devinjdangelo commented on code in PR #7283:
URL: https://github.com/apache/arrow-datafusion/pull/7283#discussion_r1295116687
##########
datafusion/core/tests/sqllogictests/test_files/copy.slt:
##########
@@ -16,29 +16,141 @@
# under the License.
# tests for copy command
-
statement ok
create table source_table(col1 integer, col2 varchar) as values (1, 'Foo'),
(2, 'Bar');
-# Copy from table
-statement error DataFusion error: This feature is not implemented: `COPY \.\.
TO \.\.` statement is not yet supported
-COPY source_table to '/tmp/table.parquet';
+# Copy to directory as multiple files
+query IT
+COPY source_table TO 'tests/sqllogictests/test_files/scratch/table' (format
parquet, per_thread_output true);
+----
+2
+
+#Explain copy queries not currently working
+query error DataFusion error: This feature is not implemented: Unsupported SQL
statement: Some\("COPY source_table TO
'tests/sqllogictests/test_files/scratch/table'"\)
+EXPLAIN COPY source_table to 'tests/sqllogictests/test_files/scratch/table'
+
+query error DataFusion error: SQL error: ParserError\("Expected end of
statement, found: source_table"\)
+EXPLAIN COPY source_table to 'tests/sqllogictests/test_files/scratch/table'
(format parquet, per_thread_output true)
+
+# Copy more files to directory via query
+query IT
+COPY (select * from source_table UNION ALL select * from source_table) to
'tests/sqllogictests/test_files/scratch/table' (format parquet,
per_thread_output true);
+----
+4
+
+# validate multiple parquet file output
+statement ok
+CREATE EXTERNAL TABLE validate_parquet STORED AS PARQUET LOCATION
'tests/sqllogictests/test_files/scratch/table/';
+
+query IT
+select * from validate_parquet;
+----
+1 Foo
+2 Bar
+1 Foo
+2 Bar
+1 Foo
+2 Bar
+
+# Copy from table to single file
+query IT
+COPY source_table to 'tests/sqllogictests/test_files/scratch/table.parquet';
+----
+2
+
+# validate single parquet file output
+statement ok
+CREATE EXTERNAL TABLE validate_parquet_single STORED AS PARQUET LOCATION
'tests/sqllogictests/test_files/scratch/table.parquet';
+
+query IT
+select * from validate_parquet_single;
+----
+1 Foo
+2 Bar
+
+# copy from table to folder of csv files
+query IT
+COPY source_table to 'tests/sqllogictests/test_files/scratch/table_csv'
(format csv, per_thread_output true);
+----
+2
+
+# validate folder of csv files
+statement ok
+CREATE EXTERNAL TABLE validate_csv STORED AS csv WITH HEADER ROW LOCATION
'tests/sqllogictests/test_files/scratch/table_csv';
+
+query IT
+select * from validate_csv;
+----
+1 Foo
+2 Bar
+
+# Copy from table to single csv
+query IT
+COPY source_table to 'tests/sqllogictests/test_files/scratch/table.csv';
+----
+2
+
+# Validate single csv output
+statement ok
+CREATE EXTERNAL TABLE validate_single_csv STORED AS csv WITH HEADER ROW
LOCATION 'tests/sqllogictests/test_files/scratch/table.csv';
+
+query IT
+select * from validate_single_csv;
+----
+1 Foo
+2 Bar
+
+# Copy from table to folder of json
+query IT
+COPY source_table to 'tests/sqllogictests/test_files/scratch/table_json'
(format json, per_thread_output true);
+----
+2
+
+# Validate json output
+statement ok
+CREATE EXTERNAL TABLE validate_json STORED AS json LOCATION
'tests/sqllogictests/test_files/scratch/table_json';
+
+query IT
+select * from validate_json;
+----
+1 Foo
+2 Bar
+
+# Copy from table to single json file
+query IT
+COPY source_table to 'tests/sqllogictests/test_files/scratch/table.json';
+----
+2
+
+# Validate single JSON file`
+statement ok
+CREATE EXTERNAL TABLE validate_single_json STORED AS json LOCATION
'tests/sqllogictests/test_files/scratch/table_json';
+
+query IT
+select * from validate_single_json;
+----
+1 Foo
+2 Bar
# Copy from table with options
-statement error DataFusion error: This feature is not implemented: `COPY \.\.
TO \.\.` statement is not yet supported
-COPY source_table to '/tmp/table.parquet' (row_group_size 55);
+query IT
+COPY source_table to 'tests/sqllogictests/test_files/scratch/table.json'
(row_group_size 55);
Review Comment:
Ah, setting that as JSON with row_group_size is a mistake. It doesn't cause
any issue because options are ignored right now.
This raises an interesting question about the desired behavior in this
scenario. If the options specify an irrelevant setting (row_group_size for a
json setting), should DataFusion:
1. Ignore the irrelevant setting (current behavior)
2. Ignore the irrelevant setting but emit a warning
3. Raise an error and refuse to execute the query entirely
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
