Merge branch 'main' into boolean-encoder-valid-and-true

.github/workflows/r.yml

@@ -133,6 +133,9 @@ jobs:
         with:
           fetch-depth: 0
           submodules: recursive
+      - name: Free up disk space
+        run: |
+          ci/scripts/util_free_space.sh
       - name: Cache Docker Volumes
         uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0
         with:

c_glib/arrow-glib/file-system.cpp

@@ -56,6 +56,8 @@ G_BEGIN_DECLS
  * #GArrowS3FileSystem is a class for S3-backed file system.
  *
  * #GArrowGCSFileSystem is a class for GCS-backed file system.
+ *
+ * #GArrowAzureFileSystem is a class for Azure-backed file system.
  */
 
 /* arrow::fs::FileInfo */
@@ -1561,6 +1563,18 @@ garrow_gcs_file_system_class_init(GArrowGCSFileSystemClass *klass)
 {
 }
 
+G_DEFINE_TYPE(GArrowAzureFileSystem, garrow_azure_file_system, GARROW_TYPE_FILE_SYSTEM)
+
+static void
+garrow_azure_file_system_init(GArrowAzureFileSystem *file_system)
+{
+}
+
+static void
+garrow_azure_file_system_class_init(GArrowAzureFileSystemClass *klass)
+{
+}
+
 G_END_DECLS
 
 GArrowFileInfo *
@@ -1592,6 +1606,8 @@ garrow_file_system_new_raw(std::shared_ptr<arrow::fs::FileSystem> *arrow_file_sy
     file_system_type = GARROW_TYPE_S3_FILE_SYSTEM;
   } else if (type_name == "gcs") {
     file_system_type = GARROW_TYPE_GCS_FILE_SYSTEM;
+  } else if (type_name == "abfs") {
+    file_system_type = GARROW_TYPE_AZURE_FILE_SYSTEM;
   } else if (type_name == "mock") {
     file_system_type = GARROW_TYPE_MOCK_FILE_SYSTEM;
   }

c_glib/arrow-glib/file-system.h

@@ -337,4 +337,16 @@ struct _GArrowGCSFileSystemClass
   GArrowFileSystemClass parent_class;
 };
 
+#define GARROW_TYPE_AZURE_FILE_SYSTEM (garrow_azure_file_system_get_type())
+GARROW_AVAILABLE_IN_18_0
+G_DECLARE_DERIVABLE_TYPE(GArrowAzureFileSystem,
+                         garrow_azure_file_system,
+                         GARROW,
+                         AZURE_FILE_SYSTEM,
+                         GArrowFileSystem)
+struct _GArrowAzureFileSystemClass
+{
+  GArrowFileSystemClass parent_class;
+};
+
 G_END_DECLS

r/tests/testthat/test-extra-package-roundtrip.R

@@ -24,7 +24,7 @@ skip_on_cran()
 # So that we can force these in CI
 load_or_skip <- function(pkg) {
   if (identical(tolower(Sys.getenv("ARROW_R_FORCE_EXTRA_PACKAGE_TESTS")), "true")) {
-    # because of this indirection on the package name we also avoid a CHECK note and 
+    # because of this indirection on the package name we also avoid a CHECK note and
     # we don't otherwise need to Suggest this
     requireNamespace(pkg, quietly = TRUE)
   } else {
@@ -46,11 +46,11 @@ test_that("readr read csvs roundtrip", {
 
   # we should still be able to turn this into a table
   new_df <- read_csv(tf, show_col_types = FALSE)
-  expect_equal(new_df, as_tibble(arrow_table(new_df)))    
+  expect_equal(new_df, as_tibble(arrow_table(new_df)))
 
   # we should still be able to turn this into a table
   new_df <- read_csv(tf, show_col_types = FALSE, lazy = TRUE)
-  expect_equal(new_df, as_tibble(arrow_table(new_df)))    
+  expect_equal(new_df, as_tibble(arrow_table(new_df)))
 
   # and can roundtrip to a parquet file
   pq_tmp_file <- tempfile()
@@ -65,11 +65,11 @@ test_that("data.table objects roundtrip", {
   load_or_skip("data.table")
 
   # https://github.com/Rdatatable/data.table/blob/83fd2c05ce2d8555ceb8ba417833956b1b574f7e/R/cedta.R#L25-L27
-  .datatable.aware=TRUE
+  .datatable.aware <- TRUE
 
   DT <- as.data.table(example_data)
 
-  # Table -> collect which is what writing + reading to parquet uses under the hood to roundtrip
+  # Table to collect which is what writing + reading to parquet uses under the hood to roundtrip
   tab <- as_arrow_table(DT)
   DT_read <- collect(tab)
 
@@ -80,9 +80,9 @@ test_that("data.table objects roundtrip", {
   # and we can set keys + indices + create new columns
   setkey(DT, chr)
   setindex(DT, dbl)
-  DT[, dblshift := data.table::shift(dbl, 1)]
+  DT[, dblshift := shift(dbl, 1)]
 
-  # Table -> collect
+  # Table to collect
   tab <- as_arrow_table(DT)
   DT_read <- collect(tab)
 
@@ -96,7 +96,7 @@ test_that("units roundtrip", {
   tbl <- example_data
   units(tbl$dbl) <- "s"
 
-   # Table -> collect which is what writing + reading to parquet uses under the hood to roundtrip
+  # Table to collect which is what writing + reading to parquet uses under the hood to roundtrip
   tab <- as_arrow_table(tbl)
   tbl_read <- collect(tab)