(commons-codec) branch master updated: CODEC-312: Fix possible StringIndexOutOfBoundException thrown by MatchRatingApproachEncoder.encode() method (#220)

[ggregory]

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

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


The following commit(s) were added to refs/heads/master by this push:
     new 047d2472 CODEC-312: Fix possible StringIndexOutOfBoundException thrown 
by MatchRatingApproachEncoder.encode() method (#220)
047d2472 is described below

commit 047d24724c4aaae158331cfef0de0a9d5df2686e
Author: Arthur Chan <game...@hotmail.com>
AuthorDate: Sat Nov 25 03:05:19 2023 +0000

    CODEC-312: Fix possible StringIndexOutOfBoundException thrown by 
MatchRatingApproachEncoder.encode() method (#220)
    
    * CODEC-312: Fix possible StringIndexOutOfBoundException
    
    Signed-off-by: Arthur Chan <arthur.c...@adalogics.com>
    
    * CODEC-312: Add unit test
    
    Signed-off-by: Arthur Chan <arthur.c...@adalogics.com>
    
    * Remove unmaintained comments
    
    ---------
    
    Signed-off-by: Arthur Chan <arthur.c...@adalogics.com>
    Co-authored-by: Gary Gregory <garydgreg...@users.noreply.github.com>
---
 .../codec/language/MatchRatingApproachEncoder.java | 10 ++++++++
 .../language/MatchRatingApproachEncoderTest.java   | 28 +++++++++++-----------
 2 files changed, 24 insertions(+), 14 deletions(-)

diff --git 
a/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java
 
b/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java
index 86f08437..d871cc48 100644
--- 
a/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java
+++ 
b/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java
@@ -126,10 +126,20 @@ public class MatchRatingApproachEncoder implements 
StringEncoder {
         // Preprocessing
         name = cleanName(name);
 
+        // Bulletproof if name becomes empty after cleanName(name)
+        if (SPACE.equals(name) || name.isEmpty()) {
+            return EMPTY;
+        }
+
         // BEGIN: Actual encoding part of the algorithm...
         // 1. Delete all vowels unless the vowel begins the word
         name = removeVowels(name);
 
+        // Bulletproof if name becomes empty after removeVowels(name)
+        if (SPACE.equals(name) || name.isEmpty()) {
+            return EMPTY;
+        }
+
         // 2. Remove second consonant from any double consonant
         name = removeDoubleConsonants(name);
 
diff --git 
a/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java
 
b/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java
index bf7508e8..7f10ecd8 100644
--- 
a/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java
+++ 
b/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java
@@ -35,8 +35,6 @@ import org.junit.jupiter.api.Test;
  */
 public class MatchRatingApproachEncoderTest extends 
AbstractStringEncoderTest<MatchRatingApproachEncoder> {
 
-    // ********** BEGIN REGION - TEST SUPPORT METHODS
-
     @Override
     protected MatchRatingApproachEncoder createStringEncoder() {
         return new MatchRatingApproachEncoder();
@@ -248,10 +246,6 @@ public class MatchRatingApproachEncoderTest extends 
AbstractStringEncoderTest<Ma
         assertTrue(this.getStringEncoder().isEncodeEquals("O'Sullivan", "Ó ' 
Súilleabháin"));
     }
 
-    // ***** END REGION - TEST SUPPORT METHODS
-
-    // ***** BEGIN REGION - TEST GET MRA ENCODING
-
     @Test
     public final void 
testCompare_Surname_PRZEMYSL_PSHEMESHIL_SuccessfullyMatched() {
         assertTrue(this.getStringEncoder().isEncodeEquals(" P rz e m y s l", " 
P sh e m e sh i l"));
@@ -297,10 +291,6 @@ public class MatchRatingApproachEncoderTest extends 
AbstractStringEncoderTest<Ma
         assertTrue(this.getStringEncoder().isEncodeEquals("Zach", "Zacharia"));
     }
 
-    // ***** END REGION - TEST GET MRA ENCODING
-
-    // ***** BEGIN REGION - TEST GET MRA COMPARISONS
-
     @Test
     public final void testCompareNameNullSpace_ReturnsFalseSuccessfully() {
         assertFalse(getStringEncoder().isEncodeEquals(null, " "));
@@ -433,8 +423,6 @@ public class MatchRatingApproachEncoderTest extends 
AbstractStringEncoderTest<Ma
         assertFalse(this.getStringEncoder().isEncodeEquals("", "test"));
     }
 
-    // **** BEGIN YIDDISH/SLAVIC SECTION ****
-
     @Test
     public final void 
testIsEncodeEquals_CornerCase_FirstNameNull_ReturnsFalse() {
         assertFalse(this.getStringEncoder().isEncodeEquals(null, "test"));
@@ -470,8 +458,6 @@ public class MatchRatingApproachEncoderTest extends 
AbstractStringEncoderTest<Ma
         assertTrue(this.getStringEncoder().isVowel("I"));
     }
 
-    // **** END YIDDISH/SLAVIC SECTION ****
-
     @Test
     public final void testIsVowel_SmallD_ReturnsFalse() {
         assertFalse(this.getStringEncoder().isVowel("d"));
@@ -519,4 +505,18 @@ public class MatchRatingApproachEncoderTest extends 
AbstractStringEncoderTest<Ma
 
     // ***** END REGION - TEST GET MRA COMPARISONS
 
+    @Test
+    public final void testPunctuationOnly() {
+        assertEquals(this.getStringEncoder().encode(".,-"), "");
+    }
+
+    @Test
+    public final void testVowelOnly() {
+        assertEquals(this.getStringEncoder().encode("aeiouAEIOU"), "A");
+    }
+
+    @Test
+    public final void testVowelAndPunctuationOnly() {
+        assertEquals(this.getStringEncoder().encode("uoiea.,-AEIOU"), "U");
+    }
 }