sh: Add $'quoting' (C-style escape sequences).

A string between $' and ' may contain backslash escape sequences similar to
the ones in a C string constant (except that a single-quote must be escaped
and a double-quote need not be). Details are in the sh(1) man page.

This construct is useful to include unprintable characters, tabs and
newlines in strings; while this can be done with a command substitution
containing a printf command, that needs ugly workarounds if the result is to
end with a newline as command substitution removes all trailing newlines.

The construct may also be useful in future to describe unprintable
characters without needing to write those characters themselves in 'set -x',
'export -p' and the like.

The implementation attempts to comply to the proposal for the next issue of
the POSIX specification. Because this construct is not in POSIX.1-2008,
using it in scripts intended to be portable is unwise.

Matching the minimal locale support in the rest of sh, the \u and \U
sequences are currently not useful.

Exp-run done by: pav (with some other sh(1) changes)

9 files changed, 100 insertions, 0 deletions

diff --git a/tools/regression/bin/sh/parser/dollar-quote1.0 b/tools/regression/bin/sh/parser/dollar-quote1.0
new file mode 100644
index 0000000..1206141
--- /dev/null
+++ b/tools/regression/bin/sh/parser/dollar-quote1.0
@@ -0,0 +1,12 @@
+# $FreeBSD$
+
+set -e
+
+[ $'hi' = hi ]
+[ $'hi
+there' = 'hi
+there' ]
+[ $'\"\'\\\a\b\f\t\v' = "\"'\\$(printf "\a\b\f\t\v")" ]
+[ $'hi\nthere' = 'hi
+there' ]
+[ $'a\rb' = "$(printf "a\rb")" ]
diff --git a/tools/regression/bin/sh/parser/dollar-quote2.0 b/tools/regression/bin/sh/parser/dollar-quote2.0
new file mode 100644
index 0000000..4617ed8
--- /dev/null
+++ b/tools/regression/bin/sh/parser/dollar-quote2.0
@@ -0,0 +1,5 @@
+# $FreeBSD$
+
+# This depends on the ASCII character set.
+
+[ $'\e' = "$(printf "\033")" ]
diff --git a/tools/regression/bin/sh/parser/dollar-quote3.0 b/tools/regression/bin/sh/parser/dollar-quote3.0
new file mode 100644
index 0000000..a7e6852
--- /dev/null
+++ b/tools/regression/bin/sh/parser/dollar-quote3.0
@@ -0,0 +1,22 @@
+# $FreeBSD$
+
+unset LC_ALL
+LC_CTYPE=en_US.ISO8859-1
+export LC_CTYPE
+
+e=
+for i in 0 1 2 3; do
+	for j in 0 1 2 3 4 5 6 7; do
+		for k in 0 1 2 3 4 5 6 7; do
+			case $i$j$k in
+			000) continue ;;
+			esac
+			e="$e\\$i$j$k"
+		done
+	done
+done
+ee=`printf "$e"`
+[ "${#ee}" = 255 ] || echo length bad
+
+# Start a new shell so the locale change is picked up.
+[ "$(${SH} -c "printf %s \$'$e'")" = "$ee" ]
diff --git a/tools/regression/bin/sh/parser/dollar-quote4.0 b/tools/regression/bin/sh/parser/dollar-quote4.0
new file mode 100644
index 0000000..f620af5
--- /dev/null
+++ b/tools/regression/bin/sh/parser/dollar-quote4.0
@@ -0,0 +1,19 @@
+# $FreeBSD$
+
+unset LC_ALL
+LC_CTYPE=en_US.ISO8859-1
+export LC_CTYPE
+
+e=
+for i in 0 1 2 3 4 5 6 7 8 9 a b c d e f; do
+	for j in 0 1 2 3 4 5 6 7 8 9 a b c d e f; do
+		case $i$j in
+		00) continue ;;
+		esac
+		e="$e\x$i$j"
+	done
+done
+
+# Start a new shell so the locale change is picked up.
+ee="$(${SH} -c "printf %s \$'$e'")"
+[ "${#ee}" = 255 ] || echo length bad
diff --git a/tools/regression/bin/sh/parser/dollar-quote5.0 b/tools/regression/bin/sh/parser/dollar-quote5.0
new file mode 100644
index 0000000..c2c44ca
--- /dev/null
+++ b/tools/regression/bin/sh/parser/dollar-quote5.0
@@ -0,0 +1,12 @@
+# $FreeBSD$
+
+# This depends on the ASCII character set.
+
+set -e
+
+[ $'\ca\cb\cc\cd\ce\cf\cg\ch\ci\cj\ck\cl\cm\cn\co\cp\cq\cr\cs\ct\cu\cv\cw\cx\cy\cz' = $'\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032' ]
+[ $'\cA\cB\cC\cD\cE\cF\cG\cH\cI\cJ\cK\cL\cM\cN\cO\cP\cQ\cR\cS\cT\cU\cV\cW\cX\cY\cZ' = $'\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032' ]
+[ $'\c[' = $'\033' ]
+[ $'\c]' = $'\035' ]
+[ $'\c^' = $'\036' ]
+[ $'\c_' = $'\037' ]
diff --git a/tools/regression/bin/sh/parser/dollar-quote6.0 b/tools/regression/bin/sh/parser/dollar-quote6.0
new file mode 100644
index 0000000..a4b1e3f
--- /dev/null
+++ b/tools/regression/bin/sh/parser/dollar-quote6.0
@@ -0,0 +1,5 @@
+# $FreeBSD$
+
+# This depends on the ASCII character set.
+
+[ $'\c\\' = $'\034' ]
diff --git a/tools/regression/bin/sh/parser/dollar-quote7.0 b/tools/regression/bin/sh/parser/dollar-quote7.0
new file mode 100644
index 0000000..c866b1a
--- /dev/null
+++ b/tools/regression/bin/sh/parser/dollar-quote7.0
@@ -0,0 +1,6 @@
+# $FreeBSD$
+
+set -e
+
+[ $'\u0024\u0040\u0060' = '$@`' ]
+[ $'\U00000024\U00000040\U00000060' = '$@`' ]
diff --git a/tools/regression/bin/sh/parser/dollar-quote8.0 b/tools/regression/bin/sh/parser/dollar-quote8.0
new file mode 100644
index 0000000..8f0b41a
--- /dev/null
+++ b/tools/regression/bin/sh/parser/dollar-quote8.0
@@ -0,0 +1,11 @@
+# $FreeBSD$
+
+[ $'hello\0' = hello ]
+[ $'hello\0world' = hello ]
+[ $'hello\0'$'world' = helloworld ]
+[ $'hello\000' = hello ]
+[ $'hello\000world' = hello ]
+[ $'hello\000'$'world' = helloworld ]
+[ $'hello\x00' = hello ]
+[ $'hello\x00world' = hello ]
+[ $'hello\x00'$'world' = helloworld ]
diff --git a/tools/regression/bin/sh/parser/dollar-quote9.0 b/tools/regression/bin/sh/parser/dollar-quote9.0
new file mode 100644
index 0000000..df64b7d
--- /dev/null
+++ b/tools/regression/bin/sh/parser/dollar-quote9.0
@@ -0,0 +1,8 @@
+# $FreeBSD$
+
+# POSIX and C99 say D800-DFFF are undefined in a universal character name.
+# We reject this but many other shells expand to something that looks like
+# CESU-8.
+
+v=$( (eval ": \$'\uD800'") 2>&1 >/dev/null)
+[ $? -ne 0 ] && [ -n "$v" ]