From ecde0adfcac572fd677dfa622a3227d00e7257f5 Mon Sep 17 00:00:00 2001
From: Billy Seol <seol@foursquare.com>
Date: Mon, 19 Oct 2015 21:42:07 +0000
Subject: [PATCH 1/5] slf4j-nop needs a non-default scope

---
 pom.xml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/pom.xml b/pom.xml
index 167c7d0..aef2268 100644
--- a/pom.xml
+++ b/pom.xml
@@ -91,6 +91,7 @@
       <groupId>org.slf4j</groupId>
       <artifactId>slf4j-nop</artifactId>
       <version>1.5.8</version>
+      <scope>provided</scope>
     </dependency>
     <dependency>
       <groupId>org.scalatest</groupId>

From 939842e03ae7955955e66775c33fa3c53e14e550 Mon Sep 17 00:00:00 2001
From: Will Hohyon Ryu <Softbass@gmail.com>
Date: Mon, 26 Oct 2015 17:20:15 -0700
Subject: [PATCH 2/5] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 07cf60c..3472d3a 100644
--- a/README.md
+++ b/README.md
@@ -39,7 +39,7 @@ Opensourced here: [twitter-korean-tokenizer-api](https://github.com/gunjaag/twit
 ## API
 [scaladoc](http://twitter.github.io/twitter-korean-text/scaladocs/#com.twitter.penguin.korean.TwitterKoreanProcessor$)
 
-[Auto-generated Documentation](http://twitter.github.io/twitter-korean-text)
+[Machine-generated Documentation](http://twitter.github.io/twitter-korean-text)
 
 
 ## Maven

From 97006e5543e850c556ea68369020b58acce14bc4 Mon Sep 17 00:00:00 2001
From: Will Hohyon Ryu <Softbass@gmail.com>
Date: Mon, 26 Oct 2015 17:20:50 -0700
Subject: [PATCH 3/5] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 3472d3a..afab1d0 100644
--- a/README.md
+++ b/README.md
@@ -39,7 +39,7 @@ Opensourced here: [twitter-korean-tokenizer-api](https://github.com/gunjaag/twit
 ## API
 [scaladoc](http://twitter.github.io/twitter-korean-text/scaladocs/#com.twitter.penguin.korean.TwitterKoreanProcessor$)
 
-[Machine-generated Documentation](http://twitter.github.io/twitter-korean-text)
+[mavendoc](http://twitter.github.io/twitter-korean-text)
 
 
 ## Maven

From 4d1e36aaa4133210618de9979a6a091af623bdee Mon Sep 17 00:00:00 2001
From: Will Hohyon Ryu <Softbass@gmail.com>
Date: Tue, 27 Oct 2015 10:38:29 -0700
Subject: [PATCH 4/5] Update README.md

---
 README.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/README.md b/README.md
index afab1d0..f018083 100644
--- a/README.md
+++ b/README.md
@@ -27,6 +27,9 @@ twitter-korean-text는 normalization, tokenization, stemming, phrase extraction
 
 * 한국어를 처리하는 예시입니다 ㅋㅋ -> 한국어, 처리, 예시, 처리하는 예시
 
+Introductory Presentation: [Google Slides](https://docs.google.com/presentation/d/10CZj8ry03oCk_Jqw879HFELzOLjJZ0EOi4KJbtRSIeU)
+
+
 ## Try it here
 
 Gunja Agrawal kindly created a test API webpage for this project: [http://gunjaagrawal.com/langhack/](http://gunjaagrawal.com/langhack/)

From ed7521797a3e3b04f3dfa51fe013c14ca22e095b Mon Sep 17 00:00:00 2001
From: Will Hohyon Ryu <hohyonryu@twitter.com>
Date: Thu, 5 Nov 2015 12:10:01 -0800
Subject: [PATCH 5/5] tokenization error message

---
 .../korean/tokenizer/KoreanTokenizer.scala    | 22 ++++++++++++-------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanTokenizer.scala b/src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanTokenizer.scala
index 877263e..0fe6679 100644
--- a/src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanTokenizer.scala
+++ b/src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanTokenizer.scala
@@ -251,14 +251,20 @@ object KoreanTokenizer {
    * @return sequence of KoreanTokens
    */
   def tokenize(text: CharSequence): Seq[KoreanToken] = {
-    chunk(text).flatMap {
-      case token: KoreanToken if token.pos == Korean =>
-        // Get the best parse of each chunk
-        val parsed = parseKoreanChunk(token)
-
-        // Collapse sequence of one-char nouns into one unknown noun: (가Noun 회Noun -> 가회Noun*)
-        collapseNouns(parsed)
-      case token: KoreanToken => Seq(token)
+    try {
+      chunk(text).flatMap {
+        case token: KoreanToken if token.pos == Korean =>
+          // Get the best parse of each chunk
+          val parsed = parseKoreanChunk(token)
+
+          // Collapse sequence of one-char nouns into one unknown noun: (가Noun 회Noun -> 가회Noun*)
+          collapseNouns(parsed)
+        case token: KoreanToken => Seq(token)
+      }
+    } catch {
+      case e: Exception =>
+        System.err.println(s"Error tokenizing a chunk: $text")
+        throw e
     }
   }
 }
\ No newline at end of file