Commit d41473f3 authored by unknown's avatar unknown
Browse files

Fix error in parsing string literals containing a backslash followed 

by a multi-byte character with a second byte of 0x5c (\). (Bug #8903)


sql/sql_lex.cc:
  Fix lex error when multi-byte character containing 0x5c (\) follows a
  backslash
mysql-test/t/ctype_sjis.test:
  Add regression test for Bug #8303
mysql-test/r/ctype_sjis.result:
  Add test results
parent d743b102

mysql-test/r/ctype_sjis.result

+4 −0
Original line number Diff line number Diff line
@@ -91,3 +91,7 @@ sjis_bin 6109 
sjis_bin	61

sjis_bin	6120

drop table t1;

SET NAMES sjis;

SELECT HEX('佐淘 \圭') FROM DUAL;

HEX('佐淘 ＼圭')

8DB2939181408C5C

mysql-test/t/ctype_sjis.test

+7 −0
Original line number Diff line number Diff line
@@ -68,3 +68,10 @@ SET collation_connection='sjis_japanese_ci'; 
-- source include/ctype_filesort.inc

SET collation_connection='sjis_bin';

-- source include/ctype_filesort.inc



# Check parsing of string literals in SJIS with multibyte characters that

# have an embedded \ in them. (Bug #8303)



--character_set sjis

SET NAMES sjis;

SELECT HEX('@\\') FROM DUAL;

sql/sql_lex.cc

+26 −6
Original line number Diff line number Diff line
@@ -295,6 +295,17 @@ static char *get_text(LEX *lex) 
      found_escape=1;

      if (lex->ptr == lex->end_of_query)

	return 0;

#ifdef USE_MB

      int l;

      if (use_mb(cs) &&

          (l = my_ismbchar(cs,

                           (const char *)lex->ptr,

                           (const char *)lex->end_of_query))) {

          lex->ptr += l;

          continue;

      }

      else

#endif

        yySkip();

    }

    else if (c == sep)
@@ -323,6 +334,10 @@ static char *get_text(LEX *lex) 
      else

      {

	uchar *to;



        /* Re-use found_escape for tracking state of escapes */

        found_escape= 0;



	for (to=start ; str != end ; str++)

	{

#ifdef USE_MB
@@ -336,7 +351,7 @@ static char *get_text(LEX *lex) 
	      continue;

	  }

#endif

	  if (*str == '\\' && str+1 != end)

	  if (!found_escape && *str == '\\' && str+1 != end)

	  {

	    switch(*++str) {

	    case 'n':
@@ -362,15 +377,20 @@ static char *get_text(LEX *lex) 
	      *to++= '\\';		// remember prefix for wildcard

	      /* Fall through */

	    default:

	      *to++ = *str;

              found_escape= 1;

              str--;

	      break;

	    }

	  }

	  else if (*str == sep)

	    *to++= *str++;		// Two ' or "

	  else if (!found_escape && *str == sep)

          {

            found_escape= 1;

          }

	  else

          {

	    *to++ = *str;



            found_escape= 0;

          }

	}

	*to=0;

	lex->yytoklen=(uint) (to-start);