Merge branch 'es/chainlint'

Revamp chainlint script for our tests.

* es/chainlint:
  chainlint: colorize problem annotations and test delimiters
  t: retire unused chainlint.sed
  t/Makefile: teach `make test` and `make prove` to run chainlint.pl
  test-lib: replace chainlint.sed with chainlint.pl
  test-lib: retire "lint harder" optimization hack
  t/chainlint: add more chainlint.pl self-tests
  chainlint.pl: allow `|| echo` to signal failure upstream of a pipe
  chainlint.pl: complain about loops lacking explicit failure handling
  chainlint.pl: don't flag broken &&-chain if failure indicated explicitly
  chainlint.pl: don't flag broken &&-chain if `$?` handled explicitly
  chainlint.pl: don't require `&` background command to end with `&&`
  t/Makefile: apply chainlint.pl to existing self-tests
  chainlint.pl: don't require `return|exit|continue` to end with `&&`
  chainlint.pl: validate test scripts in parallel
  chainlint.pl: add parser to identify test definitions
  chainlint.pl: add parser to validate tests
  chainlint.pl: add POSIX shell parser
  chainlint.pl: add POSIX shell lexical analyzer
  t: add skeleton chainlint.pl

contrib/buildsystems/CMakeLists.txt

@@ -1076,7 +1076,7 @@ if(NOT ${CMAKE_BINARY_DIR}/CMakeCache.txt STREQUAL ${CACHE_PATH})
 		"string(REPLACE \"\${GIT_BUILD_DIR_REPL}\" \"GIT_BUILD_DIR=\\\"$TEST_DIRECTORY/../${BUILD_DIR_RELATIVE}\\\"\" content \"\${content}\")\n"
 		"file(WRITE ${CMAKE_SOURCE_DIR}/t/test-lib.sh \${content})")
 	#misc copies
-	file(COPY ${CMAKE_SOURCE_DIR}/t/chainlint.sed DESTINATION ${CMAKE_BINARY_DIR}/t/)
+	file(COPY ${CMAKE_SOURCE_DIR}/t/chainlint.pl DESTINATION ${CMAKE_BINARY_DIR}/t/)
 	file(COPY ${CMAKE_SOURCE_DIR}/po/is.po DESTINATION ${CMAKE_BINARY_DIR}/po/)
 	file(COPY ${CMAKE_SOURCE_DIR}/mergetools/tkdiff DESTINATION ${CMAKE_BINARY_DIR}/mergetools/)
 	file(COPY ${CMAKE_SOURCE_DIR}/contrib/completion/git-prompt.sh DESTINATION ${CMAKE_BINARY_DIR}/contrib/completion/)

t/Makefile

@@ -36,14 +36,21 @@ CHAINLINTTMP_SQ = $(subst ','\'',$(CHAINLINTTMP))
 
 T = $(sort $(wildcard t[0-9][0-9][0-9][0-9]-*.sh))
 THELPERS = $(sort $(filter-out $(T),$(wildcard *.sh)))
+TLIBS = $(sort $(wildcard lib-*.sh)) annotate-tests.sh
 TPERF = $(sort $(wildcard perf/p[0-9][0-9][0-9][0-9]-*.sh))
+TINTEROP = $(sort $(wildcard interop/i[0-9][0-9][0-9][0-9]-*.sh))
 CHAINLINTTESTS = $(sort $(patsubst chainlint/%.test,%,$(wildcard chainlint/*.test)))
-CHAINLINT = sed -f chainlint.sed
+CHAINLINT = '$(PERL_PATH_SQ)' chainlint.pl
+
+# `test-chainlint` (which is a dependency of `test-lint`, `test` and `prove`)
+# checks all tests in all scripts via a single invocation, so tell individual
+# scripts not to "chainlint" themselves
+CHAINLINTSUPPRESS = GIT_TEST_CHAIN_LINT=0 && export GIT_TEST_CHAIN_LINT &&
 
 all: $(DEFAULT_TEST_TARGET)
 
 test: pre-clean check-chainlint $(TEST_LINT)
-	$(MAKE) aggregate-results-and-cleanup
+	$(CHAINLINTSUPPRESS) $(MAKE) aggregate-results-and-cleanup
 
 failed:
 	@failed=$$(cd '$(TEST_RESULTS_DIRECTORY_SQ)' && \
@@ -52,7 +59,7 @@ failed:
 	test -z "$$failed" || $(MAKE) $$failed
 
 prove: pre-clean check-chainlint $(TEST_LINT)
-	@echo "*** prove ***"; $(PROVE) --exec '$(TEST_SHELL_PATH_SQ)' $(GIT_PROVE_OPTS) $(T) :: $(GIT_TEST_OPTS)
+	@echo "*** prove ***"; $(CHAINLINTSUPPRESS) $(PROVE) --exec '$(TEST_SHELL_PATH_SQ)' $(GIT_PROVE_OPTS) $(T) :: $(GIT_TEST_OPTS)
 	$(MAKE) clean-except-prove-cache
 
 $(T):
@@ -73,13 +80,35 @@ clean-chainlint:
 
 check-chainlint:
 	@mkdir -p '$(CHAINLINTTMP_SQ)' && \
-	sed -e '/^# LINT: /d' $(patsubst %,chainlint/%.test,$(CHAINLINTTESTS)) >'$(CHAINLINTTMP_SQ)'/tests && \
+	for i in $(CHAINLINTTESTS); do \
-	sed -e '/^[ 	]*$$/d' $(patsubst %,chainlint/%.expect,$(CHAINLINTTESTS)) >'$(CHAINLINTTMP_SQ)'/expect && \
+		echo "test_expect_success '$$i' '" && \
-	$(CHAINLINT) '$(CHAINLINTTMP_SQ)'/tests | grep -v '^[	]*$$' >'$(CHAINLINTTMP_SQ)'/actual && \
+		sed -e '/^# LINT: /d' chainlint/$$i.test && \
-	diff -u '$(CHAINLINTTMP_SQ)'/expect '$(CHAINLINTTMP_SQ)'/actual
+		echo "'"; \
+	done >'$(CHAINLINTTMP_SQ)'/tests && \
+	{ \
+		echo "# chainlint: $(CHAINLINTTMP_SQ)/tests" && \
+		for i in $(CHAINLINTTESTS); do \
+			echo "# chainlint: $$i" && \
+			sed -e '/^[ 	]*$$/d' chainlint/$$i.expect; \
+		done \
+	} >'$(CHAINLINTTMP_SQ)'/expect && \
+	$(CHAINLINT) --emit-all '$(CHAINLINTTMP_SQ)'/tests | \
+		grep -v '^[ 	]*$$' >'$(CHAINLINTTMP_SQ)'/actual && \
+	if test -f ../GIT-BUILD-OPTIONS; then \
+		. ../GIT-BUILD-OPTIONS; \
+	fi && \
+	if test -x ../git$$X; then \
+		DIFFW="../git$$X --no-pager diff -w --no-index"; \
+	else \
+		DIFFW="diff -w -u"; \
+	fi && \
+	$$DIFFW '$(CHAINLINTTMP_SQ)'/expect '$(CHAINLINTTMP_SQ)'/actual
 
 test-lint: test-lint-duplicates test-lint-executable test-lint-shell-syntax \
 	test-lint-filenames
+ifneq ($(GIT_TEST_CHAIN_LINT),0)
+test-lint: test-chainlint
+endif
 
 test-lint-duplicates:
 	@dups=`echo $(T) $(TPERF) | tr ' ' '\n' | sed 's/-.*//' | sort | uniq -d` && \
@@ -102,6 +131,9 @@ test-lint-filenames:
 		test -z "$$bad" || { \
 		echo >&2 "non-portable file name(s): $$bad"; exit 1; }
 
+test-chainlint:
+	@$(CHAINLINT) $(T) $(TLIBS) $(TPERF) $(TINTEROP)
+
 aggregate-results-and-cleanup: $(T)
 	$(MAKE) aggregate-results
 	$(MAKE) clean
@@ -117,4 +149,5 @@ valgrind:
 perf:
 	$(MAKE) -C perf/ all
 
-.PHONY: pre-clean $(T) aggregate-results clean valgrind perf check-chainlint clean-chainlint
+.PHONY: pre-clean $(T) aggregate-results clean valgrind perf \
+	check-chainlint clean-chainlint test-chainlint

t/README

@@ -196,11 +196,6 @@ appropriately before running "make". Short options can be bundled, i.e.
 	this feature by setting the GIT_TEST_CHAIN_LINT environment
 	variable to "1" or "0", respectively.
 
-	A few test scripts disable some of the more advanced
-	chain-linting detection in the name of efficiency. You can
-	override this by setting the GIT_TEST_CHAIN_LINT_HARDER
-	environment variable to "1".
-
 --stress::
 	Run the test script repeatedly in multiple parallel jobs until
 	one of them fails.  Useful for reproducing rare failures in

t/chainlint.pl

@@ -0,0 +1,770 @@
+#!/usr/bin/env perl
+#
+# Copyright (c) 2021-2022 Eric Sunshine <sunshine@sunshineco.com>
+#
+# This tool scans shell scripts for test definitions and checks those tests for
+# problems, such as broken &&-chains, which might hide bugs in the tests
+# themselves or in behaviors being exercised by the tests.
+#
+# Input arguments are pathnames of shell scripts containing test definitions,
+# or globs referencing a collection of scripts. For each problem discovered,
+# the pathname of the script containing the test is printed along with the test
+# name and the test body with a `?!FOO?!` annotation at the location of each
+# detected problem, where "FOO" is a tag such as "AMP" which indicates a broken
+# &&-chain. Returns zero if no problems are discovered, otherwise non-zero.
+
+use warnings;
+use strict;
+use Config;
+use File::Glob;
+use Getopt::Long;
+
+my $jobs = -1;
+my $show_stats;
+my $emit_all;
+
+# Lexer tokenizes POSIX shell scripts. It is roughly modeled after section 2.3
+# "Token Recognition" of POSIX chapter 2 "Shell Command Language". Although
+# similar to lexical analyzers for other languages, this one differs in a few
+# substantial ways due to quirks of the shell command language.
+#
+# For instance, in many languages, newline is just whitespace like space or
+# TAB, but in shell a newline is a command separator, thus a distinct lexical
+# token. A newline is significant and returned as a distinct token even at the
+# end of a shell comment.
+#
+# In other languages, `1+2` would typically be scanned as three tokens
+# (`1`, `+`, and `2`), but in shell it is a single token. However, the similar
+# `1 + 2`, which embeds whitepace, is scanned as three token in shell, as well.
+# In shell, several characters with special meaning lose that meaning when not
+# surrounded by whitespace. For instance, the negation operator `!` is special
+# when standing alone surrounded by whitespace; whereas in `foo!uucp` it is
+# just a plain character in the longer token "foo!uucp". In many other
+# languages, `"string"/foo:'string'` might be scanned as five tokens ("string",
+# `/`, `foo`, `:`, and 'string'), but in shell, it is just a single token.
+#
+# The lexical analyzer for the shell command language is also somewhat unusual
+# in that it recursively invokes the parser to handle the body of `$(...)`
+# expressions which can contain arbitrary shell code. Such expressions may be
+# encountered both inside and outside of double-quoted strings.
+#
+# The lexical analyzer is responsible for consuming shell here-doc bodies which
+# extend from the line following a `<<TAG` operator until a line consisting
+# solely of `TAG`. Here-doc consumption begins when a newline is encountered.
+# It is legal for multiple here-doc `<<TAG` operators to be present on a single
+# line, in which case their bodies must be present one following the next, and
+# are consumed in the (left-to-right) order the `<<TAG` operators appear on the
+# line. A special complication is that the bodies of all here-docs must be
+# consumed when the newline is encountered even if the parse context depth has
+# changed. For instance, in `cat <<A && x=$(cat <<B &&\n`, bodies of here-docs
+# "A" and "B" must be consumed even though "A" was introduced outside the
+# recursive parse context in which "B" was introduced and in which the newline
+# is encountered.
+package Lexer;
+
+sub new {
+	my ($class, $parser, $s) = @_;
+	bless {
+		parser => $parser,
+		buff => $s,
+		heretags => []
+	} => $class;
+}
+
+sub scan_heredoc_tag {
+	my $self = shift @_;
+	${$self->{buff}} =~ /\G(-?)/gc;
+	my $indented = $1;
+	my $tag = $self->scan_token();
+	$tag =~ s/['"\\]//g;
+	push(@{$self->{heretags}}, $indented ? "\t$tag" : "$tag");
+	return "<<$indented$tag";
+}
+
+sub scan_op {
+	my ($self, $c) = @_;
+	my $b = $self->{buff};
+	return $c unless $$b =~ /\G(.)/sgc;
+	my $cc = $c . $1;
+	return scan_heredoc_tag($self) if $cc eq '<<';
+	return $cc if $cc =~ /^(?:&&|\|\||>>|;;|<&|>&|<>|>\|)$/;
+	pos($$b)--;
+	return $c;
+}
+
+sub scan_sqstring {
+	my $self = shift @_;
+	${$self->{buff}} =~ /\G([^']*'|.*\z)/sgc;
+	return "'" . $1;
+}
+
+sub scan_dqstring {
+	my $self = shift @_;
+	my $b = $self->{buff};
+	my $s = '"';
+	while (1) {
+		# slurp up non-special characters
+		$s .= $1 if $$b =~ /\G([^"\$\\]+)/gc;
+		# handle special characters
+		last unless $$b =~ /\G(.)/sgc;
+		my $c = $1;
+		$s .= '"', last if $c eq '"';
+		$s .= '$' . $self->scan_dollar(), next if $c eq '$';
+		if ($c eq '\\') {
+			$s .= '\\', last unless $$b =~ /\G(.)/sgc;
+			$c = $1;
+			next if $c eq "\n"; # line splice
+			# backslash escapes only $, `, ", \ in dq-string
+			$s .= '\\' unless $c =~ /^[\$`"\\]$/;
+			$s .= $c;
+			next;
+		}
+		die("internal error scanning dq-string '$c'\n");
+	}
+	return $s;
+}
+
+sub scan_balanced {
+	my ($self, $c1, $c2) = @_;
+	my $b = $self->{buff};
+	my $depth = 1;
+	my $s = $c1;
+	while ($$b =~ /\G([^\Q$c1$c2\E]*(?:[\Q$c1$c2\E]|\z))/gc) {
+		$s .= $1;
+		$depth++, next if $s =~ /\Q$c1\E$/;
+		$depth--;
+		last if $depth == 0;
+	}
+	return $s;
+}
+
+sub scan_subst {
+	my $self = shift @_;
+	my @tokens = $self->{parser}->parse(qr/^\)$/);
+	$self->{parser}->next_token(); # closing ")"
+	return @tokens;
+}
+
+sub scan_dollar {
+	my $self = shift @_;
+	my $b = $self->{buff};
+	return $self->scan_balanced('(', ')') if $$b =~ /\G\((?=\()/gc; # $((...))
+	return '(' . join(' ', $self->scan_subst()) . ')' if $$b =~ /\G\(/gc; # $(...)
+	return $self->scan_balanced('{', '}') if $$b =~ /\G\{/gc; # ${...}
+	return $1 if $$b =~ /\G(\w+)/gc; # $var
+	return $1 if $$b =~ /\G([@*#?$!0-9-])/gc; # $*, $1, $$, etc.
+	return '';
+}
+
+sub swallow_heredocs {
+	my $self = shift @_;
+	my $b = $self->{buff};
+	my $tags = $self->{heretags};
+	while (my $tag = shift @$tags) {
+		my $indent = $tag =~ s/^\t// ? '\\s*' : '';
+		$$b =~ /(?:\G|\n)$indent\Q$tag\E(?:\n|\z)/gc;
+	}
+}
+
+sub scan_token {
+	my $self = shift @_;
+	my $b = $self->{buff};
+	my $token = '';
+RESTART:
+	$$b =~ /\G[ \t]+/gc; # skip whitespace (but not newline)
+	return "\n" if $$b =~ /\G#[^\n]*(?:\n|\z)/gc; # comment
+	while (1) {
+		# slurp up non-special characters
+		$token .= $1 if $$b =~ /\G([^\\;&|<>(){}'"\$\s]+)/gc;
+		# handle special characters
+		last unless $$b =~ /\G(.)/sgc;
+		my $c = $1;
+		last if $c =~ /^[ \t]$/; # whitespace ends token
+		pos($$b)--, last if length($token) && $c =~ /^[;&|<>(){}\n]$/;
+		$token .= $self->scan_sqstring(), next if $c eq "'";
+		$token .= $self->scan_dqstring(), next if $c eq '"';
+		$token .= $c . $self->scan_dollar(), next if $c eq '$';
+		$self->swallow_heredocs(), $token = $c, last if $c eq "\n";
+		$token = $self->scan_op($c), last if $c =~ /^[;&|<>]$/;
+		$token = $c, last if $c =~ /^[(){}]$/;
+		if ($c eq '\\') {
+			$token .= '\\', last unless $$b =~ /\G(.)/sgc;
+			$c = $1;
+			next if $c eq "\n" && length($token); # line splice
+			goto RESTART if $c eq "\n"; # line splice
+			$token .= '\\' . $c;
+			next;
+		}
+		die("internal error scanning character '$c'\n");
+	}
+	return length($token) ? $token : undef;
+}
+
+# ShellParser parses POSIX shell scripts (with minor extensions for Bash). It
+# is a recursive descent parser very roughly modeled after section 2.10 "Shell
+# Grammar" of POSIX chapter 2 "Shell Command Language".
+package ShellParser;
+
+sub new {
+	my ($class, $s) = @_;
+	my $self = bless {
+		buff => [],
+		stop => [],
+		output => []
+	} => $class;
+	$self->{lexer} = Lexer->new($self, $s);
+	return $self;
+}
+
+sub next_token {
+	my $self = shift @_;
+	return pop(@{$self->{buff}}) if @{$self->{buff}};
+	return $self->{lexer}->scan_token();
+}
+
+sub untoken {
+	my $self = shift @_;
+	push(@{$self->{buff}}, @_);
+}
+
+sub peek {
+	my $self = shift @_;
+	my $token = $self->next_token();
+	return undef unless defined($token);
+	$self->untoken($token);
+	return $token;
+}
+
+sub stop_at {
+	my ($self, $token) = @_;
+	return 1 unless defined($token);
+	my $stop = ${$self->{stop}}[-1] if @{$self->{stop}};
+	return defined($stop) && $token =~ $stop;
+}
+
+sub expect {
+	my ($self, $expect) = @_;
+	my $token = $self->next_token();
+	return $token if defined($token) && $token eq $expect;
+	push(@{$self->{output}}, "?!ERR?! expected '$expect' but found '" . (defined($token) ? $token : "<end-of-input>") . "'\n");
+	$self->untoken($token) if defined($token);
+	return ();
+}
+
+sub optional_newlines {
+	my $self = shift @_;
+	my @tokens;
+	while (my $token = $self->peek()) {
+		last unless $token eq "\n";
+		push(@tokens, $self->next_token());
+	}
+	return @tokens;
+}
+
+sub parse_group {
+	my $self = shift @_;
+	return ($self->parse(qr/^}$/),
+		$self->expect('}'));
+}
+
+sub parse_subshell {
+	my $self = shift @_;
+	return ($self->parse(qr/^\)$/),
+		$self->expect(')'));
+}
+
+sub parse_case_pattern {
+	my $self = shift @_;
+	my @tokens;
+	while (defined(my $token = $self->next_token())) {
+		push(@tokens, $token);
+		last if $token eq ')';
+	}
+	return @tokens;
+}
+
+sub parse_case {
+	my $self = shift @_;
+	my @tokens;
+	push(@tokens,
+	     $self->next_token(), # subject
+	     $self->optional_newlines(),
+	     $self->expect('in'),
+	     $self->optional_newlines());
+	while (1) {
+		my $token = $self->peek();
+		last unless defined($token) && $token ne 'esac';
+		push(@tokens,
+		     $self->parse_case_pattern(),
+		     $self->optional_newlines(),
+		     $self->parse(qr/^(?:;;|esac)$/)); # item body
+		$token = $self->peek();
+		last unless defined($token) && $token ne 'esac';
+		push(@tokens,
+		     $self->expect(';;'),
+		     $self->optional_newlines());
+	}
+	push(@tokens, $self->expect('esac'));
+	return @tokens;
+}
+
+sub parse_for {
+	my $self = shift @_;
+	my @tokens;
+	push(@tokens,
+	     $self->next_token(), # variable
+	     $self->optional_newlines());
+	my $token = $self->peek();
+	if (defined($token) && $token eq 'in') {
+		push(@tokens,
+		     $self->expect('in'),
+		     $self->optional_newlines());
+	}
+	push(@tokens,
+	     $self->parse(qr/^do$/), # items
+	     $self->expect('do'),
+	     $self->optional_newlines(),
+	     $self->parse_loop_body(),
+	     $self->expect('done'));
+	return @tokens;
+}
+
+sub parse_if {
+	my $self = shift @_;
+	my @tokens;
+	while (1) {
+		push(@tokens,
+		     $self->parse(qr/^then$/), # if/elif condition
+		     $self->expect('then'),
+		     $self->optional_newlines(),
+		     $self->parse(qr/^(?:elif|else|fi)$/)); # if/elif body
+		my $token = $self->peek();
+		last unless defined($token) && $token eq 'elif';
+		push(@tokens, $self->expect('elif'));
+	}
+	my $token = $self->peek();
+	if (defined($token) && $token eq 'else') {
+		push(@tokens,
+		     $self->expect('else'),
+		     $self->optional_newlines(),
+		     $self->parse(qr/^fi$/)); # else body
+	}
+	push(@tokens, $self->expect('fi'));
+	return @tokens;
+}
+
+sub parse_loop_body {
+	my $self = shift @_;
+	return $self->parse(qr/^done$/);
+}
+
+sub parse_loop {
+	my $self = shift @_;
+	return ($self->parse(qr/^do$/), # condition
+		$self->expect('do'),
+		$self->optional_newlines(),
+		$self->parse_loop_body(),
+		$self->expect('done'));
+}
+
+sub parse_func {
+	my $self = shift @_;
+	return ($self->expect('('),
+		$self->expect(')'),
+		$self->optional_newlines(),
+		$self->parse_cmd()); # body
+}
+
+sub parse_bash_array_assignment {
+	my $self = shift @_;
+	my @tokens = $self->expect('(');
+	while (defined(my $token = $self->next_token())) {
+		push(@tokens, $token);
+		last if $token eq ')';
+	}
+	return @tokens;
+}
+
+my %compound = (
+	'{' => \&parse_group,
+	'(' => \&parse_subshell,
+	'case' => \&parse_case,
+	'for' => \&parse_for,
+	'if' => \&parse_if,
+	'until' => \&parse_loop,
+	'while' => \&parse_loop);
+
+sub parse_cmd {
+	my $self = shift @_;
+	my $cmd = $self->next_token();
+	return () unless defined($cmd);
+	return $cmd if $cmd eq "\n";
+
+	my $token;
+	my @tokens = $cmd;
+	if ($cmd eq '!') {
+		push(@tokens, $self->parse_cmd());
+		return @tokens;
+	} elsif (my $f = $compound{$cmd}) {
+		push(@tokens, $self->$f());
+	} elsif (defined($token = $self->peek()) && $token eq '(') {
+		if ($cmd !~ /\w=$/) {
+			push(@tokens, $self->parse_func());
+			return @tokens;
+		}
+		$tokens[-1] .= join(' ', $self->parse_bash_array_assignment());
+	}
+
+	while (defined(my $token = $self->next_token())) {
+		$self->untoken($token), last if $self->stop_at($token);
+		push(@tokens, $token);
+		last if $token =~ /^(?:[;&\n|]|&&|\|\|)$/;
+	}
+	push(@tokens, $self->next_token()) if $tokens[-1] ne "\n" && defined($token = $self->peek()) && $token eq "\n";
+	return @tokens;
+}
+
+sub accumulate {
+	my ($self, $tokens, $cmd) = @_;
+	push(@$tokens, @$cmd);
+}
+
+sub parse {
+	my ($self, $stop) = @_;
+	push(@{$self->{stop}}, $stop);
+	goto DONE if $self->stop_at($self->peek());
+	my @tokens;
+	while (my @cmd = $self->parse_cmd()) {
+		$self->accumulate(\@tokens, \@cmd);
+		last if $self->stop_at($self->peek());
+	}
+DONE:
+	pop(@{$self->{stop}});
+	return @tokens;
+}
+
+# TestParser is a subclass of ShellParser which, beyond parsing shell script
+# code, is also imbued with semantic knowledge of test construction, and checks
+# tests for common problems (such as broken &&-chains) which might hide bugs in
+# the tests themselves or in behaviors being exercised by the tests. As such,
+# TestParser is only called upon to parse test bodies, not the top-level
+# scripts in which the tests are defined.
+package TestParser;
+
+use base 'ShellParser';
+
+sub find_non_nl {
+	my $tokens = shift @_;
+	my $n = shift @_;
+	$n = $#$tokens if !defined($n);
+	$n-- while $n >= 0 && $$tokens[$n] eq "\n";
+	return $n;
+}
+
+sub ends_with {
+	my ($tokens, $needles) = @_;
+	my $n = find_non_nl($tokens);
+	for my $needle (reverse(@$needles)) {
+		return undef if $n < 0;
+		$n = find_non_nl($tokens, $n), next if $needle eq "\n";
+		return undef if $$tokens[$n] !~ $needle;
+		$n--;
+	}
+	return 1;
+}
+
+sub match_ending {
+	my ($tokens, $endings) = @_;
+	for my $needles (@$endings) {
+		next if @$tokens < scalar(grep {$_ ne "\n"} @$needles);
+		return 1 if ends_with($tokens, $needles);
+	}
+	return undef;
+}
+
+sub parse_loop_body {
+	my $self = shift @_;
+	my @tokens = $self->SUPER::parse_loop_body(@_);
+	# did loop signal failure via "|| return" or "|| exit"?
+	return @tokens if !@tokens || grep(/^(?:return|exit|\$\?)$/, @tokens);
+	# did loop upstream of a pipe signal failure via "|| echo 'impossible
+	# text'" as the final command in the loop body?
+	return @tokens if ends_with(\@tokens, [qr/^\|\|$/, "\n", qr/^echo$/, qr/^.+$/]);
+	# flag missing "return/exit" handling explicit failure in loop body
+	my $n = find_non_nl(\@tokens);
+	splice(@tokens, $n + 1, 0, '?!LOOP?!');
+	return @tokens;
+}
+
+my @safe_endings = (
+	[qr/^(?:&&|\|\||\||&)$/],
+	[qr/^(?:exit|return)$/, qr/^(?:\d+|\$\?)$/],
+	[qr/^(?:exit|return)$/, qr/^(?:\d+|\$\?)$/, qr/^;$/],
+	[qr/^(?:exit|return|continue)$/],
+	[qr/^(?:exit|return|continue)$/, qr/^;$/]);
+
+sub accumulate {
+	my ($self, $tokens, $cmd) = @_;
+	goto DONE unless @$tokens;
+	goto DONE if @$cmd == 1 && $$cmd[0] eq "\n";
+
+	# did previous command end with "&&", "|", "|| return" or similar?
+	goto DONE if match_ending($tokens, \@safe_endings);
+
+	# if this command handles "$?" specially, then okay for previous
+	# command to be missing "&&"
+	for my $token (@$cmd) {
+		goto DONE if $token =~ /\$\?/;
+	}
+
+	# if this command is "false", "return 1", or "exit 1" (which signal
+	# failure explicitly), then okay for all preceding commands to be
+	# missing "&&"
+	if ($$cmd[0] =~ /^(?:false|return|exit)$/) {
+		@$tokens = grep(!/^\?!AMP\?!$/, @$tokens);
+		goto DONE;
+	}
+
+	# flag missing "&&" at end of previous command
+	my $n = find_non_nl($tokens);
+	splice(@$tokens, $n + 1, 0, '?!AMP?!') unless $n < 0;
+
+DONE:
+	$self->SUPER::accumulate($tokens, $cmd);
+}
+
+# ScriptParser is a subclass of ShellParser which identifies individual test
+# definitions within test scripts, and passes each test body through TestParser
+# to identify possible problems. ShellParser detects test definitions not only
+# at the top-level of test scripts but also within compound commands such as
+# loops and function definitions.
+package ScriptParser;
+
+use base 'ShellParser';
+
+sub new {
+	my $class = shift @_;
+	my $self = $class->SUPER::new(@_);
+	$self->{ntests} = 0;
+	return $self;
+}
+
+# extract the raw content of a token, which may be a single string or a
+# composition of multiple strings and non-string character runs; for instance,
+# `"test body"` unwraps to `test body`; `word"a b"42'c d'` to `worda b42c d`
+sub unwrap {
+	my $token = @_ ? shift @_ : $_;
+	# simple case: 'sqstring' or "dqstring"
+	return $token if $token =~ s/^'([^']*)'$/$1/;
+	return $token if $token =~ s/^"([^"]*)"$/$1/;
+
+	# composite case
+	my ($s, $q, $escaped);
+	while (1) {
+		# slurp up non-special characters
+		$s .= $1 if $token =~ /\G([^\\'"]*)/gc;
+		# handle special characters
+		last unless $token =~ /\G(.)/sgc;
+		my $c = $1;
+		$q = undef, next if defined($q) && $c eq $q;
+		$q = $c, next if !defined($q) && $c =~ /^['"]$/;
+		if ($c eq '\\') {
+			last unless $token =~ /\G(.)/sgc;
+			$c = $1;
+			$s .= '\\' if $c eq "\n"; # preserve line splice
+		}
+		$s .= $c;
+	}
+	return $s
+}
+
+sub check_test {
+	my $self = shift @_;
+	my ($title, $body) = map(unwrap, @_);
+	$self->{ntests}++;
+	my $parser = TestParser->new(\$body);
+	my @tokens = $parser->parse();
+	return unless $emit_all || grep(/\?![^?]+\?!/, @tokens);
+	my $c = main::fd_colors(1);
+	my $checked = join(' ', @tokens);
+	$checked =~ s/^\n//;
+	$checked =~ s/^ //mg;
+	$checked =~ s/ $//mg;
+	$checked =~ s/(\?![^?]+\?!)/$c->{rev}$c->{red}$1$c->{reset}/mg;
+	$checked .= "\n" unless $checked =~ /\n$/;
+	push(@{$self->{output}}, "$c->{blue}# chainlint: $title$c->{reset}\n$checked");
+}
+
+sub parse_cmd {
+	my $self = shift @_;
+	my @tokens = $self->SUPER::parse_cmd();
+	return @tokens unless @tokens && $tokens[0] =~ /^test_expect_(?:success|failure)$/;
+	my $n = $#tokens;
+	$n-- while $n >= 0 && $tokens[$n] =~ /^(?:[;&\n|]|&&|\|\|)$/;
+	$self->check_test($tokens[1], $tokens[2]) if $n == 2; # title body
+	$self->check_test($tokens[2], $tokens[3]) if $n > 2;  # prereq title body
+	return @tokens;
+}
+
+# main contains high-level functionality for processing command-line switches,
+# feeding input test scripts to ScriptParser, and reporting results.
+package main;
+
+my $getnow = sub { return time(); };
+my $interval = sub { return time() - shift; };
+if (eval {require Time::HiRes; Time::HiRes->import(); 1;}) {
+	$getnow = sub { return [Time::HiRes::gettimeofday()]; };
+	$interval = sub { return Time::HiRes::tv_interval(shift); };
+}
+
+# Restore TERM if test framework set it to "dumb" so 'tput' will work; do this
+# outside of get_colors() since under 'ithreads' all threads use %ENV of main
+# thread and ignore %ENV changes in subthreads.
+$ENV{TERM} = $ENV{USER_TERM} if $ENV{USER_TERM};
+
+my @NOCOLORS = (bold => '', rev => '', reset => '', blue => '', green => '', red => '');
+my %COLORS = ();
+sub get_colors {
+	return \%COLORS if %COLORS;
+	if (exists($ENV{NO_COLOR}) ||
+	    system("tput sgr0 >/dev/null 2>&1") != 0 ||
+	    system("tput bold >/dev/null 2>&1") != 0 ||
+	    system("tput rev  >/dev/null 2>&1") != 0 ||
+	    system("tput setaf 1 >/dev/null 2>&1") != 0) {
+		%COLORS = @NOCOLORS;
+		return \%COLORS;
+	}
+	%COLORS = (bold  => `tput bold`,
+		   rev   => `tput rev`,
+		   reset => `tput sgr0`,
+		   blue  => `tput setaf 4`,
+		   green => `tput setaf 2`,
+		   red   => `tput setaf 1`);
+	chomp(%COLORS);
+	return \%COLORS;
+}
+
+my %FD_COLORS = ();
+sub fd_colors {
+	my $fd = shift;
+	return $FD_COLORS{$fd} if exists($FD_COLORS{$fd});
+	$FD_COLORS{$fd} = -t $fd ? get_colors() : {@NOCOLORS};
+	return $FD_COLORS{$fd};
+}
+
+sub ncores {
+	# Windows
+	return $ENV{NUMBER_OF_PROCESSORS} if exists($ENV{NUMBER_OF_PROCESSORS});
+	# Linux / MSYS2 / Cygwin / WSL
+	do { local @ARGV='/proc/cpuinfo'; return scalar(grep(/^processor\s*:/, <>)); } if -r '/proc/cpuinfo';
+	# macOS & BSD
+	return qx/sysctl -n hw.ncpu/ if $^O =~ /(?:^darwin$|bsd)/;
+	return 1;
+}
+
+sub show_stats {
+	my ($start_time, $stats) = @_;
+	my $walltime = $interval->($start_time);
+	my ($usertime) = times();
+	my ($total_workers, $total_scripts, $total_tests, $total_errs) = (0, 0, 0, 0);
+	my $c = fd_colors(2);
+	print(STDERR $c->{green});
+	for (@$stats) {
+		my ($worker, $nscripts, $ntests, $nerrs) = @$_;
+		print(STDERR "worker $worker: $nscripts scripts, $ntests tests, $nerrs errors\n");
+		$total_workers++;
+		$total_scripts += $nscripts;
+		$total_tests += $ntests;
+		$total_errs += $nerrs;
+	}
+	printf(STDERR "total: %d workers, %d scripts, %d tests, %d errors, %.2fs/%.2fs (wall/user)$c->{reset}\n", $total_workers, $total_scripts, $total_tests, $total_errs, $walltime, $usertime);
+}
+
+sub check_script {
+	my ($id, $next_script, $emit) = @_;
+	my ($nscripts, $ntests, $nerrs) = (0, 0, 0);
+	while (my $path = $next_script->()) {
+		$nscripts++;
+		my $fh;
+		unless (open($fh, "<", $path)) {
+			$emit->("?!ERR?! $path: $!\n");
+			next;
+		}
+		my $s = do { local $/; <$fh> };
+		close($fh);
+		my $parser = ScriptParser->new(\$s);
+		1 while $parser->parse_cmd();
+		if (@{$parser->{output}}) {
+			my $c = fd_colors(1);
+			my $s = join('', @{$parser->{output}});
+			$emit->("$c->{bold}$c->{blue}# chainlint: $path$c->{reset}\n" . $s);
+			$nerrs += () = $s =~ /\?![^?]+\?!/g;
+		}
+		$ntests += $parser->{ntests};
+	}
+	return [$id, $nscripts, $ntests, $nerrs];
+}
+
+sub exit_code {
+	my $stats = shift @_;
+	for (@$stats) {
+		my ($worker, $nscripts, $ntests, $nerrs) = @$_;
+		return 1 if $nerrs;
+	}
+	return 0;
+}
+
+Getopt::Long::Configure(qw{bundling});
+GetOptions(
+	"emit-all!" => \$emit_all,
+	"jobs|j=i" => \$jobs,
+	"stats|show-stats!" => \$show_stats) or die("option error\n");
+$jobs = ncores() if $jobs < 1;
+
+my $start_time = $getnow->();
+my @stats;
+
+my @scripts;
+push(@scripts, File::Glob::bsd_glob($_)) for (@ARGV);
+unless (@scripts) {
+	show_stats($start_time, \@stats) if $show_stats;
+	exit;
+}
+
+unless ($Config{useithreads} && eval {
+	require threads; threads->import();
+	require Thread::Queue; Thread::Queue->import();
+	1;
+	}) {
+	push(@stats, check_script(1, sub { shift(@scripts); }, sub { print(@_); }));
+	show_stats($start_time, \@stats) if $show_stats;
+	exit(exit_code(\@stats));
+}
+
+my $script_queue = Thread::Queue->new();
+my $output_queue = Thread::Queue->new();
+
+sub next_script { return $script_queue->dequeue(); }
+sub emit { $output_queue->enqueue(@_); }
+
+sub monitor {
+	while (my $s = $output_queue->dequeue()) {
+		print($s);
+	}
+}
+
+my $mon = threads->create({'context' => 'void'}, \&monitor);
+threads->create({'context' => 'list'}, \&check_script, $_, \&next_script, \&emit) for 1..$jobs;
+
+$script_queue->enqueue(@scripts);
+$script_queue->end();
+
+for (threads->list()) {
+	push(@stats, $_->join()) unless $_ == $mon;
+}
+
+$output_queue->end();
+$mon->join();
+
+show_stats($start_time, \@stats) if $show_stats;
+exit(exit_code(\@stats));

t/chainlint.sed

@@ -1,399 +0,0 @@
-#------------------------------------------------------------------------------
-# Detect broken &&-chains in tests.
-#
-# At present, only &&-chains in subshells are examined by this linter;
-# top-level &&-chains are instead checked directly by the test framework. Like
-# the top-level &&-chain linter, the subshell linter (intentionally) does not
-# check &&-chains within {...} blocks.
-#
-# Checking for &&-chain breakage is done line-by-line by pure textual
-# inspection.
-#
-# Incomplete lines (those ending with "\") are stitched together with following
-# lines to simplify processing, particularly of "one-liner" statements.
-# Top-level here-docs are swallowed to avoid false positives within the
-# here-doc body, although the statement to which the here-doc is attached is
-# retained.
-#
-# Heuristics are used to detect end-of-subshell when the closing ")" is cuddled
-# with the final subshell statement on the same line:
-#
-#    (cd foo &&
-#        bar)
-#
-# in order to avoid misinterpreting the ")" in constructs such as "x=$(...)"
-# and "case $x in *)" as ending the subshell.
-#
-# Lines missing a final "&&" are flagged with "?!AMP?!", as are lines which
-# chain commands with ";" internally rather than "&&". A line may be flagged
-# for both violations.
-#
-# Detection of a missing &&-link in a multi-line subshell is complicated by the
-# fact that the last statement before the closing ")" must not end with "&&".
-# Since processing is line-by-line, it is not known whether a missing "&&" is
-# legitimate or not until the _next_ line is seen. To accommodate this, within
-# multi-line subshells, each line is stored in sed's "hold" area until after
-# the next line is seen and processed. If the next line is a stand-alone ")",
-# then a missing "&&" on the previous line is legitimate; otherwise a missing
-# "&&" is a break in the &&-chain.
-#
-#    (
-#         cd foo &&
-#         bar
-#    )
-#
-# In practical terms, when "bar" is encountered, it is flagged with "?!AMP?!",
-# but when the stand-alone ")" line is seen which closes the subshell, the
-# "?!AMP?!" violation is removed from the "bar" line (retrieved from the "hold"
-# area) since the final statement of a subshell must not end with "&&". The
-# final line of a subshell may still break the &&-chain by using ";" internally
-# to chain commands together rather than "&&", but an internal "?!AMP?!" is
-# never removed from a line even though a line-ending "?!AMP?!" might be.
-#
-# Care is taken to recognize the last _statement_ of a multi-line subshell, not
-# necessarily the last textual _line_ within the subshell, since &&-chaining
-# applies to statements, not to lines. Consequently, blank lines, comment
-# lines, and here-docs are swallowed (but not the command to which the here-doc
-# is attached), leaving the last statement in the "hold" area, not the last
-# line, thus simplifying &&-link checking.
-#
-# The final statement before "done" in for- and while-loops, and before "elif",
-# "else", and "fi" in if-then-else likewise must not end with "&&", thus
-# receives similar treatment.
-#
-# Swallowing here-docs with arbitrary tags requires a bit of finesse. When a
-# line such as "cat <<EOF" is seen, the here-doc tag is copied to the front of
-# the line enclosed in angle brackets as a sentinel, giving "<EOF>cat <<EOF".
-# As each subsequent line is read, it is appended to the target line and a
-# (whitespace-loose) back-reference match /^<(.*)>\n\1$/ is attempted to see if
-# the content inside "<...>" matches the entirety of the newly-read line. For
-# instance, if the next line read is "some data", when concatenated with the
-# target line, it becomes "<EOF>cat <<EOF\nsome data", and a match is attempted
-# to see if "EOF" matches "some data". Since it doesn't, the next line is
-# attempted. When a line consisting of only "EOF" (and possible whitespace) is
-# encountered, it is appended to the target line giving "<EOF>cat <<EOF\nEOF",
-# in which case the "EOF" inside "<...>" does match the text following the
-# newline, thus the closing here-doc tag has been found. The closing tag line
-# and the "<...>" prefix on the target line are then discarded, leaving just
-# the target line "cat <<EOF".
-#------------------------------------------------------------------------------
-
-# incomplete line -- slurp up next line
-:squash
-/\\$/ {
-	N
-	s/\\\n//
-	bsquash
-}
-
-# here-doc -- swallow it to avoid false hits within its body (but keep the
-# command to which it was attached)
-/<<-*[ 	]*[\\'"]*[A-Za-z0-9_]/ {
-	/"[^"]*<<[^"]*"/bnotdoc
-	s/^\(.*<<-*[ 	]*\)[\\'"]*\([A-Za-z0-9_][A-Za-z0-9_]*\)['"]*/<\2>\1\2/
-	:hered
-	N
-	/^<\([^>]*\)>.*\n[ 	]*\1[ 	]*$/!{
-		s/\n.*$//
-		bhered
-	}
-	s/^<[^>]*>//
-	s/\n.*$//
-}
-:notdoc
-
-# one-liner "(...) &&"
-/^[ 	]*!*[ 	]*(..*)[ 	]*&&[ 	]*$/boneline
-
-# same as above but without trailing "&&"
-/^[ 	]*!*[ 	]*(..*)[ 	]*$/boneline
-
-# one-liner "(...) >x" (or "2>x" or "<x" or "|x" or "&"
-/^[ 	]*!*[ 	]*(..*)[ 	]*[0-9]*[<>|&]/boneline
-
-# multi-line "(...\n...)"
-/^[ 	]*(/bsubsh
-
-# innocuous line -- print it and advance to next line
-b
-
-# found one-liner "(...)" -- mark suspect if it uses ";" internally rather than
-# "&&" (but not ";" in a string)
-:oneline
-/;/{
-	/"[^"]*;[^"]*"/!s/;/; ?!AMP?!/
-}
-b
-
-:subsh
-# bare "(" line? -- stash for later printing
-/^[ 	]*([	]*$/ {
-	h
-	bnextln
-}
-# "(..." 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/.*//
-x
-s/(/^/
-bslurp
-
-:nextln
-N
-s/.*\n//
-
-:slurp
-# incomplete line "...\"
-/\\$/bicmplte
-# multi-line quoted string "...\n..."?
-/"/bdqstr
-# multi-line quoted string '...\n...'? (but not contraction in string "it's")
-/'/{
-	/"[^'"]*'[^'"]*"/!bsqstr
-}
-:folded
-# here-doc -- swallow it (but not "<<" in a string)
-/<<-*[ 	]*[\\'"]*[A-Za-z0-9_]/{
-	/"[^"]*<<[^"]*"/!bheredoc
-}
-# comment or empty line -- discard since final non-comment, non-empty line
-# before closing ")", "done", "elsif", "else", or "fi" will need to be
-# re-visited to drop "suspect" marking since final line of those constructs
-# legitimately lacks "&&", so "suspect" mark must be removed
-/^[ 	]*#/bnextln
-/^[ 	]*$/bnextln
-# in-line comment -- strip it (but not "#" in a string, Bash ${#...} array
-# length, or Perforce "//depot/path#42" revision in filespec)
-/[ 	]#/{
-	/"[^"]*#[^"]*"/!s/[ 	]#.*$//
-}
-# one-liner "case ... esac"
-/^[ 	^]*case[ 	]*..*esac/bchkchn
-# multi-line "case ... esac"
-/^[ 	^]*case[ 	]..*[ 	]in/bcase
-# multi-line "for ... done" or "while ... done"
-/^[ 	^]*for[ 	]..*[ 	]in/bcont
-/^[ 	^]*while[ 	]/bcont
-/^[ 	]*do[ 	]/bcont
-/^[ 	]*do[ 	]*$/bcont
-/;[ 	]*do/bcont
-/^[ 	]*done[ 	]*&&[ 	]*$/bdone
-/^[ 	]*done[ 	]*$/bdone
-/^[ 	]*done[ 	]*[<>|]/bdone
-/^[ 	]*done[ 	]*)/bdone
-/||[ 	]*exit[ 	]/bcont
-/||[ 	]*exit[ 	]*$/bcont
-# multi-line "if...elsif...else...fi"
-/^[ 	^]*if[ 	]/bcont
-/^[ 	]*then[ 	]/bcont
-/^[ 	]*then[ 	]*$/bcont
-/;[ 	]*then/bcont
-/^[ 	]*elif[ 	]/belse
-/^[ 	]*elif[ 	]*$/belse
-/^[ 	]*else[ 	]/belse
-/^[ 	]*else[ 	]*$/belse
-/^[ 	]*fi[ 	]*&&[ 	]*$/bdone
-/^[ 	]*fi[ 	]*$/bdone
-/^[ 	]*fi[ 	]*[<>|]/bdone
-/^[ 	]*fi[ 	]*)/bdone
-# nested one-liner "(...) &&"
-/^[ 	^]*(.*)[ 	]*&&[ 	]*$/bchkchn
-# nested one-liner "(...)"
-/^[ 	^]*(.*)[ 	]*$/bchkchn
-# nested one-liner "(...) >x" (or "2>x" or "<x" or "|x")
-/^[ 	^]*(.*)[ 	]*[0-9]*[<>|]/bchkchn
-# nested multi-line "(...\n...)"
-/^[ 	^]*(/bnest
-# multi-line "{...\n...}"
-/^[ 	^]*{/bblock
-# closing ")" on own line -- exit subshell
-/^[ 	]*)/bclssolo
-# "$((...))" -- arithmetic expansion; not closing ")"
-/\$(([^)][^)]*))[^)]*$/bchkchn
-# "$(...)" -- command substitution; not closing ")"
-/\$([^)][^)]*)[^)]*$/bchkchn
-# multi-line "$(...\n...)" -- command substitution; treat as nested subshell
-/\$([^)]*$/bnest
-# "=(...)" -- Bash array assignment; not closing ")"
-/=(/bchkchn
-# closing "...) &&"
-/)[ 	]*&&[ 	]*$/bclose
-# closing "...)"
-/)[ 	]*$/bclose
-# closing "...) >x" (or "2>x" or "<x" or "|x")
-/)[ 	]*[<>|]/bclose
-:chkchn
-# mark suspect if line uses ";" internally rather than "&&" (but not ";" in a
-# string and not ";;" in one-liner "case...esac")
-/;/{
-	/;;/!{
-		/"[^"]*;[^"]*"/!s/;/; ?!AMP?!/
-	}
-}
-# line ends with pipe "...|" -- valid; not missing "&&"
-/|[ 	]*$/bcont
-# missing end-of-line "&&" -- mark suspect
-/&&[ 	]*$/!s/$/ ?!AMP?!/
-:cont
-# retrieve and print previous line
-x
-s/^\([ 	]*\)^/\1(/
-s/?!HERE?!/<</g
-n
-bslurp
-
-# found incomplete line "...\" -- slurp up next line
-:icmplte
-N
-s/\\\n//
-bslurp
-
-# check for multi-line double-quoted string "...\n..." -- fold to one line
-:dqstr
-# remove all quote pairs
-s/"\([^"]*\)"/@!\1@!/g
-# done if no dangling quote
-/"/!bdqdone
-# otherwise, slurp next line and try again
-N
-s/\n//
-bdqstr
-:dqdone
-s/@!/"/g
-bfolded
-
-# check for multi-line single-quoted string '...\n...' -- fold to one line
-:sqstr
-# remove all quote pairs
-s/'\([^']*\)'/@!\1@!/g
-# done if no dangling quote
-/'/!bsqdone
-# otherwise, slurp next line and try again
-N
-s/\n//
-bsqstr
-:sqdone
-s/@!/'/g
-bfolded
-
-# found here-doc -- swallow it to avoid false hits within its body (but keep
-# the command to which it was attached)
-:heredoc
-s/^\(.*\)<<\(-*[ 	]*\)[\\'"]*\([A-Za-z0-9_][A-Za-z0-9_]*\)['"]*/<\3>\1?!HERE?!\2\3/
-:hdocsub
-N
-/^<\([^>]*\)>.*\n[ 	]*\1[ 	]*$/!{
-	s/\n.*$//
-	bhdocsub
-}
-s/^<[^>]*>//
-s/\n.*$//
-bfolded
-
-# found "case ... in" -- pass through untouched
-:case
-x
-s/^\([ 	]*\)^/\1(/
-s/?!HERE?!/<</g
-n
-:cascom
-/^[ 	]*#/{
-	N
-	s/.*\n//
-	bcascom
-}
-/^[ 	]*esac/bslurp
-bcase
-
-# found "else" or "elif" -- drop "suspect" from final line before "else" since
-# that line legitimately lacks "&&"
-:else
-x
-s/\( ?!AMP?!\)* ?!AMP?!$//
-x
-bcont
-
-# found "done" closing for-loop or while-loop, or "fi" closing if-then -- drop
-# "suspect" from final contained line since that line legitimately lacks "&&"
-:done
-x
-s/\( ?!AMP?!\)* ?!AMP?!$//
-x
-# is 'done' or 'fi' cuddled with ")" to close subshell?
-/done.*)/bclose
-/fi.*)/bclose
-bchkchn
-
-# found nested multi-line "(...\n...)" -- pass through untouched
-:nest
-x
-:nstslrp
-s/^\([ 	]*\)^/\1(/
-s/?!HERE?!/<</g
-n
-:nstcom
-# comment -- not closing ")" if in comment
-/^[ 	]*#/{
-	N
-	s/.*\n//
-	bnstcom
-}
-# closing ")" on own line -- stop nested slurp
-/^[ 	]*)/bnstcl
-# "$((...))" -- arithmetic expansion; not closing ")"
-/\$(([^)][^)]*))[^)]*$/bnstcnt
-# "$(...)" -- command substitution; not closing ")"
-/\$([^)][^)]*)[^)]*$/bnstcnt
-# closing "...)" -- stop nested slurp
-/)/bnstcl
-:nstcnt
-x
-bnstslrp
-:nstcl
-# is it "))" which closes nested and parent subshells?
-/)[ 	]*)/bslurp
-bchkchn
-
-# found multi-line "{...\n...}" block -- pass through untouched
-:block
-x
-s/^\([ 	]*\)^/\1(/
-s/?!HERE?!/<</g
-n
-:blkcom
-/^[ 	]*#/{
-	N
-	s/.*\n//
-	bblkcom
-}
-# closing "}" -- stop block slurp
-/}/bchkchn
-bblock
-
-# found closing ")" on own line -- drop "suspect" from final line of subshell
-# since that line legitimately lacks "&&" and exit subshell loop
-: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/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

@@ -1,7 +1,7 @@
 (
 	foo &&
 	{
-		echo a
+		echo a ?!AMP?!
 		echo b
 	} &&
 	bar &&
@@ -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/chain-break-background.expect

@@ -0,0 +1,9 @@
+JGIT_DAEMON_PID= &&
+git init --bare empty.git &&
+> empty.git/git-daemon-export-ok &&
+mkfifo jgit_daemon_output &&
+{
+	jgit daemon --port="$JGIT_DAEMON_PORT" . > jgit_daemon_output &
+	JGIT_DAEMON_PID=$!
+} &&
+test_expect_code 2 git ls-remote --exit-code git://localhost:$JGIT_DAEMON_PORT/empty.git

t/chainlint/chain-break-background.test

@@ -0,0 +1,10 @@
+JGIT_DAEMON_PID= &&
+git init --bare empty.git &&
+>empty.git/git-daemon-export-ok &&
+mkfifo jgit_daemon_output &&
+{
+# LINT: exit status of "&" is always 0 so &&-chaining immaterial
+	jgit daemon --port="$JGIT_DAEMON_PORT" . >jgit_daemon_output &
+	JGIT_DAEMON_PID=$!
+} &&
+test_expect_code 2 git ls-remote --exit-code git://localhost:$JGIT_DAEMON_PORT/empty.git

t/chainlint/chain-break-continue.expect

@@ -0,0 +1,12 @@
+git ls-tree --name-only -r refs/notes/many_notes |
+while read path
+do
+	test "$path" = "foobar/non-note.txt" && continue
+	test "$path" = "deadbeef" && continue
+	test "$path" = "de/adbeef" && continue
+
+	if test $(expr length "$path") -ne $hexsz
+	then
+		return 1
+	fi
+done

t/chainlint/chain-break-continue.test

@@ -0,0 +1,13 @@
+git ls-tree --name-only -r refs/notes/many_notes |
+while read path
+do
+# LINT: broken &&-chain okay if explicit "continue"
+	test "$path" = "foobar/non-note.txt" && continue
+	test "$path" = "deadbeef" && continue
+	test "$path" = "de/adbeef" && continue
+
+	if test $(expr length "$path") -ne $hexsz
+	then
+		return 1
+	fi
+done

t/chainlint/chain-break-false.expect

@@ -0,0 +1,9 @@
+if condition not satisified
+then
+	echo it did not work...
+	echo failed!
+	false
+else
+	echo it went okay ?!AMP?!
+	congratulate user
+fi

t/chainlint/chain-break-false.test

@@ -0,0 +1,10 @@
+# LINT: broken &&-chain okay if explicit "false" signals failure
+if condition not satisified
+then
+	echo it did not work...
+	echo failed!
+	false
+else
+	echo it went okay
+	congratulate user
+fi

t/chainlint/chain-break-return-exit.expect

@@ -0,0 +1,19 @@
+case "$(git ls-files)" in
+one ) echo pass one ;;
+* ) echo bad one ; return 1 ;;
+esac &&
+(
+	case "$(git ls-files)" in
+	two ) echo pass two ;;
+	* ) echo bad two ; exit 1 ;;
+esac
+) &&
+case "$(git ls-files)" in
+dir/two"$LF"one ) echo pass both ;;
+* ) echo bad ; return 1 ;;
+esac &&
+
+for i in 1 2 3 4 ; do
+	git checkout main -b $i || return $?
+	test_commit $i $i $i tag$i || return $?
+done

t/chainlint/chain-break-return-exit.test

@@ -0,0 +1,23 @@
+case "$(git ls-files)" in
+one) echo pass one ;;
+# LINT: broken &&-chain okay if explicit "return 1" signals failuire
+*) echo bad one; return 1 ;;
+esac &&
+(
+	case "$(git ls-files)" in
+	two) echo pass two ;;
+# LINT: broken &&-chain okay if explicit "exit 1" signals failuire
+	*) echo bad two; exit 1 ;;
+	esac
+) &&
+case "$(git ls-files)" in
+dir/two"$LF"one) echo pass both ;;
+# LINT: broken &&-chain okay if explicit "return 1" signals failuire
+*) echo bad; return 1 ;;
+esac &&
+
+for i in 1 2 3 4 ; do
+# LINT: broken &&-chain okay if explicit "return $?" signals failure
+	git checkout main -b $i || return $?
+	test_commit $i $i $i tag$i || return $?
+done

t/chainlint/chain-break-status.expect

@@ -0,0 +1,9 @@
+OUT=$(( ( large_git ; echo $? 1 >& 3 ) | : ) 3 >& 1) &&
+test_match_signal 13 "$OUT" &&
+
+{ test-tool sigchain > actual ; ret=$? ; } &&
+{
+	test_match_signal 15 "$ret" ||
+	test "$ret" = 3
+} &&
+test_cmp expect actual

t/chainlint/chain-break-status.test

@@ -0,0 +1,11 @@
+# LINT: broken &&-chain okay if next command handles "$?" explicitly
+OUT=$( ((large_git; echo $? 1>&3) | :) 3>&1 ) &&
+test_match_signal 13 "$OUT" &&
+
+# LINT: broken &&-chain okay if next command handles "$?" explicitly
+{ test-tool sigchain >actual; ret=$?; } &&
+{
+	test_match_signal 15 "$ret" ||
+	test "$ret" = 3
+} &&
+test_cmp expect actual

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

@@ -4,6 +4,6 @@
      :
    else
      echo >file
-   fi
+   fi ?!LOOP?!
  done) &&
 test ! -f file

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/for-loop.expect

@@ -2,10 +2,10 @@
 	for i in a b c
 	do
 		echo $i ?!AMP?!
-		cat <<-EOF
+		cat <<-EOF ?!LOOP?!
 	done ?!AMP?!
 	for i in a b c; do
 		echo $i &&
-		cat $i
+		cat $i ?!LOOP?!
 	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/here-doc-multi-line-string.expect

@@ -1,4 +1,5 @@
 (
-	cat <<-TXT && echo "multi-line	string" ?!AMP?!
+	cat <<-TXT && echo "multi-line
+	string" ?!AMP?!
 	bap
 )

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/if-in-loop.expect

@@ -3,7 +3,7 @@
 	do
 		if false
 		then
-			echo "err" ?!AMP?!
+			echo "err"
 			exit 1
 		fi ?!AMP?!
 		foo

t/chainlint/if-in-loop.test

@@ -3,7 +3,7 @@
 	do
 		if false
 		then
-# LINT: missing "&&" on "echo"
+# LINT: missing "&&" on "echo" okay since "exit 1" signals error explicitly
 			echo "err"
 			exit 1
 # LINT: missing "&&" on "fi"

t/chainlint/loop-detect-failure.expect

@@ -0,0 +1,15 @@
+git init r1 &&
+for n in 1 2 3 4 5
+do
+	echo "This is file: $n" > r1/file.$n &&
+	git -C r1 add file.$n &&
+	git -C r1 commit -m "$n" || return 1
+done &&
+
+git init r2 &&
+for n in 1000 10000
+do
+	printf "%"$n"s" X > r2/large.$n &&
+	git -C r2 add large.$n &&
+	git -C r2 commit -m "$n" ?!LOOP?!
+done

t/chainlint/loop-detect-failure.test

@@ -0,0 +1,17 @@
+git init r1 &&
+# LINT: loop handles failure explicitly with "|| return 1"
+for n in 1 2 3 4 5
+do
+	echo "This is file: $n" > r1/file.$n &&
+	git -C r1 add file.$n &&
+	git -C r1 commit -m "$n" || return 1
+done &&
+
+git init r2 &&
+# LINT: loop fails to handle failure explicitly with "|| return 1"
+for n in 1000 10000
+do
+	printf "%"$n"s" X > r2/large.$n &&
+	git -C r2 add large.$n &&
+	git -C r2 commit -m "$n"
+done

t/chainlint/loop-detect-status.expect

@@ -0,0 +1,18 @@
+( while test $i -le $blobcount
+do
+	printf "Generating blob $i/$blobcount\r" >& 2 &&
+	printf "blob\nmark :$i\ndata $blobsize\n" &&
+
+	printf "%-${blobsize}s" $i &&
+	echo "M 100644 :$i $i" >> commit &&
+	i=$(($i+1)) ||
+	echo $? > exit-status
+done &&
+echo "commit refs/heads/main" &&
+echo "author A U Thor <author@email.com> 123456789 +0000" &&
+echo "committer C O Mitter <committer@email.com> 123456789 +0000" &&
+echo "data 5" &&
+echo ">2gb" &&
+cat commit ) |
+git fast-import --big-file-threshold=2 &&
+test ! -f exit-status

t/chainlint/loop-detect-status.test

@@ -0,0 +1,19 @@
+# LINT: "$?" handled explicitly within loop body
+(while test $i -le $blobcount
+ do
+	printf "Generating blob $i/$blobcount\r" >&2 &&
+	printf "blob\nmark :$i\ndata $blobsize\n" &&
+	#test-tool genrandom $i $blobsize &&
+	printf "%-${blobsize}s" $i &&
+	echo "M 100644 :$i $i" >> commit &&
+	i=$(($i+1)) ||
+	echo $? > exit-status
+ done &&
+ echo "commit refs/heads/main" &&
+ echo "author A U Thor <author@email.com> 123456789 +0000" &&
+ echo "committer C O Mitter <committer@email.com> 123456789 +0000" &&
+ echo "data 5" &&
+ echo ">2gb" &&
+ cat commit) |
+git fast-import --big-file-threshold=2 &&
+test ! -f exit-status

t/chainlint/loop-in-if.expect

@@ -4,7 +4,7 @@
 		while true
 		do
 			echo "pop" ?!AMP?!
-			echo "glup"
+			echo "glup" ?!LOOP?!
 		done ?!AMP?!
 		foo
 	fi ?!AMP?!

t/chainlint/loop-upstream-pipe.expect

@@ -0,0 +1,10 @@
+(
+	git rev-list --objects --no-object-names base..loose |
+	while read oid
+	do
+		path="$objdir/$(test_oid_to_path "$oid")" &&
+		printf "%s %d\n" "$oid" "$(test-tool chmtime --get "$path")" ||
+		echo "object list generation failed for $oid"
+	done |
+	sort -k1
+) >expect &&

t/chainlint/loop-upstream-pipe.test

@@ -0,0 +1,11 @@
+(
+	git rev-list --objects --no-object-names base..loose |
+	while read oid
+	do
+# LINT: "|| echo" signals failure in loop upstream of a pipe
+		path="$objdir/$(test_oid_to_path "$oid")" &&
+		printf "%s %d\n" "$oid" "$(test-tool chmtime --get "$path")" ||
+		echo "object list generation failed for $oid"
+	done |
+	sort -k1
+) >expect &&

t/chainlint/multi-line-string.expect

@@ -1,9 +1,14 @@
 (
-	x="line 1		line 2		line 3" &&
+	x="line 1
-	y="line 1		line2" ?!AMP?!
+		line 2
+		line 3" &&
+	y="line 1
+		line2" ?!AMP?!
 	foobar
 ) &&
 (
-	echo "xyz" "abc		def		ghi" &&
+	echo "xyz" "abc
+		def
+		ghi" &&
 	barfoo
 )

t/chainlint/nested-loop-detect-failure.expect

@@ -0,0 +1,31 @@
+for i in 0 1 2 3 4 5 6 7 8 9 ;
+do
+	for j in 0 1 2 3 4 5 6 7 8 9 ;
+	do
+		echo "$i$j" > "path$i$j" ?!LOOP?!
+	done ?!LOOP?!
+done &&
+
+for i in 0 1 2 3 4 5 6 7 8 9 ;
+do
+	for j in 0 1 2 3 4 5 6 7 8 9 ;
+	do
+		echo "$i$j" > "path$i$j" || return 1
+	done
+done &&
+
+for i in 0 1 2 3 4 5 6 7 8 9 ;
+do
+	for j in 0 1 2 3 4 5 6 7 8 9 ;
+	do
+		echo "$i$j" > "path$i$j" ?!LOOP?!
+	done || return 1
+done &&
+
+for i in 0 1 2 3 4 5 6 7 8 9 ;
+do
+	for j in 0 1 2 3 4 5 6 7 8 9 ;
+	do
+		echo "$i$j" > "path$i$j" || return 1
+	done || return 1
+done

t/chainlint/nested-loop-detect-failure.test

@@ -0,0 +1,35 @@
+# LINT: neither loop handles failure explicitly with "|| return 1"
+for i in 0 1 2 3 4 5 6 7 8 9;
+do
+	for j in 0 1 2 3 4 5 6 7 8 9;
+	do
+		echo "$i$j" >"path$i$j"
+	done
+done &&
+
+# LINT: inner loop handles failure explicitly with "|| return 1"
+for i in 0 1 2 3 4 5 6 7 8 9;
+do
+	for j in 0 1 2 3 4 5 6 7 8 9;
+	do
+		echo "$i$j" >"path$i$j" || return 1
+	done
+done &&
+
+# LINT: outer loop handles failure explicitly with "|| return 1"
+for i in 0 1 2 3 4 5 6 7 8 9;
+do
+	for j in 0 1 2 3 4 5 6 7 8 9;
+	do
+		echo "$i$j" >"path$i$j"
+	done || return 1
+done &&
+
+# LINT: inner & outer loops handles failure explicitly with "|| return 1"
+for i in 0 1 2 3 4 5 6 7 8 9;
+do
+	for j in 0 1 2 3 4 5 6 7 8 9;
+	do
+		echo "$i$j" >"path$i$j" || return 1
+	done || return 1
+done

t/chainlint/nested-subshell.expect

@@ -6,7 +6,7 @@
 	) >file &&
 	cd foo &&
 	(
-		echo a
+		echo a ?!AMP?!
 		echo b
 	) >file
 )

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/return-loop.expect

@@ -0,0 +1,5 @@
+while test $i -lt $((num - 5))
+do
+	git notes add -m "notes for commit$i" HEAD~$i || return 1
+	i=$((i + 1))
+done

t/chainlint/return-loop.test

@@ -0,0 +1,6 @@
+while test $i -lt $((num - 5))
+do
+# LINT: "|| return {n}" valid loop escape outside subshell; no "&&" needed
+	git notes add -m "notes for commit$i" HEAD~$i || return 1
+	i=$((i + 1))
+done

t/chainlint/semicolon.expect

@@ -15,5 +15,5 @@
 ) &&
 (cd foo &&
 	for i in a b c; do
-		echo;
+		echo; ?!LOOP?!
 	done)

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/t7900-subtree.expect

@@ -1,10 +1,17 @@
 (
-	chks="sub1sub2sub3sub4" &&
+	chks="sub1
+sub2
+sub3
+sub4" &&
 	chks_sub=$(cat <<TXT | sed "s,^,sub dir/,"
 ) &&
-	chkms="main-sub1main-sub2main-sub3main-sub4" &&
+	chkms="main-sub1
+main-sub2
+main-sub3
+main-sub4" &&
 	chkms_sub=$(cat <<TXT | sed "s,^,sub dir/,"
 ) &&
 	subfiles=$(git ls-files) &&
-	check_equal "$subfiles" "$chkms$chks"
+	check_equal "$subfiles" "$chkms
+$chks"
 )

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'\''
+)

t/chainlint/while-loop.expect

@@ -2,10 +2,10 @@
 	while true
 	do
 		echo foo ?!AMP?!
-		cat <<-EOF
+		cat <<-EOF ?!LOOP?!
 	done ?!AMP?!
 	while true; do
 		echo foo &&
-		cat bar
+		cat bar ?!LOOP?!
 	done
 )

t/t0027-auto-crlf.sh

@@ -387,9 +387,7 @@ test_expect_success 'setup main' '
 	test_tick
 '
 
-# Disable extra chain-linting for the next set of tests. There are many
+
-# auto-generated ones that are not worth checking over and over.
-GIT_TEST_CHAIN_LINT_HARDER_DEFAULT=0
 
 warn_LF_CRLF="LF will be replaced by CRLF"
 warn_CRLF_LF="CRLF will be replaced by LF"
@@ -606,9 +604,6 @@ do
 	checkout_files     ""    "$id" "crlf" true    ""       CRLF  CRLF  CRLF         CRLF_mix_CR  CRLF_nul
 done
 
-# The rest of the tests are unique; do the usual linting.
-unset GIT_TEST_CHAIN_LINT_HARDER_DEFAULT
-
 # Should be the last test case: remove some files from the worktree
 test_expect_success 'ls-files --eol -d -z' '
 	rm crlf_false_attr__CRLF.txt crlf_false_attr__CRLF_mix_LF.txt crlf_false_attr__LF.txt .gitattributes &&

t/t3070-wildmatch.sh

@@ -5,11 +5,6 @@ test_description='wildmatch tests'
 TEST_PASSES_SANITIZE_LEAK=true
 . ./test-lib.sh
 
-# Disable expensive chain-lint tests; all of the tests in this script
-# are variants of a few trivial test-tool invocations, and there are a lot of
-# them.
-GIT_TEST_CHAIN_LINT_HARDER_DEFAULT=0
-
 should_create_test_file() {
 	file=$1
 

t/test-lib.sh

@@ -1091,11 +1091,7 @@ test_run_ () {
 		trace=
 		# 117 is magic because it is unlikely to match the exit
 		# code of other programs
-		if test "OK-117" != "$(test_eval_ "(exit 117) && $1${LF}${LF}echo OK-\$?" 3>&1)" ||
+		if test "OK-117" != "$(test_eval_ "(exit 117) && $1${LF}${LF}echo OK-\$?" 3>&1)"
-		   {
-			test "${GIT_TEST_CHAIN_LINT_HARDER:-${GIT_TEST_CHAIN_LINT_HARDER_DEFAULT:-1}}" != 0 &&
-			$(printf '%s\n' "$1" | sed -f "$GIT_BUILD_DIR/t/chainlint.sed" | grep -q '?![A-Z][A-Z]*?!')
-		   }
 		then
 			BUG "broken &&-chain or run-away HERE-DOC: $1"
 		fi
@@ -1591,6 +1587,12 @@ then
 	BAIL_OUT_ENV_NEEDS_SANITIZE_LEAK "GIT_TEST_SANITIZE_LEAK_LOG=true"
 fi
 
+if test "${GIT_TEST_CHAIN_LINT:-1}" != 0
+then
+	"$PERL_PATH" "$TEST_DIRECTORY/chainlint.pl" "$0" ||
+		BUG "lint error (see '?!...!? annotations above)"
+fi
+
 # Last-minute variable setup
 USER_HOME="$HOME"
 HOME="$TRASH_DIRECTORY"