michalbcz · November 11, 2022 09:14 · Nov 11, 2022
diff --git a/delete_duplicated.groovy b/delete_duplicated.groovy
@@ -0,0 +1,47 @@
+/*
+  Delete duplicated files
+  
+  Naive implementation which consider duplicated files as files with same file size in bytes.
+ 
+  Note: this implementation delete *.jpg files but you can easily change it with another regexp. See line 17.
+*/
+
+import groovy.io.*
+
+def dir = new File(/your directory with duplicated files/)
+
+def filesOfSameSize = [:]
+
+println "Start processing files..."
+dir.eachFileRecurse(FileType.FILES, { 
+  if (it.name ==~ /.*\.jpg/) /* when you want delete just duplicated jpg files, change it on your will */ {
+      def fileSizeInBytes = it.size()
+      def fileSizeInMb = Math.round( fileSizeInBytes / (1024 * 1024 /* MBs */) * 1000) / 1000
+      println "${it} (${fileSizeInMb} MB)" 
+      if (filesOfSameSize.containsKey(fileSizeInBytes)) {
+          filesOfSameSize[fileSizeInBytes] << it
+      } else {
+          filesOfSameSize[fileSizeInBytes] = []
+          filesOfSameSize[fileSizeInBytes] << it
+      }
+
+  }
+})
+
+println ""
+println "Looking for duplicates..."
+
+filesOfSameSize.each { size, files ->
+    if (files.size() > 1) {
+       files.sort({a, b -> a.name.size() <=> b.name.size()}) // the shortest name is always first 
+
+       // leave file with the shortest name and delete others
+       files[1..-1].each { it -> 
+           println "Deleting duplicate ${it}" 
+           it.delete() 
+
+          // or if you are on Windows and has Java 9 you can use https://docs.oracle.com/javase/9/docs/api/java/awt/Desktop.html#moveToTrash-java.io.File-
+          //java.awt.Desktop.getDesktop().moveToTrash(it)
+       } 
+    }
+}
No results found