RUST-2149 Sync additional vector tests (#514)

Author: isabelatkinson

src/tests/spec/json/bson-binary-vector/README.md

@@ -29,7 +29,7 @@ Each JSON file contains three top-level keys.
 
 - `description`: string describing the test.
 - `valid`: boolean indicating if the vector, dtype, and padding should be considered a valid input.
-- `vector`: list of numbers
+- `vector`: (required if valid is true) list of numbers
 - `dtype_hex`: string defining the data type in hex (e.g. "0x10", "0x27")
 - `dtype_alias`: (optional) string defining the data dtype, perhaps as Enum.
 - `padding`: (optional) integer for byte padding. Defaults to 0.
@@ -50,7 +50,10 @@ MUST assert that the input float array is the same after encoding and decoding.
 
 #### To prove correct in an invalid case (`valid:false`), one MUST
 
-- raise an exception when attempting to encode a document from the numeric values, dtype, and padding.
+- if the vector field is present, raise an exception when attempting to encode a document from the numeric values,
+    dtype, and padding.
+- if the canonical_bson field is present, raise an exception when attempting to deserialize it into the corresponding
+    numeric values, as the field contains corrupted data.
 
 ## FAQ
 

src/tests/spec/json/bson-binary-vector/float32.json

@@ -44,8 +44,22 @@
       "vector": [127.0, 7.0],
       "dtype_hex": "0x27",
       "dtype_alias": "FLOAT32",
-      "padding": 3
+      "padding": 3,
+      "canonical_bson": "1C00000005766563746F72000A0000000927030000FE420000E04000"
+    },
+    {
+      "description": "Insufficient vector data with 3 bytes FLOAT32",
+      "valid": false,
+      "dtype_hex": "0x27",
+      "dtype_alias": "FLOAT32",
+      "canonical_bson": "1700000005766563746F7200050000000927002A2A2A00"
+    },
+    {
+      "description": "Insufficient vector data with 5 bytes FLOAT32",
+      "valid": false,
+      "dtype_hex": "0x27",
+      "dtype_alias": "FLOAT32",
+      "canonical_bson": "1900000005766563746F7200070000000927002A2A2A2A2A00"
     }
   ]
 }
-

src/tests/spec/json/bson-binary-vector/int8.json

@@ -42,7 +42,8 @@
       "vector": [127, 7],
       "dtype_hex": "0x03",
       "dtype_alias": "INT8",
-      "padding": 3
+      "padding": 3,
+      "canonical_bson": "1600000005766563746F7200040000000903037F0700"
     },
     {
       "description": "INT8 with float inputs",
@@ -54,4 +55,3 @@
     }
   ]
 }
-

src/tests/spec/json/bson-binary-vector/packed_bit.json

@@ -8,7 +8,8 @@
       "vector": [],
       "dtype_hex": "0x10",
       "dtype_alias": "PACKED_BIT",
-      "padding": 1
+      "padding": 1,
+      "canonical_bson": "1400000005766563746F72000200000009100100"
     },
     {
       "description": "Simple Vector PACKED_BIT",
@@ -61,21 +62,14 @@
       "dtype_alias": "PACKED_BIT",
       "padding": 0
     },
-    {
-      "description": "Padding specified with no vector data PACKED_BIT",
-      "valid": false,
-      "vector": [],
-      "dtype_hex": "0x10",
-      "dtype_alias": "PACKED_BIT",
-      "padding": 1
-    },
     {
       "description": "Exceeding maximum padding PACKED_BIT",
       "valid": false,
       "vector": [1],
       "dtype_hex": "0x10",
       "dtype_alias": "PACKED_BIT",
-      "padding": 8
+      "padding": 8,
+      "canonical_bson": "1500000005766563746F7200030000000910080100"
     },
     {
       "description": "Negative padding PACKED_BIT",
@@ -84,15 +78,6 @@
       "dtype_hex": "0x10",
       "dtype_alias": "PACKED_BIT",
       "padding": -1
-    },
-    {
-      "description": "Vector with float values PACKED_BIT",
-      "valid": false,
-      "vector": [127.5],
-      "dtype_hex": "0x10",
-      "dtype_alias": "PACKED_BIT",
-      "padding": 0
     }
   ]
 }
-

src/tests/spec/vector.rs

@@ -31,7 +31,7 @@ struct TestFile {
 struct Test {
     description: String,
     valid: bool,
-    vector: Vec<Number>,
+    vector: Option<Vec<Number>>,
     #[serde(
         rename = "dtype_hex",
         deserialize_with = "deserialize_u8_from_hex_string"
@@ -131,51 +131,68 @@ fn vector_from_numbers(
     }
 }
 
+// Only return the binary if it represents a valid vector; otherwise, return an error.
+fn binary_from_bytes(bson: &str, test_key: &str, description: &str) -> Result<Binary, String> {
+    let bytes = hex::decode(bson).expect(description);
+    let mut test_document = Document::from_reader(bytes.as_slice()).expect(description);
+    let bson = test_document.remove(test_key).expect(description);
+    let binary = match bson {
+        Bson::Binary(binary) => binary,
+        other => panic!("{}: expected binary, got {}", description, other),
+    };
+    if let Err(error) = Vector::try_from(&binary) {
+        Err(error.to_string())
+    } else {
+        Ok(binary)
+    }
+}
+
 fn run_test_file(test_file: TestFile) {
     for test in test_file.tests {
         let description = format!("{} ({})", test.description, test_file.description);
 
-        let test_vector = match (
-            vector_from_numbers(test.vector, test.d_type, test.padding),
-            test.valid,
-        ) {
-            (Ok(vector), true) => vector,
-            (Err(_), false) => return,
-            (Ok(vector), false) => panic!(
-                "{}: valid was false but successfully constructed vector {:?}",
-                description, vector
-            ),
-            (Err(error), true) => panic!(
-                "{}: valid was true but vector construction failed with error {}",
-                description, error
-            ),
+        let test_vector = match test.vector {
+            Some(vector) => match vector_from_numbers(vector, test.d_type, test.padding) {
+                Ok(vector) => {
+                    assert!(test.valid, "{}", description);
+                    Some(vector)
+                }
+                Err(error) => {
+                    assert!(!test.valid, "{}: {}", description, error);
+                    None
+                }
+            },
+            None => None,
+        };
+
+        let test_binary = match test.canonical_bson {
+            Some(bson) => match binary_from_bytes(&bson, &test_file.test_key, &description) {
+                Ok(vector) => {
+                    assert!(test.valid, "{}", description);
+                    Some(vector)
+                }
+                Err(error) => {
+                    assert!(!test.valid, "{}: {}", description, error);
+                    None
+                }
+            },
+            None => None,
         };
 
-        let Some(canonical_bson) = test.canonical_bson else {
+        let (Some(test_vector), Some(test_binary)) = (test_vector, test_binary) else {
             return;
         };
 
-        let bytes = hex::decode(canonical_bson).expect(&description);
-        let mut test_document = Document::from_reader(bytes.as_slice()).expect(&description);
-        // Rename the field to match the name used in the struct below.
-        let vector = test_document
-            .remove(&test_file.test_key)
-            .expect(&description);
-        test_document.insert("vector", vector);
-        let bson = test_document.get("vector").expect(&description);
-        let test_binary = match bson {
-            Bson::Binary(binary) => binary,
-            other => panic!("{}: expected binary, got {}", description, other),
-        };
+        let test_document = doc! { "vector": &test_binary };
 
         // TryFrom<Binary> for Vector
-        let parsed_vector = Vector::try_from(test_binary).expect(&description);
+        let parsed_vector = Vector::try_from(&test_binary).expect(&description);
         assert_eq!(parsed_vector, test_vector);
 
         // From<Vector> for Binary
         let binary = Binary::from(&test_vector);
         assert_eq!(binary.subtype, BinarySubtype::Vector);
-        assert_eq!(&binary, test_binary);
+        assert_eq!(binary, test_binary);
 
         // From<Vector> for Bson
         let document = doc! { "vector": &test_vector };