add is_valid_email_address

Author: lyqio

DIRECTORY.md

@@ -314,6 +314,7 @@
     * [Burrows Wheeler Transform](https://github.com/TheAlgorithms/Rust/blob/master/src/string/burrows_wheeler_transform.rs)
     * [Duval Algorithm](https://github.com/TheAlgorithms/Rust/blob/master/src/string/duval_algorithm.rs)
     * [Hamming Distance](https://github.com/TheAlgorithms/Rust/blob/master/src/string/hamming_distance.rs)
+    * [Is Valid Email Address](https://github.com/TheAlgorithms/Rust/blob/master/src/string/is_valid_email_address.rs)
     * [Isomorphism](https://github.com/TheAlgorithms/Rust/blob/master/src/string/isomorphism.rs)
     * [Jaro Winkler Distance](https://github.com/TheAlgorithms/Rust/blob/master/src/string/jaro_winkler_distance.rs)
     * [Knuth Morris Pratt](https://github.com/TheAlgorithms/Rust/blob/master/src/string/knuth_morris_pratt.rs)

src/string/is_valid_email_address.rs

@@ -0,0 +1,139 @@
+const MAX_LOCAL_PART_LENGTH: u32 = 64;
+const MAX_DOMAIN_LENGTH: u32 = 255;
+const CHARACTERS: &str = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz1234567890";
+const SYMBOLS: &str = "!#$%&'*+-/=?^_`{|}~";
+
+fn clear_quotes(input: &str) -> String {
+    let mut quote_count = input.starts_with('"') as u32;
+    let mut new_local_part: String = String::from(input.chars().next().unwrap());
+    for i in 1..input.len() {
+        if input.chars().nth(i).unwrap() == '"' && input.chars().nth(i - 1).unwrap() != '\\' {
+            quote_count += 1;
+
+            if !new_local_part.starts_with('"') && quote_count != 1 {
+                new_local_part.push('"');
+            }
+        }
+
+        if quote_count % 2 == 0 {
+            new_local_part.push(input.chars().nth(i).unwrap());
+        }
+    }
+
+    new_local_part
+}
+
+/// Follows email address rules as listed:
+/// https://en.wikipedia.org/wiki/Email_address#Examples
+pub fn is_valid_email_address(input_email_address: &str) -> bool {
+    let email_address = clear_quotes(input_email_address);
+
+    let parts: Vec<String> = email_address
+        .split('@')
+        .map(|x| x.to_string())
+        .collect::<Vec<String>>();
+
+    // (1)  ensure there is only one '@' symbol in the address
+    if parts.len() != 2 {
+        return false;
+    }
+
+    let (local_part, domain): (String, String) = (parts[0].clone(), parts[1].clone());
+
+    // (2)  check that the length of the two parts are within the valid range
+    if local_part.len() > MAX_LOCAL_PART_LENGTH as usize
+        || domain.len() > MAX_DOMAIN_LENGTH as usize
+    {
+        return false;
+    }
+
+    // (3)  check quote dots
+    for i in 1..local_part.len() {
+        if local_part.chars().nth(i - 1).unwrap() == '"'
+            && local_part.chars().nth(i).unwrap() == '"'
+        {
+            let proceeding_quote = local_part.chars().nth(i + 1);
+            if proceeding_quote.is_some() && proceeding_quote.unwrap() != '.' {
+                return false;
+            }
+        }
+    }
+
+    // (4)  validate the dots in the local part
+    if local_part.starts_with('.') || local_part.ends_with('.') || local_part.contains("..") {
+        return false;
+    }
+
+    // (5)  check that the characters in the local part are valid
+    for item in local_part.chars() {
+        if !CHARACTERS.contains(item) && !SYMBOLS.contains(item) && item != '.' && item != '"' {
+            return false;
+        }
+    }
+
+    // (6)  check that the domain contains valid characters
+    for item in domain.chars() {
+        if !CHARACTERS.contains(item) && item != '-' && item != '.' && !"[]:".contains(item) {
+            return false;
+        }
+    }
+
+    // (7)  validate the dots in the domain
+    if domain.starts_with('.') || domain.ends_with('.') || domain.contains("..") {
+        return false;
+    }
+
+    // (8)  validate the dashes in the domain
+    if domain.starts_with('-') || domain.ends_with('-') {
+        return false;
+    }
+
+    true
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::string::is_valid_email_address::is_valid_email_address;
+
+    macro_rules! test_is_valid_email_address {
+        ($($name:ident: $inputs:expr,)*) => {
+        $(
+            #[test]
+            fn $name() {
+                let (s, expected) = $inputs;
+                assert_eq!(is_valid_email_address(s), expected);
+            }
+        )*
+        }
+    }
+
+    test_is_valid_email_address! {
+        basic: ("[email protected]", true),
+        basic_2: ("[email protected]", true),
+        cases: ("[email protected]", true),
+        one_letter_local: ("[email protected]", true),
+        long_email_subdomains: ("[email protected]", true),
+        tags: ("[email protected]", true),
+        slashes: ("name/[email protected]", true),
+        no_tld: ("admin@example", true),
+        tld: ("[email protected]", true),
+        quotes_with_space: ("\" \"@example.org", true),
+        quoted_double_dot: ("\"john..doe\"@example.org", true),
+        host_route: ("[email protected]", true),
+        quoted_non_letters: (r#""very.(),:;<>[]\".VERY.\"very@\\ \"very\".unusual"@strange.example.com"#, true),
+        percent_symbol: ("user%[email protected]", true),
+        local_end_symbol: ("[email protected]", true),
+        ip_address: ("postmaster@[123.123.123.123]", true),
+        other_ip: ("postmaster@[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:7334]", true),
+        begin_with_underscore: ("_test@[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:7334]", true),
+
+        no_at: ("abc.example.com", false),
+        multiple_ats: ("a@b@[email protected]", false),
+        bad_local_characters: ("a\"b(c)d,e:f;g<h>i[j\\k][email protected]", false),
+        bad_local_string: ("just\"not\"[email protected]", false),
+        bad_backslash: ("this is\"not\\[email protected]", false),
+        escaped_backslash: ("this\\ still\\\"not\\\\[email protected]", false),
+        long_local_part: ("1234567890123456789012345678901234567890123456789012345678901234+x@example.com", false),
+        domain_underscore: ("i.like.underscores@but_they_are_not_allowed_in_this_part", false),
+    }
+}

src/string/mod.rs

@@ -5,6 +5,7 @@ mod boyer_moore_search;
 mod burrows_wheeler_transform;
 mod duval_algorithm;
 mod hamming_distance;
+mod is_valid_email_address;
 mod isomorphism;
 mod jaro_winkler_distance;
 mod knuth_morris_pratt;
@@ -31,6 +32,7 @@ pub use self::burrows_wheeler_transform::{
 };
 pub use self::duval_algorithm::duval_algorithm;
 pub use self::hamming_distance::hamming_distance;
+pub use self::is_valid_email_address::is_valid_email_address;
 pub use self::isomorphism::is_isomorphic;
 pub use self::jaro_winkler_distance::jaro_winkler_distance;
 pub use self::knuth_morris_pratt::knuth_morris_pratt;