@ -106,6 +106,18 @@ const uint16 ScanKeywordTokens[] = {
*/
#define ADVANCE_YYLLOC(delta) ( *(yylloc) += (delta) )
/*
* Sometimes, we do want yylloc to point into the middle of a token; this is
* useful for instance to throw an error about an escape sequence within a
* string literal. But if we find no error there, we want to revert yylloc
* to the token start, so that that's the location reported to the parser.
* Use PUSH_YYLLOC/POP_YYLLOC to save/restore yylloc around such code.
* (Currently the implied "stack" is just one location, but someday we might
* need to nest these.)
*/
#define PUSH_YYLLOC() (yyextra->save_yylloc = *(yylloc))
#define POP_YYLLOC() (*(yylloc) = yyextra->save_yylloc)
#define startlit() ( yyextra->literallen = 0 )
static void addlit(char *ytext, int yleng, core_yyscan_t yyscanner);
static void addlitchar(unsigned char ychar, core_yyscan_t yyscanner);
@ -605,8 +617,18 @@ other .
<xe>{xeunicode} {
pg_wchar c = strtoul(yytext + 2, NULL, 16);
/*
* For consistency with other productions, issue any
* escape warning with cursor pointing to start of string.
* We might want to change that, someday.
*/
check_escape_warning(yyscanner);
/* Remember start of overall string token ... */
PUSH_YYLLOC();
/* ... and set the error cursor to point at this esc seq */
SET_YYLLOC();
if (is_utf16_surrogate_first(c))
{
yyextra->utf16_first_part = c;
@ -616,10 +638,18 @@ other .
yyerror("invalid Unicode surrogate pair");
else
addunicode(c, yyscanner);
/* Restore yylloc to be start of string token */
POP_YYLLOC();
}
<xeu>{xeunicode} {
pg_wchar c = strtoul(yytext + 2, NULL, 16);
/* Remember start of overall string token ... */
PUSH_YYLLOC();
/* ... and set the error cursor to point at this esc seq */
SET_YYLLOC();
if (!is_utf16_surrogate_second(c))
yyerror("invalid Unicode surrogate pair");
@ -627,12 +657,21 @@ other .
addunicode(c, yyscanner);
/* Restore yylloc to be start of string token */
POP_YYLLOC();
BEGIN(xe);
}
<xeu>. { yyerror("invalid Unicode surrogate pair"); }
<xeu>\n { yyerror("invalid Unicode surrogate pair"); }
<xeu><<EOF>> { yyerror("invalid Unicode surrogate pair"); }
<xeu>. |
<xeu>\n |
<xeu><<EOF>> {
/* Set the error cursor to point at missing esc seq */
SET_YYLLOC();
yyerror("invalid Unicode surrogate pair");
}
<xe,xeu>{xeunicodefail} {
/* Set the error cursor to point at malformed esc seq */
SET_YYLLOC();
ereport(ERROR,
(errcode(ERRCODE_INVALID_ESCAPE_SEQUENCE),
errmsg("invalid Unicode escape"),
@ -1029,12 +1068,13 @@ other .
* scanner_errposition
* Report a lexer or grammar error cursor position, if possible.
*
* This is expected to be used within an ereport() call. The return value
* This is expected to be used within an ereport() call, or via an error
* callback such as setup_scanner_errposition_callback(). The return value
* is a dummy (always 0, in fact).
*
* Note that this can only be used for messages emitted during raw parsing
* (essentially, scan.l and gram.y), since it requires the yyscanner struct
* to still be available.
* (essentially, scan.l, parser.c, and gram.y), since it requires the
* yyscanner struct to still be available.
*/
int
scanner_errposition(int location, core_yyscan_t yyscanner)
@ -1050,6 +1090,62 @@ scanner_errposition(int location, core_yyscan_t yyscanner)
return errposition(pos);
}
/*
* Error context callback for inserting scanner error location.
*
* Note that this will be called for *any* error occurring while the
* callback is installed. We avoid inserting an irrelevant error location
* if the error is a query cancel --- are there any other important cases?
*/
static void
scb_error_callback(void *arg)
{
ScannerCallbackState *scbstate = (ScannerCallbackState *) arg;
if (geterrcode() != ERRCODE_QUERY_CANCELED)
(void) scanner_errposition(scbstate->location, scbstate->yyscanner);
}
/*
* setup_scanner_errposition_callback
* Arrange for non-scanner errors to report an error position
*
* Sometimes the scanner calls functions that aren't part of the scanner
* subsystem and can't reasonably be passed the yyscanner pointer; yet
* we would like any errors thrown in those functions to be tagged with an
* error location. Use this function to set up an error context stack
* entry that will accomplish that. Usage pattern:
*
* declare a local variable "ScannerCallbackState scbstate"
* ...
* setup_scanner_errposition_callback(&scbstate, yyscanner, location);
* call function that might throw error;
* cancel_scanner_errposition_callback(&scbstate);
*/
void
setup_scanner_errposition_callback(ScannerCallbackState *scbstate,
core_yyscan_t yyscanner,
int location)
{
/* Setup error traceback support for ereport() */
scbstate->yyscanner = yyscanner;
scbstate->location = location;
scbstate->errcallback.callback = scb_error_callback;
scbstate->errcallback.arg = (void *) scbstate;
scbstate->errcallback.previous = error_context_stack;
error_context_stack = &scbstate->errcallback;
}
/*
* Cancel a previously-set-up errposition callback.
*/
void
cancel_scanner_errposition_callback(ScannerCallbackState *scbstate)
{
/* Pop the error context stack */
error_context_stack = scbstate->errcallback.previous;
}
/*
* scanner_yyerror
* Report a lexer or grammar error.
@ -1226,19 +1322,20 @@ process_integer_literal(const char *token, YYSTYPE *lval)
static void
addunicode(pg_wchar c, core_yyscan_t yyscanner)
{
char buf[8];
ScannerCallbackState scbstate;
char buf[MAX_UNICODE_EQUIVALENT_STRING + 1];
/* See also check_unicode_value() in parser.c */
if (c == 0 || c > 0x10FFFF)
if (!is_valid_unicode_codepoint(c))
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);
/*
* We expect that pg_unicode_to_server() will complain about any
* unconvertible code point, so we don't have to set saw_non_ascii.
*/
setup_scanner_errposition_callback(&scbstate, yyscanner, *(yylloc));
pg_unicode_to_server(c, (unsigned char *) buf);
cancel_scanner_errposition_callback(&scbstate);
addlit(buf, strlen(buf), yyscanner);
}
static unsigned char
Tom Lane
5 years ago