Vendor dependencies

This commit is contained in:
2026-08-01 16:11:49 +03:00
parent 7f139a0241
commit 6b5e7f0f8b
29706 changed files with 9575646 additions and 0 deletions
+1
View File
@@ -0,0 +1 @@
{"$comment":"This file only protects against accidental modifications. It is not a security mechanism and does not protect against malicious changes.","files":{".cargo_vcs_info.json":"c3eea9b5b6ce627f4737cc4ec6f7451bd272595ab3ce2f489a9e190f9332d36e","COPYING":"01c266bced4a434da0051174d6bee16a4c82cf634e2679b6155d40d75012390f","Cargo.lock":"dbf34343e7a4b605fa044bb92466b4dee74aa77acd5e11e297a64d2b397e5305","Cargo.toml":"1bc50c3e5e15d039f6739e245c7ab283a7d1cfff485d207378c4216eebfb0150","Cargo.toml.orig":"a30097a90d753c2a2f7567343651c2ad1ebba98ae1b0db74d6d5d90fa87dc52f","LICENSE-MIT":"0f96a83840e146e43c0ec96a22ec1f392e0680e6c1226e6f3ba87e0740af850f","README.md":"f521ea13d4b8622f86998487e6a00ec12663dbe0a59a6c9e13ef44ece0284332","UNLICENSE":"7e12e5df4bae12cb21581ba157ced20e1986a0508dd10d0e8a4ab9a4cf94e85c","benches/bench.rs":"05a00ec1b35dbd7a202e280e862a784b3a972574b19201ef66ac7980521ce4ac","src/fnv.rs":"bf67b20b542db2a159f91da8b980fca27d93253a8fafaee7173d6493de985bd8","src/glob.rs":"d230e938384da768864b4aff78836271c1e923ee9f1ffae2d9319fed8bb2ccb4","src/lib.rs":"7e34c24673ee164d779de7d0efdaf97f19176f9e0bfc71e0842345ef76f0a38a","src/pathutil.rs":"5780ad5ec2bc89a42201a1532295e06a90f493929583c453f135759b39a70fa5","src/serde_impl.rs":"4fdc2b4a456fd9ffbe4555d27c760861adaec2ed2524a5f4149ebe827d4779f1"},"package":"e47d37d2ae4464254884b60ab7071be2b876a9c35b696bd018ddcc76847309cd"}
+6
View File
@@ -0,0 +1,6 @@
{
"git": {
"sha1": "28c687d630f1491ccdea078a9be56b4cdc124519"
},
"path_in_vcs": "crates/globset"
}
+3
View File
@@ -0,0 +1,3 @@
This project is dual-licensed under the Unlicense and MIT licenses.
You may use this code under the terms of either license.
+181
View File
@@ -0,0 +1,181 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 4
[[package]]
name = "aho-corasick"
version = "1.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
dependencies = [
"memchr",
]
[[package]]
name = "arbitrary"
version = "1.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c3d036a3c4ab069c7b410a2ce876bd74808d2d0888a82667669f8e783a898bf1"
dependencies = [
"derive_arbitrary",
]
[[package]]
name = "bstr"
version = "1.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1f7dc094d718f2e1c1559ad110e27eeaae14a5465d3d56dd6dbd793079fbd530"
dependencies = [
"memchr",
"serde_core",
]
[[package]]
name = "derive_arbitrary"
version = "1.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1e567bd82dcff979e4b03460c307b3cdc9e96fde3d73bed1496d2bc75d9dd62a"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "glob"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
[[package]]
name = "globset"
version = "0.4.19"
dependencies = [
"aho-corasick",
"arbitrary",
"bstr",
"glob",
"log",
"regex-automata",
"regex-syntax",
"serde",
"serde_json",
]
[[package]]
name = "itoa"
version = "1.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
[[package]]
name = "log"
version = "0.4.33"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0ceec5bc11778974d1bcb055b18002eba7f4b3518b6a0081b3af5f21666da9ad"
[[package]]
name = "memchr"
version = "2.8.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cf8baf1c55e62ffcace7a9f06f4bd9cd3f0c4beb022d3b367256b91b87513d98"
[[package]]
name = "proc-macro2"
version = "1.0.106"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.46"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dfbc457d0c7a0759a614551b11a6409e5951f6c7537be1f1b7682b9ae9230368"
dependencies = [
"proc-macro2",
]
[[package]]
name = "regex-automata"
version = "0.4.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1f388202e4b80542a0921078cc23b6333bcf1409c1e3f86404cae4766a6131db"
dependencies = [
"aho-corasick",
"memchr",
"regex-syntax",
]
[[package]]
name = "regex-syntax"
version = "0.8.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d6f6ff9a378485b298a5286656da665ba74413d36db0979633275d2e708145d4"
[[package]]
name = "serde"
version = "1.0.228"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
dependencies = [
"serde_core",
]
[[package]]
name = "serde_core"
version = "1.0.228"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.228"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "serde_json"
version = "1.0.150"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e8014e44b4736ed0538adeecded0fce2a272f22dc9578a7eb6b2d9993c74cfb9"
dependencies = [
"itoa",
"memchr",
"serde",
"serde_core",
"zmij",
]
[[package]]
name = "syn"
version = "2.0.119"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "872831b642d1a07999a962a351ed35b955ea2cfc8f3862091e2a240a84f17297"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "unicode-ident"
version = "1.0.24"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
[[package]]
name = "zmij"
version = "1.0.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "29666d0abbfad1e3dc4dcf6144730dd3a3ab225bbbdac83319345b1b44ccfc1b"
+98
View File
@@ -0,0 +1,98 @@
# 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 = "2024"
name = "globset"
version = "0.4.19"
authors = ["Andrew Gallant <jamslam@gmail.com>"]
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = """
Cross platform single glob and glob set matching. Glob set matching is the
process of matching one or more glob patterns against a single candidate path
simultaneously, and returning all of the globs that matched.
"""
homepage = "https://github.com/BurntSushi/ripgrep/tree/master/crates/globset"
documentation = "https://docs.rs/globset"
readme = "README.md"
keywords = [
"regex",
"glob",
"multiple",
"set",
"pattern",
]
license = "Unlicense OR MIT"
repository = "https://github.com/BurntSushi/ripgrep/tree/master/crates/globset"
[features]
arbitrary = ["dep:arbitrary"]
default = ["log"]
serde1 = ["serde"]
simd-accel = []
[lib]
name = "globset"
path = "src/lib.rs"
bench = false
[[bench]]
name = "bench"
path = "benches/bench.rs"
[dependencies.aho-corasick]
version = "1.1.1"
[dependencies.arbitrary]
version = "1.3.2"
features = ["derive"]
optional = true
[dependencies.bstr]
version = "1.6.2"
features = ["std"]
default-features = false
[dependencies.log]
version = "0.4.20"
optional = true
[dependencies.regex-automata]
version = "0.4.0"
features = [
"std",
"perf",
"syntax",
"meta",
"nfa",
"hybrid",
]
default-features = false
[dependencies.regex-syntax]
version = "0.8.0"
features = ["std"]
default-features = false
[dependencies.serde]
version = "1.0.188"
optional = true
[dev-dependencies.glob]
version = "0.3.1"
[dev-dependencies.serde_json]
version = "1.0.107"
+49
View File
@@ -0,0 +1,49 @@
[package]
name = "globset"
version = "0.4.19" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Cross platform single glob and glob set matching. Glob set matching is the
process of matching one or more glob patterns against a single candidate path
simultaneously, and returning all of the globs that matched.
"""
documentation = "https://docs.rs/globset"
homepage = "https://github.com/BurntSushi/ripgrep/tree/master/crates/globset"
repository = "https://github.com/BurntSushi/ripgrep/tree/master/crates/globset"
readme = "README.md"
keywords = ["regex", "glob", "multiple", "set", "pattern"]
license = "Unlicense OR MIT"
edition = "2024"
[lib]
name = "globset"
bench = false
[dependencies]
aho-corasick = "1.1.1"
arbitrary = { version = "1.3.2", optional = true, features = ["derive"] }
bstr = { version = "1.6.2", default-features = false, features = ["std"] }
log = { version = "0.4.20", optional = true }
serde = { version = "1.0.188", optional = true }
[dependencies.regex-syntax]
version = "0.8.0"
default-features = false
features = ["std"]
[dependencies.regex-automata]
version = "0.4.0"
default-features = false
features = ["std", "perf", "syntax", "meta", "nfa", "hybrid"]
[dev-dependencies]
glob = "0.3.1"
serde_json = "1.0.107"
[features]
default = ["log"]
arbitrary = ["dep:arbitrary"]
# DEPRECATED. It is a no-op. SIMD is done automatically through runtime
# dispatch.
simd-accel = []
serde1 = ["serde"]
+21
View File
@@ -0,0 +1,21 @@
The MIT License (MIT)
Copyright (c) 2015 Andrew Gallant
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.
+119
View File
@@ -0,0 +1,119 @@
globset
=======
Cross platform single glob and glob set matching. Glob set matching is the
process of matching one or more glob patterns against a single candidate path
simultaneously, and returning all of the globs that matched.
[![Build status](https://github.com/BurntSushi/ripgrep/workflows/ci/badge.svg)](https://github.com/BurntSushi/ripgrep/actions)
[![](https://img.shields.io/crates/v/globset.svg)](https://crates.io/crates/globset)
Dual-licensed under MIT or the [UNLICENSE](https://unlicense.org/).
### Documentation
[https://docs.rs/globset](https://docs.rs/globset)
### Usage
Add this to your `Cargo.toml`:
```toml
[dependencies]
globset = "0.4"
```
### Features
* `serde1`: Enables implementing Serde traits on the `Glob` type.
### Example: one glob
This example shows how to match a single glob against a single file path.
```rust
use globset::Glob;
let glob = Glob::new("*.rs")?.compile_matcher();
assert!(glob.is_match("foo.rs"));
assert!(glob.is_match("foo/bar.rs"));
assert!(!glob.is_match("Cargo.toml"));
```
### Example: configuring a glob matcher
This example shows how to use a `GlobBuilder` to configure aspects of match
semantics. In this example, we prevent wildcards from matching path separators.
```rust
use globset::GlobBuilder;
let glob = GlobBuilder::new("*.rs")
.literal_separator(true).build()?.compile_matcher();
assert!(glob.is_match("foo.rs"));
assert!(!glob.is_match("foo/bar.rs")); // no longer matches
assert!(!glob.is_match("Cargo.toml"));
```
### Example: match multiple globs at once
This example shows how to match multiple glob patterns at once.
```rust
use globset::{Glob, GlobSetBuilder};
let mut builder = GlobSetBuilder::new();
// A GlobBuilder can be used to configure each glob's match semantics
// independently.
builder.add(Glob::new("*.rs")?);
builder.add(Glob::new("src/lib.rs")?);
builder.add(Glob::new("src/**/foo.rs")?);
let set = builder.build()?;
assert_eq!(set.matches("src/bar/baz/foo.rs"), vec![0, 2]);
```
### Performance
This crate implements globs by converting them to regular expressions, and
executing them with the
[`regex`](https://github.com/rust-lang/regex)
crate.
For single glob matching, performance of this crate should be roughly on par
with the performance of the
[`glob`](https://github.com/rust-lang/glob)
crate. (`*_regex` correspond to benchmarks for this library while `*_glob`
correspond to benchmarks for the `glob` library.)
Optimizations in the `regex` crate may propel this library past `glob`,
particularly when matching longer paths.
```
test ext_glob ... bench: 425 ns/iter (+/- 21)
test ext_regex ... bench: 175 ns/iter (+/- 10)
test long_glob ... bench: 182 ns/iter (+/- 11)
test long_regex ... bench: 173 ns/iter (+/- 10)
test short_glob ... bench: 69 ns/iter (+/- 4)
test short_regex ... bench: 83 ns/iter (+/- 2)
```
The primary performance advantage of this crate is when matching multiple
globs against a single path. With the `glob` crate, one must match each glob
synchronously, one after the other. In this crate, many can be matched
simultaneously. For example:
```
test many_short_glob ... bench: 1,063 ns/iter (+/- 47)
test many_short_regex_set ... bench: 186 ns/iter (+/- 11)
```
### Comparison with the [`glob`](https://github.com/rust-lang/glob) crate
* Supports alternate "or" globs, e.g., `*.{foo,bar}`.
* Can match non-UTF-8 file paths correctly.
* Supports matching multiple globs at once.
* Doesn't provide a recursive directory iterator of matching file paths,
although I believe this crate should grow one eventually.
* Supports case insensitive and require-literal-separator match options, but
**doesn't** support the require-literal-leading-dot option.
+24
View File
@@ -0,0 +1,24 @@
This is free and unencumbered software released into the public domain.
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
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 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.
For more information, please refer to <http://unlicense.org/>
+113
View File
@@ -0,0 +1,113 @@
/*!
This module benchmarks the glob implementation. For benchmarks on the ripgrep
tool itself, see the benchsuite directory.
*/
#![feature(test)]
extern crate test;
use globset::{Candidate, Glob, GlobMatcher, GlobSet, GlobSetBuilder};
const EXT: &'static str = "some/a/bigger/path/to/the/crazy/needle.txt";
const EXT_PAT: &'static str = "*.txt";
const SHORT: &'static str = "some/needle.txt";
const SHORT_PAT: &'static str = "some/**/needle.txt";
const LONG: &'static str = "some/a/bigger/path/to/the/crazy/needle.txt";
const LONG_PAT: &'static str = "some/**/needle.txt";
fn new_glob(pat: &str) -> glob::Pattern {
glob::Pattern::new(pat).unwrap()
}
fn new_reglob(pat: &str) -> GlobMatcher {
Glob::new(pat).unwrap().compile_matcher()
}
fn new_reglob_many(pats: &[&str]) -> GlobSet {
let mut builder = GlobSetBuilder::new();
for pat in pats {
builder.add(Glob::new(pat).unwrap());
}
builder.build().unwrap()
}
#[bench]
fn ext_glob(b: &mut test::Bencher) {
let pat = new_glob(EXT_PAT);
b.iter(|| assert!(pat.matches(EXT)));
}
#[bench]
fn ext_regex(b: &mut test::Bencher) {
let set = new_reglob(EXT_PAT);
let cand = Candidate::new(EXT);
b.iter(|| assert!(set.is_match_candidate(&cand)));
}
#[bench]
fn short_glob(b: &mut test::Bencher) {
let pat = new_glob(SHORT_PAT);
b.iter(|| assert!(pat.matches(SHORT)));
}
#[bench]
fn short_regex(b: &mut test::Bencher) {
let set = new_reglob(SHORT_PAT);
let cand = Candidate::new(SHORT);
b.iter(|| assert!(set.is_match_candidate(&cand)));
}
#[bench]
fn long_glob(b: &mut test::Bencher) {
let pat = new_glob(LONG_PAT);
b.iter(|| assert!(pat.matches(LONG)));
}
#[bench]
fn long_regex(b: &mut test::Bencher) {
let set = new_reglob(LONG_PAT);
let cand = Candidate::new(LONG);
b.iter(|| assert!(set.is_match_candidate(&cand)));
}
const MANY_SHORT_GLOBS: &'static [&'static str] = &[
// Taken from a random .gitignore on my system.
".*.swp",
"tags",
"target",
"*.lock",
"tmp",
"*.csv",
"*.fst",
"*-got",
"*.csv.idx",
"words",
"98m*",
"dict",
"test",
"months",
];
const MANY_SHORT_SEARCH: &'static str = "98m-blah.csv.idx";
#[bench]
fn many_short_glob(b: &mut test::Bencher) {
let pats: Vec<_> = MANY_SHORT_GLOBS.iter().map(|&s| new_glob(s)).collect();
b.iter(|| {
let mut count = 0;
for pat in &pats {
if pat.matches(MANY_SHORT_SEARCH) {
count += 1;
}
}
assert_eq!(2, count);
})
}
#[bench]
fn many_short_regex_set(b: &mut test::Bencher) {
let set = new_reglob_many(MANY_SHORT_GLOBS);
b.iter(|| assert_eq!(2, set.matches(MANY_SHORT_SEARCH).iter().count()));
}
+30
View File
@@ -0,0 +1,30 @@
/// A convenience alias for creating a hash map with an FNV hasher.
pub(crate) type HashMap<K, V> =
std::collections::HashMap<K, V, std::hash::BuildHasherDefault<Hasher>>;
/// A hasher that implements the FowlerNollVo (FNV) hash.
pub(crate) struct Hasher(u64);
impl Hasher {
const OFFSET_BASIS: u64 = 0xcbf29ce484222325;
const PRIME: u64 = 0x100000001b3;
}
impl Default for Hasher {
fn default() -> Hasher {
Hasher(Hasher::OFFSET_BASIS)
}
}
impl std::hash::Hasher for Hasher {
fn finish(&self) -> u64 {
self.0
}
fn write(&mut self, bytes: &[u8]) {
for &byte in bytes.iter() {
self.0 = self.0 ^ u64::from(byte);
self.0 = self.0.wrapping_mul(Hasher::PRIME);
}
}
}
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+141
View File
@@ -0,0 +1,141 @@
use std::borrow::Cow;
use bstr::ByteSlice;
/// The final component of the path, if it is a normal file.
///
/// If the path terminates in `..`, or consists solely of a root of prefix,
/// file_name will return `None`.
pub(crate) fn file_name<'a>(path: &Cow<'a, [u8]>) -> Option<Cow<'a, [u8]>> {
if path.is_empty() {
return None;
}
let last_slash = path.rfind_byte(b'/').map(|i| i + 1).unwrap_or(0);
let got = match *path {
Cow::Borrowed(path) => Cow::Borrowed(&path[last_slash..]),
Cow::Owned(ref path) => Cow::Owned(path[last_slash..].to_vec()),
};
if got == &b".."[..] {
return None;
}
Some(got)
}
/// Return a file extension given a path's file name.
///
/// Note that this does NOT match the semantics of std::path::Path::extension.
/// Namely, the extension includes the `.` and matching is otherwise more
/// liberal. Specifically, the extension is:
///
/// * None, if the file name given is empty;
/// * None, if there is no embedded `.`;
/// * Otherwise, the portion of the file name starting with the final `.`.
///
/// e.g., A file name of `.rs` has an extension `.rs`.
///
/// N.B. This is done to make certain glob match optimizations easier. Namely,
/// a pattern like `*.rs` is obviously trying to match files with a `rs`
/// extension, but it also matches files like `.rs`, which doesn't have an
/// extension according to std::path::Path::extension.
pub(crate) fn file_name_ext<'a>(
name: &Cow<'a, [u8]>,
) -> Option<Cow<'a, [u8]>> {
if name.is_empty() {
return None;
}
let last_dot_at = match name.rfind_byte(b'.') {
None => return None,
Some(i) => i,
};
Some(match *name {
Cow::Borrowed(name) => Cow::Borrowed(&name[last_dot_at..]),
Cow::Owned(ref name) => Cow::Owned(name[last_dot_at..].to_vec()),
})
}
/// Normalizes a path to use `/` as a separator everywhere, even on platforms
/// that recognize other characters as separators.
#[cfg(unix)]
pub(crate) fn normalize_path(path: Cow<'_, [u8]>) -> Cow<'_, [u8]> {
// UNIX only uses /, so we're good.
path
}
/// Normalizes a path to use `/` as a separator everywhere, even on platforms
/// that recognize other characters as separators.
#[cfg(not(unix))]
pub(crate) fn normalize_path(mut path: Cow<[u8]>) -> Cow<[u8]> {
use std::path::is_separator;
for i in 0..path.len() {
if path[i] == b'/' || !is_separator(char::from(path[i])) {
continue;
}
path.to_mut()[i] = b'/';
}
path
}
#[cfg(test)]
mod tests {
use std::borrow::Cow;
use bstr::{B, ByteVec};
use super::{file_name, file_name_ext, normalize_path};
macro_rules! name {
($name:ident, $path:expr, $expected:expr) => {
#[test]
fn $name() {
let bs = Vec::from($path);
let got = file_name(&Cow::Owned(bs));
assert_eq!($expected.map(|s| Cow::Borrowed(B(s))), got);
}
};
}
name!(name1, "foo/bar", Some("bar"));
name!(name2, "foo", Some("foo"));
name!(name3, "foo/..", None::<&str>);
name!(name4, "", None::<&str>);
macro_rules! ext {
($name:ident, $file_name:expr, $ext:expr) => {
#[test]
fn $name() {
let bs = Vec::from($file_name);
let got = file_name_ext(&Cow::Owned(bs));
assert_eq!($ext.map(|s| Cow::Borrowed(B(s))), got);
}
};
}
ext!(ext1, "foo.rs", Some(".rs"));
ext!(ext2, ".rs", Some(".rs"));
ext!(ext3, "..rs", Some(".rs"));
ext!(ext4, "", None::<&str>);
ext!(ext5, "foo", None::<&str>);
macro_rules! normalize {
($name:ident, $path:expr, $expected:expr) => {
#[test]
fn $name() {
let bs = Vec::from_slice($path);
let got = normalize_path(Cow::Owned(bs));
assert_eq!($expected.to_vec(), got.into_owned());
}
};
}
normalize!(normal1, b"foo", b"foo");
normalize!(normal2, b"foo/bar", b"foo/bar");
#[cfg(unix)]
normalize!(normal3, b"foo\\bar", b"foo\\bar");
#[cfg(not(unix))]
normalize!(normal3, b"foo\\bar", b"foo/bar");
#[cfg(unix)]
normalize!(normal4, b"foo\\bar/baz", b"foo\\bar/baz");
#[cfg(not(unix))]
normalize!(normal4, b"foo\\bar/baz", b"foo/bar/baz");
}
+128
View File
@@ -0,0 +1,128 @@
use serde::{
de::{Error, SeqAccess, Visitor},
{Deserialize, Deserializer, Serialize, Serializer},
};
use crate::{Glob, GlobSet, GlobSetBuilder};
impl Serialize for Glob {
fn serialize<S: Serializer>(
&self,
serializer: S,
) -> Result<S::Ok, S::Error> {
serializer.serialize_str(self.glob())
}
}
struct GlobVisitor;
impl<'de> Visitor<'de> for GlobVisitor {
type Value = Glob;
fn expecting(
&self,
formatter: &mut std::fmt::Formatter,
) -> std::fmt::Result {
formatter.write_str("a glob pattern")
}
fn visit_str<E>(self, v: &str) -> Result<Self::Value, E>
where
E: Error,
{
Glob::new(v).map_err(serde::de::Error::custom)
}
}
impl<'de> Deserialize<'de> for Glob {
fn deserialize<D: Deserializer<'de>>(
deserializer: D,
) -> Result<Self, D::Error> {
deserializer.deserialize_str(GlobVisitor)
}
}
struct GlobSetVisitor;
impl<'de> Visitor<'de> for GlobSetVisitor {
type Value = GlobSet;
fn expecting(
&self,
formatter: &mut std::fmt::Formatter,
) -> std::fmt::Result {
formatter.write_str("an array of glob patterns")
}
fn visit_seq<A>(self, mut seq: A) -> Result<Self::Value, A::Error>
where
A: SeqAccess<'de>,
{
let mut builder = GlobSetBuilder::new();
while let Some(glob) = seq.next_element()? {
builder.add(glob);
}
builder.build().map_err(serde::de::Error::custom)
}
}
impl<'de> Deserialize<'de> for GlobSet {
fn deserialize<D: Deserializer<'de>>(
deserializer: D,
) -> Result<Self, D::Error> {
deserializer.deserialize_seq(GlobSetVisitor)
}
}
#[cfg(test)]
mod tests {
use std::collections::HashMap;
use crate::{Glob, GlobSet};
#[test]
fn glob_deserialize_borrowed() {
let string = r#"{"markdown": "*.md"}"#;
let map: HashMap<String, Glob> =
serde_json::from_str(&string).unwrap();
assert_eq!(map["markdown"], Glob::new("*.md").unwrap());
}
#[test]
fn glob_deserialize_owned() {
let string = r#"{"markdown": "*.md"}"#;
let v: serde_json::Value = serde_json::from_str(&string).unwrap();
let map: HashMap<String, Glob> = serde_json::from_value(v).unwrap();
assert_eq!(map["markdown"], Glob::new("*.md").unwrap());
}
#[test]
fn glob_deserialize_error() {
let string = r#"{"error": "["}"#;
let map = serde_json::from_str::<HashMap<String, Glob>>(&string);
assert!(map.is_err());
}
#[test]
fn glob_json_works() {
let test_glob = Glob::new("src/**/*.rs").unwrap();
let ser = serde_json::to_string(&test_glob).unwrap();
assert_eq!(ser, "\"src/**/*.rs\"");
let de: Glob = serde_json::from_str(&ser).unwrap();
assert_eq!(test_glob, de);
}
#[test]
fn glob_set_deserialize() {
let j = r#" ["src/**/*.rs", "README.md"] "#;
let set: GlobSet = serde_json::from_str(j).unwrap();
assert!(set.is_match("src/lib.rs"));
assert!(!set.is_match("Cargo.lock"));
}
}