* extract only archives that contain at least one video file

source/net/sourceforge/filebot/archive/Archive.java

@@ -95,6 +95,27 @@ public class Archive implements Closeable {
 	}
 	
 	
+	public void extract(ExtractOutProvider outputMapper, FileFilter filter) throws SevenZipException {
+		List<Integer> selection = new ArrayList<Integer>();
+		
+		for (int i = 0; i < inArchive.getNumberOfItems(); i++) {
+			boolean isFolder = (Boolean) inArchive.getProperty(i, PropID.IS_FOLDER);
+			if (!isFolder) {
+				String path = (String) inArchive.getProperty(i, PropID.PATH);
+				if (path != null && filter.accept(new File(path))) {
+					selection.add(i);
+				}
+			}
+		}
+		
+		int[] indices = new int[selection.size()];
+		for (int i = 0; i < indices.length; i++) {
+			indices[i] = selection.get(i);
+		}
+		inArchive.extract(indices, false, new ExtractCallback(inArchive, outputMapper));
+	}
+	
+	
 	@Override
 	public void close() throws IOException {
 		try {
@@ -121,7 +142,6 @@ public class Archive implements Closeable {
 		return extensions;
 	}
 	
-	
 	public static final FileFilter VOLUME_ONE_FILTER = new FileFilter() {
 		
 		private Pattern volume = Pattern.compile("[.]r[0-9]+$|[.]part[0-9]+|[.][0-9]+$", Pattern.CASE_INSENSITIVE);

source/net/sourceforge/filebot/cli/ArgumentProcessor.java

@@ -79,7 +79,7 @@ public class ArgumentProcessor {
 				Collection<File> files = new LinkedHashSet<File>(args.getFiles(true));
 				
 				if (args.extract) {
-					files.addAll(cli.extract(files, args.output, args.conflict));
+					files.addAll(cli.extract(files, args.output, args.conflict, null, true));
 				}
 				
 				if (args.getSubtitles) {

source/net/sourceforge/filebot/cli/CmdlineInterface.java

@@ -3,6 +3,7 @@ package net.sourceforge.filebot.cli;
 
 
 import java.io.File;
+import java.io.FileFilter;
 import java.util.Collection;
 import java.util.List;
 
@@ -32,6 +33,6 @@ public interface CmdlineInterface {
 	String getMediaInfo(File file, String format) throws Exception;
 	
 	
-	List<File> extract(Collection<File> files, String output, String conflict) throws Exception;
+	List<File> extract(Collection<File> files, String output, String conflict, FileFilter filter, boolean forceExtractAll) throws Exception;
 	
 }

source/net/sourceforge/filebot/cli/CmdlineOperations.java

@@ -980,7 +980,7 @@ public class CmdlineOperations implements CmdlineInterface {
 	
 	
 	@Override
-	public List<File> extract(Collection<File> files, String output, String conflict) throws Exception {
+	public List<File> extract(Collection<File> files, String output, String conflict, FileFilter filter, boolean forceExtractAll) throws Exception {
 		ConflictAction conflictAction = ConflictAction.forName(conflict);
 		
 		// only keep single-volume archives or first part of multi-volume archives
@@ -995,22 +995,51 @@ public class CmdlineOperations implements CmdlineInterface {
 					outputFolder = new File(file.getParentFile(), outputFolder.getPath());
 				}
 				
-				CLILogger.info(String.format("Extract archive [%s] to [%s]", file.getName(), outputFolder));
+				CLILogger.info(String.format("Read archive [%s] to [%s]", file.getName(), outputFolder));
 				FileMapper outputMapper = new FileMapper(outputFolder, false);
 				
-				List<File> entries = archive.listFiles();
+				final List<File> outputMapping = new ArrayList<File>();
+				for (File entry : archive.listFiles()) {
+					outputMapping.add(outputMapper.getOutputFile(entry));
+				}
+				
+				final Set<File> selection = new TreeSet<File>();
+				for (File future : outputMapping) {
+					if (filter == null || filter.accept(future)) {
+						selection.add(future);
+					}
+				}
+				
+				// check if there is anything to extract at all
+				if (selection.isEmpty()) {
+					continue;
+				}
+				
 				boolean skip = true;
-				for (File entry : entries) {
-					File outputFile = outputMapper.getOutputFile(entry);
-					skip &= outputFile.exists();
-					extractedFiles.add(outputFile);
+				for (File future : filter == null || forceExtractAll ? outputMapping : selection) {
+					skip &= future.exists();
 				}
 				
 				if (!skip || conflictAction == ConflictAction.OVERRIDE) {
-					CLILogger.finest("Extracting files " + entries);
-					archive.extract(outputMapper);
+					if (filter == null || forceExtractAll) {
+						CLILogger.finest("Extracting files " + outputMapping);
+						// extract all files
+						archive.extract(outputMapper);
+						extractedFiles.addAll(outputMapping);
+					} else {
+						CLILogger.finest("Extracting files " + selection);
+						// extract files selected by the given filter
+						archive.extract(outputMapper, new FileFilter() {
+							
+							@Override
+							public boolean accept(File entry) {
+								return selection.contains(entry);
+							}
+						});
+						extractedFiles.addAll(selection);
+					}
 				} else {
-					CLILogger.finest("Skipped extracting files " + entries);
+					CLILogger.finest("Skipped extracting files " + selection);
 				}
 			} finally {
 				archive.close();
@@ -1019,5 +1048,4 @@ public class CmdlineOperations implements CmdlineInterface {
 		
 		return extractedFiles;
 	}
-	
 }

source/net/sourceforge/filebot/cli/ScriptShell.lib.groovy

@@ -264,7 +264,7 @@ def compute(args) { args = _defaults(args)
 
 def extract(args) { args = _defaults(args)
 	synchronized (_cli) {
-		_guarded { _cli.extract(_files(args), args.output as String, args.conflict as String) }
+		_guarded { _cli.extract(_files(args), args.output as String, args.conflict as String, args.filter instanceof Closure ? args.filter as FileFilter : null, args.forceExtractAll != null ? args.forceExtractAll : false) }
 	}
 }
 
@@ -319,17 +319,10 @@ def _renameFunction(fn) {
  * Fill in default values from cmdline arguments
  */
 def _defaults(args) {
-		args.action      = args.action     ?: _args.action
-		args.conflict    = args.conflict   ?: _args.conflict
-		args.query       = args.query      ?: _args.query
-		args.filter      = args.filter     ?: _args.filter
-		args.format      = args.format     ?: _args.format
-		args.db          = args.db         ?: _args.db
-		args.order       = args.order      ?: _args.order
-		args.lang        = args.lang       ?: _args.lang
-		args.output      = args.output     ?: _args.output
-		args.encoding    = args.encoding   ?: _args.encoding
-		args.strict      = args.strict     != null ? args.strict : !_args.nonStrict
+		['action', 'conflict', 'query', 'filter', 'format', 'db', 'order', 'lang', 'output', 'encoding'].each{ k ->
+				args[k] = args.containsKey(k) ? args[k] : _args[k]
+		}
+		args.strict = args.strict != null ? args.strict : !_args.nonStrict // invert strict/non-strict
 		return args
 }
 

website/scripts/utorrent-postprocess.groovy

@@ -47,11 +47,12 @@ if (args.empty) {
 	input += args.getFiles()
 }
 
-// extract archives if necessary
-input += extract(file:input, output:".", conflict:"override")
+
+// extract archives (zip, rar, etc) that contain at least one video file
+input += extract(file: input.findAll{ it.isArchive() }, output: null, conflict: 'override', filter: { it.isVideo() }, forceExtractAll: true)
 
 // process only media files
-input = input.findAll{ it.isVideo() || it.isSubtitle() }
+input = input.unique().findAll{ it.isVideo() || it.isSubtitle() }
 
 // ignore clutter files
 input = input.findAll{ !(it.path =~ /\b(?i:sample|trailer|extras|deleted.scenes|music.video|scrapbook)\b/) }