[SEDONA-390] Add codespell with pre-commit

apache · Sep 9, 2023 · 6e8a77d · 6e8a77d
1 parent d58baa8
commit 6e8a77d
Show file tree

Hide file tree

Showing 16 changed files with 106 additions and 42 deletions.
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -0,0 +1,30 @@
+name: Lint
+
+on: [pull_request]
+
+permissions:
+  contents: read
+
+jobs:
+  pre-commit:
+    name: Run pre-commit  # https://pre-commit.com/
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Checkout ${{ github.ref }} ( ${{ github.sha }} )"
+        uses: actions/checkout@v4
+      - uses: actions/setup-python@v4  # https://www.python.org/
+        with:
+          python-version: '3.x'  # Version range or exact version of a Python version to use, using SemVer's version range syntax
+          architecture: 'x64'  # optional x64 or x86. Defaults to x64 if not specified
+      - name: Install dependencies  # https://pip.pypa.io/en/stable/
+        run: |
+          python -m pip install --upgrade pip
+          pip install pre-commit
+      - name: set PY
+        run: echo "PY=$(python -VV | sha256sum | cut -d' ' -f1)" >> $GITHUB_ENV
+      - uses: actions/cache@v3
+        with:
+          path: ~/.cache/pre-commit
+          key: pre-commit|${{ env.PY }}|${{ hashFiles('.pre-commit-config.yaml') }}
+      - name: Run pre-commit
+        run: pre-commit run --all-files
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -0,0 +1,20 @@
+---
+# https://pre-commit.com/#installation
+default_stages: [commit, push]
+default_language_version:
+  # force all unspecified Python hooks to run python3
+  python: python3
+minimum_pre_commit_version: '2.18.1'
+repos:
+  - repo: meta
+    hooks:
+      - id: identity
+      - id: check-hooks-apply
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.5
+    hooks:
+      - id: codespell
+        name: Run codespell
+        description: Check spelling with codespell
+        entry: codespell --ignore-words=codespell.txt
+        exclude: ^docs/image|^spark/common/src/test/resources/points\.csv$
diff --git a/binder/Sedona_OvertureMaps_GeoParquet.ipynb b/binder/Sedona_OvertureMaps_GeoParquet.ipynb
@@ -80,7 +80,7 @@
    "source": [
     "### Visualizing Overture Maps\n",
     "\n",
-    "Explanation to the each step is similar accross the different datasets. [Click here to learn more about Overture Maps.](https://docs.overturemaps.org)\n",
+    "Explanation to the each step is similar across the different datasets. [Click here to learn more about Overture Maps.](https://docs.overturemaps.org)\n",
     "\n",
     "1. `df = sedona.read.format(\"geoparquet\").load(DATA_LINK+\"theme=XX/type=YY\")`\n",
     "\n",

diff --git a/codespell.txt b/codespell.txt
@@ -0,0 +1,14 @@
+actualy
+afterall
+bu
+eiter
+fpt
+limite
+nd
+ois
+parm
+pixelx
+refere
+ser
+shouldbe
+wel
diff --git a/common/src/test/java/org/apache/sedona/common/FunctionsTest.java b/common/src/test/java/org/apache/sedona/common/FunctionsTest.java
@@ -76,29 +76,29 @@ public void asEWKT() throws Exception{
         Geometry geometry = geometryFactory.createPoint(new Coordinate(1.0, 2.0));
         String actualResult = Functions.asEWKT(geometry);
         String expectedResult = "SRID=4236;POINT (1 2)";
-        Geometry acutal = Constructors.geomFromEWKT(expectedResult);
-        assertEquals(geometry, acutal);
+        Geometry actual = Constructors.geomFromEWKT(expectedResult);
+        assertEquals(geometry, actual);
         assertEquals(expectedResult, actualResult);
 
         geometry = geometryFactory.createPoint(new Coordinate(1.0, 2.0, 3.0));
         actualResult = Functions.asEWKT(geometry);
         expectedResult = "SRID=4236;POINT Z(1 2 3)";
-        acutal = Constructors.geomFromEWKT(expectedResult);
-        assertEquals(geometry, acutal);
+        actual = Constructors.geomFromEWKT(expectedResult);
+        assertEquals(geometry, actual);
         assertEquals(expectedResult, actualResult);
 
         geometry = geometryFactory.createPoint(new CoordinateXYM(1.0, 2.0, 3.0));
         actualResult = Functions.asEWKT(geometry);
         expectedResult = "SRID=4236;POINT M(1 2 3)";
-        acutal = Constructors.geomFromEWKT(expectedResult);
-        assertEquals(geometry, acutal);
+        actual = Constructors.geomFromEWKT(expectedResult);
+        assertEquals(geometry, actual);
         assertEquals(expectedResult, actualResult);
 
         geometry = geometryFactory.createPoint(new CoordinateXYZM(1.0, 2.0, 3.0, 4.0));
         actualResult = Functions.asEWKT(geometry);
         expectedResult = "SRID=4236;POINT ZM(1 2 3 4)";
-        acutal = Constructors.geomFromEWKT(expectedResult);
-        assertEquals(geometry, acutal);
+        actual = Constructors.geomFromEWKT(expectedResult);
+        assertEquals(geometry, actual);
         assertEquals(expectedResult, actualResult);
     }
 
@@ -107,29 +107,29 @@ public void asWKT() throws Exception {
         Geometry geometry = GEOMETRY_FACTORY.createPoint(new Coordinate(1.0, 2.0));
         String actualResult = Functions.asWKT(geometry);
         String expectedResult = "POINT (1 2)";
-        Geometry acutal = Constructors.geomFromEWKT(expectedResult);
-        assertEquals(geometry, acutal);
+        Geometry actual = Constructors.geomFromEWKT(expectedResult);
+        assertEquals(geometry, actual);
         assertEquals(expectedResult, actualResult);
 
         geometry = GEOMETRY_FACTORY.createPoint(new Coordinate(1.0, 2.0, 3.0));
         actualResult = Functions.asWKT(geometry);
         expectedResult = "POINT Z(1 2 3)";
-        acutal = Constructors.geomFromEWKT(expectedResult);
-        assertEquals(geometry, acutal);
+        actual = Constructors.geomFromEWKT(expectedResult);
+        assertEquals(geometry, actual);
         assertEquals(expectedResult, actualResult);
 
         geometry = GEOMETRY_FACTORY.createPoint(new CoordinateXYM(1.0, 2.0, 3.0));
         actualResult = Functions.asWKT(geometry);
         expectedResult = "POINT M(1 2 3)";
-        acutal = Constructors.geomFromEWKT(expectedResult);
-        assertEquals(geometry, acutal);
+        actual = Constructors.geomFromEWKT(expectedResult);
+        assertEquals(geometry, actual);
         assertEquals(expectedResult, actualResult);
 
         geometry = GEOMETRY_FACTORY.createPoint(new CoordinateXYZM(1.0, 2.0, 3.0, 4.0));
         actualResult = Functions.asWKT(geometry);
         expectedResult = "POINT ZM(1 2 3 4)";
-        acutal = Constructors.geomFromEWKT(expectedResult);
-        assertEquals(geometry, acutal);
+        actual = Constructors.geomFromEWKT(expectedResult);
+        assertEquals(geometry, actual);
         assertEquals(expectedResult, actualResult);
     }
 
@@ -942,22 +942,22 @@ public void makeLine3d() {
         WKTWriter wktWriter3D = new WKTWriter(3);
         Point point1 = GEOMETRY_FACTORY.createPoint(new Coordinate(1, 1, 1));
         Point point2 = GEOMETRY_FACTORY.createPoint(new Coordinate(2, 2, 2));
-        LineString acutalLinestring = (LineString) Functions.makeLine(point1, point2);
+        LineString actualLinestring = (LineString) Functions.makeLine(point1, point2);
         LineString expectedLineString = GEOMETRY_FACTORY.createLineString(coordArray3d( 1, 1, 1, 2, 2, 2));
-        assertEquals(wktWriter3D.write(acutalLinestring), wktWriter3D.write(expectedLineString));
+        assertEquals(wktWriter3D.write(actualLinestring), wktWriter3D.write(expectedLineString));
 
         MultiPoint multiPoint1 = GEOMETRY_FACTORY.createMultiPointFromCoords(coordArray3d(0.5, 0.5, 1, 1, 1, 1));
         MultiPoint multiPoint2 = GEOMETRY_FACTORY.createMultiPointFromCoords(coordArray3d(0.5, 0.5, 2, 2, 2, 2));
-        acutalLinestring = (LineString) Functions.makeLine(multiPoint1, multiPoint2);
+        actualLinestring = (LineString) Functions.makeLine(multiPoint1, multiPoint2);
         expectedLineString = GEOMETRY_FACTORY.createLineString(coordArray3d( 0.5, 0.5, 1, 1, 1, 1, 0.5, 0.5, 2, 2, 2, 2));
-        assertEquals(wktWriter3D.write(acutalLinestring), wktWriter3D.write(expectedLineString));
+        assertEquals(wktWriter3D.write(actualLinestring), wktWriter3D.write(expectedLineString));
 
         LineString line1 = GEOMETRY_FACTORY.createLineString(coordArray3d(0, 0, 1, 1, 1, 1));
         LineString line2 = GEOMETRY_FACTORY.createLineString(coordArray3d(2, 2, 2, 2, 3, 3));
         Geometry[] geoms = new Geometry[]{line1, line2};
-        acutalLinestring = (LineString) Functions.makeLine(geoms);
+        actualLinestring = (LineString) Functions.makeLine(geoms);
         expectedLineString = GEOMETRY_FACTORY.createLineString(coordArray3d( 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3));
-        assertEquals(wktWriter3D.write(acutalLinestring), wktWriter3D.write(expectedLineString));
+        assertEquals(wktWriter3D.write(actualLinestring), wktWriter3D.write(expectedLineString));
     }
 
     @Test

diff --git a/common/src/test/java/org/apache/sedona/common/utils/RasterUtilsTest.java b/common/src/test/java/org/apache/sedona/common/utils/RasterUtilsTest.java
@@ -80,7 +80,7 @@ public void testNoDataValueUsingComplexCategoryList() {
         Assert.assertNull(band5.getCategory(10));
         Assert.assertEquals("GrayScale", band5.getCategory(100).getName().toString());
 
-        // If the new no data value falls within the range of an existing quantitative category, the category is splitted
+        // If the new no data value falls within the range of an existing quantitative category, the category is split
         // into two categories.
         GridSampleDimension band6 = RasterUtils.createSampleDimensionWithNoDataValue(band, 150);
         Assert.assertEquals(150, RasterUtils.getNoDataValue(band6), 1e-9);

diff --git a/docs/api/flink/Function.md b/docs/api/flink/Function.md
@@ -1100,7 +1100,7 @@ LINESTRING EMPTY
 
 ## ST_FrechetDistance
 
-Introduction: Computes and returns discrete [Frechet Distance](https://en.wikipedia.org/wiki/Fr%C3%A9chet_distance) between the given two geometrie,
+Introduction: Computes and returns discrete [Frechet Distance](https://en.wikipedia.org/wiki/Fr%C3%A9chet_distance) between the given two geometries,
 based on [Computing Discrete Frechet Distance](http://www.kr.tuwien.ac.at/staff/eiter/et-archive/cdtr9464.pdf)
 
 If any of the geometries is empty, returns 0.0

diff --git a/docs/api/sql/Function.md b/docs/api/sql/Function.md
@@ -1109,7 +1109,7 @@ LINESTRING EMPTY
 
 ## ST_FrechetDistance
 
-Introduction: Computes and returns discrete [Frechet Distance](https://en.wikipedia.org/wiki/Fr%C3%A9chet_distance) between the given two geometrie,
+Introduction: Computes and returns discrete [Frechet Distance](https://en.wikipedia.org/wiki/Fr%C3%A9chet_distance) between the given two geometries,
 based on [Computing Discrete Frechet Distance](http://www.kr.tuwien.ac.at/staff/eiter/et-archive/cdtr9464.pdf)
 
 If any of the geometries is empty, returns 0.0

diff --git a/docs/setup/release-notes.md b/docs/setup/release-notes.md
@@ -19,7 +19,7 @@ Sedona 1.4.1 is compiled against, Spark 3.3 / Spark 3.4 / Flink 1.12, Java 8.
 * [X] **Sedona Spark & Flink** Introduced `SedonaContext` to unify Sedona entry points.
 * [X] **Sedona Spark** Support Spark 3.4.
 * [X] **Sedona Spark** Added a number of new ST functions.
-* [X] **Zeppelin** Zeppelin helium plugin supports ploting geometries like linestring, polygon.
+* [X] **Zeppelin** Zeppelin helium plugin supports plotting geometries like linestring, polygon.
 
 ### API change
 
@@ -74,7 +74,7 @@ Sedona 1.4.1 is compiled against, Spark 3.3 / Spark 3.4 / Flink 1.12, Java 8.
 </li>
 <li>[<a href='https://issues.apache.org/jira/browse/SEDONA-239'>SEDONA-239</a>] -         Implement ST_NumPoints
 </li>
-<li>[<a href='https://issues.apache.org/jira/browse/SEDONA-264'>SEDONA-264</a>] -         zeppelin helium plugin supports ploting geometry like linestring, polygon
+<li>[<a href='https://issues.apache.org/jira/browse/SEDONA-264'>SEDONA-264</a>] -         zeppelin helium plugin supports plotting geometry like linestring, polygon
 </li>
 <li>[<a href='https://issues.apache.org/jira/browse/SEDONA-280'>SEDONA-280</a>] -         Add ST_GeometricMedian
 </li>
@@ -335,7 +335,7 @@ GEOGCS["WGS 84",
   * [SEDONA-143](https://issues.apache.org/jira/browse/SEDONA-143) - Add missing unit tests for the Flink predicates
   * [SEDONA-144](https://issues.apache.org/jira/browse/SEDONA-144) - Add ST_AsGeoJSON to the Flink API
   * [SEDONA-145](https://issues.apache.org/jira/browse/SEDONA-145) - Fix ST_AsEWKT to reserve the Z coordinate
-  * [SEDONA-146](https://issues.apache.org/jira/browse/SEDONA-146) - Add missing output funtions to the Flink API
+  * [SEDONA-146](https://issues.apache.org/jira/browse/SEDONA-146) - Add missing output functions to the Flink API
   * [SEDONA-147](https://issues.apache.org/jira/browse/SEDONA-147) - Add SRID functions to the Flink API
   * [SEDONA-148](https://issues.apache.org/jira/browse/SEDONA-148) - Add boolean functions to the Flink API
   * [SEDONA-149](https://issues.apache.org/jira/browse/SEDONA-149) - Add Python 3.10 support

diff --git a/docs/tutorial/rdd.md b/docs/tutorial/rdd.md
@@ -364,7 +364,7 @@ Assume you now have an SpatialRDD (typed or generic). You can use the following
 
 Besides the rectangle (Envelope) type range query window, Sedona range query window can be Point/Polygon/LineString.
 
-The code to create a point, linestring (4 vertexes) and polygon (4 vertexes) is as follows:
+The code to create a point, linestring (4 vertices) and polygon (4 vertices) is as follows:
 
 === "Scala"
 

diff --git a/docs/tutorial/sql.md b/docs/tutorial/sql.md
@@ -691,7 +691,7 @@ A map rendered by accessing the map object created by SedonaKepler includes a co
 
 #### Saving and setting config
 
-A map object's current config can be accessed by accessing its 'config' attribute like `map.config`. This config can be saved for future use or use across notebooks if the exact same map is to be rendered everytime.
+A map object's current config can be accessed by accessing its 'config' attribute like `map.config`. This config can be saved for future use or use across notebooks if the exact same map is to be rendered every time.
 
 !!!Note
 	The map config references each applied customization with the name given to the dataframe and hence will work only on maps with the same name of dataframe supplied.

diff --git a/flink-shaded/pom.xml b/flink-shaded/pom.xml
@@ -53,7 +53,7 @@
         <plugins>
             <plugin>
                 <!-- Skip running resolved-pom-maven-plugin since shade will
-                     generate dependency reduced pom which substitudes property
+                     generate dependency reduced pom which substitutes property
                      values. resolved-pom-maven-plugin will break pom
                      installation when working with maven-shade-plugin.  -->
                 <groupId>io.paradoxical</groupId>

diff --git a/python/sedona/sql/st_functions.py b/python/sedona/sql/st_functions.py
@@ -823,7 +823,7 @@ def ST_MakeLine(geom1: ColumnOrName, geom2: Optional[ColumnOrName] = None) -> Co
     :type geometry: ColumnOrName
     :param geom2: Geometry column to convert. If geoms is empty, then geom1 is an array of geometries.
     :type geometry: Optional[ColumnOrName], optional
-    :return: LineString geometry column created from the input geomtries.
+    :return: LineString geometry column created from the input geometries.
     :rtype: Column
     """
     args = (geom1,) if geom2 is None else (geom1, geom2)
@@ -1387,7 +1387,7 @@ def ST_Affine(geometry: ColumnOrName, a: Union[ColumnOrName, float], b: Union[Co
                 g: Optional[Union[ColumnOrName, float]] = None, h: Optional[Union[ColumnOrName, float]] = None,
                 i: Optional[Union[ColumnOrName, float]] = None,  zOff: Optional[Union[ColumnOrName, float]] = None) -> Column:
     """
-    Apply a 3D/2D affine tranformation to the given geometry
+    Apply a 3D/2D affine transformation to the given geometry
     x = a * x + b * y + c * z + xOff | x = a * x + b * y + xOff
     y = d * x + e * y + f * z + yOff | y = d * x + e * y + yOff
     z = g * x + h * y + i * z + zOff
@@ -1476,7 +1476,7 @@ def ST_CoordDim(geometry: ColumnOrName) -> Column:
 
     :param geometry: Geometry column to return for.
     :type geometry: ColumnOrName
-    :return: Number of dimensinos in a coordinate column as an integer column.
+    :return: Number of dimensions in a coordinate column as an integer column.
     :rtype: Column
     """
     return _call_st_function("ST_CoordDim", geometry)

diff --git a/spark-shaded/pom.xml b/spark-shaded/pom.xml
@@ -90,7 +90,7 @@
         <plugins>
             <plugin>
                 <!-- Skip running resolved-pom-maven-plugin since shade will
-                     generate dependency reduced pom which substitudes property
+                     generate dependency reduced pom which substitutes property
                      values. resolved-pom-maven-plugin will break pom
                      installation when working with maven-shade-plugin.  -->
                 <groupId>io.paradoxical</groupId>

diff --git a/...n/java/org/apache/sedona/core/formatMapper/shapefileParser/parseUtils/shp/ShapeSerde.java b/...n/java/org/apache/sedona/core/formatMapper/shapefileParser/parseUtils/shp/ShapeSerde.java
@@ -46,12 +46,12 @@
  * Point: 8 bytes for X coordinate, followed by 8 bytes for Y coordinate.
  * LineString is serialized as MultiLineString.
  * MultiLineString: 16 bytes for envelope, 4 bytes for the number of line strings,
- * 4 bytes for total number of vertexes, 16 * num-vertexes for
- * XY coordinates of all the vertexes.
+ * 4 bytes for total number of vertices, 16 * num-vertices for
+ * XY coordinates of all the vertices.
  * Polygons is serialized as MultiPolygon.
  * MultiPolygon: 16 bytes for envelope, 4 bytes for the total number of exterior and
- * interior rings of all polygons, 4 bytes for total number of vertexes,
- * 16 * num-vertexes for XY coordinates of all the vertexes. The vertexes
+ * interior rings of all polygons, 4 bytes for total number of vertices,
+ * 16 * num-vertices for XY coordinates of all the vertices. The vertices
  * are written one polygon at a time, exterior ring first, followed by
  * interior rings.
  */

diff --git a/...n/src/main/java/org/apache/sedona/core/spatialPartitioning/quadtree/StandardQuadTree.java b/...n/src/main/java/org/apache/sedona/core/spatialPartitioning/quadtree/StandardQuadTree.java
@@ -85,7 +85,7 @@ private int findRegion(QuadRectangle r, boolean split)
                 this.split();
             }
 
-            // can be null if not splitted
+            // can be null if not split
             if (regions != null) {
                 for (int i = 0; i < regions.length; i++) {
                     if (regions[i].getZone().contains(r)) {
@@ -102,7 +102,7 @@ private int findRegion(QuadRectangle r, boolean split)
     private int findRegion(int x, int y)
     {
         int region = REGION_SELF;
-        // can be null if not splitted
+        // can be null if not split
         if (regions != null) {
             for (int i = 0; i < regions.length; i++) {
                 if (regions[i].getZone().contains(x, y)) {