tustvold commented on issue #3658:
URL:
https://github.com/apache/arrow-datafusion/issues/3658#issuecomment-1270008874
You will want to do something vaguely like (not properly tested)
```
async fn infer_schema(
&self,
store: &Arc<dyn ObjectStore>,
objects: &[ObjectMeta],
) -> Result<SchemaRef> {
let mut schemas = vec![];
let mut records_to_read =
self.schema_infer_max_rec.unwrap_or(usize::MAX);
for object in objects {
match store.get(&object.location).await? {
GetResult::File(f, _) => {
let (schema, records_read) =
arrow::csv::reader::infer_reader_schema(
f,
self.delimiter,
Some(records_to_read),
self.has_header,
)?;
schemas.push(schema);
records_to_read -= records_read;
}
GetResult::Stream(s) => {
let mut has_header = self.has_header;
let s = newline_delimited_stream(s.map_err(Into::into));
pin_mut!(s);
while let Some(bytes) = s.next().await.transpose()? {
let (schema, records_read) =
arrow::csv::reader::infer_reader_schema(
bytes.as_ref(),
self.delimiter,
Some(records_to_read),
has_header,
)?;
has_header = false;
schemas.push(schema);
records_to_read -= records_read;
if records_to_read == 0 {
break;
}
}
}
}
}
let merged_schema = Schema::try_merge(schemas)?;
Ok(Arc::new(merged_schema))
}
```
--
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]
