[DOCS] pre-commit: remove trailing whitespace from .md and .Rmd f… (

apache#1169)

.pre-commit-config.yaml

@@ -36,7 +36,7 @@ repos:
       - id: end-of-file-fixer
         exclude: \.svg$|^docs/image|^spark/common/src/test/resources
       - id: trailing-whitespace
-        files: \.(ipynb|java|py|R|scala|sh|xml|yaml|yml)$
+        exclude: ^docs-overrides/main\.html$|\.Rd$
   - repo: https://github.com/igorshubovych/markdownlint-cli
     rev: v0.38.0
     hooks:

R/vignettes/articles/apache-sedona.Rmd

@@ -135,8 +135,8 @@ data_tbl <- copy_to(sc, data)
 
 data_tbl
 
-data_tbl %>% 
-  transmute(geometry = st_geomfromtext(X1)) %>% 
+data_tbl %>%
+  transmute(geometry = st_geomfromtext(X1)) %>%
   sdf_schema()
 ```
 No automatic translation of `{sf}` objects is provided, they need to be converted to text (or binary) format before copying to spark.
@@ -146,18 +146,18 @@ data <- sf::st_read(here::here("../spark/common/src/test/resources/testPolygon.j
 
 data %>% glimpse()
 
-data_tbl <- 
+data_tbl <-
   copy_to(
-    sc, 
-    data %>% 
-    mutate(geometry_wkb = geometry %>% sf::st_as_text()) %>% 
+    sc,
+    data %>%
+    mutate(geometry_wkb = geometry %>% sf::st_as_text()) %>%
     sf::st_drop_geometry(),
   name = "data",
   overwrite = TRUE
 )
 
-data_tbl %>% 
-  transmute(geometry = st_geomfromtext(geometry_wkb)) %>% 
+data_tbl %>%
+  transmute(geometry = st_geomfromtext(geometry_wkb)) %>%
   sdf_schema()
 ```
 
@@ -168,20 +168,20 @@ Loading data in R and then copying it to Spark will most likely not be the optim
 ```{r}
 data_tbl <- spark_read_geojson(sc, path = here::here("../spark/common/src/test/resources/testPolygon.json"), name = "data")
 
-data_tbl %>% 
+data_tbl %>%
   glimpse()
 
-data_tbl %>% 
-  # select(geometry) %>% 
-  sdf_schema() %>% 
+data_tbl %>%
+  # select(geometry) %>%
+  sdf_schema() %>%
   lobstr::tree()
 ```
 
 
 ## Manipulating
 
 The dbplyr interface transparently translates dbplyr workflows into SQL, and gives access to all Apache Sedona SQL functions:
- 
+
 * [Vector functions](../../../api/sql/Function/)
 * [Vector predicates](../../../api/sql/Predicate/)
 * [Vector aggregate functions](../../../api/sql/AggregateFunction/)
@@ -191,45 +191,45 @@ Results are then collected back into R with `collect`.
 
 ```{r}
 ## ! ST_transform uses lon/lat order since v1.5.0. Before, it used lat/lon order.
-data_tbl %>% 
+data_tbl %>%
   mutate(
     ALAND = ALAND %>% as.numeric(),
     AWATER = AWATER %>% as.numeric(),
     area = ALAND + AWATER,
     geometry_proj = st_transform(geometry, "epsg:4326", "epsg:5070", TRUE),
     area_geom = st_area(geometry_proj)
-    ) %>% 
-  select(STATEFP, COUNTYFP, area, area_geom) %>% 
-  head() %>% 
+    ) %>%
+  select(STATEFP, COUNTYFP, area, area_geom) %>%
+  head() %>%
   collect()
 ```
 
 Geometries need to be converted to a serializable (text or binary) format before `collect` is called:
 ```{r}
 ## Setting the CRS in R post-collect
-data_tbl %>% 
+data_tbl %>%
   mutate(
     area = st_area(st_transform(geometry, "epsg:4326", "epsg:5070", TRUE)),
     geometry_wkb = geometry %>% st_asBinary()
-    ) %>% 
-  select(COUNTYFP, geometry_wkb) %>% 
-  head() %>% 
-  collect() %>% 
+    ) %>%
+  select(COUNTYFP, geometry_wkb) %>%
+  head() %>%
+  collect() %>%
   sf::st_as_sf(crs = 4326)
 ```
 
 
 ```{r}
 ## Setting the CRS in Spark (and using EWKT to keep it)
-data_tbl %>% 
+data_tbl %>%
   mutate(
     area = st_area(st_transform(geometry, "epsg:4326", "epsg:5070", TRUE)),
     geometry_ewkt = geometry %>% st_setsrid(4326) %>% st_asewkt()
-    ) %>% 
-  select(COUNTYFP, geometry_ewkt) %>% 
-  head() %>% 
-  collect() %>% 
-  sf::st_as_sf(wkt = "geometry_ewkt") 
+    ) %>%
+  select(COUNTYFP, geometry_ewkt) %>%
+  head() %>%
+  collect() %>%
+  sf::st_as_sf(wkt = "geometry_ewkt")
 ```
 
 
@@ -238,8 +238,8 @@ Collected results can be saved from R. In many cases it will be more efficient t
 
 ```{r}
 dest_file <- tempfile() ## Destination folder
-data_tbl %>% 
-  filter(str_sub(COUNTYFP, 1, 2) == "00") %>% 
+data_tbl %>%
+  filter(str_sub(COUNTYFP, 1, 2) == "00") %>%
   spark_write_geoparquet(path = dest_file)
 
 dest_file %>% dir(recursive = TRUE)
@@ -249,8 +249,8 @@ The output can be partitioned by the columns present in the data:
 
 ```{r}
 dest_file <- tempfile()  ## Destination folder
-data_tbl %>% 
-  filter(str_sub(COUNTYFP, 1, 2) == "00") %>% 
+data_tbl %>%
+  filter(str_sub(COUNTYFP, 1, 2) == "00") %>%
   spark_write_geoparquet(path = dest_file, partition_by = "COUNTYFP")
 
 dest_file %>% dir(recursive = TRUE)
@@ -439,21 +439,21 @@ sc <- spark_connect(master = "local", config = config)
 
 Check
 ```{r}
-invoke_new(sc, "org.apache.sedona.core.utils.SedonaConf", invoke(spark_session(sc), "conf")) 
+invoke_new(sc, "org.apache.sedona.core.utils.SedonaConf", invoke(spark_session(sc), "conf"))
 ```
 (Still true)
 
 Or change at runtime:
 ```{r}
-spark_session(sc) %>% 
-  invoke("conf") %>% 
+spark_session(sc) %>%
+  invoke("conf") %>%
   invoke("set", "sedona.global.index","false")
 
-invoke_new(sc, "org.apache.sedona.core.utils.SedonaConf", invoke(spark_session(sc), "conf")) 
+invoke_new(sc, "org.apache.sedona.core.utils.SedonaConf", invoke(spark_session(sc), "conf"))
 ```
 
 ```{r}
-invoke_new(sc, "org.apache.sedona.core.utils.SedonaConf", invoke(spark_session(sc), "conf")) 
+invoke_new(sc, "org.apache.sedona.core.utils.SedonaConf", invoke(spark_session(sc), "conf"))
 ```
 
 

R/vignettes/articles/raster.Rmd

@@ -36,11 +36,11 @@ sc <- spark_connect(master = "local")
 
 data_tbl <- spark_read_binary(sc, dir = here::here("/../spark/common/src/test/resources/raster/"), name = "data")
 
-raster <- 
-  data_tbl %>% 
+raster <-
+  data_tbl %>%
   mutate(raster = RS_FromGeoTiff(content))
 
-raster 
+raster
 
 raster %>% sdf_schema()
 ```
@@ -55,34 +55,34 @@ Functions taking in `raster: Raster` arguments are meant to be used with data lo
 
 For example, getting the number of bands:
 ```{r}
-raster %>% 
+raster %>%
   mutate(
     nbands = RS_NumBands(raster)
-  ) %>% 
-  select(path, nbands) %>% 
-  collect() %>% 
+  ) %>%
+  select(path, nbands) %>%
+  collect() %>%
   mutate(path = path %>% basename())
 ```
 
 Or getting values the envelope:
 ```{r}
-raster %>% 
+raster %>%
   mutate(
     env = RS_Envelope(raster) %>% st_astext()
-  ) %>% 
-  select(path, env) %>% 
-  collect() %>% 
+  ) %>%
+  select(path, env) %>%
+  collect() %>%
   mutate(path = path %>% basename())
 ```
 
 Or getting values at specific points:
 ```{r}
-raster %>% 
+raster %>%
   mutate(
     val = RS_Value(raster, ST_Point(-13077301.685, 4002565.802))
-  ) %>% 
-  select(path, val) %>% 
-  collect() %>% 
+  ) %>%
+  select(path, val) %>%
+  collect() %>%
   mutate(path = path %>% basename())
 ```
 
@@ -96,8 +96,8 @@ To write a Sedona binary DataFrame to external storage using Sedona's built-in `
 
 ```{r}
 dest_file <- tempfile()
-raster %>% 
-  mutate(content = RS_AsGeoTiff(raster)) %>% 
+raster %>%
+  mutate(content = RS_AsGeoTiff(raster)) %>%
   spark_write_raster(path = dest_file)
 
 dir(dest_file, recursive = TRUE)
@@ -112,10 +112,10 @@ Available options see [Raster writer](../../../api/sql/Raster-writer/):
 
 ```{r}
 dest_file <- tempfile()
-raster %>% 
-  mutate(content = RS_AsArcGrid(raster)) %>% 
-  spark_write_raster(path = dest_file, 
-                     options = list("rasterField" = "content", 
+raster %>%
+  mutate(content = RS_AsArcGrid(raster)) %>%
+  spark_write_raster(path = dest_file,
+                     options = list("rasterField" = "content",
                                     "fileExtension" = ".asc",
                                     "pathField" = "path"
                      ))

docs/api/flink/Constructor.md

@@ -102,7 +102,7 @@ Example:
 SELECT ST_GeomFromGML('
     <gml:LineString srsName="EPSG:4269">
     	<gml:coordinates>
-        	-71.16028,42.258729  
+        	-71.16028,42.258729
         	-71.160837,42.259112
         	-71.161143,42.25932
     	</gml:coordinates>
@@ -131,7 +131,7 @@ Example:
 SELECT ST_GeomFromKML('
 	<LineString>
 		<coordinates>
-			-71.1663,42.2614 
+			-71.1663,42.2614
 			-71.1667,42.2616
 		</coordinates>
 	</LineString>
@@ -397,10 +397,10 @@ POINT (1.2345 2.3456)
 
 ## ST_PointZ
 
-Introduction: Construct a Point from X, Y and Z and an optional srid. If srid is not set, it defaults to 0 (unknown). 
+Introduction: Construct a Point from X, Y and Z and an optional srid. If srid is not set, it defaults to 0 (unknown).
 Must use ST_AsEWKT function to print the Z coordinate.
 
-Format: 
+Format:
 
 `ST_PointZ (X: Double, Y: Double, Z: Double)`
 
@@ -444,7 +444,7 @@ POINT (40.7128 -74.006)
 
 Introduction: Construct a Polygon from MinX, MinY, MaxX, MaxY.
 
-Format: 
+Format:
 
 `ST_PolygonFromEnvelope (MinX: Double, MinY: Double, MaxX: Double, MaxY: Double)`