Mu - 011load.cc

https://github.com/akkartik/mu/blob/master/011load.cc

  1 //: Phase 1 of running Mu code: load it from a textual representation.
  2 //:
  3 //: The process of running Mu code:
  4 //:   load -> transform -> run
  5 
  6 :(scenarios load)  // use 'load' instead of 'run' in all scenarios in this layer
  7 :(scenario first_recipe)
  8 def main [
  9   1:number <- copy 23
 10 ]
 11 +parse: instruction: copy
 12 +parse:   ingredient: {23: "literal"}
 13 +parse:   product: {1: "number"}
 14 
 15 pre { line-height: 125%; }
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
.highlight .hll { background-color: #ffffcc }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .ges { font-weight: bold; font-style: italic } /* Generic.EmphStrong */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #666666 } /* Generic.Subheading */
.highlight .gt { color: #aa0000 } /* Generic.Traceback */
.highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #008800 } /* Keyword.Pseudo */
.highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */
.highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */
.highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */
.highlight .na { color: #336699 } /* Name.Attribute */
.highlight .nb { color: #003388 } /* Name.Builtin */
.highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */
.highlight .no { color: #003366; font-weight: bold } /* Name.Constant */
.highlight .nd { color: #555555 } /* Name.Decorator */
.highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */
.highlight .nl { color: #336699; font-style: italic } /* Name.Label */
.highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */
.highlight .py { color: #336699; font-weight: bold } /* Name.Property */
.highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */
.highlight .nv { color: #336699 } /* Name.Variable */
.highlight .ow { color: #008800 } /* Operator.Word */
.highlight .w { color: #bbbbbb } /* Text.Whitespace */
.highlight .mb { color: #0000DD; font-weight: bold } /* Literal.Number.Bin */
.highlight .mf { color: #0000DD; font-weight: bold } /* Literal.Number.Float */
.highlight .mh { color: #0000DD; font-weight: bold } /* Literal.Number.Hex */
.highlight .mi { color: #0000DD; font-weight: bold } /* Literal.Number.Integer */
.highlight .mo { color: #0000DD; font-weight: bold } /* Literal.Number.Oct */
.highlight .sa { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Affix */
.highlight .sb { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Backtick */
.highlight .sc { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Char */
.highlight .dl { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Delimiter */
.highlight .sd { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Doc */
.highlight .s2 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Double */
.highlight .se { color: #0044dd; background-color: #fff0f0 } /* Literal.String.Escape */
.highlight .sh { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Heredoc */
.highlight .si { color: #3333bb; background-color: #fff0f0 } /* Literal.String.Interpol */
.highlight .sx { color: #22bb22; background-color: #f0fff0 } /* Literal.String.Other */
.highlight .sr { color: #008800; background-color: #fff0ff } /* Literal.String.Regex */
.highlight .s1 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Single */
.highlight .ss { color: #aa6600; background-color: #fff0f0 } /* Literal.String.Symbol */
.highlight .bp { color: #003388 } /* Name.Builtin.Pseudo */
.highlight .fm { color: #0066bb; font-weight: bold } /* Name.Function.Magic */
.highlight .vc { color: #336699 } /* Name.Variable.Class */
.highlight .vg { color: #dd7700 } /* Name.Variable.Global */
.highlight .vi { color: #3333bb } /* Name.Variable.Instance */
.highlight .vm { color: #336699 } /* Name.Variable.Magic */
.highlight .il { color: #0000DD; font-weight: bold } /* Literal.Number.Integer.Long */discard """
  errormsg: "The variable name cannot be `result`!"
"""

import sugar

proc begin(): int =
  capture result:
    echo 1+1
  result

/span>empty()) { 57 assert(!has_data(in)); 58 raise << "file ended with 'recipe'\n" << end(); 59 return -1; 60 } 61 // End Load Recipe Name 62 skip_whitespace_but_not_newline(in); 63 // End Recipe Refinements 64 if (result.name.empty()) 65 raise << "empty result.name\n" << end(); 66 trace(9991, "parse") << "--- defining " << result.name << end(); 67 if (!contains_key(Recipe_ordinal, result.name)) 68 put(Recipe_ordinal, result.name, Next_recipe_ordinal); 69 result.ordinal = get(Recipe_ordinal, result.name); 70 ++Next_recipe_ordinal; 71 if (Recipe.find(get(Recipe_ordinal, result.name)) != Recipe.end()) { 72 trace(9991, "parse") << "already exists" << end(); 73 if (should_check_for_redefine(result.name)) 74 raise << "redefining recipe " << result.name << "\n" << end(); 75 Recipe.erase(get(Recipe_ordinal, result.name)); 76 } 77 slurp_body(in, result); 78 // End Recipe Body(result) 79 put(Recipe, get(Recipe_ordinal, result.name), result); 80 return get(Recipe_ordinal, result.name); 81 } 82 83 void slurp_body(istream& in, recipe& result) { 84 in >> std::noskipws; 85 skip_whitespace_but_not_newline(in); 86 if (in.get() != '[') 87 raise << result.name << ": recipe body must begin with '['\n" << end(); 88 skip_whitespace_and_comments(in); // permit trailing comment after '[' 89 instruction curr; 90 while (next_instruction(in, &curr)) { 91 curr.original_string = to_original_string(curr); 92 // End Rewrite Instruction(curr, recipe result) 93 trace(9992, "load") << "after rewriting: " << to_string(curr) << end(); 94 if (!curr.is_empty()) result.steps.push_back(curr); 95 } 96 } 97 98 bool next_instruction(istream& in, instruction* curr) { 99 curr->clear(); 100 skip_whitespace_and_comments(in); 101 if (!has_data(in)) { 102 raise << "incomplete recipe at end of file (0)\n" << end(); 103 return false; 104 } 105 106 vector<string> words; 107 while (has_data(in) && in.peek() != '\n') { 108 skip_whitespace_but_not_newline(in); 109 if (!has_data(in)) { 110 raise << "incomplete recipe at end of file (1)\n" << end(); 111 return false; 112 } 113 string word = next_word(in); 114 if (word.empty()) { 115 assert(!has_data(in)); 116 raise << "incomplete recipe at end of file (2)\n" << end(); 117 return false; 118 } 119 words.push_back(word); 120 skip_whitespace_but_not_newline(in); 121 } 122 skip_whitespace_and_comments(in); 123 if (SIZE(words) == 1 && words.at(0) == "]") 124 return false; // end of recipe 125 126 if (SIZE(words) == 1 && is_label_word(words.at(0))) { 127 curr->is_label = true; 128 curr->label = words.at(0); 129 trace(9993, "parse") << "label: " << curr->label << end(); 130 if (!has_data(in)) { 131 raise << "incomplete recipe at end of file (3)\n" << end(); 132 return false; 133 } 134 return true; 135 } 136 137 vector<string>::iterator p = words.begin(); 138 if (find(words.begin(), words.end(), "<-") != words.end()) { 139 for (; *p != "<-"; ++p) 140 curr->products.push_back(reagent(*p)); 141 ++p; // skip <- 142 } 143 144 if (p == words.end()) { 145 raise << "instruction prematurely ended with '<-'\n" << end(); 146 return false; 147 } 148 curr->name = *p; ++p; 149 // curr->operation will be set at transform time 150 151 for (; p != words.end(); ++p) 152 curr->ingredients.push_back(reagent(*p)); 153 154 trace(9993, "parse") << "instruction: " << curr->name << end(); 155 trace(9993, "parse") << " number of ingredients: " << SIZE(curr->ingredients) << end(); 156 for (vector<reagent>::iterator p = curr->ingredients.begin(); p != curr->ingredients.end(); ++p) 157 trace(9993, "parse") << " ingredient: " << to_string(*p) << end(); 158 for (vector<reagent>::iterator p = curr->products.begin(); p != curr->products.end(); ++p) 159 trace(9993, "parse") << " product: " << to_string(*p) << end(); 160 if (!has_data(in)) { 161 raise << "9: unbalanced '[' for recipe\n" << end(); 162 return false; 163 } 164 // End next_instruction(curr) 165 return true; 166 } 167 168 // can return empty string -- only if 'in' has no more data 169 string next_word(istream& in) { 170 skip_whitespace_but_not_newline(in); 171 // End next_word Special-cases 172 ostringstream out; 173 slurp_word(in, out); 174 skip_whitespace_and_comments_but_not_newline(in); 175 string result = out.str(); 176 if (result != "[" && ends_with(result, '[')) 177 raise << "insert a space before '[' in '" << result << "'\n" << end(); 178 return result; 179 } 180 181 bool is_label_word(const string& word) { 182 if (word.empty()) return false; // error raised elsewhere 183 return !isalnum(word.at(0)) && string("$_*@&,=-[]()").find(word.at(0)) == string::npos; 184 } 185 186 bool ends_with(const string& s, const char c) { 187 if (s.empty()) return false; 188 return *s.rbegin() == c; 189 } 190 191 :(before "End Globals") 192 // word boundaries 193 extern const string Terminators("(){}"); 194 :(code) 195 void slurp_word(istream& in, ostream& out) { 196 char c; 197 if (has_data(in) && Terminators.find(in.peek()) != string::npos) { 198 in >> c; 199 out << c; 200 return; 201 } 202 while (in >> c) { 203 if (isspace(c) || Terminators.find(c) != string::npos || Ignore.find(c) != string::npos) { 204 in.putback(c); 205 break; 206 } 207 out << c; 208 } 209 } 210 211 void skip_whitespace_and_comments(istream& in) { 212 while (true) { 213 if (!has_data(in)) break; 214 if (isspace(in.peek())) in.get(); 215 else if (Ignore.find(in.peek()) != string::npos) in.get(); 216 else if (in.peek() == '#') skip_comment(in); 217 else break; 218 } 219 } 220 221 // confusing; move to the next line only to skip a comment, but never otherwise 222 void skip_whitespace_and_comments_but_not_newline(istream& in) { 223 while (true) { 224 if (!has_data(in)) break; 225 if (in.peek() == '\n') break; 226 if (isspace(in.peek())) in.get(); 227 else if (Ignore.find(in.peek()) != string::npos) in.get(); 228 else if (in.peek() == '#') skip_comment(in); 229 else break; 230 } 231 } 232 233 void skip_comment(istream& in) { 234 if (has_data(in) && in.peek() == '#') { 235 in.get(); 236 while (has_data(in) && in.peek() != '\n') in.get(); 237 } 238 } 239 240 :(scenario recipe_instead_of_def) 241 recipe main [ 242 1:number <- copy 23 243 ] 244 +parse: instruction: copy 245 +parse: ingredient: {23: "literal"} 246 +parse: product: {1: "number"} 247 248 :(scenario parse_comment_outside_recipe) 249 # this comment will be dropped by the tangler, so we need a dummy recipe to stop that 250 def f1 [ 251 ] 252 # this comment will go through to 'load' 253 def main [ 254 1:number <- copy 23 255 ] 256 +parse: instruction: copy 257 +parse: ingredient: {23: "literal"} 258 +parse: product: {1: "number"} 259 260 :(scenario parse_comment_amongst_instruction) 261 def main [ 262 # comment 263 1:number <- copy 23 264 ] 265 +parse: instruction: copy 266 +parse: ingredient: {23: "literal"} 267 +parse: product: {1: "number"} 268 269 :(scenario parse_comment_amongst_instruction_2) 270 def main [ 271 # comment 272 1:number <- copy 23 273 # comment 274 ] 275 +parse: instruction: copy 276 +parse: ingredient: {23: "literal"} 277 +parse: product: {1: "number"} 278 279 :(scenario parse_comment_amongst_instruction_3) 280 def main [ 281 1:number <- copy 23 282 # comment 283 2:number <- copy 23 284 ] 285 +parse: instruction: copy 286 +parse: ingredient: {23: "literal"} 287 +parse: product: {1: "number"} 288 +parse: instruction: copy 289 +parse: ingredient: {23: "literal"} 290 +parse: product: {2: "number"} 291 292 :(scenario parse_comment_after_instruction) 293 def main [ 294 1:number <- copy 23 # comment 295 ] 296 +parse: instruction: copy 297 +parse: ingredient: {23: "literal"} 298 +parse: product: {1: "number"} 299 300 :(scenario parse_label) 301 def main [ 302 +foo 303 ] 304 +parse: label: +foo 305 306 :(scenario parse_dollar_as_recipe_name) 307 def main [ 308 $foo 309 ] 310 +parse: instruction: $foo 311 312 :(scenario parse_multiple_properties) 313 def main [ 314 1:number <- copy 23/foo:bar:baz 315 ] 316 +parse: instruction: copy 317 +parse: ingredient: {23: "literal", "foo": ("bar" "baz")} 318 +parse: product: {1: "number"} 319 320 :(scenario parse_multiple_products) 321 def main [ 322 1:number, 2:number <- copy 23 323 ] 324 +parse: instruction: copy 325 +parse: ingredient: {23: "literal"} 326 +parse: product: {1: "number"} 327 +parse: product: {2: "number"} 328 329 :(scenario parse_multiple_ingredients) 330 def main [ 331 1:number, 2:number <- copy 23, 4:number 332 ] 333 +parse: instruction: copy 334 +parse: ingredient: {23: "literal"} 335 +parse: ingredient: {4: "number"} 336 +parse: product: {1: "number"} 337 +parse: product: {2: "number"} 338 339 :(scenario parse_multiple_types) 340 def main [ 341 1:number, 2:address:number <- copy 23, 4:number 342 ] 343 +parse: instruction: copy 344 +parse: ingredient: {23: "literal"} 345 +parse: ingredient: {4: "number"} 346 +parse: product: {1: "number"} 347 +parse: product: {2: ("address" "number")} 348 349 :(scenario parse_properties) 350 def main [ 351 1:address:number/lookup <- copy 23 352 ] 353 +parse: product: {1: ("address" "number"), "lookup": ()} 354 355 //: this test we can't represent with a scenario 356 :(code) 357 void test_parse_comment_terminated_by_eof() { 358 load("recipe main [\n" 359 " a:number <- copy 34\n" 360 "]\n" 361 "# abc"); // no newline after comment 362 cerr << "."; // termination = success 363 } 364 365 :(scenario warn_on_missing_space_before_bracket) 366 % Hide_errors = true; 367 def main[ 368 1:number <- copy 23 369 ] 370 +error: insert a space before '[' in 'main[' 371 372 //: Warn if a recipe gets redefined, because large codebases can accidentally 373 //: step on their own toes. But there'll be many occasions later where 374 //: we'll want to disable the errors. 375 :(before "End Globals") 376 bool Disable_redefine_checks = false; 377 :(before "End Reset") 378 Disable_redefine_checks = false; 379 :(code) 380 bool should_check_for_redefine(const string& recipe_name) { 381 if (Disable_redefine_checks) return false; 382 return true; 383 } 384 385 :(scenario forbid_redefining_recipes) 386 % Hide_errors = true; 387 def main [ 388 1:number <- copy 23 389 ] 390 def main [ 391 1:number <- copy 24 392 ] 393 +error: redefining recipe main 394 395 :(scenario permit_forcibly_redefining_recipes) 396 def main [ 397 1:number <- copy 23 398 ] 399 def! main [ 400 1:number <- copy 24 401 ] 402 -error: redefining recipe main 403 $error: 0 404 405 :(code) 406 // for debugging 407 void show_rest_of_stream(istream& in) { 408 cerr << '^'; 409 char c; 410 while (in >> c) 411 cerr << c; 412 cerr << "$\n"; 413 exit(0); 414 }