comparison: src/lexer_scanner.cc
src/lexer_scanner.cc
- changeset 75
- bf8c57437231
- parent 73
- 1ee9b312dc18
- child 79
- 2425fa6a4f21
equal
deleted
inserted
replaced
| 74:007fbadfa7f9 | 75:bf8c57437231 |
|---|---|
| 1 /* | 1 /* |
| 2 Copyright (c) 2013-2014, Santeri Piippo | 2 Copyright (c) 2014, Santeri Piippo |
| 3 All rights reserved. | 3 All rights reserved. |
| 4 | 4 |
| 5 Redistribution and use in source and binary forms, with or without | 5 Redistribution and use in source and binary forms, with or without |
| 6 modification, are permitted provided that the following conditions are met: | 6 modification, are permitted provided that the following conditions are met: |
| 7 | 7 |
| 32 #include <cstdlib> | 32 #include <cstdlib> |
| 33 #include <cassert> | 33 #include <cassert> |
| 34 #include <cstring> | 34 #include <cstring> |
| 35 #include <string> | 35 #include <string> |
| 36 #include "lexer_scanner.h" | 36 #include "lexer_scanner.h" |
| 37 #include "lexer.h" | |
| 37 | 38 |
| 38 static const string g_token_strings[] = | 39 static const string g_token_strings[] = |
| 39 { | 40 { |
| 40 "==", | 41 "==", |
| 41 "[]", | 42 "[]", |
| 91 "enum", | 92 "enum", |
| 92 "func", | 93 "func", |
| 93 "return", | 94 "return", |
| 94 }; | 95 }; |
| 95 | 96 |
| 96 static_assert (countof (g_token_strings) == (int) last_named_token + 1, | 97 static_assert (countof (g_token_strings) == (int) last_named_token, |
| 97 "Count of g_token_strings is not the same as the amount of named token identifiers."); | 98 "Count of g_token_strings is not the same as the amount of named token identifiers."); |
| 98 | 99 |
| 99 // ============================================================================= | 100 // ============================================================================= |
| 100 // | 101 // |
| 101 lexer_scanner::lexer_scanner (FILE* fp) : | 102 lexer_scanner::lexer_scanner (FILE* fp) : |
| 128 // There is to be whitespace after words | 129 // There is to be whitespace after words |
| 129 if (r && (flags & f_check_word) && !isspace (m_ptr[strlen (c)])) | 130 if (r && (flags & f_check_word) && !isspace (m_ptr[strlen (c)])) |
| 130 r = false; | 131 r = false; |
| 131 | 132 |
| 132 // Advance the cursor unless we want to just peek | 133 // Advance the cursor unless we want to just peek |
| 133 if (r && ! (flags & f_check_peek)) | 134 if (r && !(flags & f_check_peek)) |
| 134 m_ptr += strlen (c); | 135 m_ptr += strlen (c); |
| 135 | 136 |
| 136 return r; | 137 return r; |
| 137 } | 138 } |
| 138 | 139 |
| 151 } | 152 } |
| 152 | 153 |
| 153 m_ptr++; | 154 m_ptr++; |
| 154 } | 155 } |
| 155 | 156 |
| 157 // Check for comments | |
| 158 if (strncmp (m_ptr, "//", 2) == 0) | |
| 159 { | |
| 160 m_ptr += 2; | |
| 161 | |
| 162 while (*(++m_ptr) != '\n') | |
| 163 ; | |
| 164 | |
| 165 return get_next_token(); | |
| 166 } | |
| 167 elif (strncmp (m_ptr, "/*", 2) == 0) | |
| 168 { | |
| 169 m_ptr += 2; | |
| 170 | |
| 171 while (strncmp (++m_ptr, "*/", 2) != 0) | |
| 172 { | |
| 173 if (*m_ptr == '\n') | |
| 174 { | |
| 175 m_line++; | |
| 176 m_line_break_pos = m_ptr; | |
| 177 } | |
| 178 } | |
| 179 | |
| 180 m_ptr += 2; // skip the */ | |
| 181 return get_next_token(); | |
| 182 } | |
| 183 | |
| 156 if (*m_ptr == '\0') | 184 if (*m_ptr == '\0') |
| 157 return false; | 185 return false; |
| 158 | 186 |
| 159 // Check tokens | 187 // Check tokens |
| 160 for (int i = 0; i < (int) (sizeof g_token_strings / sizeof * g_token_strings); ++i) | 188 for (int i = 0; i < (int) (sizeof g_token_strings / sizeof * g_token_strings); ++i) |
| 161 { | 189 { |
| 162 if (check_string (g_token_strings[i], f_check_word)) | 190 if (check_string (g_token_strings[i], f_check_word)) |
| 163 { | 191 { |
| 164 m_token_text = g_token_strings[i]; | 192 m_token_text = g_token_strings[i]; |
| 165 m_e_token = (e_token) i; | 193 m_token_type = (e_token) i; |
| 166 return true; | 194 return true; |
| 167 } | 195 } |
| 168 } | 196 } |
| 169 | 197 |
| 170 // Check and parse string | 198 // Check and parse string |
| 194 } | 222 } |
| 195 | 223 |
| 196 m_token_text += *m_ptr++; | 224 m_token_text += *m_ptr++; |
| 197 } | 225 } |
| 198 | 226 |
| 199 m_e_token = tk_string; | 227 m_token_type = tk_string; |
| 200 m_ptr++; // skip the final quote | 228 m_ptr++; // skip the final quote |
| 201 return true; | 229 return true; |
| 202 } | 230 } |
| 203 | 231 |
| 204 m_e_token = tk_symbol; | 232 m_token_type = tk_symbol; |
| 205 | 233 |
| 206 if (isdigit (*m_ptr)) | 234 if (isdigit (*m_ptr)) |
| 207 { | 235 { |
| 208 while (isdigit (*m_ptr)) | 236 while (isdigit (*m_ptr)) |
| 209 m_token_text += *m_ptr++; | 237 m_token_text += *m_ptr++; |
| 210 | 238 |
| 211 m_e_token = tk_number; | 239 m_token_type = tk_number; |
| 212 return true; | 240 return true; |
| 213 } | 241 } |
| 214 | 242 |
| 215 if (is_symbol_char (*m_ptr)) | 243 if (is_symbol_char (*m_ptr)) |
| 216 { | 244 { |
| 237 } | 265 } |
| 238 | 266 |
| 239 return true; | 267 return true; |
| 240 } | 268 } |
| 241 | 269 |
| 270 error ("unknown character \"%1\"", *m_ptr); | |
| 242 return false; | 271 return false; |
| 243 } | 272 } |
| 244 | 273 |
| 274 // ============================================================================= | |
| 275 // | |
| 245 string lexer_scanner::get_token_string (e_token a) | 276 string lexer_scanner::get_token_string (e_token a) |
| 246 { | 277 { |
| 247 assert ((int) a <= (int) last_named_token); | 278 assert ((int) a <= last_named_token); |
| 248 return g_token_strings[a]; | 279 return g_token_strings[a]; |
| 249 } | 280 } |
