fix(ENGKNOW-2733): Fail GOR if file schema is not found.

gortools/src/main/java/org/gorpipe/gor/manager/BucketManager.java

@@ -42,6 +42,7 @@
 import org.slf4j.LoggerFactory;
 
 import java.io.IOException;
+import java.nio.file.Path;
 import java.time.Duration;
 import java.util.*;
 import java.util.function.Function;
@@ -456,7 +457,7 @@ private int doBucketize(TableLock bucketizeLock, BucketPackLevel packLevel, int
     private void doBucketizeForBucketDir(DictionaryTable tempTable, String bucketDir, Map<String, List<T>> newBucketsMap, int maxBucketCount) throws IOException {
         Map<String, List<T>> newBucketsMapForBucketDir =
                 newBucketsMap.keySet().stream()
-                        .filter(p -> PathUtils.getParent(p).equals(PathUtils.stripTrailingSlash(bucketDir)))
+                        .filter(p -> PathUtils.pathEquals(PathUtils.getParent(p), bucketDir))
                         .collect(Collectors.toMap(Function.identity(), newBucketsMap::get));
 
         //  Create the bucket files

gortools/src/test/java/org/gorpipe/gor/manager/UTestBucketManager.java

@@ -665,7 +665,7 @@ public void testBucketFolders() throws Exception {
             buckets = table.filter().get().stream().map(l -> l.getBucket()).distinct().collect(Collectors.toList());
             List<String> bucketFolders = buckets.stream().map(l -> PathUtils.getParent(l)).distinct().collect(Collectors.toList());
             Assert.assertEquals("Incorrect number of bucket folders", 1, bucketFolders.size());
-            Assert.assertEquals("Incorrect bucket folder(s)", buc.pickBucketDir(), bucketFolders.get(0));
+            Assert.assertEquals("Incorrect bucket folder(s)", Path.of(buc.pickBucketDir()), Path.of(bucketFolders.get(0)));
             for (String bucket : buckets) {
                 Assert.assertTrue("Bucket does not exists", Files.exists(Path.of(PathUtils.resolve(table.getRootPath(), bucket))));
             }
@@ -839,7 +839,9 @@ private void testBucketDirsHelper(BucketManager buc, GorDictionaryTable table, L
         buckets = table.filter().get().stream().map(l -> l.getBucket()).distinct().collect(Collectors.toList());
         List<String> createdBucketFolders = buckets.stream().map(p -> PathUtils.getParent(p)).distinct().collect(Collectors.toList());
         Assert.assertEquals("Incorrect number of bucket folders", bucketDirs.size(), createdBucketFolders.size());
-        Assert.assertEquals("Incorrect bucket folder(s)", new TreeSet(bucketDirs), new TreeSet(createdBucketFolders));
+        Assert.assertEquals("Incorrect bucket folder(s)",
+                new TreeSet(bucketDirs.stream().map(s -> Path.of(s)).toList()),
+                new TreeSet(createdBucketFolders.stream().map(s -> Path.of(s)).toList()));
         for (String bucket : buckets) {
             Assert.assertTrue(String.format("Bucket %s does not exists", PathUtils.resolve(table.getRootPath(), bucket)),
                     Files.exists(Path.of(PathUtils.resolve(table.getRootPath(), bucket))));

model/src/main/java/org/gorpipe/gor/driver/providers/stream/sources/file/FileSourceType.java

@@ -40,9 +40,6 @@ public PRIORITY getPriority() {
     @Override
     public boolean match(String file) {
         // TODO: Until we get better matching strategy we must exclude mem here.
-        // TODO: Should check if file (as commented out), but a lot code seems to pass various
-        //       non file elements so simply match everything (like the former impl).
-        //       We should be the last matcher anyway.
-        return !DataUtil.isMem(file); //&& (file.startsWith("file:") || !file.contains(":"));
+        return !DataUtil.isMem(file) && (file.startsWith("file:") || !file.contains(":/"));
     }
 }

model/src/main/java/org/gorpipe/gor/table/util/PathUtils.java

@@ -261,7 +261,7 @@ public static URI toRealPath(URI uri) {
     public static String getParent(String path) {
         String p = stripTrailingSlash(path);
         var idx = p.lastIndexOf("/");
-        return idx >= 0 ? p.substring(0,idx) : "";
+        return idx >= 0 ? p.substring(0,idx+1) : "";
     }
 
     public static String getFileName(String path) {
@@ -343,4 +343,14 @@ public static Path getTempFilePath(Path filePath) {
         return tempFileName;
     }
 
+    public static boolean pathEquals(String path1, String path2) {
+        if (path1 == null && path2 == null) {
+            return true;
+        }
+        if (path1 == null || path2 == null) {
+            return false;
+        }
+        return Path.of(path1).normalize().equals(Path.of(path2).normalize());
+    }
+
 }

model/src/test/java/org/gorpipe/gor/driver/UTestPluggableGorDriver.java

@@ -23,8 +23,10 @@
 package org.gorpipe.gor.driver;
 
 import gorsat.TestUtils;
+import org.gorpipe.exceptions.GorResourceException;
 import org.gorpipe.gor.driver.meta.DataType;
 import org.gorpipe.gor.driver.meta.SourceReference;
+import org.gorpipe.gor.driver.providers.stream.sources.file.FileSource;
 import org.gorpipe.gor.model.GenomicIterator;
 import org.junit.Assert;
 import org.junit.Test;
@@ -64,4 +66,35 @@ public void noGuice() throws IOException {
         Assert.assertNotNull(iterator);
     }
 
+    @Test
+    public void testResolveDataSourceFile() throws IOException {
+        String fileName = "testfile.gor";
+        DataSource source = gorDriver.resolveDataSource(new SourceReference(fileName));
+        Assert.assertTrue(source instanceof FileSource);
+        Assert.assertEquals(fileName, source.getName());
+    }
+
+    @Test
+    public void testResolveDataSourceFileSchema() throws IOException {
+        String fileName = "testfile.gor";
+        DataSource source = gorDriver.resolveDataSource(new SourceReference("file://" + fileName));
+        Assert.assertTrue(source instanceof FileSource);
+        Assert.assertEquals(fileName, source.getName());
+    }
+
+    @Test
+    public void testResolveDataSourceS3Schema() throws IOException {
+        String fileName = "s3://testfile.gor";
+        DataSource source = gorDriver.resolveDataSource(new SourceReference(fileName));
+        Assert.assertEquals(fileName, source.getName());
+    }
+
+    @Test
+    public void testResolveDataSourceUnknownSchema() throws IOException {
+        String fileName = "bla://testfile" + DataType.GOR.suffix;
+        Assert.assertThrows(GorResourceException.class, () -> {
+            gorDriver.resolveDataSource(new SourceReference(fileName));
+        });
+    }
+
 }