├── .github └── workflows │ └── rust.yml ├── .gitignore ├── COPYRIGHT ├── Cargo.toml ├── LICENSE-APACHE ├── LICENSE-MIT ├── README.md ├── benches ├── chars.rs ├── texts │ ├── LICENSE │ ├── README │ ├── arabic.txt │ ├── english.txt │ ├── hindi.txt │ ├── japanese.txt │ ├── korean.txt │ ├── log.txt │ ├── mandarin.txt │ ├── russian.txt │ └── source_code.txt ├── unicode_word_indices.rs ├── word_bounds.rs └── words.rs ├── fuzz ├── .gitignore ├── Cargo.toml └── fuzz_targets │ └── fuzz_target_1.rs ├── scripts ├── unicode.py └── unicode_gen_breaktests.py ├── src ├── grapheme.rs ├── lib.rs ├── sentence.rs ├── tables.rs └── word.rs └── tests ├── test.rs └── testdata └── mod.rs /.github/workflows/rust.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/.github/workflows/rust.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/.gitignore -------------------------------------------------------------------------------- /COPYRIGHT: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/COPYRIGHT -------------------------------------------------------------------------------- /Cargo.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/Cargo.toml -------------------------------------------------------------------------------- /LICENSE-APACHE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/LICENSE-APACHE -------------------------------------------------------------------------------- /LICENSE-MIT: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/LICENSE-MIT -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/README.md -------------------------------------------------------------------------------- /benches/chars.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/chars.rs -------------------------------------------------------------------------------- /benches/texts/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/LICENSE -------------------------------------------------------------------------------- /benches/texts/README: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/README -------------------------------------------------------------------------------- /benches/texts/arabic.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/arabic.txt -------------------------------------------------------------------------------- /benches/texts/english.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/english.txt -------------------------------------------------------------------------------- /benches/texts/hindi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/hindi.txt -------------------------------------------------------------------------------- /benches/texts/japanese.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/japanese.txt -------------------------------------------------------------------------------- /benches/texts/korean.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/korean.txt -------------------------------------------------------------------------------- /benches/texts/log.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/log.txt -------------------------------------------------------------------------------- /benches/texts/mandarin.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/mandarin.txt -------------------------------------------------------------------------------- /benches/texts/russian.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/russian.txt -------------------------------------------------------------------------------- /benches/texts/source_code.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/texts/source_code.txt -------------------------------------------------------------------------------- /benches/unicode_word_indices.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/unicode_word_indices.rs -------------------------------------------------------------------------------- /benches/word_bounds.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/word_bounds.rs -------------------------------------------------------------------------------- /benches/words.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/benches/words.rs -------------------------------------------------------------------------------- /fuzz/.gitignore: -------------------------------------------------------------------------------- 1 | 2 | target 3 | corpus 4 | artifacts 5 | -------------------------------------------------------------------------------- /fuzz/Cargo.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/fuzz/Cargo.toml -------------------------------------------------------------------------------- /fuzz/fuzz_targets/fuzz_target_1.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/fuzz/fuzz_targets/fuzz_target_1.rs -------------------------------------------------------------------------------- /scripts/unicode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/scripts/unicode.py -------------------------------------------------------------------------------- /scripts/unicode_gen_breaktests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/scripts/unicode_gen_breaktests.py -------------------------------------------------------------------------------- /src/grapheme.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/src/grapheme.rs -------------------------------------------------------------------------------- /src/lib.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/src/lib.rs -------------------------------------------------------------------------------- /src/sentence.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/src/sentence.rs -------------------------------------------------------------------------------- /src/tables.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/src/tables.rs -------------------------------------------------------------------------------- /src/word.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/src/word.rs -------------------------------------------------------------------------------- /tests/test.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/tests/test.rs -------------------------------------------------------------------------------- /tests/testdata/mod.rs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/unicode-rs/unicode-segmentation/HEAD/tests/testdata/mod.rs --------------------------------------------------------------------------------