Completed example showing how to find duplicate files

Author: cboehme

main/resources/example/filter-duplicates.xml

@@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<metamorph xmlns="http://www.culturegraph.org/metamorph"
+	version="1" entityMarker=".">
+	<meta>
+		<name>Filter out records which contain only one hash</name>
+	</meta>
+	
+	<rules>
+		<data source="SHA1" name="MATCH">
+			<occurrence  only="moreThen 1" />
+		</data>
+	</rules>
+</metamorph>

main/resources/example/find-duplicate-files.flux

@@ -0,0 +1,11 @@
+default in = ".";
+
+in
+|walk-filetree
+|digest-file("sha1")
+|sort-triples(by="OBJECT")
+|reorder-triple(subjectFrom="object", objectFrom="subject")
+|collect-triples
+|filter(FLUX_DIR + "filter-duplicates.xml")
+|encode-formeta(style="multiline")
+|write("stdout");