[SPARK-9213] Improve regular expression performance (via joni)

• Type: Umbrella
• Status: Resolved
• Priority: Major
• Resolution: Incomplete
• Component/s: SQL
• Labels: bulk-closed
• Epic Link: Tungsten Phase 2
• Assignee: Unassigned
• Reporter: Reynold Xin
• Created: 21/Jul/15 06:48
• Updated: 09/Oct/22 06:52
• Resolved: 21/May/19 04:10

Description

I'm creating an umbrella ticket to improve regular expression performance for string expressions. Right now our use of regular expressions is inefficient for two reasons:

1. Java regex in general is slow.
2. We have to convert everything from UTF8 encoded bytes into Java String, and then run regex on it, and then convert it back.

There are libraries in Java that provide regex support directly on UTF8 encoded bytes. One prominent example is joni, used in JRuby.

Note: all regex functions are in https://github.com/apache/spark/blob/master/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala

Issue Links

• is related to: SPARK-8829 Improve expression performance
• links to: [Github] Pull Request #8715 (watermen)
• links to: [Github] Pull Request #38171 (lyy-pineapple)