Catch typos in .Sh names; suggested by jmc@.

I'm using a very simple, linear time / zero space fuzzy string
matching heuristic rather than a full Levenshtein metric, to keep
the code both simple and fast.

4 files changed, 73 insertions, 5 deletions

diff --git a/mandoc.1 b/mandoc.1
index 9906a39d..156db98d 100644
--- a/mandoc.1
+++ b/mandoc.1
@@ -1,4 +1,4 @@
-.\"	$Id: mandoc.1,v 1.206 2017/06/25 11:42:02 schwarze Exp $
+.\"	$Id: mandoc.1,v 1.207 2017/06/25 17:43:45 schwarze Exp $
 .\"
 .\" Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
 .\" Copyright (c) 2012, 2014-2017 Ingo Schwarze <schwarze@openbsd.org>
@@ -857,6 +857,11 @@ A single manual page contains two copies of the RCS identifier for
 the same operating system.
 Consider deleting the later instance and moving the first one up
 to the top of the page.
+.It Sy "typo in section name"
+.Pq mdoc
+Fuzzy string matching revealed that the argument of an
+.Ic \&Sh
+macro is similar, but not identical to a standard section name.
 .It Sy "useless macro"
 .Pq mdoc
 A
diff --git a/mandoc.h b/mandoc.h
index e6b48f11..8e7ddf44 100644
--- a/mandoc.h
+++ b/mandoc.h
@@ -1,4 +1,4 @@
-/*	$Id: mandoc.h,v 1.235 2017/06/24 18:58:33 schwarze Exp $ */
+/*	$Id: mandoc.h,v 1.236 2017/06/25 17:43:45 schwarze Exp $ */
 /*
  * Copyright (c) 2010, 2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010-2017 Ingo Schwarze <schwarze@openbsd.org>
@@ -56,6 +56,7 @@ enum	mandocerr {
 
 	MANDOCERR_DATE_LEGACY, /* legacy man(7) date format: Dd ... */
 	MANDOCERR_RCS_REP, /* duplicate RCS id: ... */
+	MANDOCERR_SEC_TYPO,  /* typo in section name: Sh ... */
 	MANDOCERR_MACRO_USELESS, /* useless macro: macro */
 	MANDOCERR_BX, /* consider using OS macro: macro */
 	MANDOCERR_ER_ORDER, /* errnos out of order: Er ... */
diff --git a/mdoc_validate.c b/mdoc_validate.c
index da9be6d1..08f23583 100644
--- a/mdoc_validate.c
+++ b/mdoc_validate.c
@@ -1,4 +1,4 @@
-/*	$Id: mdoc_validate.c,v 1.342 2017/06/24 18:58:33 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, const char *);
 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);
@@ -2148,11 +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;
 
 	/*
@@ -2190,8 +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
diff --git a/read.c b/read.c
index c1bb13a7..f1c14c1d 100644
--- a/read.c
+++ b/read.c
@@ -1,4 +1,4 @@
-/*	$Id: read.c,v 1.181 2017/06/24 18:58:33 schwarze Exp $ */
+/*	$Id: read.c,v 1.182 2017/06/25 17:43:45 schwarze Exp $ */
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010-2017 Ingo Schwarze <schwarze@openbsd.org>
@@ -98,6 +98,7 @@ static	const char * const	mandocerrs[MANDOCERR_MAX] = {
 
 	"legacy man(7) date format",
 	"duplicate RCS id",
+	"typo in section name",
 	"useless macro",
 	"consider using OS macro",
 	"errnos out of order",