[GitHub] [jena] kinow commented on a change in pull request #871: JENA-2003: Handle file URIs with URI scheme name

[GitBox <gi...@apache.org>]

kinow commented on a change in pull request #871:
URL: https://github.com/apache/jena/pull/871#discussion_r530282869



##########
File path: jena-base/src/main/java/org/apache/jena/atlas/io/IO.java
##########
@@ -85,24 +88,75 @@ static public InputStream openFileEx(String filename) throws IOException, FileNo
             filename = IRILib.decodeHex(filename);
         }
         InputStream in = new FileInputStream(filename);
-        String ext = FilenameUtils.getExtension(filename);
+        String ext = getExtension(filename);
         switch ( ext ) {
             case "":        return in;
-            case "gz":      return new GZIPInputStream(in);
-            case "bz2":     return new BZip2CompressorInputStream(in);
-            case "sz":      return new SnappyCompressorInputStream(in);
+            case ext_gz:    return new GZIPInputStream(in);
+            case ext_bz2:   return new BZip2CompressorInputStream(in);
+            case ext_sz:    return new SnappyCompressorInputStream(in);
         }
         return in;
     }
 
-    private static String[] extensions = { "gz", "bz2", "sz" };
+    // ---- Extracted from Apache CommonsIO : FilenameUtils (2.8.0) because of the drive letter handling.
+    private static final int NOT_FOUND = -1;
+    private static final String EMPTY_STRING = "";
+    private static final String EXTENSION_SEPARATOR = ".";
+    private static final char UNIX_SEPARATOR = '/';
+    private static final char WINDOWS_SEPARATOR = '\\';
+
+    private static int indexOfLastSeparator(final String fileName) {
+        if (fileName == null) {
+            return NOT_FOUND;
+        }
+        final int lastUnixPos = fileName.lastIndexOf(UNIX_SEPARATOR);
+        final int lastWindowsPos = fileName.lastIndexOf(WINDOWS_SEPARATOR);
+        return Math.max(lastUnixPos, lastWindowsPos);
+    }
 
-    /** The filename without any compression extension, or the original filename.
-     *  It tests for compression types handled by {@link #openFileEx}.
+    private static int indexOfExtension(final String fileName) throws IllegalArgumentException {
+        if (fileName == null) {
+            return NOT_FOUND;
+        }
+//        if (isSystemWindows()) {
+//            // Special handling for NTFS ADS: Don't accept colon in the fileName.
+//            final int offset = fileName.indexOf(':', getAdsCriticalOffset(fileName));
+//            if (offset != -1) {
+//                throw new IllegalArgumentException("NTFS ADS separator (':') in file name is forbidden.");
+//            }
+//        }

Review comment:
       :+1: 




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: pr-unsubscribe@jena.apache.org
For additional commands, e-mail: pr-help@jena.apache.org