scroll(1): renamed from pg(1)

I could trace strcmp(1) as far back as
<293436c5ad/src/streq.c>
in my repo.

CONDUCT

@@ -0,0 +1,83 @@
+Code of Conduct
+
+This Code of Conduct is derived from the 10 Pāramitās of Theravadin Buddhism.
+You can read more about them in Ṭhānissaro Bhikkhu’s Ten Perfections: A Study
+Guide [0].
+
+1. Generosity (Dāna)
+
+Give contributions freely and willingly under the terms of the GNU Affero
+General Public License, version 3 or later, or a compatible license.
+
+2. Ethics (Sīla)
+
+Do not use nonfree code or uncredited code in contributions. Do not contribute
+code of dubious origins, such as code generated by large language models or
+unlicensed snippets found online [1]. Do not take credit for others’
+contributions. Make sure to utilize the copyright header and license notice on
+source files to credit yourself and others for their work.
+
+3. Renunciation (Nekkhamma)
+
+Stay committed to the principles of simplicity and interoperability embodied by
+the project. Keep your personal will and desire out of the project, for it can
+only prove harmful to its success.
+
+4. Wisdom (Pañña)
+
+Look to established sources for standards, best practices, and important
+implementation details when setting new precedence. Follow the existing
+precedence where it applies.
+
+5. Energy (Viriya)
+
+Focus on the currently-open, currently-assigned, and currently-in-progress
+issues, pull requests, and other endeavors in order to keep yourself and others
+from being overwhelmed with responsibility, either from your zeal or your
+negligence.
+
+If you notice an issue, open an issue as soon as you can. If you see a neglected
+branch, open a pull request or comment on an existing one, if applicable. Be
+diligent in your commitment to making this project work.
+
+6. Patience (Khanti)
+
+Be patient with maintainers and other contributors. We all have our own lives
+going on and may need significant time to get to things.
+
+7. Truthfulness (Sacca)
+
+Communicate honestly and openly. Do not embellish facts to get your way. Make
+sure to let maintainers know about any issues along the way and keep ample
+communication channels open.
+
+8. Determination (Adhiṭṭhāna)
+
+Stay focused on long-term objectives and cultivate attainment to that
+achievement by utilizing to the fullest extent possible the tools available to
+you for managing the workload.
+
+9. Loving-Kindness (Mettā)
+
+Treat everyone with respect, even if they treat you poorly. This does not mean
+you have to put up with abuse, but make sure to respond with kindness and with
+love in your heart. Support and uplift maintainers and other contributors with
+your words and actions.
+
+Do not use angry or hateful language toward contributors, such as demeaning
+phrases and slurs. Make sure that if you do not know the pronouns of a
+contributor to ask for them and, in the meantime, use gender-neutral they/them
+or equivalent pronouns.
+
+10. Equanimity (Upekkhā)
+
+Keep a balanced perspective on all suggestions and contributions and make
+judgements not from a place of ego and personal preference but on their
+usefulness and suitability to the project. Make sure to keep an eye on the
+bigger picture as implementing individual features may seem intuitive at first
+but scale poorly in practical use. Keep a level head about your own work: it is
+not shameful to make a mistake in this vein, and fixing it usually leads to
+more insight.
+
+[0] <https://www.dhammatalks.org/books/#/books/TenPerfections/Section0001.html>
+[1] <https://www.fsf.org/news/publication-of-the-fsf-funded-white-papers-on-questions-around-copilot>

CONTRIBUTING

@@ -1,3 +1,5 @@
+Make sure to read our code of conduct in the CONDUCT file.
+
 When contributing a pull request to the main branch, please sign your commits
 with a PGP key and add your name and the year to the bottom of the list of
 copyright holders for the file. For example, an existing copyright header might

Makefile

@@ -8,16 +8,20 @@
 # permitted in any medium without royalty provided the copyright notice and this
 # notice are preserved.  This file is offered as-is, without any warranty.
 
-.POSIX:
+# The octal escape \043 is utilized twice in this file as make(1p) will
+# interpret a hash in a rule as an inline comment.
 
-# if using BSD make(1), remove these pragmas because they break it
-.PRAGMA: posix_202x # future POSIX standard support à la pdpmake(1)
-.PRAGMA: command_comment # breaks without this?
+.POSIX:
 
 DESTDIR ?= dist
 PREFIX ?= /usr/local
 
-SYSEXITS != printf '\043include <sysexits.h>\n' | cpp -M - | sed 's/ /\n/g' \
+# normalized prefix
+PREFIX_N != (test -d $(PREFIX) && [ '-' != $(PREFIX) ] \
+	&& CDPATH= cd -P -- $(PREFIX) && pwd -P)
+MANDIR != [ $(PREFIX_N) = / ] && printf '/usr/share/man\n' \
+	|| printf '/share/man\n'
+SYSEXITS != printf '\043include <sysexits.h>\n' | cpp -M - | tr ' ' '\n' \
 	| sed -n 's/sysexits\.h//p' || printf 'include\n'
 
 CC ?= cc
@@ -28,50 +32,61 @@ RUSTLIBS = --extern getopt=build/o/libgetopt.rlib \
 CFLAGS += -I$(SYSEXITS)
 
 .PHONY: all
-all: dj false fop hru intcmp mm npc rpn scrut str strcmp swab true
+all: dj false fop hru intcmp mm npc rpn scroll scrut str strcmp swab true
 
+# keep build/include until bindgen(1) has stdin support
+# https://github.com/rust-lang/rust-bindgen/issues/2703
 build:
-	# keep build/include until bindgen(1) has stdin support
-	# https://github.com/rust-lang/rust-bindgen/issues/2703
-	mkdir -p build/bin build/include build/lib build/o build/test
+	mkdir -p build/bin build/docs build/include build/lib build/o build/test
 
 .PHONY: clean
 clean:
 	rm -rf build dist
 
-dist: all
-	mkdir -p $(DESTDIR)/$(PREFIX)/bin $(DESTDIR)/$(PREFIX)/share/man/man1
+dist: all docs
+	mkdir -p $(DESTDIR)/$(PREFIX)/bin $(DESTDIR)/$(PREFIX)/$(MANDIR)/man1
 	cp build/bin/* $(DESTDIR)/$(PREFIX)/bin
-	cp docs/*.1 $(DESTDIR)/$(PREFIX)/share/man/man1
+	cp build/docs/*.1 $(DESTDIR)/$(PREFIX)/$(MANDIR)/man1
 
 .PHONY: install
 install: dist
 	cp -r $(DESTDIR)/* /
 
 .PHONY: test
-test: build
+test: build /tmp/getopt
+	/tmp/getopt
 	tests/posix-compat.sh
-	$(RUSTC) --test src/getopt-rs/lib.rs -o build/test/getopt
+
+/tmp/getopt: src/libgetopt.rs
+	$(RUSTC) --test -o /tmp/getopt src/libgetopt.rs
+
+.PHONY: docs
+docs: docs/ build
+	for file in docs/*; do original="$$(sed -n '/^\.TH/p' <"$$file")"; \
+		title="$$(printf '%s\n' "$$original" | sed \
+		"s/X\.X\.X/$$(git describe --tags --long | cut -d'-' -f1)/g")"; \
+		sed "s/$$original/$$title/g" <"$$file" >"build/$$file"; done
 
 .PHONY: rustlibs
 rustlibs: build/o/libsysexits.rlib build/o/libgetopt.rlib \
 	build/o/libstrerror.rlib
 
-build/o/libgetopt.rlib: build src/getopt-rs/lib.rs
+build/o/libgetopt.rlib: build src/libgetopt.rs
 	$(RUSTC) $(RUSTFLAGS) --crate-type=lib --crate-name=getopt \
-		-o $@ src/getopt-rs/lib.rs
+		-o $@ src/libgetopt.rs
 
-build/o/libstrerror.rlib: build src/strerror.rs
+build/o/libstrerror.rlib: build src/libstrerror.rs
 	$(RUSTC) $(RUSTFLAGS) --crate-type=lib -o $@ \
-		src/strerror.rs
+		src/libstrerror.rs
 
-build/o/libsysexits.rlib: build $(SYSEXITS)sysexits.h
-	# bandage solution until bindgen(1) gets stdin support
-	printf '#define EXIT_FAILURE 1\n' | cat - $(SYSEXITS)sysexits.h \
-		> build/include/sysexits.h 
+build/o/libsysexits.rlib: build/include/sysexits.h
 	bindgen --default-macro-constant-type signed --use-core --formatter=none \
 		build/include/sysexits.h | $(RUSTC) $(RUSTFLAGS) --crate-type lib -o $@ -
 
+# bandage solution until bindgen(1) gets stdin support
+build/include/sysexits.h: build $(SYSEXITS)sysexits.h
+	printf '\043define EXIT_FAILURE 1\n' | cat - $(SYSEXITS)sysexits.h > $@
+
 .PHONY: dj
 dj: build/bin/dj
 build/bin/dj: src/dj.c build
@@ -94,23 +109,23 @@ build/bin/hru: src/hru.rs build rustlibs
 
 .PHONY: intcmp
 intcmp: build/bin/intcmp
-build/bin/intcmp: src/intcmp.c build
-	$(CC) $(CFLAGS) -o $@ src/intcmp.c
+build/bin/intcmp: src/intcmp.rs build rustlibs
+	$(RUSTC) $(RUSTFLAGS) $(RUSTLIBS) -o $@ src/intcmp.rs
 
 .PHONY: mm
 mm: build/bin/mm
-build/bin/mm: src/mm.c build
-	$(CC) $(CFLAGS) -o $@ src/mm.c
+build/bin/mm: src/mm.rs build rustlibs 
+	$(RUSTC) $(RUSTFLAGS) $(RUSTLIBS) -o $@ src/mm.rs
 
 .PHONY: npc
 npc: build/bin/npc
 build/bin/npc: src/npc.c build
 	$(CC) $(CFLAGS) -o $@ src/npc.c
 
-.PHONY: pg
-pg: build/bin/pg
-build/bin/pg: src/pg.c build
-	$(CC) $(CFLAGS) -o $@ src/pg.c
+.PHONY: scroll
+scroll: build/bin/scroll
+build/bin/scroll: src/scroll.c build
+	$(CC) $(CFLAGS) -o $@ src/scroll.c
 
 .PHONY: rpn
 rpn: build/bin/rpn
@@ -134,10 +149,8 @@ build/bin/strcmp: src/strcmp.c build
 
 .PHONY: swab
 swab: build/bin/swab
-build/bin/swab: src/swab.rs build build/o/libsysexits.rlib
-	$(RUSTC) $(RUSTFLAGS) --extern getopt=build/o/libgetopt.rlib \
-		--extern sysexits=build/o/libsysexits.rlib \
-		-o $@ src/swab.rs
+build/bin/swab: src/swab.rs build rustlibs
+	$(RUSTC) $(RUSTFLAGS) $(RUSTLIBS) -o $@ src/swab.rs
 
 .PHONY: true
 true: build/bin/true

README

@@ -1,28 +1,29 @@
 “Seek not to walk the path of the masters; seek what they sought.”
 – Matsuo Basho
 
-The Bonsai core utilities are the result of the careful examination of the
-current state of POSIX and Unix utilies. The Unix Philosophy, “do one thing and
-do it well” is its core but these tools do not cling to the names of the past.
+The Bonsai harakit utilities are a replacement for standard POSIX utilities
+which aim to fill its niche while expanding on their capabilities. These new
+tools are the result of the careful examination of the current state of POSIX
+and Unix utilies. The Unix Philosophy of “do one thing and do it well” are their
+core but they avoid clinging to the past.
 
 The era of the original Unix tools has been long and fruitful, but they have
-their flaws. The new, non-POSIX era of this project started with frustration
-with the way certain tools work and how other projects that extend POSIX don’t
-make anything better.
+their flaws. This project originated from frustrations with the way certain
+tools work and how other projects that extend POSIX don’t make anything better.
 
 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.
+harakit utilities will intentionally discourage use of the shell for purposes
+beyond its scope.
 
 See docs/ for more on the specific utilities currently implemented.
 
 Building
 
-The coreutils require a POSIX-compliant environment to compile, including a C
-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.
+Harakit utilities require a POSIX-compliant environment to compile, including a
+C compiler and preprocessor (cc(1) and cpp(1) by default), an edition 2023 Rust
+compiler (rustc(1) by default), bindgen(1), and a POSIX-compliant make(1)
+utility.
 
 To build and install:
 
@@ -38,7 +39,7 @@ To test the utilities:
 
 $ make test
 
-To remove all untracked files:
+To remove all build and distributable files:
 
 $ make clean
 

STYLE

@@ -0,0 +1,124 @@
+The following guidelines are conducive to clear and readable code that is
+consistent with the style of the rest of the Bonsai Computer System.
+
+0. Braces are mandatory for all control flow.
+
+1. Nested indentation should be kept to a minimum.
+
+2. Empty lines should be placed between different kinds of statements:
+
+	int t;
+
+	assert(io->bufuse > 0);
+	assert(io->bufuse <= io->bs);
+
+	if ((t = write(io->fd, io->buf, io->bufuse)) < 0) {
+		io->error = errno;
+		t = 0;
+	} else if (t > 0) {
+		memmove(io->buf, &(io->buf)[t], (io->bufuse -= t));
+	}
+
+	io->bytes += t;
+	io->prec  += (t > 0 && io->bufuse > 0);
+	io->rec   += (t > 0 && io->bufuse == 0);
+
+	return io;
+
+3. Each block of code should be indented once more than the keyword which
+initiated the block:
+
+	switch (c) {
+		case 'e': mode |= EQUAL;   break;
+		case 'g': mode |= GREATER; break;
+		case 'l': mode |= LESS;    break;
+		default:  return usage(s);
+	}
+
+4. In C, spaces should be placed in control flow statements after the keyword
+and before the opening brace:
+
+	for (i = 2; i < argc; ++i) {
+
+5. If a function, a C control flow statement, or a Rust macro has arguments that
+cause the statement to be broken into multiple lines, this should be done by
+placing the arguments on a new line inside the parentheses: 
+
+	let usage = format!(
+		"Usage: {} [-d delimiter] index command [args...]",
+		argv[0],
+	);
+
+6. If Rust function arguments or fields are on their own lines, they should
+always have a trailing comma:
+
+	return Err(EvaluationError {
+		message: format!("{}: Invalid token", i),
+		code: EX_DATAERR,
+	})
+
+7. If text is on the same line as a brace, spaces should be placed after an
+opening curly brace and before a closing one:
+
+	use sysexits::{ EX_DATAERR, EX_IOERR, EX_UNAVAILABLE, EX_USAGE };
+
+8. If a control flow statement is short enough to be easily understood in a
+glance, it may be placed on a single line:
+
+	if !(argc < 0) { usage(program_name); }
+
+9. In C, note everything you use from a library in a comment subsequent to its
+#include statement:
+
+	#include <unistd.h> /* close(2), getopt(3), lseek(2), read(2), write(2),
+                         * optarg, optind, STDIN_FILENO, STDOUT_FILENO */
+
+10. In Rust, place extern statements after use statements that include standard
+library crates. Group alike statements:
+
+	use std::fs::Path;
+
+	extern crate strerror;
+	extern crate sysexits;
+
+	use strerror::StrError;
+	use sysexits::{ EX_OSERR, EX_USAGE };
+
+11. Do not use do while loops in C.
+
+12. Adhere to the following rules from the paper The Power of 10: Rules for
+Developing Safety-Critical Code [0]:
+	1. Avoid complex flow constructs, such as goto and recursion.
+	2. All loops must have fixed bounds. This prevents runaway code.
+	3. Avoid heap memory allocation.
+	4. Restrict functions to the length of a single printed page.
+
+	6. Restrict the scope of data to the smallest possible.
+	7. Check the return value of all non-void functions, or cast to void to
+	indicate the return value is useless (such as in the case of using
+	fprintf(3p)	to print to the standard error).
+	8. Use the preprocessor sparingly.
+	9. Limit pointer use to a single dereference, and do not use function
+	pointers.
+	10. Compile with all possible warnings active; all warnings should then be
+	addressed before release of the software (for C compilers, compile with
+	-Wpedantic).
+
+13. Remember this quote from The Elements of Programming Style by Brian
+Kernighan:
+	Everyone knows that debugging is twice as hard as writing a program in the
+	first place. So if you're as clever as you can be when you write it, how
+	will you ever debug it?
+
+
+References
+==========
+
+[0] <https://web.eecs.umich.edu/~imarkov/10rules.pdf>
+
+--
+Copyright © 2024 Emma Tebibyte <emma@tebibyte.media>
+Copyright © Wikipedia contributors
+
+This work is licensed under CC BY-SA 4.0. To view a copy of this license, visit
+<http://creativecommons.org/licenses/by-sa/4.0/>.

docs/dj.1

@@ -1,160 +1,226 @@
 .\" Copyright (c) 2024 DTB <trinity@trinity.moe>
+.\" Copyright (c) 2024 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 dj 1
-
+.\"
+.TH DJ 1 2024-07-14 "Harakit X.X.X"
 .SH NAME
-
 dj \(en disk jockey
-
+.\"
 .SH SYNOPSIS
 
 dj
-.RB ( -AdHnq )
-.RB ( -a
-.RB [ byte ])
-.RB ( -c
-.RB [ count ])
+.RB [ -Hn ]
+.RB [ -a\ byte ]
+.RB [ -c\ count ]
 
-.RB ( -i
-.R [
-.B input file
-.R ])
-.RB ( -b
-.R [
-.B input block size
-.R ])
-.RB ( -s
-.R [
-.B input offset
-.R ])
+.RB [ -i\ file ]
+.RB [ -b\ block_size ]
+.RB [ -s\ offset ]
 
-.RB ( -o
-.R [
-.B output file
-.R ])
-.RB ( -B
-.R [
-.B output block size
-.R ])
-.RB ( -S
-.R [
-.B output offset
-.R ])
+.RB [ -o\ file ]
+.RB [ -B\ block_size ]
+.RB [ -S\ offset ]
+.\"
+.SH DESCRIPTION
 
-.SH USAGE
+Perform precise read and write operations on files. This utility is useful for
+reading and writing binary data to and from disks.
 
-The
-.B -i
-option takes a path as an argument to open and use in place of standard input.
-The
-.B -o
-option does the same in place of standard output. Dj does not truncate output
-files and instead writes over the bytes in the existing file.
-.PP
-The
-.B -b
-option takes a numeric argument as the size in bytes of the input buffer and
-the
-.B -B
-option does the same for the output buffer, the default for both being 1024
-bytes, or one kibibyte (KiB).
-.PP
-The
-.B -s
-option takes a numeric argument as the number of bytes to skip into the input
-before starting to read, and the
-.B -S
-option skips a number of bytes through the output before starting to write from
-the input. If the input is a stream the bytes are read and discarded. If the
-output is a stream, nul characters are printed.
-.PP
-The
-.B -a
-option takes one argument of one byte in length and pads the input buffer with
-that byte in the event that a read doesn't fill the input buffer, and the
-.B -A
-option takes no arguments and pads with nuls.
-The
-.B -c
-option specifies an amount of reads to make, and if 0 (the default) dj will
-continue reading until a partial or empty read.
-.PP
-On a partial or empty read, dj prints a diagnostic message (unless the
-.B -q
-option is specified) and exits (unless the
-.B -n
-option is specified, in which case only two consecutive empty reads will cause
-dj to exit).
-At exit, usage statistics are printed unless the option
-.B -q
-is specified a second time. The
-.B -H
-option will make these diagnostics human-readable.
+This manual page uses the terms \(lqskip\(rq and \(lqseek\(rq to refer to moving
+to a specified byte by index in the input and output of the program
+respectively. This language is inherited from the
+.BR dd (1p)
+utility and used here to decrease ambiguity.
 
+The offset used when skipping or seeking refers to how many bytes are skipped
+or sought. Running
+.BR dj (1)
+with a skip offset of 1 skips one byte into the input and reads from the second
+byte onwards. A programmer may think of a file as a zero-indexed array of
+bytes; in this analogy, the offset given is the index of the byte at which to
+start reading or writing.
+.\"
+.SH OPTIONS
+
+.IP \fB-i\fP\ \fIfile\fP
+Takes a file path as an argument and opens it for use as an input.
+.IP \fB-b\fP\ \fIblock_size\fP
+Takes a numeric argument as the size in bytes of the input buffer, the default
+being 1024.
+.IP \fB-s\fP
+Takes a numeric argument as the index of the byte at which reading will
+commence; \(lqskips\(rq that number of bytes. If the standard input is used,
+bytes read to this point are discarded.
+.IP \fB-o\fP
+Takes a file path as an argument and opens it for use as an output.
+.IP \fB-B\fP\ \fIblock_size\fP
+Takes a numeric argument as the size in bytes of the output buffer, the default
+being 1024. Note that this option only affects the size of output writes and not
+the amount of output data itself. See the CAVEATS section.
+.IP \fB-S\fP
+Takes a numeric argument as the index of the byte at which writing will
+commence; \(lqseeks\(rq that number of bytes. If the standard output is used,
+null characters are printed.
+.IP \fB-a\fP
+Accepts a single literal byte with which the input buffer is padded in the event
+of an incomplete read from the input file. If the option argument is empty, the
+null byte is used.
+.IP \fB-c\fP
+Specifies a number of blocks to read. The default is 0, in which case the input
+is read until a partial or empty read is made.
+.IP \fB-H\fP
+Prints diagnostic messages in a human-readable manner as described in the
+DIAGNOSTICS section.
+.IP \fB-n\fP
+Retries failed reads once before exiting.
+.\"
+.SH STANDARD INPUT
+
+The standard input shall be used as an input if no inputs are specified or if
+input file is \(lq-\(rq.
+.\"
+.SH STANDARD OUTPUT
+The standard output shall be used as an output if no inputs are specified or if
+the output file is \(lq-\(rq.
+.\"
+.SH EXAMPLES
+
+The following
+.BR sh (1p)
+line:
+
+.RS
+printf 'Hello, world!\(rsn' | dj -c 1 -b 7 -s 7 2>/dev/null
+.RE
+
+Produces the following output:
+
+.RS
+world!
+.RE
+
+The following
+.BR sh (1p)
+lines run sequentially:
+
+.RS
+tr '\(rs0' 0    </dev/zero | dj -c 1 -b 6 -o hello.txt
+
+tr '\(rs0' H    </dev/zero | dj -c 1 -b 1 -o hello.txt
+
+tr '\(rs0' e    </dev/zero | dj -c 1 -b 1 -o hello.txt -S 1
+
+tr '\(rs0' l    </dev/zero | dj -c 1 -b 2 -o hello.txt -S 2
+
+tr '\(rs0' o    </dev/zero | dj -c 1 -b 1 -o hello.txt -S 4
+
+tr '\(rs0' '\(rsn' </dev/zero | dj -c 1 -b 1 -o hello.txt -S 5
+
+dj -i hello.txt
+.RE
+
+Produce the following output:
+
+.RS
+Hello
+.RE
+
+It may be particularly illuminating to print the contents of the example
+.B hello.txt
+after each
+.BR dj (1)
+invocation.
+.\"
 .SH DIAGNOSTICS
 
-The
-.B -d
-option prints all information, user-specified or otherwise, before program
-execution.
-.PP
-When dj exits, by default statistics are printed for input and output to
-standard error in the following format:
-.PP
-.R {records read} {ASCII unit separator} {partial records read}
-.R {ASCII record separator} {records written} {ASCII unit separator}
-.R {partial records written} {ASCII group separator} {bytes read}
-.R {ASCII record separator} {bytes written} {ASCII file separator}
-.PP
-If the
-.B -H
-option is specified dj instead uses this following format:
-.PP
-.R {records read} '+' {partial records read} '>' {records written}
-.R '+' {partial records written} ';' {bytes read} '>' {bytes written}
-.R {ASCII line feed}
-.PP
-The
-.B -q
-option suppresses error messages which print when a read or write is partial or
-empty and when used twice suppresses diagnostic output entirely.
-.PP
-In non-recoverable errors that don't pertain to dj's read-write cycle, a
-diagnostic message is printed and dj exits with the appropriate sysexits(3)
-status.
+On a partial or empty read, a diagnostic message is printed. Then, the program
+exits unless the
+.B -n
+option is specified.
 
+By default, statistics are printed for input and output to the standard error in
+the following format:
+
+.RS
+{records read} {ASCII unit separator} {partial records read}
+{ASCII record separator} {records written} {ASCII unit separator}
+{partial records written} {ASCII group separator} {bytes read}
+{ASCII record separator} {bytes written} {ASCII file separator}
+.RE
+
+This format for diagnostic output is designed to be machine-parseable for
+convenience. For a more human-readable format, the
+.B -H
+option may be specified. In this event, the following format is used instead:
+
+.RS
+{records read} '+' {partial records read} '>' {records written}
+'+' {partial records written} ';' {bytes read} '>' {bytes written}
+{ASCII line feed}
+.RE
+
+In non-recoverable errors that don\(cqt pertain to the read-write cycle, a
+diagnostic message is printed and the program exits with the appropriate
+.BR sysexits.h (3)
+status.
+.\"
 .SH BUGS
 
 If
 .B -n
-is specified along with a specified count, actual byte output may be lower than
-expected (the product of the count multiplied by the input block size). If the
+is specified along with the
+.B -c
+option and a count, actual byte output is the product of the count and the input
+block size and therefore may be lower than expected. If the
 .B -a
-or
-.B -A
-options are used this could make data written nonsensical.
-.PP
-Many lowercase options have capitalized variants and vice-versa which can be
-confusing. Capitalized options tend to affect output or are more intense
-versions of lowercase options.
+option is specified, this could make written data nonsensical.
+.\"
+.SH CAVEATS
 
+Existing files are not truncated on ouput and are instead overwritten.
+
+Option variants that have lowercase and uppercase forms could be confused for
+each other. The former affects input and the latter affects output.
+
+The
+.B -B
+option could be mistaken for the count in bytes of data written to the output.
+This conception is intuitive but incorrect, as the
+.B -c
+option controls the number of blocks to read and the
+.B -b
+option sets the size of the blocks. The
+.B -B
+option is similar to the latter but sets the size of blocks to be written,
+regardless of the amount of data that will actually be written. In practice,
+this means the input buffer should be very large to make use of modern hardware
+input and output speeds.
+
+The skipped or sought bytes while processing irregular files, such as streams,
+are reported in the diagnostic output, because they were actually read or
+written. This is as opposed to bytes skipped while processing regular files,
+which are not reported.
+.\"
 .SH RATIONALE
 
-Dj was modeled after the dd utility specified in POSIX but adds additional
-features: typical option formatting, allowing seeks to be specified in bytes
-rather than in blocks, allowing arbitrary bytes as padding, and printing in a
-format that's easy to parse for machines. It also neglects character
-conversion, which may be dd's original intent but is irrelevant to its modern
-use.
-
+This program was based on the
+.BR dd (1p)
+utility as specified in POSIX. While character conversion may have been the
+original intent of
+.BR dd (1p),
+it is irrelevant to its modern use. Because of this, this program eschews
+character conversion and adds typical option formatting, allowing seeks to be
+specified in bytes rather than in blocks, allowing arbitrary bytes as padding,
+and printing in a format that\(cqs easy for machines to parse.
+.\"
 .SH COPYRIGHT
 
-Copyright (C) 2023 DTB. License AGPLv3+: GNU AGPL version 3 or later
+Copyright \(co 2023 DTB. License AGPLv3+: GNU AGPL version 3 or later
 <https://gnu.org/licenses/agpl.html>.
-
+.\"
 .SH SEE ALSO
-
-dd(1)
+.BR dd (1p)
+.BR lseek (3p)
+.BR mm (1)

docs/false.1

@@ -1,35 +1,35 @@
 .\" Copyright (c) 2022, 2024 DTB <trinity@trinity.moe>
-.\" Copyright (c) 2023 Emma Tebibyte <emma@tebibyte.media>
+.\" Copyright (c) 2023–2024 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 FALSE 1
-
+.\"
+.TH FALSE 1 2024-06-06 "Harakit X.X.X"
 .SH NAME
-
 false \(en do nothing, unsuccessfully
-
+.\"
 .SH DESCRIPTION
 
-False does nothing regardless of operands or standard input.
-False will always return an exit code of 1.
-
+Do nothing regardless of operands or standard input. An exit code of 1 will
+always be returned.
+.\"
 .SH RATIONALE
 
-False exists for the construction of control flow and loops based on a failure.
-
-False functions as described in POSIX.1-2017.
-
+In POSIX.1-2017,
+.BR false (1p)
+exists for the construction of control flow and loops based on a failure. This
+implementation functions as described in that standard.
+.\"
 .SH AUTHOR
 
-Written by Emma Tebibyte <emma@tebibyte.media>.
-
+Written by Emma Tebibyte
+.MT emma@tebibyte.media
+.ME .
+.\"
 .SH COPYRIGHT
 
 This work is marked with CC0 1.0. To see a copy of this license, visit
 <http://creativecommons.org/publicdomain/zero/1.0>.
-
+.\"
 .SH SEE ALSO
-
-true(1p)
+.BR true (1p)

docs/fop.1

@@ -0,0 +1,62 @@
+.\" Copyright (c) 2024 DTB <trinity@trinity.moe>
+.\" Copyright (c) 2024 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 FOP 1 2024-06-17 "Harakit X.X.X"
+.SH NAME
+fop \(en field operator
+.\"
+.SH SYNOPSIS
+
+fop
+.RB ( -d )
+.RB [ delimiter ]
+.RB index 
+.RB program...
+.\"
+.SH DESCRIPTION
+
+Performs operations on specified fields in data read from the standard input.
+.\"
+.SH OPTIONS
+
+.IP \fB-d\fP\ \fIdelimiter\fP
+Sets a delimiter by which the input data will be split into fields. The default
+is an ASCII record separator.
+.\"
+.SH CAVEATS
+
+Field indices are zero-indexed, which may be unexpected behavior for some users.
+.\"
+.SH RATIONALE
+
+With the assumption that tools will output data separated with ASCII field
+separators, there is a need for the ability to modify select fields in this data
+easily and quickly.
+
+The idea for this utility originated in the fact that the GNU
+.BR ls (1)
+utility contains a
+.B -h
+option which enables human-readable units in file size outputs. This
+functionality was broken out into
+.BR hru (1),
+but there was no easy way to modify the field in the ouput of
+.BR ls (1p)
+without creating a new tool.
+.\"
+.SH AUTHOR
+
+Written by Emma Tebibyte
+.MT emma@tebibyte.media
+.ME .
+.\"
+.SH COPYRIGHT
+
+Copyright \(co 2024 Emma Tebibyte. License AGPLv3+: GNU AGPL version 3 or later
+<https://gnu.org/licenses/agpl.html>.
+.\"
+.SH SEE ALSO
+.BR sed (1p)

docs/hru.1

@@ -2,56 +2,68 @@
 .\"
 .\" 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 rpn 1
-
+.\"
+.TH HRU 1 2024-06-17 "Harakit X.X.X"
 .SH NAME
-
 hru \(en human readable units
-
+.\"
 .SH SYNOPSIS
 
 hru
-
+.\"
 .SH DESCRIPTION
 
-Hru reads byte counts in the form of whole numbers from the standard input and
-writes to the standard output the same number converted one of the units of data
-defined by the International System of Units.
+Convert counts to higher units.
+
+Byte counts will be read in the form of whole numbers from the standard input
+and be written to the standard output the same number converted to a higher unit
+of data as defined by the \fIInternational System of Units\fP.
 
 The program will convert the byte count to the highest unit possible where the
 value is greater than one.
-
+.\"
 .SH DIAGNOSTICS
 
-If encountering non-integer characters in the standard input, hru will exit with
-the appropriate error code as defined by sysexits.h(3) and print an error
-message.
-
+If encountering non-integer characters in the standard input, the program will
+exit with the appropriate error code as defined by
+.BR sysexits.h (3)
+and print an error message.
+.\"
 .SH RATIONALE
 
-The GNU project’s ls(1) implementation contains a human-readable option (-h)
-that, when specified, makes the tool print size information in a format more
-immediately readable. This functionality is useful not only in the context of
-ls(1) so the decision was made to split it into a new tool. The original
-functionality in GNU’s ls(1) can be emulated with fop(1) combined with this
-program.
-
+The GNU project\(cqs
+.BR ls (1)
+implementation contains a human-readable option (\fB-h\fP) that, when specified,
+makes the tool print size information in a format more immediately
+readable. This functionality is useful not only in this context, so the decision
+was made to split it into a new tool. The original functionality from GNU\(cqs
+.BR ls (1)
+can be emulated with
+.BR fop (1)
+combined with this program.
+.\"
 .SH STANDARDS
 
-Hru follows the standard unit prefixes as specified by the Bureau International
-des Poids et Mesures (BIPM) in the ninth edition of The International System of
-Units (SI).
-
+The standard unit prefixes as specified by the
+.I Bureau International des Poids et Mesures
+.RI ( BIPM )
+in the ninth edition of
+.I The International System of Units
+.RI ( SI )
+are utilized for the ouput of conversions.
+.\"
 .SH AUTHOR
 
-Written by Emma Tebibyte <emma@tebibyte.media>.
-
+Written by Emma Tebibyte
+.MT emma@tebibyte.media
+.ME .
+.\"
 .SH COPYRIGHT
 
-Copyright (c) 2024 Emma Tebibyte. License AGPLv3+: GNU AGPL version 3 or later
+Copyright \(co 2024 Emma Tebibyte. License AGPLv3+: GNU AGPL version 3 or later
 <https://gnu.org/licenses/agpl.html>.
-
+.\"
 .SH SEE ALSO
-
-GNU ls(1), The International System of Units (SI) 9th Edition
+GNU
+.BR ls (1),
+.I The International System of Units (SI) 9th Edition

docs/intcmp.1

@@ -1,78 +1,103 @@
 .\" Copyright (c) 2023–2024 DTB <trinity@trinity.moe>
-.\" Copyright (c) 2023 Emma Tebibyte <emma@tebibyte.media>
+.\" Copyright (c) 2023–2024 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 intcmp 1
-
+.\"
+.TH INTCMP 1 2024-06-06 "Harakit X.X.X"
 .SH NAME
-
 intcmp \(en compare integers
-
+.\"
 .SH SYNOPSIS
 
 intcmp
-.RB ( -eghl )
-.RB [ integer ]
-.RB [ integer... ]
-
+.RB [ -egl ]\ integer\ integer...
 .SH DESCRIPTION
+Compare integers to each other.
+.\"
+.SH OPTIONS
 
-Intcmp compares integers.
-
-.SH USAGE
-
-The -e option permits given integers to be equal to each other. If combined
-with -g or -l, only adjacent integers in the argument sequence can be equal.
-.PP
-The -g option permits a given integer to be greater than the following integer.
-.PP
-The -l option permits a given integer to be less than the following integer.
-.PP
-It may help to think of the -e, -g, and -l options as equivalent to the
-infix algebraic “=”, “>”, and “<” operators respectively, with each option
-putting its symbol between every given integer. For example,
-.R intcmp -l 1 2 3
-is equivalent to evaluating "1 < 2 < 3".
+.IP \fB-e\fP
+Permits given integers to be equal to each other.
+.IP \fB-g\fP
+Permits a given integer to be greater than the following integer.
+.IP \fB-l\fP
+Permits a given integer to be less than the following integer.
+.\"
+.SH EXAMPLES
 
+It may help to think of the
+.BR -e ,
+.BR -g ,
+and
+.B -l
+options as equivalent to the infix algebraic \(lq=\(rq, \(lq>\(rq, and \(lq<\(rq
+operators respectively, with each option putting its symbol between every given
+integer. The following example is equivalent to evaluating \(lq1 < 2 < 3\(rq:
+\"
+.RS
+intcmp -l 1 2 3
+.RE
+.\"
 .SH DIAGNOSTICS
 
-Intcmp exits 0 for a valid expression and 1 for an invalid expression.
-.PP
-Intcmp prints a debug message and exits with the appropriate sysexits(3) error
-code in the event of an error.
+The program will exit with a successfully for a valid expression and with an
+error code of 1 for an invalid expression.
 
+In the event of an error, a debug message will be printed and the program will
+exit with the appropriate
+.BR sysexits.h (3)
+error code.
+.\"
 .SH BUGS
 
-There are multiple ways to express compound comparisons; “less than or equal
-to” can be -le or -el, for example.
-.PP
-The inequality comparison is -gl or -lg for “less than or greater than”; this
-is elegant but unintuitive.
-.PP
--egl, "equal to or less than or greater than", exits 0 no matter what for valid
-program usage and may be abused to function as an integer validator.
-Use str(1) instead.
+.BR -egl ,
+\(lqequal to or less than or greater than\(rq, always exits successfully for
+valid program usage and may be abused to function as an integer validator. Use
+.BR str (1)
+instead.
+.\"
+.SH CAVEATS
 
+There are multiple ways to express compound comparisons; \(lqless than or equal
+to\(rq can be
+.B -le
+or
+.BR -el ,
+for example.
+
+The inequality comparison is
+.B -gl
+.B or
+.B -lg
+for \(lqless than or greater than\(rq;
+this is elegant but unintuitive.
+.\"
 .SH RATIONALE
 
 The traditional tool for integer comparisons in POSIX and other Unix shells has
-been test(1). This tool also handles string comparisons and file scrutiny.
-These parts of its functionality have been broken out into multiple utilities.
-
-Strcmp’s functionality may be performed on a POSIX-compliant system with
-test(1p).
+been
+.BR test (1).
+This tool also handles string comparisons and file scrutiny. These parts of its
+functionality have been broken out into multiple utilities.
 
+This program\(cqs functionality may be performed on a POSIX-compliant system
+with
+.BR test (1p).
+.\"
 .SH AUTHOR
 
-Written by DTB <trinity@trinity.moe>.
-
+Written by DTB
+.MT trinity@trinity.moe
+.ME .
+.\"
 .SH COPYRIGHT
-
-Copyright © 2023 DTB. License AGPLv3+: GNU AGPL version 3 or later
+.\"
+Copyright \(co 2023 DTB. License AGPLv3+: GNU AGPL version 3 or later
 <https://gnu.org/licenses/gpl.html>.
-
+.\"
 .SH SEE ALSO
-
-strcmp(1), scrut(1), str(1), test(1p)
+.BR scrut (1),
+.BR strcmp (1),
+.BR str (1),
+.BR test (1p)

docs/mm.1

@@ -2,75 +2,72 @@
 .\"
 .\" 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 mm 1
-
+.\"
+.TH MM 1 2024-07-14 "Harakit X.X.X"
 .SH NAME
-
 mm \(en middleman
-
+.\"
 .SH SYNOPSIS
 
 mm
-.RB ( -aenu )
-.RB ( -i
-.RB [ input ])
-.RB ( -o
-.RB [ output ])
-
+.RB [ -aetu ]
+.RB [ -i\ input ]
+.RB [ -o\ output ]
+.\"
 .SH DESCRIPTION
 
-Mm catenates input files and writes them to the start of each output file.
-
+Catenate input files and write them to the start of each output file or stream.
+.\"
 .SH OPTIONS
 
-Mm, upon receiving the
-.B -a
-option, will open subsequent outputs for appending rather than updating.
-.PP
-The
-.B -i
-option opens a path as an input. Without any inputs specified mm will use
-standard input. Standard input itself can be specified by giving the path '-'.
-.PP
-The
-.B -o
-option opens a path as an output. Without any outputs specified mm will use
-standard output. Standard output itself can be specified by giving the
-path '-'. Standard error itself can be specified with the
+.IP \fB-a\fP
+Opens outputs for appending rather than updating.
+.IP \fB-e\fP
+Use the standard error as an output.
+.IP \fB-t\fP
+Causes outputs to be overwritten instead of being truncated.
+.IP \fB-u\fP
+Ensures neither input or output will be buffered.
+.IP \fB-i\fP\ \fIinput\fP
+Opens a path as an input. If one or more of the input files is \(lq-\(rq or if
+no inputs are specified, the standard input shall be used. If specified as the
+last option and if there are trailing arguments to the program, they shall be
+appended to the list of files to use as inputs.
+.IP \fB-o\fP\ \fIoutput\fP
+Opens a path as an output. If one or more of the output files is \(lq-\(rq or if
+no outputs are specified and the
 .B -e
-option.
-.PP
-The
-.B -u
-option ensures neither input or output will be buffered.
-.PP
-The
-.B -n
-option tells mm to ignore SIGINT signals.
-
+option is not specified, the standard output shall be used. If specified as the
+last option and if there are trailing arguments to the program, they shall be
+appended to the list of files to use as outputs.
+.\"
 .SH DIAGNOSTICS
 
-If an output can no longer be written mm prints a diagnostic message, ceases
-writing to that particular output, and if there are more outputs specified,
-continues, eventually exiting unsuccessfully.
-.PP
-On error mm prints a diagnostic message and exits with the appropriate
-sysexits.h(3) status.
-
-.SH BUGS
-
-Mm does not truncate existing files, which may lead to unexpected results.
+If an output cannot be written to, an error occurs; however, exiting will be 
+deferred until writing to any other specified outputs completes.
 
+When an error is encountered, a diagnostic message is printed and the program
+exits with the appropriate
+.BR sysexits.h (3)
+status.
+.\"
 .SH RATIONALE
 
-Mm was modeled after the cat and tee utilities specified in POSIX.
-
+The
+.BR cat (1p)
+and
+.BR tee (1p)
+programs specified in POSIX together provide similar functionality. The
+separation of the two sets of functionality into separate APIs seemed
+unncessary.
+.\"
 .SH COPYRIGHT
 
-Copyright (c) 2024 DTB. License AGPLv3+: GNU AGPL version 3 or later
+Copyright \(co 2024 DTB. License AGPLv3+: GNU AGPL version 3 or later
 <https://gnu.org/licenses/agpl.html>.
-
+.\"
 .SH SEE ALSO
-
-cat(1p), dd(1), dj(1), tee(1p)
+.BR cat (1p),
+.BR dd (1),
+.BR dj (1),
+.BR tee (1p)

docs/npc.1

@@ -1,68 +1,74 @@
 .\" Copyright (c) 2023–2024 DTB <trinity@trinity.moe>
-.\" Copyright (c) 2023 Emma Tebibyte <emma@tebibyte.media>
+.\" Copyright (c) 2023–2024 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 npc 1
-
+.\"
+.TH NPC 1 2024-06-17 "Harakit X.X.X"
 .SH NAME
-
 npc \(en show non-printing characters
-
+.\"
 .SH SYNOPSIS
 
 npc
-.RB ( -eht )
-
+.RB [ -et ]
+.\"
 .SH DESCRIPTION
 
-Npc reads from standard input and writes to standard output, replacing non-
-printing characters with printable equivalents. Control characters print as a
-carat ('^') followed by the character '@' through '_' corresponding to the
-character replaced (e.g. control-X becomes "^X"). The delete character (0x7F)
-becomes "^?". Characters with the high bit set (>127) are printed as "M-"
+Print normally non-printing characters.
+
+The program reads from standard input and writes to standard output, replacing
+non-printing characters with printable equivalents. Control characters print as
+a carat ('^') followed by the character '@' through '_' corresponding to the
+character replaced (e.g. control-X becomes '^X'). The delete character (0x7F)
+becomes '^?'. Characters with the high bit set (>127) are printed as 'M-'
 followed by the graphical representation for the same character without the
 high bit set.
-.PP
-The
-.B -e
-option prints a currency sign ('$') before each line ending.
-.PP
-The
-.B -t
-option prints tab characters as "^I" rather than a literal horizontal tab.
+.\"
+.SH OPTIONS
 
+.IP \fB-e\fP
+Prints a dollar sign ('$') before each newline.
+.IP \fB-t\fP
+Prints tab characters as '^I' rather than a literal horizontal tab.
+.\"
 .SH DIAGNOSTICS
 
-Npc prints a debug message and exits with the appropriate sysexits(3) error
-code in the event of an error, otherwise it exits successfully.
-
+In the event of an error, a debug message will be printed and the program will
+exit with the appropriate
+.BR sysexits.h (3)
+error code.
+.\"
 .SH BUGS
 
-Npc operates in single-byte chunks regardless of intended encoding.
-
+The program operates in single-byte chunks regardless of intended encoding.
+.\"
 .SH RATIONALE
 
 POSIX currently lacks a way to display non-printing characters in the terminal
-using a standard tool. A popular extension to cat(1p), the -v option, is the
-bandage solution GNU and other software suites use.
-
-This functionality should be a separate tool because its usefulness extends
-beyond that of cat(1p).
+using a standard tool. A popular extension to
+.BR cat (1p),
+the
+.B -v
+option, is the bandage solution GNU and other software suites use.
 
+This functionality is included in a separate tool because its usefulness extends
+beyond that of
+.BR cat (1p).
+.\"
 .SH AUTHOR
 
-Written by DTB <trinity@trinity.moe>.
-
+Written by DTB
+.MT trinity@trinity.moe
+.ME .
+.\"
 .SH COPYRIGHT
 
 Copyright © 2023 DTB. License AGPLv3+: GNU AGPL version 3 or later
 <https://gnu.org/licenses/agpl.html>.
-
+.\"
 .SH SEE ALSO
-
-cat(1p), cat-v(1)
-
+.BR cat (1p),
+.BR cat-v (1),
 .I UNIX Style, or cat -v Considered Harmful
 by Rob Pike

docs/rpn.1

@@ -3,68 +3,84 @@
 .\"
 .\" 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 rpn 1
-
+.\"
+.TH RPN 1 2024-06-17 "Harakit X.X.X"
 .SH NAME
-
 rpn \(en reverse polish notation evaluation
-
+.\"
 .SH SYNOPSIS
 
 rpn
-.RB [numbers...]\ [operators...]
-
+.RB [ numbers... ]
+.RB [ operators... ]
+.\"
 .SH DESCRIPTION
 
-Rpn evaluates reverse polish notation expressions either read from the standard
-input or parsed from provided arguments. See the STANDARD INPUT section.
+Evaluate reverse polish notation.
 
-Upon evaluation, rpn will print the resulting number on the stack to the
-standard output. Any further specified numbers will be placed at the end of the
+The program evaluates reverse polish notation expressions read either from the
+standard input or parsed from provided arguments. See the STANDARD INPUT
+section.
+
+Upon evaluation, the resulting number on the stack will be printed to the
+standard output. Any further numbers specified will be placed at the end of the
 stack.
 
-For information on for reverse polish notation syntax, see rpn(7).
-
+For information on for reverse polish notation syntax, see
+.BR rpn (7).
+.\"
 .SH STANDARD INPUT
 
-If arguments are passed to rpn, it interprets them as an expression to be
-evaluated. Otherwise, it reads whitespace-delimited numbers and operations from
+If arguments are specified, they are interpreted as an expression to be
+evaluated. Otherwise, whitespace-delimited numbers and operations are read from
 the standard input.
-
+.\"
 .SH DIAGNOSTICS
 
-If encountering a syntax error, rpn will exit with the appropriate error code
-as defined by sysexits.h(3) and print an error message.
-
+In the event of an error, a debug message will be printed and the program will
+exit with the appropriate
+.BR sysexits.h (3)
+error code; however, in the event of a syntax error, the program will print an
+error message and continue accepting input.
+.\"
 .SH CAVEATS
 
 Due to precision constraints and the way floats are represented in accordance
-with the IEEE Standard for Floating Point Arithmetic (IEEE 754), floating-point
-arithmetic has rounding errors. This is somewhat curbed by using the
-machine epsilon as provided by the Rust standard library to which to round
-numbers. Because of this, variation is expected in the number of decimal places 
-rpn can handle based on the platform and hardware of any given machine.
-
+with the
+.I IEEE Standard for Floating Point Arithmetic
+(\fIIEEE 754\fP), floating-point arithmetic has rounding errors. This is
+somewhat curbed by using the machine epsilon as provided by the Rust standard
+library to which numbers are rounded. Because of this, variation is expected in
+the number of decimal places the program can handle based on the platform and
+hardware of any given machine.
+.\"
 .SH RATIONALE
 
-An infix notation calculation utility, bc(1p), is included in the POSIX
-standard, but does not accept expressions as arguments; in scripts, any
-predefined, non-interactive input must be piped into the program. A dc(1)
-pre-dates the standardized bc(1p), the latter originally being a preprocessor
-for the former, and was included in UNIX v2 onward. While it implements reverse
-polish notation, it still suffers from being unable to accept an expression as
-an argument.
-
+An infix notation calculation utility,
+.BR bc (1p),
+is included in the POSIX standard, but does not accept expressions as arguments;
+in scripts, any predefined, non-interactive input must be piped into the
+program. A
+.BR dc (1)
+pre-dates the standardized
+.BR bc (1p),
+the latter originally being a preprocessor for the former, and was included in
+Second Edition UNIX and onward. While it implements reverse polish notation, it
+still suffers from being unable to accept an expression as an argument.
+.\"
 .SH AUTHOR
 
-Written by Emma Tebibyte <emma@tebibyte.media>.
-
+Written by Emma Tebibyte
+.MT emma@tebibyte.media
+.ME .
+.\"
 .SH COPYRIGHT
 
 Copyright (c) 2024 Emma Tebibyte. License AGPLv3+: GNU AGPL version 3 or later
 <https://gnu.org/licenses/agpl.html>.
-
+.\"
 .SH SEE ALSO
-
-bc(1p), dc(1), rpn(7), IEEE 754
+.BR bc (1p),
+.BR dc (1),
+.BR rpn (7),
+.I IEEE 754

docs/scroll.1

@@ -4,13 +4,13 @@
 .\" 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 PG 1 2024-06-26 "Harakit X.X.X"
+.TH PG 1 2024-07-31 "Harakit X.X.X"
 .SH NAME
-pg \(en paginate
+scroll \(en present output
 .\"
 .SH SYNOPSIS
 
-pg
+scroll
 .RB ( -p
 .RB [ prompt ])
 .\"

docs/scrut.1

@@ -1,93 +1,86 @@
 .\" Copyright (c) 2024 DTB <trinity@trinity.moe>
+.\" Copyright (c) 2024 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 scrut 1
-
+.\"
+.TH SCRUT 1 2024-06-06 "Harakit X.X.X"
 .SH NAME
-
 scrut \(en scrutinize file properties
-
 .SH SYNOPSIS
 
 scrut
-.RB ( -bcdefgkprsuwxLS )
-.RB [ file... ]
-
+.RB [ -LSbcdefgkprsuwx ]
+.B file...
+.\"
 .SH DESCRIPTION
 
-Scrut determines if given files comply with the opted requirements.
-
+Determine if files comply with requirements. If the given files comply with the
+specified requirements, the program will exit successfully. Otherwise, it exits
+unsuccessfully.
+.\"
 .SH OPTIONS
 
-.B -b
-requires the given files to exist and be block special files.
-.PP
-.B -c
-requires the given files to exist and be character special files.
-.PP
-.B -d
-requires the given files to exist and be directories.
-.PP
-.B -e
-requires the given files to exist, and is redundant to any other option.
-.PP
-.B -e
-requires the given files to exist and be regular files.
-.PP
-.B -g
-requires the given files to exist and have their set group ID flags set.
-.PP
-.B -k
-requires the given files to exist and have their sticky bit set.
-.PP
-.B -p
-requires the given files to exist and be named pipes.
-.PP
-.B -r
-requires the given files to exist and be readable.
-.PP
-.B -u
-requires the given files to exist and have their set user ID flags set.
-.PP
-.B -w
-requires the given files to exist and be writable.
-.PP
-.B -x
-requires the given files to exist and be executable.
-.PP
-.B -L
-requires the given files to exist and be symbolic links.
-.PP
-.B -S
-requires the given files to exist and be sockets.
+.IP \fB-L\fB
+Requires the given files to exist and be symbolic links.
+.IP \fB-S\fP
+Requires the given files to exist and be sockets.
+.IP \fB-b\fP
+Requires the given files to exist and be block special files.
+.IP \fB-c\fP
+Requires the given files to exist and be character special files.
+.IP \fB-d\fP
+Requires the given files to exist and be directories.
+.IP \fB-e\fP
+Requires the given files to exist, and is redundant to any other option.
+.IP \fB-f\fP
+Requires the given files to exist and be regular files.
+.IP \fB-g\fP
+Requires the given files to exist and have their set group ID flags set.
+.IP \fB-k\fP
+Requires the given files to exist and have their sticky bit set.
+.IP \fB-p\fP
+Requires the given files to exist and be named pipes.
+.IP \fB-r\fP
+Requires the given files to exist and be readable.
+.IP \fB-u\fP
+Requires the given files to exist and have their set user ID flags set.
+.IP \fB-w\fP
+Requires the given files to exist and be writable.
+.IP \fB-x\fP
+Requires the given files to exist and be executable.
+.\"
+.SH DIAGNOSTICS
 
-.SH EXIT STATUS
+When invoked incorrectly, a debug message will be printed and the program will
+exit with the appropriate
+.BR sysexits.h (3)
+error code.
+.\"
+.SH RATIONALE 
 
-Scrut prints a debug message and exits unsuccessfully with the appropriate
-sysexits.h(3) error code if invoked incorrectly. Scrut exits successfully if
-the given files comply with their requirements and unsuccessfully otherwise.
-
-.SH STANDARDS
-
-Scrut is nearly compatible with POSIX's test utility though it is narrower in
-scope. Notably, the
+The 
+.BR test (1p)
+utility contains functionality that was broken out into separate programs. Thus,
+the scope of this program is narrower than it. Notably, the
 .B -h
 option is now invalid and therefore shows usage information instead of being an
 alias to the modern
 .B -L
 option.
-
+.\"
 .SH AUTHOR
 
-Written by DTB <trinity@trinity.moe>.
-
+Written by DTB
+.MT trinity@trinity.moe
+.ME .
+.\"
 .SH COPYRIGHT
 
-Copyright © 2024 DTB. License AGPLv3+: GNU AGPL version 3 or later
+Copyright \(co 2024 DTB. License AGPLv3+: GNU AGPL version 3 or later
 <https://gnu.org/licenses/agpl.html>.
-
+.\"
 .SH SEE ALSO
-
-access(3p), lstat(3p), test(1p)
+.BR access (3p),
+.BR lstat (3p),
+.BR test (1p)

docs/str.1

@@ -1,58 +1,59 @@
 .\" Copyright (c) 2023–2024 DTB <trinity@trinity.moe>
-.\" Copyright (c) 2023 Emma Tebibyte <emma@tebibyte.media>
+.\" Copyright (c) 2023–2024 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
-
+.\"
+.TH STR 1 2024-06-17 "Harakit X.X.X"
 .SH NAME
-
-str \(en test the character types of string arguments
-
+str \(en test string arguments
+.\"
 .SH SYNOPSIS
 
 str
-.RB [ type ]
-.RB [ string... ]
-
+.B type string...
+.\"
 .SH DESCRIPTION
 
-Str tests each character in an arbitrary quantity of string arguments against
-the function of the same name within ctype(3).
+Test the character types of string arguments.
 
+The tests in this program are equivalent to the functions with the same names in
+.BR ctype.h (0p)
+and are the methods by which string arguments are tested.
+.\"
 .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.
+If all tests pass, the program will exit successfully. If any of the tests fail,
+the program will exit unsuccessfully with an error code of 1.
 
-.SH DEPRECATED FEATURES
+When invoked incorrectly, a debug message will be printed and the program will
+exit with the appropriate
+.BR sysexits.h (3)
+error code.
+.\"
+.SH CAVEATS
 
-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
-('').
+None of an empty string\(cqs contents pass any of the tests, so the program will
+exit unsuccessfully if one is specified.
 
-.SH BUGS
-
-There's no way of knowing which argument failed the test without re-testing
+There\(cqs 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.
 
+If a character in a string isn\(cqt valid ASCII, the program will exit
+unsuccessfully.
+.\"
 .SH AUTHOR
 
-Written by DTB <trinity@trinity.moe>.
-
+Written by DTB
+.MT trinity@trinity.moe
+.ME .
+.\"
 .SH COPYRIGHT
 
-Copyright © 2023 DTB. License AGPLv3+: GNU AGPL version 3 or later
+Copyright \(co 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)
+.BR ctype (3p),
+.BR strcmp(1),
+.BR ascii(7)

docs/strcmp.1

@@ -1,62 +1,75 @@
 .\" Copyright (c) 2023–2024 DTB <trinity@trinity.moe>
-.\" Copyright (c) 2023 Emma Tebibyte <emma@tebibyte.media>
+.\" Copyright (c) 2023–2024 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 STRCMP 1
-
+.\"
+.TH STRCMP 1 2024-07-15 "Harakit X.X.X"
 .SH NAME
-
 strcmp \(en compare strings
-
+.\"
 .SH SYNOPSIS
 
 strcmp
-.RM [ string ]
-.RB [ strings... ]
-
+.B string string...
+.\"
 .SH DESCRIPTION
 
-Strcmp checks whether the given strings are the same.
-Strcmp exits successfully if the strings are identical. Otherwise, strcmp exits
-with the value 1 if an earlier string has a greater byte value than a later
-string (e.g.
-.R strcmp b a
-)
-and 255 if an earlier string has a lesser byte value (e.g.
-.R strcmp a b
-).
-
+Check whether string arguments are the same.
+.\"
 .SH DIAGNOSTICS
 
-Strcmp will print an error message and exit unsuccessfully with a status
-described in sysexits(3) if used incorrectly (given less than two operands).
+The program will exit successfully if the strings are identical. Otherwise, it
+will exit with an error code less than 128 if a string passed has a lesser byte
+value than one of the prior strings:
 
-.SH UNICODE
+.RS
+strcmp b a
+.RE
 
-Strcmp will exit unsuccessfully if the given strings are not identical;
-Unicode strings may need to be normalized if the intent is to check visual
-similarity and not byte similarity.
+or with an error code greater than 128 if it has a greater byte value than one
+of the prior strings:
 
+.RS
+strcmp a b
+.RE
+
+When invoked incorrectly, a debug message will be printed and the program will
+exit with the appropriate
+.BR sysexits.h (3)
+error code.
+.\"
+.SH CAVEATS
+
+The program will exit unsuccessfully if the given strings are not identical;
+therefore, Unicode strings may need to be normalized if the intent is to check
+visual similarity and not byte similarity.
+.\"
 .SH RATIONALE
 
 The traditional tool for string comparisons in POSIX and other Unix shells has
-been test(1). This tool also handles integer comparisons and file scrutiny.
-These parts of its functionality have been broken out into multiple utilities.
-
-Strcmp’s functionality may be performed on a POSIX-compliant system with
-test(1p).
+been
+.BR test (1).
+This tool also handles integer comparisons and file scrutiny. These parts of its
+functionality have been broken out into multiple utilities.
 
+This program\(cqs functionality may be performed on a POSIX-compliant system
+with
+.BR test (1p).
+.\"
 .SH AUTHOR
 
-Written by DTB <trinity@trinity.moe>.
-
+Written by DTB 
+.MT trinity@trinity.moe
+.ME .
+.\"
 .SH COPYRIGHT
 
-Copyright © 2023 DTB. License AGPLv3+: GNU AGPL version 3 or later
+Copyright \(co 2023 DTB. License AGPLv3+: GNU AGPL version 3 or later
 <https://gnu.org/licenses/gpl.html>.
-
+.\"
 .SH SEE ALSO
-
-strcmp(3), intcmp(1), scrut(1), test(1p)
+.BR strcmp (3),
+.BR intcmp (1),
+.BR scrut (1),
+.BR test (1p)

docs/swab.1

@@ -1,71 +1,74 @@
 .\" Copyright (c) 2024 DTB <trinity@trinity.moe>
+.\" Copyright (c) 2024 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 swab 1
-
+.\"
+.TH SWAB 1 2024-06-17 "Harakit X.X.X"
 .SH NAME
-
 swab \(en swap bytes
-
+.\"
 .SH SYNOPSIS
 
 swab
-.RB ( -f )
-.RB ( -w
-.R [
-.B word size
-.R ])
+.RB [ -w\ word_size ]
+.\"
+.SH DESCRIPTION
 
-.SH USAGE
-
-Swab swaps the latter and former halves of a block of bytes.
+Swap the latter and former halves of a block of bytes.
+.\"
+.SH OPTIONS
 
+.IP \fB-w\fP\ \fIword_size\fP
+Configures the word size; that is, the size in bytes of the block size on which
+to operate. The default word size is 2. The word size must be cleanly divisible
+by 2, otherwise the block of bytes being processed can\(cqt be halved.
+.\"
 .SH EXAMPLES
 
-The following sh(1p) line:
+The following
+.BR sh (1p)
+line:
 
-.R printf 'hello world!\n' | swab
+.RS
+printf 'hello world!\(rsn' | swab
+.RE
 
 Produces the following output:
 
-.R ehll oowlr!d
-
-.SH OPTIONS
-
-The
-.B -f
-option ignores system call interruptions.
-.PP
-The
-.B -w
-option configures the word size; that is, the size in bytes of the block size
-on which to operate. By default the word size is 2. The word size must be
-cleanly divisible by 2, otherwise the block of bytes being processed can't be
-halved.
-
+.RS
+ehll oowlr!d
+.RE
+.\"
 .SH DIAGNOSTICS
 
-If an error is encountered in input, output, or invocation, a diagnostic
-message will be written to standard error and swab will exit with the
-appropriate status from sysexits.h(3).
-
+In the event of an error, a debug message will be printed and the program will
+exit with the appropriate
+.BR sysexits.h (3)
+error code.
+.\"
 .SH RATIONALE
 
-Swab was modeled after the
-.R conv=swab
-functionality specified in the POSIX dd utility but additionally allows the
-word size to be configured.
-.PP
-Swab is useful for fixing the endianness of binary files produced on other
-machines.
+This program was modeled and named after the
+.B conv=swab
+functionality specified
+in the
+.BR dd (1p)
+utility. It additionally allows the word size to be configured.
 
+This functionality is useful for fixing the endianness of binary files produced
+on other machines.
+.\"
+.SH AUTHOR
+
+Written by DTB
+.MT trinity@trinity.moe
+.ME .
+.\"
 .SH COPYRIGHT
 
-Copyright (c) 2024 DTB. License AGPLv3+: GNU AGPL version 3 or later
+Copyright \(co 2024 DTB. License AGPLv3+: GNU AGPL version 3 or later
 <https://gnu.org/licenses/agpl.html>.
-
+.\"
 .SH SEE ALSO
-
-dd(1p)
+.BR dd (1p)

docs/true.1

@@ -1,35 +1,36 @@
 .\" Copyright (c) 2022, 2024 DTB <trinity@trinity.moe>
-.\" Copyright (c) 2023 Emma Tebibyte <emma@tebibyte.media>
+.\" Copyright (c) 2023–2024 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 TRUE 1
-
+.\"
+.TH TRUE 1 2024-06-06 "Harakit X.X.X"
 .SH NAME
-
 true \(en do nothing, successfully
-
+.\"
 .SH DESCRIPTION
 
-True does nothing regardless of operands or standard input.
-True will always return an exit code of 0.
-
+Do nothing regardless of operands or standard input. An exit code of 0 will
+always be returned.
+.\"
 .SH RATIONALE
 
-True exists for the construction of control flow and loops based on a success.
-
-True functions as described in POSIX.1-2017.
-
+In \fIPOSIX.1-2017\fP,
+.BR true (1p)
+exists for the construction of control flow and loops based on a success. This
+implementation functions as described in that standard.
+.\"
 .SH AUTHOR
 
-Written by Emma Tebibyte <emma@tebibyte.media>.
-
+Written by Emma Tebibyte
+.MT emma@tebibyte.media
+.ME .
+.\"
 .SH COPYRIGHT
 
 This work is marked with CC0 1.0. To see a copy of this license, visit
 <http://creativecommons.org/publicdomain/zero/1.0>.
-
+.\"
 .SH SEE ALSO
-
-false(1p)
+.BR false (1p),
+.BR true (1p)

src/dj.c

@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2024 DTB <trinity@trinity.moe>
+ * Copyright (c) 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
@@ -16,437 +17,403 @@
  * along with this program. If not, see https://www.gnu.org/licenses/.
  */
 
-#include <ctype.h> /* isupper(3), tolower(3) */
+#include <assert.h> /* assert(3) */
 #include <errno.h> /* errno */
 #include <fcntl.h> /* open(2) */
+#include <stdbool.h> /* bool */
 #include <stdio.h> /* fprintf(3), stderr */
-#include <stdlib.h> /* free(3), malloc(3), strtol(3), size_t */
+#include <stdlib.h> /* malloc(3), strtol(3), size_t */
 #include <string.h> /* memcpy(3), memmove(3), memset(3) */
-#include <sysexits.h> /* EX_OK, EX_USAGE */
+#include <sysexits.h> /* EX_OK, EX_OSERR, EX_USAGE */
 #include <unistd.h> /* close(2), getopt(3), lseek(2), read(2), write(2),
                      * optarg, optind, STDIN_FILENO, STDOUT_FILENO */
-extern int errno;
+#include <sys/stat.h> /* S_IRGRP, S_IROTH, S_IRUSR, S_IWGRP, S_IWOTH, S_IWUSR */
+
+char *program_name = "dj";
 
 /* dj uses two structures that respectively correspond to the reading and
  * writing ends of its jockeyed "pipe". User-configurable members are noted
  * with their relevant options. */
-struct Io{
-	int bs;			/* buffer size (-bB) */
+struct Io {
+	char *buf;      /* buffer */
+	char *fn;       /* file name (-io) */
+	size_t bs;    	/* buffer size (-bB) */
 	size_t bufuse;	/* buffer usage */
-	char *buf;		/* buffer */
-	int bytes;		/* bytes processed */
-	int fd;			/* file descriptor */
-	int fl;			/* file opening flags */
-	char *fn;		/* file name (may be stdin_name or stdout_name) (-io) */
-	int prec;		/* partial records processed */
-	int rec;		/* records processed */
-	long seek;		/* bytes to seek/skip (will be 0 after skippage) (-sS) */
-} ep[2]; /* "engineered pipe"; also "extended play", for the deejay */
+	size_t bytes; 	/* bytes processed */
+	size_t prec;  	/* partial records processed */
+	size_t rec;   	/* records processed */
+	long seek;  	/* remaining bytes to seek/skip (-sS) */
+	int error;  	/* errno */
+	int fd;         /* file descriptor */
+	int fl;         /* file opening flags */
+};
 
-/* Additionally, the following global variables are used to store user options.
- */
-
-/* (-a)  */ static int align; /* Only the lower 8b are used but align is
-                               * negative if no alignment is being done. */
-
-/* (-c)  */ static int count; /* 0 if dj(1) runs until no more reads are
-                               * possible. */
-
-/* ASCII field separator delimited statistics */
-            static char *fmt_asv   = "%d\037%d\036%d\037%d\035%d\036%d\034";
-/* human-readable statistics */
-            static char *fmt_human = "%d+%d > %d+%d; %d > %d\n";
-/* pointer to chosen formatting */
-/* (-H)  */ static char *fmt_output; /* fmt_asv (default) or fmt_human (-H) */
-
-/* (-dq) */ static char debug;       /*
- *  -d  increments             dj -qq | 0 - no diagnostic output whatsoever
- *   -q decrements             dj -q  | 1 - typical output without
- *                                    |     notifications on partial reads or
- *                                    |     writes
- *                             dj     | 2 - typical output (default)
- *                             dj -d  | 3 - verbose status messages */
-
-/* (-n)  */ static char noerror;     /* 0 - exits on partial reads or writes
-                                      *     (default)
-                                      * 1 - retries on partial reads/writes
-                                      *     (-n) */
-
-/* Non-configurable defaults. */
-#define bs_default 1024 /* GNU dd(1) default; twice POSIX but a neat 2^10 */
-static char *program_name = "<no argv[0]>";
 static char *stdin_name = "<stdin>";
 static char *stdout_name = "<stdout>";
-static int read_flags = O_RDONLY; /* These flags are consistent with Busybox */
-static int write_flags = O_WRONLY | O_CREAT; /* dd(1). */
 
-/* Macro to set defaults for user-configurable options. */
-#define setdefaults do{ \
-	align = -1; \
-	count = 0; \
-	debug = 2; \
-	fmt_output = fmt_asv; \
-	noerror = 0; \
-	ep[0].fl = read_flags; \
-	Io_setdefaults(&ep[0]); \
-	ep[1].fl = write_flags; \
-	Io_setdefaults(&ep[1]); }while(0)
+static int creat_mode = S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH
+	| S_IWOTH; /* Consistent with touch(1p). */
+static int read_flags = O_RDONLY; /* Consistent with Busybox dd(1). */
+static int write_flags = O_WRONLY | O_CREAT;
 
 #define MIN(a, b) (((a) < (b)) ? (a) : (b))
 
-/* Macro to check if fd is a std* file, e.g. stdin. */
-#define fdisstd(fd) \
-		((fd) == STDIN_FILENO \
-		|| (fd) == STDOUT_FILENO \
-		|| (fd) == STDERR_FILENO)
+/* Macro to check if fd is stdin or stdout */
+#define fdisstd(fd) ((fd) == STDIN_FILENO || (fd) == STDOUT_FILENO)
 
-/* Macro to call the cleanup functions that operate on struct io on the
- * particular io[2] used in main. Error conditions are not checked because this
- * is only used when the program is about to terminate (hence its name). */
-#define terminate(io) do{ \
-	Io_buffree(&(io)[0]); \
-	Io_buffree(&(io)[1]); \
-	Io_fdclose(&(io)[0]); \
-	Io_fdclose(&(io)[1]); }while(0)
-
-/* Allocates *io's buffer. Returns NULL if unsuccessful. */
-static void *
-Io_bufalloc(struct Io *io){
-
-	return (io->buf = malloc(io->bs * (sizeof *io->buf)));
-}
-
-/* Frees *io's buffer. Returns io. */
+/* Completes one Io block read */
 static struct Io *
-Io_buffree(struct Io *io){
-
-	free(io->buf);
-
-	return io;
-}
-
-/* Fills the unused portion of io's buffer with padding, updating io->bufuse.
- * Returns io. */
-static struct Io *
-Io_bufrpad(struct Io *io, int padding){
-	
-	memset(io->buf + io->bufuse, padding, io->bs - io->bufuse);
-	io->bufuse = io->bs;
-
-	return io;
-}
-
-/* Copies from the buffer in src as much as possible to the free space in the
- * dest buffer, removing the copied units from src and permuting the remaining
- * units in the src buffer to the start of the buffer, modifying both the src
- * and dest bufuse and returning dest. */
-static struct Io*
-Io_bufxapp(struct Io *dest, struct Io *src){
-	int n;
-
-	n = MIN(src->bufuse, dest->bs - dest->bufuse);
-	memcpy(dest->buf + dest->bufuse, src->buf, n);
-	dest->bufuse += n;
-	memmove(src->buf, src->buf + n, src->bs - n);
-	src->bufuse -= n;
-
-	return dest;
-}
-
-/* Copies from the buffer in src to the buffer in dest no more than n units,
- * removing the copied units from src and permuting the remaining units in the
- * src buffer to the start of the buffer, modifying both the src and dest
- * bufuse and returning dest. */
-static struct Io*
-Io_bufxfer(struct Io *dest, struct Io *src, int n){
-
-	memcpy(dest->buf, src->buf, (dest->bufuse = n));
-	memmove(src->buf, src->buf + n, (src->bufuse -= n));
-
-	return dest;
-}
-
-/* Closes io->fn and returns -1 on error, otherwise io->fd. */
-static int
-Io_fdclose(struct Io *io){
-
-	return fdisstd(io->fd)
-		? 0
-		: close(io->fd);
-}
-
-/* Opens io->fn and saves the file descriptor into io->fd. Returns io->fd,
- * which will be -1 if an error occured. */
-static int
-Io_fdopen(struct Io *io, char *fn){
-	int fd;
-	
-	if((fd = open(fn, io->fl,
-					/* these are the flags used by touch(1p) */
-					S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH))
-				!= -1
-			&& Io_fdclose(io) == 0){
-		io->fd = fd;
-		io->fn = fn;
-	}
-
-	return fd;
-}
-
-/* Seeks io->seek bytes through *io's file descriptor, (counter-intuitively)
- * returning -1 if successful and a sysexits.h exit code if an unrecoverable
- * error occurred. io->buf will be cleared of useful bytes and io->seek will
- * be set to zero to indicate the seek occurred. */
-static int
-Io_fdseek(struct Io *io){
-	int (*op)(int, void *, size_t);
-	
-	if(!fdisstd(io->fd) && lseek(io->fd, io->seek, SEEK_SET) != -1)
-		return -1;
-
-	/* repeated code to get the condition out of the loop */
-	if(io->fl == write_flags){
-		memset(io->buf, '\0', io->bs);
-		/* We're going to cheat and use bufuse as the retval for write(2),
-		 * which is fine because it'll be zeroed as this function returns
-		 * anyway. */
-		do{
-			if((io->bufuse = write(io->fd, io->buf, MIN(io->bs, io->seek)))
-					== 0)
-				/* second chance */
-				io->bufuse = write(io->fd, io->buf, MIN(io->bs, io->seek));
-		}while((io->seek -= io->bufuse) > 0 && io->bufuse != 0);
-	}else if(io->fl == read_flags){
-		do{
-			if((io->bufuse = read(io->fd, io->buf, MIN(io->bs, io->seek)))
-					== 0)
-				/* second chance */
-				io->bufuse = read(io->fd, io->buf, MIN(io->bs, io->seek));
-		}while((io->seek -= io->bufuse) > 0 && io->bufuse != 0);
-	}else
-		return EX_SOFTWARE;
-
-	io->bufuse = 0;
-
-	return -1;
-}
-
-/* Reads io->bs bytes from *io's file descriptor into io->buf, storing the
- * number of read bytes in io->bufuse and updating io->bytes. If io->bufuse is
- * 0, errno will probably be set. Returns io. */
-static struct Io *
-Io_read(struct Io *io){
-
-	io->bytes += (io->bufuse = read(io->fd, io->buf, io->bs));
-
-	return io;
-}
-
-/* Sets the variables in a struct *io to the defaults. Identifies the read/
- * write ends of the "pipe" by checking io->fl. Returns io. */
-static struct Io *
-Io_setdefaults(struct Io *io){
-
-	io->bs = bs_default;
-	io->buf = NULL;
-	io->bytes = 0;
-	io->fd = (io->fl == read_flags) ? STDIN_FILENO : STDOUT_FILENO;
-	io->fn = (io->fl == read_flags) ? stdin_name   : stdout_name;
-	io->prec = 0;
-	io->rec = 0;
-	io->seek = 0;
-
-	return io;
-}
-
-/* Writes io->bufuse units from io->buf to io->fd, permuting any unwritten
- * bytes to the start of io->buf and updating io->bufuse. If io->bufuse doesn't
- * change, errno will probably be set. Returns io. */
-static struct Io *
-Io_write(struct Io *io){
+Io_read(struct Io *io) {
 	int t;
 
-	if((t = write(io->fd, io->buf, io->bufuse)) > 0)
-		memmove(io->buf, io->buf + t, (io->bufuse -= t));
-	io->bytes += t;
+	assert(io->bs > 0);
+	assert(io->bufuse < io->bs);
+
+	if ((t = read(io->fd, &(io->buf)[io->bufuse], io->bs - io->bufuse)) < 0) {
+		io->error = errno;
+		t = 0;
+	}
+
+	io->bufuse += t;
+	io->bytes  += t;
+	io->prec   += (0 < io->bufuse && io->bufuse < io->bs);
+	io->rec    += (io->bufuse == io->bs);
+
+	assert(io->bufuse <= io->bs);
 
 	return io;
 }
 
-/* Prints an error message suitable for the event of an operating system error,
- * with the error itself to be described in the string s. */
-static int
-oserr(char *s){
+/* Completes one Io block write */
+static struct Io *
+Io_write(struct Io *io) {
+	int t;
 
-	fprintf(stderr, "%s: %s: %s\n", program_name, s, strerror(errno));
+	assert(io->bufuse > 0);
+	assert(io->bufuse <= io->bs);
+
+	if ((t = write(io->fd, io->buf, io->bufuse)) < 0) {
+		io->error = errno;
+		t = 0;
+	} else if (t > 0) {
+		(void)memmove(io->buf, &(io->buf)[t], (io->bufuse -= t));
+	}
+
+	io->bytes += t;
+	io->prec  += (t > 0 && io->bufuse > 0);
+	io->rec   += (t > 0 && io->bufuse == 0);
+
+	return io;
+}
+
+static int
+oserr(char *e, int n) {
+	(void)fprintf(stderr, "%s: %s: %s\n", program_name, e, strerror(n));
 
 	return EX_OSERR;
 }
 
 /* Prints statistics regarding the use of dj, particularly partially and
- * completely read and written records, accessing debug, ep, and fmt_output. */
-static void
-output(void){
-
-	if(debug >= 1)
-		fprintf(stderr, fmt_output,
-			ep[0].rec, ep[0].prec, ep[1].rec, ep[1].prec,
-			ep[0].bytes, ep[1].bytes);
-
-	return;
+ * completely read and written records. */
+static int
+fprintio(FILE *stream, char *fmt, struct Io io[2]) {
+	return fprintf(
+		stream,
+		fmt,
+		io[0].rec,
+		io[0].prec,
+		io[1].rec,
+		io[1].prec,
+		io[0].bytes,
+		io[1].bytes
+	);
 }
 
+/* To be assigned to main:fmt and used with printio(). */
+static char *fmt_asv =
+	"%d" /* io[0].rec   */ "\037" /* ASCII US */
+	"%d" /* io[0].prec  */ "\036" /* ASCII RS */
+	"%d" /* io[1].rec   */ "\037" /* ASCII US */
+	"%d" /* io[1].prec  */ "\035" /* ASCII GS */
+	"%d" /* io[0].bytes */ "\036" /* ASCII RS */
+	"%d" /* io[1].bytes */ "\034" /* ASCII FS */
+	"\n"
+;
+static char *fmt_human = "%d+%d > %d+%d; %d > %d\n";
+
 /* Parses the string s to an integer, returning either the integer or in the
  * case of an error a negative integer. This is used for argument parsing
  * (e.g. -B [int]) in dj and no negative integer would be valid anyway. */
 static long
-parse(char *s){
+parse(char *s) {
 	long r;
 
 	errno = 0;
 	r = strtol(s, &s, 0);
-	return (*s == '\0' /* no chars left unparsed */ && errno == 0)
-		? r
-		: -1;
+	return (*s == '\0' /* no chars left unparsed */ && errno == 0) ? r : -1;
 }
 
 static int
-usage(void){
-
-	fprintf(stderr, "Usage: %s (-AdfHqQ) (-a [byte]) (-c [count])\n"
-		"\t(-i [input file]) (-b [input block size]) (-s [input offset])\n"
-		"\t(-o [output file]) (-B [output block size]) (-S [output offset])\n",
-		program_name);
+usage(char *argv0) {
+	(void)fprintf(
+		stderr,
+		"Usage: %s [-Hn] [-a byte] [-c count]\n"
+		"\t[-i file] [-b block_size] [-s offset]\n"
+		"\t[-o file] [-B block_size] [-S offset]\n",
+		argv0
+	);
 
 	return EX_USAGE;
 }
 
-int main(int argc, char *argv[]){
-	int c;
-	int i;
+int main(int argc, char *argv[]) {
+   	int align;    /* low 8b used, negative if no alignment is being done */
+	int count;    /* -1 if dj(1) runs until no more reads are possible */
+	char *fmt;    /* set to fmt_asv (default) or fmt_human (-H) */
+	size_t i;     /* side of io (in or out) being modified */
+	bool retry;   /* false if exits on partial reads or writes */
+	struct Io io[2 /* { in, out } */];
 
-	setdefaults;
+	/* Set defaults. */
+	align = -1;
+	count = -1;
+	fmt = fmt_asv;
+	retry = 0;
+	for (i = 0; i < (sizeof io) / (sizeof *io); ++i) {
+		io[i].bs = 1024 /* 1 KiB */; /* GNU dd(1) default; POSIX says 512B */
+		io[i].bufuse = 0;
+		io[i].bytes = 0;
+		io[i].fd = i == 0 ? STDIN_FILENO : STDOUT_FILENO;
+		io[i].fn = i == 0 ? stdin_name   : stdout_name;
+		io[i].fl = i == 0 ? read_flags   : write_flags;
+		io[i].error = 0;
+		io[i].prec = 0;
+		io[i].rec = 0;
+		io[i].seek = 0;
+	}
+
+	if (argc > 0) {
+		int c;
 
-	if(argc > 0){
 		program_name = argv[0];
-		while((c = getopt(argc, argv, "a:Ab:B:c:di:hHnqs:S:o:")) != -1)
-			switch(c){
-			case 'i': case 'o':
-				i = (c == 'o');
-				if(optarg[0] == '-' && optarg[1] == '\0'){ /* optarg == "-" */
-					ep[i].fd = (i == 0) ? STDIN_FILENO : STDOUT_FILENO;
-					ep[i].fn = (i == 0) ? stdin_name   : stdout_name;
-					break;
-				}else if(Io_fdopen(&ep[i], optarg) != -1)
-					break;
-				terminate(ep);
-				return oserr(optarg);
-			case 'A': align = '\0'; break;
-			case 'd': ++debug; break;
-			case 'n': noerror = 1; break;
-			case 'H': fmt_output = fmt_human; break;
-			case 'q': --debug; break;
-			case 'a':
-				if(optarg[0] != '\0' && optarg[1] == '\0'){
-					align = optarg[0];
-					break;
-				}
-				/* FALLTHROUGH */
-			case 'c': case 'b': case 's': case 'B': case 'S':
-				if(c == 'c' && (count = parse(optarg)) >= 0)
-					break;
-				i = isupper(c);
-				c = tolower(c);
-				if((c == 'b' && (ep[i].bs = parse(optarg)) > 0)
-						|| (c == 's' && (ep[i].seek = parse(optarg)) >= 0))
-					break;
-				/* FALLTHROUGH */
-			default:
-				terminate(ep);
-				return usage();
+		while ((c = getopt(argc, argv, "a:b:B:c:i:hHns:S:o:")) != -1) {
+			switch (c) {
+				case 'i': case 'o': /* input, output */
+					i = (c == 'o');
+
+					/* optarg == "-" (stdin/stdout) */
+					if (optarg[0] == '-' && optarg[1] == '\0') { 
+						io[i].fd = i == 0 ? STDIN_FILENO : STDOUT_FILENO;
+						io[i].fn = i == 0 ? stdin_name   : stdout_name;
+						break;
+					} else {
+						int fd;
+
+						if (
+							(fd = open(optarg, io[i].fl, creat_mode)) != -1
+							&& (fdisstd(io[i].fd) || close(io[i].fd) == 0)
+						) {
+							io[i].fd = fd;
+							io[i].fn = optarg;
+							break;
+						}
+					}
+
+					return oserr(optarg, errno);
+					/* UNREACHABLE */
+				case 'n': retry = 1; break; /* retry failed reads once */
+				case 'H': fmt = fmt_human; break; /* human-readable output */
+				case 'a': /* input buffer padding */
+					if (optarg[0] == '\0' || optarg[1] == '\0') {
+						align = optarg[0];
+						break;
+					}
+					/* FALLTHROUGH */
+				case 'c': /* number of reads */
+				case 'b': case 'B': /* input/output block size */
+				case 's': case 'S': /* (s)kip/(S)eek in input/output */
+					if (c == 'c' && (count = parse(optarg)) >= 0) { break; }
+
+					i = (c >= 'A' && c <= 'Z');
+					c |= 0x20; /* 0b 0010 0000 (ASCII) make lowercase */
+
+					if ( /* if -b or -s is parsed out correctly */
+						(c == 'b' && (io[i].bs = parse(optarg)) > 0)
+						|| (c == 's' && (io[i].seek = parse(optarg)) >= 0)
+					) { break; } /* don't error */
+
+					/* FALLTHROUGH */
+				default:
+					return usage(program_name);
 			}
+		}
 	}
 
-	if(debug >= 3)
-		fprintf(stderr,
-			"argv0=%s\n"
-			"in=%s\tibs=%d\tskip=%ld\talign=%hhx\tcount=%d\n"
-			"out=%s\tobs=%d\tseek=%ld\tdebug=%2d\tnoerror=%d\n",
-			program_name,
-			ep[0].fn, ep[0].bs, ep[0].seek, align, count,
-			ep[1].fn, ep[1].bs, ep[1].seek, debug, noerror);
+	assert(io->fd != STDIN_FILENO  || io->fl == read_flags);
+	assert(io->fd != STDOUT_FILENO || io->fl == write_flags);
 
-	if(argc > optind){
-		terminate(ep);
-		return usage();
-	}
+	if (argc > optind) { return usage(program_name); }
 
-	for(i = 0; i <= 1; ++i){
-		if(Io_bufalloc(&ep[i]) == NULL){
-			fprintf(stderr, "%s: Failed to allocate %d bytes\n",
-				program_name, ep[i].bs);
-			terminate(ep);
+	for (i = 0; i < (sizeof io) / (sizeof *io); ++i) {
+		/* buffer allocation */
+		if ((io[i].buf = malloc(io[i].bs * (sizeof *(io[i].buf)))) == NULL) {
+			(void)fprintf(
+				stderr, "%s: Failed to allocate %zd bytes\n",
+				program_name, io[i].bs
+			);
 			return EX_OSERR;
-		}else if(ep[i].seek > 0)
-			switch(Io_fdseek(&ep[i])){
-			case EX_OK:
-				output();
-				terminate(ep);
-				return EX_OK;
-			}
+		}
+
+		/* easy seeking */
+		if (!fdisstd(io[i].fd) && lseek(io[i].fd, io[i].seek, SEEK_SET) != -1) {
+			io[i].seek = 0;
+		}
 	}
 
-	do{	/* read */
-		Io_read(&ep[0]);
-		if(!noerror && ep[0].bufuse == 0)
-			Io_read(&ep[0]); /* second chance */
-		if(ep[0].bufuse == 0) /* that's all she wrote */
-			break;
-		else if(ep[0].bufuse < ep[0].bs){
-			++ep[0].prec;
-			if(debug >= 2){
-				fprintf(stderr, "%s: Partial read:\n\t", program_name);
-				output();
+	assert(io[1].bufuse == 0); /* requirement for hard seeking */
+
+	/* hard seeking; t is io[1].bufuse, before Io_write subtracts from it */
+	for(size_t t; io[1].seek > 0; io[1].seek -= (t - io[1].bufuse)) {
+		(void)memset(
+			io[1].buf, '\0', /* set buf to all nulls */
+			(t = io[1].bufuse = MIN(io[1].bs, io[1].seek)) /* saturate block */
+		);
+
+		if (Io_write(&io[1])->bufuse == t && !retry && io[1].error == 0) {
+			(void)Io_write(&io[1]); /* second chance */
+		}
+
+		if (io[1].error != 0) { return oserr(io[1].fn, io[1].error); }
+
+		if (io[1].bufuse == t) { break; } /* all writes failed! */
+	}
+
+	io[1].bufuse = 0; /* reset after hard seek */
+
+	if (io[1].seek > 0) { /* hard seeking failed */
+		(void)fprintio(stderr, fmt, io);
+		return oserr(io[1].fn, errno);
+	}
+
+	for (	;
+			count == -1 || count > 0;
+			count -= (count != -1) /* decrement if counting */
+	) {
+		assert(io[0].bufuse == 0);
+
+		{ /* read */
+			long skipping;
+			size_t t;
+
+			/* hack to intentionally get a partial read from Io_read */
+			if ((skipping = MIN(io[0].seek, io[0].bs)) > 0) {
+				io[0].bufuse = io[0].bs - (size_t)skipping;
 			}
-			if(!noerror)
-				count = 1;
-			if(align >= 0)
-				Io_bufrpad(&ep[0], align);
-		}else
-			++ep[0].rec;
 
-		/* write */
-		do{	if(ep[1].bs > ep[0].bs){ /* io[1].bs > io[0].bs */
-				Io_bufxapp(&ep[1], &ep[0]);
-				if(ep[0].bs + ep[1].bufuse <= ep[1].bs && count != 1)
-					continue; /* we could write more */
-			}else
-				Io_bufxfer(&ep[1], &ep[0], MIN(ep[0].bufuse, ep[1].bs));
+			t = io[0].bufuse;
+			if (Io_read(&io[0])->bufuse == t && !retry && io[0].error == 0) {
+				(void)Io_read(&io[0]); /* second chance */
+			}
 
-			c = ep[1].bufuse;
-			Io_write(&ep[1]);
-			if(!noerror && ep[1].bufuse == c)
-				Io_write(&ep[1]); /* second chance */
-			if(c == ep[1].bufuse){ /* no more love */
-				count = 1;
-				break;
-			}else if(c > ep[1].bufuse && ep[1].bufuse > 0){
-				ep[1].prec += 1;
-				if(debug >= 2){
-					fprintf(stderr, "%s: Partial write:\n\t", program_name);
-					output();
+			assert(io[0].bufuse >= t);
+
+			if (io[0].bufuse == t) { break; } /* that's all she wrote */
+
+			if (/* t < io[0].bufuse && */ io[0].bufuse < io[0].bs) {
+				(void)fprintf(stderr, "%s: Partial read:\n\t", program_name);
+				(void)fprintio(stderr, fmt, io);
+
+				if (!retry) { count = 1; }
+
+				if (align >= 0) {
+					/* fill the rest of the ibuf with padding */
+					(void)memset(
+						&(io[0].buf)[io[0].bufuse],
+						align,
+						io[0].bs - io[0].bufuse
+					);
+
+					io->bufuse = io->bs;
 				}
-				if(!noerror)
-					count = 1;
-			}else if(ep[1].bufuse == 0 && c < ep[1].bs)
-				++ep[1].prec;
-			else
-				++ep[1].rec;
-		}while(ep[0].bufuse > 0);
-	}while(count == 0 || --count > 0);
+			}
 
-	output();
-	terminate(ep);
+			if (skipping > 0) {
+				io[0].seek -= skipping;
+				io[0].bufuse = 0;
+				count += (count != -1); /* increment if counting */
+				continue;
+			}
+		}
+
+		assert(io[0].bufuse > 0);
+
+		while (io[0].bufuse > 0) { /* write */
+			if (io[0].bs <= io[1].bs) {
+				int n;
+
+				(void)memcpy( /* saturate obuf */
+					io[1].buf, io[0].buf,
+				   (io[1].bufuse = (n = MIN(io[0].bufuse, io[1].bs)))
+				);
+
+				/* permute the copied units out of ibuf */
+				(void)memmove(io[0].buf, &(io[0].buf)[n], (io[0].bufuse -= n));
+			} else /* if(io[0].bs > io[1].bs) */ {
+				int n;
+
+				/* drain what we can from ibuf */
+				(void)memcpy(
+					&(io[1].buf)[io[1].bufuse], io[0].buf,
+				    (n = MIN(io[0].bufuse, io[1].bs - io[1].bufuse))
+				);
+				io[1].bufuse += n;
+
+				/* permute out the copied units */
+				(void)memmove(io[0].buf, &(io[0].buf)[n], io[0].bs - n);
+				io[0].bufuse -= n;
+
+				if(io[0].bs + io[1].bufuse <= io[1].bs && count != 1) {
+					continue; /* obuf not saturated - we could write more */
+				}
+			}
+
+			{ /* writes actually happen, or die */
+				size_t t;
+
+				t = io[1].bufuse;
+				if (Io_write(&io[1])->bufuse == t
+						&& !retry
+						&& io[1].error == 0) {
+					(void)Io_write(&io[1]); /* second chance */
+				}
+
+				assert(io[1].error == 0 || io[1].bufuse == t);
+				/* if the Io_writes errored, bufuse wouldn't have changed, and
+				 * the error will be reported at the end of the read/write
+				 * loop */
+
+				assert(io[1].bufuse <= t);
+
+				if (io[1].bufuse == t) { /* no more love */
+					count = 1;
+					break;
+				}
+			}
+
+			if (0 < io[1].bufuse /* && io[1].bufuse < t */) {
+				(void)fprintf(stderr, "%s: Partial write:\n\t", program_name);
+				(void)fprintio(stderr, fmt, io);
+
+				if(!retry) { count = 1; }
+			}
+		}
+	}
+
+	(void)fprintio(stderr, fmt, io);
+
+	for (i = 0; i < (sizeof io) / (sizeof *io); ++i) {
+		if (io[i].error) { return oserr(io[i].fn, io[i].error); }
+	}
 
 	return EX_OK;
 }

src/fop.rs

@@ -26,61 +26,78 @@ extern crate getopt;
 extern crate strerror;
 extern crate sysexits;
 
-use getopt::{ Opt, Parser };
+use getopt::GetOpt;
 use strerror::StrError;
 use sysexits::{ EX_DATAERR, EX_IOERR, EX_UNAVAILABLE, EX_USAGE };
 
 fn main() {
 	let argv = args().collect::<Vec<String>>();
-	let mut d = '␞';
-	let mut arg_parser = Parser::new(&argv, "d:");
+	let mut d = '\u{1E}'.to_string(); /* ASCII record separator */
+	let mut optind = 1;
 
-	while let Some(opt) = arg_parser.next() {
-		match opt {
-			Ok(Opt('d', Some(arg))) => {
-				let arg_char = arg.chars().collect::<Vec<char>>();
-				if arg_char.len() > 1 {
-					eprintln!("{}: {}: Not a character.", argv[0], arg);
-					exit(EX_USAGE);
-				} else { d = arg_char[0]; }
+	let usage = format!(
+		"Usage: {} [-d delimiter] index command [args...]",
+		argv[0],
+	);
+
+	while let Some(opt) = argv.getopt("d:") {
+		match opt.opt() {
+			Ok("d") => {
+				/* delimiter */
+				d = opt.arg().unwrap();
+				optind = opt.ind();
 			},
-			_ => {},
+			_ => {
+				eprintln!("{}", usage);
+				exit(EX_USAGE);
+			}
 		};
 	}
 
-	let index_arg = arg_parser.index();
-	let command_arg = arg_parser.index() + 1;
-
-	argv.get(command_arg).unwrap_or_else(|| {
-		eprintln!("Usage: {} [-d delimiter] index command [args...]", argv[0]);
-		exit(EX_USAGE);
-	});
-
-	let index = argv[index_arg].parse::<usize>().unwrap_or_else(|e| {
+	/* parse the specified index as a number we can use */
+	let index = argv[optind].parse::<usize>().unwrap_or_else(|e| {
 		eprintln!("{}: {}: {}", argv[0], argv[1], e);
 		exit(EX_DATAERR);
 	});
 
-	let mut buf = String::new();
-	let _ = stdin().read_to_string(&mut buf);
-	let mut fields = buf.split(d).collect::<Vec<&str>>();
+	/* index of the argv[0] for the operator command */
+	let command_arg = optind as usize + 1;
 
-	let opts = argv
+	/* argv[0] of the operator command */
+	let operator = argv.get(command_arg).unwrap_or_else(|| {
+		eprintln!("{}", usage);
+		exit(EX_USAGE);
+	});
+
+	/* read entire standard input into memory */
+	let mut buf = String::new();
+	if let Err(e) = stdin().read_to_string(&mut buf) {
+		eprintln!("{}: {}", argv[0], e.strerror());
+		exit(EX_IOERR);
+	};
+
+	/* split the buffer by the delimiter (by default, '\u{1E}') */
+	let mut fields = buf.split(&d).collect::<Vec<&str>>();
+
+	/* collect arguments for the operator command */
+	let command_args = argv
 		.iter()
 		.clone()
-		.skip(command_arg + 1)
+		.skip(command_arg + 1) /* skip the command name */
 		.collect::<Vec<&String>>();
 
-	let mut spawned = Command::new(argv.get(command_arg).unwrap())
-		.args(opts)
+	/* spawn the command to operate on the field */
+	let mut spawned = Command::new(operator)
+		.args(command_args) /* spawn with the specified arguments */
 		.stdin(Stdio::piped())
-		.stdout(Stdio::piped())
+		.stdout(Stdio::piped()) /* piped stdout to handle output ourselves */
 		.spawn()
 		.unwrap_or_else( |e| {
 			eprintln!("{}: {}: {}", argv[0], argv[command_arg], e.strerror());
 			exit(EX_UNAVAILABLE);
 		});
 
+	/* get field we want to pipe into spawned program */
 	let field = fields.get(index).unwrap_or_else(|| {
 		eprintln!(
 			"{}: {}: No such index in input",
@@ -90,9 +107,10 @@ fn main() {
 		exit(EX_DATAERR);
 	});
 
+	/* get the stdin of the newly spawned program and feed it the field val */
 	if let Some(mut child_stdin) = spawned.stdin.take() {
 		let _ = child_stdin.write_all(field.as_bytes());
-		drop(child_stdin);
+		drop(child_stdin); /* stay safe! drop your children! */
 	}
 
 	let output = spawned.wait_with_output().unwrap_or_else(|e| {
@@ -100,17 +118,27 @@ fn main() {
 		exit(EX_IOERR);
 	});
 
+	/* get the output with which the original field will be replaced */
 	let mut replace = output.stdout.clone();
 
-	if replace.pop() != Some(b'\n') { replace = output.stdout; }
+	/* pop trailing newline out if the input did not contain it */
+	if fields[index].chars().last() != Some('\n') /* no newline */
+		&& replace.pop() != Some(b'\n') { /* pop last char of replacement */
+		/* restore replacement to original command output if popped char was not
+		 * a newline */
+		replace = output.stdout;
+	}
 
+	/* convert the output of the program to UTF-8 */
 	let new_field = String::from_utf8(replace).unwrap_or_else(|e| {
 		eprintln!("{}: {}: {}", argv[0], argv[command_arg], e);
 		exit(EX_IOERR);
 	});
 
+	/* store the new field in the old fields vector */
 	fields[index] = &new_field;
 
+	/* fop it */ 
 	stdout().write_all(
 		fields.join(&d.to_string()).as_bytes()
 	).unwrap_or_else(|e| {

src/getopt-rs/error.rs

@@ -1,95 +0,0 @@
-/*
- * Copyright (c) 2023 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/.
- *
- * This file incorporates work covered by the following copyright and permission
- * notice:
- *     The Clear BSD License
- *
- *     Copyright © 2017-2023 David Wildasin
- *     All rights reserved.
- *
- *     Redistribution and use in source and binary forms, with or without
- *     modification, are permitted (subject to the limitations in the disclaimer
- *     below) provided that the following conditions are met:
- *
- *          * Redistributions of source code must retain the above copyright
- *          notice, this list of conditions, and the following disclaimer.
- *
- *          * Redistributions in binary form must reproduce the above copyright
- *          notice, this list of conditions, and the following disclaimer in the
- *          documentation and/or other materials provided with the distribution.
- *
- *          * Neither the name of the copyright holder nor the names of its
- *          contributors may be used to endorse or promote products derived from
- *          this software without specific prior written permission.
- *
- *     NO EXPRESS OR IMPLIED LICENSES TO ANY PARTY'S PATENT RIGHTS ARE GRANTED
- *     BY THIS LICENSE. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
- *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,
- *     BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
- *     FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *     HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
- *     TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- *     PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *     LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *     NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *     SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-use std::{ error, fmt };
-
-use crate::ErrorKind::{ self, * };
-
-/// A basic error type for [`Parser`](struct.Parser.html)
-#[derive(Debug, Eq, PartialEq)]
-pub struct Error {
-    culprit: char,
-    kind: ErrorKind,
-}
-
-impl Error {
-    /// Creates a new error using a known kind and the character that caused the
-	/// issue.
-    pub fn new(kind: ErrorKind, culprit: char) -> Self {
-        Self { culprit, kind }
-    }
-
-    /// Returns the [`ErrorKind`](enum.ErrorKind.html) for this error.
-    pub fn kind(self) -> ErrorKind {
-        self.kind
-    }
-}
-
-impl fmt::Display for Error {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        match self.kind {
-            MissingArgument => write!(
-				f, 
-				"option requires an argument -- {:?}",
-				self.culprit,
-			),
-            UnknownOption => write!(f, "unknown option -- {:?}", self.culprit),
-        }
-    }
-}
-
-impl error::Error for Error {
-    fn source(&self) -> Option<&(dyn error::Error + 'static)> {
-        None
-    }
-}

src/getopt-rs/errorkind.rs

@@ -1,61 +0,0 @@
-/*
- * Copyright (c) 2023 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/.
- *
- * This file incorporates work covered by the following copyright and permission
- * notice:
- *     The Clear BSD License
- *
- *     Copyright © 2017-2023 David Wildasin
- *     All rights reserved.
- *
- *     Redistribution and use in source and binary forms, with or without
- *     modification, are permitted (subject to the limitations in the disclaimer
- *     below) provided that the following conditions are met:
- *
- *          * Redistributions of source code must retain the above copyright
- *          notice, this list of conditions, and the following disclaimer.
- *
- *          * Redistributions in binary form must reproduce the above copyright
- *          notice, this list of conditions, and the following disclaimer in the
- *          documentation and/or other materials provided with the distribution.
- *
- *          * Neither the name of the copyright holder nor the names of its
- *          contributors may be used to endorse or promote products derived from
- *          this software without specific prior written permission.
- *
- *     NO EXPRESS OR IMPLIED LICENSES TO ANY PARTY'S PATENT RIGHTS ARE GRANTED
- *     BY THIS LICENSE. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
- *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,
- *     BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
- *     FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *     HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
- *     TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- *     PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *     LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *     NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *     SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-/// What kinds of errors [`Parser`](struct.Parser.html) can return.
-#[derive(Debug, Eq, PartialEq)]
-pub enum ErrorKind {
-    /// An argument was not found for an option that was expecting one.
-    MissingArgument,
-    /// An unknown option character was encountered.
-    UnknownOption,
-}

src/getopt-rs/lib.rs

@@ -1,72 +0,0 @@
-/*
- * Copyright (c) 2023 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/.
- *
- * This file incorporates work covered by the following copyright and permission
- * notice:
- *     The Clear BSD License
- *
- *     Copyright © 2017-2023 David Wildasin
- *     All rights reserved.
- *
- *     Redistribution and use in source and binary forms, with or without
- *     modification, are permitted (subject to the limitations in the disclaimer
- *     below) provided that the following conditions are met:
- *
- *          * Redistributions of source code must retain the above copyright
- *          notice, this list of conditions, and the following disclaimer.
- *
- *          * Redistributions in binary form must reproduce the above copyright
- *          notice, this list of conditions, and the following disclaimer in the
- *          documentation and/or other materials provided with the distribution.
- *
- *          * Neither the name of the copyright holder nor the names of its
- *          contributors may be used to endorse or promote products derived from
- *          this software without specific prior written permission.
- *
- *     NO EXPRESS OR IMPLIED LICENSES TO ANY PARTY'S PATENT RIGHTS ARE GRANTED
- *     BY THIS LICENSE. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
- *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,
- *     BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
- *     FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *     HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
- *     TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- *     PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *     LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *     NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *     SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-//! # getopt
-//!
-//! `getopt` provides a minimal, (essentially) POSIX-compliant option parser.
-
-pub use crate::{
-	error::Error,
-	errorkind::ErrorKind,
-	opt::Opt,
-	parser::Parser,
-	result::Result
-};
-
-mod error;
-mod errorkind;
-mod opt;
-mod parser;
-mod result;
-#[cfg(test)]
-mod tests;

src/getopt-rs/opt.rs

@@ -1,89 +0,0 @@
-/*
- * Copyright (c) 2023 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/.
- *
- * This file incorporates work covered by the following copyright and permission
- * notice:
- *     The Clear BSD License
- *
- *     Copyright © 2017-2023 David Wildasin
- *     All rights reserved.
- *
- *     Redistribution and use in source and binary forms, with or without
- *     modification, are permitted (subject to the limitations in the disclaimer
- *     below) provided that the following conditions are met:
- *
- *          * Redistributions of source code must retain the above copyright
- *          notice, this list of conditions, and the following disclaimer.
- *
- *          * Redistributions in binary form must reproduce the above copyright
- *          notice, this list of conditions, and the following disclaimer in the
- *          documentation and/or other materials provided with the distribution.
- *
- *          * Neither the name of the copyright holder nor the names of its
- *          contributors may be used to endorse or promote products derived from
- *          this software without specific prior written permission.
- *
- *     NO EXPRESS OR IMPLIED LICENSES TO ANY PARTY'S PATENT RIGHTS ARE GRANTED
- *     BY THIS LICENSE. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
- *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,
- *     BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
- *     FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *     HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
- *     TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- *     PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *     LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *     NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *     SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-use std::fmt;
-
-/// A single option.
-///
-/// For `Opt(x, y)`:
-///   - `x` is the character representing the option.
-///   - `y` is `Some` string, or `None` if no argument was expected.
-///
-/// # Example
-///
-/// ```
-/// # fn main() -> Result<(), Box<dyn std::error::Error>> {
-/// use getopt::Opt;
-///
-/// // args = ["program", "-abc", "foo"];
-/// # let args: Vec<String> = vec!["program", "-abc", "foo"]
-/// #     .into_iter()
-/// #     .map(String::from)
-/// #     .collect();
-/// let optstring = "ab:c";
-/// let mut opts = getopt::Parser::new(&args, optstring);
-///
-/// assert_eq!(Opt('a', None), opts.next().transpose()?.unwrap());
-/// assert_eq!(Opt('b', Some("c".to_string())), opts.next().transpose()?.unwrap());
-/// assert_eq!(None, opts.next().transpose()?);
-/// # Ok(())
-/// # }
-/// ```
-#[derive(Debug, Eq, Ord, PartialEq, PartialOrd)]
-pub struct Opt(pub char, pub Option<String>);
-
-impl fmt::Display for Opt {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "Opt({:?}, {:?})", self.0, self.1)
-    }
-}

src/getopt-rs/parser.rs

@@ -1,382 +0,0 @@
-/*
- * Copyright (c) 2023 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/.
- *
- * This file incorporates work covered by the following copyright and permission
- * notice:
- *     The Clear BSD License
- *
- *     Copyright © 2017-2023 David Wildasin
- *     All rights reserved.
- *
- *     Redistribution and use in source and binary forms, with or without
- *     modification, are permitted (subject to the limitations in the disclaimer
- *     below) provided that the following conditions are met:
- *
- *          * Redistributions of source code must retain the above copyright
- *          notice, this list of conditions, and the following disclaimer.
- *
- *          * Redistributions in binary form must reproduce the above copyright
- *          notice, this list of conditions, and the following disclaimer in the
- *          documentation and/or other materials provided with the distribution.
- *
- *          * Neither the name of the copyright holder nor the names of its
- *          contributors may be used to endorse or promote products derived from
- *          this software without specific prior written permission.
- *
- *     NO EXPRESS OR IMPLIED LICENSES TO ANY PARTY'S PATENT RIGHTS ARE GRANTED
- *     BY THIS LICENSE. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
- *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,
- *     BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
- *     FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *     HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
- *     TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- *     PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *     LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *     NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *     SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-use std::collections::HashMap;
-
-use crate::{ error::Error, errorkind::ErrorKind, opt::Opt, result::Result };
-
-/// The core of the `getopt` crate.
-///
-/// `Parser` is implemented as an iterator over the options present in the given
-/// argument vector.
-///
-/// The method [`next`](#method.next) does the heavy lifting.
-///
-/// # Examples
-///
-/// ## Simplified usage:
-/// ```
-/// # fn main() -> Result<(), Box<dyn std::error::Error>> {
-/// use getopt::Opt;
-///
-/// // args = ["program", "-abc", "foo"];
-/// # let args: Vec<String> = vec!["program", "-abc", "foo"]
-/// #     .into_iter()
-/// #     .map(String::from)
-/// #     .collect();
-/// let mut opts = getopt::Parser::new(&args, "ab:c");
-///
-/// assert_eq!(Some(Opt('a', None)), opts.next().transpose()?);
-/// assert_eq!(1, opts.index());
-/// assert_eq!(Some(Opt('b', Some("c".to_string()))), opts.next().transpose()?);
-/// assert_eq!(2, opts.index());
-/// assert_eq!(None, opts.next());
-/// assert_eq!(2, opts.index());
-/// assert_eq!("foo", args[opts.index()]);
-/// # Ok(())
-/// # }
-/// ```
-///
-/// ## A more idiomatic example:
-/// ```
-/// # fn main() -> Result<(), Box<dyn std::error::Error>> {
-/// use getopt::Opt;
-///
-/// // args = ["program", "-abc", "-d", "foo", "-e", "bar"];
-/// # let mut args: Vec<String> = vec!["program", "-abc", "-d", "foo", "-e", "bar"]
-/// #     .into_iter()
-/// #     .map(String::from)
-/// #     .collect();
-/// let mut opts = getopt::Parser::new(&args, "ab:cd:e");
-///
-/// let mut a_flag = false;
-/// let mut b_flag = String::new();
-/// let mut c_flag = false;
-/// let mut d_flag = String::new();
-/// let mut e_flag = false;
-///
-/// loop {
-///     match opts.next().transpose()? {
-///         None => break,
-///         Some(opt) => match opt {
-///             Opt('a', None) => a_flag = true,
-///             Opt('b', Some(arg)) => b_flag = arg.clone(),
-///             Opt('c', None) => c_flag = true,
-///             Opt('d', Some(arg)) => d_flag = arg.clone(),
-///             Opt('e', None) => e_flag = true,
-///             _ => unreachable!(),
-///         },
-///     }
-/// }
-///
-/// let new_args = args.split_off(opts.index());
-///
-/// assert_eq!(true, a_flag);
-/// assert_eq!("c", b_flag);
-/// assert_eq!(false, c_flag);
-/// assert_eq!("foo", d_flag);
-/// assert_eq!(true, e_flag);
-///
-/// assert_eq!(1, new_args.len());
-/// assert_eq!("bar", new_args.first().unwrap());
-/// # Ok(())
-/// # }
-/// ```
-#[derive(Debug, Eq, PartialEq)]
-pub struct Parser {
-    opts: HashMap<char, bool>,
-    args: Vec<Vec<char>>,
-    index: usize,
-    point: usize,
-}
-
-impl Parser {
-    /// Create a new `Parser`, which will process the arguments in `args`
-	/// according to the options specified in `optstring`.
-    ///
-    /// For compatibility with
-	/// [`std::env::args`](https://doc.rust-lang.org/std/env/fn.args.html),
-    /// valid options are expected to begin at the second element of `args`, and
-	/// `index` is
-    /// initialised to `1`.
-    /// If `args` is structured differently, be sure to call
-	/// [`set_index`](#method.set_index) before the first invocation of
-	/// [`next`](#method.next).
-    ///
-    /// `optstring` is a string of recognised option characters; if a character
-	/// is followed by a colon (`:`), that option takes an argument.
-    ///
-    /// # Note:
-    /// Transforming the OS-specific argument strings into a vector of `String`s
-	/// is the sole responsibility of the calling program, as it involves some
-	/// level of potential information loss (which this crate does not presume
-	/// to handle unilaterally) and error handling (which would complicate the
-	/// interface).
-    pub fn new(args: &[String], optstring: &str) -> Self {
-        let optstring: Vec<char> = optstring.chars().collect();
-        let mut opts = HashMap::new();
-        let mut i = 0;
-        let len = optstring.len();
-
-        while i < len {
-            let j = i + 1;
-
-            if j < len && optstring[j] == ':' {
-                opts.insert(optstring[i], true);
-                i += 1;
-            } else {
-                opts.insert(optstring[i], false);
-            }
-            i += 1;
-        }
-
-        Self {
-            opts,
-            // "explode" the args into a vector of character vectors, to allow
-			// indexing
-            args: args.iter().map(|e| e.chars().collect()).collect(),
-            index: 1,
-            point: 0,
-        }
-    }
-
-    /// Return the current `index` of the parser.
-    ///
-    /// `args[index]` will always point to the the next element of `args`; when
-	/// the parser is
-    /// finished with an element, it will increment `index`.
-    ///
-    /// After the last option has been parsed (and [`next`](#method.next) is
-	/// returning `None`),
-    /// `index` will point to the first non-option argument.
-    pub fn index(&self) -> usize {
-        self.index
-    }
-
-    // `point` must be reset to 0 whenever `index` is changed
-
-    /// Modify the current `index` of the parser.
-    pub fn set_index(&mut self, value: usize) {
-        self.index = value;
-        self.point = 0;
-    }
-
-    /// Increment the current `index` of the parser.
-    ///
-    /// This use case is common enough to warrant its own optimised method.
-    pub fn incr_index(&mut self) {
-        self.index += 1;
-        self.point = 0;
-    }
-}
-
-impl Iterator for Parser {
-    type Item = Result<Opt>;
-
-    /// Returns the next option, if any.
-    ///
-    /// Returns an [`Error`](struct.Error.html) if an unexpected option is
-	/// encountered or if an
-    /// expected argument is not found.
-    ///
-    /// Parsing stops at the first non-hyphenated argument; or at the first
-	/// argument matching "-";
-    /// or after the first argument matching "--".
-    ///
-    /// When no more options are available, `next` returns `None`.
-    ///
-    /// # Examples
-    ///
-    /// ## "-"
-    /// ```
-    /// use getopt::Parser;
-    ///
-    /// // args = ["program", "-", "-a"];
-    /// # let args: Vec<String> = vec!["program", "-", "-a"]
-    /// #     .into_iter()
-    /// #     .map(String::from)
-    /// #     .collect();
-    /// let mut opts = Parser::new(&args, "a");
-    ///
-    /// assert_eq!(None, opts.next());
-    /// assert_eq!("-", args[opts.index()]);
-    /// ```
-    ///
-    /// ## "--"
-    /// ```
-    /// use getopt::Parser;
-    ///
-    /// // args = ["program", "--", "-a"];
-    /// # let args: Vec<String> = vec!["program", "--", "-a"]
-    /// #     .into_iter()
-    /// #     .map(String::from)
-    /// #     .collect();
-    /// let mut opts = Parser::new(&args, "a");
-    ///
-    /// assert_eq!(None, opts.next());
-    /// assert_eq!("-a", args[opts.index()]);
-    /// ```
-    ///
-    /// ## Unexpected option:
-    /// ```
-    /// use getopt::Parser;
-    ///
-    /// // args = ["program", "-b"];
-    /// # let args: Vec<String> = vec!["program", "-b"]
-    /// #     .into_iter()
-    /// #     .map(String::from)
-    /// #     .collect();
-    /// let mut opts = Parser::new(&args, "a");
-    ///
-    /// assert_eq!(
-    ///     "unknown option -- 'b'".to_string(),
-    ///     opts.next().unwrap().unwrap_err().to_string()
-    /// );
-    /// ```
-    ///
-    /// ## Missing argument:
-    /// ```
-    /// use getopt::Parser;
-    ///
-    /// // args = ["program", "-a"];
-    /// # let args: Vec<String> = vec!["program", "-a"]
-    /// #     .into_iter()
-    /// #     .map(String::from)
-    /// #     .collect();
-    /// let mut opts = Parser::new(&args, "a:");
-    ///
-    /// assert_eq!(
-    ///     "option requires an argument -- 'a'".to_string(),
-    ///     opts.next().unwrap().unwrap_err().to_string()
-    /// );
-    /// ```
-    fn next(&mut self) -> Option<Result<Opt>> {
-        if self.point == 0 {
-            /*
-             * Rationale excerpts below taken verbatim from "The Open Group Base
-			 * Specifications Issue 7, 2018 edition", IEEE Std 1003.1-2017
-			 * (Revision of IEEE Std 1003.1-2008).
-             * Copyright © 2001-2018 IEEE and The Open Group.
-             */
-
-            /*
-             * 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 self.index >= self.args.len()
-                || self.args[self.index].is_empty()
-                || self.args[self.index][0] != '-'
-                || self.args[self.index].len() == 1
-            {
-                return None;
-            }
-
-            /*
-             * If:
-             *      argv[optind]    points to the string "--"
-             * getopt() shall return -1 after incrementing index.
-             */
-            if self.args[self.index][1] == '-' && self.args[self.index].len() == 2 {
-                self.incr_index();
-                return None;
-            }
-
-            // move past the starting '-'
-            self.point += 1;
-        }
-
-        let opt = self.args[self.index][self.point];
-        self.point += 1;
-
-        match self.opts.get(&opt) {
-            None => {
-                if self.point >= self.args[self.index].len() {
-                    self.incr_index();
-                }
-                Some(Err(Error::new(ErrorKind::UnknownOption, opt)))
-            }
-            Some(false) => {
-                if self.point >= self.args[self.index].len() {
-                    self.incr_index();
-                }
-
-                Some(Ok(Opt(opt, None)))
-            }
-            Some(true) => {
-                let arg: String = if self.point >= self.args[self.index].len() {
-                    self.incr_index();
-                    if self.index >= self.args.len() {
-                        return Some(Err(Error::new(
-									ErrorKind::MissingArgument,
-									opt,
-								)));
-                    }
-                    self.args[self.index].iter().collect()
-                } else {
-                    self.args[self.index]
-                        .clone()
-                        .split_off(self.point)
-                        .iter()
-                        .collect()
-                };
-
-                self.incr_index();
-
-                Some(Ok(Opt(opt, Some(arg))))
-            }
-        }
-    }
-}

src/getopt-rs/result.rs

@@ -1,59 +0,0 @@
-/*
- * Copyright (c) 2023 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/.
- *
- * This file incorporates work covered by the following copyright and permission
- * notice:
- *     The Clear BSD License
- *
- *     Copyright © 2017-2023 David Wildasin
- *     All rights reserved.
- *
- *     Redistribution and use in source and binary forms, with or without
- *     modification, are permitted (subject to the limitations in the disclaimer
- *     below) provided that the following conditions are met:
- *
- *          * Redistributions of source code must retain the above copyright
- *          notice, this list of conditions, and the following disclaimer.
- *
- *          * Redistributions in binary form must reproduce the above copyright
- *          notice, this list of conditions, and the following disclaimer in the
- *          documentation and/or other materials provided with the distribution.
- *
- *          * Neither the name of the copyright holder nor the names of its
- *          contributors may be used to endorse or promote products derived from
- *          this software without specific prior written permission.
- *
- *     NO EXPRESS OR IMPLIED LICENSES TO ANY PARTY'S PATENT RIGHTS ARE GRANTED
- *     BY THIS LICENSE. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
- *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,
- *     BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
- *     FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *     HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
- *     TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- *     PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *     LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *     NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *     SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-use std::result;
-
-use crate::error::Error;
-
-/// A specialized `Result` type for use with [`Parser`](struct.Parser.html)
-pub type Result<T> = result::Result<T, Error>;

src/getopt-rs/tests.rs

@@ -1,228 +0,0 @@
-/*
- * Copyright (c) 2023 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/.
- *
- * This file incorporates work covered by the following copyright and permission
- * notice:
- *     The Clear BSD License
- *
- *     Copyright © 2017-2023 David Wildasin
- *     All rights reserved.
- *
- *     Redistribution and use in source and binary forms, with or without
- *     modification, are permitted (subject to the limitations in the disclaimer
- *     below) provided that the following conditions are met:
- *
- *          * Redistributions of source code must retain the above copyright
- *          notice, this list of conditions, and the following disclaimer.
- *
- *          * Redistributions in binary form must reproduce the above copyright
- *          notice, this list of conditions, and the following disclaimer in the
- *          documentation and/or other materials provided with the distribution.
- *
- *          * Neither the name of the copyright holder nor the names of its
- *          contributors may be used to endorse or promote products derived from
- *          this software without specific prior written permission.
- *
- *     NO EXPRESS OR IMPLIED LICENSES TO ANY PARTY'S PATENT RIGHTS ARE GRANTED
- *     BY THIS LICENSE. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
- *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,
- *     BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
- *     FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *     HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
- *     TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- *     PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *     LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *     NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *     SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-use crate::{Opt, Parser};
-
-macro_rules! basic_test {
-    ($name:ident, $expect:expr, $next:expr, [$($arg:expr),+], $optstr:expr) => (
-        #[test]
-        fn $name() -> Result<(), String> {
-            let expect: Option<Opt> = $expect;
-            let args: Vec<String> = vec![$($arg),+]
-				.into_iter()
-				.map(String::from)
-				.collect();
-            let next: Option<String> = $next;
-            let mut opts = Parser::new(&args, $optstr);
-
-            match opts.next().transpose() {
-                Err(error) => {
-                    return Err(format!("next() returned {:?}", error))
-                },
-                Ok(actual) => if actual != expect {
-                    return Err(
-						format!("expected {:?}; got {:?}", expect, actual)
-					)
-                },
-            };
-
-            match next {
-                None => if opts.index() < args.len() {
-                    return Err(format!(
-							"expected end of args; got {:?}", args[opts.index()]
-					))
-                },
-                Some(n) => if args[opts.index()] != n {
-                    return Err(format!(
-							"next arg: expected {:?}; got {:?}",
-							n,
-							args[opts.index()]
-					))
-                },
-            };
-
-            Ok(())
-        }
-    )
-}
-
-#[rustfmt::skip] basic_test!(
-	blank_arg, None, Some(String::new()), ["x", ""], "a"
-);
-#[rustfmt::skip] basic_test!(
-	double_dash, None, Some("-a".to_string()), ["x", "--", "-a", "foo"], "a"
-);
-#[rustfmt::skip] basic_test!(no_opts_1, None, None, ["x"], "a");
-#[rustfmt::skip] basic_test!(
-	no_opts_2, None, Some("foo".to_string()), ["x", "foo"], "a"
-);
-#[rustfmt::skip] basic_test!(
-	no_opts_3, None, Some("foo".to_string()), ["x", "foo", "-a"], "a"
-);
-#[rustfmt::skip] basic_test!(
-	single_dash, None, Some("-".to_string()), ["x", "-", "-a", "foo"], "a"
-);
-#[rustfmt::skip] basic_test!(
-	single_opt,
-	Some(Opt('a', None)),
-	Some("foo".to_string()),
-	["x", "-a", "foo"],
-	"a"
-);
-#[rustfmt::skip] basic_test!(
-	single_optarg,
-	Some(Opt('a', Some("foo".to_string()))),
-	None,
-	["x", "-a", "foo"],
-	"a:"
-);
-
-macro_rules! error_test {
-    ($name:ident, $expect:expr, [$($arg:expr),+], $optstr:expr) => (
-        #[test]
-        fn $name() -> Result<(), String> {
-            let expect: String = $expect.to_string();
-            let args: Vec<String> = vec![$($arg),+]
-				.into_iter()
-				.map(String::from)
-				.collect();
-            let mut opts = Parser::new(&args, $optstr);
-
-            match opts.next() {
-                None => {
-                    return Err(format!(
-							"unexpected successful response: end of options"
-					))
-                },
-                Some(Err(actual)) => {
-                    let actual = actual.to_string();
-
-                    if actual != expect {
-                        return Err(
-							format!("expected {:?}; got {:?}", expect, actual)
-						);
-                    }
-                },
-                Some(Ok(opt)) => {
-                    return Err(
-						format!("unexpected successful response: {:?}", opt)
-					)
-                },
-            };
-
-            Ok(())
-        }
-    )
-}
-
-#[rustfmt::skip] error_test!(
-	bad_opt,
-	"unknown option -- 'b'",
-	["x", "-b"],
-	"a"
-);
-
-#[rustfmt::skip] error_test!(
-	missing_optarg,
-	"option requires an argument -- 'a'",
-	["x", "-a"],
-	"a:"
-);
-
-#[test]
-fn multiple() -> Result<(), String> {
-    let args: Vec<String> = vec!["x", "-abc", "-d", "foo", "-e", "bar"]
-        .into_iter()
-        .map(String::from)
-        .collect();
-    let optstring = "ab:d:e".to_string();
-    let mut opts = Parser::new(&args, &optstring);
-
-    macro_rules! check_result {
-        ($expect:expr) => {
-            let expect: Option<Opt> = $expect;
-            match opts.next().transpose() {
-                Err(error) => {
-					return Err(format!("next() returned {:?}", error));
-				},
-                Ok(actual) => {
-                    if actual != expect {
-                        return Err(
-							format!("expected {:?}; got {:?}", expect, actual)
-						);
-                    }
-                }
-            };
-        };
-    }
-
-    check_result!(Some(Opt('a', None)));
-    check_result!(Some(Opt('b', Some("c".to_string()))));
-    check_result!(Some(Opt('d', Some("foo".to_string()))));
-    check_result!(Some(Opt('e', None)));
-    check_result!(None);
-
-    Ok(())
-}
-
-#[test]
-fn continue_after_error() {
-    let args: Vec<String> = vec!["x", "-z", "-abc"]
-        .into_iter()
-        .map(String::from)
-        .collect();
-    let optstring = "ab:d:e".to_string();
-    for _opt in Parser::new(&args, &optstring) {
-        // do nothing, should not panic
-    }
-}

src/hru.rs

@@ -29,40 +29,45 @@ extern crate sysexits;
 use strerror::StrError;
 use sysexits::{ EX_DATAERR, EX_IOERR, EX_SOFTWARE };
 
+/* list of SI prefixes */
 const LIST: [(u32, &str); 10] = [
-	(3, "k"),
-	(6, "M"),
-	(9, "G"),
-	(12, "T"),
-	(15, "P"),
-	(18, "E"),
-	(21, "Z"),
-	(24, "Y"),
-	(27, "R"),
-	(30, "Q")
+	(3, "k"), /* kilo */
+	(6, "M"), /* mega */
+	(9, "G"), /* giga */
+	(12, "T"), /* tera */
+	(15, "P"), /* peta */
+	(18, "E"), /* exa */
+	(21, "Z"), /* zetta */
+	(24, "Y"), /* yotta */
+	(27, "R"), /* ronna */
+	(30, "Q"), /* quetta */
 ];
 
 fn convert(input: u128) -> Result<(f64, (u32, &'static str)), String> {
+	/* preserve decimal places in output by casting to a float */
+	let mut out = (input as f64, (0_u32, "")); 
 
-	let mut out = (input as f64, (0_u32, ""));
-	if input < 1000 { return Ok(out); }
+	if input < 1000 { return Ok(out); } /* too low to convert */
 
 	for (n, p) in LIST {
 		let c = match 10_u128.checked_pow(n) {
 			Some(c) => c,
-			None => {
+			None => { /* too big for the laws of computing :( */
 				return Err(format!("10^{}: Integer overflow", n.to_string()));
 			},
 		};
 
 		match c.cmp(&input) {
-			Ordering::Less => {
+			Ordering::Less => { /* c < input */
+				/* the program will keep assigning out every loop until either
+				 * the list runs out of higher prefix bases or the input is
+				 * greater than the prefix base */
 				out = (input as f64 / c as f64, (n, p));
 			},
-			Ordering::Equal => {
+			Ordering::Equal => { /* c == input */
 				return Ok((input as f64 / c as f64, (n, p)));
 			},
-			Ordering::Greater => {},
+			Ordering::Greater => {}, /* c > input */
 		};
 	}
 
@@ -72,6 +77,7 @@ fn convert(input: u128) -> Result<(f64, (u32, &'static str)), String> {
 fn main() -> ExitCode {
 	let argv = args().collect::<Vec<String>>();
 	let mut buf = String::new();
+
 	while let Ok(_) = stdin().read_line(&mut buf) {
 		if buf.is_empty() { return ExitCode::SUCCESS; }
 
@@ -96,6 +102,7 @@ fn main() -> ExitCode {
 
 		let si_prefix = format!("{}B", prefix.1);
 
+		/* round output number to one decimal place */
 		let out = ((number * 10.0).round() / 10.0).to_string();
 
 		stdout().write_all(format!("{} {}\n", out, si_prefix).as_bytes())

src/intcmp.c

@@ -1,82 +0,0 @@
-/*
- * Copyright (c) 2023 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/.
- */
-
-#include <errno.h> /* errno */
-#include <stdio.h> /* fprintf(3), stderr */
-#include <stdlib.h> /* strtol(3), size_t, EXIT_FAILURE */
-#include <unistd.h> /* getopt(3), optind */
-#include <sysexits.h>
-
-/* 0b00? */		/*                     Equal | -e  | 0b001 | 1 */
-#define EQUAL	0x01	/*                   Greater | -g  | 0b010 | 2 */
-/* 0b0?0 */		/*          Greater or Equal | -ge | 0b011 | 3 */
-#define GREATER	0x02	/*                      Less | -l  | 0b100 | 4 */
-/* 0b?00 */		/*             Less or Equal | -le | 0b101 | 5 */
-#define LESS	0x04	/* Inequal (Greater or Less) | -gl | 0b110 | 6 */
-
-static char *program_name = "intcmp";
-
-int main(int argc, char *argv[]){
-	int c;
-	size_t i;
-	unsigned char mode;
-	int r; /* reference integer */
-
-	mode = 0;
-
-	if(argc < 3)
-		goto usage;
-
-	while((c = getopt(argc, argv, "egl")) != -1)
-		switch(c){
-		case 'e': mode |= EQUAL;   break;
-		case 'g': mode |= GREATER; break;
-		case 'l': mode |= LESS;	   break;
-		default:  goto usage;
-		}
-
-	if(optind + 2 /* ref cmp */ > argc){
-usage:		fprintf(stderr,
-			"Usage: %s (-eghl) [integer] [integer...]\n",
-			argv[0] == NULL ? program_name : argv[0]);
-		return EX_USAGE;
-	}
-
-	i = optind;
-
-	do{	r = c;
-		c = strtol(argv[i], &argv[i], 10);
-		if(*argv[i] != '\0' || errno != 0){
-			fprintf(stderr, "%s: argument #%d: Invalid integer\n",
-				argv[0], (int)i);
-			return EX_USAGE;
-		}
-
-		if(i == optind)
-			continue;
-
-		/* rule enforcement; if a mode isn't permitted and the numbers
-		 * correspond to it, return 1 */
-		if(		(!(mode & EQUAL) && r == c)
-				|| (!(mode & GREATER) && r > c)
-				|| (!(mode & LESS) && r < c))
-			return 1;
-	}while(++i < argc);
-	
-	return 0;
-}

src/intcmp.rs

@@ -0,0 +1,79 @@
+/*
+ * Copyright (c) 2023–2024 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
+};
+
+extern crate getopt;
+use getopt::GetOpt;
+
+extern crate sysexits;
+use sysexits::EX_USAGE;
+
+fn usage(s: &str) -> ExitCode {
+	eprintln!("Usage: {} [-egl] integer integer...", s);
+	ExitCode::from(EX_USAGE as u8)
+}
+
+fn main() -> ExitCode {
+	let argv = args().collect::<Vec<String>>();
+	let mut e = false; /* args can be == */
+	let mut g = false; /* args can be > */
+	let mut l = false; /* args can be < */
+	let mut optind = 0;
+
+	if argv.len() < 3 { return usage(&argv[0]); }
+
+	while let Some(opt) = argv.getopt("egl") {
+		match opt.opt() {
+			Ok("e") => e = true,
+			Ok("g") => g = true,
+			Ok("l") => l = true,
+			_ => { return usage(&argv[0]); },
+		}
+		optind = opt.ind();
+	}
+
+	if argv.len() - optind < 2 /* see usage */ { return usage(&argv[0]); }
+
+	let mut prev: Option<usize> = None; /* no previous operand */
+	let mut currn: usize;
+
+	for arg in argv.iter().skip(optind) { /* iterate operands */
+		match arg.parse::<usize>() { /* parse current operand */
+			Ok(n) => currn = n,
+			_ => {
+				eprintln!("{}: {}: Invalid integer", &argv[0], arg);
+				return ExitCode::from(EX_USAGE as u8);
+			}
+		}
+
+		if let Some(prevn) = prev { /* if there was a previous opr., test */
+			if (!e && prevn == currn)
+					|| (!g && prevn > currn)
+					|| (!l && prevn < currn)
+				{ return ExitCode::FAILURE; }
+		}
+
+		prev = Some(currn); /* there is a previous operand */
+	}
+
+	ExitCode::SUCCESS
+}

src/libgetopt.rs

@@ -0,0 +1,202 @@
+/*
+ * 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);
+		}
+	}
+}

src/mm.c

@@ -1,224 +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/.
- */
-
-#include <errno.h> /* errno */
-#include <signal.h> /* signal(2), SIG_ERR, SIG_IGN, SIGINT */
-#include <stdio.h> /* fclose(3), fopen(3), fprintf(3), getc(3), putc(3),
-                    * setvbuf(3), size_t, _IONBF, NULL */
-#include <stdlib.h> /* free(3), realloc(3) */
-#include <string.h> /* strcmp(3), strerror(3) */
-#include <unistd.h> /* getopt(3) */
-#if !defined EX_IOERR || !defined EX_OK || !defined EX_OSERR \
-		|| !defined EX_USAGE
-#	include <sysexits.h>
-#endif
-extern int errno;
-
-/* This structure is how open files are tracked. */
-struct Files{
-	size_t a;	/* allocation */
-	size_t s;	/* used size */
-	char *mode;	/* file opening mode */
-	char **names;	/* file names */
-	FILE **files;	/* file pointers */
-};
-
-/* How much to grow the allocation when it's saturated. */
-#ifndef ALLOC_INCREMENT
-#	define ALLOC_INCREMENT 1
-#endif
-
-/* How much to grow the allocation at program start. */
-#ifndef ALLOC_INITIAL
-#	define ALLOC_INITIAL 10
-#endif
-
-/* pre-allocated strings */
-static char *program_name = "<no argv[0]>";
-static char *stdin_name = "<stdin>";
-static char *stdout_name = "<stdout>";
-static char *stderr_name = "<stderr>";
-static char *(fmode[]) = { (char []){"rb"}, (char []){"rb+"} };
-static char *wharsh = "wb";
-
-/* Adds the open FILE pointer for the file at the path s to the files struct,
- * returning the FILE if successful and NULL if not, allocating more memory in
- * the files buffers as needed. */
-static FILE *
-Files_append(struct Files *files, FILE *file, char *name){
-
-	if(file == NULL || (files->s == files->a
-			&& ((files->files = realloc(files->files,
-					(files->a += (files->a == 0)
-						? ALLOC_INITIAL
-						: ALLOC_INCREMENT)
-					* sizeof *(files->files))) == NULL
-				|| (files->names = realloc(files->names,
-					files->a * sizeof *(files->names))) == NULL)))
-		return NULL;
-
-	files->names[files->s] = name;
-	return files->files[files->s++] = file;
-}
-
-/* Opens the file at the path p and puts it in the files struct, returning NULL
- * if either the opening or the placement of the open FILE pointer fail. */
-#define Files_open(files, p) \
-	Files_append((files), fopen((p), (files)->mode), (p))
-
-/* Prints a diagnostic message based on errno and returns an exit status
- * appropriate for an OS error. */
-static int
-oserr(char *s, char *r){
-
-	fprintf(stderr, "%s: %s: %s\n", s, r, strerror(errno));
-
-	return EX_OSERR;
-}
-
-/* Hijacks i and j from main and destructs the files[2] struct used by main by
- * closing its files and freeing its files and names arrays, returning retval
- * from main. */
-#define terminate \
-	for(i = 0; i < 2; ++i){ \
-		for(j = 0; j < files[i].s; ++j) \
-			if(files[i].files[j] != stdin \
-					&& files[i].files[j] != stdout \
-					&& files[i].files[j] != stderr) \
-				fclose(files[i].files[j]); \
-		free(files[i].files); \
-		free(files[i].names); \
-	} \
-	return retval
-
-int main(int argc, char *argv[]){
-	int c;
-	struct Files files[2]; /* {read, write} */
-	size_t i;
-	size_t j;
-	size_t k; /* loop index but also unbuffer status */
-	int retval;
-
-	/* Initializes the files structs with their default values, standard
-	 * input and standard output. If an input or an output is specified
-	 * these initial values will be overwritten, so to, say, use mm(1)
-	 * equivalently to tee(1p), -o - will need to be specified before
-	 * additional files to ensure standard output is still written. */
-	for(i = 0; i < 2; ++i){
-		files[i].a = 0;
-		files[i].s = 0;
-		files[i].mode = fmode[i];
-		files[i].files = NULL;
-		files[i].names = NULL;
-		Files_append(&files[i], i == 0 ? stdin : stdout,
-			i == 0 ? stdin_name : stdout_name);
-		files[i].s = 0;
-	}
-
-	k = 0;
-
-	if(argc > 0)
-		program_name = argv[0];
-
-	if(argc > 1)
-		while((c = getopt(argc, argv, "aehi:no:u")) != -1)
-			switch(c){
-			case 'a': /* "rb+" -> "ab" */
-				files[1].mode[0] = 'a';
-				files[1].mode[2] = '\0';
-				break;
-			case 'e':
-				if(Files_append(&files[1], stderr, stderr_name) != NULL)
-					break;
-				retval = oserr(argv[0], "-e");
-				terminate;
-			case 'i':
-				if((strcmp(optarg, "-") == 0 && Files_append(&files[0],
-							stdin, stdin_name) != NULL)
-						|| Files_open(&files[0], optarg) != NULL)
-					break;
-				retval = oserr(argv[0], optarg);
-				terminate;
-			case 'o':
-				if((strcmp(optarg, "-") == 0 && Files_append(&files[1],
-							stdout, stdout_name) != NULL)
-						|| Files_open(&files[1], optarg) != NULL)
-					break;
-				/* does not exist, so try to create it */
-				if(errno == ENOENT){
-					files[1].mode = wharsh;
-					if(Files_open(&files[1], optarg) != NULL){
-						files[1].mode = fmode[1];
-						break;
-					}
-				}
-				retval = oserr(argv[0], optarg);
-				terminate;
-			case 'n':
-				if(signal(SIGINT, SIG_IGN) != SIG_ERR)
-					break;
-				retval = oserr(argv[0], "-n");
-				terminate;
-			case 'u':
-				k = 1;
-				break;
-			default:
-				fprintf(stderr, "Usage: %s (-aenu) (-i [input])..."
-					" (-o [output])...\n", argv[0]);
-				retval = EX_USAGE;
-				terminate;
-			}
-
-	files[0].s += files[0].s == 0;
-	files[1].s += files[1].s == 0;
-	
-	/* Unbuffer files. */
-	if(k){
-		for(i = 0;
-			i < files[0].s;
-			setvbuf(files[0].files[i++], NULL, _IONBF, 0));
-		for(i = 0;
-			i < files[1].s;
-			setvbuf(files[1].files[i++], NULL, _IONBF, 0));
-	}
-
-	retval = EX_OK;
-
-	/* Actual program loop. */
-	for(i = 0; i < files[0].s; ++i) /* iterate ins */
-		while((c = getc(files[0].files[i])) != EOF) /* iterate chars */
-			for(j = 0; j < files[1].s; ++j) /* iterate outs */
-				if(putc(c, files[1].files[j]) == EOF){
-					/* notebook's full */
-					retval = EX_IOERR;
-					fprintf(stderr, "%s: %s: %s\n",
-						program_name, files[1].names[j], strerror(errno));
-					if(fclose(files[1].files[j]) == EOF)
-						fprintf(stderr, "%s: %s: %s\n",
-							program_name, files[1].names[j], strerror(errno));
-					/* massage out the tense muscle */
-					for(k = j--; k < files[1].s - 1; ++k){
-						files[1].files[k] = files[1].files[k+1];
-						files[1].names[k] = files[1].names[k+1];
-					}
-					if(--files[1].s == 0)
-						terminate;
-				}
-
-	terminate;
-}

src/mm.rs

@@ -0,0 +1,185 @@
+/*
+ * Copyright (c) 2024 Emma Tebibyte <emma@tebibyte.media>
+ * 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,
+	fs::File,
+	io::{ stdin, stdout, stderr, BufWriter, Read, Write },
+	os::fd::{ AsRawFd, FromRawFd },
+	process::{ exit, ExitCode },
+};
+
+extern crate getopt;
+extern crate strerror;
+extern crate sysexits;
+
+use getopt::GetOpt;
+use strerror::StrError;
+use sysexits::{ EX_IOERR, EX_USAGE };
+
+use ArgMode::*;
+
+enum ArgMode { In, Out }
+
+fn main() -> ExitCode {
+	let argv = args().collect::<Vec<_>>();
+	let usage = format!("Usage: {} [-aetu] [-i input] [-o output]", argv[0]);
+
+	let mut a = false; /* append to the file */
+	let mut e = false; /* use stderr as an output */
+	let mut t = true; /* do not truncate the file before writing */
+	let mut u = false; /* unbuffer i/o */
+	let mut ins = Vec::new(); /* initial input file path vector */
+	let mut outs = Vec::new(); /* initial output file path vector */
+	let mut mode: Option<ArgMode> = None; /* mode set by last-used option */
+	let mut optind = 0;
+
+	while let Some(opt) = argv.getopt("aei:o:tu") {
+		match opt.opt() {
+			Ok("a") => a = true,
+			Ok("e") => e = true, 
+			Ok("u") => u = true,
+			Ok("t") => t = false,
+			Ok("i") => { /* add inputs */
+				let input = opt.arg().unwrap();
+				ins.push(input);
+				mode = Some(In); /* latest argument == -i */
+			},
+			Ok("o") => { /* add output */
+				let output = opt.arg().unwrap(); 
+				outs.push(output);
+				mode = Some(Out); /* latest argument == -o */
+			},
+			Err(_) | Ok(_) => {
+				eprintln!("{}", usage);
+				return ExitCode::from(EX_USAGE as u8);
+			},
+		};
+
+		optind = opt.ind();
+	}
+
+	let remaining = argv.iter().skip(optind);
+
+	/* check the last flag specified */
+	if let Some(m) = mode {
+		for arg in remaining {
+			/* move the subsequent arguments to the list of inputs or outputs */
+			match m {
+				In => ins.push(arg.to_string()),
+				Out => outs.push(arg.to_string()),
+			};
+		}
+	} else {
+		eprintln!("{}", usage);
+		return ExitCode::from(EX_USAGE as u8);
+	}
+
+	/* use stdin if no inputs are specified */
+	if ins.is_empty() { ins.push("-".to_string()); }
+
+	/* use stdout if no outputs are specified */
+	if outs.is_empty() && !e { outs.push("-".to_string()); }
+	
+	/* map all path strings to files */
+	let inputs = ins.iter().map(|file| {
+		/* if a file is “-”, it is stdin */
+		if *file == "-" {
+			/* portable way to access stdin as a file */
+			return unsafe { File::from_raw_fd(stdin().as_raw_fd()) };
+		}
+
+		match File::open(file) {
+			Ok(f) => f,
+			Err(e) => {
+				eprintln!("{}: {}: {}", argv[0], file, e.strerror());
+				exit(EX_IOERR);
+			},
+		}
+	}).collect::<Vec<_>>();
+
+	/* map all path strings to files */
+	let mut outputs = outs.iter().map(|file| {
+		/* of a file is “-”, it is stdout */
+		if *file == "-" {
+			/* portable way to access stdout as a file */
+			return unsafe { File::from_raw_fd(stdout().as_raw_fd()) }; 
+		}
+
+		let options = File::options()
+			/* don’t truncate if -t is specified, append if -a is specified */
+			.truncate(t)
+			.append(a)
+			/* enable the ability to create and write to files */
+			.create(true)
+			.write(true)
+			/* finally, open the file! */
+			.open(file);
+
+		match options {
+			Ok(f) => return f,
+			Err(e) => {
+				eprintln!("{}: {}: {}", argv[0], file, e.strerror());
+				exit(EX_IOERR);
+			},
+		};
+	}).collect::<Vec<_>>();
+
+	/* if -e is specified, use stderr */
+	if e {
+		/* portable way to access stderr as a file */
+		outputs.push(unsafe { File::from_raw_fd(stderr().as_raw_fd()) });
+	}
+
+	let mut outputs = outputs.iter().map(|o| {
+		if u {
+			/* unbuffered writing through a buffer of capacity 0 */
+			BufWriter::with_capacity(0, o)
+		} else {
+			/* theoretically buffered writing */
+			BufWriter::new(o)
+		}
+	}).collect::<Vec<_>>();
+
+	for file in inputs {
+		for byte in file.bytes().map(|b| {
+			b.unwrap_or_else(|e| {
+				eprintln!("{}: {}", argv[0], e.strerror());
+				exit(EX_IOERR);
+			})
+		}) {
+			for out in &mut outputs {
+				if let Err(e) = out.write(&[byte]) {
+					eprintln!("{}: {}", argv[0], e.strerror());
+					return ExitCode::from(EX_IOERR as u8);
+				}
+
+				if u {
+					/* immediately flush the output for -u */
+					if let Err(e) = out.flush() { 
+						eprintln!("{}: {}", argv[0], e.strerror());
+						return ExitCode::from(EX_IOERR as u8);
+					}
+				}
+			}
+		}
+	}
+
+	ExitCode::SUCCESS
+}

src/npc.c

@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2023 DTB <trinity@trinity.moe>
+ * Copyright (c) 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
@@ -16,46 +17,65 @@
  * along with this program. If not, see https://www.gnu.org/licenses/.
  */
 
-#include <stdio.h> /* fprintf(3), fputs(3), getc(3), putc(3), stdin, stdout,
-                    * EOF */
-#include <stdlib.h> /* EXIT_FAILURE, EXIT_SUCCESS */
+#include <stdio.h> /* fprintf(3), fputs(3), getc(3), perror(3), putc(3), stdin,
+                    * stdout, EOF */
+#include <sysexits.h> /* EX_IOERR, EX_OK, EX_USAGE */
 #include <unistd.h> /* getopt(3) */
-#include <sysexits.h>
 
-int main(int argc, char *argv[]){
+char *program_name = "npc";
+
+static int
+ioerr(char *argv0) {
+	perror(argv0);
+
+	return EX_IOERR;
+}
+
+static int
+usage(char *argv0) {
+	(void)fprintf(stderr, "Usage: %s [-et]\n", argv0);
+
+	return EX_USAGE;
+}
+
+int main(int argc, char *argv[]) {
 	int c;
-	char showend;
-	char showtab;
+	char showend = 0; /* print a dollar sign before each newline */
+	char showtab = 0; /* prints tab characters in caret notation */
 
-	showend = 0;
-	showtab = 0;
+	if (argc > 0) {
+		program_name = argv[0];
 
-	if(argc > 0)
-		while((c = getopt(argc, argv, "et")) != -1)
-			switch(c){
-			case 'e':	showend = 1; break;
-			case 't':	showtab = 1; break;
-			default:	goto usage;
+		while ((c = getopt(argc, argv, "et")) != -1) {
+			switch (c){
+				case 'e': showend = 1; break;
+				case 't': showtab = 1; break;
+				default:  return usage(program_name);
 			}
-
-	if(argc > optind){
-usage:		fprintf(stderr, "Usage: %s (-eht)\n", argv[0]);
-		return EX_USAGE;
+		}
 	}
 
-	while((c = getc(stdin)) != EOF){
-		if((c & 0x80) != 0)
-			fputs("M-", stdout);
-		switch(c ^ 0x80 /* 0b 1000 0000 */){
-		case 0x7f:	fputs("^?", stdout);
+	if (argc > optind) { return usage(program_name); }
+
+	while ((c = getc(stdin)) != EOF) {
+		if ((c & 0x80) != 0 && fputs("M-", stdout) == EOF) {
+			return ioerr(argv[0]);
+		}
+
+		switch (c ^ 0x80 /* 0b 1000 0000 */) {
+			case 0x7f: /* ASCII DEL (127d) */
+				if(fputs("^?", stdout) == EOF) { return ioerr(argv[0]); }
 				break;
-		case '\n':	if(showend)
-					putc('$', stdout);
-		default:
-			if(c >= ' ' || c == '\n' || (!showtab && c == '\t'))
-				putc(c, stdout);
-			else
-				fprintf(stdout, "^%c", c + '@');
+			case '\n':
+				if (showend && fputc('$', stdout) == EOF) {
+					return ioerr(argv[0]);
+				}
+			default:
+				if (c >= ' ' || c == '\n' || (!showtab && c == '\t')) {
+					if (fputc(c, stdout) == EOF) { return ioerr(argv[0]); }
+				} else if (fprintf(stdout, "^%c", c + '@') < 0) {
+					return ioerr(argv[0]);
+				}
 		}
 	}
 

src/pg.c

@@ -1,260 +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/.
- */
-
-#include <errno.h> /* errno */
-#include <stdio.h> /* fclose(3), feof(3), fgetc(3), fgets(3), fopen(3),
-                    * fprintf(3), fputc(3), stderr, stdin, stdout, EOF, FILE,
-                    * NULL */
-#include <stdlib.h> /* size_t */
-#include <string.h> /* strchr(3), strcmp(3), strerror(3), strtok(3) */
-#include <unistd.h> /* getopt(3) */
-
-/* Commands start with cmd_. They take an argc and NULL-terminated argv, like
- * main, and return a status from <sysexits.h>. Return values other than EX_OK
- * and EX_USAGE cause pg(1) to exit with that value, except EX_UNAVAILABLE,
- * which causes pg(1) to exit with the status EX_OK. */
-#include <sysexits.h>
-
-#define CMDLINE_MAX 99+1 /* Maximum length of command line. */
-
-static char *whitespace = " \n\r\t\v";
-
-static struct {
-	size_t quantity;
-	enum { LINES = 0, BYTES = 1 } type;
-} default_page_unit = { 22, LINES } /* Plan 9 default */;
-static FILE *input;
-static char *prompt = ": ";
-static char *program_name = "pg";
-
-static char *permute_out(char *str, size_t index){
-	size_t j;
-
-	for(j = index; str[j - 1] != '\0'; ++j)
-		str[j - 1] = str[j];
-
-	return str;
-}
-
-/* strtok(3p), but supports double-quotes and escapes (but only for escaping
- * quotes). UTF-8 is safe only in str. Unmatched quotes in str are considered
- * literal. The behavior of strtok_quoted when '"' or '\\' are in sep is
- * undefined. */
-/* TODO: Seems to only ever return NULL. */
-static char *strtok_quoted(char *str, char *sep){
-	static char *s;
-	size_t i;
-	size_t j;
-
-	if(str != NULL)
-		s = str;
-
-	while(strchr(sep, *s) == NULL)
-		if(*++s == '\0')
-			return NULL; /* no remaining characters except seperators */
-
-	{
-		char in_escape;
-		int in_quotes;
-
-		in_escape = 0;
-		in_quotes = -1;
-		for(i = 0; s[i] != '\0'; ++i)
-			switch(s[i]){
-			case '\\':
-				if(in_escape)
-					permute_out(s, i--);
-				in_escape = !in_escape;
-				break;
-			case '"':
-				if(in_escape){
-					s[i] = s[i - 1];
-					permute_out(s, i--);
-				}else if(in_quotes != -1){
-					permute_out(s, in_quotes);
-					--i;
-					permute_out(s, i--);
-					in_quotes = -1;
-				}else
-					in_quotes = i;
-				break;
-			case '\0':
-				return s;
-			default:
-				if(!in_escape && strchr(sep, s[i]) != NULL){
-					s[i] = '\0';
-					return s;
-				}
-			}
-	}
-
-	return s;
-}
-
-/* Page at most l bytes from f without consideration of a buffer (print them to
- * stdout). */
-static int pg_b_u(FILE *f, size_t l){
-	int c;
-
-	while((c = fgetc(f)) != EOF)
-		if((c = fputc(c, stdout)) == EOF || --l == 0)
-			break;
-
-	return c;
-}
-
-/* Page at most l lines, which are lengths of characters terminated by nl, from
- * f without consideration of a buffer (print them to stdout). */
-static int pg_l_u(FILE *f, size_t l, char nl){
-	int c;
-
-	while((c = fgetc(f)) != EOF)
-		if((c = fputc(c, stdout)) == EOF || (l -= (c == nl)) == 0)
-			break;
-
-	return c;
-}
-
-static int cmd_quit(int argc, char **argv, char **envp){return EX_UNAVAILABLE;}
-static int cmd_default_page(int argc, char **argv, char **envp){
-
-	if(argc > 1) /* This shouldn't be possible. */
-		return EX_USAGE;
-	if(default_page_unit.type == BYTES)
-		return pg_b_u(input, default_page_unit.quantity) == EOF
-			? EX_UNAVAILABLE
-			: EX_OK;
-	else if(default_page_unit.type == LINES)
-		return pg_l_u(input, default_page_unit.quantity, '\n') == EOF
-			? EX_UNAVAILABLE
-			: EX_OK;
-	else
-		return EX_SOFTWARE;
-}
-static int cmd_page_down_lines(int argc, char **argv, char **envp){
-
-	switch(argc){
-	case 1:
-		return cmd_default_page(argc, argv, envp);
-	case 2: /* not implemented */
-	default:
-		fprintf(stderr, "Usage: %s" /*" (lines)"*/ "\n", argv[0]);
-		return EX_USAGE;
-	}
-}
-
-/* A CmdMap must be NULL-terminated. */
-static struct CmdMap{ char *name; int (*fn)(int, char **, char **); }
-builtins[] = {
-	{ "", cmd_default_page },
-	{ "+", cmd_page_down_lines },
-
-	/* don't make the user feel trapped */
-	{ ":q", cmd_quit }, { ":q!", cmd_quit },
-	{ "exit", cmd_quit }, { "q", cmd_quit }, { "Q", cmd_quit },
-	{ "quit", cmd_quit }, { "ZZ", cmd_quit },
-	
-	{ NULL, NULL }
-};
-
-#define ARGV_MAX 10
-/* Find and execute the command in the command map, given a corresponding
- * command line. */
-static int cmdline_exec(struct CmdMap *map, char *cmdline, char **envp){
-	/* Command line word splitting is naive and based on whitespace ONLY; no
-	 * fancy quoting or escaping here. Adding that would (ideally) entail
-	 * replacing strtok(3) with something specific to this task. */
-	static int argc;
-	static char *argv[ARGV_MAX];
-
-	if((argv[(argc = 0)] = strtok(cmdline, whitespace)) == NULL){
-		while(cmdline[0] != '\0')
-			cmdline = &cmdline[1];
-		argv[argc] = cmdline;
-		argv[++argc] = NULL;
-	}else{
-		while((argv[++argc] = strtok(NULL, whitespace)) != NULL
-		      && argc < ARGV_MAX);
-	}
-
-	for(; map->name != NULL; map = &map[1])
-		if(strcmp(map->name, argv[0]) == 0)
-			return map->fn(argc, argv, envp);
-
-	fprintf(stderr, "%s: %s: not found\n", program_name, argv[0]);
-	return EX_USAGE;
-}
-
-int usage(char *s){
-	fprintf(stderr, "Usage: %s (-p [prompt])\n", s);
-	return EX_USAGE;
-}
-
-int main(int argc, char *argv[]){
-	unsigned char cmd[CMDLINE_MAX];
-	FILE *t;
-
-	input = stdin;
-
-	if(argc < 1)
-		program_name = argv[0];
-	else{
-		int c;
-
-		while((c = getopt(argc, argv, "p:")) != -1)
-			switch(c){
-			case 'p': prompt = optarg; break;
-			default:
-				return usage(program_name);
-			}
-	}
-
-	if(argc > optind)
-		return usage(program_name);
-
-
-	if((t = fopen("/dev/tty", "rb")) == NULL){
-		fprintf(stderr, "%s: /dev/tty: %s\n", program_name, strerror(errno));
-		return EX_OSERR;
-	}
-
-	for(;;){
-		fputs(prompt, stderr);
-		fgets((char *)cmd, (sizeof cmd) / (sizeof *cmd), t);
-		if(strchr((char *)cmd, '\n') == NULL){ /* fast-forward stream */
-			int c;
-
-			while((c = fgetc(t)) != '\n')
-				if(c == EOF)
-					break;
-		}
-
-		if(feof(t))
-			return EX_OK;
-
-		{	int r;
-			switch((r = cmdline_exec(builtins, (char *)cmd, NULL))){
-			case EX_OK: case EX_USAGE: break;
-			case EX_UNAVAILABLE: return EX_OK;
-			default: return r;
-		}	}
-	}
-
-	/* UNREACHABLE */
-	return EX_SOFTWARE;
-}

src/rpn.rs

@@ -57,7 +57,7 @@ extern crate sysexits;
 use sysexits::EX_DATAERR;
 
 #[derive(Clone, PartialEq, PartialOrd, Debug)]
-// enum CalcType is a type containing operations used in the calculator
+/* enum CalcType is a type containing operations used in the calculator */
 enum CalcType {
 	Add,
 	Subtract,
@@ -117,8 +117,8 @@ struct EvaluationError {
 	code: i32,
 }
 
-// I’m no math nerd but I want the highest possible approximation of 0.9
-// repeating and it seems this can give it to me
+/* I’m no math nerd but I want the highest possible approximation of 0.9
+ * repeating and it seems this can give it to me */
 const PRECISION_MOD: f64 = 0.9 + f64::EPSILON * 100.0;
 
 fn eval(
@@ -133,7 +133,7 @@ fn eval(
 		return Ok((stack, oper));
 	}
 
-	// Split the input into tokens.
+	/* Split the input into tokens. */
 	let mut toks: VecDeque<CalcType> = input
 		.split_whitespace()
 		.rev()
@@ -183,7 +183,7 @@ fn eval(
 	Ok((stack, oper))
 }
 
-// Round a float to the given precision level
+/* Round a float to the given precision level */
 fn round_precise(value: &f64, precision: usize) -> f64 {
 	let multiplier = 10_f64.powi(precision as i32);
 	(value * multiplier).round() / multiplier
@@ -193,11 +193,11 @@ fn main() -> ExitCode {
 	let argv = args().collect::<Vec<String>>();
 	let mut stack = VecDeque::new();
 	let mut buf = String::new();
-	// Set floating-point precision for correcting rounding errors based on
-	// machine epsilon
+	/* Set floating-point precision for correcting rounding errors based on
+	 * machine epsilon */
 	let precision = (-f64::EPSILON.log10() * PRECISION_MOD).ceil() as usize;
 	
-	if argv.get(1).is_none() {
+	if argv.get(1).is_none() { /* read from stdin */
 		while let Ok(_) = stdin().read_line(&mut buf) {
 			match eval(&buf.trim(), stack) {
 				Ok(s) => {
@@ -219,12 +219,13 @@ fn main() -> ExitCode {
 				},
 			};
 		}
-	} else {
+	} else { /* read from argv */
+		/* join argv into an owned String joined by spaces minus argv[0] */
 		let input = argv
 			.iter()
 			.skip(1)
 			.map(|x| x.to_owned())
-			.collect::<Vec<String>>()
+			.collect::<Vec<_>>()
 			.join(" ");
 
 		match eval(&input, stack) {
@@ -233,7 +234,7 @@ fn main() -> ExitCode {
 
 				let val = match stack.iter().last() {
 					Some(v) => v,
-					None => return ExitCode::from(0),
+					None => return ExitCode::SUCCESS,
 				};
 
 				println!("{}", round_precise(val, precision).to_string())
@@ -244,5 +245,5 @@ fn main() -> ExitCode {
 			},
 		};
 	}
-	ExitCode::from(0)
+	ExitCode::SUCCESS
 }

src/scroll.c

@@ -0,0 +1,288 @@
+/*
+ * 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/.
+ */
+
+#include <assert.h> /* assert(3) */
+#include <errno.h> /* errno */
+#include <stdbool.h> /* bool */
+#include <stdio.h> /* fclose(3), feof(3), fgetc(3), fgets(3), fopen(3),
+                    * fprintf(3), fputc(3), perror(3), stderr, stdin, stdout,
+                    * EOF, FILE, NULL */
+#include <stdlib.h> /* size_t */
+#include <string.h> /* strchr(3), strcmp(3) */
+#include <unistd.h> /* getopt(3) */
+
+/* Commands start with cmd_. They take an argc and NULL-terminated argv, like
+ * main, and return a status from <sysexits.h>. Return values other than EX_OK
+ * and EX_USAGE cause pg(1) to exit with that value, except EX_UNAVAILABLE,
+ * which causes pg(1) to exit with the status EX_OK. */
+#include <sysexits.h>
+
+#define CMDLINE_MAX 99+1 /* Maximum length of command line. */
+
+static char *whitespace = " \n\r\t\v";
+
+//static
+struct Tube {
+	char *name;   // command line
+	FILE *in;     // process stdin
+	FILE *out;    // process stdoout
+	size_t index; // in pipeline
+};
+
+static struct {
+	size_t quantity;
+	enum { LINES = 0, BYTES = 1 } type;
+} default_page_unit = { 22, LINES } /* Plan 9 default */;
+
+static char *prompt = ": ";
+static char *program_name = "pg";
+
+static char *
+permute_out(char *s, size_t i) {
+	for (
+		;
+		s[i] != '\0';
+		s[i] = s[i + 1], ++i
+	);
+
+	return s;
+}
+
+/* strtok(3p), but supports double-quotes and escapes (but only for escaping
+ * quotes).  Unmatched quotes in str are considered literal. The behavior of
+ * strtok_quoted when '\'', '"', or '\\' are in sep is undefined. Use of UTF-8
+ * separators with strtok_quoted is undefined. */
+static char *
+strtok_quoted(char *str, char *sep) {
+	static char *s;
+
+	if (str != NULL) { s = str; }
+
+	while (strchr(sep, *s) != NULL) { // skip beginning whitespace
+		if(*++s == '\0') { return NULL; } // no remaining except seps
+	}
+
+	{
+		bool in_escape = 0; // previous char was '\\'
+		char quote = '\0';  // quotation mark used, or '\0' if none
+
+		for (int i = 0; s[i] != '\0'; ++i)
+			switch (s[i]) {
+				case '\\':
+					// if literal "\\", permute out a backslash
+					if (in_escape) { (void)permute_out(s, i--); }
+					in_escape = !in_escape;
+					break;
+				case '\'': case '"':
+					if (in_escape) { // \"
+						s[i] = s[i - 1];
+						(void)permute_out(s, i--); // permute out backslash
+					} else if (s[i] == quote) {
+						quote = '\0';
+						(void)permute_out(s, i--); // second quote
+					} else {
+						quote = s[i];
+						if (strchr(&s[i + 1], quote) != NULL) { // has a match
+							(void)permute_out(s, i--); // permute out lquote
+						}
+					}
+					break;
+				case '\0': return s;
+				default:
+					if (!in_escape
+					    	&& quote == '\0'
+					    	&& (strchr(sep, s[i]) != NULL || s[i] == '\0')) {
+						char *t; // start of current token
+
+						t = s;
+						s = s[i] != '\0'
+							? &t[i + 1] // store start of next token,
+							: &t[i];    // or the address of the nul if found
+						s[i] = '\0'; // NUL terminate current token
+
+						return t;
+					}
+			}
+	}
+
+	return s;
+}
+
+/* Page at most l bytes from f without consideration of a buffer (print them to
+ * stdout). */
+static int
+pg_b_u(FILE *f, size_t l) {
+	int c;
+
+	while ((c = fgetc(f)) != EOF) {
+		if ((c = fputc(c, stdout)) == EOF || --l == 0) { break; }
+	}
+
+	return c;
+}
+
+/* Page at most l lines, which are lengths of characters terminated by nl, from
+ * f without consideration of a buffer (print them to stdout). */
+static int
+pg_l_u(FILE *f, size_t l, char nl) {
+	int c;
+
+	while ((c = fgetc(f)) != EOF) {
+		if ((c = fputc(c, stdout)) == EOF || (l -= (c == nl)) == 0) { break; }
+	}
+
+	return c;
+}
+
+static int
+cmd_quit(int argc, char **argv, char **envp) { return EX_UNAVAILABLE; }
+
+static int
+cmd_default_page(int argc, char **argv, char **envp) {
+	if (argc > 1) { return EX_USAGE; } // should be impossible
+	else if (default_page_unit.type == BYTES) {
+		return pg_b_u(stdin, default_page_unit.quantity) == EOF
+			? EX_UNAVAILABLE
+			: EX_OK;
+	} else if (default_page_unit.type == LINES) {
+		return pg_l_u(stdin, default_page_unit.quantity, '\n') == EOF
+			? EX_UNAVAILABLE
+			: EX_OK;
+	} else { return EX_SOFTWARE; }
+}
+
+static int
+cmd_page_down_lines(int argc, char **argv, char **envp) {
+	switch (argc) {
+		case 1: return cmd_default_page(argc, argv, envp);
+		case 2: /* not implemented */
+		default:
+			(void)fprintf(stderr, "Usage: %s" /*" (lines)"*/ "\n", argv[0]);
+			return EX_USAGE;
+	}
+}
+
+/* A CmdMap must be NULL-terminated. */
+static struct CmdMap{ char *name; int (*fn)(int, char **, char **); }
+builtins[] = {
+	/* don't make the user feel trapped */
+	{ ":q", cmd_quit }, { ":q!", cmd_quit },
+	{ "exit", cmd_quit }, { "q", cmd_quit }, { "Q", cmd_quit },
+	{ "quit", cmd_quit }, { "ZZ", cmd_quit },
+	
+	{ NULL, NULL }
+};
+
+#define ARGV_MAX 10
+/* Find and execute the command in the command map, given a corresponding
+ * command line. */
+static int
+cmdline_exec(struct CmdMap *map, char *cmdline, char **envp) {
+	static int argc;
+	static char *argv[ARGV_MAX];
+
+	if ((argv[(argc = 0)] = strtok_quoted(cmdline, whitespace)) == NULL) {
+		while (cmdline[0] != '\0') { cmdline = &cmdline[1]; }
+		argv[argc] = cmdline;
+		argv[++argc] = NULL;
+	} else {
+		while (
+			(argv[++argc] = strtok_quoted(NULL, whitespace)) != NULL
+			&& argc < ARGV_MAX
+		);
+	}
+
+	for (; map->name != NULL; map = &map[1]) {
+		if(strcmp(map->name, argv[0]) == 0) {
+			return map->fn(argc, argv, envp);
+		}
+	}
+
+	(void)fprintf(stderr, "%s: %s: not found\n", program_name, argv[0]);
+	return EX_USAGE;
+}
+
+static int
+ioerr(char *argv0) {
+	perror(argv0);
+
+	return EX_IOERR;
+}
+
+static int
+usage(char *argv0) {
+	(void)fprintf(stderr, "Usage: %s [-p prompt]\n", argv0);
+
+	return EX_USAGE;
+}
+
+int main(int argc, char *argv[]) {
+	unsigned char cmd[CMDLINE_MAX];
+	FILE *t;
+
+	if (argc > 0) {
+		int c;
+
+		program_name = argv[0];
+
+		while ((c = getopt(argc, argv, "p:")) != -1) {
+			switch (c) {
+				case 'p': prompt = optarg; break;
+				default:  return usage(program_name);
+			}
+		}
+	}
+
+	if (argc > optind) { return usage(program_name); }
+
+
+	if ((t = fopen("/dev/tty", "rb")) == NULL) {
+		perror(program_name);
+
+		return EX_OSERR;
+	}
+
+	for (;;) {
+		if (fputs(prompt, stderr) == EOF) { return ioerr(program_name); }
+
+		// if the line...
+		if (fgets((char *)cmd, (sizeof cmd) / (sizeof *cmd), t) != NULL) {
+			if (strchr((char *)cmd, '\n') == NULL) { // was taken incompletely
+				int c;
+
+				while ((c = fgetc(t)) != '\n') { // ...fast-forward stream
+					if (c == EOF) { break; }
+				}
+			}
+		} else { fputc('\n', stdout); } // EOF at start of line; finish prompt
+
+		if (feof(t)) { return EX_OK; }
+
+		{
+			int r;
+
+			switch ((r = cmdline_exec(builtins, (char *)cmd, NULL))){
+				case EX_OK: case EX_USAGE: break;
+				case EX_UNAVAILABLE: return EX_OK;
+				default: return r;
+			}
+		}
+	}
+
+	/* UNREACHABLE */ assert(0);
+}

src/scrut.c

@@ -1,5 +1,6 @@
 /*
- * Copyright (c) 2023 DTB <trinity@trinity.moe>
+ * Copyright (c) 2023–2024 DTB <trinity@trinity.moe>
+ * Copyright (c) 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
@@ -17,88 +18,77 @@
  */
 
 #include <stdio.h> /* fprintf(3), stderr, NULL */
-#include <stdlib.h> /* EXIT_FAILURE */
+#include <stdlib.h> /* EXIT_FAILURE, EXIT_SUCCESS */
 #include <string.h> /* memset(3), strchr(3) */
+#include <sysexits.h> /* EX_USAGE */
 #include <unistd.h> /* access(3), getopt(3), F_OK, R_OK, W_OK, X_OK */
 #include <sys/stat.h> /* lstat(3), stat struct, S_ISBLK, S_ISCHR, S_ISDIR,
                        * S_ISFIFO, S_ISGID, S_ISREG, S_ISLNK, S_ISSOCK,
                        * S_ISUID, S_ISVTX */
-#include <sysexits.h>
 
-static char args[] = "bcdefghkprsuwxLS";
-static char ops[(sizeof args) / (sizeof *args)];
-static char *program_name = "scrut";
+char *program_name = "scrut";
+#define OPTS "bcdefgkprsuwxLS"
+static char *opts = OPTS;
 
-int main(int argc, char *argv[]){
-	struct stat buf;
-	int c;
-	size_t i;
-	char *p;
+static int
+usage(char *argv0) {
+	(void)fprintf(stderr, "Usage: %s [-" OPTS "] file...\n", argv0);
 
-	if(argc < 2)
-		goto usage;
+	return EX_USAGE;
+}
 
-	memset(ops, '\0', sizeof ops);
-	while((c = getopt(argc, argv, args)) != -1)
-		if((p = strchr(args, c)) == NULL)
-			goto usage;
-		else
-			ops[p - args] = c;
-	/* straighten out ops */
-	for(i = 0, p = ops; i < (sizeof ops) / (sizeof *ops); ++i)
-		if(ops[i] != '\0'){
-			*p = ops[i];
-			if(&ops[i] != p++)
-				ops[i] = '\0';
+int main(int argc, char *argv[]) {
+	char sel[(sizeof opts) / (sizeof *opts)];
+
+	if (argc < 2) { return usage(argv[0] == NULL ? program_name : argv[0]); }
+
+	{ /* option parsing */
+		char *p;
+
+		memset(sel, '\0', sizeof sel);
+		for (int c; (c = getopt(argc, argv, opts)) != -1;) {
+			if ((p = strchr(opts, c)) == NULL) { return usage(argv[0]); }
+			else { sel[p - opts] = c; }
 		}
 
-	if(optind == argc)
-		goto usage;
+		/* straighten out selections; permute out nulls */
+		p = sel;
+		for (size_t i = 0; i < (sizeof sel) / (sizeof *sel); ++i) {
+			if (sel[i] != '\0') {
+				*p = sel[i];
+				if (&sel[i] != p++) { sel[i] = '\0'; }
+			}
+		}
+	}
 
-	argv += optind;
-	do{	if(access(*argv, F_OK) != 0 || lstat(*argv, &buf) == -1)
-			return 1; /* doesn't exist or isn't stattable */
+	if (optind == argc) { return usage(argv[0]); }
 
-		for(i = 0; ops[i] != '\0'; ++i)
-			if(ops[i] == 'e')
-				continue;
-			else if(ops[i] == 'h'){
-usage:				fprintf(stderr, "Usage: %s (-%s) [file...]\n",
-					argv[0] == NULL
-						? program_name
-						: argv[0],
-					args);
+	for (argv += optind ; *argv != NULL; ++argv) {
+		struct stat buf;
 
-				return EX_USAGE;
-			}else if(
-					(ops[i] == 'b'
-						&& !S_ISBLK(buf.st_mode))
-					|| (ops[i] == 'c'
-						&& !S_ISCHR(buf.st_mode))
-					|| (ops[i] == 'd'
-						&& !S_ISDIR(buf.st_mode))
-					|| (ops[i] == 'f'
-						&& !S_ISREG(buf.st_mode))
-					|| (ops[i] == 'g'
-						&& !(buf.st_mode & S_ISGID))
-					|| (ops[i] == 'k'
-						&& !(buf.st_mode & S_ISVTX))
-					|| (ops[i] == 'p'
-						&& !S_ISFIFO(buf.st_mode))
-					|| (ops[i] == 'r'
-						&& access(*argv, R_OK) != 0)
-					|| (ops[i] == 'u'
-						&& !(buf.st_mode & S_ISUID))
-					|| (ops[i] == 'w'
-						&& access(*argv, W_OK) != 0)
-					|| (ops[i] == 'x'
-						&& access(*argv, X_OK) != 0)
-					|| (ops[i] == 'L'
-						&& !S_ISLNK(buf.st_mode))
-					|| (ops[i] == 'S'
-						&& !S_ISSOCK(buf.st_mode)))
-				return 1;
-	}while(*++argv != NULL);
+		if(access(*argv, F_OK) != 0 || lstat(*argv, &buf) == -1) {
+			return EXIT_FAILURE; /* doesn't exist or isn't stattable */
+		}
 
-	return 0;
+		for (size_t i = 0; sel[i] != '\0'; ++i) {
+			if (
+					(sel[i] == 'b' && !S_ISBLK(buf.st_mode))
+					|| (sel[i] == 'c' && !S_ISCHR(buf.st_mode))
+					|| (sel[i] == 'd' && !S_ISDIR(buf.st_mode))
+					|| (sel[i] == 'e' && 0)
+					|| (sel[i] == 'f' && !S_ISREG(buf.st_mode))
+					|| (sel[i] == 'g' && !(buf.st_mode & S_ISGID))
+					|| (sel[i] == 'k' && !(buf.st_mode & S_ISVTX))
+					|| (sel[i] == 'p' && !S_ISFIFO(buf.st_mode))
+					|| (sel[i] == 'r' && access(*argv, R_OK) != 0)
+					|| (sel[i] == 'u' && !(buf.st_mode & S_ISUID))
+					|| (sel[i] == 'w' && access(*argv, W_OK) != 0)
+					|| (sel[i] == 'x' && access(*argv, X_OK) != 0)
+					|| (sel[i] == 'L' && !S_ISLNK(buf.st_mode))
+					|| (sel[i] == 'S' && !S_ISSOCK(buf.st_mode))
+			) { return EXIT_FAILURE; }
+		}
+	}
+
+	return EXIT_SUCCESS;
 }

src/str.c

@@ -20,16 +20,16 @@
 #include <ctype.h>
 #include <stddef.h> /* NULL */
 #include <stdio.h> /* fprintf(3) */
-#include <stdlib.h> /* EXIT_FAILURE */
+#include <stdlib.h> /* size_t, EXIT_FAILURE */
 #include <string.h> /* strcmp(3) */
-#include <sysexits.h>
+#include <sysexits.h> /* EX_USAGE */
 
-static char *program_name = "str";
+char *program_name = "str";
 
 static struct {
 	char *name;
 	int (*f)(int);
-}ctypes[] = {
+} ctypes[] = {
 	{ "isalnum", isalnum },
 	{ "isalpha", isalpha },
 	{ "isblank", isblank },
@@ -41,35 +41,44 @@ static struct {
 	{ "isprint", isprint },
 	{ "ispunct", ispunct },
 	{ "isspace", isspace },
-	{ "isupper", isupper }
+	{ "isupper", isupper },
+	{ NULL, NULL } /* marks end */
 };
 
-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]);
+static int
+usage(char *argv0) {
+	(void)fprintf(stderr, "Usage: %s type string...\n", argv0);
 
 	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;
+}
+
+int main(int argc, char *argv[]) {
+	size_t ctype; // selected from ctypes.h; index of ctype
+	int retval; // initially fail but becomes success on the first valid char
+
+	if (argc < 3) { return usage(argv[0] == NULL ? program_name : argv[0]); }
+
+	for ( /* iterate ctypes */
+		ctype = 0;
+		ctypes[ctype].f != NULL /* break at the end of ctypes */
+			&& strcmp(argv[1], ctypes[ctype].name) != 0; /* break at match */
+		++ctype
+	);
+
+	if (ctypes[ctype].f == NULL) { return usage(argv[0]); }
+
+	/* iterate args */
+	for (argv += 2, retval = EXIT_FAILURE; *argv != NULL; ++argv) {
+		for (size_t i = 0; argv[0][i] != '\0'; ++i) { /* iterate arg bytes */
+			/* 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 // argv[0][i] is ASCII,
+					&& !ctypes[ctype].f(argv[0][i]) // so use ctypes(3)
+			) { return EXIT_FAILURE; }
+			else { retval = EXIT_SUCCESS; }
+		}
+	}
+
+	return retval;
 }

src/strcmp.c

@@ -1,24 +1,50 @@
+/*
+ * Copyright (c) 2023 DTB <trinity@trinity.moe>
+ * 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/.
+ */
 #include <stdio.h> /* fprintf(3), stderr */
-#include <stdlib.h> /* EXIT_FAILURE */
-#include <sysexits.h>
+#include <sysexits.h> /* EX_OK, EX_USAGE */
 
-static char *program_name = "strcmp";
+char *program_name = "strcmp";
 
-int main(int argc, char *argv[]){
+int main(int argc, char *argv[]) {
 	int i;
 
-	if(argc < 3){
-		fprintf(stderr, "Usage: %s [string] [string...]\n",
-			argv[0] == NULL ? program_name : argv[0]);
+	if (argc < 3) {
+		(void)fprintf(
+			stderr,
+			"Usage: %s string string...\n",
+			argv[0] == NULL ? program_name : argv[0]
+		);
+
 		return EX_USAGE;
 	}
 
-	for(; *argv[1] != '\0'; ++argv[1])
-		for(i = 2; i < argc; ++i)
-			if(*argv[i-1] > *argv[i])
+	for (; *argv[1] != '\0'; ++argv[1]) {
+		for (i = 2; i < argc; ++i) {
+			/* a former string has a greater byte value */
+			if (*argv[i-1] > *argv[i]) { 
 				return 1;
-			else if(*argv[i-1] < *argv[i]++)
+			/* a latter string has a greater byte value */
+			} else if (*argv[i-1] < *argv[i]++) {
 				return -1; /* actually 255 */
+			}
+		}
+	}
 
-	return 0;
+	return EX_OK;
 }

src/swab.rs

@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2024 DTB <trinity@trinity.moe>
+ * Copyright (c) 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
@@ -18,72 +19,78 @@
 
 use std::{
 	env::args,
-	io::{ stdin, stdout, Error, ErrorKind, Read, Write },
+	io::{ stdin, stdout, Error, Read, Write },
 	process::ExitCode,
 	vec::Vec
 };
 
 extern crate getopt;
-use getopt::{ Opt, Parser };
-
 extern crate sysexits;
-use sysexits::{ EX_OK, EX_OSERR, EX_USAGE };
+extern crate strerror;
 
-fn oserr(s: &str, e: Error) -> ExitCode {
-	eprintln!("{}: {}", s, e);
+use getopt::GetOpt;
+use sysexits::{ EX_IOERR, EX_OK, EX_OSERR, EX_USAGE };
+use strerror::StrError;
+
+fn oserr(argv0: &str, e: Error) -> ExitCode {
+	eprintln!("{}: {}", argv0, e.strerror());
 	ExitCode::from(EX_OSERR as u8)
 }
 
+fn ioerr(argv0: &str, e: Error) -> ExitCode {
+	eprintln!("{}: {}", argv0, e.strerror());
+	ExitCode::from(EX_IOERR as u8)
+}
+
 fn usage(s: &str) -> ExitCode {
-	eprintln!("Usage: {} (-f) (-w [wordsize])", s);
+	eprintln!("Usage: {} [-w word_size]", s);
 	ExitCode::from(EX_USAGE as u8)
 }
 
 fn main() -> ExitCode {
 	let argv = args().collect::<Vec<String>>();
-	let mut buf: Vec<u8> = Vec::new();
+	let mut buf: Vec<u8> = Vec::new(); // holds the sequence getting swabbed
 	let mut input = stdin();
 	let mut output = stdout().lock();
+	let mut optind: usize = 1;   // argv[0]
+	let mut wordsize: usize = 2; // default; mimics dd(1p) conv=swab
 
-	let mut opts = Parser::new(&argv, "fw:");
-	let mut force = false;
-	let mut wordsize: usize = 2;
-
-	loop {
-		match opts.next() {
-			None => break,
-			Some(opt) =>
-				match opt {
-					Ok(Opt('f', None)) => force = true,
-					Ok(Opt('w', Some(arg))) => {
-						match arg.parse::<usize>() {
-							Ok(w) if w % 2 == 0 => { wordsize = w; () },
-							_ => { return usage(&argv[0]); },
-						}
-					},
-					_ => { return usage(&argv[0]); }
-				}
+	while let Some(opt) = argv.getopt("w:") {
+		match opt.opt() {
+			Ok("w") => {
+					match opt.arg().unwrap().parse::<usize>() {
+						Ok(w) if w % 2 == 0 => { wordsize = w; },
+						_ => { return usage(&argv[0]); },
+					}
+				optind = opt.ind();
+			},
+			_ => { return usage(&argv[0]); }
 		}
 	}
 
+	if optind < argv.len() {
+		return usage(&argv[0]);
+	}
+
 	buf.resize(wordsize, 0);
 
 	loop {
 		match input.read(&mut buf) {
-			Ok(0) => break ExitCode::from(EX_OK as u8),
-			Ok(v) if v == wordsize => {
+			Ok(0) => break ExitCode::from(EX_OK as u8), // read nothing; bye
+			Ok(v) if v == wordsize => { // read full block; swab
 				let (left, right) = buf.split_at(v/2);
+
 				if let Err(e) = output.write(&right)
 						.and_then(|_| output.write(&left)) {
-					break oserr(&argv[0], e)
+					break ioerr(&argv[0], e);
 				}
+
 			},
-			Ok(v) => {
+			Ok(v) => { // partial read; partially write
 				if let Err(e) = output.write(&buf[..v]) {
-					break oserr(&argv[0], e)
+					break ioerr(&argv[0], e);
 				}
 			},
-			Err(e) if e.kind() == ErrorKind::Interrupted && force => continue,
 			Err(e) => break oserr(&argv[0], e)
 		}
 	}

src/test.rs

@@ -1,10 +0,0 @@
-extern crate strerror;
-
-use strerror::raw_message;
-
-fn main() {
-	stdout.write_all(b"meow\n").unwrap_or_else(|e| {
-		eprintln!("{}", raw_message(e));
-		std::process::exit(1);
-	});
-}