config.sub: Systematize parsing of machine code formats

Instead of treating them as OSes, we treat them as their own category.
This is modeled on what LLVM does with its `ObjectFormatType` enum [1],
advancing my long-running project of trying to nudge GNU config and LLVM
towards each other, taking the best ideas of both.

Currently, my emphasis is just on code cleanup. There are just a few
tests for newly supported changes that fall out of this. But down the
road, this also opens the door to parsing configs with more than 4
components, like [2].

[1]: https://llvm.org/doxygen/classllvm_1_1Triple.html#a83e907e55fa50e093caa96a0aff96201

[2]: a18266473b/llvm/unittests/TargetParser/TripleTest.cpp (L1873C50-L1873C77)
added in
28b82bc39e

* config.sub: Save machine code format name separately from the OS name.
* doc/config.sub.1: Regenerate.
* testsuite/config-sub.data (arm-unknown-none-aout,
arm-unknown-none-pe): New entries.

Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>

config.sub

@@ -4,7 +4,7 @@
 
 # shellcheck disable=SC2006,SC2268 # see below for rationale
 
-timestamp='2023-07-31'
+timestamp='2023-08-07'
 
 # This file is free software; you can redistribute it and/or modify it
 # under the terms of the GNU General Public License as published by
@@ -1284,11 +1284,12 @@ esac
 
 # Decode manufacturer-specific aliases for certain operating systems.
 
-if test x$basic_os != x
+if test x"$basic_os" != x
 then
 
 # First recognize some ad-hoc cases, or perhaps split kernel-os, or else just
 # set os.
+obj=
 case $basic_os in
 	gnu/linux*)
 		kernel=linux
@@ -1488,10 +1489,16 @@ case $os in
 			os=eabi
 			;;
 		    *)
-			os=elf
+			os=
+			obj=elf
 			;;
 		esac
 		;;
+	aout* | coff* | elf* | pe*)
+		# These are machine code file formats, not OSes
+		obj=$os
+		os=
+		;;
 	*)
 		# No normalization, but not necessarily accepted, that comes below.
 		;;
@@ -1510,12 +1517,15 @@ else
 # system, and we'll never get to this point.
 
 kernel=
+obj=
 case $cpu-$vendor in
 	score-*)
-		os=elf
+		os=
+		obj=elf
 		;;
 	spu-*)
-		os=elf
+		os=
+		obj=elf
 		;;
 	*-acorn)
 		os=riscix1.2
@@ -1525,28 +1535,35 @@ case $cpu-$vendor in
 		os=gnu
 		;;
 	arm*-semi)
-		os=aout
+		os=
+		obj=aout
 		;;
 	c4x-* | tic4x-*)
-		os=coff
+		os=
+		obj=coff
 		;;
 	c8051-*)
-		os=elf
+		os=
+		obj=elf
 		;;
 	clipper-intergraph)
 		os=clix
 		;;
 	hexagon-*)
-		os=elf
+		os=
+		obj=elf
 		;;
 	tic54x-*)
-		os=coff
+		os=
+		obj=coff
 		;;
 	tic55x-*)
-		os=coff
+		os=
+		obj=coff
 		;;
 	tic6x-*)
-		os=coff
+		os=
+		obj=coff
 		;;
 	# This must come before the *-dec entry.
 	pdp10-*)
@@ -1568,19 +1585,24 @@ case $cpu-$vendor in
 		os=sunos3
 		;;
 	m68*-cisco)
-		os=aout
+		os=
+		obj=aout
 		;;
 	mep-*)
-		os=elf
+		os=
+		obj=elf
 		;;
 	mips*-cisco)
-		os=elf
+		os=
+		obj=elf
 		;;
 	mips*-*)
-		os=elf
+		os=
+		obj=elf
 		;;
 	or32-*)
-		os=coff
+		os=
+		obj=coff
 		;;
 	*-tti)	# must be before sparc entry or we get the wrong os.
 		os=sysv3
@@ -1589,7 +1611,8 @@ case $cpu-$vendor in
 		os=sunos4.1.1
 		;;
 	pru-*)
-		os=elf
+		os=
+		obj=elf
 		;;
 	*-be)
 		os=beos
@@ -1670,10 +1693,12 @@ case $cpu-$vendor in
 		os=uxpv
 		;;
 	*-rom68k)
-		os=coff
+		os=
+		obj=coff
 		;;
 	*-*bug)
-		os=coff
+		os=
+		obj=coff
 		;;
 	*-apple)
 		os=macos
@@ -1691,7 +1716,8 @@ esac
 
 fi
 
-# Now, validate our (potentially fixed-up) OS.
+# Now, validate our (potentially fixed-up) individual pieces (OS, OBJ).
+
 case $os in
 	# Sometimes we do "kernel-libc", so those need to count as OSes.
 	musl* | newlib* | relibc* | uclibc*)
@@ -1719,11 +1745,11 @@ case $os in
 	     | mirbsd* | netbsd* | dicos* | openedition* | ose* \
 	     | bitrig* | openbsd* | secbsd* | solidbsd* | libertybsd* | os108* \
 	     | ekkobsd* | freebsd* | riscix* | lynxos* | os400* \
-	     | bosx* | nextstep* | cxux* | aout* | elf* | oabi* \
+	     | bosx* | nextstep* | cxux* | oabi* \
-	     | ptx* | coff* | ecoff* | winnt* | domain* | vsta* \
+	     | ptx* | ecoff* | winnt* | domain* | vsta* \
 	     | udi* | lites* | ieee* | go32* | aux* | hcos* \
 	     | chorusrdb* | cegcc* | glidix* | serenity* \
-	     | cygwin* | msys* | pe* | moss* | proelf* | rtems* \
+	     | cygwin* | msys* | moss* | proelf* | rtems* \
 	     | midipix* | mingw32* | mingw64* | mint* \
 	     | uxpv* | beos* | mpeix* | udk* | moxiebox* \
 	     | interix* | uwin* | mks* | rhapsody* | darwin* \
@@ -1747,60 +1773,81 @@ case $os in
 	kernel* | msvc* )
 		# Restricted further below
 		;;
+	'')
+		if test x"$obj" = x
+		then
+			echo "Invalid configuration '$1': Blank OS only allowed with explicit machine code file format" 1>&2
+		fi
+		;;
 	*)
 		echo "Invalid configuration '$1': OS '$os' not recognized" 1>&2
 		exit 1
 		;;
 esac
 
+case $obj in
+	aout* | coff* | elf* | pe*)
+		;;
+	'')
+		# empty is fine
+		;;
+	*)
+		echo "Invalid configuration '$1': Machine code format '$obj' not recognized" 1>&2
+		exit 1
+		;;
+esac
+
 # As a final step for OS-related things, validate the OS-kernel combination
 # (given a valid OS), if there is a kernel.
-case $kernel-$os in
+case $kernel-$os-$obj in
-	linux-gnu* | linux-dietlibc* | linux-android* | linux-newlib* \
+	linux-gnu*- | linux-dietlibc*- | linux-android*- | linux-newlib*- \
-		   | linux-musl* | linux-relibc* | linux-uclibc* | linux-mlibc* )
+		   | linux-musl*- | linux-relibc*- | linux-uclibc*- | linux-mlibc*- )
 		;;
-	uclinux-uclibc* )
+	uclinux-uclibc*- )
 		;;
-	managarm-mlibc* | managarm-kernel* )
+	managarm-mlibc*- | managarm-kernel*- )
 		;;
-	windows*-gnu* | windows*-msvc*)
+	windows*-gnu*- | windows*-msvc*-)
 		;;
-	-dietlibc* | -newlib* | -musl* | -relibc* | -uclibc* | -mlibc* )
+	-dietlibc*- | -newlib*- | -musl*- | -relibc*- | -uclibc*- | -mlibc*- )
 		# These are just libc implementations, not actual OSes, and thus
 		# require a kernel.
 		echo "Invalid configuration '$1': libc '$os' needs explicit kernel." 1>&2
 		exit 1
 		;;
-	-kernel* )
+	-kernel*- )
 		echo "Invalid configuration '$1': '$os' needs explicit kernel." 1>&2
 		exit 1
 		;;
-	*-kernel* )
+	*-kernel*- )
 		echo "Invalid configuration '$1': '$kernel' does not support '$os'." 1>&2
 		exit 1
 		;;
-	*-msvc* )
+	*-msvc*- )
 		echo "Invalid configuration '$1': '$os' needs 'windows'." 1>&2
 		exit 1
 		;;
-	kfreebsd*-gnu* | kopensolaris*-gnu*)
+	kfreebsd*-gnu*- | kopensolaris*-gnu*-)
 		;;
-	vxworks-simlinux | vxworks-simwindows | vxworks-spe)
+	vxworks-simlinux- | vxworks-simwindows- | vxworks-spe-)
 		;;
-	nto-qnx*)
+	nto-qnx*-)
 		;;
-	os2-emx)
+	os2-emx-)
 		;;
-	*-eabi* | *-gnueabi*)
+	*-eabi*- | *-gnueabi*-)
 		;;
-	none-coff* | none-elf*)
+	none--*)
 		# None (no kernel, i.e. freestanding / bare metal),
-		# can be paired with an output format "OS"
+		# can be paired with an machine code file format
 		;;
-	-*)
+	-*-)
 		# Blank kernel with real OS is always fine.
 		;;
-	*-*)
+	--*)
+		# Blank kernel and OS with real machine code file format is always fine.
+		;;
+	*-*-*)
 		echo "Invalid configuration '$1': Kernel '$kernel' not known to work with OS '$os'." 1>&2
 		exit 1
 		;;
@@ -1884,7 +1931,7 @@ case $vendor in
 		;;
 esac
 
-echo "$cpu-$vendor-${kernel:+$kernel-}$os"
+echo "$cpu-$vendor${kernel:+-$kernel}${os:+-$os}${obj:+-$obj}"
 exit
 
 # Local variables:

doc/config.sub.1

@@ -1,5 +1,5 @@
 .\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.48.5.
-.TH CONFIG.SUB "1" "July 2023" "GNU config.sub (2023-07-31)" "User Commands"
+.TH CONFIG.SUB "1" "August 2023" "GNU config.sub (2023-08-07)" "User Commands"
 .SH NAME
 config.sub \- validate and canonicalize a configuration triplet
 .SH SYNOPSIS

testsuite/config-sub.data

@@ -91,9 +91,11 @@ arm-sysgo-pikeos				arm-sysgo-eabi
 arm-tirtos					arm-unknown-tirtos
 arm-uclinux-uclibcgnueabi			arm-unknown-uclinux-uclibcgnueabi
 arm-unknown-netbsdelf7.0			arm-unknown-netbsdelf7.0
+arm-unknown-none-aout				arm-unknown-none-aout
 arm-unknown-none-coff				arm-unknown-none-coff
 arm-unknown-none-eabi				arm-unknown-none-eabi
 arm-unknown-none-elf				arm-unknown-none-elf
+arm-unknown-none-pe				arm-unknown-none-pe
 arm-unknown-riscos				arm-unknown-riscos
 arm-zephyr					arm-unknown-zephyr
 arm64-apple-darwin20.0.0			aarch64-apple-darwin20.0.0