HDFS-16503. Should verify whether the path name is valid in the WebHDFS (#4067). Contributed by tomscut.

Signed-off-by: Ayush Saxena <ayushsaxena@apache.org>

hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/web/WebHdfsFileSystem.java

@@ -478,7 +478,8 @@ private Path makeAbsolute(Path f) {
     return f.isAbsolute()? f: new Path(workingDir, f);
   }
 
-  static Map<?, ?> jsonParse(final HttpURLConnection c,
+  @VisibleForTesting
+  public static Map<?, ?> jsonParse(final HttpURLConnection c,
       final boolean useErrorStream) throws IOException {
     if (c.getContentLength() == 0) {
       return null;

hadoop-hdfs-project/hadoop-hdfs-rbf/src/main/java/org/apache/hadoop/hdfs/server/federation/router/RouterWebHdfsMethods.java

@@ -19,6 +19,8 @@
 
 import static org.apache.hadoop.util.StringUtils.getTrimmedStringCollection;
 
+import org.apache.hadoop.fs.InvalidPathException;
+import org.apache.hadoop.hdfs.DFSUtil;
 import org.apache.hadoop.hdfs.protocol.ClientProtocol;
 import org.apache.hadoop.hdfs.protocol.DatanodeInfo;
 import org.apache.hadoop.hdfs.protocol.HdfsFileStatus;
@@ -419,6 +421,9 @@ private URI redirectURI(final Router router, final UserGroupInformation ugi,
       final DoAsParam doAsUser, final String path, final HttpOpParam.Op op,
       final long openOffset, final String excludeDatanodes,
       final Param<?, ?>... parameters) throws URISyntaxException, IOException {
+    if (!DFSUtil.isValidName(path)) {
+      throw new InvalidPathException(path);
+    }
     final DatanodeInfo dn =
         chooseDatanode(router, path, op, openOffset, excludeDatanodes);
 

hadoop-hdfs-project/hadoop-hdfs-rbf/src/test/java/org/apache/hadoop/hdfs/server/federation/router/TestRouterWebHdfsMethods.java

@@ -23,9 +23,12 @@
 import static org.junit.Assert.fail;
 
 import java.io.FileNotFoundException;
+import java.io.IOException;
 import java.net.HttpURLConnection;
 import java.net.URL;
 import java.util.Collections;
+import java.util.LinkedHashMap;
+import java.util.Map;
 
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FileSystem;
@@ -34,6 +37,7 @@
 import org.apache.hadoop.hdfs.server.federation.RouterConfigBuilder;
 import org.apache.hadoop.hdfs.server.federation.StateStoreDFSCluster;
 import org.apache.hadoop.hdfs.server.federation.resolver.order.DestinationOrder;
+import org.apache.hadoop.hdfs.web.WebHdfsFileSystem;
 import org.junit.AfterClass;
 import org.junit.BeforeClass;
 import org.junit.Test;
@@ -145,4 +149,24 @@ public void testGetNsFromDataNodeNetworkLocation() {
     assertEquals("", RouterWebHdfsMethods
         .getNsFromDataNodeNetworkLocation("whatever-rack-info1"));
   }
+
+  @Test
+  public void testWebHdfsCreateWithInvalidPath() throws Exception {
+    // A path name include duplicated slashes.
+    String path = "//tmp//file";
+    assertResponse(path);
+  }
+
+  private void assertResponse(String path) throws IOException {
+    URL url = new URL(getUri(path));
+    HttpURLConnection conn = (HttpURLConnection) url.openConnection();
+    conn.setRequestMethod("PUT");
+    // Assert response code.
+    assertEquals(HttpURLConnection.HTTP_BAD_REQUEST, conn.getResponseCode());
+    // Assert exception.
+    Map<?, ?> response = WebHdfsFileSystem.jsonParse(conn, true);
+    assertEquals("InvalidPathException",
+        ((LinkedHashMap) response.get("RemoteException")).get("exception"));
+    conn.disconnect();
+  }
 }

hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/namenode/web/resources/NamenodeWebHdfsMethods.java

@@ -55,6 +55,7 @@
 import javax.ws.rs.core.Response.ResponseBuilder;
 import javax.ws.rs.core.Response.Status;
 
+import org.apache.hadoop.fs.InvalidPathException;
 import org.apache.hadoop.fs.QuotaUsage;
 import org.apache.hadoop.fs.StorageType;
 import org.apache.hadoop.hdfs.protocol.HdfsConstants;
@@ -401,6 +402,9 @@ private URI redirectURI(ResponseBuilder rb, final NameNode namenode,
       final String path, final HttpOpParam.Op op, final long openOffset,
       final long blocksize, final String excludeDatanodes,
       final Param<?, ?>... parameters) throws URISyntaxException, IOException {
+    if (!DFSUtil.isValidName(path)) {
+      throw new InvalidPathException(path);
+    }
     final DatanodeInfo dn;
     final NamenodeProtocols np = getRPCServer(namenode);
     HdfsFileStatus status = null;

hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/web/TestWebHDFS.java

@@ -55,6 +55,7 @@
 import java.util.Collection;
 import java.util.EnumSet;
 import java.util.Iterator;
+import java.util.LinkedHashMap;
 import java.util.Map;
 import java.util.NoSuchElementException;
 import java.util.Random;
@@ -522,6 +523,38 @@ public void testCreateWithNoDN() throws Exception {
     }
   }
 
+  @Test
+  public void testWebHdfsCreateWithInvalidPath() throws Exception {
+    final Configuration conf = WebHdfsTestUtil.createConf();
+    cluster = new MiniDFSCluster.Builder(conf).numDataNodes(0).build();
+    // A path name include duplicated slashes.
+    String path = "//tmp//file";
+    assertResponse(path);
+  }
+
+  private String getUri(String path) {
+    final String user = System.getProperty("user.name");
+    final StringBuilder uri = new StringBuilder(cluster.getHttpUri(0));
+    uri.append("/webhdfs/v1").
+        append(path).
+        append("?op=CREATE").
+        append("&user.name=" + user);
+    return uri.toString();
+  }
+
+  private void assertResponse(String path) throws IOException {
+    URL url = new URL(getUri(path));
+    HttpURLConnection conn = (HttpURLConnection) url.openConnection();
+    conn.setRequestMethod("PUT");
+    // Assert response code.
+    assertEquals(HttpURLConnection.HTTP_BAD_REQUEST, conn.getResponseCode());
+    // Assert exception.
+    Map<?, ?> response = WebHdfsFileSystem.jsonParse(conn, true);
+    assertEquals("InvalidPathException",
+        ((LinkedHashMap) response.get("RemoteException")).get("exception"));
+    conn.disconnect();
+  }
+
   /**
    * Test allow and disallow snapshot through WebHdfs. Verifying webhdfs with
    * Distributed filesystem methods.