This is an automated email from the ASF dual-hosted git repository.
garydgregory pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/commons-text.git
The following commit(s) were added to refs/heads/master by this push:
new 80fa2efe Internal WordsUtils refactoring from PR #758.
80fa2efe is described below
commit 80fa2efe6dbf74840ca2cc677b152928d10bc152
Author: Gary Gregory <[email protected]>
AuthorDate: Thu Jul 9 06:37:47 2026 -0400
Internal WordsUtils refactoring from PR #758.
---
.../java/org/apache/commons/text/WordUtils.java | 98 ++++++++++------------
1 file changed, 44 insertions(+), 54 deletions(-)
diff --git a/src/main/java/org/apache/commons/text/WordUtils.java
b/src/main/java/org/apache/commons/text/WordUtils.java
index aeff4149..0beaf534 100644
--- a/src/main/java/org/apache/commons/text/WordUtils.java
+++ b/src/main/java/org/apache/commons/text/WordUtils.java
@@ -19,6 +19,7 @@ package org.apache.commons.text;
import java.util.HashSet;
import java.util.Locale;
import java.util.Set;
+import java.util.function.IntUnaryOperator;
import java.util.function.Predicate;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
@@ -114,6 +115,47 @@ public class WordUtils {
return result.toString();
}
+ /**
+ * Applies a function to the first character of each word in a String.
+ * <p>
+ * This is used by {@link #capitalize(String, char...)} and {@link
#uncapitalize(String, char...)}. The {@code transform} function is applied to
the first
+ * code point of each word; all other code points are passed through
unchanged.
+ * </p>
+ *
+ * @param str The String to transform, may be null.
+ * @param delimiters The set of characters to determine word boundaries,
null means whitespace.
+ * @param transform The casing function to apply to the first code point
of each word (e.g., {@code Character::toTitleCase} or
+ * {@code Character::toLowerCase}).
+ * @return The transformed String, or {@code null}/{@code ""} if the input
is null/empty.
+ */
+ private static String applyWordCaseTransform(final String str, final
char[] delimiters, final IntUnaryOperator transform) {
+ if (StringUtils.isEmpty(str)) {
+ return str;
+ }
+ final Predicate<Integer> isDelimiter =
generateIsDelimiterFunction(delimiters);
+ final int strLen = str.length();
+ final int[] newCodePoints = new int[strLen];
+ int outOffset = 0;
+ boolean transformNext = true;
+ for (int index = 0; index < strLen;) {
+ final int codePoint = str.codePointAt(index);
+ if (isDelimiter.test(codePoint)) {
+ transformNext = true;
+ newCodePoints[outOffset++] = codePoint;
+ index += Character.charCount(codePoint);
+ } else if (transformNext) {
+ final int transformed = transform.applyAsInt(codePoint);
+ newCodePoints[outOffset++] = transformed;
+ index += Character.charCount(transformed);
+ transformNext = false;
+ } else {
+ newCodePoints[outOffset++] = codePoint;
+ index += Character.charCount(codePoint);
+ }
+ }
+ return new String(newCodePoints, 0, outOffset);
+ }
+
/**
* Capitalizes all the whitespace separated words in a String.
* Only the first character of each word is changed. To convert the
@@ -170,33 +212,7 @@ public class WordUtils {
* @see #capitalizeFully(String)
*/
public static String capitalize(final String str, final char...
delimiters) {
- if (StringUtils.isEmpty(str)) {
- return str;
- }
- final Predicate<Integer> isDelimiter =
generateIsDelimiterFunction(delimiters);
- final int strLen = str.length();
- final int[] newCodePoints = new int[strLen];
- int outOffset = 0;
-
- boolean capitalizeNext = true;
- for (int index = 0; index < strLen;) {
- final int codePoint = str.codePointAt(index);
-
- if (isDelimiter.test(codePoint)) {
- capitalizeNext = true;
- newCodePoints[outOffset++] = codePoint;
- index += Character.charCount(codePoint);
- } else if (capitalizeNext) {
- final int titleCaseCodePoint =
Character.toTitleCase(codePoint);
- newCodePoints[outOffset++] = titleCaseCodePoint;
- index += Character.charCount(titleCaseCodePoint);
- capitalizeNext = false;
- } else {
- newCodePoints[outOffset++] = codePoint;
- index += Character.charCount(codePoint);
- }
- }
- return new String(newCodePoints, 0, outOffset);
+ return applyWordCaseTransform(str, delimiters, Character::toTitleCase);
}
/**
@@ -530,33 +546,7 @@ public class WordUtils {
* @see #capitalize(String)
*/
public static String uncapitalize(final String str, final char...
delimiters) {
- if (StringUtils.isEmpty(str)) {
- return str;
- }
- final Predicate<Integer> isDelimiter =
generateIsDelimiterFunction(delimiters);
- final int strLen = str.length();
- final int[] newCodePoints = new int[strLen];
- int outOffset = 0;
-
- boolean uncapitalizeNext = true;
- for (int index = 0; index < strLen;) {
- final int codePoint = str.codePointAt(index);
-
- if (isDelimiter.test(codePoint)) {
- uncapitalizeNext = true;
- newCodePoints[outOffset++] = codePoint;
- index += Character.charCount(codePoint);
- } else if (uncapitalizeNext) {
- final int titleCaseCodePoint =
Character.toLowerCase(codePoint);
- newCodePoints[outOffset++] = titleCaseCodePoint;
- index += Character.charCount(titleCaseCodePoint);
- uncapitalizeNext = false;
- } else {
- newCodePoints[outOffset++] = codePoint;
- index += Character.charCount(codePoint);
- }
- }
- return new String(newCodePoints, 0, outOffset);
+ return applyWordCaseTransform(str, delimiters, Character::toLowerCase);
}
/**
