ahmedabu98 commented on code in PR #35435:
URL: https://github.com/apache/beam/pull/35435#discussion_r2213730337


##########
sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigtable/BigtableWriteSchemaTransformProvider.java:
##########
@@ -140,40 +148,74 @@ public PCollectionRowTuple expand(PCollectionRowTuple 
input) {
           String.format(
               "Could not find expected input [%s] to %s.", INPUT_TAG, 
getClass().getSimpleName()));
 
-      Schema testOriginialSchema =
-          Schema.builder()
-              .addByteArrayField("key")
-              .addArrayField(
-                  "mutations",
-                  Schema.FieldType.map(Schema.FieldType.STRING, 
Schema.FieldType.BYTES))
-              .build();
-
       Schema inputSchema = input.getSinglePCollection().getSchema();
 
-      System.out.println("Input Schema for BigTableMutations: " + inputSchema);
-
       PCollection<KV<ByteString, Iterable<Mutation>>> bigtableMutations = null;
-      if (inputSchema.equals(testOriginialSchema)) {
+      if (inputSchema.equals(BATCHED_MUTATIONS_SCHEMA)) {
         PCollection<Row> beamRowMutations = input.get(INPUT_TAG);
         bigtableMutations =
             beamRowMutations.apply(
                 // Original schema inputs gets sent out to the original 
transform provider mutations
                 // function
-                MapElements.via(
-                    new 
BigtableWriteSchemaTransformProvider.GetMutationsFromBeamRow()));
+                MapElements.via(new GetMutationsFromBeamRow()));
       } else if (inputSchema.hasField("type")) {
+        checkState(
+            
inputSchema.getField("type").getType().equals(Schema.FieldType.STRING),
+            "Schema field 'type' should be of type STRING.");
+
+        if (inputSchema.hasField("value")) {
+          checkState(
+              
inputSchema.getField("value").getType().equals(Schema.FieldType.BYTES),
+              "Schema field 'value' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("column_qualifier")) {
+          checkState(
+              
inputSchema.getField("column_qualifier").getType().equals(Schema.FieldType.BYTES),
+              "Schema field 'column_qualifier' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("family_name")) {
+          checkState(
+              
inputSchema.getField("family_name").getType().equals(Schema.FieldType.BYTES),
+              "Schema field 'family_name' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("timestamp_micros")) {
+          checkState(
+              
inputSchema.getField("timestamp_micros").getType().equals(Schema.FieldType.INT64),
+              "Schema field 'timestamp_micros' should be of type BYTES.");

Review Comment:
   ```suggestion
                 "Schema field 'timestamp_micros' should be of type INT64.");
   ```



##########
sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigtable/BigtableWriteSchemaTransformProvider.java:
##########
@@ -140,40 +148,74 @@ public PCollectionRowTuple expand(PCollectionRowTuple 
input) {
           String.format(
               "Could not find expected input [%s] to %s.", INPUT_TAG, 
getClass().getSimpleName()));
 
-      Schema testOriginialSchema =
-          Schema.builder()
-              .addByteArrayField("key")
-              .addArrayField(
-                  "mutations",
-                  Schema.FieldType.map(Schema.FieldType.STRING, 
Schema.FieldType.BYTES))
-              .build();
-
       Schema inputSchema = input.getSinglePCollection().getSchema();
 
-      System.out.println("Input Schema for BigTableMutations: " + inputSchema);
-
       PCollection<KV<ByteString, Iterable<Mutation>>> bigtableMutations = null;
-      if (inputSchema.equals(testOriginialSchema)) {
+      if (inputSchema.equals(BATCHED_MUTATIONS_SCHEMA)) {
         PCollection<Row> beamRowMutations = input.get(INPUT_TAG);
         bigtableMutations =
             beamRowMutations.apply(
                 // Original schema inputs gets sent out to the original 
transform provider mutations
                 // function
-                MapElements.via(
-                    new 
BigtableWriteSchemaTransformProvider.GetMutationsFromBeamRow()));
+                MapElements.via(new GetMutationsFromBeamRow()));
       } else if (inputSchema.hasField("type")) {
+        checkState(
+            
inputSchema.getField("type").getType().equals(Schema.FieldType.STRING),
+            "Schema field 'type' should be of type STRING.");
+
+        if (inputSchema.hasField("value")) {
+          checkState(
+              
inputSchema.getField("value").getType().equals(Schema.FieldType.BYTES),
+              "Schema field 'value' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("column_qualifier")) {
+          checkState(
+              
inputSchema.getField("column_qualifier").getType().equals(Schema.FieldType.BYTES),
+              "Schema field 'column_qualifier' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("family_name")) {
+          checkState(
+              
inputSchema.getField("family_name").getType().equals(Schema.FieldType.BYTES),
+              "Schema field 'family_name' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("timestamp_micros")) {
+          checkState(
+              
inputSchema.getField("timestamp_micros").getType().equals(Schema.FieldType.INT64),
+              "Schema field 'timestamp_micros' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("start_timestamp_micros")) {
+          checkState(
+              inputSchema
+                  .getField("start_timestamp_micros")
+                  .getType()
+                  .equals(Schema.FieldType.INT64),
+              "Schema field 'start_timestamp_micros' should be of type 
BYTES.");
+        }
+
+        if (inputSchema.hasField("end_timestamp_micros")) {
+          checkState(
+              
inputSchema.getField("end_timestamp_micros").getType().equals(Schema.FieldType.INT64),
+              "Schema field 'end_timestamp_micros' should be of type BYTES.");

Review Comment:
   ```suggestion
                 "Schema field 'end_timestamp_micros' should be of type 
INT64.");
   ```



##########
sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigtable/BigtableWriteSchemaTransformProvider.java:
##########
@@ -140,40 +148,74 @@ public PCollectionRowTuple expand(PCollectionRowTuple 
input) {
           String.format(
               "Could not find expected input [%s] to %s.", INPUT_TAG, 
getClass().getSimpleName()));
 
-      Schema testOriginialSchema =
-          Schema.builder()
-              .addByteArrayField("key")
-              .addArrayField(
-                  "mutations",
-                  Schema.FieldType.map(Schema.FieldType.STRING, 
Schema.FieldType.BYTES))
-              .build();
-
       Schema inputSchema = input.getSinglePCollection().getSchema();
 
-      System.out.println("Input Schema for BigTableMutations: " + inputSchema);
-
       PCollection<KV<ByteString, Iterable<Mutation>>> bigtableMutations = null;
-      if (inputSchema.equals(testOriginialSchema)) {
+      if (inputSchema.equals(BATCHED_MUTATIONS_SCHEMA)) {
         PCollection<Row> beamRowMutations = input.get(INPUT_TAG);
         bigtableMutations =
             beamRowMutations.apply(
                 // Original schema inputs gets sent out to the original 
transform provider mutations
                 // function
-                MapElements.via(
-                    new 
BigtableWriteSchemaTransformProvider.GetMutationsFromBeamRow()));
+                MapElements.via(new GetMutationsFromBeamRow()));
       } else if (inputSchema.hasField("type")) {
+        checkState(
+            
inputSchema.getField("type").getType().equals(Schema.FieldType.STRING),
+            "Schema field 'type' should be of type STRING.");
+
+        if (inputSchema.hasField("value")) {
+          checkState(
+              
inputSchema.getField("value").getType().equals(Schema.FieldType.BYTES),
+              "Schema field 'value' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("column_qualifier")) {
+          checkState(
+              
inputSchema.getField("column_qualifier").getType().equals(Schema.FieldType.BYTES),
+              "Schema field 'column_qualifier' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("family_name")) {
+          checkState(
+              
inputSchema.getField("family_name").getType().equals(Schema.FieldType.BYTES),
+              "Schema field 'family_name' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("timestamp_micros")) {
+          checkState(
+              
inputSchema.getField("timestamp_micros").getType().equals(Schema.FieldType.INT64),
+              "Schema field 'timestamp_micros' should be of type BYTES.");
+        }
+
+        if (inputSchema.hasField("start_timestamp_micros")) {
+          checkState(
+              inputSchema
+                  .getField("start_timestamp_micros")
+                  .getType()
+                  .equals(Schema.FieldType.INT64),
+              "Schema field 'start_timestamp_micros' should be of type 
BYTES.");

Review Comment:
   ```suggestion
                 "Schema field 'start_timestamp_micros' should be of type 
INT64.");
   ```



-- 
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: github-unsubscr...@beam.apache.org

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

Reply via email to