[arrow-rs] branch master updated: Fix ilike_utf8_scalar kernals (#2545)

[tustvold]

This is an automated email from the ASF dual-hosted git repository.

tustvold pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git


The following commit(s) were added to refs/heads/master by this push:
     new b2f0c65e1 Fix ilike_utf8_scalar kernals (#2545)
b2f0c65e1 is described below

commit b2f0c65e15a40c7f2f01e1d96335ea8ec362f65d
Author: Vrishabh <psvrish...@gmail.com>
AuthorDate: Tue Aug 23 16:10:22 2022 +0530

    Fix ilike_utf8_scalar kernals (#2545)
    
    * fix ilike kernals
    
    * minor refactor for perf improvements
    
    * Remove wrongly added file
---
 arrow/src/compute/kernels/comparison.rs | 50 +++++++++++++--------------------
 1 file changed, 19 insertions(+), 31 deletions(-)

diff --git a/arrow/src/compute/kernels/comparison.rs 
b/arrow/src/compute/kernels/comparison.rs
index 39828b64f..714b4b1b7 100644
--- a/arrow/src/compute/kernels/comparison.rs
+++ b/arrow/src/compute/kernels/comparison.rs
@@ -467,29 +467,24 @@ pub fn ilike_utf8_scalar<OffsetSize: OffsetSizeTrait>(
 
     if !right.contains(is_like_pattern) {
         // fast path, can use equals
+        let right_uppercase = right.to_uppercase();
         for i in 0..left.len() {
-            result.append(left.value(i) == right);
+            result.append(left.value(i).to_uppercase() == right_uppercase);
         }
     } else if right.ends_with('%')
         && !right.ends_with("\\%")
         && !right[..right.len() - 1].contains(is_like_pattern)
     {
-        // fast path, can use ends_with
+        // fast path, can use starts_with
+        let start_str = &right[..right.len() - 1].to_uppercase();
         for i in 0..left.len() {
-            result.append(
-                left.value(i)
-                    .to_uppercase()
-                    .starts_with(&right[..right.len() - 1].to_uppercase()),
-            );
+            result.append(left.value(i).to_uppercase().starts_with(start_str));
         }
     } else if right.starts_with('%') && !right[1..].contains(is_like_pattern) {
-        // fast path, can use starts_with
+        // fast path, can use ends_with
+        let ends_str = &right[1..].to_uppercase();
         for i in 0..left.len() {
-            result.append(
-                left.value(i)
-                    .to_uppercase()
-                    .ends_with(&right[1..].to_uppercase()),
-            );
+            result.append(left.value(i).to_uppercase().ends_with(ends_str));
         }
     } else {
         let re_pattern = replace_like_wildcards(right)?;
@@ -550,31 +545,24 @@ pub fn nilike_utf8_scalar<OffsetSize: OffsetSizeTrait>(
 
     if !right.contains(is_like_pattern) {
         // fast path, can use equals
+        let right_uppercase = right.to_uppercase();
         for i in 0..left.len() {
-            result.append(left.value(i) != right);
+            result.append(left.value(i).to_uppercase() != right_uppercase);
         }
     } else if right.ends_with('%')
         && !right.ends_with("\\%")
         && !right[..right.len() - 1].contains(is_like_pattern)
     {
-        // fast path, can use ends_with
+        // fast path, can use starts_with
+        let start_str = &right[..right.len() - 1].to_uppercase();
         for i in 0..left.len() {
-            result.append(
-                !left
-                    .value(i)
-                    .to_uppercase()
-                    .starts_with(&right[..right.len() - 1].to_uppercase()),
-            );
+            
result.append(!left.value(i).to_uppercase().starts_with(start_str));
         }
     } else if right.starts_with('%') && !right[1..].contains(is_like_pattern) {
-        // fast path, can use starts_with
+        // fast path, can use ends_with
+        let end_str = &right[1..].to_uppercase();
         for i in 0..left.len() {
-            result.append(
-                !left
-                    .value(i)
-                    .to_uppercase()
-                    .ends_with(&right[1..].to_uppercase()),
-            );
+            result.append(!left.value(i).to_uppercase().ends_with(end_str));
         }
     } else {
         let re_pattern = replace_like_wildcards(right)?;
@@ -4181,7 +4169,7 @@ mod tests {
     test_utf8_scalar!(
         test_utf8_array_ilike_scalar_equals,
         vec!["arrow", "parrow", "arrows", "arr"],
-        "arrow",
+        "Arrow",
         ilike_utf8_scalar,
         vec![true, false, false, false]
     );
@@ -4234,8 +4222,8 @@ mod tests {
 
     test_utf8_scalar!(
         test_utf8_array_nilike_scalar_equals,
-        vec!["arrow", "parrow", "arrows", "arr"],
-        "arrow",
+        vec!["arRow", "parrow", "arrows", "arr"],
+        "Arrow",
         nilike_utf8_scalar,
         vec![false, true, true, true]
     );