t/chainlint: add more chainlint.pl self-tests

During the development of chainlint.pl, numerous new self-tests were
created to verify correct functioning beyond the checks already
represented by the existing self-tests. The new checks fall into several
categories:

* behavior of the lexical analyzer for complex cases, such as line
  splicing, token pasting, entering and exiting string contexts inside
  and outside of test script bodies; for instance:

    test_expect_success 'title' '
      x=$(echo "something" |
        sed -e '\''s/\\/\\\\/g'\'' -e '\''s/[[/.*^$]/\\&/g'\''
    '

* behavior of the parser for all compound grammatical constructs, such
  as `if...fi`, `case...esac`, `while...done`, `{...}`, etc., and for
  other legal shell grammatical constructs not covered by existing
  chainlint.sed self-tests, as well as complex cases, such as:

    OUT=$( ((large_git 1>&3) | :) 3>&1 ) &&

* detection of problems, such as &&-chain breakage, from top-level to
  any depth since the existing self-tests do not cover any top-level
  context and only cover subshells one level deep due to limitations of
  chainlint.sed

* address blind spots in chainlint.sed (such as not detecting a broken
  &&-chain on a one-line for-loop in a subshell[1]) which chainlint.pl
  correctly detects

* real-world cases which tripped up chainlint.pl during its development

[1]: https://lore.kernel.org/git/dce35a47012fecc6edc11c68e91dbb485c5bc36f.1661663880.git.gitgitgadget@gmail.com/

Signed-off-by: Eric Sunshine <sunshine@sunshineco.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

t/chainlint/blank-line-before-esac.expect

@@ -0,0 +1,18 @@
+test_done ( ) {
+	case "$test_failure" in
+	0 )
+		test_at_end_hook_
+
+		exit 0 ;;
+
+	* )
+		if test $test_external_has_tap -eq 0
+		then
+			say_color error "# failed $test_failure among $msg"
+			say "1..$test_count"
+		fi
+
+		exit 1 ;;
+
+		esac
+}

t/chainlint/blank-line-before-esac.test

@@ -0,0 +1,19 @@
+# LINT: blank line before "esac"
+test_done () {
+	case "$test_failure" in
+	0)
+		test_at_end_hook_
+
+		exit 0 ;;
+
+	*)
+		if test $test_external_has_tap -eq 0
+		then
+			say_color error "# failed $test_failure among $msg"
+			say "1..$test_count"
+		fi
+
+		exit 1 ;;
+
+	esac
+}

t/chainlint/block.expect

@@ -9,4 +9,15 @@
 		echo c
 	} ?!AMP?!
 	baz
-)
+) &&
+
+{
+	echo a ; ?!AMP?! echo b
+} &&
+{ echo a ; ?!AMP?! echo b ; } &&
+
+{
+	echo "${var}9" &&
+	echo "done"
+} &&
+finis

t/chainlint/block.test

@@ -11,4 +11,17 @@
 		echo c
 	}
 	baz
-)
+) &&
+
+# LINT: ";" not allowed in place of "&&"
+{
+	echo a; echo b
+} &&
+{ echo a; echo b; } &&
+
+# LINT: "}" inside string not mistaken as end of block
+{
+	echo "${var}9" &&
+	echo "done"
+} &&
+finis

t/chainlint/chained-block.expect

@@ -0,0 +1,9 @@
+echo nobody home && {
+	test the doohicky ?!AMP?!
+	right now
+} &&
+
+GIT_EXTERNAL_DIFF=echo git diff | {
+	read path oldfile oldhex oldmode newfile newhex newmode &&
+	test "z$oh" = "z$oldhex"
+}

t/chainlint/chained-block.test

@@ -0,0 +1,11 @@
+# LINT: start of block chained to preceding command
+echo nobody home && {
+	test the doohicky
+	right now
+} &&
+
+# LINT: preceding command pipes to block on same line
+GIT_EXTERNAL_DIFF=echo git diff | {
+	read path oldfile oldhex oldmode newfile newhex newmode &&
+	test "z$oh" = "z$oldhex"
+}

t/chainlint/chained-subshell.expect

@@ -0,0 +1,10 @@
+mkdir sub && (
+	cd sub &&
+	foo the bar ?!AMP?!
+	nuff said
+) &&
+
+cut "-d " -f actual | ( read s1 s2 s3 &&
+test -f $s1 ?!AMP?!
+test $(cat $s2) = tree2path1 &&
+test $(cat $s3) = tree3path1 )

t/chainlint/chained-subshell.test

@@ -0,0 +1,13 @@
+# LINT: start of subshell chained to preceding command
+mkdir sub && (
+	cd sub &&
+	foo the bar
+	nuff said
+) &&
+
+# LINT: preceding command pipes to subshell on same line
+cut "-d " -f actual | (read s1 s2 s3 &&
+test -f $s1
+test $(cat $s2) = tree2path1 &&
+# LINT: closing subshell ")" correctly detected on same line as "$(...)"
+test $(cat $s3) = tree3path1)

t/chainlint/command-substitution-subsubshell.expect

@@ -0,0 +1,2 @@
+OUT=$(( ( large_git 1 >& 3 ) | : ) 3 >& 1) &&
+test_match_signal 13 "$OUT"

t/chainlint/command-substitution-subsubshell.test

@@ -0,0 +1,3 @@
+# LINT: subshell nested in subshell nested in command substitution
+OUT=$( ((large_git 1>&3) | :) 3>&1 ) &&
+test_match_signal 13 "$OUT"

t/chainlint/double-here-doc.expect

@@ -0,0 +1,2 @@
+run_sub_test_lib_test_err run-inv-range-start "--run invalid range start" --run="a-5" <<-EOF &&
+check_sub_test_lib_test_err run-inv-range-start <<-EOF_OUT 3 <<-EOF_ERR

t/chainlint/double-here-doc.test

@@ -0,0 +1,12 @@
+run_sub_test_lib_test_err run-inv-range-start \
+	"--run invalid range start" \
+	--run="a-5" <<-\EOF &&
+test_expect_success "passing test #1" "true"
+test_done
+EOF
+check_sub_test_lib_test_err run-inv-range-start \
+	<<-\EOF_OUT 3<<-EOF_ERR
+> FATAL: Unexpected exit with code 1
+EOF_OUT
+> error: --run: invalid non-numeric in range start: ${SQ}a-5${SQ}
+EOF_ERR

t/chainlint/dqstring-line-splice.expect

@@ -0,0 +1,3 @@
+echo 'fatal: reword option of --fixup is mutually exclusive with' '--patch/--interactive/--all/--include/--only' > expect &&
+test_must_fail git commit --fixup=reword:HEAD~ $1 2 > actual &&
+test_cmp expect actual

t/chainlint/dqstring-line-splice.test

@@ -0,0 +1,7 @@
+# LINT: line-splice within DQ-string
+'"
+echo 'fatal: reword option of --fixup is mutually exclusive with'\
+	'--patch/--interactive/--all/--include/--only' >expect &&
+test_must_fail git commit --fixup=reword:HEAD~ $1 2>actual &&
+test_cmp expect actual
+"'

t/chainlint/dqstring-no-interpolate.expect

@@ -0,0 +1,11 @@
+grep "^ ! [rejected][ ]*$BRANCH -> $BRANCH (non-fast-forward)$" out &&
+
+grep "^\.git$" output.txt &&
+
+
+(
+	cd client$version &&
+	GIT_TEST_PROTOCOL_VERSION=$version git fetch-pack --no-progress .. $(cat ../input)
+) > output &&
+	cut -d ' ' -f 2 < output | sort > actual &&
+	test_cmp expect actual

t/chainlint/dqstring-no-interpolate.test

@@ -0,0 +1,15 @@
+# LINT: regex dollar-sign eol anchor in double-quoted string not special
+grep "^ ! \[rejected\][ ]*$BRANCH -> $BRANCH (non-fast-forward)$" out &&
+
+# LINT: escaped "$" not mistaken for variable expansion
+grep "^\\.git\$" output.txt &&
+
+'"
+(
+	cd client$version &&
+# LINT: escaped dollar-sign in double-quoted test body
+	GIT_TEST_PROTOCOL_VERSION=$version git fetch-pack --no-progress .. \$(cat ../input)
+) >output &&
+	cut -d ' ' -f 2 <output | sort >actual &&
+	test_cmp expect actual
+"'

t/chainlint/empty-here-doc.expect

@@ -0,0 +1,3 @@
+git ls-tree $tree path > current &&
+cat > expected <<EOF &&
+test_output

t/chainlint/empty-here-doc.test

@@ -0,0 +1,5 @@
+git ls-tree $tree path >current &&
+# LINT: empty here-doc
+cat >expected <<\EOF &&
+EOF
+test_output

t/chainlint/exclamation.expect

@@ -0,0 +1,4 @@
+if ! condition ; then echo nope ; else yep ; fi &&
+test_prerequisite !MINGW &&
+mail uucp!address &&
+echo !whatever!

t/chainlint/exclamation.test

@@ -0,0 +1,8 @@
+# LINT: "! word" is two tokens
+if ! condition; then echo nope; else yep; fi &&
+# LINT: "!word" is single token, not two tokens "!" and "word"
+test_prerequisite !MINGW &&
+# LINT: "word!word" is single token, not three tokens "word", "!", and "word"
+mail uucp!address &&
+# LINT: "!word!" is single token, not three tokens "!", "word", and "!"
+echo !whatever!

t/chainlint/for-loop-abbreviated.expect

@@ -0,0 +1,5 @@
+for it
+do
+	path=$(expr "$it" : ( [^:]*) ) &&
+	git update-index --add "$path" || exit
+done

t/chainlint/for-loop-abbreviated.test

@@ -0,0 +1,6 @@
+# LINT: for-loop lacking optional "in [word...]" before "do"
+for it
+do
+	path=$(expr "$it" : '\([^:]*\)') &&
+	git update-index --add "$path" || exit
+done

t/chainlint/function.expect

@@ -0,0 +1,11 @@
+sha1_file ( ) {
+	echo "$*" | sed "s#..#.git/objects/&/#"
+} &&
+
+remove_object ( ) {
+	file=$(sha1_file "$*") &&
+	test -e "$file" ?!AMP?!
+	rm -f "$file"
+} ?!AMP?!
+
+sha1_file arg && remove_object arg

t/chainlint/function.test

@@ -0,0 +1,13 @@
+# LINT: "()" in function definition not mistaken for subshell
+sha1_file() {
+	echo "$*" | sed "s#..#.git/objects/&/#"
+} &&
+
+# LINT: broken &&-chain in function and after function
+remove_object() {
+	file=$(sha1_file "$*") &&
+	test -e "$file"
+	rm -f "$file"
+}
+
+sha1_file arg && remove_object arg

t/chainlint/here-doc-indent-operator.expect

@@ -0,0 +1,5 @@
+cat > expect <<-EOF &&
+
+cat > expect <<-EOF ?!AMP?!
+
+cleanup

t/chainlint/here-doc-indent-operator.test

@@ -0,0 +1,13 @@
+# LINT: whitespace between operator "<<-" and tag legal
+cat >expect <<- EOF &&
+header: 43475048 1 $(test_oid oid_version) $NUM_CHUNKS 0
+num_commits: $1
+chunks: oid_fanout oid_lookup commit_metadata generation_data bloom_indexes bloom_data
+EOF
+
+# LINT: not an indented here-doc; just a plain here-doc with tag named "-EOF"
+cat >expect << -EOF
+this is not indented
+-EOF
+
+cleanup

t/chainlint/if-condition-split.expect

@@ -0,0 +1,7 @@
+if bob &&
+   marcia ||
+   kevin
+then
+	echo "nomads" ?!AMP?!
+	echo "for sure"
+fi

t/chainlint/if-condition-split.test

@@ -0,0 +1,8 @@
+# LINT: "if" condition split across multiple lines at "&&" or "||"
+if bob &&
+   marcia ||
+   kevin
+then
+	echo "nomads"
+	echo "for sure"
+fi

t/chainlint/one-liner-for-loop.expect

@@ -0,0 +1,9 @@
+git init dir-rename-and-content &&
+(
+	cd dir-rename-and-content &&
+	test_write_lines 1 2 3 4 5 >foo &&
+	mkdir olddir &&
+	for i in a b c; do echo $i >olddir/$i; ?!LOOP?! done ?!AMP?!
+	git add foo olddir &&
+	git commit -m "original" &&
+)

t/chainlint/one-liner-for-loop.test

@@ -0,0 +1,10 @@
+git init dir-rename-and-content &&
+(
+	cd dir-rename-and-content &&
+	test_write_lines 1 2 3 4 5 >foo &&
+	mkdir olddir &&
+# LINT: one-liner for-loop missing "|| exit"; also broken &&-chain
+	for i in a b c; do echo $i >olddir/$i; done
+	git add foo olddir &&
+	git commit -m "original" &&
+)

t/chainlint/sqstring-in-sqstring.expect

@@ -0,0 +1,4 @@
+perl -e '
+	defined($_ = -s $_) or die for @ARGV;
+	exit 1 if $ARGV[0] <= $ARGV[1];
+' test-2-$packname_2.pack test-3-$packname_3.pack

t/chainlint/sqstring-in-sqstring.test

@@ -0,0 +1,5 @@
+# LINT: SQ-string Perl code fragment within SQ-string
+perl -e '\''
+	defined($_ = -s $_) or die for @ARGV;
+	exit 1 if $ARGV[0] <= $ARGV[1];
+'\'' test-2-$packname_2.pack test-3-$packname_3.pack

t/chainlint/token-pasting.expect

@@ -0,0 +1,27 @@
+git config filter.rot13.smudge ./rot13.sh &&
+git config filter.rot13.clean ./rot13.sh &&
+
+{
+    echo "*.t filter=rot13" ?!AMP?!
+    echo "*.i ident"
+} > .gitattributes &&
+
+{
+    echo a b c d e f g h i j k l m ?!AMP?!
+    echo n o p q r s t u v w x y z ?!AMP?!
+    echo '$Id$'
+} > test &&
+cat test > test.t &&
+cat test > test.o &&
+cat test > test.i &&
+git add test test.t test.i &&
+rm -f test test.t test.i &&
+git checkout -- test test.t test.i &&
+
+echo "content-test2" > test2.o &&
+echo "content-test3 - filename with special characters" > "test3 'sq',$x=.o" ?!AMP?!
+
+downstream_url_for_sed=$(
+	printf "%sn" "$downstream_url" |
+	sed -e 's/\/\\/g' -e 's/[[/.*^$]/\&/g'
+)

t/chainlint/token-pasting.test

@@ -0,0 +1,32 @@
+# LINT: single token; composite of multiple strings
+git config filter.rot13.smudge ./rot13.sh &&
+git config filter.rot13.clean ./rot13.sh &&
+
+{
+    echo "*.t filter=rot13"
+    echo "*.i ident"
+} >.gitattributes &&
+
+{
+    echo a b c d e f g h i j k l m
+    echo n o p q r s t u v w x y z
+# LINT: exit/enter string context and escaped-quote outside of string
+    echo '\''$Id$'\''
+} >test &&
+cat test >test.t &&
+cat test >test.o &&
+cat test >test.i &&
+git add test test.t test.i &&
+rm -f test test.t test.i &&
+git checkout -- test test.t test.i &&
+
+echo "content-test2" >test2.o &&
+# LINT: exit/enter string context and escaped-quote outside of string
+echo "content-test3 - filename with special characters" >"test3 '\''sq'\'',\$x=.o"
+
+# LINT: single token; composite of multiple strings
+downstream_url_for_sed=$(
+	printf "%s\n" "$downstream_url" |
+# LINT: exit/enter string context; "&" inside string not command terminator
+	sed -e '\''s/\\/\\\\/g'\'' -e '\''s/[[/.*^$]/\\&/g'\''
+)