houqp commented on a change in pull request #7210:
URL: https://github.com/apache/arrow/pull/7210#discussion_r427602640
##########
File path: rust/datafusion/src/execution/physical_plan/csv.rs
##########
@@ -71,15 +75,35 @@ impl CsvExec {
/// Create a new execution plan for reading a set of CSV files
pub fn try_new(
path: &str,
- schema: Arc<Schema>,
+ schema: Option<Arc<Schema>>,
has_header: bool,
+ delimiter: Option<u8>,
projection: Option<Vec<usize>>,
batch_size: usize,
) -> Result<Self> {
+ let schema = match schema {
+ Some(s) => s,
+ None => {
+ let mut filenames: Vec<String> = vec![];
+ common::build_file_list(path, &mut filenames, ".csv")?;
+ if filenames.is_empty() {
+ return Err(ExecutionError::General("No files
found".to_string()));
+ }
+
+ let f = File::open(&filenames[0])?;
+ Arc::new(csv::infer_file_schema(
+ &mut BufReader::new(f),
+ delimiter.unwrap_or(b','),
+ Some(30),
Review comment:
good catch, will change to 1000, that 30 was a number i used for
debugging purpose, forgot to change it back :P
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
