diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 19:33:14 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 19:33:14 +0000 |
commit | 36d22d82aa202bb199967e9512281e9a53db42c9 (patch) | |
tree | 105e8c98ddea1c1e4784a60a5a6410fa416be2de /third_party/rust/camino | |
parent | Initial commit. (diff) | |
download | firefox-esr-upstream.tar.xz firefox-esr-upstream.zip |
Adding upstream version 115.7.0esr.upstream/115.7.0esrupstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'third_party/rust/camino')
-rw-r--r-- | third_party/rust/camino/.cargo-checksum.json | 1 | ||||
-rw-r--r-- | third_party/rust/camino/CHANGELOG.md | 123 | ||||
-rw-r--r-- | third_party/rust/camino/CODE_OF_CONDUCT.md | 133 | ||||
-rw-r--r-- | third_party/rust/camino/Cargo.toml | 58 | ||||
-rw-r--r-- | third_party/rust/camino/LICENSE-APACHE | 201 | ||||
-rw-r--r-- | third_party/rust/camino/LICENSE-MIT | 23 | ||||
-rw-r--r-- | third_party/rust/camino/README.md | 132 | ||||
-rw-r--r-- | third_party/rust/camino/build.rs | 65 | ||||
-rw-r--r-- | third_party/rust/camino/clippy.toml | 1 | ||||
-rw-r--r-- | third_party/rust/camino/release.toml | 8 | ||||
-rw-r--r-- | third_party/rust/camino/rustfmt.toml | 2 | ||||
-rw-r--r-- | third_party/rust/camino/src/lib.rs | 2930 | ||||
-rw-r--r-- | third_party/rust/camino/src/proptest_impls.rs | 60 | ||||
-rw-r--r-- | third_party/rust/camino/src/serde_impls.rs | 57 | ||||
-rw-r--r-- | third_party/rust/camino/src/tests.rs | 46 | ||||
-rw-r--r-- | third_party/rust/camino/tests/integration_tests.rs | 115 |
16 files changed, 3955 insertions, 0 deletions
diff --git a/third_party/rust/camino/.cargo-checksum.json b/third_party/rust/camino/.cargo-checksum.json new file mode 100644 index 0000000000..8686980ae5 --- /dev/null +++ b/third_party/rust/camino/.cargo-checksum.json @@ -0,0 +1 @@ +{"files":{"CHANGELOG.md":"ea1979dff05f6bdd9e2c6c65b8fdb28395bf59f16e7e7fa2a9d398bdd6ae106f","CODE_OF_CONDUCT.md":"f51e207c2961ec061cac5c8aa9dd3098c3437de2c106d740c2aae90771bc0f86","Cargo.toml":"b024a45f39757c112132e6ae883c0052b8bd86bfc166b89b9615621744fd8583","LICENSE-APACHE":"a60eea817514531668d7e00765731449fe14d059d3249e0bc93b36de45f759f2","LICENSE-MIT":"23f18e03dc49df91622fe2a76176497404e46ced8a715d9d2b67a7446571cca3","README.md":"84762d717d0f2358c56f54ee46a6ca5f1582b7d3843f7a4d6e553ea04a57ca1b","build.rs":"ca6914ad35e69842b6fba6e436d0417f39dbe6ee18694d4dd89b372d31cbf715","clippy.toml":"818cba7332cc56b019d59e09805a3498f523da788f51454742905f1987c0b563","release.toml":"287514631fde7a1d29a8e8027bc37c585c7e30c173c8254f551b042e38f4bb81","rustfmt.toml":"bf9776adb152b3fdc0d75c0929ede148c3e28c58f909a7d052865bc332e8958f","src/lib.rs":"52da457eae1c189a1728df994b478fbf37baa85b630541b7a6cbb48670c1c329","src/proptest_impls.rs":"4f36f5804bd3cbbf65177db4b20d808ed56405388b552bad375aab308a535236","src/serde_impls.rs":"eb7f00d1ceb7135506047dbefd7e6acee0364b5a9194111f49dbf2d1eb3661ac","src/tests.rs":"d6108c540dc93446b17d297b50372f799ef777c2cb0280fd37824a102ec24533","tests/integration_tests.rs":"56aa396a173d0c255369159b57e4a7db294e607aa6cfb65efebd95d79cc51a04"},"package":"c77df041dc383319cc661b428b6961a005db4d6808d5e12536931b1ca9556055"}
\ No newline at end of file diff --git a/third_party/rust/camino/CHANGELOG.md b/third_party/rust/camino/CHANGELOG.md new file mode 100644 index 0000000000..03d6722426 --- /dev/null +++ b/third_party/rust/camino/CHANGELOG.md @@ -0,0 +1,123 @@ +# Changelog + +The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), +and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). + +## [1.1.2] - 2022-08-12 + +### Added + +- New convenience methods [`FromPathBufError::into_io_error`] and + [`FromPathError::into_io_error`]. + +## [1.1.1] - 2022-08-12 + +### Fixed + +- Fixed a build regression on older nightlies in the 1.63 series + ([#22](https://github.com/camino-rs/camino/issues/22)). +- Documentation fixes. + +## [1.1.0] - 2022-08-11 + +### Added + +- New methods, mirroring those in recent versions of Rust: + - `Utf8Path::try_exists` checks whether a path exists. Note that while `std::path::Path` only provides this method for Rust 1.58 and above, `camino` backfills the method for all Rust versions it supports. + - `Utf8PathBuf::shrink_to` shrinks a `Utf8PathBuf` to a given size. This was added in, and is gated on, Rust 1.56+. + - `Utf8PathBuf::try_reserve` and `Utf8PathBuf::try_reserve_exact` implement fallible allocations. These were added in, and are gated on, Rust 1.63+. +- A number of `#[must_use]` annotations to APIs, mirroring those added to `Path` and `PathBuf` in recent versions of Rust. The minor version bump is due to this change. + +## [1.0.9] - 2022-05-19 + +### Fixed + +- Documentation fixes. + +## [1.0.8] - 2022-05-09 + +### Added + +- New methods `canonicalize_utf8`, `read_link_utf8` and `read_dir_utf8` return `Utf8PathBuf`s, erroring out if a resulting path is not valid UTF-8. +- New feature `proptest1` introduces proptest `Arbitrary` impls for `Utf8PathBuf` and + `Box<Utf8Path>` ([#18], thanks [mcronce](https://github.com/mcronce) for your first contribution!) + +[#18]: https://github.com/camino-rs/camino/pull/18 + +## [1.0.7] - 2022-01-16 + +### Added + +- `Utf8Path::is_symlink` checks whether a path is a symlink. Note that while `std::path::Path` only + provides this method for version 1.58 and above, `camino` backfills the method for all Rust versions + it supports. + +### Changed + +- Update repository links to new location [camino-rs/camino](https://github.com/camino-rs/camino). +- Update `structopt` example to clap 3's builtin derive feature. + (camino continues to work with structopt as before.) + +## [1.0.6] - 2022-01-16 + +(This release was yanked due to a publishing issue.) + +## [1.0.5] - 2021-07-27 + +### Added + +- `Utf8PathBuf::into_std_path_buf` converts a `Utf8PathBuf` to a `PathBuf`; equivalent to the + `From<Utf8PathBuf> for PathBuf` impl, but may aid in type inference. +- `Utf8Path::as_std_path` converts a `Utf8Path` to a `Path`; equivalent to the + `AsRef<&Path> for &Utf8Path` impl, but may aid in type inference. + +## [1.0.4] - 2021-03-19 + +### Fixed + +- `Hash` impls for `Utf8PathBuf` and `Utf8Path` now match as required by the `Borrow` contract ([#9]). + +[#9]: https://github.com/camino-rs/camino/issues/9 + +## [1.0.3] - 2021-03-11 + +### Added + +- `TryFrom<PathBuf> for Utf8PathBuf` and `TryFrom<&Path> for &Utf8Path`, both of which return new error types ([#6]). +- `AsRef<Utf8Path>`, `AsRef<Path>`, `AsRef<str>` and `AsRef<OsStr>` impls for `Utf8Components`, `Utf8Component` and + `Iter`. + +[#6]: https://github.com/camino-rs/camino/issues/6 + +## [1.0.2] - 2021-03-02 + +### Added + +- `From` impls for converting a `&Utf8Path` or a `Utf8PathBuf` into `Box<Path>`, `Rc<Path>`, `Arc<Path>` and `Cow<'a, Path>`. +- `PartialEq` and `PartialOrd` implementations comparing `Utf8Path` and `Utf8PathBuf` with `Path`, `PathBuf` and its + variants, and comparing `OsStr`, `OsString` and its variants. + +## [1.0.1] - 2021-02-25 + +### Added + +- More `PartialEq` and `PartialOrd` implementations. +- MSRV lowered to 1.34. + +## [1.0.0] - 2021-02-23 + +Initial release. + +[1.1.2]: https://github.com/camino-rs/camino/releases/tag/camino-1.1.2 +[1.1.1]: https://github.com/camino-rs/camino/releases/tag/camino-1.1.1 +[1.1.0]: https://github.com/camino-rs/camino/releases/tag/camino-1.1.0 +[1.0.9]: https://github.com/camino-rs/camino/releases/tag/camino-1.0.9 +[1.0.8]: https://github.com/camino-rs/camino/releases/tag/camino-1.0.8 +[1.0.7]: https://github.com/camino-rs/camino/releases/tag/camino-1.0.7 +[1.0.6]: https://github.com/camino-rs/camino/releases/tag/camino-1.0.6 +[1.0.5]: https://github.com/camino-rs/camino/releases/tag/camino-1.0.5 +[1.0.4]: https://github.com/camino-rs/camino/releases/tag/camino-1.0.4 +[1.0.3]: https://github.com/camino-rs/camino/releases/tag/camino-1.0.3 +[1.0.2]: https://github.com/camino-rs/camino/releases/tag/camino-1.0.2 +[1.0.1]: https://github.com/camino-rs/camino/releases/tag/camino-1.0.1 +[1.0.0]: https://github.com/camino-rs/camino/releases/tag/camino-1.0.0 diff --git a/third_party/rust/camino/CODE_OF_CONDUCT.md b/third_party/rust/camino/CODE_OF_CONDUCT.md new file mode 100644 index 0000000000..2ea2606d04 --- /dev/null +++ b/third_party/rust/camino/CODE_OF_CONDUCT.md @@ -0,0 +1,133 @@ +# Contributor Covenant Code of Conduct + +## Our Pledge + +We as members, contributors, and leaders pledge to make participation in our +community a harassment-free experience for everyone, regardless of age, body +size, visible or invisible disability, ethnicity, sex characteristics, gender +identity and expression, level of experience, education, socio-economic status, +nationality, personal appearance, race, caste, color, religion, or sexual identity +and orientation. + +We pledge to act and interact in ways that contribute to an open, welcoming, +diverse, inclusive, and healthy community. + +## Our Standards + +Examples of behavior that contributes to a positive environment for our +community include: + +* Demonstrating empathy and kindness toward other people +* Being respectful of differing opinions, viewpoints, and experiences +* Giving and gracefully accepting constructive feedback +* Accepting responsibility and apologizing to those affected by our mistakes, + and learning from the experience +* Focusing on what is best not just for us as individuals, but for the + overall community + +Examples of unacceptable behavior include: + +* The use of sexualized language or imagery, and sexual attention or + advances of any kind +* Trolling, insulting or derogatory comments, and personal or political attacks +* Public or private harassment +* Publishing others' private information, such as a physical or email + address, without their explicit permission +* Other conduct which could reasonably be considered inappropriate in a + professional setting + +## Enforcement Responsibilities + +Community leaders are responsible for clarifying and enforcing our standards of +acceptable behavior and will take appropriate and fair corrective action in +response to any behavior that they deem inappropriate, threatening, offensive, +or harmful. + +Community leaders have the right and responsibility to remove, edit, or reject +comments, commits, code, wiki edits, issues, and other contributions that are +not aligned to this Code of Conduct, and will communicate reasons for moderation +decisions when appropriate. + +## Scope + +This Code of Conduct applies within all community spaces, and also applies when +an individual is officially representing the community in public spaces. +Examples of representing our community include using an official e-mail address, +posting via an official social media account, or acting as an appointed +representative at an online or offline event. + +## Enforcement + +Instances of abusive, harassing, or otherwise unacceptable behavior may be +reported to the community leaders responsible for enforcement at the email +address: [codeofconduct@sunshowers.io](mailto:codeofconduct@sunshowers.io). +All complaints will be reviewed and investigated promptly and fairly. + +All community leaders are obligated to respect the privacy and security of the +reporter of any incident. + +## Enforcement Guidelines + +Community leaders will follow these Community Impact Guidelines in determining +the consequences for any action they deem in violation of this Code of Conduct: + +### 1. Correction + +**Community Impact**: Use of inappropriate language or other behavior deemed +unprofessional or unwelcome in the community. + +**Consequence**: A private, written warning from community leaders, providing +clarity around the nature of the violation and an explanation of why the +behavior was inappropriate. A public apology may be requested. + +### 2. Warning + +**Community Impact**: A violation through a single incident or series +of actions. + +**Consequence**: A warning with consequences for continued behavior. No +interaction with the people involved, including unsolicited interaction with +those enforcing the Code of Conduct, for a specified period of time. This +includes avoiding interactions in community spaces as well as external channels +like social media. Violating these terms may lead to a temporary or +permanent ban. + +### 3. Temporary Ban + +**Community Impact**: A serious violation of community standards, including +sustained inappropriate behavior. + +**Consequence**: A temporary ban from any sort of interaction or public +communication with the community for a specified period of time. No public or +private interaction with the people involved, including unsolicited interaction +with those enforcing the Code of Conduct, is allowed during this period. +Violating these terms may lead to a permanent ban. + +### 4. Permanent Ban + +**Community Impact**: Demonstrating a pattern of violation of community +standards, including sustained inappropriate behavior, harassment of an +individual, or aggression toward or disparagement of classes of individuals. + +**Consequence**: A permanent ban from any sort of public interaction within +the community. + +## Attribution + +This Code of Conduct is adapted from the [Contributor Covenant][homepage], +version 2.0, available at +[https://www.contributor-covenant.org/version/2/0/code_of_conduct.html][v2.0]. + +Community Impact Guidelines were inspired by +[Mozilla's code of conduct enforcement ladder][Mozilla CoC]. + +For answers to common questions about this code of conduct, see the FAQ at +[https://www.contributor-covenant.org/faq][FAQ]. Translations are available +at [https://www.contributor-covenant.org/translations][translations]. + +[homepage]: https://www.contributor-covenant.org +[v2.0]: https://www.contributor-covenant.org/version/2/0/code_of_conduct.html +[Mozilla CoC]: https://github.com/mozilla/diversity +[FAQ]: https://www.contributor-covenant.org/faq +[translations]: https://www.contributor-covenant.org/translations + diff --git a/third_party/rust/camino/Cargo.toml b/third_party/rust/camino/Cargo.toml new file mode 100644 index 0000000000..1b2eb24d8b --- /dev/null +++ b/third_party/rust/camino/Cargo.toml @@ -0,0 +1,58 @@ +# 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" +name = "camino" +version = "1.1.2" +authors = [ + "Without Boats <saoirse@without.boats>", + "Ashley Williams <ashley666ashley@gmail.com>", + "Steve Klabnik <steve@steveklabnik.com>", + "Rain <rain@sunshowers.io>", +] +exclude = [ + ".cargo/**/*", + ".github/**/*", +] +description = "UTF-8 paths" +documentation = "https://docs.rs/camino" +readme = "README.md" +keywords = [ + "paths", + "utf8", + "unicode", + "filesystem", +] +categories = [ + "development-tools", + "filesystem", + "os", +] +license = "MIT OR Apache-2.0" +repository = "https://github.com/camino-rs/camino" + +[package.metadata.docs.rs] +all-features = true +rustdoc-args = ["--cfg=doc_cfg"] + +[dependencies.proptest] +version = "1.0.0" +optional = true + +[dependencies.serde] +version = "1" +features = ["derive"] +optional = true + +[features] +proptest1 = ["proptest"] +serde1 = ["serde"] diff --git a/third_party/rust/camino/LICENSE-APACHE b/third_party/rust/camino/LICENSE-APACHE new file mode 100644 index 0000000000..16fe87b06e --- /dev/null +++ b/third_party/rust/camino/LICENSE-APACHE @@ -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. diff --git a/third_party/rust/camino/LICENSE-MIT b/third_party/rust/camino/LICENSE-MIT new file mode 100644 index 0000000000..31aa79387f --- /dev/null +++ b/third_party/rust/camino/LICENSE-MIT @@ -0,0 +1,23 @@ +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. diff --git a/third_party/rust/camino/README.md b/third_party/rust/camino/README.md new file mode 100644 index 0000000000..9fad93a02f --- /dev/null +++ b/third_party/rust/camino/README.md @@ -0,0 +1,132 @@ +# camino - UTF-8 encoded paths + +[![camino on crates.io](https://img.shields.io/crates/v/camino)](https://crates.io/crates/camino) +[![crates.io download count](https://img.shields.io/crates/d/camino)](https://crates.io/crates/camino) +[![Documentation (latest release)](https://img.shields.io/badge/docs-latest%20version-brightgreen.svg)](https://docs.rs/camino) +[![Documentation (main)](https://img.shields.io/badge/docs-main-purple.svg)](https://camino-rs.github.io/camino/rustdoc/camino/) +[![License](https://img.shields.io/badge/license-Apache-green.svg)](LICENSE-APACHE) +[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE-MIT) + +This repository contains the source code for `camino`, an extension of the `std::path` module that adds new +[`Utf8PathBuf`] and [`Utf8Path`] types. + +## What is camino? + +`camino`'s [`Utf8PathBuf`] and [`Utf8Path`] types are like the standard library's [`PathBuf`] and [`Path`] types, except +they are guaranteed to only contain UTF-8 encoded data. Therefore, they expose the ability to get their +contents as strings, they implement `Display`, etc. + +The `std::path` types are not guaranteed to be valid UTF-8. This is the right decision for the standard library, +since it must be as general as possible. However, on all platforms, non-Unicode paths are vanishingly uncommon for a +number of reasons: +* Unicode won. There are still some legacy codebases that store paths in encodings like [Shift JIS], but most + have been converted to Unicode at this point. +* Unicode is the common subset of supported paths across Windows and Unix platforms. (On Windows, Rust stores paths + as [an extension to UTF-8](https://simonsapin.github.io/wtf-8/), and converts them to UTF-16 at Win32 + API boundaries.) +* There are already many systems, such as Cargo, that only support UTF-8 paths. If your own tool interacts with any such + system, you can assume that paths are valid UTF-8 without creating any additional burdens on consumers. +* The ["makefile problem"](https://www.mercurial-scm.org/wiki/EncodingStrategy#The_.22makefile_problem.22) asks: given a + Makefile or other metadata file (such as `Cargo.toml`) that lists the names of other files, how should the names in + the Makefile be matched with the ones on disk? This has *no general, cross-platform solution* in systems that support + non-UTF-8 paths. However, restricting paths to UTF-8 eliminates this problem. + +[Shift JIS]: https://en.wikipedia.org/wiki/Shift_JIS + +Therefore, many programs that want to manipulate paths *do* assume they contain UTF-8 data, and convert them to `str`s +as necessary. However, because this invariant is not encoded in the `Path` type, conversions such as +`path.to_str().unwrap()` need to be repeated again and again, creating a frustrating experience. + +Instead, `camino` allows you to check that your paths are UTF-8 *once*, and then manipulate them +as valid UTF-8 from there on, avoiding repeated lossy and confusing conversions. + +## Examples + +The documentation for [`Utf8PathBuf`] and [`Utf8Path`] contains several examples. + +For examples of how to use `camino` with other libraries like `serde` and `clap`, see the [`camino-examples`] directory. + +## API design + +`camino` is a very thin wrapper around `std::path`. [`Utf8Path`] and [`Utf8PathBuf`] are drop-in replacements +for [`Path`] and [`PathBuf`]. + +Most APIs are the same, but those at the boundary with `str` are different. Some examples: +* `Path::to_str() -> Option<&str>` has been renamed to `Utf8Path::as_str() -> &str`. +* [`Utf8Path`] implements `Display`, and `Path::display()` has been removed. +* Iterating over a [`Utf8Path`] returns `&str`, not `&OsStr`. + +Every [`Utf8Path`] is a valid [`Path`], so [`Utf8Path`] implements `AsRef<Path>`. Any APIs that accept `impl AsRef<Path>` +will continue to work with [`Utf8Path`] instances. + +## Should you use camino? + +`camino` trades off some utility for a great deal of simplicity. Whether `camino` is appropriate for a project or not +is ultimately a case-by-case decision. Here are some general guidelines that may help. + +*You should consider using camino if...* + +* **You're building portable, cross-platform software.** While both Unix and Windows platforms support different kinds + of non-Unicode paths, Unicode is the common subset that's supported across them. +* **Your system has files that contain the names of other files.** If you don't use UTF-8 paths, you will run into the + makefile problem described above, which has no general, cross-platform solution. +* **You're interacting with existing systems that already assume UTF-8 paths.** In that case you won't be adding any new + burdens on downstream consumers. +* **You're building something brand new and are willing to ask your users to rename their paths if necessary.** Projects + that don't have to worry about legacy compatibility have more flexibility in choosing what paths they support. + +In general, using camino is the right choice for most projects. + +*You should **NOT** use camino, if...* + +* **You're writing a core system utility.** If you're writing, say, an `mv` or `cat` replacement, you should + **not** use camino. Instead, use [`std::path::Path`] and add extensive tests for non-UTF-8 paths. +* **You have legacy compatibility constraints.** For example, Git supports non-UTF-8 paths. If your tool needs to handle + arbitrary Git repositories, it should use its own path type that's a wrapper around `Vec<u8>`. + * [`std::path::Path`] supports arbitrary bytestrings [on Unix] but not on Windows. +* **There's some other reason you need to support non-UTF-8 paths.** Some tools like disk recovery utilities need to + handle potentially corrupt filenames: only being able to handle UTF-8 paths would greatly diminish their utility. + +[on Unix]: https://doc.rust-lang.org/std/os/unix/ffi/index.html + +## Optional features + +By default, `camino` has **no dependencies** other than `std`. There are some optional features that enable +dependencies: +* `serde1` adds serde [`Serialize`] and [`Deserialize`] impls for [`Utf8PathBuf`] and [`Utf8Path`] + (zero-copy). +* `proptest1` adds [proptest](https://altsysrq.github.io/proptest-book/) [`Arbitrary`] + implementations for [`Utf8PathBuf`] and `Box<Utf8Path>`. + +## Rust version support + +The minimum supported Rust version (MSRV) for `camino` with default features is **1.34**. This project is tested in CI +against the latest stable version of Rust and the MSRV. +* *Stable APIs* added in later Rust versions are supported either through conditional compilation in `build.rs`, or through backfills that also work on older versions. +* *Deprecations* are kept in sync with the version of Rust they're added in. +* *Unstable APIs* are currently not supported. Please + [file an issue on GitHub](https://github.com/camino-rs/camino/issues/new) if you need an unstable API. + +`camino` is designed to be a core library and has a conservative MSRV policy. MSRV increases will only happen for +a compelling enough reason, and will involve at least a minor version bump. + +Optional features may pull in dependencies that require a newer version of Rust. + +## License + +This project is available under the terms of either the [Apache 2.0 license](LICENSE-APACHE) or the [MIT +license](LICENSE-MIT). + +This project's documentation is adapted from [The Rust Programming Language](https://github.com/rust-lang/rust/), which is +available under the terms of either the [Apache 2.0 license](https://github.com/rust-lang/rust/blob/master/LICENSE-APACHE) +or the [MIT license](https://github.com/rust-lang/rust/blob/master/LICENSE-MIT). + +[`Utf8PathBuf`]: https://docs.rs/camino/*/camino/struct.Utf8PathBuf.html +[`Utf8Path`]: https://docs.rs/camino/*/camino/struct.Utf8Path.html +[`PathBuf`]: https://doc.rust-lang.org/std/path/struct.PathBuf.html +[`Path`]: https://doc.rust-lang.org/std/path/struct.Path.html +[`std::path::Path`]: https://doc.rust-lang.org/std/path/struct.Path.html +[`Serialize`]: https://docs.rs/serde/1/serde/trait.Serialize.html +[`Deserialize`]: https://docs.rs/serde/1/serde/trait.Deserialize.html +[`camino-examples`]: https://github.com/camino-rs/camino/tree/main/camino-examples +[`Arbitrary`]: https://docs.rs/proptest/1/proptest/arbitrary/trait.Arbitrary.html diff --git a/third_party/rust/camino/build.rs b/third_party/rust/camino/build.rs new file mode 100644 index 0000000000..7f5cbdf9b6 --- /dev/null +++ b/third_party/rust/camino/build.rs @@ -0,0 +1,65 @@ +// Copyright (c) The camino Contributors +// SPDX-License-Identifier: MIT OR Apache-2.0 + +//! Adapted from +//! https://github.com/dtolnay/syn/blob/a54fb0098c6679f1312113ae2eec0305c51c7390/build.rs. + +use std::{env, process::Command, str}; + +// The rustc-cfg strings below are *not* public API. Please let us know by +// opening a GitHub issue if your build environment requires some way to enable +// these cfgs other than by executing our build script. +fn main() { + let compiler = match rustc_version() { + Some(compiler) => compiler, + None => return, + }; + + // NOTE: + // Adding a new cfg gated by Rust version MUST be accompanied by an addition to the matrix in + // .github/workflows/ci.yml. + if compiler.minor >= 44 { + println!("cargo:rustc-cfg=path_buf_capacity"); + } + if compiler.minor >= 56 { + println!("cargo:rustc-cfg=shrink_to"); + } + // Stable and beta 1.63 have a stable try_reserve_2. + if (compiler.minor >= 63 + && (compiler.channel == ReleaseChannel::Stable || compiler.channel == ReleaseChannel::Beta)) + || compiler.minor >= 64 + { + println!("cargo:rustc-cfg=try_reserve_2"); + } +} + +struct Compiler { + minor: u32, + channel: ReleaseChannel, +} + +#[derive(Clone, Copy, Debug, Eq, PartialEq)] +enum ReleaseChannel { + Stable, + Beta, + Nightly, +} + +fn rustc_version() -> Option<Compiler> { + let rustc = env::var_os("RUSTC")?; + let output = Command::new(rustc).arg("--version").output().ok()?; + let version = str::from_utf8(&output.stdout).ok()?; + let mut pieces = version.split('.'); + if pieces.next() != Some("rustc 1") { + return None; + } + let minor = pieces.next()?.parse().ok()?; + let channel = if version.contains("nightly") { + ReleaseChannel::Nightly + } else if version.contains("beta") { + ReleaseChannel::Beta + } else { + ReleaseChannel::Stable + }; + Some(Compiler { minor, channel }) +} diff --git a/third_party/rust/camino/clippy.toml b/third_party/rust/camino/clippy.toml new file mode 100644 index 0000000000..b32f6d50a4 --- /dev/null +++ b/third_party/rust/camino/clippy.toml @@ -0,0 +1 @@ +msrv = "1.34.0" diff --git a/third_party/rust/camino/release.toml b/third_party/rust/camino/release.toml new file mode 100644 index 0000000000..b7977bad50 --- /dev/null +++ b/third_party/rust/camino/release.toml @@ -0,0 +1,8 @@ +sign-tag = true +# Required for templates below to work +consolidate-commits = false +pre-release-commit-message = "[{{crate_name}}] version {{version}}" +tag-message = "[{{crate_name}}] version {{version}}" +tag-name = "camino-{{version}}" +publish = false +dependent-version = "upgrade" diff --git a/third_party/rust/camino/rustfmt.toml b/third_party/rust/camino/rustfmt.toml new file mode 100644 index 0000000000..80eeb4054d --- /dev/null +++ b/third_party/rust/camino/rustfmt.toml @@ -0,0 +1,2 @@ +edition = "2018" +use_field_init_shorthand = true diff --git a/third_party/rust/camino/src/lib.rs b/third_party/rust/camino/src/lib.rs new file mode 100644 index 0000000000..44684b096f --- /dev/null +++ b/third_party/rust/camino/src/lib.rs @@ -0,0 +1,2930 @@ +// Copyright (c) The camino Contributors +// SPDX-License-Identifier: MIT OR Apache-2.0 + +#![warn(missing_docs)] +#![cfg_attr(doc_cfg, feature(doc_cfg, doc_auto_cfg))] + +//! UTF-8 encoded paths. +//! +//! `camino` is an extension of the `std::path` module that adds new [`Utf8PathBuf`] and [`Utf8Path`] +//! types. These are like the standard library's [`PathBuf`] and [`Path`] types, except they are +//! guaranteed to only contain UTF-8 encoded data. Therefore, they expose the ability to get their +//! contents as strings, they implement `Display`, etc. +//! +//! The `std::path` types are not guaranteed to be valid UTF-8. This is the right decision for the standard library, +//! since it must be as general as possible. However, on all platforms, non-Unicode paths are vanishingly uncommon for a +//! number of reasons: +//! * Unicode won. There are still some legacy codebases that store paths in encodings like Shift-JIS, but most +//! have been converted to Unicode at this point. +//! * Unicode is the common subset of supported paths across Windows and Unix platforms. (On Windows, Rust stores paths +//! as [an extension to UTF-8](https://simonsapin.github.io/wtf-8/), and converts them to UTF-16 at Win32 +//! API boundaries.) +//! * There are already many systems, such as Cargo, that only support UTF-8 paths. If your own tool interacts with any such +//! system, you can assume that paths are valid UTF-8 without creating any additional burdens on consumers. +//! * The ["makefile problem"](https://www.mercurial-scm.org/wiki/EncodingStrategy#The_.22makefile_problem.22) +//! (which also applies to `Cargo.toml`, and any other metadata file that lists the names of other files) has *no general, +//! cross-platform solution* in systems that support non-UTF-8 paths. However, restricting paths to UTF-8 eliminates +//! this problem. +//! +//! Therefore, many programs that want to manipulate paths *do* assume they contain UTF-8 data, and convert them to `str`s +//! as necessary. However, because this invariant is not encoded in the `Path` type, conversions such as +//! `path.to_str().unwrap()` need to be repeated again and again, creating a frustrating experience. +//! +//! Instead, `camino` allows you to check that your paths are UTF-8 *once*, and then manipulate them +//! as valid UTF-8 from there on, avoiding repeated lossy and confusing conversions. + +use std::{ + borrow::{Borrow, Cow}, + cmp::Ordering, + convert::{Infallible, TryFrom, TryInto}, + error, + ffi::{OsStr, OsString}, + fmt, + fs::{self, Metadata}, + hash::{Hash, Hasher}, + io, + iter::FusedIterator, + ops::Deref, + path::*, + rc::Rc, + str::FromStr, + sync::Arc, +}; + +#[cfg(feature = "proptest1")] +mod proptest_impls; +#[cfg(feature = "serde1")] +mod serde_impls; +#[cfg(test)] +mod tests; + +/// An owned, mutable UTF-8 path (akin to [`String`]). +/// +/// This type provides methods like [`push`] and [`set_extension`] that mutate +/// the path in place. It also implements [`Deref`] to [`Utf8Path`], meaning that +/// all methods on [`Utf8Path`] slices are available on `Utf8PathBuf` values as well. +/// +/// [`push`]: Utf8PathBuf::push +/// [`set_extension`]: Utf8PathBuf::set_extension +/// +/// # Examples +/// +/// You can use [`push`] to build up a `Utf8PathBuf` from +/// components: +/// +/// ``` +/// use camino::Utf8PathBuf; +/// +/// let mut path = Utf8PathBuf::new(); +/// +/// path.push(r"C:\"); +/// path.push("windows"); +/// path.push("system32"); +/// +/// path.set_extension("dll"); +/// ``` +/// +/// However, [`push`] is best used for dynamic situations. This is a better way +/// to do this when you know all of the components ahead of time: +/// +/// ``` +/// use camino::Utf8PathBuf; +/// +/// let path: Utf8PathBuf = [r"C:\", "windows", "system32.dll"].iter().collect(); +/// ``` +/// +/// We can still do better than this! Since these are all strings, we can use +/// `From::from`: +/// +/// ``` +/// use camino::Utf8PathBuf; +/// +/// let path = Utf8PathBuf::from(r"C:\windows\system32.dll"); +/// ``` +/// +/// Which method works best depends on what kind of situation you're in. +// NB: Internal PathBuf must only contain utf8 data +#[derive(Clone, Default)] +#[cfg_attr(feature = "serde1", derive(serde::Serialize, serde::Deserialize))] +#[cfg_attr(feature = "serde1", serde(transparent))] +#[repr(transparent)] +pub struct Utf8PathBuf(PathBuf); + +impl Utf8PathBuf { + /// Allocates an empty `Utf8PathBuf`. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8PathBuf; + /// + /// let path = Utf8PathBuf::new(); + /// ``` + #[must_use] + pub fn new() -> Utf8PathBuf { + Utf8PathBuf(PathBuf::new()) + } + + /// Creates a new `Utf8PathBuf` from a `PathBuf` containing valid UTF-8 characters. + /// + /// Errors with the original `PathBuf` if it is not valid UTF-8. + /// + /// For a version that returns a type that implements [`std::error::Error`], use the + /// `TryFrom<PathBuf>` impl. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8PathBuf; + /// use std::ffi::OsStr; + /// # #[cfg(unix)] + /// use std::os::unix::ffi::OsStrExt; + /// use std::path::PathBuf; + /// + /// let unicode_path = PathBuf::from("/valid/unicode"); + /// Utf8PathBuf::from_path_buf(unicode_path).expect("valid Unicode path succeeded"); + /// + /// // Paths on Unix can be non-UTF-8. + /// # #[cfg(unix)] + /// let non_unicode_str = OsStr::from_bytes(b"\xFF\xFF\xFF"); + /// # #[cfg(unix)] + /// let non_unicode_path = PathBuf::from(non_unicode_str); + /// # #[cfg(unix)] + /// Utf8PathBuf::from_path_buf(non_unicode_path).expect_err("non-Unicode path failed"); + /// ``` + pub fn from_path_buf(path: PathBuf) -> Result<Utf8PathBuf, PathBuf> { + match path.into_os_string().into_string() { + Ok(string) => Ok(Utf8PathBuf::from(string)), + Err(os_string) => Err(PathBuf::from(os_string)), + } + } + + /// Converts a `Utf8PathBuf` to a [`PathBuf`]. + /// + /// This is equivalent to the `From<Utf8PathBuf> for PathBuf` impl, but may aid in type + /// inference. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8PathBuf; + /// use std::path::PathBuf; + /// + /// let utf8_path_buf = Utf8PathBuf::from("foo.txt"); + /// let std_path_buf = utf8_path_buf.into_std_path_buf(); + /// assert_eq!(std_path_buf.to_str(), Some("foo.txt")); + /// + /// // Convert back to a Utf8PathBuf. + /// let new_utf8_path_buf = Utf8PathBuf::from_path_buf(std_path_buf).unwrap(); + /// assert_eq!(new_utf8_path_buf, "foo.txt"); + /// ``` + #[must_use = "`self` will be dropped if the result is not used"] + pub fn into_std_path_buf(self) -> PathBuf { + self.into() + } + + /// Creates a new `Utf8PathBuf` with a given capacity used to create the internal [`PathBuf`]. + /// See [`with_capacity`] defined on [`PathBuf`]. + /// + /// *Requires Rust 1.44 or newer.* + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8PathBuf; + /// + /// let mut path = Utf8PathBuf::with_capacity(10); + /// let capacity = path.capacity(); + /// + /// // This push is done without reallocating + /// path.push(r"C:\"); + /// + /// assert_eq!(capacity, path.capacity()); + /// ``` + /// + /// [`with_capacity`]: PathBuf::with_capacity + #[cfg(path_buf_capacity)] + #[must_use] + pub fn with_capacity(capacity: usize) -> Utf8PathBuf { + Utf8PathBuf(PathBuf::with_capacity(capacity)) + } + + /// Coerces to a [`Utf8Path`] slice. + /// + /// # Examples + /// + /// ``` + /// use camino::{Utf8Path, Utf8PathBuf}; + /// + /// let p = Utf8PathBuf::from("/test"); + /// assert_eq!(Utf8Path::new("/test"), p.as_path()); + /// ``` + #[must_use] + pub fn as_path(&self) -> &Utf8Path { + // SAFETY: every Utf8PathBuf constructor ensures that self is valid UTF-8 + unsafe { Utf8Path::assume_utf8(&self.0) } + } + + /// Extends `self` with `path`. + /// + /// If `path` is absolute, it replaces the current path. + /// + /// On Windows: + /// + /// * if `path` has a root but no prefix (e.g., `\windows`), it + /// replaces everything except for the prefix (if any) of `self`. + /// * if `path` has a prefix but no root, it replaces `self`. + /// + /// # Examples + /// + /// Pushing a relative path extends the existing path: + /// + /// ``` + /// use camino::Utf8PathBuf; + /// + /// let mut path = Utf8PathBuf::from("/tmp"); + /// path.push("file.bk"); + /// assert_eq!(path, Utf8PathBuf::from("/tmp/file.bk")); + /// ``` + /// + /// Pushing an absolute path replaces the existing path: + /// + /// ``` + /// use camino::Utf8PathBuf; + /// + /// let mut path = Utf8PathBuf::from("/tmp"); + /// path.push("/etc"); + /// assert_eq!(path, Utf8PathBuf::from("/etc")); + /// ``` + pub fn push(&mut self, path: impl AsRef<Utf8Path>) { + self.0.push(&path.as_ref().0) + } + + /// Truncates `self` to [`self.parent`]. + /// + /// Returns `false` and does nothing if [`self.parent`] is [`None`]. + /// Otherwise, returns `true`. + /// + /// [`self.parent`]: Utf8Path::parent + /// + /// # Examples + /// + /// ``` + /// use camino::{Utf8Path, Utf8PathBuf}; + /// + /// let mut p = Utf8PathBuf::from("/spirited/away.rs"); + /// + /// p.pop(); + /// assert_eq!(Utf8Path::new("/spirited"), p); + /// p.pop(); + /// assert_eq!(Utf8Path::new("/"), p); + /// ``` + pub fn pop(&mut self) -> bool { + self.0.pop() + } + + /// Updates [`self.file_name`] to `file_name`. + /// + /// If [`self.file_name`] was [`None`], this is equivalent to pushing + /// `file_name`. + /// + /// Otherwise it is equivalent to calling [`pop`] and then pushing + /// `file_name`. The new path will be a sibling of the original path. + /// (That is, it will have the same parent.) + /// + /// [`self.file_name`]: Utf8Path::file_name + /// [`pop`]: Utf8PathBuf::pop + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8PathBuf; + /// + /// let mut buf = Utf8PathBuf::from("/"); + /// assert_eq!(buf.file_name(), None); + /// buf.set_file_name("bar"); + /// assert_eq!(buf, Utf8PathBuf::from("/bar")); + /// assert!(buf.file_name().is_some()); + /// buf.set_file_name("baz.txt"); + /// assert_eq!(buf, Utf8PathBuf::from("/baz.txt")); + /// ``` + pub fn set_file_name(&mut self, file_name: impl AsRef<str>) { + self.0.set_file_name(file_name.as_ref()) + } + + /// Updates [`self.extension`] to `extension`. + /// + /// Returns `false` and does nothing if [`self.file_name`] is [`None`], + /// returns `true` and updates the extension otherwise. + /// + /// If [`self.extension`] is [`None`], the extension is added; otherwise + /// it is replaced. + /// + /// [`self.file_name`]: Utf8Path::file_name + /// [`self.extension`]: Utf8Path::extension + /// + /// # Examples + /// + /// ``` + /// use camino::{Utf8Path, Utf8PathBuf}; + /// + /// let mut p = Utf8PathBuf::from("/feel/the"); + /// + /// p.set_extension("force"); + /// assert_eq!(Utf8Path::new("/feel/the.force"), p.as_path()); + /// + /// p.set_extension("dark_side"); + /// assert_eq!(Utf8Path::new("/feel/the.dark_side"), p.as_path()); + /// ``` + pub fn set_extension(&mut self, extension: impl AsRef<str>) -> bool { + self.0.set_extension(extension.as_ref()) + } + + /// Consumes the `Utf8PathBuf`, yielding its internal [`String`] storage. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8PathBuf; + /// + /// let p = Utf8PathBuf::from("/the/head"); + /// let s = p.into_string(); + /// assert_eq!(s, "/the/head"); + /// ``` + #[must_use = "`self` will be dropped if the result is not used"] + pub fn into_string(self) -> String { + self.into_os_string().into_string().unwrap() + } + + /// Consumes the `Utf8PathBuf`, yielding its internal [`OsString`] storage. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8PathBuf; + /// use std::ffi::OsStr; + /// + /// let p = Utf8PathBuf::from("/the/head"); + /// let s = p.into_os_string(); + /// assert_eq!(s, OsStr::new("/the/head")); + /// ``` + #[must_use = "`self` will be dropped if the result is not used"] + pub fn into_os_string(self) -> OsString { + self.0.into_os_string() + } + + /// Converts this `Utf8PathBuf` into a [boxed](Box) [`Utf8Path`]. + #[must_use = "`self` will be dropped if the result is not used"] + pub fn into_boxed_path(self) -> Box<Utf8Path> { + let ptr = Box::into_raw(self.0.into_boxed_path()) as *mut Utf8Path; + // SAFETY: + // * self is valid UTF-8 + // * ptr was constructed by consuming self so it represents an owned path + // * Utf8Path is marked as #[repr(transparent)] so the conversion from *mut Path to + // *mut Utf8Path is valid + unsafe { Box::from_raw(ptr) } + } + + /// Invokes [`capacity`] on the underlying instance of [`PathBuf`]. + /// + /// *Requires Rust 1.44 or newer.* + /// + /// [`capacity`]: PathBuf::capacity + #[cfg(path_buf_capacity)] + #[must_use] + pub fn capacity(&self) -> usize { + self.0.capacity() + } + + /// Invokes [`clear`] on the underlying instance of [`PathBuf`]. + /// + /// *Requires Rust 1.44 or newer.* + /// + /// [`clear`]: PathBuf::clear + #[cfg(path_buf_capacity)] + pub fn clear(&mut self) { + self.0.clear() + } + + /// Invokes [`reserve`] on the underlying instance of [`PathBuf`]. + /// + /// *Requires Rust 1.44 or newer.* + /// + /// [`reserve`]: PathBuf::reserve + #[cfg(path_buf_capacity)] + pub fn reserve(&mut self, additional: usize) { + self.0.reserve(additional) + } + + /// Invokes [`try_reserve`] on the underlying instance of [`PathBuf`]. + /// + /// *Requires Rust 1.63 or newer.* + /// + /// [`try_reserve`]: PathBuf::try_reserve + #[cfg(try_reserve_2)] + #[inline] + pub fn try_reserve( + &mut self, + additional: usize, + ) -> Result<(), std::collections::TryReserveError> { + self.0.try_reserve(additional) + } + + /// Invokes [`reserve_exact`] on the underlying instance of [`PathBuf`]. + /// + /// *Requires Rust 1.44 or newer.* + /// + /// [`reserve_exact`]: PathBuf::reserve_exact + #[cfg(path_buf_capacity)] + pub fn reserve_exact(&mut self, additional: usize) { + self.0.reserve_exact(additional) + } + + /// Invokes [`try_reserve_exact`] on the underlying instance of [`PathBuf`]. + /// + /// *Requires Rust 1.63 or newer.* + /// + /// [`try_reserve_exact`]: PathBuf::try_reserve_exact + #[cfg(try_reserve_2)] + #[inline] + pub fn try_reserve_exact( + &mut self, + additional: usize, + ) -> Result<(), std::collections::TryReserveError> { + self.0.try_reserve_exact(additional) + } + + /// Invokes [`shrink_to_fit`] on the underlying instance of [`PathBuf`]. + /// + /// *Requires Rust 1.44 or newer.* + /// + /// [`shrink_to_fit`]: PathBuf::shrink_to_fit + #[cfg(path_buf_capacity)] + pub fn shrink_to_fit(&mut self) { + self.0.shrink_to_fit() + } + + /// Invokes [`shrink_to`] on the underlying instance of [`PathBuf`]. + /// + /// *Requires Rust 1.56 or newer.* + /// + /// [`shrink_to`]: PathBuf::shrink_to + #[cfg(shrink_to)] + #[inline] + pub fn shrink_to(&mut self, min_capacity: usize) { + self.0.shrink_to(min_capacity) + } +} + +impl Deref for Utf8PathBuf { + type Target = Utf8Path; + + fn deref(&self) -> &Utf8Path { + self.as_path() + } +} + +impl fmt::Debug for Utf8PathBuf { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + fmt::Debug::fmt(&**self, f) + } +} + +impl fmt::Display for Utf8PathBuf { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + fmt::Display::fmt(self.as_str(), f) + } +} + +impl<P: AsRef<Utf8Path>> Extend<P> for Utf8PathBuf { + fn extend<I: IntoIterator<Item = P>>(&mut self, iter: I) { + for path in iter { + self.push(path); + } + } +} + +/// A slice of a UTF-8 path (akin to [`str`]). +/// +/// This type supports a number of operations for inspecting a path, including +/// breaking the path into its components (separated by `/` on Unix and by either +/// `/` or `\` on Windows), extracting the file name, determining whether the path +/// is absolute, and so on. +/// +/// This is an *unsized* type, meaning that it must always be used behind a +/// pointer like `&` or [`Box`]. For an owned version of this type, +/// see [`Utf8PathBuf`]. +/// +/// # Examples +/// +/// ``` +/// use camino::Utf8Path; +/// +/// // Note: this example does work on Windows +/// let path = Utf8Path::new("./foo/bar.txt"); +/// +/// let parent = path.parent(); +/// assert_eq!(parent, Some(Utf8Path::new("./foo"))); +/// +/// let file_stem = path.file_stem(); +/// assert_eq!(file_stem, Some("bar")); +/// +/// let extension = path.extension(); +/// assert_eq!(extension, Some("txt")); +/// ``` +// NB: Internal Path must only contain utf8 data +#[repr(transparent)] +pub struct Utf8Path(Path); + +impl Utf8Path { + /// Directly wraps a string slice as a `Utf8Path` slice. + /// + /// This is a cost-free conversion. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// Utf8Path::new("foo.txt"); + /// ``` + /// + /// You can create `Utf8Path`s from `String`s, or even other `Utf8Path`s: + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let string = String::from("foo.txt"); + /// let from_string = Utf8Path::new(&string); + /// let from_path = Utf8Path::new(&from_string); + /// assert_eq!(from_string, from_path); + /// ``` + pub fn new(s: &(impl AsRef<str> + ?Sized)) -> &Utf8Path { + let path = Path::new(s.as_ref()); + // SAFETY: s is a str which means it is always valid UTF-8 + unsafe { Utf8Path::assume_utf8(path) } + } + + /// Converts a [`Path`] to a `Utf8Path`. + /// + /// Returns `None` if the path is not valid UTF-8. + /// + /// For a version that returns a type that implements [`std::error::Error`], use the + /// `TryFrom<&Path>` impl. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// use std::ffi::OsStr; + /// # #[cfg(unix)] + /// use std::os::unix::ffi::OsStrExt; + /// use std::path::Path; + /// + /// let unicode_path = Path::new("/valid/unicode"); + /// Utf8Path::from_path(unicode_path).expect("valid Unicode path succeeded"); + /// + /// // Paths on Unix can be non-UTF-8. + /// # #[cfg(unix)] + /// let non_unicode_str = OsStr::from_bytes(b"\xFF\xFF\xFF"); + /// # #[cfg(unix)] + /// let non_unicode_path = Path::new(non_unicode_str); + /// # #[cfg(unix)] + /// assert!(Utf8Path::from_path(non_unicode_path).is_none(), "non-Unicode path failed"); + /// ``` + pub fn from_path(path: &Path) -> Option<&Utf8Path> { + path.as_os_str().to_str().map(Utf8Path::new) + } + + /// Converts a `Utf8Path` to a [`Path`]. + /// + /// This is equivalent to the `AsRef<&Path> for &Utf8Path` impl, but may aid in type inference. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// use std::path::Path; + /// + /// let utf8_path = Utf8Path::new("foo.txt"); + /// let std_path: &Path = utf8_path.as_std_path(); + /// assert_eq!(std_path.to_str(), Some("foo.txt")); + /// + /// // Convert back to a Utf8Path. + /// let new_utf8_path = Utf8Path::from_path(std_path).unwrap(); + /// assert_eq!(new_utf8_path, "foo.txt"); + /// ``` + pub fn as_std_path(&self) -> &Path { + self.as_ref() + } + + /// Yields the underlying [`str`] slice. + /// + /// Unlike [`Path::to_str`], this always returns a slice because the contents of a `Utf8Path` + /// are guaranteed to be valid UTF-8. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let s = Utf8Path::new("foo.txt").as_str(); + /// assert_eq!(s, "foo.txt"); + /// ``` + /// + /// [`str`]: str + #[must_use] + pub fn as_str(&self) -> &str { + // SAFETY: every Utf8Path constructor ensures that self is valid UTF-8 + unsafe { assume_utf8(self.as_os_str()) } + } + + /// Yields the underlying [`OsStr`] slice. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let os_str = Utf8Path::new("foo.txt").as_os_str(); + /// assert_eq!(os_str, std::ffi::OsStr::new("foo.txt")); + /// ``` + #[must_use] + pub fn as_os_str(&self) -> &OsStr { + self.0.as_os_str() + } + + /// Converts a `Utf8Path` to an owned [`Utf8PathBuf`]. + /// + /// # Examples + /// + /// ``` + /// use camino::{Utf8Path, Utf8PathBuf}; + /// + /// let path_buf = Utf8Path::new("foo.txt").to_path_buf(); + /// assert_eq!(path_buf, Utf8PathBuf::from("foo.txt")); + /// ``` + #[must_use = "this returns the result of the operation, \ + without modifying the original"] + pub fn to_path_buf(&self) -> Utf8PathBuf { + Utf8PathBuf(self.0.to_path_buf()) + } + + /// Returns `true` if the `Utf8Path` is absolute, i.e., if it is independent of + /// the current directory. + /// + /// * On Unix, a path is absolute if it starts with the root, so + /// `is_absolute` and [`has_root`] are equivalent. + /// + /// * On Windows, a path is absolute if it has a prefix and starts with the + /// root: `c:\windows` is absolute, while `c:temp` and `\temp` are not. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// assert!(!Utf8Path::new("foo.txt").is_absolute()); + /// ``` + /// + /// [`has_root`]: Utf8Path::has_root + #[must_use] + pub fn is_absolute(&self) -> bool { + self.0.is_absolute() + } + + /// Returns `true` if the `Utf8Path` is relative, i.e., not absolute. + /// + /// See [`is_absolute`]'s documentation for more details. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// assert!(Utf8Path::new("foo.txt").is_relative()); + /// ``` + /// + /// [`is_absolute`]: Utf8Path::is_absolute + #[must_use] + pub fn is_relative(&self) -> bool { + self.0.is_relative() + } + + /// Returns `true` if the `Utf8Path` has a root. + /// + /// * On Unix, a path has a root if it begins with `/`. + /// + /// * On Windows, a path has a root if it: + /// * has no prefix and begins with a separator, e.g., `\windows` + /// * has a prefix followed by a separator, e.g., `c:\windows` but not `c:windows` + /// * has any non-disk prefix, e.g., `\\server\share` + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// assert!(Utf8Path::new("/etc/passwd").has_root()); + /// ``` + #[must_use] + pub fn has_root(&self) -> bool { + self.0.has_root() + } + + /// Returns the `Path` without its final component, if there is one. + /// + /// Returns [`None`] if the path terminates in a root or prefix. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("/foo/bar"); + /// let parent = path.parent().unwrap(); + /// assert_eq!(parent, Utf8Path::new("/foo")); + /// + /// let grand_parent = parent.parent().unwrap(); + /// assert_eq!(grand_parent, Utf8Path::new("/")); + /// assert_eq!(grand_parent.parent(), None); + /// ``` + #[must_use] + pub fn parent(&self) -> Option<&Utf8Path> { + self.0.parent().map(|path| { + // SAFETY: self is valid UTF-8, so parent is valid UTF-8 as well + unsafe { Utf8Path::assume_utf8(path) } + }) + } + + /// Produces an iterator over `Utf8Path` and its ancestors. + /// + /// The iterator will yield the `Utf8Path` that is returned if the [`parent`] method is used zero + /// or more times. That means, the iterator will yield `&self`, `&self.parent().unwrap()`, + /// `&self.parent().unwrap().parent().unwrap()` and so on. If the [`parent`] method returns + /// [`None`], the iterator will do likewise. The iterator will always yield at least one value, + /// namely `&self`. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let mut ancestors = Utf8Path::new("/foo/bar").ancestors(); + /// assert_eq!(ancestors.next(), Some(Utf8Path::new("/foo/bar"))); + /// assert_eq!(ancestors.next(), Some(Utf8Path::new("/foo"))); + /// assert_eq!(ancestors.next(), Some(Utf8Path::new("/"))); + /// assert_eq!(ancestors.next(), None); + /// + /// let mut ancestors = Utf8Path::new("../foo/bar").ancestors(); + /// assert_eq!(ancestors.next(), Some(Utf8Path::new("../foo/bar"))); + /// assert_eq!(ancestors.next(), Some(Utf8Path::new("../foo"))); + /// assert_eq!(ancestors.next(), Some(Utf8Path::new(".."))); + /// assert_eq!(ancestors.next(), Some(Utf8Path::new(""))); + /// assert_eq!(ancestors.next(), None); + /// ``` + /// + /// [`parent`]: Utf8Path::parent + pub fn ancestors(&self) -> Utf8Ancestors<'_> { + Utf8Ancestors(self.0.ancestors()) + } + + /// Returns the final component of the `Utf8Path`, if there is one. + /// + /// If the path is a normal file, this is the file name. If it's the path of a directory, this + /// is the directory name. + /// + /// Returns [`None`] if the path terminates in `..`. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// assert_eq!(Some("bin"), Utf8Path::new("/usr/bin/").file_name()); + /// assert_eq!(Some("foo.txt"), Utf8Path::new("tmp/foo.txt").file_name()); + /// assert_eq!(Some("foo.txt"), Utf8Path::new("foo.txt/.").file_name()); + /// assert_eq!(Some("foo.txt"), Utf8Path::new("foo.txt/.//").file_name()); + /// assert_eq!(None, Utf8Path::new("foo.txt/..").file_name()); + /// assert_eq!(None, Utf8Path::new("/").file_name()); + /// ``` + #[must_use] + pub fn file_name(&self) -> Option<&str> { + self.0.file_name().map(|s| { + // SAFETY: self is valid UTF-8, so file_name is valid UTF-8 as well + unsafe { assume_utf8(s) } + }) + } + + /// Returns a path that, when joined onto `base`, yields `self`. + /// + /// # Errors + /// + /// If `base` is not a prefix of `self` (i.e., [`starts_with`] + /// returns `false`), returns [`Err`]. + /// + /// [`starts_with`]: Utf8Path::starts_with + /// + /// # Examples + /// + /// ``` + /// use camino::{Utf8Path, Utf8PathBuf}; + /// + /// let path = Utf8Path::new("/test/haha/foo.txt"); + /// + /// assert_eq!(path.strip_prefix("/"), Ok(Utf8Path::new("test/haha/foo.txt"))); + /// assert_eq!(path.strip_prefix("/test"), Ok(Utf8Path::new("haha/foo.txt"))); + /// assert_eq!(path.strip_prefix("/test/"), Ok(Utf8Path::new("haha/foo.txt"))); + /// assert_eq!(path.strip_prefix("/test/haha/foo.txt"), Ok(Utf8Path::new(""))); + /// assert_eq!(path.strip_prefix("/test/haha/foo.txt/"), Ok(Utf8Path::new(""))); + /// + /// assert!(path.strip_prefix("test").is_err()); + /// assert!(path.strip_prefix("/haha").is_err()); + /// + /// let prefix = Utf8PathBuf::from("/test/"); + /// assert_eq!(path.strip_prefix(prefix), Ok(Utf8Path::new("haha/foo.txt"))); + /// ``` + pub fn strip_prefix(&self, base: impl AsRef<Path>) -> Result<&Utf8Path, StripPrefixError> { + self.0.strip_prefix(base).map(|path| { + // SAFETY: self is valid UTF-8, and strip_prefix returns a part of self (or an empty + // string), so it is valid UTF-8 as well. + unsafe { Utf8Path::assume_utf8(path) } + }) + } + + /// Determines whether `base` is a prefix of `self`. + /// + /// Only considers whole path components to match. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("/etc/passwd"); + /// + /// assert!(path.starts_with("/etc")); + /// assert!(path.starts_with("/etc/")); + /// assert!(path.starts_with("/etc/passwd")); + /// assert!(path.starts_with("/etc/passwd/")); // extra slash is okay + /// assert!(path.starts_with("/etc/passwd///")); // multiple extra slashes are okay + /// + /// assert!(!path.starts_with("/e")); + /// assert!(!path.starts_with("/etc/passwd.txt")); + /// + /// assert!(!Utf8Path::new("/etc/foo.rs").starts_with("/etc/foo")); + /// ``` + #[must_use] + pub fn starts_with(&self, base: impl AsRef<Path>) -> bool { + self.0.starts_with(base) + } + + /// Determines whether `child` is a suffix of `self`. + /// + /// Only considers whole path components to match. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("/etc/resolv.conf"); + /// + /// assert!(path.ends_with("resolv.conf")); + /// assert!(path.ends_with("etc/resolv.conf")); + /// assert!(path.ends_with("/etc/resolv.conf")); + /// + /// assert!(!path.ends_with("/resolv.conf")); + /// assert!(!path.ends_with("conf")); // use .extension() instead + /// ``` + #[must_use] + pub fn ends_with(&self, base: impl AsRef<Path>) -> bool { + self.0.ends_with(base) + } + + /// Extracts the stem (non-extension) portion of [`self.file_name`]. + /// + /// [`self.file_name`]: Utf8Path::file_name + /// + /// The stem is: + /// + /// * [`None`], if there is no file name; + /// * The entire file name if there is no embedded `.`; + /// * The entire file name if the file name begins with `.` and has no other `.`s within; + /// * Otherwise, the portion of the file name before the final `.` + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// assert_eq!("foo", Utf8Path::new("foo.rs").file_stem().unwrap()); + /// assert_eq!("foo.tar", Utf8Path::new("foo.tar.gz").file_stem().unwrap()); + /// ``` + #[must_use] + pub fn file_stem(&self) -> Option<&str> { + self.0.file_stem().map(|s| { + // SAFETY: self is valid UTF-8, so file_stem is valid UTF-8 as well + unsafe { assume_utf8(s) } + }) + } + + /// Extracts the extension of [`self.file_name`], if possible. + /// + /// The extension is: + /// + /// * [`None`], if there is no file name; + /// * [`None`], if there is no embedded `.`; + /// * [`None`], if the file name begins with `.` and has no other `.`s within; + /// * Otherwise, the portion of the file name after the final `.` + /// + /// [`self.file_name`]: Utf8Path::file_name + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// assert_eq!("rs", Utf8Path::new("foo.rs").extension().unwrap()); + /// assert_eq!("gz", Utf8Path::new("foo.tar.gz").extension().unwrap()); + /// ``` + #[must_use] + pub fn extension(&self) -> Option<&str> { + self.0.extension().map(|s| { + // SAFETY: self is valid UTF-8, so extension is valid UTF-8 as well + unsafe { assume_utf8(s) } + }) + } + + /// Creates an owned [`Utf8PathBuf`] with `path` adjoined to `self`. + /// + /// See [`Utf8PathBuf::push`] for more details on what it means to adjoin a path. + /// + /// # Examples + /// + /// ``` + /// use camino::{Utf8Path, Utf8PathBuf}; + /// + /// assert_eq!(Utf8Path::new("/etc").join("passwd"), Utf8PathBuf::from("/etc/passwd")); + /// ``` + #[must_use] + pub fn join(&self, path: impl AsRef<Utf8Path>) -> Utf8PathBuf { + Utf8PathBuf(self.0.join(&path.as_ref().0)) + } + + /// Creates an owned [`PathBuf`] with `path` adjoined to `self`. + /// + /// See [`PathBuf::push`] for more details on what it means to adjoin a path. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// use std::path::PathBuf; + /// + /// assert_eq!(Utf8Path::new("/etc").join_os("passwd"), PathBuf::from("/etc/passwd")); + /// ``` + #[must_use] + pub fn join_os(&self, path: impl AsRef<Path>) -> PathBuf { + self.0.join(path) + } + + /// Creates an owned [`Utf8PathBuf`] like `self` but with the given file name. + /// + /// See [`Utf8PathBuf::set_file_name`] for more details. + /// + /// # Examples + /// + /// ``` + /// use camino::{Utf8Path, Utf8PathBuf}; + /// + /// let path = Utf8Path::new("/tmp/foo.txt"); + /// assert_eq!(path.with_file_name("bar.txt"), Utf8PathBuf::from("/tmp/bar.txt")); + /// + /// let path = Utf8Path::new("/tmp"); + /// assert_eq!(path.with_file_name("var"), Utf8PathBuf::from("/var")); + /// ``` + #[must_use] + pub fn with_file_name(&self, file_name: impl AsRef<str>) -> Utf8PathBuf { + Utf8PathBuf(self.0.with_file_name(file_name.as_ref())) + } + + /// Creates an owned [`Utf8PathBuf`] like `self` but with the given extension. + /// + /// See [`Utf8PathBuf::set_extension`] for more details. + /// + /// # Examples + /// + /// ``` + /// use camino::{Utf8Path, Utf8PathBuf}; + /// + /// let path = Utf8Path::new("foo.rs"); + /// assert_eq!(path.with_extension("txt"), Utf8PathBuf::from("foo.txt")); + /// + /// let path = Utf8Path::new("foo.tar.gz"); + /// assert_eq!(path.with_extension(""), Utf8PathBuf::from("foo.tar")); + /// assert_eq!(path.with_extension("xz"), Utf8PathBuf::from("foo.tar.xz")); + /// assert_eq!(path.with_extension("").with_extension("txt"), Utf8PathBuf::from("foo.txt")); + /// ``` + pub fn with_extension(&self, extension: impl AsRef<str>) -> Utf8PathBuf { + Utf8PathBuf(self.0.with_extension(extension.as_ref())) + } + + /// Produces an iterator over the [`Utf8Component`]s of the path. + /// + /// When parsing the path, there is a small amount of normalization: + /// + /// * Repeated separators are ignored, so `a/b` and `a//b` both have + /// `a` and `b` as components. + /// + /// * Occurrences of `.` are normalized away, except if they are at the + /// beginning of the path. For example, `a/./b`, `a/b/`, `a/b/.` and + /// `a/b` all have `a` and `b` as components, but `./a/b` starts with + /// an additional [`CurDir`] component. + /// + /// * A trailing slash is normalized away, `/a/b` and `/a/b/` are equivalent. + /// + /// Note that no other normalization takes place; in particular, `a/c` + /// and `a/b/../c` are distinct, to account for the possibility that `b` + /// is a symbolic link (so its parent isn't `a`). + /// + /// # Examples + /// + /// ``` + /// use camino::{Utf8Component, Utf8Path}; + /// + /// let mut components = Utf8Path::new("/tmp/foo.txt").components(); + /// + /// assert_eq!(components.next(), Some(Utf8Component::RootDir)); + /// assert_eq!(components.next(), Some(Utf8Component::Normal("tmp"))); + /// assert_eq!(components.next(), Some(Utf8Component::Normal("foo.txt"))); + /// assert_eq!(components.next(), None) + /// ``` + /// + /// [`CurDir`]: Utf8Component::CurDir + pub fn components(&self) -> Utf8Components { + Utf8Components(self.0.components()) + } + + /// Produces an iterator over the path's components viewed as [`str`] + /// slices. + /// + /// For more information about the particulars of how the path is separated + /// into components, see [`components`]. + /// + /// [`components`]: Utf8Path::components + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let mut it = Utf8Path::new("/tmp/foo.txt").iter(); + /// assert_eq!(it.next(), Some(std::path::MAIN_SEPARATOR.to_string().as_str())); + /// assert_eq!(it.next(), Some("tmp")); + /// assert_eq!(it.next(), Some("foo.txt")); + /// assert_eq!(it.next(), None) + /// ``` + pub fn iter(&self) -> Iter<'_> { + Iter { + inner: self.components(), + } + } + + /// Queries the file system to get information about a file, directory, etc. + /// + /// This function will traverse symbolic links to query information about the + /// destination file. + /// + /// This is an alias to [`fs::metadata`]. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("/Minas/tirith"); + /// let metadata = path.metadata().expect("metadata call failed"); + /// println!("{:?}", metadata.file_type()); + /// ``` + pub fn metadata(&self) -> io::Result<fs::Metadata> { + self.0.metadata() + } + + /// Queries the metadata about a file without following symlinks. + /// + /// This is an alias to [`fs::symlink_metadata`]. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("/Minas/tirith"); + /// let metadata = path.symlink_metadata().expect("symlink_metadata call failed"); + /// println!("{:?}", metadata.file_type()); + /// ``` + pub fn symlink_metadata(&self) -> io::Result<fs::Metadata> { + self.0.symlink_metadata() + } + + /// Returns the canonical, absolute form of the path with all intermediate + /// components normalized and symbolic links resolved. + /// + /// This returns a [`PathBuf`] because even if a symlink is valid Unicode, its target may not + /// be. For a version that returns a [`Utf8PathBuf`], see + /// [`canonicalize_utf8`](Self::canonicalize_utf8). + /// + /// This is an alias to [`fs::canonicalize`]. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// use std::path::PathBuf; + /// + /// let path = Utf8Path::new("/foo/test/../test/bar.rs"); + /// assert_eq!(path.canonicalize().unwrap(), PathBuf::from("/foo/test/bar.rs")); + /// ``` + pub fn canonicalize(&self) -> io::Result<PathBuf> { + self.0.canonicalize() + } + + /// Returns the canonical, absolute form of the path with all intermediate + /// components normalized and symbolic links resolved. + /// + /// This method attempts to convert the resulting [`PathBuf`] into a [`Utf8PathBuf`]. For a + /// version that does not attempt to do this conversion, see + /// [`canonicalize`](Self::canonicalize). + /// + /// # Errors + /// + /// The I/O operation may return an error: see the [`fs::canonicalize`] + /// documentation for more. + /// + /// If the resulting path is not UTF-8, an [`io::Error`] is returned with the + /// [`ErrorKind`](io::ErrorKind) set to `InvalidData` and the payload set to a + /// [`FromPathBufError`]. + /// + /// # Examples + /// + /// ```no_run + /// use camino::{Utf8Path, Utf8PathBuf}; + /// + /// let path = Utf8Path::new("/foo/test/../test/bar.rs"); + /// assert_eq!(path.canonicalize_utf8().unwrap(), Utf8PathBuf::from("/foo/test/bar.rs")); + /// ``` + pub fn canonicalize_utf8(&self) -> io::Result<Utf8PathBuf> { + self.canonicalize() + .and_then(|path| path.try_into().map_err(FromPathBufError::into_io_error)) + } + + /// Reads a symbolic link, returning the file that the link points to. + /// + /// This returns a [`PathBuf`] because even if a symlink is valid Unicode, its target may not + /// be. For a version that returns a [`Utf8PathBuf`], see + /// [`read_link_utf8`](Self::read_link_utf8). + /// + /// This is an alias to [`fs::read_link`]. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("/laputa/sky_castle.rs"); + /// let path_link = path.read_link().expect("read_link call failed"); + /// ``` + pub fn read_link(&self) -> io::Result<PathBuf> { + self.0.read_link() + } + + /// Reads a symbolic link, returning the file that the link points to. + /// + /// This method attempts to convert the resulting [`PathBuf`] into a [`Utf8PathBuf`]. For a + /// version that does not attempt to do this conversion, see [`read_link`](Self::read_link). + /// + /// # Errors + /// + /// The I/O operation may return an error: see the [`fs::read_link`] + /// documentation for more. + /// + /// If the resulting path is not UTF-8, an [`io::Error`] is returned with the + /// [`ErrorKind`](io::ErrorKind) set to `InvalidData` and the payload set to a + /// [`FromPathBufError`]. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("/laputa/sky_castle.rs"); + /// let path_link = path.read_link_utf8().expect("read_link call failed"); + /// ``` + pub fn read_link_utf8(&self) -> io::Result<Utf8PathBuf> { + self.read_link() + .and_then(|path| path.try_into().map_err(FromPathBufError::into_io_error)) + } + + /// Returns an iterator over the entries within a directory. + /// + /// The iterator will yield instances of [`io::Result`]`<`[`fs::DirEntry`]`>`. New + /// errors may be encountered after an iterator is initially constructed. + /// + /// This is an alias to [`fs::read_dir`]. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("/laputa"); + /// for entry in path.read_dir().expect("read_dir call failed") { + /// if let Ok(entry) = entry { + /// println!("{:?}", entry.path()); + /// } + /// } + /// ``` + pub fn read_dir(&self) -> io::Result<fs::ReadDir> { + self.0.read_dir() + } + + /// Returns an iterator over the entries within a directory. + /// + /// The iterator will yield instances of [`io::Result`]`<`[`Utf8DirEntry`]`>`. New + /// errors may be encountered after an iterator is initially constructed. + /// + /// # Errors + /// + /// The I/O operation may return an error: see the [`fs::read_dir`] + /// documentation for more. + /// + /// If a directory entry is not UTF-8, an [`io::Error`] is returned with the + /// [`ErrorKind`](io::ErrorKind) set to `InvalidData` and the payload set to a + /// [`FromPathBufError`]. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("/laputa"); + /// for entry in path.read_dir_utf8().expect("read_dir call failed") { + /// if let Ok(entry) = entry { + /// println!("{}", entry.path()); + /// } + /// } + /// ``` + #[inline] + pub fn read_dir_utf8(&self) -> io::Result<ReadDirUtf8> { + self.0.read_dir().map(|inner| ReadDirUtf8 { inner }) + } + + /// Returns `true` if the path points at an existing entity. + /// + /// Warning: this method may be error-prone, consider using [`try_exists()`] instead! + /// It also has a risk of introducing time-of-check to time-of-use (TOCTOU) bugs. + /// + /// This function will traverse symbolic links to query information about the + /// destination file. In case of broken symbolic links this will return `false`. + /// + /// If you cannot access the directory containing the file, e.g., because of a + /// permission error, this will return `false`. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// assert!(!Utf8Path::new("does_not_exist.txt").exists()); + /// ``` + /// + /// # See Also + /// + /// This is a convenience function that coerces errors to false. If you want to + /// check errors, call [`fs::metadata`]. + /// + /// [`try_exists()`]: Self::try_exists + #[must_use] + pub fn exists(&self) -> bool { + self.0.exists() + } + + /// Returns `Ok(true)` if the path points at an existing entity. + /// + /// This function will traverse symbolic links to query information about the + /// destination file. In case of broken symbolic links this will return `Ok(false)`. + /// + /// As opposed to the [`exists()`] method, this one doesn't silently ignore errors + /// unrelated to the path not existing. (E.g. it will return `Err(_)` in case of permission + /// denied on some of the parent directories.) + /// + /// Note that while this avoids some pitfalls of the `exists()` method, it still can not + /// prevent time-of-check to time-of-use (TOCTOU) bugs. You should only use it in scenarios + /// where those bugs are not an issue. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// assert!(!Utf8Path::new("does_not_exist.txt").try_exists().expect("Can't check existence of file does_not_exist.txt")); + /// assert!(Utf8Path::new("/root/secret_file.txt").try_exists().is_err()); + /// ``` + /// + /// [`exists()`]: Self::exists + #[inline] + pub fn try_exists(&self) -> io::Result<bool> { + // Note: this block is written this way rather than with a pattern guard to appease Rust + // 1.34. + match fs::metadata(self) { + Ok(_) => Ok(true), + Err(error) => { + if error.kind() == io::ErrorKind::NotFound { + Ok(false) + } else { + Err(error) + } + } + } + } + + /// Returns `true` if the path exists on disk and is pointing at a regular file. + /// + /// This function will traverse symbolic links to query information about the + /// destination file. In case of broken symbolic links this will return `false`. + /// + /// If you cannot access the directory containing the file, e.g., because of a + /// permission error, this will return `false`. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// assert_eq!(Utf8Path::new("./is_a_directory/").is_file(), false); + /// assert_eq!(Utf8Path::new("a_file.txt").is_file(), true); + /// ``` + /// + /// # See Also + /// + /// This is a convenience function that coerces errors to false. If you want to + /// check errors, call [`fs::metadata`] and handle its [`Result`]. Then call + /// [`fs::Metadata::is_file`] if it was [`Ok`]. + /// + /// When the goal is simply to read from (or write to) the source, the most + /// reliable way to test the source can be read (or written to) is to open + /// it. Only using `is_file` can break workflows like `diff <( prog_a )` on + /// a Unix-like system for example. See [`fs::File::open`] or + /// [`fs::OpenOptions::open`] for more information. + #[must_use] + pub fn is_file(&self) -> bool { + self.0.is_file() + } + + /// Returns `true` if the path exists on disk and is pointing at a directory. + /// + /// This function will traverse symbolic links to query information about the + /// destination file. In case of broken symbolic links this will return `false`. + /// + /// If you cannot access the directory containing the file, e.g., because of a + /// permission error, this will return `false`. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// assert_eq!(Utf8Path::new("./is_a_directory/").is_dir(), true); + /// assert_eq!(Utf8Path::new("a_file.txt").is_dir(), false); + /// ``` + /// + /// # See Also + /// + /// This is a convenience function that coerces errors to false. If you want to + /// check errors, call [`fs::metadata`] and handle its [`Result`]. Then call + /// [`fs::Metadata::is_dir`] if it was [`Ok`]. + #[must_use] + pub fn is_dir(&self) -> bool { + self.0.is_dir() + } + + /// Returns `true` if the path exists on disk and is pointing at a symbolic link. + /// + /// This function will not traverse symbolic links. + /// In case of a broken symbolic link this will also return true. + /// + /// If you cannot access the directory containing the file, e.g., because of a + /// permission error, this will return false. + /// + /// # Examples + /// + #[cfg_attr(unix, doc = "```no_run")] + #[cfg_attr(not(unix), doc = "```ignore")] + /// use camino::Utf8Path; + /// use std::os::unix::fs::symlink; + /// + /// let link_path = Utf8Path::new("link"); + /// symlink("/origin_does_not_exist/", link_path).unwrap(); + /// assert_eq!(link_path.is_symlink(), true); + /// assert_eq!(link_path.exists(), false); + /// ``` + /// + /// # See Also + /// + /// This is a convenience function that coerces errors to false. If you want to + /// check errors, call [`Utf8Path::symlink_metadata`] and handle its [`Result`]. Then call + /// [`fs::Metadata::is_symlink`] if it was [`Ok`]. + #[must_use] + pub fn is_symlink(&self) -> bool { + self.symlink_metadata() + .map(|m| m.file_type().is_symlink()) + .unwrap_or(false) + } + + /// Converts a `Box<Utf8Path>` into a [`Utf8PathBuf`] without copying or allocating. + #[must_use = "`self` will be dropped if the result is not used"] + pub fn into_path_buf(self: Box<Utf8Path>) -> Utf8PathBuf { + let ptr = Box::into_raw(self) as *mut Path; + // SAFETY: + // * self is valid UTF-8 + // * ptr was constructed by consuming self so it represents an owned path. + // * Utf8Path is marked as #[repr(transparent)] so the conversion from a *mut Utf8Path to a + // *mut Path is valid. + let boxed_path = unsafe { Box::from_raw(ptr) }; + Utf8PathBuf(boxed_path.into_path_buf()) + } + + // invariant: Path must be guaranteed to be utf-8 data + unsafe fn assume_utf8(path: &Path) -> &Utf8Path { + // SAFETY: Utf8Path is marked as #[repr(transparent)] so the conversion from a + // *const Path to a *const Utf8Path is valid. + &*(path as *const Path as *const Utf8Path) + } +} + +impl Clone for Box<Utf8Path> { + fn clone(&self) -> Self { + let boxed: Box<Path> = self.0.into(); + let ptr = Box::into_raw(boxed) as *mut Utf8Path; + // SAFETY: + // * self is valid UTF-8 + // * ptr was created by consuming a Box<Path> so it represents an rced pointer + // * Utf8Path is marked as #[repr(transparent)] so the conversion from *mut Path to + // *mut Utf8Path is valid + unsafe { Box::from_raw(ptr) } + } +} + +impl fmt::Display for Utf8Path { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + fmt::Display::fmt(self.as_str(), f) + } +} + +impl fmt::Debug for Utf8Path { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + fmt::Debug::fmt(self.as_str(), f) + } +} + +/// An iterator over [`Utf8Path`] and its ancestors. +/// +/// This `struct` is created by the [`ancestors`] method on [`Utf8Path`]. +/// See its documentation for more. +/// +/// # Examples +/// +/// ``` +/// use camino::Utf8Path; +/// +/// let path = Utf8Path::new("/foo/bar"); +/// +/// for ancestor in path.ancestors() { +/// println!("{}", ancestor); +/// } +/// ``` +/// +/// [`ancestors`]: Utf8Path::ancestors +#[derive(Copy, Clone)] +#[must_use = "iterators are lazy and do nothing unless consumed"] +#[repr(transparent)] +pub struct Utf8Ancestors<'a>(Ancestors<'a>); + +impl<'a> fmt::Debug for Utf8Ancestors<'a> { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + fmt::Debug::fmt(&self.0, f) + } +} + +impl<'a> Iterator for Utf8Ancestors<'a> { + type Item = &'a Utf8Path; + + fn next(&mut self) -> Option<Self::Item> { + self.0.next().map(|path| { + // SAFETY: Utf8Ancestors was constructed from a Utf8Path, so it is guaranteed to + // be valid UTF-8 + unsafe { Utf8Path::assume_utf8(path) } + }) + } +} + +impl<'a> FusedIterator for Utf8Ancestors<'a> {} + +/// An iterator over the [`Utf8Component`]s of a [`Utf8Path`]. +/// +/// This `struct` is created by the [`components`] method on [`Utf8Path`]. +/// See its documentation for more. +/// +/// # Examples +/// +/// ``` +/// use camino::Utf8Path; +/// +/// let path = Utf8Path::new("/tmp/foo/bar.txt"); +/// +/// for component in path.components() { +/// println!("{:?}", component); +/// } +/// ``` +/// +/// [`components`]: Utf8Path::components +#[derive(Clone, Eq, Ord, PartialEq, PartialOrd)] +#[must_use = "iterators are lazy and do nothing unless consumed"] +pub struct Utf8Components<'a>(Components<'a>); + +impl<'a> Utf8Components<'a> { + /// Extracts a slice corresponding to the portion of the path remaining for iteration. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let mut components = Utf8Path::new("/tmp/foo/bar.txt").components(); + /// components.next(); + /// components.next(); + /// + /// assert_eq!(Utf8Path::new("foo/bar.txt"), components.as_path()); + /// ``` + #[must_use] + pub fn as_path(&self) -> &'a Utf8Path { + // SAFETY: Utf8Components was constructed from a Utf8Path, so it is guaranteed to be valid + // UTF-8 + unsafe { Utf8Path::assume_utf8(self.0.as_path()) } + } +} + +impl<'a> Iterator for Utf8Components<'a> { + type Item = Utf8Component<'a>; + + fn next(&mut self) -> Option<Self::Item> { + self.0.next().map(|component| { + // SAFETY: Utf8Component was constructed from a Utf8Path, so it is guaranteed to be + // valid UTF-8 + unsafe { Utf8Component::new(component) } + }) + } +} + +impl<'a> FusedIterator for Utf8Components<'a> {} + +impl<'a> DoubleEndedIterator for Utf8Components<'a> { + fn next_back(&mut self) -> Option<Self::Item> { + self.0.next_back().map(|component| { + // SAFETY: Utf8Component was constructed from a Utf8Path, so it is guaranteed to be + // valid UTF-8 + unsafe { Utf8Component::new(component) } + }) + } +} + +impl<'a> fmt::Debug for Utf8Components<'a> { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + fmt::Debug::fmt(&self.0, f) + } +} + +impl AsRef<Utf8Path> for Utf8Components<'_> { + fn as_ref(&self) -> &Utf8Path { + self.as_path() + } +} + +impl AsRef<Path> for Utf8Components<'_> { + fn as_ref(&self) -> &Path { + self.as_path().as_ref() + } +} + +impl AsRef<str> for Utf8Components<'_> { + fn as_ref(&self) -> &str { + self.as_path().as_ref() + } +} + +impl AsRef<OsStr> for Utf8Components<'_> { + fn as_ref(&self) -> &OsStr { + self.as_path().as_os_str() + } +} + +/// An iterator over the [`Utf8Component`]s of a [`Utf8Path`], as [`str`] slices. +/// +/// This `struct` is created by the [`iter`] method on [`Utf8Path`]. +/// See its documentation for more. +/// +/// [`iter`]: Utf8Path::iter +#[derive(Clone)] +#[must_use = "iterators are lazy and do nothing unless consumed"] +pub struct Iter<'a> { + inner: Utf8Components<'a>, +} + +impl fmt::Debug for Iter<'_> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + struct DebugHelper<'a>(&'a Utf8Path); + + impl fmt::Debug for DebugHelper<'_> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.debug_list().entries(self.0.iter()).finish() + } + } + + f.debug_tuple("Iter") + .field(&DebugHelper(self.as_path())) + .finish() + } +} + +impl<'a> Iter<'a> { + /// Extracts a slice corresponding to the portion of the path remaining for iteration. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let mut iter = Utf8Path::new("/tmp/foo/bar.txt").iter(); + /// iter.next(); + /// iter.next(); + /// + /// assert_eq!(Utf8Path::new("foo/bar.txt"), iter.as_path()); + /// ``` + #[must_use] + pub fn as_path(&self) -> &'a Utf8Path { + self.inner.as_path() + } +} + +impl AsRef<Utf8Path> for Iter<'_> { + fn as_ref(&self) -> &Utf8Path { + self.as_path() + } +} + +impl AsRef<Path> for Iter<'_> { + fn as_ref(&self) -> &Path { + self.as_path().as_ref() + } +} + +impl AsRef<str> for Iter<'_> { + fn as_ref(&self) -> &str { + self.as_path().as_ref() + } +} + +impl AsRef<OsStr> for Iter<'_> { + fn as_ref(&self) -> &OsStr { + self.as_path().as_os_str() + } +} + +impl<'a> Iterator for Iter<'a> { + type Item = &'a str; + + fn next(&mut self) -> Option<&'a str> { + self.inner.next().map(|component| component.as_str()) + } +} + +impl<'a> DoubleEndedIterator for Iter<'a> { + fn next_back(&mut self) -> Option<&'a str> { + self.inner.next_back().map(|component| component.as_str()) + } +} + +impl FusedIterator for Iter<'_> {} + +/// A single component of a path. +/// +/// A `Utf8Component` roughly corresponds to a substring between path separators +/// (`/` or `\`). +/// +/// This `enum` is created by iterating over [`Utf8Components`], which in turn is +/// created by the [`components`](Utf8Path::components) method on [`Utf8Path`]. +/// +/// # Examples +/// +/// ```rust +/// use camino::{Utf8Component, Utf8Path}; +/// +/// let path = Utf8Path::new("/tmp/foo/bar.txt"); +/// let components = path.components().collect::<Vec<_>>(); +/// assert_eq!(&components, &[ +/// Utf8Component::RootDir, +/// Utf8Component::Normal("tmp"), +/// Utf8Component::Normal("foo"), +/// Utf8Component::Normal("bar.txt"), +/// ]); +/// ``` +#[derive(Copy, Clone, Eq, PartialEq, Hash, Ord, PartialOrd)] +pub enum Utf8Component<'a> { + /// A Windows path prefix, e.g., `C:` or `\\server\share`. + /// + /// There is a large variety of prefix types, see [`Utf8Prefix`]'s documentation + /// for more. + /// + /// Does not occur on Unix. + Prefix(Utf8PrefixComponent<'a>), + + /// The root directory component, appears after any prefix and before anything else. + /// + /// It represents a separator that designates that a path starts from root. + RootDir, + + /// A reference to the current directory, i.e., `.`. + CurDir, + + /// A reference to the parent directory, i.e., `..`. + ParentDir, + + /// A normal component, e.g., `a` and `b` in `a/b`. + /// + /// This variant is the most common one, it represents references to files + /// or directories. + Normal(&'a str), +} + +impl<'a> Utf8Component<'a> { + unsafe fn new(component: Component<'a>) -> Utf8Component<'a> { + match component { + Component::Prefix(prefix) => Utf8Component::Prefix(Utf8PrefixComponent(prefix)), + Component::RootDir => Utf8Component::RootDir, + Component::CurDir => Utf8Component::CurDir, + Component::ParentDir => Utf8Component::ParentDir, + Component::Normal(s) => Utf8Component::Normal(assume_utf8(s)), + } + } + + /// Extracts the underlying [`str`] slice. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("./tmp/foo/bar.txt"); + /// let components: Vec<_> = path.components().map(|comp| comp.as_str()).collect(); + /// assert_eq!(&components, &[".", "tmp", "foo", "bar.txt"]); + /// ``` + #[must_use] + pub fn as_str(&self) -> &'a str { + // SAFETY: Utf8Component was constructed from a Utf8Path, so it is guaranteed to be + // valid UTF-8 + unsafe { assume_utf8(self.as_os_str()) } + } + + /// Extracts the underlying [`OsStr`] slice. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// let path = Utf8Path::new("./tmp/foo/bar.txt"); + /// let components: Vec<_> = path.components().map(|comp| comp.as_os_str()).collect(); + /// assert_eq!(&components, &[".", "tmp", "foo", "bar.txt"]); + /// ``` + #[must_use] + pub fn as_os_str(&self) -> &'a OsStr { + match *self { + Utf8Component::Prefix(prefix) => prefix.as_os_str(), + Utf8Component::RootDir => Component::RootDir.as_os_str(), + Utf8Component::CurDir => Component::CurDir.as_os_str(), + Utf8Component::ParentDir => Component::ParentDir.as_os_str(), + Utf8Component::Normal(s) => OsStr::new(s), + } + } +} + +impl<'a> fmt::Debug for Utf8Component<'a> { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + fmt::Debug::fmt(self.as_os_str(), f) + } +} + +impl<'a> fmt::Display for Utf8Component<'a> { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + fmt::Display::fmt(self.as_str(), f) + } +} + +impl AsRef<Utf8Path> for Utf8Component<'_> { + fn as_ref(&self) -> &Utf8Path { + self.as_str().as_ref() + } +} + +impl AsRef<Path> for Utf8Component<'_> { + fn as_ref(&self) -> &Path { + self.as_os_str().as_ref() + } +} + +impl AsRef<str> for Utf8Component<'_> { + fn as_ref(&self) -> &str { + self.as_str() + } +} + +impl AsRef<OsStr> for Utf8Component<'_> { + fn as_ref(&self) -> &OsStr { + self.as_os_str() + } +} + +/// Windows path prefixes, e.g., `C:` or `\\server\share`. +/// +/// Windows uses a variety of path prefix styles, including references to drive +/// volumes (like `C:`), network shared folders (like `\\server\share`), and +/// others. In addition, some path prefixes are "verbatim" (i.e., prefixed with +/// `\\?\`), in which case `/` is *not* treated as a separator and essentially +/// no normalization is performed. +/// +/// # Examples +/// +/// ``` +/// use camino::{Utf8Component, Utf8Path, Utf8Prefix}; +/// use camino::Utf8Prefix::*; +/// +/// fn get_path_prefix(s: &str) -> Utf8Prefix { +/// let path = Utf8Path::new(s); +/// match path.components().next().unwrap() { +/// Utf8Component::Prefix(prefix_component) => prefix_component.kind(), +/// _ => panic!(), +/// } +/// } +/// +/// # if cfg!(windows) { +/// assert_eq!(Verbatim("pictures"), get_path_prefix(r"\\?\pictures\kittens")); +/// assert_eq!(VerbatimUNC("server", "share"), get_path_prefix(r"\\?\UNC\server\share")); +/// assert_eq!(VerbatimDisk(b'C'), get_path_prefix(r"\\?\c:\")); +/// assert_eq!(DeviceNS("BrainInterface"), get_path_prefix(r"\\.\BrainInterface")); +/// assert_eq!(UNC("server", "share"), get_path_prefix(r"\\server\share")); +/// assert_eq!(Disk(b'C'), get_path_prefix(r"C:\Users\Rust\Pictures\Ferris")); +/// # } +/// ``` +#[derive(Copy, Clone, Debug, Hash, PartialOrd, Ord, PartialEq, Eq)] +pub enum Utf8Prefix<'a> { + /// Verbatim prefix, e.g., `\\?\cat_pics`. + /// + /// Verbatim prefixes consist of `\\?\` immediately followed by the given + /// component. + Verbatim(&'a str), + + /// Verbatim prefix using Windows' _**U**niform **N**aming **C**onvention_, + /// e.g., `\\?\UNC\server\share`. + /// + /// Verbatim UNC prefixes consist of `\\?\UNC\` immediately followed by the + /// server's hostname and a share name. + VerbatimUNC(&'a str, &'a str), + + /// Verbatim disk prefix, e.g., `\\?\C:`. + /// + /// Verbatim disk prefixes consist of `\\?\` immediately followed by the + /// drive letter and `:`. + VerbatimDisk(u8), + + /// Device namespace prefix, e.g., `\\.\COM42`. + /// + /// Device namespace prefixes consist of `\\.\` immediately followed by the + /// device name. + DeviceNS(&'a str), + + /// Prefix using Windows' _**U**niform **N**aming **C**onvention_, e.g. + /// `\\server\share`. + /// + /// UNC prefixes consist of the server's hostname and a share name. + UNC(&'a str, &'a str), + + /// Prefix `C:` for the given disk drive. + Disk(u8), +} + +impl<'a> Utf8Prefix<'a> { + /// Determines if the prefix is verbatim, i.e., begins with `\\?\`. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Prefix::*; + /// + /// assert!(Verbatim("pictures").is_verbatim()); + /// assert!(VerbatimUNC("server", "share").is_verbatim()); + /// assert!(VerbatimDisk(b'C').is_verbatim()); + /// assert!(!DeviceNS("BrainInterface").is_verbatim()); + /// assert!(!UNC("server", "share").is_verbatim()); + /// assert!(!Disk(b'C').is_verbatim()); + /// ``` + #[must_use] + pub fn is_verbatim(&self) -> bool { + use Utf8Prefix::*; + match self { + Verbatim(_) | VerbatimDisk(_) | VerbatimUNC(..) => true, + _ => false, + } + } +} + +/// A structure wrapping a Windows path prefix as well as its unparsed string +/// representation. +/// +/// In addition to the parsed [`Utf8Prefix`] information returned by [`kind`], +/// `Utf8PrefixComponent` also holds the raw and unparsed [`str`] slice, +/// returned by [`as_str`]. +/// +/// Instances of this `struct` can be obtained by matching against the +/// [`Prefix` variant] on [`Utf8Component`]. +/// +/// Does not occur on Unix. +/// +/// # Examples +/// +/// ``` +/// # if cfg!(windows) { +/// use camino::{Utf8Component, Utf8Path, Utf8Prefix}; +/// use std::ffi::OsStr; +/// +/// let path = Utf8Path::new(r"c:\you\later\"); +/// match path.components().next().unwrap() { +/// Utf8Component::Prefix(prefix_component) => { +/// assert_eq!(Utf8Prefix::Disk(b'C'), prefix_component.kind()); +/// assert_eq!("c:", prefix_component.as_str()); +/// } +/// _ => unreachable!(), +/// } +/// # } +/// ``` +/// +/// [`as_str`]: Utf8PrefixComponent::as_str +/// [`kind`]: Utf8PrefixComponent::kind +/// [`Prefix` variant]: Utf8Component::Prefix +#[repr(transparent)] +#[derive(Clone, Copy, Eq, PartialEq, Hash, Ord, PartialOrd)] +pub struct Utf8PrefixComponent<'a>(PrefixComponent<'a>); + +impl<'a> Utf8PrefixComponent<'a> { + /// Returns the parsed prefix data. + /// + /// See [`Utf8Prefix`]'s documentation for more information on the different + /// kinds of prefixes. + #[must_use] + pub fn kind(&self) -> Utf8Prefix<'a> { + // SAFETY for all the below unsafe blocks: the path self was originally constructed from was + // UTF-8 so any parts of it are valid UTF-8 + match self.0.kind() { + Prefix::Verbatim(prefix) => Utf8Prefix::Verbatim(unsafe { assume_utf8(prefix) }), + Prefix::VerbatimUNC(server, share) => { + let server = unsafe { assume_utf8(server) }; + let share = unsafe { assume_utf8(share) }; + Utf8Prefix::VerbatimUNC(server, share) + } + Prefix::VerbatimDisk(drive) => Utf8Prefix::VerbatimDisk(drive), + Prefix::DeviceNS(prefix) => Utf8Prefix::DeviceNS(unsafe { assume_utf8(prefix) }), + Prefix::UNC(server, share) => { + let server = unsafe { assume_utf8(server) }; + let share = unsafe { assume_utf8(share) }; + Utf8Prefix::UNC(server, share) + } + Prefix::Disk(drive) => Utf8Prefix::Disk(drive), + } + } + + /// Returns the [`str`] slice for this prefix. + #[must_use] + pub fn as_str(&self) -> &'a str { + // SAFETY: Utf8PrefixComponent was constructed from a Utf8Path, so it is guaranteed to be + // valid UTF-8 + unsafe { assume_utf8(self.as_os_str()) } + } + + /// Returns the raw [`OsStr`] slice for this prefix. + #[must_use] + pub fn as_os_str(&self) -> &'a OsStr { + self.0.as_os_str() + } +} + +impl<'a> fmt::Debug for Utf8PrefixComponent<'a> { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + fmt::Debug::fmt(&self.0, f) + } +} + +impl<'a> fmt::Display for Utf8PrefixComponent<'a> { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + fmt::Display::fmt(self.as_str(), f) + } +} + +// --- +// read_dir_utf8 +// --- + +/// Iterator over the entries in a directory. +/// +/// This iterator is returned from [`Utf8Path::read_dir_utf8`] and will yield instances of +/// <code>[io::Result]<[Utf8DirEntry]></code>. Through a [`Utf8 DirEntry`] information like the entry's path +/// and possibly other metadata can be learned. +/// +/// The order in which this iterator returns entries is platform and filesystem +/// dependent. +/// +/// # Errors +/// +/// This [`io::Result`] will be an [`Err`] if there's some sort of intermittent +/// IO error during iteration. +/// +/// If a directory entry is not UTF-8, an [`io::Error`] is returned with the +/// [`ErrorKind`](io::ErrorKind) set to `InvalidData` and the payload set to a [`FromPathBufError`]. +#[derive(Debug)] +pub struct ReadDirUtf8 { + inner: fs::ReadDir, +} + +impl Iterator for ReadDirUtf8 { + type Item = io::Result<Utf8DirEntry>; + + fn next(&mut self) -> Option<io::Result<Utf8DirEntry>> { + self.inner + .next() + .map(|entry| entry.and_then(Utf8DirEntry::new)) + } +} + +/// Entries returned by the [`ReadDirUtf8`] iterator. +/// +/// An instance of `Utf8DirEntry` represents an entry inside of a directory on the filesystem. Each +/// entry can be inspected via methods to learn about the full path or possibly other metadata. +#[derive(Debug)] +pub struct Utf8DirEntry { + inner: fs::DirEntry, + path: Utf8PathBuf, +} + +impl Utf8DirEntry { + fn new(inner: fs::DirEntry) -> io::Result<Self> { + let path = inner + .path() + .try_into() + .map_err(|err| io::Error::new(io::ErrorKind::InvalidData, err))?; + Ok(Self { inner, path }) + } + + /// Returns the full path to the file that this entry represents. + /// + /// The full path is created by joining the original path to `read_dir` + /// with the filename of this entry. + /// + /// # Examples + /// + /// ```no_run + /// use camino::Utf8Path; + /// + /// fn main() -> std::io::Result<()> { + /// for entry in Utf8Path::new(".").read_dir_utf8()? { + /// let dir = entry?; + /// println!("{}", dir.path()); + /// } + /// Ok(()) + /// } + /// ``` + /// + /// This prints output like: + /// + /// ```text + /// ./whatever.txt + /// ./foo.html + /// ./hello_world.rs + /// ``` + /// + /// The exact text, of course, depends on what files you have in `.`. + #[inline] + pub fn path(&self) -> &Utf8Path { + &self.path + } + + /// Returns the metadata for the file that this entry points at. + /// + /// This function will not traverse symlinks if this entry points at a symlink. To traverse + /// symlinks use [`Utf8Path::metadata`] or [`fs::File::metadata`]. + /// + /// # Platform-specific behavior + /// + /// On Windows this function is cheap to call (no extra system calls + /// needed), but on Unix platforms this function is the equivalent of + /// calling `symlink_metadata` on the path. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// if let Ok(entries) = Utf8Path::new(".").read_dir_utf8() { + /// for entry in entries { + /// if let Ok(entry) = entry { + /// // Here, `entry` is a `Utf8DirEntry`. + /// if let Ok(metadata) = entry.metadata() { + /// // Now let's show our entry's permissions! + /// println!("{}: {:?}", entry.path(), metadata.permissions()); + /// } else { + /// println!("Couldn't get metadata for {}", entry.path()); + /// } + /// } + /// } + /// } + /// ``` + #[inline] + pub fn metadata(&self) -> io::Result<Metadata> { + self.inner.metadata() + } + + /// Returns the file type for the file that this entry points at. + /// + /// This function will not traverse symlinks if this entry points at a + /// symlink. + /// + /// # Platform-specific behavior + /// + /// On Windows and most Unix platforms this function is free (no extra + /// system calls needed), but some Unix platforms may require the equivalent + /// call to `symlink_metadata` to learn about the target file type. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// if let Ok(entries) = Utf8Path::new(".").read_dir_utf8() { + /// for entry in entries { + /// if let Ok(entry) = entry { + /// // Here, `entry` is a `DirEntry`. + /// if let Ok(file_type) = entry.file_type() { + /// // Now let's show our entry's file type! + /// println!("{}: {:?}", entry.path(), file_type); + /// } else { + /// println!("Couldn't get file type for {}", entry.path()); + /// } + /// } + /// } + /// } + /// ``` + #[inline] + pub fn file_type(&self) -> io::Result<fs::FileType> { + self.inner.file_type() + } + + /// Returns the bare file name of this directory entry without any other + /// leading path component. + /// + /// # Examples + /// + /// ``` + /// use camino::Utf8Path; + /// + /// if let Ok(entries) = Utf8Path::new(".").read_dir_utf8() { + /// for entry in entries { + /// if let Ok(entry) = entry { + /// // Here, `entry` is a `DirEntry`. + /// println!("{}", entry.file_name()); + /// } + /// } + /// } + /// ``` + pub fn file_name(&self) -> &str { + self.path + .file_name() + .expect("path created through DirEntry must have a filename") + } + + /// Returns the original [`fs::DirEntry`] within this [`Utf8DirEntry`]. + #[inline] + pub fn into_inner(self) -> fs::DirEntry { + self.inner + } +} + +impl From<String> for Utf8PathBuf { + fn from(string: String) -> Utf8PathBuf { + Utf8PathBuf(string.into()) + } +} + +impl FromStr for Utf8PathBuf { + type Err = Infallible; + + fn from_str(s: &str) -> Result<Self, Self::Err> { + Ok(Utf8PathBuf(s.into())) + } +} + +// --- +// From impls: borrowed -> borrowed +// --- + +impl<'a> From<&'a str> for &'a Utf8Path { + fn from(s: &'a str) -> &'a Utf8Path { + Utf8Path::new(s) + } +} + +// --- +// From impls: borrowed -> owned +// --- + +impl<T: ?Sized + AsRef<str>> From<&T> for Utf8PathBuf { + fn from(s: &T) -> Utf8PathBuf { + Utf8PathBuf::from(s.as_ref().to_owned()) + } +} + +impl<T: ?Sized + AsRef<str>> From<&T> for Box<Utf8Path> { + fn from(s: &T) -> Box<Utf8Path> { + Utf8PathBuf::from(s).into_boxed_path() + } +} + +impl From<&'_ Utf8Path> for Arc<Utf8Path> { + fn from(path: &Utf8Path) -> Arc<Utf8Path> { + let arc: Arc<Path> = Arc::from(AsRef::<Path>::as_ref(path)); + let ptr = Arc::into_raw(arc) as *const Utf8Path; + // SAFETY: + // * path is valid UTF-8 + // * ptr was created by consuming an Arc<Path> so it represents an arced pointer + // * Utf8Path is marked as #[repr(transparent)] so the conversion from *const Path to + // *const Utf8Path is valid + unsafe { Arc::from_raw(ptr) } + } +} + +impl From<&'_ Utf8Path> for Rc<Utf8Path> { + fn from(path: &Utf8Path) -> Rc<Utf8Path> { + let rc: Rc<Path> = Rc::from(AsRef::<Path>::as_ref(path)); + let ptr = Rc::into_raw(rc) as *const Utf8Path; + // SAFETY: + // * path is valid UTF-8 + // * ptr was created by consuming an Rc<Path> so it represents an rced pointer + // * Utf8Path is marked as #[repr(transparent)] so the conversion from *const Path to + // *const Utf8Path is valid + unsafe { Rc::from_raw(ptr) } + } +} + +impl<'a> From<&'a Utf8Path> for Cow<'a, Utf8Path> { + fn from(path: &'a Utf8Path) -> Cow<'a, Utf8Path> { + Cow::Borrowed(path) + } +} + +impl From<&'_ Utf8Path> for Box<Path> { + fn from(path: &Utf8Path) -> Box<Path> { + AsRef::<Path>::as_ref(path).into() + } +} + +impl From<&'_ Utf8Path> for Arc<Path> { + fn from(path: &Utf8Path) -> Arc<Path> { + AsRef::<Path>::as_ref(path).into() + } +} + +impl From<&'_ Utf8Path> for Rc<Path> { + fn from(path: &Utf8Path) -> Rc<Path> { + AsRef::<Path>::as_ref(path).into() + } +} + +impl<'a> From<&'a Utf8Path> for Cow<'a, Path> { + fn from(path: &'a Utf8Path) -> Cow<'a, Path> { + Cow::Borrowed(path.as_ref()) + } +} + +// --- +// From impls: owned -> owned +// --- + +impl From<Box<Utf8Path>> for Utf8PathBuf { + fn from(path: Box<Utf8Path>) -> Utf8PathBuf { + path.into_path_buf() + } +} + +impl From<Utf8PathBuf> for Box<Utf8Path> { + fn from(path: Utf8PathBuf) -> Box<Utf8Path> { + path.into_boxed_path() + } +} + +impl<'a> From<Cow<'a, Utf8Path>> for Utf8PathBuf { + fn from(path: Cow<'a, Utf8Path>) -> Utf8PathBuf { + path.into_owned() + } +} + +impl From<Utf8PathBuf> for String { + fn from(path: Utf8PathBuf) -> String { + path.into_string() + } +} + +impl From<Utf8PathBuf> for OsString { + fn from(path: Utf8PathBuf) -> OsString { + path.into_os_string() + } +} + +impl<'a> From<Utf8PathBuf> for Cow<'a, Utf8Path> { + fn from(path: Utf8PathBuf) -> Cow<'a, Utf8Path> { + Cow::Owned(path) + } +} + +impl From<Utf8PathBuf> for Arc<Utf8Path> { + fn from(path: Utf8PathBuf) -> Arc<Utf8Path> { + let arc: Arc<Path> = Arc::from(path.0); + let ptr = Arc::into_raw(arc) as *const Utf8Path; + // SAFETY: + // * path is valid UTF-8 + // * ptr was created by consuming an Arc<Path> so it represents an arced pointer + // * Utf8Path is marked as #[repr(transparent)] so the conversion from *const Path to + // *const Utf8Path is valid + unsafe { Arc::from_raw(ptr) } + } +} + +impl From<Utf8PathBuf> for Rc<Utf8Path> { + fn from(path: Utf8PathBuf) -> Rc<Utf8Path> { + let rc: Rc<Path> = Rc::from(path.0); + let ptr = Rc::into_raw(rc) as *const Utf8Path; + // SAFETY: + // * path is valid UTF-8 + // * ptr was created by consuming an Rc<Path> so it represents an rced pointer + // * Utf8Path is marked as #[repr(transparent)] so the conversion from *const Path to + // *const Utf8Path is valid + unsafe { Rc::from_raw(ptr) } + } +} + +impl From<Utf8PathBuf> for PathBuf { + fn from(path: Utf8PathBuf) -> PathBuf { + path.0 + } +} + +impl From<Utf8PathBuf> for Box<Path> { + fn from(path: Utf8PathBuf) -> Box<Path> { + PathBuf::from(path).into_boxed_path() + } +} + +impl From<Utf8PathBuf> for Arc<Path> { + fn from(path: Utf8PathBuf) -> Arc<Path> { + PathBuf::from(path).into() + } +} + +impl From<Utf8PathBuf> for Rc<Path> { + fn from(path: Utf8PathBuf) -> Rc<Path> { + PathBuf::from(path).into() + } +} + +impl<'a> From<Utf8PathBuf> for Cow<'a, Path> { + fn from(path: Utf8PathBuf) -> Cow<'a, Path> { + PathBuf::from(path).into() + } +} + +// --- +// TryFrom impls +// --- + +impl TryFrom<PathBuf> for Utf8PathBuf { + type Error = FromPathBufError; + + fn try_from(path: PathBuf) -> Result<Utf8PathBuf, Self::Error> { + Utf8PathBuf::from_path_buf(path).map_err(|path| FromPathBufError { + path, + error: FromPathError(()), + }) + } +} + +impl<'a> TryFrom<&'a Path> for &'a Utf8Path { + type Error = FromPathError; + + fn try_from(path: &'a Path) -> Result<&'a Utf8Path, Self::Error> { + Utf8Path::from_path(path).ok_or(FromPathError(())) + } +} + +/// A possible error value while converting a [`PathBuf`] to a [`Utf8PathBuf`]. +/// +/// Produced by the `TryFrom<PathBuf>` implementation for [`Utf8PathBuf`]. +/// +/// # Examples +/// +/// ``` +/// use camino::{Utf8PathBuf, FromPathBufError}; +/// use std::convert::{TryFrom, TryInto}; +/// use std::ffi::OsStr; +/// # #[cfg(unix)] +/// use std::os::unix::ffi::OsStrExt; +/// use std::path::PathBuf; +/// +/// let unicode_path = PathBuf::from("/valid/unicode"); +/// let utf8_path_buf: Utf8PathBuf = unicode_path.try_into().expect("valid Unicode path succeeded"); +/// +/// // Paths on Unix can be non-UTF-8. +/// # #[cfg(unix)] +/// let non_unicode_str = OsStr::from_bytes(b"\xFF\xFF\xFF"); +/// # #[cfg(unix)] +/// let non_unicode_path = PathBuf::from(non_unicode_str); +/// # #[cfg(unix)] +/// let err: FromPathBufError = Utf8PathBuf::try_from(non_unicode_path.clone()) +/// .expect_err("non-Unicode path failed"); +/// # #[cfg(unix)] +/// assert_eq!(err.as_path(), &non_unicode_path); +/// # #[cfg(unix)] +/// assert_eq!(err.into_path_buf(), non_unicode_path); +/// ``` +#[derive(Clone, Debug, Eq, PartialEq)] +pub struct FromPathBufError { + path: PathBuf, + error: FromPathError, +} + +impl FromPathBufError { + /// Returns the [`Path`] slice that was attempted to be converted to [`Utf8PathBuf`]. + pub fn as_path(&self) -> &Path { + &self.path + } + + /// Returns the [`PathBuf`] that was attempted to be converted to [`Utf8PathBuf`]. + pub fn into_path_buf(self) -> PathBuf { + self.path + } + + /// Fetches a [`FromPathError`] for more about the conversion failure. + /// + /// At the moment this struct does not contain any additional information, but is provided for + /// completeness. + pub fn from_path_error(&self) -> FromPathError { + self.error + } + + /// Converts self into a [`std::io::Error`] with kind + /// [`InvalidData`](io::ErrorKind::InvalidData). + /// + /// Many users of `FromPathBufError` will want to convert it into an `io::Error`. This is a + /// convenience method to do that. + pub fn into_io_error(self) -> io::Error { + // NOTE: we don't currently implement `From<FromPathBufError> for io::Error` because we want + // to ensure the user actually desires that conversion. + io::Error::new(io::ErrorKind::InvalidData, self) + } +} + +impl fmt::Display for FromPathBufError { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + write!(f, "PathBuf contains invalid UTF-8: {}", self.path.display()) + } +} + +impl error::Error for FromPathBufError { + fn source(&self) -> Option<&(dyn error::Error + 'static)> { + Some(&self.error) + } +} + +/// A possible error value while converting a [`Path`] to a [`Utf8Path`]. +/// +/// Produced by the `TryFrom<&Path>` implementation for [`&Utf8Path`](Utf8Path). +/// +/// +/// # Examples +/// +/// ``` +/// use camino::{Utf8Path, FromPathError}; +/// use std::convert::{TryFrom, TryInto}; +/// use std::ffi::OsStr; +/// # #[cfg(unix)] +/// use std::os::unix::ffi::OsStrExt; +/// use std::path::Path; +/// +/// let unicode_path = Path::new("/valid/unicode"); +/// let utf8_path: &Utf8Path = unicode_path.try_into().expect("valid Unicode path succeeded"); +/// +/// // Paths on Unix can be non-UTF-8. +/// # #[cfg(unix)] +/// let non_unicode_str = OsStr::from_bytes(b"\xFF\xFF\xFF"); +/// # #[cfg(unix)] +/// let non_unicode_path = Path::new(non_unicode_str); +/// # #[cfg(unix)] +/// let err: FromPathError = <&Utf8Path>::try_from(non_unicode_path) +/// .expect_err("non-Unicode path failed"); +/// ``` +#[derive(Copy, Clone, Debug, Eq, PartialEq)] +pub struct FromPathError(()); + +impl FromPathError { + /// Converts self into a [`std::io::Error`] with kind + /// [`InvalidData`](io::ErrorKind::InvalidData). + /// + /// Many users of `FromPathError` will want to convert it into an `io::Error`. This is a + /// convenience method to do that. + pub fn into_io_error(self) -> io::Error { + // NOTE: we don't currently implement `From<FromPathBufError> for io::Error` because we want + // to ensure the user actually desires that conversion. + io::Error::new(io::ErrorKind::InvalidData, self) + } +} + +impl fmt::Display for FromPathError { + fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { + write!(f, "Path contains invalid UTF-8") + } +} + +impl error::Error for FromPathError { + fn source(&self) -> Option<&(dyn error::Error + 'static)> { + None + } +} + +// --- +// AsRef impls +// --- + +impl AsRef<Utf8Path> for Utf8Path { + fn as_ref(&self) -> &Utf8Path { + self + } +} + +impl AsRef<Utf8Path> for Utf8PathBuf { + fn as_ref(&self) -> &Utf8Path { + self.as_path() + } +} + +impl AsRef<Utf8Path> for str { + fn as_ref(&self) -> &Utf8Path { + Utf8Path::new(self) + } +} + +impl AsRef<Utf8Path> for String { + fn as_ref(&self) -> &Utf8Path { + Utf8Path::new(self) + } +} + +impl AsRef<Path> for Utf8Path { + fn as_ref(&self) -> &Path { + &self.0 + } +} + +impl AsRef<Path> for Utf8PathBuf { + fn as_ref(&self) -> &Path { + &self.0 + } +} + +impl AsRef<str> for Utf8Path { + fn as_ref(&self) -> &str { + self.as_str() + } +} + +impl AsRef<str> for Utf8PathBuf { + fn as_ref(&self) -> &str { + self.as_str() + } +} + +impl AsRef<OsStr> for Utf8Path { + fn as_ref(&self) -> &OsStr { + self.as_os_str() + } +} + +impl AsRef<OsStr> for Utf8PathBuf { + fn as_ref(&self) -> &OsStr { + self.as_os_str() + } +} + +// --- +// Borrow and ToOwned +// --- + +impl Borrow<Utf8Path> for Utf8PathBuf { + fn borrow(&self) -> &Utf8Path { + self.as_path() + } +} + +impl ToOwned for Utf8Path { + type Owned = Utf8PathBuf; + + fn to_owned(&self) -> Utf8PathBuf { + self.to_path_buf() + } +} + +impl<P: AsRef<Utf8Path>> std::iter::FromIterator<P> for Utf8PathBuf { + fn from_iter<I: IntoIterator<Item = P>>(iter: I) -> Utf8PathBuf { + let mut buf = Utf8PathBuf::new(); + buf.extend(iter); + buf + } +} + +// --- +// [Partial]Eq, [Partial]Ord, Hash +// --- + +impl PartialEq for Utf8PathBuf { + fn eq(&self, other: &Utf8PathBuf) -> bool { + self.components() == other.components() + } +} + +impl Eq for Utf8PathBuf {} + +impl Hash for Utf8PathBuf { + fn hash<H: Hasher>(&self, state: &mut H) { + self.as_path().hash(state) + } +} + +impl PartialOrd for Utf8PathBuf { + fn partial_cmp(&self, other: &Utf8PathBuf) -> Option<Ordering> { + self.components().partial_cmp(other.components()) + } +} + +impl Ord for Utf8PathBuf { + fn cmp(&self, other: &Utf8PathBuf) -> Ordering { + self.components().cmp(other.components()) + } +} + +impl PartialEq for Utf8Path { + fn eq(&self, other: &Utf8Path) -> bool { + self.components().eq(other.components()) + } +} + +impl Eq for Utf8Path {} + +impl Hash for Utf8Path { + fn hash<H: Hasher>(&self, state: &mut H) { + for component in self.components() { + component.hash(state) + } + } +} + +impl PartialOrd for Utf8Path { + fn partial_cmp(&self, other: &Utf8Path) -> Option<Ordering> { + self.components().partial_cmp(other.components()) + } +} + +impl Ord for Utf8Path { + fn cmp(&self, other: &Utf8Path) -> Ordering { + self.components().cmp(other.components()) + } +} + +impl<'a> IntoIterator for &'a Utf8PathBuf { + type Item = &'a str; + type IntoIter = Iter<'a>; + fn into_iter(self) -> Iter<'a> { + self.iter() + } +} + +impl<'a> IntoIterator for &'a Utf8Path { + type Item = &'a str; + type IntoIter = Iter<'a>; + fn into_iter(self) -> Iter<'a> { + self.iter() + } +} + +macro_rules! impl_cmp { + ($lhs:ty, $rhs: ty) => { + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialEq<$rhs> for $lhs { + #[inline] + fn eq(&self, other: &$rhs) -> bool { + <Utf8Path as PartialEq>::eq(self, other) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialEq<$lhs> for $rhs { + #[inline] + fn eq(&self, other: &$lhs) -> bool { + <Utf8Path as PartialEq>::eq(self, other) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialOrd<$rhs> for $lhs { + #[inline] + fn partial_cmp(&self, other: &$rhs) -> Option<Ordering> { + <Utf8Path as PartialOrd>::partial_cmp(self, other) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialOrd<$lhs> for $rhs { + #[inline] + fn partial_cmp(&self, other: &$lhs) -> Option<Ordering> { + <Utf8Path as PartialOrd>::partial_cmp(self, other) + } + } + }; +} + +impl_cmp!(Utf8PathBuf, Utf8Path); +impl_cmp!(Utf8PathBuf, &'a Utf8Path); +impl_cmp!(Cow<'a, Utf8Path>, Utf8Path); +impl_cmp!(Cow<'a, Utf8Path>, &'b Utf8Path); +impl_cmp!(Cow<'a, Utf8Path>, Utf8PathBuf); + +macro_rules! impl_cmp_std_path { + ($lhs:ty, $rhs: ty) => { + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialEq<$rhs> for $lhs { + #[inline] + fn eq(&self, other: &$rhs) -> bool { + <Path as PartialEq>::eq(self.as_ref(), other) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialEq<$lhs> for $rhs { + #[inline] + fn eq(&self, other: &$lhs) -> bool { + <Path as PartialEq>::eq(self, other.as_ref()) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialOrd<$rhs> for $lhs { + #[inline] + fn partial_cmp(&self, other: &$rhs) -> Option<std::cmp::Ordering> { + <Path as PartialOrd>::partial_cmp(self.as_ref(), other) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialOrd<$lhs> for $rhs { + #[inline] + fn partial_cmp(&self, other: &$lhs) -> Option<std::cmp::Ordering> { + <Path as PartialOrd>::partial_cmp(self, other.as_ref()) + } + } + }; +} + +impl_cmp_std_path!(Utf8PathBuf, Path); +impl_cmp_std_path!(Utf8PathBuf, &'a Path); +impl_cmp_std_path!(Utf8PathBuf, Cow<'a, Path>); +impl_cmp_std_path!(Utf8PathBuf, PathBuf); +impl_cmp_std_path!(Utf8Path, Path); +impl_cmp_std_path!(Utf8Path, &'a Path); +impl_cmp_std_path!(Utf8Path, Cow<'a, Path>); +impl_cmp_std_path!(Utf8Path, PathBuf); +impl_cmp_std_path!(&'a Utf8Path, Path); +impl_cmp_std_path!(&'a Utf8Path, Cow<'b, Path>); +impl_cmp_std_path!(&'a Utf8Path, PathBuf); +// NOTE: impls for Cow<'a, Utf8Path> cannot be defined because of the orphan rule (E0117) + +macro_rules! impl_cmp_str { + ($lhs:ty, $rhs: ty) => { + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialEq<$rhs> for $lhs { + #[inline] + fn eq(&self, other: &$rhs) -> bool { + <Utf8Path as PartialEq>::eq(self, Utf8Path::new(other)) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialEq<$lhs> for $rhs { + #[inline] + fn eq(&self, other: &$lhs) -> bool { + <Utf8Path as PartialEq>::eq(Utf8Path::new(self), other) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialOrd<$rhs> for $lhs { + #[inline] + fn partial_cmp(&self, other: &$rhs) -> Option<std::cmp::Ordering> { + <Utf8Path as PartialOrd>::partial_cmp(self, Utf8Path::new(other)) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialOrd<$lhs> for $rhs { + #[inline] + fn partial_cmp(&self, other: &$lhs) -> Option<std::cmp::Ordering> { + <Utf8Path as PartialOrd>::partial_cmp(Utf8Path::new(self), other) + } + } + }; +} + +impl_cmp_str!(Utf8PathBuf, str); +impl_cmp_str!(Utf8PathBuf, &'a str); +impl_cmp_str!(Utf8PathBuf, Cow<'a, str>); +impl_cmp_str!(Utf8PathBuf, String); +impl_cmp_str!(Utf8Path, str); +impl_cmp_str!(Utf8Path, &'a str); +impl_cmp_str!(Utf8Path, Cow<'a, str>); +impl_cmp_str!(Utf8Path, String); +impl_cmp_str!(&'a Utf8Path, str); +impl_cmp_str!(&'a Utf8Path, Cow<'b, str>); +impl_cmp_str!(&'a Utf8Path, String); +// NOTE: impls for Cow<'a, Utf8Path> cannot be defined because of the orphan rule (E0117) + +macro_rules! impl_cmp_os_str { + ($lhs:ty, $rhs: ty) => { + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialEq<$rhs> for $lhs { + #[inline] + fn eq(&self, other: &$rhs) -> bool { + <Path as PartialEq>::eq(self.as_ref(), other.as_ref()) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialEq<$lhs> for $rhs { + #[inline] + fn eq(&self, other: &$lhs) -> bool { + <Path as PartialEq>::eq(self.as_ref(), other.as_ref()) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialOrd<$rhs> for $lhs { + #[inline] + fn partial_cmp(&self, other: &$rhs) -> Option<std::cmp::Ordering> { + <Path as PartialOrd>::partial_cmp(self.as_ref(), other.as_ref()) + } + } + + #[allow(clippy::extra_unused_lifetimes)] + impl<'a, 'b> PartialOrd<$lhs> for $rhs { + #[inline] + fn partial_cmp(&self, other: &$lhs) -> Option<std::cmp::Ordering> { + <Path as PartialOrd>::partial_cmp(self.as_ref(), other.as_ref()) + } + } + }; +} + +impl_cmp_os_str!(Utf8PathBuf, OsStr); +impl_cmp_os_str!(Utf8PathBuf, &'a OsStr); +impl_cmp_os_str!(Utf8PathBuf, Cow<'a, OsStr>); +impl_cmp_os_str!(Utf8PathBuf, OsString); +impl_cmp_os_str!(Utf8Path, OsStr); +impl_cmp_os_str!(Utf8Path, &'a OsStr); +impl_cmp_os_str!(Utf8Path, Cow<'a, OsStr>); +impl_cmp_os_str!(Utf8Path, OsString); +impl_cmp_os_str!(&'a Utf8Path, OsStr); +impl_cmp_os_str!(&'a Utf8Path, Cow<'b, OsStr>); +impl_cmp_os_str!(&'a Utf8Path, OsString); +// NOTE: impls for Cow<'a, Utf8Path> cannot be defined because of the orphan rule (E0117) + +// invariant: OsStr must be guaranteed to be utf8 data +unsafe fn assume_utf8(string: &OsStr) -> &str { + &*(string as *const OsStr as *const str) +} diff --git a/third_party/rust/camino/src/proptest_impls.rs b/third_party/rust/camino/src/proptest_impls.rs new file mode 100644 index 0000000000..81776f226f --- /dev/null +++ b/third_party/rust/camino/src/proptest_impls.rs @@ -0,0 +1,60 @@ +// Copyright (c) The camino Contributors +// SPDX-License-Identifier: MIT OR Apache-2.0 + +//! [proptest::Arbitrary](Arbitrary) implementation for `Utf8PathBuf` and `Box<Utf8Path>`. Note +//! that implementions for `Rc<Utf8Path>` and `Arc<Utf8Path>` are not currently possible due to +//! orphan rules - this crate doesn't define `Rc`/`Arc` nor `Arbitrary`, so it can't define those +//! implementations. + +// NOTE: #[cfg(feature = "proptest1")] is specified here to work with `doc_cfg`. + +use crate::{Utf8Path, Utf8PathBuf}; +use proptest::{arbitrary::StrategyFor, prelude::*, strategy::MapInto}; + +/// The [`Arbitrary`] impl for `Utf8PathBuf` returns a path with between 0 and 8 components, +/// joined by the [`MAIN_SEPARATOR`](std::path::MAIN_SEPARATOR) for the platform. (Each component is +/// randomly generated, and may itself contain one or more separators.) +/// +/// On Unix, this generates an absolute path half of the time and a relative path the other half. +/// +/// On Windows, this implementation doesn't currently generate +/// [`Utf8PrefixComponent`](crate::Utf8PrefixComponent) instances, though in the future it might. +#[cfg(feature = "proptest1")] +impl Arbitrary for Utf8PathBuf { + type Parameters = <String as Arbitrary>::Parameters; + type Strategy = BoxedStrategy<Self>; + + fn arbitrary_with(args: Self::Parameters) -> Self::Strategy { + ( + any::<bool>(), + prop::collection::vec(any_with::<String>(args), 0..8), + ) + .prop_map(|(is_relative, components)| { + let initial_component = + is_relative.then(|| format!("{}", std::path::MAIN_SEPARATOR)); + initial_component + .into_iter() + .chain(components.into_iter()) + .collect() + }) + .boxed() + } +} + +/// The [`Arbitrary`] impl for `Box<Utf8Path>` returns a path with between 0 and 8 components, +/// joined by the [`MAIN_SEPARATOR`](std::path::MAIN_SEPARATOR) for the platform. (Each component is +/// randomly generated, and may itself contain one or more separators.) +/// +/// On Unix, this generates an absolute path half of the time and a relative path the other half. +/// +/// On Windows, this implementation doesn't currently generate +/// [`Utf8PrefixComponent`](crate::Utf8PrefixComponent) instances, though in the future it might. +#[cfg(feature = "proptest1")] +impl Arbitrary for Box<Utf8Path> { + type Parameters = <Utf8PathBuf as Arbitrary>::Parameters; + type Strategy = MapInto<StrategyFor<Utf8PathBuf>, Self>; + + fn arbitrary_with(args: Self::Parameters) -> Self::Strategy { + any_with::<Utf8PathBuf>(args).prop_map_into() + } +} diff --git a/third_party/rust/camino/src/serde_impls.rs b/third_party/rust/camino/src/serde_impls.rs new file mode 100644 index 0000000000..d4c4ecab99 --- /dev/null +++ b/third_party/rust/camino/src/serde_impls.rs @@ -0,0 +1,57 @@ +// Copyright (c) The camino Contributors +// SPDX-License-Identifier: MIT OR Apache-2.0 + +//! Serde implementations for `Utf8Path`. +//! +//! The Serde implementations for `Utf8PathBuf` are derived, but `Utf8Path` is an unsized type which +//! the derive impls can't handle. Implement these by hand. + +use crate::Utf8Path; +use serde::{de, Deserialize, Deserializer, Serialize, Serializer}; +use std::fmt; + +struct Utf8PathVisitor; + +impl<'a> de::Visitor<'a> for Utf8PathVisitor { + type Value = &'a Utf8Path; + + fn expecting(&self, formatter: &mut fmt::Formatter) -> fmt::Result { + formatter.write_str("a borrowed path") + } + + fn visit_borrowed_str<E>(self, v: &'a str) -> Result<Self::Value, E> + where + E: de::Error, + { + Ok(v.as_ref()) + } + + fn visit_borrowed_bytes<E>(self, v: &'a [u8]) -> Result<Self::Value, E> + where + E: de::Error, + { + std::str::from_utf8(v) + .map(AsRef::as_ref) + .map_err(|_| de::Error::invalid_value(de::Unexpected::Bytes(v), &self)) + } +} + +#[cfg(feature = "serde1")] +impl<'de: 'a, 'a> Deserialize<'de> for &'a Utf8Path { + fn deserialize<D>(deserializer: D) -> Result<Self, D::Error> + where + D: Deserializer<'de>, + { + deserializer.deserialize_str(Utf8PathVisitor) + } +} + +#[cfg(feature = "serde1")] +impl Serialize for Utf8Path { + fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error> + where + S: Serializer, + { + self.as_str().serialize(serializer) + } +} diff --git a/third_party/rust/camino/src/tests.rs b/third_party/rust/camino/src/tests.rs new file mode 100644 index 0000000000..305b760910 --- /dev/null +++ b/third_party/rust/camino/src/tests.rs @@ -0,0 +1,46 @@ +// Copyright (c) The camino Contributors +// SPDX-License-Identifier: MIT OR Apache-2.0 + +// Test that all required impls exist. + +use crate::{Utf8Path, Utf8PathBuf}; +use std::{ + borrow::Cow, + path::{Path, PathBuf}, + rc::Rc, + sync::Arc, +}; + +macro_rules! all_into { + ($t:ty, $x:ident) => { + test_into::<$t, Utf8PathBuf>($x.clone()); + test_into::<$t, Box<Utf8Path>>($x.clone()); + test_into::<$t, Arc<Utf8Path>>($x.clone()); + test_into::<$t, Rc<Utf8Path>>($x.clone()); + test_into::<$t, Cow<'_, Utf8Path>>($x.clone()); + test_into::<$t, PathBuf>($x.clone()); + test_into::<$t, Box<Path>>($x.clone()); + test_into::<$t, Arc<Path>>($x.clone()); + test_into::<$t, Rc<Path>>($x.clone()); + test_into::<$t, Cow<'_, Path>>($x.clone()); + }; +} + +#[test] +fn test_borrowed_into() { + let utf8_path = Utf8Path::new("test/path"); + all_into!(&Utf8Path, utf8_path); +} + +#[test] +fn test_owned_into() { + let utf8_path_buf = Utf8PathBuf::from("test/path"); + all_into!(Utf8PathBuf, utf8_path_buf); +} + +fn test_into<T, U>(orig: T) +where + T: Into<U>, +{ + let _ = orig.into(); +} diff --git a/third_party/rust/camino/tests/integration_tests.rs b/third_party/rust/camino/tests/integration_tests.rs new file mode 100644 index 0000000000..190ba82bab --- /dev/null +++ b/third_party/rust/camino/tests/integration_tests.rs @@ -0,0 +1,115 @@ +// Copyright (c) The camino Contributors +// SPDX-License-Identifier: MIT OR Apache-2.0 + +use camino::{Utf8Path, Utf8PathBuf}; +use std::{ + collections::hash_map::DefaultHasher, + hash::{Hash, Hasher}, + path::Path, +}; + +static PATH_CORPUS: &[&str] = &[ + "", + "foo", + "foo/bar", + "foo//bar", + "foo/bar/baz", + "foo/bar/./baz", + "foo/bar/../baz", + "../foo/bar/./../baz", + "/foo", + "/foo/bar", + "/", + "///", + // --- + // Windows-only paths + // --- + #[cfg(windows)] + "foo\\bar", + #[cfg(windows)] + "\\foo\\bar", + #[cfg(windows)] + "C:\\foo", + #[cfg(windows)] + "C:foo\\bar", + #[cfg(windows)] + "C:\\foo\\..\\.\\bar", + #[cfg(windows)] + "\\\\server\\foo\\bar", + #[cfg(windows)] + "\\\\.\\C:\\foo\\bar.txt", +]; + +#[test] +fn test_borrow_eq_ord() { + // Utf8PathBuf implements Borrow<Utf8Path> so equality and ordering comparisons should + // match. + for (idx, &path1) in PATH_CORPUS.iter().enumerate() { + for &path2 in &PATH_CORPUS[idx..] { + let borrowed1 = Utf8Path::new(path1); + let borrowed2 = Utf8Path::new(path2); + let owned1 = Utf8PathBuf::from(path1); + let owned2 = Utf8PathBuf::from(path2); + + assert_eq!( + borrowed1 == borrowed2, + owned1 == owned2, + "Eq impls match: {} == {}", + borrowed1, + borrowed2 + ); + assert_eq!( + borrowed1.cmp(borrowed2), + owned1.cmp(&owned2), + "Ord impls match: {} and {}", + borrowed1, + borrowed2 + ); + + // Also check against std paths. + let std1 = Path::new(path1); + let std2 = Path::new(path2); + assert_eq!( + borrowed1, std1, + "Eq between Path and Utf8Path: {}", + borrowed1 + ); + assert_eq!( + borrowed1 == borrowed2, + std1 == std2, + "Eq impl matches Path: {} == {}", + borrowed1, + borrowed2 + ); + assert_eq!( + borrowed1.cmp(borrowed2), + std1.cmp(std2), + "Ord impl matches Path: {} and {}", + borrowed1, + borrowed2 + ); + } + } +} + +#[test] +fn test_borrow_hash() { + // Utf8PathBuf implements Borrow<Utf8Path> so hash comparisons should match. + fn hash_output(x: impl Hash) -> u64 { + let mut hasher = DefaultHasher::new(); + x.hash(&mut hasher); + hasher.finish() + } + + for &path in PATH_CORPUS { + let borrowed = Utf8Path::new(path); + let owned = Utf8PathBuf::from(path); + + assert_eq!( + hash_output(owned), + hash_output(borrowed), + "consistent Hash: {}", + borrowed + ); + } +} |