From 330911389a77957a61cabb890140f86781d45c93 Mon Sep 17 00:00:00 2001
From: Jun Ohtani <johtani@gmail.com>
Date: Thu, 14 May 2015 13:41:44 +0900
Subject: [PATCH] Add user dictionary test case

Closes #59
---
 README.md                                     |  2 +-
 pom.xml                                       |  1 +
 .../index/analysis/KuromojiAnalysisTests.java | 20 +++++++++++++++++++
 .../index/analysis/empty_user_dict.txt        |  0
 .../index/analysis/kuromoji_analysis.json     | 11 ++++++++--
 .../index/analysis/user_dict.txt              |  1 +
 6 files changed, 32 insertions(+), 3 deletions(-)
 create mode 100644 src/test/java/org/elasticsearch/index/analysis/empty_user_dict.txt
 create mode 100644 src/test/java/org/elasticsearch/index/analysis/user_dict.txt

diff --git a/README.md b/README.md
index 65e37c88b52..42346cb31b2 100644
--- a/README.md
+++ b/README.md
@@ -88,7 +88,7 @@ The following are settings that can be set for a `kuromoji_tokenizer` tokenizer
 |:--------------------|:--------------------------------------------------------------------------------------------------------------------------|:------------------|
 | mode                | Tokenization mode: this determines how the tokenizer handles compound and unknown words. `normal` and `search`, `extended`| `search`          |
 | discard_punctuation | `true` if punctuation tokens should be dropped from the output.                                                           | `true`            |
-| user_dict           | set User Dictionary file                                                                                                  |                   |
+| user_dictionary     | set User Dictionary file                                                                                                  |                   |
 
 ### Tokenization mode
 
diff --git a/pom.xml b/pom.xml
index 1845da9de14..447e278d287 100644
--- a/pom.xml
+++ b/pom.xml
@@ -87,6 +87,7 @@
                 <directory>src/test/java</directory>
                 <includes>
                     <include>**/*.json</include>
+                    <include>**/*.txt</include>
                 </includes>
             </testResource>
             <testResource>
diff --git a/src/test/java/org/elasticsearch/index/analysis/KuromojiAnalysisTests.java b/src/test/java/org/elasticsearch/index/analysis/KuromojiAnalysisTests.java
index 73fd78047bf..02749c7c952 100644
--- a/src/test/java/org/elasticsearch/index/analysis/KuromojiAnalysisTests.java
+++ b/src/test/java/org/elasticsearch/index/analysis/KuromojiAnalysisTests.java
@@ -245,4 +245,24 @@ public class KuromojiAnalysisTests extends ElasticsearchTestCase {
         return buffer.toString();
     }
 
+    @Test
+    public void testKuromojiUserDict() throws IOException {
+        AnalysisService analysisService = createAnalysisService();
+        TokenizerFactory tokenizerFactory = analysisService.tokenizer("kuromoji_user_dict");
+        String source = "私は制限スピードを超える。";
+        String[] expected = new String[]{"私", "は", "制限スピード", "を", "超える"};
+
+        Tokenizer tokenizer = tokenizerFactory.create();
+        tokenizer.setReader(new StringReader(source));
+        assertSimpleTSOutput(tokenizer, expected);
+    }
+
+    // fix #59
+    @Test
+    public void testKuromojiEmptyUserDict() {
+        AnalysisService analysisService = createAnalysisService();
+        TokenizerFactory tokenizerFactory = analysisService.tokenizer("kuromoji_empty_user_dict");
+        assertThat(tokenizerFactory, instanceOf(KuromojiTokenizerFactory.class));
+    }
+
 }
diff --git a/src/test/java/org/elasticsearch/index/analysis/empty_user_dict.txt b/src/test/java/org/elasticsearch/index/analysis/empty_user_dict.txt
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/src/test/java/org/elasticsearch/index/analysis/kuromoji_analysis.json b/src/test/java/org/elasticsearch/index/analysis/kuromoji_analysis.json
index 7642e756ceb..a36b4ae2197 100644
--- a/src/test/java/org/elasticsearch/index/analysis/kuromoji_analysis.json
+++ b/src/test/java/org/elasticsearch/index/analysis/kuromoji_analysis.json
@@ -39,9 +39,16 @@
 
             "tokenizer" : {
                 "kuromoji" : {
-                   "type":"kuromoji_tokenizer"
+                    "type":"kuromoji_tokenizer"
+                },
+                "kuromoji_empty_user_dict" : {
+                    "type":"kuromoji_tokenizer",
+                    "user_dictionary":"org/elasticsearch/index/analysis/empty_user_dict.txt"
+                },
+                "kuromoji_user_dict" : {
+                    "type":"kuromoji_tokenizer",
+                    "user_dictionary":"org/elasticsearch/index/analysis/user_dict.txt"
                 }
-            
             },
             "analyzer" : {
                 "my_analyzer" : {
diff --git a/src/test/java/org/elasticsearch/index/analysis/user_dict.txt b/src/test/java/org/elasticsearch/index/analysis/user_dict.txt
new file mode 100644
index 00000000000..54b59d66130
--- /dev/null
+++ b/src/test/java/org/elasticsearch/index/analysis/user_dict.txt
@@ -0,0 +1 @@
+制限スピード,制限スピード,セイゲンスピード,テスト名詞