── Jobs
+        ├── Notebooks
+        └── Unity Catalog
+        │
+        ▼
+      DevOps
+        │
+        ├── Git
+        ├── GitHub Actions
+        ├── CI/CD
+        └── Service Principal
+```
+
+The main objective is to demonstrate how a Data Engineering workload can move from **local development to a controlled production deployment** using modern software engineering practices.
+
+---
+
+# Author
+
+**Ruben Cruz**
+
+Data Engineering · Data Integration · Python · PySpark · Databricks · CI/CD

From eed02ed5197ee17e2c4bdc9117fc1b11a1292182 Mon Sep 17 00:00:00 2001
From: "Ruben Cruz H." <rubencruzh@gmail.com>
Date: Wed, 12 Aug 2026 16:27:32 -0300
Subject: [PATCH 24/24] Update README with detailed project description

Expanded project description to include CI/CD reference implementation.
---
 README.md | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/README.md b/README.md
index e7ae401..5d9096e 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,4 @@
-# Databricks Asset Bundle — Python Data Engineering
-
+# Databricks Asset Bundle — Python Data Engineering - Databricks platform engineering / CI/CD reference implementation.
 A practical Databricks Data Engineering project demonstrating how to develop, test, package, deploy, and execute Python workloads using **Databricks Asset Bundles (DAB)** and **GitHub Actions CI/CD**.
 
 The project implements separate **DEV and PROD environments**, Python Wheel packaging, automated testing, parameterized Databricks Jobs, OAuth Service Principal authentication, and a reproducible development environment using VS Code Dev Containers.