static int lex_one_token()

in sql/sql_lex.cc [1416:2156]


static int lex_one_token(YYSTYPE *yylval, THD *thd)
{
  uchar c= 0;
  bool comment_closed;
  int tokval, result_state;
  uint length;
  enum my_lex_states state;
  Lex_input_stream *lip= & thd->m_parser_state->m_lip;
  const CHARSET_INFO *cs= thd->charset();
  const my_lex_states *state_map= cs->state_maps->main_map;
  const uchar *ident_map= cs->ident_map;

  lip->yylval=yylval;			// The global state

  lip->start_token();
  state=lip->next_state;
  lip->next_state=MY_LEX_START;
  for (;;)
  {
    switch (state) {
    case MY_LEX_START:			// Start of token
      // Skip starting whitespace
      while(state_map[c= lip->yyPeek()] == MY_LEX_SKIP)
      {
	if (c == '\n')
	  lip->yylineno++;

        lip->yySkip();
      }

      /* Start of real token */
      lip->restart_token();
      c= lip->yyGet();
      state= state_map[c];
      break;
    case MY_LEX_CHAR:			// Unknown or single char token
    case MY_LEX_SKIP:			// This should not happen
      if (c == '-' && lip->yyPeek() == '-' &&
          (my_isspace(cs,lip->yyPeekn(1)) ||
           my_iscntrl(cs,lip->yyPeekn(1))))
      {
        state=MY_LEX_COMMENT;
        break;
      }

      if (c == '-' && lip->yyPeek() == '>')    // '->'
      {
        lip->yySkip();
        lip->next_state= MY_LEX_START;
        if (lip->yyPeek() == '>')
        {
          lip->yySkip();
          return JSON_UNQUOTED_SEPARATOR_SYM;
        }
        return JSON_SEPARATOR_SYM;
      }

      if (c != ')')
	lip->next_state= MY_LEX_START;	// Allow signed numbers

      if (c == ',')
      {
        /*
          Warning:
          This is a work around, to make the "remember_name" rule in
          sql/sql_yacc.yy work properly.
          The problem is that, when parsing "select expr1, expr2",
          the code generated by bison executes the *pre* action
          remember_name (see select_item) *before* actually parsing the
          first token of expr2.
        */
        lip->restart_token();
      }
      else
      {
        /*
          Check for a placeholder: it should not precede a possible identifier
          because of binlogging: when a placeholder is replaced with
          its value in a query for the binlog, the query must stay
          grammatically correct.
        */
        if (c == '?' && lip->stmt_prepare_mode && !ident_map[lip->yyPeek()])
        return(PARAM_MARKER);
      }

      return((int) c);

    case MY_LEX_IDENT_OR_NCHAR:
      if (lip->yyPeek() != '\'')
      {
	state= MY_LEX_IDENT;
	break;
      }
      /* Found N'string' */
      lip->yySkip();                         // Skip '
      if (!(yylval->lex_str.str = get_text(lip, 2, 1)))
      {
	state= MY_LEX_CHAR;             // Read char by char
	break;
      }
      yylval->lex_str.length= lip->yytoklen;
      return(NCHAR_STRING);

    case MY_LEX_IDENT_OR_HEX:
      if (lip->yyPeek() == '\'')
      {					// Found x'hex-number'
	state= MY_LEX_HEX_NUMBER;
	break;
      }
      // Fall through.
    case MY_LEX_IDENT_OR_BIN:
      if (lip->yyPeek() == '\'')
      {                                 // Found b'bin-number'
        state= MY_LEX_BIN_NUMBER;
        break;
      }
      // Fall through.
    case MY_LEX_IDENT:
      const char *start;
      if (use_mb(cs))
      {
	result_state= IDENT_QUOTED;
        switch (my_mbcharlen(cs, lip->yyGetLast()))
        {
        case 1:
          break;
        case 0:
          if (my_mbmaxlenlen(cs) < 2)
            break;
          /* else fall through */
        default:
          int l = my_ismbchar(cs,
                              lip->get_ptr() -1,
                              lip->get_end_of_query());
          if (l == 0) {
            state = MY_LEX_CHAR;
            continue;
          }
          lip->skip_binary(l - 1);
        }
        while (ident_map[c=lip->yyGet()])
        {
          switch (my_mbcharlen(cs, c))
          {
          case 1:
            break;
          case 0:
            if (my_mbmaxlenlen(cs) < 2)
              break;
            /* else fall through */
          default:
            int l;
            if ((l = my_ismbchar(cs,
                                 lip->get_ptr() -1,
                                 lip->get_end_of_query())) == 0)
              break;
            lip->skip_binary(l-1);
          }
        }
      }
      else
      {
        for (result_state= c; ident_map[c= lip->yyGet()]; result_state|= c) ;
        /* If there were non-ASCII characters, mark that we must convert */
        result_state= result_state & 0x80 ? IDENT_QUOTED : IDENT;
      }
      length= lip->yyLength();
      start= lip->get_ptr();
      if (lip->ignore_space)
      {
        /*
          If we find a space then this can't be an identifier. We notice this
          below by checking start != lex->ptr.
        */
        for (; state_map[c] == MY_LEX_SKIP ; c= lip->yyGet())
        {
          if (c == '\n')
            lip->yylineno++;
        }
      }
      if (start == lip->get_ptr() && c == '.' && ident_map[lip->yyPeek()])
	lip->next_state=MY_LEX_IDENT_SEP;
      else
      {					// '(' must follow directly if function
        lip->yyUnget();
	if ((tokval = find_keyword(lip, length, c == '(')))
	{
	  lip->next_state= MY_LEX_START;	// Allow signed numbers
	  return(tokval);		// Was keyword
	}
        lip->yySkip();                  // next state does a unget
      }
      yylval->lex_str=get_token(lip, 0, length);

      /*
         Note: "SELECT _bla AS 'alias'"
         _bla should be considered as a IDENT if charset haven't been found.
         So we don't use MYF(MY_WME) with get_charset_by_csname to avoid
         producing an error.
      */

      if (yylval->lex_str.str[0] == '_')
      {
        CHARSET_INFO *cs= get_charset_by_csname(yylval->lex_str.str + 1,
                                                MY_CS_PRIMARY, MYF(0));
        if (cs)
        {
          yylval->charset= cs;
          lip->m_underscore_cs= cs;

          lip->body_utf8_append(lip->m_cpp_text_start,
                                lip->get_cpp_tok_start() + length);
          return(UNDERSCORE_CHARSET);
        }
      }

      lip->body_utf8_append(lip->m_cpp_text_start);

      lip->body_utf8_append_literal(thd, &yylval->lex_str, cs,
                                    lip->m_cpp_text_end);

      return(result_state);			// IDENT or IDENT_QUOTED

    case MY_LEX_IDENT_SEP:		// Found ident and now '.'
      yylval->lex_str.str= (char*) lip->get_ptr();
      yylval->lex_str.length= 1;
      c= lip->yyGet();                  // should be '.'
      lip->next_state= MY_LEX_IDENT_START;// Next is an ident (not a keyword)
      if (!ident_map[lip->yyPeek()])            // Probably ` or "
	lip->next_state= MY_LEX_START;
      return((int) c);

    case MY_LEX_NUMBER_IDENT:		// number or ident which num-start
      if (lip->yyGetLast() == '0')
      {
        c= lip->yyGet();
        if (c == 'x')
        {
          while (my_isxdigit(cs,(c = lip->yyGet()))) ;
          if ((lip->yyLength() >= 3) && !ident_map[c])
          {
            /* skip '0x' */
            yylval->lex_str=get_token(lip, 2, lip->yyLength()-2);
            return (HEX_NUM);
          }
          lip->yyUnget();
          state= MY_LEX_IDENT_START;
          break;
        }
        else if (c == 'b')
        {
          while ((c= lip->yyGet()) == '0' || c == '1') ;
          if ((lip->yyLength() >= 3) && !ident_map[c])
          {
            /* Skip '0b' */
            yylval->lex_str= get_token(lip, 2, lip->yyLength()-2);
            return (BIN_NUM);
          }
          lip->yyUnget();
          state= MY_LEX_IDENT_START;
          break;
        }
        lip->yyUnget();
      }

      while (my_isdigit(cs, (c = lip->yyGet()))) ;
      if (!ident_map[c])
      {					// Can't be identifier
	state=MY_LEX_INT_OR_REAL;
	break;
      }
      if (c == 'e' || c == 'E')
      {
	// The following test is written this way to allow numbers of type 1e1
        if (my_isdigit(cs,lip->yyPeek()) ||
            (c=(lip->yyGet())) == '+' || c == '-')
	{				// Allow 1E+10
          if (my_isdigit(cs,lip->yyPeek()))     // Number must have digit after sign
	  {
            lip->yySkip();
            while (my_isdigit(cs,lip->yyGet())) ;
            yylval->lex_str=get_token(lip, 0, lip->yyLength());
	    return(FLOAT_NUM);
	  }
	}
        lip->yyUnget();
      }
      // fall through
    case MY_LEX_IDENT_START:			// We come here after '.'
      result_state= IDENT;
      if (use_mb(cs))
      {
	result_state= IDENT_QUOTED;
        while (ident_map[c=lip->yyGet()])
        {
          switch (my_mbcharlen(cs, c))
          {
          case 1:
            break;
          case 0:
            if (my_mbmaxlenlen(cs) < 2)
              break;
            /* else fall through */
          default:
            int l;
            if ((l = my_ismbchar(cs,
                                 lip->get_ptr() -1,
                                 lip->get_end_of_query())) == 0)
              break;
            lip->skip_binary(l-1);
          }
        }
      }
      else
      {
        for (result_state=0; ident_map[c= lip->yyGet()]; result_state|= c) ;
        /* If there were non-ASCII characters, mark that we must convert */
        result_state= result_state & 0x80 ? IDENT_QUOTED : IDENT;
      }
      if (c == '.' && ident_map[lip->yyPeek()])
	lip->next_state=MY_LEX_IDENT_SEP;// Next is '.'

      yylval->lex_str= get_token(lip, 0, lip->yyLength());

      lip->body_utf8_append(lip->m_cpp_text_start);

      lip->body_utf8_append_literal(thd, &yylval->lex_str, cs,
                                    lip->m_cpp_text_end);

      return(result_state);

    case MY_LEX_USER_VARIABLE_DELIMITER:	// Found quote char
    {
      uint double_quotes= 0;
      char quote_char= c;                       // Used char
      for(;;)
      {
        c= lip->yyGet();
        if (c == 0)
        {
          lip->yyUnget();
          return ABORT_SYM;                     // Unmatched quotes
        }

	int var_length;
	if ((var_length= my_mbcharlen(cs, c)) == 1)
	{
	  if (c == quote_char)
	  {
            if (lip->yyPeek() != quote_char)
	      break;
            c=lip->yyGet();
	    double_quotes++;
	    continue;
	  }
	}
        else if (use_mb(cs))
        {
          if ((var_length= my_ismbchar(cs, lip->get_ptr() - 1,
                                       lip->get_end_of_query())))
            lip->skip_binary(var_length-1);
        }
      }
      if (double_quotes)
	yylval->lex_str=get_quoted_token(lip, 1,
                                         lip->yyLength() - double_quotes -1,
					 quote_char);
      else
        yylval->lex_str=get_token(lip, 1, lip->yyLength() -1);
      if (c == quote_char)
        lip->yySkip();                  // Skip end `
      lip->next_state= MY_LEX_START;

      lip->body_utf8_append(lip->m_cpp_text_start);

      lip->body_utf8_append_literal(thd, &yylval->lex_str, cs,
                                    lip->m_cpp_text_end);

      return(IDENT_QUOTED);
    }
    case MY_LEX_INT_OR_REAL:		// Complete int or incomplete real
      if (c != '.')
      {					// Found complete integer number.
        yylval->lex_str=get_token(lip, 0, lip->yyLength());
	return int_token(yylval->lex_str.str, (uint) yylval->lex_str.length);
      }
      // fall through
    case MY_LEX_REAL:			// Incomplete real number
      while (my_isdigit(cs,c = lip->yyGet())) ;

      if (c == 'e' || c == 'E')
      {
        c = lip->yyGet();
	if (c == '-' || c == '+')
          c = lip->yyGet();                     // Skip sign
	if (!my_isdigit(cs,c))
	{				// No digit after sign
	  state= MY_LEX_CHAR;
	  break;
	}
        while (my_isdigit(cs,lip->yyGet())) ;
        yylval->lex_str=get_token(lip, 0, lip->yyLength());
	return(FLOAT_NUM);
      }
      yylval->lex_str=get_token(lip, 0, lip->yyLength());
      return(DECIMAL_NUM);

    case MY_LEX_HEX_NUMBER:		// Found x'hexstring'
      lip->yySkip();                    // Accept opening '
      while (my_isxdigit(cs, (c= lip->yyGet()))) ;
      if (c != '\'')
        return(ABORT_SYM);              // Illegal hex constant
      lip->yySkip();                    // Accept closing '
      length= lip->yyLength();          // Length of hexnum+3
      if ((length % 2) == 0)
        return(ABORT_SYM);              // odd number of hex digits
      yylval->lex_str=get_token(lip,
                                2,          // skip x'
                                length-3);  // don't count x' and last '
      return (HEX_NUM);

    case MY_LEX_BIN_NUMBER:           // Found b'bin-string'
      lip->yySkip();                  // Accept opening '
      while ((c= lip->yyGet()) == '0' || c == '1') ;
      if (c != '\'')
        return(ABORT_SYM);            // Illegal hex constant
      lip->yySkip();                  // Accept closing '
      length= lip->yyLength();        // Length of bin-num + 3
      yylval->lex_str= get_token(lip,
                                 2,         // skip b'
                                 length-3); // don't count b' and last '
      return (BIN_NUM);

    case MY_LEX_CMP_OP:			// Incomplete comparison operator
      if (state_map[lip->yyPeek()] == MY_LEX_CMP_OP ||
          state_map[lip->yyPeek()] == MY_LEX_LONG_CMP_OP)
        lip->yySkip();
      if ((tokval = find_keyword(lip, lip->yyLength() + 1, 0)))
      {
	lip->next_state= MY_LEX_START;	// Allow signed numbers
	return(tokval);
      }
      state = MY_LEX_CHAR;		// Something fishy found
      break;

    case MY_LEX_LONG_CMP_OP:		// Incomplete comparison operator
      if (state_map[lip->yyPeek()] == MY_LEX_CMP_OP ||
          state_map[lip->yyPeek()] == MY_LEX_LONG_CMP_OP)
      {
        lip->yySkip();
        if (state_map[lip->yyPeek()] == MY_LEX_CMP_OP)
          lip->yySkip();
      }
      if ((tokval = find_keyword(lip, lip->yyLength() + 1, 0)))
      {
	lip->next_state= MY_LEX_START;	// Found long op
	return(tokval);
      }
      state = MY_LEX_CHAR;		// Something fishy found
      break;

    case MY_LEX_BOOL:
      if (c != lip->yyPeek())
      {
	state=MY_LEX_CHAR;
	break;
      }
      lip->yySkip();
      tokval = find_keyword(lip,2,0);	// Is a bool operator
      lip->next_state= MY_LEX_START;	// Allow signed numbers
      return(tokval);

    case MY_LEX_STRING_OR_DELIMITER:
      if (thd->variables.sql_mode & MODE_ANSI_QUOTES)
      {
	state= MY_LEX_USER_VARIABLE_DELIMITER;
	break;
      }
      /* " used for strings */
      // Fall through.
    case MY_LEX_STRING:			// Incomplete text string
      if (!(yylval->lex_str.str = get_text(lip, 1, 1)))
      {
	state= MY_LEX_CHAR;		// Read char by char
	break;
      }
      yylval->lex_str.length=lip->yytoklen;

      lip->body_utf8_append(lip->m_cpp_text_start);

      lip->body_utf8_append_literal(thd, &yylval->lex_str,
        lip->m_underscore_cs ? lip->m_underscore_cs : cs,
        lip->m_cpp_text_end);

      lip->m_underscore_cs= NULL;

      return(TEXT_STRING);

    case MY_LEX_COMMENT:			//  Comment
      thd->m_parser_state->add_comment();
      while ((c = lip->yyGet()) != '\n' && c) ;
      lip->yyUnget();                   // Safety against eof
      state = MY_LEX_START;		// Try again
      break;
    case MY_LEX_LONG_COMMENT:		/* Long C comment? */
      if (lip->yyPeek() != '*')
      {
	state=MY_LEX_CHAR;		// Probable division
	break;
      }
      thd->m_parser_state->add_comment();
      /* Reject '/' '*', since we might need to turn off the echo */
      lip->yyUnget();

      lip->save_in_comment_state();

      if (lip->yyPeekn(2) == '!')
      {
        lip->in_comment= DISCARD_COMMENT;
        /* Accept '/' '*' '!', but do not keep this marker. */
        lip->set_echo(FALSE);
        lip->yySkip();
        lip->yySkip();
        lip->yySkip();

        /*
          The special comment format is very strict:
          '/' '*' '!', followed by exactly
          1 digit (major), 2 digits (minor), then 2 digits (dot).
          32302 -> 3.23.02
          50032 -> 5.0.32
          50114 -> 5.1.14
        */
        char version_str[6];
        if (  my_isdigit(cs, (version_str[0]= lip->yyPeekn(0)))
           && my_isdigit(cs, (version_str[1]= lip->yyPeekn(1)))
           && my_isdigit(cs, (version_str[2]= lip->yyPeekn(2)))
           && my_isdigit(cs, (version_str[3]= lip->yyPeekn(3)))
           && my_isdigit(cs, (version_str[4]= lip->yyPeekn(4)))
           )
        {
          version_str[5]= 0;
          ulong version;
          version=strtol(version_str, NULL, 10);

          if (version <= MYSQL_VERSION_ID)
          {
            /* Accept 'M' 'm' 'm' 'd' 'd' */
            lip->yySkipn(5);
            /* Expand the content of the special comment as real code */
            lip->set_echo(TRUE);
            state=MY_LEX_START;
            break;  /* Do not treat contents as a comment.  */
          }
          else
          {
            /*
              Patch and skip the conditional comment to avoid it
              being propagated infinitely (eg. to a slave).
            */
            char *pcom= lip->yyUnput(' ');
            comment_closed= ! consume_comment(lip, 1);
            if (! comment_closed)
            {
              *pcom= '!';
            }
            /* version allowed to have one level of comment inside. */
          }
        }
        else
        {
          /* Not a version comment. */
          state=MY_LEX_START;
          lip->set_echo(TRUE);
          break;
        }
      }
      else
      {
        lip->in_comment= PRESERVE_COMMENT;
        lip->yySkip();                  // Accept /
        lip->yySkip();                  // Accept *
        comment_closed= ! consume_comment(lip, 0);
        /* regular comments can have zero comments inside. */
      }
      /*
        Discard:
        - regular '/' '*' comments,
        - special comments '/' '*' '!' for a future version,
        by scanning until we find a closing '*' '/' marker.

        Nesting regular comments isn't allowed.  The first 
        '*' '/' returns the parser to the previous state.

        /#!VERSI oned containing /# regular #/ is allowed #/

		Inside one versioned comment, another versioned comment
		is treated as a regular discardable comment.  It gets
		no special parsing.
      */

      /* Unbalanced comments with a missing '*' '/' are a syntax error */
      if (! comment_closed)
        return (ABORT_SYM);
      state = MY_LEX_START;             // Try again
      lip->restore_in_comment_state();
      break;
    case MY_LEX_END_LONG_COMMENT:
      if ((lip->in_comment != NO_COMMENT) && lip->yyPeek() == '/')
      {
        /* Reject '*' '/' */
        lip->yyUnget();
        /* Accept '*' '/', with the proper echo */
        lip->set_echo(lip->in_comment == PRESERVE_COMMENT);
        lip->yySkipn(2);
        /* And start recording the tokens again */
        lip->set_echo(TRUE);
        
        /*
          C-style comments are replaced with a single space (as it
          is in C and C++).  If there is already a whitespace 
          character at this point in the stream, the space is
          not inserted.

          See also ISO/IEC 9899:1999 §5.1.1.2  
          ("Programming languages — C")
        */
        if (!my_isspace(cs, lip->yyPeek()) &&
            lip->get_cpp_ptr() != lip->get_cpp_buf() &&
            !my_isspace(cs, *(lip->get_cpp_ptr() - 1)))
          lip->cpp_inject(' ');

        lip->in_comment=NO_COMMENT;
        state=MY_LEX_START;
      }
      else
	state=MY_LEX_CHAR;		// Return '*'
      break;
    case MY_LEX_SET_VAR:		// Check if ':='
      if (lip->yyPeek() != '=')
      {
	state=MY_LEX_CHAR;		// Return ':'
	break;
      }
      lip->yySkip();
      return (SET_VAR);
    case MY_LEX_SEMICOLON:			// optional line terminator
      state= MY_LEX_CHAR;               // Return ';'
      break;
    case MY_LEX_EOL:
      if (lip->eof())
      {
        lip->yyUnget();                 // Reject the last '\0'
        lip->set_echo(FALSE);
        lip->yySkip();
        lip->set_echo(TRUE);
        /* Unbalanced comments with a missing '*' '/' are a syntax error */
        if (lip->in_comment != NO_COMMENT)
          return (ABORT_SYM);
        lip->next_state=MY_LEX_END;     // Mark for next loop
        return(END_OF_INPUT);
      }
      state=MY_LEX_CHAR;
      break;
    case MY_LEX_END:
      lip->next_state=MY_LEX_END;
      return(0);			// We found end of input last time

      /* Actually real shouldn't start with . but allow them anyhow */
    case MY_LEX_REAL_OR_POINT:
      if (my_isdigit(cs,lip->yyPeek()))
	state = MY_LEX_REAL;		// Real
      else
      {
	state= MY_LEX_IDENT_SEP;	// return '.'
        lip->yyUnget();                 // Put back '.'
      }
      break;
    case MY_LEX_USER_END:		// end '@' of user@hostname
      switch (state_map[lip->yyPeek()]) {
      case MY_LEX_STRING:
      case MY_LEX_USER_VARIABLE_DELIMITER:
      case MY_LEX_STRING_OR_DELIMITER:
        break;
      case MY_LEX_USER_END:
	lip->next_state=MY_LEX_SYSTEM_VAR;
	break;
      default:
	lip->next_state=MY_LEX_HOSTNAME;
	break;
      }
      yylval->lex_str.str=(char*) lip->get_ptr();
      yylval->lex_str.length=1;
      return((int) '@');
    case MY_LEX_HOSTNAME:		// end '@' of user@hostname
      for (c=lip->yyGet() ;
	   my_isalnum(cs,c) || c == '.' || c == '_' ||  c == '$';
           c= lip->yyGet()) ;
      yylval->lex_str=get_token(lip, 0, lip->yyLength());
      return(LEX_HOSTNAME);
    case MY_LEX_SYSTEM_VAR:
      yylval->lex_str.str=(char*) lip->get_ptr();
      yylval->lex_str.length=1;
      lip->yySkip();                                    // Skip '@'
      lip->next_state= (state_map[lip->yyPeek()] ==
			MY_LEX_USER_VARIABLE_DELIMITER ?
			MY_LEX_START :
			MY_LEX_IDENT_OR_KEYWORD);
      return((int) '@');
    case MY_LEX_IDENT_OR_KEYWORD:
      /*
	We come here when we have found two '@' in a row.
	We should now be able to handle:
	[(global | local | session) .]variable_name
      */

      for (result_state= 0; ident_map[c= lip->yyGet()]; result_state|= c) ;
      /* If there were non-ASCII characters, mark that we must convert */
      result_state= result_state & 0x80 ? IDENT_QUOTED : IDENT;

      if (c == '.')
	lip->next_state=MY_LEX_IDENT_SEP;
      length= lip->yyLength();
      if (length == 0)
        return(ABORT_SYM);              // Names must be nonempty.
      if ((tokval= find_keyword(lip, length,0)))
      {
        lip->yyUnget();                         // Put back 'c'
	return(tokval);				// Was keyword
      }
      yylval->lex_str=get_token(lip, 0, length);

      lip->body_utf8_append(lip->m_cpp_text_start);

      lip->body_utf8_append_literal(thd, &yylval->lex_str, cs,
                                    lip->m_cpp_text_end);

      return(result_state);
    }
  }
}