(celeborn) branch main updated: [CELEBORN-1448] Use static regex Pattern instances in JavaUtils.timeStringAs and JavaUtils.byteStringAs

[fchen]

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

fchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/celeborn.git


The following commit(s) were added to refs/heads/main by this push:
     new dc2826a61 [CELEBORN-1448] Use static regex Pattern instances in 
JavaUtils.timeStringAs and JavaUtils.byteStringAs
dc2826a61 is described below

commit dc2826a6149bed15310a73107b2565e7bc1d095e
Author: sychen <syc...@ctrip.com>
AuthorDate: Mon Jun 3 23:42:27 2024 +0800

    [CELEBORN-1448] Use static regex Pattern instances in 
JavaUtils.timeStringAs and JavaUtils.byteStringAs
    
    ### What changes were proposed in this pull request?
    
    ### Why are the changes needed?
    
    [SPARK-48496](https://issues.apache.org/jira/browse/SPARK-48496)[CORE] Use 
static regex Pattern instances in JavaUtils.timeStringAs and 
JavaUtils.byteStringAs
    
    ### Does this PR introduce _any_ user-facing change?
    No
    
    ### How was this patch tested?
    GA
    
    Closes #2541 from cxzl25/CELEBORN-1448.
    
    Authored-by: sychen <syc...@ctrip.com>
    Signed-off-by: Fu Chen <cfmcgr...@gmail.com>
---
 .../main/java/org/apache/celeborn/common/util/JavaUtils.java | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git 
a/common/src/main/java/org/apache/celeborn/common/util/JavaUtils.java 
b/common/src/main/java/org/apache/celeborn/common/util/JavaUtils.java
index 32c53bcee..d4ce0bf2e 100644
--- a/common/src/main/java/org/apache/celeborn/common/util/JavaUtils.java
+++ b/common/src/main/java/org/apache/celeborn/common/util/JavaUtils.java
@@ -242,6 +242,8 @@ public class JavaUtils {
           .put("pi", ByteUnit.PiB)
           .build();
 
+  private static final Pattern TIME_STRING_PATTERN = 
Pattern.compile("(-?[0-9]+)([a-z]+)?");
+
   /**
    * Convert a passed time string (e.g. 50s, 100ms, or 250us) to a time count 
in the given unit. The
    * unit is also considered the default if the given string does not specify 
a unit.
@@ -250,7 +252,7 @@ public class JavaUtils {
     String lower = str.toLowerCase(Locale.ROOT).trim();
 
     try {
-      Matcher m = Pattern.compile("(-?[0-9]+)([a-z]+)?").matcher(lower);
+      Matcher m = TIME_STRING_PATTERN.matcher(lower);
       if (!m.matches()) {
         throw new NumberFormatException("Failed to parse time string: " + str);
       }
@@ -291,6 +293,10 @@ public class JavaUtils {
     return timeStringAs(str, TimeUnit.SECONDS);
   }
 
+  private static final Pattern BYTE_STRING_PATTERN = 
Pattern.compile("([0-9]+)([a-z]+)?");
+  private static final Pattern BYTE_STRING_FRACTION_PATTERN =
+      Pattern.compile("([0-9]+\\.[0-9]+)([a-z]+)?");
+
   /**
    * Convert a passed byte string (e.g. 50b, 100kb, or 250mb) to the given. If 
no suffix is
    * provided, a direct conversion to the provided unit is attempted.
@@ -299,8 +305,8 @@ public class JavaUtils {
     String lower = str.toLowerCase(Locale.ROOT).trim();
 
     try {
-      Matcher m = Pattern.compile("([0-9]+)([a-z]+)?").matcher(lower);
-      Matcher fractionMatcher = 
Pattern.compile("([0-9]+\\.[0-9]+)([a-z]+)?").matcher(lower);
+      Matcher m = BYTE_STRING_PATTERN.matcher(lower);
+      Matcher fractionMatcher = BYTE_STRING_FRACTION_PATTERN.matcher(lower);
 
       if (m.matches()) {
         long val = Long.parseLong(m.group(1));