Verify valid UTF-8 when converting byte array (#2205) (#2686)

* Verify valid UTF-8 when converting byte array (#2205)

* Add doc comment

arrow/src/array/array_string.rs

@@ -129,8 +129,13 @@ impl<OffsetSize: OffsetSizeTrait> GenericStringArray<OffsetSize> {
     }
 
     /// Convert a list array to a string array.
-    /// This method is unsound because it does
-    /// not check the utf-8 validation for each element.
+    ///
+    /// Note: this performs potentially expensive UTF-8 validation, consider using
+    /// [`StringBuilder`][crate::array::StringBuilder] to avoid this
+    ///
+    /// # Panics
+    ///
+    /// This method panics if the array contains non-UTF-8 data
     fn from_list(v: GenericListArray<OffsetSize>) -> Self {
         assert_eq!(
             v.data_ref().child_data().len(),
@@ -164,8 +169,7 @@ impl<OffsetSize: OffsetSizeTrait> GenericStringArray<OffsetSize> {
             .add_buffer(child_data.buffers()[0].slice(child_data.offset()))
             .null_bit_buffer(v.data().null_buffer().cloned());
 
-        let array_data = unsafe { builder.build_unchecked() };
-        Self::from(array_data)
+        Self::from(builder.build().unwrap())
     }
 
     /// Creates a [`GenericStringArray`] based on an iterator of values without nulls
@@ -352,8 +356,7 @@ impl<OffsetSize: OffsetSizeTrait> From<GenericBinaryArray<OffsetSize>>
 {
     fn from(v: GenericBinaryArray<OffsetSize>) -> Self {
         let builder = v.into_data().into_builder().data_type(Self::DATA_TYPE);
-        let data = unsafe { builder.build_unchecked() };
-        Self::from(data)
+        Self::from(builder.build().unwrap())
     }
 }
 

arrow/src/array/builder/generic_string_builder.rs

@@ -15,7 +15,7 @@
 // specific language governing permissions and limitations
 // under the License.
 
-use crate::array::{ArrayBuilder, ArrayRef, GenericStringArray, OffsetSizeTrait};
+use crate::array::{Array, ArrayBuilder, ArrayRef, GenericStringArray, OffsetSizeTrait};
 use std::any::Any;
 use std::sync::Arc;
 
@@ -67,7 +67,15 @@ impl<OffsetSize: OffsetSizeTrait> GenericStringBuilder<OffsetSize> {
 
     /// Builds the [`GenericStringArray`] and reset this builder.
     pub fn finish(&mut self) -> GenericStringArray<OffsetSize> {
-        GenericStringArray::<OffsetSize>::from(self.builder.finish())
+        let t = GenericStringArray::<OffsetSize>::DATA_TYPE;
+        let v = self.builder.finish();
+        let builder = v.into_data().into_builder().data_type(t);
+
+        // SAFETY:
+        // Data must be UTF-8 as only support writing `str`
+        // Offsets must be valid as guaranteed by `GenericBinaryBuilder`
+        let data = unsafe { builder.build_unchecked() };
+        data.into()
     }
 
     /// Returns the current values buffer as a slice