yordan-pavlov commented on a change in pull request #1389:
URL: https://github.com/apache/arrow-rs/pull/1389#discussion_r819865424
##########
File path: parquet/src/file/serialized_reader.rs
##########
@@ -127,6 +127,56 @@ pub struct SerializedFileReader<R: ChunkReader> {
metadata: ParquetMetaData,
}
+/// A builder for [`ReadOptions`].
+/// For the predicates that are added to the builder,
+/// they will be chained using 'AND' to filter the row groups.
+pub struct ReadOptionsBuilder {
+ predicate: Vec<Box<dyn FnMut(&RowGroupMetaData, usize) -> bool>>,
+}
+
+impl ReadOptionsBuilder {
+ /// New builder
+ pub fn new() -> Self {
+ ReadOptionsBuilder { predicate: vec![] }
+ }
+
+ /// Add a predicate on row group metadata to the reading option,
+ /// Filter only row groups that match the predicate criteria
+ pub fn with_predicate(
+ mut self,
+ predicate: Box<dyn FnMut(&RowGroupMetaData, usize) -> bool>,
+ ) -> Self {
+ self.predicate.push(predicate);
+ self
+ }
+
+ /// Add a range predicate on filtering row groups if their midpoints are
within the range
+ pub fn with_range(mut self, start: i64, end: i64) -> Self {
+ assert!(start < end);
+ let predicate = move |rg: &RowGroupMetaData, _: usize| {
+ let mid = get_midpoint_offset(rg);
+ mid >= start && mid < end
+ };
+ self.predicate.push(Box::new(predicate));
+ self
+ }
+
+ /// Seal the builder and return the read options
+ pub fn build(self) -> ReadOptions {
+ ReadOptions {
+ predicate: self.predicate,
+ }
+ }
+}
+
+/// A collection of options for reading a Parquet file.
+///
+/// Currently, only predicates on row group metadata are supported.
+/// All predicates will be chained using 'AND' to filter the row groups.
+pub struct ReadOptions {
+ predicate: Vec<Box<dyn FnMut(&RowGroupMetaData, usize) -> bool>>,
Review comment:
same here - this should be plural - `predicates` since it contains a
list of many predicate functions?
--
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]
