pg_locale_libc.c File Reference

#include "postgres.h"
#include "catalog/pg_collation.h"
#include "mb/pg_wchar.h"
#include "utils/formatting.h"
#include "utils/pg_locale.h"

Include dependency graph for pg_locale_libc.c:

Go to the source code of this file.

Macros
#define	TEXTBUFLEN   1024

Functions
locale_t	make_libc_collator (const char *collate, const char *ctype)
int	strncoll_libc (const char *arg1, ssize_t len1, const char *arg2, ssize_t len2, pg_locale_t locale)
size_t	strnxfrm_libc (char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale)
static void	report_newlocale_failure (const char *localename)
static size_t	mbstowcs_l (wchar_t *dest, const char *src, size_t n, locale_t loc)
static size_t	wcstombs_l (char *dest, const wchar_t *src, size_t n, locale_t loc)
size_t	wchar2char (char *to, const wchar_t *from, size_t tolen, pg_locale_t locale)
size_t	char2wchar (wchar_t *to, size_t tolen, const char *from, size_t fromlen, pg_locale_t locale)

Macro Definition Documentation

TEXTBUFLEN

#define TEXTBUFLEN   1024

Definition at line 25 of file pg_locale_libc.c.

Function Documentation

char2wchar()

size_t char2wchar	(	wchar_t *	to,
		size_t	tolen,
		const char *	from,
		size_t	fromlen,
		pg_locale_t	locale
	)

Definition at line 433 of file pg_locale_libc.c.

{
    size_t      result;
 
    if (tolen == 0)
        return 0;
 
#ifdef WIN32
    /* See WIN32 "Unicode" comment above */
    if (GetDatabaseEncoding() == PG_UTF8)
    {
        /* Win32 API does not work for zero-length input */
        if (fromlen == 0)
            result = 0;
        else
        {
            result = MultiByteToWideChar(CP_UTF8, 0, from, fromlen, to, tolen - 1);
            /* A zero return is failure */
            if (result == 0)
                result = -1;
        }
 
        if (result != -1)
        {
            Assert(result < tolen);
            /* Append trailing null wchar (MultiByteToWideChar() does not) */
            to[result] = 0;
        }
    }
    else
#endif                          /* WIN32 */
    {
        /* mbstowcs requires ending '\0' */
        char       *str = pnstrdup(from, fromlen);
 
        if (locale == (pg_locale_t) 0)
        {
            /* Use mbstowcs directly for the default locale */
            result = mbstowcs(to, str, tolen);
        }
        else
        {
            /* Use mbstowcs_l for nondefault locales */
            result = mbstowcs_l(to, str, tolen, locale->info.lt);
        }
 
        pfree(str);
    }
 
    if (result == -1)
    {
        /*
         * Invalid multibyte character encountered.  We try to give a useful
         * error message by letting pg_verifymbstr check the string.  But it's
         * possible that the string is OK to us, and not OK to mbstowcs ---
         * this suggests that the LC_CTYPE locale is different from the
         * database encoding.  Give a generic error message if pg_verifymbstr
         * can't find anything wrong.
         */
        pg_verifymbstr(from, fromlen, false);   /* might not return */
        /* but if it does ... */
        ereport(ERROR,
                (errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
                 errmsg("invalid multibyte character for locale"),
                 errhint("The server's LC_CTYPE locale is probably incompatible with the database encoding.")));
    }
 
    return result;
}

References Assert, ereport, errcode(), errhint(), errmsg(), ERROR, GetDatabaseEncoding(), locale, mbstowcs_l(), pfree(), PG_UTF8, pg_verifymbstr(), pnstrdup(), and str.

Referenced by lowerstr_with_len(), str_initcap(), str_tolower(), str_toupper(), t_isalnum(), t_isalpha(), t_isdigit(), t_isprint(), t_isspace(), and TParserInit().

make_libc_collator()

locale_t make_libc_collator	(	const char *	collate,
		const char *	ctype
	)

Definition at line 53 of file pg_locale_libc.c.

{
    locale_t    loc = 0;
 
    if (strcmp(collate, ctype) == 0)
    {
        if (strcmp(ctype, "C") != 0 && strcmp(ctype, "POSIX") != 0)
        {
            /* Normal case where they're the same */
            errno = 0;
#ifndef WIN32
            loc = newlocale(LC_COLLATE_MASK | LC_CTYPE_MASK, collate,
                            NULL);
#else
            loc = _create_locale(LC_ALL, collate);
#endif
            if (!loc)
                report_newlocale_failure(collate);
        }
    }
    else
    {
#ifndef WIN32
        /* We need two newlocale() steps */
        locale_t    loc1 = 0;
 
        if (strcmp(collate, "C") != 0 && strcmp(collate, "POSIX") != 0)
        {
            errno = 0;
            loc1 = newlocale(LC_COLLATE_MASK, collate, NULL);
            if (!loc1)
                report_newlocale_failure(collate);
        }
 
        if (strcmp(ctype, "C") != 0 && strcmp(ctype, "POSIX") != 0)
        {
            errno = 0;
            loc = newlocale(LC_CTYPE_MASK, ctype, loc1);
            if (!loc)
            {
                if (loc1)
                    freelocale(loc1);
                report_newlocale_failure(ctype);
            }
        }
        else
            loc = loc1;
#else
 
        /*
         * XXX The _create_locale() API doesn't appear to support this. Could
         * perhaps be worked around by changing pg_locale_t to contain two
         * separate fields.
         */
        ereport(ERROR,
                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                 errmsg("collations with different collate and ctype values are not supported on this platform")));
#endif
    }
 
    return loc;
}

References ereport, errcode(), errmsg(), ERROR, locale_t, and report_newlocale_failure().

Referenced by init_database_collation(), and pg_newlocale_from_collation().

mbstowcs_l()

static size_t mbstowcs_l ( wchar_t *  dest, const char *  src, size_t  n, locale_t  loc  )

static

Definition at line 335 of file pg_locale_libc.c.

{
#ifdef WIN32
    return _mbstowcs_l(dest, src, n, loc);
#else
    size_t      result;
    locale_t    save_locale = uselocale(loc);
 
    result = mbstowcs(dest, src, n);
    uselocale(save_locale);
    return result;
#endif
}

References generate_unaccent_rules::dest, and locale_t.

Referenced by char2wchar().

report_newlocale_failure()

static void report_newlocale_failure ( const char *  localename )

static

Definition at line 301 of file pg_locale_libc.c.

{
    int         save_errno;
 
    /*
     * Windows doesn't provide any useful error indication from
     * _create_locale(), and BSD-derived platforms don't seem to feel they
     * need to set errno either (even though POSIX is pretty clear that
     * newlocale should do so).  So, if errno hasn't been set, assume ENOENT
     * is what to report.
     */
    if (errno == 0)
        errno = ENOENT;
 
    /*
     * ENOENT means "no such locale", not "no such file", so clarify that
     * errno with an errdetail message.
     */
    save_errno = errno;         /* auxiliary funcs might change errno */
    ereport(ERROR,
            (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
             errmsg("could not create locale \"%s\": %m",
                    localename),
             (save_errno == ENOENT ?
              errdetail("The operating system could not find any locale data for the locale name \"%s\".",
                        localename) : 0)));
}

References ereport, errcode(), errdetail(), errmsg(), and ERROR.

Referenced by make_libc_collator().

strncoll_libc()

int strncoll_libc	(	const char *	arg1,
		ssize_t	len1,
		const char *	arg2,
		ssize_t	len2,
		pg_locale_t	locale
	)

Definition at line 124 of file pg_locale_libc.c.

{
    char        sbuf[TEXTBUFLEN];
    char       *buf = sbuf;
    size_t      bufsize1 = (len1 == -1) ? 0 : len1 + 1;
    size_t      bufsize2 = (len2 == -1) ? 0 : len2 + 1;
    const char *arg1n;
    const char *arg2n;
    int         result;
 
    Assert(locale->provider == COLLPROVIDER_LIBC);
 
#ifdef WIN32
    /* check for this case before doing the work for nul-termination */
    if (GetDatabaseEncoding() == PG_UTF8)
        return strncoll_libc_win32_utf8(arg1, len1, arg2, len2, locale);
#endif                          /* WIN32 */
 
    if (bufsize1 + bufsize2 > TEXTBUFLEN)
        buf = palloc(bufsize1 + bufsize2);
 
    /* nul-terminate arguments if necessary */
    if (len1 == -1)
    {
        arg1n = arg1;
    }
    else
    {
        char       *buf1 = buf;
 
        memcpy(buf1, arg1, len1);
        buf1[len1] = '\0';
        arg1n = buf1;
    }
 
    if (len2 == -1)
    {
        arg2n = arg2;
    }
    else
    {
        char       *buf2 = buf + bufsize1;
 
        memcpy(buf2, arg2, len2);
        buf2[len2] = '\0';
        arg2n = buf2;
    }
 
    result = strcoll_l(arg1n, arg2n, locale->info.lt);
 
    if (buf != sbuf)
        pfree(buf);
 
    return result;
}

References Assert, buf, GetDatabaseEncoding(), locale, palloc(), pfree(), PG_UTF8, strcoll_l, and TEXTBUFLEN.

Referenced by pg_strcoll(), and pg_strncoll().

strnxfrm_libc()

size_t strnxfrm_libc	(	char *	dest,
		size_t	destsize,
		const char *	src,
		ssize_t	srclen,
		pg_locale_t	locale
	)

Definition at line 189 of file pg_locale_libc.c.

{
    char        sbuf[TEXTBUFLEN];
    char       *buf = sbuf;
    size_t      bufsize = srclen + 1;
    size_t      result;
 
    Assert(locale->provider == COLLPROVIDER_LIBC);
 
    if (srclen == -1)
        return strxfrm_l(dest, src, destsize, locale->info.lt);
 
    if (bufsize > TEXTBUFLEN)
        buf = palloc(bufsize);
 
    /* nul-terminate argument */
    memcpy(buf, src, srclen);
    buf[srclen] = '\0';
 
    result = strxfrm_l(dest, buf, destsize, locale->info.lt);
 
    if (buf != sbuf)
        pfree(buf);
 
    /* if dest is defined, it should be nul-terminated */
    Assert(result >= destsize || dest[result] == '\0');
 
    return result;
}

References Assert, buf, bufsize, generate_unaccent_rules::dest, locale, palloc(), pfree(), strxfrm_l, and TEXTBUFLEN.

Referenced by pg_strnxfrm(), and pg_strxfrm().

wchar2char()

size_t wchar2char	(	char *	to,
		const wchar_t *	from,
		size_t	tolen,
		pg_locale_t	locale
	)

Definition at line 379 of file pg_locale_libc.c.

{
    size_t      result;
 
    if (tolen == 0)
        return 0;
 
#ifdef WIN32
 
    /*
     * On Windows, the "Unicode" locales assume UTF16 not UTF8 encoding, and
     * for some reason mbstowcs and wcstombs won't do this for us, so we use
     * MultiByteToWideChar().
     */
    if (GetDatabaseEncoding() == PG_UTF8)
    {
        result = WideCharToMultiByte(CP_UTF8, 0, from, -1, to, tolen,
                                     NULL, NULL);
        /* A zero return is failure */
        if (result <= 0)
            result = -1;
        else
        {
            Assert(result <= tolen);
            /* Microsoft counts the zero terminator in the result */
            result--;
        }
    }
    else
#endif                          /* WIN32 */
    if (locale == (pg_locale_t) 0)
    {
        /* Use wcstombs directly for the default locale */
        result = wcstombs(to, from, tolen);
    }
    else
    {
        /* Use wcstombs_l for nondefault locales */
        result = wcstombs_l(to, from, tolen, locale->info.lt);
    }
 
    return result;
}

References Assert, GetDatabaseEncoding(), locale, PG_UTF8, and wcstombs_l().

Referenced by lowerstr_with_len(), str_initcap(), str_tolower(), and str_toupper().

wcstombs_l()

static size_t wcstombs_l ( char *  dest, const wchar_t *  src, size_t  n, locale_t  loc  )

static

Definition at line 351 of file pg_locale_libc.c.

{
#ifdef WIN32
    return _wcstombs_l(dest, src, n, loc);
#else
    size_t      result;
    locale_t    save_locale = uselocale(loc);
 
    result = wcstombs(dest, src, n);
    uselocale(save_locale);
    return result;
#endif
}

References generate_unaccent_rules::dest, and locale_t.

Referenced by wchar2char().