re2c::utf8 Class Reference

#include <utf8.h>

Public Types
enum	{ MAX_RUNE_LENGTH = 4u }
typedef uint32_t	rune

Static Public Member Functions
static uint32_t	rune_to_bytes (uint32_t *s, rune r)
static uint32_t	rune_length (rune r)
static rune	max_rune (uint32_t i)

Static Public Attributes
static const uint32_t	ERROR = 0xFFFDu
static const rune	MAX_1BYTE_RUNE = 0x7Fu
static const rune	MAX_2BYTE_RUNE = 0x7FFu
static const rune	MAX_3BYTE_RUNE = 0xFFFFu
static const rune	MAX_4BYTE_RUNE = 0x10FFFFu
static const rune	MAX_RUNE = utf8::MAX_4BYTE_RUNE
static const uint32_t	PREFIX_1BYTE = 0u
static const uint32_t	INFIX = 0x80u
static const uint32_t	PREFIX_2BYTE = 0xC0u
static const uint32_t	PREFIX_3BYTE = 0xE0u
static const uint32_t	PREFIX_4BYTE = 0xF0u
static const uint32_t	SHIFT = 6u
static const uint32_t	MASK = 0x3Fu

Detailed Description

Definition at line 8 of file utf8.h.

Member Typedef Documentation

typedef uint32_t re2c::utf8::rune

Definition at line 11 of file utf8.h.

Member Enumeration Documentation

anonymous enum

Enumerator
MAX_RUNE_LENGTH

Definition at line 15 of file utf8.h.

{ MAX_RUNE_LENGTH = 4u };

Member Function Documentation

utf8::rune re2c::utf8::max_rune ( uint32_t  i )

static

Definition at line 72 of file utf8.cc.

{
    switch (i)
    {
        case 1:  return MAX_1BYTE_RUNE;
        case 2:  return MAX_2BYTE_RUNE;
        case 3:  return MAX_3BYTE_RUNE;
        case 4:  return MAX_4BYTE_RUNE;
        default: return ERROR;
    }
}

Here is the caller graph for this function:

uint32_t re2c::utf8::rune_length ( rune  r )

static

Definition at line 64 of file utf8.cc.

{
    if (r <= MAX_2BYTE_RUNE)
        return r <= MAX_1BYTE_RUNE ? 1 : 2;
    else
        return r <= MAX_3BYTE_RUNE ? 3 : 4;
}

Here is the caller graph for this function:

uint32_t re2c::utf8::rune_to_bytes ( uint32_t *  s, rune  r  )

static

Definition at line 22 of file utf8.cc.

{
    // one byte sequence: 0-0x7F => 0xxxxxxx
    if (c <= MAX_1BYTE_RUNE)
    {
        str[0] = PREFIX_1BYTE | c;
        return 1;
    }

    // two byte sequence: 0x80-0x7FF => 110xxxxx 10xxxxxx
    if (c <= MAX_2BYTE_RUNE)
    {
        str[0] = PREFIX_2BYTE | (c >> 1*SHIFT);
        str[1] = INFIX        | (c & MASK);
        return 2;
    }

    // If the Rune is out of range, convert it to the error rune.
    // Do this test here because the error rune encodes to three bytes.
    // Doing it earlier would duplicate work, since an out of range
    // Rune wouldn't have fit in one or two bytes.
    if (c > MAX_RUNE)
        c = ERROR;

    // three byte sequence: 0x800 - 0xFFFF => 1110xxxx 10xxxxxx 10xxxxxx
    if (c <= MAX_3BYTE_RUNE)
    {
        str[0] = PREFIX_3BYTE | (c >> 2*SHIFT);
        str[1] = INFIX        | ((c >> 1*SHIFT) & MASK);
        str[2] = INFIX        | (c & MASK);
        return 3;
    }

    // four byte sequence (21-bit value):
    // 0x10000 - 0x1FFFFF => 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
    str[0] = PREFIX_4BYTE | (c >> 3*SHIFT);
    str[1] = INFIX        | ((c >> 2*SHIFT) & MASK);
    str[2] = INFIX        | ((c >> 1*SHIFT) & MASK);
    str[3] = INFIX        | (c & MASK);
    return 4;
}

Here is the caller graph for this function:

Member Data Documentation

const uint32_t re2c::utf8::ERROR = 0xFFFDu

static

Definition at line 18 of file utf8.h.

const uint32_t re2c::utf8::INFIX = 0x80u

static

Definition at line 28 of file utf8.h.

const uint32_t re2c::utf8::MASK = 0x3Fu

static

Definition at line 34 of file utf8.h.

const utf8::rune re2c::utf8::MAX_1BYTE_RUNE = 0x7Fu

static

Definition at line 21 of file utf8.h.

const utf8::rune re2c::utf8::MAX_2BYTE_RUNE = 0x7FFu

static

Definition at line 22 of file utf8.h.

const utf8::rune re2c::utf8::MAX_3BYTE_RUNE = 0xFFFFu

static

Definition at line 23 of file utf8.h.

const utf8::rune re2c::utf8::MAX_4BYTE_RUNE = 0x10FFFFu

static

Definition at line 24 of file utf8.h.

const utf8::rune re2c::utf8::MAX_RUNE = utf8::MAX_4BYTE_RUNE

static

Definition at line 25 of file utf8.h.

const uint32_t re2c::utf8::PREFIX_1BYTE = 0u

static

Definition at line 27 of file utf8.h.

const uint32_t re2c::utf8::PREFIX_2BYTE = 0xC0u

static

Definition at line 29 of file utf8.h.

const uint32_t re2c::utf8::PREFIX_3BYTE = 0xE0u

static

Definition at line 30 of file utf8.h.

const uint32_t re2c::utf8::PREFIX_4BYTE = 0xF0u

static

Definition at line 31 of file utf8.h.

const uint32_t re2c::utf8::SHIFT = 6u

static

Definition at line 33 of file utf8.h.

---

The documentation for this class was generated from the following files:

• ir/regexp/encoding/utf8/utf8.h
• ir/regexp/encoding/utf8/utf8.cc