#stringprep.mbt

Preparation of Internationalized Strings ("stringprep") as defined in RFC 3454 in MoonBit

#Installation

moon add chawyehsu/stringprep

#API

#stringprep.saslprep(s: String): String raise StringprepError

@stringprep.saslprep("user") // "user"
@stringprep.saslprep("I\u{00AD}X") // "IX" (soft hyphen removed)
@stringprep.saslprep("a\u{00A0}b") // "a b" (non-ASCII space mapped to ASCII space)
@stringprep.saslprep("\u{2168}") // "IX" (roman numeral normalized via NFKC)

#stringprep.nameprep(s: String): String raise StringprepError

@stringprep.nameprep("CAFE") // "cafe" (case folding)
@stringprep.nameprep("\u{00DF}") // "ss" (German sharp s)
@stringprep.nameprep("安室奈美恵-with-SUPER-MONKEYS") // "安室奈美恵-with-super-monkeys"

#stringprep.nodeprep(s: String): String raise StringprepError

@stringprep.nodeprep("räksmörgås.josefßon.org") // "räksmörgås.josefsson.org"

#stringprep.resourceprep(s: String): String raise StringprepError

@stringprep.resourceprep("foo@bar") // "foo@bar"

#stringprep.x520prep(s: String, case_fold~ : Bool): String raise StringprepError

@stringprep.x520prep("UPPERCASED", case_fold=true) // "uppercased"
@stringprep.x520prep("foo@bar", case_fold=true) // "foo@bar"

#Error Handling

• ProhibitedCharacter(Char) - The string contains a prohibited character
• ProhibitedBidirectionalText - The string violates bidirectional text rules
• StartsWithCombiningCharacter - The string starts with a combining character (x520prep only)
• EmptyString - The input string is empty (x520prep only)

try @stringprep.saslprep("a\u{007F}b") catch {
  StringprepError::ProhibitedCharacter(c) => println("Prohibited: \{c}")
  _ => ()
}

#Contributing

moonup pin toolchain-version

#Code Generation

# Generate NFKC normalization tables (Unicode 3.2)
python3 codegen/unicode_nfkc.py

# Generate RFC 3454 stringprep tables
python3 codegen/rfc3454_tables.py

#References

• RFC 3454 - Preparation of Internationalized Strings ("stringprep")
• RFC 3491 - Nameprep: A Stringprep Profile for Internationalized Domain Names
• RFC 3920 - Extensible Messaging and Presence Protocol (XMPP): Core
• RFC 4013 - SASLprep: Stringprep Profile for User Names and Passwords
• ITU-T X.520 - Information technology – Open Systems Interconnection – The Directory: Selected attribute types
• Unicode 3.2.0 - Unicode Character Database

#License

Blog · GitHub @chawyehsu · Twitter @chawyehsu