Jefffrey commented on code in PR #9220:
URL: https://github.com/apache/arrow-rs/pull/9220#discussion_r2730456687
##########
arrow-cast/src/cast/mod.rs:
##########
@@ -5718,6 +5718,418 @@ mod tests {
assert_eq!(dict_array.values().len(), 3);
}
+ #[test]
+ fn test_cast_string_array_to_dict_utf8_view() {
+ let array = StringArray::from(vec![Some("one"), None, Some("three"),
Some("one")]);
+
+ let cast_type =
+ DataType::Dictionary(Box::new(DataType::UInt16),
Box::new(DataType::Utf8View));
+ let cast_array = cast(&array, &cast_type).unwrap();
+ assert_eq!(cast_array.data_type(), &cast_type);
+
+ let dict_array = cast_array
+ .as_any()
+ .downcast_ref::<DictionaryArray<UInt16Type>>()
+ .unwrap();
Review Comment:
```suggestion
let dict_array = cast_array.as_dictionary::<UInt16Type>();
```
Less verbose casting
##########
arrow-cast/src/cast/mod.rs:
##########
@@ -5718,6 +5718,418 @@ mod tests {
assert_eq!(dict_array.values().len(), 3);
}
+ #[test]
+ fn test_cast_string_array_to_dict_utf8_view() {
+ let array = StringArray::from(vec![Some("one"), None, Some("three"),
Some("one")]);
+
+ let cast_type =
+ DataType::Dictionary(Box::new(DataType::UInt16),
Box::new(DataType::Utf8View));
+ let cast_array = cast(&array, &cast_type).unwrap();
Review Comment:
Can we also assert `can_cast_types` alongside these tests?
##########
arrow-cast/src/cast/mod.rs:
##########
@@ -5718,6 +5718,418 @@ mod tests {
assert_eq!(dict_array.values().len(), 3);
}
+ #[test]
+ fn test_cast_string_array_to_dict_utf8_view() {
+ let array = StringArray::from(vec![Some("one"), None, Some("three"),
Some("one")]);
+
+ let cast_type =
+ DataType::Dictionary(Box::new(DataType::UInt16),
Box::new(DataType::Utf8View));
+ let cast_array = cast(&array, &cast_type).unwrap();
+ assert_eq!(cast_array.data_type(), &cast_type);
+
+ let dict_array = cast_array
+ .as_any()
+ .downcast_ref::<DictionaryArray<UInt16Type>>()
+ .unwrap();
+ assert_eq!(dict_array.values().data_type(), &DataType::Utf8View);
+ assert_eq!(dict_array.values().len(), 2); // "one" and "three"
deduplicated
+
+ let typed = dict_array.downcast_dict::<StringViewArray>().unwrap();
+ let actual: Vec<Option<&str>> = typed.into_iter().collect();
+ assert_eq!(actual, vec![Some("one"), None, Some("three"),
Some("one")]);
+
+ let keys = dict_array.keys();
+ assert!(keys.is_null(1));
+ assert_eq!(keys.value(0), keys.value(3));
+ assert_ne!(keys.value(0), keys.value(2));
+ }
+
+ #[test]
+ fn test_cast_string_array_to_dict_utf8_view_null_vs_literal_null() {
+ let array = StringArray::from(vec![Some("one"), None, Some("null"),
Some("one")]);
+
+ let cast_type =
+ DataType::Dictionary(Box::new(DataType::UInt16),
Box::new(DataType::Utf8View));
+ let cast_array = cast(&array, &cast_type).unwrap();
+ assert_eq!(cast_array.data_type(), &cast_type);
+
+ let dict_array = cast_array
+ .as_any()
+ .downcast_ref::<DictionaryArray<UInt16Type>>()
+ .unwrap();
+ assert_eq!(dict_array.values().data_type(), &DataType::Utf8View);
+ assert_eq!(dict_array.values().len(), 2);
+
+ let typed = dict_array.downcast_dict::<StringViewArray>().unwrap();
+ let actual: Vec<Option<&str>> = typed.into_iter().collect();
+ assert_eq!(actual, vec![Some("one"), None, Some("null"), Some("one")]);
+
+ let keys = dict_array.keys();
+ assert!(keys.is_null(1));
+ assert_eq!(keys.value(0), keys.value(3));
+ assert_ne!(keys.value(0), keys.value(2));
+ }
+
+ #[test]
+ fn test_cast_string_view_array_to_dict_utf8_view_null_vs_literal_null() {
+ let array = StringArray::from(vec![Some("one"), None, Some("null"),
Some("one")]);
+ let view = cast(&array, &DataType::Utf8View).unwrap();
Review Comment:
Might as well just construct the view array directly instead of casting it
from a string array? Since we're testing dict casting
Actually how does this test differ from the above one? 🤔
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
