# "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
# 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.*$//
}
# one-liner "(...) &&"
:slurp
# incomplete line "...\"
/\\$/bincomplete
-# multi-line quoted string "...\n..."
-/^[^"]*"[^"]*$/bdqstring
-# multi-line quoted string '...\n...' (but not contraction in string "it's so")
-/^[^']*'[^']*$/{
+# multi-line quoted string "...\n..."?
+/"/bdqstring
+# multi-line quoted string '...\n...'? (but not contraction in string "it's")
+/'/{
/"[^'"]*'[^'"]*"/!bsqstring
}
+:folded
# 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
# "$(...)" -- command substitution; not closing ")"
/\$([^)][^)]*)[^)]*$/bcheckchain
# multi-line "$(...\n...)" -- command substitution; treat as nested subshell
-/\$([ ]*$/bnest
+/\$([^)]*$/bnest
# "=(...)" -- Bash array assignment; not closing ")"
/=(/bcheckchain
# closing "...) &&"
s/\\\n//
bslurp
-# found multi-line double-quoted string "...\n..." -- slurp until end of string
+# check for multi-line double-quoted string "...\n..." -- fold to one line
:dqstring
-s/"//g
+# remove all quote pairs
+s/"\([^"]*\)"/@!\1@!/g
+# done if no dangling quote
+/"/!bdqdone
+# otherwise, slurp next line and try again
N
s/\n//
-/"/!bdqstring
-bcheckchain
+bdqstring
+:dqdone
+s/@!/"/g
+bfolded
-# found multi-line single-quoted string '...\n...' -- slurp until end of string
+# check for multi-line single-quoted string '...\n...' -- fold to one line
:sqstring
-s/'//g
+# remove all quote pairs
+s/'\([^']*\)'/@!\1@!/g
+# done if no dangling quote
+/'/!bsqdone
+# otherwise, slurp next line and try again
N
s/\n//
-/'/!bsqstring
-bcheckchain
+bsqstring
+: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); 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
+bfolded
# found "case ... in" -- pass through untouched
:case