INNER CODE UNIT · Rust
build_regex_query
Drew-Alleman/DataSurgeon · src/main.rs:328
fn build_regex_query(&self) -> HashMap<String, Regex>{
let mut regex_map: HashMap<String, Regex> = [
("credit_card", Regex::new(r"\b(\d{4}[- ]?\d{4}[- ]?\d{4}[- ]?\d{4})\b").unwrap()),
("email", Regex::new(r"\b([A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4})\b").unwrap()),
("url", Regex::new(r#"(https?://(?:[^\s.,;:"'<>()\[\]{}]+\.)*[^\s.,;:"'<>()\[\]{}]+(/[^\s]*[^\s.,;:"'<>()\[\]{}\s])?)"#).unwrap()),
("ip_address", Regex::new(r"((25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)){3})\b").unwrap()),
("social_security", Regex::new(r"\b(\d{3}-\d{2}-\d{4})\b").unwrap()),
("phone_number", Regex::new(r"(\b[2-9]\d{2}-\d{3}-\d{4}\b)").unwrap()),
("ipv6_address", Regex::new(r"((?:[0-9a-fA-F]{1,4}:){1,7}[0-9a-fA-F]{1,4}|(?:[0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|(?:[0-9a-fA-F]{1,4}:){1,5}(?::[0-9a-fA-F]{1,4}){1,2}|(?:[0-9a-fA-F]{1,4}:){1,4}(?::[0-9a-fA-F]{1,4}){1,3}|(?:[0-9a-fA-F]{1,4}:){1,3}(?::[0-9a-fA-F]{1,4}){1,4}|(?:[0-9a-fA-F]{1,4}:){1,2}(?::[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:(?:(?::[0-9a-fA-F]{1,4}){1,6})|:(?:(?::[0-9a-fA-F]{1,4}){1,7}|:))(?:/\d{1,3})?").unwrap()),
("srv_dns", Regex::new(r"\b(.+?)\s+IN\s+SRV\s+\d+\s+\d+\s+\d+\s+(.+)\b").unwrap()),
("mac_address", Regex::new(r"([0-9a-fA-F]{2}(:[0-9a-fA-F]{2}){5})").unwrap()),
("google", Regex::new(r#""private_key_id":\s*"(\w{40})""#).unwrap()),
("aws_keys", Regex::new(r"\b(?:ACCESS_KEY|aws_access_key_id|aws_secret_access_key|secret_key)\s*=\s*([a-zA-Z0-9/+]{20,40})\s*\b").unwrap()),
("bitcoin_wallet", Regex::new(r"\b([13][a-km-zA-HJ-NP-Z1-9]{25,34})\b").unwrap()),
// ("ssh_keys", Regex::new(r"(ssh-rsa AAAA[0-9A-Za-z+/]+[=]{0,3}( [^@]+@[^@]+)?)").unwrap())
("files", Regex::new(r"([\w,\s-]+\.(txt|pdf|doc|docx|xls|xlsx|xml|jpg|jpeg|png|gif|bmp|csv|json|yaml|log|tar|tgz|gz|zip|rar|7z|exe|dll|bat|ps1|sh|py|rb|js|mdb|sql|db|dbf|ini|cfg|conf|bak|old|backup|pgp|gpg|aes|dll|sys|drv|ocx|pcap|tcpdump))").unwrap()),
("hashes", Regex::new(r"\b([0-9a-fA-F]{32}|[0-9a-fA-F]{40}|[0-9a-fA-F]{56}|[0-9a-fA-F]{64}|[0-9a-fA-F]{96}|[0-9a-fA-F]{128}|[0-9a-fA-F]{56}|[0-9a-fA-F]{128}|[0-9a-fA-F]{224}|[0-9a-fA-F]{256}|[0-9a-fA-F]{384}|[0-9a-fA-F]{512}|[a-fA-F0-9*]{16}|[a-fA-F0-9*]{40}|[a-fA-F0-9*]{64}|[a-fA-F0-9*]{96}|[a