MFC r318574: bsdgrep: Correct per-line line metadata printing

Metadata printing with -b, -H, or -n flags suffered from a few flaws:

1) -b/offset printing was broken when used in conjunction with -o

2) With -o, bsdgrep did not print metadata for every match/line, just
   the first match of a line

3) There were no tests for this

Address these issues by outputting this data per-match if the -o flag is
specified, and prior to outputting any matches if -o but not --color,
since --color alone will not generate a new line of output for every
iteration over the matches.

To correct -b output, fudge the line offset as we're printing matches.

While here, make sure we're using grep_printline in -A context.  Context
printing should *never* look at the parsing context, just the line.

The tests included do not pass with gnugrep in base due to it exhibiting
similar quirky behavior that bsdgrep previously exhibited.

Approved by:	emaste (mentor, blanket MFC)

4 files changed, 62 insertions, 11 deletions

diff --git a/contrib/netbsd-tests/usr.bin/grep/t_grep.sh b/contrib/netbsd-tests/usr.bin/grep/t_grep.sh
index b0c39f1..75bfd16 100755
--- a/contrib/netbsd-tests/usr.bin/grep/t_grep.sh
+++ b/contrib/netbsd-tests/usr.bin/grep/t_grep.sh
@@ -430,7 +430,7 @@ excessive_matches_body()
 	done
 
 	atf_check -s exit:0 -x '[ $(grep -o x test.in | wc -l) -eq 4096 ]'
-	#atf_check -s exit:1 -x 'grep -on x test.in | grep -v "1:x"'
+	atf_check -s exit:1 -x 'grep -on x test.in | grep -v "1:x"'
 }
 
 atf_test_case fgrep_sanity
@@ -510,6 +510,39 @@ wv_combo_break_body()
 	atf_check -s exit:1 grep -v -w "x" test2
 }
 
+atf_test_case ocolor_metadata
+ocolor_metadata_head()
+{
+	atf_set "descr" "Check for -n/-b producing per-line metadata output"
+}
+ocolor_metadata_body()
+{
+	grep_type
+	if [ $? -eq $GREP_TYPE_GNU_FREEBSD ]; then
+		atf_expect_fail "this test does not pass with GNU grep in base"
+	fi
+
+	printf "xxx\nyyyy\nzzz\nfoobarbaz\n" > test1
+	check_expr="^[^:]*[0-9][^:]*:[^:]+$"
+
+	atf_check -o inline:"1:1:xx\n" grep -bon "xx$" test1
+
+	atf_check -o inline:"2:4:yyyy\n" grep -bn "yy" test1
+
+	atf_check -o inline:"2:6:yy\n" grep -bon "yy$" test1
+
+	# These checks ensure that grep isn't producing bogus line numbering
+	# in the middle of a line.
+	atf_check -s exit:1 -x \
+	    "grep -Eon 'x|y|z|f' test1 | grep -Ev '${check_expr}'"
+
+	atf_check -s exit:1 -x \
+	    "grep -En 'x|y|z|f' --color=always test1 | grep -Ev '${check_expr}'"
+
+	atf_check -s exit:1 -x \
+	    "grep -Eon 'x|y|z|f' --color=always test1 | grep -Ev '${check_expr}'"
+}
+
 atf_test_case grep_nomatch_flags
 grep_nomatch_flags_head()
 {
@@ -668,6 +701,7 @@ atf_init_test_cases()
 	atf_add_test_case fgrep_sanity
 	atf_add_test_case egrep_sanity
 	atf_add_test_case grep_sanity
+	atf_add_test_case ocolor_metadata
 	atf_add_test_case grep_nomatch_flags
 	atf_add_test_case binary_flags
 	atf_add_test_case badcontext
diff --git a/usr.bin/grep/grep.h b/usr.bin/grep/grep.h
index 906318c..9128984 100644
--- a/usr.bin/grep/grep.h
+++ b/usr.bin/grep/grep.h
@@ -90,6 +90,7 @@ struct file {
 };
 
 struct str {
+	off_t		 boff;
 	off_t		 off;
 	size_t		 len;
 	char		*dat;
diff --git a/usr.bin/grep/queue.c b/usr.bin/grep/queue.c
index 272dedf..f094f8a 100644
--- a/usr.bin/grep/queue.c
+++ b/usr.bin/grep/queue.c
@@ -65,6 +65,7 @@ enqueue(struct str *x)
 	item->data.dat = grep_malloc(sizeof(char) * x->len);
 	item->data.len = x->len;
 	item->data.line_no = x->line_no;
+	item->data.boff = x->boff;
 	item->data.off = x->off;
 	memcpy(item->data.dat, x->dat, x->len);
 	item->data.file = x->file;
diff --git a/usr.bin/grep/util.c b/usr.bin/grep/util.c
index 0101c06..7b0a50b 100644
--- a/usr.bin/grep/util.c
+++ b/usr.bin/grep/util.c
@@ -61,11 +61,12 @@ static bool	 first_match = true;
  * other useful bits
  */
 struct parsec {
-	regmatch_t matches[MAX_LINE_MATCHES];	/* Matches made */
-	struct str ln;				/* Current line */
-	size_t lnstart;				/* Start of line processing */
-	size_t matchidx;			/* Latest used match index */
-	bool binary;				/* Binary file? */
+	regmatch_t	matches[MAX_LINE_MATCHES];	/* Matches made */
+	struct str	ln;				/* Current line */
+	size_t		lnstart;			/* Position in line */
+	size_t		matchidx;			/* Latest match index */
+	int		printed;			/* Metadata printed? */
+	bool		binary;				/* Binary file? */
 };
 
 
@@ -233,8 +234,10 @@ procfile(const char *fn)
 	strcpy(pc.ln.file, fn);
 	pc.ln.line_no = 0;
 	pc.ln.len = 0;
+	pc.ln.boff = 0;
 	pc.ln.off = -1;
 	pc.binary = f->binary;
+	pc.printed = 0;
 	tail = 0;
 	last_outed = 0;
 	same_file = false;
@@ -248,9 +251,11 @@ procfile(const char *fn)
 	mcount = mlimit;
 
 	for (c = 0;  c == 0 || !(lflag || qflag); ) {
-		/* Reset match count and line start for every line processed */
+		/* Reset per-line statistics */
+		pc.printed = 0;
 		pc.matchidx = 0;
 		pc.lnstart = 0;
+		pc.ln.boff = 0;
 		pc.ln.off += pc.ln.len + 1;
 		if ((pc.ln.dat = grep_fgetln(f, &pc.ln.len)) == NULL ||
 		    pc.ln.len == 0) {
@@ -305,7 +310,7 @@ procfile(const char *fn)
 		if (t != 0 && doctx) {
 			/* Deal with any -A context */
 			if (tail > 0) {
-				printline(&pc, '-');
+				grep_printline(&pc.ln, '-');
 				tail--;
 				if (Bflag > 0)
 					clearqueue();
@@ -607,7 +612,7 @@ printline_metadata(struct str *line, int sep)
 	if (bflag) {
 		if (printsep)
 			putchar(sep);
-		printf("%lld", (long long)line->off);
+		printf("%lld", (long long)(line->off + line->boff));
 		printsep = true;
 	}
 	if (printsep)
@@ -632,13 +637,22 @@ printline(struct parsec *pc, int sep)
 
 	/* --color and -o */
 	if ((oflag || color) && matchidx > 0) {
-		printline_metadata(&pc->ln, sep);
+		/* Only print metadata once per line if --color */
+		if (!oflag && pc->printed == 0)
+			printline_metadata(&pc->ln, sep);
 		for (i = 0; i < matchidx; i++) {
 			match = pc->matches[i];
 			/* Don't output zero length matches */
 			if (match.rm_so == match.rm_eo)
 				continue;
-			if (!oflag)
+			/*
+			 * Metadata is printed on a per-line basis, so every
+			 * match gets file metadata with the -o flag.
+			 */
+			if (oflag) {
+				pc->ln.boff = match.rm_so;
+				printline_metadata(&pc->ln, sep);
+			} else
 				fwrite(pc->ln.dat + a, match.rm_so - a, 1,
 				    stdout);
 			if (color)
@@ -659,4 +673,5 @@ printline(struct parsec *pc, int sep)
 		}
 	} else
 		grep_printline(&pc->ln, sep);
+	pc->printed++;
 }