comparison: src/lexerScanner.cpp
src/lexerScanner.cpp
- changeset 119
- bdf8d46c145f
- child 126
- c5858c0cd476
equal
deleted
inserted
replaced
| 118:e3361cf7cbf4 | 119:bdf8d46c145f |
|---|---|
| 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 "lexerScanner.h" | |
| 35 #include "lexer.h" | |
| 36 | |
| 37 static const String gTokenStrings[] = | |
| 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 "%", | |
| 70 ",", | |
| 71 "<", | |
| 72 ">", | |
| 73 ".", | |
| 74 ":", | |
| 75 ";", | |
| 76 "#", | |
| 77 "!", | |
| 78 "&", | |
| 79 "|", | |
| 80 "^", | |
| 81 "?", | |
| 82 "->", | |
| 83 "bool", | |
| 84 "break", | |
| 85 "case", | |
| 86 "continue", | |
| 87 "const", | |
| 88 "constexpr", | |
| 89 "default", | |
| 90 "do", | |
| 91 "else", | |
| 92 "event", | |
| 93 "eventdef", | |
| 94 "for", | |
| 95 "funcdef", | |
| 96 "if", | |
| 97 "int", | |
| 98 "mainloop", | |
| 99 "onenter", | |
| 100 "onexit", | |
| 101 "state", | |
| 102 "switch", | |
| 103 "str", | |
| 104 "using", | |
| 105 "var", | |
| 106 "void", | |
| 107 "while", | |
| 108 "true", | |
| 109 "false", | |
| 110 "enum", | |
| 111 "func", | |
| 112 "return", | |
| 113 }; | |
| 114 | |
| 115 static_assert (countof (gTokenStrings) == (int)gLastNamedToken + 1, | |
| 116 "Count of gTokenStrings is not the same as the amount of named token identifiers."); | |
| 117 | |
| 118 // ============================================================================= | |
| 119 // | |
| 120 LexerScanner::LexerScanner (FILE* fp) : | |
| 121 m_line (1) | |
| 122 { | |
| 123 long fsize, bytes; | |
| 124 | |
| 125 fseek (fp, 0l, SEEK_END); | |
| 126 fsize = ftell (fp); | |
| 127 rewind (fp); | |
| 128 m_data = new char[fsize]; | |
| 129 m_position = m_lineBreakPosition = &m_data[0]; | |
| 130 bytes = fread (m_data, 1, fsize, fp); | |
| 131 assert (bytes >= fsize); | |
| 132 } | |
| 133 | |
| 134 // ============================================================================= | |
| 135 // | |
| 136 LexerScanner::~LexerScanner() | |
| 137 { | |
| 138 delete m_data; | |
| 139 } | |
| 140 | |
| 141 // ============================================================================= | |
| 142 // | |
| 143 bool LexerScanner::checkString (const char* c, int flags) | |
| 144 { | |
| 145 bool r = strncmp (m_position, c, strlen (c)) == 0; | |
| 146 | |
| 147 // There is to be a non-symbol character after words | |
| 148 if (r && (flags & FCheckWord) && isSymbolChar (m_position[strlen (c)], true)) | |
| 149 r = false; | |
| 150 | |
| 151 // Advance the cursor unless we want to just peek | |
| 152 if (r && !(flags & FCheckPeek)) | |
| 153 m_position += strlen (c); | |
| 154 | |
| 155 return r; | |
| 156 } | |
| 157 | |
| 158 // ============================================================================= | |
| 159 // | |
| 160 bool LexerScanner::getNextToken() | |
| 161 { | |
| 162 m_tokenText = ""; | |
| 163 | |
| 164 while (isspace (*m_position)) | |
| 165 skip(); | |
| 166 | |
| 167 // Check for comments | |
| 168 if (strncmp (m_position, "//", 2) == 0) | |
| 169 { | |
| 170 m_position += 2; | |
| 171 | |
| 172 while (*m_position != '\n') | |
| 173 skip(); | |
| 174 | |
| 175 return getNextToken(); | |
| 176 } | |
| 177 elif (strncmp (m_position, "/*", 2) == 0) | |
| 178 { | |
| 179 skip (2); // skip the start symbols | |
| 180 | |
| 181 while (strncmp (m_position, "*/", 2) != 0) | |
| 182 skip(); | |
| 183 | |
| 184 skip (2); // skip the end symbols | |
| 185 return getNextToken(); | |
| 186 } | |
| 187 | |
| 188 if (*m_position == '\0') | |
| 189 return false; | |
| 190 | |
| 191 // Check tokens | |
| 192 for (int i = 0; i < countof (gTokenStrings); ++i) | |
| 193 { | |
| 194 int flags = 0; | |
| 195 | |
| 196 if (i >= gFirstNamedToken) | |
| 197 flags |= FCheckWord; | |
| 198 | |
| 199 if (checkString (gTokenStrings[i], flags)) | |
| 200 { | |
| 201 m_tokenText = gTokenStrings[i]; | |
| 202 m_tokenType = (ETokenType) i; | |
| 203 return true; | |
| 204 } | |
| 205 } | |
| 206 | |
| 207 // Check and parse string | |
| 208 if (*m_position == '\"') | |
| 209 { | |
| 210 m_position++; | |
| 211 | |
| 212 while (*m_position != '\"') | |
| 213 { | |
| 214 if (!*m_position) | |
| 215 error ("unterminated string"); | |
| 216 | |
| 217 if (checkString ("\\n")) | |
| 218 { | |
| 219 m_tokenText += '\n'; | |
| 220 continue; | |
| 221 } | |
| 222 elif (checkString ("\\t")) | |
| 223 { | |
| 224 m_tokenText += '\t'; | |
| 225 continue; | |
| 226 } | |
| 227 elif (checkString ("\\\"")) | |
| 228 { | |
| 229 m_tokenText += '"'; | |
| 230 continue; | |
| 231 } | |
| 232 | |
| 233 m_tokenText += *m_position++; | |
| 234 } | |
| 235 | |
| 236 m_tokenType =TK_String; | |
| 237 skip(); // skip the final quote | |
| 238 return true; | |
| 239 } | |
| 240 | |
| 241 if (isdigit (*m_position)) | |
| 242 { | |
| 243 while (isdigit (*m_position)) | |
| 244 m_tokenText += *m_position++; | |
| 245 | |
| 246 m_tokenType =TK_Number; | |
| 247 return true; | |
| 248 } | |
| 249 | |
| 250 if (isSymbolChar (*m_position, false)) | |
| 251 { | |
| 252 m_tokenType =TK_Symbol; | |
| 253 | |
| 254 do | |
| 255 { | |
| 256 if (!isSymbolChar (*m_position, true)) | |
| 257 break; | |
| 258 | |
| 259 m_tokenText += *m_position++; | |
| 260 } while (*m_position != '\0'); | |
| 261 | |
| 262 return true; | |
| 263 } | |
| 264 | |
| 265 error ("unknown character \"%1\"", *m_position); | |
| 266 return false; | |
| 267 } | |
| 268 | |
| 269 // ============================================================================= | |
| 270 // | |
| 271 void LexerScanner::skip() | |
| 272 { | |
| 273 if (*m_position == '\n') | |
| 274 { | |
| 275 m_line++; | |
| 276 m_lineBreakPosition = m_position; | |
| 277 } | |
| 278 | |
| 279 m_position++; | |
| 280 } | |
| 281 | |
| 282 // ============================================================================= | |
| 283 // | |
| 284 void LexerScanner::skip (int chars) | |
| 285 { | |
| 286 for (int i = 0; i < chars; ++i) | |
| 287 skip(); | |
| 288 } | |
| 289 | |
| 290 // ============================================================================= | |
| 291 // | |
| 292 String LexerScanner::getTokenString (ETokenType a) | |
| 293 { | |
| 294 assert ((int) a <= gLastNamedToken); | |
| 295 return gTokenStrings[a]; | |
| 296 } | |
| 297 | |
| 298 // ============================================================================= | |
| 299 // | |
| 300 String LexerScanner::readLine() | |
| 301 { | |
| 302 String line; | |
| 303 | |
| 304 while (*m_position != '\n') | |
| 305 line += *(m_position++); | |
| 306 | |
| 307 return line; | |
| 308 } |
