lidavidm commented on a change in pull request #12620:
URL: https://github.com/apache/arrow/pull/12620#discussion_r825900232
##########
File path: cpp/examples/arrow/CMakeLists.txt
##########
@@ -123,6 +123,19 @@ if(ARROW_PARQUET AND ARROW_DATASET)
${DATASET_EXAMPLES_LINK_LIBS})
add_dependencies(dataset-parquet-scan-example parquet)
+ if (ARROW_SKYHOOK)
+ if (ARROW_BUILD_SHARED)
+ set(DATASET_EXAMPLES_LINK_LIBS ${DATASET_EXAMPLES_LINK_LIBS}
Review comment:
two nits: since we're reusing the same variable, maybe move this to the
bottom of the enclosing if block so we don't link the other examples against
Skyhook; and use `list(APPEND ...)`?
##########
File path: cpp/examples/arrow/dataset_skyhook_scan_example.cc
##########
@@ -0,0 +1,187 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements. See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership. The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License. You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied. See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+#include <arrow/api.h>
+#include <arrow/compute/exec/expression.h>
+#include <arrow/dataset/dataset.h>
+#include <arrow/dataset/discovery.h>
+#include <arrow/dataset/file_base.h>
+#include <arrow/dataset/scanner.h>
+#include <arrow/filesystem/filesystem.h>
+#include <arrow/filesystem/path_util.h>
+#include <skyhook/client/file_skyhook.h>
+
+#include <cstdlib>
+#include <iostream>
+
+using arrow::field;
+using arrow::int16;
+using arrow::Schema;
+using arrow::Table;
+
+namespace fs = arrow::fs;
+
+namespace ds = arrow::dataset;
+
+namespace cp = arrow::compute;
+
+#define ABORT_ON_FAILURE(expr) \
+ do { \
+ arrow::Status status_ = (expr); \
+ if (!status_.ok()) { \
+ std::cerr << status_.message() << std::endl; \
+ abort(); \
+ } \
+ } while (0);
+
+struct Configuration {
+ // Increase the ds::DataSet by repeating `repeat` times the ds::Dataset.
+ size_t repeat = 1;
+
+ // Indicates if the Scanner::ToTable should consume in parallel.
+ bool use_threads = true;
+
+ // Indicates to the Scan operator which columns are requested. This
+ // optimization avoid deserializing unneeded columns.
+ std::vector<std::string> projected_columns = {"pickup_at", "dropoff_at",
+ "total_amount"};
+
+ // Indicates the filter by which rows will be filtered. This optimization can
+ // make use of partition information and/or file metadata if possible.
+ cp::Expression filter =
+ cp::greater(cp::field_ref("total_amount"), cp::literal(1000.0f));
+
+ ds::InspectOptions inspect_options{};
+ ds::FinishOptions finish_options{};
+} conf;
Review comment:
nit: if this is effectively a static global, follow the naming
convention and name it `kConfiguration` or something like that?
##########
File path: cpp/examples/arrow/dataset_skyhook_scan_example.cc
##########
@@ -0,0 +1,187 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements. See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership. The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License. You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied. See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+#include <arrow/api.h>
+#include <arrow/compute/exec/expression.h>
+#include <arrow/dataset/dataset.h>
+#include <arrow/dataset/discovery.h>
+#include <arrow/dataset/file_base.h>
+#include <arrow/dataset/scanner.h>
+#include <arrow/filesystem/filesystem.h>
+#include <arrow/filesystem/path_util.h>
+#include <skyhook/client/file_skyhook.h>
+
+#include <cstdlib>
+#include <iostream>
+
+using arrow::field;
+using arrow::int16;
+using arrow::Schema;
+using arrow::Table;
+
+namespace fs = arrow::fs;
+
+namespace ds = arrow::dataset;
+
+namespace cp = arrow::compute;
+
+#define ABORT_ON_FAILURE(expr) \
+ do { \
+ arrow::Status status_ = (expr); \
+ if (!status_.ok()) { \
+ std::cerr << status_.message() << std::endl; \
+ abort(); \
+ } \
+ } while (0);
+
+struct Configuration {
+ // Increase the ds::DataSet by repeating `repeat` times the ds::Dataset.
+ size_t repeat = 1;
+
+ // Indicates if the Scanner::ToTable should consume in parallel.
+ bool use_threads = true;
+
+ // Indicates to the Scan operator which columns are requested. This
+ // optimization avoid deserializing unneeded columns.
+ std::vector<std::string> projected_columns = {"pickup_at", "dropoff_at",
+ "total_amount"};
+
+ // Indicates the filter by which rows will be filtered. This optimization can
+ // make use of partition information and/or file metadata if possible.
+ cp::Expression filter =
+ cp::greater(cp::field_ref("total_amount"), cp::literal(1000.0f));
+
+ ds::InspectOptions inspect_options{};
+ ds::FinishOptions finish_options{};
+} conf;
+
+std::shared_ptr<fs::FileSystem> GetFileSystemFromUri(const std::string& uri,
+ std::string* path) {
+ return fs::FileSystemFromUri(uri, path).ValueOrDie();
Review comment:
in general we could stick to using `ARROW_ASSIGN_FROM_RAISE` and only
check the status in `main` (we can have a `Status Main()` or something to wrap
all the Status/Result-using calls)
##########
File path: cpp/examples/arrow/dataset_skyhook_scan_example.cc
##########
@@ -0,0 +1,187 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements. See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership. The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License. You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied. See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+#include <arrow/api.h>
+#include <arrow/compute/exec/expression.h>
+#include <arrow/dataset/dataset.h>
+#include <arrow/dataset/discovery.h>
+#include <arrow/dataset/file_base.h>
+#include <arrow/dataset/scanner.h>
+#include <arrow/filesystem/filesystem.h>
+#include <arrow/filesystem/path_util.h>
+#include <skyhook/client/file_skyhook.h>
+
+#include <cstdlib>
+#include <iostream>
+
+using arrow::field;
+using arrow::int16;
+using arrow::Schema;
+using arrow::Table;
+
+namespace fs = arrow::fs;
+
+namespace ds = arrow::dataset;
+
+namespace cp = arrow::compute;
+
+#define ABORT_ON_FAILURE(expr) \
+ do { \
+ arrow::Status status_ = (expr); \
+ if (!status_.ok()) { \
+ std::cerr << status_.message() << std::endl; \
+ abort(); \
+ } \
+ } while (0);
+
+struct Configuration {
+ // Increase the ds::DataSet by repeating `repeat` times the ds::Dataset.
+ size_t repeat = 1;
+
+ // Indicates if the Scanner::ToTable should consume in parallel.
+ bool use_threads = true;
+
+ // Indicates to the Scan operator which columns are requested. This
+ // optimization avoid deserializing unneeded columns.
+ std::vector<std::string> projected_columns = {"pickup_at", "dropoff_at",
+ "total_amount"};
+
+ // Indicates the filter by which rows will be filtered. This optimization can
+ // make use of partition information and/or file metadata if possible.
+ cp::Expression filter =
+ cp::greater(cp::field_ref("total_amount"), cp::literal(1000.0f));
+
+ ds::InspectOptions inspect_options{};
+ ds::FinishOptions finish_options{};
+} conf;
Review comment:
Ah, I see now this is effectively based on the Parquet scan example,
still, it would be good to clean up some of these things
--
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]
