+ support n-alias data files

BuildData.groovy

@@ -157,10 +157,15 @@ if (thetvdb_txt.size() < 30000) { throw new Exception('TheTVDB index sanity fail
 // BUILD anidb-index.gz
 def anidb = new net.sourceforge.filebot.web.AnidbClient(null, 0).getAnimeTitles()
 
-def anidb_index = anidb.findResults{ [it.getAnimeId(), it.getPrimaryTitle(), it.getEnglishTitle()] }
+def anidb_index = anidb.findResults{
+	def row = []
+	row += it.getAnimeId().pad(5)
+	row += it.names*.replaceAll(/\s+/, ' ')*.replaceAll(/['`´‘’ʻ]+/, /'/)*.trim().unique()
+	return row
+}
 
 // join and sort
-def anidb_txt = anidb_index.findResults{ [it[0].pad(5), it[1] ?: '', it[2] == null || it[2].equals(it[1]) ? '' : it[2]]*.replaceAll(/\s+/, ' ')*.trim().join('\t').replaceAll(/['`´‘’ʻ]+/, /'/) }.sort().unique()
+def anidb_txt = anidb_index.findResults{ row -> row.join('\t') }.sort().unique()
 pack(anidb_out, anidb_txt)
 println "AniDB Index: " + anidb_txt.size()
 

source/net/sourceforge/filebot/WebServices.java

@@ -2,9 +2,11 @@
 package net.sourceforge.filebot;
 
 
-import static java.util.Arrays.*;
+import static java.util.Arrays.asList;
-import static java.util.Collections.*;
+import static java.util.Collections.emptyList;
-import static net.sourceforge.filebot.Settings.*;
+import static net.sourceforge.filebot.Settings.getApplicationName;
+import static net.sourceforge.filebot.Settings.getApplicationProperty;
+import static net.sourceforge.filebot.Settings.getApplicationVersion;
 
 import java.io.IOException;
 import java.util.ArrayList;
@@ -142,7 +144,7 @@ public final class WebServices {
 					
 					@Override
 					protected Set<String> getFields(SearchResult object) {
-						return set(object.getName());
+						return set(object.getNames());
 					}
 				};
 				

source/net/sourceforge/filebot/media/MediaDetection.java

@@ -61,7 +61,6 @@ import net.sourceforge.filebot.similarity.SequenceMatchSimilarity;
 import net.sourceforge.filebot.similarity.SeriesNameMatcher;
 import net.sourceforge.filebot.similarity.SimilarityComparator;
 import net.sourceforge.filebot.similarity.SimilarityMetric;
-import net.sourceforge.filebot.web.AnidbSearchResult;
 import net.sourceforge.filebot.web.Date;
 import net.sourceforge.filebot.web.Episode;
 import net.sourceforge.filebot.web.Movie;
@@ -377,13 +376,11 @@ public class MediaDetection {
 	public static synchronized List<Entry<String, SearchResult>> getSeriesIndex() throws IOException {
 		if (seriesIndex.isEmpty()) {
 			try {
-				for (TheTVDBSearchResult it : releaseInfo.getTheTVDBIndex()) {
+				for (SearchResult[] index : new SearchResult[][] { releaseInfo.getTheTVDBIndex(), releaseInfo.getAnidbIndex() }) {
-					seriesIndex.add(new SimpleEntry<String, SearchResult>(normalizePunctuation(it.getName()).toLowerCase(), it));
+					for (SearchResult item : index) {
+						for (String name : item.getNames()) {
+							seriesIndex.add(new SimpleEntry<String, SearchResult>(normalizePunctuation(name).toLowerCase(), item));
 						}
-				for (AnidbSearchResult it : releaseInfo.getAnidbIndex()) {
-					seriesIndex.add(new SimpleEntry<String, SearchResult>(normalizePunctuation(it.getPrimaryTitle()).toLowerCase(), it));
-					if (it.getEnglishTitle() != null) {
-						seriesIndex.add(new SimpleEntry<String, SearchResult>(normalizePunctuation(it.getEnglishTitle()).toLowerCase(), it));
 					}
 				}
 			} catch (Exception e) {

source/net/sourceforge/filebot/media/ReleaseInfo.java

@@ -1,12 +1,15 @@
 package net.sourceforge.filebot.media;
 
+import static java.lang.Integer.parseInt;
 import static java.util.Arrays.asList;
+import static java.util.Arrays.copyOfRange;
 import static java.util.Collections.unmodifiableMap;
 import static java.util.ResourceBundle.getBundle;
 import static java.util.regex.Pattern.CASE_INSENSITIVE;
 import static java.util.regex.Pattern.UNICODE_CASE;
 import static java.util.regex.Pattern.compile;
 import static net.sourceforge.filebot.similarity.Normalization.normalizePunctuation;
+import static net.sourceforge.tuned.FileUtilities.readCSV;
 import static net.sourceforge.tuned.StringUtilities.join;
 
 import java.io.File;
@@ -26,7 +29,6 @@ import java.util.LinkedHashMap;
 import java.util.List;
 import java.util.Locale;
 import java.util.Map;
-import java.util.Scanner;
 import java.util.Set;
 import java.util.TreeMap;
 import java.util.regex.Matcher;
@@ -274,14 +276,15 @@ public class ReleaseInfo {
 
 		@Override
 		public Movie[] process(ByteBuffer data) throws IOException {
-			Scanner scanner = new Scanner(new XZInputStream(new ByteBufferInputStream(data)), "UTF-8").useDelimiter("\t|\n");
+			List<String[]> rows = readCSV(new XZInputStream(new ByteBufferInputStream(data)), "UTF-8", "\t");
+			List<Movie> movies = new ArrayList<Movie>(rows.size());
 
-			List<Movie> movies = new ArrayList<Movie>();
+			for (String[] row : rows) {
-			while (scanner.hasNext()) {
+				int imdbid = parseInt(row[0]);
-				int imdbid = scanner.nextInt();
+				int year = parseInt(row[1]);
-				String name = scanner.next().trim();
+				String name = row[2];
-				int year = scanner.nextInt();
+				String[] aliasNames = copyOfRange(row, 3, row.length);
-				movies.add(new Movie(name, year, imdbid, -1));
+				movies.add(new Movie(name, aliasNames, year, imdbid, -1));
 			}
 
 			return movies.toArray(new Movie[0]);
@@ -296,13 +299,14 @@ public class ReleaseInfo {
 
 		@Override
 		public TheTVDBSearchResult[] process(ByteBuffer data) throws IOException {
-			Scanner scanner = new Scanner(new XZInputStream(new ByteBufferInputStream(data)), "UTF-8").useDelimiter("\t|\n");
+			List<String[]> rows = readCSV(new XZInputStream(new ByteBufferInputStream(data)), "UTF-8", "\t");
+			List<TheTVDBSearchResult> tvshows = new ArrayList<TheTVDBSearchResult>(rows.size());
 
-			List<TheTVDBSearchResult> tvshows = new ArrayList<TheTVDBSearchResult>();
+			for (String[] row : rows) {
-			while (scanner.hasNext() && scanner.hasNextInt()) {
+				int id = parseInt(row[0]);
-				int id = scanner.nextInt();
+				String name = row[1];
-				String name = scanner.next().trim();
+				String[] aliasNames = copyOfRange(row, 2, row.length);
-				tvshows.add(new TheTVDBSearchResult(name, id));
+				tvshows.add(new TheTVDBSearchResult(name, aliasNames, id));
 			}
 
 			return tvshows.toArray(new TheTVDBSearchResult[0]);
@@ -317,15 +321,14 @@ public class ReleaseInfo {
 
 		@Override
 		public AnidbSearchResult[] process(ByteBuffer data) throws IOException {
-			Scanner scanner = new Scanner(new XZInputStream(new ByteBufferInputStream(data)), "UTF-8").useDelimiter("\t|\n");
+			List<String[]> rows = readCSV(new XZInputStream(new ByteBufferInputStream(data)), "UTF-8", "\t");
+			List<AnidbSearchResult> anime = new ArrayList<AnidbSearchResult>(rows.size());
 
-			List<AnidbSearchResult> anime = new ArrayList<AnidbSearchResult>();
+			for (String[] row : rows) {
-			while (scanner.hasNext() && scanner.hasNextInt()) {
+				int aid = parseInt(row[0]);
-				int aid = scanner.nextInt();
+				String primaryTitle = row[1];
-				String primaryTitle = scanner.next().trim();
+				String[] aliasNames = copyOfRange(row, 2, row.length);
-				String englishTitle = scanner.next().trim();
+				anime.add(new AnidbSearchResult(aid, primaryTitle, aliasNames));
-
-				anime.add(new AnidbSearchResult(aid, primaryTitle, englishTitle.isEmpty() ? null : englishTitle));
 			}
 
 			return anime.toArray(new AnidbSearchResult[0]);

source/net/sourceforge/filebot/web/AnidbClient.java

@@ -1,10 +1,12 @@
-
 package net.sourceforge.filebot.web;
 
-
+import static net.sourceforge.filebot.web.EpisodeUtilities.sortEpisodes;
-import static net.sourceforge.filebot.web.EpisodeUtilities.*;
+import static net.sourceforge.filebot.web.WebRequest.getDocument;
-import static net.sourceforge.filebot.web.WebRequest.*;
+import static net.sourceforge.tuned.XPathUtilities.getAttribute;
-import static net.sourceforge.tuned.XPathUtilities.*;
+import static net.sourceforge.tuned.XPathUtilities.getChild;
+import static net.sourceforge.tuned.XPathUtilities.getTextContent;
+import static net.sourceforge.tuned.XPathUtilities.selectNodes;
+import static net.sourceforge.tuned.XPathUtilities.selectString;
 
 import java.net.URI;
 import java.net.URISyntaxException;
@@ -30,7 +32,6 @@ import net.sourceforge.filebot.ResourceManager;
 import org.w3c.dom.Document;
 import org.w3c.dom.Node;
 
-
 public class AnidbClient extends AbstractEpisodeListProvider {
 
 	private static final FloodLimit REQUEST_LIMIT = new FloodLimit(5, 12, TimeUnit.SECONDS); // no more than 5 requests within a 10 second window (+2 seconds for good measure)
@@ -40,64 +41,55 @@ public class AnidbClient extends AbstractEpisodeListProvider {
 	private final String client;
 	private final int clientver;
 
-	
 	public AnidbClient(String client, int clientver) {
 		this.client = client;
 		this.clientver = clientver;
 	}
 
-	
 	@Override
 	public String getName() {
 		return "AniDB";
 	}
 
-	
 	@Override
 	public Icon getIcon() {
 		return ResourceManager.getIcon("search.anidb");
 	}
 
-	
 	@Override
 	public boolean hasSingleSeasonSupport() {
 		return false;
 	}
 
-	
 	@Override
 	public boolean hasLocaleSupport() {
 		return true;
 	}
 
-	
 	@Override
 	public ResultCache getCache() {
 		return new ResultCache(host, Cache.getCache("web-datasource-lv2"));
 	}
 
-	
 	@Override
 	public List<SearchResult> search(String query, final Locale locale) throws Exception {
 		// bypass automatic caching since search is based on locally cached data anyway
 		return fetchSearchResult(query, locale);
 	}
 
-	
 	@Override
 	public List<SearchResult> fetchSearchResult(String query, final Locale locale) throws Exception {
-		LocalSearch<AnidbSearchResult> index = new LocalSearch<AnidbSearchResult>(getAnimeTitles()) {
+		LocalSearch<SearchResult> index = new LocalSearch<SearchResult>(getAnimeTitles()) {
 
 			@Override
-			protected Set<String> getFields(AnidbSearchResult anime) {
+			protected Set<String> getFields(SearchResult it) {
-				return set(anime.getPrimaryTitle(), anime.getEnglishTitle());
+				return set(it.getNames());
 			}
 		};
 
 		return new ArrayList<SearchResult>(index.search(query));
 	}
 
-	
 	@Override
 	public List<Episode> fetchEpisodeList(SearchResult searchResult, SortOrder sortOrder, Locale language) throws Exception {
 		AnidbSearchResult anime = (AnidbSearchResult) searchResult;
@@ -152,7 +144,6 @@ public class AnidbClient extends AbstractEpisodeListProvider {
 		return episodes;
 	}
 
-	
 	@Override
 	public URI getEpisodeListLink(SearchResult searchResult) {
 		try {
@@ -162,7 +153,6 @@ public class AnidbClient extends AbstractEpisodeListProvider {
 		}
 	}
 
-	
 	public synchronized List<AnidbSearchResult> getAnimeTitles() throws Exception {
 		URL url = new URL("http", host, "/api/anime-titles.dat.gz");
 		ResultCache cache = getCache();
@@ -224,7 +214,8 @@ public class AnidbClient extends AbstractEpisodeListProvider {
 				localizedTitles.putAll(officialTitleMap.get(entry.getKey())); // primarily use official title if available
 			}
 
-			anime.add(new AnidbSearchResult(entry.getKey(), entry.getValue(), localizedTitles.get("en")));
+			String englishTitle = localizedTitles.get("en"); // ONLY SUPPORT ENGLISH LOCALIZATION
+			anime.add(new AnidbSearchResult(entry.getKey(), entry.getValue(), englishTitle == null || englishTitle.isEmpty() ? new String[] {} : new String[] { englishTitle }));
 		}
 
 		// populate cache

source/net/sourceforge/filebot/web/AnidbSearchResult.java

@@ -8,8 +8,8 @@ public class AnidbSearchResult extends SearchResult {
 		// used by serializer
 	}
 
-	public AnidbSearchResult(int aid, String primaryTitle, String englishTitle) {
+	public AnidbSearchResult(int aid, String primaryTitle, String[] localizedTitles) {
-		super(primaryTitle, englishTitle);
+		super(primaryTitle, localizedTitles);
 		this.aid = aid;
 	}
 
@@ -30,10 +30,6 @@ public class AnidbSearchResult extends SearchResult {
 		return name;
 	}
 
-	public String getEnglishTitle() {
-		return aliasNames.length > 0 ? aliasNames[0] : null;
-	}
-
 	@Override
 	public int hashCode() {
 		return aid;

source/net/sourceforge/filebot/web/LocalSearch.java

@@ -1,9 +1,8 @@
-
 package net.sourceforge.filebot.web;
 
-
+import static java.util.Collections.singleton;
-import static java.util.Collections.*;
+import static java.util.Collections.sort;
-import static net.sourceforge.filebot.similarity.Normalization.*;
+import static net.sourceforge.filebot.similarity.Normalization.normalizePunctuation;
 
 import java.util.AbstractList;
 import java.util.AbstractMap.SimpleEntry;
@@ -25,7 +24,6 @@ import uk.ac.shef.wit.simmetrics.similaritymetrics.QGramsDistance;
 
 import com.ibm.icu.text.Transliterator;
 
-
 public class LocalSearch<T> {
 
 	private final AbstractStringMetric metric = new QGramsDistance();
@@ -37,7 +35,6 @@ public class LocalSearch<T> {
 	private final List<T> objects;
 	private final List<Set<String>> fields;
 
-	
 	public LocalSearch(Collection<? extends T> data) {
 		objects = new ArrayList<T>(data);
 		fields = new ArrayList<Set<String>>(objects.size());
@@ -47,7 +44,6 @@ public class LocalSearch<T> {
 		}
 	}
 
-	
 	public List<T> search(String query) throws ExecutionException, InterruptedException {
 		final String q = normalize(query);
 		List<Callable<Entry<T, Float>>> tasks = new ArrayList<Callable<Entry<T, Float>>>(objects.size());
@@ -105,7 +101,6 @@ public class LocalSearch<T> {
 				return resultSet.get(index).getKey();
 			}
 
-			
 			@Override
 			public int size() {
 				return Math.min(resultSetSize, resultSet.size());
@@ -113,24 +108,20 @@ public class LocalSearch<T> {
 		};
 	}
 
-	
 	public void setResultMinimumSimilarity(float resultMinimumSimilarity) {
 		this.resultMinimumSimilarity = resultMinimumSimilarity;
 	}
 
-	
 	public void setResultSetSize(int resultSetSize) {
 		this.resultSetSize = resultSetSize;
 	}
 
-	
 	protected Set<String> getFields(T object) {
-		return set(object.toString());
+		return set(singleton(object.toString()));
 	}
 
-	
+	protected Set<String> set(Collection<String> values) {
-	protected Set<String> set(String... values) {
+		Set<String> set = new HashSet<String>(values.size());
-		Set<String> set = new HashSet<String>(values.length);
 		for (String value : values) {
 			if (value != null) {
 				set.add(normalize(value));
@@ -139,7 +130,6 @@ public class LocalSearch<T> {
 		return set;
 	}
 
-	
 	protected String normalize(String value) {
 		// normalize separator, normalize case and trim
 		return normalizePunctuation(transliterator.transform(value)).toLowerCase();

source/net/sourceforge/filebot/web/SearchResult.java

@@ -1,6 +1,8 @@
 package net.sourceforge.filebot.web;
 
 import java.io.Serializable;
+import java.util.AbstractList;
+import java.util.List;
 
 public abstract class SearchResult implements Serializable {
 
@@ -24,6 +26,21 @@ public abstract class SearchResult implements Serializable {
 		return aliasNames.clone();
 	}
 
+	public List<String> getNames() {
+		return new AbstractList<String>() {
+
+			@Override
+			public String get(int index) {
+				return index == 0 ? name : aliasNames[index - 1];
+			}
+
+			@Override
+			public int size() {
+				return 1 + aliasNames.length;
+			}
+		};
+	}
+
 	@Override
 	public String toString() {
 		return name;

source/net/sourceforge/filebot/web/SerienjunkiesClient.java

@@ -1,15 +1,15 @@
-
 package net.sourceforge.filebot.web;
 
-
+import static net.sourceforge.filebot.web.EpisodeUtilities.sortEpisodes;
-import static net.sourceforge.filebot.web.EpisodeUtilities.*;
+import static net.sourceforge.filebot.web.WebRequest.createIgnoreCertificateSocketFactory;
-import static net.sourceforge.filebot.web.WebRequest.*;
+import static net.sourceforge.filebot.web.WebRequest.getReader;
 
 import java.io.IOException;
 import java.io.Reader;
 import java.net.URI;
 import java.net.URL;
 import java.util.ArrayList;
+import java.util.LinkedHashSet;
 import java.util.List;
 import java.util.Locale;
 import java.util.Set;
@@ -24,64 +24,55 @@ import org.json.simple.JSONArray;
 import org.json.simple.JSONObject;
 import org.json.simple.JSONValue;
 
-
 public class SerienjunkiesClient extends AbstractEpisodeListProvider {
 
 	private final String host = "api.serienjunkies.de";
 
 	private final String apikey;
 
-	
 	public SerienjunkiesClient(String apikey) {
 		this.apikey = apikey;
 	}
 
-	
 	@Override
 	public String getName() {
 		return "Serienjunkies";
 	}
 
-	
 	@Override
 	public Icon getIcon() {
 		return ResourceManager.getIcon("search.serienjunkies");
 	}
 
-	
 	@Override
 	public Locale getDefaultLocale() {
 		return Locale.GERMAN;
 	}
 
-	
 	@Override
 	public ResultCache getCache() {
 		return new ResultCache(host, Cache.getCache("web-datasource"));
 	}
 
-	
 	@Override
 	public List<SearchResult> search(String query, final Locale locale) throws Exception {
 		// bypass automatic caching since search is based on locally cached data anyway
 		return fetchSearchResult(query, locale);
 	}
 
-	
 	@Override
 	public List<SearchResult> fetchSearchResult(String query, Locale locale) throws Exception {
-		LocalSearch<SerienjunkiesSearchResult> index = new LocalSearch<SerienjunkiesSearchResult>(getSeriesTitles()) {
+		LocalSearch<SearchResult> index = new LocalSearch<SearchResult>(getSeriesTitles()) {
 
 			@Override
-			protected Set<String> getFields(SerienjunkiesSearchResult series) {
+			protected Set<String> getFields(SearchResult series) {
-				return set(series.getMainTitle(), series.getGermanTitle());
+				return set(series.getNames());
 			}
 		};
 
 		return new ArrayList<SearchResult>(index.search(query));
 	}
 
-	
 	protected synchronized List<SerienjunkiesSearchResult> getSeriesTitles() throws IOException {
 		ResultCache cache = getCache();
 
@@ -106,14 +97,22 @@ public class SerienjunkiesClient extends AbstractEpisodeListProvider {
 			String germanTitle = (String) obj.get("short_german");
 			Date startDate = Date.parse((String) obj.get("firstepisode"), "yyyy-MM-dd");
 
-			seriesList.add(new SerienjunkiesSearchResult(sid, link, mainTitle, germanTitle != null && !germanTitle.isEmpty() ? germanTitle : null, startDate));
+			Set<String> titleSet = new LinkedHashSet<String>(2);
+			for (String title : new String[] { germanTitle, mainTitle }) {
+				if (title != null && title.length() > 0) {
+					titleSet.add(title);
+				}
+			}
+			if (titleSet.size() > 0) {
+				List<String> titleList = new ArrayList<String>(titleSet);
+				seriesList.add(new SerienjunkiesSearchResult(sid, link, titleList.get(0), titleList.subList(1, titleList.size()).toArray(new String[0]), startDate));
+			}
 		}
 
 		// populate cache
 		return cache.putSearchResult(null, Locale.ROOT, seriesList);
 	}
 
-	
 	@Override
 	public List<Episode> fetchEpisodeList(SearchResult searchResult, SortOrder sortOrder, Locale locale) throws IOException {
 		SerienjunkiesSearchResult series = (SerienjunkiesSearchResult) searchResult;
@@ -121,7 +120,7 @@ public class SerienjunkiesClient extends AbstractEpisodeListProvider {
 		// fetch episode data
 		List<Episode> episodes = new ArrayList<Episode>(25);
 
-		String seriesName = locale.equals(Locale.GERMAN) && series.getGermanTitle() != null ? series.getGermanTitle() : series.getMainTitle();
+		String seriesName = series.getName();
 		JSONObject data = (JSONObject) request("/allepisodes.php?d=" + apikey + "&q=" + series.getSeriesId());
 		JSONArray list = (JSONArray) data.get("allepisodes");
 
@@ -152,7 +151,6 @@ public class SerienjunkiesClient extends AbstractEpisodeListProvider {
 		return episodes;
 	}
 
-	
 	protected Object request(String resource) throws IOException {
 		URL url = new URL("https", host, resource);
 		HttpsURLConnection connection = (HttpsURLConnection) url.openConnection();
@@ -169,7 +167,6 @@ public class SerienjunkiesClient extends AbstractEpisodeListProvider {
 		}
 	}
 
-	
 	@Override
 	public URI getEpisodeListLink(SearchResult searchResult) {
 		return URI.create(String.format("http://www.serienjunkies.de/%s/alle-serien-staffeln.html", ((SerienjunkiesSearchResult) searchResult).getLink()));

source/net/sourceforge/filebot/web/SerienjunkiesSearchResult.java

@@ -1,72 +1,43 @@
-
 package net.sourceforge.filebot.web;
 
-
 public class SerienjunkiesSearchResult extends SearchResult {
 
 	protected int sid;
 	protected String link;
-	protected String mainTitle;
-	protected String germanTitle;
 	protected Date startDate;
 
-	
 	protected SerienjunkiesSearchResult() {
 		// used by serializer
 	}
 
-	
+	public SerienjunkiesSearchResult(int sid, String link, String germanTitle, String[] otherTitles, Date startDate) {
-	public SerienjunkiesSearchResult(int sid, String link, String mainTitle, String germanTitle, Date startDate) {
+		super(germanTitle, otherTitles);
 		this.sid = sid;
 		this.link = link;
-		this.mainTitle = mainTitle;
-		this.germanTitle = germanTitle;
 		this.startDate = startDate;
 	}
 
-	
 	public int getId() {
 		return sid;
 	}
 
-	
-	@Override
-	public String getName() {
-		return germanTitle != null ? germanTitle : mainTitle; // prefer German title
-	}
-	
-	
 	public int getSeriesId() {
 		return sid;
 	}
 
-	
 	public String getLink() {
 		return link;
 	}
 
-	
-	public String getMainTitle() {
-		return mainTitle;
-	}
-	
-	
-	public String getGermanTitle() {
-		return germanTitle;
-	}
-	
-	
 	public Date getStartDate() {
 		return startDate;
 	}
 
-	
 	@Override
 	public int hashCode() {
 		return sid;
 	}
 
-	
 	@Override
 	public boolean equals(Object object) {
 		if (object instanceof SerienjunkiesSearchResult) {

source/net/sourceforge/tuned/FileUtilities.java

@@ -21,6 +21,7 @@ import java.util.Iterator;
 import java.util.LinkedList;
 import java.util.List;
 import java.util.Map;
+import java.util.Scanner;
 import java.util.SortedMap;
 import java.util.TreeMap;
 import java.util.regex.Matcher;
@@ -160,6 +161,18 @@ public final class FileUtilities {
 		}
 	}
 
+	public static List<String[]> readCSV(InputStream source, String charsetName, String separatorPattern) {
+		Scanner scanner = new Scanner(source, charsetName);
+		Pattern separator = Pattern.compile(separatorPattern);
+		List<String[]> rows = new ArrayList<String[]>(65536);
+
+		while (scanner.hasNextLine()) {
+			rows.add(separator.split(scanner.nextLine()));
+		}
+
+		return rows;
+	}
+
 	public static Reader createTextReader(File file) throws IOException {
 		CharsetDetector detector = new CharsetDetector();
 		detector.setDeclaredEncoding("UTF-8"); // small boost for UTF-8 as default encoding