You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@arrow.apache.org by GitBox <gi...@apache.org> on 2020/10/01 17:08:08 UTC
[GitHub] [arrow] pitrou opened a new pull request #8319: ARROW-10057: [C++] Add hand-written Parquet nested tests
pitrou opened a new pull request #8319:
URL: https://github.com/apache/arrow/pull/8319
One of the tests fails and is disabled.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [arrow] emkornfield commented on pull request #8319: ARROW-10057: [C++] Add hand-written Parquet nested tests
Posted by GitBox <gi...@apache.org>.
emkornfield commented on pull request #8319:
URL: https://github.com/apache/arrow/pull/8319#issuecomment-702508695
+1 thanks.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [arrow] emkornfield commented on a change in pull request #8319: ARROW-10057: [C++] Add hand-written Parquet nested tests
Posted by GitBox <gi...@apache.org>.
emkornfield commented on a change in pull request #8319:
URL: https://github.com/apache/arrow/pull/8319#discussion_r498617525
##########
File path: cpp/src/parquet/arrow/arrow_reader_writer_test.cc
##########
@@ -2434,6 +2435,145 @@ TEST(TestArrowReadWrite, CanonicalNestedRoundTrip) {
CheckSimpleRoundtrip(expected, 2);
}
+TEST(ArrowReadWrite, ListOfStruct) {
+ using ::arrow::field;
+
+ auto type = ::arrow::list(::arrow::struct_(
+ {field("a", ::arrow::int16(), /*nullable=*/false), field("b", ::arrow::utf8())}));
+
+ const char* json = R"([
+ [{"a": 4, "b": "foo"}, {"a": 5}, {"a": 6, "b": "bar"}],
+ [null, {"a": 7}],
+ null,
+ []])";
+ auto array = ::arrow::ArrayFromJSON(type, json);
+ auto table = ::arrow::Table::Make(::arrow::schema({field("root", type)}), {array});
+ CheckSimpleRoundtrip(table, 2);
+}
+
+TEST(ArrowReadWrite, ListOfStructOfList1) {
+ using ::arrow::field;
+ using ::arrow::list;
+ using ::arrow::struct_;
+
+ auto type = list(struct_({field("a", ::arrow::int16(), /*nullable=*/false),
+ field("b", list(::arrow::int64()))}));
+
+ const char* json = R"([
+ [{"a": 123, "b": [1, 2, null, 3]}, null],
+ null,
+ [],
+ [{"a": 456}, {"a": 789, "b": []}, {"a": 876, "b": [4, 5, 6]}]])";
+ auto array = ::arrow::ArrayFromJSON(type, json);
+ auto table = ::arrow::Table::Make(::arrow::schema({field("root", type)}), {array});
+ CheckSimpleRoundtrip(table, 2);
+}
+
+TEST(ArrowReadWrite, DISABLED_ListOfStructOfList2) {
+ using ::arrow::field;
+ using ::arrow::list;
+ using ::arrow::struct_;
+
+ auto type =
+ list(field("item",
+ struct_({field("a", ::arrow::int16(), /*nullable=*/false),
+ field("b", list(::arrow::int64()), /*nullable=*/false)}),
+ /*nullable=*/false));
+
+ const char* json = R"([
+ [{"a": 123, "b": [1, 2, 3]}],
+ null,
+ [],
+ [{"a": 456}, {"a": 789, "b": [null]}, {"a": 876, "b": [4, 5, 6]}]])";
Review comment:
I think the problem with this test, was we mark B as not null in the schema, but the samebelow on the last list implicitly sets b to null for 456. When I add "a": 456, b: []. The test passes.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [arrow] emkornfield commented on pull request #8319: ARROW-10057: [C++] Add hand-written Parquet nested tests
Posted by GitBox <gi...@apache.org>.
emkornfield commented on pull request #8319:
URL: https://github.com/apache/arrow/pull/8319#issuecomment-702275839
LGTM, I'll look into the failing test case.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [arrow] pitrou commented on a change in pull request #8319: ARROW-10057: [C++] Add hand-written Parquet nested tests
Posted by GitBox <gi...@apache.org>.
pitrou commented on a change in pull request #8319:
URL: https://github.com/apache/arrow/pull/8319#discussion_r498727490
##########
File path: cpp/src/parquet/arrow/arrow_reader_writer_test.cc
##########
@@ -2434,6 +2435,145 @@ TEST(TestArrowReadWrite, CanonicalNestedRoundTrip) {
CheckSimpleRoundtrip(expected, 2);
}
+TEST(ArrowReadWrite, ListOfStruct) {
+ using ::arrow::field;
+
+ auto type = ::arrow::list(::arrow::struct_(
+ {field("a", ::arrow::int16(), /*nullable=*/false), field("b", ::arrow::utf8())}));
+
+ const char* json = R"([
+ [{"a": 4, "b": "foo"}, {"a": 5}, {"a": 6, "b": "bar"}],
+ [null, {"a": 7}],
+ null,
+ []])";
+ auto array = ::arrow::ArrayFromJSON(type, json);
+ auto table = ::arrow::Table::Make(::arrow::schema({field("root", type)}), {array});
+ CheckSimpleRoundtrip(table, 2);
+}
+
+TEST(ArrowReadWrite, ListOfStructOfList1) {
+ using ::arrow::field;
+ using ::arrow::list;
+ using ::arrow::struct_;
+
+ auto type = list(struct_({field("a", ::arrow::int16(), /*nullable=*/false),
+ field("b", list(::arrow::int64()))}));
+
+ const char* json = R"([
+ [{"a": 123, "b": [1, 2, null, 3]}, null],
+ null,
+ [],
+ [{"a": 456}, {"a": 789, "b": []}, {"a": 876, "b": [4, 5, 6]}]])";
+ auto array = ::arrow::ArrayFromJSON(type, json);
+ auto table = ::arrow::Table::Make(::arrow::schema({field("root", type)}), {array});
+ CheckSimpleRoundtrip(table, 2);
+}
+
+TEST(ArrowReadWrite, DISABLED_ListOfStructOfList2) {
+ using ::arrow::field;
+ using ::arrow::list;
+ using ::arrow::struct_;
+
+ auto type =
+ list(field("item",
+ struct_({field("a", ::arrow::int16(), /*nullable=*/false),
+ field("b", list(::arrow::int64()), /*nullable=*/false)}),
+ /*nullable=*/false));
+
+ const char* json = R"([
+ [{"a": 123, "b": [1, 2, 3]}],
+ null,
+ [],
+ [{"a": 456}, {"a": 789, "b": [null]}, {"a": 876, "b": [4, 5, 6]}]])";
Review comment:
Ah, you may be right indeed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [arrow] emkornfield closed pull request #8319: ARROW-10057: [C++] Add hand-written Parquet nested tests
Posted by GitBox <gi...@apache.org>.
emkornfield closed pull request #8319:
URL: https://github.com/apache/arrow/pull/8319
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [arrow] github-actions[bot] commented on pull request #8319: ARROW-10057: [C++] Add hand-written Parquet nested tests
Posted by GitBox <gi...@apache.org>.
github-actions[bot] commented on pull request #8319:
URL: https://github.com/apache/arrow/pull/8319#issuecomment-702283022
https://issues.apache.org/jira/browse/ARROW-10057
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org