Added speaking (and unambigues) filenames.

We use a transformed version of the title field plus the URI plus
a content type specific extension. To remove the URI from the file name
we would need to extract the filename policy and keep track of file
names we already used to avoid duplicates.

git-svn-id: https://develop.sub.uni-goettingen.de/repos/textgrid/trunk/services/aggregator@14101 7c539038-3410-0410-b1ec-0f2a7bf1c452

pom.xml

@@ -149,6 +149,11 @@
                         <artifactId>servlet-api</artifactId>
                         <version>2.5</version>
                 </dependency>
+                <dependency>
+                	<groupId>com.ibm.icu</groupId>
+                	<artifactId>icu4j</artifactId>
+                	<version>51.1</version>
+                </dependency>
         </dependencies>
 
 

src/main/java/info/textgrid/services/aggregator/tree/AggregationEntry.java

@@ -53,9 +53,13 @@ public ObjectType getMetadata() {
 	 *            whether to append a content type specific extension.
 	 */
 	protected String getSimpleFileName(final boolean withExtension) {
-		final String baseName = URI.create(
-				getMetadata().getGeneric().getGenerated().getTextgridUri()
-						.getValue()).getSchemeSpecificPart();
+		final String baseName = 
+				FilenamePolicy.getTransliterator().transliterate(
+						getMetadata().getGeneric().getProvided().getTitle().get(0))
+				.concat(".")
+				.concat(URI.create(
+						getMetadata().getGeneric().getGenerated().getTextgridUri()
+						.getValue()).getSchemeSpecificPart());
 		if (withExtension)
 			return FileExtensionMap.getInstance().addExtension(baseName,
 					getFormat());

src/main/java/info/textgrid/services/aggregator/tree/FilenamePolicy.java

+package info.textgrid.services.aggregator.tree;
+
+import com.ibm.icu.text.Transliterator;
+
+public class FilenamePolicy {
+	
+	private static String TRANSFORM_RULES = "::Any-Latin;\n" + 
+			"{ Ä } [:LowercaseLetter:] > Ae;\n" + 
+			"Ä > AE;\n" + 
+			"{ Ö } [:LowercaseLetter:] > Oe;\n" + 
+			"Ö > OE;\n" + 
+			"{ Ü } [:LowercaseLetter:] > Ue;\n" + 
+			"Ü > UE;\n" + 
+			"ä > ae;\n" + 
+			"ö > oe;\n" + 
+			"ü > ue;\n" + 
+			"ſ > s;\n" + 
+			"ß > ss;\n" + 
+			"::Latin-ASCII;\n" + 
+			"[^A-Za-z0-9.,;!\\_\\n\\r-]+ > \\_";
+	
+	private static Transliterator transliterator;
+	
+	public static Transliterator getTransliterator() {
+		if (transliterator == null)
+			transliterator = Transliterator.createFromRules("TgFilenames", TRANSFORM_RULES, Transliterator.FORWARD);
+		return transliterator;
+	}
+	
+	
+}