Minimal support for deep linking into man(7) pages.

As the man(7) language does not provide semantic markup,
only .SH, .SS, and .UR become anchors for now.

5 files changed, 82 insertions, 41 deletions

diff --git a/html.c b/html.c
index 9d3ca523..e424754b 100644
--- a/html.c
+++ b/html.c
@@ -1,4 +1,4 @@
-/*	$Id: html.c,v 1.209 2017/03/14 01:35:15 schwarze Exp $ */
+/*	$Id: html.c,v 1.210 2017/03/15 11:29:53 schwarze Exp $ */
 /*
  * Copyright (c) 2008-2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2011-2015, 2017 Ingo Schwarze <schwarze@openbsd.org>
@@ -28,8 +28,9 @@
 #include <string.h>
 #include <unistd.h>
 
-#include "mandoc.h"
 #include "mandoc_aux.h"
+#include "mandoc.h"
+#include "roff.h"
 #include "out.h"
 #include "html.h"
 #include "manconf.h"
@@ -236,6 +237,28 @@ print_metaf(struct html *h, enum mandoc_esc deco)
 	}
 }
 
+char *
+html_make_id(const struct roff_node *n)
+{
+	const struct roff_node	*nch;
+	char			*buf, *cp;
+
+	for (nch = n->child; nch != NULL; nch = nch->next)
+		if (nch->type != ROFFT_TEXT)
+			return NULL;
+
+	buf = NULL;
+	deroff(&buf, n);
+
+	/* http://www.w3.org/TR/html5/dom.html#the-id-attribute */
+
+	for (cp = buf; *cp != '\0'; cp++)
+		if (*cp == ' ')
+			*cp = '_';
+
+	return buf;
+}
+
 int
 html_strlen(const char *cp)
 {
diff --git a/html.h b/html.h
index 5be2f82d..02d5c57d 100644
--- a/html.h
+++ b/html.h
@@ -1,4 +1,4 @@
-/*	$Id: html.h,v 1.83 2017/02/05 20:22:04 schwarze Exp $ */
+/*	$Id: html.h,v 1.84 2017/03/15 11:29:53 schwarze Exp $ */
 /*
  * Copyright (c) 2008-2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2017 Ingo Schwarze <schwarze@openbsd.org>
@@ -112,6 +112,7 @@ struct	html {
 };
 
 
+struct	roff_node;
 struct	tbl_span;
 struct	eqn;
 
@@ -127,4 +128,5 @@ void		  print_eqn(struct html *, const struct eqn *);
 void		  print_paragraph(struct html *);
 void		  print_endline(struct html *);
 
+char		 *html_make_id(const struct roff_node *);
 int		  html_strlen(const char *);
diff --git a/man_html.c b/man_html.c
index 9151e4c7..10c544f9 100644
--- a/man_html.c
+++ b/man_html.c
@@ -1,4 +1,4 @@
-/*	$Id: man_html.c,v 1.133 2017/02/05 18:15:39 schwarze Exp $ */
+/*	$Id: man_html.c,v 1.134 2017/03/15 11:29:53 schwarze Exp $ */
 /*
  * Copyright (c) 2008-2012, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2013, 2014, 2015, 2017 Ingo Schwarze <schwarze@openbsd.org>
@@ -435,8 +435,14 @@ man_br_pre(MAN_ARGS)
 static int
 man_SH_pre(MAN_ARGS)
 {
-	if (n->type == ROFFT_HEAD)
-		print_otag(h, TAG_H1, "c", "Sh");
+	char	*id;
+
+	if (n->type == ROFFT_HEAD) {
+		id = html_make_id(n);
+		print_otag(h, TAG_H1, "cTi", "Sh", id);
+		print_otag(h, TAG_A, "chR", "selflink", id);
+		free(id);
+	}
 	return 1;
 }
 
@@ -498,8 +504,14 @@ man_SM_pre(MAN_ARGS)
 static int
 man_SS_pre(MAN_ARGS)
 {
-	if (n->type == ROFFT_HEAD)
-		print_otag(h, TAG_H2, "c", "Ss");
+	char	*id;
+
+	if (n->type == ROFFT_HEAD) {
+		id = html_make_id(n);
+		print_otag(h, TAG_H2, "cTi", "Ss", id);
+		print_otag(h, TAG_A, "chR", "selflink", id);
+		free(id);
+	}
 	return 1;
 }
 
@@ -656,7 +668,7 @@ man_UR_pre(MAN_ARGS)
 	assert(n->type == ROFFT_HEAD);
 	if (n->child != NULL) {
 		assert(n->child->type == ROFFT_TEXT);
-		print_otag(h, TAG_A, "ch", "Lk", n->child->string);
+		print_otag(h, TAG_A, "cTh", "Lk", n->child->string);
 	}
 
 	assert(n->next->type == ROFFT_BODY);
diff --git a/mandoc_html.3 b/mandoc_html.3
index a274fd03..1382a2f8 100644
--- a/mandoc_html.3
+++ b/mandoc_html.3
@@ -1,4 +1,4 @@
-.\"	$Id: mandoc_html.3,v 1.6 2017/03/13 19:01:38 schwarze Exp $
+.\"	$Id: mandoc_html.3,v 1.7 2017/03/15 11:29:53 schwarze Exp $
 .\"
 .\" Copyright (c) 2014, 2017 Ingo Schwarze <schwarze@openbsd.org>
 .\"
@@ -14,7 +14,7 @@
 .\" ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
 .\" OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 .\"
-.Dd $Mdocdate: March 13 2017 $
+.Dd $Mdocdate: March 15 2017 $
 .Dt MANDOC_HTML 3
 .Os
 .Sh NAME
@@ -48,6 +48,14 @@
 .Fa "struct html *h"
 .Fa "const char *word"
 .Fc
+.Ft char *
+.Fo html_make_id
+.Fa "const struct roff_node *n"
+.Fc
+.Ft int
+.Fo html_strlen
+.Fa "const char *cp"
+.Fc
 .Sh DESCRIPTION
 The mandoc HTML formatter is not a formal library.
 However, as it is compiled into more than one program, in particular
@@ -306,8 +314,27 @@ and
 .Fn print_tagq
 functions.
 .Pp
+The function
+.Fn html_make_id
+takes a node containing one or more text children
+and returns a newly allocated string containing the concatenation
+of the child strings, with blanks replaced by underscores.
+If the node
+.Fa n
+contains any non-text child node,
+.Fn html_make_id
+returns
+.Dv NULL
+instead.
+The caller is responsible for freeing the returned string.
+.Pp
+The function
+.Fn html_strlen
+counts the number of characters in
+.Fa cp .
+It is used as a crude estimate of the width needed to display a string.
+.Pp
 The functions
-.Fn html_strlen ,
 .Fn print_eqn ,
 .Fn print_tbl ,
 and
diff --git a/mdoc_html.c b/mdoc_html.c
index 8a0eb8dc..0f71a16b 100644
--- a/mdoc_html.c
+++ b/mdoc_html.c
@@ -1,4 +1,4 @@
-/*	$Id: mdoc_html.c,v 1.276 2017/03/14 01:35:15 schwarze Exp $ */
+/*	$Id: mdoc_html.c,v 1.277 2017/03/15 11:29:53 schwarze Exp $ */
 /*
  * Copyright (c) 2008-2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2014, 2015, 2016, 2017 Ingo Schwarze <schwarze@openbsd.org>
@@ -49,7 +49,6 @@ struct	htmlmdoc {
 };
 
 static	char		 *cond_id(const struct roff_node *);
-static	char		 *make_id(const struct roff_node *);
 static	void		  print_mdoc_head(MDOC_ARGS);
 static	void		  print_mdoc_node(MDOC_ARGS);
 static	void		  print_mdoc_nodelist(MDOC_ARGS);
@@ -478,28 +477,6 @@ mdoc_root_pre(MDOC_ARGS)
 }
 
 static char *
-make_id(const struct roff_node *n)
-{
-	const struct roff_node	*nch;
-	char			*buf, *cp;
-
-	for (nch = n->child; nch != NULL; nch = nch->next)
-		if (nch->type != ROFFT_TEXT)
-			return NULL;
-
-	buf = NULL;
-	deroff(&buf, n);
-
-	/* http://www.w3.org/TR/html5/dom.html#the-id-attribute */
-
-	for (cp = buf; *cp != '\0'; cp++)
-		if (*cp == ' ')
-			*cp = '_';
-
-	return buf;
-}
-
-static char *
 cond_id(const struct roff_node *n)
 {
 	if (n->child != NULL &&
@@ -511,7 +488,7 @@ cond_id(const struct roff_node *n)
 	     (n->parent->tok == MDOC_Xo &&
 	      n->parent->parent->prev == NULL &&
 	      n->parent->parent->parent->tok == MDOC_It)))
-		return make_id(n);
+		return html_make_id(n);
 	return NULL;
 }
 
@@ -522,7 +499,7 @@ mdoc_sh_pre(MDOC_ARGS)
 
 	switch (n->type) {
 	case ROFFT_HEAD:
-		id = make_id(n);
+		id = html_make_id(n);
 		print_otag(h, TAG_H1, "cTi", "Sh", id);
 		print_otag(h, TAG_A, "chR", "selflink", id);
 		free(id);
@@ -545,7 +522,7 @@ mdoc_ss_pre(MDOC_ARGS)
 	if (n->type != ROFFT_HEAD)
 		return 1;
 
-	id = make_id(n);
+	id = html_make_id(n);
 	print_otag(h, TAG_H2, "cTi", "Ss", id);
 	print_otag(h, TAG_A, "chR", "selflink", id);
 	free(id);
@@ -955,7 +932,7 @@ mdoc_sx_pre(MDOC_ARGS)
 {
 	char	*id;
 
-	id = make_id(n);
+	id = html_make_id(n);
 	print_otag(h, TAG_A, "cThR", "Sx", id);
 	free(id);
 	return 1;
@@ -1128,7 +1105,7 @@ mdoc_er_pre(MDOC_ARGS)
 	    (n->parent->tok == MDOC_It ||
 	     (n->parent->tok == MDOC_Bq &&
 	      n->parent->parent->parent->tok == MDOC_It)) ?
-	    make_id(n) : NULL;
+	    html_make_id(n) : NULL;
 
 	if (id != NULL)
 		print_otag(h, TAG_A, "chR", "selflink", id);