Add pre-commit (#15)

* Add pre-commit

* Update to Python 3.12

* Update pre-commit

.github/workflows/deploy.yml

@@ -10,12 +10,12 @@ on:
       - master
 # This job installs dependencies, build the book, and pushes it to `gh-pages`
 jobs:
-  build-and-deploy-book:
+  build-and-deploy:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
         os: [ubuntu-latest]
-        python-version: [3.9]
+        python-version: ["3.12"]
     steps:
       - uses: actions/checkout@v3
 

.github/workflows/maxar_data_catalog.yml

@@ -14,16 +14,16 @@ jobs:
       - name: setup python
         uses: actions/setup-python@v4
         with:
-          python-version: "3.10"
+          python-version: "3.12"
       - name: Install GDAL
         run: |
-            python -m pip install --upgrade pip
-            pip install --no-cache-dir Cython
-            pip install --find-links=https://girder.github.io/large_image_wheels --no-cache GDAL
+          python -m pip install --upgrade pip
+          pip install --no-cache-dir Cython
+          pip install --find-links=https://girder.github.io/large_image_wheels --no-cache GDAL
       - name: Test GDAL installation
         run: |
-            python -c "from osgeo import gdal"
-            gdalinfo --version
+          python -c "from osgeo import gdal"
+          gdalinfo --version
       - name: install dependencies
         run: |
           pip install -r requirements.txt

.pre-commit-config.yaml

@@ -0,0 +1,31 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-toml
+      - id: check-yaml
+      - id: end-of-file-fixer
+        types: [python]
+      - id: requirements-txt-fixer
+      - id: check-added-large-files
+        args: ["--maxkb=500"]
+
+  - repo: https://github.com/psf/black
+    rev: 24.10.0
+    hooks:
+      - id: black-jupyter
+
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+      - id: codespell
+        args:
+          [
+            "--ignore-words-list=aci,acount,acounts,fallow,ges,hart,hist,nd,ned,ois,wqs,watermask,tre",
+            "--skip=*.csv,*.geojson,*.json,*.yml*.js,*.html,*cff,*.pdf",
+          ]
+
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.7.1
+    hooks:
+      - id: nbstripout

examples/maxar_open_data.ipynb

@@ -3,7 +3,7 @@
   {
    "attachments": {},
    "cell_type": "markdown",
-   "id": "aa6cb20e",
+   "id": "0",
    "metadata": {},
    "source": [
     "[![image](https://studiolab.sagemaker.aws/studiolab.svg)](https://studiolab.sagemaker.aws/import/github/opengeos/maxar-open-data/blob/master/examples/maxar_open_data.ipynb)\n",
@@ -26,7 +26,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d0c79e4c",
+   "id": "1",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -36,7 +36,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3a64fb57",
+   "id": "2",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -48,59 +48,59 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5e4c4039",
+   "id": "3",
    "metadata": {},
    "outputs": [],
    "source": [
-    "repo = 'https://raw.githubusercontent.com/opengeos/maxar-open-data/master/'"
+    "repo = \"https://raw.githubusercontent.com/opengeos/maxar-open-data/master/\""
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "96a0534d",
+   "id": "4",
    "metadata": {},
    "outputs": [],
    "source": [
-    "datasets = pd.read_csv(f'{repo}datasets.csv')\n",
+    "datasets = pd.read_csv(f\"{repo}datasets.csv\")\n",
     "datasets"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2795e43b",
+   "id": "5",
    "metadata": {},
    "outputs": [],
    "source": [
-    "dataset = 'Kahramanmaras-turkey-earthquake-23'"
+    "dataset = \"Kahramanmaras-turkey-earthquake-23\""
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "82615421",
+   "id": "6",
    "metadata": {},
    "outputs": [],
    "source": [
-    "df = pd.read_csv(f'{repo}datasets/{dataset}.tsv', sep='\\t')\n",
+    "df = pd.read_csv(f\"{repo}datasets/{dataset}.tsv\", sep=\"\\t\")\n",
     "df.head()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "18f7ffc7",
+   "id": "7",
    "metadata": {},
    "outputs": [],
    "source": [
-    "geojson = f'{repo}datasets/{dataset}.geojson'"
+    "geojson = f\"{repo}datasets/{dataset}.geojson\""
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c9d39bdb",
+   "id": "8",
    "metadata": {},
    "outputs": [],
    "source": [