[
https://issues.apache.org/jira/browse/AVRO-3786?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17742869#comment-17742869
]
Evan Blackwell commented on AVRO-3786:
--------------------------------------
Additionally, here's the test that I created that more closely resembles a part
of our schema to find this error
{code:java}
#[test]
fn
deserialize_union_with_record_with_enum_defined_inline_reader_has_different_indices()
-> TestResult {
#[derive(Debug, PartialEq, Eq, Hash, PartialOrd, Ord, Clone,
serde::Deserialize, serde::Serialize)]
pub enum DefinedInRecord {
#[serde(rename = "val0")]
Val0,
#[serde(rename = "val1")]
Val1,
#[serde(rename = "val2")]
Val2,
#[serde(rename = "UNKNOWN")]
Unknown,
}
#[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize,
serde::Serialize)]
pub struct Parent {
pub date: i64,
#[serde(rename = "barUse")]
pub bar_use: Bar,
#[serde(rename = "bazUse")]
pub baz_use: Option<Vec<Baz>>,
#[serde(rename = "definedInRecord")]
pub defined_in_record: DefinedInRecord,
#[serde(rename = "optionalString")]
pub optional_string: Option<String>,
}
#[derive(Debug, PartialEq, Eq, Hash, PartialOrd, Ord, Clone,
serde::Deserialize, serde::Serialize)]
pub enum Baz {
#[serde(rename = "baz0")]
Baz0,
#[serde(rename = "baz1")]
Baz1,
#[serde(rename = "baz2")]
Baz2,
}
#[derive(Debug, PartialEq, Eq, Hash, PartialOrd, Ord, Clone,
serde::Deserialize, serde::Serialize)]
pub enum Bar {
#[serde(rename = "bar0")]
Bar0,
#[serde(rename = "bar1")]
Bar1,
#[serde(rename = "bar2")]
Bar2,
}
#[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize,
serde::Serialize)]
pub struct Foo {
#[serde(rename = "barInit")]
pub bar_init: Bar,
pub baz: Baz,
pub parent: Option<Parent>,
}
let writer_schema = r#"{
"type": "record",
"name": "Foo",
"namespace": "fake",
"fields":
[
{
"name": "barInit",
"type":
{
"type": "enum",
"name": "Bar",
"symbols":
[
"bar0",
"bar1",
"bar2"
],
"default": "bar0"
}
},
{
"name": "baz",
"type":
{
"type": "enum",
"name": "Baz",
"symbols":
[
"baz0",
"baz1",
"baz2"
],
"default": "baz0"
}
},
{
"name": "parent",
"type": [
"null",
{
"type": "record",
"name": "Parent",
"fields": [
{
"name": "date",
"type": {
"type": "long",
"avro.java.long": "Long"
}
},
{
"name": "barUse",
"type": "Bar"
},
{
"name": "bazUse",
"type": [
"null",
{
"type": "array",
"items": {
"type": "Baz"
}
}
]
},
{
"name": "definedInRecord",
"type": {
"name": "DefinedInRecord",
"type": "enum",
"symbols": [
"val0",
"val1",
"val2",
"UNKNOWN"
],
"default": "UNKNOWN"
}
},
{
"name": "optionalString",
"type": [
"null",
"string"
]
}
]
}
]
}
]
}"#;
let reader_schema = r#"{
"type": "record",
"name": "Foo",
"namespace": "fake",
"fields":
[
{
"name": "barInit",
"type":
{
"type": "enum",
"name": "Bar",
"symbols":
[
"bar0",
"bar2"
],
"default": "bar0"
}
},
{
"name": "baz",
"type":
{
"type": "enum",
"name": "Baz",
"symbols":
[
"baz0",
"baz2"
],
"default": "baz0"
}
},
{
"name": "parent",
"type": [
"null",
{
"type": "record",
"name": "Parent",
"fields": [
{
"name": "date",
"type": {
"type": "long",
"avro.java.long": "Long"
}
},
{
"name": "barUse",
"type": "Bar"
},
{
"name": "bazUse",
"type": [
"null",
{
"type": "array",
"items": {
"type": "Baz"
}
}
]
},
{
"name": "definedInRecord",
"type": {
"name": "DefinedInRecord",
"type": "enum",
"symbols": [
"val1",
"val2",
"UNKNOWN"
],
"default": "UNKNOWN"
}
},
{
"name": "optionalString",
"type": [
"null",
"string"
]
}
]
}
]
}
]
}"#;
let writer_schema = Schema::parse_str(writer_schema)?;
let foo = Foo {
bar_init: Bar::Bar0,
baz: Baz::Baz0,
parent: Some(Parent {
bar_use: Bar::Bar0,
baz_use: Some(vec![Baz::Baz0]),
optional_string: Some("test".to_string()),
date: 1689197893,
defined_in_record: DefinedInRecord::Val1
})
};
let avro_value = crate::to_value(foo)?;
assert!(
avro_value.validate(&writer_schema),
"value is valid for schema",
);
let datum = crate::to_avro_datum(&writer_schema, avro_value)?;
let mut x = &datum[..];
let reader_schema = Schema::parse_str(reader_schema)?;
let deser_value = crate::from_avro_datum(&writer_schema, &mut x,
Some(&reader_schema))?;
match deser_value {
types::Value::Record(fields) => {
assert_eq!(fields.len(), 3);
assert_eq!(fields[0].0, "barInit");
assert_eq!(fields[0].1, types::Value::Enum(0,
"bar0".to_string()));
// TODO: better validation
}
_ => panic!("Expected Value::Record"),
}
Ok(())
} {code}
> [Rust] Deserialization results in FindUnionVariant error if the writer and
> reader have the same symbol but at different positions
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: AVRO-3786
> URL: https://issues.apache.org/jira/browse/AVRO-3786
> Project: Apache Avro
> Issue Type: Bug
> Components: rust
> Reporter: Evan Blackwell
> Assignee: Martin Tzvetanov Grigorov
> Priority: Major
> Labels: pull-request-available
> Fix For: 1.12.0, 1.11.3
>
> Time Spent: 20m
> Remaining Estimate: 0h
>
> When calling from_avro_datum with a reader schema that has the same enum
> symbol but in a different position as the writer schema, a FindUnionVariant
> error occurs. The value in the message is available in both schemas. The enum
> is defined elsewhere in the schema, so it's worth checking if the problem is
> with the reference type or the enum itself.
>
> Sample test
> {code:java}
> #[test]
> fn deserialize_union_with_different_enum_order() -> TestResult {
> #[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize,
> serde::Serialize)]
> pub struct BarUseParent {
> #[serde(rename = "barUse")]
> pub bar_use: Bar,
> }
> #[derive(Debug, PartialEq, Eq, Hash, PartialOrd, Ord, Clone,
> serde::Deserialize, serde::Serialize)]
> pub enum Bar {
> #[serde(rename = "bar0")]
> Bar0,
> #[serde(rename = "bar1")]
> Bar1,
> #[serde(rename = "bar2")]
> Bar2,
> }
> #[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize,
> serde::Serialize)]
> pub struct Foo {
> #[serde(rename = "barInit")]
> pub bar_init: Bar,
> #[serde(rename = "barUseParent")]
> pub bar_use_parent: Option<BarUseParent>,
> }
> let writer_schema = r#"{
> "type": "record",
> "name": "Foo",
> "fields":
> [
> {
> "name": "barInit",
> "type":
> {
> "type": "enum",
> "name": "Bar",
> "symbols":
> [
> "bar0",
> "bar1",
> "bar2"
> ],
> "default": "bar0"
> }
> },
> {
> "name": "barUseParent",
> "type": [
> "null",
> {
> "type": "record",
> "name": "BarUseParent",
> "fields": [
> {
> "name": "barUse",
> "type": "Bar"
> }
> ]
> }
> ]
> }
> ]
> }"#;
> let reader_schema = r#"{
> "type": "record",
> "name": "Foo",
> "fields":
> [
> {
> "name": "barInit",
> "type":
> {
> "type": "enum",
> "name": "Bar",
> "symbols":
> [
> "bar1"
> ],
> "default": "bar1"
> }
> },
> {
> "name": "barUseParent",
> "type": [
> "null",
> {
> "type": "record",
> "name": "BarUseParent",
> "fields": [
> {
> "name": "barUse",
> "type": "Bar"
> }
> ]
> }
> ]
> }
> ]
> }"#;
> let writer_schema = Schema::parse_str(writer_schema)?;
> let foo = Foo {
> bar_init: Bar::Bar1,
> bar_use_parent: Some(BarUseParent { bar_use: Bar::Bar1} ),
> };
> let avro_value = crate::to_value(foo)?;
> assert!(
> avro_value.validate(&writer_schema),
> "value is valid for schema",
> );
> let datum = crate::to_avro_datum(&writer_schema, avro_value)?;
> let mut x = &datum[..];
> let reader_schema = Schema::parse_str(reader_schema)?;
> let deser_value = crate::from_avro_datum(&writer_schema, &mut x,
> Some(&reader_schema))?;
> match deser_value {
> types::Value::Record(fields) => {
> assert_eq!(fields.len(), 2);
> assert_eq!(fields[0].0, "barInit");
> assert_eq!(fields[0].1, types::Value::Enum(1,
> "bar1".to_string()));
> assert_eq!(fields[1].0, "barUseParent");
> // TODO: assert barUseParent value
> }
> _ => panic!("Expected Value::Record"),
> } Ok(())
> } Ok(()) } {code}
> Resulting error:
> {code:java}
> apache_avro::error::Error: Could not find matching type in union {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
