unic-segment 0.9.0

UNIC β€” Unicode Text Segmentation Algorithms
Documentation
// Copyright 2012-2015 The Rust Project Developers.
// Copyright 2017 The UNIC Project Developers.
//
// See the COPYRIGHT file at the top-level directory of this distribution.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.

// TODO: This could be improved with more tests like flag emoji with interspersed Extend chars and
// ZWJ

&[
    ("hello world", &["hello", " ", "world"]),

    // Long chains of flag emoji
    (
        "πŸ‡¦πŸ‡«πŸ‡¦πŸ‡½πŸ‡¦πŸ‡±πŸ‡©πŸ‡ΏπŸ‡¦πŸ‡ΈπŸ‡¦πŸ‡©πŸ‡¦πŸ‡΄",
        &["πŸ‡¦πŸ‡«", "πŸ‡¦πŸ‡½", "πŸ‡¦πŸ‡±", "πŸ‡©πŸ‡Ώ", "πŸ‡¦πŸ‡Έ", "πŸ‡¦πŸ‡©", "πŸ‡¦πŸ‡΄"],
    ),

    // Long chains of flag emoji
    (
        "πŸ‡¦πŸ‡«πŸ‡¦πŸ‡½πŸ‡¦πŸ‡±πŸ‡©πŸ‡ΏπŸ‡¦πŸ‡ΈπŸ‡¦πŸ‡©πŸ‡¦",
        &["πŸ‡¦πŸ‡«", "πŸ‡¦πŸ‡½", "πŸ‡¦πŸ‡±", "πŸ‡©πŸ‡Ώ", "πŸ‡¦πŸ‡Έ", "πŸ‡¦πŸ‡©", "πŸ‡¦"],
    ),

    // Long chains of flag emoji
    (
        "πŸ‡¦aπŸ‡«πŸ‡¦πŸ‡½aπŸ‡¦πŸ‡±πŸ‡©πŸ‡ΏπŸ‡¦πŸ‡ΈπŸ‡¦πŸ‡©πŸ‡¦",
        &["πŸ‡¦", "a", "πŸ‡«πŸ‡¦", "πŸ‡½", "a", "πŸ‡¦πŸ‡±", "πŸ‡©πŸ‡Ώ", "πŸ‡¦πŸ‡Έ", "πŸ‡¦πŸ‡©", "πŸ‡¦"],
    ),

    (
        "\u{1f468}\u{200d}\u{1f468}\u{200d}\u{1f466}",
        &["\u{1f468}\u{200d}\u{1f468}\u{200d}\u{1f466}"],
    ),

    (
        "πŸ˜ŒπŸ‘ŽπŸΌ",
        &["😌", "πŸ‘ŽπŸΌ"],
    ),

    (
        "πŸ‡¨πŸ‡¦πŸ‡¨πŸ‡­πŸ‡ΏπŸ‡²πŸ‡Ώ hi",
        &["πŸ‡¨πŸ‡¦", "πŸ‡¨πŸ‡­", "πŸ‡ΏπŸ‡²", "πŸ‡Ώ", " ", "hi"],
    ),
]