apacheGH-33209: [C++] Support for reading JSON Datasets (apache#33732)

This adds initial support the JSON file format to the Dataset library. Since there's currently no public API for writing JSON files, this only deals with the reader-side facilities. * Closes: apache#33209 Lead-authored-by: benibus <[email protected]> Co-authored-by: Ben Harkins <[email protected]> Co-authored-by: Weston Pace <[email protected]> Signed-off-by: Weston Pace <[email protected]>
khwilson · Feb 16, 2023 · 45918a9 · 45918a9
1 parent 9033573
commit 45918a9
Show file tree

Hide file tree

Showing 5 changed files with 889 additions and 5 deletions.
diff --git a/cpp/src/arrow/dataset/CMakeLists.txt b/cpp/src/arrow/dataset/CMakeLists.txt
@@ -46,6 +46,10 @@ if(ARROW_CSV)
   set(ARROW_DATASET_SRCS ${ARROW_DATASET_SRCS} file_csv.cc)
 endif()
 
+if(ARROW_JSON)
+  set(ARROW_DATASET_SRCS ${ARROW_DATASET_SRCS} file_json.cc)
+endif()
+
 if(ARROW_ORC)
   set(ARROW_DATASET_SRCS ${ARROW_DATASET_SRCS} file_orc.cc)
 endif()
@@ -148,6 +152,10 @@ if(ARROW_CSV)
   add_arrow_dataset_test(file_csv_test)
 endif()
 
+if(ARROW_JSON)
+  add_arrow_dataset_test(file_json_test)
+endif()
+
 if(ARROW_ORC)
   add_arrow_dataset_test(file_orc_test)
 endif()