@techreport{duerst-i18n-norm-04,
    number =    {draft-duerst-i18n-norm-04},
    type =      {Internet-Draft},
    institution =   {Internet Engineering Task Force},
    publisher = {Internet Engineering Task Force},
    note =      {Work in Progress},
    url =       {https://datatracker.ietf.org/doc/draft-duerst-i18n-norm/04/},
    author =    {Martin J. Dürst and Mark Davis},
    title =     {{Character Normalization in IETF Protocols}},
    pagetotal = 12,
    year =      2000,
    month =     sep,
    day =       13,
    abstract =  {The Universal Character Set (UCS) {[}ISO10646, Unicode{]} covers a very wide repertoire of characters. The IETF, in {[}RFC 2277{]}, requires that future IETF protocols support UTF-8 {[}RFC 2279{]}, an ASCII-compatible encoding of UCS. The wide range of characters included in the UCS has lead to some cases of duplicate encodings. This document proposes that in IETF protocols, the class of duplicates called canonical equivalents be dealt with by using Early Uniform Normalization according to Unicode Normalization Form C, Canonical Composition (NFC) {[}UTR15{]}. This document describes both Early Uniform Normalization and Normalization Form C.},
}