===================================================================
RCS file: /cvs/mandoc/mdoc_validate.c,v
retrieving revision 1.340
retrieving revision 1.343
diff -u -p -r1.340 -r1.343
--- mandoc/mdoc_validate.c	2017/06/24 14:38:33	1.340
+++ mandoc/mdoc_validate.c	2017/06/25 17:43:45	1.343
@@ -1,4 +1,4 @@
-/*	$Id: mdoc_validate.c,v 1.340 2017/06/24 14:38:33 schwarze Exp $ */
+/*	$Id: mdoc_validate.c,v 1.343 2017/06/25 17:43:45 schwarze Exp $ */
 /*
  * Copyright (c) 2008-2012 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010-2017 Ingo Schwarze <schwarze@openbsd.org>
@@ -60,6 +60,7 @@ static	void	 check_toptext(struct roff_man *, int, int
 static	int	 child_an(const struct roff_node *);
 static	size_t		macro2len(enum roff_tok);
 static	void	 rewrite_macro2len(struct roff_man *, char **);
+static	int	 similar(const char *, const char *);
 
 static	void	 post_an(POST_ARGS);
 static	void	 post_an_norm(POST_ARGS);
@@ -1786,7 +1787,29 @@ post_sm(POST_ARGS)
 static void
 post_root(POST_ARGS)
 {
+	const char *openbsd_arch[] = {
+		"alpha", "amd64", "arm64", "armv7", "hppa", "i386",
+		"landisk", "loongson", "luna88k", "macppc", "mips64",
+		"octeon", "sgi", "socppc", "sparc64", NULL
+	};
+	const char *netbsd_arch[] = {
+		"acorn26", "acorn32", "algor", "alpha", "amiga",
+		"arc", "atari",
+		"bebox", "cats", "cesfic", "cobalt", "dreamcast",
+		"emips", "evbarm", "evbmips", "evbppc", "evbsh3", "evbsh5",
+		"hp300", "hpcarm", "hpcmips", "hpcsh", "hppa",
+		"i386", "ibmnws", "luna68k",
+		"mac68k", "macppc", "mipsco", "mmeye", "mvme68k", "mvmeppc",
+		"netwinder", "news68k", "newsmips", "next68k",
+		"pc532", "playstation2", "pmax", "pmppc", "prep",
+		"sandpoint", "sbmips", "sgimips", "shark",
+		"sparc", "sparc64", "sun2", "sun3",
+		"vax", "walnut", "x68k", "x86", "x86_64", "xen", NULL
+        };
+	const char **arches[] = { NULL, netbsd_arch, openbsd_arch };
+
 	struct roff_node *n;
+	const char **arch;
 
 	/* Add missing prologue data. */
 
@@ -1813,6 +1836,23 @@ post_root(POST_ARGS)
 		    mdoc->meta.os_e == MANDOC_OS_OPENBSD ?
 		    "(OpenBSD)" : "(NetBSD)");
 
+	if (mdoc->meta.arch != NULL &&
+	    (arch = arches[mdoc->meta.os_e]) != NULL) {
+		while (*arch != NULL && strcmp(*arch, mdoc->meta.arch))
+			arch++;
+		if (*arch == NULL) {
+			n = mdoc->first->child;
+			while (n->tok != MDOC_Dt)
+				n = n->next;
+			n = n->child->next->next;
+			mandoc_vmsg(MANDOCERR_ARCH_BAD,
+			    mdoc->parse, n->line, n->pos,
+			    "Dt ... %s %s", mdoc->meta.arch,
+			    mdoc->meta.os_e == MANDOC_OS_OPENBSD ?
+			    "(OpenBSD)" : "(NetBSD)");
+		}
+	}
+
 	/* Check that we begin with a proper `Sh'. */
 
 	n = mdoc->first->child;
@@ -2109,11 +2149,54 @@ post_sh_authors(POST_ARGS)
 		    mdoc->last->line, mdoc->last->pos, NULL);
 }
 
+/*
+ * Return an upper bound for the string distance (allowing
+ * transpositions).  Not a full Levenshtein implementation
+ * because Levenshtein is quadratic in the string length
+ * and this function is called for every standard name,
+ * so the check for each custom name would be cubic.
+ * The following crude heuristics is linear, resulting
+ * in quadratic behaviour for checking one custom name,
+ * which does not cause measurable slowdown.
+ */
+static int
+similar(const char *s1, const char *s2)
+{
+	const int	maxdist = 3;
+	int		dist = 0;
+
+	while (s1[0] != '\0' && s2[0] != '\0') {
+		if (s1[0] == s2[0]) {
+			s1++;
+			s2++;
+			continue;
+		}
+		if (++dist > maxdist)
+			return INT_MAX;
+		if (s1[1] == s2[1]) {  /* replacement */
+			s1++;
+			s2++;
+		} else if (s1[0] == s2[1] && s1[1] == s2[0]) {
+			s1 += 2;	/* transposition */
+			s2 += 2;
+		} else if (s1[0] == s2[1])  /* insertion */
+			s2++;
+		else if (s1[1] == s2[0])  /* deletion */
+			s1++;
+		else
+			return INT_MAX;
+	}
+	dist += strlen(s1) + strlen(s2);
+	return dist > maxdist ? INT_MAX : dist;
+}
+
 static void
 post_sh_head(POST_ARGS)
 {
 	struct roff_node	*nch;
 	const char		*goodsec;
+	const char *const	*testsec;
+	int			 dist, mindist;
 	enum roff_sec		 sec;
 
 	/*
@@ -2151,8 +2234,25 @@ post_sh_head(POST_ARGS)
 
 	/* We don't care about custom sections after this. */
 
-	if (sec == SEC_CUSTOM)
+	if (sec == SEC_CUSTOM) {
+		if ((nch = mdoc->last->child) == NULL ||
+		    nch->type != ROFFT_TEXT || nch->next != NULL)
+			return;
+		goodsec = NULL;
+		mindist = INT_MAX;
+		for (testsec = secnames + 1; *testsec != NULL; testsec++) {
+			dist = similar(nch->string, *testsec);
+			if (dist < mindist) {
+				goodsec = *testsec;
+				mindist = dist;
+			}
+		}
+		if (goodsec != NULL)
+			mandoc_vmsg(MANDOCERR_SEC_TYPO, mdoc->parse,
+			    nch->line, nch->pos, "Sh %s instead of %s",
+			    nch->string, goodsec);
 		return;
+	}
 
 	/*
 	 * Check whether our non-custom section is being repeated or is
@@ -2583,6 +2683,13 @@ out:
 	 * Mdocdate conventions because we don't know
 	 * the operating system earlier.
 	 */
+
+	if (n->child != NULL)
+		mandoc_vmsg(MANDOCERR_OS_ARG, mdoc->parse,
+		    n->child->line, n->child->pos,
+		    "Os %s (%s)", n->child->string,
+		    mdoc->meta.os_e == MANDOC_OS_OPENBSD ?
+		    "OpenBSD" : "NetBSD");
 
 	while (n->tok != MDOC_Dd)
 		if ((n = n->prev) == NULL)