comparison: src/lexer.cc
src/lexer.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 <cstring> | |
| 30 #include "lexer.h" | |
| 31 | |
| 32 static string_list g_file_name_stack; | |
| 33 static lexer* g_main_lexer = null; | |
| 34 | |
| 35 // ============================================================================= | |
| 36 // | |
| 37 lexer::lexer() | |
| 38 { | |
| 39 assert (g_main_lexer == null); | |
| 40 g_main_lexer = this; | |
| 41 } | |
| 42 | |
| 43 // ============================================================================= | |
| 44 // | |
| 45 lexer::~lexer() | |
| 46 { | |
| 47 g_main_lexer = null; | |
| 48 } | |
| 49 | |
| 50 // ============================================================================= | |
| 51 // | |
| 52 void lexer::process_file (string file_name) | |
| 53 { | |
| 54 g_file_name_stack << file_name; | |
| 55 FILE* fp = fopen (file_name, "r"); | |
| 56 | |
| 57 if (fp == null) | |
| 58 error ("couldn't open %1 for reading: %2", file_name, strerror (errno)); | |
| 59 | |
| 60 lexer_scanner sc (fp); | |
| 61 check_file_header (sc); | |
| 62 | |
| 63 while (sc.get_next_token()) | |
| 64 { | |
| 65 // Preprocessor commands: | |
| 66 if (sc.get_token_type() == tk_hash) | |
| 67 { | |
| 68 must_get_next_from_scanner (sc, tk_symbol); | |
| 69 | |
| 70 if (sc.get_token_text() == "include") | |
| 71 { | |
| 72 must_get_next_from_scanner (sc, tk_string); | |
| 73 string file_name = sc.get_token_text(); | |
| 74 | |
| 75 if (g_file_name_stack.contains (file_name)) | |
| 76 error ("attempted to #include %1 recursively", sc.get_token_text()); | |
| 77 | |
| 78 process_file (file_name); | |
| 79 } | |
| 80 else | |
| 81 error ("unknown preprocessor directive \"#%1\"", sc.get_token_text()); | |
| 82 } | |
| 83 else | |
| 84 { | |
| 85 token tok; | |
| 86 tok.file = file_name; | |
| 87 tok.line = sc.get_line(); | |
| 88 tok.column = sc.get_column(); | |
| 89 tok.type = sc.get_token_type(); | |
| 90 tok.text = sc.get_token_text(); | |
| 91 | |
| 92 // devf ("Token #%1: %2:%3:%4: %5 (%6)\n", m_tokens.size(), | |
| 93 // tok.file, tok.line, tok.column, describe_token (&tok), describe_token_type (tok.type)); | |
| 94 | |
| 95 m_tokens << tok; | |
| 96 } | |
| 97 } | |
| 98 | |
| 99 m_token_position = m_tokens.begin() - 1; | |
| 100 g_file_name_stack.remove (file_name); | |
| 101 } | |
| 102 | |
| 103 // ============================================================================ | |
| 104 // | |
| 105 static bool is_valid_header (string header) | |
| 106 { | |
| 107 if (header.ends_with ("\n")) | |
| 108 header.remove_from_end (1); | |
| 109 | |
| 110 string_list tokens = header.split (" "); | |
| 111 | |
| 112 if (tokens.size() != 2 || tokens[0] != "#!botc" || tokens[1].empty()) | |
| 113 return false; | |
| 114 | |
| 115 string_list nums = tokens[1].split ("."); | |
| 116 | |
| 117 if (nums.size() == 2) | |
| 118 nums << "0"; | |
| 119 elif (nums.size() != 3) | |
| 120 return false; | |
| 121 | |
| 122 bool ok_a, ok_b, ok_c; | |
| 123 long major = nums[0].to_long (&ok_a); | |
| 124 long minor = nums[1].to_long (&ok_b); | |
| 125 long patch = nums[2].to_long (&ok_c); | |
| 126 | |
| 127 if (!ok_a || !ok_b || !ok_c) | |
| 128 return false; | |
| 129 | |
| 130 if (VERSION_NUMBER < MAKE_VERSION_NUMBER (major, minor, patch)) | |
| 131 error ("The script file requires " APPNAME " v%1, this is v%2", | |
| 132 make_version_string (major, minor, patch), get_version_string (e_short_form)); | |
| 133 | |
| 134 return true; | |
| 135 } | |
| 136 | |
| 137 // ============================================================================ | |
| 138 // | |
| 139 void lexer::check_file_header (lexer_scanner& sc) | |
| 140 { | |
| 141 if (!is_valid_header (sc.read_line())) | |
| 142 error ("Not a valid botscript file! File must start with '#!botc <version>'"); | |
| 143 } | |
| 144 | |
| 145 // ============================================================================= | |
| 146 // | |
| 147 bool lexer::get_next (e_token req) | |
| 148 { | |
| 149 iterator pos = m_token_position; | |
| 150 | |
| 151 if (m_tokens.is_empty()) | |
| 152 return false; | |
| 153 | |
| 154 m_token_position++; | |
| 155 | |
| 156 if (is_at_end() || (req != tk_any && get_token_type() != req)) | |
| 157 { | |
| 158 m_token_position = pos; | |
| 159 return false; | |
| 160 } | |
| 161 | |
| 162 return true; | |
| 163 } | |
| 164 | |
| 165 // ============================================================================= | |
| 166 // | |
| 167 void lexer::must_get_next (e_token tt) | |
| 168 { | |
| 169 if (!get_next()) | |
| 170 error ("unexpected EOF"); | |
| 171 | |
| 172 if (tt != tk_any) | |
| 173 must_be (tt); | |
| 174 } | |
| 175 | |
| 176 // ============================================================================= | |
| 177 // eugh.. | |
| 178 // | |
| 179 void lexer::must_get_next_from_scanner (lexer_scanner& sc, e_token tt) | |
| 180 { | |
| 181 if (!sc.get_next_token()) | |
| 182 error ("unexpected EOF"); | |
| 183 | |
| 184 if (tt != tk_any && sc.get_token_type() != tt) | |
| 185 { // TODO | |
| 186 token tok; | |
| 187 tok.type = sc.get_token_type(); | |
| 188 tok.text = sc.get_token_text(); | |
| 189 | |
| 190 error ("at %1:%2: expected %3, got %4", | |
| 191 g_file_name_stack.last(), | |
| 192 sc.get_line(), | |
| 193 describe_token_type (tt), | |
| 194 describe_token (&tok)); | |
| 195 } | |
| 196 } | |
| 197 | |
| 198 // ============================================================================= | |
| 199 // | |
| 200 void lexer::must_get_any_of (const list<e_token>& toks) | |
| 201 { | |
| 202 if (!get_next()) | |
| 203 error ("unexpected EOF"); | |
| 204 | |
| 205 for (e_token tok : toks) | |
| 206 if (get_token_type() == tok) | |
| 207 return; | |
| 208 | |
| 209 string toknames; | |
| 210 | |
| 211 for (const e_token& tok_type : toks) | |
| 212 { | |
| 213 if (&tok_type == &toks.last()) | |
| 214 toknames += " or "; | |
| 215 elif (toknames.is_empty() == false) | |
| 216 toknames += ", "; | |
| 217 | |
| 218 toknames += describe_token_type (tok_type); | |
| 219 } | |
| 220 | |
| 221 error ("expected %1, got %2", toknames, describe_token (get_token())); | |
| 222 } | |
| 223 | |
| 224 // ============================================================================= | |
| 225 // | |
| 226 int lexer::get_one_symbol (const string_list& syms) | |
| 227 { | |
| 228 if (!get_next()) | |
| 229 error ("unexpected EOF"); | |
| 230 | |
| 231 if (get_token_type() == tk_symbol) | |
| 232 { | |
| 233 for (int i = 0; i < syms.size(); ++i) | |
| 234 { | |
| 235 if (syms[i] == get_token()->text) | |
| 236 return i; | |
| 237 } | |
| 238 } | |
| 239 | |
| 240 error ("expected one of %1, got %2", syms, describe_token (get_token())); | |
| 241 return -1; | |
| 242 } | |
| 243 | |
| 244 // ============================================================================= | |
| 245 // | |
| 246 void lexer::must_be (e_token tok) | |
| 247 { | |
| 248 if (get_token_type() != tok) | |
| 249 error ("expected %1, got %2", describe_token_type (tok), | |
| 250 describe_token (get_token())); | |
| 251 } | |
| 252 | |
| 253 // ============================================================================= | |
| 254 // | |
| 255 string lexer::describe_token_private (e_token tok_type, lexer::token* tok) | |
| 256 { | |
| 257 if (tok_type < tk_last_named_token) | |
| 258 return "\"" + lexer_scanner::get_token_string (tok_type) + "\""; | |
| 259 | |
| 260 switch (tok_type) | |
| 261 { | |
| 262 case tk_symbol: return tok ? tok->text : "a symbol"; | |
| 263 case tk_number: return tok ? tok->text : "a number"; | |
| 264 case tk_string: return tok ? ("\"" + tok->text + "\"") : "a string"; | |
| 265 case tk_any: return tok ? tok->text : "any token"; | |
| 266 default: break; | |
| 267 } | |
| 268 | |
| 269 return ""; | |
| 270 } | |
| 271 | |
| 272 // ============================================================================= | |
| 273 // | |
| 274 bool lexer::peek_next (lexer::token* tk) | |
| 275 { | |
| 276 iterator pos = m_token_position; | |
| 277 bool r = get_next(); | |
| 278 | |
| 279 if (r && tk != null) | |
| 280 *tk = *m_token_position; | |
| 281 | |
| 282 m_token_position = pos; | |
| 283 return r; | |
| 284 } | |
| 285 | |
| 286 // ============================================================================= | |
| 287 // | |
| 288 lexer* lexer::get_current_lexer() | |
| 289 { | |
| 290 return g_main_lexer; | |
| 291 } | |
| 292 | |
| 293 // ============================================================================= | |
| 294 // | |
| 295 string lexer::peek_next_string (int a) | |
| 296 { | |
| 297 if (m_token_position + a >= m_tokens.end()) | |
| 298 return ""; | |
| 299 | |
| 300 iterator oldpos = m_token_position; | |
| 301 m_token_position += a; | |
| 302 string result = get_token()->text; | |
| 303 m_token_position = oldpos; | |
| 304 return result; | |
| 305 } |
