diff options
Diffstat (limited to 'src/backend/parser')
| -rw-r--r-- | src/backend/parser/scan.l | 60 |
1 files changed, 57 insertions, 3 deletions
diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l index caab9a002cf..b788a42bc98 100644 --- a/src/backend/parser/scan.l +++ b/src/backend/parser/scan.l @@ -10,7 +10,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.114 2004/02/21 00:34:52 tgl Exp $ + * $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.115 2004/02/24 21:45:18 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -37,6 +37,7 @@ extern YYSTYPE yylval; static int xcdepth = 0; /* depth of nesting in slash-star comments */ +static char *dolqstart; /* current $foo$ quote start string */ /* * literalbuf is used to accumulate literal values when multiple rules @@ -74,6 +75,7 @@ unsigned char unescape_single_char(unsigned char c); %option 8bit %option never-interactive +%option nodefault %option nounput %option noyywrap %option prefix="base_yy" @@ -94,6 +96,7 @@ unsigned char unescape_single_char(unsigned char c); * <xd> delimited identifiers (double-quoted identifiers) * <xh> hexadecimal numeric string * <xq> quoted strings + * <xdolq> $foo$ quoted strings */ %x xb @@ -101,6 +104,7 @@ unsigned char unescape_single_char(unsigned char c); %x xd %x xh %x xq +%x xdolq /* * In order to make the world safe for Windows and Mac clients as well as @@ -175,6 +179,17 @@ xqescape [\\][^0-7] xqoctesc [\\][0-7]{1,3} xqcat {quote}{whitespace_with_newline}{quote} +/* $foo$ 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 "$", + * and extends to the first occurrence of an identical string. + * There is *no* processing of the quoted text. + */ +dolq_start [A-Za-z\200-\377_] +dolq_cont [A-Za-z\200-\377_0-9] +dolqdelim \$({dolq_start}{dolq_cont}*)?\$ +dolqinside [^$]+ + /* Double quote * Allows embedded spaces and other special characters into identifiers. */ @@ -242,7 +257,8 @@ param \${integer} other . /* - * Quoted strings must allow some special characters such as single-quote + * 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 @@ -388,8 +404,46 @@ other . <xq>{xqcat} { /* 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(); + } +<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>. { + /* 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); @@ -407,7 +461,7 @@ other . yylval.str = ident; return IDENT; } -<xd>{xddouble} { +<xd>{xddouble} { addlitchar('"'); } <xd>{xdinside} { |