Initial checkin

BeefySysLib/util/UTF8.h

@@ -0,0 +1,88 @@
+#pragma once
+
+#include "../Common.h"
+
+NS_BF_BEGIN;
+
+/* is c the start of a utf8 sequence? */
+#define isutf(c) (((c)&0xC0)!=0x80)
+
+/* convert UTF-8 data to wide character */
+int u8_toucs(wchar_t *dest, int sz, char *src, int srcsz);
+
+uint32 u8_toucs(const char* src, int srcsz, int* outLen = NULL);
+
+/* the opposite conversion */
+int u8_toutf8(char *dest, int sz, wchar_t *src, int srcsz);
+
+/* the opposite conversion */
+int u8_toutf8(char *dest, int sz, uint32 ch);
+
+/* single character to UTF-8 */
+int u8_wc_toutf8(char *dest, uint32 ch);
+
+/* character number to byte offset */
+int u8_offset(char *str, int charnum);
+
+/* byte offset to character number */
+int u8_charnum(char *s, int offset);
+
+/* return next character, updating an index variable */
+uint32 u8_nextchar(char *s, int *i);
+
+/* move to next character */
+void u8_inc(char *s, int *i);
+
+/* move to previous character */
+void u8_dec(char *s, int *i);
+
+/* returns length of next utf-8 sequence */
+int u8_seqlen(char *s);
+
+int u8_seqlen(uint32 ch);
+
+/* assuming src points to the character after a backslash, read an
+ escape sequence, storing the result in dest and returning the number of
+ input characters processed */
+int u8_read_escape_sequence(char *src, uint32 *dest);
+
+/* given a wide character, convert it to an ASCII escape sequence stored in
+ buf, where buf is "sz" bytes. returns the number of characters output. */
+int u8_escape_wchar(char *buf, int sz, uint32 ch);
+
+/* convert a string "src" containing escape sequences to UTF-8 */
+int u8_unescape(char *buf, int sz, char *src);
+
+/* convert UTF-8 "src" to ASCII with escape sequences.
+ if escape_quotes is nonzero, quote characters will be preceded by
+ backslashes as well. */
+int u8_escape(char *buf, int sz, char *src, int escape_quotes);
+
+/* utility predicates used by the above */
+int octal_digit(char c);
+int hex_digit(char c);
+
+/* return a pointer to the first occurrence of ch in s, or NULL if not
+ found. character index of found character returned in *charn. */
+char *u8_strchr(char *s, uint32 ch, int *charn);
+
+/* same as the above, but searches a buffer of a given size instead of
+ a NUL-terminated string. */
+char *u8_memchr(char *s, uint32 ch, size_t sz, int *charn);
+
+/* count the number of characters in a UTF-8 string */
+int u8_strlen(char *s);
+
+int u8_is_locale_utf8(char *locale);
+
+/* printf where the format string and arguments may be in UTF-8.
+ you can avoid this function and just use ordinary printf() if the current
+ locale is UTF-8. */
+int u8_vprintf(char *fmt, va_list ap);
+int u8_printf(char *fmt, ...);
+
+bool UTF8IsCombiningMark(uint32 c);
+bool UTF8GetGraphemeClusterSpan(const char* str, int strLength, int idx, int& startIdx, int& spanLength);
+void UTF8Categorize(const char* str, int strLength, int& numCodePoints, int& numCombiningMarks);
+
+NS_BF_END;