| 1 | /* |
| 2 | Copyright (c) 2011, 2015, Oracle and/or its affiliates. All rights reserved. |
| 3 | |
| 4 | This program is free software; you can redistribute it and/or modify |
| 5 | it under the terms of the GNU General Public License as published by |
| 6 | the Free Software Foundation; version 2 of the License. |
| 7 | |
| 8 | This program is distributed in the hope that it will be useful, |
| 9 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 10 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 11 | GNU General Public License for more details. |
| 12 | |
| 13 | You should have received a copy of the GNU General Public License |
| 14 | along with this program; if not, write to the Free Software Foundation, |
| 15 | 51 Franklin Street, Suite 500, Boston, MA 02110-1335 USA */ |
| 16 | |
| 17 | #include "mariadb.h" |
| 18 | #include <string.h> |
| 19 | |
| 20 | /* We only need the tokens here */ |
| 21 | #define YYSTYPE_IS_DECLARED |
| 22 | #include <sql_yacc.h> |
| 23 | #include <lex.h> |
| 24 | |
| 25 | #include <welcome_copyright_notice.h> /* ORACLE_WELCOME_COPYRIGHT_NOTICE */ |
| 26 | |
| 27 | /* |
| 28 | This is a tool used during build only, |
| 29 | so MY_MAX_TOKEN does not need to be exact, |
| 30 | only big enough to hold: |
| 31 | - 256 character terminal tokens |
| 32 | - YYNTOKENS named terminal tokens |
| 33 | from bison. |
| 34 | See also YYMAXUTOK. |
| 35 | */ |
| 36 | #define MY_MAX_TOKEN 1000 |
| 37 | /** Generated token. */ |
| 38 | struct gen_lex_token_string |
| 39 | { |
| 40 | const char *m_token_string; |
| 41 | int m_token_length; |
| 42 | bool m_append_space; |
| 43 | bool m_start_expr; |
| 44 | }; |
| 45 | |
| 46 | gen_lex_token_string compiled_token_array[MY_MAX_TOKEN]; |
| 47 | int max_token_seen= 0; |
| 48 | |
| 49 | char char_tokens[256]; |
| 50 | |
| 51 | int tok_generic_value= 0; |
| 52 | int tok_generic_value_list= 0; |
| 53 | int tok_row_single_value= 0; |
| 54 | int tok_row_single_value_list= 0; |
| 55 | int tok_row_multiple_value= 0; |
| 56 | int tok_row_multiple_value_list= 0; |
| 57 | int tok_ident= 0; |
| 58 | int tok_unused= 0; |
| 59 | |
| 60 | void set_token(int tok, const char *str) |
| 61 | { |
| 62 | if (tok <= 0) |
| 63 | { |
| 64 | fprintf(stderr, "Bad token found\n" ); |
| 65 | exit(1); |
| 66 | } |
| 67 | |
| 68 | if (tok > max_token_seen) |
| 69 | { |
| 70 | max_token_seen= tok; |
| 71 | } |
| 72 | |
| 73 | if (max_token_seen >= MY_MAX_TOKEN) |
| 74 | { |
| 75 | fprintf(stderr, "Added that many new keywords ? Increase MY_MAX_TOKEN\n" ); |
| 76 | exit(1); |
| 77 | } |
| 78 | |
| 79 | compiled_token_array[tok].m_token_string= str; |
| 80 | compiled_token_array[tok].m_token_length= (int)strlen(str); |
| 81 | compiled_token_array[tok].m_append_space= true; |
| 82 | compiled_token_array[tok].m_start_expr= false; |
| 83 | } |
| 84 | |
| 85 | void set_start_expr_token(int tok) |
| 86 | { |
| 87 | compiled_token_array[tok].m_start_expr= true; |
| 88 | } |
| 89 | |
| 90 | void compute_tokens() |
| 91 | { |
| 92 | int tok; |
| 93 | unsigned int i; |
| 94 | char *str; |
| 95 | |
| 96 | /* |
| 97 | Default value. |
| 98 | */ |
| 99 | for (tok= 0; tok < MY_MAX_TOKEN; tok++) |
| 100 | { |
| 101 | compiled_token_array[tok].m_token_string= "(unknown)" ; |
| 102 | compiled_token_array[tok].m_token_length= 9; |
| 103 | compiled_token_array[tok].m_append_space= true; |
| 104 | compiled_token_array[tok].m_start_expr= false; |
| 105 | } |
| 106 | |
| 107 | /* |
| 108 | Tokens made of just one terminal character |
| 109 | */ |
| 110 | for (tok=0; tok < 256; tok++) |
| 111 | { |
| 112 | str= & char_tokens[tok]; |
| 113 | str[0]= (char) tok; |
| 114 | compiled_token_array[tok].m_token_string= str; |
| 115 | compiled_token_array[tok].m_token_length= 1; |
| 116 | compiled_token_array[tok].m_append_space= true; |
| 117 | } |
| 118 | |
| 119 | max_token_seen= 255; |
| 120 | |
| 121 | /* |
| 122 | String terminal tokens, used in sql_yacc.yy |
| 123 | */ |
| 124 | set_token(NEG, "~" ); |
| 125 | set_token(TABLE_REF_PRIORITY, "TABLE_REF_PRIORITY" ); |
| 126 | |
| 127 | /* |
| 128 | Tokens hard coded in sql_lex.cc |
| 129 | */ |
| 130 | |
| 131 | set_token(WITH_CUBE_SYM, "WITH CUBE" ); |
| 132 | set_token(WITH_ROLLUP_SYM, "WITH ROLLUP" ); |
| 133 | set_token(WITH_SYSTEM_SYM, "WITH SYSTEM" ); |
| 134 | set_token(FOR_SYSTEM_TIME_SYM, "FOR SYSTEM_TIME" ); |
| 135 | set_token(VALUES_IN_SYM, "VALUES IN" ); |
| 136 | set_token(VALUES_LESS_SYM, "VALUES LESS" ); |
| 137 | set_token(NOT2_SYM, "!" ); |
| 138 | set_token(OR2_SYM, "|" ); |
| 139 | set_token(PARAM_MARKER, "?" ); |
| 140 | set_token(SET_VAR, ":=" ); |
| 141 | set_token(UNDERSCORE_CHARSET, "(_charset)" ); |
| 142 | set_token(END_OF_INPUT, "" ); |
| 143 | |
| 144 | /* |
| 145 | Values. |
| 146 | These tokens are all normalized later, |
| 147 | so this strings will never be displayed. |
| 148 | */ |
| 149 | set_token(BIN_NUM, "(bin)" ); |
| 150 | set_token(DECIMAL_NUM, "(decimal)" ); |
| 151 | set_token(FLOAT_NUM, "(float)" ); |
| 152 | set_token(HEX_NUM, "(hex)" ); |
| 153 | set_token(LEX_HOSTNAME, "(hostname)" ); |
| 154 | set_token(LONG_NUM, "(long)" ); |
| 155 | set_token(NUM, "(num)" ); |
| 156 | set_token(TEXT_STRING, "(text)" ); |
| 157 | set_token(NCHAR_STRING, "(nchar)" ); |
| 158 | set_token(ULONGLONG_NUM, "(ulonglong)" ); |
| 159 | |
| 160 | /* |
| 161 | Identifiers. |
| 162 | */ |
| 163 | set_token(IDENT, "(id)" ); |
| 164 | set_token(IDENT_QUOTED, "(id_quoted)" ); |
| 165 | |
| 166 | /* |
| 167 | Unused tokens |
| 168 | */ |
| 169 | set_token(LOCATOR_SYM, "LOCATOR" ); |
| 170 | set_token(SERVER_OPTIONS, "SERVER_OPTIONS" ); |
| 171 | set_token(UDF_RETURNS_SYM, "UDF_RETURNS" ); |
| 172 | |
| 173 | /* |
| 174 | See symbols[] in sql/lex.h |
| 175 | */ |
| 176 | for (i= 0; i< sizeof(symbols)/sizeof(symbols[0]); i++) |
| 177 | { |
| 178 | set_token(symbols[i].tok, symbols[i].name); |
| 179 | } |
| 180 | |
| 181 | /* |
| 182 | See sql_functions[] in sql/lex.h |
| 183 | */ |
| 184 | for (i= 0; i< sizeof(sql_functions)/sizeof(sql_functions[0]); i++) |
| 185 | { |
| 186 | set_token(sql_functions[i].tok, sql_functions[i].name); |
| 187 | } |
| 188 | |
| 189 | /* |
| 190 | Additional FAKE tokens, |
| 191 | used internally to normalize a digest text. |
| 192 | */ |
| 193 | |
| 194 | max_token_seen++; |
| 195 | tok_generic_value= max_token_seen; |
| 196 | set_token(tok_generic_value, "?" ); |
| 197 | |
| 198 | max_token_seen++; |
| 199 | tok_generic_value_list= max_token_seen; |
| 200 | set_token(tok_generic_value_list, "?, ..." ); |
| 201 | |
| 202 | max_token_seen++; |
| 203 | tok_row_single_value= max_token_seen; |
| 204 | set_token(tok_row_single_value, "(?)" ); |
| 205 | |
| 206 | max_token_seen++; |
| 207 | tok_row_single_value_list= max_token_seen; |
| 208 | set_token(tok_row_single_value_list, "(?) /* , ... */" ); |
| 209 | |
| 210 | max_token_seen++; |
| 211 | tok_row_multiple_value= max_token_seen; |
| 212 | set_token(tok_row_multiple_value, "(...)" ); |
| 213 | |
| 214 | max_token_seen++; |
| 215 | tok_row_multiple_value_list= max_token_seen; |
| 216 | set_token(tok_row_multiple_value_list, "(...) /* , ... */" ); |
| 217 | |
| 218 | max_token_seen++; |
| 219 | tok_ident= max_token_seen; |
| 220 | set_token(tok_ident, "(tok_id)" ); |
| 221 | |
| 222 | max_token_seen++; |
| 223 | tok_unused= max_token_seen; |
| 224 | set_token(tok_unused, "UNUSED" ); |
| 225 | |
| 226 | /* |
| 227 | Fix whitespace for some special tokens. |
| 228 | */ |
| 229 | |
| 230 | /* |
| 231 | The lexer parses "@@variable" as '@', '@', 'variable', |
| 232 | returning a token for '@' alone. |
| 233 | |
| 234 | This is incorrect, '@' is not really a token, |
| 235 | because the syntax "@ @ variable" (with spaces) is not accepted: |
| 236 | The lexer keeps some internal state after the '@' fake token. |
| 237 | |
| 238 | To work around this, digest text are printed as "@@variable". |
| 239 | */ |
| 240 | compiled_token_array[(int) '@'].m_append_space= false; |
| 241 | |
| 242 | /* |
| 243 | Define additional properties for tokens. |
| 244 | |
| 245 | List all the token that are followed by an expression. |
| 246 | This is needed to differentiate unary from binary |
| 247 | '+' and '-' operators, because we want to: |
| 248 | - reduce <unary +> <NUM> to <?>, |
| 249 | - preserve <...> <binary +> <NUM> as is. |
| 250 | */ |
| 251 | set_start_expr_token('('); |
| 252 | set_start_expr_token(','); |
| 253 | set_start_expr_token(EVERY_SYM); |
| 254 | set_start_expr_token(AT_SYM); |
| 255 | set_start_expr_token(STARTS_SYM); |
| 256 | set_start_expr_token(ENDS_SYM); |
| 257 | set_start_expr_token(DEFAULT); |
| 258 | set_start_expr_token(RETURN_SYM); |
| 259 | set_start_expr_token(IF_SYM); |
| 260 | set_start_expr_token(ELSEIF_SYM); |
| 261 | set_start_expr_token(CASE_SYM); |
| 262 | set_start_expr_token(WHEN_SYM); |
| 263 | set_start_expr_token(WHILE_SYM); |
| 264 | set_start_expr_token(UNTIL_SYM); |
| 265 | set_start_expr_token(SELECT_SYM); |
| 266 | |
| 267 | set_start_expr_token(OR_SYM); |
| 268 | set_start_expr_token(OR2_SYM); |
| 269 | set_start_expr_token(XOR); |
| 270 | set_start_expr_token(AND_SYM); |
| 271 | set_start_expr_token(AND_AND_SYM); |
| 272 | set_start_expr_token(NOT_SYM); |
| 273 | set_start_expr_token(BETWEEN_SYM); |
| 274 | set_start_expr_token(LIKE); |
| 275 | set_start_expr_token(REGEXP); |
| 276 | |
| 277 | set_start_expr_token('|'); |
| 278 | set_start_expr_token('&'); |
| 279 | set_start_expr_token(SHIFT_LEFT); |
| 280 | set_start_expr_token(SHIFT_RIGHT); |
| 281 | set_start_expr_token('+'); |
| 282 | set_start_expr_token('-'); |
| 283 | set_start_expr_token(INTERVAL_SYM); |
| 284 | set_start_expr_token('*'); |
| 285 | set_start_expr_token('/'); |
| 286 | set_start_expr_token('%'); |
| 287 | set_start_expr_token(DIV_SYM); |
| 288 | set_start_expr_token(MOD_SYM); |
| 289 | set_start_expr_token('^'); |
| 290 | } |
| 291 | |
| 292 | void print_tokens() |
| 293 | { |
| 294 | int tok; |
| 295 | |
| 296 | printf("#ifdef LEX_TOKEN_WITH_DEFINITION\n" ); |
| 297 | printf("lex_token_string lex_token_array[]=\n" ); |
| 298 | printf("{\n" ); |
| 299 | printf("/* PART 1: character tokens. */\n" ); |
| 300 | |
| 301 | for (tok= 0; tok<256; tok++) |
| 302 | { |
| 303 | printf("/* %03d */ { \"\\x%02x\", 1, %s, %s},\n" , |
| 304 | tok, |
| 305 | tok, |
| 306 | compiled_token_array[tok].m_append_space ? "true" : "false" , |
| 307 | compiled_token_array[tok].m_start_expr ? "true" : "false" ); |
| 308 | } |
| 309 | |
| 310 | printf("/* PART 2: named tokens. */\n" ); |
| 311 | |
| 312 | for (tok= 256; tok<= max_token_seen; tok++) |
| 313 | { |
| 314 | printf("/* %03d */ { \"%s\", %d, %s, %s},\n" , |
| 315 | tok, |
| 316 | compiled_token_array[tok].m_token_string, |
| 317 | compiled_token_array[tok].m_token_length, |
| 318 | compiled_token_array[tok].m_append_space ? "true" : "false" , |
| 319 | compiled_token_array[tok].m_start_expr ? "true" : "false" ); |
| 320 | } |
| 321 | |
| 322 | printf("/* DUMMY */ { \"\", 0, false, false}\n" ); |
| 323 | printf("};\n" ); |
| 324 | printf("#endif /* LEX_TOKEN_WITH_DEFINITION */\n" ); |
| 325 | |
| 326 | printf("/* DIGEST specific tokens. */\n" ); |
| 327 | printf("#define TOK_GENERIC_VALUE %d\n" , tok_generic_value); |
| 328 | printf("#define TOK_GENERIC_VALUE_LIST %d\n" , tok_generic_value_list); |
| 329 | printf("#define TOK_ROW_SINGLE_VALUE %d\n" , tok_row_single_value); |
| 330 | printf("#define TOK_ROW_SINGLE_VALUE_LIST %d\n" , tok_row_single_value_list); |
| 331 | printf("#define TOK_ROW_MULTIPLE_VALUE %d\n" , tok_row_multiple_value); |
| 332 | printf("#define TOK_ROW_MULTIPLE_VALUE_LIST %d\n" , tok_row_multiple_value_list); |
| 333 | printf("#define TOK_IDENT %d\n" , tok_ident); |
| 334 | printf("#define TOK_UNUSED %d\n" , tok_unused); |
| 335 | } |
| 336 | |
| 337 | int main(int argc,char **argv) |
| 338 | { |
| 339 | puts("/*" ); |
| 340 | puts(ORACLE_WELCOME_COPYRIGHT_NOTICE("2011" )); |
| 341 | puts("*/" ); |
| 342 | |
| 343 | printf("/*\n" ); |
| 344 | printf(" This file is generated, do not edit.\n" ); |
| 345 | printf(" See file sql/gen_lex_token.cc.\n" ); |
| 346 | printf("*/\n" ); |
| 347 | printf("struct lex_token_string\n" ); |
| 348 | printf("{\n" ); |
| 349 | printf(" const char *m_token_string;\n" ); |
| 350 | printf(" int m_token_length;\n" ); |
| 351 | printf(" bool m_append_space;\n" ); |
| 352 | printf(" bool m_start_expr;\n" ); |
| 353 | printf("};\n" ); |
| 354 | printf("typedef struct lex_token_string lex_token_string;\n" ); |
| 355 | |
| 356 | compute_tokens(); |
| 357 | print_tokens(); |
| 358 | |
| 359 | return 0; |
| 360 | } |
| 361 | |
| 362 | |