psqlscan.l

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

	/*
	 * These rules are specific to psql --- they implement parenthesis
	 * counting and detection of command-ending semicolon.  These must
	 * appear before the {self} rule so that they take precedence over it.
	 */

"("				{
					cur_state->paren_depth++;
					ECHO;
				}

")"				{
					if (cur_state->paren_depth > 0)
						cur_state->paren_depth--;
					ECHO;
				}

";"				{
					ECHO;
					if (cur_state->paren_depth == 0)
					{
						/* Terminate lexing temporarily */
						return LEXRES_SEMI;
					}
				}

	/*
	 * psql-specific rules to handle backslash commands and variable
	 * substitution.  We want these before {self}, also.
	 */

"\\"[;:]		{
					/* Force a semicolon or colon into the query buffer */
					emit(yytext + 1, 1);
				}

"\\"			{
					/* Terminate lexing temporarily */
					return LEXRES_BACKSLASH;
				}

:[A-Za-z0-9_]+	{
					/* Possible psql variable substitution */
					const char *value;

					value = GetVariable(pset.vars, yytext + 1);

					if (value)
					{
						/* It is a variable, perform substitution */
						push_new_buffer(value);
						/* yy_scan_string already made buffer active */
					}
					else
					{
						/*
						 * if the variable doesn't exist we'll copy the
						 * string as is
						 */
						ECHO;
					}
				}

	/*
	 * Back to backend-compatible rules.
	 */

{self}			{
					ECHO;
				}

{operator}		{
					/*
					 * Check for embedded slash-star or dash-dash; those
					 * are comment starts, so operator must stop there.
					 * Note that slash-star or dash-dash at the first
					 * character will match a prior rule, not this one.
					 */
					int		nchars = yyleng;
					char   *slashstar = strstr(yytext, "/*");
					char   *dashdash = strstr(yytext, "--");

					if (slashstar && dashdash)
					{
						/* if both appear, take the first one */
						if (slashstar > dashdash)
							slashstar = dashdash;
					}
					else if (!slashstar)
						slashstar = dashdash;
					if (slashstar)
						nchars = slashstar - yytext;

					/*
					 * For SQL compatibility, '+' and '-' cannot be the
					 * last char of a multi-char operator unless the operator
					 * contains chars that are not in SQL operators.
					 * The idea is to lex '=-' as two operators, but not
					 * to forbid operator names like '?-' that could not be
					 * sequences of SQL operators.
					 */
					while (nchars > 1 &&
						   (yytext[nchars-1] == '+' ||
							yytext[nchars-1] == '-'))
					{
						int		ic;

						for (ic = nchars-2; ic >= 0; ic--)
						{
							if (strchr("~!@#^&|`?%", yytext[ic]))
								break;
						}
						if (ic >= 0)
							break; /* found a char that makes it OK */
						nchars--; /* else remove the +/-, and check again */
					}

					if (nchars < yyleng)
					{
						/* Strip the unwanted chars from the token */
						yyless(nchars);
					}
					ECHO;
				}

{param}			{
					ECHO;
				}

{integer}		{
					ECHO;
				}
{decimal}		{
					ECHO;
				}
{real}			{
					ECHO;
				}
{realfail1}		{
					/*
					 * throw back the [Ee], and treat as {decimal}.  Note
					 * that it is possible the input is actually {integer},
					 * but since this case will almost certainly lead to a
					 * syntax error anyway, we don't bother to distinguish.
					 */
					yyless(yyleng-1);
					ECHO;
				}
{realfail2}		{
					/* throw back the [Ee][+-], and proceed as above */
					yyless(yyleng-2);
					ECHO;
				}


{identifier}	{
					ECHO;
				}

{other}			{
					ECHO;
				}


	/*
	 * Everything from here down is psql-specific.
	 */

<<EOF>>			{
					StackElem  *stackelem = cur_state->buffer_stack;

					if (stackelem == NULL)
						return LEXRES_EOL; /* end of input reached */

					/*
					 * We were expanding a variable, so pop the inclusion
					 * stack and keep lexing
					 */
					cur_state->buffer_stack = stackelem->next;
					yy_delete_buffer(stackelem->buf);
					free(stackelem->bufstring);
					if (stackelem->origstring)
						free(stackelem->origstring);
					free(stackelem);

					stackelem = cur_state->buffer_stack;
					if (stackelem != NULL)
					{
						yy_switch_to_buffer(stackelem->buf);
						cur_state->curline = stackelem->bufstring;
						cur_state->refline = stackelem->origstring ? stackelem->origstring : stackelem->bufstring;
					}
					else
					{
						yy_switch_to_buffer(cur_state->scanbufhandle);
						cur_state->curline = cur_state->scanbuf;
						cur_state->refline = cur_state->scanline;
					}
				}

	/*
	 * Exclusive lexer states to handle backslash command lexing
	 */

<xslashcmd>{
	/* command name ends at whitespace or backslash; eat all else */

{space}|"\\"	{
					yyless(0);
					return LEXRES_OK;
				}

{other}			{ ECHO; }

}

<xslasharg>{
	/* eat any whitespace, then decide what to do at first nonblank */

{space}+		{ }

"\\"			{
					/*
					 * backslash is end of command or next command, do not eat
					 *
					 * XXX this means we can't conveniently accept options
					 * that start with a backslash; therefore, option
					 * processing that encourages use of backslashes is rather
					 * broken.
					 */
					yyless(0);
					return LEXRES_OK;
				}

{quote}			{
					*option_quote = '\'';
					BEGIN(xslashquote);
				}

"`"				{
					if (option_type == OT_VERBATIM)
					{
						/* in verbatim mode, backquote is not special */
						ECHO;
						BEGIN(xslashdefaultarg);
					}
					else
					{
						*option_quote = '`';
						BEGIN(xslashbackquote);
					}
				}

:[A-Za-z0-9_]*	{
					/* Possible psql variable substitution */
					if (option_type == OT_VERBATIM)
						ECHO;
					else
					{
						const char *value;

						value = GetVariable(pset.vars, yytext + 1);

						/*
						 * The variable value is just emitted without any
						 * further examination.  This is consistent with the
						 * pre-8.0 code behavior, if not with the way that
						 * variables are handled outside backslash commands.
						 */
						if (value)
							appendPQExpBufferStr(output_buf, value);
					}

					*option_quote = ':';

					return LEXRES_OK;
				}

"|"				{
					ECHO;
					if (option_type == OT_FILEPIPE)
					{
						/* treat like whole-string case */
						BEGIN(xslashwholeline);
					}
					else
					{
						/* treat like default case */
						BEGIN(xslashdefaultarg);
					}
				}

{dquote}		{
					*option_quote = '"';
					ECHO;
					BEGIN(xslashquotedarg);
				}

{other}			{
					ECHO;
					BEGIN(xslashdefaultarg);
				}

}

<xslashquote>{
	/* single-quoted text: copy literally except for backslash sequences */

{quote}			{ return LEXRES_OK; }

"\\n"			{ appendPQExpBufferChar(output_buf, '\n'); }
"\\t"			{ appendPQExpBufferChar(output_buf, '\t'); }
"\\b"			{ appendPQExpBufferChar(output_buf, '\b'); }
"\\r"			{ appendPQExpBufferChar(output_buf, '\r'); }
"\\f"			{ appendPQExpBufferChar(output_buf, '\f'); }

{xqoctesc}		{
					/* octal case */
					appendPQExpBufferChar(output_buf,
										  (char) strtol(yytext + 1, NULL, 8));
				}

{xqhexesc}		{
					/* hex case */
					appendPQExpBufferChar(output_buf,
										  (char) strtol(yytext + 2, NULL, 16));
				}

"\\".			{ emit(yytext + 1, 1); }

{other}|\n		{ ECHO; }

}

<xslashbackquote>{
	/*
	 * backticked text: copy everything until next backquote or end of line.
	 * Invocation of the command will happen in psql_scan_slash_option.
	 */

"`"				{ return LEXRES_OK; }

{other}|\n		{ ECHO; }

}

<xslashdefaultarg>{
	/*
	 * Copy everything until unquoted whitespace or end of line.  Quotes
	 * do not get stripped yet.
	 */

{space}			{
					yyless(0);
					return LEXRES_OK;
				}

"\\"			{
					/*
					 * unquoted backslash is end of command or next command,
					 * do not eat
					 *
					 * (this was not the behavior pre-8.0, but it seems
					 * consistent)
					 */
					yyless(0);
					return LEXRES_OK;
				}

{dquote}		{
					*option_quote = '"';
					ECHO;
					BEGIN(xslashquotedarg);
				}

{other}			{ ECHO; }

}

<xslashquotedarg>{
	/* double-quoted text within a default-type argument: copy */

{dquote}		{
					ECHO;
					BEGIN(xslashdefaultarg);
				}

{other}|\n		{ ECHO; }

}

<xslashwholeline>{
	/* copy everything until end of input line */
	/* but suppress leading whitespace */

{space}+		{
					if (output_buf->len > 0)
						ECHO;
				}

{other}			{ ECHO; }

}

<xslashend>{
	/* at end of command, eat a double backslash, but not anything else */

"\\\\"			{ return LEXRES_OK; }

{other}|\n		{
					yyless(0);
					return LEXRES_OK;
				}

}

%%

/*
 * Create a lexer working state struct.
 */
PsqlScanState
psql_scan_create(void)
{
	PsqlScanState state;

	state = (PsqlScanStateData *) pg_malloc_zero(sizeof(PsqlScanStateData));

	psql_scan_reset(state);

	return state;
}

/*
 * Destroy a lexer working state struct, releasing all resources.
 */
void
psql_scan_destroy(PsqlScanState state)
{
	psql_scan_finish(state);

	psql_scan_reset(state);

	free(state);
}

/*
 * Set up to perform lexing of the given input line.
 *
 * The text at *line, extending for line_len bytes, will be scanned by
 * subsequent calls to the psql_scan routines.  psql_scan_finish should
 * be called when scanning is complete.  Note that the lexer retains
 * a pointer to the storage at *line --- this string must not be altered
 * or freed until after psql_scan_finish is called.
 */
void
psql_scan_setup(PsqlScanState state,
				const char *line, int line_len)
{
	/* Mustn't be scanning already */
	psql_assert(state->scanbufhandle == NULL);
	psql_assert(state->buffer_stack == NULL);

	/* Do we need to hack the character set encoding? */
	state->encoding = pset.encoding;
	state->safe_encoding = PG_VALID_BE_ENCODING(state->encoding);

	/* needed for prepare_buffer */
	cur_state = state;

	/* Set up flex input buffer with appropriate translation and padding */
	state->scanbufhandle = prepare_buffer(line, line_len,
										  &state->scanbuf);
	state->scanline = line;

	/* Set lookaside data in case we have to map unsafe encoding */
	state->curline = state->scanbuf;
	state->refline = state->scanline;
}

/*
 * Do lexical analysis of SQL command text.
 *
 * The text previously passed to psql_scan_setup is scanned, and appended
 * (possibly with transformation) to query_buf.
 *
 * The return value indicates the condition that stopped scanning:
 *
 * PSCAN_SEMICOLON: found a command-ending semicolon.  (The semicolon is
 * transferred to query_buf.)  The command accumulated in query_buf should
 * be executed, then clear query_buf and call again to scan the remainder
 * of the line.
 *
 * PSCAN_BACKSLASH: found a backslash that starts a psql special command.
 * Any previous data on the line has been transferred to query_buf.
 * The caller will typically next call psql_scan_slash_command(),
 * perhaps psql_scan_slash_option(), and psql_scan_slash_command_end().
 *
 * PSCAN_INCOMPLETE: the end of the line was reached, but we have an
 * incomplete SQL command.  *prompt is set to the appropriate prompt type.
 *
 * PSCAN_EOL: the end of the line was reached, and there is no lexical
 * reason to consider the command incomplete.  The caller may or may not
 * choose to send it.  *prompt is set to the appropriate prompt type if
 * the caller chooses to collect more input.
 *
 * In the PSCAN_INCOMPLETE and PSCAN_EOL cases, psql_scan_finish() should
 * be called next, then the cycle may be repeated with a fresh input line.
 *
 * In all cases, *prompt is set to an appropriate prompt type code for the
 * next line-input operation.
 */
PsqlScanResult
psql_scan(PsqlScanState state,
		  PQExpBuffer query_buf,
		  promptStatus_t *prompt)
{
	PsqlScanResult result;
	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 = query_buf;

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

	BEGIN(state->start_state);

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

	/* Update static vars back to the state struct */
	state->start_state = YY_START;

	/*
	 * Check termination state and return appropriate result info.
	 */
	switch (lexresult)