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 2020/05/01 14:02:53 UTC
[GitHub] [arrow] fsaintjacques commented on a change in pull request #7073: ARROW-8318: [C++][Dataset] Construct FileSystemDataset from fragments
fsaintjacques commented on a change in pull request #7073:
URL: https://github.com/apache/arrow/pull/7073#discussion_r418554202
##########
File path: cpp/src/arrow/dataset/file_base.cc
##########
@@ -83,131 +83,67 @@ Result<ScanTaskIterator> FileFragment::Scan(std::shared_ptr<ScanOptions> options
FileSystemDataset::FileSystemDataset(std::shared_ptr<Schema> schema,
std::shared_ptr<Expression> root_partition,
- std::shared_ptr<FileFormat> format,
- std::shared_ptr<fs::FileSystem> filesystem,
- fs::PathForest forest,
- ExpressionVector file_partitions)
+ std::vector<std::shared_ptr<FileFragment>> fragments)
: Dataset(std::move(schema), std::move(root_partition)),
- format_(std::move(format)),
- filesystem_(std::move(filesystem)),
- forest_(std::move(forest)),
- partitions_(std::move(file_partitions)) {
- DCHECK_EQ(static_cast<size_t>(forest_.size()), partitions_.size());
-}
-
-Result<std::shared_ptr<FileSystemDataset>> FileSystemDataset::Make(
- std::shared_ptr<Schema> schema, std::shared_ptr<Expression> root_partition,
- std::shared_ptr<FileFormat> format, std::shared_ptr<fs::FileSystem> filesystem,
- std::vector<fs::FileInfo> infos) {
- ExpressionVector partitions(infos.size(), scalar(true));
- return Make(std::move(schema), std::move(root_partition), std::move(format),
- std::move(filesystem), std::move(infos), std::move(partitions));
-}
+ fragments_(std::move(fragments)) {}
Result<std::shared_ptr<FileSystemDataset>> FileSystemDataset::Make(
std::shared_ptr<Schema> schema, std::shared_ptr<Expression> root_partition,
- std::shared_ptr<FileFormat> format, std::shared_ptr<fs::FileSystem> filesystem,
- std::vector<fs::FileInfo> infos, ExpressionVector partitions) {
- ARROW_ASSIGN_OR_RAISE(auto forest, fs::PathForest::Make(std::move(infos), &partitions));
- return Make(std::move(schema), std::move(root_partition), std::move(format),
- std::move(filesystem), std::move(forest), std::move(partitions));
-}
+ FragmentVector fragments) {
+ std::vector<std::shared_ptr<FileFragment>> file_fragments;
+ for (const auto& fragment : fragments) {
+ auto file_fragment = internal::checked_pointer_cast<FileFragment>(fragment);
Review comment:
derp, I actually forgot to check.
----------------------------------------------------------------
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