# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO # # When uploading crates to the registry Cargo will automatically # "normalize" Cargo.toml files for maximal compatibility # with all versions of Cargo and also rewrite `path` dependencies # to registry (e.g., crates.io) dependencies. # # If you are reading this file be aware that the original Cargo.toml # will likely look very different (and much more reasonable). # See Cargo.toml.orig for the original contents. [package] edition = "2021" name = "charabia" version = "0.9.2" authors = ["Many "] build = false exclude = ["dictionaries/txt/thai/words.txt"] autobins = false autoexamples = false autotests = false autobenches = false description = "A simple library to detect the language, tokenize the text and normalize the tokens" documentation = "https://docs.rs/charabia" readme = "README.md" keywords = [ "segmenter", "tokenizer", "normalize", "language", ] categories = ["text-processing"] license = "MIT" repository = "https://github.com/meilisearch/charabia" [lib] name = "charabia" path = "src/lib.rs" [[bench]] name = "bench" path = "benches/bench.rs" harness = false [dependencies.aho-corasick] version = "1.1.3" [dependencies.csv] version = "1.3.0" [dependencies.either] version = "1.13.0" [dependencies.finl_unicode] version = "1.2.0" optional = true [dependencies.fst] version = "0.4" [dependencies.irg-kvariants] version = "=0.1.1" [dependencies.jieba-rs] version = "0.7" optional = true [dependencies.lindera] version = "=0.32.2" optional = true default-features = false [dependencies.once_cell] version = "1.19.0" [dependencies.pinyin] version = "0.10" features = ["with_tone"] optional = true default-features = false [dependencies.serde] version = "1.0.192" [dependencies.slice-group-by] version = "0.3.1" [dependencies.unicode-normalization] version = "0.1.23" [dependencies.wana_kana] version = "4.0.0" optional = true [dependencies.whatlang] version = "0.16.4" [dev-dependencies.criterion] version = "0.5" [dev-dependencies.mimalloc] version = "0.1.43" [dev-dependencies.quickcheck] version = "1" [dev-dependencies.quickcheck_macros] version = "1" [features] chinese = [ "chinese-segmentation", "chinese-normalization", ] chinese-normalization = [] chinese-normalization-pinyin = [ "dep:pinyin", "chinese-normalization", ] chinese-segmentation = ["dep:jieba-rs"] default = [ "chinese", "hebrew", "japanese", "thai", "korean", "greek", "khmer", "vietnamese", "swedish-recomposition", "turkish", "german-segmentation", ] german-segmentation = [] greek = [] hebrew = [] japanese = [ "japanese-segmentation-unidic", "japanese-transliteration", ] japanese-segmentation-ipadic = [ "lindera/ipadic", "lindera/compress", ] japanese-segmentation-unidic = [ "lindera/unidic", "lindera/compress", ] japanese-transliteration = ["dep:wana_kana"] khmer = [] korean = [ "lindera/ko-dic", "lindera/compress", ] latin-camelcase = ["dep:finl_unicode"] latin-snakecase = ["dep:finl_unicode"] swedish-recomposition = [] thai = [] turkish = [] vietnamese = []