| 1 |
/*! |
| 2 |
Types and routines for working with look-around assertions. |
| 3 |
|
| 4 |
This module principally defines two types: |
| 5 |
|
| 6 |
* [`Look`] enumerates all of the assertions supported by this crate. |
| 7 |
* [`LookSet`] provides a way to efficiently store a set of [`Look`] values. |
| 8 |
* [`LookMatcher`] provides routines for checking whether a `Look` or a |
| 9 |
`LookSet` matches at a particular position in a haystack. |
| 10 |
*/ |
| 11 |
|
| 12 |
// LAMENTATION: Sadly, a lot of the API of `Look` and `LookSet` were basically |
| 13 |
// copied verbatim from the regex-syntax crate. I would have no problems using |
| 14 |
// the regex-syntax types and defining the matching routines (only found |
| 15 |
// in this crate) as free functions, except the `Look` and `LookSet` types |
| 16 |
// are used in lots of places. Including in places we expect to work when |
| 17 |
// regex-syntax is *not* enabled, such as in the definition of the NFA itself. |
| 18 |
// |
| 19 |
// Thankfully the code we copy is pretty simple and there isn't much of it. |
| 20 |
// Otherwise, the rest of this module deals with *matching* the assertions, |
| 21 |
// which is not something that regex-syntax handles. |
| 22 |
|
| 23 |
use crate::util::{escape::DebugByte, utf8}; |
| 24 |
|
| 25 |
/// A look-around assertion. |
| 26 |
/// |
| 27 |
/// An assertion matches at a position between characters in a haystack. |
| 28 |
/// Namely, it does not actually "consume" any input as most parts of a regular |
| 29 |
/// expression do. Assertions are a way of stating that some property must be |
| 30 |
/// true at a particular point during matching. |
| 31 |
/// |
| 32 |
/// For example, `(?m)^[a-z]+$` is a pattern that: |
| 33 |
/// |
| 34 |
/// * Scans the haystack for a position at which `(?m:^)` is satisfied. That |
| 35 |
/// occurs at either the beginning of the haystack, or immediately following |
| 36 |
/// a `\n` character. |
| 37 |
/// * Looks for one or more occurrences of `[a-z]`. |
| 38 |
/// * Once `[a-z]+` has matched as much as it can, an overall match is only |
| 39 |
/// reported when `[a-z]+` stops just before a `\n`. |
| 40 |
/// |
| 41 |
/// So in this case, `abc` and `\nabc\n` match, but `\nabc1\n` does not. |
| 42 |
/// |
| 43 |
/// Assertions are also called "look-around," "look-behind" and "look-ahead." |
| 44 |
/// Specifically, some assertions are look-behind (like `^`), other assertions |
| 45 |
/// are look-ahead (like `$`) and yet other assertions are both look-ahead and |
| 46 |
/// look-behind (like `\b`). |
| 47 |
/// |
| 48 |
/// # Assertions in an NFA |
| 49 |
/// |
| 50 |
/// An assertion in a [`thompson::NFA`](crate::nfa::thompson::NFA) can be |
| 51 |
/// thought of as a conditional epsilon transition. That is, a matching engine |
| 52 |
/// like the [`PikeVM`](crate::nfa::thompson::pikevm::PikeVM) only permits |
| 53 |
/// moving through conditional epsilon transitions when their condition |
| 54 |
/// is satisfied at whatever position the `PikeVM` is currently at in the |
| 55 |
/// haystack. |
| 56 |
/// |
| 57 |
/// How assertions are handled in a `DFA` is trickier, since a DFA does not |
| 58 |
/// have epsilon transitions at all. In this case, they are compiled into the |
| 59 |
/// automaton itself, at the expense of more states than what would be required |
| 60 |
/// without an assertion. |
| 61 |
#[derive(Clone, Copy, Debug, Eq, PartialEq)] |
| 62 |
pub enum Look { |
| 63 |
/// Match the beginning of text. Specifically, this matches at the starting |
| 64 |
/// position of the input. |
| 65 |
Start = 1 << 0, |
| 66 |
/// Match the end of text. Specifically, this matches at the ending |
| 67 |
/// position of the input. |
| 68 |
End = 1 << 1, |
| 69 |
/// Match the beginning of a line or the beginning of text. Specifically, |
| 70 |
/// this matches at the starting position of the input, or at the position |
| 71 |
/// immediately following a `\n` character. |
| 72 |
StartLF = 1 << 2, |
| 73 |
/// Match the end of a line or the end of text. Specifically, this matches |
| 74 |
/// at the end position of the input, or at the position immediately |
| 75 |
/// preceding a `\n` character. |
| 76 |
EndLF = 1 << 3, |
| 77 |
/// Match the beginning of a line or the beginning of text. Specifically, |
| 78 |
/// this matches at the starting position of the input, or at the position |
| 79 |
/// immediately following either a `\r` or `\n` character, but never after |
| 80 |
/// a `\r` when a `\n` follows. |
| 81 |
StartCRLF = 1 << 4, |
| 82 |
/// Match the end of a line or the end of text. Specifically, this matches |
| 83 |
/// at the end position of the input, or at the position immediately |
| 84 |
/// preceding a `\r` or `\n` character, but never before a `\n` when a `\r` |
| 85 |
/// precedes it. |
| 86 |
EndCRLF = 1 << 5, |
| 87 |
/// Match an ASCII-only word boundary. That is, this matches a position |
| 88 |
/// where the left adjacent character and right adjacent character |
| 89 |
/// correspond to a word and non-word or a non-word and word character. |
| 90 |
WordAscii = 1 << 6, |
| 91 |
/// Match an ASCII-only negation of a word boundary. |
| 92 |
WordAsciiNegate = 1 << 7, |
| 93 |
/// Match a Unicode-aware word boundary. That is, this matches a position |
| 94 |
/// where the left adjacent character and right adjacent character |
| 95 |
/// correspond to a word and non-word or a non-word and word character. |
| 96 |
WordUnicode = 1 << 8, |
| 97 |
/// Match a Unicode-aware negation of a word boundary. |
| 98 |
WordUnicodeNegate = 1 << 9, |
| 99 |
/// Match the start of an ASCII-only word boundary. That is, this matches a |
| 100 |
/// position at either the beginning of the haystack or where the previous |
| 101 |
/// character is not a word character and the following character is a word |
| 102 |
/// character. |
| 103 |
WordStartAscii = 1 << 10, |
| 104 |
/// Match the end of an ASCII-only word boundary. That is, this matches |
| 105 |
/// a position at either the end of the haystack or where the previous |
| 106 |
/// character is a word character and the following character is not a word |
| 107 |
/// character. |
| 108 |
WordEndAscii = 1 << 11, |
| 109 |
/// Match the start of a Unicode word boundary. That is, this matches a |
| 110 |
/// position at either the beginning of the haystack or where the previous |
| 111 |
/// character is not a word character and the following character is a word |
| 112 |
/// character. |
| 113 |
WordStartUnicode = 1 << 12, |
| 114 |
/// Match the end of a Unicode word boundary. That is, this matches a |
| 115 |
/// position at either the end of the haystack or where the previous |
| 116 |
/// character is a word character and the following character is not a word |
| 117 |
/// character. |
| 118 |
WordEndUnicode = 1 << 13, |
| 119 |
/// Match the start half of an ASCII-only word boundary. That is, this |
| 120 |
/// matches a position at either the beginning of the haystack or where the |
| 121 |
/// previous character is not a word character. |
| 122 |
WordStartHalfAscii = 1 << 14, |
| 123 |
/// Match the end half of an ASCII-only word boundary. That is, this |
| 124 |
/// matches a position at either the end of the haystack or where the |
| 125 |
/// following character is not a word character. |
| 126 |
WordEndHalfAscii = 1 << 15, |
| 127 |
/// Match the start half of a Unicode word boundary. That is, this matches |
| 128 |
/// a position at either the beginning of the haystack or where the |
| 129 |
/// previous character is not a word character. |
| 130 |
WordStartHalfUnicode = 1 << 16, |
| 131 |
/// Match the end half of a Unicode word boundary. That is, this matches |
| 132 |
/// a position at either the end of the haystack or where the following |
| 133 |
/// character is not a word character. |
| 134 |
WordEndHalfUnicode = 1 << 17, |
| 135 |
} |
| 136 |
|
| 137 |
impl Look { |
| 138 |
/// Flip the look-around assertion to its equivalent for reverse searches. |
| 139 |
/// For example, `StartLF` gets translated to `EndLF`. |
| 140 |
/// |
| 141 |
/// Some assertions, such as `WordUnicode`, remain the same since they |
| 142 |
/// match the same positions regardless of the direction of the search. |
| 143 |
#[inline] |
| 144 |
pub const fn reversed(self) -> Look { |
| 145 |
match self { |
| 146 |
Look::Start => Look::End, |
| 147 |
Look::End => Look::Start, |
| 148 |
Look::StartLF => Look::EndLF, |
| 149 |
Look::EndLF => Look::StartLF, |
| 150 |
Look::StartCRLF => Look::EndCRLF, |
| 151 |
Look::EndCRLF => Look::StartCRLF, |
| 152 |
Look::WordAscii => Look::WordAscii, |
| 153 |
Look::WordAsciiNegate => Look::WordAsciiNegate, |
| 154 |
Look::WordUnicode => Look::WordUnicode, |
| 155 |
Look::WordUnicodeNegate => Look::WordUnicodeNegate, |
| 156 |
Look::WordStartAscii => Look::WordEndAscii, |
| 157 |
Look::WordEndAscii => Look::WordStartAscii, |
| 158 |
Look::WordStartUnicode => Look::WordEndUnicode, |
| 159 |
Look::WordEndUnicode => Look::WordStartUnicode, |
| 160 |
Look::WordStartHalfAscii => Look::WordEndHalfAscii, |
| 161 |
Look::WordEndHalfAscii => Look::WordStartHalfAscii, |
| 162 |
Look::WordStartHalfUnicode => Look::WordEndHalfUnicode, |
| 163 |
Look::WordEndHalfUnicode => Look::WordStartHalfUnicode, |
| 164 |
} |
| 165 |
} |
| 166 |
|
| 167 |
/// Return the underlying representation of this look-around enumeration |
| 168 |
/// as an integer. Giving the return value to the [`Look::from_repr`] |
| 169 |
/// constructor is guaranteed to return the same look-around variant that |
| 170 |
/// one started with within a semver compatible release of this crate. |
| 171 |
#[inline] |
| 172 |
pub const fn as_repr(self) -> u32 { |
| 173 |
// AFAIK, 'as' is the only way to zero-cost convert an int enum to an |
| 174 |
// actual int. |
| 175 |
self as u32 |
| 176 |
} |
| 177 |
|
| 178 |
/// Given the underlying representation of a `Look` value, return the |
| 179 |
/// corresponding `Look` value if the representation is valid. Otherwise |
| 180 |
/// `None` is returned. |
| 181 |
#[inline] |
| 182 |
pub const fn from_repr(repr: u32) -> Option<Look> { |
| 183 |
match repr { |
| 184 |
0b00_0000_0000_0000_0001 => Some(Look::Start), |
| 185 |
0b00_0000_0000_0000_0010 => Some(Look::End), |
| 186 |
0b00_0000_0000_0000_0100 => Some(Look::StartLF), |
| 187 |
0b00_0000_0000_0000_1000 => Some(Look::EndLF), |
| 188 |
0b00_0000_0000_0001_0000 => Some(Look::StartCRLF), |
| 189 |
0b00_0000_0000_0010_0000 => Some(Look::EndCRLF), |
| 190 |
0b00_0000_0000_0100_0000 => Some(Look::WordAscii), |
| 191 |
0b00_0000_0000_1000_0000 => Some(Look::WordAsciiNegate), |
| 192 |
0b00_0000_0001_0000_0000 => Some(Look::WordUnicode), |
| 193 |
0b00_0000_0010_0000_0000 => Some(Look::WordUnicodeNegate), |
| 194 |
0b00_0000_0100_0000_0000 => Some(Look::WordStartAscii), |
| 195 |
0b00_0000_1000_0000_0000 => Some(Look::WordEndAscii), |
| 196 |
0b00_0001_0000_0000_0000 => Some(Look::WordStartUnicode), |
| 197 |
0b00_0010_0000_0000_0000 => Some(Look::WordEndUnicode), |
| 198 |
0b00_0100_0000_0000_0000 => Some(Look::WordStartHalfAscii), |
| 199 |
0b00_1000_0000_0000_0000 => Some(Look::WordEndHalfAscii), |
| 200 |
0b01_0000_0000_0000_0000 => Some(Look::WordStartHalfUnicode), |
| 201 |
0b10_0000_0000_0000_0000 => Some(Look::WordEndHalfUnicode), |
| 202 |
_ => None, |
| 203 |
} |
| 204 |
} |
| 205 |
|
| 206 |
/// Returns a convenient single codepoint representation of this |
| 207 |
/// look-around assertion. Each assertion is guaranteed to be represented |
| 208 |
/// by a distinct character. |
| 209 |
/// |
| 210 |
/// This is useful for succinctly representing a look-around assertion in |
| 211 |
/// human friendly but succinct output intended for a programmer working on |
| 212 |
/// regex internals. |
| 213 |
#[inline] |
| 214 |
pub const fn as_char(self) -> char { |
| 215 |
match self { |
| 216 |
Look::Start => 'A', |
| 217 |
Look::End => 'z', |
| 218 |
Look::StartLF => '^', |
| 219 |
Look::EndLF => '$', |
| 220 |
Look::StartCRLF => 'r', |
| 221 |
Look::EndCRLF => 'R', |
| 222 |
Look::WordAscii => 'b', |
| 223 |
Look::WordAsciiNegate => 'B', |
| 224 |
Look::WordUnicode => '𝛃', |
| 225 |
Look::WordUnicodeNegate => '𝚩', |
| 226 |
Look::WordStartAscii => '<', |
| 227 |
Look::WordEndAscii => '>', |
| 228 |
Look::WordStartUnicode => '〈', |
| 229 |
Look::WordEndUnicode => '〉', |
| 230 |
Look::WordStartHalfAscii => '◁', |
| 231 |
Look::WordEndHalfAscii => '▷', |
| 232 |
Look::WordStartHalfUnicode => '◀', |
| 233 |
Look::WordEndHalfUnicode => '▶', |
| 234 |
} |
| 235 |
} |
| 236 |
} |
| 237 |
|
| 238 |
/// LookSet is a memory-efficient set of look-around assertions. |
| 239 |
/// |
| 240 |
/// This is useful for efficiently tracking look-around assertions. For |
| 241 |
/// example, a [`thompson::NFA`](crate::nfa::thompson::NFA) provides properties |
| 242 |
/// that return `LookSet`s. |
| 243 |
#[derive(Clone, Copy, Default, Eq, PartialEq)] |
| 244 |
pub struct LookSet { |
| 245 |
/// The underlying representation this set is exposed to make it possible |
| 246 |
/// to store it somewhere efficiently. The representation is that |
| 247 |
/// of a bitset, where each assertion occupies bit `i` where |
| 248 |
/// `i = Look::as_repr()`. |
| 249 |
/// |
| 250 |
/// Note that users of this internal representation must permit the full |
| 251 |
/// range of `u16` values to be represented. For example, even if the |
| 252 |
/// current implementation only makes use of the 10 least significant bits, |
| 253 |
/// it may use more bits in a future semver compatible release. |
| 254 |
pub bits: u32, |
| 255 |
} |
| 256 |
|
| 257 |
impl LookSet { |
| 258 |
/// Create an empty set of look-around assertions. |
| 259 |
#[inline] |
| 260 |
pub fn empty() -> LookSet { |
| 261 |
LookSet { bits: 0 } |
| 262 |
} |
| 263 |
|
| 264 |
/// Create a full set of look-around assertions. |
| 265 |
/// |
| 266 |
/// This set contains all possible look-around assertions. |
| 267 |
#[inline] |
| 268 |
pub fn full() -> LookSet { |
| 269 |
LookSet { bits: !0 } |
| 270 |
} |
| 271 |
|
| 272 |
/// Create a look-around set containing the look-around assertion given. |
| 273 |
/// |
| 274 |
/// This is a convenience routine for creating an empty set and inserting |
| 275 |
/// one look-around assertions. |
| 276 |
#[inline] |
| 277 |
pub fn singleton(look: Look) -> LookSet { |
| 278 |
LookSet::empty().insert(look) |
| 279 |
} |
| 280 |
|
| 281 |
/// Returns the total number of look-around assertions in this set. |
| 282 |
#[inline] |
| 283 |
pub fn len(self) -> usize { |
| 284 |
// OK because max value always fits in a u8, which in turn always |
| 285 |
// fits in a usize, regardless of target. |
| 286 |
usize::try_from(self.bits.count_ones()).unwrap() |
| 287 |
} |
| 288 |
|
| 289 |
/// Returns true if and only if this set is empty. |
| 290 |
#[inline] |
| 291 |
pub fn is_empty(self) -> bool { |
| 292 |
self.len() == 0 |
| 293 |
} |
| 294 |
|
| 295 |
/// Returns true if and only if the given look-around assertion is in this |
| 296 |
/// set. |
| 297 |
#[inline] |
| 298 |
pub fn contains(self, look: Look) -> bool { |
| 299 |
self.bits & look.as_repr() != 0 |
| 300 |
} |
| 301 |
|
| 302 |
/// Returns true if and only if this set contains any anchor assertions. |
| 303 |
/// This includes both "start/end of haystack" and "start/end of line." |
| 304 |
#[inline] |
| 305 |
pub fn contains_anchor(&self) -> bool { |
| 306 |
self.contains_anchor_haystack() || self.contains_anchor_line() |
| 307 |
} |
| 308 |
|
| 309 |
/// Returns true if and only if this set contains any "start/end of |
| 310 |
/// haystack" anchors. This doesn't include "start/end of line" anchors. |
| 311 |
#[inline] |
| 312 |
pub fn contains_anchor_haystack(&self) -> bool { |
| 313 |
self.contains(Look::Start) || self.contains(Look::End) |
| 314 |
} |
| 315 |
|
| 316 |
/// Returns true if and only if this set contains any "start/end of line" |
| 317 |
/// anchors. This doesn't include "start/end of haystack" anchors. This |
| 318 |
/// includes both `\n` line anchors and CRLF (`\r\n`) aware line anchors. |
| 319 |
#[inline] |
| 320 |
pub fn contains_anchor_line(&self) -> bool { |
| 321 |
self.contains(Look::StartLF) |
| 322 |
|| self.contains(Look::EndLF) |
| 323 |
|| self.contains(Look::StartCRLF) |
| 324 |
|| self.contains(Look::EndCRLF) |
| 325 |
} |
| 326 |
|
| 327 |
/// Returns true if and only if this set contains any "start/end of line" |
| 328 |
/// anchors that only treat `\n` as line terminators. This does not include |
| 329 |
/// haystack anchors or CRLF aware line anchors. |
| 330 |
#[inline] |
| 331 |
pub fn contains_anchor_lf(&self) -> bool { |
| 332 |
self.contains(Look::StartLF) || self.contains(Look::EndLF) |
| 333 |
} |
| 334 |
|
| 335 |
/// Returns true if and only if this set contains any "start/end of line" |
| 336 |
/// anchors that are CRLF-aware. This doesn't include "start/end of |
| 337 |
/// haystack" or "start/end of line-feed" anchors. |
| 338 |
#[inline] |
| 339 |
pub fn contains_anchor_crlf(&self) -> bool { |
| 340 |
self.contains(Look::StartCRLF) || self.contains(Look::EndCRLF) |
| 341 |
} |
| 342 |
|
| 343 |
/// Returns true if and only if this set contains any word boundary or |
| 344 |
/// negated word boundary assertions. This include both Unicode and ASCII |
| 345 |
/// word boundaries. |
| 346 |
#[inline] |
| 347 |
pub fn contains_word(self) -> bool { |
| 348 |
self.contains_word_unicode() || self.contains_word_ascii() |
| 349 |
} |
| 350 |
|
| 351 |
/// Returns true if and only if this set contains any Unicode word boundary |
| 352 |
/// or negated Unicode word boundary assertions. |
| 353 |
#[inline] |
| 354 |
pub fn contains_word_unicode(self) -> bool { |
| 355 |
self.contains(Look::WordUnicode) |
| 356 |
|| self.contains(Look::WordUnicodeNegate) |
| 357 |
|| self.contains(Look::WordStartUnicode) |
| 358 |
|| self.contains(Look::WordEndUnicode) |
| 359 |
|| self.contains(Look::WordStartHalfUnicode) |
| 360 |
|| self.contains(Look::WordEndHalfUnicode) |
| 361 |
} |
| 362 |
|
| 363 |
/// Returns true if and only if this set contains any ASCII word boundary |
| 364 |
/// or negated ASCII word boundary assertions. |
| 365 |
#[inline] |
| 366 |
pub fn contains_word_ascii(self) -> bool { |
| 367 |
self.contains(Look::WordAscii) |
| 368 |
|| self.contains(Look::WordAsciiNegate) |
| 369 |
|| self.contains(Look::WordStartAscii) |
| 370 |
|| self.contains(Look::WordEndAscii) |
| 371 |
|| self.contains(Look::WordStartHalfAscii) |
| 372 |
|| self.contains(Look::WordEndHalfAscii) |
| 373 |
} |
| 374 |
|
| 375 |
/// Returns an iterator over all of the look-around assertions in this set. |
| 376 |
#[inline] |
| 377 |
pub fn iter(self) -> LookSetIter { |
| 378 |
LookSetIter { set: self } |
| 379 |
} |
| 380 |
|
| 381 |
/// Return a new set that is equivalent to the original, but with the given |
| 382 |
/// assertion added to it. If the assertion is already in the set, then the |
| 383 |
/// returned set is equivalent to the original. |
| 384 |
#[inline] |
| 385 |
pub fn insert(self, look: Look) -> LookSet { |
| 386 |
LookSet { bits: self.bits | look.as_repr() } |
| 387 |
} |
| 388 |
|
| 389 |
/// Updates this set in place with the result of inserting the given |
| 390 |
/// assertion into this set. |
| 391 |
#[inline] |
| 392 |
pub fn set_insert(&mut self, look: Look) { |
| 393 |
*self = self.insert(look); |
| 394 |
} |
| 395 |
|
| 396 |
/// Return a new set that is equivalent to the original, but with the given |
| 397 |
/// assertion removed from it. If the assertion is not in the set, then the |
| 398 |
/// returned set is equivalent to the original. |
| 399 |
#[inline] |
| 400 |
pub fn remove(self, look: Look) -> LookSet { |
| 401 |
LookSet { bits: self.bits & !look.as_repr() } |
| 402 |
} |
| 403 |
|
| 404 |
/// Updates this set in place with the result of removing the given |
| 405 |
/// assertion from this set. |
| 406 |
#[inline] |
| 407 |
pub fn set_remove(&mut self, look: Look) { |
| 408 |
*self = self.remove(look); |
| 409 |
} |
| 410 |
|
| 411 |
/// Returns a new set that is the result of subtracting the given set from |
| 412 |
/// this set. |
| 413 |
#[inline] |
| 414 |
pub fn subtract(self, other: LookSet) -> LookSet { |
| 415 |
LookSet { bits: self.bits & !other.bits } |
| 416 |
} |
| 417 |
|
| 418 |
/// Updates this set in place with the result of subtracting the given set |
| 419 |
/// from this set. |
| 420 |
#[inline] |
| 421 |
pub fn set_subtract(&mut self, other: LookSet) { |
| 422 |
*self = self.subtract(other); |
| 423 |
} |
| 424 |
|
| 425 |
/// Returns a new set that is the union of this and the one given. |
| 426 |
#[inline] |
| 427 |
pub fn union(self, other: LookSet) -> LookSet { |
| 428 |
LookSet { bits: self.bits | other.bits } |
| 429 |
} |
| 430 |
|
| 431 |
/// Updates this set in place with the result of unioning it with the one |
| 432 |
/// given. |
| 433 |
#[inline] |
| 434 |
pub fn set_union(&mut self, other: LookSet) { |
| 435 |
*self = self.union(other); |
| 436 |
} |
| 437 |
|
| 438 |
/// Returns a new set that is the intersection of this and the one given. |
| 439 |
#[inline] |
| 440 |
pub fn intersect(self, other: LookSet) -> LookSet { |
| 441 |
LookSet { bits: self.bits & other.bits } |
| 442 |
} |
| 443 |
|
| 444 |
/// Updates this set in place with the result of intersecting it with the |
| 445 |
/// one given. |
| 446 |
#[inline] |
| 447 |
pub fn set_intersect(&mut self, other: LookSet) { |
| 448 |
*self = self.intersect(other); |
| 449 |
} |
| 450 |
|
| 451 |
/// Return a `LookSet` from the slice given as a native endian 32-bit |
| 452 |
/// integer. |
| 453 |
/// |
| 454 |
/// # Panics |
| 455 |
/// |
| 456 |
/// This panics if `slice.len() < 4`. |
| 457 |
#[inline] |
| 458 |
pub fn read_repr(slice: &[u8]) -> LookSet { |
| 459 |
let bits = u32::from_ne_bytes(slice[..4].try_into().unwrap()); |
| 460 |
LookSet { bits } |
| 461 |
} |
| 462 |
|
| 463 |
/// Write a `LookSet` as a native endian 32-bit integer to the beginning |
| 464 |
/// of the slice given. |
| 465 |
/// |
| 466 |
/// # Panics |
| 467 |
/// |
| 468 |
/// This panics if `slice.len() < 4`. |
| 469 |
#[inline] |
| 470 |
pub fn write_repr(self, slice: &mut [u8]) { |
| 471 |
let raw = self.bits.to_ne_bytes(); |
| 472 |
slice[0] = raw[0]; |
| 473 |
slice[1] = raw[1]; |
| 474 |
slice[2] = raw[2]; |
| 475 |
slice[3] = raw[3]; |
| 476 |
} |
| 477 |
|
| 478 |
/// Checks that all assertions in this set can be matched. |
| 479 |
/// |
| 480 |
/// Some assertions, such as Unicode word boundaries, require optional (but |
| 481 |
/// enabled by default) tables that may not be available. If there are |
| 482 |
/// assertions in this set that require tables that are not available, then |
| 483 |
/// this will return an error. |
| 484 |
/// |
| 485 |
/// Specifically, this returns an error when the the |
| 486 |
/// `unicode-word-boundary` feature is _not_ enabled _and_ this set |
| 487 |
/// contains a Unicode word boundary assertion. |
| 488 |
/// |
| 489 |
/// It can be useful to use this on the result of |
| 490 |
/// [`NFA::look_set_any`](crate::nfa::thompson::NFA::look_set_any) |
| 491 |
/// when building a matcher engine to ensure methods like |
| 492 |
/// [`LookMatcher::matches_set`] do not panic at search time. |
| 493 |
pub fn available(self) -> Result<(), UnicodeWordBoundaryError> { |
| 494 |
if self.contains_word_unicode() { |
| 495 |
UnicodeWordBoundaryError::check()?; |
| 496 |
} |
| 497 |
Ok(()) |
| 498 |
} |
| 499 |
} |
| 500 |
|
| 501 |
impl core::fmt::Debug for LookSet { |
| 502 |
fn fmt(&self, f: &mut core::fmt::Formatter) -> core::fmt::Result { |
| 503 |
if self.is_empty() { |
| 504 |
return write!(f, "∅"); |
| 505 |
} |
| 506 |
for look in self.iter() { |
| 507 |
write!(f, "{}", look.as_char())?; |
| 508 |
} |
| 509 |
Ok(()) |
| 510 |
} |
| 511 |
} |
| 512 |
|
| 513 |
/// An iterator over all look-around assertions in a [`LookSet`]. |
| 514 |
/// |
| 515 |
/// This iterator is created by [`LookSet::iter`]. |
| 516 |
#[derive(Clone, Debug)] |
| 517 |
pub struct LookSetIter { |
| 518 |
set: LookSet, |
| 519 |
} |
| 520 |
|
| 521 |
impl Iterator for LookSetIter { |
| 522 |
type Item = Look; |
| 523 |
|
| 524 |
#[inline] |
| 525 |
fn next(&mut self) -> Option<Look> { |
| 526 |
if self.set.is_empty() { |
| 527 |
return None; |
| 528 |
} |
| 529 |
// We'll never have more than u8::MAX distinct look-around assertions, |
| 530 |
// so 'bit' will always fit into a u16. |
| 531 |
let bit = u16::try_from(self.set.bits.trailing_zeros()).unwrap(); |
| 532 |
let look = Look::from_repr(1 << bit)?; |
| 533 |
self.set = self.set.remove(look); |
| 534 |
Some(look) |
| 535 |
} |
| 536 |
} |
| 537 |
|
| 538 |
/// A matcher for look-around assertions. |
| 539 |
/// |
| 540 |
/// This matcher permits configuring aspects of how look-around assertions are |
| 541 |
/// matched. |
| 542 |
/// |
| 543 |
/// # Example |
| 544 |
/// |
| 545 |
/// A `LookMatcher` can change the line terminator used for matching multi-line |
| 546 |
/// anchors such as `(?m:^)` and `(?m:$)`. |
| 547 |
/// |
| 548 |
/// ``` |
| 549 |
/// use regex_automata::{ |
| 550 |
/// nfa::thompson::{self, pikevm::PikeVM}, |
| 551 |
/// util::look::LookMatcher, |
| 552 |
/// Match, Input, |
| 553 |
/// }; |
| 554 |
/// |
| 555 |
/// let mut lookm = LookMatcher::new(); |
| 556 |
/// lookm.set_line_terminator(b'\x00'); |
| 557 |
/// |
| 558 |
/// let re = PikeVM::builder() |
| 559 |
/// .thompson(thompson::Config::new().look_matcher(lookm)) |
| 560 |
/// .build(r"(?m)^[a-z]+$")?; |
| 561 |
/// let mut cache = re.create_cache(); |
| 562 |
/// |
| 563 |
/// // Multi-line assertions now use NUL as a terminator. |
| 564 |
/// assert_eq!( |
| 565 |
/// Some(Match::must(0, 1..4)), |
| 566 |
/// re.find(&mut cache, b"\x00abc\x00"), |
| 567 |
/// ); |
| 568 |
/// // ... and \n is no longer recognized as a terminator. |
| 569 |
/// assert_eq!( |
| 570 |
/// None, |
| 571 |
/// re.find(&mut cache, b"\nabc\n"), |
| 572 |
/// ); |
| 573 |
/// |
| 574 |
/// # Ok::<(), Box<dyn std::error::Error>>(()) |
| 575 |
/// ``` |
| 576 |
#[derive(Clone, Debug)] |
| 577 |
pub struct LookMatcher { |
| 578 |
lineterm: DebugByte, |
| 579 |
} |
| 580 |
|
| 581 |
impl LookMatcher { |
| 582 |
/// Creates a new default matcher for look-around assertions. |
| 583 |
pub fn new() -> LookMatcher { |
| 584 |
LookMatcher { lineterm: DebugByte(b'\n') } |
| 585 |
} |
| 586 |
|
| 587 |
/// Sets the line terminator for use with `(?m:^)` and `(?m:$)`. |
| 588 |
/// |
| 589 |
/// Namely, instead of `^` matching after `\n` and `$` matching immediately |
| 590 |
/// before a `\n`, this will cause it to match after and before the byte |
| 591 |
/// given. |
| 592 |
/// |
| 593 |
/// It can occasionally be useful to use this to configure the line |
| 594 |
/// terminator to the NUL byte when searching binary data. |
| 595 |
/// |
| 596 |
/// Note that this does not apply to CRLF-aware line anchors such as |
| 597 |
/// `(?Rm:^)` and `(?Rm:$)`. CRLF-aware line anchors are hard-coded to |
| 598 |
/// use `\r` and `\n`. |
| 599 |
pub fn set_line_terminator(&mut self, byte: u8) -> &mut LookMatcher { |
| 600 |
self.lineterm.0 = byte; |
| 601 |
self |
| 602 |
} |
| 603 |
|
| 604 |
/// Returns the line terminator that was configured for this matcher. |
| 605 |
/// |
| 606 |
/// If no line terminator was configured, then this returns `\n`. |
| 607 |
/// |
| 608 |
/// Note that the line terminator should only be used for matching `(?m:^)` |
| 609 |
/// and `(?m:$)` assertions. It specifically should _not_ be used for |
| 610 |
/// matching the CRLF aware assertions `(?Rm:^)` and `(?Rm:$)`. |
| 611 |
pub fn get_line_terminator(&self) -> u8 { |
| 612 |
self.lineterm.0 |
| 613 |
} |
| 614 |
|
| 615 |
/// Returns true when the position `at` in `haystack` satisfies the given |
| 616 |
/// look-around assertion. |
| 617 |
/// |
| 618 |
/// # Panics |
| 619 |
/// |
| 620 |
/// This panics when testing any Unicode word boundary assertion in this |
| 621 |
/// set and when the Unicode word data is not available. Specifically, this |
| 622 |
/// only occurs when the `unicode-word-boundary` feature is not enabled. |
| 623 |
/// |
| 624 |
/// Since it's generally expected that this routine is called inside of |
| 625 |
/// a matching engine, callers should check the error condition when |
| 626 |
/// building the matching engine. If there is a Unicode word boundary |
| 627 |
/// in the matcher and the data isn't available, then the matcher should |
| 628 |
/// fail to build. |
| 629 |
/// |
| 630 |
/// Callers can check the error condition with [`LookSet::available`]. |
| 631 |
/// |
| 632 |
/// This also may panic when `at > haystack.len()`. Note that `at == |
| 633 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 634 |
#[inline] |
| 635 |
pub fn matches(&self, look: Look, haystack: &[u8], at: usize) -> bool { |
| 636 |
self.matches_inline(look, haystack, at) |
| 637 |
} |
| 638 |
|
| 639 |
/// Like `matches`, but forcefully inlined. |
| 640 |
/// |
| 641 |
/// # Panics |
| 642 |
/// |
| 643 |
/// This panics when testing any Unicode word boundary assertion in this |
| 644 |
/// set and when the Unicode word data is not available. Specifically, this |
| 645 |
/// only occurs when the `unicode-word-boundary` feature is not enabled. |
| 646 |
/// |
| 647 |
/// Since it's generally expected that this routine is called inside of |
| 648 |
/// a matching engine, callers should check the error condition when |
| 649 |
/// building the matching engine. If there is a Unicode word boundary |
| 650 |
/// in the matcher and the data isn't available, then the matcher should |
| 651 |
/// fail to build. |
| 652 |
/// |
| 653 |
/// Callers can check the error condition with [`LookSet::available`]. |
| 654 |
/// |
| 655 |
/// This also may panic when `at > haystack.len()`. Note that `at == |
| 656 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 657 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 658 |
pub(crate) fn matches_inline( |
| 659 |
&self, |
| 660 |
look: Look, |
| 661 |
haystack: &[u8], |
| 662 |
at: usize, |
| 663 |
) -> bool { |
| 664 |
match look { |
| 665 |
Look::Start => self.is_start(haystack, at), |
| 666 |
Look::End => self.is_end(haystack, at), |
| 667 |
Look::StartLF => self.is_start_lf(haystack, at), |
| 668 |
Look::EndLF => self.is_end_lf(haystack, at), |
| 669 |
Look::StartCRLF => self.is_start_crlf(haystack, at), |
| 670 |
Look::EndCRLF => self.is_end_crlf(haystack, at), |
| 671 |
Look::WordAscii => self.is_word_ascii(haystack, at), |
| 672 |
Look::WordAsciiNegate => self.is_word_ascii_negate(haystack, at), |
| 673 |
Look::WordUnicode => self.is_word_unicode(haystack, at).unwrap(), |
| 674 |
Look::WordUnicodeNegate => { |
| 675 |
self.is_word_unicode_negate(haystack, at).unwrap() |
| 676 |
} |
| 677 |
Look::WordStartAscii => self.is_word_start_ascii(haystack, at), |
| 678 |
Look::WordEndAscii => self.is_word_end_ascii(haystack, at), |
| 679 |
Look::WordStartUnicode => { |
| 680 |
self.is_word_start_unicode(haystack, at).unwrap() |
| 681 |
} |
| 682 |
Look::WordEndUnicode => { |
| 683 |
self.is_word_end_unicode(haystack, at).unwrap() |
| 684 |
} |
| 685 |
Look::WordStartHalfAscii => { |
| 686 |
self.is_word_start_half_ascii(haystack, at) |
| 687 |
} |
| 688 |
Look::WordEndHalfAscii => { |
| 689 |
self.is_word_end_half_ascii(haystack, at) |
| 690 |
} |
| 691 |
Look::WordStartHalfUnicode => { |
| 692 |
self.is_word_start_half_unicode(haystack, at).unwrap() |
| 693 |
} |
| 694 |
Look::WordEndHalfUnicode => { |
| 695 |
self.is_word_end_half_unicode(haystack, at).unwrap() |
| 696 |
} |
| 697 |
} |
| 698 |
} |
| 699 |
|
| 700 |
/// Returns true when _all_ of the assertions in the given set match at the |
| 701 |
/// given position in the haystack. |
| 702 |
/// |
| 703 |
/// # Panics |
| 704 |
/// |
| 705 |
/// This panics when testing any Unicode word boundary assertion in this |
| 706 |
/// set and when the Unicode word data is not available. Specifically, this |
| 707 |
/// only occurs when the `unicode-word-boundary` feature is not enabled. |
| 708 |
/// |
| 709 |
/// Since it's generally expected that this routine is called inside of |
| 710 |
/// a matching engine, callers should check the error condition when |
| 711 |
/// building the matching engine. If there is a Unicode word boundary |
| 712 |
/// in the matcher and the data isn't available, then the matcher should |
| 713 |
/// fail to build. |
| 714 |
/// |
| 715 |
/// Callers can check the error condition with [`LookSet::available`]. |
| 716 |
/// |
| 717 |
/// This also may panic when `at > haystack.len()`. Note that `at == |
| 718 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 719 |
#[inline] |
| 720 |
pub fn matches_set( |
| 721 |
&self, |
| 722 |
set: LookSet, |
| 723 |
haystack: &[u8], |
| 724 |
at: usize, |
| 725 |
) -> bool { |
| 726 |
self.matches_set_inline(set, haystack, at) |
| 727 |
} |
| 728 |
|
| 729 |
/// Like `LookSet::matches`, but forcefully inlined for perf. |
| 730 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 731 |
pub(crate) fn matches_set_inline( |
| 732 |
&self, |
| 733 |
set: LookSet, |
| 734 |
haystack: &[u8], |
| 735 |
at: usize, |
| 736 |
) -> bool { |
| 737 |
// This used to luse LookSet::iter with Look::matches on each element, |
| 738 |
// but that proved to be quite diastrous for perf. The manual "if |
| 739 |
// the set has this assertion, check it" turns out to be quite a bit |
| 740 |
// faster. |
| 741 |
if set.contains(Look::Start) { |
| 742 |
if !self.is_start(haystack, at) { |
| 743 |
return false; |
| 744 |
} |
| 745 |
} |
| 746 |
if set.contains(Look::End) { |
| 747 |
if !self.is_end(haystack, at) { |
| 748 |
return false; |
| 749 |
} |
| 750 |
} |
| 751 |
if set.contains(Look::StartLF) { |
| 752 |
if !self.is_start_lf(haystack, at) { |
| 753 |
return false; |
| 754 |
} |
| 755 |
} |
| 756 |
if set.contains(Look::EndLF) { |
| 757 |
if !self.is_end_lf(haystack, at) { |
| 758 |
return false; |
| 759 |
} |
| 760 |
} |
| 761 |
if set.contains(Look::StartCRLF) { |
| 762 |
if !self.is_start_crlf(haystack, at) { |
| 763 |
return false; |
| 764 |
} |
| 765 |
} |
| 766 |
if set.contains(Look::EndCRLF) { |
| 767 |
if !self.is_end_crlf(haystack, at) { |
| 768 |
return false; |
| 769 |
} |
| 770 |
} |
| 771 |
if set.contains(Look::WordAscii) { |
| 772 |
if !self.is_word_ascii(haystack, at) { |
| 773 |
return false; |
| 774 |
} |
| 775 |
} |
| 776 |
if set.contains(Look::WordAsciiNegate) { |
| 777 |
if !self.is_word_ascii_negate(haystack, at) { |
| 778 |
return false; |
| 779 |
} |
| 780 |
} |
| 781 |
if set.contains(Look::WordUnicode) { |
| 782 |
if !self.is_word_unicode(haystack, at).unwrap() { |
| 783 |
return false; |
| 784 |
} |
| 785 |
} |
| 786 |
if set.contains(Look::WordUnicodeNegate) { |
| 787 |
if !self.is_word_unicode_negate(haystack, at).unwrap() { |
| 788 |
return false; |
| 789 |
} |
| 790 |
} |
| 791 |
if set.contains(Look::WordStartAscii) { |
| 792 |
if !self.is_word_start_ascii(haystack, at) { |
| 793 |
return false; |
| 794 |
} |
| 795 |
} |
| 796 |
if set.contains(Look::WordEndAscii) { |
| 797 |
if !self.is_word_end_ascii(haystack, at) { |
| 798 |
return false; |
| 799 |
} |
| 800 |
} |
| 801 |
if set.contains(Look::WordStartUnicode) { |
| 802 |
if !self.is_word_start_unicode(haystack, at).unwrap() { |
| 803 |
return false; |
| 804 |
} |
| 805 |
} |
| 806 |
if set.contains(Look::WordEndUnicode) { |
| 807 |
if !self.is_word_end_unicode(haystack, at).unwrap() { |
| 808 |
return false; |
| 809 |
} |
| 810 |
} |
| 811 |
if set.contains(Look::WordStartHalfAscii) { |
| 812 |
if !self.is_word_start_half_ascii(haystack, at) { |
| 813 |
return false; |
| 814 |
} |
| 815 |
} |
| 816 |
if set.contains(Look::WordEndHalfAscii) { |
| 817 |
if !self.is_word_end_half_ascii(haystack, at) { |
| 818 |
return false; |
| 819 |
} |
| 820 |
} |
| 821 |
if set.contains(Look::WordStartHalfUnicode) { |
| 822 |
if !self.is_word_start_half_unicode(haystack, at).unwrap() { |
| 823 |
return false; |
| 824 |
} |
| 825 |
} |
| 826 |
if set.contains(Look::WordEndHalfUnicode) { |
| 827 |
if !self.is_word_end_half_unicode(haystack, at).unwrap() { |
| 828 |
return false; |
| 829 |
} |
| 830 |
} |
| 831 |
true |
| 832 |
} |
| 833 |
|
| 834 |
/// Split up the given byte classes into equivalence classes in a way that |
| 835 |
/// is consistent with this look-around assertion. |
| 836 |
#[cfg(feature = "alloc")] |
| 837 |
pub(crate) fn add_to_byteset( |
| 838 |
&self, |
| 839 |
look: Look, |
| 840 |
set: &mut crate::util::alphabet::ByteClassSet, |
| 841 |
) { |
| 842 |
match look { |
| 843 |
Look::Start | Look::End => {} |
| 844 |
Look::StartLF | Look::EndLF => { |
| 845 |
set.set_range(self.lineterm.0, self.lineterm.0); |
| 846 |
} |
| 847 |
Look::StartCRLF | Look::EndCRLF => { |
| 848 |
set.set_range(b'\r', b'\r'); |
| 849 |
set.set_range(b'\n', b'\n'); |
| 850 |
} |
| 851 |
Look::WordAscii |
| 852 |
| Look::WordAsciiNegate |
| 853 |
| Look::WordUnicode |
| 854 |
| Look::WordUnicodeNegate |
| 855 |
| Look::WordStartAscii |
| 856 |
| Look::WordEndAscii |
| 857 |
| Look::WordStartUnicode |
| 858 |
| Look::WordEndUnicode |
| 859 |
| Look::WordStartHalfAscii |
| 860 |
| Look::WordEndHalfAscii |
| 861 |
| Look::WordStartHalfUnicode |
| 862 |
| Look::WordEndHalfUnicode => { |
| 863 |
// We need to mark all ranges of bytes whose pairs result in |
| 864 |
// evaluating \b differently. This isn't technically correct |
| 865 |
// for Unicode word boundaries, but DFAs can't handle those |
| 866 |
// anyway, and thus, the byte classes don't need to either |
| 867 |
// since they are themselves only used in DFAs. |
| 868 |
// |
| 869 |
// FIXME: It seems like the calls to 'set_range' here are |
| 870 |
// completely invariant, which means we could just hard-code |
| 871 |
// them here without needing to write a loop. And we only need |
| 872 |
// to do this dance at most once per regex. |
| 873 |
// |
| 874 |
// FIXME: Is this correct for \B? |
| 875 |
let iswb = utf8::is_word_byte; |
| 876 |
// This unwrap is OK because we guard every use of 'asu8' with |
| 877 |
// a check that the input is <= 255. |
| 878 |
let asu8 = |b: u16| u8::try_from(b).unwrap(); |
| 879 |
let mut b1: u16 = 0; |
| 880 |
let mut b2: u16; |
| 881 |
while b1 <= 255 { |
| 882 |
b2 = b1 + 1; |
| 883 |
while b2 <= 255 && iswb(asu8(b1)) == iswb(asu8(b2)) { |
| 884 |
b2 += 1; |
| 885 |
} |
| 886 |
// The guards above guarantee that b2 can never get any |
| 887 |
// bigger. |
| 888 |
assert!(b2 <= 256); |
| 889 |
// Subtracting 1 from b2 is always OK because it is always |
| 890 |
// at least 1 greater than b1, and the assert above |
| 891 |
// guarantees that the asu8 conversion will succeed. |
| 892 |
set.set_range(asu8(b1), asu8(b2.checked_sub(1).unwrap())); |
| 893 |
b1 = b2; |
| 894 |
} |
| 895 |
} |
| 896 |
} |
| 897 |
} |
| 898 |
|
| 899 |
/// Returns true when [`Look::Start`] is satisfied `at` the given position |
| 900 |
/// in `haystack`. |
| 901 |
/// |
| 902 |
/// # Panics |
| 903 |
/// |
| 904 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 905 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 906 |
#[inline] |
| 907 |
pub fn is_start(&self, _haystack: &[u8], at: usize) -> bool { |
| 908 |
at == 0 |
| 909 |
} |
| 910 |
|
| 911 |
/// Returns true when [`Look::End`] is satisfied `at` the given position in |
| 912 |
/// `haystack`. |
| 913 |
/// |
| 914 |
/// # Panics |
| 915 |
/// |
| 916 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 917 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 918 |
#[inline] |
| 919 |
pub fn is_end(&self, haystack: &[u8], at: usize) -> bool { |
| 920 |
at == haystack.len() |
| 921 |
} |
| 922 |
|
| 923 |
/// Returns true when [`Look::StartLF`] is satisfied `at` the given |
| 924 |
/// position in `haystack`. |
| 925 |
/// |
| 926 |
/// # Panics |
| 927 |
/// |
| 928 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 929 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 930 |
#[inline] |
| 931 |
pub fn is_start_lf(&self, haystack: &[u8], at: usize) -> bool { |
| 932 |
self.is_start(haystack, at) || haystack[at - 1] == self.lineterm.0 |
| 933 |
} |
| 934 |
|
| 935 |
/// Returns true when [`Look::EndLF`] is satisfied `at` the given position |
| 936 |
/// in `haystack`. |
| 937 |
/// |
| 938 |
/// # Panics |
| 939 |
/// |
| 940 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 941 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 942 |
#[inline] |
| 943 |
pub fn is_end_lf(&self, haystack: &[u8], at: usize) -> bool { |
| 944 |
self.is_end(haystack, at) || haystack[at] == self.lineterm.0 |
| 945 |
} |
| 946 |
|
| 947 |
/// Returns true when [`Look::StartCRLF`] is satisfied `at` the given |
| 948 |
/// position in `haystack`. |
| 949 |
/// |
| 950 |
/// # Panics |
| 951 |
/// |
| 952 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 953 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 954 |
#[inline] |
| 955 |
pub fn is_start_crlf(&self, haystack: &[u8], at: usize) -> bool { |
| 956 |
self.is_start(haystack, at) |
| 957 |
|| haystack[at - 1] == b'\n' |
| 958 |
|| (haystack[at - 1] == b'\r' |
| 959 |
&& (at >= haystack.len() || haystack[at] != b'\n')) |
| 960 |
} |
| 961 |
|
| 962 |
/// Returns true when [`Look::EndCRLF`] is satisfied `at` the given |
| 963 |
/// position in `haystack`. |
| 964 |
/// |
| 965 |
/// # Panics |
| 966 |
/// |
| 967 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 968 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 969 |
#[inline] |
| 970 |
pub fn is_end_crlf(&self, haystack: &[u8], at: usize) -> bool { |
| 971 |
self.is_end(haystack, at) |
| 972 |
|| haystack[at] == b'\r' |
| 973 |
|| (haystack[at] == b'\n' |
| 974 |
&& (at == 0 || haystack[at - 1] != b'\r')) |
| 975 |
} |
| 976 |
|
| 977 |
/// Returns true when [`Look::WordAscii`] is satisfied `at` the given |
| 978 |
/// position in `haystack`. |
| 979 |
/// |
| 980 |
/// # Panics |
| 981 |
/// |
| 982 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 983 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 984 |
#[inline] |
| 985 |
pub fn is_word_ascii(&self, haystack: &[u8], at: usize) -> bool { |
| 986 |
let word_before = at > 0 && utf8::is_word_byte(haystack[at - 1]); |
| 987 |
let word_after = |
| 988 |
at < haystack.len() && utf8::is_word_byte(haystack[at]); |
| 989 |
word_before != word_after |
| 990 |
} |
| 991 |
|
| 992 |
/// Returns true when [`Look::WordAsciiNegate`] is satisfied `at` the given |
| 993 |
/// position in `haystack`. |
| 994 |
/// |
| 995 |
/// # Panics |
| 996 |
/// |
| 997 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 998 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 999 |
#[inline] |
| 1000 |
pub fn is_word_ascii_negate(&self, haystack: &[u8], at: usize) -> bool { |
| 1001 |
!self.is_word_ascii(haystack, at) |
| 1002 |
} |
| 1003 |
|
| 1004 |
/// Returns true when [`Look::WordUnicode`] is satisfied `at` the given |
| 1005 |
/// position in `haystack`. |
| 1006 |
/// |
| 1007 |
/// # Panics |
| 1008 |
/// |
| 1009 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 1010 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 1011 |
/// |
| 1012 |
/// # Errors |
| 1013 |
/// |
| 1014 |
/// This returns an error when Unicode word boundary tables |
| 1015 |
/// are not available. Specifically, this only occurs when the |
| 1016 |
/// `unicode-word-boundary` feature is not enabled. |
| 1017 |
#[inline] |
| 1018 |
pub fn is_word_unicode( |
| 1019 |
&self, |
| 1020 |
haystack: &[u8], |
| 1021 |
at: usize, |
| 1022 |
) -> Result<bool, UnicodeWordBoundaryError> { |
| 1023 |
let word_before = is_word_char::rev(haystack, at)?; |
| 1024 |
let word_after = is_word_char::fwd(haystack, at)?; |
| 1025 |
Ok(word_before != word_after) |
| 1026 |
} |
| 1027 |
|
| 1028 |
/// Returns true when [`Look::WordUnicodeNegate`] is satisfied `at` the |
| 1029 |
/// given position in `haystack`. |
| 1030 |
/// |
| 1031 |
/// # Panics |
| 1032 |
/// |
| 1033 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 1034 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 1035 |
/// |
| 1036 |
/// # Errors |
| 1037 |
/// |
| 1038 |
/// This returns an error when Unicode word boundary tables |
| 1039 |
/// are not available. Specifically, this only occurs when the |
| 1040 |
/// `unicode-word-boundary` feature is not enabled. |
| 1041 |
#[inline] |
| 1042 |
pub fn is_word_unicode_negate( |
| 1043 |
&self, |
| 1044 |
haystack: &[u8], |
| 1045 |
at: usize, |
| 1046 |
) -> Result<bool, UnicodeWordBoundaryError> { |
| 1047 |
// This is pretty subtle. Why do we need to do UTF-8 decoding here? |
| 1048 |
// Well... at time of writing, the is_word_char_{fwd,rev} routines will |
| 1049 |
// only return true if there is a valid UTF-8 encoding of a "word" |
| 1050 |
// codepoint, and false in every other case (including invalid UTF-8). |
| 1051 |
// This means that in regions of invalid UTF-8 (which might be a |
| 1052 |
// subset of valid UTF-8!), it would result in \B matching. While this |
| 1053 |
// would be questionable in the context of truly invalid UTF-8, it is |
| 1054 |
// *certainly* wrong to report match boundaries that split the encoding |
| 1055 |
// of a codepoint. So to work around this, we ensure that we can decode |
| 1056 |
// a codepoint on either side of `at`. If either direction fails, then |
| 1057 |
// we don't permit \B to match at all. |
| 1058 |
// |
| 1059 |
// Now, this isn't exactly optimal from a perf perspective. We could |
| 1060 |
// try and detect this in is_word_char::{fwd,rev}, but it's not clear |
| 1061 |
// if it's worth it. \B is, after all, rarely used. Even worse, |
| 1062 |
// is_word_char::{fwd,rev} could do its own UTF-8 decoding, and so this |
| 1063 |
// will wind up doing UTF-8 decoding twice. Owch. We could fix this |
| 1064 |
// with more code complexity, but it just doesn't feel worth it for \B. |
| 1065 |
// |
| 1066 |
// And in particular, we do *not* have to do this with \b, because \b |
| 1067 |
// *requires* that at least one side of `at` be a "word" codepoint, |
| 1068 |
// which in turn implies one side of `at` must be valid UTF-8. This in |
| 1069 |
// turn implies that \b can never split a valid UTF-8 encoding of a |
| 1070 |
// codepoint. In the case where one side of `at` is truly invalid UTF-8 |
| 1071 |
// and the other side IS a word codepoint, then we want \b to match |
| 1072 |
// since it represents a valid UTF-8 boundary. It also makes sense. For |
| 1073 |
// example, you'd want \b\w+\b to match 'abc' in '\xFFabc\xFF'. |
| 1074 |
// |
| 1075 |
// Note also that this is not just '!is_word_unicode(..)' like it is |
| 1076 |
// for the ASCII case. For example, neither \b nor \B is satisfied |
| 1077 |
// within invalid UTF-8 sequences. |
| 1078 |
let word_before = at > 0 |
| 1079 |
&& match utf8::decode_last(&haystack[..at]) { |
| 1080 |
None | Some(Err(_)) => return Ok(false), |
| 1081 |
Some(Ok(_)) => is_word_char::rev(haystack, at)?, |
| 1082 |
}; |
| 1083 |
let word_after = at < haystack.len() |
| 1084 |
&& match utf8::decode(&haystack[at..]) { |
| 1085 |
None | Some(Err(_)) => return Ok(false), |
| 1086 |
Some(Ok(_)) => is_word_char::fwd(haystack, at)?, |
| 1087 |
}; |
| 1088 |
Ok(word_before == word_after) |
| 1089 |
} |
| 1090 |
|
| 1091 |
/// Returns true when [`Look::WordStartAscii`] is satisfied `at` the given |
| 1092 |
/// position in `haystack`. |
| 1093 |
/// |
| 1094 |
/// # Panics |
| 1095 |
/// |
| 1096 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 1097 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 1098 |
#[inline] |
| 1099 |
pub fn is_word_start_ascii(&self, haystack: &[u8], at: usize) -> bool { |
| 1100 |
let word_before = at > 0 && utf8::is_word_byte(haystack[at - 1]); |
| 1101 |
let word_after = |
| 1102 |
at < haystack.len() && utf8::is_word_byte(haystack[at]); |
| 1103 |
!word_before && word_after |
| 1104 |
} |
| 1105 |
|
| 1106 |
/// Returns true when [`Look::WordEndAscii`] is satisfied `at` the given |
| 1107 |
/// position in `haystack`. |
| 1108 |
/// |
| 1109 |
/// # Panics |
| 1110 |
/// |
| 1111 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 1112 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 1113 |
#[inline] |
| 1114 |
pub fn is_word_end_ascii(&self, haystack: &[u8], at: usize) -> bool { |
| 1115 |
let word_before = at > 0 && utf8::is_word_byte(haystack[at - 1]); |
| 1116 |
let word_after = |
| 1117 |
at < haystack.len() && utf8::is_word_byte(haystack[at]); |
| 1118 |
word_before && !word_after |
| 1119 |
} |
| 1120 |
|
| 1121 |
/// Returns true when [`Look::WordStartUnicode`] is satisfied `at` the |
| 1122 |
/// given position in `haystack`. |
| 1123 |
/// |
| 1124 |
/// # Panics |
| 1125 |
/// |
| 1126 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 1127 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 1128 |
/// |
| 1129 |
/// # Errors |
| 1130 |
/// |
| 1131 |
/// This returns an error when Unicode word boundary tables |
| 1132 |
/// are not available. Specifically, this only occurs when the |
| 1133 |
/// `unicode-word-boundary` feature is not enabled. |
| 1134 |
#[inline] |
| 1135 |
pub fn is_word_start_unicode( |
| 1136 |
&self, |
| 1137 |
haystack: &[u8], |
| 1138 |
at: usize, |
| 1139 |
) -> Result<bool, UnicodeWordBoundaryError> { |
| 1140 |
let word_before = is_word_char::rev(haystack, at)?; |
| 1141 |
let word_after = is_word_char::fwd(haystack, at)?; |
| 1142 |
Ok(!word_before && word_after) |
| 1143 |
} |
| 1144 |
|
| 1145 |
/// Returns true when [`Look::WordEndUnicode`] is satisfied `at` the |
| 1146 |
/// given position in `haystack`. |
| 1147 |
/// |
| 1148 |
/// # Panics |
| 1149 |
/// |
| 1150 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 1151 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 1152 |
/// |
| 1153 |
/// # Errors |
| 1154 |
/// |
| 1155 |
/// This returns an error when Unicode word boundary tables |
| 1156 |
/// are not available. Specifically, this only occurs when the |
| 1157 |
/// `unicode-word-boundary` feature is not enabled. |
| 1158 |
#[inline] |
| 1159 |
pub fn is_word_end_unicode( |
| 1160 |
&self, |
| 1161 |
haystack: &[u8], |
| 1162 |
at: usize, |
| 1163 |
) -> Result<bool, UnicodeWordBoundaryError> { |
| 1164 |
let word_before = is_word_char::rev(haystack, at)?; |
| 1165 |
let word_after = is_word_char::fwd(haystack, at)?; |
| 1166 |
Ok(word_before && !word_after) |
| 1167 |
} |
| 1168 |
|
| 1169 |
/// Returns true when [`Look::WordStartHalfAscii`] is satisfied `at` the |
| 1170 |
/// given position in `haystack`. |
| 1171 |
/// |
| 1172 |
/// # Panics |
| 1173 |
/// |
| 1174 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 1175 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 1176 |
#[inline] |
| 1177 |
pub fn is_word_start_half_ascii( |
| 1178 |
&self, |
| 1179 |
haystack: &[u8], |
| 1180 |
at: usize, |
| 1181 |
) -> bool { |
| 1182 |
let word_before = at > 0 && utf8::is_word_byte(haystack[at - 1]); |
| 1183 |
!word_before |
| 1184 |
} |
| 1185 |
|
| 1186 |
/// Returns true when [`Look::WordEndHalfAscii`] is satisfied `at` the |
| 1187 |
/// given position in `haystack`. |
| 1188 |
/// |
| 1189 |
/// # Panics |
| 1190 |
/// |
| 1191 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 1192 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 1193 |
#[inline] |
| 1194 |
pub fn is_word_end_half_ascii(&self, haystack: &[u8], at: usize) -> bool { |
| 1195 |
let word_after = |
| 1196 |
at < haystack.len() && utf8::is_word_byte(haystack[at]); |
| 1197 |
!word_after |
| 1198 |
} |
| 1199 |
|
| 1200 |
/// Returns true when [`Look::WordStartHalfUnicode`] is satisfied `at` the |
| 1201 |
/// given position in `haystack`. |
| 1202 |
/// |
| 1203 |
/// # Panics |
| 1204 |
/// |
| 1205 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 1206 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 1207 |
/// |
| 1208 |
/// # Errors |
| 1209 |
/// |
| 1210 |
/// This returns an error when Unicode word boundary tables |
| 1211 |
/// are not available. Specifically, this only occurs when the |
| 1212 |
/// `unicode-word-boundary` feature is not enabled. |
| 1213 |
#[inline] |
| 1214 |
pub fn is_word_start_half_unicode( |
| 1215 |
&self, |
| 1216 |
haystack: &[u8], |
| 1217 |
at: usize, |
| 1218 |
) -> Result<bool, UnicodeWordBoundaryError> { |
| 1219 |
// See `is_word_unicode_negate` for why we need to do this. We don't |
| 1220 |
// need to do it for `is_word_start_unicode` because that guarantees |
| 1221 |
// that the position matched falls on a valid UTF-8 boundary given |
| 1222 |
// that the right side must be in \w. |
| 1223 |
let word_before = at > 0 |
| 1224 |
&& match utf8::decode_last(&haystack[..at]) { |
| 1225 |
None | Some(Err(_)) => return Ok(false), |
| 1226 |
Some(Ok(_)) => is_word_char::rev(haystack, at)?, |
| 1227 |
}; |
| 1228 |
Ok(!word_before) |
| 1229 |
} |
| 1230 |
|
| 1231 |
/// Returns true when [`Look::WordEndHalfUnicode`] is satisfied `at` the |
| 1232 |
/// given position in `haystack`. |
| 1233 |
/// |
| 1234 |
/// # Panics |
| 1235 |
/// |
| 1236 |
/// This may panic when `at > haystack.len()`. Note that `at == |
| 1237 |
/// haystack.len()` is legal and guaranteed not to panic. |
| 1238 |
/// |
| 1239 |
/// # Errors |
| 1240 |
/// |
| 1241 |
/// This returns an error when Unicode word boundary tables |
| 1242 |
/// are not available. Specifically, this only occurs when the |
| 1243 |
/// `unicode-word-boundary` feature is not enabled. |
| 1244 |
#[inline] |
| 1245 |
pub fn is_word_end_half_unicode( |
| 1246 |
&self, |
| 1247 |
haystack: &[u8], |
| 1248 |
at: usize, |
| 1249 |
) -> Result<bool, UnicodeWordBoundaryError> { |
| 1250 |
// See `is_word_unicode_negate` for why we need to do this. We don't |
| 1251 |
// need to do it for `is_word_end_unicode` because that guarantees |
| 1252 |
// that the position matched falls on a valid UTF-8 boundary given |
| 1253 |
// that the left side must be in \w. |
| 1254 |
let word_after = at < haystack.len() |
| 1255 |
&& match utf8::decode(&haystack[at..]) { |
| 1256 |
None | Some(Err(_)) => return Ok(false), |
| 1257 |
Some(Ok(_)) => is_word_char::fwd(haystack, at)?, |
| 1258 |
}; |
| 1259 |
Ok(!word_after) |
| 1260 |
} |
| 1261 |
} |
| 1262 |
|
| 1263 |
impl Default for LookMatcher { |
| 1264 |
fn default() -> LookMatcher { |
| 1265 |
LookMatcher::new() |
| 1266 |
} |
| 1267 |
} |
| 1268 |
|
| 1269 |
/// An error that occurs when the Unicode-aware `\w` class is unavailable. |
| 1270 |
/// |
| 1271 |
/// This error can occur when the data tables necessary for the Unicode aware |
| 1272 |
/// Perl character class `\w` are unavailable. The `\w` class is used to |
| 1273 |
/// determine whether a codepoint is considered a word character or not when |
| 1274 |
/// determining whether a Unicode aware `\b` (or `\B`) matches at a particular |
| 1275 |
/// position. |
| 1276 |
/// |
| 1277 |
/// This error can only occur when the `unicode-word-boundary` feature is |
| 1278 |
/// disabled. |
| 1279 |
#[derive(Clone, Debug)] |
| 1280 |
pub struct UnicodeWordBoundaryError(()); |
| 1281 |
|
| 1282 |
impl UnicodeWordBoundaryError { |
| 1283 |
#[cfg(not(feature = "unicode-word-boundary"))] |
| 1284 |
pub(crate) fn new() -> UnicodeWordBoundaryError { |
| 1285 |
UnicodeWordBoundaryError(()) |
| 1286 |
} |
| 1287 |
|
| 1288 |
/// Returns an error if and only if Unicode word boundary data is |
| 1289 |
/// unavailable. |
| 1290 |
pub fn check() -> Result<(), UnicodeWordBoundaryError> { |
| 1291 |
is_word_char::check() |
| 1292 |
} |
| 1293 |
} |
| 1294 |
|
| 1295 |
#[cfg(feature = "std")] |
| 1296 |
impl std::error::Error for UnicodeWordBoundaryError {} |
| 1297 |
|
| 1298 |
impl core::fmt::Display for UnicodeWordBoundaryError { |
| 1299 |
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result { |
| 1300 |
write!( |
| 1301 |
f, |
| 1302 |
"Unicode-aware \\b and \\B are unavailable because the \ |
| 1303 |
requisite data tables are missing, please enable the \ |
| 1304 |
unicode-word-boundary feature" |
| 1305 |
) |
| 1306 |
} |
| 1307 |
} |
| 1308 |
|
| 1309 |
// Below are FOUR different ways for checking whether whether a "word" |
| 1310 |
// codepoint exists at a particular position in the haystack. The four |
| 1311 |
// different approaches are, in order of preference: |
| 1312 |
// |
| 1313 |
// 1. Parse '\w', convert to an NFA, convert to a fully compiled DFA on the |
| 1314 |
// first call, and then use that DFA for all subsequent calls. |
| 1315 |
// 2. Do UTF-8 decoding and use regex_syntax::is_word_character if available. |
| 1316 |
// 3. Do UTF-8 decoding and use our own 'perl_word' table. |
| 1317 |
// 4. Return an error. |
| 1318 |
// |
| 1319 |
// The reason for all of these approaches is a combination of perf and |
| 1320 |
// permitting one to build regex-automata without the Unicode data necessary |
| 1321 |
// for handling Unicode-aware word boundaries. (In which case, '(?-u:\b)' would |
| 1322 |
// still work.) |
| 1323 |
// |
| 1324 |
// The DFA approach is the fastest, but it requires the regex parser, the |
| 1325 |
// NFA compiler, the DFA builder and the DFA search runtime. That's a lot to |
| 1326 |
// bring in, but if it's available, it's (probably) the best we can do. |
| 1327 |
// |
| 1328 |
// Approaches (2) and (3) are effectively equivalent, but (2) reuses the |
| 1329 |
// data in regex-syntax and avoids duplicating it in regex-automata. |
| 1330 |
// |
| 1331 |
// Finally, (4) unconditionally returns an error since the requisite data isn't |
| 1332 |
// available anywhere. |
| 1333 |
// |
| 1334 |
// There are actually more approaches possible that we didn't implement. For |
| 1335 |
// example, if the DFA builder is available but the syntax parser is not, we |
| 1336 |
// could technically hand construct our own NFA from the 'perl_word' data |
| 1337 |
// table. But to avoid some pretty hairy code duplication, we would in turn |
| 1338 |
// need to pull the UTF-8 compiler out of the NFA compiler. Yikes. |
| 1339 |
// |
| 1340 |
// A possibly more sensible alternative is to use a lazy DFA when the full |
| 1341 |
// DFA builder isn't available... |
| 1342 |
// |
| 1343 |
// Yet another choice would be to build the full DFA and then embed it into the |
| 1344 |
// source. Then we'd only need to bring in the DFA search runtime, which is |
| 1345 |
// considerably smaller than the DFA builder code. The problem here is that the |
| 1346 |
// Debian people have spooked me[1] into avoiding cyclic dependencies. Namely, |
| 1347 |
// we'd need to build regex-cli, which depends on regex-automata in order to |
| 1348 |
// build some part of regex-automata. But to be honest, something like this has |
| 1349 |
// to be allowed somehow? I just don't know what the right process is. |
| 1350 |
// |
| 1351 |
// There are perhaps other choices as well. Why did I stop at these 4? Because |
| 1352 |
// I wanted to preserve my sanity. I suspect I'll wind up adding the lazy DFA |
| 1353 |
// approach eventually, as the benefits of the DFA approach are somewhat |
| 1354 |
// compelling. The 'boundary-words-holmes' benchmark tests this. (Note that |
| 1355 |
// the commands below no longer work. If necessary, we should re-capitulate |
| 1356 |
// the benchmark from whole cloth in rebar.) |
| 1357 |
// |
| 1358 |
// $ regex-cli bench measure -f boundary-words-holmes -e pikevm > dfa.csv |
| 1359 |
// |
| 1360 |
// Then I changed the code below so that the util/unicode_data/perl_word table |
| 1361 |
// was used and re-ran the benchmark: |
| 1362 |
// |
| 1363 |
// $ regex-cli bench measure -f boundary-words-holmes -e pikevm > table.csv |
| 1364 |
// |
| 1365 |
// And compared them: |
| 1366 |
// |
| 1367 |
// $ regex-cli bench diff dfa.csv table.csv |
| 1368 |
// benchmark engine dfa table |
| 1369 |
// --------- ------ --- ----- |
| 1370 |
// internal/count/boundary-words-holmes regex/automata/pikevm 18.6 MB/s 12.9 MB/s |
| 1371 |
// |
| 1372 |
// Which is a nice improvement. |
| 1373 |
// |
| 1374 |
// UPDATE: It turns out that it takes approximately 22ms to build the reverse |
| 1375 |
// DFA for \w. (And about 3ms for the forward DFA.) It's probably not much in |
| 1376 |
// the grand scheme things, but that is a significant latency cost. So I'm not |
| 1377 |
// sure that's a good idea. I then tried using a lazy DFA instead, and that |
| 1378 |
// eliminated the overhead, but since the lazy DFA requires mutable working |
| 1379 |
// memory, that requires introducing a 'Cache' for every simultaneous call. |
| 1380 |
// |
| 1381 |
// I ended up deciding for now to just keep the "UTF-8 decode and check the |
| 1382 |
// table." The DFA and lazy DFA approaches are still below, but commented out. |
| 1383 |
// |
| 1384 |
// [1]: https://github.com/BurntSushi/ucd-generate/issues/11 |
| 1385 |
|
| 1386 |
/* |
| 1387 |
/// A module that looks for word codepoints using lazy DFAs. |
| 1388 |
#[cfg(all( |
| 1389 |
feature = "unicode-word-boundary", |
| 1390 |
feature = "syntax", |
| 1391 |
feature = "unicode-perl", |
| 1392 |
feature = "hybrid" |
| 1393 |
))] |
| 1394 |
mod is_word_char { |
| 1395 |
use alloc::vec::Vec; |
| 1396 |
|
| 1397 |
use crate::{ |
| 1398 |
hybrid::dfa::{Cache, DFA}, |
| 1399 |
nfa::thompson::NFA, |
| 1400 |
util::{lazy::Lazy, pool::Pool, primitives::StateID}, |
| 1401 |
Anchored, Input, |
| 1402 |
}; |
| 1403 |
|
| 1404 |
pub(super) fn check() -> Result<(), super::UnicodeWordBoundaryError> { |
| 1405 |
Ok(()) |
| 1406 |
} |
| 1407 |
|
| 1408 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1409 |
pub(super) fn fwd( |
| 1410 |
haystack: &[u8], |
| 1411 |
mut at: usize, |
| 1412 |
) -> Result<bool, super::UnicodeWordBoundaryError> { |
| 1413 |
static WORD: Lazy<DFA> = Lazy::new(|| DFA::new(r"\w").unwrap()); |
| 1414 |
static CACHE: Lazy<Pool<Cache>> = |
| 1415 |
Lazy::new(|| Pool::new(|| WORD.create_cache())); |
| 1416 |
let dfa = Lazy::get(&WORD); |
| 1417 |
let mut cache = Lazy::get(&CACHE).get(); |
| 1418 |
let mut sid = dfa |
| 1419 |
.start_state_forward( |
| 1420 |
&mut cache, |
| 1421 |
&Input::new("").anchored(Anchored::Yes), |
| 1422 |
) |
| 1423 |
.unwrap(); |
| 1424 |
while at < haystack.len() { |
| 1425 |
let byte = haystack[at]; |
| 1426 |
sid = dfa.next_state(&mut cache, sid, byte).unwrap(); |
| 1427 |
at += 1; |
| 1428 |
if sid.is_tagged() { |
| 1429 |
if sid.is_match() { |
| 1430 |
return Ok(true); |
| 1431 |
} else if sid.is_dead() { |
| 1432 |
return Ok(false); |
| 1433 |
} |
| 1434 |
} |
| 1435 |
} |
| 1436 |
Ok(dfa.next_eoi_state(&mut cache, sid).unwrap().is_match()) |
| 1437 |
} |
| 1438 |
|
| 1439 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1440 |
pub(super) fn rev( |
| 1441 |
haystack: &[u8], |
| 1442 |
mut at: usize, |
| 1443 |
) -> Result<bool, super::UnicodeWordBoundaryError> { |
| 1444 |
static WORD: Lazy<DFA> = Lazy::new(|| { |
| 1445 |
DFA::builder() |
| 1446 |
.thompson(NFA::config().reverse(true)) |
| 1447 |
.build(r"\w") |
| 1448 |
.unwrap() |
| 1449 |
}); |
| 1450 |
static CACHE: Lazy<Pool<Cache>> = |
| 1451 |
Lazy::new(|| Pool::new(|| WORD.create_cache())); |
| 1452 |
let dfa = Lazy::get(&WORD); |
| 1453 |
let mut cache = Lazy::get(&CACHE).get(); |
| 1454 |
let mut sid = dfa |
| 1455 |
.start_state_reverse( |
| 1456 |
&mut cache, |
| 1457 |
&Input::new("").anchored(Anchored::Yes), |
| 1458 |
) |
| 1459 |
.unwrap(); |
| 1460 |
while at > 0 { |
| 1461 |
at -= 1; |
| 1462 |
let byte = haystack[at]; |
| 1463 |
sid = dfa.next_state(&mut cache, sid, byte).unwrap(); |
| 1464 |
if sid.is_tagged() { |
| 1465 |
if sid.is_match() { |
| 1466 |
return Ok(true); |
| 1467 |
} else if sid.is_dead() { |
| 1468 |
return Ok(false); |
| 1469 |
} |
| 1470 |
} |
| 1471 |
} |
| 1472 |
Ok(dfa.next_eoi_state(&mut cache, sid).unwrap().is_match()) |
| 1473 |
} |
| 1474 |
} |
| 1475 |
*/ |
| 1476 |
|
| 1477 |
/* |
| 1478 |
/// A module that looks for word codepoints using fully compiled DFAs. |
| 1479 |
#[cfg(all( |
| 1480 |
feature = "unicode-word-boundary", |
| 1481 |
feature = "syntax", |
| 1482 |
feature = "unicode-perl", |
| 1483 |
feature = "dfa-build" |
| 1484 |
))] |
| 1485 |
mod is_word_char { |
| 1486 |
use alloc::vec::Vec; |
| 1487 |
|
| 1488 |
use crate::{ |
| 1489 |
dfa::{dense::DFA, Automaton, StartKind}, |
| 1490 |
nfa::thompson::NFA, |
| 1491 |
util::{lazy::Lazy, primitives::StateID}, |
| 1492 |
Anchored, Input, |
| 1493 |
}; |
| 1494 |
|
| 1495 |
pub(super) fn check() -> Result<(), super::UnicodeWordBoundaryError> { |
| 1496 |
Ok(()) |
| 1497 |
} |
| 1498 |
|
| 1499 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1500 |
pub(super) fn fwd( |
| 1501 |
haystack: &[u8], |
| 1502 |
mut at: usize, |
| 1503 |
) -> Result<bool, super::UnicodeWordBoundaryError> { |
| 1504 |
static WORD: Lazy<(DFA<Vec<u32>>, StateID)> = Lazy::new(|| { |
| 1505 |
let dfa = DFA::builder() |
| 1506 |
.configure(DFA::config().start_kind(StartKind::Anchored)) |
| 1507 |
.build(r"\w") |
| 1508 |
.unwrap(); |
| 1509 |
// OK because our regex has no look-around. |
| 1510 |
let start_id = dfa.universal_start_state(Anchored::Yes).unwrap(); |
| 1511 |
(dfa, start_id) |
| 1512 |
}); |
| 1513 |
let &(ref dfa, mut sid) = Lazy::get(&WORD); |
| 1514 |
while at < haystack.len() { |
| 1515 |
let byte = haystack[at]; |
| 1516 |
sid = dfa.next_state(sid, byte); |
| 1517 |
at += 1; |
| 1518 |
if dfa.is_special_state(sid) { |
| 1519 |
if dfa.is_match_state(sid) { |
| 1520 |
return Ok(true); |
| 1521 |
} else if dfa.is_dead_state(sid) { |
| 1522 |
return Ok(false); |
| 1523 |
} |
| 1524 |
} |
| 1525 |
} |
| 1526 |
Ok(dfa.is_match_state(dfa.next_eoi_state(sid))) |
| 1527 |
} |
| 1528 |
|
| 1529 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1530 |
pub(super) fn rev( |
| 1531 |
haystack: &[u8], |
| 1532 |
mut at: usize, |
| 1533 |
) -> Result<bool, super::UnicodeWordBoundaryError> { |
| 1534 |
static WORD: Lazy<(DFA<Vec<u32>>, StateID)> = Lazy::new(|| { |
| 1535 |
let dfa = DFA::builder() |
| 1536 |
.configure(DFA::config().start_kind(StartKind::Anchored)) |
| 1537 |
// From ad hoc measurements, it looks like setting |
| 1538 |
// shrink==false is slightly faster than shrink==true. I kind |
| 1539 |
// of feel like this indicates that shrinking is probably a |
| 1540 |
// failure, although it can help in some cases. Sigh. |
| 1541 |
.thompson(NFA::config().reverse(true).shrink(false)) |
| 1542 |
.build(r"\w") |
| 1543 |
.unwrap(); |
| 1544 |
// OK because our regex has no look-around. |
| 1545 |
let start_id = dfa.universal_start_state(Anchored::Yes).unwrap(); |
| 1546 |
(dfa, start_id) |
| 1547 |
}); |
| 1548 |
let &(ref dfa, mut sid) = Lazy::get(&WORD); |
| 1549 |
while at > 0 { |
| 1550 |
at -= 1; |
| 1551 |
let byte = haystack[at]; |
| 1552 |
sid = dfa.next_state(sid, byte); |
| 1553 |
if dfa.is_special_state(sid) { |
| 1554 |
if dfa.is_match_state(sid) { |
| 1555 |
return Ok(true); |
| 1556 |
} else if dfa.is_dead_state(sid) { |
| 1557 |
return Ok(false); |
| 1558 |
} |
| 1559 |
} |
| 1560 |
} |
| 1561 |
Ok(dfa.is_match_state(dfa.next_eoi_state(sid))) |
| 1562 |
} |
| 1563 |
} |
| 1564 |
*/ |
| 1565 |
|
| 1566 |
/// A module that looks for word codepoints using regex-syntax's data tables. |
| 1567 |
#[cfg(all( |
| 1568 |
feature = "unicode-word-boundary", |
| 1569 |
feature = "syntax", |
| 1570 |
feature = "unicode-perl", |
| 1571 |
))] |
| 1572 |
mod is_word_char { |
| 1573 |
use regex_syntax::try_is_word_character; |
| 1574 |
|
| 1575 |
use crate::util::utf8; |
| 1576 |
|
| 1577 |
pub(super) fn check() -> Result<(), super::UnicodeWordBoundaryError> { |
| 1578 |
Ok(()) |
| 1579 |
} |
| 1580 |
|
| 1581 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1582 |
pub(super) fn fwd( |
| 1583 |
haystack: &[u8], |
| 1584 |
at: usize, |
| 1585 |
) -> Result<bool, super::UnicodeWordBoundaryError> { |
| 1586 |
Ok(match utf8::decode(&haystack[at..]) { |
| 1587 |
None | Some(Err(_)) => false, |
| 1588 |
Some(Ok(ch)) => try_is_word_character(ch).expect( |
| 1589 |
"since unicode-word-boundary, syntax and unicode-perl \ |
| 1590 |
are all enabled, it is expected that \ |
| 1591 |
try_is_word_character succeeds", |
| 1592 |
), |
| 1593 |
}) |
| 1594 |
} |
| 1595 |
|
| 1596 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1597 |
pub(super) fn rev( |
| 1598 |
haystack: &[u8], |
| 1599 |
at: usize, |
| 1600 |
) -> Result<bool, super::UnicodeWordBoundaryError> { |
| 1601 |
Ok(match utf8::decode_last(&haystack[..at]) { |
| 1602 |
None | Some(Err(_)) => false, |
| 1603 |
Some(Ok(ch)) => try_is_word_character(ch).expect( |
| 1604 |
"since unicode-word-boundary, syntax and unicode-perl \ |
| 1605 |
are all enabled, it is expected that \ |
| 1606 |
try_is_word_character succeeds", |
| 1607 |
), |
| 1608 |
}) |
| 1609 |
} |
| 1610 |
} |
| 1611 |
|
| 1612 |
/// A module that looks for word codepoints using regex-automata's data tables |
| 1613 |
/// (which are only compiled when regex-syntax's tables aren't available). |
| 1614 |
/// |
| 1615 |
/// Note that the cfg should match the one in src/util/unicode_data/mod.rs for |
| 1616 |
/// perl_word. |
| 1617 |
#[cfg(all( |
| 1618 |
feature = "unicode-word-boundary", |
| 1619 |
not(all(feature = "syntax", feature = "unicode-perl")), |
| 1620 |
))] |
| 1621 |
mod is_word_char { |
| 1622 |
use crate::util::utf8; |
| 1623 |
|
| 1624 |
pub(super) fn check() -> Result<(), super::UnicodeWordBoundaryError> { |
| 1625 |
Ok(()) |
| 1626 |
} |
| 1627 |
|
| 1628 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1629 |
pub(super) fn fwd( |
| 1630 |
haystack: &[u8], |
| 1631 |
at: usize, |
| 1632 |
) -> Result<bool, super::UnicodeWordBoundaryError> { |
| 1633 |
Ok(match utf8::decode(&haystack[at..]) { |
| 1634 |
None | Some(Err(_)) => false, |
| 1635 |
Some(Ok(ch)) => is_word_character(ch), |
| 1636 |
}) |
| 1637 |
} |
| 1638 |
|
| 1639 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1640 |
pub(super) fn rev( |
| 1641 |
haystack: &[u8], |
| 1642 |
at: usize, |
| 1643 |
) -> Result<bool, super::UnicodeWordBoundaryError> { |
| 1644 |
Ok(match utf8::decode_last(&haystack[..at]) { |
| 1645 |
None | Some(Err(_)) => false, |
| 1646 |
Some(Ok(ch)) => is_word_character(ch), |
| 1647 |
}) |
| 1648 |
} |
| 1649 |
|
| 1650 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1651 |
fn is_word_character(c: char) -> bool { |
| 1652 |
use crate::util::{unicode_data::perl_word::PERL_WORD, utf8}; |
| 1653 |
|
| 1654 |
if u8::try_from(c).map_or(false, utf8::is_word_byte) { |
| 1655 |
return true; |
| 1656 |
} |
| 1657 |
PERL_WORD |
| 1658 |
.binary_search_by(|&(start, end)| { |
| 1659 |
use core::cmp::Ordering; |
| 1660 |
|
| 1661 |
if start <= c && c <= end { |
| 1662 |
Ordering::Equal |
| 1663 |
} else if start > c { |
| 1664 |
Ordering::Greater |
| 1665 |
} else { |
| 1666 |
Ordering::Less |
| 1667 |
} |
| 1668 |
}) |
| 1669 |
.is_ok() |
| 1670 |
} |
| 1671 |
} |
| 1672 |
|
| 1673 |
/// A module that always returns an error if Unicode word boundaries are |
| 1674 |
/// disabled. When this feature is disabled, then regex-automata will not |
| 1675 |
/// include its own data tables even if regex-syntax is disabled. |
| 1676 |
#[cfg(not(feature = "unicode-word-boundary"))] |
| 1677 |
mod is_word_char { |
| 1678 |
pub(super) fn check() -> Result<(), super::UnicodeWordBoundaryError> { |
| 1679 |
Err(super::UnicodeWordBoundaryError::new()) |
| 1680 |
} |
| 1681 |
|
| 1682 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1683 |
pub(super) fn fwd( |
| 1684 |
_bytes: &[u8], |
| 1685 |
_at: usize, |
| 1686 |
) -> Result<bool, super::UnicodeWordBoundaryError> { |
| 1687 |
Err(super::UnicodeWordBoundaryError::new()) |
| 1688 |
} |
| 1689 |
|
| 1690 |
#[cfg_attr(feature = "perf-inline", inline(always))] |
| 1691 |
pub(super) fn rev( |
| 1692 |
_bytes: &[u8], |
| 1693 |
_at: usize, |
| 1694 |
) -> Result<bool, super::UnicodeWordBoundaryError> { |
| 1695 |
Err(super::UnicodeWordBoundaryError::new()) |
| 1696 |
} |
| 1697 |
} |
| 1698 |
|
| 1699 |
#[cfg(test)] |
| 1700 |
mod tests { |
| 1701 |
use super::*; |
| 1702 |
|
| 1703 |
macro_rules! testlook { |
| 1704 |
($look:expr, $haystack:expr, $at:expr) => { |
| 1705 |
LookMatcher::default().matches($look, $haystack.as_bytes(), $at) |
| 1706 |
}; |
| 1707 |
} |
| 1708 |
|
| 1709 |
#[test] |
| 1710 |
fn look_matches_start_line() { |
| 1711 |
let look = Look::StartLF; |
| 1712 |
|
| 1713 |
assert!(testlook!(look, "", 0)); |
| 1714 |
assert!(testlook!(look, "\n", 0)); |
| 1715 |
assert!(testlook!(look, "\n", 1)); |
| 1716 |
assert!(testlook!(look, "a", 0)); |
| 1717 |
assert!(testlook!(look, "\na", 1)); |
| 1718 |
|
| 1719 |
assert!(!testlook!(look, "a", 1)); |
| 1720 |
assert!(!testlook!(look, "a\na", 1)); |
| 1721 |
} |
| 1722 |
|
| 1723 |
#[test] |
| 1724 |
fn look_matches_end_line() { |
| 1725 |
let look = Look::EndLF; |
| 1726 |
|
| 1727 |
assert!(testlook!(look, "", 0)); |
| 1728 |
assert!(testlook!(look, "\n", 1)); |
| 1729 |
assert!(testlook!(look, "\na", 0)); |
| 1730 |
assert!(testlook!(look, "\na", 2)); |
| 1731 |
assert!(testlook!(look, "a\na", 1)); |
| 1732 |
|
| 1733 |
assert!(!testlook!(look, "a", 0)); |
| 1734 |
assert!(!testlook!(look, "\na", 1)); |
| 1735 |
assert!(!testlook!(look, "a\na", 0)); |
| 1736 |
assert!(!testlook!(look, "a\na", 2)); |
| 1737 |
} |
| 1738 |
|
| 1739 |
#[test] |
| 1740 |
fn look_matches_start_text() { |
| 1741 |
let look = Look::Start; |
| 1742 |
|
| 1743 |
assert!(testlook!(look, "", 0)); |
| 1744 |
assert!(testlook!(look, "\n", 0)); |
| 1745 |
assert!(testlook!(look, "a", 0)); |
| 1746 |
|
| 1747 |
assert!(!testlook!(look, "\n", 1)); |
| 1748 |
assert!(!testlook!(look, "\na", 1)); |
| 1749 |
assert!(!testlook!(look, "a", 1)); |
| 1750 |
assert!(!testlook!(look, "a\na", 1)); |
| 1751 |
} |
| 1752 |
|
| 1753 |
#[test] |
| 1754 |
fn look_matches_end_text() { |
| 1755 |
let look = Look::End; |
| 1756 |
|
| 1757 |
assert!(testlook!(look, "", 0)); |
| 1758 |
assert!(testlook!(look, "\n", 1)); |
| 1759 |
assert!(testlook!(look, "\na", 2)); |
| 1760 |
|
| 1761 |
assert!(!testlook!(look, "\na", 0)); |
| 1762 |
assert!(!testlook!(look, "a\na", 1)); |
| 1763 |
assert!(!testlook!(look, "a", 0)); |
| 1764 |
assert!(!testlook!(look, "\na", 1)); |
| 1765 |
assert!(!testlook!(look, "a\na", 0)); |
| 1766 |
assert!(!testlook!(look, "a\na", 2)); |
| 1767 |
} |
| 1768 |
|
| 1769 |
#[test] |
| 1770 |
#[cfg(all(not(miri), feature = "unicode-word-boundary"))] |
| 1771 |
fn look_matches_word_unicode() { |
| 1772 |
let look = Look::WordUnicode; |
| 1773 |
|
| 1774 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 1775 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 1776 |
|
| 1777 |
// Simple ASCII word boundaries. |
| 1778 |
assert!(testlook!(look, "a", 0)); |
| 1779 |
assert!(testlook!(look, "a", 1)); |
| 1780 |
assert!(testlook!(look, "a ", 1)); |
| 1781 |
assert!(testlook!(look, " a ", 1)); |
| 1782 |
assert!(testlook!(look, " a ", 2)); |
| 1783 |
|
| 1784 |
// Unicode word boundaries with a non-ASCII codepoint. |
| 1785 |
assert!(testlook!(look, "𝛃", 0)); |
| 1786 |
assert!(testlook!(look, "𝛃", 4)); |
| 1787 |
assert!(testlook!(look, "𝛃 ", 4)); |
| 1788 |
assert!(testlook!(look, " 𝛃 ", 1)); |
| 1789 |
assert!(testlook!(look, " 𝛃 ", 5)); |
| 1790 |
|
| 1791 |
// Unicode word boundaries between non-ASCII codepoints. |
| 1792 |
assert!(testlook!(look, "𝛃𐆀", 0)); |
| 1793 |
assert!(testlook!(look, "𝛃𐆀", 4)); |
| 1794 |
|
| 1795 |
// Non word boundaries for ASCII. |
| 1796 |
assert!(!testlook!(look, "", 0)); |
| 1797 |
assert!(!testlook!(look, "ab", 1)); |
| 1798 |
assert!(!testlook!(look, "a ", 2)); |
| 1799 |
assert!(!testlook!(look, " a ", 0)); |
| 1800 |
assert!(!testlook!(look, " a ", 3)); |
| 1801 |
|
| 1802 |
// Non word boundaries with a non-ASCII codepoint. |
| 1803 |
assert!(!testlook!(look, "𝛃b", 4)); |
| 1804 |
assert!(!testlook!(look, "𝛃 ", 5)); |
| 1805 |
assert!(!testlook!(look, " 𝛃 ", 0)); |
| 1806 |
assert!(!testlook!(look, " 𝛃 ", 6)); |
| 1807 |
assert!(!testlook!(look, "𝛃", 1)); |
| 1808 |
assert!(!testlook!(look, "𝛃", 2)); |
| 1809 |
assert!(!testlook!(look, "𝛃", 3)); |
| 1810 |
|
| 1811 |
// Non word boundaries with non-ASCII codepoints. |
| 1812 |
assert!(!testlook!(look, "𝛃𐆀", 1)); |
| 1813 |
assert!(!testlook!(look, "𝛃𐆀", 2)); |
| 1814 |
assert!(!testlook!(look, "𝛃𐆀", 3)); |
| 1815 |
assert!(!testlook!(look, "𝛃𐆀", 5)); |
| 1816 |
assert!(!testlook!(look, "𝛃𐆀", 6)); |
| 1817 |
assert!(!testlook!(look, "𝛃𐆀", 7)); |
| 1818 |
assert!(!testlook!(look, "𝛃𐆀", 8)); |
| 1819 |
} |
| 1820 |
|
| 1821 |
#[test] |
| 1822 |
fn look_matches_word_ascii() { |
| 1823 |
let look = Look::WordAscii; |
| 1824 |
|
| 1825 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 1826 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 1827 |
|
| 1828 |
// Simple ASCII word boundaries. |
| 1829 |
assert!(testlook!(look, "a", 0)); |
| 1830 |
assert!(testlook!(look, "a", 1)); |
| 1831 |
assert!(testlook!(look, "a ", 1)); |
| 1832 |
assert!(testlook!(look, " a ", 1)); |
| 1833 |
assert!(testlook!(look, " a ", 2)); |
| 1834 |
|
| 1835 |
// Unicode word boundaries with a non-ASCII codepoint. Since this is |
| 1836 |
// an ASCII word boundary, none of these match. |
| 1837 |
assert!(!testlook!(look, "𝛃", 0)); |
| 1838 |
assert!(!testlook!(look, "𝛃", 4)); |
| 1839 |
assert!(!testlook!(look, "𝛃 ", 4)); |
| 1840 |
assert!(!testlook!(look, " 𝛃 ", 1)); |
| 1841 |
assert!(!testlook!(look, " 𝛃 ", 5)); |
| 1842 |
|
| 1843 |
// Unicode word boundaries between non-ASCII codepoints. Again, since |
| 1844 |
// this is an ASCII word boundary, none of these match. |
| 1845 |
assert!(!testlook!(look, "𝛃𐆀", 0)); |
| 1846 |
assert!(!testlook!(look, "𝛃𐆀", 4)); |
| 1847 |
|
| 1848 |
// Non word boundaries for ASCII. |
| 1849 |
assert!(!testlook!(look, "", 0)); |
| 1850 |
assert!(!testlook!(look, "ab", 1)); |
| 1851 |
assert!(!testlook!(look, "a ", 2)); |
| 1852 |
assert!(!testlook!(look, " a ", 0)); |
| 1853 |
assert!(!testlook!(look, " a ", 3)); |
| 1854 |
|
| 1855 |
// Non word boundaries with a non-ASCII codepoint. |
| 1856 |
assert!(testlook!(look, "𝛃b", 4)); |
| 1857 |
assert!(!testlook!(look, "𝛃 ", 5)); |
| 1858 |
assert!(!testlook!(look, " 𝛃 ", 0)); |
| 1859 |
assert!(!testlook!(look, " 𝛃 ", 6)); |
| 1860 |
assert!(!testlook!(look, "𝛃", 1)); |
| 1861 |
assert!(!testlook!(look, "𝛃", 2)); |
| 1862 |
assert!(!testlook!(look, "𝛃", 3)); |
| 1863 |
|
| 1864 |
// Non word boundaries with non-ASCII codepoints. |
| 1865 |
assert!(!testlook!(look, "𝛃𐆀", 1)); |
| 1866 |
assert!(!testlook!(look, "𝛃𐆀", 2)); |
| 1867 |
assert!(!testlook!(look, "𝛃𐆀", 3)); |
| 1868 |
assert!(!testlook!(look, "𝛃𐆀", 5)); |
| 1869 |
assert!(!testlook!(look, "𝛃𐆀", 6)); |
| 1870 |
assert!(!testlook!(look, "𝛃𐆀", 7)); |
| 1871 |
assert!(!testlook!(look, "𝛃𐆀", 8)); |
| 1872 |
} |
| 1873 |
|
| 1874 |
#[test] |
| 1875 |
#[cfg(all(not(miri), feature = "unicode-word-boundary"))] |
| 1876 |
fn look_matches_word_unicode_negate() { |
| 1877 |
let look = Look::WordUnicodeNegate; |
| 1878 |
|
| 1879 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 1880 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 1881 |
|
| 1882 |
// Simple ASCII word boundaries. |
| 1883 |
assert!(!testlook!(look, "a", 0)); |
| 1884 |
assert!(!testlook!(look, "a", 1)); |
| 1885 |
assert!(!testlook!(look, "a ", 1)); |
| 1886 |
assert!(!testlook!(look, " a ", 1)); |
| 1887 |
assert!(!testlook!(look, " a ", 2)); |
| 1888 |
|
| 1889 |
// Unicode word boundaries with a non-ASCII codepoint. |
| 1890 |
assert!(!testlook!(look, "𝛃", 0)); |
| 1891 |
assert!(!testlook!(look, "𝛃", 4)); |
| 1892 |
assert!(!testlook!(look, "𝛃 ", 4)); |
| 1893 |
assert!(!testlook!(look, " 𝛃 ", 1)); |
| 1894 |
assert!(!testlook!(look, " 𝛃 ", 5)); |
| 1895 |
|
| 1896 |
// Unicode word boundaries between non-ASCII codepoints. |
| 1897 |
assert!(!testlook!(look, "𝛃𐆀", 0)); |
| 1898 |
assert!(!testlook!(look, "𝛃𐆀", 4)); |
| 1899 |
|
| 1900 |
// Non word boundaries for ASCII. |
| 1901 |
assert!(testlook!(look, "", 0)); |
| 1902 |
assert!(testlook!(look, "ab", 1)); |
| 1903 |
assert!(testlook!(look, "a ", 2)); |
| 1904 |
assert!(testlook!(look, " a ", 0)); |
| 1905 |
assert!(testlook!(look, " a ", 3)); |
| 1906 |
|
| 1907 |
// Non word boundaries with a non-ASCII codepoint. |
| 1908 |
assert!(testlook!(look, "𝛃b", 4)); |
| 1909 |
assert!(testlook!(look, "𝛃 ", 5)); |
| 1910 |
assert!(testlook!(look, " 𝛃 ", 0)); |
| 1911 |
assert!(testlook!(look, " 𝛃 ", 6)); |
| 1912 |
// These don't match because they could otherwise return an offset that |
| 1913 |
// splits the UTF-8 encoding of a codepoint. |
| 1914 |
assert!(!testlook!(look, "𝛃", 1)); |
| 1915 |
assert!(!testlook!(look, "𝛃", 2)); |
| 1916 |
assert!(!testlook!(look, "𝛃", 3)); |
| 1917 |
|
| 1918 |
// Non word boundaries with non-ASCII codepoints. These also don't |
| 1919 |
// match because they could otherwise return an offset that splits the |
| 1920 |
// UTF-8 encoding of a codepoint. |
| 1921 |
assert!(!testlook!(look, "𝛃𐆀", 1)); |
| 1922 |
assert!(!testlook!(look, "𝛃𐆀", 2)); |
| 1923 |
assert!(!testlook!(look, "𝛃𐆀", 3)); |
| 1924 |
assert!(!testlook!(look, "𝛃𐆀", 5)); |
| 1925 |
assert!(!testlook!(look, "𝛃𐆀", 6)); |
| 1926 |
assert!(!testlook!(look, "𝛃𐆀", 7)); |
| 1927 |
// But this one does, since 𐆀 isn't a word codepoint, and 8 is the end |
| 1928 |
// of the haystack. So the "end" of the haystack isn't a word and 𐆀 |
| 1929 |
// isn't a word, thus, \B matches. |
| 1930 |
assert!(testlook!(look, "𝛃𐆀", 8)); |
| 1931 |
} |
| 1932 |
|
| 1933 |
#[test] |
| 1934 |
fn look_matches_word_ascii_negate() { |
| 1935 |
let look = Look::WordAsciiNegate; |
| 1936 |
|
| 1937 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 1938 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 1939 |
|
| 1940 |
// Simple ASCII word boundaries. |
| 1941 |
assert!(!testlook!(look, "a", 0)); |
| 1942 |
assert!(!testlook!(look, "a", 1)); |
| 1943 |
assert!(!testlook!(look, "a ", 1)); |
| 1944 |
assert!(!testlook!(look, " a ", 1)); |
| 1945 |
assert!(!testlook!(look, " a ", 2)); |
| 1946 |
|
| 1947 |
// Unicode word boundaries with a non-ASCII codepoint. Since this is |
| 1948 |
// an ASCII word boundary, none of these match. |
| 1949 |
assert!(testlook!(look, "𝛃", 0)); |
| 1950 |
assert!(testlook!(look, "𝛃", 4)); |
| 1951 |
assert!(testlook!(look, "𝛃 ", 4)); |
| 1952 |
assert!(testlook!(look, " 𝛃 ", 1)); |
| 1953 |
assert!(testlook!(look, " 𝛃 ", 5)); |
| 1954 |
|
| 1955 |
// Unicode word boundaries between non-ASCII codepoints. Again, since |
| 1956 |
// this is an ASCII word boundary, none of these match. |
| 1957 |
assert!(testlook!(look, "𝛃𐆀", 0)); |
| 1958 |
assert!(testlook!(look, "𝛃𐆀", 4)); |
| 1959 |
|
| 1960 |
// Non word boundaries for ASCII. |
| 1961 |
assert!(testlook!(look, "", 0)); |
| 1962 |
assert!(testlook!(look, "ab", 1)); |
| 1963 |
assert!(testlook!(look, "a ", 2)); |
| 1964 |
assert!(testlook!(look, " a ", 0)); |
| 1965 |
assert!(testlook!(look, " a ", 3)); |
| 1966 |
|
| 1967 |
// Non word boundaries with a non-ASCII codepoint. |
| 1968 |
assert!(!testlook!(look, "𝛃b", 4)); |
| 1969 |
assert!(testlook!(look, "𝛃 ", 5)); |
| 1970 |
assert!(testlook!(look, " 𝛃 ", 0)); |
| 1971 |
assert!(testlook!(look, " 𝛃 ", 6)); |
| 1972 |
assert!(testlook!(look, "𝛃", 1)); |
| 1973 |
assert!(testlook!(look, "𝛃", 2)); |
| 1974 |
assert!(testlook!(look, "𝛃", 3)); |
| 1975 |
|
| 1976 |
// Non word boundaries with non-ASCII codepoints. |
| 1977 |
assert!(testlook!(look, "𝛃𐆀", 1)); |
| 1978 |
assert!(testlook!(look, "𝛃𐆀", 2)); |
| 1979 |
assert!(testlook!(look, "𝛃𐆀", 3)); |
| 1980 |
assert!(testlook!(look, "𝛃𐆀", 5)); |
| 1981 |
assert!(testlook!(look, "𝛃𐆀", 6)); |
| 1982 |
assert!(testlook!(look, "𝛃𐆀", 7)); |
| 1983 |
assert!(testlook!(look, "𝛃𐆀", 8)); |
| 1984 |
} |
| 1985 |
|
| 1986 |
#[test] |
| 1987 |
fn look_matches_word_start_ascii() { |
| 1988 |
let look = Look::WordStartAscii; |
| 1989 |
|
| 1990 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 1991 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 1992 |
|
| 1993 |
// Simple ASCII word boundaries. |
| 1994 |
assert!(testlook!(look, "a", 0)); |
| 1995 |
assert!(!testlook!(look, "a", 1)); |
| 1996 |
assert!(!testlook!(look, "a ", 1)); |
| 1997 |
assert!(testlook!(look, " a ", 1)); |
| 1998 |
assert!(!testlook!(look, " a ", 2)); |
| 1999 |
|
| 2000 |
// Unicode word boundaries with a non-ASCII codepoint. Since this is |
| 2001 |
// an ASCII word boundary, none of these match. |
| 2002 |
assert!(!testlook!(look, "𝛃", 0)); |
| 2003 |
assert!(!testlook!(look, "𝛃", 4)); |
| 2004 |
assert!(!testlook!(look, "𝛃 ", 4)); |
| 2005 |
assert!(!testlook!(look, " 𝛃 ", 1)); |
| 2006 |
assert!(!testlook!(look, " 𝛃 ", 5)); |
| 2007 |
|
| 2008 |
// Unicode word boundaries between non-ASCII codepoints. Again, since |
| 2009 |
// this is an ASCII word boundary, none of these match. |
| 2010 |
assert!(!testlook!(look, "𝛃𐆀", 0)); |
| 2011 |
assert!(!testlook!(look, "𝛃𐆀", 4)); |
| 2012 |
|
| 2013 |
// Non word boundaries for ASCII. |
| 2014 |
assert!(!testlook!(look, "", 0)); |
| 2015 |
assert!(!testlook!(look, "ab", 1)); |
| 2016 |
assert!(!testlook!(look, "a ", 2)); |
| 2017 |
assert!(!testlook!(look, " a ", 0)); |
| 2018 |
assert!(!testlook!(look, " a ", 3)); |
| 2019 |
|
| 2020 |
// Non word boundaries with a non-ASCII codepoint. |
| 2021 |
assert!(testlook!(look, "𝛃b", 4)); |
| 2022 |
assert!(!testlook!(look, "b𝛃", 1)); |
| 2023 |
assert!(!testlook!(look, "𝛃 ", 5)); |
| 2024 |
assert!(!testlook!(look, " 𝛃 ", 0)); |
| 2025 |
assert!(!testlook!(look, " 𝛃 ", 6)); |
| 2026 |
assert!(!testlook!(look, "𝛃", 1)); |
| 2027 |
assert!(!testlook!(look, "𝛃", 2)); |
| 2028 |
assert!(!testlook!(look, "𝛃", 3)); |
| 2029 |
|
| 2030 |
// Non word boundaries with non-ASCII codepoints. |
| 2031 |
assert!(!testlook!(look, "𝛃𐆀", 1)); |
| 2032 |
assert!(!testlook!(look, "𝛃𐆀", 2)); |
| 2033 |
assert!(!testlook!(look, "𝛃𐆀", 3)); |
| 2034 |
assert!(!testlook!(look, "𝛃𐆀", 5)); |
| 2035 |
assert!(!testlook!(look, "𝛃𐆀", 6)); |
| 2036 |
assert!(!testlook!(look, "𝛃𐆀", 7)); |
| 2037 |
assert!(!testlook!(look, "𝛃𐆀", 8)); |
| 2038 |
} |
| 2039 |
|
| 2040 |
#[test] |
| 2041 |
fn look_matches_word_end_ascii() { |
| 2042 |
let look = Look::WordEndAscii; |
| 2043 |
|
| 2044 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 2045 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 2046 |
|
| 2047 |
// Simple ASCII word boundaries. |
| 2048 |
assert!(!testlook!(look, "a", 0)); |
| 2049 |
assert!(testlook!(look, "a", 1)); |
| 2050 |
assert!(testlook!(look, "a ", 1)); |
| 2051 |
assert!(!testlook!(look, " a ", 1)); |
| 2052 |
assert!(testlook!(look, " a ", 2)); |
| 2053 |
|
| 2054 |
// Unicode word boundaries with a non-ASCII codepoint. Since this is |
| 2055 |
// an ASCII word boundary, none of these match. |
| 2056 |
assert!(!testlook!(look, "𝛃", 0)); |
| 2057 |
assert!(!testlook!(look, "𝛃", 4)); |
| 2058 |
assert!(!testlook!(look, "𝛃 ", 4)); |
| 2059 |
assert!(!testlook!(look, " 𝛃 ", 1)); |
| 2060 |
assert!(!testlook!(look, " 𝛃 ", 5)); |
| 2061 |
|
| 2062 |
// Unicode word boundaries between non-ASCII codepoints. Again, since |
| 2063 |
// this is an ASCII word boundary, none of these match. |
| 2064 |
assert!(!testlook!(look, "𝛃𐆀", 0)); |
| 2065 |
assert!(!testlook!(look, "𝛃𐆀", 4)); |
| 2066 |
|
| 2067 |
// Non word boundaries for ASCII. |
| 2068 |
assert!(!testlook!(look, "", 0)); |
| 2069 |
assert!(!testlook!(look, "ab", 1)); |
| 2070 |
assert!(!testlook!(look, "a ", 2)); |
| 2071 |
assert!(!testlook!(look, " a ", 0)); |
| 2072 |
assert!(!testlook!(look, " a ", 3)); |
| 2073 |
|
| 2074 |
// Non word boundaries with a non-ASCII codepoint. |
| 2075 |
assert!(!testlook!(look, "𝛃b", 4)); |
| 2076 |
assert!(testlook!(look, "b𝛃", 1)); |
| 2077 |
assert!(!testlook!(look, "𝛃 ", 5)); |
| 2078 |
assert!(!testlook!(look, " 𝛃 ", 0)); |
| 2079 |
assert!(!testlook!(look, " 𝛃 ", 6)); |
| 2080 |
assert!(!testlook!(look, "𝛃", 1)); |
| 2081 |
assert!(!testlook!(look, "𝛃", 2)); |
| 2082 |
assert!(!testlook!(look, "𝛃", 3)); |
| 2083 |
|
| 2084 |
// Non word boundaries with non-ASCII codepoints. |
| 2085 |
assert!(!testlook!(look, "𝛃𐆀", 1)); |
| 2086 |
assert!(!testlook!(look, "𝛃𐆀", 2)); |
| 2087 |
assert!(!testlook!(look, "𝛃𐆀", 3)); |
| 2088 |
assert!(!testlook!(look, "𝛃𐆀", 5)); |
| 2089 |
assert!(!testlook!(look, "𝛃𐆀", 6)); |
| 2090 |
assert!(!testlook!(look, "𝛃𐆀", 7)); |
| 2091 |
assert!(!testlook!(look, "𝛃𐆀", 8)); |
| 2092 |
} |
| 2093 |
|
| 2094 |
#[test] |
| 2095 |
#[cfg(all(not(miri), feature = "unicode-word-boundary"))] |
| 2096 |
fn look_matches_word_start_unicode() { |
| 2097 |
let look = Look::WordStartUnicode; |
| 2098 |
|
| 2099 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 2100 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 2101 |
|
| 2102 |
// Simple ASCII word boundaries. |
| 2103 |
assert!(testlook!(look, "a", 0)); |
| 2104 |
assert!(!testlook!(look, "a", 1)); |
| 2105 |
assert!(!testlook!(look, "a ", 1)); |
| 2106 |
assert!(testlook!(look, " a ", 1)); |
| 2107 |
assert!(!testlook!(look, " a ", 2)); |
| 2108 |
|
| 2109 |
// Unicode word boundaries with a non-ASCII codepoint. |
| 2110 |
assert!(testlook!(look, "𝛃", 0)); |
| 2111 |
assert!(!testlook!(look, "𝛃", 4)); |
| 2112 |
assert!(!testlook!(look, "𝛃 ", 4)); |
| 2113 |
assert!(testlook!(look, " 𝛃 ", 1)); |
| 2114 |
assert!(!testlook!(look, " 𝛃 ", 5)); |
| 2115 |
|
| 2116 |
// Unicode word boundaries between non-ASCII codepoints. |
| 2117 |
assert!(testlook!(look, "𝛃𐆀", 0)); |
| 2118 |
assert!(!testlook!(look, "𝛃𐆀", 4)); |
| 2119 |
|
| 2120 |
// Non word boundaries for ASCII. |
| 2121 |
assert!(!testlook!(look, "", 0)); |
| 2122 |
assert!(!testlook!(look, "ab", 1)); |
| 2123 |
assert!(!testlook!(look, "a ", 2)); |
| 2124 |
assert!(!testlook!(look, " a ", 0)); |
| 2125 |
assert!(!testlook!(look, " a ", 3)); |
| 2126 |
|
| 2127 |
// Non word boundaries with a non-ASCII codepoint. |
| 2128 |
assert!(!testlook!(look, "𝛃b", 4)); |
| 2129 |
assert!(!testlook!(look, "b𝛃", 1)); |
| 2130 |
assert!(!testlook!(look, "𝛃 ", 5)); |
| 2131 |
assert!(!testlook!(look, " 𝛃 ", 0)); |
| 2132 |
assert!(!testlook!(look, " 𝛃 ", 6)); |
| 2133 |
assert!(!testlook!(look, "𝛃", 1)); |
| 2134 |
assert!(!testlook!(look, "𝛃", 2)); |
| 2135 |
assert!(!testlook!(look, "𝛃", 3)); |
| 2136 |
|
| 2137 |
// Non word boundaries with non-ASCII codepoints. |
| 2138 |
assert!(!testlook!(look, "𝛃𐆀", 1)); |
| 2139 |
assert!(!testlook!(look, "𝛃𐆀", 2)); |
| 2140 |
assert!(!testlook!(look, "𝛃𐆀", 3)); |
| 2141 |
assert!(!testlook!(look, "𝛃𐆀", 5)); |
| 2142 |
assert!(!testlook!(look, "𝛃𐆀", 6)); |
| 2143 |
assert!(!testlook!(look, "𝛃𐆀", 7)); |
| 2144 |
assert!(!testlook!(look, "𝛃𐆀", 8)); |
| 2145 |
} |
| 2146 |
|
| 2147 |
#[test] |
| 2148 |
#[cfg(all(not(miri), feature = "unicode-word-boundary"))] |
| 2149 |
fn look_matches_word_end_unicode() { |
| 2150 |
let look = Look::WordEndUnicode; |
| 2151 |
|
| 2152 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 2153 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 2154 |
|
| 2155 |
// Simple ASCII word boundaries. |
| 2156 |
assert!(!testlook!(look, "a", 0)); |
| 2157 |
assert!(testlook!(look, "a", 1)); |
| 2158 |
assert!(testlook!(look, "a ", 1)); |
| 2159 |
assert!(!testlook!(look, " a ", 1)); |
| 2160 |
assert!(testlook!(look, " a ", 2)); |
| 2161 |
|
| 2162 |
// Unicode word boundaries with a non-ASCII codepoint. |
| 2163 |
assert!(!testlook!(look, "𝛃", 0)); |
| 2164 |
assert!(testlook!(look, "𝛃", 4)); |
| 2165 |
assert!(testlook!(look, "𝛃 ", 4)); |
| 2166 |
assert!(!testlook!(look, " 𝛃 ", 1)); |
| 2167 |
assert!(testlook!(look, " 𝛃 ", 5)); |
| 2168 |
|
| 2169 |
// Unicode word boundaries between non-ASCII codepoints. |
| 2170 |
assert!(!testlook!(look, "𝛃𐆀", 0)); |
| 2171 |
assert!(testlook!(look, "𝛃𐆀", 4)); |
| 2172 |
|
| 2173 |
// Non word boundaries for ASCII. |
| 2174 |
assert!(!testlook!(look, "", 0)); |
| 2175 |
assert!(!testlook!(look, "ab", 1)); |
| 2176 |
assert!(!testlook!(look, "a ", 2)); |
| 2177 |
assert!(!testlook!(look, " a ", 0)); |
| 2178 |
assert!(!testlook!(look, " a ", 3)); |
| 2179 |
|
| 2180 |
// Non word boundaries with a non-ASCII codepoint. |
| 2181 |
assert!(!testlook!(look, "𝛃b", 4)); |
| 2182 |
assert!(!testlook!(look, "b𝛃", 1)); |
| 2183 |
assert!(!testlook!(look, "𝛃 ", 5)); |
| 2184 |
assert!(!testlook!(look, " 𝛃 ", 0)); |
| 2185 |
assert!(!testlook!(look, " 𝛃 ", 6)); |
| 2186 |
assert!(!testlook!(look, "𝛃", 1)); |
| 2187 |
assert!(!testlook!(look, "𝛃", 2)); |
| 2188 |
assert!(!testlook!(look, "𝛃", 3)); |
| 2189 |
|
| 2190 |
// Non word boundaries with non-ASCII codepoints. |
| 2191 |
assert!(!testlook!(look, "𝛃𐆀", 1)); |
| 2192 |
assert!(!testlook!(look, "𝛃𐆀", 2)); |
| 2193 |
assert!(!testlook!(look, "𝛃𐆀", 3)); |
| 2194 |
assert!(!testlook!(look, "𝛃𐆀", 5)); |
| 2195 |
assert!(!testlook!(look, "𝛃𐆀", 6)); |
| 2196 |
assert!(!testlook!(look, "𝛃𐆀", 7)); |
| 2197 |
assert!(!testlook!(look, "𝛃𐆀", 8)); |
| 2198 |
} |
| 2199 |
|
| 2200 |
#[test] |
| 2201 |
fn look_matches_word_start_half_ascii() { |
| 2202 |
let look = Look::WordStartHalfAscii; |
| 2203 |
|
| 2204 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 2205 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 2206 |
|
| 2207 |
// Simple ASCII word boundaries. |
| 2208 |
assert!(testlook!(look, "a", 0)); |
| 2209 |
assert!(!testlook!(look, "a", 1)); |
| 2210 |
assert!(!testlook!(look, "a ", 1)); |
| 2211 |
assert!(testlook!(look, " a ", 1)); |
| 2212 |
assert!(!testlook!(look, " a ", 2)); |
| 2213 |
|
| 2214 |
// Unicode word boundaries with a non-ASCII codepoint. Since this is |
| 2215 |
// an ASCII word boundary, none of these match. |
| 2216 |
assert!(testlook!(look, "𝛃", 0)); |
| 2217 |
assert!(testlook!(look, "𝛃", 4)); |
| 2218 |
assert!(testlook!(look, "𝛃 ", 4)); |
| 2219 |
assert!(testlook!(look, " 𝛃 ", 1)); |
| 2220 |
assert!(testlook!(look, " 𝛃 ", 5)); |
| 2221 |
|
| 2222 |
// Unicode word boundaries between non-ASCII codepoints. Again, since |
| 2223 |
// this is an ASCII word boundary, none of these match. |
| 2224 |
assert!(testlook!(look, "𝛃𐆀", 0)); |
| 2225 |
assert!(testlook!(look, "𝛃𐆀", 4)); |
| 2226 |
|
| 2227 |
// Non word boundaries for ASCII. |
| 2228 |
assert!(testlook!(look, "", 0)); |
| 2229 |
assert!(!testlook!(look, "ab", 1)); |
| 2230 |
assert!(testlook!(look, "a ", 2)); |
| 2231 |
assert!(testlook!(look, " a ", 0)); |
| 2232 |
assert!(testlook!(look, " a ", 3)); |
| 2233 |
|
| 2234 |
// Non word boundaries with a non-ASCII codepoint. |
| 2235 |
assert!(testlook!(look, "𝛃b", 4)); |
| 2236 |
assert!(!testlook!(look, "b𝛃", 1)); |
| 2237 |
assert!(testlook!(look, "𝛃 ", 5)); |
| 2238 |
assert!(testlook!(look, " 𝛃 ", 0)); |
| 2239 |
assert!(testlook!(look, " 𝛃 ", 6)); |
| 2240 |
assert!(testlook!(look, "𝛃", 1)); |
| 2241 |
assert!(testlook!(look, "𝛃", 2)); |
| 2242 |
assert!(testlook!(look, "𝛃", 3)); |
| 2243 |
|
| 2244 |
// Non word boundaries with non-ASCII codepoints. |
| 2245 |
assert!(testlook!(look, "𝛃𐆀", 1)); |
| 2246 |
assert!(testlook!(look, "𝛃𐆀", 2)); |
| 2247 |
assert!(testlook!(look, "𝛃𐆀", 3)); |
| 2248 |
assert!(testlook!(look, "𝛃𐆀", 5)); |
| 2249 |
assert!(testlook!(look, "𝛃𐆀", 6)); |
| 2250 |
assert!(testlook!(look, "𝛃𐆀", 7)); |
| 2251 |
assert!(testlook!(look, "𝛃𐆀", 8)); |
| 2252 |
} |
| 2253 |
|
| 2254 |
#[test] |
| 2255 |
fn look_matches_word_end_half_ascii() { |
| 2256 |
let look = Look::WordEndHalfAscii; |
| 2257 |
|
| 2258 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 2259 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 2260 |
|
| 2261 |
// Simple ASCII word boundaries. |
| 2262 |
assert!(!testlook!(look, "a", 0)); |
| 2263 |
assert!(testlook!(look, "a", 1)); |
| 2264 |
assert!(testlook!(look, "a ", 1)); |
| 2265 |
assert!(!testlook!(look, " a ", 1)); |
| 2266 |
assert!(testlook!(look, " a ", 2)); |
| 2267 |
|
| 2268 |
// Unicode word boundaries with a non-ASCII codepoint. Since this is |
| 2269 |
// an ASCII word boundary, none of these match. |
| 2270 |
assert!(testlook!(look, "𝛃", 0)); |
| 2271 |
assert!(testlook!(look, "𝛃", 4)); |
| 2272 |
assert!(testlook!(look, "𝛃 ", 4)); |
| 2273 |
assert!(testlook!(look, " 𝛃 ", 1)); |
| 2274 |
assert!(testlook!(look, " 𝛃 ", 5)); |
| 2275 |
|
| 2276 |
// Unicode word boundaries between non-ASCII codepoints. Again, since |
| 2277 |
// this is an ASCII word boundary, none of these match. |
| 2278 |
assert!(testlook!(look, "𝛃𐆀", 0)); |
| 2279 |
assert!(testlook!(look, "𝛃𐆀", 4)); |
| 2280 |
|
| 2281 |
// Non word boundaries for ASCII. |
| 2282 |
assert!(testlook!(look, "", 0)); |
| 2283 |
assert!(!testlook!(look, "ab", 1)); |
| 2284 |
assert!(testlook!(look, "a ", 2)); |
| 2285 |
assert!(testlook!(look, " a ", 0)); |
| 2286 |
assert!(testlook!(look, " a ", 3)); |
| 2287 |
|
| 2288 |
// Non word boundaries with a non-ASCII codepoint. |
| 2289 |
assert!(!testlook!(look, "𝛃b", 4)); |
| 2290 |
assert!(testlook!(look, "b𝛃", 1)); |
| 2291 |
assert!(testlook!(look, "𝛃 ", 5)); |
| 2292 |
assert!(testlook!(look, " 𝛃 ", 0)); |
| 2293 |
assert!(testlook!(look, " 𝛃 ", 6)); |
| 2294 |
assert!(testlook!(look, "𝛃", 1)); |
| 2295 |
assert!(testlook!(look, "𝛃", 2)); |
| 2296 |
assert!(testlook!(look, "𝛃", 3)); |
| 2297 |
|
| 2298 |
// Non word boundaries with non-ASCII codepoints. |
| 2299 |
assert!(testlook!(look, "𝛃𐆀", 1)); |
| 2300 |
assert!(testlook!(look, "𝛃𐆀", 2)); |
| 2301 |
assert!(testlook!(look, "𝛃𐆀", 3)); |
| 2302 |
assert!(testlook!(look, "𝛃𐆀", 5)); |
| 2303 |
assert!(testlook!(look, "𝛃𐆀", 6)); |
| 2304 |
assert!(testlook!(look, "𝛃𐆀", 7)); |
| 2305 |
assert!(testlook!(look, "𝛃𐆀", 8)); |
| 2306 |
} |
| 2307 |
|
| 2308 |
#[test] |
| 2309 |
#[cfg(all(not(miri), feature = "unicode-word-boundary"))] |
| 2310 |
fn look_matches_word_start_half_unicode() { |
| 2311 |
let look = Look::WordStartHalfUnicode; |
| 2312 |
|
| 2313 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 2314 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 2315 |
|
| 2316 |
// Simple ASCII word boundaries. |
| 2317 |
assert!(testlook!(look, "a", 0)); |
| 2318 |
assert!(!testlook!(look, "a", 1)); |
| 2319 |
assert!(!testlook!(look, "a ", 1)); |
| 2320 |
assert!(testlook!(look, " a ", 1)); |
| 2321 |
assert!(!testlook!(look, " a ", 2)); |
| 2322 |
|
| 2323 |
// Unicode word boundaries with a non-ASCII codepoint. |
| 2324 |
assert!(testlook!(look, "𝛃", 0)); |
| 2325 |
assert!(!testlook!(look, "𝛃", 4)); |
| 2326 |
assert!(!testlook!(look, "𝛃 ", 4)); |
| 2327 |
assert!(testlook!(look, " 𝛃 ", 1)); |
| 2328 |
assert!(!testlook!(look, " 𝛃 ", 5)); |
| 2329 |
|
| 2330 |
// Unicode word boundaries between non-ASCII codepoints. |
| 2331 |
assert!(testlook!(look, "𝛃𐆀", 0)); |
| 2332 |
assert!(!testlook!(look, "𝛃𐆀", 4)); |
| 2333 |
|
| 2334 |
// Non word boundaries for ASCII. |
| 2335 |
assert!(testlook!(look, "", 0)); |
| 2336 |
assert!(!testlook!(look, "ab", 1)); |
| 2337 |
assert!(testlook!(look, "a ", 2)); |
| 2338 |
assert!(testlook!(look, " a ", 0)); |
| 2339 |
assert!(testlook!(look, " a ", 3)); |
| 2340 |
|
| 2341 |
// Non word boundaries with a non-ASCII codepoint. |
| 2342 |
assert!(!testlook!(look, "𝛃b", 4)); |
| 2343 |
assert!(!testlook!(look, "b𝛃", 1)); |
| 2344 |
assert!(testlook!(look, "𝛃 ", 5)); |
| 2345 |
assert!(testlook!(look, " 𝛃 ", 0)); |
| 2346 |
assert!(testlook!(look, " 𝛃 ", 6)); |
| 2347 |
assert!(!testlook!(look, "𝛃", 1)); |
| 2348 |
assert!(!testlook!(look, "𝛃", 2)); |
| 2349 |
assert!(!testlook!(look, "𝛃", 3)); |
| 2350 |
|
| 2351 |
// Non word boundaries with non-ASCII codepoints. |
| 2352 |
assert!(!testlook!(look, "𝛃𐆀", 1)); |
| 2353 |
assert!(!testlook!(look, "𝛃𐆀", 2)); |
| 2354 |
assert!(!testlook!(look, "𝛃𐆀", 3)); |
| 2355 |
assert!(!testlook!(look, "𝛃𐆀", 5)); |
| 2356 |
assert!(!testlook!(look, "𝛃𐆀", 6)); |
| 2357 |
assert!(!testlook!(look, "𝛃𐆀", 7)); |
| 2358 |
assert!(testlook!(look, "𝛃𐆀", 8)); |
| 2359 |
} |
| 2360 |
|
| 2361 |
#[test] |
| 2362 |
#[cfg(all(not(miri), feature = "unicode-word-boundary"))] |
| 2363 |
fn look_matches_word_end_half_unicode() { |
| 2364 |
let look = Look::WordEndHalfUnicode; |
| 2365 |
|
| 2366 |
// \xF0\x9D\x9B\x83 = 𝛃 (in \w) |
| 2367 |
// \xF0\x90\x86\x80 = 𐆀 (not in \w) |
| 2368 |
|
| 2369 |
// Simple ASCII word boundaries. |
| 2370 |
assert!(!testlook!(look, "a", 0)); |
| 2371 |
assert!(testlook!(look, "a", 1)); |
| 2372 |
assert!(testlook!(look, "a ", 1)); |
| 2373 |
assert!(!testlook!(look, " a ", 1)); |
| 2374 |
assert!(testlook!(look, " a ", 2)); |
| 2375 |
|
| 2376 |
// Unicode word boundaries with a non-ASCII codepoint. |
| 2377 |
assert!(!testlook!(look, "𝛃", 0)); |
| 2378 |
assert!(testlook!(look, "𝛃", 4)); |
| 2379 |
assert!(testlook!(look, "𝛃 ", 4)); |
| 2380 |
assert!(!testlook!(look, " 𝛃 ", 1)); |
| 2381 |
assert!(testlook!(look, " 𝛃 ", 5)); |
| 2382 |
|
| 2383 |
// Unicode word boundaries between non-ASCII codepoints. |
| 2384 |
assert!(!testlook!(look, "𝛃𐆀", 0)); |
| 2385 |
assert!(testlook!(look, "𝛃𐆀", 4)); |
| 2386 |
|
| 2387 |
// Non word boundaries for ASCII. |
| 2388 |
assert!(testlook!(look, "", 0)); |
| 2389 |
assert!(!testlook!(look, "ab", 1)); |
| 2390 |
assert!(testlook!(look, "a ", 2)); |
| 2391 |
assert!(testlook!(look, " a ", 0)); |
| 2392 |
assert!(testlook!(look, " a ", 3)); |
| 2393 |
|
| 2394 |
// Non word boundaries with a non-ASCII codepoint. |
| 2395 |
assert!(!testlook!(look, "𝛃b", 4)); |
| 2396 |
assert!(!testlook!(look, "b𝛃", 1)); |
| 2397 |
assert!(testlook!(look, "𝛃 ", 5)); |
| 2398 |
assert!(testlook!(look, " 𝛃 ", 0)); |
| 2399 |
assert!(testlook!(look, " 𝛃 ", 6)); |
| 2400 |
assert!(!testlook!(look, "𝛃", 1)); |
| 2401 |
assert!(!testlook!(look, "𝛃", 2)); |
| 2402 |
assert!(!testlook!(look, "𝛃", 3)); |
| 2403 |
|
| 2404 |
// Non word boundaries with non-ASCII codepoints. |
| 2405 |
assert!(!testlook!(look, "𝛃𐆀", 1)); |
| 2406 |
assert!(!testlook!(look, "𝛃𐆀", 2)); |
| 2407 |
assert!(!testlook!(look, "𝛃𐆀", 3)); |
| 2408 |
assert!(!testlook!(look, "𝛃𐆀", 5)); |
| 2409 |
assert!(!testlook!(look, "𝛃𐆀", 6)); |
| 2410 |
assert!(!testlook!(look, "𝛃𐆀", 7)); |
| 2411 |
assert!(testlook!(look, "𝛃𐆀", 8)); |
| 2412 |
} |
| 2413 |
|
| 2414 |
#[test] |
| 2415 |
fn look_set() { |
| 2416 |
let mut f = LookSet::default(); |
| 2417 |
assert!(!f.contains(Look::Start)); |
| 2418 |
assert!(!f.contains(Look::End)); |
| 2419 |
assert!(!f.contains(Look::StartLF)); |
| 2420 |
assert!(!f.contains(Look::EndLF)); |
| 2421 |
assert!(!f.contains(Look::WordUnicode)); |
| 2422 |
assert!(!f.contains(Look::WordUnicodeNegate)); |
| 2423 |
assert!(!f.contains(Look::WordAscii)); |
| 2424 |
assert!(!f.contains(Look::WordAsciiNegate)); |
| 2425 |
|
| 2426 |
f = f.insert(Look::Start); |
| 2427 |
assert!(f.contains(Look::Start)); |
| 2428 |
f = f.remove(Look::Start); |
| 2429 |
assert!(!f.contains(Look::Start)); |
| 2430 |
|
| 2431 |
f = f.insert(Look::End); |
| 2432 |
assert!(f.contains(Look::End)); |
| 2433 |
f = f.remove(Look::End); |
| 2434 |
assert!(!f.contains(Look::End)); |
| 2435 |
|
| 2436 |
f = f.insert(Look::StartLF); |
| 2437 |
assert!(f.contains(Look::StartLF)); |
| 2438 |
f = f.remove(Look::StartLF); |
| 2439 |
assert!(!f.contains(Look::StartLF)); |
| 2440 |
|
| 2441 |
f = f.insert(Look::EndLF); |
| 2442 |
assert!(f.contains(Look::EndLF)); |
| 2443 |
f = f.remove(Look::EndLF); |
| 2444 |
assert!(!f.contains(Look::EndLF)); |
| 2445 |
|
| 2446 |
f = f.insert(Look::StartCRLF); |
| 2447 |
assert!(f.contains(Look::StartCRLF)); |
| 2448 |
f = f.remove(Look::StartCRLF); |
| 2449 |
assert!(!f.contains(Look::StartCRLF)); |
| 2450 |
|
| 2451 |
f = f.insert(Look::EndCRLF); |
| 2452 |
assert!(f.contains(Look::EndCRLF)); |
| 2453 |
f = f.remove(Look::EndCRLF); |
| 2454 |
assert!(!f.contains(Look::EndCRLF)); |
| 2455 |
|
| 2456 |
f = f.insert(Look::WordUnicode); |
| 2457 |
assert!(f.contains(Look::WordUnicode)); |
| 2458 |
f = f.remove(Look::WordUnicode); |
| 2459 |
assert!(!f.contains(Look::WordUnicode)); |
| 2460 |
|
| 2461 |
f = f.insert(Look::WordUnicodeNegate); |
| 2462 |
assert!(f.contains(Look::WordUnicodeNegate)); |
| 2463 |
f = f.remove(Look::WordUnicodeNegate); |
| 2464 |
assert!(!f.contains(Look::WordUnicodeNegate)); |
| 2465 |
|
| 2466 |
f = f.insert(Look::WordAscii); |
| 2467 |
assert!(f.contains(Look::WordAscii)); |
| 2468 |
f = f.remove(Look::WordAscii); |
| 2469 |
assert!(!f.contains(Look::WordAscii)); |
| 2470 |
|
| 2471 |
f = f.insert(Look::WordAsciiNegate); |
| 2472 |
assert!(f.contains(Look::WordAsciiNegate)); |
| 2473 |
f = f.remove(Look::WordAsciiNegate); |
| 2474 |
assert!(!f.contains(Look::WordAsciiNegate)); |
| 2475 |
|
| 2476 |
f = f.insert(Look::WordStartAscii); |
| 2477 |
assert!(f.contains(Look::WordStartAscii)); |
| 2478 |
f = f.remove(Look::WordStartAscii); |
| 2479 |
assert!(!f.contains(Look::WordStartAscii)); |
| 2480 |
|
| 2481 |
f = f.insert(Look::WordEndAscii); |
| 2482 |
assert!(f.contains(Look::WordEndAscii)); |
| 2483 |
f = f.remove(Look::WordEndAscii); |
| 2484 |
assert!(!f.contains(Look::WordEndAscii)); |
| 2485 |
|
| 2486 |
f = f.insert(Look::WordStartUnicode); |
| 2487 |
assert!(f.contains(Look::WordStartUnicode)); |
| 2488 |
f = f.remove(Look::WordStartUnicode); |
| 2489 |
assert!(!f.contains(Look::WordStartUnicode)); |
| 2490 |
|
| 2491 |
f = f.insert(Look::WordEndUnicode); |
| 2492 |
assert!(f.contains(Look::WordEndUnicode)); |
| 2493 |
f = f.remove(Look::WordEndUnicode); |
| 2494 |
assert!(!f.contains(Look::WordEndUnicode)); |
| 2495 |
|
| 2496 |
f = f.insert(Look::WordStartHalfAscii); |
| 2497 |
assert!(f.contains(Look::WordStartHalfAscii)); |
| 2498 |
f = f.remove(Look::WordStartHalfAscii); |
| 2499 |
assert!(!f.contains(Look::WordStartHalfAscii)); |
| 2500 |
|
| 2501 |
f = f.insert(Look::WordEndHalfAscii); |
| 2502 |
assert!(f.contains(Look::WordEndHalfAscii)); |
| 2503 |
f = f.remove(Look::WordEndHalfAscii); |
| 2504 |
assert!(!f.contains(Look::WordEndHalfAscii)); |
| 2505 |
|
| 2506 |
f = f.insert(Look::WordStartHalfUnicode); |
| 2507 |
assert!(f.contains(Look::WordStartHalfUnicode)); |
| 2508 |
f = f.remove(Look::WordStartHalfUnicode); |
| 2509 |
assert!(!f.contains(Look::WordStartHalfUnicode)); |
| 2510 |
|
| 2511 |
f = f.insert(Look::WordEndHalfUnicode); |
| 2512 |
assert!(f.contains(Look::WordEndHalfUnicode)); |
| 2513 |
f = f.remove(Look::WordEndHalfUnicode); |
| 2514 |
assert!(!f.contains(Look::WordEndHalfUnicode)); |
| 2515 |
} |
| 2516 |
|
| 2517 |
#[test] |
| 2518 |
fn look_set_iter() { |
| 2519 |
let set = LookSet::empty(); |
| 2520 |
assert_eq!(0, set.iter().count()); |
| 2521 |
|
| 2522 |
let set = LookSet::full(); |
| 2523 |
assert_eq!(18, set.iter().count()); |
| 2524 |
|
| 2525 |
let set = |
| 2526 |
LookSet::empty().insert(Look::StartLF).insert(Look::WordUnicode); |
| 2527 |
assert_eq!(2, set.iter().count()); |
| 2528 |
|
| 2529 |
let set = LookSet::empty().insert(Look::StartLF); |
| 2530 |
assert_eq!(1, set.iter().count()); |
| 2531 |
|
| 2532 |
let set = LookSet::empty().insert(Look::WordAsciiNegate); |
| 2533 |
assert_eq!(1, set.iter().count()); |
| 2534 |
|
| 2535 |
let set = LookSet::empty().insert(Look::WordEndHalfUnicode); |
| 2536 |
assert_eq!(1, set.iter().count()); |
| 2537 |
} |
| 2538 |
|
| 2539 |
#[test] |
| 2540 |
#[cfg(feature = "alloc")] |
| 2541 |
fn look_set_debug() { |
| 2542 |
let res = alloc::format!("{:?}", LookSet::empty()); |
| 2543 |
assert_eq!("∅", res); |
| 2544 |
let res = alloc::format!("{:?}", LookSet::full()); |
| 2545 |
assert_eq!("Az^$rRbB𝛃𝚩<>〈〉◁▷◀▶", res); |
| 2546 |
} |
| 2547 |
} |