Aren
/
toaruos
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[bim] Copy UTF8 decoder into bim so it is single-file

This commit is contained in:
K. Lange 2018-08-19 21:06:22 +09:00
parent fa4b4daca8
commit 5bdaa7b77b
1 changed files with 41 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
apps/bim.c
View File

@ -49,10 +49,8 @@
#ifdef __toaru__
#include <sys/fswait.h>
#include <toaru/decodeutf8.h>
#else
#include <poll.h>
#include "../base/usr/include/toaru/decodeutf8.h"
#endif
#define BLOCK_SIZE 4096
@ -2056,6 +2054,47 @@ void goto_line(int line) {
static uint32_t codepoint_r;
static uint32_t state = 0;
#define UTF8_ACCEPT 0
#define UTF8_REJECT 1
static inline uint32_t decode(uint32_t* state, uint32_t* codep, uint32_t byte) {
static int state_table[32] = {
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 0xxxxxxx */
1,1,1,1,1,1,1,1, /* 10xxxxxx */
2,2,2,2, /* 110xxxxx */
3,3, /* 1110xxxx */
4, /* 11110xxx */
1 /* 11111xxx */
};
static int mask_bytes[32] = {
0x7F,0x7F,0x7F,0x7F,0x7F,0x7F,0x7F,0x7F,
0x7F,0x7F,0x7F,0x7F,0x7F,0x7F,0x7F,0x7F,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x1F,0x1F,0x1F,0x1F,
0x0F,0x0F,
0x07,
0x00
};
static int next[5] = {
0,
1,
0,
2,
3
};
if (*state == UTF8_ACCEPT) {
*codep = byte & mask_bytes[byte >> 3];
*state = state_table[byte >> 3];
} else if (*state > 0) {
*codep = (byte & 0x3F) | (*codep << 6);
*state = next[*state];
}
return *state;
}
/**
* Processs (part of) a file and add it to a buffer.
*/