Last active
October 15, 2017 09:28
-
-
Save s4y/7c95f1ebeb2c069cfb09db3c3251eca3 to your computer and use it in GitHub Desktop.
A simple UTF-8 parser that happens to be fast.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <inttypes.h> | |
typedef enum { | |
UTF8_OK = 0, | |
UTF8_ERROR = 4, | |
} utf8_decode_state_t; | |
typedef struct { | |
utf8_decode_state_t state; | |
uint32_t codepoint; | |
} utf8_decode_context_t; | |
static inline void utf8_decode( | |
utf8_decode_context_t *context, unsigned char byte | |
) { | |
switch ((int)context->state) { | |
case UTF8_OK: | |
if (byte < 0x80) { | |
context->codepoint = byte; | |
} else if (byte < 0xc0){ | |
context->state = UTF8_ERROR; | |
} else if (byte < 0xe0){ | |
context->state = 1; | |
context->codepoint = byte & 0x1f; | |
} else if (byte < 0xf0) { | |
context->state = 2; | |
context->codepoint = byte & 0xf; | |
} else if (byte < 0xf8) { | |
context->state = 3; | |
context->codepoint = byte & 0x7; | |
} else { | |
context->state = UTF8_ERROR; | |
} | |
break; | |
case 1: | |
case 2: | |
case 3: | |
if (byte >= 0x80 && byte <= 0xbf) { | |
context->state -= 1; | |
context->codepoint = | |
(context->codepoint << 6) | (byte & 0x3f); | |
} else { | |
context->state = UTF8_ERROR; | |
} | |
} | |
} | |
// - - - | |
#include <stdio.h> | |
#include <unistd.h> | |
int main() { | |
unsigned char buf[1024 * 1024]; | |
size_t count = 0; | |
size_t avail; | |
uint32_t codepoint_hash = 0; | |
utf8_decode_context_t state = { UTF8_OK, 0 }; | |
while ((avail = read(STDIN_FILENO, buf, sizeof(buf) / sizeof(*buf))) > 0) { | |
for (size_t i = 0; i < avail; i++) { | |
utf8_decode(&state, buf[i]); | |
switch (state.state) { | |
case UTF8_OK: | |
count += 1; | |
codepoint_hash ^= state.codepoint; | |
break; | |
case UTF8_ERROR: | |
return 1; | |
} | |
} | |
} | |
if (state.state != UTF8_OK) { | |
return 2; | |
} | |
printf("Decoded %zu code points and got a hash of %u.\n", count, codepoint_hash); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment