scripts/library: introduce parseopts

This will replace our current options parser used in pacman-key,
makepkg, and ideally elsewhere. It follows heuristics closer to that of
GNU getopt long (and thus pacman itself), with the exception that it
does not allow for options with optional arguments. Due to the way this
parser will be used, this sort of functionality will not be needed.

Instead of relying on eval+set, options are normalized into an array,
OPTRET, which callers should expect to be populated after returning from
parseopts. This avoids problems with quotes and spaces in arguments,
assuming that the user quotes properly when passing into the
application.

A new test harness for parseopts is added in test/scripts.

Signed-off-by: Dave Reisner <dreisner@archlinux.org>

8 files changed, 315 insertions, 2 deletions

diff --git a/Makefile.am b/Makefile.am
index a024a2e6..e08b809b 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -1,4 +1,4 @@
-SUBDIRS = lib/libalpm src/util src/pacman scripts etc test/pacman test/util
+SUBDIRS = lib/libalpm src/util src/pacman scripts etc test/pacman test/util test/scripts
 if WANT_DOC
 SUBDIRS += doc
 endif
@@ -23,7 +23,7 @@ dist_pkgdata_DATA = \
 	proto/ChangeLog.proto
 
 # run the pactest test suite and vercmp tests
-check-local: test/pacman test/util src/pacman src/util
+check-local: test/pacman test/scripts test/util src/pacman src/util
 	LC_ALL=C $(PYTHON) $(top_srcdir)/test/pacman/pactest.py --debug=1 \
 		--test $(top_srcdir)/test/pacman/tests/*.py \
 		-p $(top_builddir)/src/pacman/pacman
@@ -31,6 +31,8 @@ check-local: test/pacman test/util src/pacman src/util
 		$(top_builddir)/src/util/pacsort
 	$(SH) $(top_srcdir)/test/util/vercmptest.sh \
 		$(top_builddir)/src/util/vercmp
+	$(BASH_SHELL) $(top_srcdir)/test/scripts/parseopts_test.sh \
+		$(top_srcdir)/scripts/library/parseopts.sh
 
 # create the pacman DB and cache directories upon install
 install-data-local:
diff --git a/configure.ac b/configure.ac
index 8898f146..d488bfaf 100644
--- a/configure.ac
+++ b/configure.ac
@@ -442,6 +442,7 @@ doc/Makefile
 etc/Makefile
 test/pacman/Makefile
 test/pacman/tests/Makefile
+test/scripts/Makefile
 test/util/Makefile
 contrib/Makefile
 Makefile
diff --git a/scripts/Makefile.am b/scripts/Makefile.am
index 328fbff2..7662fba6 100644
--- a/scripts/Makefile.am
+++ b/scripts/Makefile.am
@@ -27,6 +27,7 @@ EXTRA_DIST = \
 
 LIBRARY = \
 	library/output_format.sh \
+	library/parseopts.sh \
 	library/parse_options.sh
 
 # Files that should be removed, but which Automake does not know.
diff --git a/scripts/library/README b/scripts/library/README
index 1e9c962b..f43873f3 100644
--- a/scripts/library/README
+++ b/scripts/library/README
@@ -13,3 +13,23 @@ A getopt replacement to avoids portability issues, in particular the
 lack of long option name support in the default getopt provided by some
 platforms.
 Usage: parse_option $SHORT_OPTS $LONG_OPTS "$@"
+
+parseopts.sh:
+A getopt_long-like parser which portably supports longopts and shortopts
+with some GNU extensions. It does not allow for options with optional
+arguments. For both short and long opts, options requiring an argument
+should be suffixed with a colon. After the first argument containing
+the short opts, any number of valid long opts may be be passed. The end
+of the options delimiter must then be added, followed by the user arguments
+to the calling program.
+
+Reccommended Usage:
+  OPT_SHORT='fb:z'
+  OPT_LONG=('foo' 'bar:' 'baz')
+  if ! parseopts "$OPT_SHORT" "${OPT_LONG[@]}" -- "$@"; then
+    exit 1
+  fi
+  set -- "${OPTRET[@]}"
+Returns:
+  0: parse success
+  1: parse failure (error message supplied)
diff --git a/scripts/library/parseopts.sh b/scripts/library/parseopts.sh
new file mode 100644
index 00000000..11589ce3
--- /dev/null
+++ b/scripts/library/parseopts.sh
@@ -0,0 +1,141 @@
+# getopt-like parser
+parseopts() {
+	local opt= optarg= i= shortopts=$1
+	local -a longopts=() unused_argv=()
+
+	shift
+	while [[ $1 && $1 != '--' ]]; do
+		longopts+=("$1")
+		shift
+	done
+	shift
+
+	longoptmatch() {
+		local o longmatch=()
+		for o in "${longopts[@]}"; do
+			if [[ ${o%:} = "$1" ]]; then
+				longmatch=("$o")
+				break
+			fi
+			[[ ${o%:} = "$1"* ]] && longmatch+=("$o")
+		done
+
+		case ${#longmatch[*]} in
+			1)
+				# success, override with opt and return arg req (0 == none, 1 == required)
+				opt=${longmatch%:}
+				if [[ $longmatch = *: ]]; then
+					return 1
+				else
+					return 0
+				fi ;;
+			0)
+				# fail, no match found
+				return 255 ;;
+			*)
+				# fail, ambiguous match
+				printf "@SCRIPTNAME@: $(gettext "option '%s' is ambiguous; possibilities:")" "--$1"
+				printf " '%s'" "${longmatch[@]%:}"
+				printf '\n'
+				return 254 ;;
+		esac >&2
+	}
+
+	while (( $# )); do
+		case $1 in
+			--) # explicit end of options
+				shift
+				break
+				;;
+			-[!-]*) # short option
+				for (( i = 1; i < ${#1}; i++ )); do
+					opt=${1:i:1}
+
+					# option doesn't exist
+					if [[ $shortopts != *$opt* ]]; then
+						printf "@SCRIPTNAME@: $(gettext "invalid option") -- '%s'\n" "$opt" >&2
+						OPTRET=(--)
+						return 1
+					fi
+
+					OPTRET+=("-$opt")
+					# option requires optarg
+					if [[ $shortopts = *$opt:* ]]; then
+						# if we're not at the end of the option chunk, the rest is the optarg
+						if (( i < ${#1} - 1 )); then
+							OPTRET+=("${1:i+1}")
+							break
+						# if we're at the end, grab the the next positional, if it exists
+						elif (( i == ${#1} - 1 )) && [[ $2 ]]; then
+							OPTRET+=("$2")
+							shift
+							break
+						# parse failure
+						else
+							printf "@SCRIPTNAME@: $(gettext "option requires an argument") -- '%s'\n" "$opt" >&2
+							OPTRET=(--)
+							return 1
+						fi
+					fi
+				done
+				;;
+			--?*=*|--?*) # long option
+				IFS='=' read -r opt optarg <<< "${1#--}"
+				longoptmatch "$opt"
+				case $? in
+					0)
+						# parse failure
+						if [[ $optarg ]]; then
+							printf "@SCRIPTNAME@: $(gettext "option '%s' does not allow an argument")\n" "--$opt" >&2
+							OPTRET=(--)
+							return 1
+						# --longopt
+						else
+							OPTRET+=("--$opt")
+							shift
+							continue 2
+						fi
+						;;
+					1)
+						# --longopt=optarg
+						if [[ $optarg ]]; then
+							OPTRET+=("--$opt" "$optarg")
+							shift
+						# --longopt optarg
+						elif [[ $2 ]]; then
+							OPTRET+=("--$opt" "$2" )
+							shift 2
+						# parse failure
+						else
+							printf "@SCRIPTNAME@: $(gettext "option '%s' requires an argument")\n" "--$opt" >&2
+							OPTRET=(--)
+							return 1
+						fi
+						continue 2
+						;;
+					254)
+						# ambiguous option -- error was reported for us by longoptmatch()
+						OPTRET=(--)
+						return 1
+						;;
+					255)
+						# parse failure
+						printf "@SCRIPTNAME@: $(gettext "invalid option") '--%s'\n" "$opt" >&2
+						OPTRET=(--)
+						return 1
+						;;
+				esac
+				;;
+			*) # non-option arg encountered, add it as a parameter
+				unused_argv+=("$1")
+				;;
+		esac
+		shift
+	done
+
+	# add end-of-opt terminator and any leftover positional parameters
+	OPTRET+=('--' "${unused_argv[@]}" "$@")
+	unset longoptmatch
+
+	return 0
+}
diff --git a/scripts/po/POTFILES.in b/scripts/po/POTFILES.in
index 007e535f..01cc235f 100644
--- a/scripts/po/POTFILES.in
+++ b/scripts/po/POTFILES.in
@@ -9,3 +9,4 @@ scripts/pkgdelta.sh.in
 scripts/repo-add.sh.in
 scripts/library/output_format.sh
 scripts/library/parse_options.sh
+scripts/library/parseopts.sh
diff --git a/test/scripts/Makefile.am b/test/scripts/Makefile.am
new file mode 100644
index 00000000..b949e880
--- /dev/null
+++ b/test/scripts/Makefile.am
@@ -0,0 +1,9 @@
+check_SCRIPTS = \
+	parseopts_test.sh
+
+noinst_SCRIPTS = $(check_SCRIPTS)
+
+EXTRA_DIST = \
+	$(check_SCRIPTS)
+
+# vim:set ts=2 sw=2 noet:
diff --git a/test/scripts/parseopts_test.sh b/test/scripts/parseopts_test.sh
new file mode 100755
index 00000000..b5c07b5d
--- /dev/null
+++ b/test/scripts/parseopts_test.sh
@@ -0,0 +1,138 @@
+#!/bin/bash
+
+declare -i testcount=0 pass=0 fail=0
+
+# source the library function
+if [[ -z $1 || ! -f $1 ]]; then
+  printf "error: path to parseopts library not provided or does not exist\n"
+  exit 1
+fi
+. "$1"
+
+if ! type -t parseopts >/dev/null; then
+  printf 'parseopts function not found\n'
+  exit 1
+fi
+
+# borrow opts from makepkg
+OPT_SHORT="AcdefFghiLmop:rRsV"
+OPT_LONG=('allsource' 'asroot' 'ignorearch' 'check' 'clean:' 'cleanall' 'nodeps'
+          'noextract' 'force' 'forcever:' 'geninteg' 'help' 'holdver'
+          'install' 'key:' 'log' 'nocolor' 'nobuild' 'nocheck' 'nosign' 'pkg:' 'rmdeps'
+          'repackage' 'skipinteg' 'sign' 'source' 'syncdeps' 'version' 'config:'
+          'noconfirm' 'noprogressbar')
+
+parse() {
+  local result=$1 tokencount=$2; shift 2
+
+  (( ++testcount ))
+  parseopts "$OPT_SHORT" "${OPT_LONG[@]}" -- "$@" 2>/dev/null
+  test_result "$result" "$tokencount" "$*" "${OPTRET[@]}"
+  unset OPTRET
+}
+
+test_result() {
+  local result=$1 tokencount=$2 input=$3; shift 3
+
+  if [[ $result = "$*" ]] && (( tokencount == $# )); then
+    (( ++pass ))
+  else
+    printf '[TEST %3s]: FAIL\n' "$testcount"
+    printf '      input: %s\n' "$input"
+    printf '     output: %s (%s tokens)\n' "$*" "$#"
+    printf '   expected: %s (%s tokens)\n' "$result" "$tokencount"
+    echo
+    (( ++fail ))
+  fi
+}
+
+summarize() {
+  if (( !fail )); then
+    printf 'All %s tests successful\n' "$testcount"
+    exit 0
+  else
+    printf '%s of %s tests failed\n' "$fail" "$testcount"
+    exit 1
+  fi
+}
+trap 'summarize' EXIT
+
+printf 'Beginning parseopts tests\n'
+
+# usage: parse <expected result> <token count> test-params...
+# a failed parse will match only the end of options marker '--'
+
+# no options
+parse '--' 1
+
+# short options
+parse '-s -r --' 3 -s -r
+
+# short options, no spaces
+parse '-s -r --' 3 -sr
+
+# short opt missing an opt arg
+parse '--' 1 -s -p
+
+# short opt with an opt arg
+parse '-p PKGBUILD -L --' 4 -p PKGBUILD -L
+
+# short opt with an opt arg, no space
+parse '-p PKGBUILD --' 3 -pPKGBUILD
+
+# valid shortopts as a long opt
+parse '--' 1 --sir
+
+# long opt wiht no optarg
+parse '--log --' 2 --log
+
+# long opt with missing optarg
+parse '--' 1 -sr --pkg
+
+# long opt with optarg
+parse '--pkg foo --' 3 --pkg foo
+
+# long opt with optarg with whitespace
+parse '--pkg foo bar -- baz' 4 --pkg "foo bar" baz
+
+# long opt with optarg with =
+parse '--pkg foo=bar -- baz' 4 --pkg foo=bar baz
+
+# long opt with explicit optarg
+parse '--pkg bar -- foo baz' 5 foo --pkg=bar baz
+
+# long opt with explicit optarg, with whitespace
+parse '--pkg foo bar -- baz' 4 baz --pkg="foo bar"
+
+# long opt with explicit optarg that doesn't take optarg
+parse '--' 1 --force=always -s
+
+# long opt with explicit optarg with =
+parse '--pkg foo=bar --' 3 --pkg=foo=bar
+
+# explicit end of options with options after
+parse '-s -r -- foo bar baz' 6 -s -r -- foo bar baz
+
+# non-option parameters mixed in with options
+parse '-s -r -- foo baz' 5 -s foo baz -r
+
+# optarg with whitespace
+parse '-p foo bar -s --' 4 -p'foo bar' -s
+
+# non-option parameter with whitespace
+parse '-i -- foo bar' 3 -i 'foo bar'
+
+# successful stem match (opt has no arg)
+parse '--nocolor --' 2 --nocol
+
+# successful stem match (opt has arg)
+parse '--config foo --' 3 --conf foo
+
+# ambiguous long opt
+parse '--' 1 '--for'
+
+# exact match on a possible stem (--force & --forcever)
+parse '--force --' 2 --force
+
+# exact match on possible stem (opt has optarg)
+parse '--clean foo --' 3 --clean=foo