===================================================================
RCS file: /cvs/mandoc/mdoc_validate.c,v
retrieving revision 1.336
retrieving revision 1.345
diff -u -p -r1.336 -r1.345
--- mandoc/mdoc_validate.c	2017/06/11 17:16:51	1.336
+++ mandoc/mdoc_validate.c	2017/06/29 15:22:17	1.345
@@ -1,4 +1,4 @@
-/*	$Id: mdoc_validate.c,v 1.336 2017/06/11 17:16:51 schwarze Exp $ */
+/*	$Id: mdoc_validate.c,v 1.345 2017/06/29 15:22:17 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);
@@ -1459,15 +1460,30 @@ post_it(POST_ARGS)
 
 		assert(nit->head->child == NULL);
 
-		i = 0;
-		for (nch = nit->child; nch != NULL; nch = nch->next)
-			if (nch->type == ROFFT_BODY)
-				i++;
+		if (nit->head->next->child == NULL &&
+		    nit->head->next->next == NULL) {
+			mandoc_msg(MANDOCERR_MACRO_EMPTY, mdoc->parse,
+			    nit->line, nit->pos, "It");
+			roff_node_delete(mdoc, nit);
+			break;
+		}
 
+		i = 0;
+		for (nch = nit->child; nch != NULL; nch = nch->next) {
+			if (nch->type != ROFFT_BODY)
+				continue;
+			if (i++ && nch->flags & NODE_LINE)
+				mandoc_msg(MANDOCERR_TA_LINE, mdoc->parse,
+				    nch->line, nch->pos, "Ta");
+		}
 		if (i < cols || i > cols + 1)
 			mandoc_vmsg(MANDOCERR_BL_COL,
 			    mdoc->parse, nit->line, nit->pos,
 			    "%d columns, %d cells", cols, i);
+		else if (nit->head->next->child != NULL &&
+		    nit->head->next->child->line > nit->line)
+			mandoc_msg(MANDOCERR_IT_NOARG, mdoc->parse,
+			    nit->line, nit->pos, "Bl -column It");
 		break;
 	default:
 		abort();
@@ -1709,7 +1725,7 @@ post_bl(POST_ARGS)
 		nchild = nnext;
 	}
 
-	if (mdoc->meta.os_e != MDOC_OS_NETBSD)
+	if (mdoc->meta.os_e != MANDOC_OS_NETBSD)
 		return;
 
 	prev_Er = NULL;
@@ -1728,11 +1744,12 @@ post_bl(POST_ARGS)
 			if (order > 0)
 				mandoc_vmsg(MANDOCERR_ER_ORDER,
 				    mdoc->parse, nnext->line, nnext->pos,
-				    "Er %s %s", prev_Er, nnext->string);
+				    "Er %s %s (NetBSD)",
+				    prev_Er, nnext->string);
 			else if (order == 0)
 				mandoc_vmsg(MANDOCERR_ER_REP,
 				    mdoc->parse, nnext->line, nnext->pos,
-				    "Er %s", prev_Er);
+				    "Er %s (NetBSD)", prev_Er);
 		}
 		prev_Er = nnext->string;
 	}
@@ -1785,14 +1802,35 @@ 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. */
 
 	if (mdoc->meta.date == NULL)
-		mdoc->meta.date = mdoc->quick ?
-		    mandoc_strdup("") :
-		    mandoc_normdate(mdoc->parse, NULL, 0, 0);
+		mdoc->meta.date = mdoc->quick ? mandoc_strdup("") :
+		    mandoc_normdate(mdoc, NULL, 0, 0);
 
 	if (mdoc->meta.title == NULL) {
 		mandoc_msg(MANDOCERR_DT_NOTITLE,
@@ -1807,6 +1845,27 @@ post_root(POST_ARGS)
 		mandoc_msg(MANDOCERR_OS_MISSING,
 		    mdoc->parse, 0, 0, NULL);
 		mdoc->meta.os = mandoc_strdup("");
+	} else if (mdoc->meta.os_e &&
+	    (mdoc->meta.rcsids & (1 << mdoc->meta.os_e)) == 0)
+		mandoc_msg(MANDOCERR_RCS_MISSING, mdoc->parse, 0, 0,
+		    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'. */
@@ -1939,10 +1998,13 @@ post_hyph(POST_ARGS)
 static void
 post_ns(POST_ARGS)
 {
+	struct roff_node	*n;
 
-	if (mdoc->last->flags & NODE_LINE)
+	n = mdoc->last;
+	if (n->flags & NODE_LINE ||
+	    (n->next != NULL && n->next->flags & NODE_DELIMC))
 		mandoc_msg(MANDOCERR_NS_SKIP, mdoc->parse,
-		    mdoc->last->line, mdoc->last->pos, NULL);
+		    n->line, n->pos, NULL);
 }
 
 static void
@@ -2105,11 +2167,54 @@ 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;
 
 	/*
@@ -2147,8 +2252,25 @@ 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
@@ -2348,7 +2470,7 @@ post_dd(POST_ARGS)
 
 	if (n->child == NULL || n->child->string[0] == '\0') {
 		mdoc->meta.date = mdoc->quick ? mandoc_strdup("") :
-		    mandoc_normdate(mdoc->parse, NULL, n->line, n->pos);
+		    mandoc_normdate(mdoc, NULL, n->line, n->pos);
 		return;
 	}
 
@@ -2357,7 +2479,7 @@ post_dd(POST_ARGS)
 	if (mdoc->quick)
 		mdoc->meta.date = datestr;
 	else {
-		mdoc->meta.date = mandoc_normdate(mdoc->parse,
+		mdoc->meta.date = mandoc_normdate(mdoc,
 		    datestr, n->line, n->pos);
 		free(datestr);
 	}
@@ -2546,8 +2668,8 @@ post_os(POST_ARGS)
 	if (mdoc->meta.os)
 		goto out;
 
-	if (mdoc->defos) {
-		mdoc->meta.os = mandoc_strdup(mdoc->defos);
+	if (mdoc->os_s != NULL) {
+		mdoc->meta.os = mandoc_strdup(mdoc->os_s);
 		goto out;
 	}
 
@@ -2566,9 +2688,43 @@ post_os(POST_ARGS)
 	mdoc->meta.os = mandoc_strdup(defbuf);
 #endif /*!OSNAME*/
 
-out:	mdoc->meta.os_e = strstr(mdoc->meta.os, "OpenBSD") != NULL ?
-	    MDOC_OS_OPENBSD : strstr(mdoc->meta.os, "NetBSD") != NULL ?
-	    MDOC_OS_NETBSD : MDOC_OS_OTHER;
+out:
+	if (mdoc->meta.os_e == MANDOC_OS_OTHER) {
+		if (strstr(mdoc->meta.os, "OpenBSD") != NULL)
+			mdoc->meta.os_e = MANDOC_OS_OPENBSD;
+		else if (strstr(mdoc->meta.os, "NetBSD") != NULL)
+			mdoc->meta.os_e = MANDOC_OS_NETBSD;
+	}
+
+	/*
+	 * This is the earliest point where we can check
+	 * 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)
+			return;
+	if ((n = n->child) == NULL)
+		return;
+	if (strncmp(n->string, "$" "Mdocdate", 9)) {
+		if (mdoc->meta.os_e == MANDOC_OS_OPENBSD)
+			mandoc_vmsg(MANDOCERR_MDOCDATE_MISSING,
+			    mdoc->parse, n->line, n->pos,
+			    "Dd %s (OpenBSD)", n->string);
+	} else {
+		if (mdoc->meta.os_e == MANDOC_OS_NETBSD)
+			mandoc_vmsg(MANDOCERR_MDOCDATE,
+			    mdoc->parse, n->line, n->pos,
+			    "Dd %s (NetBSD)", n->string);
+	}
 }
 
 enum roff_sec