Fixed some case-folding and added Table A.1 for IDNA (#42).

This commit is contained in:
Richard Moore 2019-08-03 00:43:22 -04:00
parent c09de16347
commit f955dca417
No known key found for this signature in database
GPG Key ID: 665176BE8E9DC651
10 changed files with 10456 additions and 87 deletions

@ -2,14 +2,12 @@
import { toUtf8CodePoints, _toUtf8String, UnicodeNormalizationForm } from "./utf8";
let _tmp = 0;
type Ranged = {
l: number,
h: number,
d?: number,
s?: number,
e?: Array<number>
l: number, // Lo value
h: number, // High value (less the lo)
d?: number, // Delta/stride (default: 1)
s?: number, // Shift (default: 1)
e?: Array<number> // Exceptions to skip
};
type Table = { [ src: number ]: Array<number> };
@ -40,6 +38,37 @@ function createTable(data: string, func?: (value: string) => Array<number>): Tab
return result;
}
function createRangeTable(data: string): Array<Ranged> {
let hi = 0;
return data.split(",").map((v) => {
let comps = v.split("-");
if (comps.length === 1) {
comps[1] = "0";
} else if (comps[1] === "") {
comps[1] = "1";
}
let lo = hi + parseInt(comps[0], 16);
hi = parseInt(comps[1], 16);
return { l: lo, h: hi };
});
}
function matchMap(value: number, ranges: Array<Ranged>): Ranged {
let lo = 0;
for (let i = 0; i < ranges.length; i++) {
let range = ranges[i];
lo += range.l;
if (value >= lo && value <= lo + range.h && ((value - lo) % (range.d || 1)) === 0) {
if (range.e && range.e.indexOf(value - lo) !== -1) { continue; }
return range;
}
}
return null;
}
const Table_A_1_ranges = createRangeTable("221,13-1b,5f-,40-10,51-f,11-3,3-3,2-2,2-4,8,2,15,2d,28-8,88,48,27-,3-5,11-20,27-,8,28,3-5,12,18,b-a,1c-4,6-16,2-d,2-2,2,1b-4,17-9,8f-,10,f,1f-2,1c-34,33-14e,4,36-,13-,6-2,1a-f,4,9-,3-,17,8,2-2,5-,2,8-,3-,4-8,2-3,3,6-,16-6,2-,7-3,3-,17,8,3,3,3-,2,6-3,3-,4-a,5,2-6,10-b,4,8,2,4,17,8,3,6-,b,4,4-,2-e,2-4,b-10,4,9-,3-,17,8,3-,5-,9-2,3-,4-7,3-3,3,4-3,c-10,3,7-2,4,5-2,3,2,3-2,3-2,4-2,9,4-3,6-2,4,5-8,2-e,d-d,4,9,4,18,b,6-3,8,4,5-6,3-8,3-3,b-11,3,9,4,18,b,6-3,8,4,5-6,3-6,2,3-3,b-11,3,9,4,18,11-3,7-,4,5-8,2-7,3-3,b-11,3,13-2,19,a,2-,8-2,2-3,7,2,9-11,4-b,3b-3,1e-24,3,2-,3,2-,2-5,5,8,4,2,2-,3,e,4-,6,2,7-,b-,3-21,49,23-5,1c-3,9,25,10-,2-2f,23,6,3,8-2,5-5,1b-45,27-9,2a-,2-3,5b-4,45-4,53-5,8,40,2,5-,8,2,5-,28,2,5-,20,2,5-,8,2,5-,8,8,18,20,2,5-,8,28,14-5,1d-22,56-b,277-8,1e-2,52-e,e,8-a,18-8,15-b,e,4,3-b,5e-2,b-15,10,b-5,59-7,2b-555,9d-3,5b-5,17-,7-,27-,7-,9,2,2,2,20-,36,10,f-,7,14-,4,a,54-3,2-6,6-5,9-,1c-10,13-1d,1c-14,3c-,10-6,32-b,240-30,28-18,c-14,a0,115-,3,66-,b-76,5,5-,1d,24,2,5-2,2,8-,35-2,19,f-10,1d-3,311-37f,1b,5a-b,d7-19,d-3,41,57-,68-4,29-3,5f,29-37,2e-2,25-c,2c-2,4e-3,30,78-3,64-,20,19b7-49,51a7-59,48e-2,38-738,2ba5-5b,222f-,3c-94,8-b,6-4,1b,6,2,3,3,6d-20,16e-f,41-,37-7,2e-2,11-f,5-b,18-,b,14,5-3,6,88-,2,bf-2,7-,7-,7-,4-2,8,8-9,8-2ff,20,5-b,1c-b4,27-,27-cbb1,f7-9,28-2,b5-221,56,48,3-,2-,3-,5,d,2,5,3,42,5-,9,8,1d,5,6,2-2,8,153-3,123-3,33-27fd,a6da-5128,21f-5df,3-fffd,3-fffd,3-fffd,3-fffd,3-fffd,3-fffd,3-fffd,3-fffd,3-fffd,3-fffd,3-fffd,3,2-1d,61-ff7d");
// @TODO: Make this relative...
const Table_B_1_flags = "ad,34f,1806,180b,180c,180d,200b,200c,200d,2060,feff".split(",").map((v) => parseInt(v, 16));
@ -91,31 +120,8 @@ const Table_B_2_lut_abs = createTable("b5:3bc,c3:ff,7:73,2:253,5:254,3:256,1:257
const Table_B_2_lut_rel = createTable("179:1,2:1,2:1,5:1,2:1,a:4f,a:1,8:1,2:1,2:1,3:1,5:1,3:1,4:1,2:1,3:1,4:1,8:2,1:1,2:2,1:1,2:2,27:2,195:26,2:25,1:25,1:25,2:40,2:3f,1:3f,33:1,11:-6,1:-9,1ac7:-3a,6d:-8,1:-8,1:-8,1:-8,1:-8,1:-8,1:-8,1:-8,9:-8,1:-8,1:-8,1:-8,1:-8,1:-8,b:-8,1:-8,1:-8,1:-8,1:-8,1:-8,1:-8,1:-8,9:-8,1:-8,1:-8,1:-8,1:-8,1:-8,1:-8,1:-8,9:-8,1:-8,1:-8,1:-8,1:-8,1:-8,c:-8,2:-8,2:-8,2:-8,9:-8,1:-8,1:-8,1:-8,1:-8,1:-8,1:-8,1:-8,49:-8,1:-8,1:-4a,1:-4a,d:-56,1:-56,1:-56,1:-56,d:-8,1:-8,f:-8,1:-8,3:-7");
const Table_B_2_complex = createTable("df:00730073,51:00690307,19:02BC006E,a7:006A030C,18a:002003B9,16:03B903080301,20:03C503080301,1d7:05650582,190f:00680331,1:00740308,1:0077030A,1:0079030A,1:006102BE,b6:03C50313,2:03C503130300,2:03C503130301,2:03C503130342,2a:1F0003B9,1:1F0103B9,1:1F0203B9,1:1F0303B9,1:1F0403B9,1:1F0503B9,1:1F0603B9,1:1F0703B9,1:1F0003B9,1:1F0103B9,1:1F0203B9,1:1F0303B9,1:1F0403B9,1:1F0503B9,1:1F0603B9,1:1F0703B9,1:1F2003B9,1:1F2103B9,1:1F2203B9,1:1F2303B9,1:1F2403B9,1:1F2503B9,1:1F2603B9,1:1F2703B9,1:1F2003B9,1:1F2103B9,1:1F2203B9,1:1F2303B9,1:1F2403B9,1:1F2503B9,1:1F2603B9,1:1F2703B9,1:1F6003B9,1:1F6103B9,1:1F6203B9,1:1F6303B9,1:1F6403B9,1:1F6503B9,1:1F6603B9,1:1F6703B9,1:1F6003B9,1:1F6103B9,1:1F6203B9,1:1F6303B9,1:1F6403B9,1:1F6503B9,1:1F6603B9,1:1F6703B9,3:1F7003B9,1:03B103B9,1:03AC03B9,2:03B10342,1:03B1034203B9,5:03B103B9,6:1F7403B9,1:03B703B9,1:03AE03B9,2:03B70342,1:03B7034203B9,5:03B703B9,6:03B903080300,1:03B903080301,3:03B90342,1:03B903080342,b:03C503080300,1:03C503080301,1:03C10313,2:03C50342,1:03C503080342,b:1F7C03B9,1:03C903B9,1:03CE03B9,2:03C90342,1:03C9034203B9,5:03C903B9,ac:00720073,5b:00B00063,6:00B00066,d:006E006F,a:0073006D,1:00740065006C,1:0074006D,124f:006800700061,2:00610075,2:006F0076,b:00700061,1:006E0061,1:03BC0061,1:006D0061,1:006B0061,1:006B0062,1:006D0062,1:00670062,3:00700066,1:006E0066,1:03BC0066,4:0068007A,1:006B0068007A,1:006D0068007A,1:00670068007A,1:00740068007A,15:00700061,1:006B00700061,1:006D00700061,1:006700700061,8:00700076,1:006E0076,1:03BC0076,1:006D0076,1:006B0076,1:006D0076,1:00700077,1:006E0077,1:03BC0077,1:006D0077,1:006B0077,1:006D0077,1:006B03C9,1:006D03C9,2:00620071,3:00632215006B0067,1:0063006F002E,1:00640062,1:00670079,2:00680070,2:006B006B,1:006B006D,9:00700068,2:00700070006D,1:00700072,2:00730076,1:00770062,c723:00660066,1:00660069,1:0066006C,1:006600660069,1:00660066006C,1:00730074,1:00730074,d:05740576,1:05740565,1:0574056B,1:057E0576,1:0574056D", bytes2);
_tmp = 0;
const Table_C_flags = "70f,f71,18e".split(",").map((v) => {
_tmp += parseInt(v, 16);
return _tmp;
});
_tmp = 0;
const Table_C_ranges = "80-20,2c0,1cc0-f,28-7,37-4,b-5,f86-b,a810-20ff,25d0-1f,229-6,d17a-7,2e8b,10000,10000,10000,10000,10000,10000,10000,10000,10000,10000,10000,10000,22-5f".split(",").map((v) => {
let comps = v.split("-");
if (comps.length === 1) { comps[1] = "1"; }
_tmp += parseInt(comps[0], 16);
return { l: _tmp, h: parseInt(comps[1], 16) }
});
const Table_C_ranges = createRangeTable("80-20,2a0-,39c,32,f71,18e,7f2-f,19-7,30-4,7-5,f81-b,5,a800-20ff,4d1-1f,110,fa-6,d174-7,2e84-,ffff-,ffff-,ffff-,ffff-,ffff-,ffff-,ffff-,ffff-,ffff-,ffff-,ffff-,ffff-,2,1f-5f,ff7f-20001");
function matchMap(value: number, ranges: Array<Ranged>): Ranged {
let lo = 0;
for (let i = 0; i < ranges.length; i++) {
let range = ranges[i];
lo += range.l;
if (value >= lo && value <= lo + range.h && ((value - lo) % (range.d || 1)) === 0) {
if (range.e && range.e.indexOf(value - lo) !== -1) { continue; }
return range;
}
}
return null;
}
function flatten(values: Array<Array<number>>): Array<number> {
return values.reduce((accum, value) => {
@ -124,20 +130,28 @@ function flatten(values: Array<Array<number>>): Array<number> {
}, [ ]);
}
export function _nameprepTableA1(codepoint: number): boolean {
return !!matchMap(codepoint, Table_A_1_ranges);
}
export function _nameprepTableB2(codepoint: number): Array<number> {
let match = matchMap(codepoint, Table_B_2_ranges);
if (match) { return [ codepoint + match.s ]; }
let range = matchMap(codepoint, Table_B_2_ranges);
if (range) { return [ codepoint + range.s ]; }
let codes = Table_B_2_lut_abs[codepoint];
if (codes) { return codes; }
let codes = Table_B_2_lut_abs[codepoint];
if (codes) { return codes; }
let shift = Table_B_2_lut_rel[codepoint];
if (shift) { return [ codepoint + shift[0] ]; }
let shift = Table_B_2_lut_rel[codepoint];
if (shift) { return [ codepoint + shift[0] ]; }
let complex = Table_B_2_complex[codepoint];
if (complex) { return complex; }
let complex = Table_B_2_complex[codepoint];
if (complex) { return complex; }
return null;
return null;
}
export function _nameprepTableC(codepoint: number): boolean {
return !!matchMap(codepoint, Table_C_ranges);
}
export function nameprep(value: string): string {
@ -145,7 +159,7 @@ export function nameprep(value: string): string {
// This allows platforms with incomplete normalize to bypass
// it for very basic names which the built-in toLowerCase
// will certainly handle correctly
if (value.match(/^[a-z0-9-]*$/i)) { return value.toLowerCase(); }
if (value.match(/^[a-z0-9-]*$/i) && value.length <= 59) { return value.toLowerCase(); }
// Get the code points (keeping the current normalization)
let codes = toUtf8CodePoints(value);
@ -163,17 +177,21 @@ export function nameprep(value: string): string {
return [ code ];
}));
// Normalize using fomr KC
// Normalize using form KC
codes = toUtf8CodePoints(_toUtf8String(codes), UnicodeNormalizationForm.NFKC);
// Prohibit C.1.2, C.2.2, C.3, C.4, C.5, C.6, C.7, C.8, C.9
// Prohibit Tables C.1.2, C.2.2, C.3, C.4, C.5, C.6, C.7, C.8, C.9
codes.forEach((code) => {
if (Table_C_flags.indexOf(code) >= 0) { throw new Error("invalid character code"); }
Table_C_ranges.forEach((range) => {
if (code >= range.l && code <= range.l + range.h) {
throw new Error("STRINGPREP_CONTAINS_PROHIBITED");
}
});
if (_nameprepTableC(code)) {
throw new Error("STRINGPREP_CONTAINS_PROHIBITED");
}
});
// Prohibit Unassigned Code Points (Table A.1)
codes.forEach((code) => {
if (_nameprepTableA1(code)) {
throw new Error("STRINGPREP_CONTAINS_UNASSIGNED");
}
});
// IDNA extras
@ -187,6 +205,8 @@ export function nameprep(value: string): string {
// IDNA: 4.2.4
if (name.length > 63) { throw new Error("too long"); }
return name;
}

@ -0,0 +1,46 @@
import json
import re
output = ""
for line in file("test-vectors-00.txt"):
line = line.strip()
if line == "" or line[0:1] == "#":
continue
if line.startswith("Josefsson") or line.startswith("Internet-Draft"):
continue
output += line.replace("\n", "")
Tests = [ ]
def get_byte(v):
if len(v) == 1:
return ord(v)
return int(v[2:4], 16)
def get_string(value):
value = value.strip()
if value[0] == '"' and value[-1] == '"':
return map(get_byte, re.findall("(\\\\x[0-9a-fA-F]{2}|.)", value[1:-1].replace('""', '')))
if value.lower() == "null":
return None
raise Exception("unhandled")
Tests = [ ]
matches = re.findall("({(?:.|\n)*?})", output)
for m in matches:
comps = m[1:-1].split(",")
test = dict(
comment = comps[0].strip()[1:-1],
input = get_string(comps[1]),
output = get_string(comps[2])
)
if len(comps) >= 4:
test["profile"] = get_string(comps[3])
if len(comps) >= 5:
test["flags"] = comps[4].strip()
if len(comps) >= 6:
test["rc"] = comps[5].strip()
Tests.append(test)
print json.dumps(Tests)

@ -149,17 +149,28 @@ for delta in deltas:
mappings.append(data)
debug[data["l"]] = "MAP:" + str(data)
# Create complex table (things that map to more than one byte)
complex = { }
complex_output = [ ];
for (src, dst, reason) in weird:
for word in dst.split(" "):
complex_output.append(int(word, 16))
if len(word) != 4: raise Exception("hmmm")
complex[int(src, 16)] = dst.replace(" ", "")
# Experimenting: We can easily create a LUT for the individual
# components, as there is substantial overlap.
#complex_output = dict((x, True) for x in complex_output).keys()
#complex_output.sort()
#print "COM", complex_output, len(complex_output)
# Sort mappings by lo
mappings.sort(lambda a, b: cmp(a["l"], b["l"]))
debug_keys = debug.keys()
debug_keys.sort()
for d in debug_keys:
print d, debug[d]
#debug_keys = debug.keys()
#debug_keys.sort()
#for d in debug_keys:
# print d, debug[d]
#print mappings

@ -1,3 +1,6 @@
def hexify(v):
return hex(v)[2:]
prohibit = [ ]
table = None
@ -28,42 +31,27 @@ print prohibit
prohibit = list(dict([(p, True) for p in prohibit]).keys())
prohibit.sort()
prohibit_single = [ ]
prohibit_range = [ ]
output = [ dict(lo = prohibit[0], hi = prohibit[0]) ]
last_range_start = None
last = 0
for p in prohibit:
if p - 1 == last:
if last_range_start is None:
last_range_start = last
if len(prohibit_single) > 0 and prohibit_single[-1] == last:
prohibit_single.pop()
for p in prohibit[1:]:
if p - 1 == output[-1]["hi"]:
output[-1]["hi"] = p
else:
if last_range_start is not None:
print "Range", last_range_start, last - last_range_start, hex(last_range_start)
length = last - last_range_start
if length == 1:
length = ""
else:
length = "-" + hex(length)[2:]
prohibit_range.append([ last_range_start, length ])
last_range_start = None
else:
print "Single", p, hex(p)
prohibit_single.append(p)
last = p
output.append(dict(lo = p, hi = p))
print output
last = 0
for i in xrange(0, len(prohibit_single)):
v = prohibit_single[i]
prohibit_single[i] -= last
last = v
print 'const Table_C_lut = "' + ",".join(hex(x)[2:] for x in prohibit_single) + '";'
for r in output:
r["h"] = r["hi"] - r["lo"]
r["l"] = r["lo"] - last
last = r["hi"]
r["range"] = hexify(r["l"])
if r["h"] > 1:
r["range"] += "-" + hexify(r["h"])
elif r["h"] > 0:
r["range"] += "-"
print 'const Table_C_ranges = "' + ",".join(x["range"] for x in output) + '";'
last = 0
for item in prohibit_range:
v = item[0]
item[0] -= last
last = v
print 'const Table_C_ranges = "' + ",".join(("%s%s" % (hex(p[0])[2:], p[1])) for p in prohibit_range) + '";';

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

@ -0,0 +1,395 @@
Network Working Group P. Hoffman
Request for Comments: 3491 IMC & VPNC
Category: Standards Track M. Blanchet
Viagenie
March 2003
Nameprep: A Stringprep Profile for
Internationalized Domain Names (IDN)
Status of this Memo
This document specifies an Internet standards track protocol for the
Internet community, and requests discussion and suggestions for
improvements. Please refer to the current edition of the "Internet
Official Protocol Standards" (STD 1) for the standardization state
and status of this protocol. Distribution of this memo is unlimited.
Copyright Notice
Copyright (C) The Internet Society (2003). All Rights Reserved.
Abstract
This document describes how to prepare internationalized domain name
(IDN) labels in order to increase the likelihood that name input and
name comparison work in ways that make sense for typical users
throughout the world. This profile of the stringprep protocol is
used as part of a suite of on-the-wire protocols for
internationalizing the Domain Name System (DNS).
1. Introduction
This document specifies processing rules that will allow users to
enter internationalized domain names (IDNs) into applications and
have the highest chance of getting the content of the strings
correct. It is a profile of stringprep [STRINGPREP]. These
processing rules are only intended for internationalized domain
names, not for arbitrary text.
This profile defines the following, as required by [STRINGPREP].
- The intended applicability of the profile: internationalized
domain names processed by IDNA.
- The character repertoire that is the input and output to
stringprep: Unicode 3.2, specified in section 2.
Hoffman & Blanchet Standards Track [Page 1]
RFC 3491 IDN Nameprep March 2003
- The mappings used: specified in section 3.
- The Unicode normalization used: specified in section 4.
- The characters that are prohibited as output: specified in section
5.
- Bidirectional character handling: specified in section 6.
1.1 Interaction of protocol parts
Nameprep is used by the IDNA [IDNA] protocol for preparing domain
names; it is not designed for any other purpose. It is explicitly
not designed for processing arbitrary free text and SHOULD NOT be
used for that purpose. Nameprep is a profile of Stringprep
[STRINGPREP]. Implementations of Nameprep MUST fully implement
Stringprep.
Nameprep is used to process domain name labels, not domain names.
IDNA calls nameprep for each label in a domain name, not for the
whole domain name.
1.2 Terminology
The key words "MUST", "MUST NOT", "SHOULD", "SHOULD NOT", and "MAY"
in this document are to be interpreted as described in BCP 14, RFC
2119 [RFC2119].
2. Character Repertoire
This profile uses Unicode 3.2, as defined in [STRINGPREP] Appendix A.
3. Mapping
This profile specifies mapping using the following tables from
[STRINGPREP]:
Table B.1
Table B.2
4. Normalization
This profile specifies using Unicode normalization form KC, as
described in [STRINGPREP].
Hoffman & Blanchet Standards Track [Page 2]
RFC 3491 IDN Nameprep March 2003
5. Prohibited Output
This profile specifies prohibiting using the following tables from
[STRINGPREP]:
Table C.1.2
Table C.2.2
Table C.3
Table C.4
Table C.5
Table C.6
Table C.7
Table C.8
Table C.9
IMPORTANT NOTE: This profile MUST be used with the IDNA protocol.
The IDNA protocol has additional prohibitions that are checked
outside of this profile.
6. Bidirectional characters
This profile specifies checking bidirectional strings as described in
[STRINGPREP] section 6.
7. Unassigned Code Points in Internationalized Domain Names
If the processing in [IDNA] specifies that a list of unassigned code
points be used, the system uses table A.1 from [STRINGPREP] as its
list of unassigned code points.
8. References
8.1 Normative References
[RFC2119] Bradner, S., "Key words for use in RFCs to Indicate
Requirement Levels", BCP 14, RFC 2119, March 1997.
[STRINGPREP] Hoffman, P. and M. Blanchet, "Preparation of
Internationalized Strings ("stringprep")", RFC 3454,
December 2002.
[IDNA] Faltstrom, P., Hoffman, P. and A. Costello,
"Internationalizing Domain Names in Applications
(IDNA)", RFC 3490, March 2003.
Hoffman & Blanchet Standards Track [Page 3]
RFC 3491 IDN Nameprep March 2003
8.2 Informative references
[STD13] Mockapetris, P., "Domain names - concepts and
facilities", STD 13, RFC 1034, and "Domain names -
implementation and specification", STD 13, RFC 1035,
November 1987.
9. Security Considerations
The Unicode and ISO/IEC 10646 repertoires have many characters that
look similar. In many cases, users of security protocols might do
visual matching, such as when comparing the names of trusted third
parties. Because it is impossible to map similar-looking characters
without a great deal of context such as knowing the fonts used,
stringprep does nothing to map similar-looking characters together
nor to prohibit some characters because they look like others.
Security on the Internet partly relies on the DNS. Thus, any change
to the characteristics of the DNS can change the security of much of
the Internet.
Domain names are used by users to connect to Internet servers. The
security of the Internet would be compromised if a user entering a
single internationalized name could be connected to different servers
based on different interpretations of the internationalized domain
name.
Current applications might assume that the characters allowed in
domain names will always be the same as they are in [STD13]. This
document vastly increases the number of characters available in
domain names. Every program that uses "special" characters in
conjunction with domain names may be vulnerable to attack based on
the new characters allowed by this specification.
Hoffman & Blanchet Standards Track [Page 4]
RFC 3491 IDN Nameprep March 2003
10. IANA Considerations
This is a profile of stringprep. It has been registered by the IANA
in the stringprep profile registry
(www.iana.org/assignments/stringprep-profiles).
Name of this profile:
Nameprep
RFC in which the profile is defined:
This document.
Indicator whether or not this is the newest version of the
profile:
This is the first version of Nameprep.
11. Acknowledgements
Many people from the IETF IDN Working Group and the Unicode Technical
Committee contributed ideas that went into this document.
The IDN Nameprep design team made many useful changes to the
document. That team and its advisors include:
Asmus Freytag
Cathy Wissink
Francois Yergeau
James Seng
Marc Blanchet
Mark Davis
Martin Duerst
Patrik Faltstrom
Paul Hoffman
Additional significant improvements were proposed by:
Jonathan Rosenne
Kent Karlsson
Scott Hollenbeck
Dave Crocker
Erik Nordmark
Matitiahu Allouche
Hoffman & Blanchet Standards Track [Page 5]
RFC 3491 IDN Nameprep March 2003
12. Authors' Addresses
Paul Hoffman
Internet Mail Consortium and VPN Consortium
127 Segre Place
Santa Cruz, CA 95060 USA
EMail: paul.hoffman@imc.org and paul.hoffman@vpnc.org
Marc Blanchet
Viagenie inc.
2875 boul. Laurier, bur. 300
Ste-Foy, Quebec, Canada, G1V 2M2
EMail: Marc.Blanchet@viagenie.qc.ca
Hoffman & Blanchet Standards Track [Page 6]
RFC 3491 IDN Nameprep March 2003
13. Full Copyright Statement
Copyright (C) The Internet Society (2003). All Rights Reserved.
This document and translations of it may be copied and furnished to
others, and derivative works that comment on or otherwise explain it
or assist in its implementation may be prepared, copied, published
and distributed, in whole or in part, without restriction of any
kind, provided that the above copyright notice and this paragraph are
included on all such copies and derivative works. However, this
document itself may not be modified in any way, such as by removing
the copyright notice or references to the Internet Society or other
Internet organizations, except as needed for the purpose of
developing Internet standards in which case the procedures for
copyrights defined in the Internet Standards process must be
followed, or as required to translate it into languages other than
English.
The limited permissions granted above are perpetual and will not be
revoked by the Internet Society or its successors or assigns.
This document and the information contained herein is provided on an
"AS IS" basis and THE INTERNET SOCIETY AND THE INTERNET ENGINEERING
TASK FORCE DISCLAIMS ALL WARRANTIES, EXPRESS OR IMPLIED, INCLUDING
BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF THE INFORMATION
HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED WARRANTIES OF
MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.
Acknowledgement
Funding for the RFC Editor function is currently provided by the
Internet Society.
Hoffman & Blanchet Standards Track [Page 7]

File diff suppressed because it is too large Load Diff

@ -0,0 +1,955 @@
Internet Engineering Task Force (IETF) J. Klensin
Request for Comments: 5891 August 2010
Obsoletes: 3490, 3491
Updates: 3492
Category: Standards Track
ISSN: 2070-1721
Internationalized Domain Names in Applications (IDNA): Protocol
Abstract
This document is the revised protocol definition for
Internationalized Domain Names (IDNs). The rationale for changes,
the relationship to the older specification, and important
terminology are provided in other documents. This document specifies
the protocol mechanism, called Internationalized Domain Names in
Applications (IDNA), for registering and looking up IDNs in a way
that does not require changes to the DNS itself. IDNA is only meant
for processing domain names, not free text.
Status of This Memo
This is an Internet Standards Track document.
This document is a product of the Internet Engineering Task Force
(IETF). It represents the consensus of the IETF community. It has
received public review and has been approved for publication by the
Internet Engineering Steering Group (IESG). Further information on
Internet Standards is available in Section 2 of RFC 5741.
Information about the current status of this document, any errata,
and how to provide feedback on it may be obtained at
http://www.rfc-editor.org/info/rfc5891.
Klensin Standards Track [Page 1]
RFC 5891 IDNA2008 Protocol August 2010
Copyright Notice
Copyright (c) 2010 IETF Trust and the persons identified as the
document authors. All rights reserved.
This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents
(http://trustee.ietf.org/license-info) in effect on the date of
publication of this document. Please review these documents
carefully, as they describe your rights and restrictions with respect
to this document. Code Components extracted from this document must
include Simplified BSD License text as described in Section 4.e of
the Trust Legal Provisions and are provided without warranty as
described in the Simplified BSD License.
This document may contain material from IETF Documents or IETF
Contributions published or made publicly available before November
10, 2008. The person(s) controlling the copyright in some of this
material may not have granted the IETF Trust the right to allow
modifications of such material outside the IETF Standards Process.
Without obtaining an adequate license from the person(s) controlling
the copyright in such materials, this document may not be modified
outside the IETF Standards Process, and derivative works of it may
not be created outside the IETF Standards Process, except to format
it for publication as an RFC or to translate it into languages other
than English.
Klensin Standards Track [Page 2]
RFC 5891 IDNA2008 Protocol August 2010
Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . 4
2. Terminology . . . . . . . . . . . . . . . . . . . . . . . . . 4
3. Requirements and Applicability . . . . . . . . . . . . . . . . 5
3.1. Requirements . . . . . . . . . . . . . . . . . . . . . . . 5
3.2. Applicability . . . . . . . . . . . . . . . . . . . . . . 5
3.2.1. DNS Resource Records . . . . . . . . . . . . . . . . . 6
3.2.2. Non-Domain-Name Data Types Stored in the DNS . . . . . 6
4. Registration Protocol . . . . . . . . . . . . . . . . . . . . 6
4.1. Input to IDNA Registration . . . . . . . . . . . . . . . . 7
4.2. Permitted Character and Label Validation . . . . . . . . . 7
4.2.1. Input Format . . . . . . . . . . . . . . . . . . . . . 7
4.2.2. Rejection of Characters That Are Not Permitted . . . . 8
4.2.3. Label Validation . . . . . . . . . . . . . . . . . . . 8
4.2.4. Registration Validation Requirements . . . . . . . . . 9
4.3. Registry Restrictions . . . . . . . . . . . . . . . . . . 9
4.4. Punycode Conversion . . . . . . . . . . . . . . . . . . . 9
4.5. Insertion in the Zone . . . . . . . . . . . . . . . . . . 10
5. Domain Name Lookup Protocol . . . . . . . . . . . . . . . . . 10
5.1. Label String Input . . . . . . . . . . . . . . . . . . . . 10
5.2. Conversion to Unicode . . . . . . . . . . . . . . . . . . 10
5.3. A-label Input . . . . . . . . . . . . . . . . . . . . . . 10
5.4. Validation and Character List Testing . . . . . . . . . . 11
5.5. Punycode Conversion . . . . . . . . . . . . . . . . . . . 13
5.6. DNS Name Resolution . . . . . . . . . . . . . . . . . . . 13
6. Security Considerations . . . . . . . . . . . . . . . . . . . 13
7. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 13
8. Contributors . . . . . . . . . . . . . . . . . . . . . . . . . 13
9. Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . 14
10. References . . . . . . . . . . . . . . . . . . . . . . . . . . 14
10.1. Normative References . . . . . . . . . . . . . . . . . . . 14
10.2. Informative References . . . . . . . . . . . . . . . . . . 15
Appendix A. Summary of Major Changes from IDNA2003 . . . . . . . 17
Klensin Standards Track [Page 3]
RFC 5891 IDNA2008 Protocol August 2010
1. Introduction
This document supplies the protocol definition for Internationalized
Domain Names in Applications (IDNA), with the version specified here
known as IDNA2008. Essential definitions and terminology for
understanding this document and a road map of the collection of
documents that make up IDNA2008 appear in a separate Definitions
document [RFC5890]. Appendix A discusses the relationship between
this specification and the earlier version of IDNA (referred to here
as "IDNA2003"). The rationale for these changes, along with
considerable explanatory material and advice to zone administrators
who support IDNs, is provided in another document, known informally
in this series as the "Rationale document" [RFC5894].
IDNA works by allowing applications to use certain ASCII [ASCII]
string labels (beginning with a special prefix) to represent
non-ASCII name labels. Lower-layer protocols need not be aware of
this; therefore, IDNA does not change any infrastructure. In
particular, IDNA does not depend on any changes to DNS servers,
resolvers, or DNS protocol elements, because the ASCII name service
provided by the existing DNS can be used for IDNA.
IDNA applies only to a specific subset of DNS labels. The base DNS
standards [RFC1034] [RFC1035] and their various updates specify how
to combine labels into fully-qualified domain names and parse labels
out of those names.
This document describes two separate protocols, one for IDN
registration (Section 4) and one for IDN lookup (Section 5). These
two protocols share some terminology, reference data, and operations.
2. Terminology
As mentioned above, terminology used as part of the definition of
IDNA appears in the Definitions document [RFC5890]. It is worth
noting that some of this terminology overlaps with, and is consistent
with, that used in Unicode or other character set standards and the
DNS. Readers of this document are assumed to be familiar with the
associated Definitions document and with the DNS-specific terminology
in RFC 1034 [RFC1034].
The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
"SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
document are to be interpreted as described in BCP 14, RFC 2119
[RFC2119].
Klensin Standards Track [Page 4]
RFC 5891 IDNA2008 Protocol August 2010
3. Requirements and Applicability
3.1. Requirements
IDNA makes the following requirements:
1. Whenever a domain name is put into a domain name slot that is not
IDNA-aware (see Section 2.3.2.6 of the Definitions document
[RFC5890]), it MUST contain only ASCII characters (i.e., its
labels must be either A-labels or NR-LDH labels), unless the DNS
application is not subject to historical recommendations for
"hostname"-style names (see RFC 1034 [RFC1034] and
Section 3.2.1).
2. Labels MUST be compared using equivalent forms: either both
A-label forms or both U-label forms. Because A-labels and
U-labels can be transformed into each other without loss of
information, these comparisons are equivalent (however, in
practice, comparison of U-labels requires first verifying that
they actually are U-labels and not just Unicode strings). A pair
of A-labels MUST be compared as case-insensitive ASCII (as with
all comparisons of ASCII DNS labels). U-labels MUST be compared
as-is, without case folding or other intermediate steps. While
it is not necessary to validate labels in order to compare them,
successful comparison does not imply validity. In many cases,
not limited to comparison, validation may be important for other
reasons and SHOULD be performed.
3. Labels being registered MUST conform to the requirements of
Section 4. Labels being looked up and the lookup process MUST
conform to the requirements of Section 5.
3.2. Applicability
IDNA applies to all domain names in all domain name slots in
protocols except where it is explicitly excluded. It does not apply
to domain name slots that do not use the LDH syntax rules as
described in the Definitions document [RFC5890].
Because it uses the DNS, IDNA applies to many protocols that were
specified before it was designed. IDNs occupying domain name slots
in those older protocols MUST be in A-label form until and unless
those protocols and their implementations are explicitly upgraded to
be aware of IDNs and to accept the U-label form. IDNs actually
appearing in DNS queries or responses MUST be A-labels.
Klensin Standards Track [Page 5]
RFC 5891 IDNA2008 Protocol August 2010
IDNA-aware protocols and implementations MAY accept U-labels,
A-labels, or both as those particular protocols specify. IDNA is not
defined for extended label types (see RFC 2671 [RFC2671], Section 3).
3.2.1. DNS Resource Records
IDNA applies only to domain names in the NAME and RDATA fields of DNS
resource records whose CLASS is IN. See the DNS specification
[RFC1035] for precise definitions of these terms.
The application of IDNA to DNS resource records depends entirely on
the CLASS of the record, and not on the TYPE except as noted below.
This will remain true, even as new TYPEs are defined, unless a new
TYPE defines TYPE-specific rules. Special naming conventions for SRV
records (and "underscore labels" more generally) are incompatible
with IDNA coding as discussed in the Definitions document [RFC5890],
especially Section 2.3.2.3. Of course, underscore labels may be part
of a domain that uses IDN labels at higher levels in the tree.
3.2.2. Non-Domain-Name Data Types Stored in the DNS
Although IDNA enables the representation of non-ASCII characters in
domain names, that does not imply that IDNA enables the
representation of non-ASCII characters in other data types that are
stored in domain names, specifically in the RDATA field for types
that have structured RDATA format. For example, an email address
local part is stored in a domain name in the RNAME field as part of
the RDATA of an SOA record (e.g., hostmaster@example.com would be
represented as hostmaster.example.com). IDNA does not update the
existing email standards, which allow only ASCII characters in local
parts. Even though work is in progress to define
internationalization for email addresses [RFC4952], changes to the
email address part of the SOA RDATA would require action in, or
updates to, other standards, specifically those that specify the
format of the SOA RR.
4. Registration Protocol
This section defines the model for registering an IDN. The model is
implementation independent; any sequence of steps that produces
exactly the same result for all labels is considered a valid
implementation.
Note that, while the registration (this section) and lookup protocols
(Section 5) are very similar in most respects, they are not
identical, and implementers should carefully follow the steps
described in this specification.
Klensin Standards Track [Page 6]
RFC 5891 IDNA2008 Protocol August 2010
4.1. Input to IDNA Registration
Registration processes, especially processing by entities (often
called "registrars") who deal with registrants before the request
actually reaches the zone manager ("registry") are outside the scope
of this definition and may differ significantly depending on local
needs. By the time a string enters the IDNA registration process as
described in this specification, it MUST be in Unicode and in
Normalization Form C (NFC [Unicode-UAX15]). Entities responsible for
zone files ("registries") MUST accept only the exact string for which
registration is requested, free of any mappings or local adjustments.
They MAY accept that input in any of three forms:
1. As a pair of A-label and U-label.
2. As an A-label only.
3. As a U-label only.
The first two of these forms are RECOMMENDED because the use of
A-labels avoids any possibility of ambiguity. The first is normally
preferred over the second because it permits further verification of
user intent (see Section 4.2.1).
4.2. Permitted Character and Label Validation
4.2.1. Input Format
If both the U-label and A-label forms are available, the registry
MUST ensure that the A-label form is in lowercase, perform a
conversion to a U-label, perform the steps and tests described below
on that U-label, and then verify that the A-label produced by the
step in Section 4.4 matches the one provided as input. In addition,
the U-label that was provided as input and the one obtained by
conversion of the A-label MUST match exactly. If, for some reason,
these tests fail, the registration MUST be rejected.
If only an A-label was provided and the conversion to a U-label is
not performed, the registry MUST still verify that the A-label is
superficially valid, i.e., that it does not violate any of the rules
of Punycode encoding [RFC3492] such as the prohibition on trailing
hyphen-minus, the requirement that all characters be ASCII, and so
on. Strings that appear to be A-labels (e.g., they start with
"xn--") and strings that are supplied to the registry in a context
reserved for A-labels (such as a field in a form to be filled out),
but that are not valid A-labels as described in this paragraph, MUST
NOT be placed in DNS zones that support IDNA.
Klensin Standards Track [Page 7]
RFC 5891 IDNA2008 Protocol August 2010
If only an A-label is provided, the conversion to a U-label is not
performed, but the superficial tests described in the previous
paragraph are performed, registration procedures MAY, and usually
will, bypass the tests and actions in the balance of Section 4.2 and
in Sections 4.3 and 4.4.
4.2.2. Rejection of Characters That Are Not Permitted
The candidate Unicode string MUST NOT contain characters that appear
in the "DISALLOWED" and "UNASSIGNED" lists specified in the Tables
document [RFC5892].
4.2.3. Label Validation
The proposed label (in the form of a Unicode string, i.e., a string
that at least superficially appears to be a U-label) is then examined
using tests that require examination of more than one character.
Character order is considered to be the on-the-wire order. That
order may not be the same as the display order.
4.2.3.1. Hyphen Restrictions
The Unicode string MUST NOT contain "--" (two consecutive hyphens) in
the third and fourth character positions and MUST NOT start or end
with a "-" (hyphen).
4.2.3.2. Leading Combining Marks
The Unicode string MUST NOT begin with a combining mark or combining
character (see The Unicode Standard, Section 2.11 [Unicode] for an
exact definition).
4.2.3.3. Contextual Rules
The Unicode string MUST NOT contain any characters whose validity is
context-dependent, unless the validity is positively confirmed by a
contextual rule. To check this, each code point identified as
CONTEXTJ or CONTEXTO in the Tables document [RFC5892] MUST have a
non-null rule. If such a code point is missing a rule, the label is
invalid. If the rule exists but the result of applying the rule is
negative or inconclusive, the proposed label is invalid.
4.2.3.4. Labels Containing Characters Written Right to Left
If the proposed label contains any characters from scripts that are
written from right to left, it MUST meet the Bidi criteria [RFC5893].
Klensin Standards Track [Page 8]
RFC 5891 IDNA2008 Protocol August 2010
4.2.4. Registration Validation Requirements
Strings that contain at least one non-ASCII character, have been
produced by the steps above, whose contents pass all of the tests in
Section 4.2.3, and are 63 or fewer characters long in
ASCII-compatible encoding (ACE) form (see Section 4.4), are U-labels.
To summarize, tests are made in Section 4.2 for invalid characters,
invalid combinations of characters, for labels that are invalid even
if the characters they contain are valid individually, and for labels
that do not conform to the restrictions for strings containing
right-to-left characters.
4.3. Registry Restrictions
In addition to the rules and tests above, there are many reasons why
a registry could reject a label. Registries at all levels of the
DNS, not just the top level, are expected to establish policies about
label registrations. Policies are likely to be informed by the local
languages and the scripts that are used to write them and may depend
on many factors including what characters are in the label (for
example, a label may be rejected based on other labels already
registered). See the Rationale document [RFC5894], Section 3.2, for
further discussion and recommendations about registry policies.
The string produced by the steps in Section 4.2 is checked and
processed as appropriate to local registry restrictions. Application
of those registry restrictions may result in the rejection of some
labels or the application of special restrictions to others.
4.4. Punycode Conversion
The resulting U-label is converted to an A-label (defined in Section
2.3.2.1 of the Definitions document [RFC5890]). The A-label is the
encoding of the U-label according to the Punycode algorithm [RFC3492]
with the ACE prefix "xn--" added at the beginning of the string. The
resulting string must, of course, conform to the length limits
imposed by the DNS. This document does not update or alter the
Punycode algorithm specified in RFC 3492 in any way. RFC 3492 does
make a non-normative reference to the information about the value and
construction of the ACE prefix that appears in RFC 3490 or Nameprep
[RFC3491]. For consistency and reader convenience, IDNA2008
effectively updates that reference to point to this document. That
change does not alter the prefix itself. The prefix, "xn--", is the
same in both sets of documents.
Klensin Standards Track [Page 9]
RFC 5891 IDNA2008 Protocol August 2010
With the exception of the maximum string length test on Punycode
output, the failure conditions identified in the Punycode encoding
procedure cannot occur if the input is a U-label as determined by the
steps in Sections 4.1 through 4.3 above.
4.5. Insertion in the Zone
The label is registered in the DNS by inserting the A-label into a
zone.
5. Domain Name Lookup Protocol
Lookup is different from registration and different tests are applied
on the client. Although some validity checks are necessary to avoid
serious problems with the protocol, the lookup-side tests are more
permissive and rely on the assumption that names that are present in
the DNS are valid. That assumption is, however, a weak one because
the presence of wildcards in the DNS might cause a string that is not
actually registered in the DNS to be successfully looked up.
5.1. Label String Input
The user supplies a string in the local character set, for example,
by typing it, clicking on it, or copying and pasting it from a
resource identifier, e.g., a Uniform Resource Identifier (URI)
[RFC3986] or an Internationalized Resource Identifier (IRI)
[RFC3987], from which the domain name is extracted. Alternately,
some process not directly involving the user may read the string from
a file or obtain it in some other way. Processing in this step and
the one specified in Section 5.2 are local matters, to be
accomplished prior to actual invocation of IDNA.
5.2. Conversion to Unicode
The string is converted from the local character set into Unicode, if
it is not already in Unicode. Depending on local needs, this
conversion may involve mapping some characters into other characters
as well as coding conversions. Those issues are discussed in the
mapping-related sections (Sections 4.2, 4.4, 6, and 7.3) of the
Rationale document [RFC5894] and in the separate Mapping document
[IDNA2008-Mapping]. The result MUST be a Unicode string in NFC form.
5.3. A-label Input
If the input to this procedure appears to be an A-label (i.e., it
starts in "xn--", interpreted case-insensitively), the lookup
application MAY attempt to convert it to a U-label, first ensuring
that the A-label is entirely in lowercase (converting it to lowercase
Klensin Standards Track [Page 10]
RFC 5891 IDNA2008 Protocol August 2010
if necessary), and apply the tests of Section 5.4 and the conversion
of Section 5.5 to that form. If the label is converted to Unicode
(i.e., to U-label form) using the Punycode decoding algorithm, then
the processing specified in those two sections MUST be performed, and
the label MUST be rejected if the resulting label is not identical to
the original. See Section 8.1 of the Rationale document [RFC5894]
for additional discussion on this topic.
Conversion from the A-label and testing that the result is a U-label
SHOULD be performed if the domain name will later be presented to the
user in native character form (this requires that the lookup
application be IDNA-aware). If those steps are not performed, the
lookup process SHOULD at least test to determine that the string is
actually an A-label, examining it for the invalid formats specified
in the Punycode decoding specification. Applications that are not
IDNA-aware will obviously omit that testing; others MAY treat the
string as opaque to avoid the additional processing at the expense of
providing less protection and information to users.
5.4. Validation and Character List Testing
As with the registration procedure described in Section 4, the
Unicode string is checked to verify that all characters that appear
in it are valid as input to IDNA lookup processing. As discussed
above and in the Rationale document [RFC5894], the lookup check is
more liberal than the registration one. Labels that have not been
fully evaluated for conformance to the applicable rules are referred
to as "putative" labels as discussed in Section 2.3.2.1 of the
Definitions document [RFC5890]. Putative U-labels with any of the
following characteristics MUST be rejected prior to DNS lookup:
o Labels that are not in NFC [Unicode-UAX15].
o Labels containing "--" (two consecutive hyphens) in the third and
fourth character positions.
o Labels whose first character is a combining mark (see The Unicode
Standard, Section 2.11 [Unicode]).
o Labels containing prohibited code points, i.e., those that are
assigned to the "DISALLOWED" category of the Tables document
[RFC5892].
o Labels containing code points that are identified in the Tables
document as "CONTEXTJ", i.e., requiring exceptional contextual
rule processing on lookup, but that do not conform to those rules.
Note that this implies that a rule must be defined, not null: a
Klensin Standards Track [Page 11]
RFC 5891 IDNA2008 Protocol August 2010
character that requires a contextual rule but for which the rule
is null is treated in this step as having failed to conform to the
rule.
o Labels containing code points that are identified in the Tables
document as "CONTEXTO", but for which no such rule appears in the
table of rules. Applications resolving DNS names or carrying out
equivalent operations are not required to test contextual rules
for "CONTEXTO" characters, only to verify that a rule is defined
(although they MAY make such tests to provide better protection or
give better information to the user).
o Labels containing code points that are unassigned in the version
of Unicode being used by the application, i.e., in the UNASSIGNED
category of the Tables document.
This requirement means that the application must use a list of
unassigned characters that is matched to the version of Unicode
that is being used for the other requirements in this section. It
is not required that the application know which version of Unicode
is being used; that information might be part of the operating
environment in which the application is running.
In addition, the application SHOULD apply the following test.
o Verification that the string is compliant with the requirements
for right-to-left characters specified in the Bidi document
[RFC5893].
This test may be omitted in special circumstances, such as when the
lookup application knows that the conditions are enforced elsewhere,
because an attempt to look up and resolve such strings will almost
certainly lead to a DNS lookup failure except when wildcards are
present in the zone. However, applying the test is likely to give
much better information about the reason for a lookup failure --
information that may be usefully passed to the user when that is
feasible -- than DNS resolution failure information alone.
For all other strings, the lookup application MUST rely on the
presence or absence of labels in the DNS to determine the validity of
those labels and the validity of the characters they contain. If
they are registered, they are presumed to be valid; if they are not,
their possible validity is not relevant. While a lookup application
may reasonably issue warnings about strings it believes may be
problematic, applications that decline to process a string that
conforms to the rules above (i.e., does not look it up in the DNS)
are not in conformance with this protocol.
Klensin Standards Track [Page 12]
RFC 5891 IDNA2008 Protocol August 2010
5.5. Punycode Conversion
The string that has now been validated for lookup is converted to ACE
form by applying the Punycode algorithm to the string and then adding
the ACE prefix ("xn--").
5.6. DNS Name Resolution
The A-label resulting from the conversion in Section 5.5 or supplied
directly (see Section 5.3) is combined with other labels as needed to
form a fully-qualified domain name that is then looked up in the DNS,
using normal DNS resolver procedures. The lookup can obviously
either succeed (returning information) or fail.
6. Security Considerations
Security Considerations for this version of IDNA are described in the
Definitions document [RFC5890], except for the special issues
associated with right-to-left scripts and characters. The latter are
discussed in the Bidi document [RFC5893].
In order to avoid intentional or accidental attacks from labels that
might be confused with others, special problems in rendering, and so
on, the IDNA model requires that registries exercise care and
thoughtfulness about what labels they choose to permit. That issue
is discussed in Section 4.3 of this document which, in turn, points
to a somewhat more extensive discussion in the Rationale document
[RFC5894].
7. IANA Considerations
IANA actions for this version of IDNA are specified in the Tables
document [RFC5892] and discussed informally in the Rationale document
[RFC5894]. The components of IDNA described in this document do not
require any IANA actions.
8. Contributors
While the listed editor held the pen, the original versions of this
document represent the joint work and conclusions of an ad hoc design
team consisting of the editor and, in alphabetic order, Harald
Alvestrand, Tina Dam, Patrik Faltstrom, and Cary Karp. This document
draws significantly on the original version of IDNA [RFC3490] both
conceptually and for specific text. This second-generation version
would not have been possible without the work that went into that
first version and especially the contributions of its authors Patrik
Faltstrom, Paul Hoffman, and Adam Costello. While Faltstrom was
Klensin Standards Track [Page 13]
RFC 5891 IDNA2008 Protocol August 2010
actively involved in the creation of this version, Hoffman and
Costello were not and should not be held responsible for any errors
or omissions.
9. Acknowledgments
This revision to IDNA would have been impossible without the
accumulated experience since RFC 3490 was published and resulting
comments and complaints of many people in the IETF, ICANN, and other
communities (too many people to list here). Nor would it have been
possible without RFC 3490 itself and the efforts of the Working Group
that defined it. Those people whose contributions are acknowledged
in RFC 3490, RFC 4690 [RFC4690], and the Rationale document [RFC5894]
were particularly important.
Specific textual changes were incorporated into this document after
suggestions from the other contributors, Stephane Bortzmeyer, Vint
Cerf, Lisa Dusseault, Paul Hoffman, Kent Karlsson, James Mitchell,
Erik van der Poel, Marcos Sanz, Andrew Sullivan, Wil Tan, Ken
Whistler, Chris Wright, and other WG participants and reviewers
including Martin Duerst, James Mitchell, Subramanian Moonesamy, Peter
Saint-Andre, Margaret Wasserman, and Dan Winship who caught specific
errors and recommended corrections. Special thanks are due to Paul
Hoffman for permission to extract material to form the basis for
Appendix A from a draft document that he prepared.
10. References
10.1. Normative References
[RFC1034] Mockapetris, P., "Domain names - concepts and
facilities", STD 13, RFC 1034, November 1987.
[RFC1035] Mockapetris, P., "Domain names - implementation and
specification", STD 13, RFC 1035, November 1987.
[RFC2119] Bradner, S., "Key words for use in RFCs to Indicate
Requirement Levels", BCP 14, RFC 2119, March 1997.
[RFC3492] Costello, A., "Punycode: A Bootstring encoding of
Unicode for Internationalized Domain Names in
Applications (IDNA)", RFC 3492, March 2003.
[RFC5890] Klensin, J., "Internationalized Domain Names for
Applications (IDNA): Definitions and Document
Framework", RFC 5890, August 2010.
Klensin Standards Track [Page 14]
RFC 5891 IDNA2008 Protocol August 2010
[RFC5892] Faltstrom, P., Ed., "The Unicode Code Points and
Internationalized Domain Names for Applications (IDNA)",
RFC 5892, August 2010.
[RFC5893] Alvestrand, H., Ed. and C. Karp, "Right-to-Left Scripts
for Internationalized Domain Names for Applications
(IDNA)", RFC 5893, August 2010.
[Unicode-UAX15]
The Unicode Consortium, "Unicode Standard Annex #15:
Unicode Normalization Forms", September 2009,
<http://www.unicode.org/reports/tr15/>.
10.2. Informative References
[ASCII] American National Standards Institute (formerly United
States of America Standards Institute), "USA Code for
Information Interchange", ANSI X3.4-1968, 1968. ANSI
X3.4-1968 has been replaced by newer versions with
slight modifications, but the 1968 version remains
definitive for the Internet.
[IDNA2008-Mapping]
Resnick, P. and P. Hoffman, "Mapping Characters in
Internationalized Domain Names for Applications (IDNA)",
Work in Progress, April 2010.
[RFC2671] Vixie, P., "Extension Mechanisms for DNS (EDNS0)",
RFC 2671, August 1999.
[RFC3490] Faltstrom, P., Hoffman, P., and A. Costello,
"Internationalizing Domain Names in Applications
(IDNA)", RFC 3490, March 2003.
[RFC3491] Hoffman, P. and M. Blanchet, "Nameprep: A Stringprep
Profile for Internationalized Domain Names (IDN)",
RFC 3491, March 2003.
[RFC3986] Berners-Lee, T., Fielding, R., and L. Masinter, "Uniform
Resource Identifier (URI): Generic Syntax", STD 66,
RFC 3986, January 2005.
[RFC3987] Duerst, M. and M. Suignard, "Internationalized Resource
Identifiers (IRIs)", RFC 3987, January 2005.
[RFC4690] Klensin, J., Faltstrom, P., Karp, C., and IAB, "Review
and Recommendations for Internationalized Domain Names
(IDNs)", RFC 4690, September 2006.
Klensin Standards Track [Page 15]
RFC 5891 IDNA2008 Protocol August 2010
[RFC4952] Klensin, J. and Y. Ko, "Overview and Framework for
Internationalized Email", RFC 4952, July 2007.
[RFC5894] Klensin, J., "Internationalized Domain Names for
Applications (IDNA): Background, Explanation, and
Rationale", RFC 5894, August 2010.
[Unicode] The Unicode Consortium, "The Unicode Standard, Version
5.0", 2007. Boston, MA, USA: Addison-Wesley. ISBN
0-321-48091-0. This printed reference has now been
updated online to reflect additional code points. For
code points, the reference at the time this document was
published is to Unicode 5.2.
Klensin Standards Track [Page 16]
RFC 5891 IDNA2008 Protocol August 2010
Appendix A. Summary of Major Changes from IDNA2003
1. Update base character set from Unicode 3.2 to Unicode version
agnostic.
2. Separate the definitions for the "registration" and "lookup"
activities.
3. Disallow symbol and punctuation characters except where special
exceptions are necessary.
4. Remove the mapping and normalization steps from the protocol and
have them, instead, done by the applications themselves,
possibly in a local fashion, before invoking the protocol.
5. Change the way that the protocol specifies which characters are
allowed in labels from "humans decide what the table of code
points contains" to "decision about code points are based on
Unicode properties plus a small exclusion list created by
humans".
6. Introduce the new concept of characters that can be used only in
specific contexts.
7. Allow typical words and names in languages such as Dhivehi and
Yiddish to be expressed.
8. Make bidirectional domain names (delimited strings of labels,
not just labels standing on their own) display in a less
surprising fashion, whether they appear in obvious domain name
contexts or as part of running text in paragraphs.
9. Remove the dot separator from the mandatory part of the
protocol.
10. Make some currently valid labels that are not actually IDNA
labels invalid.
Author's Address
John C Klensin
1770 Massachusetts Ave, Ste 322
Cambridge, MA 02140
USA
Phone: +1 617 245 1457
EMail: john+ietf@jck.com
Klensin Standards Track [Page 17]

@ -0,0 +1,269 @@
# struct stringprep
# {
# char *comment;
# char *in;
# char *out;
# char *profile;
# int flags;
# int rc;
# }
{
"Map to nothing",
"foo\xC2\xAD\xCD\x8F\xE1\xA0\x86\xE1\xA0\x8B"
"bar""\xE2\x80\x8B\xE2\x81\xA0""baz\xEF\xB8\x80\xEF\xB8\x88"
"\xEF\xB8\x8F\xEF\xBB\xBF", "foobarbaz"
},
{
"Case folding ASCII U+0043 U+0041 U+0046 U+0045",
"CAFE", "cafe"
Josefsson Expires August 2, 2003 [Page 31]
Internet-Draft Nameprep and IDNA Test Vectors February 2003
},
{
"Case folding 8bit U+00DF (german sharp s)",
# There is a bug here: RicMoo
# VV
# "\xC3\xDF", "ss"
"\xC3\x9f", "ss"
},
{
"Case folding U+0130 (turkish capital I with dot)",
"\xC4\xB0", "i\xcc\x87"
},
{
"Case folding multibyte U+0143 U+037A",
"\xC5\x83\xCD\xBA", "\xC5\x84 \xCE\xB9"
},
{
"Case folding U+2121 U+33C6 U+1D7BB",
"\xE2\x84\xA1\xE3\x8F\x86\xF0\x9D\x9E\xBB",
"telc\xE2\x88\x95""kg\xCF\x83"
},
{
"Normalization of U+006a U+030c U+00A0 U+00AA",
"\x6A\xCC\x8C\xC2\xA0\xC2\xAA", "\xC7\xB0 a"
},
{
"Case folding U+1FB7 and normalization",
"\xE1\xBE\xB7", "\xE1\xBE\xB6\xCE\xB9"
},
{
"Self-reverting case folding U+01F0 and normalization",
# There is a bug here: RicMoo
# VV
# "\xC7\xF0", "\xC7\xB0"
"\xC7\xb0", "\xC7\xB0"
},
{
"Self-reverting case folding U+0390 and normalization",
"\xCE\x90", "\xCE\x90"
},
{
"Self-reverting case folding U+03B0 and normalization",
"\xCE\xB0", "\xCE\xB0"
},
{
"Self-reverting case folding U+1E96 and normalization",
"\xE1\xBA\x96", "\xE1\xBA\x96"
},
{
"Self-reverting case folding U+1F56 and normalization",
"\xE1\xBD\x96", "\xE1\xBD\x96"
},
{
"ASCII space character U+0020",
Josefsson Expires August 2, 2003 [Page 32]
Internet-Draft Nameprep and IDNA Test Vectors February 2003
"\x20", "\x20"
},
{
"Non-ASCII 8bit space character U+00A0",
"\xC2\xA0", "\x20"
},
{
"Non-ASCII multibyte space character U+1680",
"\xE1\x9A\x80", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Non-ASCII multibyte space character U+2000",
"\xE2\x80\x80", "\x20"
},
{
"Zero Width Space U+200b",
"\xE2\x80\x8b", ""
},
{
"Non-ASCII multibyte space character U+3000",
"\xE3\x80\x80", "\x20"
},
{
"ASCII control characters U+0010 U+007F",
"\x10\x7F", "\x10\x7F"
},
{
"Non-ASCII 8bit control character U+0085",
"\xC2\x85", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Non-ASCII multibyte control character U+180E",
"\xE1\xA0\x8E", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Zero Width No-Break Space U+FEFF",
"\xEF\xBB\xBF", ""
},
{
"Non-ASCII control character U+1D175",
"\xF0\x9D\x85\xB5", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Plane 0 private use character U+F123",
Josefsson Expires August 2, 2003 [Page 33]
Internet-Draft Nameprep and IDNA Test Vectors February 2003
"\xEF\x84\xA3", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Plane 15 private use character U+F1234",
"\xF3\xB1\x88\xB4", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Plane 16 private use character U+10F234",
"\xF4\x8F\x88\xB4", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Non-character code point U+8FFFE",
"\xF2\x8F\xBF\xBE", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Non-character code point U+10FFFF",
"\xF4\x8F\xBF\xBF", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Surrogate code U+DF42",
"\xED\xBD\x82", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Non-plain text character U+FFFD",
"\xEF\xBF\xBD", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Ideographic description character U+2FF5",
"\xE2\xBF\xB5", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Display property character U+0341",
"\xCD\x81", "\xCC\x81"
},
{
"Left-to-right mark U+200E",
"\xE2\x80\x8E", "\xCC\x81", "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
Josefsson Expires August 2, 2003 [Page 34]
Internet-Draft Nameprep and IDNA Test Vectors February 2003
"Deprecated U+202A",
"\xE2\x80\xAA", "\xCC\x81", "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Language tagging character U+E0001",
"\xF3\xA0\x80\x81", "\xCC\x81", "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Language tagging character U+E0042",
"\xF3\xA0\x81\x82", NULL, "Nameprep", 0,
STRINGPREP_CONTAINS_PROHIBITED
},
{
"Bidi: RandALCat character U+05BE and LCat characters",
"foo\xD6\xBE""bar", NULL, "Nameprep", 0,
STRINGPREP_BIDI_BOTH_L_AND_RAL
},
{
"Bidi: RandALCat character U+FD50 and LCat characters",
"foo\xEF\xB5\x90""bar", NULL, "Nameprep", 0,
STRINGPREP_BIDI_BOTH_L_AND_RAL
},
{
"Bidi: RandALCat character U+FB38 and LCat characters",
"foo\xEF\xB9\xB6""bar", "foo \xd9\x8e""bar"
},
{ "Bidi: RandALCat without trailing RandALCat U+0627 U+0031",
"\xD8\xA7\x31", NULL, "Nameprep", 0,
STRINGPREP_BIDI_LEADTRAIL_NOT_RAL}
,
{
"Bidi: RandALCat character U+0627 U+0031 U+0628",
"\xD8\xA7\x31\xD8\xA8", "\xD8\xA7\x31\xD8\xA8"
},
{
"Unassigned code point U+E0002",
"\xF3\xA0\x80\x82", NULL, "Nameprep", STRINGPREP_NO_UNASSIGNED,
STRINGPREP_CONTAINS_UNASSIGNED
},
{
"Larger test (shrinking)",
# There is a bug here: RicMoo
# VV
# "X\xC2\xAD\xC3\xDF\xC4\xB0\xE2\x84\xA1\x6a\xcc\x8c\xc2\xa0\xc2"
"X\xC2\xAD\xC3\x9F\xC4\xB0\xE2\x84\xA1\x6a\xcc\x8c\xc2\xa0\xc2"
"\xaa\xce\xb0\xe2\x80\x80", "xssi\xcc\x87""tel\xc7\xb0 a\xce\xb0 ",
"Nameprep"
},
{
Josefsson Expires August 2, 2003 [Page 35]
Internet-Draft Nameprep and IDNA Test Vectors February 2003
"Larger test (expanding)",
# There is a bug here: RicMoo
# VV
# "X\xC3\xDF\xe3\x8c\x96\xC4\xB0\xE2\x84\xA1\xE2\x92\x9F\xE3\x8c\x80",
"X\xc3\x9F\xe3\x8c\x96\xC4\xB0\xE2\x84\xA1\xE2\x92\x9F\xE3\x8c\x80",
"xss\xe3\x82\xad\xe3\x83\xad\xe3\x83\xa1\xe3\x83\xbc\xe3\x83\x88"
"\xe3\x83\xab""i\xcc\x87""tel\x28""d\x29\xe3\x82\xa2\xe3\x83\x91"
"\xe3\x83\xbc\xe3\x83\x88"
},