RussellSpitzer commented on code in PR #11294:
URL: https://github.com/apache/iceberg/pull/11294#discussion_r1795984898
##########
azure/src/main/java/org/apache/iceberg/azure/adlsv2/ADLSLocation.java:
##########
@@ -18,24 +18,34 @@
*/
package org.apache.iceberg.azure.adlsv2;
+import java.net.URI;
+import java.net.URISyntaxException;
import java.util.Optional;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.iceberg.exceptions.ValidationException;
import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
/**
- * This class represents a fully qualified location in Azure expressed as a
URI.
+ * This class represents a fully qualified location in Azure Data Lake
Storage, expressed as a URI.
*
* <p>Locations follow the conventions used by Hadoop's Azure support, i.e.
*
- * <pre>{@code abfs[s]://[<container>@]<storage account host>/<file
path>}</pre>
+ * <pre>{@code
abfs[s]://[<container>@]<storageAccount>.dfs.core.windows.net/<path>}</pre>
*
- * <p>See <a
href="https://hadoop.apache.org/docs/stable/hadoop-azure/abfs.html";>Hadoop Azure
- * Support</a>
+ * or
+ *
+ * <pre>{@code
wasb[s]://<container>@<storageAccount>.blob.core.windows.net/<path>}</pre>
+ *
+ * For compatibility, paths using the wasb scheme are also accepted but will
be processed via the
+ * Azure Data Lake Storage Gen2 APIs and not the Blob Storage APIs.
+ *
+ * <p>See <a
+ *
href="https://learn.microsoft.com/en-us/azure/storage/blobs/data-lake-storage-introduction-abfs-uri#uri-syntax";>Hadoop
+ * Azure Support</a>
*/
class ADLSLocation {
- private static final Pattern URI_PATTERN =
Pattern.compile("^abfss?://([^/?#]+)(.*)?$");
+ private static final Pattern URI_PATTERN =
Pattern.compile("^(abfss?|wasbs?)://([^/?#]+)(.*)?$");
Review Comment:
We aren't using the capture groups any more? Should we remove them from the
regex?
--
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.
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
