Merge patch series "regex patches"

Rasmus Villemoes <ravi@prevas.dk> says:

This started as a rather simple patch, 1/12, adding the ability to
more conveniently do regex matching in shell.

But with that, it became very easy to see what the slre library can
and especially what it cannot do, and that way I found both outright
bugs and a "wow, doesn't it support that syntax" gotcha. I couldn't
find any tests ('git grep slre -- test/' was empty), so I added a
small test suite and tweaked slre.c.

Link: https://lore.kernel.org/r/20250513084034.654865-1-ravi@prevas.dk

1 files changed, 53 insertions, 25 deletions

diff --git a/lib/slre.c b/lib/slre.c
index 277a59a03a7..117815a6d60 100644
--- a/lib/slre.c
+++ b/lib/slre.c
@@ -30,7 +30,7 @@
 #include <slre.h>
 
 enum {END, BRANCH, ANY, EXACT, ANYOF, ANYBUT, OPEN, CLOSE, BOL, EOL,
-	STAR, PLUS, STARQ, PLUSQ, QUEST, SPACE, NONSPACE, DIGIT};
+	STAR, PLUS, STARQ, PLUSQ, QUEST, SPACE, NONSPACE, DIGIT, RANGE};
 
 #ifdef SLRE_TEST
 static struct {
@@ -55,7 +55,8 @@ static struct {
 	{"QUEST",	1, "o"},	/* Match zero or one time, "?"	*/
 	{"SPACE",	0, ""},		/* Match whitespace, "\s"	*/
 	{"NONSPACE",	0, ""},		/* Match non-space, "\S"	*/
-	{"DIGIT",	0, ""}		/* Match digit, "\d"		*/
+	{"DIGIT",	0, ""},		/* Match digit, "\d"		*/
+	{"RANGE",	0, ""},		/* Range separator -		*/
 };
 #endif /* SLRE_TEST */
 
@@ -260,6 +261,15 @@ anyof(struct slre *r, const char **re)
 			return;
 			/* NOTREACHED */
 			break;
+		case '-':
+			if (r->data_size == old_data_size || **re == ']') {
+				/* First or last character, just match - itself. */
+				store_char_in_data(r, '-');
+				break;
+			}
+			store_char_in_data(r, 0);
+			store_char_in_data(r, RANGE);
+			break;
 		case '\\':
 			esc = get_escape_char(re);
 			if ((esc & 0xff) == 0) {
@@ -413,10 +423,7 @@ int
 slre_compile(struct slre *r, const char *re)
 {
 	r->err_str = NULL;
-	r->code_size = r->data_size = r->num_caps = r->anchored = 0;
-
-	if (*re == '^')
-		r->anchored++;
+	r->code_size = r->data_size = r->num_caps = 0;
 
 	emit(r, OPEN);	/* This will capture what matches full RE */
 	emit(r, 0);
@@ -475,29 +482,54 @@ is_any_of(const unsigned char *p, int len, const char *s, int *ofs)
 
 	ch = s[*ofs];
 
-	for (i = 0; i < len; i++)
-		if (p[i] == ch) {
-			(*ofs)++;
-			return 1;
+	for (i = 0; i < len; i++) {
+		if (p[i] == '\0') {
+			switch (p[++i]) {
+			case NONSPACE:
+				if (!isspace(ch))
+					goto match;
+				break;
+			case SPACE:
+				if (isspace(ch))
+					goto match;
+				break;
+			case DIGIT:
+				if (isdigit(ch))
+					goto match;
+				break;
+			case RANGE:
+				/*
+				 * a-z is represented in the data array as {'a', \0, RANGE, 'z'}
+				 */
+				++i;
+				if (p[i - 3] <= (unsigned char)ch && (unsigned char)ch <= p[i])
+					goto match;
+				break;
+			}
+			continue;
 		}
+		if (p[i] == ch)
+			goto match;
+	}
 
 	return 0;
+
+match:
+	(*ofs)++;
+	return 1;
 }
 
 static int
 is_any_but(const unsigned char *p, int len, const char *s, int *ofs)
 {
-	int	i, ch;
-
-	ch = s[*ofs];
+	int	dummy = *ofs;
 
-	for (i = 0; i < len; i++) {
-		if (p[i] == ch)
-			return 0;
+	if (is_any_of(p, len, s, &dummy)) {
+		return 0;
+	} else {
+		(*ofs)++;
+		return 1;
 	}
-
-	(*ofs)++;
-	return 1;
 }
 
 static int
@@ -650,13 +682,9 @@ slre_match(const struct slre *r, const char *buf, int len,
 {
 	int	i, ofs = 0, res = 0;
 
-	if (r->anchored) {
+	for (i = 0; i <= len && res == 0; i++) {
+		ofs = i;
 		res = match(r, 0, buf, len, &ofs, caps);
-	} else {
-		for (i = 0; i < len && res == 0; i++) {
-			ofs = i;
-			res = match(r, 0, buf, len, &ofs, caps);
-		}
 	}
 
 	return res;