gfwleak/zhangyang-zerotierone
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

RPM build fix (reverted CI changes which will need to be un-reverted or made conditional) and vendor Rust dependencies to make builds much faster in any CI system.

Browse Source
This commit is contained in:
Adam Ierymenko
2022-06-08 07:32:16 -04:00
parent 373ca30269
commit d5ca4e5f52
12611 changed files with 2898014 additions and 284 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
zeroidc/vendor/idna/.cargo-checksum.json vendored Normal file
View File

@@ -0,0 +1 @@
{"files":{"Cargo.toml":"fa141dcb135262e5fda9f680671699045326d96779bb1acf38d48c70c712bcdf","LICENSE-APACHE":"a60eea817514531668d7e00765731449fe14d059d3249e0bc93b36de45f759f2","LICENSE-MIT":"20c7855c364d57ea4c97889a5e8d98470a9952dade37bd9248b9a54431670e5e","benches/all.rs":"e734b9c9092ed66986725f86cfe90f3756cfddb058af308b796ba494f9beefc2","src/IdnaMappingTable.txt":"87d6553a4b86bc49dcade38bf26b745cd81800eb8af295dc3fb99b4729eaea38","src/lib.rs":"d61b2bfcf4265b9a41eedd1de33ab49ea615e3c06df944321b30c57950a85342","src/make_uts46_mapping_table.py":"917055fa841f813de2bcf79cc79b595da3d5551559ee768db8660ab77cb26c34","src/punycode.rs":"07edf5293bc384a164eebb01bc18fe3d4b2d009b4565a36b74a3030978ea6e04","src/uts46.rs":"40521a01e5b8c38667252d5b1e0141c5a71f63aeae2f451b986792984e633b09","src/uts46_mapping_table.rs":"942fff78147c61da942f5f3a7ff4e90f9d7a00a29285733ac3fc3357eb2ed06f","tests/IdnaTestV2.txt":"c6f3778b0545fd150c8063286c7f5adc901e16557eddccc3751213646d07593d","tests/punycode.rs":"e6fb978f48445d1525a6b97351c41c5393a1612a35f85b9a7f45b8794fce9aba","tests/punycode_tests.json":"3d4ac0cf25984c37b9ce197f5df680a0136f728fb8ec82bc76624e42139eb3a8","tests/tests.rs":"de7425a3e4e6e871255721107803704d1431246601fa9c87105224d88dfe60d6","tests/unit.rs":"be025a7d9bab3bd1ce134c87f9d848269e157b31ca5ba0ea03426c1ac736b69e","tests/uts46.rs":"ca91d48811d366fb9e32d7aa79cfda1261b93c271b6ed7fb5535de9a2500205b"},"package":"418a0a6fab821475f634efe3ccc45c013f742efe03d853e8d3355d5cb850ecf8"}

54
zeroidc/vendor/idna/Cargo.toml vendored Normal file
View File

@@ -0,0 +1,54 @@
# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
#
# When uploading crates to the registry Cargo will automatically
# "normalize" Cargo.toml files for maximal compatibility
# with all versions of Cargo and also rewrite `path` dependencies
# to registry (e.g., crates.io) dependencies
#
# If you believe there's an error in this file please file an
# issue against the rust-lang/cargo repository. If you're
# editing this file be aware that the upstream Cargo.toml
# will likely look very different (and much more reasonable)
[package]
edition = "2018"
name = "idna"
version = "0.2.3"
authors = ["The rust-url developers"]
autotests = false
description = "IDNA (Internationalizing Domain Names in Applications) and Punycode."
license = "MIT/Apache-2.0"
repository = "https://github.com/servo/rust-url/"
[lib]
doctest = false
[[test]]
name = "tests"
harness = false
[[test]]
name = "unit"
[[bench]]
name = "all"
harness = false
[dependencies.matches]
version = "0.1"
[dependencies.unicode-bidi]
version = "0.3"
[dependencies.unicode-normalization]
version = "0.1.17"
[dev-dependencies.assert_matches]
version = "1.3"
[dev-dependencies.bencher]
version = "0.1"
[dev-dependencies.rustc-test]
version = "0.3"
[dev-dependencies.serde_json]
version = "1.0"

201
zeroidc/vendor/idna/LICENSE-APACHE vendored Normal file
View File

@@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

25
zeroidc/vendor/idna/LICENSE-MIT vendored Normal file
View File

@@ -0,0 +1,25 @@
Copyright (c) 2013-2016 The rust-url developers
Permission is hereby granted, free of charge, to any
person obtaining a copy of this software and associated
documentation files (the "Software"), to deal in the
Software without restriction, including without
limitation the rights to use, copy, modify, merge,
publish, distribute, sublicense, and/or sell copies of
the Software, and to permit persons to whom the Software
is furnished to do so, subject to the following
conditions:
The above copyright notice and this permission notice
shall be included in all copies or substantial portions
of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF
ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED
TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR
IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.

53
zeroidc/vendor/idna/benches/all.rs vendored Normal file
View File

@@ -0,0 +1,53 @@
#[macro_use]
extern crate bencher;
extern crate idna;
use bencher::{black_box, Bencher};
use idna::Config;
fn to_unicode_puny_label(bench: &mut Bencher) {
let encoded = "abc.xn--mgbcm";
let config = Config::default();
bench.iter(|| config.to_unicode(black_box(encoded)));
}
fn to_unicode_ascii(bench: &mut Bencher) {
let encoded = "example.com";
let config = Config::default();
bench.iter(|| config.to_unicode(black_box(encoded)));
}
fn to_unicode_merged_label(bench: &mut Bencher) {
let encoded = "Beispiel.xn--vermgensberater-ctb";
let config = Config::default();
bench.iter(|| config.to_unicode(black_box(encoded)));
}
fn to_ascii_puny_label(bench: &mut Bencher) {
let encoded = "abc.ابج";
let config = Config::default();
bench.iter(|| config.to_ascii(black_box(encoded)));
}
fn to_ascii_simple(bench: &mut Bencher) {
let encoded = "example.com";
let config = Config::default();
bench.iter(|| config.to_ascii(black_box(encoded)));
}
fn to_ascii_merged(bench: &mut Bencher) {
let encoded = "beispiel.vermögensberater";
let config = Config::default();
bench.iter(|| config.to_ascii(black_box(encoded)));
}
benchmark_group!(
benches,
to_unicode_puny_label,
to_unicode_ascii,
to_unicode_merged_label,
to_ascii_puny_label,
to_ascii_simple,
to_ascii_merged,
);
benchmark_main!(benches);

8727
zeroidc/vendor/idna/src/IdnaMappingTable.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

73
zeroidc/vendor/idna/src/lib.rs vendored Normal file
View File

@@ -0,0 +1,73 @@
// Copyright 2016 The rust-url developers.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//! This Rust crate implements IDNA
//! [per the WHATWG URL Standard](https://url.spec.whatwg.org/#idna).
//!
//! It also exposes the underlying algorithms from [*Unicode IDNA Compatibility Processing*
//! (Unicode Technical Standard #46)](http://www.unicode.org/reports/tr46/)
//! and [Punycode (RFC 3492)](https://tools.ietf.org/html/rfc3492).
//!
//! Quoting from [UTS #46’s introduction](http://www.unicode.org/reports/tr46/#Introduction):
//!
//! > Initially, domain names were restricted to ASCII characters.
//! > A system was introduced in 2003 for internationalized domain names (IDN).
//! > This system is called Internationalizing Domain Names for Applications,
//! > or IDNA2003 for short.
//! > This mechanism supports IDNs by means of a client software transformation
//! > into a format known as Punycode.
//! > A revision of IDNA was approved in 2010 (IDNA2008).
//! > This revision has a number of incompatibilities with IDNA2003.
//! >
//! > The incompatibilities force implementers of client software,
//! > such as browsers and emailers,
//! > to face difficult choices during the transition period
//! > as registries shift from IDNA2003 to IDNA2008.
//! > This document specifies a mechanism
//! > that minimizes the impact of this transition for client software,
//! > allowing client software to access domains that are valid under either system.
#[macro_use]
extern crate matches;
pub mod punycode;
mod uts46;
pub use crate::uts46::{Config, Errors, Idna};
/// The [domain to ASCII](https://url.spec.whatwg.org/#concept-domain-to-ascii) algorithm.
///
/// Return the ASCII representation a domain name,
/// normalizing characters (upper-case to lower-case and other kinds of equivalence)
/// and using Punycode as necessary.
///
/// This process may fail.
pub fn domain_to_ascii(domain: &str) -> Result<String, uts46::Errors> {
Config::default().to_ascii(domain)
}
/// The [domain to ASCII](https://url.spec.whatwg.org/#concept-domain-to-ascii) algorithm,
/// with the `beStrict` flag set.
pub fn domain_to_ascii_strict(domain: &str) -> Result<String, uts46::Errors> {
Config::default()
.use_std3_ascii_rules(true)
.verify_dns_length(true)
.to_ascii(domain)
}
/// The [domain to Unicode](https://url.spec.whatwg.org/#concept-domain-to-unicode) algorithm.
///
/// Return the Unicode representation of a domain name,
/// normalizing characters (upper-case to lower-case and other kinds of equivalence)
/// and decoding Punycode as necessary.
///
/// This may indicate [syntax violations](https://url.spec.whatwg.org/#syntax-violation)
/// but always returns a string for the mapped domain.
pub fn domain_to_unicode(domain: &str) -> (String, Result<(), uts46::Errors>) {
Config::default().to_unicode(domain)
}

185
zeroidc/vendor/idna/src/make_uts46_mapping_table.py vendored Normal file
View File

@@ -0,0 +1,185 @@
# Copyright 2013-2014 The rust-url developers.
#
# Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
# http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
# <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
# option. This file may not be copied, modified, or distributed
# except according to those terms.
# Run as: python make_uts46_mapping_table.py IdnaMappingTable.txt > uts46_mapping_table.rs
# You can get the latest idna table from
# http://www.unicode.org/Public/idna/latest/IdnaMappingTable.txt
import collections
import itertools
print('''\
// Copyright 2013-2020 The rust-url developers.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
// Generated by make_idna_table.py
''')
txt = open("IdnaMappingTable.txt")
def escape_char(c):
return "\\u{%x}" % ord(c[0])
def char(s):
return chr(int(s, 16))
strtab = collections.OrderedDict()
strtab_offset = 0
def strtab_slice(s):
global strtab, strtab_offset
if s in strtab:
return strtab[s]
else:
utf8_len = len(s.encode('utf8'))
c = (strtab_offset, utf8_len)
strtab[s] = c
strtab_offset += utf8_len
return c
def rust_slice(s):
start = s[0]
length = s[1]
start_lo = start & 0xff
start_hi = start >> 8
assert length <= 255
assert start_hi <= 255
return "(StringTableSlice { byte_start_lo: %d, byte_start_hi: %d, byte_len: %d })" % (start_lo, start_hi, length)
ranges = []
for line in txt:
# remove comments
line, _, _ = line.partition('#')
# skip empty lines
if len(line.strip()) == 0:
continue
fields = line.split(';')
if fields[0].strip() == 'D800..DFFF':
continue # Surrogates don't occur in Rust strings.
first, _, last = fields[0].strip().partition('..')
if not last:
last = first
mapping = fields[1].strip().replace('_', ' ').title().replace(' ', '')
unicode_str = None
if len(fields) > 2:
if fields[2].strip():
unicode_str = u''.join(char(c) for c in fields[2].strip().split(' '))
elif mapping == "Deviation":
unicode_str = u''
if len(fields) > 3:
assert fields[3].strip() in ('NV8', 'XV8'), fields[3]
assert mapping == 'Valid', mapping
mapping = 'DisallowedIdna2008'
ranges.append((first, last, mapping, unicode_str))
def mergeable_key(r):
mapping = r[2]
# These types have associated data, so we should not merge them.
if mapping in ('Mapped', 'Deviation', 'DisallowedStd3Mapped'):
return r
assert mapping in ('Valid', 'Ignored', 'Disallowed', 'DisallowedStd3Valid', 'DisallowedIdna2008')
return mapping
grouped_ranges = itertools.groupby(ranges, key=mergeable_key)
optimized_ranges = []
for (k, g) in grouped_ranges:
group = list(g)
if len(group) == 1:
optimized_ranges.append(group[0])
continue
# Assert that nothing in the group has an associated unicode string.
for g in group:
if g[3] is not None and len(g[3]) > 2:
assert not g[3][2].strip()
# Assert that consecutive members of the group don't leave gaps in
# the codepoint space.
a, b = itertools.tee(group)
next(b, None)
for (g1, g2) in zip(a, b):
last_char = int(g1[1], 16)
next_char = int(g2[0], 16)
if last_char + 1 == next_char:
continue
# There's a gap where surrogates would appear, but we don't have to
# worry about that gap, as surrogates never appear in Rust strings.
# Assert we're seeing the surrogate case here.
assert last_char == 0xd7ff
assert next_char == 0xe000
optimized_ranges.append((group[0][0], group[-1][1]) + group[0][2:])
def is_single_char_range(r):
(first, last, _, _) = r
return first == last
# We can reduce the size of the character range table and the index table to about 1/4
# by merging runs of single character ranges and using character offsets from the start
# of that range to retrieve the correct `Mapping` value
def merge_single_char_ranges(ranges):
current = []
for r in ranges:
if not current or is_single_char_range(current[-1]) and is_single_char_range(r):
current.append(r)
continue
if len(current) != 0:
ret = current
current = [r]
yield ret
continue
current.append(r)
ret = current
current = []
yield ret
yield current
optimized_ranges = list(merge_single_char_ranges(optimized_ranges))
SINGLE_MARKER = 1 << 15
print("static TABLE: &[(char, u16)] = &[")
offset = 0
for ranges in optimized_ranges:
assert offset < SINGLE_MARKER
block_len = len(ranges)
single = SINGLE_MARKER if block_len == 1 else 0
index = offset | single
offset += block_len
start = escape_char(char(ranges[0][0]))
print(" ('%s', %s)," % (start, index))
print("];\n")
print("static MAPPING_TABLE: &[Mapping] = &[")
for ranges in optimized_ranges:
for (first, last, mapping, unicode_str) in ranges:
if unicode_str is not None:
mapping += rust_slice(strtab_slice(unicode_str))
print(" %s," % mapping)
print("];\n")
def escape_str(s):
return [escape_char(c) for c in s]
print("static STRING_TABLE: &str = \"%s\";"
% '\\\n '.join(itertools.chain(*[escape_str(s) for s in strtab.keys()])))

315
zeroidc/vendor/idna/src/punycode.rs vendored Normal file
View File

@@ -0,0 +1,315 @@
// Copyright 2013 The rust-url developers.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//! Punycode ([RFC 3492](http://tools.ietf.org/html/rfc3492)) implementation.
//!
//! Since Punycode fundamentally works on unicode code points,
//! `encode` and `decode` take and return slices and vectors of `char`.
//! `encode_str` and `decode_to_string` provide convenience wrappers
//! that convert from and to Rust’s UTF-8 based `str` and `String` types.
use std::char;
use std::u32;
// Bootstring parameters for Punycode
static BASE: u32 = 36;
static T_MIN: u32 = 1;
static T_MAX: u32 = 26;
static SKEW: u32 = 38;
static DAMP: u32 = 700;
static INITIAL_BIAS: u32 = 72;
static INITIAL_N: u32 = 0x80;
static DELIMITER: char = '-';
#[inline]
fn adapt(mut delta: u32, num_points: u32, first_time: bool) -> u32 {
delta /= if first_time { DAMP } else { 2 };
delta += delta / num_points;
let mut k = 0;
while delta > ((BASE - T_MIN) * T_MAX) / 2 {
delta /= BASE - T_MIN;
k += BASE;
}
k + (((BASE - T_MIN + 1) * delta) / (delta + SKEW))
}
/// Convert Punycode to an Unicode `String`.
///
/// This is a convenience wrapper around `decode`.
#[inline]
pub fn decode_to_string(input: &str) -> Option<String> {
decode(input).map(|chars| chars.into_iter().collect())
}
/// Convert Punycode to Unicode.
///
/// Return None on malformed input or overflow.
/// Overflow can only happen on inputs that take more than
/// 63 encoded bytes, the DNS limit on domain name labels.
pub fn decode(input: &str) -> Option<Vec<char>> {
Some(Decoder::default().decode(input).ok()?.collect())
}
#[derive(Default)]
pub(crate) struct Decoder {
insertions: Vec<(usize, char)>,
}
impl Decoder {
/// Split the input iterator and return a Vec with insertions of encoded characters
pub(crate) fn decode<'a>(&'a mut self, input: &'a str) -> Result<Decode<'a>, ()> {
self.insertions.clear();
// Handle "basic" (ASCII) code points.
// They are encoded as-is before the last delimiter, if any.
let (base, input) = match input.rfind(DELIMITER) {
None => ("", input),
Some(position) => (
&input[..position],
if position > 0 {
&input[position + 1..]
} else {
input
},
),
};
if !base.is_ascii() {
return Err(());
}
let base_len = base.len();
let mut length = base_len as u32;
let mut code_point = INITIAL_N;
let mut bias = INITIAL_BIAS;
let mut i = 0;
let mut iter = input.bytes();
loop {
let previous_i = i;
let mut weight = 1;
let mut k = BASE;
let mut byte = match iter.next() {
None => break,
Some(byte) => byte,
};
// Decode a generalized variable-length integer into delta,
// which gets added to i.
loop {
let digit = match byte {
byte @ b'0'..=b'9' => byte - b'0' + 26,
byte @ b'A'..=b'Z' => byte - b'A',
byte @ b'a'..=b'z' => byte - b'a',
_ => return Err(()),
} as u32;
if digit > (u32::MAX - i) / weight {
return Err(()); // Overflow
}
i += digit * weight;
let t = if k <= bias {
T_MIN
} else if k >= bias + T_MAX {
T_MAX
} else {
k - bias
};
if digit < t {
break;
}
if weight > u32::MAX / (BASE - t) {
return Err(()); // Overflow
}
weight *= BASE - t;
k += BASE;
byte = match iter.next() {
None => return Err(()), // End of input before the end of this delta
Some(byte) => byte,
};
}
bias = adapt(i - previous_i, length + 1, previous_i == 0);
if i / (length + 1) > u32::MAX - code_point {
return Err(()); // Overflow
}
// i was supposed to wrap around from length+1 to 0,
// incrementing code_point each time.
code_point += i / (length + 1);
i %= length + 1;
let c = match char::from_u32(code_point) {
Some(c) => c,
None => return Err(()),
};
// Move earlier insertions farther out in the string
for (idx, _) in &mut self.insertions {
if *idx >= i as usize {
*idx += 1;
}
}
self.insertions.push((i as usize, c));
length += 1;
i += 1;
}
self.insertions.sort_by_key(|(i, _)| *i);
Ok(Decode {
base: base.chars(),
insertions: &self.insertions,
inserted: 0,
position: 0,
len: base_len + self.insertions.len(),
})
}
}
pub(crate) struct Decode<'a> {
base: std::str::Chars<'a>,
pub(crate) insertions: &'a [(usize, char)],
inserted: usize,
position: usize,
len: usize,
}
impl<'a> Iterator for Decode<'a> {
type Item = char;
fn next(&mut self) -> Option<Self::Item> {
loop {
match self.insertions.get(self.inserted) {
Some((pos, c)) if *pos == self.position => {
self.inserted += 1;
self.position += 1;
return Some(*c);
}
_ => {}
}
if let Some(c) = self.base.next() {
self.position += 1;
return Some(c);
} else if self.inserted >= self.insertions.len() {
return None;
}
}
}
fn size_hint(&self) -> (usize, Option<usize>) {
let len = self.len - self.position;
(len, Some(len))
}
}
impl<'a> ExactSizeIterator for Decode<'a> {
fn len(&self) -> usize {
self.len - self.position
}
}
/// Convert an Unicode `str` to Punycode.
///
/// This is a convenience wrapper around `encode`.
#[inline]
pub fn encode_str(input: &str) -> Option<String> {
let mut buf = String::with_capacity(input.len());
encode_into(input.chars(), &mut buf).ok().map(|()| buf)
}
/// Convert Unicode to Punycode.
///
/// Return None on overflow, which can only happen on inputs that would take more than
/// 63 encoded bytes, the DNS limit on domain name labels.
pub fn encode(input: &[char]) -> Option<String> {
let mut buf = String::with_capacity(input.len());
encode_into(input.iter().copied(), &mut buf)
.ok()
.map(|()| buf)
}
pub(crate) fn encode_into<I>(input: I, output: &mut String) -> Result<(), ()>
where
I: Iterator<Item = char> + Clone,
{
// Handle "basic" (ASCII) code points. They are encoded as-is.
let (mut input_length, mut basic_length) = (0, 0);
for c in input.clone() {
input_length += 1;
if c.is_ascii() {
output.push(c);
basic_length += 1;
}
}
if basic_length > 0 {
output.push('-')
}
let mut code_point = INITIAL_N;
let mut delta = 0;
let mut bias = INITIAL_BIAS;
let mut processed = basic_length;
while processed < input_length {
// All code points < code_point have been handled already.
// Find the next larger one.
let min_code_point = input
.clone()
.map(|c| c as u32)
.filter(|&c| c >= code_point)
.min()
.unwrap();
if min_code_point - code_point > (u32::MAX - delta) / (processed + 1) {
return Err(()); // Overflow
}
// Increase delta to advance the decoder’s <code_point,i> state to <min_code_point,0>
delta += (min_code_point - code_point) * (processed + 1);
code_point = min_code_point;
for c in input.clone() {
let c = c as u32;
if c < code_point {
delta += 1;
if delta == 0 {
return Err(()); // Overflow
}
}
if c == code_point {
// Represent delta as a generalized variable-length integer:
let mut q = delta;
let mut k = BASE;
loop {
let t = if k <= bias {
T_MIN
} else if k >= bias + T_MAX {
T_MAX
} else {
k - bias
};
if q < t {
break;
}
let value = t + ((q - t) % (BASE - t));
output.push(value_to_digit(value));
q = (q - t) / (BASE - t);
k += BASE;
}
output.push(value_to_digit(q));
bias = adapt(delta, processed + 1, processed == basic_length);
delta = 0;
processed += 1;
}
}
delta += 1;
code_point += 1;
}
Ok(())
}
#[inline]
fn value_to_digit(value: u32) -> char {
match value {
0..=25 => (value as u8 + b'a') as char, // a..z
26..=35 => (value as u8 - 26 + b'0') as char, // 0..9
_ => panic!(),
}
}

727
zeroidc/vendor/idna/src/uts46.rs vendored Normal file
View File

@@ -0,0 +1,727 @@
// Copyright 2013-2014 The rust-url developers.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//! [*Unicode IDNA Compatibility Processing*
//! (Unicode Technical Standard #46)](http://www.unicode.org/reports/tr46/)
use self::Mapping::*;
use crate::punycode;
use std::{error::Error as StdError, fmt};
use unicode_bidi::{bidi_class, BidiClass};
use unicode_normalization::char::is_combining_mark;
use unicode_normalization::{is_nfc, UnicodeNormalization};
include!("uts46_mapping_table.rs");
const PUNYCODE_PREFIX: &str = "xn--";
#[derive(Debug)]
struct StringTableSlice {
// Store these as separate fields so the structure will have an
// alignment of 1 and thus pack better into the Mapping enum, below.
byte_start_lo: u8,
byte_start_hi: u8,
byte_len: u8,
}
fn decode_slice(slice: &StringTableSlice) -> &'static str {
let lo = slice.byte_start_lo as usize;
let hi = slice.byte_start_hi as usize;
let start = (hi << 8) | lo;
let len = slice.byte_len as usize;
&STRING_TABLE[start..(start + len)]
}
#[repr(u8)]
#[derive(Debug)]
enum Mapping {
Valid,
Ignored,
Mapped(StringTableSlice),
Deviation(StringTableSlice),
Disallowed,
DisallowedStd3Valid,
DisallowedStd3Mapped(StringTableSlice),
DisallowedIdna2008,
}
fn find_char(codepoint: char) -> &'static Mapping {
let idx = match TABLE.binary_search_by_key(&codepoint, |&val| val.0) {
Ok(idx) => idx,
Err(idx) => idx - 1,
};
const SINGLE_MARKER: u16 = 1 << 15;
let (base, x) = TABLE[idx];
let single = (x & SINGLE_MARKER) != 0;
let offset = !SINGLE_MARKER & x;
if single {
&MAPPING_TABLE[offset as usize]
} else {
&MAPPING_TABLE[(offset + (codepoint as u16 - base as u16)) as usize]
}
}
struct Mapper<'a> {
chars: std::str::Chars<'a>,
config: Config,
errors: &'a mut Errors,
slice: Option<std::str::Chars<'static>>,
}
impl<'a> Iterator for Mapper<'a> {
type Item = char;
fn next(&mut self) -> Option<Self::Item> {
loop {
if let Some(s) = &mut self.slice {
match s.next() {
Some(c) => return Some(c),
None => {
self.slice = None;
}
}
}
let codepoint = self.chars.next()?;
if let '.' | '-' | 'a'..='z' | '0'..='9' = codepoint {
return Some(codepoint);
}
return Some(match *find_char(codepoint) {
Mapping::Valid => codepoint,
Mapping::Ignored => continue,
Mapping::Mapped(ref slice) => {
self.slice = Some(decode_slice(slice).chars());
continue;
}
Mapping::Deviation(ref slice) => {
if self.config.transitional_processing {
self.slice = Some(decode_slice(slice).chars());
continue;
} else {
codepoint
}
}
Mapping::Disallowed => {
self.errors.disallowed_character = true;
codepoint
}
Mapping::DisallowedStd3Valid => {
if self.config.use_std3_ascii_rules {
self.errors.disallowed_by_std3_ascii_rules = true;
};
codepoint
}
Mapping::DisallowedStd3Mapped(ref slice) => {
if self.config.use_std3_ascii_rules {
self.errors.disallowed_mapped_in_std3 = true;
};
self.slice = Some(decode_slice(slice).chars());
continue;
}
Mapping::DisallowedIdna2008 => {
if self.config.use_idna_2008_rules {
self.errors.disallowed_in_idna_2008 = true;
}
codepoint
}
});
}
}
}
// http://tools.ietf.org/html/rfc5893#section-2
fn passes_bidi(label: &str, is_bidi_domain: bool) -> bool {
// Rule 0: Bidi Rules apply to Bidi Domain Names: a name with at least one RTL label. A label
// is RTL if it contains at least one character of bidi class R, AL or AN.
if !is_bidi_domain {
return true;
}
let mut chars = label.chars();
let first_char_class = match chars.next() {
Some(c) => bidi_class(c),
None => return true, // empty string
};
match first_char_class {
// LTR label
BidiClass::L => {
// Rule 5
while let Some(c) = chars.next() {
if !matches!(
bidi_class(c),
BidiClass::L
| BidiClass::EN
| BidiClass::ES
| BidiClass::CS
| BidiClass::ET
| BidiClass::ON
| BidiClass::BN
| BidiClass::NSM
) {
return false;
}
}
// Rule 6
// must end in L or EN followed by 0 or more NSM
let mut rev_chars = label.chars().rev();
let mut last_non_nsm = rev_chars.next();
loop {
match last_non_nsm {
Some(c) if bidi_class(c) == BidiClass::NSM => {
last_non_nsm = rev_chars.next();
continue;
}
_ => {
break;
}
}
}
match last_non_nsm {
Some(c) if bidi_class(c) == BidiClass::L || bidi_class(c) == BidiClass::EN => {}
Some(_) => {
return false;
}
_ => {}
}
}
// RTL label
BidiClass::R | BidiClass::AL => {
let mut found_en = false;
let mut found_an = false;
// Rule 2
for c in chars {
let char_class = bidi_class(c);
if char_class == BidiClass::EN {
found_en = true;
} else if char_class == BidiClass::AN {
found_an = true;
}
if !matches!(
char_class,
BidiClass::R
| BidiClass::AL
| BidiClass::AN
| BidiClass::EN
| BidiClass::ES
| BidiClass::CS
| BidiClass::ET
| BidiClass::ON
| BidiClass::BN
| BidiClass::NSM
) {
return false;
}
}
// Rule 3
let mut rev_chars = label.chars().rev();
let mut last = rev_chars.next();
loop {
// must end in L or EN followed by 0 or more NSM
match last {
Some(c) if bidi_class(c) == BidiClass::NSM => {
last = rev_chars.next();
continue;
}
_ => {
break;
}
}
}
match last {
Some(c)
if matches!(
bidi_class(c),
BidiClass::R | BidiClass::AL | BidiClass::EN | BidiClass::AN
) => {}
_ => {
return false;
}
}
// Rule 4
if found_an && found_en {
return false;
}
}
// Rule 1: Should start with L or R/AL
_ => {
return false;
}
}
true
}
/// Check the validity criteria for the given label
///
/// V1 (NFC) and V8 (Bidi) are checked inside `processing()` to prevent doing duplicate work.
///
/// http://www.unicode.org/reports/tr46/#Validity_Criteria
fn check_validity(label: &str, config: Config, errors: &mut Errors) {
let first_char = label.chars().next();
if first_char == None {
// Empty string, pass
return;
}
// V2: No U+002D HYPHEN-MINUS in both third and fourth positions.
//
// NOTE: Spec says that the label must not contain a HYPHEN-MINUS character in both the
// third and fourth positions. But nobody follows this criteria. See the spec issue below:
// https://github.com/whatwg/url/issues/53
// V3: neither begin nor end with a U+002D HYPHEN-MINUS
if config.check_hyphens && (label.starts_with('-') || label.ends_with('-')) {
errors.check_hyphens = true;
return;
}
// V4: not contain a U+002E FULL STOP
//
// Here, label can't contain '.' since the input is from .split('.')
// V5: not begin with a GC=Mark
if is_combining_mark(first_char.unwrap()) {
errors.start_combining_mark = true;
return;
}
// V6: Check against Mapping Table
if label.chars().any(|c| match *find_char(c) {
Mapping::Valid | Mapping::DisallowedIdna2008 => false,
Mapping::Deviation(_) => config.transitional_processing,
Mapping::DisallowedStd3Valid => config.use_std3_ascii_rules,
_ => true,
}) {
errors.invalid_mapping = true;
}
// V7: ContextJ rules
//
// TODO: Implement rules and add *CheckJoiners* flag.
// V8: Bidi rules are checked inside `processing()`
}
/// http://www.unicode.org/reports/tr46/#Processing
#[allow(clippy::manual_strip)] // introduced in 1.45, MSRV is 1.36
fn processing(
domain: &str,
config: Config,
normalized: &mut String,
output: &mut String,
) -> Errors {
// Weed out the simple cases: only allow all lowercase ASCII characters and digits where none
// of the labels start with PUNYCODE_PREFIX and labels don't start or end with hyphen.
let (mut prev, mut simple, mut puny_prefix) = ('?', !domain.is_empty(), 0);
for c in domain.chars() {
if c == '.' {
if prev == '-' {
simple = false;
break;
}
puny_prefix = 0;
continue;
} else if puny_prefix == 0 && c == '-' {
simple = false;
break;
} else if puny_prefix < 5 {
if c == ['x', 'n', '-', '-'][puny_prefix] {
puny_prefix += 1;
if puny_prefix == 4 {
simple = false;
break;
}
} else {
puny_prefix = 5;
}
}
if !c.is_ascii_lowercase() && !c.is_ascii_digit() {
simple = false;
break;
}
prev = c;
}
if simple {
output.push_str(domain);
return Errors::default();
}
normalized.clear();
let mut errors = Errors::default();
let offset = output.len();
let iter = Mapper {
chars: domain.chars(),
config,
errors: &mut errors,
slice: None,
};
normalized.extend(iter.nfc());
let mut decoder = punycode::Decoder::default();
let non_transitional = config.transitional_processing(false);
let (mut first, mut has_bidi_labels) = (true, false);
for label in normalized.split('.') {
if !first {
output.push('.');
}
first = false;
if label.starts_with(PUNYCODE_PREFIX) {
match decoder.decode(&label[PUNYCODE_PREFIX.len()..]) {
Ok(decode) => {
let start = output.len();
output.extend(decode);
let decoded_label = &output[start..];
if !has_bidi_labels {
has_bidi_labels |= is_bidi_domain(decoded_label);
}
if !errors.is_err() {
if !is_nfc(&decoded_label) {
errors.nfc = true;
} else {
check_validity(decoded_label, non_transitional, &mut errors);
}
}
}
Err(()) => {
has_bidi_labels = true;
errors.punycode = true;
}
}
} else {
if !has_bidi_labels {
has_bidi_labels |= is_bidi_domain(label);
}
// `normalized` is already `NFC` so we can skip that check
check_validity(label, config, &mut errors);
output.push_str(label)
}
}
for label in output[offset..].split('.') {
// V8: Bidi rules
//
// TODO: Add *CheckBidi* flag
if !passes_bidi(label, has_bidi_labels) {
errors.check_bidi = true;
break;
}
}
errors
}
#[derive(Default)]
pub struct Idna {
config: Config,
normalized: String,
output: String,
}
impl Idna {
pub fn new(config: Config) -> Self {
Self {
config,
normalized: String::new(),
output: String::new(),
}
}
/// http://www.unicode.org/reports/tr46/#ToASCII
#[allow(clippy::wrong_self_convention)]
pub fn to_ascii<'a>(&'a mut self, domain: &str, out: &mut String) -> Result<(), Errors> {
let mut errors = processing(domain, self.config, &mut self.normalized, &mut self.output);
let mut first = true;
for label in self.output.split('.') {
if !first {
out.push('.');
}
first = false;
if label.is_ascii() {
out.push_str(label);
} else {
let offset = out.len();
out.push_str(PUNYCODE_PREFIX);
if let Err(()) = punycode::encode_into(label.chars(), out) {
errors.punycode = true;
out.truncate(offset);
}
}
}
if self.config.verify_dns_length {
let domain = if out.ends_with('.') {
&out[..out.len() - 1]
} else {
&*out
};
if domain.is_empty() || domain.split('.').any(|label| label.is_empty()) {
errors.too_short_for_dns = true;
}
if domain.len() > 253 || domain.split('.').any(|label| label.len() > 63) {
errors.too_long_for_dns = true;
}
}
errors.into()
}
/// http://www.unicode.org/reports/tr46/#ToUnicode
#[allow(clippy::wrong_self_convention)]
pub fn to_unicode<'a>(&'a mut self, domain: &str, out: &mut String) -> Result<(), Errors> {
processing(domain, self.config, &mut self.normalized, out).into()
}
}
#[derive(Clone, Copy)]
pub struct Config {
use_std3_ascii_rules: bool,
transitional_processing: bool,
verify_dns_length: bool,
check_hyphens: bool,
use_idna_2008_rules: bool,
}
/// The defaults are that of https://url.spec.whatwg.org/#idna
impl Default for Config {
fn default() -> Self {
Config {
use_std3_ascii_rules: false,
transitional_processing: false,
check_hyphens: false,
// check_bidi: true,
// check_joiners: true,
// Only use for to_ascii, not to_unicode
verify_dns_length: false,
use_idna_2008_rules: false,
}
}
}
impl Config {
#[inline]
pub fn use_std3_ascii_rules(mut self, value: bool) -> Self {
self.use_std3_ascii_rules = value;
self
}
#[inline]
pub fn transitional_processing(mut self, value: bool) -> Self {
self.transitional_processing = value;
self
}
#[inline]
pub fn verify_dns_length(mut self, value: bool) -> Self {
self.verify_dns_length = value;
self
}
#[inline]
pub fn check_hyphens(mut self, value: bool) -> Self {
self.check_hyphens = value;
self
}
#[inline]
pub fn use_idna_2008_rules(mut self, value: bool) -> Self {
self.use_idna_2008_rules = value;
self
}
/// http://www.unicode.org/reports/tr46/#ToASCII
pub fn to_ascii(self, domain: &str) -> Result<String, Errors> {
let mut result = String::new();
let mut codec = Idna::new(self);
codec.to_ascii(domain, &mut result).map(|()| result)
}
/// http://www.unicode.org/reports/tr46/#ToUnicode
pub fn to_unicode(self, domain: &str) -> (String, Result<(), Errors>) {
let mut codec = Idna::new(self);
let mut out = String::with_capacity(domain.len());
let result = codec.to_unicode(domain, &mut out);
(out, result)
}
}
fn is_bidi_domain(s: &str) -> bool {
for c in s.chars() {
if c.is_ascii_graphic() {
continue;
}
match bidi_class(c) {
BidiClass::R | BidiClass::AL | BidiClass::AN => return true,
_ => {}
}
}
false
}
/// Errors recorded during UTS #46 processing.
///
/// This is opaque for now, indicating what types of errors have been encountered at least once.
/// More details may be exposed in the future.
#[derive(Default)]
pub struct Errors {
punycode: bool,
check_hyphens: bool,
check_bidi: bool,
start_combining_mark: bool,
invalid_mapping: bool,
nfc: bool,
disallowed_by_std3_ascii_rules: bool,
disallowed_mapped_in_std3: bool,
disallowed_character: bool,
too_long_for_dns: bool,
too_short_for_dns: bool,
disallowed_in_idna_2008: bool,
}
impl Errors {
fn is_err(&self) -> bool {
let Errors {
punycode,
check_hyphens,
check_bidi,
start_combining_mark,
invalid_mapping,
nfc,
disallowed_by_std3_ascii_rules,
disallowed_mapped_in_std3,
disallowed_character,
too_long_for_dns,
too_short_for_dns,
disallowed_in_idna_2008,
} = *self;
punycode
|| check_hyphens
|| check_bidi
|| start_combining_mark
|| invalid_mapping
|| nfc
|| disallowed_by_std3_ascii_rules
|| disallowed_mapped_in_std3
|| disallowed_character
|| too_long_for_dns
|| too_short_for_dns
|| disallowed_in_idna_2008
}
}
impl fmt::Debug for Errors {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
let Errors {
punycode,
check_hyphens,
check_bidi,
start_combining_mark,
invalid_mapping,
nfc,
disallowed_by_std3_ascii_rules,
disallowed_mapped_in_std3,
disallowed_character,
too_long_for_dns,
too_short_for_dns,
disallowed_in_idna_2008,
} = *self;
let fields = [
("punycode", punycode),
("check_hyphens", check_hyphens),
("check_bidi", check_bidi),
("start_combining_mark", start_combining_mark),
("invalid_mapping", invalid_mapping),
("nfc", nfc),
(
"disallowed_by_std3_ascii_rules",
disallowed_by_std3_ascii_rules,
),
("disallowed_mapped_in_std3", disallowed_mapped_in_std3),
("disallowed_character", disallowed_character),
("too_long_for_dns", too_long_for_dns),
("too_short_for_dns", too_short_for_dns),
("disallowed_in_idna_2008", disallowed_in_idna_2008),
];
let mut empty = true;
f.write_str("Errors { ")?;
for (name, val) in &fields {
if *val {
if !empty {
f.write_str(", ")?;
}
f.write_str(*name)?;
empty = false;
}
}
if !empty {
f.write_str(" }")
} else {
f.write_str("}")
}
}
}
impl From<Errors> for Result<(), Errors> {
fn from(e: Errors) -> Result<(), Errors> {
if !e.is_err() {
Ok(())
} else {
Err(e)
}
}
}
impl StdError for Errors {}
impl fmt::Display for Errors {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
fmt::Debug::fmt(self, f)
}
}
#[cfg(test)]
mod tests {
use super::{find_char, Mapping};
#[test]
fn mapping_fast_path() {
assert_matches!(find_char('-'), &Mapping::Valid);
assert_matches!(find_char('.'), &Mapping::Valid);
for c in &['0', '1', '2', '3', '4', '5', '6', '7', '8', '9'] {
assert_matches!(find_char(*c), &Mapping::Valid);
}
for c in &[
'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q',
'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
] {
assert_matches!(find_char(*c), &Mapping::Valid);
}
}
}

15256
zeroidc/vendor/idna/src/uts46_mapping_table.rs vendored Normal file
View File

File diff suppressed because it is too large Load Diff

6334
zeroidc/vendor/idna/tests/IdnaTestV2.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

77
zeroidc/vendor/idna/tests/punycode.rs vendored Normal file
View File

@@ -0,0 +1,77 @@
// Copyright 2013 The rust-url developers.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
use crate::test::TestFn;
use idna::punycode::{decode, encode_str};
use serde_json::map::Map;
use serde_json::Value;
use std::str::FromStr;
fn one_test(decoded: &str, encoded: &str) {
match decode(encoded) {
None => panic!("Decoding {} failed.", encoded),
Some(result) => {
let result = result.into_iter().collect::<String>();
assert!(
result == decoded,
"Incorrect decoding of \"{}\":\n \"{}\"\n!= \"{}\"\n",
encoded,
result,
decoded
)
}
}
match encode_str(decoded) {
None => panic!("Encoding {} failed.", decoded),
Some(result) => assert!(
result == encoded,
"Incorrect encoding of \"{}\":\n \"{}\"\n!= \"{}\"\n",
decoded,
result,
encoded
),
}
}
fn get_string<'a>(map: &'a Map<String, Value>, key: &str) -> &'a str {
match map.get(&key.to_string()) {
Some(&Value::String(ref s)) => s,
None => "",
_ => panic!(),
}
}
pub fn collect_tests<F: FnMut(String, TestFn)>(add_test: &mut F) {
match Value::from_str(include_str!("punycode_tests.json")) {
Ok(Value::Array(tests)) => {
for (i, test) in tests.into_iter().enumerate() {
match test {
Value::Object(o) => {
let test_name = {
let desc = get_string(&o, "description");
if desc.is_empty() {
format!("Punycode {}", i + 1)
} else {
format!("Punycode {}: {}", i + 1, desc)
}
};
add_test(
test_name,
TestFn::dyn_test_fn(move || {
one_test(get_string(&o, "decoded"), get_string(&o, "encoded"))
}),
)
}
_ => panic!(),
}
}
}
other => panic!("{:?}", other),
}
}

120
zeroidc/vendor/idna/tests/punycode_tests.json vendored Normal file
View File

@@ -0,0 +1,120 @@
[
{
"description": "These tests are copied from https://github.com/bestiejs/punycode.js/blob/master/tests/tests.js , used under the MIT license.",
"decoded": "",
"encoded": ""
},
{
"description": "a single basic code point",
"decoded": "Bach",
"encoded": "Bach-"
},
{
"description": "a single non-ASCII character",
"decoded": "\u00FC",
"encoded": "tda"
},
{
"description": "multiple non-ASCII characters",
"decoded": "\u00FC\u00EB\u00E4\u00F6\u2665",
"encoded": "4can8av2009b"
},
{
"description": "mix of ASCII and non-ASCII characters",
"decoded": "b\u00FCcher",
"encoded": "bcher-kva"
},
{
"description": "long string with both ASCII and non-ASCII characters",
"decoded": "Willst du die Bl\u00FCthe des fr\u00FChen, die Fr\u00FCchte des sp\u00E4teren Jahres",
"encoded": "Willst du die Blthe des frhen, die Frchte des spteren Jahres-x9e96lkal"
},
{
"description": "Arabic (Egyptian)",
"decoded": "\u0644\u064A\u0647\u0645\u0627\u0628\u062A\u0643\u0644\u0645\u0648\u0634\u0639\u0631\u0628\u064A\u061F",
"encoded": "egbpdaj6bu4bxfgehfvwxn"
},
{
"description": "Chinese (simplified)",
"decoded": "\u4ED6\u4EEC\u4E3A\u4EC0\u4E48\u4E0D\u8BF4\u4E2d\u6587",
"encoded": "ihqwcrb4cv8a8dqg056pqjye"
},
{
"description": "Chinese (traditional)",
"decoded": "\u4ED6\u5011\u7232\u4EC0\u9EBD\u4E0D\u8AAA\u4E2D\u6587",
"encoded": "ihqwctvzc91f659drss3x8bo0yb"
},
{
"description": "Czech",
"decoded": "Pro\u010Dprost\u011Bnemluv\u00ED\u010Desky",
"encoded": "Proprostnemluvesky-uyb24dma41a"
},
{
"description": "Hebrew",
"decoded": "\u05DC\u05DE\u05D4\u05D4\u05DD\u05E4\u05E9\u05D5\u05D8\u05DC\u05D0\u05DE\u05D3\u05D1\u05E8\u05D9\u05DD\u05E2\u05D1\u05E8\u05D9\u05EA",
"encoded": "4dbcagdahymbxekheh6e0a7fei0b"
},
{
"description": "Hindi (Devanagari)",
"decoded": "\u092F\u0939\u0932\u094B\u0917\u0939\u093F\u0928\u094D\u0926\u0940\u0915\u094D\u092F\u094B\u0902\u0928\u0939\u0940\u0902\u092C\u094B\u0932\u0938\u0915\u0924\u0947\u0939\u0948\u0902",
"encoded": "i1baa7eci9glrd9b2ae1bj0hfcgg6iyaf8o0a1dig0cd"
},
{
"description": "Japanese (kanji and hiragana)",
"decoded": "\u306A\u305C\u307F\u3093\u306A\u65E5\u672C\u8A9E\u3092\u8A71\u3057\u3066\u304F\u308C\u306A\u3044\u306E\u304B",
"encoded": "n8jok5ay5dzabd5bym9f0cm5685rrjetr6pdxa"
},
{
"description": "Korean (Hangul syllables)",
"decoded": "\uC138\uACC4\uC758\uBAA8\uB4E0\uC0AC\uB78C\uB4E4\uC774\uD55C\uAD6D\uC5B4\uB97C\uC774\uD574\uD55C\uB2E4\uBA74\uC5BC\uB9C8\uB098\uC88B\uC744\uAE4C",
"encoded": "989aomsvi5e83db1d2a355cv1e0vak1dwrv93d5xbh15a0dt30a5jpsd879ccm6fea98c"
},
{
"description": "Russian (Cyrillic)",
"decoded": "\u043F\u043E\u0447\u0435\u043C\u0443\u0436\u0435\u043E\u043D\u0438\u043D\u0435\u0433\u043E\u0432\u043E\u0440\u044F\u0442\u043F\u043E\u0440\u0443\u0441\u0441\u043A\u0438",
"encoded": "b1abfaaepdrnnbgefbadotcwatmq2g4l"
},
{
"description": "Spanish",
"decoded": "Porqu\u00E9nopuedensimplementehablarenEspa\u00F1ol",
"encoded": "PorqunopuedensimplementehablarenEspaol-fmd56a"
},
{
"description": "Vietnamese",
"decoded": "T\u1EA1isaoh\u1ECDkh\u00F4ngth\u1EC3ch\u1EC9n\u00F3iti\u1EBFngVi\u1EC7t",
"encoded": "TisaohkhngthchnitingVit-kjcr8268qyxafd2f1b9g"
},
{
"decoded": "3\u5E74B\u7D44\u91D1\u516B\u5148\u751F",
"encoded": "3B-ww4c5e180e575a65lsy2b"
},
{
"decoded": "\u5B89\u5BA4\u5948\u7F8E\u6075-with-SUPER-MONKEYS",
"encoded": "-with-SUPER-MONKEYS-pc58ag80a8qai00g7n9n"
},
{
"decoded": "Hello-Another-Way-\u305D\u308C\u305E\u308C\u306E\u5834\u6240",
"encoded": "Hello-Another-Way--fc4qua05auwb3674vfr0b"
},
{
"decoded": "\u3072\u3068\u3064\u5C4B\u6839\u306E\u4E0B2",
"encoded": "2-u9tlzr9756bt3uc0v"
},
{
"decoded": "Maji\u3067Koi\u3059\u308B5\u79D2\u524D",
"encoded": "MajiKoi5-783gue6qz075azm5e"
},
{
"decoded": "\u30D1\u30D5\u30A3\u30FCde\u30EB\u30F3\u30D0",
"encoded": "de-jg4avhby1noc0d"
},
{
"decoded": "\u305D\u306E\u30B9\u30D4\u30FC\u30C9\u3067",
"encoded": "d9juau41awczczp"
},
{
"description": "ASCII string that breaks the existing rules for host-name labels (It's not a realistic example for IDNA, because IDNA never encodes pure ASCII labels.)",
"decoded": "-> $1.00 <-",
"encoded": "-> $1.00 <--"
}
]

19
zeroidc/vendor/idna/tests/tests.rs vendored Normal file
View File

@@ -0,0 +1,19 @@
use rustc_test as test;
mod punycode;
mod uts46;
fn main() {
let mut tests = Vec::new();
{
let mut add_test = |name, run| {
tests.push(test::TestDescAndFn {
desc: test::TestDesc::new(test::DynTestName(name)),
testfn: run,
})
};
punycode::collect_tests(&mut add_test);
uts46::collect_tests(&mut add_test);
}
test::test_main(&std::env::args().collect::<Vec<_>>(), tests)
}

139
zeroidc/vendor/idna/tests/unit.rs vendored Normal file
View File

@@ -0,0 +1,139 @@
use assert_matches::assert_matches;
use unicode_normalization::char::is_combining_mark;
/// https://github.com/servo/rust-url/issues/373
#[test]
fn test_punycode_prefix_with_length_check() {
let config = idna::Config::default()
.verify_dns_length(true)
.check_hyphens(true)
.use_std3_ascii_rules(true);
assert!(config.to_ascii("xn--").is_err());
assert!(config.to_ascii("xn---").is_err());
assert!(config.to_ascii("xn-----").is_err());
assert!(config.to_ascii("xn--.").is_err());
assert!(config.to_ascii("xn--...").is_err());
assert!(config.to_ascii(".xn--").is_err());
assert!(config.to_ascii("...xn--").is_err());
assert!(config.to_ascii("xn--.xn--").is_err());
assert!(config.to_ascii("xn--.example.org").is_err());
}
/// https://github.com/servo/rust-url/issues/373
#[test]
fn test_punycode_prefix_without_length_check() {
let config = idna::Config::default()
.verify_dns_length(false)
.check_hyphens(true)
.use_std3_ascii_rules(true);
assert_eq!(config.to_ascii("xn--").unwrap(), "");
assert!(config.to_ascii("xn---").is_err());
assert!(config.to_ascii("xn-----").is_err());
assert_eq!(config.to_ascii("xn--.").unwrap(), ".");
assert_eq!(config.to_ascii("xn--...").unwrap(), "...");
assert_eq!(config.to_ascii(".xn--").unwrap(), ".");
assert_eq!(config.to_ascii("...xn--").unwrap(), "...");
assert_eq!(config.to_ascii("xn--.xn--").unwrap(), ".");
assert_eq!(config.to_ascii("xn--.example.org").unwrap(), ".example.org");
}
// http://www.unicode.org/reports/tr46/#Table_Example_Processing
#[test]
fn test_examples() {
let mut codec = idna::Idna::default();
let mut out = String::new();
assert_matches!(codec.to_unicode("Bloß.de", &mut out), Ok(()));
assert_eq!(out, "bloß.de");
out.clear();
assert_matches!(codec.to_unicode("xn--blo-7ka.de", &mut out), Ok(()));
assert_eq!(out, "bloß.de");
out.clear();
assert_matches!(codec.to_unicode("u\u{308}.com", &mut out), Ok(()));
assert_eq!(out, "ü.com");
out.clear();
assert_matches!(codec.to_unicode("xn--tda.com", &mut out), Ok(()));
assert_eq!(out, "ü.com");
out.clear();
assert_matches!(codec.to_unicode("xn--u-ccb.com", &mut out), Err(_));
out.clear();
assert_matches!(codec.to_unicode("a⒈com", &mut out), Err(_));
out.clear();
assert_matches!(codec.to_unicode("xn--a-ecp.ru", &mut out), Err(_));
out.clear();
assert_matches!(codec.to_unicode("xn--0.pt", &mut out), Err(_));
out.clear();
assert_matches!(codec.to_unicode("日本語。ＪＰ", &mut out), Ok(()));
assert_eq!(out, "日本語.jp");
out.clear();
assert_matches!(codec.to_unicode("☕.us", &mut out), Ok(()));
assert_eq!(out, "☕.us");
}
#[test]
fn test_v5() {
let config = idna::Config::default()
.verify_dns_length(true)
.use_std3_ascii_rules(true);
// IdnaTest:784 蔏｡𑰺
assert!(is_combining_mark('\u{11C3A}'));
assert!(config.to_ascii("\u{11C3A}").is_err());
assert!(config.to_ascii("\u{850f}.\u{11C3A}").is_err());
assert!(config.to_ascii("\u{850f}\u{ff61}\u{11C3A}").is_err());
}
#[test]
fn test_v8_bidi_rules() {
let config = idna::Config::default()
.verify_dns_length(true)
.use_std3_ascii_rules(true);
assert_eq!(config.to_ascii("abc").unwrap(), "abc");
assert_eq!(config.to_ascii("123").unwrap(), "123");
assert_eq!(config.to_ascii("אבּג").unwrap(), "xn--kdb3bdf");
assert_eq!(config.to_ascii("ابج").unwrap(), "xn--mgbcm");
assert_eq!(config.to_ascii("abc.ابج").unwrap(), "abc.xn--mgbcm");
assert_eq!(config.to_ascii("אבּג.ابج").unwrap(), "xn--kdb3bdf.xn--mgbcm");
// Bidi domain names cannot start with digits
assert!(config.to_ascii("0a.\u{05D0}").is_err());
assert!(config.to_ascii("0à.\u{05D0}").is_err());
// Bidi chars may be punycode-encoded
assert!(config.to_ascii("xn--0ca24w").is_err());
}
#[test]
fn emoji_domains() {
// HOT BEVERAGE is allowed here...
let config = idna::Config::default()
.verify_dns_length(true)
.use_std3_ascii_rules(true);
assert_eq!(config.to_ascii("☕.com").unwrap(), "xn--53h.com");
// ... but not here
let config = idna::Config::default()
.verify_dns_length(true)
.use_std3_ascii_rules(true)
.use_idna_2008_rules(true);
let error = format!("{:?}", config.to_ascii("☕.com").unwrap_err());
assert!(error.contains("disallowed_in_idna_2008"));
}
#[test]
fn unicode_before_delimiter() {
let config = idna::Config::default();
assert!(config.to_ascii("xn--f\u{34a}-PTP").is_err());
}

193
zeroidc/vendor/idna/tests/uts46.rs vendored Normal file
View File

@@ -0,0 +1,193 @@
// Copyright 2013-2014 The rust-url developers.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
use crate::test::TestFn;
use std::char;
use idna::Errors;
pub fn collect_tests<F: FnMut(String, TestFn)>(add_test: &mut F) {
// https://www.unicode.org/Public/idna/13.0.0/IdnaTestV2.txt
for (i, line) in include_str!("IdnaTestV2.txt").lines().enumerate() {
if line.is_empty() || line.starts_with('#') {
continue;
}
// Remove comments
let line = match line.find('#') {
Some(index) => &line[0..index],
None => line,
};
let mut pieces = line.split(';').map(|x| x.trim()).collect::<Vec<&str>>();
let source = unescape(&pieces.remove(0));
// ToUnicode
let mut to_unicode = unescape(&pieces.remove(0));
if to_unicode.is_empty() {
to_unicode = source.clone();
}
let to_unicode_status = status(pieces.remove(0));
// ToAsciiN
let to_ascii_n = pieces.remove(0);
let to_ascii_n = if to_ascii_n.is_empty() {
to_unicode.clone()
} else {
to_ascii_n.to_owned()
};
let to_ascii_n_status = pieces.remove(0);
let to_ascii_n_status = if to_ascii_n_status.is_empty() {
to_unicode_status.clone()
} else {
status(to_ascii_n_status)
};
// ToAsciiT
let to_ascii_t = pieces.remove(0);
let to_ascii_t = if to_ascii_t.is_empty() {
to_ascii_n.clone()
} else {
to_ascii_t.to_owned()
};
let to_ascii_t_status = pieces.remove(0);
let to_ascii_t_status = if to_ascii_t_status.is_empty() {
to_ascii_n_status.clone()
} else {
status(to_ascii_t_status)
};
let test_name = format!("UTS #46 line {}", i + 1);
add_test(
test_name,
TestFn::dyn_test_fn(move || {
let config = idna::Config::default()
.use_std3_ascii_rules(true)
.verify_dns_length(true)
.check_hyphens(true);
// http://unicode.org/reports/tr46/#Deviations
// applications that perform IDNA2008 lookup are not required to check
// for these contexts, so we skip all tests annotated with C*
// Everybody ignores V2
// https://github.com/servo/rust-url/pull/240
// https://github.com/whatwg/url/issues/53#issuecomment-181528158
// http://www.unicode.org/review/pri317/
// "The special error codes X3 and X4_2 are now returned where a toASCII error code
// was formerly being generated in toUnicode due to an empty label."
// This is not implemented yet, so we skip toUnicode X4_2 tests for now, too.
let (to_unicode_value, to_unicode_result) =
config.transitional_processing(false).to_unicode(&source);
let to_unicode_result = to_unicode_result.map(|()| to_unicode_value);
check(
&source,
(&to_unicode, &to_unicode_status),
to_unicode_result,
|e| e.starts_with('C') || e == "V2" || e == "X4_2",
);
let to_ascii_n_result = config.transitional_processing(false).to_ascii(&source);
check(
&source,
(&to_ascii_n, &to_ascii_n_status),
to_ascii_n_result,
|e| e.starts_with('C') || e == "V2",
);
let to_ascii_t_result = config.transitional_processing(true).to_ascii(&source);
check(
&source,
(&to_ascii_t, &to_ascii_t_status),
to_ascii_t_result,
|e| e.starts_with('C') || e == "V2",
);
}),
)
}
}
#[allow(clippy::redundant_clone)]
fn check<F>(source: &str, expected: (&str, &[&str]), actual: Result<String, Errors>, ignore: F)
where
F: Fn(&str) -> bool,
{
if !expected.1.is_empty() {
if !expected.1.iter().copied().any(ignore) {
let res = actual.ok();
assert_eq!(
res.clone(),
None,
"Expected error {:?}. result: {} | source: {}",
expected.1,
res.unwrap(),
source,
);
}
} else {
assert!(
actual.is_ok(),
"Couldn't parse {} | error: {:?}",
source,
actual.err().unwrap(),
);
assert_eq!(actual.unwrap(), expected.0, "source: {}", source);
}
}
fn unescape(input: &str) -> String {
let mut output = String::new();
let mut chars = input.chars();
loop {
match chars.next() {
None => return output,
Some(c) => {
if c == '\\' {
match chars.next().unwrap() {
'\\' => output.push('\\'),
'u' => {
let c1 = chars.next().unwrap().to_digit(16).unwrap();
let c2 = chars.next().unwrap().to_digit(16).unwrap();
let c3 = chars.next().unwrap().to_digit(16).unwrap();
let c4 = chars.next().unwrap().to_digit(16).unwrap();
match char::from_u32(((c1 * 16 + c2) * 16 + c3) * 16 + c4) {
Some(c) => output.push(c),
None => {
output
.push_str(&format!("\\u{:X}{:X}{:X}{:X}", c1, c2, c3, c4));
}
};
}
_ => panic!("Invalid test data input"),
}
} else {
output.push(c);
}
}
}
}
}
fn status(status: &str) -> Vec<&str> {
if status.is_empty() || status == "[]" {
return Vec::new();
}
let mut result = status.split(", ").collect::<Vec<_>>();
assert!(result[0].starts_with('['));
result[0] = &result[0][1..];
let idx = result.len() - 1;
let last = &mut result[idx];
assert!(last.ends_with(']'));
*last = &last[..last.len() - 1];
result
}