Main Page | Class Hierarchy | Alphabetical List | Data Structures | File List | Data Fields | Globals | Related Pages

utf8.h File Reference

C API: UTF-8 macros. More...

#include "unicode/utf.h"

Go to the source code of this file.

Defines

#define UTF8_COUNT_TRAIL_BYTES(leadByte)   (utf8_countTrailBytes[(uint8_t)leadByte])
#define UTF8_MASK_LEAD_BYTE(leadByte, countTrailBytes)   ((leadByte)&=(1<<(6-(countTrailBytes)))-1)
#define UTF8_IS_SINGLE(uchar)   (((uchar)&0x80)==0)
#define UTF8_IS_LEAD(uchar)   ((uint8_t)((uchar)-0xc0)<0x3e)
#define UTF8_IS_TRAIL(uchar)   (((uchar)&0xc0)==0x80)
#define UTF8_NEED_MULTIPLE_UCHAR(c)   ((uint32_t)(c)>0x7f)
#define UTF8_CHAR_LENGTH(c)
#define UTF8_MAX_CHAR_LENGTH   4
#define UTF8_ARRAY_SIZE(size)   ((5*(size))/2)
#define UTF8_GET_CHAR_UNSAFE(s, i, c)
#define UTF8_GET_CHAR_SAFE(s, start, i, length, c, strict)
#define UTF8_NEXT_CHAR_UNSAFE(s, i, c)
#define UTF8_APPEND_CHAR_UNSAFE(s, i, c)
#define UTF8_FWD_1_UNSAFE(s, i)
#define UTF8_FWD_N_UNSAFE(s, i, n)
#define UTF8_SET_CHAR_START_UNSAFE(s, i)
#define UTF8_NEXT_CHAR_SAFE(s, i, length, c, strict)
#define UTF8_APPEND_CHAR_SAFE(s, i, length, c)
#define UTF8_FWD_1_SAFE(s, i, length)
#define UTF8_FWD_N_SAFE(s, i, length, n)
#define UTF8_SET_CHAR_START_SAFE(s, start, i)
#define UTF8_PREV_CHAR_UNSAFE(s, i, c)
#define UTF8_BACK_1_UNSAFE(s, i)
#define UTF8_BACK_N_UNSAFE(s, i, n)
#define UTF8_SET_CHAR_LIMIT_UNSAFE(s, i)
#define UTF8_PREV_CHAR_SAFE(s, start, i, c, strict)
#define UTF8_BACK_1_SAFE(s, start, i)
#define UTF8_BACK_N_SAFE(s, start, i, n)
#define UTF8_SET_CHAR_LIMIT_SAFE(s, start, i, length)

Functions

U_CAPI UChar32 U_EXPORT2 utf8_nextCharSafeBody (const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict)
U_CAPI int32_t U_EXPORT2 utf8_appendCharSafeBody (uint8_t *s, int32_t i, int32_t length, UChar32 c)
U_CAPI UChar32 U_EXPORT2 utf8_prevCharSafeBody (const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict)
U_CAPI int32_t U_EXPORT2 utf8_back1SafeBody (const uint8_t *s, int32_t start, int32_t i)

Variables

U_CFUNC const uint8_t U_IMPORT utf8_countTrailBytes [256]


Detailed Description

C API: UTF-8 macros.

This file defines macros to deal with UTF-8 code units and code points. Signatures and semantics are the same as for the similarly named macros in utf16.h. utf8.h is included by utf.h after unicode/umachine.h and some common definitions.

Usage: ICU coding guidelines for if() statements should be followed when using these macros. Compound statements (curly braces {}) must be used for if-else-while... bodies and all macro statements should be terminated with semicolon.


Define Documentation

#define UTF8_APPEND_CHAR_SAFE s,
i,
length,
 ) 
 

Value:

{ \
    if((uint32_t)(c)<=0x7f) { \
        (s)[(i)++]=(uint8_t)(c); \
    } else { \
        (i)=utf8_appendCharSafeBody(s, (int32_t)(i), (int32_t)(length), c); \
    } \
}

#define UTF8_APPEND_CHAR_UNSAFE s,
i,
 ) 
 

Value:

{ \
    if((uint32_t)(c)<=0x7f) { \
        (s)[(i)++]=(uint8_t)(c); \
    } else { \
        if((uint32_t)(c)<=0x7ff) { \
            (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \
        } else { \
            if((uint32_t)(c)<=0xffff) { \
                (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \
            } else { \
                (s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \
                (s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \
            } \
            (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \
        } \
        (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
    } \
}

#define UTF8_BACK_1_SAFE s,
start,
 ) 
 

Value:

{ \
    if(UTF8_IS_TRAIL((s)[--(i)])) { \
        (i)=utf8_back1SafeBody(s, start, (int32_t)(i)); \
    } \
}

#define UTF8_BACK_1_UNSAFE s,
 ) 
 

Value:

{ \
    while(UTF8_IS_TRAIL((s)[--(i)])) {} \
}

#define UTF8_BACK_N_SAFE s,
start,
i,
 ) 
 

Value:

{ \
    int32_t __N=(n); \
    while(__N>0 && (i)>(start)) { \
        UTF8_BACK_1_SAFE(s, start, i); \
        --__N; \
    } \
}

#define UTF8_BACK_N_UNSAFE s,
i,
 ) 
 

Value:

{ \
    int32_t __N=(n); \
    while(__N>0) { \
        UTF8_BACK_1_UNSAFE(s, i); \
        --__N; \
    } \
}

#define UTF8_CHAR_LENGTH  ) 
 

Value:

((uint32_t)(c)<=0x7f ? 1 : \
            ((uint32_t)(c)<=0x7ff ? 2 : \
                ((uint32_t)((c)-0x10000)>0xfffff ? 3 : 4) \
            ) \
        )

#define UTF8_FWD_1_SAFE s,
i,
length   ) 
 

Value:

{ \
    uint8_t __b=(s)[(i)++]; \
    if(UTF8_IS_LEAD(__b)) { \
        uint8_t __count=UTF8_COUNT_TRAIL_BYTES(__b); \
        if((i)+__count>(length)) { \
            __count=(uint8_t)((length)-(i)); \
        } \
        while(__count>0 && UTF8_IS_TRAIL((s)[i])) { \
            ++(i); \
            --__count; \
        } \
    } \
}

#define UTF8_FWD_1_UNSAFE s,
 ) 
 

Value:

{ \
    (i)+=1+UTF8_COUNT_TRAIL_BYTES((s)[i]); \
}

#define UTF8_FWD_N_SAFE s,
i,
length,
 ) 
 

Value:

{ \
    int32_t __N=(n); \
    while(__N>0 && (i)<(length)) { \
        UTF8_FWD_1_SAFE(s, i, length); \
        --__N; \
    } \
}

#define UTF8_FWD_N_UNSAFE s,
i,
 ) 
 

Value:

{ \
    int32_t __N=(n); \
    while(__N>0) { \
        UTF8_FWD_1_UNSAFE(s, i); \
        --__N; \
    } \
}

#define UTF8_GET_CHAR_SAFE s,
start,
i,
length,
c,
strict   ) 
 

Value:

{ \
    int32_t __I=(int32_t)(i); \
    UTF8_SET_CHAR_START_SAFE(s, start, __I); \
    UTF8_NEXT_CHAR_SAFE(s, __I, length, c, strict); \
}

#define UTF8_GET_CHAR_UNSAFE s,
i,
 ) 
 

Value:

{ \
    int32_t __I=(int32_t)(i); \
    UTF8_SET_CHAR_START_UNSAFE(s, __I); \
    UTF8_NEXT_CHAR_UNSAFE(s, __I, c); \
}

#define UTF8_NEXT_CHAR_SAFE s,
i,
length,
c,
strict   ) 
 

Value:

{ \
    (c)=(s)[(i)++]; \
    if((c)>=0x80) { \
        if(UTF8_IS_LEAD(c)) { \
            (c)=utf8_nextCharSafeBody(s, &(i), (int32_t)(length), c, strict); \
        } else { \
            (c)=UTF8_ERROR_VALUE_1; \
        } \
    } \
}

#define UTF8_NEXT_CHAR_UNSAFE s,
i,
 ) 
 

Value:

{ \
    (c)=(s)[(i)++]; \
    if((uint8_t)((c)-0xc0)<0x35) { \
        uint8_t __count=UTF8_COUNT_TRAIL_BYTES(c); \
        UTF8_MASK_LEAD_BYTE(c, __count); \
        switch(__count) { \
        /* each following branch falls through to the next one */ \
        case 3: \
            (c)=((c)<<6)|((s)[(i)++]&0x3f); \
        case 2: \
            (c)=((c)<<6)|((s)[(i)++]&0x3f); \
        case 1: \
            (c)=((c)<<6)|((s)[(i)++]&0x3f); \
        /* no other branches to optimize switch() */ \
            break; \
        } \
    } \
}

#define UTF8_PREV_CHAR_SAFE s,
start,
i,
c,
strict   ) 
 

Value:

{ \
    (c)=(s)[--(i)]; \
    if((c)>=0x80) { \
        if((c)<=0xbf) { \
            (c)=utf8_prevCharSafeBody(s, start, &(i), c, strict); \
        } else { \
            (c)=UTF8_ERROR_VALUE_1; \
        } \
    } \
}

#define UTF8_PREV_CHAR_UNSAFE s,
i,
 ) 
 

Value:

{ \
    (c)=(s)[--(i)]; \
    if(UTF8_IS_TRAIL(c)) { \
        uint8_t __b, __count=1, __shift=6; \
\
        /* c is a trail byte */ \
        (c)&=0x3f; \
        for(;;) { \
            __b=(s)[--(i)]; \
            if(__b>=0xc0) { \
                UTF8_MASK_LEAD_BYTE(__b, __count); \
                (c)|=(UChar32)__b<<__shift; \
                break; \
            } else { \
                (c)|=(UChar32)(__b&0x3f)<<__shift; \
                ++__count; \
                __shift+=6; \
            } \
        } \
    } \
}

#define UTF8_SET_CHAR_LIMIT_SAFE s,
start,
i,
length   ) 
 

Value:

{ \
    if((start)<(i) && (i)<(length)) { \
        UTF8_BACK_1_SAFE(s, start, i); \
        UTF8_FWD_1_SAFE(s, i, length); \
    } \
}

#define UTF8_SET_CHAR_LIMIT_UNSAFE s,
 ) 
 

Value:

{ \
    UTF8_BACK_1_UNSAFE(s, i); \
    UTF8_FWD_1_UNSAFE(s, i); \
}

#define UTF8_SET_CHAR_START_SAFE s,
start,
 ) 
 

Value:

{ \
    if(UTF8_IS_TRAIL((s)[(i)])) { \
        (i)=utf8_back1SafeBody(s, start, (int32_t)(i)); \
    } \
}

#define UTF8_SET_CHAR_START_UNSAFE s,
 ) 
 

Value:

{ \
    while(UTF8_IS_TRAIL((s)[i])) { --(i); } \
}


Generated on Wed Nov 17 21:02:06 2004 for ICU 2.1 by  doxygen 1.3.9.1