# Use a UTF-8 locale if available, so that the UTF-8 check works.
# Use U+00A2 CENT SIGN to test whether the locale works.
-cent_sign_utf8_octal='\302\242'
-at_sign=`
- printf "${cent_sign_utf8_octal}@" |
- $awk '{print substr($0, 2)}' 2>/dev/null
-`
+cent_sign_utf8_format='\302\242\n'
+cent_sign=`printf "$cent_sign_utf8_format"`
+print_at_sign='{print substr("'$cent_sign'@", 2)}'
+at_sign=`$awk "$print_at_sign" 2>/dev/null`
if test "$at_sign" != @; then
- at_sign=`
- printf "${cent_sign_utf8_octal}@" |
- LC_ALL=en_US.UTF-8 $awk '{print substr($0, 2)}' 2>/dev/null
- `
+ at_sign=`LC_ALL=en_US.UTF-8 $awk "$print_at_sign" 2>/dev/null`
if test "$at_sign" = @; then
LC_ALL=en_US.UTF-8; export LC_ALL
fi
fi
# Check the log entry.
-exec $awk '
+exec $awk -v at_sign="$at_sign" -v cent_sign="$cent_sign" '
BEGIN {
+ # These regular expressions assume traditional Unix unibyte behavior.
+ # They are needed for old or broken versions of awk, e.g.,
+ # mawk 1.3.3 (1996), Gawk 3.0.4 (1999).
+ space = "[ \f\n\r\t\v]"
+ non_space = "[^ \f\n\r\t\v]"
+ non_print = "[\1-\37\177]"
+
+ # Prefer POSIX regular expressions if available, as they do a
+ # better job of checking. Similarly, prefer POSIX negated
+ # expressions if UTF-8 also works.
if (" " ~ /[[:space:]]/) {
space = "[[:space:]]"
- non_space = "[^[:space:]]"
- non_print = "[^[:print:]]"
- } else {
- # mawk 1.3.3 does not support POSIX bracket expressions.
- # Approximate them as best we can.
- space = "[ \f\n\r\t\v]"
- non_space = "[^ \f\n\r\t\v]"
- non_print = "[\1-\37\177]"
+ if (at_sign == "@" && cent_sign ~ /^[[:print:]]$/) {
+ non_space = "[^[:space:]]"
+ non_print = "[^[:print:]]"
+ }
}
}