mirror of
https://github.com/postgres/postgres.git
synced 2025-07-28 23:42:10 +03:00
Unicode escapes in E'...' strings
Author: Marko Kreen <markokr@gmail.com>
This commit is contained in:
Peter Eisentraut
@ -24,7 +24,7 @@
|
||||
* Portions Copyright (c) 1994, Regents of the University of California
|
||||
*
|
||||
* IDENTIFICATION
|
||||
* $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.158 2009/09/21 22:22:07 petere Exp $
|
||||
* $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.159 2009/09/22 23:52:53 petere Exp $
|
||||
*
|
||||
*-------------------------------------------------------------------------
|
||||
*/
|
||||
@ -80,6 +80,9 @@ static void addlitchar(unsigned char ychar, base_yyscan_t yyscanner);
|
||||
static char *litbufdup(base_yyscan_t yyscanner);
|
||||
static char *litbuf_udeescape(unsigned char escape, base_yyscan_t yyscanner);
|
||||
static unsigned char unescape_single_char(unsigned char c, base_yyscan_t yyscanner);
|
||||
static bool is_utf16_surrogate_first(pg_wchar c);
|
||||
static bool is_utf16_surrogate_second(pg_wchar c);
|
||||
static pg_wchar surrogate_pair_to_codepoint(pg_wchar first, pg_wchar second);
|
||||
|
||||
#define yyerror(msg) scanner_yyerror(msg, yyscanner)
|
||||
|
||||
@ -97,6 +100,8 @@ static void check_escape_warning(base_yyscan_t yyscanner);
|
||||
extern int base_yyget_column(yyscan_t yyscanner);
|
||||
extern void base_yyset_column(int column_no, yyscan_t yyscanner);
|
||||
|
||||
static void addunicode(pg_wchar c, yyscan_t yyscanner);
|
||||
|
||||
%}
|
||||
|
||||
%option reentrant
|
||||
@ -134,6 +139,7 @@ extern void base_yyset_column(int column_no, yyscan_t yyscanner);
|
||||
* <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
|
||||
@ -145,6 +151,7 @@ extern void base_yyset_column(int column_no, yyscan_t yyscanner);
|
||||
%x xdolq
|
||||
%x xui
|
||||
%x xus
|
||||
%x xeu
|
||||
|
||||
/*
|
||||
* In order to make the world safe for Windows and Mac clients as well as
|
||||
@ -223,6 +230,8 @@ 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})
|
||||
xeunicodebad [\\]([uU])
|
||||
|
||||
/* Extended quote
|
||||
* xqdouble implements embedded quote, ''''
|
||||
@ -535,6 +544,45 @@ other .
|
||||
<xe>{xeinside} {
|
||||
addlit(yytext, yyleng, yyscanner);
|
||||
}
|
||||
<xe>{xeunicode} {
|
||||
pg_wchar c = strtoul(yytext+2, NULL, 16);
|
||||
|
||||
check_escape_warning(yyscanner);
|
||||
|
||||
if (is_utf16_surrogate_first(c))
|
||||
{
|
||||
yyextra->utf16_first_part = c;
|
||||
BEGIN(xeu);
|
||||
}
|
||||
else if (is_utf16_surrogate_second(c))
|
||||
yyerror("invalid Unicode surrogate pair");
|
||||
else
|
||||
addunicode(c, yyscanner);
|
||||
}
|
||||
<xeu>{xeunicode} {
|
||||
pg_wchar c = strtoul(yytext+2, NULL, 16);
|
||||
|
||||
if (!is_utf16_surrogate_second(c))
|
||||
yyerror("invalid Unicode surrogate pair");
|
||||
|
||||
c = surrogate_pair_to_codepoint(yyextra->utf16_first_part, c);
|
||||
|
||||
addunicode(c, yyscanner);
|
||||
|
||||
BEGIN(xe);
|
||||
}
|
||||
<xeu>. |
|
||||
<xeu>\n |
|
||||
<xeu><<EOF>> { yyerror("invalid Unicode surrogate pair"); }
|
||||
|
||||
<xe>{xeunicodebad} {
|
||||
ereport(ERROR,
|
||||
(errcode(ERRCODE_INVALID_ESCAPE_SEQUENCE),
|
||||
errmsg("invalid Unicode escape"),
|
||||
errhint("Unicode escapes must be \\uXXXX or \\UXXXXXXXX."),
|
||||
lexer_errposition()));
|
||||
}
|
||||
|
||||
<xe>{xeescape} {
|
||||
if (yytext[1] == '\'')
|
||||
{
|
||||
@ -1330,3 +1378,21 @@ base_yyfree(void *ptr, base_yyscan_t yyscanner)
|
||||
if (ptr)
|
||||
pfree(ptr);
|
||||
}
|
||||
|
||||
static void
|
||||
addunicode(pg_wchar c, base_yyscan_t yyscanner)
|
||||
{
|
||||
char buf[8];
|
||||
|
||||
if (c == 0 || c > 0x10FFFF)
|
||||
yyerror("invalid Unicode escape value");
|
||||
if (c > 0x7F)
|
||||
{
|
||||
if (GetDatabaseEncoding() != PG_UTF8)
|
||||
yyerror("Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8");
|
||||
yyextra->saw_non_ascii = true;
|
||||
}
|
||||
unicode_to_utf8(c, (unsigned char *)buf);
|
||||
addlit(buf, pg_mblen(buf), yyscanner);
|
||||
}
|
||||
|
||||
|
||||
@ -11,7 +11,7 @@
|
||||
* Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
|
||||
* Portions Copyright (c) 1994, Regents of the University of California
|
||||
*
|
||||
* $PostgreSQL: pgsql/src/include/parser/gramparse.h,v 1.47 2009/07/14 20:24:10 tgl Exp $
|
||||
* $PostgreSQL: pgsql/src/include/parser/gramparse.h,v 1.48 2009/09/22 23:52:53 petere Exp $
|
||||
*
|
||||
*-------------------------------------------------------------------------
|
||||
*/
|
||||
@ -71,6 +71,9 @@ typedef struct base_yy_extra_type
|
||||
int xcdepth; /* depth of nesting in slash-star comments */
|
||||
char *dolqstart; /* current $foo$ quote start string */
|
||||
|
||||
/* first part of UTF16 surrogate pair for Unicode escapes */
|
||||
int32 utf16_first_part;
|
||||
|
||||
/* state variables for literal-lexing warnings */
|
||||
bool warn_on_first_escape;
|
||||
bool saw_non_ascii;
|
||||
|
||||
Reference in New Issue
Block a user