C++ PQmblen函数代码示例

/*
 * Advance the given char pointer over white space and SQL comments.
 */
static const char *
skip_white_space(const char *query)
{
	int			cnestlevel = 0; /* slash-star comment nest level */

	while (*query)
	{
		int			mblen = PQmblen(query, pset.encoding);

		/*
		 * Note: we assume the encoding is a superset of ASCII, so that for
		 * example "query[0] == '/'" is meaningful.  However, we do NOT assume
		 * that the second and subsequent bytes of a multibyte character
		 * couldn't look like ASCII characters; so it is critical to advance
		 * by mblen, not 1, whenever we haven't exactly identified the
		 * character we are skipping over.
		 */
		if (isspace((unsigned char) *query))
			query += mblen;
		else if (query[0] == '/' && query[1] == '*')
		{
			cnestlevel++;
			query += 2;
		}
		else if (cnestlevel > 0 && query[0] == '*' && query[1] == '/')
		{
			cnestlevel--;
			query += 2;
		}
		else if (cnestlevel == 0 && query[0] == '-' && query[1] == '-')
		{
			query += 2;

			/*
			 * We have to skip to end of line since any slash-star inside the
			 * -- comment does NOT start a slash-star comment.
			 */
			while (*query)
			{
				if (*query == '\n')
				{
					query++;
					break;
				}
				query += PQmblen(query, pset.encoding);
			}
		}
		else if (cnestlevel > 0)
			query += mblen;
		else
			break;				/* found first token */
	}

	return query;
}

/*
 * Check whether the specified command is a SELECT (or VALUES).
 */
static bool
is_select_command(const char *query)
{
	int			wordlen;

	/*
	 * First advance over any whitespace, comments and left parentheses.
	 */
	for (;;)
	{
		query = skip_white_space(query);
		if (query[0] == '(')
			query++;
		else
			break;
	}

	/*
	 * Check word length (since "selectx" is not "select").
	 */
	wordlen = 0;
	while (isalpha((unsigned char) query[wordlen]))
		wordlen += PQmblen(&query[wordlen], pset.encoding);

	if (wordlen == 6 && pg_strncasecmp(query, "select", 6) == 0)
		return true;

	if (wordlen == 6 && pg_strncasecmp(query, "values", 6) == 0)
		return true;

	return false;
}

/*
 * strip_quotes
 *
 * Remove quotes from the string at *source.  Leading and trailing occurrences
 * of 'quote' are removed; embedded double occurrences of 'quote' are reduced
 * to single occurrences; if 'escape' is not 0 then 'escape' removes special
 * significance of next character.
 *
 * Note that the source string is overwritten in-place.
 */
static void
strip_quotes(char *source, char quote, char escape, int encoding)
{
	char	   *src;
	char	   *dst;

	psql_assert(source);
	psql_assert(quote);

	src = dst = source;

	if (*src && *src == quote)
		src++;					/* skip leading quote */

	while (*src)
	{
		char		c = *src;
		int			i;

		if (c == quote && src[1] == '\0')
			break;				/* skip trailing quote */
		else if (c == quote && src[1] == quote)
			src++;				/* process doubled quote */
		else if (c == escape && src[1] != '\0')
			src++;				/* process escaped character */

		i = PQmblen(src, encoding);
		while (i--)
			*dst++ = *src++;
	}

	*dst = '\0';
}

/*
 * quote_if_needed
 *
 * Opposite of strip_quotes().  If "source" denotes itself literally without
 * quoting or escaping, returns NULL.  Otherwise, returns a malloc'd copy with
 * quoting and escaping applied:
 *
 * source -			string to parse
 * entails_quote -	any of these present?  need outer quotes
 * quote -			doubled within string, affixed to both ends
 * escape -			doubled within string
 * encoding -		the active character-set encoding
 *
 * Do not use this as a substitute for PQescapeStringConn().  Use it for
 * strings to be parsed by strtokx() or psql_scan_slash_option().
 */
char *
quote_if_needed(const char *source, const char *entails_quote,
                char quote, char escape, int encoding)
{
    const char *src;
    char	   *ret;
    char	   *dst;
    bool		need_quotes = false;
    
    Assert(source != NULL);
    Assert(quote != '\0');
    
    src = source;
    dst = ret = pg_malloc(2 * strlen(src) + 3); /* excess */
    
    *dst++ = quote;
    
    while (*src)
    {
        char		c = *src;
        int			i;
        
        if (c == quote)
        {
            need_quotes = true;
            *dst++ = quote;
        }
        else if (c == escape)
        {
            need_quotes = true;
            *dst++ = escape;
        }
        else if (strchr(entails_quote, c))
            need_quotes = true;
        
        i = PQmblen(src, encoding);
        while (i--)
            *dst++ = *src++;
    }
    
    *dst++ = quote;
    *dst = '\0';
    
    if (!need_quotes)
    {
        free(ret);
        ret = NULL;
    }
    
    return ret;
}

//.........这里部分代码省略.........
			/* Found schema/name separator, move current pattern to schema */
			resetPQExpBuffer(&schemabuf);
			appendPQExpBufferStr(&schemabuf, namebuf.data);
			resetPQExpBuffer(&namebuf);
			appendPQExpBufferStr(&namebuf, "^(");
			cp++;
		}
		else if (ch == '$')
		{
			/*
			 * Dollar is always quoted, whether inside quotes or not. The
			 * reason is that it's allowed in SQL identifiers, so there's a
			 * significant use-case for treating it literally, while because
			 * we anchor the pattern automatically there is no use-case for
			 * having it possess its regexp meaning.
			 */
			appendPQExpBufferStr(&namebuf, "\\$");
			cp++;
		}
		else
		{
			/*
			 * Ordinary data character, transfer to pattern
			 *
			 * Inside double quotes, or at all times if force_escape is true,
			 * quote regexp special characters with a backslash to avoid
			 * regexp errors.  Outside quotes, however, let them pass through
			 * as-is; this lets knowledgeable users build regexp expressions
			 * that are more powerful than shell-style patterns.
			 */
			if ((inquotes || force_escape) &&
				strchr("|*+?()[]{}.^$\\", ch))
				appendPQExpBufferChar(&namebuf, '\\');
			i = PQmblen(cp, encoding);
			while (i-- && *cp)
			{
				appendPQExpBufferChar(&namebuf, *cp);
				cp++;
			}
		}
	}

	/*
	 * Now decide what we need to emit.  Note there will be a leading "^(" in
	 * the patterns in any case.
	 */
	if (namebuf.len > 2)
	{
		/* We have a name pattern, so constrain the namevar(s) */

		appendPQExpBufferStr(&namebuf, ")$");
		/* Optimize away a "*" pattern */
		if (strcmp(namebuf.data, "^(.*)$") != 0)
		{
			WHEREAND();
			if (altnamevar)
			{
				appendPQExpBuffer(buf, "(%s ~ ", namevar);
				appendStringLiteralConn(buf, namebuf.data, conn);
				appendPQExpBuffer(buf, "\n        OR %s ~ ", altnamevar);
				appendStringLiteralConn(buf, namebuf.data, conn);
				appendPQExpBufferStr(buf, ")\n");
			}
			else
			{
				appendPQExpBuffer(buf, "%s ~ ", namevar);

/*
 * Convert a string value to an SQL string literal and append it to
 * the given buffer.  We assume the specified client_encoding and
 * standard_conforming_strings settings.
 *
 * This is essentially equivalent to libpq's PQescapeStringInternal,
 * except for the output buffer structure.	We need it in situations
 * where we do not have a PGconn available.  Where we do,
 * appendStringLiteralConn is a better choice.
 */
void
appendStringLiteral(PQExpBuffer buf, const char *str,
					int encoding, bool std_strings)
{
	size_t		length = strlen(str);
	const char *source = str;
	char	   *target;

	if (!enlargePQExpBuffer(buf, 2 * length + 2))
		return;

	target = buf->data + buf->len;
	*target++ = '\'';

	while (*source != '\0')
	{
		char		c = *source;
		int			len;
		int			i;

		/* Fast path for plain ASCII */
		if (!IS_HIGHBIT_SET(c))
		{
			/* Apply quoting if needed */
			if (SQL_STR_DOUBLE(c, !std_strings))
				*target++ = c;
			/* Copy the character */
			*target++ = c;
			source++;
			continue;
		}

		/* Slow path for possible multibyte characters */
		len = PQmblen(source, encoding);

		/* Copy the character */
		for (i = 0; i < len; i++)
		{
			if (*source == '\0')
				break;
			*target++ = *source++;
		}

		/*
		 * If we hit premature end of string (ie, incomplete multibyte
		 * character), try to pad out to the correct length with spaces. We
		 * may not be able to pad completely, but we will always be able to
		 * insert at least one pad space (since we'd not have quoted a
		 * multibyte character).  This should be enough to make a string that
		 * the server will error out on.
		 */
		if (i < len)
		{
			char	   *stop = buf->data + buf->maxlen - 2;

			for (; i < len; i++)
			{
				if (target >= stop)
					break;
				*target++ = ' ';
			}
			break;
		}
	}

	/* Write the terminating quote and NUL character. */
	*target++ = '\'';
	*target = '\0';

	buf->len = target - buf->data;
}

static void
do_field(const PQprintOpt *po, const PGresult *res,
		 const int i, const int j, const int fs_len,
		 char **fields,
		 const int nFields, char const ** fieldNames,
		 unsigned char *fieldNotNum, int *fieldMax,
		 const int fieldMaxLen, FILE *fout)
{
	const char *pval,
			   *p;
	int			plen;
	bool		skipit;

	plen = PQgetlength(res, i, j);
	pval = PQgetvalue(res, i, j);

	if (plen < 1 || !pval || !*pval)
	{
		if (po->align || po->expanded)
			skipit = true;
		else
		{
			skipit = false;
			goto efield;
		}
	}
	else
		skipit = false;

	if (!skipit)
	{
		if (po->align && !fieldNotNum[j])
		{
			/* Detect whether field contains non-numeric data */
			char		ch = '0';

			for (p = pval; *p; p += PQmblen(p, res->client_encoding))
			{
				ch = *p;
				if (!((ch >= '0' && ch <= '9') ||
					  ch == '.' ||
					  ch == 'E' ||
					  ch == 'e' ||
					  ch == ' ' ||
					  ch == '-'))
				{
					fieldNotNum[j] = 1;
					break;
				}
			}

			/*
			 * Above loop will believe E in first column is numeric; also, we
			 * insist on a digit in the last column for a numeric. This test
			 * is still not bulletproof but it handles most cases.
			 */
			if (*pval == 'E' || *pval == 'e' ||
				!(ch >= '0' && ch <= '9'))
				fieldNotNum[j] = 1;
		}

		if (!po->expanded && (po->align || po->html3))
		{
			if (plen > fieldMax[j])
				fieldMax[j] = plen;
			if (!(fields[i * nFields + j] = (char *) malloc(plen + 1)))
			{
				fprintf(stderr, libpq_gettext("out of memory\n"));
				abort();
			}
			strcpy(fields[i * nFields + j], pval);
		}
		else
		{
			if (po->expanded)
			{
				if (po->html3)
					fprintf(fout,
							"<tr><td align=\"left\"><b>%s</b></td>"
							"<td align=\"%s\">%s</td></tr>\n",
							fieldNames[j],
							fieldNotNum[j] ? "left" : "right",
							pval);
				else
				{
					if (po->align)
						fprintf(fout,
								"%-*s%s %s\n",
								fieldMaxLen - fs_len, fieldNames[j],
								po->fieldSep,
								pval);
					else
						fprintf(fout,
								"%s%s%s\n",
								fieldNames[j], po->fieldSep, pval);
				}
			}
			else
			{
				if (!po->html3)
//.........这里部分代码省略.........

/*
 * Check whether a command is one of those for which we should NOT start
 * a new transaction block (ie, send a preceding BEGIN).
 *
 * These include the transaction control statements themselves, plus
 * certain statements that the backend disallows inside transaction blocks.
 */
static bool
command_no_begin(const char *query)
{
	int			wordlen;

	/*
	 * First we must advance over any whitespace and comments.
	 */
	query = skip_white_space(query);

	/*
	 * Check word length (since "beginx" is not "begin").
	 */
	wordlen = 0;
	while (isalpha((unsigned char) query[wordlen]))
		wordlen += PQmblen(&query[wordlen], pset.encoding);

	/*
	 * Transaction control commands.  These should include every keyword that
	 * gives rise to a TransactionStmt in the backend grammar, except for the
	 * savepoint-related commands.
	 *
	 * (We assume that START must be START TRANSACTION, since there is
	 * presently no other "START foo" command.)
	 */
	if (wordlen == 5 && pg_strncasecmp(query, "abort", 5) == 0)
		return true;
	if (wordlen == 5 && pg_strncasecmp(query, "begin", 5) == 0)
		return true;
	if (wordlen == 5 && pg_strncasecmp(query, "start", 5) == 0)
		return true;
	if (wordlen == 6 && pg_strncasecmp(query, "commit", 6) == 0)
		return true;
	if (wordlen == 3 && pg_strncasecmp(query, "end", 3) == 0)
		return true;
	if (wordlen == 8 && pg_strncasecmp(query, "rollback", 8) == 0)
		return true;
	if (wordlen == 7 && pg_strncasecmp(query, "prepare", 7) == 0)
	{
		/* PREPARE TRANSACTION is a TC command, PREPARE foo is not */
		query += wordlen;

		query = skip_white_space(query);

		wordlen = 0;
		while (isalpha((unsigned char) query[wordlen]))
			wordlen += PQmblen(&query[wordlen], pset.encoding);

		if (wordlen == 11 && pg_strncasecmp(query, "transaction", 11) == 0)
			return true;
		return false;
	}

	/*
	 * Commands not allowed within transactions.  The statements checked for
	 * here should be exactly those that call PreventTransactionChain() in the
	 * backend.
	 */
	if (wordlen == 6 && pg_strncasecmp(query, "vacuum", 6) == 0)
		return true;
	if (wordlen == 7 && pg_strncasecmp(query, "cluster", 7) == 0)
	{
		/* CLUSTER with any arguments is allowed in transactions */
		query += wordlen;

		query = skip_white_space(query);

		if (isalpha((unsigned char) query[0]))
			return false;		/* has additional words */
		return true;			/* it's CLUSTER without arguments */
	}

	if (wordlen == 6 && pg_strncasecmp(query, "create", 6) == 0)
	{
		query += wordlen;

		query = skip_white_space(query);

		wordlen = 0;
		while (isalpha((unsigned char) query[wordlen]))
			wordlen += PQmblen(&query[wordlen], pset.encoding);

		if (wordlen == 8 && pg_strncasecmp(query, "database", 8) == 0)
			return true;
		if (wordlen == 10 && pg_strncasecmp(query, "tablespace", 10) == 0)
			return true;

		/* CREATE [UNIQUE] INDEX CONCURRENTLY isn't allowed in xacts */
		if (wordlen == 6 && pg_strncasecmp(query, "unique", 6) == 0)
		{
			query += wordlen;

			query = skip_white_space(query);
//.........这里部分代码省略.........

//.........这里部分代码省略.........
		if (*p != '\0')
		{
			if (!strchr(whitespace, *p))
				memmove(p + 1, p, strlen(p) + 1);
			*p = '\0';
			string = p + 1;
		}
		else
		{
			/* at end of string, so no extra work */
			string = p;
		}

		return start;
	}

	/* check for E string */
	p = start;
	if (e_strings &&
		(*p == 'E' || *p == 'e') &&
		p[1] == '\'')
	{
		quote = "'";
		escape = '\\';			/* if std strings before, not any more */
		p++;
	}

	/* test if quoting character */
	if (quote && strchr(quote, *p))
	{
		/* okay, we have a quoted token, now scan for the closer */
		char		thisquote = *p++;

		for (; *p; p += PQmblen(p, encoding))
		{
			if (*p == escape && p[1] != '\0')
				p++;			/* process escaped anything */
			else if (*p == thisquote && p[1] == thisquote)
				p++;			/* process doubled quote */
			else if (*p == thisquote)
			{
				p++;			/* skip trailing quote */
				break;
			}
		}

		/*
		 * If not at end of string, we need to insert a null to terminate the
		 * returned token.	See notes above.
		 */
		if (*p != '\0')
		{
			if (!strchr(whitespace, *p))
				memmove(p + 1, p, strlen(p) + 1);
			*p = '\0';
			string = p + 1;
		}
		else
		{
			/* at end of string, so no extra work */
			string = p;
		}

		/* Clean up the token if caller wants that */
		if (del_quotes)
			strip_quotes(start, thisquote, escape, encoding);

/**
 * @brief Performs data loading.
 *
 * Invokes pg_bulkload() user-defined function with given parameters
 * in single transaction.
 *
 * @return exitcode (always 0).
 */
static int
LoaderLoadMain(List *options)
{
	PGresult	   *res;
	const char	   *params[1];
	StringInfoData	buf;
	int				encoding;
	int				errors;
	ListCell	   *cell;

	if (options == NIL)
		ereport(ERROR,
			(errcode(EXIT_FAILURE),
			 errmsg("requires control file or command line options")));

	initStringInfo(&buf);
	reconnect(ERROR);
	encoding = PQclientEncoding(connection);

	elog(NOTICE, "BULK LOAD START");

	/* form options as text[] */
	appendStringInfoString(&buf, "{\"");
	foreach (cell, options)
	{
		const char *item = lfirst(cell);

		if (buf.len > 2)
			appendStringInfoString(&buf, "\",\"");

		/* escape " and \ */
		while (*item)
		{
			if (*item == '"' || *item == '\\')
			{
				appendStringInfoChar(&buf, '\\');
				appendStringInfoChar(&buf, *item);
				item++;
			}
			else if (!IS_HIGHBIT_SET(*item))
			{
				appendStringInfoChar(&buf, *item);
				item++;
			}
			else
			{
				int	n = PQmblen(item, encoding);
				appendBinaryStringInfo(&buf, item, n);
				item += n;
			}
		}
	}
	appendStringInfoString(&buf, "\"}");

	command("BEGIN", 0, NULL);
	params[0] = buf.data;
	res = execute("SELECT * FROM pg_bulkload($1)", 1, params);
	if (PQresultStatus(res) == PGRES_COPY_IN)
	{
		PQclear(res);
		res = RemoteLoad(connection, stdin, type_binary);
		if (PQresultStatus(res) != PGRES_TUPLES_OK)
			elog(ERROR, "copy failed: %s", PQerrorMessage(connection));
	}
	command("COMMIT", 0, NULL);

	errors = atoi(PQgetvalue(res, 0, 2)) +	/* parse errors */
			 atoi(PQgetvalue(res, 0, 3));	/* duplicate errors */

	elog(NOTICE, "BULK LOAD END\n"
				 "\t%s Rows skipped.\n"
				 "\t%s Rows successfully loaded.\n"
				 "\t%s Rows not loaded due to parse errors.\n"
				 "\t%s Rows not loaded due to duplicate errors.\n"
				 "\t%s Rows replaced with new rows.",
				 PQgetvalue(res, 0, 0), PQgetvalue(res, 0, 1),
				 PQgetvalue(res, 0, 2), PQgetvalue(res, 0, 3),
				 PQgetvalue(res, 0, 4));
	PQclear(res);

	disconnect();
	termStringInfo(&buf);

	if (errors > 0)
	{
		elog(WARNING, "some rows were not loaded due to errors.");
		return E_PG_USER;
	}
	else
		return 0;	/* succeeded without errors */
}

/*
 * Parse "arg", which is a string of column IDs separated by "separator".
 *
 * Each column ID can be:
 * - a number from 1 to PQnfields(res)
 * - an unquoted column name matching (case insensitively) one of PQfname(res,...)
 * - a quoted column name matching (case sensitively) one of PQfname(res,...)
 *
 * If max_columns > 0, it is the max number of column IDs allowed.
 *
 * On success, return number of column IDs found (possibly 0), and return a
 * malloc'd array of the matching column numbers of "res" into *col_numbers.
 *
 * On failure, return -1 and set *col_numbers to NULL.
 */
static int
parseColumnRefs(const char *arg,
				const PGresult *res,
				int **col_numbers,
				int max_columns,
				char separator)
{
	const char *p = arg;
	char		c;
	int			num_cols = 0;

	*col_numbers = NULL;
	while ((c = *p) != '\0')
	{
		const char *field_start = p;
		bool		quoted_field = false;

		/* first char */
		if (c == '"')
		{
			quoted_field = true;
			p++;
		}

		while ((c = *p) != '\0')
		{
			if (c == separator && !quoted_field)
				break;
			if (c == '"')		/* end of field or embedded double quote */
			{
				p++;
				if (*p == '"')
				{
					if (quoted_field)
					{
						p++;
						continue;
					}
				}
				else if (quoted_field && *p == separator)
					break;
			}
			if (*p)
				p += PQmblen(p, pset.encoding);
		}

		if (p != field_start)
		{
			char   *col_name;
			int		col_num;

			/* enforce max_columns limit */
			if (max_columns > 0 && num_cols == max_columns)
			{
				psql_error(_("No more than %d column references expected\n"),
						   max_columns);
				goto errfail;
			}
			/* look up the column and add its index into *col_numbers */
			col_name = pg_malloc(p - field_start + 1);
			memcpy(col_name, field_start, p - field_start);
			col_name[p - field_start] = '\0';
			col_num = indexOfColumn(col_name, res);
			pg_free(col_name);
			if (col_num < 0)
				goto errfail;
			*col_numbers = (int *) pg_realloc(*col_numbers,
											  (num_cols + 1) * sizeof(int));
			(*col_numbers)[num_cols++] = col_num;
		}
		else
		{
			psql_error(_("Empty column reference\n"));
			goto errfail;
		}

		if (*p)
			p += PQmblen(p, pset.encoding);
	}
	return num_cols;

errfail:
	pg_free(*col_numbers);
	*col_numbers = NULL;
	return -1;
//.........这里部分代码省略.........