feat: Add poetry configuration

.envrc

@@ -27,7 +27,11 @@ pvenv=lakehouse
 use python ${pyversion}
 layout virtualenv ${pyversion} ${pvenv}
 layout activate ${pvenv}-${pyversion}
-pip install -q -r requirements.txt
+poetry install
+
+# Setup Git
+pre-commit install
+
 
 # Start
 echo -e ""

.pre-commit-config.yaml

@@ -1,8 +1,40 @@
+# pre-commit autoupdate
 ---
 
 repos:
   - repo: https://github.com/kynan/nbstripout
     rev: 0.6.1
     hooks:
       - id: nbstripout
-        args: ["--extra-keys", "metadata.pycharm"]
+        files: ^notebook\/.*\.ipynb$
+        args: ["--extra-keys", "metadata.pycharm"]
+
+  - repo: https://github.com/psf/black
+    rev: 23.7.0
+    hooks:
+      - id: black
+        files: ^(dags|dbts)/
+        types: [python]
+        args: [--line-length=100]
+
+  - repo: https://github.com/pycqa/flake8
+    rev: 6.1.0
+    hooks:
+      - id: flake8
+        files: ^(dags|dbts)/
+        types: [python]
+        additional_dependencies: [
+          'flake8-blind-except',
+          'flake8-docstrings',
+          'flake8-bugbear',
+          'flake8-comprehensions',
+          'flake8-docstrings',
+          'flake8-implicit-str-concat',
+          'pydocstyle>=5.0.0',
+        ]
+
+  - repo: https://github.com/commitizen-tools/commitizen
+    rev: 3.7.0
+    hooks:
+      - id: commitizen
+        stages: [commit-msg]

notebook/spark-iceberg.ipynb

@@ -4,7 +4,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "caff0a1b-3ecb-405a-872c-07ae3040b571",
-   "metadata": {},
+   "metadata": {
+    "is_executing": true
+   },
    "outputs": [],
    "source": [
     "from pyspark.sql import SparkSession\n",
@@ -17,7 +19,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "d4efcffd-dc42-43b4-93c6-053aadc16ee2",
-   "metadata": {},
+   "metadata": {
+    "is_executing": true
+   },
    "outputs": [],
    "source": [
     "spark.sql(\"\"\"\n",
@@ -29,7 +33,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "772be00b-9223-46c2-a927-6e967ad4da78",
-   "metadata": {},
+   "metadata": {
+    "is_executing": true
+   },
    "outputs": [],
    "source": [
     "spark.sql(\"\"\"\n",
@@ -47,7 +53,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "cff13884-ff88-43a5-a42b-1fc91a95889b",
-   "metadata": {},
+   "metadata": {
+    "is_executing": true
+   },
    "outputs": [],
    "source": []
   }