Function substring_by_char

arrow-string/src/substring.rs:192–227

Substrings based on character index # Arguments `array` - The input string array `start` - The start index of all substrings. If `start >= 0`, then count from the start of the string, otherwise count from the end of the string. `length`(option) - The length of all substrings. If `length` is `None`, then the substring is from `start` to the end of the string. Attention: Both `start` and `length

(
    array: &GenericStringArray<OffsetSize>,
    start: i64,
    length: Option<u64>,
)

/// assert_eq!(result, StringArray::from(vec![Some("rrow"), None, Some(" ⊢x:")]));
/// ```
pub fn substring_by_char<OffsetSize: OffsetSizeTrait>(
    array: &GenericStringArray<OffsetSize>,
    start: i64,
    length: Option<u64>,
) -> Result<GenericStringArray<OffsetSize>, ArrowError> {
    let mut vals = BufferBuilder::<u8>::new({
        let offsets = array.value_offsets();
        (offsets[array.len()] - offsets[0]).to_usize().unwrap()
    });
    let mut new_offsets = BufferBuilder::<OffsetSize>::new(array.len() + 1);
    new_offsets.append(OffsetSize::zero());
    let length = length.map(|len| len.to_usize().unwrap());

    array.iter().for_each(|val| {
        if let Some(val) = val {
            let char_count = val.chars().count();
            let start = if start >= 0 {
                start.to_usize().unwrap()
            } else {
                char_count - (-start).to_usize().unwrap().min(char_count)
            };
            let (start_offset, end_offset) = get_start_end_offset(val, start, length);
            vals.append_slice(&val.as_bytes()[start_offset..end_offset]);
        }
        new_offsets.append(OffsetSize::from_usize(vals.len()).unwrap());
    });
    let offsets = OffsetBuffer::new(new_offsets.finish().into());
    let values = vals.finish();
    let nulls = array
        .nulls()
        .map(|n| n.inner().sliced())
        .and_then(|b| NullBuffer::from_unsliced_buffer(b, array.len()));
    Ok(GenericStringArray::<OffsetSize>::new(
        offsets, values, nulls,
    ))
}

/// * `val` - string
/// * `start` - the start char index of the substring