chainlint: match arbitrary here-docs tags rather than hard-coded names

chainlint.sed swallows top-level here-docs to avoid being fooled by
content which might look like start-of-subshell. It likewise swallows
here-docs in subshells to avoid marking content lines as breaking the
&&-chain, and to avoid being fooled by content which might look like
end-of-subshell, start-of-nested-subshell, or other specially-recognized
constructs.

At the time of implementation, it was believed that it was not possible
to support arbitrary here-doc tag names since 'sed' provides no way to
stash the opening tag name in a variable for later comparison against a
line signaling end-of-here-doc. Consequently, tag names are hard-coded,
with "EOF" being the only tag recognized at the top-level, and only
"EOF", "EOT", and "INPUT_END" being recognized within subshells. Also,
special care was taken to avoid being confused by here-docs nested
within other here-docs.

In practice, this limited number of hard-coded tag names has been "good
enough" for the 13000+ existing Git test, despite many of those tests
using tags other than the recognized ones, since the bodies of those
here-docs do not contain content which would fool the linter.
Nevertheless, the situation is not ideal since someone writing new
tests, and choosing a name not in the "blessed" set could potentially
trigger a false-positive.

To address this shortcoming, upgrade chainlint.sed to handle arbitrary
here-doc tag names, both at the top-level and within subshells.

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

7 files changed, 67 insertions, 23 deletions

diff --git a/t/chainlint.sed b/t/chainlint.sed
index 5f0882c..2af1a68 100644
--- a/t/chainlint.sed
+++ b/t/chainlint.sed
@@ -61,6 +61,22 @@
 # "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 >out" is seen, the here-doc tag is moved to the front
+# of the line enclosed in angle brackets as a sentinel, giving "<EOF>cat >out".
+# 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 >out\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 >out\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 >out".
+#
 # To facilitate regression testing (and manual debugging), a ">" annotation is
 # applied to the line containing ")" which closes a subshell, ">>" to a line
 # closing a nested subshell, and ">>>" to a line closing both at once. This
@@ -78,14 +94,17 @@
 
 # here-doc -- swallow it to avoid false hits within its body (but keep the
 # command to which it was attached)
-/<<[ 	]*[-\\]*EOF[ 	]*/ {
-	s/[ 	]*<<[ 	]*[-\\]*EOF//
-	h
+/<<[ 	]*[-\\]*[A-Za-z0-9_]/ {
+	s/^\(.*\)<<[ 	]*[-\\]*\([A-Za-z0-9_][A-Za-z0-9_]*\)/<\2>\1<</
+	s/[ 	]*<<//
 	:hereslurp
 	N
-	s/.*\n//
-	/^[ 	]*EOF[ 	]*$/!bhereslurp
-	x
+	/^<\([^>]*\)>.*\n[ 	]*\1[ 	]*$/!{
+		s/\n.*$//
+		bhereslurp
+	}
+	s/^<[^>]*>//
+	s/\n.*$//
 }
 
 # one-liner "(...) &&"
@@ -139,9 +158,7 @@ s/.*\n//
 	/"[^'"]*'[^'"]*"/!bsqstring
 }
 # here-doc -- swallow it
-/<<[ 	]*[-\\]*EOF/bheredoc
-/<<[ 	]*[-\\]*EOT/bheredoc
-/<<[ 	]*[-\\]*INPUT_END/bheredoc
+/<<[ 	]*[-\\]*[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
@@ -249,23 +266,17 @@ s/\n//
 bcheckchain
 
 # found here-doc -- swallow it to avoid false hits within its body (but keep
-# the command to which it was attached); take care to handle here-docs nested
-# within here-docs by only recognizing closing tag matching outer here-doc
-# opening tag
+# the command to which it was attached)
 :heredoc
-/EOF/{ s/[ 	]*<<[ 	]*[-\\]*EOF//; s/^/EOF/; }
-/EOT/{ s/[ 	]*<<[ 	]*[-\\]*EOT//; s/^/EOT/; }
-/INPUT_END/{ s/[ 	]*<<[ 	]*[-\\]*INPUT_END//; s/^/INPUT_END/; }
+s/^\(.*\)<<[ 	]*[-\\]*\([A-Za-z0-9_][A-Za-z0-9_]*\)/<\2>\1<</
+s/[ 	]*<<//
 :hereslurpsub
 N
-/^EOF.*\n[ 	]*EOF[ 	]*$/bhereclose
-/^EOT.*\n[ 	]*EOT[ 	]*$/bhereclose
-/^INPUT_END.*\n[ 	]*INPUT_END[ 	]*$/bhereclose
-bhereslurpsub
-:hereclose
-s/^EOF//
-s/^EOT//
-s/^INPUT_END//
+/^<\([^>]*\)>.*\n[ 	]*\1[ 	]*$/!{
+	s/\n.*$//
+	bhereslurpsub
+}
+s/^<[^>]*>//
 s/\n.*$//
 bcheckchain
 
diff --git a/t/chainlint/here-doc.expect b/t/chainlint/here-doc.expect
index 2328fe7..33bc3cc 100644
--- a/t/chainlint/here-doc.expect
+++ b/t/chainlint/here-doc.expect
@@ -1,3 +1,5 @@
 boodle wobba        gorgo snoot        wafta snurb &&
 
+cat >foo &&
+
 horticulture
diff --git a/t/chainlint/here-doc.test b/t/chainlint/here-doc.test
index bd36f6e..8986eef 100644
--- a/t/chainlint/here-doc.test
+++ b/t/chainlint/here-doc.test
@@ -7,6 +7,13 @@ quoth the raven,
 nevermore...
 EOF
 
+# LINT: swallow here-doc with arbitrary tag
+cat <<-Arbitrary_Tag_42 >foo &&
+snoz
+boz
+woz
+Arbitrary_Tag_42
+
 # LINT: swallow here-doc (EOF is last line of test)
 horticulture <<\EOF
 gomez
diff --git a/t/chainlint/nested-here-doc.expect b/t/chainlint/nested-here-doc.expect
index 559301e..0c9ef1c 100644
--- a/t/chainlint/nested-here-doc.expect
+++ b/t/chainlint/nested-here-doc.expect
@@ -1,3 +1,5 @@
+cat >foop &&
+
 (
 	cat &&
 ?!AMP?!	cat
diff --git a/t/chainlint/nested-here-doc.test b/t/chainlint/nested-here-doc.test
index 027e0bb..f35404b 100644
--- a/t/chainlint/nested-here-doc.test
+++ b/t/chainlint/nested-here-doc.test
@@ -1,3 +1,13 @@
+# LINT: inner "EOF" not misintrepreted as closing ARBITRARY here-doc
+cat <<ARBITRARY >foop &&
+naddle
+fub <<EOF
+	nozzle
+	noodle
+EOF
+formp
+ARBITRARY
+
 (
 # LINT: inner "EOF" not misintrepreted as closing INPUT_END here-doc
 	cat <<-\INPUT_END &&
diff --git a/t/chainlint/subshell-here-doc.expect b/t/chainlint/subshell-here-doc.expect
index 19d5aff..7c2da63 100644
--- a/t/chainlint/subshell-here-doc.expect
+++ b/t/chainlint/subshell-here-doc.expect
@@ -2,4 +2,8 @@
 	echo wobba 	       gorgo snoot 	       wafta snurb &&
 ?!AMP?!	cat >bip
 	echo >bop
+>) &&
+(
+	cat >bup &&
+	meep
 >)
diff --git a/t/chainlint/subshell-here-doc.test b/t/chainlint/subshell-here-doc.test
index 9c3564c..05139af 100644
--- a/t/chainlint/subshell-here-doc.test
+++ b/t/chainlint/subshell-here-doc.test
@@ -20,4 +20,12 @@
 	wednesday
 	pugsly
 	EOF
+) &&
+(
+# LINT: swallow here-doc with arbitrary tag
+	cat <<-\ARBITRARY >bup &&
+	glink
+	FIZZ
+	ARBITRARY
+	meep
 )