Convert between different charsets. More...

Collaboration diagram for Charset conversion:

Macros
#define	CHUNK_ALLOC 4

Typedefs
typedef uint32_t	ICONV_CHAR

typedef int(*	iconv_get_t) (const unsigned char p, size_t len, ICONV_CHAR out)

typedef int(*	iconv_put_t) (unsigned char *buf, size_t buf_len, ICONV_CHAR c)

Enumerations
enum	ICONV_CD_VALUE { Like_to_Like = 0x100 }

Functions
static void	_iconv_close (iconv_t *cd)

static int	collate2charset (TDSCONNECTION *conn, TDS_UCHAR collate[5])

static int	get_ascii (const unsigned char p, size_t len, ICONV_CHAR out)

static int	get_cp1252 (const unsigned char p, size_t len, ICONV_CHAR out)

static int	get_err (const unsigned char p, size_t len, ICONV_CHAR out)

static int	get_iso1 (const unsigned char p, size_t len, ICONV_CHAR out)

static int	get_ucs4be (const unsigned char p, size_t len, ICONV_CHAR out)

static int	get_ucs4le (const unsigned char p, size_t len, ICONV_CHAR out)

static int	get_utf16be (const unsigned char p, size_t len, ICONV_CHAR out)

static int	get_utf16le (const unsigned char p, size_t len, ICONV_CHAR out)

static int	get_utf8 (const unsigned char p, size_t len, ICONV_CHAR out)

static int	put_ascii (unsigned char *buf, size_t buf_len, ICONV_CHAR c)

static int	put_cp1252 (unsigned char *buf, size_t buf_len, ICONV_CHAR c)

static int	put_err (unsigned char *buf, size_t buf_len, ICONV_CHAR c)

static int	put_iso1 (unsigned char *buf, size_t buf_len, ICONV_CHAR c)

static int	put_ucs4be (unsigned char *buf, size_t buf_len, ICONV_CHAR c)

static int	put_ucs4le (unsigned char *buf, size_t buf_len, ICONV_CHAR c)

static int	put_utf16be (unsigned char *buf, size_t buf_len, ICONV_CHAR c)

static int	put_utf16le (unsigned char *buf, size_t buf_len, ICONV_CHAR c)

static int	put_utf8 (unsigned char *buf, size_t buf_len, ICONV_CHAR c)

static size_t	skip_one_input_sequence (iconv_t cd, const TDS_ENCODING charset, const char input, size_t input_size)
	Move the input sequence pointer to the next valid position.

void	tds7_srv_charset_changed (TDSCONNECTION *conn, TDS_UCHAR collation[5])

int	tds_canonical_charset (const char *charset_name)
	Determine canonical iconv character set.

const char *	tds_canonical_charset_name (const char *charset_name)
	Determine canonical iconv character set name.

size_t	tds_iconv (TDSSOCKET tds, TDSICONV conv, TDS_ICONV_DIRECTION io, const char *inbuf, size_t inbytesleft, char *outbuf, size_t outbytesleft)
	Wrapper around iconv(3).

void	tds_iconv_close (TDSCONNECTION *conn)

static void	tds_iconv_err (TDSSOCKET *tds, int err)

void	tds_iconv_free (TDSCONNECTION *conn)

TDSICONV *	tds_iconv_from_collate (TDSCONNECTION *conn, TDS_UCHAR collate[5])
	Get iconv information from a LCID (to support different column encoding under MSSQL2K)

TDSICONV *	tds_iconv_get (TDSCONNECTION conn, const char client_charset, const char *server_charset)

TDSICONV *	tds_iconv_get_info (TDSCONNECTION *conn, int canonic_client, int canonic_server)
	Get a iconv info structure, allocate and initialize if needed.

static void	tds_iconv_info_close (TDSICONV *char_conv)

static int	tds_iconv_info_init (TDSICONV *char_conv, int client_canonical, int server_canonical)
	Open iconv descriptors to convert between character sets (both directions).

TDSRET	tds_iconv_open (TDSCONNECTION conn, const char charset, int use_utf16)

void	tds_srv_charset_changed (TDSCONNECTION conn, const char charset)

static void	tds_srv_charset_changed_num (TDSCONNECTION *conn, int canonic_charset_num)

size_t	tds_sys_iconv (iconv_t cd, const char *inbuf, size_t inbytesleft, char *outbuf, size_t outbytesleft)

int	tds_sys_iconv_close (iconv_t cd)

iconv_t	tds_sys_iconv_open (const char tocode, const char fromcode)
	Inputs are FreeTDS canonical names, no other.

Variables
static const iconv_get_t	iconv_gets [16]

static const iconv_put_t	iconv_puts [16]

Detailed Description

Convert between different charsets.

Set up the initial iconv conversion descriptors.

When the socket is allocated, three TDSICONV structures are attached to iconv.
They have fixed meanings:

0. Client <-> UCS-2 (client2ucs2)
1. Client <-> server single-byte charset (client2server_chardata)

Other designs that use less data are possible, but these three conversion needs are very often needed. By reserving them, we avoid searching the array for our most common purposes.

To solve different iconv names and portability problems FreeTDS maintains a list of aliases each charset.

First we discover the names of our minimum required charsets (UTF-8, ISO8859-1 and UCS2).
Later, as and when it's needed, we try to discover others.

There is one list of canonic names (GNU iconv names) and two sets of aliases (one for other iconv implementations and another for Sybase). For every canonic charset name we cache the iconv name found during discovery.

Function Documentation

◆ skip_one_input_sequence()

static size_t skip_one_input_sequence	(	iconv_t	cd,
		const TDS_ENCODING *	charset,
		const char **	input,
		size_t *	input_size
	)

static

Move the input sequence pointer to the next valid position.

Used when an input character cannot be converted.

Returns: number of bytes to skip.

Here is the call graph for this function:

Here is the caller graph for this function:

◆ tds_canonical_charset()

int tds_canonical_charset ( const char * charset_name )

Determine canonical iconv character set.

Returns: canonical position, or -1 if lookup failed.

Remarks: Returned name can be used in bytes_per_char(), above.

Here is the caller graph for this function:

◆ tds_canonical_charset_name()

const char * tds_canonical_charset_name ( const char * charset_name )

Determine canonical iconv character set name.

Returns: canonical name, or NULL if lookup failed.

Remarks: Returned name can be used in bytes_per_char(), above.

Here is the call graph for this function:

Here is the caller graph for this function:

◆ tds_iconv()

size_t tds_iconv	(	TDSSOCKET *	tds,
		TDSICONV *	conv,
		TDS_ICONV_DIRECTION	io,
		const char **	inbuf,
		size_t *	inbytesleft,
		char **	outbuf,
		size_t *	outbytesleft
	)

Wrapper around iconv(3).

Same parameters, with slightly different behavior.

Parameters

tds	state information for the socket and the TDS protocol
io	Enumerated value indicating whether the data are being sent to or received from the server.
conv	information about the encodings involved, including the iconv(3) conversion descriptors.
inbuf	address of pointer to the input buffer of data to be converted.
inbytesleft	address of count of bytes in inbuf.
outbuf	address of pointer to the output buffer.
outbytesleft	address of count of bytes in outbuf.

Return values

number of irreversible conversions performed. -1 on error, see iconv(3) documentation for a description of the possible values of errno.

Remarks: Unlike iconv(3), none of the arguments can be nor point to NULL. Like iconv(3), all pointers will be updated. Success is signified by a nonnegative return code and *inbytesleft == 0.
If the conversion descriptor in iconv is -1 or NULL, inbuf is copied to outbuf, and all parameters updated accordingly.

If a character in inbuf cannot be converted because no such cbaracter exists in the outbuf character set, we emit messages similar to the ones Sybase emits when it fails such a conversion. The message varies depending on the direction of the data.
On a read error, we emit Msg 2403, Severity 16 (EX_INFO): "WARNING! Some character(s) could not be converted into client's character set. Unconverted bytes were changed to question marks ('?')." On a write error we emit Msg 2402, Severity 16 (EX_USER): "Error converting client characters into server's character set. Some character(s) could not be converted." and return an error code. Client libraries relying on this routine should reflect an error back to the application.

Todo:

Check for variable multibyte non-UTF-8 input character set.

Use more robust error message generation.

For reads, cope with outbuf encodings that don't have the equivalent of an ASCII '?'.

Support alternative to '?' for the replacement character.

Here is the call graph for this function:

Here is the caller graph for this function:

◆ tds_iconv_info_init()

static int tds_iconv_info_init	(	TDSICONV *	char_conv,
		int	client_canonical,
		int	server_canonical
	)

static

Open iconv descriptors to convert between character sets (both directions).

Look up the canonical names of the character sets.
Look up their widths.
Ask iconv to open a conversion descriptor.
Fail if any of the above offer any resistance.

Remarks
The charset names written to iconv will be the canonical names, not necessarily the names passed in.

Here is the call graph for this function:

Here is the caller graph for this function:

◆ tds_sys_iconv_open()

iconv_t tds_sys_iconv_open	(	const char *	tocode,
		const char *	fromcode
	)

Inputs are FreeTDS canonical names, no other.

No alias list is consulted.

Here is the caller graph for this function:

Variable Documentation

◆ iconv_gets

const iconv_get_t iconv_gets[16]

static

Initial value:

= {
    get_iso1, get_ascii, get_utf16le, get_utf16be, get_ucs4le, get_ucs4be, get_utf8, get_cp1252,
    get_err, get_err, get_err, get_err, get_err, get_err, get_err, get_err,
}

◆ iconv_puts

const iconv_put_t iconv_puts[16]

static

Initial value:

= {
    put_iso1, put_ascii, put_utf16le, put_utf16be, put_ucs4le, put_ucs4be, put_utf8, put_cp1252,
    put_err, put_err, put_err, put_err, put_err, put_err, put_err, put_err,
}

Macros

Typedefs

Enumerations

Functions

Variables

Detailed Description

Function Documentation

◆ skip_one_input_sequence()

◆ tds_canonical_charset()

◆ tds_canonical_charset_name()

◆ tds_iconv()

◆ tds_iconv_info_init()

◆ tds_sys_iconv_open()

Variable Documentation

◆ iconv_gets

◆ iconv_puts