fix: fixing unittests that fail becuase of work done to author transl…

…iterations

contrib/adsabs/src/java/org/adsabs/solr/analysis/ProcessCuratedAuthorSynonyms.java

@@ -6,6 +6,9 @@
 import java.util.HashMap;
 import java.util.HashSet;
 import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
 import org.apache.solr.analysis.WriteableExplicitSynonymMap;
 import org.apache.solr.analysis.WriteableSynonymMap;
 import org.apache.solr.analysis.author.AuthorQueryVariations;
@@ -75,9 +78,9 @@ public static HashMap<String,HashSet<String>> transformGroup(List<String> group)
 		log.debug("withAutoSynonyms: " + withAutoSynonyms.toString());
 
 		// build a map of name -> variations to be used later
-		final HashMap<String,HashSet<String>> variationsMap = new HashMap<String,HashSet<String>>();
+		final HashMap<String, Set<String>> variationsMap = new HashMap<String,Set<String>>();
 		for (String s : withAutoSynonyms) {
-			HashMap<String,String> parsedAuthor = null;
+			Map<String,String> parsedAuthor = null;
 			try {
 				parsedAuthor = AuthorUtils.parseAuthor(s);
 			} catch (Exception e) {

contrib/adsabs/src/java/org/apache/solr/analysis/author/AuthorQueryVariations.java

@@ -71,9 +71,9 @@ protected static Set<String> generateNameVariations(Map<String, String> parsedAu
 		generateSynonymVariations(parsedAuthor, variations);
 
 		// add the variations that are needed only for the query phase
-		String last = parsedAuthor.get("last");
-		String first = parsedAuthor.get("first");
-		String middle = parsedAuthor.get("middle");
+		String last = parsedAuthor.get("Last");
+		String first = parsedAuthor.get("First");
+		String middle = parsedAuthor.get("Middle");
 
 		if (first != null) {
 			if (middle != null) {
@@ -115,7 +115,7 @@ protected static Set<String> generateNameVariations(Map<String, String> parsedAu
 	 * @param authorString name in the natural form
 	 * @return map with string mappings
 	 */
-	public static HashSet<String> getQueryVariations(String authorString) {
+	public static Set<String> getQueryVariations(String authorString) {
 
 		Map<String, String> parsedAuthor = null;
 		parsedAuthor = AuthorUtils.parseAuthor(authorString);
@@ -128,12 +128,12 @@ public static HashSet<String> getQueryVariations(String authorString) {
 		return generateSynonymVariations(parsedAuthor, variations);
 	}
 
-	public static HashSet<String> generateSynonymVariations(HashMap<String, String> parsedAuthor) {
+	public static Set<String> generateSynonymVariations(Map<String, String> parsedAuthor) {
 		HashSet<String> variations = new LinkedHashSet<String>();
 		return generateSynonymVariations(parsedAuthor, variations);
 	}
 
-	protected static HashSet<String> generateSynonymVariations(Map<String, String> parsedAuthor,
+	protected static Set<String> generateSynonymVariations(Map<String, String> parsedAuthor,
 			Set<String> variations) {
 
 		String last = parsedAuthor.get("Last");

contrib/adsabs/src/java/org/apache/solr/analysis/author/AuthorUtils.java

@@ -114,11 +114,13 @@ public static ArrayList<String> getAsciiTransliteratedVariants(String a) {
 		synonyms.add(a);
 
 		// downgrade to ascii
+		synonyms.add(foldToAscii(a));
+
+		// work around unidecode not always doing what we want
 		String b = replaceUmlaut(a);
 		if (b != a) {
 			synonyms.add(foldToAscii(b));
 		}
-		synonyms.add(foldToAscii(a));
 
 		// handle russian name stuff
 		HashSet<String> transRus = transliterateRussianNames(synonyms);
@@ -143,6 +145,9 @@ private static String replaceUmlaut(String input) {
 		StringBuilder out = new StringBuilder();
 		for (char c: input.toCharArray()) {
 			switch(c) {
+			case '\u00fc':
+				out.append("ue");
+				break;
 			case '\u00f6':
 				out.append("oe");
 				break;

contrib/adsabs/src/test/org/apache/solr/analysis/author/TestAuthorTransliterationFilter.java

@@ -12,53 +12,45 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
 
-
 public class TestAuthorTransliterationFilter extends BaseTokenStreamTestCase {
-	
+
 	final class TestFilter extends TokenFilter {
 		private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
+
 		public TestFilter(TokenStream input) {
 			super(input);
 		}
+
 		public boolean incrementToken() throws IOException {
-		    if (!input.incrementToken()) return false;
-		    typeAtt.setType(AuthorUtils.AUTHOR_INPUT);
-	        return true;
+			if (!input.incrementToken())
+				return false;
+			typeAtt.setType(AuthorUtils.AUTHOR_INPUT);
+			return true;
 		}
 	}
-	
+
 	public void testAuthorSynonyms() throws Exception {
-		
+
 		checkIt("Müller, Bill", "Müller, Bill", "Mueller, Bill", "Muller, Bill");
 		checkIt("Peißker, L", "Peißker, L", "Peissker, L");
-
-
+
 	}
-	
+
 	public void testAccents() throws Exception {
-	  checkIt("Jeřábková, Tereza", "Jeřábková, Tereza", "Jerhaebkovae, Tereza", "Jerabkova, Tereza");
-	  checkIt("Dupré", "Dupré", "Dupree", "Dupre");
-	  checkIt("Duprè", "Duprè", "Dupre", "Duprè"); // Dupre\\xcc\\x80
-	  checkIt("\u0141", "Ł", "L");
-//	  System.out.println("\u0141");
-//	  System.out.println("\u0308E");
-//	  System.out.println("\u030aA");
-//	  System.out.println("\u0301E");
-//	  System.out.println("\u030cH");
-//	  //checkIt("\u0308E", "̈E");
-//	  checkIt("Mendigutıa", "Mendigutia");
-//	  checkIt("\u030aA", "\u030aA", "A");
-//	  checkIt("\u0301E", "E");
-//	  checkIt("\u030cH", "H");
-
-  }
-
+		checkIt("Jeřábková, Tereza", "Jeřábková, Tereza", "Jerabkova, Tereza");
+		checkIt("Dupré", "Dupré", "Dupre,");
+		checkIt("Duprè", "Duprè", "Dupre,"); // Dupre\\xcc\\x80
+		checkIt("\u0141", "Ł", "L,");
+		checkIt("Mendigutıa", "Mendigutıa", "Mendigutia,");
+
+	}
+
 	private void checkIt(String input, String... expected) throws Exception {
-	  Reader reader = new StringReader(input);
-    Tokenizer tokenizer = new KeywordTokenizer();
-    tokenizer.setReader(reader);
-    AuthorTransliterationFactory factory = new AuthorTransliterationFactory(new HashMap<String,String>());
-    TokenStream stream = factory.create(new TestFilter(tokenizer));
-    assertTokenStreamContents(stream, expected);
+		Reader reader = new StringReader(input);
+		Tokenizer tokenizer = new KeywordTokenizer();
+		tokenizer.setReader(reader);
+		AuthorTransliterationFactory factory = new AuthorTransliterationFactory(new HashMap<String, String>());
+		TokenStream stream = factory.create(new TestFilter(tokenizer));
+		assertTokenStreamContents(stream, expected);
 	}
 }