| 1 | /*
|
|---|
| 2 | * Copyright (c) 2010 Jiri Svoboda
|
|---|
| 3 | * All rights reserved.
|
|---|
| 4 | *
|
|---|
| 5 | * Redistribution and use in source and binary forms, with or without
|
|---|
| 6 | * modification, are permitted provided that the following conditions
|
|---|
| 7 | * are met:
|
|---|
| 8 | *
|
|---|
| 9 | * - Redistributions of source code must retain the above copyright
|
|---|
| 10 | * notice, this list of conditions and the following disclaimer.
|
|---|
| 11 | * - Redistributions in binary form must reproduce the above copyright
|
|---|
| 12 | * notice, this list of conditions and the following disclaimer in the
|
|---|
| 13 | * documentation and/or other materials provided with the distribution.
|
|---|
| 14 | * - The name of the author may not be used to endorse or promote products
|
|---|
| 15 | * derived from this software without specific prior written permission.
|
|---|
| 16 | *
|
|---|
| 17 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
|---|
| 18 | * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
|---|
| 19 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
|
|---|
| 20 | * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
|
|---|
| 21 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
|---|
| 22 | * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|---|
| 23 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|---|
| 24 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|---|
| 25 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
|
|---|
| 26 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|---|
| 27 | */
|
|---|
| 28 |
|
|---|
| 29 | #ifndef LEX_T_H_
|
|---|
| 30 | #define LEX_T_H_
|
|---|
| 31 |
|
|---|
| 32 | #include "bigint_t.h"
|
|---|
| 33 |
|
|---|
| 34 | /** Lexical element class */
|
|---|
| 35 | typedef enum {
|
|---|
| 36 | lc_invalid,
|
|---|
| 37 | lc_eof,
|
|---|
| 38 |
|
|---|
| 39 | lc_ident,
|
|---|
| 40 | lc_lit_char,
|
|---|
| 41 | lc_lit_int,
|
|---|
| 42 | lc_lit_string,
|
|---|
| 43 |
|
|---|
| 44 | /* Keywords */
|
|---|
| 45 | lc_as,
|
|---|
| 46 | lc_bool,
|
|---|
| 47 | lc_builtin,
|
|---|
| 48 | lc_char,
|
|---|
| 49 | lc_class,
|
|---|
| 50 | lc_constructor,
|
|---|
| 51 | lc_do,
|
|---|
| 52 | lc_else,
|
|---|
| 53 | lc_end,
|
|---|
| 54 | lc_except,
|
|---|
| 55 | lc_false,
|
|---|
| 56 | lc_finally,
|
|---|
| 57 | lc_for,
|
|---|
| 58 | lc_fun,
|
|---|
| 59 | lc_new,
|
|---|
| 60 | lc_get,
|
|---|
| 61 | lc_if,
|
|---|
| 62 | lc_in,
|
|---|
| 63 | lc_int,
|
|---|
| 64 | lc_interface,
|
|---|
| 65 | lc_is,
|
|---|
| 66 | lc_nil,
|
|---|
| 67 | lc_override,
|
|---|
| 68 | lc_packed,
|
|---|
| 69 | lc_private,
|
|---|
| 70 | lc_prop,
|
|---|
| 71 | lc_protected,
|
|---|
| 72 | lc_public,
|
|---|
| 73 | lc_raise,
|
|---|
| 74 | lc_resource,
|
|---|
| 75 | lc_return,
|
|---|
| 76 | lc_self,
|
|---|
| 77 | lc_set,
|
|---|
| 78 | lc_static,
|
|---|
| 79 | lc_string,
|
|---|
| 80 | lc_struct,
|
|---|
| 81 | lc_then,
|
|---|
| 82 | lc_this,
|
|---|
| 83 | lc_true,
|
|---|
| 84 | lc_var,
|
|---|
| 85 | lc_with,
|
|---|
| 86 | lc_while,
|
|---|
| 87 | lc_yield,
|
|---|
| 88 |
|
|---|
| 89 | /* Operators */
|
|---|
| 90 | lc_period,
|
|---|
| 91 | lc_slash,
|
|---|
| 92 | lc_lparen,
|
|---|
| 93 | lc_rparen,
|
|---|
| 94 | lc_lsbr,
|
|---|
| 95 | lc_rsbr,
|
|---|
| 96 | lc_equal,
|
|---|
| 97 | lc_notequal,
|
|---|
| 98 | lc_lt,
|
|---|
| 99 | lc_gt,
|
|---|
| 100 | lc_lt_equal,
|
|---|
| 101 | lc_gt_equal,
|
|---|
| 102 | lc_assign,
|
|---|
| 103 | lc_plus,
|
|---|
| 104 | lc_minus,
|
|---|
| 105 | lc_mult,
|
|---|
| 106 | lc_increase,
|
|---|
| 107 |
|
|---|
| 108 | /* Punctuators */
|
|---|
| 109 | lc_comma,
|
|---|
| 110 | lc_colon,
|
|---|
| 111 | lc_scolon,
|
|---|
| 112 |
|
|---|
| 113 | lc__limit
|
|---|
| 114 | } lclass_t;
|
|---|
| 115 |
|
|---|
| 116 | typedef struct {
|
|---|
| 117 | /* String ID */
|
|---|
| 118 | int sid;
|
|---|
| 119 | } lem_ident_t;
|
|---|
| 120 |
|
|---|
| 121 | typedef struct {
|
|---|
| 122 | /* Character value */
|
|---|
| 123 | bigint_t value;
|
|---|
| 124 | } lem_lit_char_t;
|
|---|
| 125 |
|
|---|
| 126 | typedef struct {
|
|---|
| 127 | /* Integer value */
|
|---|
| 128 | bigint_t value;
|
|---|
| 129 | } lem_lit_int_t;
|
|---|
| 130 |
|
|---|
| 131 | typedef struct {
|
|---|
| 132 | /* String value */
|
|---|
| 133 | char *value;
|
|---|
| 134 | } lem_lit_string_t;
|
|---|
| 135 |
|
|---|
| 136 | /** Lexical element */
|
|---|
| 137 | typedef struct {
|
|---|
| 138 | /* Lexical element class */
|
|---|
| 139 | lclass_t lclass;
|
|---|
| 140 |
|
|---|
| 141 | union {
|
|---|
| 142 | lem_ident_t ident;
|
|---|
| 143 | lem_lit_char_t lit_char;
|
|---|
| 144 | lem_lit_int_t lit_int;
|
|---|
| 145 | lem_lit_string_t lit_string;
|
|---|
| 146 | } u;
|
|---|
| 147 |
|
|---|
| 148 | /** Coordinates of this lexical element */
|
|---|
| 149 | int line_no, col_0;
|
|---|
| 150 | } lem_t;
|
|---|
| 151 |
|
|---|
| 152 | /** Lexer state object */
|
|---|
| 153 | typedef struct lex {
|
|---|
| 154 | /** Input object */
|
|---|
| 155 | struct input *input;
|
|---|
| 156 |
|
|---|
| 157 | /** Lexing buffer */
|
|---|
| 158 | char *inbuf;
|
|---|
| 159 |
|
|---|
| 160 | /** Pointer to current position in lexing buffer */
|
|---|
| 161 | char *ibp;
|
|---|
| 162 |
|
|---|
| 163 | /** Number of the line currently in inbuf */
|
|---|
| 164 | int ib_line;
|
|---|
| 165 |
|
|---|
| 166 | /** Column number adjustment (due to tabs) */
|
|---|
| 167 | int col_adj;
|
|---|
| 168 |
|
|---|
| 169 | /** @c b_true if we have the next lem in @c current */
|
|---|
| 170 | bool_t current_valid;
|
|---|
| 171 |
|
|---|
| 172 | /** Curent lem (only valid if @c current_valid is true) */
|
|---|
| 173 | lem_t current;
|
|---|
| 174 | } lex_t;
|
|---|
| 175 |
|
|---|
| 176 | #endif
|
|---|
