[package]
edition = "2021"
name = "langsan"
version = "0.0.14"
authors = ["Michael de Gans <michael.john.degans@gmail.com>"]
build = "build.rs"
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "A library for sanitizing language model input and output."
homepage = "https://github.com/mdegans/langsan"
readme = "README.md"
keywords = [
"sanitization",
"language",
"model",
]
categories = ["text-processing"]
license = "MIT"
repository = "https://github.com/mdegans/langsan"
[features]
aegean-numbers = []
alchemical-symbols = []
alphabetic-presentation-forms = []
anatolian-hieroglyphs = []
ancient-greek-musical-notation = []
ancient-greek-numbers = []
ancient-symbols = []
arabic = []
arabic-extended-a = []
arabic-extended-b = []
arabic-extended-c = []
arabic-mathematical-alphabetic-symbols = []
arabic-presentation-forms-a = []
arabic-presentation-forms-b = []
arabic-supplement = []
armenian = []
arrows = []
avestan = []
balinese = []
bamum = []
bamum-supplement = []
batak = []
bengali = []
bidi = []
block-elements = []
bopomofo = []
bopomofo-extended = []
box-drawing = []
braille-patterns = []
buginese = []
buhid = []
byzantine-musical-symbols = []
carian = []
caucasian-albanian = []
cham = []
cherokee = []
cherokee-supplement = []
chess-symbols = []
cjk-compatibility = []
cjk-compatibility-forms = []
cjk-compatibility-ideographs = []
cjk-compatibility-ideographs-supplement = []
cjk-radicals-supplement = []
cjk-strokes = []
cjk-symbols-and-punctuation = []
cjk-unified-ideographs = []
cjk-unified-ideographs-extension-a = []
cjk-unified-ideographs-extension-b = []
cjk-unified-ideographs-extension-c = []
cjk-unified-ideographs-extension-d = []
cjk-unified-ideographs-extension-e = []
cjk-unified-ideographs-extension-f = []
cjk-unified-ideographs-extension-g = []
cjk-unified-ideographs-extension-h = []
cjk-unified-ideographs-extension-i = []
combining-diacritical-marks = []
combining-diacritical-marks-extended = []
combining-diacritical-marks-for-symbols = []
combining-diacritical-marks-supplement = []
combining-half-marks = []
common-indic-number-forms = []
control-pictures = []
coptic = []
coptic-epact-numbers = []
counting-rod-numerals = []
cow = []
cuneiform = []
cuneiform-numbers-and-punctuation = []
currency-symbols = []
cypriot-syllabary = []
cypro-minoan = []
cyrillic = []
cyrillic-extended-a = []
cyrillic-extended-b = []
cyrillic-extended-c = []
cyrillic-extended-d = []
cyrillic-supplement = []
default = ["general-punctuation"]
deseret = []
devanagari = []
devanagari-extended = []
devanagari-extended-a = []
dingbats = []
dives-akuru = []
dogra = []
domino-tiles = []
dutch = ["latin-1-supplement"]
early-dynastic-cuneiform = []
egyptian-hieroglyph-format-controls = []
egyptian-hieroglyphs = []
elbasan = []
emoji = [
"miscellaneous-symbols-and-pictographs",
"emoticons-emoji",
"ornamental-dingbats",
"transport-and-map-symbols",
"alchemical-symbols",
"geometric-shapes-extended",
"supplemental-arrows-c",
"supplemental-symbols-and-pictographs",
"chess-symbols",
"symbols-and-pictographs-extended-a",
"symbols-for-legacy-computing",
]
emoticons-emoji = []
enclosed-alphanumeric-supplement = []
enclosed-alphanumerics = []
enclosed-cjk-letters-and-months = []
enclosed-ideographic-supplement = []
english = []
ethiopic = []
ethiopic-extended = []
ethiopic-extended-a = []
ethiopic-extended-b = []
ethiopic-supplement = []
french = ["latin-1-supplement"]
general-punctuation = []
geometric-shapes = []
geometric-shapes-extended = []
georgian = []
georgian-extended = []
georgian-supplement = []
german = ["latin-1-supplement"]
glagolitic = []
glagolitic-supplement = []
gothic = []
greek-and-coptic = []
greek-extended = []
gujarati = []
gunjala-gondi = []
gurmukhi = []
halfwidth-and-fullwidth-forms = []
hangul-compatibility-jamo = []
hangul-jamo = []
hangul-jamo-extended-a = []
hangul-jamo-extended-b = []
hangul-syllables = []
hanifi-rohingya = []
hanunoo = []
hatran = []
hebrew = []
high-surrogates = []
hiragana = []
ideographic-description-characters = []
ideographic-symbols-and-punctuation = []
imperial-aramaic = []
indic-siyaq-numbers = []
inscriptional-pahlavi = []
inscriptional-parthian = []
ipa-extensions = []
italian = ["latin-1-supplement"]
javanese = []
kaktovik-numerals = []
kana-extended-a = []
kana-extended-b = []
kana-supplement = []
kanbun = []
kangxi-radicals = []
kannada = []
katakana = []
katakana-phonetic-extensions = []
kayah-li = []
kharoshthi = []
khitan-small-script = []
khmer = []
khmer-symbols = []
lao = []
latin-1-supplement = []
latin-extended-a = []
latin-extended-additional = []
latin-extended-b = []
latin-extended-c = []
latin-extended-d = []
latin-extended-e = []
latin-extended-f = []
latin-extended-g = []
lepcha = []
letterlike-symbols = []
limbu = []
linear-a = []
linear-b-ideograms = []
linear-b-syllabary = []
lisu = []
lisu-supplement = []
low-surrogates = []
lycian = []
lydian = []
mahjong-tiles = []
malayalam = []
mandaic = []
manichaean = []
masaram-gondi = []
mathematical-alphanumeric-symbols = []
mathematical-operators = []
mayan-numerals = []
meetei-mayek = []
meetei-mayek-extensions = []
mende-kikakui = []
meroitic-cursive = []
meroitic-hieroglyphs = []
miscellaneous-mathematical-symbols-a = []
miscellaneous-mathematical-symbols-b = []
miscellaneous-symbols = []
miscellaneous-symbols-and-arrows = []
miscellaneous-symbols-and-pictographs = []
miscellaneous-technical = []
modifier-tone-letters = []
mongolian = []
mongolian-supplement = []
musical-symbols = []
myanmar = []
myanmar-extended-a = []
myanmar-extended-b = []
nabataean = []
nag-mundari = []
nandinagari = []
new-tai-lue = []
nko = []
number-forms = []
nyiakeng-puachue-hmong = []
ogham = []
ol-chiki = []
old-hungarian = []
old-italic = []
old-north-arabian = []
old-permic = []
old-persian = []
old-sogdian = []
old-south-arabian = []
old-turkic = []
old-uyghur = []
optical-character-recognition = []
oriya = []
ornamental-dingbats = []
osage = []
osmanya = []
ottoman-siyaq-numbers = []
palmyrene = []
phags-pa = []
phaistos-disc = []
phoenician = []
phonetic-extensions = []
phonetic-extensions-supplement = []
playing-cards = []
portuguese = ["latin-1-supplement"]
psalter-pahlavi = []
rejang = []
rumi-numeral-symbols = []
runic = []
russian = ["cyrillic"]
samaritan = []
saurashtra = []
serde = ["dep:serde"]
shavian = []
shorthand-format-controls = []
sinhala = []
sinhala-archaic-numbers = []
small-form-variants = []
small-kana-extension = []
sogdian = []
spacing-modifier-letters = []
spanish = ["latin-1-supplement"]
specials = []
sundanese = []
sundanese-supplement = []
superscripts-and-subscripts = []
supplemental-arrows-a = []
supplemental-arrows-b = []
supplemental-arrows-c = []
supplemental-mathematical-operators = []
supplemental-punctuation = []
supplemental-symbols-and-pictographs = []
sutton-signwriting = []
syloti-nagri = []
symbols-and-pictographs-extended-a = []
symbols-for-legacy-computing = []
syriac = []
syriac-supplement = []
tagalog = []
tagbanwa = []
tai-le = []
tai-tham = []
tai-viet = []
tai-xuan-jing-symbols = []
tamil = []
tamil-supplement = []
tangut = []
tangut-components = []
tangut-supplement = []
telugu = []
thaana = []
thai = []
tibetan = []
tifinagh = []
transport-and-map-symbols = []
ugaritic = []
unified-canadian-aboriginal-syllabics = []
unified-canadian-aboriginal-syllabics-extended = []
unified-canadian-aboriginal-syllabics-extended-a = []
vai = []
variation-selectors = []
variation-selectors-supplement = []
vedic-extensions = []
verbose = []
vertical-forms = []
vithkuqi = []
warang-citi = []
yezidi = []
yi-radicals = []
yi-syllables = []
yijing-hexagram-symbols = []
zanabazar-square = []
znamenny-musical-notation = []
[lib]
name = "langsan"
path = "src/lib.rs"
[dependencies.serde]
version = "1"
features = ["derive"]
optional = true
[dev-dependencies.serde_json]
version = "1"
[build-dependencies.serde]
version = "1"
features = ["derive"]
[build-dependencies.serde_json]
version = "1"
[build-dependencies.static_assertions]
version = "1"