Regular Expressions

Verify and extract login from an email address

regex Text processing

Validates that an email address is formatted correctly, and extracts everything before the @ symbol. The Regex is compiled only once, on first use, by declaring it as a static LazyLock.

use regex::Regex;
use std::sync::LazyLock;

fn extract_login(input: &str) -> Option<&str> {
    static RE: LazyLock<Regex> = LazyLock::new(|| {
        Regex::new(
            r"(?x)
            ^(?P<login>[^@\s]+)@
            ([[:word:]]+\.)*
            [[:word:]]+$
            ",
        )
        .expect("valid regex")
    });
    RE.captures(input)
        .and_then(|cap| cap.name("login").map(|login| login.as_str()))
}

fn main() {
    assert_eq!(extract_login(r"I❤email@example.com"), Some(r"I❤email"));
    assert_eq!(
        extract_login(r"sdf+sdsfsd.as.sdsd@jhkk.d.rl"),
        Some(r"sdf+sdsfsd.as.sdsd")
    );
    assert_eq!(extract_login(r"More@Than@One@at.com"), None);
    assert_eq!(extract_login(r"Not an email@email"), None);
}

Extract a list of unique #Hashtags from a text

regex Text processing

Extracts, sorts, and deduplicates list of hashtags from text.

The hashtag regex given here only catches Latin hashtags that start with a letter. The complete twitter hashtag regex is much more complicated.

The Regex is compiled only once, on first use, by declaring it as a static LazyLock.

use regex::Regex;
use std::collections::HashSet;
use std::sync::LazyLock;

fn extract_hashtags(text: &str) -> HashSet<&str> {
    static HASHTAG_REGEX: LazyLock<Regex> =
        LazyLock::new(|| Regex::new(r"\#[a-zA-Z][0-9a-zA-Z_]*").expect("valid regex"));
    HASHTAG_REGEX
        .find_iter(text)
        .map(|mat| mat.as_str())
        .collect()
}

fn main() {
    let tweet = "Hey #world, I just got my new #dog, say hello to Till. #dog #forever #2 #_ ";
    let tags = extract_hashtags(tweet);
    assert!(tags.contains("#dog") && tags.contains("#forever") && tags.contains("#world"));
    assert_eq!(tags.len(), 3);
}

Extract phone numbers from text

regex Text processing

Processes a string of text using Regex::captures_iter to capture multiple phone numbers. This recipe handles US convention phone numbers.

use anyhow::Result;
use regex::Regex;
use std::fmt;

struct PhoneNumber<'a> {
    area: &'a str,
    exchange: &'a str,
    subscriber: &'a str,
}

impl<'a> fmt::Display for PhoneNumber<'a> {
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        write!(f, "1 ({}) {}-{}", self.area, self.exchange, self.subscriber)
    }
}

fn main() -> Result<()> {
    let phone_text = "
    +1 505 881 9292 (v) +1 505 778 2212 (c) +1 505 881 9297 (f)
    (202) 991 9534
    Alex 5553920011
    1 (800) 233-2010
    1.299.339.1020";

    let re = Regex::new(
        r#"(?x)
          (?:\+?1)?                       # Country Code Optional
          [\s\.]?
          (([2-9]\d{2})|\(([2-9]\d{2})\)) # Area Code
          [\s\.\-]?
          ([2-9]\d{2})                    # Exchange Code
          [\s\.\-]?
          (\d{4})                         # Subscriber Number"#,
    )?;

    let phone_numbers = re.captures_iter(phone_text).filter_map(|cap| {
        let groups = (cap.get(2).or(cap.get(3)), cap.get(4), cap.get(5));
        match groups {
            (Some(area), Some(ext), Some(sub)) => Some(PhoneNumber {
                area: area.as_str(),
                exchange: ext.as_str(),
                subscriber: sub.as_str(),
            }),
            _ => None,
        }
    });

    assert_eq!(
        phone_numbers.map(|m| m.to_string()).collect::<Vec<_>>(),
        vec![
            "1 (505) 881-9292",
            "1 (505) 778-2212",
            "1 (505) 881-9297",
            "1 (202) 991-9534",
            "1 (555) 392-0011",
            "1 (800) 233-2010",
            "1 (299) 339-1020",
        ]
    );

    Ok(())
}

Filter a log file by matching multiple regular expressions

regex Text processing

Reads a file named application.log and only outputs the lines containing “version X.X.X”, some IP address followed by port 443 (e.g. “192.168.0.1:443”), or a specific warning.

A regex::RegexSetBuilder composes a regex::RegexSet. Since backslashes are very common in regular expressions, using raw string literals makes them more readable.

use anyhow::Result;
use regex::RegexSetBuilder;
use std::fs::File;
use std::io::{BufRead, BufReader};

fn main() -> Result<()> {
    let log_path = "application.log";
    let buffered = BufReader::new(File::open(log_path)?);

    let set = RegexSetBuilder::new(&[
        r#"version "\d\.\d\.\d""#,
        r#"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:443"#,
        r#"warning.*timeout expired"#,
    ])
    .case_insensitive(true)
    .build()?;

    buffered
        .lines()
        .filter_map(|line| line.ok())
        .filter(|line| set.is_match(line.as_str()))
        .for_each(|x| println!("{}", x));

    Ok(())
}

Replace all occurrences of one text pattern with another pattern.

regex Text processing

Replaces all occurrences of the standard ISO 8601 YYYY-MM-DD date pattern with the equivalent American English date with slashes. For example 2013-01-15 becomes 01/15/2013.

The method Regex::replace_all replaces all occurrences of the whole regex. &str implements the Replacer trait which allows variables like $abcde to refer to corresponding named capture groups (?P<abcde>REGEX) from the search regex. See the replacement string syntax for examples and escaping detail. The regex is compiled only once, on first use, by declaring it as a static LazyLock.

use regex::Regex;
use std::borrow::Cow;
use std::sync::LazyLock;

fn reformat_dates(before: &str) -> Cow<str> {
    static ISO8601_DATE_REGEX: LazyLock<Regex> = LazyLock::new(|| {
        Regex::new(r"(?P<y>\d{4})-(?P<m>\d{2})-(?P<d>\d{2})").expect("valid regex")
    });
    ISO8601_DATE_REGEX.replace_all(before, "$m/$d/$y")
}

fn main() {
    let before = "2012-03-14, 2013-01-15 and 2014-07-05";
    let after = reformat_dates(before);
    assert_eq!(after, "03/14/2012, 01/15/2013 and 07/05/2014");
}