stris(1): fix bug only checking the first rune of strings

Makefile

@@ -17,8 +17,6 @@
 DESTDIR ?= dist
 PREFIX ?= /usr/local
 
-MANDIR != [ $(PREFIX) = / ] && printf '/usr/share/man\n' \
-	|| printf '/share/man\n'
 SYSEXITS != printf '\043include <sysexits.h>\n' | cpp -M - | sed 's/ /\n/g' \
 	| sed -n 's/sysexits\.h//p' || printf 'include\n'
 
@@ -30,7 +28,7 @@ RUSTLIBS = --extern getopt=build/o/libgetopt.rlib \
 CFLAGS += -I$(SYSEXITS)
 
 .PHONY: all
-all: dj false fop hru intcmp mm npc rpn scrut sleep str strcmp swab true
+all: dj false fop hru intcmp mm npc rpn scrut strcmp stris swab true
 
 build:
 	# keep build/include until bindgen(1) has stdin support
@@ -44,7 +42,7 @@ clean:
 dist: all
 	mkdir -p $(DESTDIR)/$(PREFIX)/bin $(DESTDIR)/$(PREFIX)/share/man/man1
 	cp build/bin/* $(DESTDIR)/$(PREFIX)/bin
-	cp docs/*.1 $(DESTDIR)/$(PREFIX)/$(MANDIR)/man1
+	cp docs/*.1 $(DESTDIR)/$(PREFIX)/share/man/man1
 
 .PHONY: install
 install: dist
@@ -104,6 +102,7 @@ mm: build/bin/mm
 build/bin/mm: src/mm.c build
 	$(CC) $(CFLAGS) -o $@ src/mm.c
 
+
 .PHONY: npc
 npc: build/bin/npc
 build/bin/npc: src/npc.c build
@@ -119,17 +118,13 @@ scrut: build/bin/scrut
 build/bin/scrut: src/scrut.c build
 	$(CC) $(CFLAGS) -o $@ src/scrut.c
 
-.PHONY: sleep
+.PHONY: stris
-sleep: build/bin/sleep
+stris: build/bin/stris
-build/bin/sleep: src/sleep.rs build rustlibs
+build/bin/stris: src/stris.rs build build/o/libgetopt.rlib \
-	$(RUSTC) $(RUSTFLAGS) \
+		build/o/libsysexits.rlib
+	$(RUSTC) $(RUSTFLAGS) --extern getopt=build/o/libgetopt.rlib \
 		--extern sysexits=build/o/libsysexits.rlib \
-		-o $@ src/sleep.rs
+		-o $@ src/stris.rs
-
-.PHONY: str
-str: build/bin/str
-build/bin/str: src/str.c build
-	$(CC) $(CFLAGS) -o $@ src/str.c
 
 .PHONY: strcmp
 strcmp: build/bin/strcmp
@@ -138,7 +133,8 @@ build/bin/strcmp: src/strcmp.c build
 
 .PHONY: swab
 swab: build/bin/swab
-build/bin/swab: src/swab.rs build build/o/libsysexits.rlib
+build/bin/swab: src/swab.rs build build/o/libgetopt.rlib \
+		build/o/libsysexits.rlib
 	$(RUSTC) $(RUSTFLAGS) --extern getopt=build/o/libgetopt.rlib \
 		--extern sysexits=build/o/libsysexits.rlib \
 		-o $@ src/swab.rs

README

@@ -1,27 +1,27 @@
-For the Bonsai coreutils, a better Unix toolset, please visit
+“Seek not to walk the path of the masters; seek what they sought.”
-<https://git.tebibyte.media/bonsai/coreutils>.
+– Matsuo Basho
 
-      wwwww        /
+The Bonsai core utilities are the result of the careful examination of the
-     wWWWWWw      /_  _____ _       *       "It's not a very good tree, but
+current state of POSIX and Unix utilies. The Unix Philosophy, “do one thing and
-      w|||w      /  \/  \ /  | /\  / /|/     occasionally it bears fruit!"
+do it well” is its core but these tools do not cling to the names of the past.
-     _,|||._   _/\__/|__//  /_/_|_/_//|__
-     bonsix : "BOHN zix" : "Bonsai" but "POSIX"
 
-The excellent Bonsai core utilities are the result of the careful examination
+The era of the original Unix tools has been long and fruitful, but they have
-of the current state of POSIX and Unix utilities, ironing out wrinkles in the
+their flaws. The new, non-POSIX era of this project started with frustration
-implementations that ended up being worn by the POSIX standard. Bonsai's
+with the way certain tools work and how other projects that extend POSIX don’t
-guiding quote is this one from Matsuo Basho:
+make anything better.
 
-"Seek not to walk the path of the masters; seek what they sought."
+This project will not follow in the footsteps of GNU; extensions of POSIX will
+not be found here. GNU extensions are a gateway to the misuse of the shell. The
+Bonsai core utilities will intentionally discourage use of the shell for
+purposes beyond its scope.
 
-Unlike Bonsai, Bonsix intends to walk the path of the masters, implementing a
+See docs/ for more on the specific utilities currently implemented.
-POSIX userland under an AGPLv3 license and taking inspiration from the
-practices used by Bonsai.
 
 Building
 
-Bonsix requires an existing POSIX-compliant environment to compile, including a
+The coreutils require a POSIX-compliant environment to compile, including a C
-C compiler and preprocessor (cc(1) and cpp(1) by default) and a POSIX-compliant
+compiler and preprocessor (cc(1) and cpp(1) by default) with the -idirafter
+flag, a Rust compiler (rustc(1) by default), bindgen(1), and a POSIX-compliant
 make(1) utility.
 
 To build and install:
@@ -32,6 +32,29 @@ $ make PREFIX="/your/preferred/location" install
 To build with a different compiler than the default:
 
 $ make CC=clang
+$ make RUSTC=gccrs
+
+To test the utilities:
+
+$ make test
+
+To remove all untracked files:
+
+$ make clean
+
+Read More
+
+An Introduction to the Unix Shell
+<https://porkmail.org/era/unix/shell>
+
+Master Foo and the Ten Thousand Lines
+<http://www.catb.org/~esr/writings/unix-koans/ten-thousand.html>
+
+Master Foo Discourses on the Unix-Nature
+<http://www.catb.org/~esr/writings/unix-koans/unix-nature.html>
+
+Shell Programming!
+<https://tldp.org/LDP/abs/html/why-shell.html>
 
 --
 Copyright © 2023–2024 Emma Tebibyte <emma@tebibyte.media>

docs/str.1

@@ -1,58 +0,0 @@
-.\" Copyright (c) 2023–2024 DTB <trinity@trinity.moe>
-.\" Copyright (c) 2023 Emma Tebibyte <emma@tebibyte.media>
-.\"
-.\" This work is licensed under CC BY-SA 4.0. To see a copy of this license,
-.\" visit <http://creativecommons.org/licenses/by-sa/4.0/>.
-
-.TH STR 1
-
-.SH NAME
-
-str \(en test the character types of string arguments
-
-.SH SYNOPSIS
-
-str
-.RB [ type ]
-.RB [ string... ]
-
-.SH DESCRIPTION
-
-Str tests each character in an arbitrary quantity of string arguments against
-the function of the same name within ctype(3).
-
-.SH DIAGNOSTICS
-
-Str exits successfully if all tests pass and unsuccessfully if a test failed.
-.PP
-Str will exit unsuccessfully if a string is empty, as none of its contents
-passed the test.
-.PP
-Str will print a message to standard error and exit unsuccessfully if used
-improperly.
-
-.SH DEPRECATED FEATURES
-
-Str used to have an "isvalue" type as an extension to ctype(3). This was
-removed in favor of using strcmp(1) to compare strings against the empty string
-('').
-
-.SH BUGS
-
-There's no way of knowing which argument failed the test without re-testing
-arguments individually.
-.PP
-If a character in a string isn't valid ASCII str will exit unsuccessfully.
-
-.SH AUTHOR
-
-Written by DTB <trinity@trinity.moe>.
-
-.SH COPYRIGHT
-
-Copyright © 2023 DTB. License AGPLv3+: GNU AGPL version 3 or later
-<https://gnu.org/licenses/gpl.html>.
-
-.SH SEE ALSO
-
-ctype(3p), strcmp(1), ascii(7)

docs/stris.1

@@ -0,0 +1,118 @@
+.\" Copyright (c) 2023–2024 DTB <trinity@trinity.moe>
+.\" Copyright (c) 2023 Emma Tebibyte <emma@tebibyte.media>
+.\"
+.\" This work is licensed under CC BY-SA 4.0. To see a copy of this license,
+.\" visit <http://creativecommons.org/licenses/by-sa/4.0/>.
+
+.TH STRIS 1
+
+.SH NAME
+
+stris \(en test the character types of string arguments
+
+.SH SYNOPSIS
+
+stris
+.RB ( -7bcdlu )
+.RB ( -i [ inclusions ])
+.RB [ strings... ]
+
+.SH DESCRIPTION
+
+Stris tests each rune in an arbitrary quantity of string arguments, ensuring
+each meets any of the parameters specified in the program options.
+
+.SH OPTIONS
+
+.B -7
+.RS
+Tests to see if runes are fit within seven bits; that is, that they are encoded
+with ASCII.
+.RE
+
+.B -b
+.RS
+Tests to see if runes are blank or "whitespace"; characters that do not print
+but fill a predictable amount of space.
+.RE
+
+.B -c
+.RS
+Tests to see if runes are control characters; characters that are not printing
+or graphical.
+.RE
+
+.B -d
+.RS
+Tests to see if runes are numeric. This test does not only allow the ASCII
+digits but any numeric symbol.
+.RE
+
+.B -i
+.RS
+Permits, in addition to the given specified parameters, all of the runes
+supplied in its option argument.
+.RE
+
+.B -l
+.RS
+Tests to see if runes are in their lower case.
+.RE
+
+.B -u
+.RS
+Tests to see if runes are in their upper case, or capitalized.
+.RE
+
+.SH DIAGNOSTICS
+
+Stris exits successfully if all runes in all given strings meet any of the
+specified parameters, or if no parameters were specified but all given strings
+were legibly encoded. It exits unsuccessfully if the previous is untrue, and if
+invalid options were given, or if no strings were given, a usage synopsis will
+be printed to the standard error.
+
+.SH BUGS
+
+There's no way of knowing which argument failed the test without re-testing
+arguments individually.
+
+Some runes that can losslessly be encoded into ASCII from UTF-8 but in an
+"overlong encoding", where the rune was encoded with unnecessary leading
+zeroes causing it to span multiple bytes, won't be detected as ASCII.
+
+.SH EXAMPLES
+
+This is an sh(1p) snippet that checks to see if an environment variable is an
+ASCII digit.
+
+.RS
+.R stris -7 "$v" && stris -d "$v" && echo ASCII digit.
+.RE
+
+This is an sh(1p) snippet that checks to see if an environment variable is a
+hexadecimal number.
+
+.RS
+.R stris -7 "$v" && stris -di ABCDEFabcdef "$v" && echo Hexadecimal number.
+.RE
+
+.SH AUTHOR
+
+Written by DTB <trinity@trinity.moe>.
+
+.SH HISTORY
+
+Stris replaces the former str(1) which took the name of a function from
+ctype(3) as its first argument and checked the following strings against it;
+str(1) exited unsuccessfully when it encountered any non-ASCII runes and could
+only have one parameter specified.
+
+.SH COPYRIGHT
+
+Copyright © 2023–2024 DTB. License AGPLv3+: GNU AGPL version 3 or later
+<https://gnu.org/licenses/gpl.html>.
+
+.SH SEE ALSO
+
+ascii(7), ctype(3p), strcmp(1)

src/sleep.rs

@@ -1,47 +0,0 @@
-/*
- * Copyright (c) 2024 DTB <trinity@trinity.moe>
- * 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::{
-	env::args,
-	process::ExitCode,
-	thread::sleep,
-	time::Duration
-};
-
-extern crate sysexits;
-use sysexits::EX_USAGE;
-
-fn usage(s: &str) -> ExitCode {
-	eprintln!("Usage: {} [seconds]", s);
-	ExitCode::from(EX_USAGE as u8)
-}
-
-fn main() -> ExitCode {
-	let argv = args().collect::<Vec<String>>();
-
-	if argv.len() == 2 {
-		if let Ok(s) = argv[1].parse::<u64>() {
-			sleep(Duration::from_secs(s));
-			ExitCode::SUCCESS
-		} else {
-			usage(&argv[0])
-		}
-	} else {
-		usage(&argv[0])
-	}
-}

src/str.c

@@ -1,75 +0,0 @@
-/*
- * Copyright (c) 2023 DTB <trinity@trinity.moe>
- * Copyright (c) 2023 Marceline Cramer <mars@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/.
- */
-
-#include <ctype.h>
-#include <stddef.h> /* NULL */
-#include <stdio.h> /* fprintf(3) */
-#include <stdlib.h> /* EXIT_FAILURE */
-#include <string.h> /* strcmp(3) */
-#include <sysexits.h>
-
-static char *program_name = "str";
-
-static struct {
-	char *name;
-	int (*f)(int);
-}ctypes[] = {
-	{ "isalnum", isalnum },
-	{ "isalpha", isalpha },
-	{ "isblank", isblank },
-	{ "iscntrl", iscntrl },
-	{ "isdigit", isdigit },
-	{ "isxdigit", isxdigit },
-	{ "isgraph", isgraph },
-	{ "islower", islower },
-	{ "isprint", isprint },
-	{ "ispunct", ispunct },
-	{ "isspace", isspace },
-	{ "isupper", isupper }
-};
-
-int main(int argc, char *argv[]){
-	int ctype;
-	int i;
-	int r;
-
-	if(argc >= 3){
-		for(ctype = 0; ctype < (sizeof ctypes) / (sizeof *ctypes);
-				++ctype)
-			if(strcmp(argv[1], ctypes[ctype].name) == 0)
-				goto pass;
-	}
-
-	fprintf(stderr, "Usage: %s [type] [string...]\n",
-		argv[0] == NULL ? program_name : argv[0]);
-
-	return EX_USAGE;
-
-pass:	for(argv += 2, r = 1; *argv != NULL; ++argv)
-		for(i = 0; argv[0][i] != '\0'; ++i)
-			/* First checks if argv[0][i] is valid ASCII; ctypes(3)
-			 * don't handle non-ASCII.
-			 * This is bad. */
-			if((unsigned char)argv[0][i] < 0x80 && !ctypes[ctype].f(argv[0][i]))
-				return 1;
-			else
-				r = 0;
-
-	return r;
-}

src/stris.rs

@@ -0,0 +1,93 @@
+/*
+ * Copyright (c) 2023–2024 DTB <trinity@trinity.moe>
+ * Copyright (c) 2023 Marceline Cramer <mars@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::{
+	env::args,
+	process::ExitCode
+};
+
+extern crate getopt;
+use getopt::{ Opt, Parser };
+
+extern crate sysexits;
+use sysexits::EX_USAGE;
+
+struct Reqs {
+	ascii: bool, blank: bool, cntrl: bool, digit: bool, lower: bool,
+	upper: bool, inuse: bool, extra: String
+}
+
+fn usage(s: &str) -> ExitCode {
+	eprintln!("Usage: {} (-7bcdlu) (-i [inclusions]) [strings...]", s);
+	ExitCode::from(EX_USAGE as u8)
+}
+
+fn main() -> ExitCode {
+	let argv = args().collect::<Vec<String>>();
+	let mut opts = Parser::new(&argv, "7bcdi:lu");
+	let mut reqs = Reqs {
+		ascii: false, blank: false, cntrl: false, digit: false, lower: false,
+		upper: false, inuse: false, extra: String::new()
+	};
+
+	loop {
+		match opts.next() {
+			None => break,
+			Some(opt) => {
+				match opt {
+					Ok(Opt('7', None)) => reqs.ascii = true,
+					Ok(Opt('b', None)) => reqs.blank = true,
+					Ok(Opt('c', None)) => reqs.cntrl = true,
+					Ok(Opt('d', None)) => reqs.digit = true,
+					Ok(Opt('i', Some(arg))) => reqs.extra = arg,
+					Ok(Opt('l', None)) => reqs.lower = true,
+					Ok(Opt('u', None)) => reqs.upper = true,
+					_ => { return usage(&argv[0]); }
+				}
+				reqs.inuse = true;
+			}
+		}
+	}
+
+	if argv.len() == opts.index() {
+		return usage(&argv[0]);
+	}
+
+	drop(argv);
+
+	if reqs.inuse {
+		for arg in args().skip(opts.index()) {
+			for c in arg.chars() {
+				if (reqs.ascii && c.is_ascii())
+						|| (reqs.blank && c.is_whitespace())
+						|| (reqs.cntrl && c.is_control())
+						|| (reqs.digit && c.is_numeric())
+						|| (reqs.lower && c.is_lowercase())
+						|| (reqs.upper && c.is_uppercase())
+						|| reqs.extra.contains(c) {
+					continue;
+				} else {
+					return ExitCode::FAILURE;
+				}
+			}
+		}
+	}
+
+	ExitCode::SUCCESS
+}