scirs2-text 0.6.2

Text processing module for SciRS2 (scirs2-text)
Documentation
# 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 = "scirs2-text"
version = "0.6.2"
authors = ["COOLJAPAN OU (Team KitaSan)"]
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Text processing module for SciRS2 (scirs2-text)"
readme = "README.md"
keywords = [
    "text",
    "nlp",
    "scientific",
    "ai",
    "machine-learning",
]
categories = [
    "science",
    "mathematics",
    "algorithms",
]
license = "Apache-2.0"
repository = "https://github.com/cool-japan/scirs"

[package.metadata.docs.rs]
all-features = true
rustdoc-args = [
    "--cfg",
    "docsrs",
]

[features]
default = []
serde-support = [
    "dep:serde",
    "dep:serde_json",
]
simd = ["scirs2-core/simd"]
tokenization = []

[lib]
name = "scirs2_text"
path = "src/lib.rs"

[[example]]
name = "bpe_tokenization_demo"
path = "examples/bpe_tokenization_demo.rs"

[[example]]
name = "bpe_tokenizer_example"
path = "examples/bpe_tokenizer_example.rs"

[[example]]
name = "complete_integration"
path = "examples/complete_integration.rs"

[[example]]
name = "enhanced_vectorization_demo"
path = "examples/enhanced_vectorization_demo.rs"

[[example]]
name = "ml_integration_demo"
path = "examples/ml_integration_demo.rs"

[[example]]
name = "ml_sentiment_demo"
path = "examples/ml_sentiment_demo.rs"

[[example]]
name = "multilingual_demo"
path = "examples/multilingual_demo.rs"

[[example]]
name = "parallel_processing_demo"
path = "examples/parallel_processing_demo.rs"

[[example]]
name = "rule_lemmatizer_demo"
path = "examples/rule_lemmatizer_demo.rs"

[[example]]
name = "sentiment_analysis_demo"
path = "examples/sentiment_analysis_demo.rs"

[[example]]
name = "spelling_correction_demo"
path = "examples/spelling_correction_demo.rs"

[[example]]
name = "statistical_spelling_demo"
path = "examples/statistical_spelling_demo.rs"

[[example]]
name = "stemmer_benchmark"
path = "examples/stemmer_benchmark.rs"

[[example]]
name = "stemming_comparison_demo"
path = "examples/stemming_comparison_demo.rs"

[[example]]
name = "summarization_demo"
path = "examples/summarization_demo.rs"

[[example]]
name = "text_classification_demo"
path = "examples/text_classification_demo.rs"

[[example]]
name = "text_mode_demo"
path = "examples/text_mode_demo.rs"

[[example]]
name = "text_processing_demo"
path = "examples/text_processing_demo.rs"

[[example]]
name = "token_filtering_demo"
path = "examples/token_filtering_demo.rs"

[[example]]
name = "topic_coherence_demo"
path = "examples/topic_coherence_demo.rs"

[[example]]
name = "topic_modeling_demo"
path = "examples/topic_modeling_demo.rs"

[[example]]
name = "word2vec_example"
path = "examples/word2vec_example.rs"

[[test]]
name = "basic_functionality"
path = "tests/basic_functionality.rs"

[[test]]
name = "cross_lingual_tests"
path = "tests/cross_lingual_tests.rs"

[[test]]
name = "hdp_tests"
path = "tests/hdp_tests.rs"

[[test]]
name = "language_agnostic_tokenizer_tests"
path = "tests/language_agnostic_tokenizer_tests.rs"

[[test]]
name = "neural_nlp_tests"
path = "tests/neural_nlp_tests.rs"

[[test]]
name = "perplexity_tests"
path = "tests/perplexity_tests.rs"

[[test]]
name = "semantic_similarity_tests"
path = "tests/semantic_similarity_tests.rs"

[[test]]
name = "simcse_tests"
path = "tests/simcse_tests.rs"

[[test]]
name = "sts_evaluation_tests"
path = "tests/sts_evaluation_tests.rs"

[[test]]
name = "transliteration_tests"
path = "tests/transliteration_tests.rs"

[[test]]
name = "universal_encoder_tests"
path = "tests/universal_encoder_tests.rs"

[[bench]]
name = "nlp_benchmarks"
path = "benches/nlp_benchmarks.rs"

[dependencies.approx]
version = "0.5.1"

[dependencies.chrono]
version = "0.4.45"

[dependencies.lazy_static]
version = "1.5"

[dependencies.memmap2]
version = "0.9.11"

[dependencies.num_cpus]
version = "1.17.0"

[dependencies.regex]
version = "1.12.4"

[dependencies.scirs2-core]
version = "0.6.2"
features = [
    "parallel",
    "simd",
    "array",
    "random",
]
default-features = false

[dependencies.scirs2-linalg]
version = "0.6.2"
default-features = false

[dependencies.serde]
version = "1.0"
features = ["derive"]
optional = true

[dependencies.serde_json]
version = "1.0"
optional = true

[dependencies.statrs]
version = "0.18.0"

[dependencies.tempfile]
version = "3.27.0"

[dependencies.thiserror]
version = "2.0.18"

[dependencies.unicode-normalization]
version = "0.1"

[dependencies.unicode-segmentation]
version = "1.13"

[dev-dependencies.criterion]
version = "0.8.2"

[lints.clippy]
expect_used = "allow"
len_zero = "allow"
unwrap_used = "warn"

[lints.rust]
dead_code = "allow"
mismatched_lifetime_syntaxes = "allow"
unknown_lints = "allow"
unpredictable_function_pointer_comparisons = "allow"
unused_imports = "allow"
unused_mut = "allow"
unused_variables = "allow"