scan.l

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

				}
<xq>{xqinside}  {
					addlit(yytext, yyleng);
				}
<xq>{xqescape}  {
					if (yytext[1] == '\'')
					{
						if (backslash_quote == BACKSLASH_QUOTE_OFF ||
							(backslash_quote == BACKSLASH_QUOTE_SAFE_ENCODING &&
							 PG_ENCODING_IS_CLIENT_ONLY(pg_get_client_encoding())))
							ereport(ERROR,
									(errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
									 errmsg("unsafe use of \\' in a string literal"),
									 errhint("Use '' to write quotes in strings. \\' is insecure in client-only encodings."),
									 errposition(pg_err_position())));
						if (warn_on_first_escape && escape_string_warning)
							ereport(WARNING,
									(errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
									 errmsg("nonstandard use of \\' in a string literal"),
									 errhint("Use '' to write quotes in strings, or use the escape string syntax (E'...')."),
									 errposition(pg_err_position())));
						warn_on_first_escape = false;	/* warn only once per string */
					}
					else if (yytext[1] == '\\')
					{
						if (warn_on_first_escape && escape_string_warning)
							ereport(WARNING,
									(errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
									 errmsg("nonstandard use of \\\\ in a string literal"),
									 errhint("Use the escape string syntax for backslashes, e.g., E'\\\\'."),
									 errposition(pg_err_position())));
						warn_on_first_escape = false;	/* warn only once per string */
					}
					else
						check_escape_warning();
					addlitchar(unescape_single_char(yytext[1]));
				}
<xq>{xqoctesc}  {
					unsigned char c = strtoul(yytext+1, NULL, 8);

					check_escape_warning();
					addlitchar(c);
				}
<xq>{xqhexesc}  {
					unsigned char c = strtoul(yytext+2, NULL, 16);

					check_escape_warning();
					addlitchar(c);
				}
<xq>{quotecontinue} {
					/* ignore */
				}
<xq>.			{
					/* This is only needed for \ just before EOF */
					addlitchar(yytext[0]);
				}
<xq><<EOF>>		{ yyerror("unterminated quoted string"); }

{dolqdelim}		{
					token_start = yytext;
					dolqstart = pstrdup(yytext);
					BEGIN(xdolq);
					startlit();
				}
{dolqfailed}	{
					/* throw back all but the initial "$" */
					yyless(1);
					/* and treat it as {other} */
					return yytext[0];
				}
<xdolq>{dolqdelim} {
					if (strcmp(yytext, dolqstart) == 0)
					{
						pfree(dolqstart);
						BEGIN(INITIAL);
						yylval.str = litbufdup();
						return SCONST;
					}
					else
					{
						/*
						 * When we fail to match $...$ to dolqstart, transfer
						 * the $... part to the output, but put back the final
						 * $ for rescanning.  Consider $delim$...$junk$delim$
						 */
						addlit(yytext, yyleng-1);
						yyless(yyleng-1);
					}
				}
<xdolq>{dolqinside} {
					addlit(yytext, yyleng);
				}
<xdolq>{dolqfailed} {
					addlit(yytext, yyleng);
				}
<xdolq>.		{
					/* This is only needed for $ inside the quoted text */
					addlitchar(yytext[0]);
				}
<xdolq><<EOF>>	{ yyerror("unterminated dollar-quoted string"); }

{xdstart}		{
					token_start = yytext;
					BEGIN(xd);
					startlit();
				}
<xd>{xdstop}	{
					char		   *ident;

					BEGIN(INITIAL);
					if (literallen == 0)
						yyerror("zero-length delimited identifier");
					ident = litbufdup();
					if (literallen >= NAMEDATALEN)
						truncate_identifier(ident, literallen, true);
					yylval.str = ident;
					return IDENT;
				}
<xd>{xddouble}	{
					addlitchar('"');
				}
<xd>{xdinside}	{
					addlit(yytext, yyleng);
				}
<xd><<EOF>>		{ yyerror("unterminated quoted identifier"); }

{typecast}		{
					return TYPECAST;
				}

{self}			{
					return yytext[0];
				}

{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);
						/*
						 * If what we have left is only one char, and it's
						 * one of the characters matching "self", then
						 * return it as a character token the same way
						 * that the "self" rule would have.
						 */
						if (nchars == 1 &&
							strchr(",()[].;:+-*/%^<>=", yytext[0]))
							return yytext[0];
					}

					/*
					 * Complain if operator is too long.  Unlike the case
					 * for identifiers, we make this an error not a notice-
					 * and-truncate, because the odds are we are looking at
					 * a syntactic mistake anyway.
					 */
					if (nchars >= NAMEDATALEN)
						yyerror("operator too long");

					/* Convert "!=" operator to "<>" for compatibility */
					if (strcmp(yytext, "!=") == 0)
						yylval.str = pstrdup("<>");
					else
						yylval.str = pstrdup(yytext);
					return Op;
				}

{param}			{
					yylval.ival = atol(yytext + 1);
					return PARAM;
				}

{integer}		{
					long val;
					char* endptr;

					errno = 0;
					val = strtol(yytext, &endptr, 10);
					if (*endptr != '\0' || errno == ERANGE
#ifdef HAVE_LONG_INT_64
						/* if long > 32 bits, check for overflow of int4 */
						|| val != (long) ((int32) val)
#endif
						)
					{
						/* integer too large, treat it as a float */
						yylval.str = pstrdup(yytext);
						return FCONST;
					}
					yylval.ival = val;
					return ICONST;
				}
{decimal}		{
					yylval.str = pstrdup(yytext);
					return FCONST;
				}
{real}			{
					yylval.str = pstrdup(yytext);
					return FCONST;
				}
{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);
					yylval.str = pstrdup(yytext);
					return FCONST;
				}
{realfail2}		{
					/* throw back the [Ee][+-], and proceed as above */
					yyless(yyleng-2);
					yylval.str = pstrdup(yytext);
					return FCONST;
				}


{identifier}	{
					const ScanKeyword *keyword;
					char		   *ident;

					/* Is it a keyword? */
					keyword = ScanKeywordLookup(yytext);
					if (keyword != NULL)
					{
						yylval.keyword = keyword->name;
						return keyword->value;
					}

					/*
					 * No.  Convert the identifier to lower case, and truncate
					 * if necessary.
					 */
					ident = downcase_truncate_identifier(yytext, yyleng, true);
					yylval.str = ident;
					return IDENT;
				}

{other}			{
					return yytext[0];
				}

%%

static int
pg_err_position(void)
{
	const char *loc = token_start ? token_start : yytext;

	/* in multibyte encodings, return index in characters not bytes */
	return pg_mbstrlen_with_len(scanbuf, loc - scanbuf) + 1;
}

void
yyerror(const char *message)
{
	const char *loc = token_start ? token_start : yytext;
	int			cursorpos = pg_err_position();

	if (*loc == YY_END_OF_BUFFER_CHAR)
	{
		ereport(ERROR,
				(errcode(ERRCODE_SYNTAX_ERROR),
				 /* translator: %s is typically "syntax error" */
				 errmsg("%s at end of input", _(message)),
				 errposition(cursorpos)));
	}
	else
	{
		ereport(ERROR,
				(errcode(ERRCODE_SYNTAX_ERROR),
				 /* translator: first %s is typically "syntax error" */
				 errmsg("%s at or near \"%s\"", _(message), loc),
				 errposition(cursorpos)));
	}
}


/*
 * Called before any actual parsing is done
 */
void
scanner_init(const char *str)
{
	Size	slen = strlen(str);

	/*
	 * Might be left over after ereport()
	 */
	if (YY_CURRENT_BUFFER)
		yy_delete_buffer(YY_CURRENT_BUFFER);

	/*
	 * Make a scan buffer with special termination needed by flex.
	 */
	scanbuf = palloc(slen + 2);
	memcpy(scanbuf, str, slen);
	scanbuf[slen] = scanbuf[slen + 1] = YY_END_OF_BUFFER_CHAR;
	scanbufhandle = yy_scan_buffer(scanbuf, slen + 2);

	/* initialize literal buffer to a reasonable but expansible size */
	literalalloc = 128;
	literalbuf = (char *) palloc(literalalloc);
	startlit();

	BEGIN(INITIAL);
}


/*
 * Called after parsing is done to clean up after scanner_init()
 */
void
scanner_finish(void)
{
	yy_delete_buffer(scanbufhandle);
	pfree(scanbuf);
}


static void
addlit(char *ytext, int yleng)
{
	/* enlarge buffer if needed */
	if ((literallen+yleng) >= literalalloc)
	{
		do {
			literalalloc *= 2;
		} while ((literallen+yleng) >= literalalloc);
		literalbuf = (char *) repalloc(literalbuf, literalalloc);
	}
	/* append new data, add trailing null */
	memcpy(literalbuf+literallen, ytext, yleng);
	literallen += yleng;
	literalbuf[literallen] = '\0';
}


static void
addlitchar(unsigned char ychar)
{
	/* enlarge buffer if needed */
	if ((literallen+1) >= literalalloc)
	{
		literalalloc *= 2;
		literalbuf = (char *) repalloc(literalbuf, literalalloc);
	}
	/* append new data, add trailing null */
	literalbuf[literallen] = ychar;
	literallen += 1;
	literalbuf[literallen] = '\0';
}


/*
 * One might be tempted to write pstrdup(literalbuf) instead of this,
 * but for long literals this is much faster because the length is
 * already known.
 */
static char *
litbufdup(void)
{
	char *new;

	new = palloc(literallen + 1);
	memcpy(new, literalbuf, literallen+1);
	return new;
}


unsigned char
unescape_single_char(unsigned char c)
{
	switch (c)
	{
		case 'b':
			return '\b';
		case 'f':
			return '\f';
		case 'n':
			return '\n';
		case 'r':
			return '\r';
		case 't':
			return '\t';
		default:
			return c;
	}
}

static void
check_escape_warning(void)
{
	if (warn_on_first_escape && escape_string_warning)
		ereport(WARNING,
				(errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
				 errmsg("nonstandard use of escape in a string literal"),
				 errhint("Use the escape string syntax for escapes, e.g., E'\\r\\n'."),
				 errposition(pg_err_position())));
	warn_on_first_escape = false;	/* warn only once per string */
}