Date: 03 Nov 2001 03:21:50 +0100 From: Dag-Erling Smorgrav <des@ofug.org> To: arch@freebsd.org Subject: POSIX character class support for 1Tawk Message-ID: <xzpu1wca91d.fsf@flood.ping.uio.no>
next in thread | raw e-mail | index | archive | help
--=-=-=
See attached patch (which I've also submitted to bwk).
DES
--
Dag-Erling Smorgrav - des@ofug.org
--=-=-=
Content-Type: text/x-patch
Content-Disposition: attachment; filename=awk.diff
Index: b.c
===================================================================
RCS file: /home/ncvs/src/contrib/one-true-awk/b.c,v
retrieving revision 1.1.1.1
diff -u -r1.1.1.1 b.c
--- b.c 27 Oct 2001 08:07:37 -0000 1.1.1.1
+++ b.c 3 Nov 2001 01:14:16 -0000
@@ -683,12 +683,44 @@
}
}
+/*
+ * Character class definitions conformant to the POSIX locale as
+ * defined in IEEE P1003.1 draft 7 of June 2001, assuming the source
+ * and operating character sets are both ASCII (ISO646) or supersets
+ * thereof.
+ *
+ * Note that to avoid overflowing the temporary buffer used in
+ * relex(), the expanded character class (prior to range expansion)
+ * must be less than twice the size of their full name.
+ */
+struct charclass {
+ const uschar *cc_name;
+ int cc_namelen;
+ const uschar *cc_expand;
+} charclasses[] = {
+ { "alnum", 5, "0-9A-Za-z" },
+ { "alpha", 5, "A-Za-z" },
+ { "blank", 5, " \t" },
+ { "cntrl", 5, "\000-\037\177" },
+ { "digit", 5, "0-9" },
+ { "graph", 5, "\041-\176" },
+ { "lower", 5, "a-z" },
+ { "print", 5, " \041-\176" },
+ { "punct", 5, "\041-\057\072-\100\133-\140\173-\176" },
+ { "space", 5, " \f\n\r\t\v" },
+ { "upper", 5, "A-Z" },
+ { "xdigit", 6, "0-9A-Fa-f" },
+ { NULL, 0, NULL },
+};
+
int relex(void) /* lexical analyzer for reparse */
{
+ struct charclass *cc;
int c, n;
int cflag;
static uschar *buf = 0;
static int bufsz = 100;
+ const uschar *p;
uschar *bp;
switch (c = *prestr++) {
@@ -730,6 +762,17 @@
*bp++ = c;
/* } else if (c == '\n') { */
/* FATAL("newline in character class %.20s...", lastre); */
+ } else if (c == '[' && *prestr == ':') {
+ for (cc = charclasses; cc->cc_name; cc++)
+ if (strncmp(prestr + 1, cc->cc_name, cc->cc_namelen) == 0)
+ break;
+ if (cc->cc_name != NULL && prestr[1 + cc->cc_namelen] == ':' &&
+ prestr[2 + cc->cc_namelen] == ']') {
+ prestr += cc->cc_namelen + 3;
+ for (p = cc->cc_expand; *p; p++)
+ *bp++ = *p;
+ } else
+ *bp++ = c;
} else if (c == '\0') {
FATAL("nonterminated character class %.20s", lastre);
} else if (bp == buf) { /* 1st char is special */
--=-=-=--
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-arch" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?xzpu1wca91d.fsf>