scan.l

PostgreSQL7.4.6 for Linux

%{
/*-------------------------------------------------------------------------
 *
 * scan.l
 *	  lexical scanner for PostgreSQL
 *
 * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $Header: /cvsroot/pgsql/src/backend/parser/scan.l,v 1.111.2.1 2004/02/21 00:35:13 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include <ctype.h>
#include <unistd.h>
#include <errno.h>

#include "miscadmin.h"
#include "nodes/parsenodes.h"
#include "nodes/pg_list.h"
#include "parser/gramparse.h"
#include "parser/keywords.h"
/* Not needed now that this file is compiled as part of gram.y */
/* #include "parser/parse.h" */
#include "parser/scansup.h"
#include "utils/builtins.h"
#include "mb/pg_wchar.h"

/* No reason to constrain amount of data slurped */
#define YY_READ_BUF_SIZE 16777216

/* Avoid exit() on fatal scanner errors (a bit ugly -- see yy_fatal_error) */
#define fprintf(file, fmt, msg)  ereport(ERROR, (errmsg_internal("%s", msg)))

extern YYSTYPE yylval;

static int		xcdepth = 0;	/* depth of nesting in slash-star comments */

/*
 * literalbuf is used to accumulate literal values when multiple rules
 * are needed to parse a single literal.  Call startlit to reset buffer
 * to empty, addlit to add text.  Note that the buffer is palloc'd and
 * starts life afresh on every parse cycle.
 */
static char	   *literalbuf;		/* expandable buffer */
static int		literallen;		/* actual current length */
static int		literalalloc;	/* current allocated buffer size */

#define startlit()  (literalbuf[0] = '\0', literallen = 0)
static void addlit(char *ytext, int yleng);
static void addlitchar(unsigned char ychar);
static char *litbufdup(void);

/*
 * When we parse a token that requires multiple lexer rules to process,
 * we set token_start to point at the true start of the token, for use
 * by yyerror().  yytext will point at just the text consumed by the last
 * rule, so it's not very helpful (e.g., it might contain just the last
 * quote mark of a quoted identifier).  But to avoid cluttering every rule
 * with setting token_start, we allow token_start = NULL to denote that
 * it's okay to use yytext.
 */
static char	   *token_start;

/* Handles to the buffer that the lexer uses internally */
static YY_BUFFER_STATE scanbufhandle;
static char *scanbuf;

unsigned char unescape_single_char(unsigned char c);

%}

%option 8bit
%option never-interactive
%option nounput
%option noyywrap
%option prefix="base_yy"

/*
 * OK, here is a short description of lex/flex rules behavior.
 * The longest pattern which matches an input string is always chosen.
 * For equal-length patterns, the first occurring in the rules list is chosen.
 * INITIAL is the starting state, to which all non-conditional rules apply.
 * Exclusive states change parsing rules while the state is active.  When in
 * an exclusive state, only those rules defined for that state apply.
 *
 * We use exclusive states for quoted strings, extended comments,
 * and to eliminate parsing troubles for numeric strings.
 * Exclusive states:
 *  <xb> bit string literal
 *  <xc> extended C-style comments
 *  <xd> delimited identifiers (double-quoted identifiers)
 *  <xh> hexadecimal numeric string
 *  <xq> quoted strings
 */

%x xb
%x xc
%x xd
%x xh
%x xq

/* Bit string
 * It is tempting to scan the string for only those characters
 * which are allowed. However, this leads to silently swallowed
 * characters if illegal characters are included in the string.
 * For example, if xbinside is [01] then B'ABCD' is interpreted
 * as a zero-length string, and the ABCD' is lost!
 * Better to pass the string forward and let the input routines
 * validate the contents.
 */
xbstart			[bB]{quote}
xbstop			{quote}
xbinside		[^']*
xbcat			{quote}{whitespace_with_newline}{quote}

/* Hexadecimal number
 */
xhstart			[xX]{quote}
xhstop			{quote}
xhinside		[^']*
xhcat			{quote}{whitespace_with_newline}{quote}

/* National character
 */
xnstart			[nN]{quote}

/* Extended quote
 * xqdouble implements embedded quote
 * xqcat allows strings to cross input lines
 */
quote			'
xqstart			{quote}
xqstop			{quote}
xqdouble		{quote}{quote}
xqinside		[^\\']+
xqescape		[\\][^0-7]
xqoctesc		[\\][0-7]{1,3}
xqcat			{quote}{whitespace_with_newline}{quote}

/* Double quote
 * Allows embedded spaces and other special characters into identifiers.
 */
dquote			\"
xdstart			{dquote}
xdstop			{dquote}
xddouble		{dquote}{dquote}
xdinside		[^"]+

/* C-style comments
 *
 * The "extended comment" syntax closely resembles allowable operator syntax.
 * The tricky part here is to get lex to recognize a string starting with
 * slash-star as a comment, when interpreting it as an operator would produce
 * a longer match --- remember lex will prefer a longer match!  Also, if we
 * have something like plus-slash-star, lex will think this is a 3-character
 * operator whereas we want to see it as a + operator and a comment start.
 * The solution is two-fold:
 * 1. append {op_chars}* to xcstart so that it matches as much text as
 *    {operator} would. Then the tie-breaker (first matching rule of same
 *    length) ensures xcstart wins.  We put back the extra stuff with yyless()
 *    in case it contains a star-slash that should terminate the comment.
 * 2. In the operator rule, check for slash-star within the operator, and
 *    if found throw it back with yyless().  This handles the plus-slash-star
 *    problem.
 * Dash-dash comments have similar interactions with the operator rule.
 */
xcstart			\/\*{op_chars}*
xcstop			\*+\/
xcinside		[^*/]+

digit			[0-9]
ident_start		[A-Za-z\200-\377_]
ident_cont		[A-Za-z\200-\377_0-9\$]

identifier		{ident_start}{ident_cont}*

typecast		"::"

/*
 * "self" is the set of chars that should be returned as single-character
 * tokens.  "op_chars" is the set of chars that can make up "Op" tokens,
 * which can be one or more characters long (but if a single-char token
 * appears in the "self" set, it is not to be returned as an Op).  Note
 * that the sets overlap, but each has some chars that are not in the other.
 *
 * If you change either set, adjust the character lists appearing in the
 * rule for "operator"!
 */
self			[,()\[\].;\:\+\-\*\/\%\^\<\>\=]
op_chars		[\~\!\@\#\^\&\|\`\?\+\-\*\/\%\<\>\=]
operator		{op_chars}+

/* we no longer allow unary minus in numbers. 
 * instead we pass it separately to parser. there it gets
 * coerced via doNegate() -- Leon aug 20 1999 
 */

integer			{digit}+
decimal			(({digit}*\.{digit}+)|({digit}+\.{digit}*))
real			((({digit}*\.{digit}+)|({digit}+\.{digit}*)|({digit}+))([Ee][-+]?{digit}+))

param			\${integer}

/*
 * In order to make the world safe for Windows and Mac clients as well as
 * Unix ones, we accept either \n or \r as a newline.  A DOS-style \r\n
 * sequence will be seen as two successive newlines, but that doesn't cause
 * any problems.  Comments that start with -- and extend to the next
 * newline are treated as equivalent to a single whitespace character.
 *
 * NOTE a fine point: if there is no newline following --, we will absorb
 * everything to the end of the input as a comment.  This is correct.  Older
 * versions of Postgres failed to recognize -- as a comment if the input
 * did not end with a newline.
 *
 * XXX perhaps \f (formfeed) should be treated as a newline as well?
 */

space			[ \t\n\r\f]
horiz_space		[ \t\f]
newline			[\n\r]
non_newline		[^\n\r]

comment			("--"{non_newline}*)

whitespace		({space}+|{comment})

/*
 * SQL requires at least one newline in the whitespace separating
 * string literals that are to be concatenated.  Silly, but who are we
 * to argue?  Note that {whitespace_with_newline} should not have * after
 * it, whereas {whitespace} should generally have a * after it...
 */

special_whitespace		({space}+|{comment}{newline})
horiz_whitespace		({horiz_space}|{comment})
whitespace_with_newline	({horiz_whitespace}*{newline}{special_whitespace}*)

other			.

/*
 * Quoted strings must allow some special characters such as single-quote
 *  and newline.
 * Embedded single-quotes are implemented both in the SQL standard
 *  style of two adjacent single quotes "''" and in the Postgres/Java style
 *  of escaped-quote "\'".
 * Other embedded escaped characters are matched explicitly and the leading
 *  backslash is dropped from the string.
 * Note that xcstart must appear before operator, as explained above!
 *  Also whitespace (comment) must appear before operator.
 */

%%

%{
					/* code to execute during start of each call of yylex() */
					token_start = NULL;
%}

{whitespace}	{ /* ignore */ }

{xcstart}		{
					token_start = yytext;
					xcdepth = 0;
					BEGIN(xc);
					/* Put back any characters past slash-star; see above */
					yyless(2);
				}

<xc>{xcstart}	{
					xcdepth++;
					/* Put back any characters past slash-star; see above */
					yyless(2);
				}

<xc>{xcstop}	{
					if (xcdepth <= 0)
					{
						BEGIN(INITIAL);
						/* reset token_start for next token */
						token_start = NULL;
					}
					else
						xcdepth--;
				}

<xc>{xcinside}	{ /* ignore */ }

<xc>{op_chars}	{ /* ignore */ }

<xc><<EOF>>		{ yyerror("unterminated /* comment"); }

{xbstart}		{
					/* Binary bit type.
					 * At some point we should simply pass the string
					 * forward to the parser and label it there.
					 * In the meantime, place a leading "b" on the string
					 * to mark it for the input routine as a binary string.
					 */
					token_start = yytext;
					BEGIN(xb);
					startlit();
					addlitchar('b');
				}
<xb>{xbstop}	{
					BEGIN(INITIAL);
					yylval.str = litbufdup();
					return BCONST;
				}
<xh>{xhinside}	|
<xb>{xbinside}	{
					addlit(yytext, yyleng);
				}
<xh>{xhcat}		|
<xb>{xbcat}		{
					/* ignore */
				}
<xb><<EOF>>		{
					yyerror("unterminated bit string literal");
				}
{xhstart}		{
					/* Hexadecimal bit type.
					 * At some point we should simply pass the string
					 * forward to the parser and label it there.
					 * In the meantime, place a leading "x" on the string
					 * to mark it for the input routine as a hex string.
					 */
					token_start = yytext;
					BEGIN(xh);
					startlit();
					addlitchar('x');
				}
<xh>{xhstop}	{
					BEGIN(INITIAL);
					yylval.str = litbufdup();
					return XCONST;
				}
<xh><<EOF>>		{ yyerror("unterminated hexadecimal string literal"); }

{xnstart}		{