comparison: src/lexer_scanner.cc
src/lexer_scanner.cc
- changeset 88
- 5def6ff8b466
- parent 87
- 8f65914e7046
- child 89
- 029a330a9bef
equal
deleted
inserted
replaced
| 87:8f65914e7046 | 88:5def6ff8b466 |
|---|---|
| 1 /* | |
| 2 Copyright 2012-2014 Santeri Piippo | |
| 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 1. Redistributions of source code must retain the above copyright | |
| 10 notice, this list of conditions and the following disclaimer. | |
| 11 2. 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 3. 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 #include <cstdio> | |
| 30 #include <cstdlib> | |
| 31 #include <cassert> | |
| 32 #include <cstring> | |
| 33 #include <string> | |
| 34 #include "lexer_scanner.h" | |
| 35 #include "lexer.h" | |
| 36 | |
| 37 static const string g_token_strings[] = | |
| 38 { | |
| 39 "==", | |
| 40 "[]", | |
| 41 "+=", | |
| 42 "-=", | |
| 43 "*=", | |
| 44 "/=", | |
| 45 "%=", | |
| 46 "'", | |
| 47 "$", | |
| 48 "(", | |
| 49 ")", | |
| 50 "[", | |
| 51 "]", | |
| 52 "{", | |
| 53 "}", | |
| 54 "=", | |
| 55 "+", | |
| 56 "-", | |
| 57 "*", | |
| 58 "/", | |
| 59 "%", | |
| 60 ",", | |
| 61 "<", | |
| 62 ">", | |
| 63 ".", | |
| 64 ":", | |
| 65 ";", | |
| 66 "#", | |
| 67 "!", | |
| 68 "->", | |
| 69 "bool", | |
| 70 "break", | |
| 71 "case", | |
| 72 "continue", | |
| 73 "const", | |
| 74 "default", | |
| 75 "do", | |
| 76 "else", | |
| 77 "event", | |
| 78 "eventdef", | |
| 79 "for", | |
| 80 "funcdef", | |
| 81 "goto", | |
| 82 "if", | |
| 83 "int", | |
| 84 "mainloop", | |
| 85 "onenter", | |
| 86 "onexit", | |
| 87 "state", | |
| 88 "switch", | |
| 89 "str", | |
| 90 "void", | |
| 91 "while", | |
| 92 "enum", | |
| 93 "func", | |
| 94 "return", | |
| 95 }; | |
| 96 | |
| 97 static_assert (countof (g_token_strings) == (int) tk_last_named_token + 1, | |
| 98 "Count of g_token_strings is not the same as the amount of named token identifiers."); | |
| 99 | |
| 100 // ============================================================================= | |
| 101 // | |
| 102 lexer_scanner::lexer_scanner (FILE* fp) : | |
| 103 m_line (1) | |
| 104 { | |
| 105 long fsize, bytes; | |
| 106 | |
| 107 fseek (fp, 0l, SEEK_END); | |
| 108 fsize = ftell (fp); | |
| 109 rewind (fp); | |
| 110 m_data = new char[fsize]; | |
| 111 m_ptr = m_line_break_pos = &m_data[0]; | |
| 112 bytes = fread (m_data, 1, fsize, fp); | |
| 113 assert (bytes >= fsize); | |
| 114 } | |
| 115 | |
| 116 // ============================================================================= | |
| 117 // | |
| 118 lexer_scanner::~lexer_scanner() | |
| 119 { | |
| 120 delete m_data; | |
| 121 } | |
| 122 | |
| 123 // ============================================================================= | |
| 124 // | |
| 125 bool lexer_scanner::check_string (const char* c, int flags) | |
| 126 { | |
| 127 bool r = strncmp (m_ptr, c, strlen (c)) == 0; | |
| 128 | |
| 129 // There is to be a non-symbol character after words | |
| 130 if (r && (flags & f_check_word) && is_symbol_char (m_ptr[strlen (c)], true)) | |
| 131 r = false; | |
| 132 | |
| 133 // Advance the cursor unless we want to just peek | |
| 134 if (r && !(flags & f_check_peek)) | |
| 135 m_ptr += strlen (c); | |
| 136 | |
| 137 return r; | |
| 138 } | |
| 139 | |
| 140 // ============================================================================= | |
| 141 // | |
| 142 bool lexer_scanner::get_next_token() | |
| 143 { | |
| 144 m_token_text = ""; | |
| 145 | |
| 146 while (isspace (*m_ptr)) | |
| 147 skip(); | |
| 148 | |
| 149 // Check for comments | |
| 150 if (strncmp (m_ptr, "//", 2) == 0) | |
| 151 { | |
| 152 m_ptr += 2; | |
| 153 | |
| 154 while (*m_ptr != '\n') | |
| 155 skip(); | |
| 156 | |
| 157 return get_next_token(); | |
| 158 } | |
| 159 elif (strncmp (m_ptr, "/*", 2) == 0) | |
| 160 { | |
| 161 skip (2); // skip the start symbols | |
| 162 | |
| 163 while (strncmp (m_ptr, "*/", 2) != 0) | |
| 164 skip(); | |
| 165 | |
| 166 skip (2); // skip the end symbols | |
| 167 return get_next_token(); | |
| 168 } | |
| 169 | |
| 170 if (*m_ptr == '\0') | |
| 171 return false; | |
| 172 | |
| 173 // Check tokens | |
| 174 for (int i = 0; i < countof (g_token_strings); ++i) | |
| 175 { | |
| 176 int flags = 0; | |
| 177 | |
| 178 if (i >= tk_first_named_token) | |
| 179 flags |= f_check_word; | |
| 180 | |
| 181 if (check_string (g_token_strings[i], flags)) | |
| 182 { | |
| 183 m_token_text = g_token_strings[i]; | |
| 184 m_token_type = (e_token) i; | |
| 185 return true; | |
| 186 } | |
| 187 } | |
| 188 | |
| 189 // Check and parse string | |
| 190 if (*m_ptr == '\"') | |
| 191 { | |
| 192 m_ptr++; | |
| 193 | |
| 194 while (*m_ptr != '\"') | |
| 195 { | |
| 196 if (!*m_ptr) | |
| 197 error ("unterminated string"); | |
| 198 | |
| 199 if (check_string ("\\n")) | |
| 200 { | |
| 201 m_token_text += '\n'; | |
| 202 continue; | |
| 203 } | |
| 204 elif (check_string ("\\t")) | |
| 205 { | |
| 206 m_token_text += '\t'; | |
| 207 continue; | |
| 208 } | |
| 209 elif (check_string ("\\\"")) | |
| 210 { | |
| 211 m_token_text += '"'; | |
| 212 continue; | |
| 213 } | |
| 214 | |
| 215 m_token_text += *m_ptr++; | |
| 216 } | |
| 217 | |
| 218 m_token_type = tk_string; | |
| 219 skip(); // skip the final quote | |
| 220 return true; | |
| 221 } | |
| 222 | |
| 223 if (isdigit (*m_ptr)) | |
| 224 { | |
| 225 while (isdigit (*m_ptr)) | |
| 226 m_token_text += *m_ptr++; | |
| 227 | |
| 228 m_token_type = tk_number; | |
| 229 return true; | |
| 230 } | |
| 231 | |
| 232 if (is_symbol_char (*m_ptr, false)) | |
| 233 { | |
| 234 m_token_type = tk_symbol; | |
| 235 | |
| 236 do | |
| 237 { | |
| 238 if (!is_symbol_char (*m_ptr, true)) | |
| 239 break; | |
| 240 | |
| 241 m_token_text += *m_ptr++; | |
| 242 } while (*m_ptr != '\0'); | |
| 243 | |
| 244 return true; | |
| 245 } | |
| 246 | |
| 247 error ("unknown character \"%1\"", *m_ptr); | |
| 248 return false; | |
| 249 } | |
| 250 | |
| 251 // ============================================================================= | |
| 252 // | |
| 253 void lexer_scanner::skip() | |
| 254 { | |
| 255 if (*m_ptr == '\n') | |
| 256 { | |
| 257 m_line++; | |
| 258 m_line_break_pos = m_ptr; | |
| 259 } | |
| 260 | |
| 261 m_ptr++; | |
| 262 } | |
| 263 | |
| 264 // ============================================================================= | |
| 265 // | |
| 266 void lexer_scanner::skip (int chars) | |
| 267 { | |
| 268 for (int i = 0; i < chars; ++i) | |
| 269 skip(); | |
| 270 } | |
| 271 | |
| 272 // ============================================================================= | |
| 273 // | |
| 274 string lexer_scanner::get_token_string (e_token a) | |
| 275 { | |
| 276 assert ((int) a <= tk_last_named_token); | |
| 277 return g_token_strings[a]; | |
| 278 } | |
| 279 | |
| 280 // ============================================================================= | |
| 281 // | |
| 282 string lexer_scanner::read_line() | |
| 283 { | |
| 284 string line; | |
| 285 | |
| 286 while (*m_ptr != '\n') | |
| 287 line += *(m_ptr++); | |
| 288 | |
| 289 return line; | |
| 290 } |
