psqlscan.l

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

	{
		case LEXRES_EOL:		/* end of input */
			switch (state->start_state)
			{
				case INITIAL:
					if (state->paren_depth > 0)
					{
						result = PSCAN_INCOMPLETE;
						*prompt = PROMPT_PAREN;
					}
					else if (query_buf->len > 0)
					{
						result = PSCAN_EOL;
						*prompt = PROMPT_CONTINUE;
					}
					else
					{
						/* never bother to send an empty buffer */
						result = PSCAN_INCOMPLETE;
						*prompt = PROMPT_READY;
					}
					break;
				case xb:
					result = PSCAN_INCOMPLETE;
					*prompt = PROMPT_SINGLEQUOTE;
					break;
				case xc:
					result = PSCAN_INCOMPLETE;
					*prompt = PROMPT_COMMENT;
					break;
				case xd:
					result = PSCAN_INCOMPLETE;
					*prompt = PROMPT_DOUBLEQUOTE;
					break;
				case xh:
					result = PSCAN_INCOMPLETE;
					*prompt = PROMPT_SINGLEQUOTE;
					break;
				case xq:
					result = PSCAN_INCOMPLETE;
					*prompt = PROMPT_SINGLEQUOTE;
					break;
				case xdolq:
					result = PSCAN_INCOMPLETE;
					*prompt = PROMPT_DOLLARQUOTE;
					break;
				default:
					/* can't get here */
					fprintf(stderr, "invalid YY_START\n");
					exit(1);
			}
			break;
		case LEXRES_SEMI:		/* semicolon */
			result = PSCAN_SEMICOLON;
			*prompt = PROMPT_READY;
			break;
		case LEXRES_BACKSLASH:	/* backslash */
			result = PSCAN_BACKSLASH;
			*prompt = PROMPT_READY;
			break;
		default:
			/* can't get here */
			fprintf(stderr, "invalid yylex result\n");
			exit(1);
	}

	return result;
}

/*
 * Clean up after scanning a string.  This flushes any unread input and
 * releases resources (but not the PsqlScanState itself).  Note however
 * that this does not reset the lexer scan state; that can be done by
 * psql_scan_reset(), which is an orthogonal operation.
 *
 * It is legal to call this when not scanning anything (makes it easier
 * to deal with error recovery).
 */
void
psql_scan_finish(PsqlScanState state)
{
	/* Drop any incomplete variable expansions. */
	while (state->buffer_stack != NULL)
	{
		StackElem  *stackelem = state->buffer_stack;

		state->buffer_stack = stackelem->next;
		yy_delete_buffer(stackelem->buf);
		free(stackelem->bufstring);
		if (stackelem->origstring)
			free(stackelem->origstring);
		free(stackelem);
	}

	/* Done with the outer scan buffer, too */
	if (state->scanbufhandle)
		yy_delete_buffer(state->scanbufhandle);
	state->scanbufhandle = NULL;
	if (state->scanbuf)
		free(state->scanbuf);
	state->scanbuf = NULL;
}

/*
 * Reset lexer scanning state to start conditions.  This is appropriate
 * for executing \r psql commands (or any other time that we discard the
 * prior contents of query_buf).  It is not, however, necessary to do this
 * when we execute and clear the buffer after getting a PSCAN_SEMICOLON or
 * PSCAN_EOL scan result, because the scan state must be INITIAL when those
 * conditions are returned.
 *
 * Note that this is unrelated to flushing unread input; that task is
 * done by psql_scan_finish().
 */
void
psql_scan_reset(PsqlScanState state)
{
	state->start_state = INITIAL;
	state->paren_depth = 0;
	state->xcdepth = 0;			/* not really necessary */
	if (state->dolqstart)
		free(state->dolqstart);
	state->dolqstart = NULL;
}

/*
 * Return true if lexer is currently in an "inside quotes" state.
 *
 * This is pretty grotty but is needed to preserve the old behavior
 * that mainloop.c drops blank lines not inside quotes without even
 * echoing them.
 */
bool
psql_scan_in_quote(PsqlScanState state)
{
	return state->start_state != INITIAL;
}

/*
 * Scan the command name of a psql backslash command.  This should be called
 * after psql_scan() returns PSCAN_BACKSLASH.  It is assumed that the input
 * has been consumed through the leading backslash.
 *
 * The return value is a malloc'd copy of the command name, as parsed off
 * from the input.
 */
char *
psql_scan_slash_command(PsqlScanState state)
{
	PQExpBufferData mybuf;
	int			lexresult;

	/* Must be scanning already */
	psql_assert(state->scanbufhandle);

	/* Build a local buffer that we'll return the data of */
	initPQExpBuffer(&mybuf);

	/* Set up static variables that will be used by yylex */
	cur_state = state;
	output_buf = &mybuf;

	if (state->buffer_stack != NULL)
		yy_switch_to_buffer(state->buffer_stack->buf);
	else
		yy_switch_to_buffer(state->scanbufhandle);

	BEGIN(xslashcmd);

	/* And lex. */
	lexresult = yylex();

	/* There are no possible errors in this lex state... */

	return mybuf.data;
}

/*
 * Parse off the next argument for a backslash command, and return it as a
 * malloc'd string.  If there are no more arguments, returns NULL.
 *
 * type tells what processing, if any, to perform on the option string;
 * for example, if it's a SQL identifier, we want to downcase any unquoted
 * letters.
 *
 * if quote is not NULL, *quote is set to 0 if no quoting was found, else
 * the quote symbol.
 *
 * if semicolon is true, unquoted trailing semicolon(s) that would otherwise
 * be taken as part of the option string will be stripped.
 *
 * NOTE: the only possible syntax errors for backslash options are unmatched
 * quotes, which are detected when we run out of input.  Therefore, on a
 * syntax error we just throw away the string and return NULL; there is no
 * need to worry about flushing remaining input.
 */
char *
psql_scan_slash_option(PsqlScanState state,
					   enum slash_option_type type,
					   char *quote,
					   bool semicolon)
{
	PQExpBufferData mybuf;
	int			lexresult;
	char		local_quote;
	bool		badarg;

	/* Must be scanning already */
	psql_assert(state->scanbufhandle);

	if (quote == NULL)
		quote = &local_quote;
	*quote = 0;

	/* Build a local buffer that we'll return the data of */
	initPQExpBuffer(&mybuf);

	/* Set up static variables that will be used by yylex */
	cur_state = state;
	output_buf = &mybuf;
	option_type = type;
	option_quote = quote;

	if (state->buffer_stack != NULL)
		yy_switch_to_buffer(state->buffer_stack->buf);
	else
		yy_switch_to_buffer(state->scanbufhandle);

	if (type == OT_WHOLE_LINE)
		BEGIN(xslashwholeline);
	else
		BEGIN(xslasharg);

	/* And lex. */
	lexresult = yylex();

	/*
	 * Check the lex result: we should have gotten back either LEXRES_OK
	 * or LEXRES_EOL (the latter indicating end of string).  If we were inside
	 * a quoted string, as indicated by YY_START, EOL is an error.
	 */
	psql_assert(lexresult == LEXRES_EOL || lexresult == LEXRES_OK);
	badarg = false;
	switch (YY_START)
	{
		case xslasharg:
			/* empty arg, or possibly a psql variable substitution */
			break;
		case xslashquote:
			if (lexresult != LEXRES_OK)
				badarg = true;		/* hit EOL not ending quote */
			break;
		case xslashbackquote:
			if (lexresult != LEXRES_OK)
				badarg = true;		/* hit EOL not ending quote */
			else
			{
				/* Perform evaluation of backticked command */
				char	   *cmd = mybuf.data;
				FILE	   *fd;
				bool		error = false;
				PQExpBufferData output;
				char		buf[512];
				size_t		result;

				fd = popen(cmd, PG_BINARY_R);
				if (!fd)
				{
					psql_error("%s: %s\n", cmd, strerror(errno));
					error = true;
				}

				initPQExpBuffer(&output);

				if (!error)
				{
					do
					{
						result = fread(buf, 1, sizeof(buf), fd);
						if (ferror(fd))
						{
							psql_error("%s: %s\n", cmd, strerror(errno));
							error = true;
							break;
						}
						appendBinaryPQExpBuffer(&output, buf, result);
					} while (!feof(fd));
				}

				if (fd && pclose(fd) == -1)
				{
					psql_error("%s: %s\n", cmd, strerror(errno));
					error = true;
				}

				/* Now done with cmd, transfer result to mybuf */
				resetPQExpBuffer(&mybuf);

				if (!error)
				{
					/* strip any trailing newline */
					if (output.len > 0 &&
						output.data[output.len - 1] == '\n')
						output.len--;
					appendBinaryPQExpBuffer(&mybuf, output.data, output.len);
				}

				termPQExpBuffer(&output);
			}
			break;
		case xslashdefaultarg:
			/* Strip any trailing semi-colons if requested */
			if (semicolon)
			{
				while (mybuf.len > 0 &&
					   mybuf.data[mybuf.len - 1] == ';')
				{
					mybuf.data[--mybuf.len] = '\0';
				}
			}

			/*
			 * If SQL identifier processing was requested, then we strip out
			 * excess double quotes and downcase unquoted letters.
			 * Doubled double-quotes become output double-quotes, per spec.
			 *
			 * Note that a string like FOO"BAR"BAZ will be converted to
			 * fooBARbaz; this is somewhat inconsistent with the SQL spec,
			 * which would have us parse it as several identifiers.  But
			 * for psql's purposes, we want a string like "foo"."bar" to
			 * be treated as one option, so there's little choice.
			 */
			if (type == OT_SQLID || type == OT_SQLIDHACK)
			{
				bool		inquotes = false;
				char	   *cp = mybuf.data;

				while (*cp)
				{
					if (*cp == '"')
					{
						if (inquotes && cp[1] == '"')
						{
							/* Keep the first quote, remove the second */
							cp++;
						}
						inquotes = !inquotes;
						/* Collapse out quote at *cp */
						memmove(cp, cp + 1, strlen(cp));
						mybuf.len--;
						/* do not advance cp */
					}
					else
					{
						if (!inquotes && type == OT_SQLID)
							*cp = pg_tolower((unsigned char) *cp);
						cp += PQmblen(cp, pset.encoding);
					}
				}
			}
			break;
		case xslashquotedarg:
			/* must have hit EOL inside double quotes */
			badarg = true;
			break;
		case xslashwholeline:
			/* always okay */
			break;
		default:
			/* can't get here */
			fprintf(stderr, "invalid YY_START\n");
			exit(1);
	}

	if (badarg)
	{
		psql_error("unterminated quoted string\n");
		termPQExpBuffer(&mybuf);
		return NULL;
	}

	/*
	 * An unquoted empty argument isn't possible unless we are at end of
	 * command.  Return NULL instead.
	 */
	if (mybuf.len == 0 && *quote == 0)
	{
		termPQExpBuffer(&mybuf);
		return NULL;
	}

	/* Else return the completed string. */
	return mybuf.data;
}

/*
 * Eat up any unused \\ to complete a backslash command.
 */
void
psql_scan_slash_command_end(PsqlScanState state)
{
	int			lexresult;

	/* Must be scanning already */
	psql_assert(state->scanbufhandle);

	/* Set up static variables that will be used by yylex */
	cur_state = state;
	output_buf = NULL;

	if (state->buffer_stack != NULL)
		yy_switch_to_buffer(state->buffer_stack->buf);
	else
		yy_switch_to_buffer(state->scanbufhandle);

	BEGIN(xslashend);

	/* And lex. */
	lexresult = yylex();

	/* There are no possible errors in this lex state... */
}

/*
 * "Push back" the passed string so that it will be rescanned by subsequent
 * psql_scan_slash_option calls.  This is presently only used in the case
 * where a single-letter command has been concatenated with its argument.
 *
 * We use the same buffer stack mechanism as for variable expansion.
 */
void
psql_scan_slash_pushback(PsqlScanState state, const char *str)
{
	/* needed for push_new_buffer */
	cur_state = state;

	push_new_buffer(str);
}


/*
 * Push the given string onto the stack of stuff to scan.
 *
 * cur_state must point to the active PsqlScanState.
 *
 * NOTE SIDE EFFECT: the new buffer is made the active flex input buffer.
 */
static void
push_new_buffer(const char *newstr)
{
	StackElem  *stackelem;

	stackelem = (StackElem *) pg_malloc(sizeof(StackElem));
	stackelem->buf = prepare_buffer(newstr, strlen(newstr),
									&stackelem->bufstring);
	cur_state->curline = stackelem->bufstring;
	if (cur_state->safe_encoding)
	{
		stackelem->origstring = NULL;
		cur_state->refline = stackelem->bufstring;
	}
	else
	{
		stackelem->origstring = pg_strdup(newstr);
		cur_state->refline = stackelem->origstring;
	}
	stackelem->next = cur_state->buffer_stack;
	cur_state->buffer_stack = stackelem;
}

/*
 * Set up a flex input buffer to scan the given data.  We always make a
 * copy of the data.  If working in an unsafe encoding, the copy has
 * multibyte sequences replaced by FFs to avoid fooling the lexer rules.
 *
 * cur_state must point to the active PsqlScanState.
 *
 * NOTE SIDE EFFECT: the new buffer is made the active flex input buffer.
 */
static YY_BUFFER_STATE
prepare_buffer(const char *txt, int len, char **txtcopy)
{
	char	   *newtxt;

	/* Flex wants two \0 characters after the actual data */
	newtxt = pg_malloc(len + 2);
	*txtcopy = newtxt;
	newtxt[len] = newtxt[len + 1] = YY_END_OF_BUFFER_CHAR;

	if (cur_state->safe_encoding)
		memcpy(newtxt, txt, len);
	else
	{
		/* Gotta do it the hard way */
		int		i = 0;

		while (i < len)
		{
			int		thislen = PQmblen(txt + i, cur_state->encoding);

			/* first byte should always be okay... */
			newtxt[i] = txt[i];
			i++;
			while (--thislen > 0)
				newtxt[i++] = (char) 0xFF;
		}
	}

	return yy_scan_buffer(newtxt, len + 2);
}

/*
 * emit() --- body for ECHO macro
 *
 * NB: this must be used for ALL and ONLY the text copied from the flex
 * input data.  If you pass it something that is not part of the yytext
 * string, you are making a mistake.  Internally generated text can be
 * appended directly to output_buf.
 */
static void
emit(const char *txt, int len)
{
	if (cur_state->safe_encoding)
		appendBinaryPQExpBuffer(output_buf, txt, len);
	else
	{
		/* Gotta do it the hard way */
		const char *reference = cur_state->refline;
		int		i;

		reference += (txt - cur_state->curline);

		for (i = 0; i < len; i++)
		{
			char	ch = txt[i];

			if (ch == (char) 0xFF)
				ch = reference[i];
			appendPQExpBufferChar(output_buf, ch);
		}
	}
}