[ENH] Comparison (LT, GT, LTE, GTE) and prefix operations on arrow bl…

…ockfile (#2223)

## Description of changes

*Summarize the changes made by this PR.*
 - New functionality
	 - Adds gets for LT, GT, LTE, GTE and get by prefix for arrow blockfile

## Test plan
Unit-tests in arrow blockfile
- [x] Tests pass locally with `pytest` for python, `yarn test` for js,
`cargo test` for rust

## Documentation Changes
None

rust/worker/proptest-regressions/blockstore/arrow/blockfile.txt

@@ -0,0 +1,8 @@
+# Seeds for failure cases proptest has generated in the past. It is
+# automatically read and these particular cases re-run before any
+# novel cases are generated.
+#
+# It is recommended to check this file in to source control so that
+# everyone who runs the test benefits from these saved cases.
+cc 2080f026e9401a99d3066b4469ec3c40d5756edc7cf222cac08820ff3fb99264 # shrinks to num_key = 3, query_key = 1000
+cc edb389ffc15848ee1e63e29713eca3d5c2fc462f7c2dbf200d44b48c53dee47a # shrinks to num_key = 4030, query_key = 4030

rust/worker/src/blockstore/arrow/block/types.rs

@@ -92,6 +92,118 @@ impl Block {
  None
  }
 
+ pub fn get_prefix<'me, K: ArrowReadableKey<'me>, V: ArrowReadableValue<'me>>(
+ &'me self,
+ prefix: &str,
+ ) -> Option<Vec<(&str, K, V)>> {
+ let prefix_array = self
+ .data
+ .column(0)
+ .as_any()
+ .downcast_ref::<StringArray>()
+ .unwrap();
+ let mut res: Vec<(&str, K, V)> = vec![];
+ for i in 0..self.data.num_rows() {
+ let curr_prefix = prefix_array.value(i);
+ if curr_prefix == prefix {
+ res.push((
+ curr_prefix,
+ K::get(self.data.column(1), i),
+ V::get(self.data.column(2), i),
+ ));
+ }
+ }
+ return Some(res);
+ }
+
+ pub fn get_gt<'me, K: ArrowReadableKey<'me>, V: ArrowReadableValue<'me>>(
+ &'me self,
+ prefix: &str,
+ key: K,
+ ) -> Option<Vec<(&str, K, V)>> {
+ let prefix_array = self
+ .data
+ .column(0)
+ .as_any()
+ .downcast_ref::<StringArray>()
+ .unwrap();
+ let mut res: Vec<(&str, K, V)> = vec![];
+ for i in 0..self.data.num_rows() {
+ let curr_prefix = prefix_array.value(i);
+ let curr_key = K::get(self.data.column(1), i);
+ if curr_prefix == prefix && curr_key > key {
+ res.push((curr_prefix, curr_key, V::get(self.data.column(2), i)));
+ }
+ }
+ return Some(res);
+ }
+
+ pub fn get_lt<'me, K: ArrowReadableKey<'me>, V: ArrowReadableValue<'me>>(
+ &'me self,
+ prefix: &str,
+ key: K,
+ ) -> Option<Vec<(&str, K, V)>> {
+ let prefix_array = self
+ .data
+ .column(0)
+ .as_any()
+ .downcast_ref::<StringArray>()
+ .unwrap();
+ let mut res: Vec<(&str, K, V)> = vec![];
+ for i in 0..self.data.num_rows() {
+ let curr_prefix = prefix_array.value(i);
+ let curr_key = K::get(self.data.column(1), i);
+ if curr_prefix == prefix && curr_key < key {
+ res.push((curr_prefix, curr_key, V::get(self.data.column(2), i)));
+ }
+ }
+ return Some(res);
+ }
+
+ pub fn get_lte<'me, K: ArrowReadableKey<'me>, V: ArrowReadableValue<'me>>(
+ &'me self,
+ prefix: &str,
+ key: K,
+ ) -> Option<Vec<(&str, K, V)>> {
+ let prefix_array = self
+ .data
+ .column(0)
+ .as_any()
+ .downcast_ref::<StringArray>()
+ .unwrap();
+ let mut res: Vec<(&str, K, V)> = vec![];
+ for i in 0..self.data.num_rows() {
+ let curr_prefix = prefix_array.value(i);
+ let curr_key = K::get(self.data.column(1), i);
+ if curr_prefix == prefix && curr_key <= key {
+ res.push((curr_prefix, curr_key, V::get(self.data.column(2), i)));
+ }
+ }
+ return Some(res);
+ }
+
+ pub fn get_gte<'me, K: ArrowReadableKey<'me>, V: ArrowReadableValue<'me>>(
+ &'me self,
+ prefix: &str,
+ key: K,
+ ) -> Option<Vec<(&str, K, V)>> {
+ let prefix_array = self
+ .data
+ .column(0)
+ .as_any()
+ .downcast_ref::<StringArray>()
+ .unwrap();
+ let mut res: Vec<(&str, K, V)> = vec![];
+ for i in 0..self.data.num_rows() {
+ let curr_prefix = prefix_array.value(i);
+ let curr_key = K::get(self.data.column(1), i);
+ if curr_prefix == prefix && curr_key >= key {
+ res.push((curr_prefix, curr_key, V::get(self.data.column(2), i)));
+ }
+ }
+ return Some(res);
+ }
+
  pub fn get_at_index<'me, K: ArrowReadableKey<'me>, V: ArrowReadableValue<'me>>(
  &'me self,
  index: usize,