vendor/regex-syntax/src/lib.rs

   1 /*!
   2 This crate provides a robust regular expression parser.
   3
   4 This crate defines two primary types:
   5
   6 * [`Ast`](ast/enum.Ast.html) is the abstract syntax of a regular expression.
   7   An abstract syntax corresponds to a *structured representation* of the
   8   concrete syntax of a regular expression, where the concrete syntax is the
   9   pattern string itself (e.g., `foo(bar)+`). Given some abstract syntax, it
  10   can be converted back to the original concrete syntax (modulo some details,
  11   like whitespace). To a first approximation, the abstract syntax is complex
  12   and difficult to analyze.
  13 * [`Hir`](hir/struct.Hir.html) is the high-level intermediate representation
  14   ("HIR" or "high-level IR" for short) of regular expression. It corresponds to
  15   an intermediate state of a regular expression that sits between the abstract
  16   syntax and the low level compiled opcodes that are eventually responsible for
  17   executing a regular expression search. Given some high-level IR, it is not
  18   possible to produce the original concrete syntax (although it is possible to
  19   produce an equivalent concrete syntax, but it will likely scarcely resemble
  20   the original pattern). To a first approximation, the high-level IR is simple
  21   and easy to analyze.
  22
  23 These two types come with conversion routines:
  24
  25 * An [`ast::parse::Parser`](ast/parse/struct.Parser.html) converts concrete
  26   syntax (a `&str`) to an [`Ast`](ast/enum.Ast.html).
  27 * A [`hir::translate::Translator`](hir/translate/struct.Translator.html)
  28   converts an [`Ast`](ast/enum.Ast.html) to a [`Hir`](hir/struct.Hir.html).
  29
  30 As a convenience, the above two conversion routines are combined into one via
  31 the top-level [`Parser`](struct.Parser.html) type. This `Parser` will first
  32 convert your pattern to an `Ast` and then convert the `Ast` to an `Hir`.
  33
  34
  35 # Example
  36
  37 This example shows how to parse a pattern string into its HIR:
  38
  39 ```
  40 use regex_syntax::Parser;
  41 use regex_syntax::hir::{self, Hir};
  42
  43 let hir = Parser::new().parse("a|b").unwrap();
  44 assert_eq!(hir, Hir::alternation(vec![
  45     Hir::literal(hir::Literal::Unicode('a')),
  46     Hir::literal(hir::Literal::Unicode('b')),
  47 ]));
  48 ```
  49
  50
  51 # Concrete syntax supported
  52
  53 The concrete syntax is documented as part of the public API of the
  54 [`regex` crate](https://docs.rs/regex/%2A/regex/#syntax).
  55
  56
  57 # Input safety
  58
  59 A key feature of this library is that it is safe to use with end user facing
  60 input. This plays a significant role in the internal implementation. In
  61 particular:
  62
  63 1. Parsers provide a `nest_limit` option that permits callers to control how
  64    deeply nested a regular expression is allowed to be. This makes it possible
  65    to do case analysis over an `Ast` or an `Hir` using recursion without
  66    worrying about stack overflow.
  67 2. Since relying on a particular stack size is brittle, this crate goes to
  68    great lengths to ensure that all interactions with both the `Ast` and the
  69    `Hir` do not use recursion. Namely, they use constant stack space and heap
  70    space proportional to the size of the original pattern string (in bytes).
  71    This includes the type's corresponding destructors. (One exception to this
  72    is literal extraction, but this will eventually get fixed.)
  73
  74
  75 # Error reporting
  76
  77 The `Display` implementations on all `Error` types exposed in this library
  78 provide nice human readable errors that are suitable for showing to end users
  79 in a monospace font.
  80
  81
  82 # Literal extraction
  83
  84 This crate provides limited support for
  85 [literal extraction from `Hir` values](hir/literal/struct.Literals.html).
  86 Be warned that literal extraction currently uses recursion, and therefore,
  87 stack size proportional to the size of the `Hir`.
  88
  89 The purpose of literal extraction is to speed up searches. That is, if you
  90 know a regular expression must match a prefix or suffix literal, then it is
  91 often quicker to search for instances of that literal, and then confirm or deny
  92 the match using the full regular expression engine. These optimizations are
  93 done automatically in the `regex` crate.
  94
  95
  96 # Crate features
  97
  98 An important feature provided by this crate is its Unicode support. This
  99 includes things like case folding, boolean properties, general categories,
 100 scripts and Unicode-aware support for the Perl classes `\w`, `\s` and `\d`.
 101 However, a downside of this support is that it requires bundling several
 102 Unicode data tables that are substantial in size.
 103
 104 A fair number of use cases do not require full Unicode support. For this
 105 reason, this crate exposes a number of features to control which Unicode
 106 data is available.
 107
 108 If a regular expression attempts to use a Unicode feature that is not available
 109 because the corresponding crate feature was disabled, then translating that
 110 regular expression to an `Hir` will return an error. (It is still possible
 111 construct an `Ast` for such a regular expression, since Unicode data is not
 112 used until translation to an `Hir`.) Stated differently, enabling or disabling
 113 any of the features below can only add or subtract from the total set of valid
 114 regular expressions. Enabling or disabling a feature will never modify the
 115 match semantics of a regular expression.
 116
 117 The following features are available:
 118
 119 * **unicode** -
 120   Enables all Unicode features. This feature is enabled by default, and will
 121   always cover all Unicode features, even if more are added in the future.
 122 * **unicode-age** -
 123   Provide the data for the
 124   [Unicode `Age` property](https://www.unicode.org/reports/tr44/tr44-24.html#Character_Age).
 125   This makes it possible to use classes like `\p{Age:6.0}` to refer to all
 126   codepoints first introduced in Unicode 6.0
 127 * **unicode-bool** -
 128   Provide the data for numerous Unicode boolean properties. The full list
 129   is not included here, but contains properties like `Alphabetic`, `Emoji`,
 130   `Lowercase`, `Math`, `Uppercase` and `White_Space`.
 131 * **unicode-case** -
 132   Provide the data for case insensitive matching using
 133   [Unicode's "simple loose matches" specification](https://www.unicode.org/reports/tr18/#Simple_Loose_Matches).
 134 * **unicode-gencat** -
 135   Provide the data for
 136   [Uncode general categories](https://www.unicode.org/reports/tr44/tr44-24.html#General_Category_Values).
 137   This includes, but is not limited to, `Decimal_Number`, `Letter`,
 138   `Math_Symbol`, `Number` and `Punctuation`.
 139 * **unicode-perl** -
 140   Provide the data for supporting the Unicode-aware Perl character classes,
 141   corresponding to `\w`, `\s` and `\d`. This is also necessary for using
 142   Unicode-aware word boundary assertions. Note that if this feature is
 143   disabled, the `\s` and `\d` character classes are still available if the
 144   `unicode-bool` and `unicode-gencat` features are enabled, respectively.
 145 * **unicode-script** -
 146   Provide the data for
 147   [Unicode scripts and script extensions](https://www.unicode.org/reports/tr24/).
 148   This includes, but is not limited to, `Arabic`, `Cyrillic`, `Hebrew`,
 149   `Latin` and `Thai`.
 150 * **unicode-segment** -
 151   Provide the data necessary to provide the properties used to implement the
 152   [Unicode text segmentation algorithms](https://www.unicode.org/reports/tr29/).
 153   This enables using classes like `\p{gcb=Extend}`, `\p{wb=Katakana}` and
 154   `\p{sb=ATerm}`.
 155 */
 156
 157 #![deny(missing_docs)]
 158 #![forbid(unsafe_code)]
 159
 160 pub use error::{Error, Result};
 161 pub use parser::{Parser, ParserBuilder};
 162 pub use unicode::UnicodeWordError;
 163
 164 pub mod ast;
 165 mod either;
 166 mod error;
 167 pub mod hir;
 168 mod parser;
 169 mod unicode;
 170 mod unicode_tables;
 171 pub mod utf8;
 172
 173 /// Escapes all regular expression meta characters in `text`.
 174 ///
 175 /// The string returned may be safely used as a literal in a regular
 176 /// expression.
 177 pub fn escape(text: &str) -> String {
 178     let mut quoted = String::new();
 179     escape_into(text, &mut quoted);
 180     quoted
 181 }
 182
 183 /// Escapes all meta characters in `text` and writes the result into `buf`.
 184 ///
 185 /// This will append escape characters into the given buffer. The characters
 186 /// that are appended are safe to use as a literal in a regular expression.
 187 pub fn escape_into(text: &str, buf: &mut String) {
 188     buf.reserve(text.len());
 189     for c in text.chars() {
 190         if is_meta_character(c) {
 191             buf.push('\\');
 192         }
 193         buf.push(c);
 194     }
 195 }
 196
 197 /// Returns true if the give character has significance in a regex.
 198 ///
 199 /// These are the only characters that are allowed to be escaped, with one
 200 /// exception: an ASCII space character may be escaped when extended mode (with
 201 /// the `x` flag) is enabld. In particular, `is_meta_character(' ')` returns
 202 /// `false`.
 203 ///
 204 /// Note that the set of characters for which this function returns `true` or
 205 /// `false` is fixed and won't change in a semver compatible release.
 206 pub fn is_meta_character(c: char) -> bool {
 207     match c {
 208         '\\' | '.' | '+' | '*' | '?' | '(' | ')' | '|' | '[' | ']' | '{'
 209         | '}' | '^' | '$' | '#' | '&' | '-' | '~' => true,
 210         _ => false,
 211     }
 212 }
 213
 214 /// Returns true if and only if the given character is a Unicode word
 215 /// character.
 216 ///
 217 /// A Unicode word character is defined by
 218 /// [UTS#18 Annex C](http://unicode.org/reports/tr18/#Compatibility_Properties).
 219 /// In particular, a character
 220 /// is considered a word character if it is in either of the `Alphabetic` or
 221 /// `Join_Control` properties, or is in one of the `Decimal_Number`, `Mark`
 222 /// or `Connector_Punctuation` general categories.
 223 ///
 224 /// # Panics
 225 ///
 226 /// If the `unicode-perl` feature is not enabled, then this function panics.
 227 /// For this reason, it is recommended that callers use
 228 /// [`try_is_word_character`](fn.try_is_word_character.html)
 229 /// instead.
 230 pub fn is_word_character(c: char) -> bool {
 231     try_is_word_character(c).expect("unicode-perl feature must be enabled")
 232 }
 233
 234 /// Returns true if and only if the given character is a Unicode word
 235 /// character.
 236 ///
 237 /// A Unicode word character is defined by
 238 /// [UTS#18 Annex C](http://unicode.org/reports/tr18/#Compatibility_Properties).
 239 /// In particular, a character
 240 /// is considered a word character if it is in either of the `Alphabetic` or
 241 /// `Join_Control` properties, or is in one of the `Decimal_Number`, `Mark`
 242 /// or `Connector_Punctuation` general categories.
 243 ///
 244 /// # Errors
 245 ///
 246 /// If the `unicode-perl` feature is not enabled, then this function always
 247 /// returns an error.
 248 pub fn try_is_word_character(
 249     c: char,
 250 ) -> std::result::Result<bool, UnicodeWordError> {
 251     unicode::is_word_character(c)
 252 }
 253
 254 /// Returns true if and only if the given character is an ASCII word character.
 255 ///
 256 /// An ASCII word character is defined by the following character class:
 257 /// `[_0-9a-zA-Z]'.
 258 pub fn is_word_byte(c: u8) -> bool {
 259     match c {
 260         b'_' | b'0'..=b'9' | b'a'..=b'z' | b'A'..=b'Z' => true,
 261         _ => false,
 262     }
 263 }
 264
 265 #[cfg(test)]
 266 mod tests {
 267     use super::*;
 268
 269     #[test]
 270     fn escape_meta() {
 271         assert_eq!(
 272             escape(r"\.+*?()|[]{}^$#&-~"),
 273             r"\\\.\+\*\?\(\)\|\[\]\{\}\^\$\#\&\-\~".to_string()
 274         );
 275     }
 276
 277     #[test]
 278     fn word_byte() {
 279         assert!(is_word_byte(b'a'));
 280         assert!(!is_word_byte(b'-'));
 281     }
 282
 283     #[test]
 284     #[cfg(feature = "unicode-perl")]
 285     fn word_char() {
 286         assert!(is_word_character('a'), "ASCII");
 287         assert!(is_word_character('à'), "Latin-1");
 288         assert!(is_word_character('β'), "Greek");
 289         assert!(is_word_character('\u{11011}'), "Brahmi (Unicode 6.0)");
 290         assert!(is_word_character('\u{11611}'), "Modi (Unicode 7.0)");
 291         assert!(is_word_character('\u{11711}'), "Ahom (Unicode 8.0)");
 292         assert!(is_word_character('\u{17828}'), "Tangut (Unicode 9.0)");
 293         assert!(is_word_character('\u{1B1B1}'), "Nushu (Unicode 10.0)");
 294         assert!(is_word_character('\u{16E40}'), "Medefaidrin (Unicode 11.0)");
 295         assert!(!is_word_character('-'));
 296         assert!(!is_word_character('☃'));
 297     }
 298
 299     #[test]
 300     #[should_panic]
 301     #[cfg(not(feature = "unicode-perl"))]
 302     fn word_char_disabled_panic() {
 303         assert!(is_word_character('a'));
 304     }
 305
 306     #[test]
 307     #[cfg(not(feature = "unicode-perl"))]
 308     fn word_char_disabled_error() {
 309         assert!(try_is_word_character('a').is_err());
 310     }
 311 }