sbase

commit 7d3e9c6e88474effad146d77c7d4d819d3a6f75d
parent 7a644aea7d3c2cd3f44b8fa15c5ccdc91f111585
Author: FRIGN <dev@frign.de>
Date:   Thu, 15 Jan 2015 11:51:58 +0100

Resolve escape characters in tr(1)

This is one aspect which I think has blown up the complexity of many
tr-implementations around today.
Instead of complicating the set-theory-based parser itself (he should
still be relying on one rune per char, not multirunes), I added a
preprocessor, which basically scans the code for upcoming '\'s, reads
what he finds, substitutes the real character onto '\'s index and shifts
the entire following array so there are no "holes".

What is left to reflect on is what to do with octal sequences.
I have a local implementation here, which works fine, but imho,
given tr is already so focused on UTF-8, we might as well ignore
POSIX at this point and rather implement the unicode UTF-8 code points,
which are way more contemporary and future-proof.

Reading in \uC3A4 as a an array of 0xC3 and 0xA4 is not the issue,
but I'm still struggling to find a way to turn it into a well-formed
byte sequence. Hit me with a mail if you have a simple solution for
that.

Diffstat:
M
tr.c
 | 
32
+++++++++++++++++++++++++++++++-

1 file changed, 31 insertions(+), 1 deletion(-)
diff --git a/tr.c b/tr.c
@@ -70,6 +70,36 @@ rstrmatch(Rune *r, char *s, size_t n)
 }
 
 static size_t
+resolveescapes(Rune *r, size_t len)
+{
+	size_t i, off, m;
+
+	for (i = 0; i < len - 1; i++) {
+		if (r[i] != '\\')
+			continue;
+		off = 0;
+
+		switch (r[i + 1]) {
+		case '\\': r[i] = '\\'; off++; break;
+		case 'a':  r[i] = '\a'; off++; break;
+		case 'b':  r[i] = '\b'; off++; break;
+		case 'f':  r[i] = '\f'; off++; break;
+		case 'n':  r[i] = '\n'; off++; break;
+		case 'r':  r[i] = '\r'; off++; break;
+		case 't':  r[i] = '\t'; off++; break;
+		case 'v':  r[i] = '\v'; off++; break;
+		default:   continue;
+		}
+
+		for (m = i + 1; m <= len - off; m++)
+			r[m] = r[m + off];
+		len -= off;
+	}
+
+	return len;
+}
+
+static size_t
 makeset(char *str, struct range **set, int (**check)(wint_t))
 {
 	Rune  *rstr;
@@ -79,9 +109,9 @@ makeset(char *str, struct range **set, int (**check)(wint_t))
 
 	/* rstr defines at most len ranges */
 	len = chartorunearr(str, &rstr);
+	len = resolveescapes(rstr, len);
 	*set = emalloc(len * sizeof(**set));
 
-	/* todo: allow expressions */
 	for (i = 0; i < len; i++) {
 		if (rstr[i] == '[') {
 			j = i;