diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l index b86b67cc0c..b09187a2c0 100644 --- a/src/backend/parser/scan.l +++ b/src/backend/parser/scan.l @@ -24,7 +24,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.165 2010/01/02 16:57:50 momjian Exp $ + * $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.166 2010/01/16 17:39:55 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -1137,7 +1137,7 @@ process_integer_literal(const char *token, YYSTYPE *lval) return ICONST; } -static int +static unsigned int hexval(unsigned char c) { if (c >= '0' && c <= '9') @@ -1194,7 +1194,7 @@ addunicode(pg_wchar c, core_yyscan_t yyscanner) 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); + unicode_to_utf8(c, (unsigned char *) buf); addlit(buf, pg_mblen(buf), yyscanner); } @@ -1241,9 +1241,17 @@ litbuf_udeescape(unsigned char escape, core_yyscan_t yyscanner) *out++ = escape; in += 2; } - else if (isxdigit(in[1]) && isxdigit(in[2]) && isxdigit(in[3]) && isxdigit(in[4])) + else if (isxdigit((unsigned char) in[1]) && + isxdigit((unsigned char) in[2]) && + isxdigit((unsigned char) in[3]) && + isxdigit((unsigned char) in[4])) { - pg_wchar unicode = hexval(in[1]) * 16*16*16 + hexval(in[2]) * 16*16 + hexval(in[3]) * 16 + hexval(in[4]); + pg_wchar unicode; + + unicode = (hexval(in[1]) << 12) + + (hexval(in[2]) << 8) + + (hexval(in[3]) << 4) + + hexval(in[4]); check_unicode_value(unicode, in, yyscanner); if (pair_first) { @@ -1270,13 +1278,22 @@ litbuf_udeescape(unsigned char escape, core_yyscan_t yyscanner) } in += 5; } - else if (in[1] == '+' - && isxdigit(in[2]) && isxdigit(in[3]) - && isxdigit(in[4]) && isxdigit(in[5]) - && isxdigit(in[6]) && isxdigit(in[7])) + else if (in[1] == '+' && + isxdigit((unsigned char) in[2]) && + isxdigit((unsigned char) in[3]) && + isxdigit((unsigned char) in[4]) && + isxdigit((unsigned char) in[5]) && + isxdigit((unsigned char) in[6]) && + isxdigit((unsigned char) in[7])) { - pg_wchar unicode = hexval(in[2]) * 16*16*16*16*16 + hexval(in[3]) * 16*16*16*16 + hexval(in[4]) * 16*16*16 - + hexval(in[5]) * 16*16 + hexval(in[6]) * 16 + hexval(in[7]); + pg_wchar unicode; + + unicode = (hexval(in[2]) << 20) + + (hexval(in[3]) << 16) + + (hexval(in[4]) << 12) + + (hexval(in[5]) << 8) + + (hexval(in[6]) << 4) + + hexval(in[7]); check_unicode_value(unicode, in, yyscanner); if (pair_first) {