dotfiles/meta/git/hooks/pre-commit

#!/bin/sh
#
# A hook script to verify what is about to be committed.
# Called by "git commit" with no arguments. The hook should exit with non-zero
# status after issuing an appropriate message if it wants to stop the commit.
#
# To enable this hook, save this file in ".git/hooks/pre-commit".

# Source die()
. "$HOME"/.local/bin/helpers.sh

if git rev-parse --verify HEAD >/dev/null 2>&1; then
	against=HEAD
else
	# Initial commit: diff against an empty tree object
	against=$(git hash-object -t tree /dev/null)
fi

# If you want to allow non-ASCII filenames set this variable to true.
allownonascii=$(git config --type=bool hooks.allownonascii)

# Redirect output to stderr.
exec 1>&2

# Check that all filenames include only ASCII characters.
if [ "$allownonascii" != "true" ]; then
	# We exploit the fact that the printable range starts at the space
	# character and ends with tilde.
	# Note that the use of brackets around a tr range is ok here, (it's
	# even required, for portability to Solaris 10's /usr/bin/tr), since
	# the square bracket bytes happen to fall in the designated range.
	num_nonascii=$(
		git diff-index --cached --name-only --diff-filter=A -z $against \
		| LC_ALL=C tr -d '[ -~]\0' \
		| wc -c
	)
	if [ $num_nonascii != 0 ]; then
		die "Rename files with ASCII characters only, or enable hooks.allownonascii"
	fi
fi

# Check for whitespace errors.
if ! git diff-index --check --cached $against --; then
	die
fi

# Check that added symlinks are neither absolute nor broken
git diff --staged --name-only --diff-filter=AT $against \
| {
	abort=0
	while read -r line; do
		[ -h "$line" ] || continue

		target="$(readlink "$line")"
		if [ -z "${target##/*}" ]; then
			abort=1
			printf "%s\n" "$line: Absolute symlink" >&2
		fi
		if [ ! -e "$line" ]; then
			abort=1
			printf "%s\n" "$line: Broken symlink" >&2
		fi
	done
	[ "$abort" -eq 0 ] || die
} || exit

# Make sure that a deletion does not break any symlinks (including renaming a
# file)
# TODO: switch all these to null-terminated lines
deleted_files="$(git diff-index --cached --name-only --diff-filter=D $against)"
if [ -n "$deleted_files" ]; then
	# First, check for broken symlinks in the tree
	all_broken_links="$(find . -xtype l -exec stat -c '%N' '{}' '+')"

	# NOTE: The cat could be replaced by instead adding the heredoc to the
	#  `done` of the loop, but would make the code much less readable
	cat <<EOF \
	| while read -r deletion
$deleted_files
EOF
	do
		# As a first heuristic, check if there is a broken symlink with
		# a target with the same basename as the deleted file
		#
		# TODO: stat escapes quotes sometimes. Does everything work
		#  then?
		possible_links="$(
			grep "[\"'/]$(
				basename "$deletion" \
				| sed 's/[.[^$*\\]/\\&/g'
			)[\"']\$" <<EOF
$all_broken_links
EOF
		)"
		[ -n "$possible_links" ] || continue

		cat << EOF \
		| while read -r link
$possible_links
EOF
		do
			# TODO: this is probably quite brittle, depending on how
			#  `stat` quotes source and target
			target="${link##* -> [\"\']}"
			target="${target%[\"\']}"
			source="${link%%[\"\'] -> *}"
			source="${source#[\"\']}"

			if [ -z "${target##/*}" ]; then
				# absolute link
				if [ "$target" = "$PWD/$deletion" ]; then
					die "You broke the symlink $link"
				fi
			else
				# relative link
				target="$(realpath -m "$source/../$target")"
				if [ "$target" = "$PWD/$deletion" ]; then
					die "You broke the symlink $link"
				fi
			fi
		done || exit
	done || exit

	# Second, check all symlinks in the index if they still point to the
	# deleted file
	all_links_in_index="$(
		git ls-files --format="%(objectmode) %(objectname) %(path)" \
		| grep '^120000'
	)"

	cat <<EOF \
	| while read -r deletion
$deleted_files
EOF
	do
		# As a first heuristic, get all links in the tree with a target
		# with the same basename as the deleted file
		possible_links="$(
			cut -d' ' -f2 <<EOF \
			| git cat-file --batch \
			| grep -B1 "\(^\|/\)$(
				basename "$deletion" \
				| sed 's/[.[^$*\\]/\\&/g'
			)\$" \
			| paste - -
$all_links_in_index
EOF
		)"
		[ -n "$possible_links" ] || continue

		cat << EOF \
		| while read -r link
$possible_links
EOF
		do
			target="${link#*	}"
			source="$(
				grep -F "${link%% *}" <<EOF \
				| cut -d' ' -f3-
$all_links_in_index
EOF
			)"

			if [ -z "${target##/*}" ]; then
				# absolute link
				if [ "$target" = "$PWD/$deletion" ]; then
					die "You broke the symlink \"$source\" -> \"$target\""
				fi
			else
				# relative link
				target="$(realpath -m "$source/../$target")"
				if [ "$target" = "$PWD/$deletion" ]; then
					die "You broke the symlink \"$source\" -> \"$target\""
				fi
			fi
		done || exit
	done || exit

	# TODO: also check potential symlinks pointing to now empty directories
fi