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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433
//! A Word Filter for filtering text.
//!
//! A Word Filter is a system for identifying and censoring specific words or phrases in strings. Common
//! usage includes censoring vulgar or profane language and preventing spam or vandelism in
//! user-provided content.
//!
//! The Word Filter implementation provided here allows for advanced filtering functionality, including:
//! - Finding and censoring filtered words.
//! - Ignoring words that are considered "exceptions".
//! - Allowing specification of "aliases", i.e. strings that can replace other strings (for example, an
//! alias could be created to replace the letter "a" with the character "@").
//! - Ignoring specified separators (such as spaces or other characters) between letters of filtered
//! words.
//!
//! # Usage
//! [`WordFilter`]s must be created at compile-time using a
//! [build script](https://doc.rust-lang.org/cargo/reference/build-scripts.html) using the tools
//! provided in the [`codegen`] module. The generated code can then be [`include!`]ed and used.
//!
//! ## Example
//! For example, a simple [`WordFilter`] can be generated by the following.
//!
//! First, add the `word_filter` crate to both the `Cargo.toml` `[dependencies]` and
//! `[build-dependencies]` lists.
//!
//! ``` toml
//! ...
//! [dependencies]
//! word_filter = "0.7.0"
//!
//! [build-dependencies]
//! word_filter = "0.7.0"
//! ...
//! ```
//!
//! Next, generate the [`WordFilter`] in the `build.rs` file.
//!
//! ``` no_run
//! use std::{
//! env,
//! fs::File,
//! io::{BufWriter, Write},
//! path::Path,
//! };
//! use word_filter::codegen::{Visibility, WordFilterGenerator};
//!
//! fn main() {
//! let path = Path::new(&env::var("OUT_DIR").unwrap()).join("codegen.rs");
//! let mut file = BufWriter::new(File::create(&path).unwrap());
//!
//! writeln!(
//! &mut file,
//! "{}",
//! WordFilterGenerator::new()
//! .visibility(Visibility::Pub)
//! .word("foo")
//! .generate("FILTER")
//! );
//! }
//! ```
//!
//! And finally, include the generated code in the `lib.rs` file.
//!
//! ``` ignore
//! include!(concat!(env!("OUT_DIR"), "/codegen.rs"));
//!
//! assert!(FILTER.censor("Should censor foo."), "Should censor ***.");
//! ```
#![no_std]
extern crate alloc;
pub mod censor;
pub mod codegen;
pub mod pda;
mod constants;
use alloc::{string::String, vec, vec::Vec};
use constants::{EXCEPTION_INDEX, SEPARATOR_INDEX, WORD_INDEX};
use core::{cmp, iter::FromIterator};
use nested_containment_list::NestedContainmentList;
use pda::{InstantaneousDescription, State};
use unicode_segmentation::UnicodeSegmentation;
/// A word filter for identifying filtered words within strings.
///
/// A `WordFilter` is constructed from **filtered words**, **exceptions**, **separators**,
/// and **aliases**. Each of those parameters are defined as follows:
///
/// - **filtered words** - strings that should be identified and censored by the `WordFilter`.
/// - **exceptions** - strings that should explicitly not be identified and censored by the
/// `WordFilter`. Any string that contains filtered word that is contained entirely inside an
/// exception will be ignored.
/// - **separators** - strings that may appear between characters in filtered words and exceptions.
/// - **aliases** - tuples defining alias strings that may replace source strings during matching.
/// These are of the form `(<source string>, <alias string>)`.
///
/// `WordFilter`s are constructed at compile-time using the [`codegen`] module. See crate-level
/// documentation for further information.
#[derive(Debug)]
pub struct WordFilter<'a, const N: usize> {
#[doc(hidden)]
pub states: [State<'a>; N],
}
impl<'a, const N: usize> WordFilter<'a, N> {
/// Create all entry instantaneous descriptions.
///
/// This includes the standard entry state and all of its ε-transitions.
fn spawn_entry_ids(
&'a self,
start: usize,
) -> impl Iterator<Item = InstantaneousDescription<'_>> {
let mut ids = vec![
InstantaneousDescription::new(&self.states[WORD_INDEX], start),
InstantaneousDescription::new(&self.states[EXCEPTION_INDEX], start),
];
ids.extend(
ids.iter()
.map(|id| id.transition(None, &self.states[SEPARATOR_INDEX]))
.flatten()
.collect::<Vec<_>>(),
);
ids.into_iter()
}
/// Run the computation, finding all matched words within `input`.
fn compute(&'a self, input: &str) -> impl Iterator<Item = InstantaneousDescription<'_>> {
let mut ids = Vec::new();
let mut accepted_ids = Vec::new();
let mut index = 0;
// Handle the input one grapheme at a time. Only accepting states found at the end of
// graphemes are kept.
for grapheme in input.graphemes(true) {
ids.extend(self.spawn_entry_ids(index));
let mut first_c = true;
for c in grapheme.chars() {
let mut new_ids = Vec::new();
for id in ids.drain(..) {
new_ids.extend(id.step(c, &self.states[SEPARATOR_INDEX], first_c));
}
index += c.len_utf8();
ids = new_ids;
first_c = false;
}
// Now that all characters within the grapheme have been processed, determine if any
// ids are in an accepting state.
for id in &ids {
if id.is_accepting() {
accepted_ids.push(id.clone());
}
}
}
// Return outer-most nested words, ignoring words and exceptions nested within.
NestedContainmentList::from_iter(accepted_ids)
.into_iter()
.filter_map(|element| {
let instant = element.value;
if instant.is_word() {
Some(instant)
} else {
None
}
})
}
/// Find all filtered words matched by `input`.
///
/// Returns an [`Iterator`] over all matched filtered words.
///
/// # Example
///
/// Assuming a compile-time constructed `WordFilter` `FILTER`, defined in a `build.rs` as:
///
/// ``` ignore
/// use std::{
/// env,
/// fs::File,
/// io::{BufWriter, Write},
/// path::Path,
/// };
/// use word_filter::codegen::{Visibility, WordFilterGenerator};
///
/// fn main() {
/// let path = Path::new(&env::var("OUT_DIR").unwrap()).join("codegen.rs");
/// let mut file = BufWriter::new(File::create(&path).unwrap());
///
/// writeln!(
/// &mut file,
/// "{}",
/// WordFilterGenerator::new()
/// .word("foo")
/// .generate("FILTER")
/// );
/// }
/// ```
///
/// this method is used as follows:
///
/// ``` ignore
/// include!(concat!(env!("OUT_DIR"), "/codegen.rs"));
///
/// assert_eq!(FILTER.find("this string contains foo").collect::<Vec<_>>(), vec!["foo"]);
/// ```
///
/// [`Iterator`]: core::iter::Iterator
#[inline]
pub fn find(&'a self, input: &str) -> impl Iterator<Item = &str> {
self.compute(input).map(|id| unsafe {
// SAFETY: Each item returned from `self.compute()` is guaranteed to contain a word.
id.unwrap_word_unchecked()
})
}
/// Find all raw string slices matched in `input`.
///
/// Returns an iterator over all matched slices in `input`.
///
/// /// # Example
///
/// Assuming a compile-time constructed `WordFilter` `FILTER`, defined in a `build.rs` as:
///
/// ``` ignore
/// use std::{
/// env,
/// fs::File,
/// io::{BufWriter, Write},
/// path::Path,
/// };
/// use word_filter::codegen::{Visibility, WordFilterGenerator};
///
/// fn main() {
/// let path = Path::new(&env::var("OUT_DIR").unwrap()).join("codegen.rs");
/// let mut file = BufWriter::new(File::create(&path).unwrap());
///
/// writeln!(
/// &mut file,
/// "{}",
/// WordFilterGenerator::new()
/// .word("foo")
/// .alias('o', 'a')
/// .generate("FILTER")
/// );
/// }
/// ```
///
/// this method is used as follows:
///
/// ``` ignore
/// include!(concat!(env!("OUT_DIR"), "/codegen.rs"));
///
/// assert_eq!(FILTER.find_raw("this string contains fao").collect::<Vec<_>>(), vec!["fao"]);
/// ```
///
/// [`Iterator`]: core::iter::Iterator
#[inline]
pub fn find_raw<'b, 'c>(&'a self, input: &'b str) -> impl Iterator<Item = &'c str>
where
'a: 'c,
'b: 'c,
{
self.compute(input).map(move |id| unsafe {
// SAFETY: The `start` and `end` in `id` are guaranteed to be on UTF8
// bounds of `input`, since `id` is generated during `compute()` using the `char`s
// in `input`.
input.get_unchecked(id.start()..id.end())
})
}
/// Check whether `input` contains any filtered words.
///
/// Returns `true` if matches are found, and `false` otherwise.
///
/// # Example
///
/// Assuming a compile-time constructed `WordFilter` `FILTER`, defined in a `build.rs` as:
///
/// ``` ignore
/// use std::{
/// env,
/// fs::File,
/// io::{BufWriter, Write},
/// path::Path,
/// };
/// use word_filter::codegen::{Visibility, WordFilterGenerator};
///
/// fn main() {
/// let path = Path::new(&env::var("OUT_DIR").unwrap()).join("codegen.rs");
/// let mut file = BufWriter::new(File::create(&path).unwrap());
///
/// writeln!(
/// &mut file,
/// "{}",
/// WordFilterGenerator::new()
/// .word("foo")
/// .generate("FILTER")
/// );
/// }
/// ```
///
/// this method is used as follows:
///
/// ``` ignore
/// include!(concat!(env!("OUT_DIR"), "/codegen.rs"));
///
/// assert!(FILTER.check("this string contains foo"));
/// ```
#[inline]
#[must_use]
pub fn check(&'a self, input: &str) -> bool {
self.compute(input).next().is_some()
}
/// Censor all filtered words within `input`, replacing their occurances with the output of
/// `censor`.
///
/// Returns a newly-allocated `String` with all filtered words censored.
///
/// # Example
/// Assuming a compile-time constructed `WordFilter` `FILTER`, defined in a `build.rs` as:
///
/// ``` ignore
/// use std::{
/// env,
/// fs::File,
/// io::{BufWriter, Write},
/// path::Path,
/// };
/// use word_filter::codegen::{Visibility, WordFilterGenerator};
///
/// fn main() {
/// let path = Path::new(&env::var("OUT_DIR").unwrap()).join("codegen.rs");
/// let mut file = BufWriter::new(File::create(&path).unwrap());
///
/// writeln!(
/// &mut file,
/// "{}",
/// WordFilterGenerator::new()
/// .word("foo")
/// .generate("FILTER")
/// );
/// }
/// ```
///
/// this method is used as follows:
///
/// ``` ignore
/// use word_filter::censor;
///
/// include!(concat!(env!("OUT_DIR"), "/codegen.rs"));
///
/// assert!(
/// FILTER.censor_with("this string contains foo", censor::replace_graphemes_with!("#")),
/// "this string contains ###"
/// );
/// ```
#[must_use]
pub fn censor_with(&'a self, input: &str, censor: fn(&str) -> String) -> String {
let mut output = String::with_capacity(input.len());
let mut prev_end = 0;
for id in self.compute(input) {
if id.start() > prev_end {
output.push_str(unsafe {
// SAFETY: Both `prev_end` and `id.start()` are guaranteed to be on valid UTF-8
// boundaries of `input`.
input.get_unchecked(prev_end..id.start())
});
}
// Censor the covered characters for this ID.
output.push_str(&(censor)(unsafe {
// SAFETY: `id.start()`, `id.end()`, and `prev_end` are all guaranteed to be on
// valid UTF-8 boundaries of `input`.
input.get_unchecked(cmp::max(id.start(), prev_end)..id.end())
}));
prev_end = id.end();
}
output.push_str(unsafe {
// SAFETY: `prev_end` is guaranteed to be on a valid UTF-8 boundary of `input`.
input.get_unchecked(prev_end..)
});
output
}
/// Censor all filtered words within `input` with a default censor of
/// [`censor::replace_graphemes_with("*")`].
///
/// Returns a newly-allocated `String` with all filtered words censored.
///
/// # Example
/// Assuming a compile-time constructed `WordFilter` `FILTER`, defined in a `build.rs` as:
///
/// ``` ignore
/// use std::{
/// env,
/// fs::File,
/// io::{BufWriter, Write},
/// path::Path,
/// };
/// use word_filter::codegen::{Visibility, WordFilterGenerator};
///
/// fn main() {
/// let path = Path::new(&env::var("OUT_DIR").unwrap()).join("codegen.rs");
/// let mut file = BufWriter::new(File::create(&path).unwrap());
///
/// writeln!(
/// &mut file,
/// "{}",
/// WordFilterGenerator::new()
/// .word("foo")
/// .generate("FILTER")
/// );
/// }
/// ```
///
/// this method is used as follows:
///
/// ``` ignore
/// include!(concat!(env!("OUT_DIR"), "/codegen.rs"));
///
/// assert!(FILTER.censor("this string contains foo"), "this string contains ***");
/// ```
///
/// [`censor::replace_graphemes_with("*")`]: censor/macro.replace_graphemes_with.html
#[inline]
#[must_use]
pub fn censor(&'a self, input: &str) -> String {
self.censor_with(input, censor::replace_graphemes_with!("*"))
}
}