Locale support. I'm checking this in to clean up fall-out in-tree, but

it looks pretty good.  Basically, the -Tlocale option propogates into
term_ascii.c, where we set locale-specific console call-backs IFF (1)
setlocale() works; (2) locale support is compiled in (see Makefile for
-DUSE_WCHAR); (3) the internal structure of wchar_t maps directly to
Unicode codepoints as defined by __STDC_ISO_10646__; and (4) the console
supports multi-byte characters.

To date, this configuration only supports GNU/Linux.  OpenBSD doesn't
export __STDC_ISO_10646__ although I'm told by stsp@openbsd.org that it
should (it has the correct map).  Apparently FreeBSD is the same way.
NetBSD?  Don't know.  Apple also supports this, but doesn't define the
macro.  Special-casing!

Benchmark: -Tlocale incurs less than 0.2 factor overhead when run
through several thousand manuals when UTF8 output is enabled.  Native
mode (whether directly -Tascii or through no locale or whatever) is
UNCHANGED: the function callbacks are the same as before.

Note.  If the underlying system does NOT support STDC_ISO_10646, there
is a "slow" version possible with iconv or other means of flipping from
a Unicode codepoint to a wchar_t.

1 files changed, 70 insertions, 13 deletions

diff --git a/term_ascii.c b/term_ascii.c
index 5b2ee847..7619907e 100644
--- a/term_ascii.c
+++ b/term_ascii.c
@@ -1,4 +1,4 @@
-/*	$Id: term_ascii.c,v 1.14 2011/05/17 14:38:34 kristaps Exp $ */
+/*	$Id: term_ascii.c,v 1.15 2011/05/17 22:32:45 kristaps Exp $ */
 /*
  * Copyright (c) 2010 Kristaps Dzonsons <kristaps@bsd.lv>
  *
@@ -21,16 +21,26 @@
 #include <sys/types.h>
 
 #include <assert.h>
+#ifdef USE_WCHAR
+# include <locale.h>
+#endif
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
+#ifdef USE_WCHAR
+# include <wchar.h>
+#endif
 
 #include "mandoc.h"
 #include "out.h"
 #include "term.h"
 #include "main.h"
 
+#if ! defined(__STDC_ISO_10646__)
+# undef USE_WCHAR
+#endif
+
 static	struct termp	 *ascii_init(enum termenc, char *);
 static	double		  ascii_hspan(const struct termp *,
 				const struct roffsu *);
@@ -41,6 +51,13 @@ static	void		  ascii_end(struct termp *);
 static	void		  ascii_endline(struct termp *);
 static	void		  ascii_letter(struct termp *, int);
 
+#ifdef	USE_WCHAR
+static	void		  locale_advance(struct termp *, size_t);
+static	void		  locale_endline(struct termp *);
+static	void		  locale_letter(struct termp *, int);
+static	size_t		  locale_width(const struct termp *, int);
+#endif
+
 static struct termp *
 ascii_init(enum termenc enc, char *outopts)
 {
@@ -54,15 +71,28 @@ ascii_init(enum termenc enc, char *outopts)
 	p->tabwidth = 5;
 	p->defrmargin = 78;
 
-	p->advance = ascii_advance;
 	p->begin = ascii_begin;
 	p->end = ascii_end;
-	p->endline = ascii_endline;
 	p->hspan = ascii_hspan;
-	p->letter = ascii_letter;
 	p->type = TERMTYPE_CHAR;
+
+	p->enc = TERMENC_ASCII;
+	p->advance = ascii_advance;
+	p->endline = ascii_endline;
+	p->letter = ascii_letter;
 	p->width = ascii_width;
 
+#if defined (USE_WCHAR)
+	if (TERMENC_LOCALE == enc)
+		if (setlocale(LC_ALL, "") && MB_CUR_MAX > 1) {
+			p->enc = enc;
+			p->advance = locale_advance;
+			p->endline = locale_endline;
+			p->letter = locale_letter;
+			p->width = locale_width;
+		}
+#endif
+
 	toks[0] = "width";
 	toks[1] = NULL;
 
@@ -104,7 +134,6 @@ ascii_width(const struct termp *p, int c)
 	return(1);
 }
 
-
 void
 ascii_free(void *arg)
 {
@@ -112,17 +141,14 @@ ascii_free(void *arg)
 	term_free((struct termp *)arg);
 }
 
-
 /* ARGSUSED */
 static void
 ascii_letter(struct termp *p, int c)
 {
 	
-	/* LINTED */
 	putchar(c);
 }
 
-
 static void
 ascii_begin(struct termp *p)
 {
@@ -130,7 +156,6 @@ ascii_begin(struct termp *p)
 	(*p->headf)(p, p->argf);
 }
 
-
 static void
 ascii_end(struct termp *p)
 {
@@ -138,7 +163,6 @@ ascii_end(struct termp *p)
 	(*p->footf)(p, p->argf);
 }
 
-
 /* ARGSUSED */
 static void
 ascii_endline(struct termp *p)
@@ -147,19 +171,16 @@ ascii_endline(struct termp *p)
 	putchar('\n');
 }
 
-
 /* ARGSUSED */
 static void
 ascii_advance(struct termp *p, size_t len)
 {
 	size_t	 	i;
 
-	/* Just print whitespace on the terminal. */
 	for (i = 0; i < len; i++)
 		putchar(' ');
 }
 
-
 /* ARGSUSED */
 static double
 ascii_hspan(const struct termp *p, const struct roffsu *su)
@@ -198,3 +219,39 @@ ascii_hspan(const struct termp *p, const struct roffsu *su)
 	return(r);
 }
 
+#ifdef USE_WCHAR
+/* ARGSUSED */
+static size_t
+locale_width(const struct termp *p, int c)
+{
+	int		rc;
+
+	return((rc = wcwidth(c)) < 0 ? 0 : rc);
+}
+
+/* ARGSUSED */
+static void
+locale_advance(struct termp *p, size_t len)
+{
+	size_t	 	i;
+
+	for (i = 0; i < len; i++)
+		putwchar(L' ');
+}
+
+/* ARGSUSED */
+static void
+locale_endline(struct termp *p)
+{
+
+	putwchar(L'\n');
+}
+
+/* ARGSUSED */
+static void
+locale_letter(struct termp *p, int c)
+{
+	
+	putwchar(c);
+}
+#endif