1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334
#![deny(clippy::all)]
#![warn(clippy::nursery, clippy::pedantic)]
//! # Spelling Alphabet
//!
//! A Rust library for transforming text strings into corresponding code words
//! based on predefined [spelling alphabets][], like the NATO phonetic alphabet.
//! These alphabets are designed to enhance verbal clarity, especially when
//! spelling out words over low-fidelity voice channels. This library supports
//! several standard alphabets and allows for customization to suit specific
//! communication needs.
//!
//! In operation, spellabet preserves the original capitalization of letters by
//! returning either lowercase or uppercase code words. It similarly converts
//! known digits and other symbols into code words, while unrecognized
//! characters are returned unconverted.
//!
//! This library powers the command line utility `spellout`, which provides a
//! handy interface for phonetic conversions. Check out [spellout on GitHub][]
//! for more information.
//!
//! [spelling alphabets]: https://en.wikipedia.org/wiki/Spelling_alphabet
//! [spellout on GitHub]: https://github.com/EarthmanMuons/spellout/
//!
//! # Example
//!
//! ```
//! use spellabet::{PhoneticConverter, SpellingAlphabet};
//!
//! let converter = PhoneticConverter::new(&SpellingAlphabet::Nato);
//! println!("{}", converter.convert("Example123!"));
//! ```
//!
//! ```text
//! ECHO x-ray alfa mike papa lima echo One Two Tree Exclamation
//! ```
use std::char;
use std::cmp::Ordering;
use std::collections::HashMap;
use code_words::{
DEFAULT_DIGITS_AND_SYMBOLS, JAN_ALPHABET, LAPD_ALPHABET, NATO_ALPHABET, ROYAL_NAVY_ALPHABET,
US_FINANCIAL_ALPHABET, WESTERN_UNION_ALPHABET,
};
use convert_case::{Case, Casing};
mod code_words;
/// A phonetic converter.
pub struct PhoneticConverter {
/// The map of characters to code words.
conversion_map: HashMap<char, String>,
/// Is set when the code word output will be in "nonce form".
nonce_form: bool,
}
/// A spelling alphabet.
#[derive(Default)]
pub enum SpellingAlphabet {
/// The JAN (Joint Army/Navy) spelling alphabet.
Jan,
/// The LAPD (Los Angeles Police Department) spelling alphabet.
Lapd,
/// The NATO (North Atlantic Treaty Organization) spelling alphabet.
/// This is the default.
#[default]
Nato,
/// The Royal Navy spelling alphabet.
RoyalNavy,
/// The United States Financial Industry spelling alphabet.
UsFinancial,
/// The Western Union spelling alphabet.
WesternUnion,
}
impl PhoneticConverter {
/// Creates and returns a new instance of `PhoneticConverter` using the
/// desired spelling alphabet character mappings.
///
/// # Arguments
///
/// * `alphabet` - The [`SpellingAlphabet`] to use for character
/// conversions.
///
/// # Examples
///
///
/// ```
/// # use spellabet::{PhoneticConverter, SpellingAlphabet};
/// let converter = PhoneticConverter::new(&SpellingAlphabet::default());
/// ```
#[must_use]
pub fn new(alphabet: &SpellingAlphabet) -> Self {
let conversion_map = alphabet.initialize();
Self {
conversion_map,
nonce_form: false,
}
}
/// Get the current character mappings of the `PhoneticConverter` instance.
#[must_use]
pub const fn mappings(&self) -> &HashMap<char, String> {
&self.conversion_map
}
/// Configures the current `PhoneticConverter` instance to either output
/// code words in "nonce form" or not, based on the given boolean value.
///
/// Nonce form means each letter character is expanded into the form "'A' as
/// in ALFA". Digits and symbols are always returned using the normal output
/// format.
///
/// # Arguments
///
/// * `nonce_form` - If true, enables nonce form output. Otherwise, the
/// normal output format is used.
///
/// # Examples
///
/// ```
/// # use spellabet::{PhoneticConverter, SpellingAlphabet};
/// let converter = PhoneticConverter::new(&SpellingAlphabet::default()).nonce_form(true);
/// println!("{}", converter.convert("Hello"));
/// ```
///
/// ```text
/// 'H' as in HOTEL, 'e' as in echo, 'l' as in lima, 'l' as in lima, 'o' as in oscar
/// ```
#[must_use]
pub const fn nonce_form(mut self, nonce_form: bool) -> Self {
self.nonce_form = nonce_form;
self
}
/// Modifies the conversion map of the current `PhoneticConverter` instance
/// by adding or replacing mappings based on the given overrides map.
///
/// # Arguments
///
/// * `overrides_map` - The desired character to code word mappings to
/// override. The capitalization of the keys and values will be
/// automatically normalized.
///
/// # Examples
///
/// ```
/// use std::collections::HashMap;
/// # use spellabet::{PhoneticConverter, SpellingAlphabet};
///
/// let mut converter = PhoneticConverter::new(&SpellingAlphabet::default());
///
/// let mut overrides_map = HashMap::new();
/// overrides_map.insert('a', "Apple".to_string());
/// overrides_map.insert('b', "Banana".to_string());
///
/// println!("BEFORE: {}", converter.convert("abcd"));
/// ```
///
/// ```text
/// BEFORE: alfa bravo charlie delta
/// ```
///
/// ```
/// # use std::collections::HashMap;
/// # use spellabet::{PhoneticConverter, SpellingAlphabet};
/// # let mut converter = PhoneticConverter::new(&SpellingAlphabet::default());
/// # let mut overrides_map = HashMap::new();
/// # overrides_map.insert('a', "Apple".to_string());
/// # overrides_map.insert('b', "Banana".to_string());
/// converter = converter.with_overrides(overrides_map);
/// println!("AFTER: {}", converter.convert("abcd"));
/// ```
///
/// ```text
/// AFTER: apple banana charlie delta
/// ```
#[must_use]
pub fn with_overrides(mut self, overrides_map: HashMap<char, String>) -> Self {
let normalized_overrides: HashMap<char, String> = overrides_map
.into_iter()
.map(|(k, v)| (k.to_ascii_lowercase(), v.to_case(Case::Pascal)))
.collect();
self.conversion_map.extend(normalized_overrides);
self
}
/// Converts the given text into a string of code words using the current
/// character mappings of the `PhoneticConverter` instance.
///
/// # Arguments
///
/// * `text` - The text to convert into code words.
///
/// # Examples
///
/// ```
/// # use spellabet::{PhoneticConverter, SpellingAlphabet};
/// let converter = PhoneticConverter::new(&SpellingAlphabet::default());
/// assert_eq!(converter.convert("Hello"), "HOTEL echo lima lima oscar");
/// ```
#[must_use]
pub fn convert(&self, text: &str) -> String {
let mut result = String::new();
for (i, c) in text.chars().enumerate() {
// add separator between converted characters
if i != 0 {
if self.nonce_form {
result.push_str(", ");
} else {
result.push(' ');
}
}
self.convert_char(c, &mut result);
}
result
}
fn convert_char(&self, character: char, result: &mut String) {
match self.conversion_map.get(&character.to_ascii_lowercase()) {
Some(word) => {
let code_word = match character {
_ if character.is_lowercase() => word.to_lowercase(),
_ if character.is_uppercase() => word.to_uppercase(),
_ => word.clone(),
};
if self.nonce_form && character.is_alphabetic() {
result.push_str(&format!("'{character}' as in {code_word}"));
} else {
result.push_str(&code_word);
}
}
None => result.push(character),
}
}
/// Writes the current character mappings of the `PhoneticConverter`
/// instance to the given writer.
///
/// # Arguments
///
/// * `writer` - The output destination.
/// * `verbose` - If true, dumps all characters. Otherwise, dumps only
/// letter characters.
///
/// # Errors
///
/// This function will return an error if writing to the provided writer
/// fails. The specific conditions under which this may occur depend on the
/// nature of the writer.
///
/// # Examples
///
/// ```
/// # use spellabet::{PhoneticConverter, SpellingAlphabet};
/// let converter = PhoneticConverter::new(&SpellingAlphabet::default());
///
/// let mut buf = Vec::new();
/// let verbose = false;
/// converter.dump_alphabet(&mut buf, verbose)?;
/// let output = String::from_utf8(buf)?;
/// println!("{output}");
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// ```text
/// a -> Alfa
/// b -> Bravo
/// c -> Charlie
/// ...
/// ```
pub fn dump_alphabet(
&self,
mut writer: impl std::io::Write,
verbose: bool,
) -> std::io::Result<()> {
let mut entries: Vec<_> = self.conversion_map.iter().collect();
entries.sort_by(|a, b| custom_char_ordering(*a.0, *b.0));
for (character, code_word) in entries {
if verbose || character.is_alphabetic() {
writeln!(writer, "{character} -> {code_word}")?;
}
}
Ok(())
}
}
// Sort characters in the order of letters before digits before symbols.
// Within each group, characters will be sorted in their natural order.
fn custom_char_ordering(a: char, b: char) -> Ordering {
match (
a.is_alphabetic(),
b.is_alphabetic(),
a.is_numeric(),
b.is_numeric(),
) {
(true, false, _, _) | (false, false, true, false) => Ordering::Less,
(false, true, _, _) | (false, false, false, true) => Ordering::Greater,
_ => a.cmp(&b),
}
}
impl SpellingAlphabet {
/// Generates and returns a character to code word map based on the current
/// `SpellingAlphabet`.
#[must_use]
pub fn initialize(&self) -> HashMap<char, String> {
let mut map: HashMap<char, String> = HashMap::new();
let extend_map = |map: &mut HashMap<char, String>, source_map: &[(char, &str)]| {
for (k, v) in source_map {
map.insert(*k, (*v).to_string());
}
};
extend_map(&mut map, &DEFAULT_DIGITS_AND_SYMBOLS);
match self {
Self::Jan => extend_map(&mut map, &JAN_ALPHABET),
Self::Lapd => extend_map(&mut map, &LAPD_ALPHABET),
Self::Nato => extend_map(&mut map, &NATO_ALPHABET),
Self::RoyalNavy => extend_map(&mut map, &ROYAL_NAVY_ALPHABET),
Self::UsFinancial => extend_map(&mut map, &US_FINANCIAL_ALPHABET),
Self::WesternUnion => extend_map(&mut map, &WESTERN_UNION_ALPHABET),
};
map
}
}