Merge pull request #454 from AmyAssist/characterConversion

added english character conversion

natlang/src/main/java/de/unistuttgart/iaas/amyassist/amy/natlang/languagespecifics/ChooseLanguage.java

@@ -23,10 +23,7 @@
 
 package de.unistuttgart.iaas.amyassist.amy.natlang.languagespecifics;
 
-import de.unistuttgart.iaas.amyassist.amy.natlang.languagespecifics.en.EnglishContraction;
-import de.unistuttgart.iaas.amyassist.amy.natlang.languagespecifics.en.EnglishDateTimeUtility;
-import de.unistuttgart.iaas.amyassist.amy.natlang.languagespecifics.en.EnglishNumberConversion;
-import de.unistuttgart.iaas.amyassist.amy.natlang.languagespecifics.en.EnglishStemmer;
+import de.unistuttgart.iaas.amyassist.amy.natlang.languagespecifics.en.*;
 
 /**
  * 
@@ -37,6 +34,7 @@ public class ChooseLanguage {
 	private final NumberConversion numberConversion;
 	private final DateTimeUtility timeUtility;
 	private final Contraction contraction;
+	private final SpecialCharacterConversion specialCharacterConversion;
 
 	/**
 	 * constructor for choose language
@@ -58,6 +56,7 @@ public ChooseLanguage(String language, boolean stemmerEnabled) {
 			this.numberConversion = new EnglishNumberConversion();
 			this.timeUtility = new EnglishDateTimeUtility();
 			this.contraction = new EnglishContraction();
+			this.specialCharacterConversion = new EnglishSpecialCharacterConversion();
 			break;
 		}
 	}
@@ -97,4 +96,13 @@ public DateTimeUtility getTimeUtility() {
 	public Contraction getContraction() {
 		return this.contraction;
 	}
+
+	/**
+	 * Get's {@link #specialCharacterConversion conversion}
+	 * 
+	 * @return contraction
+	 */
+	 public SpecialCharacterConversion getSpecialCharacterConversion() {
+		return this.specialCharacterConversion;
+	}
 }

natlang/src/main/java/de/unistuttgart/iaas/amyassist/amy/natlang/languagespecifics/SpecialCharacterConversion.java

@@ -0,0 +1,41 @@
+/*
+ * This source file is part of the Amy open source project.
+ * For more information see github.com/AmyAssist
+ * 
+ * Copyright (c) 2018 the Amy project authors.
+ *
+ * SPDX-License-Identifier: Apache-2.0
+ * 
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at 
+ * 
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ * 
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * For more information see notice.md
+ */
+
+package de.unistuttgart.iaas.amyassist.amy.natlang.languagespecifics;
+
+/**
+ * Utility interface to convert special characters
+ * 
+ * @author Felix Burk
+ */
+public interface SpecialCharacterConversion {
+
+	/**
+	 * formats special characters to their language counterpars
+	 * e.g. % to percent
+	 * @param toFormat input to format
+	 * @return formatted string
+	 */
+	String format(String toFormat);
+
+}

natlang/src/main/java/de/unistuttgart/iaas/amyassist/amy/natlang/languagespecifics/en/EnglishSpecialCharacterConversion.java

@@ -0,0 +1,69 @@
+/*
+ * This source file is part of the Amy open source project.
+ * For more information see github.com/AmyAssist
+ * 
+ * Copyright (c) 2018 the Amy project authors.
+ *
+ * SPDX-License-Identifier: Apache-2.0
+ * 
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at 
+ * 
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ * 
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * For more information see notice.md
+ */
+
+package de.unistuttgart.iaas.amyassist.amy.natlang.languagespecifics.en;
+
+import java.util.HashMap;
+import java.util.Map;
+import java.util.Map.Entry;
+
+import de.unistuttgart.iaas.amyassist.amy.natlang.languagespecifics.SpecialCharacterConversion;
+
+/**
+ * Special Character conversion for the english language
+ * 
+ * @author Felix Burk
+ */
+public class EnglishSpecialCharacterConversion implements SpecialCharacterConversion {
+
+	private Map<String, String> conversion;
+
+	public EnglishSpecialCharacterConversion() {
+		this.conversion = new HashMap<>();
+
+		this.conversion.put("%", "percent");
+		this.conversion.put("$", "dollar");
+		this.conversion.put("€", "euro");
+		this.conversion.put("¢", "cent");
+		this.conversion.put("£", "pound");
+		this.conversion.put("¥", "yen");
+		this.conversion.put("°", "degree");
+	}
+
+	/**
+	 * @see de.unistuttgart.iaas.amyassist.amy.natlang.languagespecifics.SpecialCharacterConversion#format(java.lang.String)
+	 */
+	@Override
+	public String format(String toFormat) {
+		String result = toFormat;
+		//this is kinda ugly buuut regex and special characters is pretty bad
+		for(Entry<String, String> e : this.conversion.entrySet()) {
+			if(result.contains(e.getKey())) {
+				result = toFormat.replaceAll(e.getKey(), e.getValue());
+			}
+		}
+
+		return result;
+	}
+
+}

natlang/src/main/java/de/unistuttgart/iaas/amyassist/amy/natlang/nl/NLLexer.java

@@ -90,6 +90,7 @@ public List<WordToken> tokenize(String nlInput) {
 		toLex = this.language.getTimeUtility().formatTime(toLex);
 		toLex = this.language.getTimeUtility().formatDate(toLex);
 		toLex = this.language.getContraction().disassemblingContraction(toLex);
+		toLex = this.language.getSpecialCharacterConversion().format(toLex);
 
 		StringBuilder currentWord = new StringBuilder();
 		if (!toLex.isEmpty()) {

natlang/src/test/java/de/unistuttgart/iaas/amyassist/amy/core/natlang/nl/NLLexerTest.java

@@ -73,8 +73,8 @@ public void setup() {
 	public static Stream<Character> badCharacters() {
 		// every ascii character except numbers of letters
 		return IntStream.range(0, 128).mapToObj(i -> (char) i)
-				.filter(c -> (0 > c && c > 33) || (34 < c && c != 37 && !(43 < c && c < 47) && c < 48)
-						|| (59 < c && c < 65 && c != 63) || (90 < c && c < 97) || 122 < c);
+				.filter(c -> ((0 > c && c > 33) || (34 < c && !(43 < c && c < 47) && c != 36 && c != 37 && c < 48)
+						|| (59 < c && c < 65 && c != 63) || (90 < c && c < 97) || 122 < c));
 	}
 
 	/**