ui: better unicode support for curses, v2.

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABAgAGBQJciLFoAAoJEEy22O7T6HE4mI8P/AknxbxN0IROgo/GX9aZMnIQ
 JiqbYxj4SSXL8P+0IqgsdGXwggGlcnpM8XQa/I1e6yEl7jHQv7sccMb4EZotRJOR
 k1zeXv4ie8SY7vMOW4MfdbjZ22FKwQ4kTAlRGUAmk1NcuqpmWTH9qwBWgegfiHYP
 DVqroDf34U32kuDmo4T+m4I5Sgn0uugrD525Z9M6yN3V0dCuPbncb297X9aPd+Ou
 xrZ50iAT3sfMNIBJU4JjEBQm+jxt2JOupWhsqLwiT7jwzo65vooLgYm4MdF3iGFv
 hvFEUkE5XdauC7eRuEsmLAtWQ7BzzEFPBZKgexDDRMDQ4ROWxbnUDNqfRmIzxHfG
 AeCuHn2/iuE4IycoDqE919LOBm/TnPb08Xe9ly7tMXS7NQGsctgruI3DOA7CCjLo
 ZoTNSHElVmmjDTS5yMWyrYMEkO+W4pjC2+7vAKfj3KvW0RYG+kG1tkWIIsZogZ7C
 XmcLAKLH9RQVH0UBC0wgHHs36fGnr3DP4WsLKdSrh3OhYXSPClNM+RD7YwTu5c3j
 +vnCgpqU3yW6Bk9oBP+tiG+KgltaS+tieoGNsvvE41pqV152WuUx9sqiK4ItA9i3
 /aEN+YE2bbWnqPAKGpzC8JiNyD75VopkxkuvKkq7TERvC+2ew0USeqfmS1GSedyg
 pYnwJoJGQa1bCBUmf/S/
 =gcY1
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/kraxel/tags/ui-20190313-pull-request' into staging

ui: better unicode support for curses, v2.

# gpg: Signature made Wed 13 Mar 2019 07:29:44 GMT
# gpg:                using RSA key 4CB6D8EED3E87138
# gpg: Good signature from "Gerd Hoffmann (work) <kraxel@redhat.com>" [full]
# gpg:                 aka "Gerd Hoffmann <gerd@kraxel.org>" [full]
# gpg:                 aka "Gerd Hoffmann (private) <kraxel@gmail.com>" [full]
# Primary key fingerprint: A032 8CFF B93A 17A7 9901  FE7D 4CB6 D8EE D3E8 7138

* remotes/kraxel/tags/ui-20190313-pull-request:
  curses: add option to specify VGA font encoding
  iconv: detect and make curses depend on it

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

configure

@@ -1224,6 +1224,10 @@ for opt do
   ;;
   --enable-curses) curses="yes"
   ;;
+  --disable-iconv) iconv="no"
+  ;;
+  --enable-iconv) iconv="yes"
+  ;;
   --disable-curl) curl="no"
   ;;
   --enable-curl) curl="yes"
@@ -1713,6 +1717,7 @@ disabled with --disable-FEATURE, default is enabled if available:
   gtk             gtk UI
   vte             vte support for the gtk UI
   curses          curses UI
+  iconv           font glyph conversion support
   vnc             VNC UI support
   vnc-sasl        SASL encryption for VNC server
   vnc-jpeg        JPEG lossy compression for VNC server
@@ -3434,8 +3439,52 @@ EOF
   fi
 fi
 
+##########################################
+# iconv probe
+if test "$iconv" != "no" ; then
+  cat > $TMPC << EOF
+#include <iconv.h>
+int main(void) {
+  iconv_t conv = iconv_open("WCHAR_T", "UCS-2");
+  return conv != (iconv_t) -1;
+}
+EOF
+  iconv_prefix_list="/usr/local:/usr"
+  iconv_lib_list=":-liconv"
+  IFS=:
+  for iconv_prefix in $iconv_prefix_list; do
+    IFS=:
+    iconv_cflags="-I$iconv_prefix/include"
+    iconv_ldflags="-L$iconv_prefix/lib"
+    for iconv_link in $iconv_lib_list; do
+      unset IFS
+      iconv_lib="$iconv_ldflags $iconv_link"
+      echo "looking at iconv in '$iconv_cflags' '$iconv_lib'" >> config.log
+      if compile_prog "$iconv_cflags" "$iconv_lib" ; then
+        iconv_found=yes
+        break
+      fi
+    done
+    if test "$iconv_found" = yes ; then
+      break
+    fi
+  done
+  if test "$iconv_found" = "yes" ; then
+    iconv=yes
+  else
+    if test "$iconv" = "yes" ; then
+      feature_not_found "iconv" "Install iconv devel"
+    fi
+    iconv=no
+  fi
+fi
+
 ##########################################
 # curses probe
+if test "$iconv" = "no" ; then
+  # curses will need iconv
+  curses=no
+fi
 if test "$curses" != "no" ; then
   if test "$mingw32" = "yes" ; then
     curses_inc_list="$($pkg_config --cflags ncurses 2>/dev/null):"
@@ -3449,14 +3498,17 @@ if test "$curses" != "no" ; then
 #include <locale.h>
 #include <curses.h>
 #include <wchar.h>
+#include <langinfo.h>
 int main(void) {
+  const char *codeset;
   wchar_t wch = L'w';
   setlocale(LC_ALL, "");
   resize_term(0, 0);
   addwstr(L"wide chars\n");
   addnwstr(&wch, 1);
   add_wch(WACS_DEGREE);
-  return 0;
+  codeset = nl_langinfo(CODESET);
+  return codeset != 0;
 }
 EOF
   IFS=:
@@ -6251,6 +6303,7 @@ echo "libgcrypt         $gcrypt"
 echo "nettle            $nettle $(echo_version $nettle $nettle_version)"
 echo "libtasn1          $tasn1"
 echo "PAM               $auth_pam"
+echo "iconv support     $iconv"
 echo "curses support    $curses"
 echo "virgl support     $virglrenderer $(echo_version $virglrenderer $virgl_version)"
 echo "curl support      $curl"
@@ -6586,6 +6639,11 @@ fi
 if test "$cocoa" = "yes" ; then
   echo "CONFIG_COCOA=y" >> $config_host_mak
 fi
+if test "$iconv" = "yes" ; then
+  echo "CONFIG_ICONV=y" >> $config_host_mak
+  echo "ICONV_CFLAGS=$iconv_cflags" >> $config_host_mak
+  echo "ICONV_LIBS=$iconv_lib" >> $config_host_mak
+fi
 if test "$curses" = "yes" ; then
   echo "CONFIG_CURSES=m" >> $config_host_mak
   echo "CURSES_CFLAGS=$curses_inc" >> $config_host_mak

qapi/ui.json

@@ -1080,6 +1080,19 @@
  { 'enum'    : 'DisplayGLMode',
    'data'    : [ 'off', 'on', 'core', 'es' ] }
 
+##
+# @DisplayCurses:
+#
+# Curses display options.
+#
+# @charset:       Font charset used by guest (default: CP437).
+#
+# Since: 4.0
+#
+##
+{ 'struct'  : 'DisplayCurses',
+  'data'    : { '*charset'       : 'str' } }
+
 ##
 # @DisplayType:
 #
@@ -1142,6 +1155,7 @@
                 '*gl'            : 'DisplayGLMode' },
   'discriminator' : 'type',
   'data'    : { 'gtk'            : 'DisplayGTK',
+                'curses'         : 'DisplayCurses',
                 'egl-headless'   : 'DisplayEGLHeadless'} }
 
 ##

qemu-options.hx

@@ -1446,7 +1446,7 @@ DEF("display", HAS_ARG, QEMU_OPTION_display,
     "            [,window_close=on|off][,gl=on|core|es|off]\n"
     "-display gtk[,grab_on_hover=on|off][,gl=on|off]|\n"
     "-display vnc=<display>[,<optargs>]\n"
-    "-display curses\n"
+    "-display curses[,charset=<encoding>]\n"
     "-display none\n"
     "-display egl-headless[,rendernode=<file>]"
     "                select display type\n"
@@ -1478,6 +1478,9 @@ support a text mode, QEMU can display this output using a
 curses/ncurses interface. Nothing is displayed when the graphics
 device is in graphical mode or if the graphics device does not support
 a text mode. Generally only the VGA device models support text mode.
+The font charset used by the guest can be specified with the
+@code{charset} option, for example @code{charset=CP850} for IBM CP850
+encoding. The default is @code{CP437}.
 @item none
 Do not display video output. The guest will still see an emulated
 graphics card, but its output will not be displayed to the QEMU

ui/Makefile.objs

@@ -46,8 +46,8 @@ endif
 
 common-obj-$(CONFIG_CURSES) += curses.mo
 curses.mo-objs := curses.o
-curses.mo-cflags := $(CURSES_CFLAGS)
+curses.mo-cflags := $(CURSES_CFLAGS) $(ICONV_CFLAGS)
-curses.mo-libs := $(CURSES_LIBS)
+curses.mo-libs := $(CURSES_LIBS) $(ICONV_LIBS)
 
 common-obj-$(call land,$(CONFIG_SPICE),$(CONFIG_GIO)) += spice-app.mo
 spice-app.mo-objs := spice-app.o

ui/curses.c

@@ -27,6 +27,10 @@
 #include <sys/ioctl.h>
 #include <termios.h>
 #endif
+#include <locale.h>
+#include <wchar.h>
+#include <langinfo.h>
+#include <iconv.h>
 
 #include "qapi/error.h"
 #include "qemu-common.h"
@@ -54,25 +58,30 @@ static WINDOW *screenpad = NULL;
 static int width, height, gwidth, gheight, invalidate;
 static int px, py, sminx, sminy, smaxx, smaxy;
 
-static chtype vga_to_curses[256];
+static const char *font_charset = "CP437";
+static cchar_t vga_to_curses[256];
 
 static void curses_update(DisplayChangeListener *dcl,
                           int x, int y, int w, int h)
 {
     console_ch_t *line;
-    chtype curses_line[width];
+    cchar_t curses_line[width];
 
     line = screen + y * width;
     for (h += y; y < h; y ++, line += width) {
         for (x = 0; x < width; x++) {
             chtype ch = line[x] & 0xff;
             chtype at = line[x] & ~0xff;
-            if (vga_to_curses[ch]) {
+            if (vga_to_curses[ch].chars[0]) {
-                ch = vga_to_curses[ch];
+                curses_line[x] = vga_to_curses[ch];
+            } else {
+                curses_line[x].chars[0] = ch;
+                curses_line[x].chars[1] = 0;
+                curses_line[x].attr = 0;
             }
-            curses_line[x] = ch | at;
+            curses_line[x].attr |= at;
         }
-        mvwaddchnstr(screenpad, y, 0, curses_line, width);
+        mvwadd_wchnstr(screenpad, y, 0, curses_line, width);
     }
 
     pnoutrefresh(screenpad, py, px, sminy, sminx, smaxy - 1, smaxx - 1);
@@ -391,6 +400,254 @@ static void curses_atexit(void)
     endwin();
 }
 
+/* Setup wchar glyph for one UCS-2 char */
+static void convert_ucs(int glyph, uint16_t ch, iconv_t conv)
+{
+    wchar_t wch;
+    char *pch, *pwch;
+    size_t sch, swch;
+
+    pch = (char *) &ch;
+    pwch = (char *) &wch;
+    sch = sizeof(ch);
+    swch = sizeof(wch);
+
+    if (iconv(conv, &pch, &sch, &pwch, &swch) == (size_t) -1) {
+        fprintf(stderr, "Could not convert 0x%04x from UCS-2 to WCHAR_T: %s\n",
+                        ch, strerror(errno));
+    } else {
+        vga_to_curses[glyph].chars[0] = wch;
+    }
+}
+
+/* Setup wchar glyph for one font character */
+static void convert_font(unsigned char ch, iconv_t conv)
+{
+    wchar_t wch;
+    char *pch, *pwch;
+    size_t sch, swch;
+
+    pch = (char *) &ch;
+    pwch = (char *) &wch;
+    sch = sizeof(ch);
+    swch = sizeof(wch);
+
+    if (iconv(conv, &pch, &sch, &pwch, &swch) == (size_t) -1) {
+        fprintf(stderr, "Could not convert 0x%02x from %s to WCHAR_T: %s\n",
+                        ch, font_charset, strerror(errno));
+    } else {
+        vga_to_curses[ch].chars[0] = wch;
+    }
+}
+
+/* Convert one wchar to UCS-2 */
+static uint16_t get_ucs(wchar_t wch, iconv_t conv)
+{
+    uint16_t ch;
+    char *pch, *pwch;
+    size_t sch, swch;
+
+    pch = (char *) &ch;
+    pwch = (char *) &wch;
+    sch = sizeof(ch);
+    swch = sizeof(wch);
+
+    if (iconv(conv, &pwch, &swch, &pch, &sch) == (size_t) -1) {
+        fprintf(stderr, "Could not convert 0x%02x from WCHAR_T to UCS-2: %s\n",
+                        wch, strerror(errno));
+        return 0xFFFD;
+    }
+
+    return ch;
+}
+
+/*
+ * Setup mapping for vga to curses line graphics.
+ */
+static void font_setup(void)
+{
+    /*
+     * Control characters are normally non-printable, but VGA does have
+     * well-known glyphs for them.
+     */
+    static uint16_t control_characters[0x20] = {
+      0x0020,
+      0x263a,
+      0x263b,
+      0x2665,
+      0x2666,
+      0x2663,
+      0x2660,
+      0x2022,
+      0x25d8,
+      0x25cb,
+      0x25d9,
+      0x2642,
+      0x2640,
+      0x266a,
+      0x266b,
+      0x263c,
+      0x25ba,
+      0x25c4,
+      0x2195,
+      0x203c,
+      0x00b6,
+      0x00a7,
+      0x25ac,
+      0x21a8,
+      0x2191,
+      0x2193,
+      0x2192,
+      0x2190,
+      0x221f,
+      0x2194,
+      0x25b2,
+      0x25bc
+    };
+
+    iconv_t ucs_to_wchar_conv;
+    iconv_t wchar_to_ucs_conv;
+    iconv_t font_conv;
+    int i;
+
+    ucs_to_wchar_conv = iconv_open("WCHAR_T", "UCS-2");
+    if (ucs_to_wchar_conv == (iconv_t) -1) {
+        fprintf(stderr, "Could not convert font glyphs from UCS-2: '%s'\n",
+                        strerror(errno));
+        exit(1);
+    }
+
+    wchar_to_ucs_conv = iconv_open("UCS-2", "WCHAR_T");
+    if (wchar_to_ucs_conv == (iconv_t) -1) {
+        fprintf(stderr, "Could not convert font glyphs to UCS-2: '%s'\n",
+                        strerror(errno));
+        exit(1);
+    }
+
+    font_conv = iconv_open("WCHAR_T", font_charset);
+    if (font_conv == (iconv_t) -1) {
+        fprintf(stderr, "Could not convert font glyphs from %s: '%s'\n",
+                        font_charset, strerror(errno));
+        exit(1);
+    }
+
+    /* Control characters */
+    for (i = 0; i <= 0x1F; i++) {
+        convert_ucs(i, control_characters[i], ucs_to_wchar_conv);
+    }
+
+    for (i = 0x20; i <= 0xFF; i++) {
+        convert_font(i, font_conv);
+    }
+
+    /* DEL */
+    convert_ucs(0x7F, 0x2302, ucs_to_wchar_conv);
+
+    if (strcmp(nl_langinfo(CODESET), "UTF-8")) {
+        /* Non-Unicode capable, use termcap equivalents for those available */
+        for (i = 0; i <= 0xFF; i++) {
+            switch (get_ucs(vga_to_curses[i].chars[0], wchar_to_ucs_conv)) {
+            case 0x00a3:
+                vga_to_curses[i] = *WACS_STERLING;
+                break;
+            case 0x2591:
+                vga_to_curses[i] = *WACS_BOARD;
+                break;
+            case 0x2592:
+                vga_to_curses[i] = *WACS_CKBOARD;
+                break;
+            case 0x2502:
+                vga_to_curses[i] = *WACS_VLINE;
+                break;
+            case 0x2524:
+                vga_to_curses[i] = *WACS_RTEE;
+                break;
+            case 0x2510:
+                vga_to_curses[i] = *WACS_URCORNER;
+                break;
+            case 0x2514:
+                vga_to_curses[i] = *WACS_LLCORNER;
+                break;
+            case 0x2534:
+                vga_to_curses[i] = *WACS_BTEE;
+                break;
+            case 0x252c:
+                vga_to_curses[i] = *WACS_TTEE;
+                break;
+            case 0x251c:
+                vga_to_curses[i] = *WACS_LTEE;
+                break;
+            case 0x2500:
+                vga_to_curses[i] = *WACS_HLINE;
+                break;
+            case 0x253c:
+                vga_to_curses[i] = *WACS_PLUS;
+                break;
+            case 0x256c:
+                vga_to_curses[i] = *WACS_LANTERN;
+                break;
+            case 0x256a:
+                vga_to_curses[i] = *WACS_NEQUAL;
+                break;
+            case 0x2518:
+                vga_to_curses[i] = *WACS_LRCORNER;
+                break;
+            case 0x250c:
+                vga_to_curses[i] = *WACS_ULCORNER;
+                break;
+            case 0x2588:
+                vga_to_curses[i] = *WACS_BLOCK;
+                break;
+            case 0x03c0:
+                vga_to_curses[i] = *WACS_PI;
+                break;
+            case 0x00b1:
+                vga_to_curses[i] = *WACS_PLMINUS;
+                break;
+            case 0x2265:
+                vga_to_curses[i] = *WACS_GEQUAL;
+                break;
+            case 0x2264:
+                vga_to_curses[i] = *WACS_LEQUAL;
+                break;
+            case 0x00b0:
+                vga_to_curses[i] = *WACS_DEGREE;
+                break;
+            case 0x25a0:
+                vga_to_curses[i] = *WACS_BULLET;
+                break;
+            case 0x2666:
+                vga_to_curses[i] = *WACS_DIAMOND;
+                break;
+            case 0x2192:
+                vga_to_curses[i] = *WACS_RARROW;
+                break;
+            case 0x2190:
+                vga_to_curses[i] = *WACS_LARROW;
+                break;
+            case 0x2191:
+                vga_to_curses[i] = *WACS_UARROW;
+                break;
+            case 0x2193:
+                vga_to_curses[i] = *WACS_DARROW;
+                break;
+            case 0x23ba:
+                vga_to_curses[i] = *WACS_S1;
+                break;
+            case 0x23bb:
+                vga_to_curses[i] = *WACS_S3;
+                break;
+            case 0x23bc:
+                vga_to_curses[i] = *WACS_S7;
+                break;
+            case 0x23bd:
+                vga_to_curses[i] = *WACS_S9;
+                break;
+            }
+        }
+    }
+}
+
 static void curses_setup(void)
 {
     int i, colour_default[8] = {
@@ -420,47 +677,7 @@ static void curses_setup(void)
         init_pair(i, COLOR_WHITE, COLOR_BLACK);
     }
 
-    /*
+    font_setup();
-     * Setup mapping for vga to curses line graphics.
-     * FIXME: for better font, have to use ncursesw and setlocale()
-     */
-#if 0
-    /* FIXME: map from where? */
-    ACS_S1;
-    ACS_S3;
-    ACS_S7;
-    ACS_S9;
-#endif
-    /* ACS_* is not constant. So, we can't initialize statically. */
-    vga_to_curses['\0'] = ' ';
-    vga_to_curses[0x04] = ACS_DIAMOND;
-    vga_to_curses[0x18] = ACS_UARROW;
-    vga_to_curses[0x19] = ACS_DARROW;
-    vga_to_curses[0x1a] = ACS_RARROW;
-    vga_to_curses[0x1b] = ACS_LARROW;
-    vga_to_curses[0x9c] = ACS_STERLING;
-    vga_to_curses[0xb0] = ACS_BOARD;
-    vga_to_curses[0xb1] = ACS_CKBOARD;
-    vga_to_curses[0xb3] = ACS_VLINE;
-    vga_to_curses[0xb4] = ACS_RTEE;
-    vga_to_curses[0xbf] = ACS_URCORNER;
-    vga_to_curses[0xc0] = ACS_LLCORNER;
-    vga_to_curses[0xc1] = ACS_BTEE;
-    vga_to_curses[0xc2] = ACS_TTEE;
-    vga_to_curses[0xc3] = ACS_LTEE;
-    vga_to_curses[0xc4] = ACS_HLINE;
-    vga_to_curses[0xc5] = ACS_PLUS;
-    vga_to_curses[0xce] = ACS_LANTERN;
-    vga_to_curses[0xd8] = ACS_NEQUAL;
-    vga_to_curses[0xd9] = ACS_LRCORNER;
-    vga_to_curses[0xda] = ACS_ULCORNER;
-    vga_to_curses[0xdb] = ACS_BLOCK;
-    vga_to_curses[0xe3] = ACS_PI;
-    vga_to_curses[0xf1] = ACS_PLMINUS;
-    vga_to_curses[0xf2] = ACS_GEQUAL;
-    vga_to_curses[0xf3] = ACS_LEQUAL;
-    vga_to_curses[0xf8] = ACS_DEGREE;
-    vga_to_curses[0xfe] = ACS_BULLET;
 }
 
 static void curses_keyboard_setup(void)
@@ -493,6 +710,10 @@ static void curses_display_init(DisplayState *ds, DisplayOptions *opts)
     }
 #endif
 
+    setlocale(LC_CTYPE, "");
+    if (opts->u.curses.charset) {
+        font_charset = opts->u.curses.charset;
+    }
     curses_setup();
     curses_keyboard_setup();
     atexit(curses_atexit);

vl.c

@@ -3201,7 +3201,7 @@ int main(int argc, char **argv, char **envp)
 #ifdef CONFIG_CURSES
                 dpy.type = DISPLAY_TYPE_CURSES;
 #else
-                error_report("curses support is disabled");
+                error_report("curses or iconv support is disabled");
                 exit(1);
 #endif
                 break;