Execute from_json with struct schema using JSONUtils.fromJSONToStructs

[ttnghia]

This adopts the newly implemented JNI function JSONUtils.fromJSONToStructs() to parse the input strings columns into a structs column, which is the case of calling from_json SQL function with struct schema. By replacing the Scala code entirely by native code, we can avoid a lot of overhead and optimize runtime performance.

Closes #11560.

This will also close the following issues:

• Parsing a column containing invalid json into StructureType with schema throws an Exception. #10891
• from_json, when input = empty object, rapids throws an exception. #10910

Depends on:

• Implement from_json_to_structs spark-rapids-jni#2510

[revans2]

I know it is still in draft so the debugging comments and commented out code is fine. I just thought I would track it anyways. It looks great.

[ttnghia]

build