bp/utf8.h

//
// utf8.h - UTF8 helper functions
//
#pragma once

#include <stdbool.h>

#define UTF8_MAXCHARLEN 4

__attribute__((nonnull, pure))
const char *next_char(const char *str, const char *end);
__attribute__((nonnull, pure))
const char *prev_char(const char *start, const char *str);
__attribute__((nonnull, pure))
bool isidstart(const char *str, const char *end);
__attribute__((nonnull, pure))
bool isidcontinue(const char *str, const char *end);

// vim: ts=4 sw=0 et cino=L2,l1,(0,W4,m1,\:0
Updated comment 2021-05-20 17:21:06 -07:00			`//`
			`// utf8.h - UTF8 helper functions`
			`//`
Use `#pragma once` 2022-11-07 19:54:59 -08:00			`#pragma once`
Mostly working version 2021-05-20 15:27:24 -07:00
Moving cache logic into match, cleaner next_match() API, and slightly less tightly coupled UTF8 API 2021-09-21 18:45:43 -07:00			`#include <stdbool.h>`

Mostly working version 2021-05-20 15:27:24 -07:00			`#define UTF8_MAXCHARLEN 4`

			`__attribute__((nonnull, pure))`
Moving cache logic into match, cleaner next_match() API, and slightly less tightly coupled UTF8 API 2021-09-21 18:45:43 -07:00			`const char next_char(const char str, const char *end);`
Moved utf8 code into a C file, fixed some potential null deref issues 2021-05-31 12:38:42 -07:00			`__attribute__((nonnull, pure))`
Moving cache logic into match, cleaner next_match() API, and slightly less tightly coupled UTF8 API 2021-09-21 18:45:43 -07:00			`const char prev_char(const char start, const char *str);`
Overhaul of word boundaries/edges. Now they use \b, which is implemented in C, and the C code understands UTF8 id chars. 2021-07-19 19:40:43 -07:00			`__attribute__((nonnull, pure))`
Moving cache logic into match, cleaner next_match() API, and slightly less tightly coupled UTF8 API 2021-09-21 18:45:43 -07:00			`bool isidstart(const char str, const char end);`
Overhaul of word boundaries/edges. Now they use \b, which is implemented in C, and the C code understands UTF8 id chars. 2021-07-19 19:40:43 -07:00			`__attribute__((nonnull, pure))`
Moving cache logic into match, cleaner next_match() API, and slightly less tightly coupled UTF8 API 2021-09-21 18:45:43 -07:00			`bool isidcontinue(const char str, const char end);`
Moved utf8 code into a C file, fixed some potential null deref issues 2021-05-31 12:38:42 -07:00
Style change: added cino=:0 (i.e. case statements on same indentation as switch). Also fixed issue where $$ would fail to match with trailing newline on file 2021-08-28 16:05:30 -07:00			`// vim: ts=4 sw=0 et cino=L2,l1,(0,W4,m1,\:0`