summaryrefslogtreecommitdiffstatshomepage
path: root/src/lib/util/unicode.h
diff options
context:
space:
mode:
author AJR <ajrhacker@users.noreply.github.com>2020-12-15 13:36:55 -0500
committer AJR <ajrhacker@users.noreply.github.com>2020-12-15 13:36:55 -0500
commit2ca5f3a386a1ca63433d6d13bb66f5e46fb2a854 (patch)
treeefc52a61e29ab44d0996e97e01782591e891f646 /src/lib/util/unicode.h
parent35bec8d2731fb775248ff3634bde538d77d6f2a0 (diff)
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
Diffstat (limited to 'src/lib/util/unicode.h')
-rw-r--r--src/lib/util/unicode.h44
1 files changed, 3 insertions, 41 deletions
diff --git a/src/lib/util/unicode.h b/src/lib/util/unicode.h
index 9c727041db8..37821122998 100644
--- a/src/lib/util/unicode.h
+++ b/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);