huyuanfeng2018 commented on code in PR #9606: URL: https://github.com/apache/iceberg/pull/9606#discussion_r1510521311
########## flink/v1.18/flink/src/main/java/org/apache/iceberg/flink/FlinkSchemaUtil.java: ########## @@ -64,26 +68,75 @@ public static Schema convert(TableSchema schema) { RowType root = (RowType) schemaType; Type converted = root.accept(new FlinkTypeToType(root)); - Schema iSchema = new Schema(converted.asStructType().fields()); - return freshIdentifierFieldIds(iSchema, schema); + Schema icebergSchema = new Schema(converted.asStructType().fields()); + return freshIdentifierFieldIds(icebergSchema, schema); } - private static Schema freshIdentifierFieldIds(Schema iSchema, TableSchema schema) { + /** Convert the flink table schema to apache iceberg schema with column comment. */ + public static Schema convert(ResolvedSchema flinkSchema) { + List<Column> tableColumns = flinkSchema.getColumns(); + // copy from org.apache.flink.table.api.Schema#toRowDataType + DataTypes.Field[] fields = + tableColumns.stream() + .map( + column -> { + if (column.getComment().isPresent()) { + return DataTypes.FIELD( + column.getName(), column.getDataType(), column.getComment().get()); + } else { + return DataTypes.FIELD(column.getName(), column.getDataType()); + } + }) + .toArray(DataTypes.Field[]::new); + + LogicalType schemaType = DataTypes.ROW(fields).notNull().getLogicalType(); + Preconditions.checkArgument( + schemaType instanceof RowType, "Schema logical type should be RowType."); + + RowType root = (RowType) schemaType; + Type converted = root.accept(new FlinkTypeToType(root)); + Schema icebergSchema = new Schema(converted.asStructType().fields()); + return freshIdentifierFieldIds(icebergSchema, flinkSchema); + } + + /** @deprecated Use {@link #freshIdentifierFieldIds(Schema, ResolvedSchema)} instead. */ + @Deprecated + private static Schema freshIdentifierFieldIds(Schema icebergSchema, TableSchema flinkSchema) { Review Comment: It does look a bit strange. This method just takes out the primary key of flink and sets the non-empty column of iceberg, so I changed the input parameters. Can you see if this is reasonable? -- 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