use regex::Regex;

let re = Regex::new(r"(?m)^([^:]+):([0-9]+):(.+)$").unwrap();
let hay = "\
path/to/foo:54:Blue Harvest
path/to/bar:90:Something, Something, Something, Dark Side
path/to/baz:3:It's a Trap!
";

let mut results = vec![];
for (_, [path, lineno, line]) in re.captures_iter(hay).map(|c| c.extract()) {
    results.push((path, lineno.parse::<u64>()?, line));
}
assert_eq!(results, vec![
    ("path/to/foo", 54, "Blue Harvest"),
    ("path/to/bar", 90, "Something, Something, Something, Dark Side"),
    ("path/to/baz", 3, "It's a Trap!"),
]);

$ mkdir regex-example
$ cd regex-example
$ crago init

$ cargo add regex

use regex::Regex;

fn main() {
    let re = Regex::new(r"Hello (?<name>\w+)!").unwrap();
    let Some(caps) = re.captures("Hello Murphy!") else {
        println!("no match!");
        return;
    };
    println!("The name is: {}", &caps["name"]);
}

$ cargo run
   Compiling memchr v2.5.0
   Compiling regex-syntax v0.7.1
   Compiling aho-corasick v1.0.1
   Compiling regex v1.8.1
   Compiling regex-example v0.1.0 (/tmp/regex-example)
    Finished dev [unoptimized + debuginfo] target(s) in 4.22s
     Running `target/debug/regex-example`
The name is: Murphy

use regex::Regex;

// We use 'unwrap()' here because it would be a bug in our program if the
// pattern failed to compile to a regex. Panicking in the presence of a bug
// is okay.
let re = Regex::new(r"Homer (.)\. Simpson").unwrap();
let hay = "Homer J. Simpson";
let Some(caps) = re.captures(hay) else { return };
assert_eq!("J", &caps[1]);

use regex::Regex;
// Note that (?P<middle>.) is a different way to spell the same thing.
let re = Regex::new(r"Homer (?<middle>.)\. Simpson").unwrap();
let hay = "Homer J. Simpson";
let Some(caps) = re.captures(hay) else {return};
assert_eq!("J", &caps["middle"]);

use regex::Regex;

let re = Regex::new(r"^\d{4}-\d{2}-\d{2}$").unwrap();
assert!(re.is_match("2010-03-14"));

use regex::Regex;

let re = Regex::new(r"^\d{4}-\d{2}-\d{2}$").unwrap();
assert!(re.is_match("𝟚𝟘𝟙𝟘-𝟘𝟛-𝟙𝟜"));

use regex::Regex;

let re = Regex::new(r"[0-9]{4}-[0-9]{2}-[0-9]{2}").unwrap();
let hay = "What do 1865-04-14, 1881-07-02, 1901-09-06 and 1963-11-22 have in common?";
// 'm' is a 'Match', and 'as_str()' returns the matching part of the haystack.
let dates: Vec<&str> = re.find_iter(hay).map(|m| m.as_str()).collect();
assert_eq!(dates, vec![
    "1865-04-14",
    "1881-07-02",
    "1901-09-06",
    "1963-11-22",
]);

(?<name>pattern)
 │ │    │       │
 │ │    │       └─ 捕获组的模式
 │ │    └─────────── 捕获组的名称
 │ └─────────────────── 命名语法的开始
 └────────────────────── 捕获组的开始

use regex::Regex;

let re = Regex::new(r"(?<y>[0-9]{4})-(?<m>[0-9]{2})-(?<d>[0-9]{2})").unwrap();
let hay = "What do 1865-04-14, 1881-07-02, 1901-09-06 and 1963-11-22 have in common?";
// 'm' is a 'Match', and 'as_str()' returns the matching part of the haystack.
let dates: Vec<(&str, &str, &str)> = re.captures_iter(hay).map(|caps| {
    // The unwraps are okay because every capture group must match if the whole
    // regex matches, and in this context, we know we have a match.
    //
    // Note that we use `caps.name("y").unwrap().as_str()` instead of
    // `&caps["y"]` because the lifetime of the former is the same as the
    // lifetime of `hay` above, but the lifetime of the latter is tied to the
    // lifetime of `caps` due to how the `Index` trait is defined.
    let year = caps.name("y").unwrap().as_str();
    let month = caps.name("m").unwrap().as_str();
    let day = caps.name("d").unwrap().as_str();
    (year, month, day)
}).collect();
assert_eq!(dates, vec![
    ("1865", "04", "14"),
    ("1881", "07", "02"),
    ("1901", "09", "06"),
    ("1963", "11", "22"),
]);

use regex::Regex;

let re = Regex::new(r"([0-9]{4})-([0-9]{2})-([0-9]{2})").unwrap();
let hay = "What do 1865-04-14, 1881-07-02, 1901-09-06 and 1963-11-22 have in common?";
let dates: Vec<(&str, &str, &str)> = re.captures_iter(hay).map(|caps| {
    let (_, [year, month, day]) = caps.extract();
    (year, month, day)
}).collect();
assert_eq!(dates, vec![
    ("1865", "04", "14"),
    ("1881", "07", "02"),
    ("1901", "09", "06"),
    ("1963", "11", "22"),
]);

use regex::Regex;

let re = Regex::new(r"(?<y>\d{4})-(?<m>\d{2})-(?<d>\d{2})").unwrap();
let before = "1973-01-05, 1975-08-25 and 1980-10-18";
let after = re.replace_all(before, "$m/$d/$y");
assert_eq!(after, "01/05/1973, 08/25/1975 and 10/18/1980");

use regex::Regex;

let re = Regex::new(r"(?x)
  (?P<y>\d{4}) # the year, including all Unicode digits
  -
  (?P<m>\d{2}) # the month, including all Unicode digits
  -
  (?P<d>\d{2}) # the day, including all Unicode digits
").unwrap();

let before = "1973-01-05, 1975-08-25 and 1980-10-18";
let after = re.replace_all(before, "$m/$d/$y");
assert_eq!(after, "01/05/1973, 08/25/1975 and 10/18/1980");

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. Each match corresponds to the
// ID of the matching pattern.
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));

use std::sync::LazyLock;

use regex::Regex;

fn some_helper_function(haystack: &str) -> bool {
    static RE: LazyLock<Regex> = LazyLock::new(|| Regex::new(r"...").unwrap());
    RE.is_match(haystack)
}

fn main() {
    assert!(some_helper_function("abc"));
    assert!(!some_helper_function("ac"));
}

use regex::Regex;

let re = Regex::new(r"(?i)Δ+").unwrap();
let m = re.find("ΔδΔ").unwrap();
assert_eq!((0, 6), (m.start(), m.end()));
// alternatively:
assert_eq!(0..6, m.range());

use regex::Regex;

let re = Regex::new(r"[\pN\p{Greek}\p{Cherokee}]+").unwrap();
let m = re.find("abcΔᎠβⅠᏴγδⅡxyz").unwrap();
assert_eq!(3..23, m.range());

.             除了换行符（包括带有 s 标志的换行符）
[0-9]         任何 ASCII 数字
\d            数字 (\p{Nd})
\D            非数字
\pX           由一个字母名称标识的Unicode字符类
\p{Greek}     Unicode字符类（通用类别或脚本）
\PX           由一个字母名称标识的否定Unicode字符类
\P{Greek}     否定的Unicode字符类（通用类别或脚本）

[xyz]         A character class matching either x, y or z (union).
[^xyz]        A character class matching any character except x, y and z.
[a-z]         A character class matching any character in range a-z.
[[:alpha:]]   ASCII character class ([A-Za-z])
[[:^alpha:]]  Negated ASCII character class ([^A-Za-z])
[x[^xyz]]     Nested/grouping character class (matching any character except y and z)
[a-y&&xyz]    Intersection (matching x or y)
[0-9&&[^4]]   Subtraction using intersection and negation (matching 0-9 except 4)
[0-9--4]      Direct subtraction (matching 0-9 except 4)
[a-g~~b-h]    Symmetric difference (matching `a` and `h` only)
[\[\]]        Escaping in character classes (matching [ or ])
[a&&b]        An empty character class matching nothing

xy    concatenation (x followed by y)
x|y   alternation (x or y, prefer x)

use regex::Regex;

let haystack = "samwise";
// If 'samwise' comes first in our alternation, then it is
// preferred as a match, even if the regex engine could
// technically detect that 'sam' led to a match earlier.
let re = Regex::new(r"samwise|sam").unwrap();
assert_eq!("samwise", re.find(haystack).unwrap().as_str());
// But if 'sam' comes first, then it will match instead.
// In this case, it is impossible for 'samwise' to match
// because 'sam' is a prefix of it.
let re = Regex::new(r"sam|samwise").unwrap();
assert_eq!("sam", re.find(haystack).unwrap().as_str());

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

let re = regex::Regex::new(r"").unwrap();
let ranges: Vec<_> = re.find_iter("💩").map(|m| m.range()).collect();
assert_eq!(ranges, vec![0..0, 4..4]);

let re = regex::bytes::Regex::new(r"").unwrap();
let ranges: Vec<_> = re.find_iter("💩".as_bytes()).map(|m| m.range()).collect();
assert_eq!(ranges, vec![0..0, 1..1, 2..2, 3..3, 4..4]);

(exp)          编号捕获组（按打开括号索引）
(?P<name>exp)  命名（也可编号）捕获组（名称必须为字母数字）
(?<name>exp)   命名（也可编号）捕获组（名称必须为字母数字）
(?:exp)        非捕获组
(?flags)       在当前组内设置标志
(?flags:exp)   设置exp的标志（非捕获）

i     不区分大小写：字母匹配大小写
m     多行模式：^ 和 $ 匹配行的开始/结束
s     允许 . 匹配 \n
R     启用CRLF模式：当启用多行模式时，使用\r\n
U     交换 x* 和 x*? 的含义
u     Unicode 支持（默认启用）
x     详细模式，忽略空白字符并允许行注释（以 `#` 开始）

use regex::Regex;

let re = Regex::new("r(?i)a+(?-i)b+").unwrap();
let m = re.find("AaAaAabbBBBb").unwrap();
assert_eq!(m.as_str(), "AaAaAabb");

use regex::Regex;

let re = Regex::new(r"(?m)^line \d+").unwrap();
let m = re.find("line one\nline 2\n").unwrap();
assert_eq!(m.as_str(), "line 2");

use regex::Regex;

let re = Regex::new(r"(?m)^").unwrap();
let m = re.find_iter("test\n").last().unwrap();
assert_eq!((m.start(), m.end()), (5, 5));

use regex::Regex;

let re = Regex::new(r"(?mR)^foo$").unwrap();
let m = re.find("\r\nfoo\r\n").unwrap();
assert_eq!(m.as_str(), "foo");

use regex::Regex;

let re = Regex::new(r"(?-u:\b).+(?-u:\b)").unwrap();
let m = re.find("$$abc$$").unwrap();
assert_eq!(m.as_str(), "abc");

\*              literal *, applies to all ASCII except [0-9A-Za-z<>]
\a              bell (\x07)
\f              form feed (\x0C)
\t              horizontal tab
\n              new line
\r              carriage return
\v              vertical tab (\x0B)
\A              matches at the beginning of a haystack
\z              matches at the end of a haystack
\b              word boundary assertion
\B              negated word boundary assertion
\b{start}, \<   start-of-word boundary assertion
\b{end}, \>     end-of-word boundary assertion
\b{start-half}  half of a start-of-word boundary assertion
\b{end-half}    half of a end-of-word boundary assertion
\123            octal character code, up to three digits (when enabled)
\x7F            hex character code (exactly two digits)
\x{10FFFF}      any hex character code corresponding to a Unicode code point
\u007F          hex character code (exactly four digits)
\u{7F}          any hex character code corresponding to a Unicode code point
\U0000007F      hex character code (exactly eight digits)
\U{7F}          any hex character code corresponding to a Unicode code point
\p{Letter}      Unicode character class
\P{Letter}      negated Unicode character class
\d, \s, \w      Perl character class
\D, \S, \W      negated Perl character class

\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

[[: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])