From 1e7927e006a94399e65974f0091e7cfc84dee149 Mon Sep 17 00:00:00 2001
From: Xiangjin <xiangjin@risingwave-labs.com>
Date: Sat, 15 Jun 2024 15:34:25 +0800
Subject: [PATCH 1/2] feat: support nan/inf/-inf as float/double default

---
 lang/rust/avro/src/types.rs | 19 +++++++++++++++++++
 lang/rust/avro/tests/io.rs  | 29 ++++++++++++++++++++++++-----
 2 files changed, 43 insertions(+), 5 deletions(-)

diff --git a/lang/rust/avro/src/types.rs b/lang/rust/avro/src/types.rs
index 9b88d8c8bfa..d4bf8cddcfc 100644
--- a/lang/rust/avro/src/types.rs
+++ b/lang/rust/avro/src/types.rs
@@ -860,6 +860,10 @@ impl Value {
             Value::Long(n) => Ok(Value::Float(n as f32)),
             Value::Float(x) => Ok(Value::Float(x)),
             Value::Double(x) => Ok(Value::Float(x as f32)),
+            Value::String(x) => match Self::parse_special_float(&x) {
+                Some(f) => Ok(Value::Float(f)),
+                None => Err(Error::GetFloat(ValueKind::String)),
+            },
             other => Err(Error::GetFloat(other.into())),
         }
     }
@@ -870,10 +874,25 @@ impl Value {
             Value::Long(n) => Ok(Value::Double(n as f64)),
             Value::Float(x) => Ok(Value::Double(f64::from(x))),
             Value::Double(x) => Ok(Value::Double(x)),
+            Value::String(x) => match Self::parse_special_float(&x) {
+                Some(f) => Ok(Value::Double(f.into())),
+                None => Err(Error::GetDouble(ValueKind::String)),
+            },
             other => Err(Error::GetDouble(other.into())),
         }
     }
 
+    /// IEEE 754 NaN and infinities are not valid JSON numbers.
+    /// So they are represented in JSON as strings.
+    fn parse_special_float(s: &str) -> Option<f32> {
+        match s.trim().to_ascii_lowercase().as_str() {
+            "nan" | "+nan" | "-nan" => Some(f32::NAN),
+            "inf" | "+inf" | "infinity" | "+infinity" => Some(f32::INFINITY),
+            "-inf" | "-infinity" => Some(f32::NEG_INFINITY),
+            _ => None,
+        }
+    }
+
     /// <https://github.com/apache/avro/blob/release-1.11.3/lang/java/avro/src/main/java/org/apache/avro/io/parsing/ResolvingGrammarGenerator.java#L315>
     fn encode_iso_8859_1(s: &str) -> Result<Vec<u8>, Error> {
         s.chars()
diff --git a/lang/rust/avro/tests/io.rs b/lang/rust/avro/tests/io.rs
index 44dfc192aa0..78e9b0200dd 100644
--- a/lang/rust/avro/tests/io.rs
+++ b/lang/rust/avro/tests/io.rs
@@ -62,6 +62,9 @@ lazy_static! {
         (r#""long""#, "5", Value::Long(5)),
         (r#""float""#, "1.1", Value::Float(1.1)),
         (r#""double""#, "1.1", Value::Double(1.1)),
+        (r#""float""#, r#""  +inf ""#, Value::Float(f32::INFINITY)),
+        (r#""double""#, r#""-Infinity""#, Value::Double(f64::NEG_INFINITY)),
+        (r#""double""#, r#""-NAN""#, Value::Double(f64::NAN)),
         (r#"{"type": "fixed", "name": "F", "size": 2}"#, r#""a""#, Value::Fixed(1, vec![97])), // ASCII 'a' => one byte
         (r#"{"type": "fixed", "name": "F", "size": 2}"#, r#""\u00FF""#, Value::Fixed(1, vec![255])), // The value is between U+0080 and U+07FF => ISO-8859-1
         (r#"{"type": "enum", "name": "F", "symbols": ["FOO", "BAR"]}"#, r#""FOO""#, Value::Enum(0, "FOO".to_string())),
@@ -264,11 +267,27 @@ fn test_default_value() -> TestResult {
             &mut Cursor::new(encoded),
             Some(&reader_schema),
         )?;
-        assert_eq!(
-            datum_read, datum_to_read,
-            "{} -> {}",
-            *field_type, *default_json
-        );
+        match default_datum {
+            Value::Double(f) if f.is_nan() => {
+                let Value::Record(fields) = datum_read else {
+                    panic!()
+                };
+                let Value::Double(f) = fields[0].1 else {
+                    panic!("double expected")
+                };
+                assert!(
+                    f.is_nan(),
+                    "{field_type} -> {default_json} is parsed as {f} rather than NaN"
+                );
+            }
+            _ => {
+                assert_eq!(
+                    datum_read, datum_to_read,
+                    "{} -> {}",
+                    *field_type, *default_json
+                );
+            }
+        }
     }
 
     Ok(())

From c38717455f8d9cb5facd83da3708d0840658c887 Mon Sep 17 00:00:00 2001
From: Xiangjin <xiangjin@risingwave-labs.com>
Date: Tue, 18 Jun 2024 13:59:22 +0800
Subject: [PATCH 2/2] update test unreachable message

---
 lang/rust/avro/tests/io.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lang/rust/avro/tests/io.rs b/lang/rust/avro/tests/io.rs
index 78e9b0200dd..e102e1f662c 100644
--- a/lang/rust/avro/tests/io.rs
+++ b/lang/rust/avro/tests/io.rs
@@ -270,7 +270,7 @@ fn test_default_value() -> TestResult {
         match default_datum {
             Value::Double(f) if f.is_nan() => {
                 let Value::Record(fields) = datum_read else {
-                    panic!()
+                    unreachable!("the test always constructs top level as record")
                 };
                 let Value::Double(f) = fields[0].1 else {
                     panic!("double expected")