unicode.h: Updates

- Remove from emu.h (except for UTF8_xxx macros, which have been transplanted to emucore.h since a lot of drivers use them) and osdepend.h
- Add std::string_view overrides for uchar_from_utf8 and normalize_unicode

src/devices/cpu/mips/r4000.cpp

@@ -30,6 +30,7 @@
 #include "debugger.h"
 #include "r4000.h"
 #include "mips3dsm.h"
+#include "unicode.h"
 
 #include "softfloat3/source/include/softfloat.h"
 

src/emu/drivenum.cpp

@@ -11,6 +11,7 @@
 #include "emu.h"
 #include "drivenum.h"
 #include "softlist_dev.h"
+#include "unicode.h"
 
 #include <algorithm>
 

src/emu/emu.h

@@ -38,7 +38,6 @@
 
 // commonly-referenced utilities imported from lib/util
 #include "palette.h"
-#include "unicode.h"
 #include "strformat.h"
 #include "vecstream.h"
 

src/emu/emucore.h

@@ -188,6 +188,47 @@ constexpr int ROT180               = ORIENTATION_FLIP_X | ORIENTATION_FLIP_Y;
 constexpr int ROT270               = ORIENTATION_SWAP_XY | ORIENTATION_FLIP_Y;  // rotate counter-clockwise 90 degrees
 
 
+// these are UTF-8 encoded strings for common characters
+#define UTF8_NBSP               "\xc2\xa0"          /* non-breaking space */
+
+#define UTF8_MULTIPLY           "\xc3\x97"          /* multiplication sign */
+#define UTF8_DIVIDE             "\xc3\xb7"          /* division sign */
+#define UTF8_SQUAREROOT         "\xe2\x88\x9a"      /* square root symbol */
+#define UTF8_PLUSMINUS          "\xc2\xb1"          /* plusminus symbol */
+
+#define UTF8_POW_2              "\xc2\xb2"          /* superscript 2 */
+#define UTF8_POW_X              "\xcb\xa3"          /* superscript x */
+#define UTF8_POW_Y              "\xca\xb8"          /* superscript y */
+#define UTF8_PRIME              "\xca\xb9"          /* prime symbol */
+#define UTF8_DEGREES            "\xc2\xb0"          /* degrees symbol */
+
+#define UTF8_SMALL_PI           "\xcf\x80"          /* Greek small letter pi */
+#define UTF8_CAPITAL_SIGMA      "\xce\xa3"          /* Greek capital letter sigma */
+#define UTF8_CAPITAL_DELTA      "\xce\x94"          /* Greek capital letter delta */
+
+#define UTF8_MACRON             "\xc2\xaf"          /* macron symbol */
+#define UTF8_NONSPACE_MACRON    "\xcc\x84"          /* nonspace macron, use after another char */
+
+#define a_RING                  "\xc3\xa5"          /* small a with a ring */
+#define a_UMLAUT                "\xc3\xa4"          /* small a with an umlaut */
+#define o_UMLAUT                "\xc3\xb6"          /* small o with an umlaut */
+#define u_UMLAUT                "\xc3\xbc"          /* small u with an umlaut */
+#define e_ACUTE                 "\xc3\xa9"          /* small e with an acute */
+#define n_TILDE                 "\xc3\xb1"          /* small n with a tilde */
+
+#define A_RING                  "\xc3\x85"          /* capital A with a ring */
+#define A_UMLAUT                "\xc3\x84"          /* capital A with an umlaut */
+#define O_UMLAUT                "\xc3\x96"          /* capital O with an umlaut */
+#define U_UMLAUT                "\xc3\x9c"          /* capital U with an umlaut */
+#define E_ACUTE                 "\xc3\x89"          /* capital E with an acute */
+#define N_TILDE                 "\xc3\x91"          /* capital N with a tilde */
+
+#define UTF8_LEFT               "\xe2\x86\x90"      /* cursor left */
+#define UTF8_RIGHT              "\xe2\x86\x92"      /* cursor right */
+#define UTF8_UP                 "\xe2\x86\x91"      /* cursor up */
+#define UTF8_DOWN               "\xe2\x86\x93"      /* cursor down */
+
+
 
 //**************************************************************************
 //  COMMON MACROS

src/emu/ioport.cpp

@@ -100,6 +100,7 @@
 #include "natkeyboard.h"
 
 #include "osdepend.h"
+#include "unicode.h"
 
 #include <cctype>
 #include <ctime>

src/emu/natkeyboard.cpp

@@ -11,6 +11,7 @@
 #include "emu.h"
 #include "natkeyboard.h"
 #include "emuopts.h"
+#include "unicode.h"
 
 #include <algorithm>
 #include <cstring>

src/emu/rendfont.cpp

@@ -15,6 +15,7 @@
 
 #include "osdepend.h"
 #include "uismall.fh"
+#include "unicode.h"
 
 #include "ui/uicmd14.fh"
 #include "ui/cmddata.h"
@@ -380,7 +381,7 @@ std::string convert_command_glyph(std::string_view str)
 	{
 		// decode UTF-8
 		char32_t uchar;
-		int const codelen(uchar_from_utf8(&uchar, &str[0], str.length()));
+		int const codelen(uchar_from_utf8(&uchar, str));
 		if (0 >= codelen)
 			break;
 		str.remove_prefix(codelen);
@@ -861,7 +862,7 @@ float render_font::string_width(float height, float aspect, std::string_view str
 	// loop over characters
 	while (!string.empty())
 	{
-		int scharcount = uchar_from_utf8(&schar, &string[0], string.length());
+		int scharcount = uchar_from_utf8(&schar, string);
 		totwidth += get_char(schar).width;
 		string.remove_prefix(scharcount);
 	}
@@ -884,7 +885,7 @@ float render_font::utf8string_width(float height, float aspect, std::string_view
 	while (!utf8string.empty())
 	{
 		char32_t uchar;
-		int count = uchar_from_utf8(&uchar, &utf8string[0], utf8string.length());
+		int count = uchar_from_utf8(&uchar, utf8string);
 		if (count < 0)
 			break;
 

src/emu/rendlay.cpp

@@ -18,6 +18,7 @@
 #include "video/rgbutil.h"
 
 #include "nanosvg.h"
+#include "unicode.h"
 #include "vecstream.h"
 #include "xmlfile.h"
 
@@ -3156,7 +3157,7 @@ protected:
 					while (!s.empty())
 					{
 						char32_t schar;
-						int scharcount = uchar_from_utf8(&schar, &s[0], s.length());
+						int scharcount = uchar_from_utf8(&schar, s);
 
 						if (scharcount == -1)
 							break;
@@ -3307,7 +3308,7 @@ private:
 					while (!s.empty())
 					{
 						char32_t schar;
-						int scharcount = uchar_from_utf8(&schar, &s[0], s.length());
+						int scharcount = uchar_from_utf8(&schar, s);
 
 						if (scharcount == -1)
 							break;
@@ -3693,7 +3694,7 @@ void layout_element::component::draw_text(
 	while (!str.empty())
 	{
 		char32_t schar;
-		int scharcount = uchar_from_utf8(&schar, &str[0], str.length());
+		int scharcount = uchar_from_utf8(&schar, str);
 
 		if (scharcount == -1)
 			break;

src/emu/softlist_dev.cpp

@@ -16,6 +16,8 @@
 #include "romload.h"
 #include "validity.h"
 
+#include "unicode.h"
+
 #include <cctype>
 
 

src/emu/validity.cpp

@@ -14,6 +14,7 @@
 #include "emuopts.h"
 #include "romload.h"
 #include "video/rgbutil.h"
+#include "unicode.h"
 
 #include <cctype>
 #include <type_traits>

src/frontend/mame/ui/selector.cpp

@@ -13,6 +13,7 @@
 
 #include "ui/ui.h"
 #include "ui/utils.h"
+#include "unicode.h"
 
 
 namespace ui {

src/frontend/mame/ui/selgame.cpp

@@ -31,6 +31,7 @@
 #include "romload.h"
 #include "softlist_dev.h"
 #include "uiinput.h"
+#include "unicode.h"
 
 #include <atomic>
 #include <condition_variable>

src/frontend/mame/ui/selsoft.cpp

@@ -24,6 +24,7 @@
 #include "softlist_dev.h"
 #include "uiinput.h"
 #include "luaengine.h"
+#include "unicode.h"
 
 #include <algorithm>
 #include <iterator>

src/frontend/mame/ui/text.cpp

@@ -12,6 +12,7 @@
 #include "text.h"
 #include "rendfont.h"
 #include "render.h"
+#include "unicode.h"
 
 #include <cstddef>
 #include <cstring>
@@ -133,7 +134,7 @@ void text_layout::add_text(std::string_view text, const char_style &style)
 		{
 			// get the current character
 			char32_t schar;
-			int const scharcount = uchar_from_utf8(&schar, &text[0], text.length());
+			int const scharcount = uchar_from_utf8(&schar, text);
 			if (scharcount < 0)
 				break;
 
@@ -151,7 +152,7 @@ void text_layout::add_text(std::string_view text, const char_style &style)
 
 		// get the current character
 		char32_t ch;
-		int const scharcount = uchar_from_utf8(&ch, &text[0], text.length());
+		int const scharcount = uchar_from_utf8(&ch, text);
 		if (scharcount < 0)
 			break;
 		text.remove_prefix(scharcount);

src/frontend/mame/ui/utils.h

@@ -19,6 +19,8 @@
 #include <unordered_map>
 #include <vector>
 
+#include "unicode.h"
+
 
 class mame_ui_manager;
 class render_container;

src/lib/util/unicode.cpp

@@ -120,6 +120,17 @@ bool uchar_is_digit(char32_t uchar)
 }
 
 
+//-------------------------------------------------
+//  uchar_from_utf8 - convert a UTF-8 sequence
+//  into a unicode character
+//-----------------------------------------------
+
+int uchar_from_utf8(char32_t *uchar, std::string_view utf8str)
+{
+	return uchar_from_utf8(uchar, utf8str.data(), utf8str.length());
+}
+
+
 //-------------------------------------------------
 //  uchar_from_utf8 - convert a UTF-8 sequence
 //  into a unicode character
@@ -494,9 +505,9 @@ std::string normalize_unicode(const char *s, unicode_normalization_form normaliz
 //  unicode
 //-------------------------------------------------
 
-std::string normalize_unicode(const char *s, size_t length, unicode_normalization_form normalization_form, bool fold_case)
+std::string normalize_unicode(std::string_view s, unicode_normalization_form normalization_form, bool fold_case)
 {
-	return internal_normalize_unicode(s, length, normalization_form, fold_case, false);
+	return internal_normalize_unicode(s.data(), s.length(), normalization_form, fold_case, false);
 }
 
 

src/lib/util/unicode.h

@@ -22,6 +22,7 @@
 #include "osdcore.h"
 
 #include <string>
+#include <string_view>
 
 #include <cstdlib>
 
@@ -36,46 +37,6 @@
 #define UTF8_CHAR_MAX   6
 #define UTF16_CHAR_MAX  2
 
-// these are UTF-8 encoded strings for common characters
-#define UTF8_NBSP               "\xc2\xa0"          /* non-breaking space */
-
-#define UTF8_MULTIPLY           "\xc3\x97"          /* multiplication sign */
-#define UTF8_DIVIDE             "\xc3\xb7"          /* division sign */
-#define UTF8_SQUAREROOT         "\xe2\x88\x9a"      /* square root symbol */
-#define UTF8_PLUSMINUS          "\xc2\xb1"          /* plusminus symbol */
-
-#define UTF8_POW_2              "\xc2\xb2"          /* superscript 2 */
-#define UTF8_POW_X              "\xcb\xa3"          /* superscript x */
-#define UTF8_POW_Y              "\xca\xb8"          /* superscript y */
-#define UTF8_PRIME              "\xca\xb9"          /* prime symbol */
-#define UTF8_DEGREES            "\xc2\xb0"          /* degrees symbol */
-
-#define UTF8_SMALL_PI           "\xcf\x80"          /* Greek small letter pi */
-#define UTF8_CAPITAL_SIGMA      "\xce\xa3"          /* Greek capital letter sigma */
-#define UTF8_CAPITAL_DELTA      "\xce\x94"          /* Greek capital letter delta */
-
-#define UTF8_MACRON             "\xc2\xaf"          /* macron symbol */
-#define UTF8_NONSPACE_MACRON    "\xcc\x84"          /* nonspace macron, use after another char */
-
-#define a_RING                  "\xc3\xa5"          /* small a with a ring */
-#define a_UMLAUT                "\xc3\xa4"          /* small a with an umlaut */
-#define o_UMLAUT                "\xc3\xb6"          /* small o with an umlaut */
-#define u_UMLAUT                "\xc3\xbc"          /* small u with an umlaut */
-#define e_ACUTE                 "\xc3\xa9"          /* small e with an acute */
-#define n_TILDE                 "\xc3\xb1"          /* small n with a tilde */
-
-#define A_RING                  "\xc3\x85"          /* capital A with a ring */
-#define A_UMLAUT                "\xc3\x84"          /* capital A with an umlaut */
-#define O_UMLAUT                "\xc3\x96"          /* capital O with an umlaut */
-#define U_UMLAUT                "\xc3\x9c"          /* capital U with an umlaut */
-#define E_ACUTE                 "\xc3\x89"          /* capital E with an acute */
-#define N_TILDE                 "\xc3\x91"          /* capital N with a tilde */
-
-#define UTF8_LEFT               "\xe2\x86\x90"      /* cursor left */
-#define UTF8_RIGHT              "\xe2\x86\x92"      /* cursor right */
-#define UTF8_UP                 "\xe2\x86\x91"      /* cursor up */
-#define UTF8_DOWN               "\xe2\x86\x93"      /* cursor down */
-
 enum class unicode_normalization_form { C, D, KC, KD };
 
 
@@ -95,6 +56,7 @@ bool uchar_is_digit(char32_t uchar);
 
 // converting strings to 32-bit Unicode chars
 int uchar_from_utf8(char32_t *uchar, const char *utf8char, size_t count);
+int uchar_from_utf8(char32_t *uchar, std::string_view utf8str);
 int uchar_from_utf16(char32_t *uchar, const char16_t *utf16char, size_t count);
 int uchar_from_utf16f(char32_t *uchar, const char16_t *utf16char, size_t count);
 std::u32string ustr_from_utf8(const std::string &utf8str);
@@ -112,7 +74,7 @@ std::string utf8_from_wstring(const std::wstring &string);
 // unicode normalization
 std::string normalize_unicode(const std::string &s, unicode_normalization_form normalization_form, bool fold_case = false);
 std::string normalize_unicode(const char *s, unicode_normalization_form normalization_form, bool fold_case = false);
-std::string normalize_unicode(const char *s, size_t length, unicode_normalization_form normalization_form, bool fold_case = false);
+std::string normalize_unicode(std::string_view s, unicode_normalization_form normalization_form, bool fold_case = false);
 
 // upper and lower case
 char32_t uchar_toupper(char32_t ch);

src/osd/modules/input/input_sdl.cpp

@@ -31,6 +31,7 @@
 #include "emu.h"
 #include "uiinput.h"
 #include "strconv.h"
+#include "unicode.h"
 
 // MAMEOS headers
 #include "input_common.h"

src/osd/modules/netdev/taptun.cpp

@@ -17,6 +17,7 @@
 #include "osdnet.h"
 #include "modules/osdmodule.h"
 #include "netdev_module.h"
+#include "unicode.h"
 
 #ifdef __linux__
 #define IFF_TAP     0x0002

src/osd/osdepend.h

@@ -15,7 +15,6 @@
 
 #include "emucore.h"
 #include "osdcore.h"
-#include "unicode.h"
 #include "../frontend/mame/ui/menuitem.h"
 
 #include <memory>