comparison: src/lexer_scanner.cc
src/lexer_scanner.cc
- changeset 73
- 1ee9b312dc18
- child 75
- bf8c57437231
equal
deleted
inserted
replaced
| 72:03e4d9db3fd9 | 73:1ee9b312dc18 |
|---|---|
| 1 /* | |
| 2 Copyright (c) 2013-2014, 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 are met: | |
| 7 | |
| 8 * Redistributions of source code must retain the above copyright | |
| 9 notice, this list of conditions and the following disclaimer. | |
| 10 | |
| 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 | |
| 15 * Neither the name of the <organization> nor the | |
| 16 names of its contributors may be used to endorse or promote products | |
| 17 derived from this software without specific prior written permission. | |
| 18 | |
| 19 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND | |
| 20 ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED | |
| 21 WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE | |
| 22 DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY | |
| 23 DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES | |
| 24 (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; | |
| 25 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND | |
| 26 ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | |
| 27 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS | |
| 28 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
| 29 */ | |
| 30 | |
| 31 #include <cstdio> | |
| 32 #include <cstdlib> | |
| 33 #include <cassert> | |
| 34 #include <cstring> | |
| 35 #include <string> | |
| 36 #include "lexer_scanner.h" | |
| 37 | |
| 38 static const string g_token_strings[] = | |
| 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 "->", | |
| 70 "bool", | |
| 71 "break", | |
| 72 "case", | |
| 73 "continue", | |
| 74 "const", | |
| 75 "default", | |
| 76 "do", | |
| 77 "else", | |
| 78 "event", | |
| 79 "for", | |
| 80 "goto", | |
| 81 "if", | |
| 82 "int", | |
| 83 "mainloop", | |
| 84 "onenter", | |
| 85 "onexit", | |
| 86 "state", | |
| 87 "switch", | |
| 88 "str" | |
| 89 "void", | |
| 90 "while", | |
| 91 "enum", | |
| 92 "func", | |
| 93 "return", | |
| 94 }; | |
| 95 | |
| 96 static_assert (countof (g_token_strings) == (int) last_named_token + 1, | |
| 97 "Count of g_token_strings is not the same as the amount of named token identifiers."); | |
| 98 | |
| 99 // ============================================================================= | |
| 100 // | |
| 101 lexer_scanner::lexer_scanner (FILE* fp) : | |
| 102 m_line (1) | |
| 103 { | |
| 104 long fsize, bytes; | |
| 105 | |
| 106 fseek (fp, 0l, SEEK_END); | |
| 107 fsize = ftell (fp); | |
| 108 rewind (fp); | |
| 109 m_data = new char[fsize]; | |
| 110 m_ptr = m_line_break_pos = &m_data[0]; | |
| 111 bytes = fread (m_data, 1, fsize, fp); | |
| 112 assert (bytes >= fsize); | |
| 113 } | |
| 114 | |
| 115 // ============================================================================= | |
| 116 // | |
| 117 lexer_scanner::~lexer_scanner() | |
| 118 { | |
| 119 delete m_data; | |
| 120 } | |
| 121 | |
| 122 // ============================================================================= | |
| 123 // | |
| 124 bool lexer_scanner::check_string (const char* c, int flags) | |
| 125 { | |
| 126 bool r = strncmp (m_ptr, c, strlen (c)) == 0; | |
| 127 | |
| 128 // There is to be whitespace after words | |
| 129 if (r && (flags & f_check_word) && !isspace (m_ptr[strlen (c)])) | |
| 130 r = false; | |
| 131 | |
| 132 // Advance the cursor unless we want to just peek | |
| 133 if (r && ! (flags & f_check_peek)) | |
| 134 m_ptr += strlen (c); | |
| 135 | |
| 136 return r; | |
| 137 } | |
| 138 | |
| 139 // ============================================================================= | |
| 140 // | |
| 141 bool lexer_scanner::get_next_token() | |
| 142 { | |
| 143 m_token_text = ""; | |
| 144 | |
| 145 while (isspace (*m_ptr) == true) | |
| 146 { | |
| 147 if (*m_ptr == '\n') | |
| 148 { | |
| 149 m_line++; | |
| 150 m_line_break_pos = m_ptr; | |
| 151 } | |
| 152 | |
| 153 m_ptr++; | |
| 154 } | |
| 155 | |
| 156 if (*m_ptr == '\0') | |
| 157 return false; | |
| 158 | |
| 159 // Check tokens | |
| 160 for (int i = 0; i < (int) (sizeof g_token_strings / sizeof * g_token_strings); ++i) | |
| 161 { | |
| 162 if (check_string (g_token_strings[i], f_check_word)) | |
| 163 { | |
| 164 m_token_text = g_token_strings[i]; | |
| 165 m_e_token = (e_token) i; | |
| 166 return true; | |
| 167 } | |
| 168 } | |
| 169 | |
| 170 // Check and parse string | |
| 171 if (*m_ptr == '\"') | |
| 172 { | |
| 173 m_ptr++; | |
| 174 | |
| 175 while (*m_ptr != '\"') | |
| 176 { | |
| 177 if (!*m_ptr) | |
| 178 return false; | |
| 179 | |
| 180 if (check_string ("\\n")) | |
| 181 { | |
| 182 m_token_text += '\n'; | |
| 183 continue; | |
| 184 } | |
| 185 elif (check_string ("\\t")) | |
| 186 { | |
| 187 m_token_text += '\t'; | |
| 188 continue; | |
| 189 } | |
| 190 elif (check_string ("\\\"")) | |
| 191 { | |
| 192 m_token_text += '"'; | |
| 193 continue; | |
| 194 } | |
| 195 | |
| 196 m_token_text += *m_ptr++; | |
| 197 } | |
| 198 | |
| 199 m_e_token = tk_string; | |
| 200 m_ptr++; // skip the final quote | |
| 201 return true; | |
| 202 } | |
| 203 | |
| 204 m_e_token = tk_symbol; | |
| 205 | |
| 206 if (isdigit (*m_ptr)) | |
| 207 { | |
| 208 while (isdigit (*m_ptr)) | |
| 209 m_token_text += *m_ptr++; | |
| 210 | |
| 211 m_e_token = tk_number; | |
| 212 return true; | |
| 213 } | |
| 214 | |
| 215 if (is_symbol_char (*m_ptr)) | |
| 216 { | |
| 217 while (m_ptr != '\0') | |
| 218 { | |
| 219 if (!is_symbol_char (*m_ptr)) | |
| 220 break; | |
| 221 | |
| 222 bool stop_here = false; | |
| 223 | |
| 224 for (string i : g_token_strings) | |
| 225 { | |
| 226 if (check_string (i, f_check_peek | f_check_word)) | |
| 227 { | |
| 228 stop_here = true; | |
| 229 break; | |
| 230 } | |
| 231 } | |
| 232 | |
| 233 if (stop_here) | |
| 234 break; | |
| 235 | |
| 236 m_token_text += *m_ptr++; | |
| 237 } | |
| 238 | |
| 239 return true; | |
| 240 } | |
| 241 | |
| 242 return false; | |
| 243 } | |
| 244 | |
| 245 string lexer_scanner::get_token_string (e_token a) | |
| 246 { | |
| 247 assert ((int) a <= (int) last_named_token); | |
| 248 return g_token_strings[a]; | |
| 249 } |
