cpp

#ifndef BJOERN_DFA

#define BJOERN_DFA

// Copyright (c) 2008-2009 Bjoern Hoehrmann <bjoern@hoehrmann.de>

// See http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.

#include "stdint.h"

#if 0

#define UTF8_ACCEPT 0

#define UTF8_REJECT 1

static const uint8_t utf8d[] = {

  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 00..1f

  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 20..3f

  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 40..5f

  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 60..7f

  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, // 80..9f

  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7, // a0..bf

  8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, // c0..df

  0xa,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x4,0x3,0x3, // e0..ef

  0xb,0x6,0x6,0x6,0x5,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8, // f0..ff

  0x0,0x1,0x2,0x3,0x5,0x8,0x7,0x1,0x1,0x1,0x4,0x6,0x1,0x1,0x1,0x1, // s0..s0

  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,0,1,1,1,1,1,0,1,0,1,1,1,1,1,1, // s1..s2

  1,2,1,1,1,1,1,2,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1, // s3..s4

  1,2,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,3,1,3,1,1,1,1,1,1, // s5..s6

  1,3,1,1,1,1,1,3,1,3,1,1,1,1,1,1,1,3,1,1,1,1,1,1,1,1,1,1,1,1,1,1, // s7..s8

};

uint32_t inline

decode(uint32_t* state, uint32_t* codep, uint32_t byte) {

  uint32_t type = utf8d[byte];

  *codep = (*state != UTF8_ACCEPT) ?

    (byte & 0x3fu) | (*codep << 6) :

    (0xff >> type) & (byte);

  *state = utf8d[256 + *state*16 + type];

  return *state;

}

#else

// Newer version, lower on the page

#define UTF8_ACCEPT 0

#define UTF8_REJECT 12

static const uint8_t utf8d[] = {

  // The first part of the table maps bytes to character classes that

  // to reduce the size of the transition table and create bitmasks.

   0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,

   0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,

   0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,

   0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,

   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,  9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,

   7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,

   8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,

  10,3,3,3,3,3,3,3,3,3,3,3,3,4,3,3, 11,6,6,6,5,8,8,8,8,8,8,8,8,8,8,8,

  // The second part is a transition table that maps a combination

  // of a state of the automaton and a character class to a state.

   0,12,24,36,60,96,84,12,12,12,48,72, 12,12,12,12,12,12,12,12,12,12,12,12,

  12, 0,12,12,12,12,12, 0,12, 0,12,12, 12,24,12,12,12,12,12,24,12,24,12,12,

  12,12,12,12,12,12,12,24,12,12,12,12, 12,24,12,12,12,12,12,12,12,24,12,12,

  12,12,12,12,12,12,12,36,12,36,12,12, 12,36,12,12,12,12,12,36,12,36,12,12,

  12,36,12,12,12,12,12,12,12,12,12,12,

};

static inline

uint32_t decode(uint32_t* state, uint32_t* codep, uint32_t byte) {

  uint32_t type = utf8d[byte];

  *codep = (*state != UTF8_ACCEPT) ?

    (byte & 0x3fu) | (*codep << 6) :

    (0xff >> type) & (byte);

  *state = utf8d[256 + *state + type];

  return *state;

}

data_lang.cc:_ZL6decodePjS_j

Line

Count

Source

73

574

uint32_t decode(uint32_t* state, uint32_t* codep, uint32_t byte) {

74

574

  uint32_t type = utf8d[byte];

75

76

574

  *codep = (*state != UTF8_ACCEPT) ?

77

42

    (byte & 0x3fu) | (*codep << 6) :

78

574

    (0xff >> type) & (byte);

79

80

574

  *state = utf8d[256 + *state + type];

81

574

  return *state;

82

574

}

j8_libc.c:_ZL6decodePjS_j

Line

Count

Source

73

267

uint32_t decode(uint32_t* state, uint32_t* codep, uint32_t byte) {

74

267

  uint32_t type = utf8d[byte];

75

76

267

  *codep = (*state != UTF8_ACCEPT) ?

77

21

    (byte & 0x3fu) | (*codep << 6) :

78

267

    (0xff >> type) & (byte);

79

80

267

  *state = utf8d[256 + *state + type];

81

267

  return *state;

82

267

}

#endif

#endif  // BJOERN_DFA