fsaintjacques commented on a change in pull request #7000:
URL: https://github.com/apache/arrow/pull/7000#discussion_r413046083
##########
File path: cpp/src/arrow/dataset/dataset.h
##########
@@ -100,16 +97,20 @@ class ARROW_DS_EXPORT InMemoryFragment : public Fragment {
RecordBatchVector record_batches_;
};
-/// \brief A container of zero or more Fragments. A Dataset acts as a
discovery mechanism
-/// of Fragments and partitions, e.g. files deeply nested in a directory.
+/// \brief A container of zero or more Fragments.
+///
+/// A Dataset acts as a union of Fragments, e.g. files deeply nested in a
+/// directory. A Dataset has a schema, also known as the "reader" schema.
+///
class ARROW_DS_EXPORT Dataset : public std::enable_shared_from_this<Dataset> {
public:
/// \brief Begin to build a new Scan operation against this Dataset
Result<std::shared_ptr<ScannerBuilder>> NewScan(std::shared_ptr<ScanContext>
context);
Result<std::shared_ptr<ScannerBuilder>> NewScan();
- /// \brief GetFragments returns an iterator of Fragments given ScanOptions.
- FragmentIterator GetFragments(std::shared_ptr<ScanOptions> options);
+ /// \brief GetFragments returns an iterator of Fragments given a predicate.
+ FragmentIterator GetFragments(std::shared_ptr<Expression> predicate);
+ FragmentIterator GetFragments();
Review comment:
Ditto.
----------------------------------------------------------------
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:
us...@infra.apache.org
