chainlint.sed: stop splitting "(..." into separate lines "(" and "..."

Because `sed` is line-oriented, for ease of implementation, when
chainlint.sed encounters an opening subshell in which the first command
is cuddled with the "(", it splits the line into two lines: one
containing only "(", and the other containing whatever follows "(".
This allows chainlint.sed to get by with a single set of regular
expressions for matching shell statements rather than having to
duplicate each expression (one set for matching non-cuddled statements,
and one set for matching cuddled statements).

However, although syntactically and semantically immaterial, this
transformation has no value to test authors and might even confuse them
into thinking that the linter is misbehaving by inserting (whitespace)
line-noise into the shell code it is validating. Moreover, it also
allows an implementation detail of chainlint.sed to seep into the
chainlint self-test "expect" files, which potentially makes it difficult
to reuse the self-tests should a more capable chainlint ever be
developed.

To address these concerns, stop splitting cuddled "(..." into two lines.

Note that, as an implementation artifact, due to sed's line-oriented
nature, this change inserts a blank line at output time just before the
"(..." line is emitted. It would be possible to suppress this blank line
but doing so would add a fair bit of complexity to chainlint.sed.
Therefore, rather than suppressing the extra blank line, the Makefile's
`check-chainlint` target which runs the chainlint self-tests is instead
modified to ignore blank lines when comparing chainlint output against
the self-test "expect" output. This is a reasonable compromise for two
reasons. First, the purpose of the chainlint self-tests is to verify
that the ?!AMP?! annotations are being correctly added; precise
whitespace is immaterial. Second, by necessity, chainlint.sed itself
already throws away all blank lines within subshells since, when
checking for a broken &&-chain, it needs to check the final _statement_
in a subshell, not the final _line_ (which might be blank), thus it has
never made any attempt to precisely reproduce blank lines in its output.

Signed-off-by: Eric Sunshine <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: sunshineco

t/Makefile

@@ -72,8 +72,8 @@ clean-chainlint:
 check-chainlint:
 	@mkdir -p '$(CHAINLINTTMP_SQ)' && \
 	sed -e '/^# LINT: /d' $(patsubst %,chainlint/%.test,$(CHAINLINTTESTS)) >'$(CHAINLINTTMP_SQ)'/tests && \
-	cat $(patsubst %,chainlint/%.expect,$(CHAINLINTTESTS)) >'$(CHAINLINTTMP_SQ)'/expect && \
-	$(CHAINLINT) '$(CHAINLINTTMP_SQ)'/tests >'$(CHAINLINTTMP_SQ)'/actual && \
+	sed -e '/^[ 	]*$$/d' $(patsubst %,chainlint/%.expect,$(CHAINLINTTESTS)) >'$(CHAINLINTTMP_SQ)'/expect && \
+	$(CHAINLINT) '$(CHAINLINTTMP_SQ)'/tests | grep -v '^[	]*$$' >'$(CHAINLINTTMP_SQ)'/actual && \
 	diff -u '$(CHAINLINTTMP_SQ)'/expect '$(CHAINLINTTMP_SQ)'/actual
 
 test-lint: test-lint-duplicates test-lint-executable test-lint-shell-syntax \

t/chainlint.sed

@@ -131,11 +131,15 @@ b
 	h
 	bnextln
 }
-# "(..." line -- split off and stash "(", then process "..." as its own line
+# "(..." line -- "(" opening subshell cuddled with command; temporarily replace
+# "(" with sentinel "^" and process the line as if "(" had been seen solo on
+# the preceding line; this temporary replacement prevents several rules from
+# accidentally thinking "(" introduces a nested subshell; "^" is changed back
+# to "(" at output time
 x
-s/.*/(/
+s/.*//
 x
-s/(//
+s/(/^/
 bslurp
 
 :nextln
@@ -168,12 +172,12 @@ s/.*\n//
 	/"[^"]*#[^"]*"/!s/[ 	]#.*$//
 }
 # one-liner "case ... esac"
-/^[ 	]*case[ 	]*..*esac/bchkchn
+/^[ 	^]*case[ 	]*..*esac/bchkchn
 # multi-line "case ... esac"
-/^[ 	]*case[ 	]..*[ 	]in/bcase
+/^[ 	^]*case[ 	]..*[ 	]in/bcase
 # multi-line "for ... done" or "while ... done"
-/^[ 	]*for[ 	]..*[ 	]in/bcont
-/^[ 	]*while[ 	]/bcont
+/^[ 	^]*for[ 	]..*[ 	]in/bcont
+/^[ 	^]*while[ 	]/bcont
 /^[ 	]*do[ 	]/bcont
 /^[ 	]*do[ 	]*$/bcont
 /;[ 	]*do/bcont
@@ -184,7 +188,7 @@ s/.*\n//
 /||[ 	]*exit[ 	]/bcont
 /||[ 	]*exit[ 	]*$/bcont
 # multi-line "if...elsif...else...fi"
-/^[ 	]*if[ 	]/bcont
+/^[ 	^]*if[ 	]/bcont
 /^[ 	]*then[ 	]/bcont
 /^[ 	]*then[ 	]*$/bcont
 /;[ 	]*then/bcont
@@ -197,15 +201,15 @@ s/.*\n//
 /^[ 	]*fi[ 	]*[<>|]/bdone
 /^[ 	]*fi[ 	]*)/bdone
 # nested one-liner "(...) &&"
-/^[ 	]*(.*)[ 	]*&&[ 	]*$/bchkchn
+/^[ 	^]*(.*)[ 	]*&&[ 	]*$/bchkchn
 # nested one-liner "(...)"
-/^[ 	]*(.*)[ 	]*$/bchkchn
+/^[ 	^]*(.*)[ 	]*$/bchkchn
 # nested one-liner "(...) >x" (or "2>x" or "<x" or "|x")
-/^[ 	]*(.*)[ 	]*[0-9]*[<>|]/bchkchn
+/^[ 	^]*(.*)[ 	]*[0-9]*[<>|]/bchkchn
 # nested multi-line "(...\n...)"
-/^[ 	]*(/bnest
+/^[ 	^]*(/bnest
 # multi-line "{...\n...}"
-/^[ 	]*{/bblock
+/^[ 	^]*{/bblock
 # closing ")" on own line -- exit subshell
 /^[ 	]*)/bclssolo
 # "$((...))" -- arithmetic expansion; not closing ")"
@@ -237,6 +241,7 @@ s/.*\n//
 :cont
 # retrieve and print previous line
 x
+s/^\([ 	]*\)^/\1(/
 s/?!HERE?!/<</g
 n
 bslurp
@@ -292,6 +297,7 @@ bfolded
 # found "case ... in" -- pass through untouched
 :case
 x
+s/^\([ 	]*\)^/\1(/
 s/?!HERE?!/<</g
 n
 :cascom
@@ -326,6 +332,7 @@ bchkchn
 :nest
 x
 :nstslrp
+s/^\([ 	]*\)^/\1(/
 s/?!HERE?!/<</g
 n
 :nstcom
@@ -354,6 +361,7 @@ bchkchn
 # found multi-line "{...\n...}" block -- pass through untouched
 :block
 x
+s/^\([ 	]*\)^/\1(/
 s/?!HERE?!/<</g
 n
 :blkcom
@@ -371,17 +379,21 @@ bblock
 :clssolo
 x
 s/\( ?!AMP?!\)* ?!AMP?!$//
+s/^\([ 	]*\)^/\1(/
 s/?!HERE?!/<</g
 p
 x
+s/^\([ 	]*\)^/\1(/
 s/?!HERE?!/<</g
 b
 
 # found closing "...)" -- exit subshell loop
 :close
 x
+s/^\([ 	]*\)^/\1(/
 s/?!HERE?!/<</g
 p
 x
+s/^\([ 	]*\)^/\1(/
 s/?!HERE?!/<</g
 b

t/chainlint/close-nested-and-parent-together.expect

@@ -1,4 +1,3 @@
-(
-cd foo &&
+(cd foo &&
 	(bar &&
 		baz))

t/chainlint/complex-if-in-cuddled-loop.expect

@@ -1,5 +1,4 @@
-(
-for i in a b c; do
+(for i in a b c; do
    if test "$(echo $(waffle bat))" = "eleventeen" &&
      test "$x" = "$y"; then
      :

t/chainlint/cuddled-if-then-else.expect

@@ -1,5 +1,4 @@
-(
-if test -z ""; then
+(if test -z ""; then
     echo empty
  else
     echo bizzy

t/chainlint/cuddled-loop.expect

@@ -1,5 +1,4 @@
-(
- while read x
+( while read x
   do foobar bop || exit 1
   done <file ) &&
 outside subshell

t/chainlint/cuddled.expect

@@ -1,21 +1,17 @@
-(
-cd foo &&
+(cd foo &&
 	bar
 ) &&
 
-(
-cd foo ?!AMP?!
+(cd foo ?!AMP?!
 	bar
 ) &&
 
 (
 	cd foo &&
 	bar) &&
 
-(
-cd foo &&
+(cd foo &&
 	bar) &&
 
-(
-cd foo ?!AMP?!
+(cd foo ?!AMP?!
 	bar)

t/chainlint/inline-comment.expect

@@ -4,6 +4,5 @@
 	flibble "not a # comment"
 ) &&
 
-(
-cd foo &&
+(cd foo &&
 	flibble "not a # comment")

t/chainlint/semicolon.expect

@@ -13,8 +13,7 @@
 (
 	foo;
 ) &&
-(
-cd foo &&
+(cd foo &&
 	for i in a b c; do
 		echo;
 	done)