diff --git a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/ChunkerTest.java b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/ChunkerTest.java index 1299983323..cc3abb422b 100644 --- a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/ChunkerTest.java +++ b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/ChunkerTest.java @@ -13,12 +13,12 @@ import org.junit.Test; public class ChunkerTest { @Test - public void givenSentence_whenChunk_thenGetChunks() throws Exception { + public void givenChunkerModel_whenChunk_thenChunksAreDetected() throws Exception { SimpleTokenizer tokenizer = SimpleTokenizer.INSTANCE; String[] tokens = tokenizer.tokenize("He reckons the current account deficit will narrow to only 8 billion."); - InputStream inputStreamPOSTagger = new FileInputStream("src/main/resources/models/en-pos-maxent.bin"); + InputStream inputStreamPOSTagger = getClass().getResourceAsStream("/models/en-pos-maxent.bin"); POSModel posModel = new POSModel(inputStreamPOSTagger); POSTaggerME posTagger = new POSTaggerME(posModel); String tags[] = posTagger.tag(tokens); diff --git a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/LanguageDetectorAndTrainingData.java b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/LanguageDetectorAndTrainingDataTest.java similarity index 91% rename from apache-opennlp/src/test/java/com/baeldung/apache/opennlp/LanguageDetectorAndTrainingData.java rename to apache-opennlp/src/test/java/com/baeldung/apache/opennlp/LanguageDetectorAndTrainingDataTest.java index 3631cbd580..d9c18862e8 100644 --- a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/LanguageDetectorAndTrainingData.java +++ b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/LanguageDetectorAndTrainingDataTest.java @@ -18,10 +18,10 @@ import opennlp.tools.util.TrainingParameters; import static org.assertj.core.api.Assertions.assertThat; import org.junit.Test; -public class LanguageDetectorAndTrainingData { +public class LanguageDetectorAndTrainingDataTest { @Test - public void test() throws FileNotFoundException, IOException { + public void givenLanguageDictionary_whenLanguageDetect_thenLanguageIsDetected() throws FileNotFoundException, IOException { InputStreamFactory dataIn = new MarkableFileInputStreamFactory(new File("src/main/resources/models/DoccatSample.txt")); ObjectStream lineStream = new PlainTextByLineStream(dataIn, "UTF-8"); LanguageDetectorSampleStream sampleStream = new LanguageDetectorSampleStream(lineStream); diff --git a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/LemmetizerTest.java b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/LemmetizerTest.java index 43e6ff1f44..bb681fb8d8 100644 --- a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/LemmetizerTest.java +++ b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/LemmetizerTest.java @@ -1,7 +1,5 @@ package com.baeldung.apache.opennlp; -import java.io.File; -import java.io.FileInputStream; import java.io.InputStream; import opennlp.tools.lemmatizer.DictionaryLemmatizer; import opennlp.tools.postag.POSModel; @@ -13,16 +11,16 @@ import org.junit.Test; public class LemmetizerTest { @Test - public void givenSentence_whenLemmetize_thenGetLemmas() throws Exception { + public void givenEnglishDictionary_whenLemmatize_thenLemmasAreDetected() throws Exception { SimpleTokenizer tokenizer = SimpleTokenizer.INSTANCE; String[] tokens = tokenizer.tokenize("John has a sister named Penny."); - InputStream inputStreamPOSTagger = new FileInputStream("src/main/resources/models/en-pos-maxent.bin"); + InputStream inputStreamPOSTagger = getClass().getResourceAsStream("/models/en-pos-maxent.bin"); POSModel posModel = new POSModel(inputStreamPOSTagger); POSTaggerME posTagger = new POSTaggerME(posModel); String tags[] = posTagger.tag(tokens); - InputStream dictLemmatizer = new FileInputStream("src/main/resources/models/en-lemmatizer.dict"); + InputStream dictLemmatizer = getClass().getResourceAsStream("/models/en-lemmatizer.dict"); DictionaryLemmatizer lemmatizer = new DictionaryLemmatizer(dictLemmatizer); String[] lemmas = lemmatizer.lemmatize(tokens, tags); diff --git a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/NamedEntityRecognitionTest.java b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/NamedEntityRecognitionTest.java index e2f7de710c..94224409d6 100644 --- a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/NamedEntityRecognitionTest.java +++ b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/NamedEntityRecognitionTest.java @@ -1,6 +1,5 @@ package com.baeldung.apache.opennlp; -import java.io.FileInputStream; import java.io.InputStream; import java.util.ArrayList; import java.util.Arrays; @@ -15,12 +14,12 @@ import org.junit.Test; public class NamedEntityRecognitionTest { @Test - public void givenTextWithPersonNames_whenNER_thenGetPersonNamesList() throws Exception { + public void givenEnglishPersonModel_whenNER_thenPersonsAreDetected() throws Exception { SimpleTokenizer tokenizer = SimpleTokenizer.INSTANCE; String[] tokens = tokenizer.tokenize("John is 26 years old. His best friend's name is Leonard. He has a sister named Penny."); - InputStream inputStreamNameFinder = new FileInputStream("src/main/resources/models/en-ner-person.bin"); + InputStream inputStreamNameFinder = getClass().getResourceAsStream("/models/en-ner-person.bin"); TokenNameFinderModel model = new TokenNameFinderModel(inputStreamNameFinder); NameFinderME nameFinderME = new NameFinderME(model); List spans = Arrays.asList(nameFinderME.find(tokens)); diff --git a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/POSTaggerTest.java b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/POSTaggerTest.java index 47670188db..1bfebe208c 100644 --- a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/POSTaggerTest.java +++ b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/POSTaggerTest.java @@ -1,6 +1,5 @@ package com.baeldung.apache.opennlp; -import java.io.FileInputStream; import java.io.InputStream; import opennlp.tools.postag.POSModel; import opennlp.tools.postag.POSTaggerME; @@ -11,12 +10,12 @@ import org.junit.Test; public class POSTaggerTest { @Test - public void givenSentence_whenPOSTagging_thenGetTags() throws Exception { + public void givenPOSModel_whenPOSTagging_thenPOSAreDetected() throws Exception { SimpleTokenizer tokenizer = SimpleTokenizer.INSTANCE; String[] tokens = tokenizer.tokenize("John has a sister named Penny."); - InputStream inputStreamPOSTagger = new FileInputStream("src/main/resources/models/en-pos-maxent.bin"); + InputStream inputStreamPOSTagger = getClass().getResourceAsStream("/models/en-pos-maxent.bin"); POSModel posModel = new POSModel(inputStreamPOSTagger); POSTaggerME posTagger = new POSTaggerME(posModel); String tags[] = posTagger.tag(tokens); diff --git a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/SentenceDetectionTest.java b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/SentenceDetectionTest.java index b59037b383..0250b12cbf 100644 --- a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/SentenceDetectionTest.java +++ b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/SentenceDetectionTest.java @@ -1,6 +1,5 @@ package com.baeldung.apache.opennlp; -import java.io.FileInputStream; import java.io.InputStream; import opennlp.tools.sentdetect.SentenceDetectorME; import opennlp.tools.sentdetect.SentenceModel; @@ -10,12 +9,12 @@ import org.junit.Test; public class SentenceDetectionTest { @Test - public void givenText_whenDetectSent_thenGetSentences() throws Exception { + public void givenEnglishModel_whenDetect_thenSentencesAreDetected() throws Exception { String paragraph = "This is a statement. This is another statement. Now is an abstract word for time, " + "that is always flying. And my email address is google@gmail.com."; - InputStream is = new FileInputStream("src/main/resources/models/en-sent.bin"); + InputStream is = getClass().getResourceAsStream("/models/en-sent.bin"); SentenceModel model = new SentenceModel(is); SentenceDetectorME sdetector = new SentenceDetectorME(model); diff --git a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/TokenizerTest.java b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/TokenizerTest.java index cf6c86e402..a4dea57cc3 100644 --- a/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/TokenizerTest.java +++ b/apache-opennlp/src/test/java/com/baeldung/apache/opennlp/TokenizerTest.java @@ -1,6 +1,6 @@ package com.baeldung.apache.opennlp; -import java.io.FileInputStream; +import java.io.InputStream; import opennlp.tools.tokenize.SimpleTokenizer; import opennlp.tools.tokenize.TokenizerME; import opennlp.tools.tokenize.TokenizerModel; @@ -11,23 +11,23 @@ import org.junit.Test; public class TokenizerTest { @Test - public void givenString_whenTokenize_thenGetTokens() throws Exception { - FileInputStream fileInputStream = new FileInputStream("src/main/resources/models/en-token.bin"); - TokenizerModel model = new TokenizerModel(fileInputStream); + public void givenEnglishModel_whenTokenize_thenTokensAreDetected() throws Exception { + InputStream inputStream = getClass().getResourceAsStream("/models/en-token.bin"); + TokenizerModel model = new TokenizerModel(inputStream); TokenizerME tokenizer = new TokenizerME(model); String[] tokens = tokenizer.tokenize("Baeldung is a Spring Resource."); assertThat(tokens).contains("Baeldung", "is", "a", "Spring", "Resource", "."); } @Test - public void givenString_whenWhitespaceTokenizer_thenGetTokens() throws Exception { + public void givenWhitespaceTokenizer_whenTokenize_thenTokensAreDetected() throws Exception { WhitespaceTokenizer tokenizer = WhitespaceTokenizer.INSTANCE; String[] tokens = tokenizer.tokenize("Baeldung is a Spring Resource."); assertThat(tokens).contains("Baeldung", "is", "a", "Spring", "Resource."); } @Test - public void givenString_whenSimpleTokenizer_thenGetTokens() throws Exception { + public void givenSimpleTokenizer_whenTokenize_thenTokensAreDetected() throws Exception { SimpleTokenizer tokenizer = SimpleTokenizer.INSTANCE; String[] tokens = tokenizer.tokenize("Baeldung is a Spring Resource."); assertThat(tokens).contains("Baeldung", "is", "a", "Spring", "Resource", ".");