clap_lex-0.6.0/.cargo_vcs_info.json0000644000000001460000000000100126270ustar { "git": { "sha1": "38b5a2f956f889baa0a8b2ec975566b0ae27fcb1" }, "path_in_vcs": "clap_lex" }clap_lex-0.6.0/Cargo.toml0000644000000037540000000000100106350ustar # 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 = "2021" rust-version = "1.70.0" name = "clap_lex" version = "0.6.0" include = [ "build.rs", "src/**/*", "Cargo.toml", "LICENSE*", "README.md", "benches/**/*", "examples/**/*", ] description = "Minimal, flexible command line parser" readme = "README.md" keywords = [ "argument", "cli", "arg", "parser", "parse", ] categories = ["command-line-interface"] license = "MIT OR Apache-2.0" repository = "https://github.com/clap-rs/clap/tree/master/clap_lex" [[package.metadata.release.pre-release-replacements]] file = "CHANGELOG.md" min = 1 replace = "{{version}}" search = "Unreleased" [[package.metadata.release.pre-release-replacements]] exactly = 1 file = "CHANGELOG.md" replace = "...{{tag_name}}" search = '\.\.\.HEAD' [[package.metadata.release.pre-release-replacements]] file = "CHANGELOG.md" min = 1 replace = "{{date}}" search = "ReleaseDate" [[package.metadata.release.pre-release-replacements]] exactly = 1 file = "CHANGELOG.md" replace = """ ## [Unreleased] - ReleaseDate """ search = "" [[package.metadata.release.pre-release-replacements]] exactly = 1 file = "CHANGELOG.md" replace = """ [Unreleased]: https://github.com/clap-rs/clap/compare/{{tag_name}}...HEAD""" search = "" [[package.metadata.release.pre-release-replacements]] exactly = 4 file = "README.md" prerelease = true replace = "github.com/clap-rs/clap/blob/{{tag_name}}/" search = "github.com/clap-rs/clap/blob/[^/]+/" [lib] bench = false clap_lex-0.6.0/Cargo.toml.orig000064400000000000000000000021771046102023000143140ustar 00000000000000[package] name = "clap_lex" version = "0.6.0" description = "Minimal, flexible command line parser" repository = "https://github.com/clap-rs/clap/tree/master/clap_lex" categories = ["command-line-interface"] keywords = [ "argument", "cli", "arg", "parser", "parse" ] license.workspace = true edition.workspace = true rust-version.workspace = true include.workspace = true [package.metadata.release] pre-release-replacements = [ {file="CHANGELOG.md", search="Unreleased", replace="{{version}}", min=1}, {file="CHANGELOG.md", search="\\.\\.\\.HEAD", replace="...{{tag_name}}", exactly=1}, {file="CHANGELOG.md", search="ReleaseDate", replace="{{date}}", min=1}, {file="CHANGELOG.md", search="", replace="\n## [Unreleased] - ReleaseDate\n", exactly=1}, {file="CHANGELOG.md", search="", replace="\n[Unreleased]: https://github.com/clap-rs/clap/compare/{{tag_name}}...HEAD", exactly=1}, {file="README.md", search="github.com/clap-rs/clap/blob/[^/]+/", replace="github.com/clap-rs/clap/blob/{{tag_name}}/", exactly=4, prerelease = true}, ] [lib] bench = false clap_lex-0.6.0/LICENSE-APACHE000064400000000000000000000261351046102023000133510ustar 00000000000000 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. clap_lex-0.6.0/LICENSE-MIT000064400000000000000000000021241046102023000130510ustar 00000000000000The MIT License (MIT) Copyright (c) 2015-2022 Kevin B. Knapp and Clap Contributors 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. clap_lex-0.6.0/README.md000064400000000000000000000017541046102023000127040ustar 00000000000000 # clap_lex > **Minimal, flexible command line parser** [![Crates.io](https://img.shields.io/crates/v/clap_lex?style=flat-square)](https://crates.io/crates/clap_lex) [![Crates.io](https://img.shields.io/crates/d/clap_lex?style=flat-square)](https://crates.io/crates/clap_lex) [![License](https://img.shields.io/badge/license-Apache%202.0-blue?style=flat-square)](https://github.com/clap-rs/clap/blob/clap_lex-v0.6.0/LICENSE-APACHE) [![License](https://img.shields.io/badge/license-MIT-blue?style=flat-square)](https://github.com/clap-rs/clap/blob/clap_lex-v0.6.0/LICENSE-MIT) Dual-licensed under [Apache 2.0](LICENSE-APACHE) or [MIT](LICENSE-MIT). 1. [About](#about) 2. [API Reference](https://docs.rs/clap_lex) 3. [Questions & Discussions](https://github.com/clap-rs/clap/discussions) 4. [CONTRIBUTING](https://github.com/clap-rs/clap/blob/clap_lex-v0.6.0/clap_lex/CONTRIBUTING.md) 5. [Sponsors](https://github.com/clap-rs/clap/blob/clap_lex-v0.6.0/README.md#sponsors) ## About clap_lex-0.6.0/src/ext.rs000064400000000000000000000250051046102023000133550ustar 00000000000000use std::ffi::OsStr; pub trait OsStrExt: private::Sealed { /// Converts to a string slice. fn try_str(&self) -> Result<&str, std::str::Utf8Error>; /// Returns `true` if the given pattern matches a sub-slice of /// this string slice. /// /// Returns `false` if it does not. /// /// # Examples /// /// ```rust /// use clap_lex::OsStrExt as _; /// let bananas = std::ffi::OsStr::new("bananas"); /// /// assert!(bananas.contains("nana")); /// assert!(!bananas.contains("apples")); /// ``` fn contains(&self, needle: &str) -> bool; /// Returns the byte index of the first character of this string slice that /// matches the pattern. /// /// Returns [`None`] if the pattern doesn't match. /// /// # Examples /// /// ```rust /// use clap_lex::OsStrExt as _; /// let s = std::ffi::OsStr::new("Löwe 老虎 Léopard Gepardi"); /// /// assert_eq!(s.find("L"), Some(0)); /// assert_eq!(s.find("é"), Some(14)); /// assert_eq!(s.find("par"), Some(17)); /// ``` /// /// Not finding the pattern: /// /// ```rust /// use clap_lex::OsStrExt as _; /// let s = std::ffi::OsStr::new("Löwe 老虎 Léopard"); /// /// assert_eq!(s.find("1"), None); /// ``` fn find(&self, needle: &str) -> Option; /// Returns a string slice with the prefix removed. /// /// If the string starts with the pattern `prefix`, returns substring after the prefix, wrapped /// in `Some`. /// /// If the string does not start with `prefix`, returns `None`. /// /// # Examples /// /// ``` /// use std::ffi::OsStr; /// use clap_lex::OsStrExt as _; /// assert_eq!(OsStr::new("foo:bar").strip_prefix("foo:"), Some(OsStr::new("bar"))); /// assert_eq!(OsStr::new("foo:bar").strip_prefix("bar"), None); /// assert_eq!(OsStr::new("foofoo").strip_prefix("foo"), Some(OsStr::new("foo"))); /// ``` fn strip_prefix(&self, prefix: &str) -> Option<&OsStr>; /// Returns `true` if the given pattern matches a prefix of this /// string slice. /// /// Returns `false` if it does not. /// /// # Examples /// /// ``` /// use clap_lex::OsStrExt as _; /// let bananas = std::ffi::OsStr::new("bananas"); /// /// assert!(bananas.starts_with("bana")); /// assert!(!bananas.starts_with("nana")); /// ``` fn starts_with(&self, prefix: &str) -> bool; /// An iterator over substrings of this string slice, separated by /// characters matched by a pattern. /// /// # Examples /// /// Simple patterns: /// /// ``` /// use std::ffi::OsStr; /// use clap_lex::OsStrExt as _; /// let v: Vec<_> = OsStr::new("Mary had a little lamb").split(" ").collect(); /// assert_eq!(v, [OsStr::new("Mary"), OsStr::new("had"), OsStr::new("a"), OsStr::new("little"), OsStr::new("lamb")]); /// /// let v: Vec<_> = OsStr::new("").split("X").collect(); /// assert_eq!(v, [OsStr::new("")]); /// /// let v: Vec<_> = OsStr::new("lionXXtigerXleopard").split("X").collect(); /// assert_eq!(v, [OsStr::new("lion"), OsStr::new(""), OsStr::new("tiger"), OsStr::new("leopard")]); /// /// let v: Vec<_> = OsStr::new("lion::tiger::leopard").split("::").collect(); /// assert_eq!(v, [OsStr::new("lion"), OsStr::new("tiger"), OsStr::new("leopard")]); /// ``` /// /// If a string contains multiple contiguous separators, you will end up /// with empty strings in the output: /// /// ``` /// use std::ffi::OsStr; /// use clap_lex::OsStrExt as _; /// let x = OsStr::new("||||a||b|c"); /// let d: Vec<_> = x.split("|").collect(); /// /// assert_eq!(d, &[OsStr::new(""), OsStr::new(""), OsStr::new(""), OsStr::new(""), OsStr::new("a"), OsStr::new(""), OsStr::new("b"), OsStr::new("c")]); /// ``` /// /// Contiguous separators are separated by the empty string. /// /// ``` /// use std::ffi::OsStr; /// use clap_lex::OsStrExt as _; /// let x = OsStr::new("(///)"); /// let d: Vec<_> = x.split("/").collect(); /// /// assert_eq!(d, &[OsStr::new("("), OsStr::new(""), OsStr::new(""), OsStr::new(")")]); /// ``` /// /// Separators at the start or end of a string are neighbored /// by empty strings. /// /// ``` /// use std::ffi::OsStr; /// use clap_lex::OsStrExt as _; /// let d: Vec<_> = OsStr::new("010").split("0").collect(); /// assert_eq!(d, &[OsStr::new(""), OsStr::new("1"), OsStr::new("")]); /// ``` /// /// When the empty string is used as a separator, it panics /// /// ```should_panic /// use std::ffi::OsStr; /// use clap_lex::OsStrExt as _; /// let f: Vec<_> = OsStr::new("rust").split("").collect(); /// assert_eq!(f, &[OsStr::new(""), OsStr::new("r"), OsStr::new("u"), OsStr::new("s"), OsStr::new("t"), OsStr::new("")]); /// ``` /// /// Contiguous separators can lead to possibly surprising behavior /// when whitespace is used as the separator. This code is correct: /// /// ``` /// use std::ffi::OsStr; /// use clap_lex::OsStrExt as _; /// let x = OsStr::new(" a b c"); /// let d: Vec<_> = x.split(" ").collect(); /// /// assert_eq!(d, &[OsStr::new(""), OsStr::new(""), OsStr::new(""), OsStr::new(""), OsStr::new("a"), OsStr::new(""), OsStr::new("b"), OsStr::new("c")]); /// ``` /// /// It does _not_ give you: /// /// ```,ignore /// assert_eq!(d, &[OsStr::new("a"), OsStr::new("b"), OsStr::new("c")]); /// ``` /// /// Use [`split_whitespace`] for this behavior. /// /// [`split_whitespace`]: str::split_whitespace fn split<'s, 'n>(&'s self, needle: &'n str) -> Split<'s, 'n>; /// Splits the string on the first occurrence of the specified delimiter and /// returns prefix before delimiter and suffix after delimiter. /// /// # Examples /// /// ``` /// use std::ffi::OsStr; /// use clap_lex::OsStrExt as _; /// assert_eq!(OsStr::new("cfg").split_once("="), None); /// assert_eq!(OsStr::new("cfg=").split_once("="), Some((OsStr::new("cfg"), OsStr::new("")))); /// assert_eq!(OsStr::new("cfg=foo").split_once("="), Some((OsStr::new("cfg"), OsStr::new("foo")))); /// assert_eq!(OsStr::new("cfg=foo=bar").split_once("="), Some((OsStr::new("cfg"), OsStr::new("foo=bar")))); /// ``` fn split_once(&self, needle: &'_ str) -> Option<(&OsStr, &OsStr)>; } impl OsStrExt for OsStr { fn try_str(&self) -> Result<&str, std::str::Utf8Error> { let bytes = to_bytes(self); std::str::from_utf8(bytes) } fn contains(&self, needle: &str) -> bool { self.find(needle).is_some() } fn find(&self, needle: &str) -> Option { let bytes = to_bytes(self); (0..=self.len().checked_sub(needle.len())?) .find(|&x| bytes[x..].starts_with(needle.as_bytes())) } fn strip_prefix(&self, prefix: &str) -> Option<&OsStr> { let bytes = to_bytes(self); bytes.strip_prefix(prefix.as_bytes()).map(|s| { // SAFETY: // - This came from `to_bytes` // - Since `prefix` is `&str`, any split will be along UTF-8 boundarie unsafe { to_os_str_unchecked(s) } }) } fn starts_with(&self, prefix: &str) -> bool { let bytes = to_bytes(self); bytes.starts_with(prefix.as_bytes()) } fn split<'s, 'n>(&'s self, needle: &'n str) -> Split<'s, 'n> { assert_ne!(needle, ""); Split { haystack: Some(self), needle, } } fn split_once(&self, needle: &'_ str) -> Option<(&OsStr, &OsStr)> { let start = self.find(needle)?; let end = start + needle.len(); let haystack = to_bytes(self); let first = &haystack[0..start]; let second = &haystack[end..]; // SAFETY: // - This came from `to_bytes` // - Since `needle` is `&str`, any split will be along UTF-8 boundarie unsafe { Some((to_os_str_unchecked(first), to_os_str_unchecked(second))) } } } mod private { pub trait Sealed {} impl Sealed for std::ffi::OsStr {} } /// Allow access to raw bytes /// /// As the non-UTF8 encoding is not defined, the bytes only make sense when compared with /// 7-bit ASCII or `&str` /// /// # Compatibility /// /// There is no guarantee how non-UTF8 bytes will be encoded, even within versions of this crate /// (since its dependent on rustc) fn to_bytes(s: &OsStr) -> &[u8] { // SAFETY: // - Lifetimes are the same // - Types are compatible (`OsStr` is effectively a transparent wrapper for `[u8]`) // - The primary contract is that the encoding for invalid surrogate code points is not // guaranteed which isn't a problem here // // There is a proposal to support this natively (https://github.com/rust-lang/rust/pull/95290) // but its in limbo unsafe { std::mem::transmute(s) } } /// Restore raw bytes as `OsStr` /// /// # Safety /// /// - `&[u8]` must either by a `&str` or originated with `to_bytes` within the same binary /// - Any splits of the original `&[u8]` must be done along UTF-8 boundaries unsafe fn to_os_str_unchecked(s: &[u8]) -> &OsStr { // SAFETY: // - Lifetimes are the same // - Types are compatible (`OsStr` is effectively a transparent wrapper for `[u8]`) // - The primary contract is that the encoding for invalid surrogate code points is not // guaranteed which isn't a problem here // // There is a proposal to support this natively (https://github.com/rust-lang/rust/pull/95290) // but its in limbo std::mem::transmute(s) } pub struct Split<'s, 'n> { haystack: Option<&'s OsStr>, needle: &'n str, } impl<'s, 'n> Iterator for Split<'s, 'n> { type Item = &'s OsStr; fn next(&mut self) -> Option { let haystack = self.haystack?; match haystack.split_once(self.needle) { Some((first, second)) => { if !haystack.is_empty() { debug_assert_ne!(haystack, second); } self.haystack = Some(second); Some(first) } None => { self.haystack = None; Some(haystack) } } } } /// Split an `OsStr` /// /// # Safety /// /// `index` must be at a valid UTF-8 boundary pub(crate) unsafe fn split_at(os: &OsStr, index: usize) -> (&OsStr, &OsStr) { let bytes = to_bytes(os); let (first, second) = bytes.split_at(index); (to_os_str_unchecked(first), to_os_str_unchecked(second)) } clap_lex-0.6.0/src/lib.rs000064400000000000000000000357371046102023000133400ustar 00000000000000//! Minimal, flexible command-line parser //! //! As opposed to a declarative parser, this processes arguments as a stream of tokens. As lexing //! a command-line is not context-free, we rely on the caller to decide how to interpret the //! arguments. //! //! # Examples //! //! ```rust //! use std::path::PathBuf; //! use std::ffi::OsStr; //! //! type BoxedError = Box; //! //! #[derive(Debug)] //! struct Args { //! paths: Vec, //! color: Color, //! verbosity: usize, //! } //! //! #[derive(Debug)] //! enum Color { //! Always, //! Auto, //! Never, //! } //! //! impl Color { //! fn parse(s: Option<&OsStr>) -> Result { //! let s = s.map(|s| s.to_str().ok_or(s)); //! match s { //! Some(Ok("always")) | Some(Ok("")) | None => { //! Ok(Color::Always) //! } //! Some(Ok("auto")) => { //! Ok(Color::Auto) //! } //! Some(Ok("never")) => { //! Ok(Color::Never) //! } //! Some(invalid) => { //! Err(format!("Invalid value for `--color`, {invalid:?}").into()) //! } //! } //! } //! } //! //! fn parse_args( //! raw: impl IntoIterator> //! ) -> Result { //! let mut args = Args { //! paths: Vec::new(), //! color: Color::Auto, //! verbosity: 0, //! }; //! //! let raw = clap_lex::RawArgs::new(raw); //! let mut cursor = raw.cursor(); //! raw.next(&mut cursor); // Skip the bin //! while let Some(arg) = raw.next(&mut cursor) { //! if arg.is_escape() { //! args.paths.extend(raw.remaining(&mut cursor).map(PathBuf::from)); //! } else if arg.is_stdio() { //! args.paths.push(PathBuf::from("-")); //! } else if let Some((long, value)) = arg.to_long() { //! match long { //! Ok("verbose") => { //! if let Some(value) = value { //! return Err(format!("`--verbose` does not take a value, got `{value:?}`").into()); //! } //! args.verbosity += 1; //! } //! Ok("color") => { //! args.color = Color::parse(value)?; //! } //! _ => { //! return Err( //! format!("Unexpected flag: --{}", arg.display()).into() //! ); //! } //! } //! } else if let Some(mut shorts) = arg.to_short() { //! while let Some(short) = shorts.next_flag() { //! match short { //! Ok('v') => { //! args.verbosity += 1; //! } //! Ok('c') => { //! let value = shorts.next_value_os(); //! args.color = Color::parse(value)?; //! } //! Ok(c) => { //! return Err(format!("Unexpected flag: -{c}").into()); //! } //! Err(e) => { //! return Err(format!("Unexpected flag: -{}", e.to_string_lossy()).into()); //! } //! } //! } //! } else { //! args.paths.push(PathBuf::from(arg.to_value_os().to_owned())); //! } //! } //! //! Ok(args) //! } //! //! let args = parse_args(["bin", "--hello", "world"]); //! println!("{args:?}"); //! ``` mod ext; use std::ffi::OsStr; use std::ffi::OsString; pub use std::io::SeekFrom; pub use ext::OsStrExt; /// Command-line arguments #[derive(Default, Clone, Debug, PartialEq, Eq)] pub struct RawArgs { items: Vec, } impl RawArgs { //// Create an argument list to parse /// /// **NOTE:** The argument returned will be the current binary. /// /// # Example /// /// ```rust,no_run /// # use std::path::PathBuf; /// let raw = clap_lex::RawArgs::from_args(); /// let mut cursor = raw.cursor(); /// let _bin = raw.next_os(&mut cursor); /// /// let mut paths = raw.remaining(&mut cursor).map(PathBuf::from).collect::>(); /// println!("{paths:?}"); /// ``` pub fn from_args() -> Self { Self::new(std::env::args_os()) } //// Create an argument list to parse /// /// # Example /// /// ```rust,no_run /// # use std::path::PathBuf; /// let raw = clap_lex::RawArgs::new(["bin", "foo.txt"]); /// let mut cursor = raw.cursor(); /// let _bin = raw.next_os(&mut cursor); /// /// let mut paths = raw.remaining(&mut cursor).map(PathBuf::from).collect::>(); /// println!("{paths:?}"); /// ``` pub fn new(iter: impl IntoIterator>) -> Self { let iter = iter.into_iter(); Self::from(iter) } /// Create a cursor for walking the arguments /// /// # Example /// /// ```rust,no_run /// # use std::path::PathBuf; /// let raw = clap_lex::RawArgs::new(["bin", "foo.txt"]); /// let mut cursor = raw.cursor(); /// let _bin = raw.next_os(&mut cursor); /// /// let mut paths = raw.remaining(&mut cursor).map(PathBuf::from).collect::>(); /// println!("{paths:?}"); /// ``` pub fn cursor(&self) -> ArgCursor { ArgCursor::new() } /// Advance the cursor, returning the next [`ParsedArg`] pub fn next(&self, cursor: &mut ArgCursor) -> Option> { self.next_os(cursor).map(ParsedArg::new) } /// Advance the cursor, returning a raw argument value. pub fn next_os(&self, cursor: &mut ArgCursor) -> Option<&OsStr> { let next = self.items.get(cursor.cursor).map(|s| s.as_os_str()); cursor.cursor = cursor.cursor.saturating_add(1); next } /// Return the next [`ParsedArg`] pub fn peek(&self, cursor: &ArgCursor) -> Option> { self.peek_os(cursor).map(ParsedArg::new) } /// Return a raw argument value. pub fn peek_os(&self, cursor: &ArgCursor) -> Option<&OsStr> { self.items.get(cursor.cursor).map(|s| s.as_os_str()) } /// Return all remaining raw arguments, advancing the cursor to the end /// /// # Example /// /// ```rust,no_run /// # use std::path::PathBuf; /// let raw = clap_lex::RawArgs::new(["bin", "foo.txt"]); /// let mut cursor = raw.cursor(); /// let _bin = raw.next_os(&mut cursor); /// /// let mut paths = raw.remaining(&mut cursor).map(PathBuf::from).collect::>(); /// println!("{paths:?}"); /// ``` pub fn remaining(&self, cursor: &mut ArgCursor) -> impl Iterator { let remaining = self.items[cursor.cursor..].iter().map(|s| s.as_os_str()); cursor.cursor = self.items.len(); remaining } /// Adjust the cursor's position pub fn seek(&self, cursor: &mut ArgCursor, pos: SeekFrom) { let pos = match pos { SeekFrom::Start(pos) => pos, SeekFrom::End(pos) => (self.items.len() as i64).saturating_add(pos).max(0) as u64, SeekFrom::Current(pos) => (cursor.cursor as i64).saturating_add(pos).max(0) as u64, }; let pos = (pos as usize).min(self.items.len()); cursor.cursor = pos; } /// Inject arguments before the [`RawArgs::next`] pub fn insert( &mut self, cursor: &ArgCursor, insert_items: impl IntoIterator>, ) { self.items.splice( cursor.cursor..cursor.cursor, insert_items.into_iter().map(Into::into), ); } /// Any remaining args? pub fn is_end(&self, cursor: &ArgCursor) -> bool { self.peek_os(cursor).is_none() } } impl From for RawArgs where I: Iterator, T: Into, { fn from(val: I) -> Self { Self { items: val.map(|x| x.into()).collect(), } } } /// Position within [`RawArgs`] #[derive(Clone, Debug, PartialEq, Eq, PartialOrd, Ord)] pub struct ArgCursor { cursor: usize, } impl ArgCursor { fn new() -> Self { Self { cursor: 0 } } } /// Command-line Argument #[derive(Clone, Debug, PartialEq, Eq, PartialOrd, Ord, Hash)] pub struct ParsedArg<'s> { inner: &'s OsStr, } impl<'s> ParsedArg<'s> { fn new(inner: &'s OsStr) -> Self { Self { inner } } /// Argument is length of 0 pub fn is_empty(&self) -> bool { self.inner.is_empty() } /// Does the argument look like a stdio argument (`-`) pub fn is_stdio(&self) -> bool { self.inner == "-" } /// Does the argument look like an argument escape (`--`) pub fn is_escape(&self) -> bool { self.inner == "--" } /// Does the argument look like a negative number? /// /// This won't parse the number in full but attempts to see if this looks /// like something along the lines of `-3`, `-0.3`, or `-33.03` pub fn is_negative_number(&self) -> bool { self.to_value() .ok() .and_then(|s| Some(is_number(s.strip_prefix('-')?))) .unwrap_or_default() } /// Treat as a long-flag pub fn to_long(&self) -> Option<(Result<&str, &OsStr>, Option<&OsStr>)> { let raw = self.inner; let remainder = raw.strip_prefix("--")?; if remainder.is_empty() { debug_assert!(self.is_escape()); return None; } let (flag, value) = if let Some((p0, p1)) = remainder.split_once("=") { (p0, Some(p1)) } else { (remainder, None) }; let flag = flag.to_str().ok_or(flag); Some((flag, value)) } /// Can treat as a long-flag pub fn is_long(&self) -> bool { self.inner.starts_with("--") && !self.is_escape() } /// Treat as a short-flag pub fn to_short(&self) -> Option> { if let Some(remainder_os) = self.inner.strip_prefix("-") { if remainder_os.starts_with("-") { None } else if remainder_os.is_empty() { debug_assert!(self.is_stdio()); None } else { Some(ShortFlags::new(remainder_os)) } } else { None } } /// Can treat as a short-flag pub fn is_short(&self) -> bool { self.inner.starts_with("-") && !self.is_stdio() && !self.inner.starts_with("--") } /// Treat as a value /// /// **NOTE:** May return a flag or an escape. pub fn to_value_os(&self) -> &OsStr { self.inner } /// Treat as a value /// /// **NOTE:** May return a flag or an escape. pub fn to_value(&self) -> Result<&str, &OsStr> { self.inner.to_str().ok_or(self.inner) } /// Safely print an argument that may contain non-UTF8 content /// /// This may perform lossy conversion, depending on the platform. If you would like an implementation which escapes the path please use Debug instead. pub fn display(&self) -> impl std::fmt::Display + '_ { self.inner.to_string_lossy() } } /// Walk through short flags within a [`ParsedArg`] #[derive(Clone, Debug)] pub struct ShortFlags<'s> { inner: &'s OsStr, utf8_prefix: std::str::CharIndices<'s>, invalid_suffix: Option<&'s OsStr>, } impl<'s> ShortFlags<'s> { fn new(inner: &'s OsStr) -> Self { let (utf8_prefix, invalid_suffix) = split_nonutf8_once(inner); let utf8_prefix = utf8_prefix.char_indices(); Self { inner, utf8_prefix, invalid_suffix, } } /// Move the iterator forward by `n` short flags pub fn advance_by(&mut self, n: usize) -> Result<(), usize> { for i in 0..n { self.next().ok_or(i)?.map_err(|_| i)?; } Ok(()) } /// No short flags left pub fn is_empty(&self) -> bool { self.invalid_suffix.is_none() && self.utf8_prefix.as_str().is_empty() } /// Does the short flag look like a number /// /// Ideally call this before doing any iterator pub fn is_negative_number(&self) -> bool { self.invalid_suffix.is_none() && is_number(self.utf8_prefix.as_str()) } /// Advance the iterator, returning the next short flag on success /// /// On error, returns the invalid-UTF8 value pub fn next_flag(&mut self) -> Option> { if let Some((_, flag)) = self.utf8_prefix.next() { return Some(Ok(flag)); } if let Some(suffix) = self.invalid_suffix { self.invalid_suffix = None; return Some(Err(suffix)); } None } /// Advance the iterator, returning everything left as a value pub fn next_value_os(&mut self) -> Option<&'s OsStr> { if let Some((index, _)) = self.utf8_prefix.next() { self.utf8_prefix = "".char_indices(); self.invalid_suffix = None; // SAFETY: `char_indices` ensures `index` is at a valid UTF-8 boundary let remainder = unsafe { ext::split_at(self.inner, index).1 }; return Some(remainder); } if let Some(suffix) = self.invalid_suffix { self.invalid_suffix = None; return Some(suffix); } None } } impl<'s> Iterator for ShortFlags<'s> { type Item = Result; fn next(&mut self) -> Option { self.next_flag() } } fn split_nonutf8_once(b: &OsStr) -> (&str, Option<&OsStr>) { match b.try_str() { Ok(s) => (s, None), Err(err) => { // SAFETY: `char_indices` ensures `index` is at a valid UTF-8 boundary let (valid, after_valid) = unsafe { ext::split_at(b, err.valid_up_to()) }; let valid = valid.try_str().unwrap(); (valid, Some(after_valid)) } } } fn is_number(arg: &str) -> bool { // Return true if this looks like an integer or a float where it's all // digits plus an optional single dot after some digits. // // For floats allow forms such as `1.`, `1.2`, `1.2e10`, etc. let mut seen_dot = false; let mut position_of_e = None; for (i, c) in arg.as_bytes().iter().enumerate() { match c { // Digits are always valid b'0'..=b'9' => {} // Allow a `.`, but only one, only if it comes before an // optional exponent, and only if it's not the first character. b'.' if !seen_dot && position_of_e.is_none() && i > 0 => seen_dot = true, // Allow an exponent `e` but only at most one after the first // character. b'e' if position_of_e.is_none() && i > 0 => position_of_e = Some(i), _ => return false, } } // Disallow `-1e` which isn't a valid float since it doesn't actually have // an exponent. match position_of_e { Some(i) => i != arg.len() - 1, None => true, } }