impl Compiler

fn new() -> Compiler

Create a new NFA builder with its default configuration.

fn build(&self, pattern: &str) -> Result<NFA, BuildError>

Compile the given regular expression pattern into an NFA.

If there was a problem parsing the regex, then that error is returned.

Otherwise, if there was a problem building the NFA, then an error is returned. The only error that can occur is if the compiled regex would exceed the size limits configured on this builder, or if any part of the NFA would exceed the integer representations used. (For example, too many states might plausibly occur on a 16-bit target.)

Example

use regex_automata::{nfa::thompson::{NFA, pikevm::PikeVM}, Match};

let config = NFA::config().nfa_size_limit(Some(1_000));
let nfa = NFA::compiler().configure(config).build(r"(?-u)\w")?;

let re = PikeVM::new_from_nfa(nfa)?;
let mut cache = re.create_cache();
let mut caps = re.create_captures();
let expected = Some(Match::must(0, 3..4));
re.captures(&mut cache, "!@#A#@!", &mut caps);
assert_eq!(expected, caps.get_match());

# Ok::<(), Box<dyn std::error::Error>>(())

fn build_many<P: AsRef<str>>(&self, patterns: &[P]) -> Result<NFA, BuildError>

Compile the given regular expression patterns into a single NFA.

When matches are returned, the pattern ID corresponds to the index of the pattern in the slice given.

Example

use regex_automata::{nfa::thompson::{NFA, pikevm::PikeVM}, Match};

let config = NFA::config().nfa_size_limit(Some(1_000));
let nfa = NFA::compiler().configure(config).build_many(&[
    r"(?-u)\s",
    r"(?-u)\w",
])?;

let re = PikeVM::new_from_nfa(nfa)?;
let mut cache = re.create_cache();
let mut caps = re.create_captures();
let expected = Some(Match::must(1, 1..2));
re.captures(&mut cache, "!A! !A!", &mut caps);
assert_eq!(expected, caps.get_match());

# Ok::<(), Box<dyn std::error::Error>>(())

fn build_from_hir(&self, expr: &Hir) -> Result<NFA, BuildError>

Compile the given high level intermediate representation of a regular expression into an NFA.

If there was a problem building the NFA, then an error is returned. The only error that can occur is if the compiled regex would exceed the size limits configured on this builder, or if any part of the NFA would exceed the integer representations used. (For example, too many states might plausibly occur on a 16-bit target.)

Example

use regex_automata::{nfa::thompson::{NFA, pikevm::PikeVM}, Match};
use regex_syntax::hir::{Hir, Class, ClassBytes, ClassBytesRange};

let hir = Hir::class(Class::Bytes(ClassBytes::new(vec![
    ClassBytesRange::new(b'0', b'9'),
    ClassBytesRange::new(b'A', b'Z'),
    ClassBytesRange::new(b'_', b'_'),
    ClassBytesRange::new(b'a', b'z'),
])));

let config = NFA::config().nfa_size_limit(Some(1_000));
let nfa = NFA::compiler().configure(config).build_from_hir(&hir)?;

let re = PikeVM::new_from_nfa(nfa)?;
let mut cache = re.create_cache();
let mut caps = re.create_captures();
let expected = Some(Match::must(0, 3..4));
re.captures(&mut cache, "!@#A#@!", &mut caps);
assert_eq!(expected, caps.get_match());

# Ok::<(), Box<dyn std::error::Error>>(())

fn build_many_from_hir<H: Borrow<Hir>>(&self, exprs: &[H]) -> Result<NFA, BuildError>

Compile the given high level intermediate representations of regular expressions into a single NFA.

When matches are returned, the pattern ID corresponds to the index of the pattern in the slice given.

Example

use regex_automata::{nfa::thompson::{NFA, pikevm::PikeVM}, Match};
use regex_syntax::hir::{Hir, Class, ClassBytes, ClassBytesRange};

let hirs = &[
    Hir::class(Class::Bytes(ClassBytes::new(vec![
        ClassBytesRange::new(b'\t', b'\r'),
        ClassBytesRange::new(b' ', b' '),
    ]))),
    Hir::class(Class::Bytes(ClassBytes::new(vec![
        ClassBytesRange::new(b'0', b'9'),
        ClassBytesRange::new(b'A', b'Z'),
        ClassBytesRange::new(b'_', b'_'),
        ClassBytesRange::new(b'a', b'z'),
    ]))),
];

let config = NFA::config().nfa_size_limit(Some(1_000));
let nfa = NFA::compiler().configure(config).build_many_from_hir(hirs)?;

let re = PikeVM::new_from_nfa(nfa)?;
let mut cache = re.create_cache();
let mut caps = re.create_captures();
let expected = Some(Match::must(1, 1..2));
re.captures(&mut cache, "!A! !A!", &mut caps);
assert_eq!(expected, caps.get_match());

# Ok::<(), Box<dyn std::error::Error>>(())

fn configure(&mut self, config: Config) -> &mut Compiler

Apply the given NFA configuration options to this builder.

Example

use regex_automata::nfa::thompson::NFA;

let config = NFA::config().nfa_size_limit(Some(1_000));
let nfa = NFA::compiler().configure(config).build(r"(?-u)\w")?;
assert_eq!(nfa.pattern_len(), 1);

# Ok::<(), Box<dyn std::error::Error>>(())

fn syntax(&mut self, config: Config) -> &mut Compiler

Set the syntax configuration for this builder using syntax::Config.

This permits setting things like case insensitivity, Unicode and multi line mode.

This syntax configuration only applies when an NFA is built directly from a pattern string. If an NFA is built from an HIR, then all syntax settings are ignored.

Example

use regex_automata::{nfa::thompson::NFA, util::syntax};

let syntax_config = syntax::Config::new().unicode(false);
let nfa = NFA::compiler().syntax(syntax_config).build(r"\w")?;
// If Unicode were enabled, the number of states would be much bigger.
assert!(nfa.states().len() < 15);

# Ok::<(), Box<dyn std::error::Error>>(())