SliceIterator of last bytes is not correct

[ritchie46]

This slicing stress test will make us more sure of the future. 🙂 (once it passes)

Cargo.toml

[dependencies]
arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "86edfd639b33d9fbc468e2f68bb6ce41de52f95e", default-features = false, features=["compute"]}
rand = "0.8"

main.rs

use rand::Rng;
use arrow::array::{Utf8Array, BooleanArray, Array};
use rand::distributions::{
    Alphanumeric, Uniform, Bernoulli
};
use arrow::compute::filter::filter;
use std::iter::FromIterator;

fn main() {
    let mut rng = rand::thread_rng();
    let length = 50000;

    let values_iter = (0..length).map(|_| {
        let len = (&mut rng).sample(Uniform::new(0usize, 8));
        let s: String = (&mut rng).sample_iter(&Alphanumeric).take(len).map(char::from).collect();
        s
    });


    let arr = Utf8Array::<i32>::from_iter_values(values_iter);
    let values_iter = (0..length).map(|_| {
        let v: bool = (&mut rng).sample(Bernoulli::new(0.5).unwrap());
        Some(v)
    });
    let mask = BooleanArray::from_iter(values_iter);

    for offset in 100usize..(length - 1) {
        let len = (&mut rng).sample(Uniform::new(0, length - offset));
        let arr_s = arr.slice(offset, len);
        let mask_s = mask.slice(offset, len);

        filter(&arr_s, &mask_s).unwrap();
    }
}

Run

RUST_BACKTRACE=1 cargo run --release

Panic

thread 'main' panicked at 'range end index 41006 out of range for slice of length 41001', /home/ritchie46/.cargo/git/checkouts/arrow2-8a2ad61d97265680/86edfd6/src/array/growable/utf8.rs:75:14
stack backtrace:
   0: rust_begin_unwind
             at /rustc/492723897e9b4db6701b3a75b72618d08a7d5319/library/std/src/panicking.rs:516:5
   1: core::panicking::panic_fmt
             at /rustc/492723897e9b4db6701b3a75b72618d08a7d5319/library/core/src/panicking.rs:93:14
   2: core::slice::index::slice_end_index_len_fail
             at /rustc/492723897e9b4db6701b3a75b72618d08a7d5319/library/core/src/slice/index.rs:41:5
   3: <core::ops::range::Range<usize> as core::slice::index::SliceIndex<[T]>>::index
             at /rustc/492723897e9b4db6701b3a75b72618d08a7d5319/library/core/src/slice/index.rs:240:13
   4: core::slice::index::<impl core::ops::index::Index<I> for [T]>::index
             at /rustc/492723897e9b4db6701b3a75b72618d08a7d5319/library/core/src/slice/index.rs:15:9
   5: <arrow2::array::growable::utf8::GrowableUtf8<O> as arrow2::array::growable::Growable>::extend
             at /home/ritchie46/.cargo/git/checkouts/arrow2-8a2ad61d97265680/86edfd6/src/array/growable/utf8.rs:75:14
   6: arrow2::compute::filter::filter::{{closure}}
             at /home/ritchie46/.cargo/git/checkouts/arrow2-8a2ad61d97265680/86edfd6/src/compute/filter.rs:244:42
   7: core::iter::traits::iterator::Iterator::for_each::call::{{closure}}
             at /rustc/492723897e9b4db6701b3a75b72618d08a7d5319/library/core/src/iter/traits/iterator.rs:734:29
   8: core::iter::traits::iterator::Iterator::fold
             at /rustc/492723897e9b4db6701b3a75b72618d08a7d5319/library/core/src/iter/traits/iterator.rs:2174:21
   9: core::iter::traits::iterator::Iterator::for_each
             at /rustc/492723897e9b4db6701b3a75b72618d08a7d5319/library/core/src/iter/traits/iterator.rs:737:9
  10: arrow2::compute::filter::filter
             at /home/ritchie46/.cargo/git/checkouts/arrow2-8a2ad61d97265680/86edfd6/src/compute/filter.rs:244:13
  11: memcheck::main
             at ./src/main.rs:32:9
  12: core::ops::function::FnOnce::call_once
             at /rustc/492723897e9b4db6701b3a75b72618d08a7d5319/library/core/src/ops/function.rs:227:5
note: Some details are omitted, run with `RUST_BACKTRACE=full` for a verbose backtrace.