[commons-text] 01/03: TEXT-156: Fix the RegexTokenizer to use a static Pattern.

[aherbert]

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

aherbert pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/commons-text.git

commit f40607a1689b96831212e73a3588187778e6dc2a
Author: Alex Herbert <aherb...@apache.org>
AuthorDate: Thu Mar 7 23:13:49 2019 +0000

    TEXT-156: Fix the RegexTokenizer to use a static Pattern.
    
    Remove the use of CharSequence.toString() to pass to the
    matcher(CharSequence) method.
    
    Fix the javadoc header @code tag.
---
 .../java/org/apache/commons/text/similarity/RegexTokenizer.java    | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git 
a/src/main/java/org/apache/commons/text/similarity/RegexTokenizer.java 
b/src/main/java/org/apache/commons/text/similarity/RegexTokenizer.java
index cc009ef..f650c0c 100644
--- a/src/main/java/org/apache/commons/text/similarity/RegexTokenizer.java
+++ b/src/main/java/org/apache/commons/text/similarity/RegexTokenizer.java
@@ -26,12 +26,14 @@ import org.apache.commons.lang3.Validate;
 
 /**
  * A simple word tokenizer that utilizes regex to find words. It applies a 
regex
- * {@code}(\w)+{@code} over the input text to extract words from a given 
character
+ * {@code (\w)+} over the input text to extract words from a given character
  * sequence.
  *
  * @since 1.0
  */
 class RegexTokenizer implements Tokenizer<CharSequence> {
+    /** The whitespace pattern. */
+    private static final Pattern PATTERN = Pattern.compile("(\\w)+");
 
     /**
      * {@inheritDoc}
@@ -41,8 +43,7 @@ class RegexTokenizer implements Tokenizer<CharSequence> {
     @Override
     public CharSequence[] tokenize(final CharSequence text) {
         Validate.isTrue(StringUtils.isNotBlank(text), "Invalid text");
-        final Pattern pattern = Pattern.compile("(\\w)+");
-        final Matcher matcher = pattern.matcher(text.toString());
+        final Matcher matcher = PATTERN.matcher(text);
         final List<String> tokens = new ArrayList<>();
         while (matcher.find()) {
             tokens.add(matcher.group(0));