C++ pg_database_encoding_max_length函数代码示例

Datum
show_trgm(PG_FUNCTION_ARGS)
{
	text	   *in = PG_GETARG_TEXT_P(0);
	TRGM	   *trg;
	Datum	   *d;
	ArrayType  *a;
	trgm	   *ptr;
	int			i;

	trg = generate_trgm(VARDATA(in), VARSIZE(in) - VARHDRSZ);
	d = (Datum *) palloc(sizeof(Datum) * (1 + ARRNELEM(trg)));

	for (i = 0, ptr = GETARR(trg); i < ARRNELEM(trg); i++, ptr++)
	{
		text	   *item = (text *) palloc(VARHDRSZ + Max(12, pg_database_encoding_max_length() * 3));

		if (pg_database_encoding_max_length() > 1 && !ISPRINTABLETRGM(ptr))
		{
			snprintf(VARDATA(item), 12, "0x%06x", trgm2int(ptr));
			SET_VARSIZE(item, VARHDRSZ + strlen(VARDATA(item)));
		}
		else
		{
			SET_VARSIZE(item, VARHDRSZ + 3);
			CPTRGM(VARDATA(item), ptr);
		}
		d[i] = PointerGetDatum(item);
	}

	a = construct_array(
						d,
						ARRNELEM(trg),
						TEXTOID,
						-1,
						false,
						'i'
		);

	for (i = 0; i < ARRNELEM(trg); i++)
		pfree(DatumGetPointer(d[i]));

	pfree(d);
	pfree(trg);
	PG_FREE_IF_COPY(in, 0);

	PG_RETURN_POINTER(a);
}

Datum
gbt_bpchar_consistent(PG_FUNCTION_ARGS)
{
	GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
	void	   *query = (void *) DatumGetPointer(PG_DETOAST_DATUM(PG_GETARG_DATUM(1)));
	StrategyNumber strategy = (StrategyNumber) PG_GETARG_UINT16(2);

	/* Oid		subtype = PG_GETARG_OID(3); */
	bool	   *recheck = (bool *) PG_GETARG_POINTER(4);
	bool		retval;
	GBT_VARKEY *key = (GBT_VARKEY *) DatumGetPointer(entry->key);
	GBT_VARKEY_R r = gbt_var_key_readable(key);
	void	   *trim = (void *) DatumGetPointer(DirectFunctionCall1(rtrim1, PointerGetDatum(query)));

	/* All cases served by this function are exact */
	*recheck = false;

	if (tinfo.eml == 0)
	{
		tinfo.eml = pg_database_encoding_max_length();
	}

	retval = gbt_var_consistent(&r, trim, &strategy, GIST_LEAF(entry), &tinfo);
	PG_RETURN_BOOL(retval);
}

TParser *
TParserInit(char *str, int len)
{
	TParser    *prs = (TParser *) palloc0(sizeof(TParser));

	prs->charmaxlen = pg_database_encoding_max_length();
	prs->str = str;
	prs->lenstr = len;

#ifdef TS_USE_WIDE

	/*
	 * Use wide char code only when max encoding length > 1.
	 */

	if (prs->charmaxlen > 1)
	{
		prs->usewide = true;
		prs->wstr = (wchar_t *) palloc(sizeof(wchar_t) * (prs->lenstr+1));
		prs->lenwstr = char2wchar(prs->wstr, prs->str, prs->lenstr);
	}
	else
#endif
		prs->usewide = false;

	prs->state = newTParserPosition(NULL);
	prs->state->state = TPS_Base;

	return prs;
}

int
ora_mb_strlen1(text *str)
{
	int r_len;
	int c;
	char *p;

	r_len = VARSIZE_ANY_EXHDR(str);

	if (pg_database_encoding_max_length() == 1)
		return r_len;

	p = VARDATA_ANY(str);
	c = 0;
	while (r_len > 0)
	{
		int sz;

		sz = _pg_mblen(p);
		p += sz;
		r_len -= sz;
		c += 1;
	}

	return c;
}

Datum
gbt_bpchar_compress(PG_FUNCTION_ARGS)
{

	GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
	GISTENTRY  *retval;

	if (tinfo.eml == 0)
	{
		tinfo.eml = pg_database_encoding_max_length();
	}

	if (entry->leafkey)
	{

		Datum		d = DirectFunctionCall1(rtrim1, entry->key);
		GISTENTRY	trim;

		gistentryinit(trim, d,
					  entry->rel, entry->page,
					  entry->offset, VARSIZE(DatumGetPointer(d)), TRUE);
		retval = gbt_var_compress(&trim, &tinfo);
	}
	else
		retval = entry;

	PG_RETURN_POINTER(retval);
}

/*
 * regexp_fixed_prefix - extract fixed prefix, if any, for a regexp
 *
 * The result is NULL if there is no fixed prefix, else a palloc'd string.
 * If it is an exact match, not just a prefix, *exact is returned as TRUE.
 */
char *
regexp_fixed_prefix(text *text_re, bool case_insensitive, Oid collation,
					bool *exact)
{
	char	   *result;
	regex_t    *re;
	int			cflags;
	int			re_result;
	pg_wchar   *str;
	size_t		slen;
	size_t		maxlen;
	char		errMsg[100];

	*exact = false;				/* default result */

	/* Compile RE */
	cflags = REG_ADVANCED;
	if (case_insensitive)
		cflags |= REG_ICASE;

	re = RE_compile_and_cache(text_re, cflags, collation);

	/* Examine it to see if there's a fixed prefix */
	re_result = pg_regprefix(re, &str, &slen);

	switch (re_result)
	{
		case REG_NOMATCH:
			return NULL;

		case REG_PREFIX:
			/* continue with wchar conversion */
			break;

		case REG_EXACT:
			*exact = true;
			/* continue with wchar conversion */
			break;

		default:
			/* re failed??? */
			CHECK_FOR_INTERRUPTS();
			pg_regerror(re_result, re, errMsg, sizeof(errMsg));
			ereport(ERROR,
					(errcode(ERRCODE_INVALID_REGULAR_EXPRESSION),
					 errmsg("regular expression failed: %s", errMsg)));
			break;
	}

	/* Convert pg_wchar result back to database encoding */
	maxlen = pg_database_encoding_max_length() * slen + 1;
	result = (char *) palloc(maxlen);
	slen = pg_wchar2mb_with_len(str, result, slen);
	Assert(slen < maxlen);

	free(str);

	return result;
}

/*
 * Guard against possible overflow in the palloc requests below.  (We
 * don't worry about the additive constants, since palloc can detect
 * requests that are a little above MaxAllocSize --- we just need to
 * prevent integer overflow in the multiplications.)
 */
static void
protect_out_of_mem(int slen)
{
	if ((Size) (slen / 2) >= (MaxAllocSize / (sizeof(trgm) * 3)) ||
		(Size) slen >= (MaxAllocSize / pg_database_encoding_max_length()))
		ereport(ERROR,
				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
				 errmsg("out of memory")));
}

/*
 * Make array of trigrams without sorting and removing duplicate items.
 *
 * trg: where to return the array of trigrams.
 * str: source string, of length slen bytes.
 * bounds: where to return bounds of trigrams (if needed).
 *
 * Returns length of the generated array.
 */
static int
generate_trgm_only(trgm *trg, char *str, int slen, TrgmBound *bounds)
{
	trgm	   *tptr;
	char	   *buf;
	int			charlen,
				bytelen;
	char	   *bword,
			   *eword;

	if (slen + LPADDING + RPADDING < 3 || slen == 0)
		return 0;

	tptr = trg;

	/* Allocate a buffer for case-folded, blank-padded words */
	buf = (char *) palloc(slen * pg_database_encoding_max_length() + 4);

	if (LPADDING > 0)
	{
		*buf = ' ';
		if (LPADDING > 1)
			*(buf + 1) = ' ';
	}

	eword = str;
	while ((bword = find_word(eword, slen - (eword - str), &eword, &charlen)) != NULL)
	{
#ifdef IGNORECASE
		bword = lowerstr_with_len(bword, eword - bword);
		bytelen = strlen(bword);
#else
		bytelen = eword - bword;
#endif

		memcpy(buf + LPADDING, bword, bytelen);

#ifdef IGNORECASE
		pfree(bword);
#endif

		buf[LPADDING + bytelen] = ' ';
		buf[LPADDING + bytelen + 1] = ' ';

		/* Calculate trigrams marking their bounds if needed */
		if (bounds)
			bounds[tptr - trg] |= TRGM_BOUND_LEFT;
		tptr = make_trigrams(tptr, buf, bytelen + LPADDING + RPADDING,
							 charlen + LPADDING + RPADDING);
		if (bounds)
			bounds[tptr - trg - 1] |= TRGM_BOUND_RIGHT;
	}

	pfree(buf);

	return tptr - trg;
}

/* Generic for all cases not requiring inline case-folding */
static inline int
GenericMatchText(char *s, int slen, char *p, int plen)
{
	if (pg_database_encoding_max_length() == 1)
		return SB_MatchText(s, slen, p, plen, 0, true);
	else if (GetDatabaseEncoding() == PG_UTF8)
		return UTF8_MatchText(s, slen, p, plen, 0, true);
	else
		return MB_MatchText(s, slen, p, plen, 0, true);
}

Datum
gbt_text_compress(PG_FUNCTION_ARGS)
{
	GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);

	if (tinfo.eml == 0)
	{
		tinfo.eml = pg_database_encoding_max_length();
	}

	PG_RETURN_POINTER(gbt_var_compress(entry, &tinfo));
}

/*
 * like_escape() --- given a pattern and an ESCAPE string,
 * convert the pattern to use Postgres' standard backslash escape convention.
 */
Datum
like_escape(PG_FUNCTION_ARGS)
{
	text	   *pat = PG_GETARG_TEXT_PP(0);
	text	   *esc = PG_GETARG_TEXT_PP(1);
	text	   *result;

	if (pg_database_encoding_max_length() == 1)
		result = SB_do_like_escape(pat, esc);
	else
		result = MB_do_like_escape(pat, esc);

	PG_RETURN_TEXT_P(result);
}

Datum
bpcharlen(PG_FUNCTION_ARGS)
{
	BpChar	   *arg = PG_GETARG_BPCHAR_P(0);
	int			len;

	/* get number of bytes, ignoring trailing spaces */
	len = bcTruelen(arg);

	/* in multibyte encoding, convert to number of characters */
	if (pg_database_encoding_max_length() != 1)
		len = pg_mbstrlen_with_len(VARDATA(arg), len);

	PG_RETURN_INT32(len);
}

Datum
orafce_bpcharlen(PG_FUNCTION_ARGS)
{
	BpChar     *arg = PG_GETARG_BPCHAR_PP(0);
	int         len;

	/* byte-length of the argument (trailing spaces not ignored) */
	len = VARSIZE_ANY_EXHDR(arg);

	/* in multibyte encoding, convert to number of characters */
	if (pg_database_encoding_max_length() != 1)
		len = pg_mbstrlen_with_len(VARDATA_ANY(arg), len);

	PG_RETURN_INT32(len);
}

/*
 * Initializes parser for the input string. If oprisdelim is set, the
 * following characters are treated as delimiters in addition to whitespace:
 * ! | & ( )
 */
TSVectorParseState
init_tsvector_parser(char *input, bool oprisdelim, bool is_tsquery)
{
	TSVectorParseState state;

	state = (TSVectorParseState) palloc(sizeof(struct TSVectorParseStateData));
	state->prsbuf = input;
	state->bufstart = input;
	state->len = 32;
	state->word = (char *) palloc(state->len);
	state->eml = pg_database_encoding_max_length();
	state->oprisdelim = oprisdelim;
	state->is_tsquery = is_tsquery;

	return state;
}

/* returns the length (counted in wchars) of a multibyte string */
int
pg_mbstrlen(const char *mbstr)
{
	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;
}