Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix(query): uri path should not be percent-encoded #17109

Merged
merged 1 commit into from
Dec 25, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Cargo.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions src/query/ast/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ logos = { workspace = true }
nom = { workspace = true }
nom-rule = { workspace = true }
ordered-float = { workspace = true }
percent-encoding = { workspace = true }
pratt = { workspace = true }
pretty = { workspace = true }
pretty_assertions = { workspace = true }
Expand Down
5 changes: 4 additions & 1 deletion src/query/ast/src/ast/statements/copy.rs
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@ use std::str::FromStr;
use derive_visitor::Drive;
use derive_visitor::DriveMut;
use itertools::Itertools;
use percent_encoding::percent_decode_str;
use url::Url;

use crate::ast::quote::QuotedString;
Expand Down Expand Up @@ -477,7 +478,9 @@ impl UriLocation {
let path = if parsed.path().is_empty() {
"/".to_string()
} else {
parsed.path().to_string()
percent_decode_str(parsed.path())
.decode_utf8_lossy()
.to_string()
};

Ok(Self {
Expand Down
1 change: 0 additions & 1 deletion src/query/sql/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,6 @@ num-derive = { workspace = true }
num-traits = { workspace = true }
opendal = { workspace = true }
parking_lot = { workspace = true }
percent-encoding = { workspace = true }
prqlc = { workspace = true }
rand = { workspace = true }
recursive = { workspace = true }
Expand Down
4 changes: 1 addition & 3 deletions src/query/sql/src/planner/binder/location.rs
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,6 @@ use databend_common_storage::STDIN_FD;
use opendal::raw::normalize_path;
use opendal::raw::normalize_root;
use opendal::Scheme;
use percent_encoding::percent_decode_str;

/// secure_omission will fix omitted endpoint url schemes into 'https://'
#[inline]
Expand Down Expand Up @@ -538,10 +537,9 @@ pub async fn parse_uri_location(
Scheme::Cos => parse_cos_params(l, root)?,
Scheme::Http => {
// Make sure path has been percent decoded before parse pattern.
let path = percent_decode_str(&l.path).decode_utf8_lossy();
let cfg = StorageHttpConfig {
endpoint_url: format!("{}://{}", l.protocol, l.name),
paths: globiter::Pattern::parse(&path)
paths: globiter::Pattern::parse(&l.path)
.map_err(|err| {
Error::new(
ErrorKind::InvalidInput,
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
>>>> create or replace connection c_00_0005 storage_type='s3' access_key_id = 'minioadmin' endpoint_url = 'http://127.0.0.1:9900' secret_access_key = 'minioadmin'
>>>> copy into 's3://testbucket/c_00_0005/ab de/f' connection=(connection_name='c_00_0005') from (select 1) detailed_output=true use_raw_path=true single=true overwrite=true
c_00_0005/ab de/f 374 1
<<<<
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
#!/usr/bin/env bash

CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
. "$CURDIR"/../../../shell_env.sh


stmt "create or replace connection c_00_0005 storage_type='s3' access_key_id = 'minioadmin' endpoint_url = 'http://127.0.0.1:9900' secret_access_key = 'minioadmin'"

query "copy into 's3://testbucket/c_00_0005/ab de/f' connection=(connection_name='c_00_0005') from (select 1) detailed_output=true use_raw_path=true single=true overwrite=true"
Loading