paleolimbot commented on code in PR #7481:
URL: https://github.com/apache/arrow-rs/pull/7481#discussion_r2078288130
##########
parquet/src/arrow/arrow_reader/mod.rs:
##########
@@ -506,37 +525,47 @@ impl ArrowReaderMetadata {
// parquet_to_arrow_field_levels is expected to throw an error if the
schemas have
// different lengths, but we check here to be safe.
if inferred_len != supplied_len {
- Err(arrow_err!(format!(
- "incompatible arrow schema, expected {} columns received {}",
+ return Err(arrow_err!(format!(
+ "Incompatible supplied Arrow schema: expected {} columns
received {}",
inferred_len, supplied_len
- )))
- } else {
- let diff_fields: Vec<_> = supplied_schema
- .fields()
- .iter()
- .zip(fields.iter())
- .filter_map(|(field1, field2)| {
- if field1 != field2 {
- Some(field1.name().clone())
- } else {
- None
- }
- })
- .collect();
+ )));
+ }
- if !diff_fields.is_empty() {
- Err(ParquetError::ArrowError(format!(
- "incompatible arrow schema, the following fields could not
be cast: [{}]",
- diff_fields.join(", ")
- )))
- } else {
- Ok(Self {
- metadata,
- schema: supplied_schema,
- fields: field_levels.levels.map(Arc::new),
- })
+ let mut errors = Vec::new();
+
+ let field_iter = supplied_schema.fields().iter().zip(fields.iter());
+
+ for (field1, field2) in field_iter {
+ if field1.data_type() != field2.data_type() {
+ errors.push(format!(
+ "data type mismatch for field {}: requested {:?} but found
{:?}",
+ field1.name(),
+ field1.data_type(),
+ field2.data_type()
+ ));
+ }
+ if field1.is_nullable() != field2.is_nullable() {
Review Comment:
Can a non-nullable field be cast to a nullable one?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
