Ok, I've converted the contents of the "testing/sed" directory into a

sed.tests file.  My brain hurts now.  (Lots of boggling at sed minutiae and 
corner cases and going "why is gnu giving that output".  The behavior of N 
and n with regard to EOF are only understandable if you read the Open Group 
spec, not if you read the sed info page, by the way...)

Some of the existing sed tests are just nuts.  For example, sed-next-line is 
testing for our behavior (which is wrong), and would fail if run against gnu 
sed (which was getting it right.  Again, this was a spec-boggling moment, 
with much head scratching.  I've got to add a debug mode where the stuff 
output by the p command is a different color from the stuff output by normal 
end of script printing (when not suppressed by -n).)

As for sed-handles-unsatisifed-backrefs: what is this test trying to _do_?  I 
ran it against gnu sed and got an error message, and this behavior sounds 
perfectly reasonable.  (It _is_ an unsatisfied backref.)  The fact we 
currently ignore this case (and treat \1 as an empty string) isn't really 
behavior we should have a test depend on for success.

The remaining one is sed-aic-commands, which is long and complicated.  I'm
trying to figure out if I should chop this into a number of smaller tests, or
if having one big "does-many-things" test is a good idea.

In any case, the _next_ step is to go through the Open Group standard and
make tests for every case not yet covered.  (And there are plenty.  There
are few comments in the file already.)  Plus I have notes about corner
cases from development that I need to collate and put into here.  This file
is maybe the first 1/3 of a truly comprehensive sed test.

Rob

23 files changed, 109 insertions, 276 deletions

diff --git a/testsuite/sed.tests b/testsuite/sed.tests
new file mode 100755
index 0000000..479dd9a
--- /dev/null
+++ b/testsuite/sed.tests
@@ -0,0 +1,109 @@
+#!/bin/sh
+
+# SUSv3 compliant sed tests.
+# Copyright 2005 by Rob Landley <rob@landley.net>
+# Licensed under GPL v2, see file LICENSE for details.
+
+[ -z "$COMMAND" ] && COMMAND=sed
+. testing.sh
+
+# testing "description" "arguments" "result" "infile" "stdin"
+
+# Corner cases
+testing "sed as cat" '"" -' "hello\n" "" "hello\n"
+testing "sed handles empty lines" "-e 's/\$/@/'" "@\n" "" "\n"
+
+# no files (stdin)
+# explicit stdin
+# mix files and stdin (various orders)
+# list stdin twice
+# Trailing EOF.
+#	Multiple files: first no EOF, second length 0.
+#	Match $, at end of each file or all files?
+#	First no EOF, second no matches at all.
+# -e corner cases
+#	without -e
+#	multiple -e
+#		interact with a
+#	-eee arg1 arg2 arg3
+# -f corner cases
+#	-e -f -e
+# -n corner cases
+#	no newline at EOF?
+# -r corner cases
+#	Just make sure it works.
+# -i corner cases:
+#	sed -i -
+#	permissions
+#	-i on a symlink
+#	on a directory
+
+# command list
+testing "sed accepts blanks before command" "-e '1 d'" "" "" ""
+testing "sed accepts newlines in -e" "-e 'i\
+1
+a\
+3'" "1\n2\n3\n" "" "2\n"
+testing "sed accepts multiple -e" "-e 'i\' -e '1' -e 'a\' -e '3'" \
+	"1\n2\n3\n" "" "2\n"
+
+# substitutions
+testing "sed -n" "-n -e s/foo/bar/ -e s/bar/baz/" "" "" "foo\n"
+testing "sed s//p" "-e s/foo/bar/p -e s/bar/baz/p" "bar\nbaz\nbaz\n" \
+	"" "foo\n"
+testing "sed -n s//p" "-ne s/abc/def/p" "def\n" "" "abc\n"
+testing "sed s//g (exhaustive)" "-e 's/[[:space:]]*/,/g'" ",1,2,3,4,5,\n" \
+	"" "12345\n"
+testing "sed s arbitrary delimiter" "-e 's woo boing '" "boing\n" "" "woo\n"
+testing "sed s chains" "-e s/foo/bar/ -e s/bar/baz/" "baz\n" "" "foo\n"
+testing "sed s chains2" "-e s/foo/bar/ -e s/baz/nee/" "bar\n" "" "foo\n"
+testing "sed s [delimiter]" "-e 's@[@]@@'" "onetwo" "" "one@two"
+
+# branch
+testing "sed b (branch)" "-e 'b one;p;: one'" "foo\n" "" "foo\n"
+testing "sed b (branch with no label jumps to end)" "-e 'b;p'" \
+	"foo\n" "" "foo\n"
+
+# test and branch
+testing "sed t (test/branch)" "-e 's/a/1/;t one;p;: one;p'" \
+	"1\n1\nb\nb\nb\nc\nc\nc\n" "" "a\nb\nc\n"
+testing "sed t (test/branch clears test bit)" "-e 's/a/b/;:loop;t loop'" \
+	"b\nb\nc\n" "" "a\nb\nc\n"
+testing "sed T (!test/branch)" "-e 's/a/1/;T notone;p;: notone;p'" \
+	"1\n1\n1\nb\nb\nc\nc\n" "" "a\nb\nc\n"
+
+# Normal sed end-of-script doesn't print "c" because n flushed the pattern
+# space.  If n hits EOF, pattern space is empty when script ends.
+# Query: how does this interact with no newline at EOF?
+testing "sed n (flushes pattern space, terminates early)" "-e 'n;p'" \
+	"a\nb\nb\nc\n" "" "a\nb\nc\n"
+# N does _not_ flush pattern space, therefore c is still in there @ script end.
+testing "sed N (doesn't flush pattern space when terminating)" "-e 'N;p'" \
+	"a\nb\na\nb\nc\n" "" "a\nb\nc\n"
+testing "sed address match newline" '"/b/N;/b\\nc/i woo"' "a\nwoo\nb\nc\nd\n" \
+	"" "a\nb\nc\nd\n"
+
+# Multiple lines in pattern space
+testing "sed N (stops at end of input) and P (prints to first newline only)" \
+	"-n 'N;P;p'" "a\na\nb\n" "" "a\nb\nc\n"
+
+# Hold space
+testing "sed G (append hold space to pattern space)" 'G' "a\n\nb\n\nc\n\n" \
+	"" "a\nb\nc\n"
+#testing "sed g/G (swap/append hold and patter space)"
+#testing "sed g (swap hold/pattern space)"
+
+testing "sed d ends script iteration" \
+	"-e '/ook/d;s/ook/ping/p;i woot'" "" "" "ook\n"
+testing "sed d ends script iteration (2)" \
+	"-e '/ook/d;a\' -e 'bang'" "woot\nbang\n" "" "ook\nwoot\n"
+
+# Ponder this a bit more, why "woo not found" from gnu version?
+#testing "sed doesn't substitute in deleted line" \
+#	"-e '/ook/d;s/ook//;t woo;a bang;'" "bang" "" "ook\n"
+
+# This makes both seds very unhappy.  Why?
+#testing "sed -g (exhaustive)" "sed -e 's/[[:space:]]*/,/g'" ",1,2,3,4,5," \
+#	"" "12345"
+
+exit $FAILCOUNT
diff --git a/testsuite/sed/sed-accepts-blanks-before-command b/testsuite/sed/sed-accepts-blanks-before-command
deleted file mode 100644
index 9597c2f..0000000
--- a/testsuite/sed/sed-accepts-blanks-before-command
+++ /dev/null
@@ -1 +0,0 @@
-busybox sed -e '1 d' </dev/null
diff --git a/testsuite/sed/sed-aic-commands b/testsuite/sed/sed-aic-commands
deleted file mode 100644
index b41c14a..0000000
--- a/testsuite/sed/sed-aic-commands
+++ /dev/null
@@ -1,134 +0,0 @@
-cat - >input <<EOF
-2i\\
-before 2
-5c\\
-Change 5
-10a\\
-After 10
-22i\\
-before 22\\
-Continued
-25c\\
-Change 25\\
-Continued
-20a\\
-After 20\\
-Continued
-  	  32i\\
-before 32\\
-Continued 1\\
-Continued 2\\
-Continued 3
-  	  35c\\
-Change 35\\
-Continued 1\\
-Continued 2\\
-Continued 3
-	30a\\
-After 30\\
-Continued 1\\
-Continued 2\\
-Continued 3
-EOF
-busybox sed -f input >output <<EOF
-     1	y
-     2	y
-     3	y
-     4	y
-     5	y
-     6	y
-     7	y
-     8	y
-     9	y
-    10	y
-    11	y
-    12	y
-    13	y
-    14	y
-    15	y
-    16	y
-    17	y
-    18	y
-    19	y
-    20	y
-    21	y
-    22	y
-    23	y
-    24	y
-    25	y
-    26	y
-    27	y
-    28	y
-    29	y
-    30	y
-    31	y
-    32	y
-    33	y
-    34	y
-    35	y
-    36	y
-    37	y
-    38	y
-    39	y
-    40	y
-EOF
-cmp -s output - <<EOF
-     1	y
-before 2
-     2	y
-     3	y
-     4	y
-Change 5
-     6	y
-     7	y
-     8	y
-     9	y
-    10	y
-After 10
-    11	y
-    12	y
-    13	y
-    14	y
-    15	y
-    16	y
-    17	y
-    18	y
-    19	y
-    20	y
-After 20
-Continued
-    21	y
-before 22
-Continued
-    22	y
-    23	y
-    24	y
-Change 25
-Continued
-    26	y
-    27	y
-    28	y
-    29	y
-    30	y
-After 30
-Continued 1
-Continued 2
-Continued 3
-    31	y
-before 32
-Continued 1
-Continued 2
-Continued 3
-    32	y
-    33	y
-    34	y
-Change 35
-Continued 1
-Continued 2
-Continued 3
-    36	y
-    37	y
-    38	y
-    39	y
-    40	y
-EOF
diff --git a/testsuite/sed/sed-append-hold-space-to-pattern-space b/testsuite/sed/sed-append-hold-space-to-pattern-space
deleted file mode 100644
index 6dda80f..0000000
--- a/testsuite/sed/sed-append-hold-space-to-pattern-space
+++ /dev/null
@@ -1,13 +0,0 @@
-busybox sed 'G'>output <<EOF
-a
-b
-c
-EOF
-cmp -s output - <<EOF
-a
-
-b
-
-c
-
-EOF
diff --git a/testsuite/sed/sed-append-next-line b/testsuite/sed/sed-append-next-line
deleted file mode 100644
index 0621a31..0000000
--- a/testsuite/sed/sed-append-next-line
+++ /dev/null
@@ -1,19 +0,0 @@
-# This will fail if CONFIG_FEATURE_SED_GNU_COMPATABILITY is defined
-busybox sed 'N;p'>output <<EOF
-a
-b
-c
-EOF
-
-set +e
-cmp -s output - <<EOF
-a
-b
-a
-b
-c
-EOF
-if [ $? != 0 ] ; then
-	exit 0;
-fi
-exit 1;
diff --git a/testsuite/sed/sed-branch b/testsuite/sed/sed-branch
deleted file mode 100644
index 4167569..0000000
--- a/testsuite/sed/sed-branch
+++ /dev/null
@@ -1 +0,0 @@
-test "$(echo foo | busybox sed 'b one;p;: one')" = foo
diff --git a/testsuite/sed/sed-branch-conditional b/testsuite/sed/sed-branch-conditional
deleted file mode 100644
index 47d0a5f..0000000
--- a/testsuite/sed/sed-branch-conditional
+++ /dev/null
@@ -1,15 +0,0 @@
-busybox sed 's/a/1/;t one;p;: one;p'>output <<EOF
-a
-b
-c
-EOF
-cmp -s output - <<EOF
-1
-1
-b
-b
-b
-c
-c
-c
-EOF
diff --git a/testsuite/sed/sed-branch-conditional-inverted b/testsuite/sed/sed-branch-conditional-inverted
deleted file mode 100755
index f4df84b..0000000
--- a/testsuite/sed/sed-branch-conditional-inverted
+++ /dev/null
@@ -1,14 +0,0 @@
-busybox sed 's/a/1/;T notone;p;: notone;p'>output <<EOF
-a
-b
-c
-EOF
-cmp -s output - <<EOF
-1
-1
-1
-b
-b
-c
-c
-EOF
diff --git a/testsuite/sed/sed-branch-conditional2 b/testsuite/sed/sed-branch-conditional2
deleted file mode 100644
index f4b11f0..0000000
--- a/testsuite/sed/sed-branch-conditional2
+++ /dev/null
@@ -1,11 +0,0 @@
-#XFAIL
-busybox sed 's/a/b/;:loop;t loop'>output <<EOF
-a
-b
-c
-EOF
-cmp -s output - <<EOF
-b
-b
-c
-EOF
diff --git a/testsuite/sed/sed-branch-no-label b/testsuite/sed/sed-branch-no-label
deleted file mode 100644
index 446c1bc..0000000
--- a/testsuite/sed/sed-branch-no-label
+++ /dev/null
@@ -1 +0,0 @@
-test "$(echo foo | busybox sed 'b;p')" = foo
diff --git a/testsuite/sed/sed-chains-substs b/testsuite/sed/sed-chains-substs
deleted file mode 100644
index 266936a..0000000
--- a/testsuite/sed/sed-chains-substs
+++ /dev/null
@@ -1 +0,0 @@
-test "$(echo foo | busybox sed -e s/foo/bar/ -e s/bar/baz/)" = baz
diff --git a/testsuite/sed/sed-chains-substs2 b/testsuite/sed/sed-chains-substs2
deleted file mode 100644
index 90568f6..0000000
--- a/testsuite/sed/sed-chains-substs2
+++ /dev/null
@@ -1 +0,0 @@
-test x"$(echo foo | busybox -n sed -e s/foo/bar/ -e s/foo/baz/)" = x
diff --git a/testsuite/sed/sed-does-not-substitute-in-deleted-line b/testsuite/sed/sed-does-not-substitute-in-deleted-line
deleted file mode 100644
index 6f106e1..0000000
--- a/testsuite/sed/sed-does-not-substitute-in-deleted-line
+++ /dev/null
@@ -1,2 +0,0 @@
-echo foo | busybox sed -e /foo/d -e s/foo/bar/ >foo
-cmp foo /dev/null
diff --git a/testsuite/sed/sed-handles-embedded-slashes b/testsuite/sed/sed-handles-embedded-slashes
deleted file mode 100644
index cc28761..0000000
--- a/testsuite/sed/sed-handles-embedded-slashes
+++ /dev/null
@@ -1 +0,0 @@
-test "$(echo fu/bar | busybox sed -e 's/[/]//')" = fubar
diff --git a/testsuite/sed/sed-handles-empty-lines b/testsuite/sed/sed-handles-empty-lines
deleted file mode 100644
index 2bb8f04..0000000
--- a/testsuite/sed/sed-handles-empty-lines
+++ /dev/null
@@ -1 +0,0 @@
-test `echo | busybox sed -e 's/$/@/'` = @
diff --git a/testsuite/sed/sed-handles-unsatisfied-backrefs b/testsuite/sed/sed-handles-unsatisfied-backrefs
deleted file mode 100644
index 61bff88..0000000
--- a/testsuite/sed/sed-handles-unsatisfied-backrefs
+++ /dev/null
@@ -1,6 +0,0 @@
-busybox sed -e 's/.*root=/\1/' >output <<EOF
-BOOT_IMAGE=vmlinuz root=/dev/hda5 initrd=init1
-EOF
-cmp -s output - <<EOF
-/dev/hda5 initrd=init1
-EOF
diff --git a/testsuite/sed/sed-next-line b/testsuite/sed/sed-next-line
deleted file mode 100644
index 38fe20c..0000000
--- a/testsuite/sed/sed-next-line
+++ /dev/null
@@ -1,12 +0,0 @@
-busybox sed 'n;p'>output <<EOF
-a
-b
-c
-EOF
-cmp -s output - <<EOF
-a
-b
-b
-c
-c
-EOF
diff --git a/testsuite/sed/sed-prints-line-once-for-multiple-substs b/testsuite/sed/sed-prints-line-once-for-multiple-substs
deleted file mode 100644
index ba8955d..0000000
--- a/testsuite/sed/sed-prints-line-once-for-multiple-substs
+++ /dev/null
@@ -1,4 +0,0 @@
-busybox sed -e s/1/2/g -e s/3/4/g >output <<EOF
-1
-EOF
-echo 2 | cmp -s output -
diff --git a/testsuite/sed/sed-recurses-properly b/testsuite/sed/sed-recurses-properly
deleted file mode 100644
index a02667b..0000000
--- a/testsuite/sed/sed-recurses-properly
+++ /dev/null
@@ -1 +0,0 @@
-test "`echo '12345' | busybox sed -e 's/[[:space:]]*/,/g')` = ',1,2,3,4,5,'"
diff --git a/testsuite/sed/sed-regex-match-newline b/testsuite/sed/sed-regex-match-newline
deleted file mode 100644
index 1057e17..0000000
--- a/testsuite/sed/sed-regex-match-newline
+++ /dev/null
@@ -1,10 +0,0 @@
-# FEATURE: CONFIG_FEATURE_SED_EMBEDED_NEWLINE
-busybox sed -n 'N;/a\nb/p'>output <<EOF
-a
-b
-c
-EOF
-cmp -s output - <<EOF
-a
-b
-EOF
diff --git a/testsuite/sed/sed-splits-edit-commands-on-command-line b/testsuite/sed/sed-splits-edit-commands-on-command-line
deleted file mode 100644
index 6421fa5..0000000
--- a/testsuite/sed/sed-splits-edit-commands-on-command-line
+++ /dev/null
@@ -1,9 +0,0 @@
-echo 2 | busybox sed -e 'i\
-1
-a\
-3' > output
-cmp output - <<EOF
-1
-2
-3
-EOF
diff --git a/testsuite/sed/sed-subst-subprint b/testsuite/sed/sed-subst-subprint
deleted file mode 100644
index 24f8bad..0000000
--- a/testsuite/sed/sed-subst-subprint
+++ /dev/null
@@ -1,9 +0,0 @@
-busybox sed 's/foo/bar/p'>output <<EOF
-foo
-bar
-EOF
-cmp -s output - <<EOF
-bar
-bar
-bar
-EOF
diff --git a/testsuite/sed/sed-write-to-stdout b/testsuite/sed/sed-write-to-stdout
deleted file mode 100644
index 95b4d72..0000000
--- a/testsuite/sed/sed-write-to-stdout
+++ /dev/null
@@ -1,10 +0,0 @@
-busybox sed -n 'N;P;p'>output <<EOF
-a
-b
-c
-EOF
-cmp -s output - <<EOF
-a
-a
-b
-EOF