comparison: src/lexer.cc
src/lexer.cc
- changeset 73
- 1ee9b312dc18
- child 74
- 007fbadfa7f9
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 <cstring> | |
| 32 #include "lexer.h" | |
| 33 | |
| 34 static string_list g_file_name_stack; | |
| 35 static lexer* g_main_lexer = null; | |
| 36 | |
| 37 lexer::lexer() | |
| 38 { | |
| 39 assert (g_main_lexer == null); | |
| 40 g_main_lexer = this; | |
| 41 devf ("Lexer initialized\n"); | |
| 42 } | |
| 43 | |
| 44 lexer::~lexer() | |
| 45 { | |
| 46 g_main_lexer = null; | |
| 47 devf ("Lexer de-initialized\n"); | |
| 48 } | |
| 49 | |
| 50 void lexer::process_file (string file_name) | |
| 51 { | |
| 52 devf ("Lexer: processing %1\n", file_name); | |
| 53 FILE* fp = fopen (file_name, "r"); | |
| 54 | |
| 55 if (fp == null) | |
| 56 error ("couldn't open %1 for reading: %2", file_name, strerror (errno)); | |
| 57 | |
| 58 lexer_scanner sc (fp); | |
| 59 | |
| 60 while (sc.get_next_token()) | |
| 61 { | |
| 62 // Preprocessor commands: | |
| 63 if (sc.get_e_token() == tk_hash) | |
| 64 { | |
| 65 must_get_next_from_scanner (sc, tk_symbol); | |
| 66 | |
| 67 if (sc.get_token_text() == "include") | |
| 68 { | |
| 69 devf ("Lexer: encountered #include\n"); | |
| 70 | |
| 71 must_get_next_from_scanner (sc, tk_string); | |
| 72 string file_name = sc.get_token_text(); | |
| 73 | |
| 74 if (g_file_name_stack.contains (file_name)) | |
| 75 error ("attempted to #include %1 recursively", sc.get_token_text()); | |
| 76 | |
| 77 process_file (file_name); | |
| 78 } | |
| 79 else | |
| 80 error ("unknown preprocessor directive \"#%1\"", sc.get_token_text()); | |
| 81 } | |
| 82 else | |
| 83 { | |
| 84 token tok; | |
| 85 tok.file = file_name; | |
| 86 tok.line = sc.get_line(); | |
| 87 tok.column = sc.get_column(); | |
| 88 tok.type = sc.get_e_token(); | |
| 89 tok.text = sc.get_token_text(); | |
| 90 m_tokens << tok; | |
| 91 devf ("Lexer: added %1 (%2)\n", describe_e_token (tok.type), | |
| 92 describe_token (&tok)); | |
| 93 } | |
| 94 } | |
| 95 | |
| 96 devf ("Lexer: File %1 processed.\n", file_name); | |
| 97 m_token_position = m_tokens.begin() - 1; | |
| 98 } | |
| 99 | |
| 100 // ============================================================================= | |
| 101 // | |
| 102 bool lexer::get_next (e_token req) | |
| 103 { | |
| 104 iterator pos = m_token_position; | |
| 105 devf ("Lexer: Requested next token, requirement: %1\n", describe_e_token (req)); | |
| 106 | |
| 107 if (is_at_end()) | |
| 108 { | |
| 109 devf ("Lexer: at end of tokens. Failed.\n"); | |
| 110 return false; | |
| 111 } | |
| 112 | |
| 113 m_token_position++; | |
| 114 | |
| 115 if (req != tk_any && get_token() != req) | |
| 116 { | |
| 117 devf ("Lexer: Token %1 does not meet the requirement\n", describe_token (get_token())); | |
| 118 m_token_position = pos; | |
| 119 return false; | |
| 120 } | |
| 121 | |
| 122 devf ("Lexer: Get successful: %1\n", describe_token (get_token())); | |
| 123 return true; | |
| 124 } | |
| 125 | |
| 126 // ============================================================================= | |
| 127 // | |
| 128 void lexer::must_get_next (e_token tok) | |
| 129 { | |
| 130 if (!get_next()) | |
| 131 error ("unexpected EOF"); | |
| 132 | |
| 133 must_be (tok); | |
| 134 } | |
| 135 | |
| 136 // ============================================================================= | |
| 137 // eugh.. | |
| 138 // | |
| 139 void lexer::must_get_next_from_scanner (lexer_scanner& sc, e_token tok) | |
| 140 { | |
| 141 if (!sc.get_next_token()) | |
| 142 error ("unexpected EOF"); | |
| 143 | |
| 144 if (tok != tk_any && sc.get_e_token() != tok) | |
| 145 error ("expected %1, got %2", describe_e_token (tok), | |
| 146 describe_token (get_token())); | |
| 147 } | |
| 148 | |
| 149 // ============================================================================= | |
| 150 // | |
| 151 void lexer::must_get_any_of (const list<e_token>& toks) | |
| 152 { | |
| 153 devf ("Lexer: need to get a token that is any of: %1\n", toks); | |
| 154 | |
| 155 if (!get_next()) | |
| 156 error ("unexpected EOF"); | |
| 157 | |
| 158 for (e_token tok : toks) | |
| 159 if (get_token() == tok) | |
| 160 return; | |
| 161 | |
| 162 string toknames; | |
| 163 | |
| 164 for (const e_token& tok_type : toks) | |
| 165 { | |
| 166 if (&tok_type == &toks.last()) | |
| 167 toknames += " or "; | |
| 168 elif (toknames.is_empty() == false) | |
| 169 toknames += ", "; | |
| 170 | |
| 171 toknames += describe_e_token (tok_type); | |
| 172 } | |
| 173 | |
| 174 error ("expected %1, got %2", toknames, describe_token (get_token())); | |
| 175 } | |
| 176 | |
| 177 // ============================================================================= | |
| 178 // | |
| 179 int lexer::get_one_symbol (const string_list& syms) | |
| 180 { | |
| 181 if (!get_next()) | |
| 182 error ("unexpected EOF"); | |
| 183 | |
| 184 if (get_token() == tk_symbol) | |
| 185 { | |
| 186 for (int i = 0; i < syms.size(); ++i) | |
| 187 { | |
| 188 if (syms[i] == get_token()->text) | |
| 189 return i; | |
| 190 } | |
| 191 } | |
| 192 | |
| 193 error ("expected one of %1, got %2", syms, describe_token (get_token())); | |
| 194 return -1; | |
| 195 } | |
| 196 | |
| 197 // ============================================================================= | |
| 198 // | |
| 199 void lexer::must_be (e_token tok) | |
| 200 { | |
| 201 if (get_token() != tok) | |
| 202 error ("expected %1, got %2", describe_e_token (tok), | |
| 203 describe_token (get_token())); | |
| 204 } | |
| 205 | |
| 206 // ============================================================================= | |
| 207 // | |
| 208 string lexer::describe_token_private (e_token tok_type, lexer::token* tok) | |
| 209 { | |
| 210 if ( (int) tok_type < (int) last_named_token) | |
| 211 return "\"" + lexer_scanner::get_token_string (tok_type) + "\""; | |
| 212 | |
| 213 switch (tok_type) | |
| 214 { | |
| 215 case tk_symbol: | |
| 216 return tok ? tok->text : "a symbol"; | |
| 217 | |
| 218 case tk_number: | |
| 219 return tok ? tok->text : "a number"; | |
| 220 | |
| 221 case tk_string: | |
| 222 return tok ? ("\"" + tok->text + "\"") : "a string"; | |
| 223 | |
| 224 case tk_any: | |
| 225 return tok ? tok->text : "any token"; | |
| 226 | |
| 227 default: | |
| 228 break; | |
| 229 } | |
| 230 | |
| 231 return ""; | |
| 232 } | |
| 233 | |
| 234 // ============================================================================= | |
| 235 // | |
| 236 bool lexer::peek_next (lexer::token* tk) | |
| 237 { | |
| 238 iterator pos = m_token_position; | |
| 239 bool r = get_next(); | |
| 240 | |
| 241 if (r && tk != null) | |
| 242 *tk = *m_token_position; | |
| 243 | |
| 244 m_token_position = pos; | |
| 245 return r; | |
| 246 } | |
| 247 | |
| 248 // ============================================================================= | |
| 249 // | |
| 250 lexer* lexer::get_main_lexer() | |
| 251 { | |
| 252 return g_main_lexer; | |
| 253 } |
