coreutils/src/libgetopt.rs

/*
 * Copyright (c) 2023–2024 Emma Tebibyte <emma@tebibyte.media>
 * SPDX-License-Identifier: AGPL-3.0-or-later
 *
 * This program is free software: you can redistribute it and/or modify it under
 * the terms of the GNU Affero General Public License as published by the Free
 * Software Foundation, either version 3 of the License, or (at your option) any
 * later version.
 * 
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
 * FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more
 * details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program. If not, see https://www.gnu.org/licenses/.
 */

use std::ffi::{ c_int, c_char, CString, CStr };

/* binding to getopt(3p) */
extern "C" {
	static mut optarg: *mut c_char;
	static mut _opterr: c_int;
	static mut optind: c_int;
	static mut optopt: c_int;

	fn getopt(
		___argc: c_int,
		___argv: *const *mut c_char,
		__shortopts: *const c_char,
	) -> c_int;
}

#[derive(Clone, Debug)]
pub enum OptError {
	MissingArg(String),
	UnknownOpt(String),
}

#[derive(Clone, Debug)]
pub struct Opt {
	arg: Option<String>, /* option argument */
	ind: *mut i32, /* option index */
	opt: Result<String, OptError>, /* option option */
}

impl Opt {
	pub fn arg(&self) -> Option<String> { self.arg.clone() }

	/* sets optarg if default is desired */
	pub fn arg_or(&self, default: impl std::fmt::Display) -> String {
		default.to_string()
	}

	/* makes matching the output of this method more bearable */
	pub fn opt(&self) -> Result<&str, OptError> {
		self.opt.as_ref().map(|o| o.as_str()).map_err(OptError::clone)
	}

	/* From getopt(3p):
	 *
	 * The variable optind is the index of the next element of the argv[]
	 * vector to be processed. It shall be initialized to 1 by the system, and
	 * getopt() shall update it when it finishes with each element of argv[].
	 * If the application sets optind to zero  before calling getopt(), the
	 * behavior is unspecified. When an element of argv[] contains multiple
	 * option characters, it is unspecified how getopt() determines which
	 * options have already been processed. */
	pub fn ind(&self) -> usize { unsafe { *self.ind as usize } }

	/* this is patently terrible and is only happening because I’m stubborn */
	pub fn set_ind(&self, ind: i32) { unsafe { *self.ind = ind; } }
}

/* function signature */
pub trait GetOpt {
	fn getopt(&self, optstring: &str) -> Option<Opt>;
}

impl GetOpt for Vec<String> {
    fn getopt(&self, optstring: &str) -> Option<Opt> {
        let c_strings: Vec<_> = self
			.iter()
			.cloned()
			.map(|x| CString::new(x).unwrap().into_raw())
			.collect();

		/* god knows what this does */
		let boxed = Box::into_raw(c_strings.into_boxed_slice());
		let argv = boxed as *const *mut c_char;

		/* operations are separated out so that everything lives long enough */
        let opts = CString::new(optstring).unwrap().into_raw();
        let len = self.len() as c_int;

        unsafe {
            let ret = match getopt(len, argv, opts) { 
				/* From getopt(3p):
				 *
				 * The getopt() function shall return the next option character
				 * specified on the command line.
				 *
				 * A <colon> (':') shall be returned if getopt() detects a
				 * missing argument and the first character of optstring was a
				 * <colon> (':').
				 *
				 * A <question-mark> ('?') shall be returned if getopt()
				 * encounters an option character not in optstring or detects a
				 * missing argument and the first character of optstring was not
				 * a <colon> (':').
				 *
				 * Otherwise, getopt() shall return -1 when all command line
				 * options are parsed. */
				58 => { /* ASCII ':' */
					Some(Opt {
						arg: None,
						ind: std::ptr::addr_of_mut!(optind),
						/* error containing option */
						opt: Err(OptError::MissingArg(optopt.to_string())),
					})
				},
				63 => { /* ASCII '?' */
					Some(Opt {
						arg: None,
						ind: std::ptr::addr_of_mut!(optind),
						/* error containing option */
						opt: Err(OptError::UnknownOpt(optopt.to_string())),
					})
				},
				/* From getopt(3p):
				 *
				 * If, when getopt() is called:
				 *
				 * argv[optind]  is a null pointer
				 * *argv[optind]  is not the character -
				 * argv[optind]  points to the string "-"
				 *
				 * getopt() shall return -1 without changing optind.  If:
				 *
				 * argv[optind]   points to the string "--"
				 *
				 * getopt() shall return -1 after incrementing optind. */
                -1 => return None,
                opt => {
					let arg: Option<String>;

					if optarg.is_null() { arg = None; }
					else {
						arg = Some(CStr::from_ptr(optarg)
							.to_string_lossy()
							.into_owned());
					}

					Some(Opt {
						arg,
						ind: std::ptr::addr_of_mut!(optind),
						/* I didn’t need to cast this before; I rewrote the
						 * pointer logic and now I do
						 *
						 * I don’t know why this is */
						opt: Ok((opt as u8 as char).to_string()),
					})
				},
            };

			/* delloc argv (something online said I should do this) */
			let _ = Box::from_raw(boxed);
			return ret;
        }
    }
}

/* tests (good) */
#[cfg(test)]
mod tests {
	use GetOpt;

	#[test]
	fn testing() {
		let argv: Vec<String> = ["test", "-b", "-f", "arg", "-o", "arg"]
			.iter()
			.map(|s| s.to_string())
			.collect();

		while let Some(opt) = argv.getopt(":abf:o:") {
			match opt.opt() {
				Ok("a") => assert_eq!(opt.ind(), 1),
				Ok("b") => assert_eq!(opt.ind(), 2),
				Ok("f") | Ok("o") => {
					assert_eq!(opt.arg(), Some("arg".into()));
				},
				_ => assert!(false),
			};
		}

		if let Some(opt) = argv.getopt("abc:") {
			opt.clone().set_ind(1);
			assert_eq!(opt.ind(), 1);
		}
	}
}