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.

Sign up for GitHub

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

Jump to bottom

fix(elasticsearch sink): Encode bulk action parameters as JSON #21293

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
+84 −22
Open

fix(elasticsearch sink): Encode bulk action parameters as JSON #21293

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e874265
fix(elasticsearch): Encode bulk action parameters as JSON
jszwedko Sep 13, 2024
88d8a79
Merge remote-tracking branch 'origin/master' into jszwedko/fix-elasti…
jszwedko Nov 1, 2024
6329720
Fix tests
jszwedko Nov 1, 2024
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: 2 additions & 0 deletions changelog.d/elasticsearch-encoding.fix.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
The `elasticsearch` sink now encodes parameters such as `index` that contain characters that need to
be escaped in JSON strings.
100 changes: 80 additions & 20 deletions src/sinks/elasticsearch/encoder.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
use std::{io, io::Write};

use serde::Serialize;
use serde_json::json;
use vector_lib::buffers::EventCount;
use vector_lib::{config::telemetry, event::Event, ByteSizeOf, EstimatedJsonEncodedSizeOf};
use vector_lib::{
Expand Down Expand Up @@ -154,48 +155,78 @@ fn write_bulk_action(
(true, DocumentMetadata::Id(id)) => {
write!(
writer,
r#"{{"{}":{{"_index":"{}","_id":"{}"}}}}"#,
bulk_action, index, id
"{}",
json!({
bulk_action: {
"_index": index,
"_id": id,
}
}),
)
}
(false, DocumentMetadata::Id(id)) => {
write!(
writer,
r#"{{"{}":{{"_index":"{}","_type":"{}","_id":"{}"}}}}"#,
bulk_action, index, doc_type, id
"{}",
json!({
bulk_action: {
"_type": doc_type,
"_index": index,
"_id": id,
}
}),
)
}
(true, DocumentMetadata::WithoutId) => {
write!(writer, r#"{{"{}":{{"_index":"{}"}}}}"#, bulk_action, index)
write!(
writer,
"{}",
json!({
bulk_action: {
"_index": index,
}
}),
)
}
(false, DocumentMetadata::WithoutId) => {
write!(
writer,
r#"{{"{}":{{"_index":"{}","_type":"{}"}}}}"#,
bulk_action, index, doc_type
"{}",
json!({
bulk_action: {
"_type": doc_type,
"_index": index,
}
}),
)
}
(true, DocumentMetadata::IdAndVersion(id, version)) => {
write!(
writer,
r#"{{"{}":{{"_index":"{}","_id":"{}","version_type":"{}","version":{}}}}}"#,
bulk_action,
index,
id,
version.kind.as_str(),
version.value
"{}",
json!({
bulk_action: {
"_id": id,
"_index": index,
"version_type": version.kind.as_str(),
"version": version.value,
}
}),
)
}
(false, DocumentMetadata::IdAndVersion(id, version)) => {
write!(
writer,
r#"{{"{}":{{"_index":"{}","_type":"{}","_id":"{}","version_type":"{}","version":{}}}}}"#,
bulk_action,
index,
doc_type,
id,
version.kind.as_str(),
version.value
"{}",
json!({
bulk_action: {
"_id": id,
"_type": doc_type,
"_index": index,
"version_type": version.kind.as_str(),
"version": version.value,
}
}),
)
}
},
Expand Down Expand Up @@ -317,4 +348,33 @@ mod tests {
assert!(nested.contains_key("_type"));
assert_eq!(nested.get("_type").unwrap().as_str(), Some("TYPE"));
}

#[test]
fn encodes_fields_with_newlines() {
let mut writer = Vec::new();

_ = write_bulk_action(
&mut writer,
"ACTION\n",
"INDEX\n",
"TYPE\n",
false,
&DocumentMetadata::Id("ID\n".to_string()),
);
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we add an .unwrap() here?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mmm, yeah, I just used the pattern the other tests here are using, but yes, it would make sense to use unwrap on all of these


let value: serde_json::Value = serde_json::from_slice(&writer).unwrap();
let value = value.as_object().unwrap();

assert!(value.contains_key("ACTION\n"));

let nested = value.get("ACTION\n").unwrap();
let nested = nested.as_object().unwrap();

assert!(nested.contains_key("_index"));
assert_eq!(nested.get("_index").unwrap().as_str(), Some("INDEX\n"));
assert!(nested.contains_key("_id"));
assert_eq!(nested.get("_id").unwrap().as_str(), Some("ID\n"));
assert!(nested.contains_key("_type"));
assert_eq!(nested.get("_type").unwrap().as_str(), Some("TYPE\n"));
}
}
Loading