public void TestDefaults()
{
JapaneseTokenizerFactory factory = new JapaneseTokenizerFactory(new Dictionary <String, String>());
factory.Inform(new StringMockResourceLoader(""));
TokenStream ts = factory.Create(new StringReader("シニアソフトウェアエンジニア"));
AssertTokenStreamContents(ts,
new String[] { "シニア", "シニアソフトウェアエンジニア", "ソフトウェア", "エンジニア" }
);
}
public void TestReadings()
{
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory(new Dictionary <String, String>());
tokenizerFactory.Inform(new StringMockResourceLoader(""));
TokenStream tokenStream = tokenizerFactory.Create(new StringReader("先ほどベルリンから来ました。"));
JapaneseReadingFormFilterFactory filterFactory = new JapaneseReadingFormFilterFactory(new Dictionary <String, String>());
AssertTokenStreamContents(filterFactory.Create(tokenStream),
new String[] { "サキ", "ホド", "ベルリン", "カラ", "キ", "マシ", "タ" }
);
}
public void TestBasics()
{
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory(new Dictionary <String, String>());
tokenizerFactory.Inform(new StringMockResourceLoader(""));
TokenStream ts = tokenizerFactory.Create(new StringReader("それはまだ実験段階にあります"));
JapaneseBaseFormFilterFactory factory = new JapaneseBaseFormFilterFactory(new Dictionary <String, String>());
ts = factory.Create(ts);
AssertTokenStreamContents(ts,
new String[] { "それ", "は", "まだ", "実験", "段階", "に", "ある", "ます" }
);
}
public void TestSimple()
{
JapaneseTokenizerFactory factory = new JapaneseTokenizerFactory(new Dictionary <String, String>());
factory.Inform(new StringMockResourceLoader(""));
TokenStream ts = factory.Create(new StringReader("これは本ではない"));
AssertTokenStreamContents(ts,
new String[] { "これ", "は", "本", "で", "は", "ない" },
new int[] { 0, 2, 3, 4, 5, 6 },
new int[] { 2, 3, 4, 5, 6, 8 }
);
}
public void TestMode()
{
IDictionary <String, String> args = new Dictionary <String, String>();
args.Put("mode", "normal");
JapaneseTokenizerFactory factory = new JapaneseTokenizerFactory(args);
factory.Inform(new StringMockResourceLoader(""));
TokenStream ts = factory.Create(new StringReader("シニアソフトウェアエンジニア"));
AssertTokenStreamContents(ts,
new String[] { "シニアソフトウェアエンジニア" }
);
}
public void TestIterationMarksWithJapaneseTokenizer()
{
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory(new Dictionary <String, String>());
tokenizerFactory.Inform(new StringMockResourceLoader(""));
JapaneseIterationMarkCharFilterFactory filterFactory = new JapaneseIterationMarkCharFilterFactory(new Dictionary <String, String>());
TextReader filter = filterFactory.Create(
new StringReader("時々馬鹿々々しいところゞゝゝミスヾ")
);
TokenStream tokenStream = tokenizerFactory.Create(filter);
AssertTokenStreamContents(tokenStream, new String[] { "時時", "馬鹿馬鹿しい", "ところどころ", "ミ", "スズ" });
}
public void TestKatakanaStemming()
{
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory(new Dictionary <String, String>());
tokenizerFactory.Inform(new StringMockResourceLoader(""));
TokenStream tokenStream = tokenizerFactory.Create(
new StringReader("明後日パーティーに行く予定がある。図書館で資料をコピーしました。")
);
JapaneseKatakanaStemFilterFactory filterFactory = new JapaneseKatakanaStemFilterFactory(new Dictionary <String, String>());;
AssertTokenStreamContents(filterFactory.Create(tokenStream),
new String[] { "明後日", "パーティ", "に", "行く", "予定", "が", "ある", // パーティー should be stemmed
"図書館", "で", "資料", "を", "コピー", "し", "まし", "た" } // コピー should not be stemmed
);
}
public void TestPreservePunctuation()
{
IDictionary <String, String> args = new Dictionary <String, String>();
args.Put("discardPunctuation", "false");
JapaneseTokenizerFactory factory = new JapaneseTokenizerFactory(args);
factory.Inform(new StringMockResourceLoader(""));
TokenStream ts = factory.Create(
new StringReader("今ノルウェーにいますが、来週の頭日本に戻ります。楽しみにしています！お寿司が食べたいな。。。")
);
AssertTokenStreamContents(ts,
new String[] { "今", "ノルウェー", "に", "い", "ます", "が", "、",
"来週", "の", "頭", "日本", "に", "戻り", "ます", "。",
"楽しみ", "に", "し", "て", "い", "ます", "！",
"お", "寿司", "が", "食べ", "たい", "な", "。", "。", "。" }
);
}
public void TestKanaOnlyIterationMarksWithJapaneseTokenizer()
{
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory(new Dictionary <String, String>());
tokenizerFactory.Inform(new StringMockResourceLoader(""));
IDictionary <String, String> filterArgs = new Dictionary <String, String>();
filterArgs.Put("normalizeKanji", "false");
filterArgs.Put("normalizeKana", "true");
JapaneseIterationMarkCharFilterFactory filterFactory = new JapaneseIterationMarkCharFilterFactory(filterArgs);
TextReader filter = filterFactory.Create(
new StringReader("時々馬鹿々々しいところゞゝゝミスヾ")
);
TokenStream tokenStream = tokenizerFactory.Create(filter);
AssertTokenStreamContents(tokenStream, new String[] { "時々", "馬鹿", "々", "々", "しい", "ところどころ", "ミ", "スズ" });
}
public void TestUserDict()
{
String userDict =
"# Custom segmentation for long entries\n" +
"日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞\n" +
"関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,テスト名詞\n" +
"# Custom reading for sumo wrestler\n" +
"朝青龍,朝青龍,アサショウリュウ,カスタム人名\n";
IDictionary <String, String> args = new Dictionary <String, String>();
args.Put("userDictionary", "userdict.txt");
JapaneseTokenizerFactory factory = new JapaneseTokenizerFactory(args);
factory.Inform(new StringMockResourceLoader(userDict));
TokenStream ts = factory.Create(new StringReader("関西国際空港に行った"));
AssertTokenStreamContents(ts,
new String[] { "関西", "国際", "空港", "に", "行っ", "た" }
);
}
public void TestBasics()
{
String tags =
"# verb-main:\n" +
"動詞-自立\n";
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory(new Dictionary <String, String>());
tokenizerFactory.Inform(new StringMockResourceLoader(""));
TokenStream ts = tokenizerFactory.Create(new StringReader("私は制限スピードを超える。"));
IDictionary <String, String> args = new Dictionary <String, String>();
args.Put("luceneMatchVersion", TEST_VERSION_CURRENT.toString());
args.Put("tags", "stoptags.txt");
JapanesePartOfSpeechStopFilterFactory factory = new JapanesePartOfSpeechStopFilterFactory(args);
factory.Inform(new StringMockResourceLoader(tags));
ts = factory.Create(ts);
AssertTokenStreamContents(ts,
new String[] { "私", "は", "制限", "スピード", "を" }
);
}