alamb commented on code in PR #8012:
URL: https://github.com/apache/arrow-datafusion/pull/8012#discussion_r1378212990
##########
datafusion/core/src/datasource/listing/url.rs:
##########
@@ -317,8 +315,27 @@ mod tests {
let url = ListingTableUrl::parse("file:///foo/bar?").unwrap();
assert_eq!(url.prefix.as_ref(), "foo/bar");
- let url = ListingTableUrl::parse("file:///foo/😺").unwrap();
- assert_eq!(url.prefix.as_ref(), "foo/%F0%9F%98%BA");
+ let err = ListingTableUrl::parse("file:///foo/😺").unwrap_err();
Review Comment:
It seems very reasonable to treat urls like `file://foo`, as urls (rather
than paths with a `file://` prefix)
##########
datafusion/core/src/datasource/listing/url.rs:
##########
@@ -138,15 +137,13 @@ impl ListingTableUrl {
.map_err(|_| DataFusionError::Internal(format!("Can not open path:
{s}")))?;
// TODO: Currently we do not have an IO-related error variant that
accepts ()
// or a string. Once we have such a variant, change the error
type above.
- Ok(Self::new(url, glob))
+ Self::try_new(url, glob)
}
/// Creates a new [`ListingTableUrl`] from a url and optional glob
expression
- fn new(url: Url, glob: Option<Pattern>) -> Self {
- let decoded_path =
-
percent_encoding::percent_decode_str(url.path()).decode_utf8_lossy();
- let prefix = Path::from(decoded_path.as_ref());
- Self { url, prefix, glob }
+ fn try_new(url: Url, glob: Option<Pattern>) -> Result<Self> {
+ let prefix = Path::from_url_path(url.path())?;
Review Comment:
Would it be possible to update the documentation on `fn parse` to explain
the percent escaping behavior (you could simply copy the very nice description
from this PR perhaps)
--
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]
