#!/bin/sh -
#
# Check spelling in comments and quoted strings from the source files.

t=__wt.$$
trap 'rm -f $t' 0 1 2 3 13 15

# Insulate against locale-specific sort order
LC_ALL=C
export LC_ALL

# If aspell has not been installed, quit
type aspell > /dev/null 2>&1 || {
	echo 'skipped: aspell not found'
	exit 0
}

# replace:
#	Create a replacement list of spelling words. This is here because the
# words we ignore changes over time and it's worth periodically collapsing
# the list. Don't it too often, the list is correct for many different aspell
# catalogs and generating a shorter list on any single system will break other
# systems.
replace() {
	aspell --mode=ccpp --lang=en_US list < ../$1 |
	sort -u |
	comm -12 /dev/stdin s_string.ok
}

# check:
#	Check the spelling of an individual file.
check() {
	# Strip out git hashes, which are seven character hex strings.
	# Strip out double quote char literals ('"'), they confuse aspell.
	sed -e 's/ [0-9a-f]\{7\} / /g' -e "s/'\"'//g" ../$2 |
	aspell --lang=en_US $1 list |
	sort -u |
	comm -23 /dev/stdin s_string.ok > $t
	test -s $t && {
		echo "==== $2"
		cat $t
	}
}

# List of files to spellchk.
l=`(cd .. &&
    find bench examples ext src test -name '*.[chsy]' &&
    find src -name '*.in')`

usage()
{
	echo 'usage: s_string [-r]' >&2
	exit 1
}
while :
	do case "$1" in
	-r)			# -r builds replacement list of OK words
		for f in $l; do
			replace $f
		done | sort -u > $t
		cp $t s_string.ok
		shift;;
	*)
		test "$#" -eq 0 || usage
		break;;
	esac
done

# Check source files.
for f in $l; do
	check "--mode=ccpp" $f
done

l="NEWS"
# Check other files.
for f in $l; do
	check "" $f
done

exit 0