DeCarabas/oden
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Vendor things

Browse source
This commit is contained in:
John Doty 2024-03-08 11:03:01 -08:00
parent 5deceec006
commit 977e3c17e5
19434 changed files with 10682014 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
third-party/vendor/data-url/.cargo-checksum.json vendored Normal file
View file

@ -0,0 +1 @@
{"files":{"Cargo.toml":"4fed6a74fde6f148669afe2beb144c87d3ba4562de11f8e86a2d4626dd54166b","LICENSE-APACHE":"a60eea817514531668d7e00765731449fe14d059d3249e0bc93b36de45f759f2","LICENSE-MIT":"76e972ac0f4ddb116e86e10100132a783931a596e7b9872eaa31be15cd4d751d","README.md":"a8f13b4b8701f2d546f7372d4b68a267da408f7ebecbafe28a1c2e8b92a774a1","src/forgiving_base64.rs":"dd2ce59aa0f209bdc9bdf82c67b0ea69e4576cb100850ae4c4e3b8f03ef31814","src/lib.rs":"6a0ccc483e4293ce6ef075352ebb718abc7b252ee7157584b20ad5b21e4261b7","src/make_base64_decode_table.py":"b7ee1b1aaa5579b6e14caae0ef7b84695a04c77048978384ffe031fc8d29d2b1","src/mime.rs":"de276878412f2a852281531454af97353d33ea3c3a64f9eef865562c3015172e","tests/base64.json":"0cdb75b4fcc46e4a6caa0e3b0005157a0d0be03e00bcf7b7054a045b1267568d","tests/data-urls.json":"b3be3d6e1d0eb7f1b5b20d7410d30cb76216d41c9fe3d8364446abecff88bba5","tests/generated-mime-types.json":"20924495060ac9633f10d57a326b95a5987863f27c5d4765b13b744304b33fed","tests/mime-types.json":"2151572862191efd4d5b46e12a586242ce1470b32b0fb62b2c9f4f6ea8c613aa","tests/wpt.rs":"22768dc0e24c735e02974fea8a53ad82f74e171843c94c47d4d7d4abfa4b8ccc"},"package":"5c297a1c74b71ae29df00c3e22dd9534821d60eb9af5a0192823fa2acea70c2a"}

48
third-party/vendor/data-url/Cargo.toml vendored Normal file
View file

@ -0,0 +1,48 @@
# 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 are reading this file be aware that the original Cargo.toml
# will likely look very different (and much more reasonable).
# See Cargo.toml.orig for the original contents.
[package]
edition = "2018"
rust-version = "1.51"
name = "data-url"
version = "0.3.1"
authors = ["Simon Sapin <simon.sapin@exyr.org>"]
autotests = false
description = "Processing of data: URL according to WHATWG’s Fetch Standard"
readme = "README.md"
categories = ["no_std"]
license = "MIT OR Apache-2.0"
repository = "https://github.com/servo/rust-url"
[package.metadata.docs.rs]
rustdoc-args = ["--generate-link-to-definition"]
[lib]
test = false
[[test]]
name = "wpt"
harness = false
[dev-dependencies.serde]
version = "1.0"
features = ["derive"]
[dev-dependencies.serde_json]
version = "1.0"
[dev-dependencies.tester]
version = "0.9"
[features]
alloc = []
default = ["std"]
std = ["alloc"]

201
third-party/vendor/data-url/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
third-party/vendor/data-url/LICENSE-MIT vendored Normal file
View file

@ -0,0 +1,25 @@
Copyright (c) 2013-2022 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.

21
third-party/vendor/data-url/README.md vendored Normal file
View file

@ -0,0 +1,21 @@
# data-url
[![crates.io](https://img.shields.io/crates/v/data-url.svg)](https://crates.io/crates/data-url)
[![docs.rs](https://img.shields.io/badge/docs.rs-%F0%9F%93%84-blue.svg)](https://docs.rs/data-url/)
Processing of `data:` URLs in Rust according to the Fetch Standard:
<https://fetch.spec.whatwg.org/#data-urls>
but starting from a string rather than a parsed URL to avoid extra copies.
```rust
use data_url::{DataUrl, mime};
let url = DataUrl::process("data:,Hello%20World!").unwrap();
let (body, fragment) = url.decode_to_vec().unwrap();
assert_eq!(url.mime_type().type_, "text");
assert_eq!(url.mime_type().subtype, "plain");
assert_eq!(url.mime_type().get_parameter("charset"), Some("US-ASCII"));
assert_eq!(body, b"Hello World!");
assert!(fragment.is_none());
```

201
third-party/vendor/data-url/src/forgiving_base64.rs vendored Normal file
View file

@ -0,0 +1,201 @@
//! <https://infra.spec.whatwg.org/#forgiving-base64-decode>
use alloc::vec::Vec;
use core::fmt;
#[derive(Debug)]
pub struct InvalidBase64(InvalidBase64Details);
impl fmt::Display for InvalidBase64 {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self.0 {
InvalidBase64Details::UnexpectedSymbol(code_point) => {
write!(f, "symbol with codepoint {} not expected", code_point)
}
InvalidBase64Details::AlphabetSymbolAfterPadding => {
write!(f, "alphabet symbol present after padding")
}
InvalidBase64Details::LoneAlphabetSymbol => write!(f, "lone alphabet symbol present"),
InvalidBase64Details::Padding => write!(f, "incorrect padding"),
}
}
}
#[cfg(feature = "std")]
impl std::error::Error for InvalidBase64 {}
#[derive(Debug)]
enum InvalidBase64Details {
UnexpectedSymbol(u8),
AlphabetSymbolAfterPadding,
LoneAlphabetSymbol,
Padding,
}
#[derive(Debug)]
pub enum DecodeError<E> {
InvalidBase64(InvalidBase64),
WriteError(E),
}
impl<E: fmt::Display> fmt::Display for DecodeError<E> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self {
Self::InvalidBase64(inner) => write!(f, "base64 not valid: {}", inner),
Self::WriteError(err) => write!(f, "write error: {}", err),
}
}
}
#[cfg(feature = "std")]
impl<E: std::error::Error> std::error::Error for DecodeError<E> {}
impl<E> From<InvalidBase64Details> for DecodeError<E> {
fn from(e: InvalidBase64Details) -> Self {
DecodeError::InvalidBase64(InvalidBase64(e))
}
}
pub(crate) enum Impossible {}
impl From<DecodeError<Impossible>> for InvalidBase64 {
fn from(e: DecodeError<Impossible>) -> Self {
match e {
DecodeError::InvalidBase64(e) => e,
DecodeError::WriteError(e) => match e {},
}
}
}
/// `input` is assumed to be in an ASCII-compatible encoding
pub fn decode_to_vec(input: &[u8]) -> Result<Vec<u8>, InvalidBase64> {
let mut v = Vec::new();
{
let mut decoder = Decoder::new(|bytes| {
v.extend_from_slice(bytes);
Ok(())
});
decoder.feed(input)?;
decoder.finish()?;
}
Ok(v)
}
/// <https://infra.spec.whatwg.org/#forgiving-base64-decode>
pub struct Decoder<F, E>
where
F: FnMut(&[u8]) -> Result<(), E>,
{
write_bytes: F,
bit_buffer: u32,
buffer_bit_length: u8,
padding_symbols: u8,
}
impl<F, E> Decoder<F, E>
where
F: FnMut(&[u8]) -> Result<(), E>,
{
pub fn new(write_bytes: F) -> Self {
Self {
write_bytes,
bit_buffer: 0,
buffer_bit_length: 0,
padding_symbols: 0,
}
}
/// Feed to the decoder partial input in an ASCII-compatible encoding
pub fn feed(&mut self, input: &[u8]) -> Result<(), DecodeError<E>> {
for &byte in input.iter() {
let value = BASE64_DECODE_TABLE[byte as usize];
if value < 0 {
// A character that’s not part of the alphabet
// Remove ASCII whitespace
if matches!(byte, b' ' | b'\t' | b'\n' | b'\r' | b'\x0C') {
continue;
}
if byte == b'=' {
self.padding_symbols = self.padding_symbols.saturating_add(1);
continue;
}
return Err(InvalidBase64Details::UnexpectedSymbol(byte).into());
}
if self.padding_symbols > 0 {
return Err(InvalidBase64Details::AlphabetSymbolAfterPadding.into());
}
self.bit_buffer <<= 6;
self.bit_buffer |= value as u32;
// 18 before incrementing means we’ve just reached 24
if self.buffer_bit_length < 18 {
self.buffer_bit_length += 6;
} else {
// We’ve accumulated four times 6 bits, which equals three times 8 bits.
let byte_buffer = [
(self.bit_buffer >> 16) as u8,
(self.bit_buffer >> 8) as u8,
self.bit_buffer as u8,
];
(self.write_bytes)(&byte_buffer).map_err(DecodeError::WriteError)?;
self.buffer_bit_length = 0;
// No need to reset bit_buffer,
// since next time we’re only gonna read relevant bits.
}
}
Ok(())
}
/// Call this to signal the end of the input
pub fn finish(mut self) -> Result<(), DecodeError<E>> {
match (self.buffer_bit_length, self.padding_symbols) {
(0, 0) => {
// A multiple of four of alphabet symbols, and nothing else.
}
(12, 2) | (12, 0) => {
// A multiple of four of alphabet symbols, followed by two more symbols,
// optionally followed by two padding characters (which make a total multiple of four).
let byte_buffer = [(self.bit_buffer >> 4) as u8];
(self.write_bytes)(&byte_buffer).map_err(DecodeError::WriteError)?;
}
(18, 1) | (18, 0) => {
// A multiple of four of alphabet symbols, followed by three more symbols,
// optionally followed by one padding character (which make a total multiple of four).
let byte_buffer = [(self.bit_buffer >> 10) as u8, (self.bit_buffer >> 2) as u8];
(self.write_bytes)(&byte_buffer).map_err(DecodeError::WriteError)?;
}
(6, _) => return Err(InvalidBase64Details::LoneAlphabetSymbol.into()),
_ => return Err(InvalidBase64Details::Padding.into()),
}
Ok(())
}
}
/// Generated by `make_base64_decode_table.py` based on "Table 1: The Base 64 Alphabet"
/// at <https://tools.ietf.org/html/rfc4648#section-4>
///
/// Array indices are the byte value of symbols.
/// Array values are their positions in the base64 alphabet,
/// or -1 for symbols not in the alphabet.
/// The position contributes 6 bits to the decoded bytes.
#[rustfmt::skip]
const BASE64_DECODE_TABLE: [i8; 256] = [
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 62, -1, -1, -1, 63,
52, 53, 54, 55, 56, 57, 58, 59, 60, 61, -1, -1, -1, -1, -1, -1,
-1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, -1, -1, -1, -1, -1,
-1, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40,
41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
];

347
third-party/vendor/data-url/src/lib.rs vendored Normal file
View file

@ -0,0 +1,347 @@
//! Processing of `data:` URLs according to the Fetch Standard:
//! <https://fetch.spec.whatwg.org/#data-urls>
//! but starting from a string rather than a parsed URL to avoid extra copies.
//!
//! ```rust
//! use data_url::{DataUrl, mime};
//!
//! let url = DataUrl::process("data:,Hello%20World!").unwrap();
//! let (body, fragment) = url.decode_to_vec().unwrap();
//!
//! assert_eq!(url.mime_type().type_, "text");
//! assert_eq!(url.mime_type().subtype, "plain");
//! assert_eq!(url.mime_type().get_parameter("charset"), Some("US-ASCII"));
//! assert_eq!(body, b"Hello World!");
//! assert!(fragment.is_none());
//! ```
#![no_std]
// For forwards compatibility
#[cfg(feature = "std")]
extern crate std;
#[macro_use]
extern crate alloc;
#[cfg(not(feature = "alloc"))]
compile_error!("the `alloc` feature must be enabled");
use alloc::{string::String, vec::Vec};
use core::fmt;
macro_rules! require {
($condition: expr) => {
if !$condition {
return None;
}
};
}
pub mod forgiving_base64;
pub mod mime;
pub struct DataUrl<'a> {
mime_type: mime::Mime,
base64: bool,
encoded_body_plus_fragment: &'a str,
}
#[derive(Debug)]
pub enum DataUrlError {
NotADataUrl,
NoComma,
}
impl fmt::Display for DataUrlError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self {
Self::NotADataUrl => write!(f, "not a valid data url"),
Self::NoComma => write!(
f,
"data url is missing comma delimiting attributes and body"
),
}
}
}
#[cfg(feature = "std")]
impl std::error::Error for DataUrlError {}
impl<'a> DataUrl<'a> {
/// <https://fetch.spec.whatwg.org/#data-url-processor>
/// but starting from a string rather than a parsed `Url`, to avoid extra string copies.
pub fn process(input: &'a str) -> Result<Self, DataUrlError> {
use crate::DataUrlError::*;
let after_colon = pretend_parse_data_url(input).ok_or(NotADataUrl)?;
let (from_colon_to_comma, encoded_body_plus_fragment) =
find_comma_before_fragment(after_colon).ok_or(NoComma)?;
let (mime_type, base64) = parse_header(from_colon_to_comma);
Ok(DataUrl {
mime_type,
base64,
encoded_body_plus_fragment,
})
}
pub fn mime_type(&self) -> &mime::Mime {
&self.mime_type
}
/// Streaming-decode the data URL’s body to `write_body_bytes`,
/// and return the URL’s fragment identifier if it has one.
pub fn decode<F, E>(
&self,
write_body_bytes: F,
) -> Result<Option<FragmentIdentifier<'a>>, forgiving_base64::DecodeError<E>>
where
F: FnMut(&[u8]) -> Result<(), E>,
{
if self.base64 {
decode_with_base64(self.encoded_body_plus_fragment, write_body_bytes)
} else {
decode_without_base64(self.encoded_body_plus_fragment, write_body_bytes)
.map_err(forgiving_base64::DecodeError::WriteError)
}
}
/// Return the decoded body, and the URL’s fragment identifier if it has one.
pub fn decode_to_vec(
&self,
) -> Result<(Vec<u8>, Option<FragmentIdentifier<'a>>), forgiving_base64::InvalidBase64> {
let mut body = Vec::new();
let fragment = self.decode(|bytes| {
body.extend_from_slice(bytes);
Ok(())
})?;
Ok((body, fragment))
}
}
/// The URL’s fragment identifier (after `#`)
pub struct FragmentIdentifier<'a>(&'a str);
impl<'a> FragmentIdentifier<'a> {
/// Like in a parsed URL
pub fn to_percent_encoded(&self) -> String {
let mut string = String::new();
for byte in self.0.bytes() {
match byte {
// Ignore ASCII tabs or newlines like the URL parser would
b'\t' | b'\n' | b'\r' => continue,
// https://url.spec.whatwg.org/#fragment-percent-encode-set
b'\0'..=b' ' | b'"' | b'<' | b'>' | b'`' | b'\x7F'..=b'\xFF' => {
percent_encode(byte, &mut string)
}
// Printable ASCII
_ => string.push(byte as char),
}
}
string
}
}
/// Similar to <https://url.spec.whatwg.org/#concept-basic-url-parser>
/// followed by <https://url.spec.whatwg.org/#concept-url-serializer>
///
/// * `None`: not a data URL.
///
/// * `Some(s)`: sort of the result of serialization, except:
///
/// - `data:` prefix removed
/// - The fragment is included
/// - Other components are **not** UTF-8 percent-encoded
/// - ASCII tabs and newlines in the middle are **not** removed
fn pretend_parse_data_url(input: &str) -> Option<&str> {
// Trim C0 control or space
let left_trimmed = input.trim_start_matches(|ch| ch <= ' ');
let mut bytes = left_trimmed.bytes();
{
// Ignore ASCII tabs or newlines like the URL parser would
let mut iter = bytes
.by_ref()
.filter(|&byte| !matches!(byte, b'\t' | b'\n' | b'\r'));
require!(iter.next()?.to_ascii_lowercase() == b'd');
require!(iter.next()?.to_ascii_lowercase() == b'a');
require!(iter.next()?.to_ascii_lowercase() == b't');
require!(iter.next()?.to_ascii_lowercase() == b'a');
require!(iter.next()? == b':');
}
let bytes_consumed = left_trimmed.len() - bytes.len();
let after_colon = &left_trimmed[bytes_consumed..];
// Trim C0 control or space
Some(after_colon.trim_end_matches(|ch| ch <= ' '))
}
fn find_comma_before_fragment(after_colon: &str) -> Option<(&str, &str)> {
for (i, byte) in after_colon.bytes().enumerate() {
if byte == b',' {
return Some((&after_colon[..i], &after_colon[i + 1..]));
}
if byte == b'#' {
break;
}
}
None
}
fn parse_header(from_colon_to_comma: &str) -> (mime::Mime, bool) {
// "Strip leading and trailing ASCII whitespace"
// \t, \n, and \r would have been filtered by the URL parser
// \f percent-encoded by the URL parser
// space is the only remaining ASCII whitespace
let trimmed = from_colon_to_comma.trim_matches(|c| matches!(c, ' ' | '\t' | '\n' | '\r'));
let without_base64_suffix = remove_base64_suffix(trimmed);
let base64 = without_base64_suffix.is_some();
let mime_type = without_base64_suffix.unwrap_or(trimmed);
let mut string = String::new();
if mime_type.starts_with(';') {
string.push_str("text/plain")
}
let mut in_query = false;
for byte in mime_type.bytes() {
match byte {
// Ignore ASCII tabs or newlines like the URL parser would
b'\t' | b'\n' | b'\r' => continue,
// https://url.spec.whatwg.org/#c0-control-percent-encode-set
b'\0'..=b'\x1F' | b'\x7F'..=b'\xFF' => percent_encode(byte, &mut string),
// Bytes other than the C0 percent-encode set that are percent-encoded
// by the URL parser in the query state.
// '#' is also in that list but cannot occur here
// since it indicates the start of the URL’s fragment.
b' ' | b'"' | b'<' | b'>' if in_query => percent_encode(byte, &mut string),
b'?' => {
in_query = true;
string.push('?')
}
// Printable ASCII
_ => string.push(byte as char),
}
}
// FIXME: does Mime::from_str match the MIME Sniffing Standard’s parsing algorithm?
// <https://mimesniff.spec.whatwg.org/#parse-a-mime-type>
let mime_type = string.parse().unwrap_or_else(|_| mime::Mime {
type_: String::from("text"),
subtype: String::from("plain"),
parameters: vec![(String::from("charset"), String::from("US-ASCII"))],
});
(mime_type, base64)
}
/// None: no base64 suffix
#[allow(clippy::skip_while_next)]
fn remove_base64_suffix(s: &str) -> Option<&str> {
let mut bytes = s.bytes();
{
// Ignore ASCII tabs or newlines like the URL parser would
let iter = bytes
.by_ref()
.filter(|&byte| !matches!(byte, b'\t' | b'\n' | b'\r'));
// Search from the end
let mut iter = iter.rev();
require!(iter.next()? == b'4');
require!(iter.next()? == b'6');
require!(iter.next()?.to_ascii_lowercase() == b'e');
require!(iter.next()?.to_ascii_lowercase() == b's');
require!(iter.next()?.to_ascii_lowercase() == b'a');
require!(iter.next()?.to_ascii_lowercase() == b'b');
require!(iter.skip_while(|&byte| byte == b' ').next()? == b';');
}
Some(&s[..bytes.len()])
}
fn percent_encode(byte: u8, string: &mut String) {
const HEX_UPPER: [u8; 16] = *b"0123456789ABCDEF";
string.push('%');
string.push(HEX_UPPER[(byte >> 4) as usize] as char);
string.push(HEX_UPPER[(byte & 0x0f) as usize] as char);
}
/// This is <https://url.spec.whatwg.org/#string-percent-decode> while also:
///
/// * Ignoring ASCII tab or newlines
/// * Stopping at the first '#' (which indicates the start of the fragment)
///
/// Anything that would have been UTF-8 percent-encoded by the URL parser
/// would be percent-decoded here.
/// We skip that round-trip and pass it through unchanged.
fn decode_without_base64<F, E>(
encoded_body_plus_fragment: &str,
mut write_bytes: F,
) -> Result<Option<FragmentIdentifier<'_>>, E>
where
F: FnMut(&[u8]) -> Result<(), E>,
{
let bytes = encoded_body_plus_fragment.as_bytes();
let mut slice_start = 0;
for (i, &byte) in bytes.iter().enumerate() {
// We only need to look for 5 different "special" byte values.
// For everything else we make slices as large as possible, borrowing the input,
// in order to make fewer write_all() calls.
if matches!(byte, b'%' | b'#' | b'\t' | b'\n' | b'\r') {
// Write everything (if anything) "non-special" we’ve accumulated
// before this special byte
if i > slice_start {
write_bytes(&bytes[slice_start..i])?;
}
// Then deal with the special byte.
match byte {
b'%' => {
let l = bytes.get(i + 2).and_then(|&b| (b as char).to_digit(16));
let h = bytes.get(i + 1).and_then(|&b| (b as char).to_digit(16));
if let (Some(h), Some(l)) = (h, l) {
// '%' followed by two ASCII hex digits
let one_byte = h as u8 * 0x10 + l as u8;
write_bytes(&[one_byte])?;
slice_start = i + 3;
} else {
// Do nothing. Leave slice_start unchanged.
// The % sign will be part of the next slice.
}
}
b'#' => {
let fragment_start = i + 1;
let fragment = &encoded_body_plus_fragment[fragment_start..];
return Ok(Some(FragmentIdentifier(fragment)));
}
// Ignore over '\t' | '\n' | '\r'
_ => slice_start = i + 1,
}
}
}
write_bytes(&bytes[slice_start..])?;
Ok(None)
}
/// `decode_without_base64()` composed with
/// <https://infra.spec.whatwg.org/#isomorphic-decode> composed with
/// <https://infra.spec.whatwg.org/#forgiving-base64-decode>.
fn decode_with_base64<F, E>(
encoded_body_plus_fragment: &str,
write_bytes: F,
) -> Result<Option<FragmentIdentifier<'_>>, forgiving_base64::DecodeError<E>>
where
F: FnMut(&[u8]) -> Result<(), E>,
{
let mut decoder = forgiving_base64::Decoder::new(write_bytes);
let fragment = decode_without_base64(encoded_body_plus_fragment, |bytes| decoder.feed(bytes))?;
decoder.finish()?;
Ok(fragment)
}

19
third-party/vendor/data-url/src/make_base64_decode_table.py vendored Normal file
View file

@ -0,0 +1,19 @@
"""
Generate the BASE64_DECODE_TABLE constant. See its doc-comment.
"""
import string
# https://tools.ietf.org/html/rfc4648#section-4
alphabet = string.ascii_uppercase + string.ascii_lowercase + string.digits + "+/"
assert len(alphabet) == 64
reverse_table = [-1] * 256
for i, symbol in enumerate(alphabet):
reverse_table[ord(symbol)] = i
print("[")
per_line = 16
for line in range(0, 256, per_line):
print(" " + "".join(" %2s," % value for value in reverse_table[line:][:per_line]))
print("]")

207
third-party/vendor/data-url/src/mime.rs vendored Normal file
View file

@ -0,0 +1,207 @@
use alloc::{borrow::ToOwned, string::String, vec::Vec};
use core::fmt::{self, Write};
use core::str::FromStr;
/// <https://mimesniff.spec.whatwg.org/#mime-type-representation>
#[derive(Debug, PartialEq, Eq)]
pub struct Mime {
pub type_: String,
pub subtype: String,
/// (name, value)
pub parameters: Vec<(String, String)>,
}
impl Mime {
pub fn get_parameter<P>(&self, name: &P) -> Option<&str>
where
P: ?Sized + PartialEq<str>,
{
self.parameters
.iter()
.find(|&(n, _)| name == &**n)
.map(|(_, v)| &**v)
}
}
#[derive(Debug)]
pub struct MimeParsingError(());
impl fmt::Display for MimeParsingError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "invalid mime type")
}
}
#[cfg(feature = "std")]
impl std::error::Error for MimeParsingError {}
/// <https://mimesniff.spec.whatwg.org/#parsing-a-mime-type>
impl FromStr for Mime {
type Err = MimeParsingError;
fn from_str(s: &str) -> Result<Self, Self::Err> {
parse(s).ok_or(MimeParsingError(()))
}
}
fn parse(s: &str) -> Option<Mime> {
let trimmed = s.trim_matches(http_whitespace);
let (type_, rest) = split2(trimmed, '/');
require!(only_http_token_code_points(type_) && !type_.is_empty());
let (subtype, rest) = split2(rest?, ';');
let subtype = subtype.trim_end_matches(http_whitespace);
require!(only_http_token_code_points(subtype) && !subtype.is_empty());
let mut parameters = Vec::new();
if let Some(rest) = rest {
parse_parameters(rest, &mut parameters)
}
Some(Mime {
type_: type_.to_ascii_lowercase(),
subtype: subtype.to_ascii_lowercase(),
parameters,
})
}
fn split2(s: &str, separator: char) -> (&str, Option<&str>) {
let mut iter = s.splitn(2, separator);
let first = iter.next().unwrap();
(first, iter.next())
}
fn parse_parameters(s: &str, parameters: &mut Vec<(String, String)>) {
let mut semicolon_separated = s.split(';');
while let Some(piece) = semicolon_separated.next() {
let piece = piece.trim_start_matches(http_whitespace);
let (name, value) = split2(piece, '=');
// We can not early return on an invalid name here, because the value
// parsing later may consume more semicolon seperated pieces.
let name_valid =
!name.is_empty() && only_http_token_code_points(name) && !contains(parameters, name);
if let Some(value) = value {
let value = if let Some(stripped) = value.strip_prefix('"') {
let max_len = stripped.len().saturating_sub(1); // without end quote
let mut unescaped_value = String::with_capacity(max_len);
let mut chars = stripped.chars();
'until_closing_quote: loop {
while let Some(c) = chars.next() {
match c {
'"' => break 'until_closing_quote,
'\\' => unescaped_value.push(chars.next().unwrap_or_else(|| {
semicolon_separated
.next()
.map(|piece| {
// A semicolon inside a quoted value is not a separator
// for the next parameter, but part of the value.
chars = piece.chars();
';'
})
.unwrap_or('\\')
})),
_ => unescaped_value.push(c),
}
}
if let Some(piece) = semicolon_separated.next() {
// A semicolon inside a quoted value is not a separator
// for the next parameter, but part of the value.
unescaped_value.push(';');
chars = piece.chars()
} else {
break;
}
}
if !name_valid || !valid_value(value) {
continue;
}
unescaped_value
} else {
let value = value.trim_end_matches(http_whitespace);
if value.is_empty() {
continue;
}
if !name_valid || !valid_value(value) {
continue;
}
value.to_owned()
};
parameters.push((name.to_ascii_lowercase(), value))
}
}
}
fn contains(parameters: &[(String, String)], name: &str) -> bool {
parameters.iter().any(|(n, _)| n == name)
}
fn valid_value(s: &str) -> bool {
s.chars().all(|c| {
// <https://mimesniff.spec.whatwg.org/#http-quoted-string-token-code-point>
matches!(c, '\t' | ' '..='~' | '\u{80}'..='\u{FF}')
})
}
/// <https://mimesniff.spec.whatwg.org/#serializing-a-mime-type>
impl fmt::Display for Mime {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.write_str(&self.type_)?;
f.write_str("/")?;
f.write_str(&self.subtype)?;
for (name, value) in &self.parameters {
f.write_str(";")?;
f.write_str(name)?;
f.write_str("=")?;
if only_http_token_code_points(value) && !value.is_empty() {
f.write_str(value)?
} else {
f.write_str("\"")?;
for c in value.chars() {
if c == '"' || c == '\\' {
f.write_str("\\")?
}
f.write_char(c)?
}
f.write_str("\"")?
}
}
Ok(())
}
}
fn http_whitespace(c: char) -> bool {
matches!(c, ' ' | '\t' | '\n' | '\r')
}
fn only_http_token_code_points(s: &str) -> bool {
s.bytes().all(|byte| IS_HTTP_TOKEN[byte as usize])
}
macro_rules! byte_map {
($($flag:expr,)*) => ([
$($flag != 0,)*
])
}
// Copied from https://github.com/hyperium/mime/blob/v0.3.5/src/parse.rs#L293
#[rustfmt::skip]
static IS_HTTP_TOKEN: [bool; 256] = byte_map![
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
];

82
third-party/vendor/data-url/tests/base64.json vendored Normal file
View file

@ -0,0 +1,82 @@
[
["", []],
["abcd", [105, 183, 29]],
[" abcd", [105, 183, 29]],
["abcd ", [105, 183, 29]],
[" abcd===", null],
["abcd=== ", null],
["abcd ===", null],
["a", null],
["ab", [105]],
["abc", [105, 183]],
["abcde", null],
["𐀀", null],
["=", null],
["==", null],
["===", null],
["====", null],
["=====", null],
["a=", null],
["a==", null],
["a===", null],
["a====", null],
["a=====", null],
["ab=", null],
["ab==", [105]],
["ab===", null],
["ab====", null],
["ab=====", null],
["abc=", [105, 183]],
["abc==", null],
["abc===", null],
["abc====", null],
["abc=====", null],
["abcd=", null],
["abcd==", null],
["abcd===", null],
["abcd====", null],
["abcd=====", null],
["abcde=", null],
["abcde==", null],
["abcde===", null],
["abcde====", null],
["abcde=====", null],
["=a", null],
["=a=", null],
["a=b", null],
["a=b=", null],
["ab=c", null],
["ab=c=", null],
["abc=d", null],
["abc=d=", null],
["ab\u000Bcd", null],
["ab\u3000cd", null],
["ab\u3001cd", null],
["ab\tcd", [105, 183, 29]],
["ab\ncd", [105, 183, 29]],
["ab\fcd", [105, 183, 29]],
["ab\rcd", [105, 183, 29]],
["ab cd", [105, 183, 29]],
["ab\u00a0cd", null],
["ab\t\n\f\r cd", [105, 183, 29]],
[" \t\n\f\r ab\t\n\f\r cd\t\n\f\r ", [105, 183, 29]],
["ab\t\n\f\r =\t\n\f\r =\t\n\f\r ", [105]],
["A", null],
["/A", [252]],
["//A", [255, 240]],
["///A", [255, 255, 192]],
["////A", null],
["/", null],
["A/", [3]],
["AA/", [0, 15]],
["AAAA/", null],
["AAA/", [0, 0, 63]],
["\u0000nonsense", null],
["abcd\u0000nonsense", null],
["YQ", [97]],
["YR", [97]],
["~~", null],
["..", null],
["--", null],
["__", null]
]

214
third-party/vendor/data-url/tests/data-urls.json vendored Normal file
View file

@ -0,0 +1,214 @@
[
["data://test/,X",
"text/plain;charset=US-ASCII",
[88]],
["data://test:test/,X",
null],
["data:,X",
"text/plain;charset=US-ASCII",
[88]],
["data:",
null],
["data:text/html",
null],
["data:text/html ;charset=x ",
null],
["data:,",
"text/plain;charset=US-ASCII",
[]],
["data:,X#X",
"text/plain;charset=US-ASCII",
[88]],
["data:,%FF",
"text/plain;charset=US-ASCII",
[255]],
["data:text/plain,X",
"text/plain",
[88]],
["data:text/plain ,X",
"text/plain",
[88]],
["data:text/plain%20,X",
"text/plain%20",
[88]],
["data:text/plain\f,X",
"text/plain%0c",
[88]],
["data:text/plain%0C,X",
"text/plain%0c",
[88]],
["data:text/plain;,X",
"text/plain",
[88]],
["data:;x=x;charset=x,X",
"text/plain;x=x;charset=x",
[88]],
["data:;x=x,X",
"text/plain;x=x",
[88]],
["data:text/plain;charset=windows-1252,%C2%B1",
"text/plain;charset=windows-1252",
[194, 177]],
["data:text/plain;Charset=UTF-8,%C2%B1",
"text/plain;charset=UTF-8",
[194, 177]],
["data:text/plain;charset=windows-1252,áñçə💩",
"text/plain;charset=windows-1252",
[195, 161, 195, 177, 195, 167, 201, 153, 240, 159, 146, 169]],
["data:text/plain;charset=UTF-8,áñçə💩",
"text/plain;charset=UTF-8",
[195, 161, 195, 177, 195, 167, 201, 153, 240, 159, 146, 169]],
["data:image/gif,%C2%B1",
"image/gif",
[194, 177]],
["data:IMAGE/gif,%C2%B1",
"image/gif",
[194, 177]],
["data:IMAGE/gif;hi=x,%C2%B1",
"image/gif;hi=x",
[194, 177]],
["data:IMAGE/gif;CHARSET=x,%C2%B1",
"image/gif;charset=x",
[194, 177]],
["data: ,%FF",
"text/plain;charset=US-ASCII",
[255]],
["data:%20,%FF",
"text/plain;charset=US-ASCII",
[255]],
["data:\f,%FF",
"text/plain;charset=US-ASCII",
[255]],
["data:%1F,%FF",
"text/plain;charset=US-ASCII",
[255]],
["data:\u0000,%FF",
"text/plain;charset=US-ASCII",
[255]],
["data:%00,%FF",
"text/plain;charset=US-ASCII",
[255]],
["data:text/html ,X",
"text/html",
[88]],
["data:text / html,X",
"text/plain;charset=US-ASCII",
[88]],
["data:†,X",
"text/plain;charset=US-ASCII",
[88]],
["data:†/†,X",
"%e2%80%a0/%e2%80%a0",
[88]],
["data:X,X",
"text/plain;charset=US-ASCII",
[88]],
["data:image/png,X X",
"image/png",
[88, 32, 88]],
["data:application/javascript,X X",
"application/javascript",
[88, 32, 88]],
["data:application/xml,X X",
"application/xml",
[88, 32, 88]],
["data:text/javascript,X X",
"text/javascript",
[88, 32, 88]],
["data:text/plain,X X",
"text/plain",
[88, 32, 88]],
["data:unknown/unknown,X X",
"unknown/unknown",
[88, 32, 88]],
["data:text/plain;a=\",\",X",
"text/plain;a=\"\"",
[34, 44, 88]],
["data:text/plain;a=%2C,X",
"text/plain;a=%2C",
[88]],
["data:;base64;base64,WA",
"text/plain",
[88]],
["data:x/x;base64;base64,WA",
"x/x",
[88]],
["data:x/x;base64;charset=x,WA",
"x/x;charset=x",
[87, 65]],
["data:x/x;base64;charset=x;base64,WA",
"x/x;charset=x",
[88]],
["data:x/x;base64;base64x,WA",
"x/x",
[87, 65]],
["data:;base64,W%20A",
"text/plain;charset=US-ASCII",
[88]],
["data:;base64,W%0CA",
"text/plain;charset=US-ASCII",
[88]],
["data:x;base64x,WA",
"text/plain;charset=US-ASCII",
[87, 65]],
["data:x;base64;x,WA",
"text/plain;charset=US-ASCII",
[87, 65]],
["data:x;base64=x,WA",
"text/plain;charset=US-ASCII",
[87, 65]],
["data:; base64,WA",
"text/plain;charset=US-ASCII",
[88]],
["data:; base64,WA",
"text/plain;charset=US-ASCII",
[88]],
["data: ;charset=x ; base64,WA",
"text/plain;charset=x",
[88]],
["data:;base64;,WA",
"text/plain",
[87, 65]],
["data:;base64 ,WA",
"text/plain;charset=US-ASCII",
[88]],
["data:;base64 ,WA",
"text/plain;charset=US-ASCII",
[88]],
["data:;base 64,WA",
"text/plain",
[87, 65]],
["data:;BASe64,WA",
"text/plain;charset=US-ASCII",
[88]],
["data:;%62ase64,WA",
"text/plain",
[87, 65]],
["data:%3Bbase64,WA",
"text/plain;charset=US-ASCII",
[87, 65]],
["data:;charset=x,X",
"text/plain;charset=x",
[88]],
["data:; charset=x,X",
"text/plain;charset=x",
[88]],
["data:;charset =x,X",
"text/plain",
[88]],
["data:;charset= x,X",
"text/plain;charset=\" x\"",
[88]],
["data:;charset=,X",
"text/plain",
[88]],
["data:;charset,X",
"text/plain",
[88]],
["data:;charset=\"x\",X",
"text/plain;charset=x",
[88]],
["data:;CHARSET=\"X\",X",
"text/plain;charset=X",
[88]]
]

3526
third-party/vendor/data-url/tests/generated-mime-types.json vendored Normal file
View file

File diff suppressed because it is too large Load diff

397
third-party/vendor/data-url/tests/mime-types.json vendored Normal file
View file

@ -0,0 +1,397 @@
[
"Basics",
{
"input": "text/html;charset=gbk",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "TEXT/HTML;CHARSET=GBK",
"output": "text/html;charset=GBK",
"navigable": true,
"encoding": "GBK"
},
"Legacy comment syntax",
{
"input": "text/html;charset=gbk(",
"output": "text/html;charset=\"gbk(\"",
"navigable": true,
"encoding": null
},
{
"input": "text/html;x=(;charset=gbk",
"output": "text/html;x=\"(\";charset=gbk",
"navigable": true,
"encoding": "GBK"
},
"Duplicate parameter",
{
"input": "text/html;charset=gbk;charset=windows-1255",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset=();charset=GBK",
"output": "text/html;charset=\"()\"",
"navigable": true,
"encoding": null
},
"Spaces",
{
"input": "text/html;charset =gbk",
"output": "text/html",
"navigable": true,
"encoding": null
},
{
"input": "text/html ;charset=gbk",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html; charset=gbk",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset= gbk",
"output": "text/html;charset=\" gbk\"",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset= \"gbk\"",
"output": "text/html;charset=\" \\\"gbk\\\"\"",
"navigable": true,
"encoding": null
},
"0x0B and 0x0C",
{
"input": "text/html;charset=\u000Bgbk",
"output": "text/html",
"navigable": true,
"encoding": null
},
{
"input": "text/html;charset=\u000Cgbk",
"output": "text/html",
"navigable": true,
"encoding": null
},
{
"input": "text/html;\u000Bcharset=gbk",
"output": "text/html",
"navigable": true,
"encoding": null
},
{
"input": "text/html;\u000Ccharset=gbk",
"output": "text/html",
"navigable": true,
"encoding": null
},
"Single quotes are a token, not a delimiter",
{
"input": "text/html;charset='gbk'",
"output": "text/html;charset='gbk'",
"navigable": true,
"encoding": null
},
{
"input": "text/html;charset='gbk",
"output": "text/html;charset='gbk",
"navigable": true,
"encoding": null
},
{
"input": "text/html;charset=gbk'",
"output": "text/html;charset=gbk'",
"navigable": true,
"encoding": null
},
{
"input": "text/html;charset=';charset=GBK",
"output": "text/html;charset='",
"navigable": true,
"encoding": null
},
"Invalid parameters",
{
"input": "text/html;test;charset=gbk",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;test=;charset=gbk",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;';charset=gbk",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;\";charset=gbk",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html ; ; charset=gbk",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;;;;charset=gbk",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset= \"\u007F;charset=GBK",
"output": "text/html;charset=GBK",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset=\"\u007F;charset=foo\";charset=GBK",
"output": "text/html;charset=GBK",
"navigable": true,
"encoding": "GBK"
},
"Double quotes",
{
"input": "text/html;charset=\"gbk\"",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset=\"gbk",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset=gbk\"",
"output": "text/html;charset=\"gbk\\\"\"",
"navigable": true,
"encoding": null
},
{
"input": "text/html;charset=\" gbk\"",
"output": "text/html;charset=\" gbk\"",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset=\"gbk \"",
"output": "text/html;charset=\"gbk \"",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset=\"\\ gbk\"",
"output": "text/html;charset=\" gbk\"",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset=\"\\g\\b\\k\"",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset=\"gbk\"x",
"output": "text/html;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
{
"input": "text/html;charset=\"\";charset=GBK",
"output": "text/html;charset=\"\"",
"navigable": true,
"encoding": null
},
{
"input": "text/html;charset=\";charset=GBK",
"output": "text/html;charset=\";charset=GBK\"",
"navigable": true,
"encoding": null
},
"Unexpected code points",
{
"input": "text/html;charset={gbk}",
"output": "text/html;charset=\"{gbk}\"",
"navigable": true,
"encoding": null
},
"Parameter name longer than 127",
{
"input": "text/html;0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789=x;charset=gbk",
"output": "text/html;0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789=x;charset=gbk",
"navigable": true,
"encoding": "GBK"
},
"type/subtype longer than 127",
{
"input": "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789/0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789",
"output": "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789/0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789"
},
"Invalid names",
{
"input": "text/html;a]=bar;b[=bar;c=bar",
"output": "text/html;c=bar"
},
"Semicolons in value",
{
"input": "text/html;valid=\";\";foo=bar",
"output": "text/html;valid=\";\";foo=bar"
},
{
"input": "text/html;in]valid=\";asd=foo\";foo=bar",
"output": "text/html;foo=bar"
},
"Valid",
{
"input": "!#$%&'*+-.^_`|~0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz/!#$%&'*+-.^_`|~0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz;!#$%&'*+-.^_`|~0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz=!#$%&'*+-.^_`|~0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz",
"output": "!#$%&'*+-.^_`|~0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz/!#$%&'*+-.^_`|~0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz;!#$%&'*+-.^_`|~0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz=!#$%&'*+-.^_`|~0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
},
{
"input": "x/x;x=\"\t !\\\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u0080\u0081\u0082\u0083\u0084\u0085\u0086\u0087\u0088\u0089\u008A\u008B\u008C\u008D\u008E\u008F\u0090\u0091\u0092\u0093\u0094\u0095\u0096\u0097\u0098\u0099\u009A\u009B\u009C\u009D\u009E\u009F\u00A0\u00A1\u00A2\u00A3\u00A4\u00A5\u00A6\u00A7\u00A8\u00A9\u00AA\u00AB\u00AC\u00AD\u00AE\u00AF\u00B0\u00B1\u00B2\u00B3\u00B4\u00B5\u00B6\u00B7\u00B8\u00B9\u00BA\u00BB\u00BC\u00BD\u00BE\u00BF\u00C0\u00C1\u00C2\u00C3\u00C4\u00C5\u00C6\u00C7\u00C8\u00C9\u00CA\u00CB\u00CC\u00CD\u00CE\u00CF\u00D0\u00D1\u00D2\u00D3\u00D4\u00D5\u00D6\u00D7\u00D8\u00D9\u00DA\u00DB\u00DC\u00DD\u00DE\u00DF\u00E0\u00E1\u00E2\u00E3\u00E4\u00E5\u00E6\u00E7\u00E8\u00E9\u00EA\u00EB\u00EC\u00ED\u00EE\u00EF\u00F0\u00F1\u00F2\u00F3\u00F4\u00F5\u00F6\u00F7\u00F8\u00F9\u00FA\u00FB\u00FC\u00FD\u00FE\u00FF\"",
"output": "x/x;x=\"\t !\\\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u0080\u0081\u0082\u0083\u0084\u0085\u0086\u0087\u0088\u0089\u008A\u008B\u008C\u008D\u008E\u008F\u0090\u0091\u0092\u0093\u0094\u0095\u0096\u0097\u0098\u0099\u009A\u009B\u009C\u009D\u009E\u009F\u00A0\u00A1\u00A2\u00A3\u00A4\u00A5\u00A6\u00A7\u00A8\u00A9\u00AA\u00AB\u00AC\u00AD\u00AE\u00AF\u00B0\u00B1\u00B2\u00B3\u00B4\u00B5\u00B6\u00B7\u00B8\u00B9\u00BA\u00BB\u00BC\u00BD\u00BE\u00BF\u00C0\u00C1\u00C2\u00C3\u00C4\u00C5\u00C6\u00C7\u00C8\u00C9\u00CA\u00CB\u00CC\u00CD\u00CE\u00CF\u00D0\u00D1\u00D2\u00D3\u00D4\u00D5\u00D6\u00D7\u00D8\u00D9\u00DA\u00DB\u00DC\u00DD\u00DE\u00DF\u00E0\u00E1\u00E2\u00E3\u00E4\u00E5\u00E6\u00E7\u00E8\u00E9\u00EA\u00EB\u00EC\u00ED\u00EE\u00EF\u00F0\u00F1\u00F2\u00F3\u00F4\u00F5\u00F6\u00F7\u00F8\u00F9\u00FA\u00FB\u00FC\u00FD\u00FE\u00FF\""
},
"End-of-file handling",
{
"input": "x/x;test",
"output": "x/x"
},
{
"input": "x/x;test=\"\\",
"output": "x/x;test=\"\\\\\""
},
"Whitespace (not handled by generated-mime-types.json or above)",
{
"input": "x/x;x= ",
"output": "x/x"
},
{
"input": "x/x;x=\t",
"output": "x/x"
},
{
"input": "x/x\n\r\t ;x=x",
"output": "x/x;x=x"
},
{
"input": "\n\r\t x/x;x=x\n\r\t ",
"output": "x/x;x=x"
},
{
"input": "x/x;\n\r\t x=x\n\r\t ;x=y",
"output": "x/x;x=x"
},
"Latin1",
{
"input": "text/html;test=\u00FF;charset=gbk",
"output": "text/html;test=\"\u00FF\";charset=gbk",
"navigable": true,
"encoding": "GBK"
},
">Latin1",
{
"input": "x/x;test=\uFFFD;x=x",
"output": "x/x;x=x"
},
"Failure",
{
"input": "\u000Bx/x",
"output": null
},
{
"input": "\u000Cx/x",
"output": null
},
{
"input": "x/x\u000B",
"output": null
},
{
"input": "x/x\u000C",
"output": null
},
{
"input": "",
"output": null
},
{
"input": "\t",
"output": null
},
{
"input": "/",
"output": null
},
{
"input": "bogus",
"output": null
},
{
"input": "bogus/",
"output": null
},
{
"input": "bogus/ ",
"output": null
},
{
"input": "bogus/bogus/;",
"output": null
},
{
"input": "</>",
"output": null
},
{
"input": "(/)",
"output": null
},
{
"input": "ÿ/ÿ",
"output": null
},
{
"input": "text/html(;doesnot=matter",
"output": null
},
{
"input": "{/}",
"output": null
},
{
"input": "\u0100/\u0100",
"output": null
},
{
"input": "text /html",
"output": null
},
{
"input": "text/ html",
"output": null
},
{
"input": "\"text/html\"",
"output": null
}
]

167
third-party/vendor/data-url/tests/wpt.rs vendored Normal file
View file

@ -0,0 +1,167 @@
use tester as test;
#[macro_use]
extern crate serde;
fn run_data_url(
input: String,
expected_mime: Option<String>,
expected_body: Option<Vec<u8>>,
expected_panic: bool,
) {
let priorhook = std::panic::take_hook();
std::panic::set_hook(Box::new(move |p| {
if !expected_panic {
priorhook(p);
}
}));
let url = data_url::DataUrl::process(&input);
if let Some(expected_mime) = expected_mime {
let url = url.unwrap();
let (body, _) = url.decode_to_vec().unwrap();
if expected_mime.is_empty() {
assert_eq!(url.mime_type().to_string(), "text/plain;charset=US-ASCII")
} else {
assert_eq!(url.mime_type().to_string(), expected_mime)
}
if let Some(expected_body) = expected_body {
assert_eq!(body, expected_body)
}
} else if let Ok(url) = url {
assert!(url.decode_to_vec().is_err(), "{:?}", url.mime_type())
}
}
fn collect_data_url<F>(add_test: &mut F)
where
F: FnMut(String, bool, test::TestFn),
{
let known_failures = ["data://test:test/,X"];
#[derive(Deserialize)]
#[serde(untagged)]
enum TestCase {
Two(String, Option<String>),
Three(String, Option<String>, Vec<u8>),
}
let v: Vec<TestCase> = serde_json::from_str(include_str!("data-urls.json")).unwrap();
for test in v {
let (input, expected_mime, expected_body) = match test {
TestCase::Two(i, m) => (i, m, None),
TestCase::Three(i, m, b) => (i, m, Some(b)),
};
let should_panic = known_failures.contains(&&*input);
add_test(
format!("data: URL {:?}", input),
should_panic,
test::TestFn::DynTestFn(Box::new(move || {
run_data_url(input, expected_mime, expected_body, should_panic)
})),
);
}
}
fn run_base64(input: String, expected: Option<Vec<u8>>) {
let result = data_url::forgiving_base64::decode_to_vec(input.as_bytes());
match (result, expected) {
(Ok(bytes), Some(expected)) => assert_eq!(bytes, expected),
(Ok(bytes), None) => panic!("Expected error, got {:?}", bytes),
(Err(e), Some(expected)) => panic!("Expected {:?}, got error {:?}", expected, e),
(Err(_), None) => {}
}
}
fn collect_base64<F>(add_test: &mut F)
where
F: FnMut(String, bool, test::TestFn),
{
let known_failures = [];
let v: Vec<(String, Option<Vec<u8>>)> =
serde_json::from_str(include_str!("base64.json")).unwrap();
for (input, expected) in v {
let should_panic = known_failures.contains(&&*input);
add_test(
format!("base64 {:?}", input),
should_panic,
test::TestFn::DynTestFn(Box::new(move || run_base64(input, expected))),
);
}
}
fn run_mime(input: String, expected: Option<String>) {
let result = input.parse::<data_url::mime::Mime>();
match (result, expected) {
(Ok(mime), Some(expected)) => assert_eq!(mime.to_string(), expected),
(Ok(mime), None) => panic!("Expected error, got {:?}", mime),
(Err(e), Some(expected)) => panic!("Expected {:?}, got error {:?}", expected, e),
(Err(_), None) => {}
}
}
fn collect_mime<F>(add_test: &mut F)
where
F: FnMut(String, bool, test::TestFn),
{
let known_failures = [];
#[derive(Deserialize)]
#[serde(untagged)]
enum Entry {
Comment(String),
TestCase {
input: String,
output: Option<String>,
},
}
let v: Vec<Entry> = serde_json::from_str(include_str!("mime-types.json")).unwrap();
let v2: Vec<Entry> = serde_json::from_str(include_str!("generated-mime-types.json")).unwrap();
let entries = v.into_iter().chain(v2);
let mut last_comment = None;
for entry in entries {
let (input, expected) = match entry {
Entry::TestCase { input, output } => (input, output),
Entry::Comment(s) => {
last_comment = Some(s);
continue;
}
};
let should_panic = known_failures.contains(&&*input);
add_test(
if let Some(ref s) = last_comment {
format!("MIME type {:?} {:?}", s, input)
} else {
format!("MIME type {:?}", input)
},
should_panic,
test::TestFn::DynTestFn(Box::new(move || run_mime(input, expected))),
);
}
}
fn main() {
let mut tests = Vec::new();
{
let mut add_one = |name: String, should_panic: bool, run: test::TestFn| {
let desc = test::TestDesc {
name: test::DynTestName(name),
ignore: false,
should_panic: match should_panic {
true => test::ShouldPanic::Yes,
false => test::ShouldPanic::No,
},
allow_fail: false,
test_type: test::TestType::Unknown,
};
tests.push(test::TestDescAndFn { desc, testfn: run })
};
collect_data_url(&mut add_one);
collect_base64(&mut add_one);
collect_mime(&mut add_one);
}
test::test_main(&std::env::args().collect::<Vec<_>>(), tests, None)
}