mirror of
https://github.com/postgres/postgres.git
synced 2025-04-22 23:02:54 +03:00
Sync psql's scanner with recent changes in backend scanner's flex rules.
Marko Kreen, Tom Lane
This commit is contained in:
parent
3686bcb9c9
commit
799ac99201
@ -24,7 +24,7 @@
|
||||
* Portions Copyright (c) 1994, Regents of the University of California
|
||||
*
|
||||
* IDENTIFICATION
|
||||
* $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.161 2009/09/25 21:13:06 petere Exp $
|
||||
* $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.162 2009/09/27 03:27:23 tgl Exp $
|
||||
*
|
||||
*-------------------------------------------------------------------------
|
||||
*/
|
||||
@ -571,10 +571,9 @@ other .
|
||||
|
||||
BEGIN(xe);
|
||||
}
|
||||
<xeu>. |
|
||||
<xeu>\n |
|
||||
<xeu>. { yyerror("invalid Unicode surrogate pair"); }
|
||||
<xeu>\n { yyerror("invalid Unicode surrogate pair"); }
|
||||
<xeu><<EOF>> { yyerror("invalid Unicode surrogate pair"); }
|
||||
|
||||
<xe,xeu>{xeunicodefail} {
|
||||
ereport(ERROR,
|
||||
(errcode(ERRCODE_INVALID_ESCAPE_SEQUENCE),
|
||||
@ -582,7 +581,6 @@ other .
|
||||
errhint("Unicode escapes must be \\uXXXX or \\UXXXXXXXX."),
|
||||
lexer_errposition()));
|
||||
}
|
||||
|
||||
<xe>{xeescape} {
|
||||
if (yytext[1] == '\'')
|
||||
{
|
||||
|
@ -33,7 +33,7 @@
|
||||
* Portions Copyright (c) 1994, Regents of the University of California
|
||||
*
|
||||
* IDENTIFICATION
|
||||
* $PostgreSQL: pgsql/src/bin/psql/psqlscan.l,v 1.28 2009/01/01 17:23:55 momjian Exp $
|
||||
* $PostgreSQL: pgsql/src/bin/psql/psqlscan.l,v 1.29 2009/09/27 03:27:24 tgl Exp $
|
||||
*
|
||||
*-------------------------------------------------------------------------
|
||||
*/
|
||||
@ -117,6 +117,7 @@ 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);
|
||||
static bool is_utf16_surrogate_first(uint32 c);
|
||||
|
||||
#define ECHO emit(yytext, yyleng)
|
||||
|
||||
@ -158,6 +159,7 @@ static void emit(const char *txt, int len);
|
||||
* <xdolq> $foo$ quoted strings
|
||||
* <xui> quoted identifier with Unicode escapes
|
||||
* <xus> quoted string with Unicode escapes
|
||||
* <xeu> Unicode surrogate pair in extended quoted string
|
||||
*/
|
||||
|
||||
%x xb
|
||||
@ -169,6 +171,7 @@ static void emit(const char *txt, int len);
|
||||
%x xdolq
|
||||
%x xui
|
||||
%x xus
|
||||
%x xeu
|
||||
/* Additional exclusive states for psql only: lex backslash commands */
|
||||
%x xslashcmd
|
||||
%x xslasharg
|
||||
@ -192,6 +195,9 @@ static void emit(const char *txt, int len);
|
||||
* did not end with a newline.
|
||||
*
|
||||
* XXX perhaps \f (formfeed) should be treated as a newline as well?
|
||||
*
|
||||
* XXX if you change the set of whitespace characters, fix scanner_isspace()
|
||||
* to agree, and see also the plpgsql lexer.
|
||||
*/
|
||||
|
||||
space [ \t\n\r\f]
|
||||
@ -253,6 +259,8 @@ xeinside [^\\']+
|
||||
xeescape [\\][^0-7]
|
||||
xeoctesc [\\][0-7]{1,3}
|
||||
xehexesc [\\]x[0-9A-Fa-f]{1,2}
|
||||
xeunicode [\\](u[0-9A-Fa-f]{4}|U[0-9A-Fa-f]{8})
|
||||
xeunicodefail [\\](u[0-9A-Fa-f]{0,3}|U[0-9A-Fa-f]{0,7})
|
||||
|
||||
/* Extended quote
|
||||
* xqdouble implements embedded quote, ''''
|
||||
@ -334,6 +342,10 @@ identifier {ident_start}{ident_cont}*
|
||||
|
||||
typecast "::"
|
||||
|
||||
/* these two token types are used by PL/pgsql, though not in core SQL */
|
||||
dot_dot \.\.
|
||||
colon_equals ":="
|
||||
|
||||
/*
|
||||
* "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,
|
||||
@ -511,6 +523,22 @@ other .
|
||||
<xe>{xeinside} {
|
||||
ECHO;
|
||||
}
|
||||
<xe>{xeunicode} {
|
||||
uint32 c = strtoul(yytext+2, NULL, 16);
|
||||
|
||||
if (is_utf16_surrogate_first(c))
|
||||
BEGIN(xeu);
|
||||
ECHO;
|
||||
}
|
||||
<xeu>{xeunicode} {
|
||||
BEGIN(xe);
|
||||
ECHO;
|
||||
}
|
||||
<xeu>. { ECHO; }
|
||||
<xeu>\n { ECHO; }
|
||||
<xe,xeu>{xeunicodefail} {
|
||||
ECHO;
|
||||
}
|
||||
<xe>{xeescape} {
|
||||
ECHO;
|
||||
}
|
||||
@ -605,6 +633,14 @@ other .
|
||||
ECHO;
|
||||
}
|
||||
|
||||
{dot_dot} {
|
||||
ECHO;
|
||||
}
|
||||
|
||||
{colon_equals} {
|
||||
ECHO;
|
||||
}
|
||||
|
||||
/*
|
||||
* These rules are specific to psql --- they implement parenthesis
|
||||
* counting and detection of command-ending semicolon. These must
|
||||
@ -1690,3 +1726,9 @@ emit(const char *txt, int len)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static bool
|
||||
is_utf16_surrogate_first(uint32 c)
|
||||
{
|
||||
return (c >= 0xD800 && c <= 0xDBFF);
|
||||
}
|
||||
|
Loading…
x
Reference in New Issue
Block a user