use super::{
LOWER_EXCEPTIONS, ND_ZEROS, RUST_UNICODE_VERSION, SIGMA_CASE_IGNORABLE, SIGMA_CASED,
is_case_ignorable, is_sigma_cased, lower_exception, nd_digit,
};
#[test]
fn ascii_digits_are_seeded() {
assert_eq!(nd_digit('0'), Some(0));
assert_eq!(nd_digit('9'), Some(9));
assert_eq!(nd_digit('/'), None);
assert_eq!(nd_digit(':'), None);
assert_eq!(nd_digit('a'), None);
assert_eq!(lower_exception('A'), None);
}
#[test]
fn the_full_nd_set_reads_as_its_digits_and_nothing_else_does() {
assert_eq!(ND_ZEROS.len(), 66);
assert!(ND_ZEROS.windows(2).all(|w| w[0] + 10 <= w[1]));
let mut digits = 0;
for cp in 0..=0x10_FFFF_u32 {
let Some(c) = char::from_u32(cp) else {
continue;
};
let run = ND_ZEROS.iter().find(|&&z| (z..z + 10).contains(&cp));
match run {
Some(&zero) => {
digits += 1;
assert!(c.is_numeric(), "U+{cp:04X}");
assert_eq!(nd_digit(c), u8::try_from(cp - zero).ok(), "U+{cp:04X}");
}
None => assert_eq!(nd_digit(c), None, "U+{cp:04X}"),
}
}
assert_eq!(digits, 660);
}
#[test]
fn non_ascii_digits_python_knows_read_and_newer_ones_do_not() {
assert_eq!(nd_digit('\u{0667}'), Some(7));
assert_eq!(nd_digit('\u{FF13}'), Some(3));
assert_eq!(nd_digit('\u{1D7FF}'), Some(9));
assert!('\u{10D40}'.is_numeric());
assert_eq!(nd_digit('\u{10D40}'), None);
}
#[test]
fn every_lower_exception_differs_from_rust() {
assert_eq!(LOWER_EXCEPTIONS.len(), 55);
assert!(LOWER_EXCEPTIONS.windows(2).all(|w| w[0].0 < w[1].0));
for &(cp, python) in LOWER_EXCEPTIONS {
let c = char::from_u32(cp).unwrap();
let rust: String = c.to_lowercase().collect();
assert_ne!(rust, python, "U+{cp:04X}");
assert_eq!(lower_exception(c), Some(python), "U+{cp:04X}");
}
assert_eq!(lower_exception('\u{A7CB}'), Some("\u{A7CB}"));
assert_eq!('\u{A7CB}'.to_lowercase().next(), Some('\u{0264}'));
}
#[test]
fn the_sigma_classes_are_unicode_14s() {
for t in [SIGMA_CASED, SIGMA_CASE_IGNORABLE] {
assert!(t.iter().all(|&(a, b)| a <= b));
assert!(t.windows(2).all(|w| w[0].1 + 1 < w[1].0));
}
for c in ['A', 'z', '\u{3A3}', '\u{1F88}'] {
assert!(is_sigma_cased(c) && !is_case_ignorable(c), "{c:?}");
}
for c in ['.', '\'', '\u{301}', '\u{2B0}'] {
assert!(is_case_ignorable(c) && !is_sigma_cased(c), "{c:?}");
}
for c in [' ', '0', '\u{5D0}'] {
assert!(!is_case_ignorable(c) && !is_sigma_cased(c), "{c:?}");
}
for c in ['\u{A7CB}', '\u{1E030}'] {
assert!(!is_case_ignorable(c) && !is_sigma_cased(c), "{c:?}");
}
assert!("\u{A7CB}\u{3A3}".to_lowercase().ends_with('\u{3C2}'));
assert!("A\u{1E030}\u{3A3}".to_lowercase().ends_with('\u{3C2}'));
}
#[test]
fn the_exceptions_were_generated_for_this_toolchain() {
assert_eq!(
char::UNICODE_VERSION,
RUST_UNICODE_VERSION,
"Rust's Unicode moved: run tools/gen/gen_tables.py"
);
}