pg_wchar.h File Reference

#include "port/simd.h"

Include dependency graph for pg_wchar.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Data Structures
struct	pg_enc2name
struct	pg_enc2gettext
struct	pg_wchar_tbl
struct	pg_mb_radix_tree
struct	pg_utf_to_local_combined
struct	pg_local_to_utf_combined

Macros
#define	MAX_MULTIBYTE_CHAR_LEN   4
#define	SS2   0x8e /* single shift 2 (JIS0201) */
#define	SS3   0x8f /* single shift 3 (JIS0212) */
#define	ISSJISHEAD(c)   (((c) >= 0x81 && (c) <= 0x9f) || ((c) >= 0xe0 && (c) <= 0xfc))
#define	ISSJISTAIL(c)   (((c) >= 0x40 && (c) <= 0x7e) || ((c) >= 0x80 && (c) <= 0xfc))
#define	LC_ISO8859_1   0x81 /* ISO8859 Latin 1 */
#define	LC_ISO8859_2   0x82 /* ISO8859 Latin 2 */
#define	LC_ISO8859_3   0x83 /* ISO8859 Latin 3 */
#define	LC_ISO8859_4   0x84 /* ISO8859 Latin 4 */
#define	LC_TIS620   0x85 /* Thai (not supported yet) */
#define	LC_ISO8859_7   0x86 /* Greek (not supported yet) */
#define	LC_ISO8859_6   0x87 /* Arabic (not supported yet) */
#define	LC_ISO8859_8   0x88 /* Hebrew (not supported yet) */
#define	LC_JISX0201K   0x89 /* Japanese 1 byte kana */
#define	LC_JISX0201R   0x8a /* Japanese 1 byte Roman */
#define	LC_KOI8_R   0x8b /* Cyrillic KOI8-R */
#define	LC_ISO8859_5   0x8c /* ISO8859 Cyrillic */
#define	LC_ISO8859_9   0x8d /* ISO8859 Latin 5 (not supported yet) */
#define	LC_ISO8859_15   0x8e /* ISO8859 Latin 15 (not supported yet) */
#define	IS_LC1(c)   ((unsigned char)(c) >= 0x81 && (unsigned char)(c) <= 0x8d)
#define	LC_JISX0208_1978   0x90 /* Japanese Kanji, old JIS (not supported) */
#define	LC_GB2312_80   0x91 /* Chinese */
#define	LC_JISX0208   0x92 /* Japanese Kanji (JIS X 0208) */
#define	LC_KS5601   0x93 /* Korean */
#define	LC_JISX0212   0x94 /* Japanese Kanji (JIS X 0212) */
#define	LC_CNS11643_1   0x95 /* CNS 11643-1992 Plane 1 */
#define	LC_CNS11643_2   0x96 /* CNS 11643-1992 Plane 2 */
#define	LC_JISX0213_1
#define	LC_BIG5_1
#define	LC_BIG5_2
#define	IS_LC2(c)   ((unsigned char)(c) >= 0x90 && (unsigned char)(c) <= 0x99)
#define	LCPRV1_A   0x9a
#define	LCPRV1_B   0x9b
#define	IS_LCPRV1(c)   ((unsigned char)(c) == LCPRV1_A || (unsigned char)(c) == LCPRV1_B)
#define	IS_LCPRV1_A_RANGE(c)    ((unsigned char)(c) >= 0xa0 && (unsigned char)(c) <= 0xdf)
#define	IS_LCPRV1_B_RANGE(c)    ((unsigned char)(c) >= 0xe0 && (unsigned char)(c) <= 0xef)
#define	LCPRV2_A   0x9c
#define	LCPRV2_B   0x9d
#define	IS_LCPRV2(c)   ((unsigned char)(c) == LCPRV2_A || (unsigned char)(c) == LCPRV2_B)
#define	IS_LCPRV2_A_RANGE(c)    ((unsigned char)(c) >= 0xf0 && (unsigned char)(c) <= 0xf4)
#define	IS_LCPRV2_B_RANGE(c)    ((unsigned char)(c) >= 0xf5 && (unsigned char)(c) <= 0xfe)
#define	LC_SISHENG
#define	LC_IPA
#define	LC_VISCII_LOWER
#define	LC_VISCII_UPPER
#define	LC_ARABIC_DIGIT   0xa4 /* Arabic digit (not supported) */
#define	LC_ARABIC_1_COLUMN   0xa5 /* Arabic 1-column (not supported) */
#define	LC_ASCII_RIGHT_TO_LEFT
#define	LC_LAO
#define	LC_ARABIC_2_COLUMN   0xa8 /* Arabic 1-column (not supported) */
#define	LC_INDIAN_1_COLUMN
#define	LC_TIBETAN_1_COLUMN
#define	LC_UNICODE_SUBSET_2
#define	LC_UNICODE_SUBSET_3
#define	LC_UNICODE_SUBSET
#define	LC_ETHIOPIC   0xf5 /* Ethiopic characters (not supported) */
#define	LC_CNS11643_3   0xf6 /* CNS 11643-1992 Plane 3 */
#define	LC_CNS11643_4   0xf7 /* CNS 11643-1992 Plane 4 */
#define	LC_CNS11643_5   0xf8 /* CNS 11643-1992 Plane 5 */
#define	LC_CNS11643_6   0xf9 /* CNS 11643-1992 Plane 6 */
#define	LC_CNS11643_7   0xfa /* CNS 11643-1992 Plane 7 */
#define	LC_INDIAN_2_COLUMN
#define	LC_TIBETAN   0xfc /* Tibetan (not supported) */
#define	PG_ENCODING_BE_LAST   PG_KOI8U
#define	PG_VALID_BE_ENCODING(_enc)    ((_enc) >= 0 && (_enc) <= PG_ENCODING_BE_LAST)
#define	PG_ENCODING_IS_CLIENT_ONLY(_enc)    ((_enc) > PG_ENCODING_BE_LAST && (_enc) < _PG_LAST_ENCODING_)
#define	PG_VALID_ENCODING(_enc)    ((_enc) >= 0 && (_enc) < _PG_LAST_ENCODING_)
#define	PG_VALID_FE_ENCODING(_enc)   PG_VALID_ENCODING(_enc)
#define	MAX_CONVERSION_GROWTH   4
#define	MAX_CONVERSION_INPUT_LENGTH   16
#define	MAX_UNICODE_EQUIVALENT_STRING   16
#define	CHECK_ENCODING_CONVERSION_ARGS(srcencoding, destencoding)

Typedefs
typedef unsigned int	pg_wchar
typedef enum pg_enc	pg_enc
typedef struct pg_enc2name	pg_enc2name
typedef struct pg_enc2gettext	pg_enc2gettext
typedef int(*	mb2wchar_with_len_converter) (const unsigned char *from, pg_wchar *to, int len)
typedef int(*	wchar2mb_with_len_converter) (const pg_wchar *from, unsigned char *to, int len)
typedef int(*	mblen_converter) (const unsigned char *mbstr)
typedef int(*	mbdisplaylen_converter) (const unsigned char *mbstr)
typedef bool(*	mbcharacter_incrementer) (unsigned char *mbstr, int len)
typedef int(*	mbchar_verifier) (const unsigned char *mbstr, int len)
typedef int(*	mbstr_verifier) (const unsigned char *mbstr, int len)
typedef uint32(*	utf_local_conversion_func) (uint32 code)

Enumerations
enum	pg_enc {   PG_SQL_ASCII = 0 , PG_EUC_JP , PG_EUC_CN , PG_EUC_KR ,   PG_EUC_TW , PG_EUC_JIS_2004 , PG_UTF8 , PG_MULE_INTERNAL ,   PG_LATIN1 , PG_LATIN2 , PG_LATIN3 , PG_LATIN4 ,   PG_LATIN5 , PG_LATIN6 , PG_LATIN7 , PG_LATIN8 ,   PG_LATIN9 , PG_LATIN10 , PG_WIN1256 , PG_WIN1258 ,   PG_WIN866 , PG_WIN874 , PG_KOI8R , PG_WIN1251 ,   PG_WIN1252 , PG_ISO_8859_5 , PG_ISO_8859_6 , PG_ISO_8859_7 ,   PG_ISO_8859_8 , PG_WIN1250 , PG_WIN1253 , PG_WIN1254 ,   PG_WIN1255 , PG_WIN1257 , PG_KOI8U , PG_SJIS ,   PG_BIG5 , PG_GBK , PG_UHC , PG_GB18030 ,   PG_JOHAB , PG_SHIFT_JIS_2004 , _PG_LAST_ENCODING_ }

Functions
static bool	is_valid_unicode_codepoint (pg_wchar c)
static bool	is_utf16_surrogate_first (pg_wchar c)
static bool	is_utf16_surrogate_second (pg_wchar c)
static pg_wchar	surrogate_pair_to_codepoint (pg_wchar first, pg_wchar second)
int	pg_char_to_encoding (const char *name)
const char *	pg_encoding_to_char (int encoding)
int	pg_valid_server_encoding_id (int encoding)
int	pg_encoding_mblen (int encoding, const char *mbstr)
int	pg_encoding_mblen_bounded (int encoding, const char *mbstr)
int	pg_encoding_dsplen (int encoding, const char *mbstr)
int	pg_encoding_verifymbchar (int encoding, const char *mbstr, int len)
int	pg_encoding_verifymbstr (int encoding, const char *mbstr, int len)
int	pg_encoding_max_length (int encoding)
int	pg_valid_client_encoding (const char *name)
int	pg_valid_server_encoding (const char *name)
bool	is_encoding_supported_by_icu (int encoding)
const char *	get_encoding_name_for_icu (int encoding)
unsigned char *	unicode_to_utf8 (pg_wchar c, unsigned char *utf8string)
pg_wchar	utf8_to_unicode (const unsigned char *c)
bool	pg_utf8_islegal (const unsigned char *source, int length)
int	pg_utf_mblen (const unsigned char *s)
int	pg_mule_mblen (const unsigned char *s)
int	pg_mb2wchar (const char *from, pg_wchar *to)
int	pg_mb2wchar_with_len (const char *from, pg_wchar *to, int len)
int	pg_encoding_mb2wchar_with_len (int encoding, const char *from, pg_wchar *to, int len)
int	pg_wchar2mb (const pg_wchar *from, char *to)
int	pg_wchar2mb_with_len (const pg_wchar *from, char *to, int len)
int	pg_encoding_wchar2mb_with_len (int encoding, const pg_wchar *from, char *to, int len)
int	pg_char_and_wchar_strcmp (const char *s1, const pg_wchar *s2)
int	pg_wchar_strncmp (const pg_wchar *s1, const pg_wchar *s2, size_t n)
int	pg_char_and_wchar_strncmp (const char *s1, const pg_wchar *s2, size_t n)
size_t	pg_wchar_strlen (const pg_wchar *str)
int	pg_mblen (const char *mbstr)
int	pg_dsplen (const char *mbstr)
int	pg_mbstrlen (const char *mbstr)
int	pg_mbstrlen_with_len (const char *mbstr, int limit)
int	pg_mbcliplen (const char *mbstr, int len, int limit)
int	pg_encoding_mbcliplen (int encoding, const char *mbstr, int len, int limit)
int	pg_mbcharcliplen (const char *mbstr, int len, int limit)
int	pg_database_encoding_max_length (void)
mbcharacter_incrementer	pg_database_encoding_character_incrementer (void)
int	PrepareClientEncoding (int encoding)
int	SetClientEncoding (int encoding)
void	InitializeClientEncoding (void)
int	pg_get_client_encoding (void)
const char *	pg_get_client_encoding_name (void)
void	SetDatabaseEncoding (int encoding)
int	GetDatabaseEncoding (void)
const char *	GetDatabaseEncodingName (void)
void	SetMessageEncoding (int encoding)
int	GetMessageEncoding (void)
unsigned char *	pg_do_encoding_conversion (unsigned char *src, int len, int src_encoding, int dest_encoding)
int	pg_do_encoding_conversion_buf (Oid proc, int src_encoding, int dest_encoding, unsigned char *src, int srclen, unsigned char *dest, int destlen, bool noError)
char *	pg_client_to_server (const char *s, int len)
char *	pg_server_to_client (const char *s, int len)
char *	pg_any_to_server (const char *s, int len, int encoding)
char *	pg_server_to_any (const char *s, int len, int encoding)
void	pg_unicode_to_server (pg_wchar c, unsigned char *s)
bool	pg_unicode_to_server_noerror (pg_wchar c, unsigned char *s)
unsigned short	BIG5toCNS (unsigned short big5, unsigned char *lc)
unsigned short	CNStoBIG5 (unsigned short cns, unsigned char lc)
int	UtfToLocal (const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, int encoding, bool noError)
int	LocalToUtf (const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, int encoding, bool noError)
bool	pg_verifymbstr (const char *mbstr, int len, bool noError)
bool	pg_verify_mbstr (int encoding, const char *mbstr, int len, bool noError)
int	pg_verify_mbstr_len (int encoding, const char *mbstr, int len, bool noError)
void	check_encoding_conversion_args (int src_encoding, int dest_encoding, int len, int expected_src_encoding, int expected_dest_encoding)
void	report_invalid_encoding (int encoding, const char *mbstr, int len) pg_attribute_noreturn()
void	report_untranslatable_char (int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn()
int	local2local (const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, const unsigned char *tab, bool noError)
int	latin2mic (const unsigned char *l, unsigned char *p, int len, int lc, int encoding, bool noError)
int	mic2latin (const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, bool noError)
int	latin2mic_with_table (const unsigned char *l, unsigned char *p, int len, int lc, int encoding, const unsigned char *tab, bool noError)
int	mic2latin_with_table (const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, const unsigned char *tab, bool noError)
static bool	is_valid_ascii (const unsigned char *s, int len)

Variables
PGDLLIMPORT const pg_enc2name	pg_enc2name_tbl []
PGDLLIMPORT const pg_enc2gettext	pg_enc2gettext_tbl []
PGDLLIMPORT const pg_wchar_tbl	pg_wchar_table []

Macro Definition Documentation

CHECK_ENCODING_CONVERSION_ARGS

#define CHECK_ENCODING_CONVERSION_ARGS	(		srcencoding,
			destencoding
	)

Value:

    check_encoding_conversion_args(PG_GETARG_INT32(0), \
                                   PG_GETARG_INT32(1), \
                                   PG_GETARG_INT32(4), \
                                   (srcencoding), \
                                   (destencoding))

Definition at line 513 of file pg_wchar.h.

IS_LC1

#define IS_LC1

(

c

)

((unsigned char)(c) >= 0x81 && (unsigned char)(c) <= 0x8d)

Definition at line 125 of file pg_wchar.h.

IS_LC2

#define IS_LC2

(

c

)

((unsigned char)(c) >= 0x90 && (unsigned char)(c) <= 0x99)

Definition at line 143 of file pg_wchar.h.

IS_LCPRV1

#define IS_LCPRV1

(

c

)

((unsigned char)(c) == LCPRV1_A || (unsigned char)(c) == LCPRV1_B)

Definition at line 151 of file pg_wchar.h.

IS_LCPRV1_A_RANGE

#define IS_LCPRV1_A_RANGE

(

c

)

((unsigned char)(c) >= 0xa0 && (unsigned char)(c) <= 0xdf)

Definition at line 152 of file pg_wchar.h.

IS_LCPRV1_B_RANGE

#define IS_LCPRV1_B_RANGE

(

c

)

((unsigned char)(c) >= 0xe0 && (unsigned char)(c) <= 0xef)

Definition at line 154 of file pg_wchar.h.

IS_LCPRV2

#define IS_LCPRV2

(

c

)

((unsigned char)(c) == LCPRV2_A || (unsigned char)(c) == LCPRV2_B)

Definition at line 163 of file pg_wchar.h.

IS_LCPRV2_A_RANGE

#define IS_LCPRV2_A_RANGE

(

c

)

((unsigned char)(c) >= 0xf0 && (unsigned char)(c) <= 0xf4)

Definition at line 164 of file pg_wchar.h.

IS_LCPRV2_B_RANGE

#define IS_LCPRV2_B_RANGE

(

c

)

((unsigned char)(c) >= 0xf5 && (unsigned char)(c) <= 0xfe)

Definition at line 166 of file pg_wchar.h.

ISSJISHEAD

#define ISSJISHEAD

(

c

)

(((c) >= 0x81 && (c) <= 0x9f) || ((c) >= 0xe0 && (c) <= 0xfc))

Definition at line 43 of file pg_wchar.h.

ISSJISTAIL

#define ISSJISTAIL

(

c

)

(((c) >= 0x40 && (c) <= 0x7e) || ((c) >= 0x80 && (c) <= 0xfc))

Definition at line 44 of file pg_wchar.h.

LC_ARABIC_1_COLUMN

#define LC_ARABIC_1_COLUMN   0xa5 /* Arabic 1-column (not supported) */

Definition at line 177 of file pg_wchar.h.

LC_ARABIC_2_COLUMN

#define LC_ARABIC_2_COLUMN   0xa8 /* Arabic 1-column (not supported) */

Definition at line 180 of file pg_wchar.h.

LC_ARABIC_DIGIT

#define LC_ARABIC_DIGIT   0xa4 /* Arabic digit (not supported) */

Definition at line 176 of file pg_wchar.h.

LC_ASCII_RIGHT_TO_LEFT

#define LC_ASCII_RIGHT_TO_LEFT

Value:

                                         0xa6   /* ASCII (left half of ISO8859-1) with
                                         * right-to-left direction (not
                                         * supported) */

Definition at line 178 of file pg_wchar.h.

LC_BIG5_1

#define LC_BIG5_1

Value:

                                     0x98   /* Plane 1 Chinese traditional (not
                                     * supported) */

Definition at line 139 of file pg_wchar.h.

LC_BIG5_2

#define LC_BIG5_2

Value:

                                     0x99   /* Plane 1 Chinese traditional (not
                                     * supported) */

Definition at line 140 of file pg_wchar.h.

LC_CNS11643_1

#define LC_CNS11643_1   0x95 /* CNS 11643-1992 Plane 1 */

Definition at line 136 of file pg_wchar.h.

LC_CNS11643_2

#define LC_CNS11643_2   0x96 /* CNS 11643-1992 Plane 2 */

Definition at line 137 of file pg_wchar.h.

LC_CNS11643_3

#define LC_CNS11643_3   0xf6 /* CNS 11643-1992 Plane 3 */

Definition at line 191 of file pg_wchar.h.

LC_CNS11643_4

#define LC_CNS11643_4   0xf7 /* CNS 11643-1992 Plane 4 */

Definition at line 192 of file pg_wchar.h.

LC_CNS11643_5

#define LC_CNS11643_5   0xf8 /* CNS 11643-1992 Plane 5 */

Definition at line 193 of file pg_wchar.h.

LC_CNS11643_6

#define LC_CNS11643_6   0xf9 /* CNS 11643-1992 Plane 6 */

Definition at line 194 of file pg_wchar.h.

LC_CNS11643_7

#define LC_CNS11643_7   0xfa /* CNS 11643-1992 Plane 7 */

Definition at line 195 of file pg_wchar.h.

LC_ETHIOPIC

#define LC_ETHIOPIC   0xf5 /* Ethiopic characters (not supported) */

Definition at line 190 of file pg_wchar.h.

LC_GB2312_80

#define LC_GB2312_80   0x91 /* Chinese */

Definition at line 132 of file pg_wchar.h.

LC_INDIAN_1_COLUMN

#define LC_INDIAN_1_COLUMN

Value:

                                     0xf0   /* Indian charset for 1-column width
                                     * glyphs (not supported) */

Definition at line 185 of file pg_wchar.h.

LC_INDIAN_2_COLUMN

#define LC_INDIAN_2_COLUMN

Value:

                                     0xfb   /* Indian charset for 2-column width
                                     * glyphs (not supported) */

Definition at line 196 of file pg_wchar.h.

LC_IPA

#define LC_IPA

Value:

                                     0xa1   /* IPA (International Phonetic
                                     * Association) (not supported) */

Definition at line 173 of file pg_wchar.h.

LC_ISO8859_1

#define LC_ISO8859_1   0x81 /* ISO8859 Latin 1 */

Definition at line 104 of file pg_wchar.h.

LC_ISO8859_15

#define LC_ISO8859_15   0x8e /* ISO8859 Latin 15 (not supported yet) */

Definition at line 121 of file pg_wchar.h.

LC_ISO8859_2

#define LC_ISO8859_2   0x82 /* ISO8859 Latin 2 */

Definition at line 105 of file pg_wchar.h.

LC_ISO8859_3

#define LC_ISO8859_3   0x83 /* ISO8859 Latin 3 */

Definition at line 106 of file pg_wchar.h.

LC_ISO8859_4

#define LC_ISO8859_4   0x84 /* ISO8859 Latin 4 */

Definition at line 107 of file pg_wchar.h.

LC_ISO8859_5

#define LC_ISO8859_5   0x8c /* ISO8859 Cyrillic */

Definition at line 119 of file pg_wchar.h.

LC_ISO8859_6

#define LC_ISO8859_6   0x87 /* Arabic (not supported yet) */

Definition at line 110 of file pg_wchar.h.

LC_ISO8859_7

#define LC_ISO8859_7   0x86 /* Greek (not supported yet) */

Definition at line 109 of file pg_wchar.h.

LC_ISO8859_8

#define LC_ISO8859_8   0x88 /* Hebrew (not supported yet) */

Definition at line 111 of file pg_wchar.h.

LC_ISO8859_9

#define LC_ISO8859_9   0x8d /* ISO8859 Latin 5 (not supported yet) */

Definition at line 120 of file pg_wchar.h.

LC_JISX0201K

#define LC_JISX0201K   0x89 /* Japanese 1 byte kana */

Definition at line 112 of file pg_wchar.h.

LC_JISX0201R

#define LC_JISX0201R   0x8a /* Japanese 1 byte Roman */

Definition at line 113 of file pg_wchar.h.

LC_JISX0208

#define LC_JISX0208   0x92 /* Japanese Kanji (JIS X 0208) */

Definition at line 133 of file pg_wchar.h.

LC_JISX0208_1978

#define LC_JISX0208_1978   0x90 /* Japanese Kanji, old JIS (not supported) */

Definition at line 131 of file pg_wchar.h.

LC_JISX0212

#define LC_JISX0212   0x94 /* Japanese Kanji (JIS X 0212) */

Definition at line 135 of file pg_wchar.h.

LC_JISX0213_1

#define LC_JISX0213_1

Value:

                                     0x97   /* Japanese Kanji (JIS X 0213 Plane 1)
                                     * (not supported) */

Definition at line 138 of file pg_wchar.h.

LC_KOI8_R

#define LC_KOI8_R   0x8b /* Cyrillic KOI8-R */

Definition at line 118 of file pg_wchar.h.

LC_KS5601

#define LC_KS5601   0x93 /* Korean */

Definition at line 134 of file pg_wchar.h.

LC_LAO

#define LC_LAO

Value:

                                     0xa7   /* Lao characters (ISO10646 0E80..0EDF)
                                     * (not supported) */

Definition at line 179 of file pg_wchar.h.

LC_SISHENG

#define LC_SISHENG

Value:

                                     0xa0   /* Chinese SiSheng characters for
                                     * PinYin/ZhuYin (not supported) */

Definition at line 172 of file pg_wchar.h.

LC_TIBETAN

#define LC_TIBETAN   0xfc /* Tibetan (not supported) */

Definition at line 197 of file pg_wchar.h.

LC_TIBETAN_1_COLUMN

#define LC_TIBETAN_1_COLUMN

Value:

                                     0xf1   /* Tibetan 1-column width glyphs (not
                                     * supported) */

Definition at line 186 of file pg_wchar.h.

LC_TIS620

#define LC_TIS620   0x85 /* Thai (not supported yet) */

Definition at line 108 of file pg_wchar.h.

LC_UNICODE_SUBSET

#define LC_UNICODE_SUBSET

Value:

                                     0xf4   /* Unicode characters of the range
                                     * U+0100..U+24FF. (not supported) */

Definition at line 189 of file pg_wchar.h.

LC_UNICODE_SUBSET_2

#define LC_UNICODE_SUBSET_2

Value:

                                     0xf2   /* Unicode characters of the range
                                     * U+2500..U+33FF. (not supported) */

Definition at line 187 of file pg_wchar.h.

LC_UNICODE_SUBSET_3

#define LC_UNICODE_SUBSET_3

Value:

                                     0xf3   /* Unicode characters of the range
                                     * U+E000..U+FFFF. (not supported) */

Definition at line 188 of file pg_wchar.h.

LC_VISCII_LOWER

#define LC_VISCII_LOWER

Value:

                                     0xa2   /* Vietnamese VISCII1.1 lower-case (not
                                     * supported) */

Definition at line 174 of file pg_wchar.h.

LC_VISCII_UPPER

#define LC_VISCII_UPPER

Value:

                                     0xa3   /* Vietnamese VISCII1.1 upper-case (not
                                     * supported) */

Definition at line 175 of file pg_wchar.h.

LCPRV1_A

#define LCPRV1_A   0x9a

Definition at line 149 of file pg_wchar.h.

LCPRV1_B

#define LCPRV1_B   0x9b

Definition at line 150 of file pg_wchar.h.

LCPRV2_A

#define LCPRV2_A   0x9c

Definition at line 161 of file pg_wchar.h.

LCPRV2_B

#define LCPRV2_B   0x9d

Definition at line 162 of file pg_wchar.h.

MAX_CONVERSION_GROWTH

#define MAX_CONVERSION_GROWTH   4

Definition at line 302 of file pg_wchar.h.

MAX_CONVERSION_INPUT_LENGTH

#define MAX_CONVERSION_INPUT_LENGTH   16

Definition at line 320 of file pg_wchar.h.

MAX_MULTIBYTE_CHAR_LEN

#define MAX_MULTIBYTE_CHAR_LEN   4

Definition at line 32 of file pg_wchar.h.

MAX_UNICODE_EQUIVALENT_STRING

#define MAX_UNICODE_EQUIVALENT_STRING   16

Definition at line 329 of file pg_wchar.h.

PG_ENCODING_BE_LAST

#define PG_ENCODING_BE_LAST   PG_KOI8U

Definition at line 275 of file pg_wchar.h.

PG_ENCODING_IS_CLIENT_ONLY

#define PG_ENCODING_IS_CLIENT_ONLY

(

_enc

)

((_enc) > PG_ENCODING_BE_LAST && (_enc) < _PG_LAST_ENCODING_)

Definition at line 284 of file pg_wchar.h.

PG_VALID_BE_ENCODING

#define PG_VALID_BE_ENCODING

(

_enc

)

((_enc) >= 0 && (_enc) <= PG_ENCODING_BE_LAST)

Definition at line 281 of file pg_wchar.h.

PG_VALID_ENCODING

#define PG_VALID_ENCODING

(

_enc

)

((_enc) >= 0 && (_enc) < _PG_LAST_ENCODING_)

Definition at line 287 of file pg_wchar.h.

PG_VALID_FE_ENCODING

#define PG_VALID_FE_ENCODING

(

_enc

)

PG_VALID_ENCODING(_enc)

Definition at line 291 of file pg_wchar.h.

SS2

#define SS2   0x8e /* single shift 2 (JIS0201) */

Definition at line 37 of file pg_wchar.h.

SS3

#define SS3   0x8f /* single shift 3 (JIS0212) */

Definition at line 38 of file pg_wchar.h.

Typedef Documentation

mb2wchar_with_len_converter

typedef int(* mb2wchar_with_len_converter) (const unsigned char *from, pg_wchar *to, int len)

Definition at line 364 of file pg_wchar.h.

mbchar_verifier

typedef int(* mbchar_verifier) (const unsigned char *mbstr, int len)

Definition at line 378 of file pg_wchar.h.

mbcharacter_incrementer

typedef bool(* mbcharacter_incrementer) (unsigned char *mbstr, int len)

Definition at line 376 of file pg_wchar.h.

mbdisplaylen_converter

typedef int(* mbdisplaylen_converter) (const unsigned char *mbstr)

Definition at line 374 of file pg_wchar.h.

mblen_converter

typedef int(* mblen_converter) (const unsigned char *mbstr)

Definition at line 372 of file pg_wchar.h.

mbstr_verifier

typedef int(* mbstr_verifier) (const unsigned char *mbstr, int len)

Definition at line 380 of file pg_wchar.h.

pg_enc

typedef enum pg_enc pg_enc

pg_enc2gettext

typedef struct pg_enc2gettext pg_enc2gettext

pg_enc2name

typedef struct pg_enc2name pg_enc2name

pg_wchar

typedef unsigned int pg_wchar

Definition at line 27 of file pg_wchar.h.

utf_local_conversion_func

typedef uint32(* utf_local_conversion_func) (uint32 code)

Definition at line 505 of file pg_wchar.h.

wchar2mb_with_len_converter

typedef int(* wchar2mb_with_len_converter) (const pg_wchar *from, unsigned char *to, int len)

Definition at line 368 of file pg_wchar.h.

Enumeration Type Documentation

pg_enc

enum pg_enc

Enumerator
PG_SQL_ASCII
PG_EUC_JP
PG_EUC_CN
PG_EUC_KR
PG_EUC_TW
PG_EUC_JIS_2004
PG_UTF8
PG_MULE_INTERNAL
PG_LATIN1
PG_LATIN2
PG_LATIN3
PG_LATIN4
PG_LATIN5
PG_LATIN6
PG_LATIN7
PG_LATIN8
PG_LATIN9
PG_LATIN10
PG_WIN1256
PG_WIN1258
PG_WIN866
PG_WIN874
PG_KOI8R
PG_WIN1251
PG_WIN1252
PG_ISO_8859_5
PG_ISO_8859_6
PG_ISO_8859_7
PG_ISO_8859_8
PG_WIN1250
PG_WIN1253
PG_WIN1254
PG_WIN1255
PG_WIN1257
PG_KOI8U
PG_SJIS
PG_BIG5
PG_GBK
PG_UHC
PG_GB18030
PG_JOHAB
PG_SHIFT_JIS_2004
_PG_LAST_ENCODING_

Definition at line 224 of file pg_wchar.h.

          : the order of this enum must be same as order of entries
 *          in the pg_enc2name_tbl[] array (in src/common/encnames.c), and
 *          in the pg_wchar_table[] array (in src/common/wchar.c)!
 *
 *          If you add some encoding don't forget to check
 *          PG_ENCODING_BE_LAST macro.
 *
 * PG_SQL_ASCII is default encoding and must be = 0.
 *
 * XXX  We must avoid renumbering any backend encoding until libpq's major
 * version number is increased beyond 5; it turns out that the backend
 * encoding IDs are effectively part of libpq's ABI as far as 8.2 initdb and
 * psql are concerned.
 */
typedef enum pg_enc
{
    PG_SQL_ASCII = 0,           /* SQL/ASCII */
    PG_EUC_JP,                  /* EUC for Japanese */
    PG_EUC_CN,                  /* EUC for Chinese */
    PG_EUC_KR,                  /* EUC for Korean */
    PG_EUC_TW,                  /* EUC for Taiwan */
    PG_EUC_JIS_2004,            /* EUC-JIS-2004 */
    PG_UTF8,                    /* Unicode UTF8 */
    PG_MULE_INTERNAL,           /* Mule internal code */
    PG_LATIN1,                  /* ISO-8859-1 Latin 1 */
    PG_LATIN2,                  /* ISO-8859-2 Latin 2 */
    PG_LATIN3,                  /* ISO-8859-3 Latin 3 */
    PG_LATIN4,                  /* ISO-8859-4 Latin 4 */
    PG_LATIN5,                  /* ISO-8859-9 Latin 5 */
    PG_LATIN6,                  /* ISO-8859-10 Latin6 */
    PG_LATIN7,                  /* ISO-8859-13 Latin7 */
    PG_LATIN8,                  /* ISO-8859-14 Latin8 */
    PG_LATIN9,                  /* ISO-8859-15 Latin9 */
    PG_LATIN10,                 /* ISO-8859-16 Latin10 */
    PG_WIN1256,                 /* windows-1256 */
    PG_WIN1258,                 /* Windows-1258 */
    PG_WIN866,                  /* (MS-DOS CP866) */
    PG_WIN874,                  /* windows-874 */
    PG_KOI8R,                   /* KOI8-R */
    PG_WIN1251,                 /* windows-1251 */
    PG_WIN1252,                 /* windows-1252 */
    PG_ISO_8859_5,              /* ISO-8859-5 */
    PG_ISO_8859_6,              /* ISO-8859-6 */
    PG_ISO_8859_7,              /* ISO-8859-7 */
    PG_ISO_8859_8,              /* ISO-8859-8 */
    PG_WIN1250,                 /* windows-1250 */
    PG_WIN1253,                 /* windows-1253 */
    PG_WIN1254,                 /* windows-1254 */

Function Documentation

BIG5toCNS()

unsigned short BIG5toCNS	(	unsigned short	big5,
		unsigned char *	lc
	)

Definition at line 292 of file big5.c.

{
    unsigned short cns = 0;
    int         i;
 
    if (big5 < 0xc940U)
    {
        /* level 1 */
 
        for (i = 0; i < sizeof(b1c4) / (sizeof(unsigned short) * 2); i++)
        {
            if (b1c4[i][0] == big5)
            {
                *lc = LC_CNS11643_4;
                return (b1c4[i][1] | 0x8080U);
            }
        }
 
        if (0 < (cns = BinarySearchRange(big5Level1ToCnsPlane1, 23, big5)))
            *lc = LC_CNS11643_1;
    }
    else if (big5 == 0xc94aU)
    {
        /* level 2 */
        *lc = LC_CNS11643_1;
        cns = 0x4442;
    }
    else
    {
        /* level 2 */
        for (i = 0; i < sizeof(b2c3) / (sizeof(unsigned short) * 2); i++)
        {
            if (b2c3[i][0] == big5)
            {
                *lc = LC_CNS11643_3;
                return (b2c3[i][1] | 0x8080U);
            }
        }
 
        if (0 < (cns = BinarySearchRange(big5Level2ToCnsPlane2, 46, big5)))
            *lc = LC_CNS11643_2;
    }
 
    if (0 == cns)
    {                           /* no mapping Big5 to CNS 11643-1992 */
        *lc = 0;
        return (unsigned short) '?';
    }
 
    return cns | 0x8080;
}

References b1c4, b2c3, big5Level1ToCnsPlane1, big5Level2ToCnsPlane2, BinarySearchRange(), i, LC_CNS11643_1, LC_CNS11643_2, LC_CNS11643_3, and LC_CNS11643_4.

Referenced by big52euc_tw(), and big52mic().

check_encoding_conversion_args()

void check_encoding_conversion_args	(	int	src_encoding,
		int	dest_encoding,
		int	len,
		int	expected_src_encoding,
		int	expected_dest_encoding
	)

Definition at line 1676 of file mbutils.c.

{
    if (!PG_VALID_ENCODING(src_encoding))
        elog(ERROR, "invalid source encoding ID: %d", src_encoding);
    if (src_encoding != expected_src_encoding && expected_src_encoding >= 0)
        elog(ERROR, "expected source encoding \"%s\", but got \"%s\"",
             pg_enc2name_tbl[expected_src_encoding].name,
             pg_enc2name_tbl[src_encoding].name);
    if (!PG_VALID_ENCODING(dest_encoding))
        elog(ERROR, "invalid destination encoding ID: %d", dest_encoding);
    if (dest_encoding != expected_dest_encoding && expected_dest_encoding >= 0)
        elog(ERROR, "expected destination encoding \"%s\", but got \"%s\"",
             pg_enc2name_tbl[expected_dest_encoding].name,
             pg_enc2name_tbl[dest_encoding].name);
    if (len < 0)
        elog(ERROR, "encoding conversion length must not be negative");
}

References elog(), ERROR, len, name, pg_enc2name_tbl, and PG_VALID_ENCODING.

CNStoBIG5()

unsigned short CNStoBIG5	(	unsigned short	cns,
		unsigned char	lc
	)

Definition at line 345 of file big5.c.

{
    int         i;
    unsigned int big5 = 0;
 
    cns &= 0x7f7f;
 
    switch (lc)
    {
        case LC_CNS11643_1:
            big5 = BinarySearchRange(cnsPlane1ToBig5Level1, 24, cns);
            break;
        case LC_CNS11643_2:
            big5 = BinarySearchRange(cnsPlane2ToBig5Level2, 47, cns);
            break;
        case LC_CNS11643_3:
            for (i = 0; i < sizeof(b2c3) / (sizeof(unsigned short) * 2); i++)
            {
                if (b2c3[i][1] == cns)
                    return b2c3[i][0];
            }
            break;
        case LC_CNS11643_4:
            for (i = 0; i < sizeof(b1c4) / (sizeof(unsigned short) * 2); i++)
            {
                if (b1c4[i][1] == cns)
                    return b1c4[i][0];
            }
        default:
            break;
    }
    return big5;
}

References b1c4, b2c3, BinarySearchRange(), cnsPlane1ToBig5Level1, cnsPlane2ToBig5Level2, i, LC_CNS11643_1, LC_CNS11643_2, LC_CNS11643_3, and LC_CNS11643_4.

Referenced by euc_tw2big5(), and mic2big5().

get_encoding_name_for_icu()

const char* get_encoding_name_for_icu

(

int

encoding

)

Definition at line 473 of file encnames.c.

{
    if (!PG_VALID_BE_ENCODING(encoding))
        return NULL;
    return pg_enc2icu_tbl[encoding];
}

References encoding, pg_enc2icu_tbl, and PG_VALID_BE_ENCODING.

GetDatabaseEncoding()

int GetDatabaseEncoding

(

void

)

Definition at line 1268 of file mbutils.c.

{
    return DatabaseEncoding->encoding;
}

References DatabaseEncoding, and pg_enc2name::encoding.

Referenced by ascii(), BeginCopyFrom(), BeginCopyTo(), char2wchar(), chr(), CollationCreate(), CollationGetCollid(), compareStrings(), convert_from_utf8(), convert_to_utf8(), CopyConversionError(), CopyConvertBuf(), cstr2sv(), dblink_connect(), dblink_get_conn(), DefineCollation(), Generic_Text_IC_like(), GenericMatchText(), get_collation_oid(), get_json_object_as_hash(), InitializeClientEncoding(), IsThereCollationInNamespace(), json_recv(), jsonb_from_cstring(), locate_stem_module(), LogicalOutputWrite(), makeJsonLexContext(), p_isspecial(), ParallelWorkerMain(), pg_database_encoding_character_incrementer(), pg_database_encoding_max_length(), pg_generic_charinc(), pg_perm_setlocale(), pg_set_regex_collation(), pg_strcoll_libc(), pg_strncoll_libc(), pg_unicode_to_server(), pg_unicode_to_server_noerror(), pg_verifymbstr(), pgss_store(), PLyUnicode_Bytes(), populate_array_json(), PrepareClientEncoding(), read_extension_script_file(), SetClientEncoding(), sv2cstr(), text_position_setup(), to_ascii_default(), type_maximum_size(), unicode_norm_form_from_string(), wchar2char(), xml_in(), xml_is_document(), xmlparse(), and xmltotext_with_options().

GetDatabaseEncodingName()

const char* GetDatabaseEncodingName

(

void

)

Definition at line 1274 of file mbutils.c.

{
    return DatabaseEncoding->name;
}

References DatabaseEncoding, and pg_enc2name::name.

Referenced by check_client_encoding(), CheckMyDatabase(), connect_pg_server(), dblink_connect(), dblink_get_conn(), get_collation_oid(), InitializeClientEncoding(), IsThereCollationInNamespace(), json_errdetail(), libpqrcv_connect(), locate_stem_module(), pg_unicode_to_server(), ProcessConfigFileInternal(), and regcollationin().

GetMessageEncoding()

int GetMessageEncoding

(

void

)

Definition at line 1315 of file mbutils.c.

{
    return MessageEncoding->encoding;
}

References pg_enc2name::encoding, and MessageEncoding.

InitializeClientEncoding()

void InitializeClientEncoding

(

void

)

Definition at line 282 of file mbutils.c.

{
    int         current_server_encoding;
 
    Assert(!backend_startup_complete);
    backend_startup_complete = true;
 
    if (PrepareClientEncoding(pending_client_encoding) < 0 ||
        SetClientEncoding(pending_client_encoding) < 0)
    {
        /*
         * Oops, the requested conversion is not available. We couldn't fail
         * before, but we can now.
         */
        ereport(FATAL,
                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                 errmsg("conversion between %s and %s is not supported",
                        pg_enc2name_tbl[pending_client_encoding].name,
                        GetDatabaseEncodingName())));
    }
 
    /*
     * Also look up the UTF8-to-server conversion function if needed.  Since
     * the server encoding is fixed within any one backend process, we don't
     * have to do this more than once.
     */
    current_server_encoding = GetDatabaseEncoding();
    if (current_server_encoding != PG_UTF8 &&
        current_server_encoding != PG_SQL_ASCII)
    {
        Oid         utf8_to_server_proc;
 
        Assert(IsTransactionState());
        utf8_to_server_proc =
            FindDefaultConversionProc(PG_UTF8,
                                      current_server_encoding);
        /* If there's no such conversion, just leave the pointer as NULL */
        if (OidIsValid(utf8_to_server_proc))
        {
            FmgrInfo   *finfo;
 
            finfo = (FmgrInfo *) MemoryContextAlloc(TopMemoryContext,
                                                    sizeof(FmgrInfo));
            fmgr_info_cxt(utf8_to_server_proc, finfo,
                          TopMemoryContext);
            /* Set Utf8ToServerConvProc only after data is fully valid */
            Utf8ToServerConvProc = finfo;
        }
    }
}

References Assert(), backend_startup_complete, ereport, errcode(), errmsg(), FATAL, FindDefaultConversionProc(), fmgr_info_cxt(), GetDatabaseEncoding(), GetDatabaseEncodingName(), IsTransactionState(), MemoryContextAlloc(), name, OidIsValid, pending_client_encoding, pg_enc2name_tbl, PG_SQL_ASCII, PG_UTF8, PrepareClientEncoding(), SetClientEncoding(), TopMemoryContext, and Utf8ToServerConvProc.

Referenced by InitPostgres().

is_encoding_supported_by_icu()

bool is_encoding_supported_by_icu

(

int

encoding

)

Definition at line 462 of file encnames.c.

{
    if (!PG_VALID_BE_ENCODING(encoding))
        return false;
    return (pg_enc2icu_tbl[encoding] != NULL);
}

References encoding, pg_enc2icu_tbl, and PG_VALID_BE_ENCODING.

Referenced by check_icu_locale_encoding(), createdb(), DefineCollation(), and lookup_collation().

is_utf16_surrogate_first()

static bool is_utf16_surrogate_first ( pg_wchar  c )

inlinestatic

Definition at line 531 of file pg_wchar.h.

{

Referenced by json_lex_string(), str_udeescape(), and unistr().

is_utf16_surrogate_second()

static bool is_utf16_surrogate_second ( pg_wchar  c )

inlinestatic

Definition at line 537 of file pg_wchar.h.

{

Referenced by json_lex_string(), str_udeescape(), and unistr().

is_valid_ascii()

static bool is_valid_ascii ( const unsigned char *  s, int  len  )

inlinestatic

Definition at line 697 of file pg_wchar.h.

{
    const unsigned char *const s_end = s + len;
    Vector8     chunk;
    Vector8     highbit_cum = vector8_broadcast(0);
#ifdef USE_NO_SIMD
    Vector8     zero_cum = vector8_broadcast(0x80);
#endif
 
    Assert(len % sizeof(chunk) == 0);
 
    while (s < s_end)
    {
        vector8_load(&chunk, s);
 
        /* Capture any zero bytes in this chunk. */
#ifdef USE_NO_SIMD
 
        /*
         * First, add 0x7f to each byte. This sets the high bit in each byte,
         * unless it was a zero. If any resulting high bits are zero, the
         * corresponding high bits in the zero accumulator will be cleared.
         *
         * If none of the bytes in the chunk had the high bit set, the max
         * value each byte can have after the addition is 0x7f + 0x7f = 0xfe,
         * and we don't need to worry about carrying over to the next byte. If
         * any input bytes did have the high bit set, it doesn't matter
         * because we check for those separately.
         */
        zero_cum &= (chunk + vector8_broadcast(0x7F));
#else
 
        /*
         * Set all bits in each lane of the highbit accumulator where input
         * bytes are zero.
         */
        highbit_cum = vector8_or(highbit_cum,
                                 vector8_eq(chunk, vector8_broadcast(0)));
#endif
 
        /* Capture all set bits in this chunk. */
        highbit_cum = vector8_or(highbit_cum, chunk);

Referenced by pg_utf8_verifystr().

is_valid_unicode_codepoint()

static bool is_valid_unicode_codepoint ( pg_wchar  c )

inlinestatic

Definition at line 525 of file pg_wchar.h.

{

Referenced by check_unicode_value(), pg_unicode_to_server(), pg_unicode_to_server_noerror(), and unistr().

latin2mic()

int latin2mic	(	const unsigned char *	l,
		unsigned char *	p,
		int	len,
		int	lc,
		int	encoding,
		bool	noError
	)

Definition at line 89 of file conv.c.

{
    const unsigned char *start = l;
    int         c1;
 
    while (len > 0)
    {
        c1 = *l;
        if (c1 == 0)
        {
            if (noError)
                break;
            report_invalid_encoding(encoding, (const char *) l, len);
        }
        if (IS_HIGHBIT_SET(c1))
            *p++ = lc;
        *p++ = c1;
        l++;
        len--;
    }
    *p = '\0';
 
    return l - start;
}

References encoding, IS_HIGHBIT_SET, len, and report_invalid_encoding().

Referenced by koi8r_to_mic(), latin1_to_mic(), latin2_to_mic(), latin3_to_mic(), and latin4_to_mic().

latin2mic_with_table()

int latin2mic_with_table	(	const unsigned char *	l,
		unsigned char *	p,
		int	len,
		int	lc,
		int	encoding,
		const unsigned char *	tab,
		bool	noError
	)

Definition at line 194 of file conv.c.

{
    const unsigned char *start = l;
    unsigned char c1,
                c2;
 
    while (len > 0)
    {
        c1 = *l;
        if (c1 == 0)
        {
            if (noError)
                break;
            report_invalid_encoding(encoding, (const char *) l, len);
        }
        if (!IS_HIGHBIT_SET(c1))
            *p++ = c1;
        else
        {
            c2 = tab[c1 - HIGHBIT];
            if (c2)
            {
                *p++ = lc;
                *p++ = c2;
            }
            else
            {
                if (noError)
                    break;
                report_untranslatable_char(encoding, PG_MULE_INTERNAL,
                                           (const char *) l, len);
            }
        }
        l++;
        len--;
    }
    *p = '\0';
 
    return l - start;
}

References encoding, HIGHBIT, IS_HIGHBIT_SET, len, PG_MULE_INTERNAL, report_invalid_encoding(), and report_untranslatable_char().

Referenced by iso_to_mic(), win1250_to_mic(), win1251_to_mic(), and win866_to_mic().

local2local()

int local2local	(	const unsigned char *	l,
		unsigned char *	p,
		int	len,
		int	src_encoding,
		int	dest_encoding,
		const unsigned char *	tab,
		bool	noError
	)

Definition at line 33 of file conv.c.

{
    const unsigned char *start = l;
    unsigned char c1,
                c2;
 
    while (len > 0)
    {
        c1 = *l;
        if (c1 == 0)
        {
            if (noError)
                break;
            report_invalid_encoding(src_encoding, (const char *) l, len);
        }
        if (!IS_HIGHBIT_SET(c1))
            *p++ = c1;
        else
        {
            c2 = tab[c1 - HIGHBIT];
            if (c2)
                *p++ = c2;
            else
            {
                if (noError)
                    break;
                report_untranslatable_char(src_encoding, dest_encoding,
                                           (const char *) l, len);
            }
        }
        l++;
        len--;
    }
    *p = '\0';
 
    return l - start;
}

References HIGHBIT, IS_HIGHBIT_SET, len, report_invalid_encoding(), and report_untranslatable_char().

Referenced by iso_to_koi8r(), iso_to_win1251(), iso_to_win866(), koi8r_to_iso(), koi8r_to_win1251(), koi8r_to_win866(), latin2_to_win1250(), win1250_to_latin2(), win1251_to_iso(), win1251_to_koi8r(), win1251_to_win866(), win866_to_iso(), win866_to_koi8r(), and win866_to_win1251().

LocalToUtf()

int LocalToUtf	(	const unsigned char *	iso,
		int	len,
		unsigned char *	utf,
		const pg_mb_radix_tree *	map,
		const pg_local_to_utf_combined *	cmap,
		int	cmapsize,
		utf_local_conversion_func	conv_func,
		int	encoding,
		bool	noError
	)

Definition at line 717 of file conv.c.

{
    uint32      iiso;
    int         l;
    const pg_local_to_utf_combined *cp;
    const unsigned char *start = iso;
 
    if (!PG_VALID_ENCODING(encoding))
        ereport(ERROR,
                (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
                 errmsg("invalid encoding number: %d", encoding)));
 
    for (; len > 0; len -= l)
    {
        unsigned char b1 = 0;
        unsigned char b2 = 0;
        unsigned char b3 = 0;
        unsigned char b4 = 0;
 
        /* "break" cases all represent errors */
        if (*iso == '\0')
            break;
 
        if (!IS_HIGHBIT_SET(*iso))
        {
            /* ASCII case is easy, assume it's one-to-one conversion */
            *utf++ = *iso++;
            l = 1;
            continue;
        }
 
        l = pg_encoding_verifymbchar(encoding, (const char *) iso, len);
        if (l < 0)
            break;
 
        /* collect coded char of length l */
        if (l == 1)
            b4 = *iso++;
        else if (l == 2)
        {
            b3 = *iso++;
            b4 = *iso++;
        }
        else if (l == 3)
        {
            b2 = *iso++;
            b3 = *iso++;
            b4 = *iso++;
        }
        else if (l == 4)
        {
            b1 = *iso++;
            b2 = *iso++;
            b3 = *iso++;
            b4 = *iso++;
        }
        else
        {
            elog(ERROR, "unsupported character length %d", l);
            iiso = 0;           /* keep compiler quiet */
        }
        iiso = (b1 << 24 | b2 << 16 | b3 << 8 | b4);
 
        if (map)
        {
            uint32      converted = pg_mb_radix_conv(map, l, b1, b2, b3, b4);
 
            if (converted)
            {
                utf = store_coded_char(utf, converted);
                continue;
            }
 
            /* If there's a combined character map, try that */
            if (cmap)
            {
                cp = bsearch(&iiso, cmap, cmapsize,
                             sizeof(pg_local_to_utf_combined), compare4);
 
                if (cp)
                {
                    utf = store_coded_char(utf, cp->utf1);
                    utf = store_coded_char(utf, cp->utf2);
                    continue;
                }
            }
        }
 
        /* if there's a conversion function, try that */
        if (conv_func)
        {
            uint32      converted = (*conv_func) (iiso);
 
            if (converted)
            {
                utf = store_coded_char(utf, converted);
                continue;
            }
        }
 
        /* failed to translate this character */
        iso -= l;
        if (noError)
            break;
        report_untranslatable_char(encoding, PG_UTF8,
                                   (const char *) iso, len);
    }
 
    /* if we broke out of loop early, must be invalid input */
    if (len > 0 && !noError)
        report_invalid_encoding(encoding, (const char *) iso, len);
 
    *utf = '\0';
 
    return iso - start;
}

References compare4(), elog(), encoding, ereport, errcode(), errmsg(), ERROR, IS_HIGHBIT_SET, len, pg_encoding_verifymbchar(), pg_mb_radix_conv(), PG_UTF8, PG_VALID_ENCODING, report_invalid_encoding(), report_untranslatable_char(), store_coded_char(), pg_local_to_utf_combined::utf1, and pg_local_to_utf_combined::utf2.

Referenced by big5_to_utf8(), euc_cn_to_utf8(), euc_jis_2004_to_utf8(), euc_jp_to_utf8(), euc_kr_to_utf8(), euc_tw_to_utf8(), gb18030_to_utf8(), gbk_to_utf8(), iso8859_to_utf8(), johab_to_utf8(), koi8r_to_utf8(), koi8u_to_utf8(), shift_jis_2004_to_utf8(), sjis_to_utf8(), uhc_to_utf8(), and win_to_utf8().

mic2latin()

int mic2latin	(	const unsigned char *	mic,
		unsigned char *	p,
		int	len,
		int	lc,
		int	encoding,
		bool	noError
	)

Definition at line 127 of file conv.c.

{
    const unsigned char *start = mic;
    int         c1;
 
    while (len > 0)
    {
        c1 = *mic;
        if (c1 == 0)
        {
            if (noError)
                break;
            report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len);
        }
        if (!IS_HIGHBIT_SET(c1))
        {
            /* easy for ASCII */
            *p++ = c1;
            mic++;
            len--;
        }
        else
        {
            int         l = pg_mule_mblen(mic);
 
            if (len < l)
            {
                if (noError)
                    break;
                report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic,
                                        len);
            }
            if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]))
            {
                if (noError)
                    break;
                report_untranslatable_char(PG_MULE_INTERNAL, encoding,
                                           (const char *) mic, len);
            }
            *p++ = mic[1];
            mic += 2;
            len -= 2;
        }
    }
    *p = '\0';
 
    return mic - start;
}

References encoding, IS_HIGHBIT_SET, len, PG_MULE_INTERNAL, pg_mule_mblen(), report_invalid_encoding(), and report_untranslatable_char().

Referenced by mic_to_koi8r(), mic_to_latin1(), mic_to_latin2(), mic_to_latin3(), and mic_to_latin4().

mic2latin_with_table()

int mic2latin_with_table	(	const unsigned char *	mic,
		unsigned char *	p,
		int	len,
		int	lc,
		int	encoding,
		const unsigned char *	tab,
		bool	noError
	)

Definition at line 257 of file conv.c.

{
    const unsigned char *start = mic;
    unsigned char c1,
                c2;
 
    while (len > 0)
    {
        c1 = *mic;
        if (c1 == 0)
        {
            if (noError)
                break;
            report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len);
        }
        if (!IS_HIGHBIT_SET(c1))
        {
            /* easy for ASCII */
            *p++ = c1;
            mic++;
            len--;
        }
        else
        {
            int         l = pg_mule_mblen(mic);
 
            if (len < l)
            {
                if (noError)
                    break;
                report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic,
                                        len);
            }
            if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) ||
                (c2 = tab[mic[1] - HIGHBIT]) == 0)
            {
                if (noError)
                    break;
                report_untranslatable_char(PG_MULE_INTERNAL, encoding,
                                           (const char *) mic, len);
                break;          /* keep compiler quiet */
            }
            *p++ = c2;
            mic += 2;
            len -= 2;
        }
    }
    *p = '\0';
 
    return mic - start;
}

References encoding, HIGHBIT, IS_HIGHBIT_SET, len, PG_MULE_INTERNAL, pg_mule_mblen(), report_invalid_encoding(), and report_untranslatable_char().

Referenced by mic_to_iso(), mic_to_win1250(), mic_to_win1251(), and mic_to_win866().

pg_any_to_server()

char* pg_any_to_server	(	const char *	s,
		int	len,
		int	encoding
	)

Definition at line 677 of file mbutils.c.

{
    if (len <= 0)
        return unconstify(char *, s);   /* empty string is always valid */
 
    if (encoding == DatabaseEncoding->encoding ||
        encoding == PG_SQL_ASCII)
    {
        /*
         * No conversion is needed, but we must still validate the data.
         */
        (void) pg_verify_mbstr(DatabaseEncoding->encoding, s, len, false);
        return unconstify(char *, s);
    }
 
    if (DatabaseEncoding->encoding == PG_SQL_ASCII)
    {
        /*
         * No conversion is possible, but we must still validate the data,
         * because the client-side code might have done string escaping using
         * the selected client_encoding.  If the client encoding is ASCII-safe
         * then we just do a straight validation under that encoding.  For an
         * ASCII-unsafe encoding we have a problem: we dare not pass such data
         * to the parser but we have no way to convert it.  We compromise by
         * rejecting the data if it contains any non-ASCII characters.
         */
        if (PG_VALID_BE_ENCODING(encoding))
            (void) pg_verify_mbstr(encoding, s, len, false);
        else
        {
            int         i;
 
            for (i = 0; i < len; i++)
            {
                if (s[i] == '\0' || IS_HIGHBIT_SET(s[i]))
                    ereport(ERROR,
                            (errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
                             errmsg("invalid byte value for encoding \"%s\": 0x%02x",
                                    pg_enc2name_tbl[PG_SQL_ASCII].name,
                                    (unsigned char) s[i])));
            }
        }
        return unconstify(char *, s);
    }
 
    /* Fast path if we can use cached conversion function */
    if (encoding == ClientEncoding->encoding)
        return perform_default_encoding_conversion(s, len, true);
 
    /* General case ... will not work outside transactions */
    return (char *) pg_do_encoding_conversion((unsigned char *) unconstify(char *, s),
                                              len,
                                              encoding,
                                              DatabaseEncoding->encoding);
}

References ClientEncoding, DatabaseEncoding, encoding, pg_enc2name::encoding, ereport, errcode(), errmsg(), ERROR, i, IS_HIGHBIT_SET, len, name, perform_default_encoding_conversion(), pg_do_encoding_conversion(), pg_enc2name_tbl, PG_SQL_ASCII, PG_VALID_BE_ENCODING, pg_verify_mbstr(), and unconstify.

Referenced by ASN1_STRING_to_text(), cache_single_string(), db_encoding_convert(), dsnowball_lexize(), pg_client_to_server(), pg_stat_statements_internal(), pgp_armor_headers(), PLyUnicode_Bytes(), read_extension_script_file(), tsearch_readline(), utf_u2e(), X509_NAME_to_cstring(), and xml_recv().

pg_char_and_wchar_strcmp()

int pg_char_and_wchar_strcmp	(	const char *	s1,
		const pg_wchar *	s2
	)

Definition at line 41 of file wstrcmp.c.

{
    while ((pg_wchar) *s1 == *s2++)
        if (*s1++ == 0)
            return 0;
    return *(const unsigned char *) s1 - *(const pg_wchar *) (s2 - 1);
}

References s1, and s2.

pg_char_and_wchar_strncmp()

int pg_char_and_wchar_strncmp	(	const char *	s1,
		const pg_wchar *	s2,
		size_t	n
	)

Definition at line 55 of file wstrncmp.c.

{
    if (n == 0)
        return 0;
    do
    {
        if ((pg_wchar) ((unsigned char) *s1) != *s2++)
            return ((pg_wchar) ((unsigned char) *s1) - *(s2 - 1));
        if (*s1++ == 0)
            break;
    } while (--n != 0);
    return 0;
}

References s1, and s2.

Referenced by element().

pg_char_to_encoding()

int pg_char_to_encoding

(

const char *

name

)

Definition at line 550 of file encnames.c.

{
    unsigned int nel = lengthof(pg_encname_tbl);
    const pg_encname *base = pg_encname_tbl,
               *last = base + nel - 1,
               *position;
    int         result;
    char        buff[NAMEDATALEN],
               *key;
 
    if (name == NULL || *name == '\0')
        return -1;
 
    if (strlen(name) >= NAMEDATALEN)
        return -1;              /* it's certainly not in the table */
 
    key = clean_encoding_name(name, buff);
 
    while (last >= base)
    {
        position = base + ((last - base) >> 1);
        result = key[0] - position->name[0];
 
        if (result == 0)
        {
            result = strcmp(key, position->name);
            if (result == 0)
                return position->encoding;
        }
        if (result < 0)
            last = position - 1;
        else
            base = position + 1;
    }
    return -1;
}

pg_client_to_server()

char* pg_client_to_server	(	const char *	s,
		int	len
	)

Definition at line 661 of file mbutils.c.

{
    return pg_any_to_server(s, len, ClientEncoding->encoding);
}

References ClientEncoding, pg_enc2name::encoding, len, and pg_any_to_server().

Referenced by exec_bind_message(), parse_fcall_arguments(), pq_getmsgstring(), and pq_getmsgtext().

pg_database_encoding_character_incrementer()

mbcharacter_incrementer pg_database_encoding_character_incrementer

(

void

)

Definition at line 1530 of file mbutils.c.

{
    /*
     * Eventually it might be best to add a field to pg_wchar_table[], but for
     * now we just use a switch.
     */
    switch (GetDatabaseEncoding())
    {
        case PG_UTF8:
            return pg_utf8_increment;
 
        case PG_EUC_JP:
            return pg_eucjp_increment;
 
        default:
            return pg_generic_charinc;
    }
}

References GetDatabaseEncoding(), PG_EUC_JP, pg_eucjp_increment(), pg_generic_charinc(), PG_UTF8, and pg_utf8_increment().

Referenced by make_greater_string().

pg_database_encoding_max_length()

int pg_database_encoding_max_length

(

void

)

Definition at line 1553 of file mbutils.c.

{
    return pg_wchar_table[GetDatabaseEncoding()].maxmblen;
}

References GetDatabaseEncoding(), pg_wchar_tbl::maxmblen, and pg_wchar_table.

Referenced by BeginCopyTo(), bpcharlen(), charlen_to_bytelen(), dotrim(), downcase_identifier(), gbt_bpchar_consistent(), gbt_text_compress(), gbt_text_consistent(), generate_trgm_only(), Generic_Text_IC_like(), GenericMatchText(), infix(), init_tsvector_parser(), like_escape(), like_fixed_prefix(), lowerstr_with_len(), lpad(), pg_mbcharcliplen(), pg_mbstrlen(), pg_mbstrlen_with_len(), protect_out_of_mem(), regexp_fixed_prefix(), rpad(), setup_regexp_matches(), setup_test_matches(), show_trgm(), str_initcap(), str_tolower(), str_toupper(), text_length(), text_position_setup(), text_reverse(), text_substring(), TParserInit(), translate(), and tsvectorout().

pg_do_encoding_conversion()

unsigned char* pg_do_encoding_conversion	(	unsigned char *	src,
		int	len,
		int	src_encoding,
		int	dest_encoding
	)

Definition at line 357 of file mbutils.c.

{
    unsigned char *result;
    Oid         proc;
 
    if (len <= 0)
        return src;             /* empty string is always valid */
 
    if (src_encoding == dest_encoding)
        return src;             /* no conversion required, assume valid */
 
    if (dest_encoding == PG_SQL_ASCII)
        return src;             /* any string is valid in SQL_ASCII */
 
    if (src_encoding == PG_SQL_ASCII)
    {
        /* No conversion is possible, but we must validate the result */
        (void) pg_verify_mbstr(dest_encoding, (const char *) src, len, false);
        return src;
    }
 
    if (!IsTransactionState())  /* shouldn't happen */
        elog(ERROR, "cannot perform encoding conversion outside a transaction");
 
    proc = FindDefaultConversionProc(src_encoding, dest_encoding);
    if (!OidIsValid(proc))
        ereport(ERROR,
                (errcode(ERRCODE_UNDEFINED_FUNCTION),
                 errmsg("default conversion function for encoding \"%s\" to \"%s\" does not exist",
                        pg_encoding_to_char(src_encoding),
                        pg_encoding_to_char(dest_encoding))));
 
    /*
     * Allocate space for conversion result, being wary of integer overflow.
     *
     * len * MAX_CONVERSION_GROWTH is typically a vast overestimate of the
     * required space, so it might exceed MaxAllocSize even though the result
     * would actually fit.  We do not want to hand back a result string that
     * exceeds MaxAllocSize, because callers might not cope gracefully --- but
     * if we just allocate more than that, and don't use it, that's fine.
     */
    if ((Size) len >= (MaxAllocHugeSize / (Size) MAX_CONVERSION_GROWTH))
        ereport(ERROR,
                (errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
                 errmsg("out of memory"),
                 errdetail("String of %d bytes is too long for encoding conversion.",
                           len)));
 
    result = (unsigned char *)
        MemoryContextAllocHuge(CurrentMemoryContext,
                               (Size) len * MAX_CONVERSION_GROWTH + 1);
 
    (void) OidFunctionCall6(proc,
                            Int32GetDatum(src_encoding),
                            Int32GetDatum(dest_encoding),
                            CStringGetDatum((char *) src),
                            CStringGetDatum((char *) result),
                            Int32GetDatum(len),
                            BoolGetDatum(false));
 
    /*
     * If the result is large, it's worth repalloc'ing to release any extra
     * space we asked for.  The cutoff here is somewhat arbitrary, but we
     * *must* check when len * MAX_CONVERSION_GROWTH exceeds MaxAllocSize.
     */
    if (len > 1000000)
    {
        Size        resultlen = strlen((char *) result);
 
        if (resultlen >= MaxAllocSize)
            ereport(ERROR,
                    (errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
                     errmsg("out of memory"),
                     errdetail("String of %d bytes is too long for encoding conversion.",
                               len)));
 
        result = (unsigned char *) repalloc(result, resultlen + 1);
    }
 
    return result;
}

References BoolGetDatum(), CStringGetDatum(), CurrentMemoryContext, elog(), ereport, errcode(), errdetail(), errmsg(), ERROR, FindDefaultConversionProc(), Int32GetDatum(), IsTransactionState(), len, MAX_CONVERSION_GROWTH, MaxAllocHugeSize, MaxAllocSize, MemoryContextAllocHuge(), OidFunctionCall6, OidIsValid, pg_encoding_to_char(), PG_SQL_ASCII, pg_verify_mbstr(), and repalloc().

Referenced by convert_charset(), pg_any_to_server(), pg_convert(), and pg_server_to_any().

pg_do_encoding_conversion_buf()

int pg_do_encoding_conversion_buf	(	Oid	proc,
		int	src_encoding,
		int	dest_encoding,
		unsigned char *	src,
		int	srclen,
		unsigned char *	dest,
		int	destlen,
		bool	noError
	)

Definition at line 470 of file mbutils.c.

{
    Datum       result;
 
    /*
     * If the destination buffer is not large enough to hold the result in the
     * worst case, limit the input size passed to the conversion function.
     */
    if ((Size) srclen >= ((destlen - 1) / (Size) MAX_CONVERSION_GROWTH))
        srclen = ((destlen - 1) / (Size) MAX_CONVERSION_GROWTH);
 
    result = OidFunctionCall6(proc,
                              Int32GetDatum(src_encoding),
                              Int32GetDatum(dest_encoding),
                              CStringGetDatum((char *) src),
                              CStringGetDatum((char *) dest),
                              Int32GetDatum(srclen),
                              BoolGetDatum(noError));
    return DatumGetInt32(result);
}

References BoolGetDatum(), CStringGetDatum(), DatumGetInt32(), generate_unaccent_rules::dest, Int32GetDatum(), MAX_CONVERSION_GROWTH, and OidFunctionCall6.

Referenced by CopyConversionError(), CopyConvertBuf(), and test_enc_conversion().

pg_dsplen()

int pg_dsplen

(

const char *

mbstr

)

Definition at line 1031 of file mbutils.c.

{
    return pg_wchar_table[DatabaseEncoding->encoding].dsplen((const unsigned char *) mbstr);
}

References DatabaseEncoding, pg_wchar_tbl::dsplen, pg_enc2name::encoding, and pg_wchar_table.

Referenced by p_isspecial().

pg_encoding_dsplen()

int pg_encoding_dsplen	(	int	encoding,
		const char *	mbstr
	)

Definition at line 2151 of file wchar.c.

{
    return (PG_VALID_ENCODING(encoding) ?
            pg_wchar_table[encoding].dsplen((const unsigned char *) mbstr) :
            pg_wchar_table[PG_SQL_ASCII].dsplen((const unsigned char *) mbstr));
}

References encoding, PG_SQL_ASCII, PG_VALID_ENCODING, and pg_wchar_table.

Referenced by PQdsplen(), and reportErrorPosition().

pg_encoding_max_length()

int pg_encoding_max_length

(

int

encoding

)

Definition at line 2188 of file wchar.c.

{
    Assert(PG_VALID_ENCODING(encoding));
 
    return pg_wchar_table[encoding].maxmblen;
}

References Assert(), encoding, pg_wchar_tbl::maxmblen, PG_VALID_ENCODING, and pg_wchar_table.

Referenced by ascii(), chr(), CopyConvertBuf(), pg_encoding_mbcliplen(), pg_verify_mbstr_len(), reportErrorPosition(), and type_maximum_size().

pg_encoding_mb2wchar_with_len()

int pg_encoding_mb2wchar_with_len	(	int	encoding,
		const char *	from,
		pg_wchar *	to,
		int	len
	)

Definition at line 994 of file mbutils.c.

{
    return pg_wchar_table[encoding].mb2wchar_with_len((const unsigned char *) from, to, len);
}

References encoding, len, pg_wchar_tbl::mb2wchar_with_len, and pg_wchar_table.

pg_encoding_mbcliplen()

int pg_encoding_mbcliplen	(	int	encoding,
		const char *	mbstr,
		int	len,
		int	limit
	)

Definition at line 1094 of file mbutils.c.

{
    mblen_converter mblen_fn;
    int         clen = 0;
    int         l;
 
    /* optimization for single byte encoding */
    if (pg_encoding_max_length(encoding) == 1)
        return cliplen(mbstr, len, limit);
 
    mblen_fn = pg_wchar_table[encoding].mblen;
 
    while (len > 0 && *mbstr)
    {
        l = (*mblen_fn) ((const unsigned char *) mbstr);
        if ((clen + l) > limit)
            break;
        clen += l;
        if (clen == limit)
            break;
        len -= l;
        mbstr += l;
    }
    return clen;
}

References cliplen(), encoding, len, pg_wchar_tbl::mblen, pg_encoding_max_length(), and pg_wchar_table.

Referenced by pg_mbcliplen().

pg_encoding_mblen()

int pg_encoding_mblen	(	int	encoding,
		const char *	mbstr
	)

Definition at line 2130 of file wchar.c.

{
    return (PG_VALID_ENCODING(encoding) ?
            pg_wchar_table[encoding].mblen((const unsigned char *) mbstr) :
            pg_wchar_table[PG_SQL_ASCII].mblen((const unsigned char *) mbstr));
}

References encoding, PG_SQL_ASCII, PG_VALID_ENCODING, and pg_wchar_table.

Referenced by CopyAttributeOutCSV(), CopyAttributeOutText(), pg_encoding_mblen_bounded(), PQescapeInternal(), PQescapeStringInternal(), PQmblen(), PQmblenBounded(), report_invalid_encoding(), and report_untranslatable_char().

pg_encoding_mblen_bounded()

int pg_encoding_mblen_bounded	(	int	encoding,
		const char *	mbstr
	)

Definition at line 2142 of file wchar.c.

{
    return strnlen(mbstr, pg_encoding_mblen(encoding, mbstr));
}

References encoding, pg_encoding_mblen(), and strnlen().

pg_encoding_to_char()

const char* pg_encoding_to_char

(

int

encoding

)

Definition at line 588 of file encnames.c.

{
    if (PG_VALID_ENCODING(encoding))
    {
        const pg_enc2name *p = &pg_enc2name_tbl[encoding];
 
        Assert(encoding == p->encoding);
        return p->name;
    }
    return "";
}

pg_encoding_verifymbchar()

int pg_encoding_verifymbchar	(	int	encoding,
		const char *	mbstr,
		int	len
	)

Definition at line 2164 of file wchar.c.

{
    return (PG_VALID_ENCODING(encoding) ?
            pg_wchar_table[encoding].mbverifychar((const unsigned char *) mbstr, len) :
            pg_wchar_table[PG_SQL_ASCII].mbverifychar((const unsigned char *) mbstr, len));
}

References encoding, len, PG_SQL_ASCII, PG_VALID_ENCODING, and pg_wchar_table.

Referenced by big52euc_tw(), big52mic(), euc_jis_20042shift_jis_2004(), euc_jp2mic(), euc_jp2sjis(), euc_kr2mic(), euc_tw2big5(), euc_tw2mic(), LocalToUtf(), mic2big5(), mic2euc_jp(), mic2euc_kr(), mic2euc_tw(), mic2sjis(), shift_jis_20042euc_jis_2004(), and sjis2euc_jp().

pg_encoding_verifymbstr()

int pg_encoding_verifymbstr	(	int	encoding,
		const char *	mbstr,
		int	len
	)

Definition at line 2177 of file wchar.c.

{
    return (PG_VALID_ENCODING(encoding) ?
            pg_wchar_table[encoding].mbverifystr((const unsigned char *) mbstr, len) :
            pg_wchar_table[PG_SQL_ASCII].mbverifystr((const unsigned char *) mbstr, len));
}

References encoding, len, PG_SQL_ASCII, PG_VALID_ENCODING, and pg_wchar_table.

Referenced by CopyConvertBuf(), and test_enc_conversion().

pg_encoding_wchar2mb_with_len()

int pg_encoding_wchar2mb_with_len	(	int	encoding,
		const pg_wchar *	from,
		char *	to,
		int	len
	)

Definition at line 1016 of file mbutils.c.

{
    return pg_wchar_table[encoding].wchar2mb_with_len(from, (unsigned char *) to, len);
}

References encoding, len, pg_wchar_table, and pg_wchar_tbl::wchar2mb_with_len.

pg_get_client_encoding()

int pg_get_client_encoding

(

void

)

Definition at line 337 of file mbutils.c.

{
    return ClientEncoding->encoding;
}

References ClientEncoding, and pg_enc2name::encoding.

Referenced by BeginCopyFrom(), BeginCopyTo(), and xml_send().

pg_get_client_encoding_name()

const char* pg_get_client_encoding_name

(

void

)

Definition at line 346 of file mbutils.c.

{
    return ClientEncoding->name;
}

References ClientEncoding, and pg_enc2name::name.

pg_mb2wchar()

int pg_mb2wchar	(	const char *	from,
		pg_wchar *	to
	)

Definition at line 980 of file mbutils.c.

{
    return pg_wchar_table[DatabaseEncoding->encoding].mb2wchar_with_len((const unsigned char *) from, to, strlen(from));
}

References DatabaseEncoding, pg_enc2name::encoding, pg_wchar_tbl::mb2wchar_with_len, and pg_wchar_table.

pg_mb2wchar_with_len()

int pg_mb2wchar_with_len	(	const char *	from,
		pg_wchar *	to,
		int	len
	)

Definition at line 987 of file mbutils.c.

{
    return pg_wchar_table[DatabaseEncoding->encoding].mb2wchar_with_len((const unsigned char *) from, to, len);
}

References DatabaseEncoding, pg_enc2name::encoding, len, pg_wchar_tbl::mb2wchar_with_len, and pg_wchar_table.

Referenced by CheckAffix(), NIAddAffix(), RE_compile(), RE_compile_and_cache(), RE_execute(), regcomp_auth_token(), regexec_auth_token(), replace_text_regexp(), setup_regexp_matches(), setup_test_matches(), test_re_compile(), and TParserInit().

pg_mbcharcliplen()

int pg_mbcharcliplen	(	const char *	mbstr,
		int	len,
		int	limit
	)

Definition at line 1126 of file mbutils.c.

{
    int         clen = 0;
    int         nch = 0;
    int         l;
 
    /* optimization for single byte encoding */
    if (pg_database_encoding_max_length() == 1)
        return cliplen(mbstr, len, limit);
 
    while (len > 0 && *mbstr)
    {
        l = pg_mblen(mbstr);
        nch++;
        if (nch > limit)
            break;
        clen += l;
        len -= l;
        mbstr += l;
    }
    return clen;
}

References cliplen(), len, pg_database_encoding_max_length(), and pg_mblen().

Referenced by bpchar(), bpchar_input(), text_left(), text_right(), varchar(), and varchar_input().

pg_mbcliplen()

int pg_mbcliplen	(	const char *	mbstr,
		int	len,
		int	limit
	)

Definition at line 1084 of file mbutils.c.

{
    return pg_encoding_mbcliplen(DatabaseEncoding->encoding, mbstr,
                                 len, limit);
}

References DatabaseEncoding, pg_enc2name::encoding, len, and pg_encoding_mbcliplen().

Referenced by appendStringInfoStringQuoted(), bpchar_name(), ChooseIndexColumnNames(), ExecBuildSlotPartitionKeyDescription(), ExecBuildSlotValueDescription(), limit_printout_length(), make_colname_unique(), make_greater_string(), makeMultirangeTypeName(), makeObjectName(), MemoryContextStatsPrint(), nameconcatoid(), namein(), pgstat_clip_activity(), pgstat_report_appname(), PutMemoryContextsStatsTupleStore(), set_rtable_names(), text_name(), text_to_cstring_buffer(), and truncate_identifier().

pg_mblen()

int pg_mblen

(

const char *

mbstr

)

Definition at line 1024 of file mbutils.c.

{
    return pg_wchar_table[DatabaseEncoding->encoding].mblen((const unsigned char *) mbstr);
}

References DatabaseEncoding, pg_enc2name::encoding, pg_wchar_tbl::mblen, and pg_wchar_table.

Referenced by addCompoundAffixFlagValue(), bit_in(), charlen_to_bytelen(), DCH_from_char(), dotrim(), find_word(), findchar(), findchar2(), findwrd(), gbt_var_node_cp_len(), get_modifiers(), get_nextfield(), get_wildcard_part(), getlexeme(), getNextFlagFromString(), gettoken_query(), gettoken_query_standard(), gettoken_query_websearch(), gettoken_tsvector(), hex_decode_safe(), infix(), initTrie(), lpad(), make_trigrams(), map_sql_identifier_to_xml_name(), map_xml_name_to_sql_identifier(), match_prosrc_to_literal(), mb_strchr(), NIImportAffixes(), NIImportDictionary(), NIImportOOAffixes(), NUM_eat_non_data_chars(), NUM_processor(), parse_affentry(), parse_format(), parse_lquery(), parse_ltree(), parse_or_operator(), parse_re_flags(), parse_test_flags(), pg_base64_decode(), pg_mbcharcliplen(), pg_mbstrlen(), pg_mbstrlen_with_len(), prssyntaxerror(), readstoplist(), report_json_context(), rpad(), RS_compile(), RS_execute(), RS_isRegis(), similar_escape_internal(), split_text(), t_isalnum(), t_isalpha(), t_isdigit(), t_isprint(), t_isspace(), text_format(), text_position_next(), text_reverse(), text_substring(), text_to_bits(), textregexreplace(), thesaurusRead(), TParserGet(), translate(), ts_stat_sql(), tsvectorout(), unaccent_lexize(), varbit_in(), varstr_levenshtein(), and wchareq().

pg_mbstrlen()

int pg_mbstrlen

(

const char *

mbstr

)

Definition at line 1038 of file mbutils.c.

{
    int         len = 0;
 
    /* optimization for single byte encoding */
    if (pg_database_encoding_max_length() == 1)
        return strlen(mbstr);
 
    while (*mbstr)
    {
        mbstr += pg_mblen(mbstr);
        len++;
    }
    return len;
}

References len, pg_database_encoding_max_length(), and pg_mblen().

Referenced by NUM_processor(), and text_format_append_string().

pg_mbstrlen_with_len()

int pg_mbstrlen_with_len	(	const char *	mbstr,
		int	limit
	)

Definition at line 1058 of file mbutils.c.

{
    int         len = 0;
 
    /* optimization for single byte encoding */
    if (pg_database_encoding_max_length() == 1)
        return limit;
 
    while (limit > 0 && *mbstr)
    {
        int         l = pg_mblen(mbstr);
 
        limit -= l;
        mbstr += l;
        len++;
    }
    return len;
}

References len, pg_database_encoding_max_length(), and pg_mblen().

Referenced by bpchar(), bpchar_input(), bpcharlen(), executor_errposition(), lpad(), match_prosrc_to_query(), parser_errposition(), plpgsql_scanner_errposition(), rpad(), similar_escape_internal(), text_left(), text_length(), text_position_get_match_pos(), text_right(), text_substring(), unicode_is_normalized(), unicode_normalize_func(), and varstr_levenshtein().

pg_mule_mblen()

int pg_mule_mblen

(

const unsigned char *

s

)

Definition at line 832 of file wchar.c.

{
    int         len;
 
    if (IS_LC1(*s))
        len = 2;
    else if (IS_LCPRV1(*s))
        len = 3;
    else if (IS_LC2(*s))
        len = 3;
    else if (IS_LCPRV2(*s))
        len = 4;
    else
        len = 1;                /* assume ASCII */
    return len;
}

References IS_LC1, IS_LC2, IS_LCPRV1, IS_LCPRV2, and len.

Referenced by mic2latin(), mic2latin_with_table(), and pg_mule_verifychar().

pg_server_to_any()

char* pg_server_to_any	(	const char *	s,
		int	len,
		int	encoding
	)

Definition at line 750 of file mbutils.c.

{
    if (len <= 0)
        return unconstify(char *, s);   /* empty string is always valid */
 
    if (encoding == DatabaseEncoding->encoding ||
        encoding == PG_SQL_ASCII)
        return unconstify(char *, s);   /* assume data is valid */
 
    if (DatabaseEncoding->encoding == PG_SQL_ASCII)
    {
        /* No conversion is possible, but we must validate the result */
        (void) pg_verify_mbstr(encoding, s, len, false);
        return unconstify(char *, s);
    }
 
    /* Fast path if we can use cached conversion function */
    if (encoding == ClientEncoding->encoding)
        return perform_default_encoding_conversion(s, len, false);
 
    /* General case ... will not work outside transactions */
    return (char *) pg_do_encoding_conversion((unsigned char *) unconstify(char *, s),
                                              len,
                                              DatabaseEncoding->encoding,
                                              encoding);
}

References ClientEncoding, DatabaseEncoding, encoding, pg_enc2name::encoding, len, perform_default_encoding_conversion(), pg_do_encoding_conversion(), PG_SQL_ASCII, pg_verify_mbstr(), and unconstify.

Referenced by compareStrings(), CopyAttributeOutCSV(), CopyAttributeOutText(), daitch_mokotoff(), DoCopyTo(), dsnowball_lexize(), hv_fetch_string(), hv_store_string(), pg_server_to_client(), PLyUnicode_FromStringAndSize(), and utf_e2u().

pg_server_to_client()

char* pg_server_to_client	(	const char *	s,
		int	len
	)

Definition at line 739 of file mbutils.c.

{
    return pg_server_to_any(s, len, ClientEncoding->encoding);
}

References ClientEncoding, pg_enc2name::encoding, len, and pg_server_to_any().

Referenced by pq_puttextmessage(), pq_sendcountedtext(), pq_sendstring(), pq_sendtext(), and pq_writestring().

pg_unicode_to_server()

void pg_unicode_to_server	(	pg_wchar	c,
		unsigned char *	s
	)

Definition at line 865 of file mbutils.c.

{
    unsigned char c_as_utf8[MAX_MULTIBYTE_CHAR_LEN + 1];
    int         c_as_utf8_len;
    int         server_encoding;
 
    /*
     * Complain if invalid Unicode code point.  The choice of errcode here is
     * debatable, but really our caller should have checked this anyway.
     */
    if (!is_valid_unicode_codepoint(c))
        ereport(ERROR,
                (errcode(ERRCODE_SYNTAX_ERROR),
                 errmsg("invalid Unicode code point")));
 
    /* Otherwise, if it's in ASCII range, conversion is trivial */
    if (c <= 0x7F)
    {
        s[0] = (unsigned char) c;
        s[1] = '\0';
        return;
    }
 
    /* If the server encoding is UTF-8, we just need to reformat the code */
    server_encoding = GetDatabaseEncoding();
    if (server_encoding == PG_UTF8)
    {
        unicode_to_utf8(c, s);
        s[pg_utf_mblen(s)] = '\0';
        return;
    }
 
    /* For all other cases, we must have a conversion function available */
    if (Utf8ToServerConvProc == NULL)
        ereport(ERROR,
                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                 errmsg("conversion between %s and %s is not supported",
                        pg_enc2name_tbl[PG_UTF8].name,
                        GetDatabaseEncodingName())));
 
    /* Construct UTF-8 source string */
    unicode_to_utf8(c, c_as_utf8);
    c_as_utf8_len = pg_utf_mblen(c_as_utf8);
    c_as_utf8[c_as_utf8_len] = '\0';
 
    /* Convert, or throw error if we can't */
    FunctionCall6(Utf8ToServerConvProc,
                  Int32GetDatum(PG_UTF8),
                  Int32GetDatum(server_encoding),
                  CStringGetDatum((char *) c_as_utf8),
                  CStringGetDatum((char *) s),
                  Int32GetDatum(c_as_utf8_len),
                  BoolGetDatum(false));
}

References BoolGetDatum(), CStringGetDatum(), ereport, errcode(), errmsg(), ERROR, FunctionCall6, GetDatabaseEncoding(), GetDatabaseEncodingName(), Int32GetDatum(), is_valid_unicode_codepoint(), MAX_MULTIBYTE_CHAR_LEN, name, pg_enc2name_tbl, PG_UTF8, pg_utf_mblen(), unicode_to_utf8(), and Utf8ToServerConvProc.

Referenced by map_xml_name_to_sql_identifier(), str_udeescape(), and unistr().

pg_unicode_to_server_noerror()

bool pg_unicode_to_server_noerror	(	pg_wchar	c,
		unsigned char *	s
	)

Definition at line 927 of file mbutils.c.

{
    unsigned char c_as_utf8[MAX_MULTIBYTE_CHAR_LEN + 1];
    int         c_as_utf8_len;
    int         converted_len;
    int         server_encoding;
 
    /* Fail if invalid Unicode code point */
    if (!is_valid_unicode_codepoint(c))
        return false;
 
    /* Otherwise, if it's in ASCII range, conversion is trivial */
    if (c <= 0x7F)
    {
        s[0] = (unsigned char) c;
        s[1] = '\0';
        return true;
    }
 
    /* If the server encoding is UTF-8, we just need to reformat the code */
    server_encoding = GetDatabaseEncoding();
    if (server_encoding == PG_UTF8)
    {
        unicode_to_utf8(c, s);
        s[pg_utf_mblen(s)] = '\0';
        return true;
    }
 
    /* For all other cases, we must have a conversion function available */
    if (Utf8ToServerConvProc == NULL)
        return false;
 
    /* Construct UTF-8 source string */
    unicode_to_utf8(c, c_as_utf8);
    c_as_utf8_len = pg_utf_mblen(c_as_utf8);
    c_as_utf8[c_as_utf8_len] = '\0';
 
    /* Convert, but without throwing error if we can't */
    converted_len = DatumGetInt32(FunctionCall6(Utf8ToServerConvProc,
                                                Int32GetDatum(PG_UTF8),
                                                Int32GetDatum(server_encoding),
                                                CStringGetDatum((char *) c_as_utf8),
                                                CStringGetDatum((char *) s),
                                                Int32GetDatum(c_as_utf8_len),
                                                BoolGetDatum(true)));
 
    /* Conversion was successful iff it consumed the whole input */
    return (converted_len == c_as_utf8_len);
}

References BoolGetDatum(), CStringGetDatum(), DatumGetInt32(), FunctionCall6, GetDatabaseEncoding(), Int32GetDatum(), is_valid_unicode_codepoint(), MAX_MULTIBYTE_CHAR_LEN, PG_UTF8, pg_utf_mblen(), unicode_to_utf8(), and Utf8ToServerConvProc.

Referenced by json_lex_string().

pg_utf8_islegal()

bool pg_utf8_islegal	(	const unsigned char *	source,
		int	length
	)

Definition at line 2013 of file wchar.c.

{
    unsigned char a;
 
    switch (length)
    {
        default:
            /* reject lengths 5 and 6 for now */
            return false;
        case 4:
            a = source[3];
            if (a < 0x80 || a > 0xBF)
                return false;
            /* FALL THRU */
        case 3:
            a = source[2];
            if (a < 0x80 || a > 0xBF)
                return false;
            /* FALL THRU */
        case 2:
            a = source[1];
            switch (*source)
            {
                case 0xE0:
                    if (a < 0xA0 || a > 0xBF)
                        return false;
                    break;
                case 0xED:
                    if (a < 0x80 || a > 0x9F)
                        return false;
                    break;
                case 0xF0:
                    if (a < 0x90 || a > 0xBF)
                        return false;
                    break;
                case 0xF4:
                    if (a < 0x80 || a > 0x8F)
                        return false;
                    break;
                default:
                    if (a < 0x80 || a > 0xBF)
                        return false;
                    break;
            }
            /* FALL THRU */
        case 1:
            a = *source;
            if (a >= 0x80 && a < 0xC2)
                return false;
            if (a > 0xF4)
                return false;
            break;
    }
    return true;
}

References a, and source.

Referenced by chr(), pg_utf8_string_len(), pg_utf8_verifychar(), utf8_to_iso8859_1(), and UtfToLocal().

pg_utf_mblen()

int pg_utf_mblen

(

const unsigned char *

s

)

Definition at line 549 of file wchar.c.

{
    int         len;
 
    if ((*s & 0x80) == 0)
        len = 1;
    else if ((*s & 0xe0) == 0xc0)
        len = 2;
    else if ((*s & 0xf0) == 0xe0)
        len = 3;
    else if ((*s & 0xf8) == 0xf0)
        len = 4;
#ifdef NOT_USED
    else if ((*s & 0xfc) == 0xf8)
        len = 5;
    else if ((*s & 0xfe) == 0xfc)
        len = 6;
#endif
    else
        len = 1;
    return len;
}

References len.

Referenced by json_lex_string(), pg_saslprep(), pg_unicode_to_server(), pg_unicode_to_server_noerror(), pg_utf8_string_len(), pg_utf8_verifystr(), pg_wchar2utf_with_len(), read_char(), unicode_is_normalized(), unicode_normalize_func(), utf8_to_iso8859_1(), and UtfToLocal().

pg_valid_client_encoding()

int pg_valid_client_encoding

(

const char *

name

)

Definition at line 486 of file encnames.c.

{
    int         enc;
 
    if ((enc = pg_char_to_encoding(name)) < 0)
        return -1;
 
    if (!PG_VALID_FE_ENCODING(enc))
        return -1;
 
    return enc;
}

References enc, name, pg_char_to_encoding(), and PG_VALID_FE_ENCODING.

Referenced by check_client_encoding().

pg_valid_server_encoding()

int pg_valid_server_encoding

(

const char *

name

)

Definition at line 500 of file encnames.c.

{
    int         enc;
 
    if ((enc = pg_char_to_encoding(name)) < 0)
        return -1;
 
    if (!PG_VALID_BE_ENCODING(enc))
        return -1;
 
    return enc;
}

References enc, name, pg_char_to_encoding(), and PG_VALID_BE_ENCODING.

Referenced by createdb(), get_encoding_id(), and parse_extension_control_file().

pg_valid_server_encoding_id()

int pg_valid_server_encoding_id

(

int

encoding

)

Definition at line 514 of file encnames.c.

{
    return PG_VALID_BE_ENCODING(encoding);
}

pg_verify_mbstr()

bool pg_verify_mbstr	(	int	encoding,
		const char *	mbstr,
		int	len,
		bool	noError
	)

Definition at line 1573 of file mbutils.c.

{
    int         oklen;
 
    Assert(PG_VALID_ENCODING(encoding));
 
    oklen = pg_wchar_table[encoding].mbverifystr((const unsigned char *) mbstr, len);
    if (oklen != len)
    {
        if (noError)
            return false;
        report_invalid_encoding(encoding, mbstr + oklen, len - oklen);
    }
    return true;
}

References Assert(), encoding, len, pg_wchar_tbl::mbverifystr, PG_VALID_ENCODING, pg_wchar_table, and report_invalid_encoding().

Referenced by AddFileToBackupManifest(), LogicalOutputWrite(), pg_any_to_server(), pg_convert(), pg_do_encoding_conversion(), pg_server_to_any(), pg_verifymbstr(), and read_extension_script_file().

pg_verify_mbstr_len()

int pg_verify_mbstr_len	(	int	encoding,
		const char *	mbstr,
		int	len,
		bool	noError
	)

Definition at line 1604 of file mbutils.c.

{
    mbchar_verifier mbverifychar;
    int         mb_len;
 
    Assert(PG_VALID_ENCODING(encoding));
 
    /*
     * In single-byte encodings, we need only reject nulls (\0).
     */
    if (pg_encoding_max_length(encoding) <= 1)
    {
        const char *nullpos = memchr(mbstr, 0, len);
 
        if (nullpos == NULL)
            return len;
        if (noError)
            return -1;
        report_invalid_encoding(encoding, nullpos, 1);
    }
 
    /* fetch function pointer just once */
    mbverifychar = pg_wchar_table[encoding].mbverifychar;
 
    mb_len = 0;
 
    while (len > 0)
    {
        int         l;
 
        /* fast path for ASCII-subset characters */
        if (!IS_HIGHBIT_SET(*mbstr))
        {
            if (*mbstr != '\0')
            {
                mb_len++;
                mbstr++;
                len--;
                continue;
            }
            if (noError)
                return -1;
            report_invalid_encoding(encoding, mbstr, len);
        }
 
        l = (*mbverifychar) ((const unsigned char *) mbstr, len);
 
        if (l < 0)
        {
            if (noError)
                return -1;
            report_invalid_encoding(encoding, mbstr, len);
        }
 
        mbstr += l;
        len -= l;
        mb_len++;
    }
    return mb_len;
}

References Assert(), encoding, IS_HIGHBIT_SET, len, pg_wchar_tbl::mbverifychar, pg_encoding_max_length(), PG_VALID_ENCODING, pg_wchar_table, and report_invalid_encoding().

Referenced by length_in_encoding().

pg_verifymbstr()

bool pg_verifymbstr	(	const char *	mbstr,
		int	len,
		bool	noError
	)

Definition at line 1563 of file mbutils.c.

{
    return pg_verify_mbstr(GetDatabaseEncoding(), mbstr, len, noError);
}

References GetDatabaseEncoding(), len, and pg_verify_mbstr().

Referenced by char2wchar(), CopyReadAttributesText(), plperl_spi_exec(), plperl_spi_prepare(), plperl_spi_query(), PLy_cursor_query(), PLy_output(), PLy_spi_execute_query(), PLy_spi_prepare(), PLyObject_AsString(), read_text_file(), and spg_text_leaf_consistent().

pg_wchar2mb()

int pg_wchar2mb	(	const pg_wchar *	from,
		char *	to
	)

Definition at line 1002 of file mbutils.c.

{
    return pg_wchar_table[DatabaseEncoding->encoding].wchar2mb_with_len(from, (unsigned char *) to, pg_wchar_strlen(from));
}

References DatabaseEncoding, pg_enc2name::encoding, pg_wchar_strlen(), pg_wchar_table, and pg_wchar_tbl::wchar2mb_with_len.

pg_wchar2mb_with_len()

int pg_wchar2mb_with_len	(	const pg_wchar *	from,
		char *	to,
		int	len
	)

Definition at line 1009 of file mbutils.c.

{
    return pg_wchar_table[DatabaseEncoding->encoding].wchar2mb_with_len(from, (unsigned char *) to, len);
}

References DatabaseEncoding, pg_enc2name::encoding, len, pg_wchar_table, and pg_wchar_tbl::wchar2mb_with_len.

Referenced by build_regexp_match_result(), build_regexp_split_result(), build_test_match_result(), convertPgWchar(), and regexp_fixed_prefix().

pg_wchar_strlen()

size_t pg_wchar_strlen

(

const pg_wchar *

str

)

Definition at line 70 of file wstrncmp.c.

{
    const pg_wchar *s;
 
    for (s = str; *s; ++s)
        ;
    return (s - str);
}

References generate_unaccent_rules::str.

Referenced by pg_wchar2mb().

pg_wchar_strncmp()

int pg_wchar_strncmp	(	const pg_wchar *	s1,
		const pg_wchar *	s2,
		size_t	n
	)

Definition at line 40 of file wstrncmp.c.

{
    if (n == 0)
        return 0;
    do
    {
        if (*s1 != *s2++)
            return (*s1 - *(s2 - 1));
        if (*s1++ == 0)
            break;
    } while (--n != 0);
    return 0;
}

References s1, and s2.

PrepareClientEncoding()

int PrepareClientEncoding

(

int

encoding

)

Definition at line 111 of file mbutils.c.

{
    int         current_server_encoding;
    ListCell   *lc;
 
    if (!PG_VALID_FE_ENCODING(encoding))
        return -1;
 
    /* Can't do anything during startup, per notes above */
    if (!backend_startup_complete)
        return 0;
 
    current_server_encoding = GetDatabaseEncoding();
 
    /*
     * Check for cases that require no conversion function.
     */
    if (current_server_encoding == encoding ||
        current_server_encoding == PG_SQL_ASCII ||
        encoding == PG_SQL_ASCII)
        return 0;
 
    if (IsTransactionState())
    {
        /*
         * If we're in a live transaction, it's safe to access the catalogs,
         * so look up the functions.  We repeat the lookup even if the info is
         * already cached, so that we can react to changes in the contents of
         * pg_conversion.
         */
        Oid         to_server_proc,
                    to_client_proc;
        ConvProcInfo *convinfo;
        MemoryContext oldcontext;
 
        to_server_proc = FindDefaultConversionProc(encoding,
                                                   current_server_encoding);
        if (!OidIsValid(to_server_proc))
            return -1;
        to_client_proc = FindDefaultConversionProc(current_server_encoding,
                                                   encoding);
        if (!OidIsValid(to_client_proc))
            return -1;
 
        /*
         * Load the fmgr info into TopMemoryContext (could still fail here)
         */
        convinfo = (ConvProcInfo *) MemoryContextAlloc(TopMemoryContext,
                                                       sizeof(ConvProcInfo));
        convinfo->s_encoding = current_server_encoding;
        convinfo->c_encoding = encoding;
        fmgr_info_cxt(to_server_proc, &convinfo->to_server_info,
                      TopMemoryContext);
        fmgr_info_cxt(to_client_proc, &convinfo->to_client_info,
                      TopMemoryContext);
 
        /* Attach new info to head of list */
        oldcontext = MemoryContextSwitchTo(TopMemoryContext);
        ConvProcList = lcons(convinfo, ConvProcList);
        MemoryContextSwitchTo(oldcontext);
 
        /*
         * We cannot yet remove any older entry for the same encoding pair,
         * since it could still be in use.  SetClientEncoding will clean up.
         */
 
        return 0;               /* success */
    }
    else
    {
        /*
         * If we're not in a live transaction, the only thing we can do is
         * restore a previous setting using the cache.  This covers all
         * transaction-rollback cases.  The only case it might not work for is
         * trying to change client_encoding on the fly by editing
         * postgresql.conf and SIGHUP'ing.  Which would probably be a stupid
         * thing to do anyway.
         */
        foreach(lc, ConvProcList)
        {
            ConvProcInfo *oldinfo = (ConvProcInfo *) lfirst(lc);
 
            if (oldinfo->s_encoding == current_server_encoding &&
                oldinfo->c_encoding == encoding)
                return 0;
        }
 
        return -1;              /* it's not cached, so fail */
    }
}

References backend_startup_complete, ConvProcInfo::c_encoding, ConvProcList, encoding, FindDefaultConversionProc(), fmgr_info_cxt(), GetDatabaseEncoding(), IsTransactionState(), lcons(), lfirst, MemoryContextAlloc(), MemoryContextSwitchTo(), OidIsValid, PG_SQL_ASCII, PG_VALID_FE_ENCODING, ConvProcInfo::s_encoding, ConvProcInfo::to_client_info, ConvProcInfo::to_server_info, and TopMemoryContext.

Referenced by check_client_encoding(), and InitializeClientEncoding().

report_invalid_encoding()

void report_invalid_encoding	(	int	encoding,
		const char *	mbstr,
		int	len
	)

Definition at line 1705 of file mbutils.c.

{
    int         l = pg_encoding_mblen(encoding, mbstr);
    char        buf[8 * 5 + 1];
    char       *p = buf;
    int         j,
                jlimit;
 
    jlimit = Min(l, len);
    jlimit = Min(jlimit, 8);    /* prevent buffer overrun */
 
    for (j = 0; j < jlimit; j++)
    {
        p += sprintf(p, "0x%02x", (unsigned char) mbstr[j]);
        if (j < jlimit - 1)
            p += sprintf(p, " ");
    }
 
    ereport(ERROR,
            (errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
             errmsg("invalid byte sequence for encoding \"%s\": %s",
                    pg_enc2name_tbl[encoding].name,
                    buf)));
}

References buf, encoding, ereport, errcode(), errmsg(), ERROR, j, len, Min, name, pg_enc2name_tbl, pg_encoding_mblen(), and sprintf.

Referenced by big52euc_tw(), big52mic(), CopyConversionError(), euc_cn2mic(), euc_jis_20042shift_jis_2004(), euc_jp2mic(), euc_jp2sjis(), euc_kr2mic(), euc_tw2big5(), euc_tw2mic(), iso8859_1_to_utf8(), latin2mic(), latin2mic_with_table(), local2local(), LocalToUtf(), mic2big5(), mic2euc_cn(), mic2euc_jp(), mic2euc_kr(), mic2euc_tw(), mic2latin(), mic2latin_with_table(), mic2sjis(), pg_verify_mbstr(), pg_verify_mbstr_len(), shift_jis_20042euc_jis_2004(), sjis2euc_jp(), sjis2mic(), test_enc_conversion(), utf8_to_iso8859_1(), and UtfToLocal().

report_untranslatable_char()

void report_untranslatable_char	(	int	src_encoding,
		int	dest_encoding,
		const char *	mbstr,
		int	len
	)

Definition at line 1737 of file mbutils.c.

{
    int         l = pg_encoding_mblen(src_encoding, mbstr);
    char        buf[8 * 5 + 1];
    char       *p = buf;
    int         j,
                jlimit;
 
    jlimit = Min(l, len);
    jlimit = Min(jlimit, 8);    /* prevent buffer overrun */
 
    for (j = 0; j < jlimit; j++)
    {
        p += sprintf(p, "0x%02x", (unsigned char) mbstr[j]);
        if (j < jlimit - 1)
            p += sprintf(p, " ");
    }
 
    ereport(ERROR,
            (errcode(ERRCODE_UNTRANSLATABLE_CHARACTER),
             errmsg("character with byte sequence %s in encoding \"%s\" has no equivalent in encoding \"%s\"",
                    buf,
                    pg_enc2name_tbl[src_encoding].name,
                    pg_enc2name_tbl[dest_encoding].name)));
}

References buf, ereport, errcode(), errmsg(), ERROR, j, len, Min, name, pg_enc2name_tbl, pg_encoding_mblen(), and sprintf.

Referenced by big52euc_tw(), big52mic(), euc_tw2big5(), latin2mic_with_table(), local2local(), LocalToUtf(), mic2big5(), mic2euc_cn(), mic2euc_jp(), mic2euc_kr(), mic2euc_tw(), mic2latin(), mic2latin_with_table(), mic2sjis(), utf8_to_iso8859_1(), and UtfToLocal().

SetClientEncoding()

int SetClientEncoding

(

int

encoding

)

Definition at line 209 of file mbutils.c.

{
    int         current_server_encoding;
    bool        found;
    ListCell   *lc;
 
    if (!PG_VALID_FE_ENCODING(encoding))
        return -1;
 
    /* Can't do anything during startup, per notes above */
    if (!backend_startup_complete)
    {
        pending_client_encoding = encoding;
        return 0;
    }
 
    current_server_encoding = GetDatabaseEncoding();
 
    /*
     * Check for cases that require no conversion function.
     */
    if (current_server_encoding == encoding ||
        current_server_encoding == PG_SQL_ASCII ||
        encoding == PG_SQL_ASCII)
    {
        ClientEncoding = &pg_enc2name_tbl[encoding];
        ToServerConvProc = NULL;
        ToClientConvProc = NULL;
        return 0;
    }
 
    /*
     * Search the cache for the entry previously prepared by
     * PrepareClientEncoding; if there isn't one, we lose.  While at it,
     * release any duplicate entries so that repeated Prepare/Set cycles don't
     * leak memory.
     */
    found = false;
    foreach(lc, ConvProcList)
    {
        ConvProcInfo *convinfo = (ConvProcInfo *) lfirst(lc);
 
        if (convinfo->s_encoding == current_server_encoding &&
            convinfo->c_encoding == encoding)
        {
            if (!found)
            {
                /* Found newest entry, so set up */
                ClientEncoding = &pg_enc2name_tbl[encoding];
                ToServerConvProc = &convinfo->to_server_info;
                ToClientConvProc = &convinfo->to_client_info;
                found = true;
            }
            else
            {
                /* Duplicate entry, release it */
                ConvProcList = foreach_delete_current(ConvProcList, lc);
                pfree(convinfo);
            }
        }
    }
 
    if (found)
        return 0;               /* success */
    else
        return -1;              /* it's not cached, so fail */
}

References backend_startup_complete, ConvProcInfo::c_encoding, ClientEncoding, ConvProcList, encoding, foreach_delete_current, GetDatabaseEncoding(), lfirst, pending_client_encoding, pfree(), pg_enc2name_tbl, PG_SQL_ASCII, PG_VALID_FE_ENCODING, ConvProcInfo::s_encoding, ConvProcInfo::to_client_info, ConvProcInfo::to_server_info, ToClientConvProc, and ToServerConvProc.

Referenced by assign_client_encoding(), InitializeClientEncoding(), and ParallelWorkerMain().

SetDatabaseEncoding()

void SetDatabaseEncoding

(

int

encoding

)

Definition at line 1162 of file mbutils.c.

{
    if (!PG_VALID_BE_ENCODING(encoding))
        elog(ERROR, "invalid database encoding: %d", encoding);
 
    DatabaseEncoding = &pg_enc2name_tbl[encoding];
    Assert(DatabaseEncoding->encoding == encoding);
}

References Assert(), DatabaseEncoding, elog(), encoding, pg_enc2name::encoding, ERROR, pg_enc2name_tbl, and PG_VALID_BE_ENCODING.

Referenced by CheckMyDatabase().

SetMessageEncoding()

void SetMessageEncoding

(

int

encoding

)

Definition at line 1172 of file mbutils.c.

{
    /* Some calls happen before we can elog()! */
    Assert(PG_VALID_ENCODING(encoding));
 
    MessageEncoding = &pg_enc2name_tbl[encoding];
    Assert(MessageEncoding->encoding == encoding);
}

References Assert(), encoding, pg_enc2name::encoding, MessageEncoding, pg_enc2name_tbl, and PG_VALID_ENCODING.

Referenced by pg_perm_setlocale().

surrogate_pair_to_codepoint()

static pg_wchar surrogate_pair_to_codepoint ( pg_wchar  first, pg_wchar  second  )

inlinestatic

Definition at line 543 of file pg_wchar.h.

{

Referenced by json_lex_string(), str_udeescape(), and unistr().

unicode_to_utf8()

unsigned char* unicode_to_utf8	(	pg_wchar	c,
		unsigned char *	utf8string
	)

Definition at line 483 of file wchar.c.

{
    if (c <= 0x7F)
    {
        utf8string[0] = c;
    }
    else if (c <= 0x7FF)
    {
        utf8string[0] = 0xC0 | ((c >> 6) & 0x1F);
        utf8string[1] = 0x80 | (c & 0x3F);
    }
    else if (c <= 0xFFFF)
    {
        utf8string[0] = 0xE0 | ((c >> 12) & 0x0F);
        utf8string[1] = 0x80 | ((c >> 6) & 0x3F);
        utf8string[2] = 0x80 | (c & 0x3F);
    }
    else
    {
        utf8string[0] = 0xF0 | ((c >> 18) & 0x07);
        utf8string[1] = 0x80 | ((c >> 12) & 0x3F);
        utf8string[2] = 0x80 | ((c >> 6) & 0x3F);
        utf8string[3] = 0x80 | (c & 0x3F);
    }
 
    return utf8string;
}

Referenced by json_lex_string(), pg_saslprep(), pg_unicode_to_server(), pg_unicode_to_server_noerror(), pg_wchar2utf_with_len(), and unicode_normalize_func().

utf8_to_unicode()

pg_wchar utf8_to_unicode

(

const unsigned char *

c

)

Definition at line 679 of file wchar.c.

{
    if ((*c & 0x80) == 0)
        return (pg_wchar) c[0];
    else if ((*c & 0xe0) == 0xc0)
        return (pg_wchar) (((c[0] & 0x1f) << 6) |
                           (c[1] & 0x3f));
    else if ((*c & 0xf0) == 0xe0)
        return (pg_wchar) (((c[0] & 0x0f) << 12) |
                           ((c[1] & 0x3f) << 6) |
                           (c[2] & 0x3f));
    else if ((*c & 0xf8) == 0xf0)
        return (pg_wchar) (((c[0] & 0x07) << 18) |
                           ((c[1] & 0x3f) << 12) |
                           ((c[2] & 0x3f) << 6) |
                           (c[3] & 0x3f));
    else
        /* that is an invalid code on purpose */
        return 0xffffffff;
}

Referenced by pg_saslprep(), pg_utf_dsplen(), read_char(), unicode_is_normalized(), and unicode_normalize_func().

UtfToLocal()

int UtfToLocal	(	const unsigned char *	utf,
		int	len,
		unsigned char *	iso,
		const pg_mb_radix_tree *	map,
		const pg_utf_to_local_combined *	cmap,
		int	cmapsize,
		utf_local_conversion_func	conv_func,
		int	encoding,
		bool	noError
	)

Definition at line 507 of file conv.c.

{
    uint32      iutf;
    int         l;
    const pg_utf_to_local_combined *cp;
    const unsigned char *start = utf;
 
    if (!PG_VALID_ENCODING(encoding))
        ereport(ERROR,
                (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
                 errmsg("invalid encoding number: %d", encoding)));
 
    for (; len > 0; len -= l)
    {
        unsigned char b1 = 0;
        unsigned char b2 = 0;
        unsigned char b3 = 0;
        unsigned char b4 = 0;
 
        /* "break" cases all represent errors */
        if (*utf == '\0')
            break;
 
        l = pg_utf_mblen(utf);
        if (len < l)
            break;
 
        if (!pg_utf8_islegal(utf, l))
            break;
 
        if (l == 1)
        {
            /* ASCII case is easy, assume it's one-to-one conversion */
            *iso++ = *utf++;
            continue;
        }
 
        /* collect coded char of length l */
        if (l == 2)
        {
            b3 = *utf++;
            b4 = *utf++;
        }
        else if (l == 3)
        {
            b2 = *utf++;
            b3 = *utf++;
            b4 = *utf++;
        }
        else if (l == 4)
        {
            b1 = *utf++;
            b2 = *utf++;
            b3 = *utf++;
            b4 = *utf++;
        }
        else
        {
            elog(ERROR, "unsupported character length %d", l);
            iutf = 0;           /* keep compiler quiet */
        }
        iutf = (b1 << 24 | b2 << 16 | b3 << 8 | b4);
 
        /* First, try with combined map if possible */
        if (cmap && len > l)
        {
            const unsigned char *utf_save = utf;
            int         len_save = len;
            int         l_save = l;
 
            /* collect next character, same as above */
            len -= l;
 
            l = pg_utf_mblen(utf);
            if (len < l)
            {
                /* need more data to decide if this is a combined char */
                utf -= l_save;
                break;
            }
 
            if (!pg_utf8_islegal(utf, l))
            {
                if (!noError)
                    report_invalid_encoding(PG_UTF8, (const char *) utf, len);
                utf -= l_save;
                break;
            }
 
            /* We assume ASCII character cannot be in combined map */
            if (l > 1)
            {
                uint32      iutf2;
                uint32      cutf[2];
 
                if (l == 2)
                {
                    iutf2 = *utf++ << 8;
                    iutf2 |= *utf++;
                }
                else if (l == 3)
                {
                    iutf2 = *utf++ << 16;
                    iutf2 |= *utf++ << 8;
                    iutf2 |= *utf++;
                }
                else if (l == 4)
                {
                    iutf2 = *utf++ << 24;
                    iutf2 |= *utf++ << 16;
                    iutf2 |= *utf++ << 8;
                    iutf2 |= *utf++;
                }
                else
                {
                    elog(ERROR, "unsupported character length %d", l);
                    iutf2 = 0;  /* keep compiler quiet */
                }
 
                cutf[0] = iutf;
                cutf[1] = iutf2;
 
                cp = bsearch(cutf, cmap, cmapsize,
                             sizeof(pg_utf_to_local_combined), compare3);
 
                if (cp)
                {
                    iso = store_coded_char(iso, cp->code);
                    continue;
                }
            }
 
            /* fail, so back up to reprocess second character next time */
            utf = utf_save;
            len = len_save;
            l = l_save;
        }
 
        /* Now check ordinary map */
        if (map)
        {
            uint32      converted = pg_mb_radix_conv(map, l, b1, b2, b3, b4);
 
            if (converted)
            {
                iso = store_coded_char(iso, converted);
                continue;
            }
        }
 
        /* if there's a conversion function, try that */
        if (conv_func)
        {
            uint32      converted = (*conv_func) (iutf);
 
            if (converted)
            {
                iso = store_coded_char(iso, converted);
                continue;
            }
        }
 
        /* failed to translate this character */
        utf -= l;
        if (noError)
            break;
        report_untranslatable_char(PG_UTF8, encoding,
                                   (const char *) utf, len);
    }
 
    /* if we broke out of loop early, must be invalid input */
    if (len > 0 && !noError)
        report_invalid_encoding(PG_UTF8, (const char *) utf, len);
 
    *iso = '\0';
 
    return utf - start;
}

References pg_utf_to_local_combined::code, compare3(), elog(), encoding, ereport, errcode(), errmsg(), ERROR, len, pg_mb_radix_conv(), PG_UTF8, pg_utf8_islegal(), pg_utf_mblen(), PG_VALID_ENCODING, report_invalid_encoding(), report_untranslatable_char(), and store_coded_char().

Referenced by utf8_to_big5(), utf8_to_euc_cn(), utf8_to_euc_jis_2004(), utf8_to_euc_jp(), utf8_to_euc_kr(), utf8_to_euc_tw(), utf8_to_gb18030(), utf8_to_gbk(), utf8_to_iso8859(), utf8_to_johab(), utf8_to_koi8r(), utf8_to_koi8u(), utf8_to_shift_jis_2004(), utf8_to_sjis(), utf8_to_uhc(), and utf8_to_win().

Variable Documentation

pg_enc2gettext_tbl

PGDLLIMPORT const pg_enc2gettext pg_enc2gettext_tbl[]

extern

Definition at line 361 of file encnames.c.

pg_enc2name_tbl

PGDLLIMPORT const pg_enc2name pg_enc2name_tbl[]

extern

Definition at line 309 of file encnames.c.

Referenced by check_encoding_conversion_args(), InitializeClientEncoding(), pg_any_to_server(), pg_encoding_to_char(), pg_unicode_to_server(), report_invalid_encoding(), report_untranslatable_char(), SetClientEncoding(), SetDatabaseEncoding(), and SetMessageEncoding().

pg_wchar_table

PGDLLIMPORT const pg_wchar_tbl pg_wchar_table[]

extern

Definition at line 2076 of file wchar.c.

Referenced by pg_database_encoding_max_length(), pg_dsplen(), pg_encoding_dsplen(), pg_encoding_max_length(), pg_encoding_max_length_sql(), pg_encoding_mb2wchar_with_len(), pg_encoding_mbcliplen(), pg_encoding_mblen(), pg_encoding_verifymbchar(), pg_encoding_verifymbstr(), pg_encoding_wchar2mb_with_len(), pg_generic_charinc(), pg_mb2wchar(), pg_mb2wchar_with_len(), pg_mblen(), pg_verify_mbstr(), pg_verify_mbstr_len(), pg_wchar2mb(), and pg_wchar2mb_with_len().