psqlscan.l

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

%{
/*-------------------------------------------------------------------------
 *
 * psqlscan.l
 *	  lexical scanner for psql
 *
 * This code is mainly needed to determine where the end of a SQL statement
 * is: we are looking for semicolons that are not within quotes, comments,
 * or parentheses.  The most reliable way to handle this is to borrow the
 * backend's flex lexer rules, lock, stock, and barrel.  The rules below
 * are (except for a few) the same as the backend's, but their actions are
 * just ECHO whereas the backend's actions generally do other things.
 *
 * XXX The rules in this file must be kept in sync with the backend lexer!!!
 *
 * XXX Avoid creating backtracking cases --- see the backend lexer for info.
 *
 * The most difficult aspect of this code is that we need to work in multibyte
 * encodings that are not ASCII-safe.  A "safe" encoding is one in which each
 * byte of a multibyte character has the high bit set (it's >= 0x80).  Since
 * all our lexing rules treat all high-bit-set characters alike, we don't
 * really need to care whether such a byte is part of a sequence or not.
 * In an "unsafe" encoding, we still expect the first byte of a multibyte
 * sequence to be >= 0x80, but later bytes might not be.  If we scan such
 * a sequence as-is, the lexing rules could easily be fooled into matching
 * such bytes to ordinary ASCII characters.  Our solution for this is to
 * substitute 0xFF for each non-first byte within the data presented to flex.
 * The flex rules will then pass the FF's through unmolested.  The emit()
 * subroutine is responsible for looking back to the original string and
 * replacing FF's with the corresponding original bytes.
 *
 * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/bin/psql/psqlscan.l,v 1.15 2005/06/26 19:16:06 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres_fe.h"

#include "psqlscan.h"

#include <ctype.h>

#include "mb/pg_wchar.h"

#include "common.h"
#include "settings.h"
#include "variables.h"


/*
 * We use a stack of flex buffers to handle substitution of psql variables.
 * Each stacked buffer contains the as-yet-unread text from one psql variable.
 * When we pop the stack all the way, we resume reading from the outer buffer
 * identified by scanbufhandle.
 */
typedef struct StackElem
{
	YY_BUFFER_STATE buf;		/* flex input control structure */
	char	   *bufstring;		/* data actually being scanned by flex */
	char	   *origstring;		/* copy of original data, if needed */
	struct StackElem *next;
} StackElem;

/*
 * All working state of the lexer must be stored in PsqlScanStateData
 * between calls.  This allows us to have multiple open lexer operations,
 * which is needed for nested include files.  The lexer itself is not
 * recursive, but it must be re-entrant.
 */
typedef struct PsqlScanStateData
{
	StackElem  *buffer_stack;	/* stack of variable expansion buffers */
	/*
	 * These variables always refer to the outer buffer, never to any
	 * stacked variable-expansion buffer.
	 */
	YY_BUFFER_STATE scanbufhandle;
	char	   *scanbuf;		/* start of outer-level input buffer */
	const char *scanline;		/* current input line at outer level */

	/* safe_encoding, curline, refline are used by emit() to replace FFs */
	int			encoding;		/* encoding being used now */
	bool		safe_encoding;	/* is current encoding "safe"? */
	const char *curline;		/* actual flex input string for cur buf */
	const char *refline;		/* original data for cur buffer */

	/*
	 * All this state lives across successive input lines, until explicitly
	 * reset by psql_scan_reset.
	 */
	int			start_state;	/* saved YY_START */
	int			paren_depth;	/* depth of nesting in parentheses */
	int			xcdepth;		/* depth of nesting in slash-star comments */
	char	   *dolqstart;		/* current $foo$ quote start string */
} PsqlScanStateData;

static PsqlScanState cur_state;	/* current state while active */

static PQExpBuffer output_buf;	/* current output buffer */

/* these variables do not need to be saved across calls */
static enum slash_option_type option_type;
static char *option_quote;


/* Return values from yylex() */
#define LEXRES_EOL			0	/* end of input */
#define LEXRES_SEMI			1	/* command-terminating semicolon found */
#define LEXRES_BACKSLASH	2	/* backslash command start */
#define LEXRES_OK			3	/* OK completion of backslash argument */


int	yylex(void);

static void push_new_buffer(const char *newstr);
static YY_BUFFER_STATE prepare_buffer(const char *txt, int len,
									  char **txtcopy);
static void emit(const char *txt, int len);

#define ECHO emit(yytext, yyleng)

%}

%option 8bit
%option never-interactive
%option nodefault
%option nounput
%option noyywrap

/*
 * All of the following definitions and rules should exactly match
 * src/backend/parser/scan.l so far as the flex patterns are concerned.
 * The rule bodies are just ECHO as opposed to what the backend does,
 * however.  (But be sure to duplicate code that affects the lexing process,
 * such as BEGIN().)  Also, psqlscan uses a single <<EOF>> rule whereas
 * scan.l has a separate one for each exclusive state.
 */

/*
 * 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
 *  <xdolq> $foo$ quoted strings
 */

%x xb
%x xc
%x xd
%x xh
%x xq
%x xdolq
/* Additional exclusive states for psql only: lex backslash commands */
%x xslashcmd
%x xslasharg
%x xslashquote
%x xslashbackquote
%x xslashdefaultarg
%x xslashquotedarg
%x xslashwholeline
%x xslashend

/*
 * 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}*)

/*
 * To ensure that {quotecontinue} can be scanned without having to back up
 * if the full pattern isn't matched, we include trailing whitespace in
 * {quotestop}.  This matches all cases where {quotecontinue} fails to match,
 * except for {quote} followed by whitespace and just one "-" (not two,
 * which would start a {comment}).  To cover that we have {quotefail}.
 * The actions for {quotestop} and {quotefail} must throw back characters
 * beyond the quote proper.
 */
quote			'
quotestop		{quote}{whitespace}*
quotecontinue	{quote}{whitespace_with_newline}{quote}
quotefail		{quote}{whitespace}*"-"

/* 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}
xbinside		[^']*

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

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

/* Quoted string that allows backslash escapes */
xestart			[eE]{quote}

/* Extended quote
 * xqdouble implements embedded quote, ''''
 */
xqstart			{quote}
xqdouble		{quote}{quote}
xqinside		[^\\']+
xqescape		[\\][^0-7]
xqoctesc		[\\][0-7]{1,3}
xqhexesc		[\\]x[0-9A-Fa-f]{1,2}

/* $foo$ style quotes ("dollar quoting")
 * The quoted string starts with $foo$ where "foo" is an optional string
 * in the form of an identifier, except that it may not contain "$", 
 * and extends to the first occurrence of an identical string.  
 * There is *no* processing of the quoted text.
 *
 * {dolqfailed} is an error rule to avoid scanner backup when {dolqdelim}
 * fails to match its trailing "$".
 */
dolq_start		[A-Za-z\200-\377_]
dolq_cont		[A-Za-z\200-\377_0-9]
dolqdelim		\$({dolq_start}{dolq_cont}*)?\$
dolqfailed		\${dolq_start}{dolq_cont}*
dolqinside		[^$]+

/* 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
 *
 * {realfail1} and {realfail2} are added to prevent the need for scanner
 * backup when the {real} rule fails to match completely.
 */

integer			{digit}+
decimal			(({digit}*\.{digit}+)|({digit}+\.{digit}*))
real			({integer}|{decimal})[Ee][-+]?{digit}+
realfail1		({integer}|{decimal})[Ee]
realfail2		({integer}|{decimal})[Ee][-+]

param			\${integer}

other			.

/*
 * Dollar quoted strings are totally opaque, and no escaping is done on them.
 * 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.
 */

%%

{whitespace}	{
					/*
					 * Note that the whitespace rule includes both true
					 * whitespace and single-line ("--" style) comments.
					 * We suppress whitespace at the start of the query
					 * buffer.  We also suppress all single-line comments,
					 * which is pretty dubious but is the historical
					 * behavior.
					 */
					if (!(output_buf->len == 0 || yytext[0] == '-'))
						ECHO;
				}

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

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

<xc>{xcstop}	{
					if (cur_state->xcdepth <= 0)
					{
						BEGIN(INITIAL);
					}
					else
						cur_state->xcdepth--;
					ECHO;
				}

<xc>{xcinside}	{
					ECHO;
				}

<xc>{op_chars}	{
					ECHO;
				}

<xc>\*+			{
					ECHO;
				}

{xbstart}		{
					BEGIN(xb);
					ECHO;
				}
<xb>{quotestop}	|
<xb>{quotefail} {
					yyless(1);
					BEGIN(INITIAL);
					ECHO;
				}
<xh>{xhinside}	|
<xb>{xbinside}	{
					ECHO;
				}
<xh>{quotecontinue}	|
<xb>{quotecontinue}	{
					ECHO;
				}

{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.
					 */
					BEGIN(xh);
					ECHO;
				}
<xh>{quotestop}	|
<xh>{quotefail} {
					yyless(1);
					BEGIN(INITIAL);
					ECHO;
				}

{xnstart}		{
					yyless(1);				/* eat only 'n' this time */
					ECHO;
				}

{xqstart}		{
					BEGIN(xq);
					ECHO;
				}
{xestart}		{
					BEGIN(xq);
					ECHO;
				}
<xq>{quotestop}	|
<xq>{quotefail} {
					yyless(1);
					BEGIN(INITIAL);
					ECHO;
				}
<xq>{xqdouble}  {
					ECHO;
				}
<xq>{xqinside}  {
					ECHO;
				}
<xq>{xqescape}  {
					ECHO;
				}
<xq>{xqoctesc}  {
					ECHO;
				}
<xq>{xqhexesc}  {
					ECHO;
				}
<xq>{quotecontinue} {
					ECHO;
				}
<xq>.			{
					/* This is only needed for \ just before EOF */
					ECHO;
				}

{dolqdelim}		{
					cur_state->dolqstart = pg_strdup(yytext);
					BEGIN(xdolq);
					ECHO;
				}
{dolqfailed}	{
					/* throw back all but the initial "$" */
					yyless(1);
					ECHO;
				}
<xdolq>{dolqdelim} {
					if (strcmp(yytext, cur_state->dolqstart) == 0)
					{
						free(cur_state->dolqstart);
						cur_state->dolqstart = NULL;
						BEGIN(INITIAL);
					}
					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$
						 */
						yyless(yyleng-1);
					}
					ECHO;
				}
<xdolq>{dolqinside} {
					ECHO;
				}
<xdolq>{dolqfailed} {
					ECHO;
				}
<xdolq>.		{
					/* This is only needed for $ inside the quoted text */
					ECHO;
				}

{xdstart}		{
					BEGIN(xd);
					ECHO;
				}
<xd>{xdstop}	{
					BEGIN(INITIAL);
					ECHO;
				}
<xd>{xddouble}	{
					ECHO;
				}
<xd>{xdinside}	{
					ECHO;
				}

{typecast}		{
					ECHO;
				}