// Copyright 2014-2015 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.

//! This crate provides a native implementation of regular expressions that is
//! heavily based on RE2 both in syntax and in implementation. Notably,
//! backreferences and arbitrary lookahead/lookbehind assertions are not
//! provided. In return, regular expression searching provided by this package
//! has excellent worst-case performance. The specific syntax supported is
//! documented further down.
//!
//! This crate's documentation provides some simple examples, describes Unicode
//! support and exhaustively lists the supported syntax. For more specific
//! details on the API, please see the documentation for the
//! [`Regex`](struct.Regex.html) type.
//!
//! # Usage
//!
//! This crate is [on crates.io](https://crates.io/crates/regex) and can be
//! used by adding `regex` to your dependencies in your project's `Cargo.toml`.
//!
//! ```toml
//! [dependencies]
//! regex = "0.1"
//! ```
//!
//! and this to your crate root:
//!
//! ```rust
//! extern crate regex;
//! ```
//!
//! # Example: find a date
//!
//! General use of regular expressions in this package involves compiling an
//! expression and then using it to search, split or replace text. For example,
//! to confirm that some text resembles a date:
//!
//! ```rust
//! use regex::Regex;
//! let re = Regex::new(r"^\d{4}-\d{2}-\d{2}$").unwrap();
//! assert!(re.is_match("2014-01-01"));
//! ```
//!
//! Notice the use of the `^` and `$` anchors. In this crate, every expression
//! is executed with an implicit `.*?` at the beginning and end, which allows
//! it to match anywhere in the text. Anchors can be used to ensure that the
//! full text matches an expression.
//!
//! This example also demonstrates the utility of
//! [raw strings](https://doc.rust-lang.org/stable/reference.html#raw-string-literals)
//! in Rust, which
//! are just like regular strings except they are prefixed with an `r` and do
//! not process any escape sequences. For example, `"\\d"` is the same
//! expression as `r"\d"`.
//!
//! # Example: Avoid compiling the same regex in a loop
//!
//! It is an anti-pattern to compile the same regular expression in a loop
//! since compilation is typically expensive. (It takes anywhere from a few
//! microseconds to a few **milliseconds** depending on the size of the
//! regex.) Not only is compilation itself expensive, but this also prevents
//! optimizations that reuse allocations internally to the matching engines.
//!
//! In Rust, it can sometimes be a pain to pass regular expressions around if
//! they're used from inside a helper function. Instead, we recommend using the
//! [`lazy_static`](https://crates.io/crates/lazy_static) crate to ensure that
//! regular expressions are compiled exactly once.
//!
//! For example:
//!
//! ```rust
//! #[macro_use] extern crate lazy_static;
//! extern crate regex;
//!
//! use regex::Regex;
//!
//! fn some_helper_function(text: &str) -> bool {
//!     lazy_static! {
//!         static ref RE: Regex = Regex::new("...").unwrap();
//!     }
//!     RE.is_match(text)
//! }
//!
//! fn main() {}
//! ```
//!
//! Specifically, in this example, the regex will be compiled when it is used for
//! the first time. On subsequent uses, it will reuse the previous compilation.
//!
//! # Example: iterating over capture groups
//!
//! This crate provides convenient iterators for matching an expression
//! repeatedly against a search string to find successive non-overlapping
//! matches. For example, to find all dates in a string and be able to access
//! them by their component pieces:
//!
//! ```rust
//! # extern crate regex; use regex::Regex;
//! # fn main() {
//! let re = Regex::new(r"(\d{4})-(\d{2})-(\d{2})").unwrap();
//! let text = "2012-03-14, 2013-01-01 and 2014-07-05";
//! for cap in re.captures_iter(text) {
//!     println!("Month: {} Day: {} Year: {}",
//!              cap.at(2).unwrap_or(""), cap.at(3).unwrap_or(""),
//!              cap.at(1).unwrap_or(""));
//! }
//! // Output:
//! // Month: 03 Day: 14 Year: 2012
//! // Month: 01 Day: 01 Year: 2013
//! // Month: 07 Day: 05 Year: 2014
//! # }
//! ```
//!
//! Notice that the year is in the capture group indexed at `1`. This is
//! because the *entire match* is stored in the capture group at index `0`.
//!
//! # Example: replacement with named capture groups
//!
//! Building on the previous example, perhaps we'd like to rearrange the date
//! formats. This can be done with text replacement. But to make the code
//! clearer, we can *name*  our capture groups and use those names as variables
//! in our replacement text:
//!
//! ```rust
//! # extern crate regex; use regex::Regex;
//! # fn main() {
//! let re = Regex::new(r"(?P<y>\d{4})-(?P<m>\d{2})-(?P<d>\d{2})").unwrap();
//! let before = "2012-03-14, 2013-01-01 and 2014-07-05";
//! let after = re.replace_all(before, "$m/$d/$y");
//! assert_eq!(after, "03/14/2012, 01/01/2013 and 07/05/2014");
//! # }
//! ```
//!
//! The `replace` methods are actually polymorphic in the replacement, which
//! provides more flexibility than is seen here. (See the documentation for
//! `Regex::replace` for more details.)
//!
//! Note that if your regex gets complicated, you can use the `x` flag to
//! enable insigificant whitespace mode, which also lets you write comments:
//!
//! ```rust
//! # extern crate regex; use regex::Regex;
//! # fn main() {
//! let re = Regex::new(r"(?x)
//!   (?P<y>\d{4}) # the year
//!   -
//!   (?P<m>\d{2}) # the month
//!   -
//!   (?P<d>\d{2}) # the day
//! ").unwrap();
//! let before = "2012-03-14, 2013-01-01 and 2014-07-05";
//! let after = re.replace_all(before, "$m/$d/$y");
//! assert_eq!(after, "03/14/2012, 01/01/2013 and 07/05/2014");
//! # }
//! ```
//!
//! # Example: match multiple regular expressions simultaneously
//!
//! This demonstrates how to use a `RegexSet` to match multiple (possibly
//! overlapping) regular expressions in a single scan of the search text:
//!
//! ```rust
//! use regex::RegexSet;
//!
//! let set = RegexSet::new(&[
//!     r"\w+",
//!     r"\d+",
//!     r"\pL+",
//!     r"foo",
//!     r"bar",
//!     r"barfoo",
//!     r"foobar",
//! ]).unwrap();
//!
//! // Iterate over and collect all of the matches.
//! let matches: Vec<_> = set.matches("foobar").into_iter().collect();
//! assert_eq!(matches, vec![0, 2, 3, 4, 6]);
//!
//! // You can also test whether a particular regex matched:
//! let matches = set.matches("foobar");
//! assert!(!matches.matched(5));
//! assert!(matches.matched(6));
//! ```
//!
//! # Pay for what you use
//!
//! With respect to searching text with a regular expression, there are three
//! questions that can be asked:
//!
//! 1. Does the text match this expression?
//! 2. If so, where does it match?
//! 3. Where are the submatches?
//!
//! Generally speaking, this crate could provide a function to answer only #3,
//! which would subsume #1 and #2 automatically. However, it can be
//! significantly more expensive to compute the location of submatches, so it's
//! best not to do it if you don't need to.
//!
//! Therefore, only use what you need. For example, don't use `find` if you
//! only need to test if an expression matches a string. (Use `is_match`
//! instead.)
//!
//! # Unicode
//!
//! This implementation executes regular expressions **only** on valid UTF-8
//! while exposing match locations as byte indices into the search string.
//!
//! Only simple case folding is supported. Namely, when matching
//! case-insensitively, the characters are first mapped using the [simple case
//! folding](ftp://ftp.unicode.org/Public/UNIDATA/CaseFolding.txt) mapping
//! before matching.
//!
//! Regular expressions themselves are **only** interpreted as a sequence of
//! Unicode scalar values. This means you can use Unicode characters directly
//! in your expression:
//!
//! ```rust
//! # extern crate regex; use regex::Regex;
//! # fn main() {
//! let re = Regex::new(r"(?i)Δ+").unwrap();
//! assert_eq!(re.find("ΔδΔ"), Some((0, 6)));
//! # }
//! ```
//!
//! Finally, Unicode general categories and scripts are available as character
//! classes. For example, you can match a sequence of numerals, Greek or
//! Cherokee letters:
//!
//! ```rust
//! # extern crate regex; use regex::Regex;
//! # fn main() {
//! let re = Regex::new(r"[\pN\p{Greek}\p{Cherokee}]+").unwrap();
//! assert_eq!(re.find("abcΔᎠβⅠᏴγδⅡxyz"), Some((3, 23)));
//! # }
//! ```
//!
//! # Opt out of Unicode support
//!
//! The `bytes` sub-module provides a `Regex` type that can be used to match
//! on `&[u8]`. By default, text is interpreted as ASCII compatible text with
//! all Unicode support disabled (e.g., `.` matches any byte instead of any
//! Unicode codepoint). Unicode support can be selectively enabled with the
//! `u` flag. See the `bytes` module documentation for more details.
//!
//! Unicode support can also be selectively *disabled* with the main `Regex`
//! type that matches on `&str`. For example, `(?-u:\b)` will match an ASCII
//! word boundary. Note though that invalid UTF-8 is not allowed to be matched
//! even when the `u` flag is disabled. For example, `(?-u:.)` will return an
//! error, since `.` matches *any byte* when Unicode support is disabled.
//!
//! # Syntax
//!
//! The syntax supported in this crate is almost in an exact correspondence
//! with the syntax supported by RE2. It is documented below.
//!
//! Note that the regular expression parser and abstract syntax are exposed in
//! a separate crate, [`regex-syntax`](../regex_syntax/index.html).
//!
//! ## Matching one character
//!
//! <pre class="rust">
//! .           any character except new line (includes new line with s flag)
//! [xyz]       A character class matching either x, y or z.
//! [^xyz]      A character class matching any character except x, y and z.
//! [a-z]       A character class matching any character in range a-z.
//! \d          digit (\p{Nd})
//! \D          not digit
//! [:alpha:]   ASCII character class ([A-Za-z])
//! [:^alpha:]  Negated ASCII character class ([^A-Za-z])
//! \pN         One-letter name Unicode character class
//! \p{Greek}   Unicode character class (general category or script)
//! \PN         Negated one-letter name Unicode character class
//! \P{Greek}   negated Unicode character class (general category or script)
//! </pre>
//!
//! Any named character class may appear inside a bracketed `[...]` character
//! class. For example, `[\p{Greek}\pN]` matches any Greek or numeral
//! character.
//!
//! ## Composites
//!
//! <pre class="rust">
//! xy    concatenation (x followed by y)
//! x|y   alternation (x or y, prefer x)
//! </pre>
//!
//! ## Repetitions
//!
//! <pre class="rust">
//! x*        zero or more of x (greedy)
//! x+        one or more of x (greedy)
//! x?        zero or one of x (greedy)
//! x*?       zero or more of x (ungreedy/lazy)
//! x+?       one or more of x (ungreedy/lazy)
//! x??       zero or one of x (ungreedy/lazy)
//! x{n,m}    at least n x and at most m x (greedy)
//! x{n,}     at least n x (greedy)
//! x{n}      exactly n x
//! x{n,m}?   at least n x and at most m x (ungreedy/lazy)
//! x{n,}?    at least n x (ungreedy/lazy)
//! x{n}?     exactly n x
//! </pre>
//!
//! ## Empty matches
//!
//! <pre class="rust">
//! ^     the beginning of text (or start-of-line with multi-line mode)
//! $     the end of text (or end-of-line with multi-line mode)
//! \A    only the beginning of text (even with multi-line mode enabled)
//! \z    only the end of text (even with multi-line mode enabled)
//! \b    a Unicode word boundary (\w on one side and \W, \A, or \z on other)
//! \B    not a Unicode word boundary
//! </pre>
//!
//! ## Grouping and flags
//!
//! <pre class="rust">
//! (exp)          numbered capture group (indexed by opening parenthesis)
//! (?P&lt;name&gt;exp)  named (also numbered) capture group (allowed chars: [_0-9a-zA-Z])
//! (?:exp)        non-capturing group
//! (?flags)       set flags within current group
//! (?flags:exp)   set flags for exp (non-capturing)
//! </pre>
//!
//! Flags are each a single character. For example, `(?x)` sets the flag `x`
//! and `(?-x)` clears the flag `x`. Multiple flags can be set or cleared at
//! the same time: `(?xy)` sets both the `x` and `y` flags and `(?x-y)` sets
//! the `x` flag and clears the `y` flag.
//!
//! All flags are by default disabled unless stated otherwise. They are:
//!
//! <pre class="rust">
//! i     case-insensitive
//! m     multi-line mode: ^ and $ match begin/end of line
//! s     allow . to match \n
//! U     swap the meaning of x* and x*?
//! u     Unicode support (enabled by default)
//! x     ignore whitespace and allow line comments (starting with `#`)
//! </pre>
//!
//! Here's an example that matches case-insensitively for only part of the
//! expression:
//!
//! ```rust
//! # extern crate regex; use regex::Regex;
//! # fn main() {
//! let re = Regex::new(r"(?i)a+(?-i)b+").unwrap();
//! let cap = re.captures("AaAaAbbBBBb").unwrap();
//! assert_eq!(cap.at(0), Some("AaAaAbb"));
//! # }
//! ```
//!
//! Notice that the `a+` matches either `a` or `A`, but the `b+` only matches
//! `b`.
//!
//! Here is an example that uses an ASCII word boundary instead of a Unicode
//! word boundary:
//!
//! ```rust
//! # extern crate regex; use regex::Regex;
//! # fn main() {
//! let re = Regex::new(r"(?-u:\b).+(?-u:\b)").unwrap();
//! let cap = re.captures("$$abc$$").unwrap();
//! assert_eq!(cap.at(0), Some("abc"));
//! # }
//! ```
//!
//! ## Escape sequences
//!
//! <pre class="rust">
//! \*         literal *, works for any punctuation character: \.+*?()|[]{}^$
//! \a         bell (\x07)
//! \f         form feed (\x0C)
//! \t         horizontal tab
//! \n         new line
//! \r         carriage return
//! \v         vertical tab (\x0B)
//! \123       octal character code (up to three digits)
//! \x7F       hex character code (exactly two digits)
//! \x{10FFFF} any hex character code corresponding to a Unicode code point
//! </pre>
//!
//! ## Perl character classes (Unicode friendly)
//!
//! These classes are based on the definitions provided in
//! [UTS#18](http://www.unicode.org/reports/tr18/#Compatibility_Properties):
//!
//! <pre class="rust">
//! \d     digit (\p{Nd})
//! \D     not digit
//! \s     whitespace (\p{White_Space})
//! \S     not whitespace
//! \w     word character (\p{Alphabetic} + \p{M} + \d + \p{Pc} + \p{Join_Control})
//! \W     not word character
//! </pre>
//!
//! ## ASCII character classes
//!
//! <pre class="rust">
//! [:alnum:]    alphanumeric ([0-9A-Za-z])
//! [:alpha:]    alphabetic ([A-Za-z])
//! [:ascii:]    ASCII ([\x00-\x7F])
//! [:blank:]    blank ([\t ])
//! [:cntrl:]    control ([\x00-\x1F\x7F])
//! [:digit:]    digits ([0-9])
//! [:graph:]    graphical ([!-~])
//! [:lower:]    lower case ([a-z])
//! [:print:]    printable ([ -~])
//! [:punct:]    punctuation ([!-/:-@[-`{-~])
//! [:space:]    whitespace ([\t\n\v\f\r ])
//! [:upper:]    upper case ([A-Z])
//! [:word:]     word characters ([0-9A-Za-z_])
//! [:xdigit:]   hex digit ([0-9A-Fa-f])
//! </pre>
//!
//! # Untrusted input
//!
//! This crate can handle both untrusted regular expressions and untrusted
//! search text.
//!
//! Untrusted regular expressions are handled by capping the size of a compiled
//! regular expression. (See `Regex::with_size_limit`.) Without this, it would
//! be trivial for an attacker to exhaust your system's memory with expressions
//! like `a{100}{100}{100}`.
//!
//! Untrusted search text is allowed because the matching engine(s) in this
//! crate have time complexity `O(mn)` (with `m ~ regex` and `n ~ search
//! text`), which means there's no way to cause exponential blow-up like with
//! some other regular expression engines. (We pay for this by disallowing
//! features like arbitrary look-ahead and backreferences.)
//!
//! When a DFA is used, pathological cases with exponential state blow up are
//! avoided by constructing the DFA lazily or in an "online" manner. Therefore,
//! at most one new state can be created for each byte of input. This satisfies
//! our time complexity guarantees, but can lead to unbounded memory growth
//! proportional to the size of the input. As a stopgap, the DFA is only
//! allowed to store a fixed number of states. (When the limit is reached, its
//! states are wiped and continues on, possibly duplicating previous work. If
//! the limit is reached too frequently, it gives up and hands control off to
//! another matching engine with fixed memory requirements.)

#![deny(missing_docs)]
#![cfg_attr(test, deny(warnings))]
#![cfg_attr(feature = "pattern", feature(pattern))]
#![cfg_attr(feature = "simd-accel", feature(cfg_target_feature))]
#![doc(html_logo_url = "https://www.rust-lang.org/logos/rust-logo-128x128-blk-v2.png",
       html_favicon_url = "https://www.rust-lang.org/favicon.ico",
       html_root_url = "https://doc.rust-lang.org/regex/")]

extern crate aho_corasick;
extern crate memchr;
extern crate thread_local;
#[cfg(test)] extern crate quickcheck;
extern crate regex_syntax as syntax;
#[cfg(feature = "simd-accel")] extern crate simd;
extern crate utf8_ranges;

pub use error::Error;
pub use re_builder::unicode::*;
pub use re_set::unicode::*;
pub use re_unicode::{
    Regex, Captures, SubCaptures, SubCapturesPos, SubCapturesNamed,
    CaptureNames, FindCaptures, FindMatches,
    Replacer, NoExpand, RegexSplits, RegexSplitsN,
    quote, is_match,
};

/**
Match regular expressions on arbitrary bytes.

This module provides a nearly identical API to the one found in the
top-level of this crate. There are two important differences:

1. Matching is done on `&[u8]` instead of `&str`. Additionally, `Vec<u8>`
is used where `String` would have been used.
2. Regular expressions are compiled with Unicode support *disabled* by
default. This means that while Unicode regular expressions can only match valid
UTF-8, regular expressions in this module can match arbitrary bytes. Unicode
support can be selectively enabled via the `u` flag in regular expressions
provided by this sub-module.

# Example: match null terminated string

This shows how to find all null-terminated strings in a slice of bytes:

```rust
# use regex::bytes::Regex;
let re = Regex::new(r"(?P<cstr>[^\x00]+)\x00").unwrap();
let text = b"foo\x00bar\x00baz\x00";

// Extract all of the strings without the null terminator from each match.
// The unwrap is OK here since a match requires the `cstr` capture to match.
let cstrs: Vec<&[u8]> =
    re.captures_iter(text)
      .map(|c| c.name("cstr").unwrap())
      .collect();
assert_eq!(vec![&b"foo"[..], &b"bar"[..], &b"baz"[..]], cstrs);
```

# Example: selectively enable Unicode support

This shows how to match an arbitrary byte pattern followed by a UTF-8 encoded
string (e.g., to extract a title from a Matroska file):

```rust
# use std::str;
# use regex::bytes::Regex;
let re = Regex::new(r"\x7b\xa9(?:[\x80-\xfe]|[\x40-\xff].)(?u:(.*))").unwrap();
let text = b"\x12\xd0\x3b\x5f\x7b\xa9\x85\xe2\x98\x83\x80\x98\x54\x76\x68\x65";
let caps = re.captures(text).unwrap();

// Notice that despite the `.*` at the end, it will only match valid UTF-8
// because Unicode mode was enabled with the `u` flag. Without the `u` flag,
// the `.*` would match the rest of the bytes.
assert_eq!((7, 10), caps.pos(1).unwrap());

// If there was a match, Unicode mode guarantees that `title` is valid UTF-8.
let title = str::from_utf8(caps.at(1).unwrap()).unwrap();
assert_eq!("☃", title);
```

In general, if the Unicode flag is enabled in a capture group and that capture
is part of the overall match, then the capture is *guaranteed* to be valid
UTF-8.

# Syntax

The supported syntax is pretty much the same as the syntax for Unicode
regular expressions with a few changes that make sense for matching arbitrary
bytes:

1. The `u` flag is *disabled* by default, but can be selectively enabled. (The
opposite is true for the main `Regex` type.) Disabling the `u` flag is said to
invoke "ASCII compatible" mode.
2. In ASCII compatible mode, neither Unicode codepoints nor Unicode character
classes are allowed.
3. In ASCII compatible mode, Perl character classes (`\w`, `\d` and `\s`)
revert to their typical ASCII definition. `\w` maps to `[[:word:]]`, `\d` maps
to `[[:digit:]]` and `\s` maps to `[[:space:]]`.
4. In ASCII compatible mode, word boundaries use the ASCII compatible `\w` to
determine whether a byte is a word byte or not.
5. Hexadecimal notation can be used to specify arbitrary bytes instead of
Unicode codepoints. For example, in ASCII compatible mode, `\xFF` matches the
literal byte `\xFF`, while in Unicode mode, `\xFF` is a Unicode codepoint that
matches its UTF-8 encoding of `\xC3\xBF`. Similarly for octal notation.
6. `.` matches any *byte* except for `\n` instead of any codepoint. When the
`s` flag is enabled, `.` matches any byte.

# Performance

In general, one should expect performance on `&[u8]` to be roughly similar to
performance on `&str`.
*/
pub mod bytes {
    pub use re_builder::bytes::*;
    pub use re_set::bytes::*;
    pub use re_bytes::*;
}

mod backtrack;
mod utf8;
mod compile;
mod dfa;
mod error;
mod exec;
mod expand;
mod freqs;
mod input;
mod literals;
#[cfg(feature = "pattern")]
mod pattern;
mod pikevm;
mod prog;
mod re_builder;
mod re_bytes;
mod re_plugin;
mod re_set;
mod re_trait;
mod re_unicode;
#[cfg(feature = "simd-accel")]
mod simd_accel;
#[cfg(not(feature = "simd-accel"))]
#[path = "simd_fallback/mod.rs"]
mod simd_accel;
mod sparse;

/// The `internal` module exists to support the `regex!` macro and other
/// suspicious activity, such as testing different matching engines and
/// supporting the `regex-debug` CLI utility.
#[doc(hidden)]
pub mod internal {
    pub use compile::Compiler;
    pub use exec::{Exec, ExecBuilder};
    pub use input::{Char, Input, CharInput, InputAt};
    pub use literals::LiteralSearcher;
    pub use prog::{Program, Inst, EmptyLook, InstRanges};
    pub use re_plugin::Plugin;
    pub use re_unicode::_Regex;
}