grep.c: expose {,inverted} match column in match_line()

When calling match_line(), callers presently cannot determine the
relative offset of the match because match_line() discards the
'regmatch_t' that contains this information.

Instead, teach match_line() to take in two 'ssize_t's. Fill the first
with the offset of the match produced by the given expression. If
extended, fill the later with the offset of the match produced as if
--invert were given.

For instance, matching "--not -e x" on this line produces a columnar
offset of 0, (i.e., the whole line does not contain an x), but "--invert
--not -e -x" will fill the later ssize_t of the column containing an
"x", because this expression is semantically equivalent to "-e x".

To determine the column for the inverted and non-inverted case, do the
following:

  - If matching an atom, the non-inverted column is as given from
    match_one_pattern(), and the inverted column is unset.

  - If matching a --not, the inverted column and non-inverted column
    swap.

  - If matching an --and, or --or, the non-inverted column is the
    minimum of the two children.

Presently, the existing short-circuiting logic for AND and OR applies as
before. This will change in the following commit when we add options to
configure the --column flag. Taken together, this and the forthcoming
change will always yield the earlier column on a given line.

This patch will become useful when we later pick between the two new
results in order to display the column number of the first match on a
line with --column.

Co-authored-by: Jeff King <peff@peff.net>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 39 insertions, 19 deletions

diff --git a/grep.c b/grep.c
index 45ec7e636c..dedfe17f93 100644
--- a/grep.c
+++ b/grep.c
@@ -1248,11 +1248,11 @@ static int match_one_pattern(struct grep_pat *p, char *bol, char *eol,
 	return hit;
 }
 
-static int match_expr_eval(struct grep_expr *x, char *bol, char *eol,
-			   enum grep_context ctx, int collect_hits)
+static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x, char *bol,
+			   char *eol, enum grep_context ctx, ssize_t *col,
+			   ssize_t *icol, int collect_hits)
 {
 	int h = 0;
-	regmatch_t match;
 
 	if (!x)
 		die("Not a valid grep expression");
@@ -1261,25 +1261,39 @@ static int match_expr_eval(struct grep_expr *x, char *bol, char *eol,
 		h = 1;
 		break;
 	case GREP_NODE_ATOM:
-		h = match_one_pattern(x->u.atom, bol, eol, ctx, &match, 0);
+		{
+			regmatch_t tmp;
+			h = match_one_pattern(x->u.atom, bol, eol, ctx,
+					      &tmp, 0);
+			if (h && (*col < 0 || tmp.rm_so < *col))
+				*col = tmp.rm_so;
+		}
 		break;
 	case GREP_NODE_NOT:
-		h = !match_expr_eval(x->u.unary, bol, eol, ctx, 0);
+		/*
+		 * Upon visiting a GREP_NODE_NOT, col and icol become swapped.
+		 */
+		h = !match_expr_eval(opt, x->u.unary, bol, eol, ctx, icol, col,
+				     0);
 		break;
 	case GREP_NODE_AND:
-		if (!match_expr_eval(x->u.binary.left, bol, eol, ctx, 0))
+		if (!match_expr_eval(opt, x->u.binary.left, bol, eol, ctx, col,
+				     icol, 0))
 			return 0;
-		h = match_expr_eval(x->u.binary.right, bol, eol, ctx, 0);
+		h = match_expr_eval(opt, x->u.binary.right, bol, eol, ctx, col,
+				    icol, 0);
 		break;
 	case GREP_NODE_OR:
 		if (!collect_hits)
-			return (match_expr_eval(x->u.binary.left,
-						bol, eol, ctx, 0) ||
-				match_expr_eval(x->u.binary.right,
-						bol, eol, ctx, 0));
-		h = match_expr_eval(x->u.binary.left, bol, eol, ctx, 0);
+			return (match_expr_eval(opt, x->u.binary.left, bol, eol,
+						ctx, col, icol, 0) ||
+				match_expr_eval(opt, x->u.binary.right, bol,
+						eol, ctx, col, icol, 0));
+		h = match_expr_eval(opt, x->u.binary.left, bol, eol, ctx, col,
+				    icol, 0);
 		x->u.binary.left->hit |= h;
-		h |= match_expr_eval(x->u.binary.right, bol, eol, ctx, 1);
+		h |= match_expr_eval(opt, x->u.binary.right, bol, eol, ctx, col,
+				     icol, 1);
 		break;
 	default:
 		die("Unexpected node type (internal error) %d", x->node);
@@ -1290,25 +1304,30 @@ static int match_expr_eval(struct grep_expr *x, char *bol, char *eol,
 }
 
 static int match_expr(struct grep_opt *opt, char *bol, char *eol,
-		      enum grep_context ctx, int collect_hits)
+		      enum grep_context ctx, ssize_t *col,
+		      ssize_t *icol, int collect_hits)
 {
 	struct grep_expr *x = opt->pattern_expression;
-	return match_expr_eval(x, bol, eol, ctx, collect_hits);
+	return match_expr_eval(opt, x, bol, eol, ctx, col, icol, collect_hits);
 }
 
 static int match_line(struct grep_opt *opt, char *bol, char *eol,
+		      ssize_t *col, ssize_t *icol,
 		      enum grep_context ctx, int collect_hits)
 {
 	struct grep_pat *p;
-	regmatch_t match;
 
 	if (opt->extended)
-		return match_expr(opt, bol, eol, ctx, collect_hits);
+		return match_expr(opt, bol, eol, ctx, col, icol,
+				  collect_hits);
 
 	/* we do not call with collect_hits without being extended */
 	for (p = opt->pattern_list; p; p = p->next) {
-		if (match_one_pattern(p, bol, eol, ctx, &match, 0))
+		regmatch_t tmp;
+		if (match_one_pattern(p, bol, eol, ctx, &tmp, 0)) {
+			*col = tmp.rm_so;
 			return 1;
+		}
 	}
 	return 0;
 }
@@ -1763,6 +1782,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle
 	while (left) {
 		char *eol, ch;
 		int hit;
+		ssize_t col = -1, icol = -1;
 
 		/*
 		 * look_ahead() skips quickly to the line that possibly
@@ -1786,7 +1806,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle
 		if ((ctx == GREP_CONTEXT_HEAD) && (eol == bol))
 			ctx = GREP_CONTEXT_BODY;
 
-		hit = match_line(opt, bol, eol, ctx, collect_hits);
+		hit = match_line(opt, bol, eol, &col, &icol, ctx, collect_hits);
 		*eol = ch;
 
 		if (collect_hits)