utf8_and_gb18030.c File Reference

#include "postgres.h"
#include "fmgr.h"
#include "mb/pg_wchar.h"
#include "../../Unicode/gb18030_to_utf8.map"
#include "../../Unicode/utf8_to_gb18030.map"

Include dependency graph for utf8_and_gb18030.c:

Go to the source code of this file.

Macros
#define	conv18030(minunicode, mincode, maxcode)
#define	convutf8(minunicode, maxunicode, mincode)

Functions
	PG_FUNCTION_INFO_V1 (gb18030_to_utf8)
	PG_FUNCTION_INFO_V1 (utf8_to_gb18030)
static uint32	gb_linear (uint32 gb)
static uint32	gb_unlinear (uint32 lin)
static uint32	unicode_to_utf8word (uint32 c)
static uint32	utf8word_to_unicode (uint32 c)
static uint32	conv_18030_to_utf8 (uint32 code)
static uint32	conv_utf8_to_18030 (uint32 code)
Datum	gb18030_to_utf8 (PG_FUNCTION_ARGS)
Datum	utf8_to_gb18030 (PG_FUNCTION_ARGS)

Variables
	PG_MODULE_MAGIC

Macro Definition Documentation

conv18030

#define conv18030	(		minunicode,
			mincode,
			maxcode
	)

Value:

    if (code >= mincode && code <= maxcode) \
        return unicode_to_utf8word(gb_linear(code) - gb_linear(mincode) + minunicode)

convutf8

#define convutf8	(		minunicode,
			maxunicode,
			mincode
	)

Value:

    if (ucs >= minunicode && ucs <= maxunicode) \
        return gb_unlinear(ucs - minunicode + gb_linear(mincode))

Function Documentation

conv_18030_to_utf8()

static uint32 conv_18030_to_utf8 ( uint32  code )

static

Definition at line 128 of file utf8_and_gb18030.c.

{
#define conv18030(minunicode, mincode, maxcode) \
    if (code >= mincode && code <= maxcode) \
        return unicode_to_utf8word(gb_linear(code) - gb_linear(mincode) + minunicode)
 
    conv18030(0x0452, 0x8130D330, 0x8136A531);
    conv18030(0x2643, 0x8137A839, 0x8138FD38);
    conv18030(0x361B, 0x8230A633, 0x8230F237);
    conv18030(0x3CE1, 0x8231D438, 0x8232AF32);
    conv18030(0x4160, 0x8232C937, 0x8232F837);
    conv18030(0x44D7, 0x8233A339, 0x8233C931);
    conv18030(0x478E, 0x8233E838, 0x82349638);
    conv18030(0x49B8, 0x8234A131, 0x8234E733);
    conv18030(0x9FA6, 0x82358F33, 0x8336C738);
    conv18030(0xE865, 0x8336D030, 0x84308534);
    conv18030(0xFA2A, 0x84309C38, 0x84318537);
    conv18030(0xFFE6, 0x8431A234, 0x8431A439);
    conv18030(0x10000, 0x90308130, 0xE3329A35);
    /* No mapping exists */
    return 0;
}

References conv18030.

Referenced by gb18030_to_utf8().

conv_utf8_to_18030()

static uint32 conv_utf8_to_18030 ( uint32  code )

static

Definition at line 155 of file utf8_and_gb18030.c.

{
    uint32      ucs = utf8word_to_unicode(code);
 
#define convutf8(minunicode, maxunicode, mincode) \
    if (ucs >= minunicode && ucs <= maxunicode) \
        return gb_unlinear(ucs - minunicode + gb_linear(mincode))
 
    convutf8(0x0452, 0x200F, 0x8130D330);
    convutf8(0x2643, 0x2E80, 0x8137A839);
    convutf8(0x361B, 0x3917, 0x8230A633);
    convutf8(0x3CE1, 0x4055, 0x8231D438);
    convutf8(0x4160, 0x4336, 0x8232C937);
    convutf8(0x44D7, 0x464B, 0x8233A339);
    convutf8(0x478E, 0x4946, 0x8233E838);
    convutf8(0x49B8, 0x4C76, 0x8234A131);
    convutf8(0x9FA6, 0xD7FF, 0x82358F33);
    convutf8(0xE865, 0xF92B, 0x8336D030);
    convutf8(0xFA2A, 0xFE2F, 0x84309C38);
    convutf8(0xFFE6, 0xFFFF, 0x8431A234);
    convutf8(0x10000, 0x10FFFF, 0x90308130);
    /* No mapping exists */
    return 0;
}

References convutf8, and utf8word_to_unicode().

Referenced by utf8_to_gb18030().

gb18030_to_utf8()

Datum gb18030_to_utf8

(

PG_FUNCTION_ARGS

)

Definition at line 194 of file utf8_and_gb18030.c.

{
    unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2);
    unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3);
    int         len = PG_GETARG_INT32(4);
    bool        noError = PG_GETARG_BOOL(5);
    int         converted;
 
    CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8);
 
    converted = LocalToUtf(src, len, dest,
                           &gb18030_to_unicode_tree,
                           NULL, 0,
                           conv_18030_to_utf8,
                           PG_GB18030,
                           noError);
 
    PG_RETURN_INT32(converted);
}

References CHECK_ENCODING_CONVERSION_ARGS, conv_18030_to_utf8(), generate_unaccent_rules::dest, len, LocalToUtf(), PG_GB18030, PG_GETARG_BOOL, PG_GETARG_CSTRING, PG_GETARG_INT32, PG_RETURN_INT32, and PG_UTF8.

gb_linear()

static uint32 gb_linear ( uint32  gb )

inlinestatic

Definition at line 32 of file utf8_and_gb18030.c.

{
    uint32      b0 = (gb & 0xff000000) >> 24;
    uint32      b1 = (gb & 0x00ff0000) >> 16;
    uint32      b2 = (gb & 0x0000ff00) >> 8;
    uint32      b3 = (gb & 0x000000ff);
 
    return b0 * 12600 + b1 * 1260 + b2 * 10 + b3 -
        (0x81 * 12600 + 0x30 * 1260 + 0x81 * 10 + 0x30);
}

gb_unlinear()

static uint32 gb_unlinear ( uint32  lin )

inlinestatic

Definition at line 44 of file utf8_and_gb18030.c.

{
    uint32      r0 = 0x81 + lin / 12600;
    uint32      r1 = 0x30 + (lin / 1260) % 10;
    uint32      r2 = 0x81 + (lin / 10) % 126;
    uint32      r3 = 0x30 + lin % 10;
 
    return (r0 << 24) | (r1 << 16) | (r2 << 8) | r3;
}

PG_FUNCTION_INFO_V1() [1/2]

PG_FUNCTION_INFO_V1

(

gb18030_to_utf8

)

PG_FUNCTION_INFO_V1() [2/2]

PG_FUNCTION_INFO_V1

(

utf8_to_gb18030

)

unicode_to_utf8word()

static uint32 unicode_to_utf8word ( uint32  c )

inlinestatic

Definition at line 60 of file utf8_and_gb18030.c.

{
    uint32      word;
 
    if (c <= 0x7F)
    {
        word = c;
    }
    else if (c <= 0x7FF)
    {
        word = (0xC0 | ((c >> 6) & 0x1F)) << 8;
        word |= 0x80 | (c & 0x3F);
    }
    else if (c <= 0xFFFF)
    {
        word = (0xE0 | ((c >> 12) & 0x0F)) << 16;
        word |= (0x80 | ((c >> 6) & 0x3F)) << 8;
        word |= 0x80 | (c & 0x3F);
    }
    else
    {
        word = (0xF0 | ((c >> 18) & 0x07)) << 24;
        word |= (0x80 | ((c >> 12) & 0x3F)) << 16;
        word |= (0x80 | ((c >> 6) & 0x3F)) << 8;
        word |= 0x80 | (c & 0x3F);
    }
 
    return word;
}

References word().

utf8_to_gb18030()

Datum utf8_to_gb18030

(

PG_FUNCTION_ARGS

)

Definition at line 215 of file utf8_and_gb18030.c.

{
    unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2);
    unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3);
    int         len = PG_GETARG_INT32(4);
    bool        noError = PG_GETARG_BOOL(5);
    int         converted;
 
    CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030);
 
    converted = UtfToLocal(src, len, dest,
                           &gb18030_from_unicode_tree,
                           NULL, 0,
                           conv_utf8_to_18030,
                           PG_GB18030,
                           noError);
 
    PG_RETURN_INT32(converted);
}

References CHECK_ENCODING_CONVERSION_ARGS, conv_utf8_to_18030(), generate_unaccent_rules::dest, len, PG_GB18030, PG_GETARG_BOOL, PG_GETARG_CSTRING, PG_GETARG_INT32, PG_RETURN_INT32, PG_UTF8, and UtfToLocal().

utf8word_to_unicode()

static uint32 utf8word_to_unicode ( uint32  c )

inlinestatic

Definition at line 91 of file utf8_and_gb18030.c.

{
    uint32      ucs;
 
    if (c <= 0x7F)
    {
        ucs = c;
    }
    else if (c <= 0xFFFF)
    {
        ucs = ((c >> 8) & 0x1F) << 6;
        ucs |= c & 0x3F;
    }
    else if (c <= 0xFFFFFF)
    {
        ucs = ((c >> 16) & 0x0F) << 12;
        ucs |= ((c >> 8) & 0x3F) << 6;
        ucs |= c & 0x3F;
    }
    else
    {
        ucs = ((c >> 24) & 0x07) << 18;
        ucs |= ((c >> 16) & 0x3F) << 12;
        ucs |= ((c >> 8) & 0x3F) << 6;
        ucs |= c & 0x3F;
    }
 
    return ucs;
}

Referenced by conv_utf8_to_18030().

Variable Documentation

PG_MODULE_MAGIC

PG_MODULE_MAGIC

Definition at line 20 of file utf8_and_gb18030.c.