From 31117d6a6ed114c2036510bb9976d9d0012ee59a Mon Sep 17 00:00:00 2001
From: robert-bor <bor.robert@gmail.com>
Date: Sat, 8 Feb 2014 12:45:55 +0100
Subject: [PATCH] Solved issue #5 by introducing a proper boundary check for
 words that are at the end of a String

---
 pom.xml                                       |  2 +-
 src/main/java/org/ahocorasick/trie/Trie.java  |  2 +-
 .../java/org/ahocorasick/trie/TrieTest.java   | 50 ++++++++++++-------
 3 files changed, 34 insertions(+), 20 deletions(-)

diff --git a/pom.xml b/pom.xml
index b1ae7cc..a9456f9 100644
--- a/pom.xml
+++ b/pom.xml
@@ -3,7 +3,7 @@
 
     <groupId>org.ahocorasick</groupId>
     <artifactId>ahocorasick</artifactId>
-    <version>0.2.0</version>
+    <version>0.3.0-SNAPSHOT</version>
     <packaging>jar</packaging>
     <name>Aho-CoraSick algorithm for efficient string matching</name>
     <description>Java library for efficient string matching against a large set of keywords</description>
diff --git a/src/main/java/org/ahocorasick/trie/Trie.java b/src/main/java/org/ahocorasick/trie/Trie.java
index 0d28c9b..fba65f0 100644
--- a/src/main/java/org/ahocorasick/trie/Trie.java
+++ b/src/main/java/org/ahocorasick/trie/Trie.java
@@ -117,7 +117,7 @@ public class Trie {
         for (Emit emit : collectedEmits) {
             if ((emit.getStart() == 0 ||
                  !Character.isAlphabetic(searchText.charAt(emit.getStart() - 1))) &&
-                (emit.getEnd() == size ||
+                (emit.getEnd() + 1 == size ||
                  !Character.isAlphabetic(searchText.charAt(emit.getEnd() + 1)))) {
                 continue;
             }
diff --git a/src/test/java/org/ahocorasick/trie/TrieTest.java b/src/test/java/org/ahocorasick/trie/TrieTest.java
index 8000d63..7203fb5 100644
--- a/src/test/java/org/ahocorasick/trie/TrieTest.java
+++ b/src/test/java/org/ahocorasick/trie/TrieTest.java
@@ -1,7 +1,5 @@
 package org.ahocorasick.trie;
 
-import org.ahocorasick.trie.Emit;
-import org.ahocorasick.trie.Trie;
 import org.junit.Test;
 
 import java.util.Collection;
@@ -135,22 +133,6 @@ public class TrieTest {
         checkEmit(emits.iterator().next(), 20, 24, "sugar");
     }
 
-    @Test
-    public void caseInsensitive() {
-        Trie trie = new Trie().caseInsensitive();
-        trie.addKeyword("turning");
-        trie.addKeyword("once");
-        trie.addKeyword("again");
-        trie.addKeyword("börkü");
-        Collection<Emit> emits = trie.parseText("TurninG OnCe AgAiN BÖRKÜ");
-        assertEquals(4, emits.size()); // Match must not be made
-        Iterator<Emit> it = emits.iterator();
-        checkEmit(it.next(), 0, 6, "turning");
-        checkEmit(it.next(), 8, 11, "once");
-        checkEmit(it.next(), 13, 17, "again");
-        checkEmit(it.next(), 19, 23, "börkü");
-    }
-
     @Test
     public void tokenizeFullSentence() {
         Trie trie = new Trie();
@@ -169,6 +151,38 @@ public class TrieTest {
         assertEquals(" in reserve", tokensIt.next().getFragment());
     }
 
+    @Test
+    public void bug5InGithubReportedByXCurry() {
+        Trie trie = new Trie().caseInsensitive().onlyWholeWords();
+        trie.addKeyword("turning");
+        trie.addKeyword("once");
+        trie.addKeyword("again");
+        trie.addKeyword("börkü");
+        Collection<Emit> emits = trie.parseText("TurninG OnCe AgAiN BÖRKÜ");
+        assertEquals(4, emits.size()); // Match must not be made
+        Iterator<Emit> it = emits.iterator();
+        checkEmit(it.next(), 0, 6, "turning");
+        checkEmit(it.next(), 8, 11, "once");
+        checkEmit(it.next(), 13, 17, "again");
+        checkEmit(it.next(), 19, 23, "börkü");
+    }
+
+    @Test
+    public void caseInsensitive() {
+        Trie trie = new Trie().caseInsensitive();
+        trie.addKeyword("turning");
+        trie.addKeyword("once");
+        trie.addKeyword("again");
+        trie.addKeyword("börkü");
+        Collection<Emit> emits = trie.parseText("TurninG OnCe AgAiN BÖRKÜ");
+        assertEquals(4, emits.size()); // Match must not be made
+        Iterator<Emit> it = emits.iterator();
+        checkEmit(it.next(), 0, 6, "turning");
+        checkEmit(it.next(), 8, 11, "once");
+        checkEmit(it.next(), 13, 17, "again");
+        checkEmit(it.next(), 19, 23, "börkü");
+    }
+
     @Test
     public void tokenizeTokensInSequence() {
         Trie trie = new Trie();