rdblue commented on code in PR #950:
URL: https://github.com/apache/parquet-mr/pull/950#discussion_r842097255
##########
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileReader.java:
##########
@@ -878,11 +880,97 @@ public String getFile() {
return blocks;
}
- public void setRequestedSchema(MessageType projection) {
+ private boolean uniqueId(GroupType schema, HashSet<Type.ID> ids) {
+ boolean unique = true;
+ List<Type> fields = schema.getFields();
+ for (Type field : fields) {
+ if (field instanceof PrimitiveType) {
+ Type.ID id = field.getId();
+ if (id != null) {
+ if (ids.contains(id)) {
+ return false;
+ }
+ ids.add(id);
+ }
+ }
+
+ if (field instanceof GroupType) {
+ Type.ID id = field.getId();
+ if (id != null) {
+ if (ids.contains(id)) {
+ return false;
+ }
+ ids.add(id);
+ }
+ if (unique) unique = uniqueId(field.asGroupType(), ids);
+ }
+ }
+ return unique;
+ }
+
+ public MessageType setRequestedSchema(MessageType projection, boolean
useColumnId) {
paths.clear();
- for (ColumnDescriptor col : projection.getColumns()) {
+ MessageType schema = null;
+ if (useColumnId) {
+ HashSet<Type.ID> ids = new HashSet<>();
+ boolean fileSchemaIdUnique = uniqueId(fileMetaData.getSchema(), ids);
+ if (!fileSchemaIdUnique) {
+ throw new RuntimeException("can't use column id resolution because
there are duplicate column ids.");
+ }
+ ids = new HashSet<>();
+ boolean projectionSchemaIdUnique = uniqueId(projection, ids);
+ if (!projectionSchemaIdUnique) {
+ throw new RuntimeException("can't use column id resolution because
there are duplicate column ids.");
+ }
+ schema = resetColumnNameBasedOnId(projection);
+ } else {
+ schema = projection;
+ }
+ for (ColumnDescriptor col : schema.getColumns()) {
paths.put(ColumnPath.get(col.getPath()), col);
}
+ return schema;
+ }
+
+ private MessageType resetColumnNameBasedOnId(MessageType schema) {
Review Comment:
This doesn't seem like the right class to contain these utility methods. I'd
recommend a utility class to handle this.
--
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: dev-unsubscr...@parquet.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
