newfangle

   1 #! /usr/bin/awk -f
   2 # newfangle - fully featured notangle replacement in awk
   3 #
   4 #  Copyright (C) Sam Liddicott 2009
   5 #
   6 #  This program is free software: you can redistribute it and/or modify
   7 #  it under the terms of the GNU General Public License as published by
   8 #  the Free Software Foundation, either version 3 of the License, or
   9 #  (at your option) any later version.
  10 #
  11 #  This program is distributed in the hope that it will be useful,
  12 #  but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 #  GNU General Public License for more details.
  15 #
  16 #  You should have received a copy of the GNU General Public License
  17 #  along with this program.  If not, see <http://www.gnu.org/licenses/>.
  18 #
  19
  20
  21 # NOTE: Arnold Robbins public domain getopt for awk is also used:
  22 # getopt.awk --- do C library getopt(3) function in awk
  23 #
  24 # Arnold Robbins, arnold@skeeve.com, Public Domain
  25 #
  26 # Initial version: March, 1991
  27 # Revised: May, 1993
  28
  29
  30 function getopt(argc, argv, options,    thisopt, i)
  31 {
  32     if (length(options) == 0)    # no options given
  33         return -1
  34     if (argv[Optind] == "--") {  # all done
  35         Optind++
  36         _opti = 0
  37         return -1
  38     } else if (argv[Optind] !~ /^-[^: \t\n\f\r\v\b]/) {
  39         _opti = 0
  40         return -1
  41     }
  42     if (_opti == 0)
  43         _opti = 2
  44     thisopt = substr(argv[Optind], _opti, 1)
  45     Optopt = thisopt
  46     i = index(options, thisopt)
  47     if (i == 0) {
  48         if (Opterr)
  49             printf("%c -- invalid option\n",
  50                                   thisopt) > "/dev/stderr"
  51         if (_opti >= length(argv[Optind])) {
  52             Optind++
  53             _opti = 0
  54         } else
  55             _opti++
  56         return "?"
  57     }
  58     if (substr(options, i + 1, 1) == ":") {
  59         # get option argument
  60         if (length(substr(argv[Optind], _opti + 1)) > 0)
  61             Optarg = substr(argv[Optind], _opti + 1)
  62         else
  63             Optarg = argv[++Optind]
  64         _opti = 0
  65     } else
  66         Optarg = ""
  67     if (_opti == 0 || _opti >= length(argv[Optind])) {
  68         Optind++
  69         _opti = 0
  70     } else
  71         _opti++
  72     return thisopt
  73 }
  74
  75 function error(message)
  76 {
  77   print "ERROR: " FILENAME ":" FNR " " message > "/dev/stderr";
  78   exit 1;
  79 }
  80 function warning(message)
  81 {
  82   print "WARNING: " FILENAME ":" FNR " " message > "/dev/stderr";
  83   warnings++;
  84 }
  85 function new_mode_tracker(context, language, mode) {
  86   context[""] = 0;
  87   context[0, "language"] = language;
  88   context[0, "mode"] = mode;
  89 }
  90 function push_mode_tracker(context, language, mode,
  91   # local vars
  92   top)
  93 {
  94   if (! ("" in context)) {
  95     split("", context);
  96     new_mode_tracker(context, language, mode);
  97   } else {
  98     top = context[""];
  99     if (context[top, "language"] == language && mode=="") mode = context[top, "mode"];
 100     top++;
 101     context[top, "language"] = language;
 102     context[top, "mode"] = mode;
 103     context[""] = top;
 104   }
 105 }
 106 function finalize_mode_tracker(context,
 107   # local vars
 108   top)
 109 {
 110   if ( ("" in context) && context[""] != 0) return 0;
 111   return 1;
 112 }
 113 function mode_tracker(context, text, values,
 114   # optional parameters
 115   # local vars
 116   mode, submodes, language,
 117   cindex, c, a, part, item, name, result, new_values, new_mode,
 118   delimiters, terminators)
 119 {
 120   cindex = context[""] + 0;
 121   mode = context[cindex, "mode"];
 122   language = context[cindex, "language" ];
 123   submodes=modes[language, mode, "submodes"];
 124
 125   if ((language, mode, "delimiters") in modes) {
 126     delimiters = modes[language, mode, "delimiters"];
 127     if (length(submodes)>0) submodes = submodes "|";
 128     submodes=submodes delimiters;
 129   } else delimiters="";
 130   if ((language, mode, "terminators") in modes) {
 131     terminators = modes[language, mode, "terminators"];
 132     if (length(submodes)>0) submodes = submodes "|";
 133     submodes=submodes terminators;
 134   } else terminators="";
 135   if (! length(submodes)) return text;
 136   while((cindex >= 0) && length(text)) {
 137     if (match(text, "(" submodes ")", a)) {
 138       if (RLENGTH<1) {
 139         error(sprintf("Internal error, matched zero length submode, should be impossible - likely regex computation error\n" \
 140                 "Language=%s\nmode=%s\nmatch=%s\n", language, mode, submodes));
 141       }
 142       part = substr(text, 1, RSTART -1);
 143       item = item part;
 144       if (match(a[1], "^" terminators "$")) {
 145 #printf("%2d EXIT  MODE [%s] by [%s] [%s]\n", cindex, mode, a[1], text) > "/dev/stderr"
 146         context[cindex, "values", ++context[cindex, "values"]] = item;
 147         delete context[cindex];
 148         context[""] = --cindex;
 149         if (cindex>=0) {
 150           mode = context[cindex, "mode"];
 151           language = context[cindex, "language"];
 152             submodes=modes[language, mode, "submodes"];
 153
 154             if ((language, mode, "delimiters") in modes) {
 155               delimiters = modes[language, mode, "delimiters"];
 156               if (length(submodes)>0) submodes = submodes "|";
 157               submodes=submodes delimiters;
 158             } else delimiters="";
 159             if ((language, mode, "terminators") in modes) {
 160               terminators = modes[language, mode, "terminators"];
 161               if (length(submodes)>0) submodes = submodes "|";
 162               submodes=submodes terminators;
 163             } else terminators="";
 164             if (! length(submodes)) return text;
 165         }
 166         item = item a[1];
 167         text = substr(text, 1 + length(part) + length(a[1]));
 168       }
 169       else if (match(a[1], "^" delimiters "$")) {
 170         if (cindex==0) {
 171           context[cindex, "values", ++context[cindex, "values"]] = item;
 172           item = "";
 173         } else {
 174           item = item a[1];
 175         }
 176         text = substr(text, 1 + length(part) + length(a[1]));
 177       }
 178  else if ((language, a[1], "terminators") in modes) {
 179         #check if new_mode is defined
 180         item = item a[1];
 181 #printf("%2d ENTER MODE [%s] in [%s]\n", cindex, a[1], text) > "/dev/stderr"
 182         text = substr(text, 1 + length(part) + length(a[1]));
 183         context[""] = ++cindex;
 184         context[cindex, "mode"] = a[1];
 185         context[cindex, "language"] = language;
 186         mode = a[1];
 187           submodes=modes[language, mode, "submodes"];
 188
 189           if ((language, mode, "delimiters") in modes) {
 190             delimiters = modes[language, mode, "delimiters"];
 191             if (length(submodes)>0) submodes = submodes "|";
 192             submodes=submodes delimiters;
 193           } else delimiters="";
 194           if ((language, mode, "terminators") in modes) {
 195             terminators = modes[language, mode, "terminators"];
 196             if (length(submodes)>0) submodes = submodes "|";
 197             submodes=submodes terminators;
 198           } else terminators="";
 199           if (! length(submodes)) return text;
 200       } else {
 201         error(sprintf("Submode '%s' set unknown mode in text: %s\nLanguage %s Mode %s\n", a[1], text, language, mode));
 202         text = substr(text, 1 + length(part) + length(a[1]));
 203       }
 204     }
 205 else {
 206       context[cindex, "values", ++context[cindex, "values"]] = item text;
 207       text = "";
 208       item = "";
 209     }
 210   }
 211
 212   context["item"] = item;
 213
 214   if (length(item)) context[cindex, "values", ++context[cindex, "values"]] = item;
 215   return text;
 216 }
 217 function transform_escape(s, r, text,
 218     # optional
 219     max,
 220         # local vars
 221         c)
 222 {
 223   for(c=1; c <= max && (c in s); c++) {
 224     gsub(s[c], r[c], text);
 225   }
 226   return text;
 227 }
 228 function mode_escaper(context, s, r, src,
 229   c, cp, cpl)
 230 {
 231         for(c = context[""]; c >= 0; c--) {
 232                 if ( (context[c, "language"], context[c, "mode"]) in escapes) {
 233                         cpl = escapes[context[c, "language"], context[c, "mode"]];
 234                         for (cp = 1; cp <= cpl; cp ++) {
 235                                 ++src;
 236                                 s[src] = escapes[context[c, "language"], context[c, "mode"], c, "s"];
 237                                 r[src] = escapes[context[c, "language"], context[c, "mode"], c, "r"];
 238                         }
 239                 }
 240         }
 241         return src;
 242 }
 243 function parse_chunk_args(language, text, values, mode,
 244   # local vars
 245   c, context, rest)
 246 {
 247   split("", context);
 248   new_mode_tracker(context, language, mode);
 249   rest = mode_tracker(context, text, values);
 250   # extract values
 251   for(c=1; c <= context[0, "values"]; c++) {
 252     values[c] = context[0, "values", c];
 253   }
 254   return rest;
 255 }
 256 function new_chunk(chunk_name, params,
 257   # local vars
 258   p, append )
 259 {
 260   # HACK WHILE WE CHANGE TO ( ) for PARAM CHUNKS
 261   gsub("\\(\\)$", "", chunk_name);
 262   if (! (chunk_name in chunk_names)) {
 263     if (debug) print "New chunk " chunk_name;
 264     chunk_names[chunk_name];
 265     for (p in params) {
 266       chunks[chunk_name, p] = params[p];
 267     }
 268     if ("append" in params) {
 269       append=params["append"];
 270       if (! (append in chunk_names)) {
 271         warning("Chunk " chunk_name " is appended to chunk " append " which is not defined yet");
 272         new_chunk(append);
 273       }
 274       chunk_include(append, chunk_name);
 275       chunk_line(append, ORS);
 276     }
 277   }
 278   active_chunk = chunk_name;
 279   prime_chunk(chunk_name);
 280 }
 281
 282 function prime_chunk(chunk_name)
 283 {
 284   chunks[chunk_name, "part", ++chunks[chunk_name, "part"] ] = \
 285          chunk_name SUBSEP "chunklet" SUBSEP "" ++chunks[chunk_name, "chunklet"];
 286   chunks[chunk_name, "part", chunks[chunk_name, "part"], "FILENAME"] = FILENAME;
 287   chunks[chunk_name, "part", chunks[chunk_name, "part"], "LINENO"] = FNR + 1;
 288 }
 289
 290 function chunk_line(chunk_name, line){
 291   chunks[chunk_name, "chunklet", chunks[chunk_name, "chunklet"],
 292          ++chunks[chunk_name, "chunklet", chunks[chunk_name, "chunklet"], "line"]  ] = line;
 293 }
 294
 295 function chunk_include(chunk_name, chunk_ref, indent, tail)
 296 {
 297   chunks[chunk_name, "part", ++chunks[chunk_name, "part"] ] = chunk_ref;
 298   chunks[chunk_name, "part", chunks[chunk_name, "part"], "type" ] = part_type_chunk;
 299   chunks[chunk_name, "part", chunks[chunk_name, "part"], "indent" ] = indent_string(indent);
 300   chunks[chunk_name, "part", chunks[chunk_name, "part"], "tail" ] = tail;
 301   prime_chunk(chunk_name);
 302 }
 303
 304 function indent_string(indent) {
 305   return sprintf("%" indent "s", "");
 306 }
 307 function output_chunk_names(   c, prefix, suffix)
 308 {
 309   if (notangle_mode) {
 310     prefix="<<";
 311     suffix=">>";
 312   }
 313   for (c in chunk_names) {
 314     print prefix c suffix "\n";
 315   }
 316 }
 317 function output_chunks(  a)
 318 {
 319   for (a in chunk_names) {
 320     output_chunk(chunk_names[a]);
 321   }
 322 }
 323
 324 function output_chunk(chunk) {
 325   newline = 1;
 326   lineno_needed = linenos;
 327
 328   write_chunk(chunk);
 329 }
 330
 331 function write_chunk(chunk_name) {
 332   split("", context);
 333   return write_chunk_r(chunk_name, context);
 334 }
 335 function write_chunk_r(chunk_name, context, indent, tail,
 336   # optional vars
 337   chunk_path, chunk_args,
 338   s, r, src, new_src,
 339   # local vars
 340   chunk_params, part, max_part, part_line, frag, max_frag, text,
 341   chunklet, only_part, call_chunk_args)
 342 {
 343   if (match(chunk_name, "^(.*)\\[([0-9]*)\\]$", chunk_name_parts)) {
 344     chunk_name = chunk_name_parts[1];
 345     only_part = chunk_name_parts[2];
 346   }
 347   split("", context);
 348   new_mode_tracker(context, chunks[chunk_name, "language"], "");
 349   split(chunks[chunk_name, "params"], chunk_params, " *; *");
 350   if (! (chunk_name in chunk_names)) {
 351     error(sprintf(_"The root module <<%s>> was not defined.\nUsed by: %s",\
 352                   chunk_name, chunk_path));
 353   }
 354
 355   max_part = chunks[chunk_name, "part"];
 356   for(part = 1; part <= max_part; part++) {
 357     if (! only_part || part == only_part) {
 358       if (linenos && (chunk_name SUBSEP "part" SUBSEP part SUBSEP "FILENAME" in chunks)) {
 359         a_filename = chunks[chunk_name, "part", part, "FILENAME"];
 360         a_lineno = chunks[chunk_name, "part", part, "LINENO"];
 361         if (a_filename != filename || a_lineno != lineno) {
 362           lineno_needed++;
 363         }
 364       }
 365
 366       chunklet = chunks[chunk_name, "part", part];
 367       if (chunks[chunk_name, "part", part, "type"] == part_type_chunk) {
 368         if (match(chunklet, "^([^\\[\\(]*)\\((.*)\\)$", chunklet_parts)) {
 369           chunklet = chunklet_parts[1];
 370           parse_chunk_args("", chunklet_parts[2], call_chunk_args, "(");
 371           for (c in call_chunk_args) {
 372             call_chunk_args[c] = expand_chunk_args(call_chunk_args[c], chunk_params, chunk_args);
 373           }
 374         } else {
 375           split("", call_chunk_args);
 376         }
 377         # update the transforms arrays
 378         new_src = mode_escaper(context, s, r, src);
 379         write_chunk_r(chunklet, context,
 380                     chunks[chunk_name, "part", part, "indent"] indent,
 381                     chunks[chunk_name, "part", part, "tail"],
 382                     chunk_path "\n         " chunk_name,
 383                     call_chunk_args,
 384                                 s, r, new_src);
 385       } else if (chunklet SUBSEP "line" in chunks) {
 386         max_frag = chunks[chunklet, "line"];
 387         for(frag = 1; frag <= max_frag; frag++) {
 388           if (newline && lineno_needed && ! lineno_suppressed) {
 389             filename = a_filename;
 390             lineno = a_lineno;
 391             print "#line " lineno " \"" filename "\"\n"
 392             lineno_needed = 0;
 393           }
 394
 395           text = chunks[chunklet, frag];
 396
 397           /* check params */
 398           text = expand_chunk_args(text, chunk_params, chunk_args);
 399
 400          if (text == "\n") {
 401             lineno++;
 402             if (part == max_part && frag == max_frag && length(chunk_path)) {
 403               text = "";
 404               break;
 405             } else {
 406               newline = 1;
 407             }
 408           } else if (length(text) || length(tail)) {
 409             if (newline) text = indent text;
 410             newline = 0;
 411           }
 412
 413           text = text tail;
 414           mode_tracker(context, text);
 415           print transform_escape(s, r, text, src);
 416           if (linenos) {
 417             lineno_suppressed = substr(lastline, length(lastline)) == "\\";
 418           }
 419         }
 420       } else {
 421         # empty last chunklet
 422       }
 423     }
 424   }
 425   if (! finalize_mode_tracker(context)) {
 426     error(sprintf(_"Module %s did not close context properly.\nUsed by: %s\n", chunk_name, chunk_path));
 427   }
 428 }
 429 function expand_chunk_args(text, params, args,
 430   p, text_array, next_text, v, t, l)
 431 {
 432   if (split(text, text_array, "\\${")) {
 433     for(p in params) {
 434       v[params[p]]=args[p];
 435     }
 436     text=text_array[1];
 437     for(t=2; t in text_array; t++) {
 438       if (match(text_array[t], "^([a-zA-Z_][a-zA-Z0-9_]*)}", l) &&
 439           l[1] in v)
 440       {
 441         text = text v[l[1]] substr(text_array[t], length(l[1])+2);
 442       } else {
 443         text = text "${" text_array[t];
 444       }
 445     }
 446   }
 447
 448   return text;
 449 }
 450 BEGIN {
 451   part_type_chunk=1;
 452   SUBSEP=",";
 453   modes["", "",  "submodes" ]="\\\\|\"|'|{|\\(|\\[";
 454   modes["", "",  "delimiters"]=" *, *";
 455   modes["", "\\", "terminators"]=".";
 456   modes["", "\"", "submodes" ]="\\\\";
 457   modes["", "\"", "terminators"]="\"";
 458   escapes["", "\"", ++escapes["", "\""], "s"]="\\";
 459   escapes["", "\"",   escapes["", "\""], "r"]="\\\\";
 460   escapes["", "\"", ++escapes["", "\""], "s"]="\"";
 461   escapes["", "\"",   escapes["", "\""], "r"]="\\" "\"";
 462   escapes["", "\"", ++escapes["", "\""], "s"]="\n";
 463   escapes["", "\"",   escapes["", "\""], "r"]="\\n";
 464   modes["", "'", "submodes" ]="\\\\";
 465   modes["", "'", "terminators"]="'";
 466   escapes["", "'", ++escapes["", "'"], "s"]="\\";
 467   escapes["", "'",   escapes["", "'"], "r"]="\\\\";
 468   escapes["", "'", ++escapes["", "'"], "s"]="'";
 469   escapes["", "'",   escapes["", "'"], "r"]="\\" "'";
 470   escapes["", "'", ++escapes["", "'"], "s"]="\n";
 471   escapes["", "'",   escapes["", "'"], "r"]="\\n";
 472   modes["", "{",  "submodes" ]="\\\\|\"|{|\\(|\\[|'|/\\*";
 473   modes["", "{",  "delimiters"]=" *, *";
 474   modes["", "{",  "terminators"]="}";
 475   modes["", "[",  "submodes" ]="\\\\|\"|{|\\(|\\[|'|/\\*";
 476   modes["", "[",  "delimiters"]=" *, *";
 477   modes["", "[",  "terminators"]="\\]";
 478   modes["", "(",  "submodes" ]="\\\\|\"|{|\\(|\\[|'|/\\*";
 479   modes["", "(",  "delimiters"]=" *, *";
 480   modes["", "(",  "terminators"]="\\)";
 481
 482   modes["c", "",  "submodes" ]="\\\\|\"|'|{|\\(|\\[";
 483   modes["c", "",  "delimiters"]=" *, *";
 484   modes["c", "\\", "terminators"]=".";
 485   modes["c", "\"", "submodes" ]="\\\\";
 486   modes["c", "\"", "terminators"]="\"";
 487   escapes["c", "\"", ++escapes["c", "\""], "s"]="\\";
 488   escapes["c", "\"",   escapes["c", "\""], "r"]="\\\\";
 489   escapes["c", "\"", ++escapes["c", "\""], "s"]="\"";
 490   escapes["c", "\"",   escapes["c", "\""], "r"]="\\" "\"";
 491   escapes["c", "\"", ++escapes["c", "\""], "s"]="\n";
 492   escapes["c", "\"",   escapes["c", "\""], "r"]="\\n";
 493   modes["c", "'", "submodes" ]="\\\\";
 494   modes["c", "'", "terminators"]="'";
 495   escapes["c", "'", ++escapes["c", "'"], "s"]="\\";
 496   escapes["c", "'",   escapes["c", "'"], "r"]="\\\\";
 497   escapes["c", "'", ++escapes["c", "'"], "s"]="'";
 498   escapes["c", "'",   escapes["c", "'"], "r"]="\\" "'";
 499   escapes["c", "'", ++escapes["c", "'"], "s"]="\n";
 500   escapes["c", "'",   escapes["c", "'"], "r"]="\\n";
 501   modes["c", "{",  "submodes" ]="\\\\|\"|{|\\(|\\[|'|/\\*";
 502   modes["c", "{",  "delimiters"]=" *, *";
 503   modes["c", "{",  "terminators"]="}";
 504   modes["c", "[",  "submodes" ]="\\\\|\"|{|\\(|\\[|'|/\\*";
 505   modes["c", "[",  "delimiters"]=" *, *";
 506   modes["c", "[",  "terminators"]="\\]";
 507   modes["c", "(",  "submodes" ]="\\\\|\"|{|\\(|\\[|'|/\\*";
 508   modes["c", "(",  "delimiters"]=" *, *";
 509   modes["c", "(",  "terminators"]="\\)";
 510   modes["c", "", "submodes"] = modes["c", "", "submodes"] "|" "/\\*";
 511   modes["c", "/*", "terminators"]="\\*/";
 512   modes["c", "", "submodes"] = modes["c", "", "submodes"] "|" "//";
 513   modes["c", "//", "terminators"]="\n";
 514   escapes["c", "//", ++escapes["c", "//"], "s"]="\n";
 515   escapes["c", "//",   escapes["c", "//"], "r"]="\n//";
 516   modes["c", "", "submodes"] = modes["c", "", "submodes"] "|" "#";
 517   modes["c", "#", "submodes" ]="\\\\";
 518   modes["c", "#", "terminators"]="\n";
 519   escapes["c", "#", ++escapes["c", "#"], "s"]="\n";
 520   escapes["c", "#",   escapes["c", "#"], "r"]="\\\\\n";
 521
 522   modes["awk", "",  "submodes" ]="\\\\|\"|'|{|\\(|\\[";
 523   modes["awk", "",  "delimiters"]=" *, *";
 524   modes["awk", "\\", "terminators"]=".";
 525   modes["awk", "\"", "submodes" ]="\\\\";
 526   modes["awk", "\"", "terminators"]="\"";
 527   escapes["awk", "\"", ++escapes["awk", "\""], "s"]="\\";
 528   escapes["awk", "\"",   escapes["awk", "\""], "r"]="\\\\";
 529   escapes["awk", "\"", ++escapes["awk", "\""], "s"]="\"";
 530   escapes["awk", "\"",   escapes["awk", "\""], "r"]="\\" "\"";
 531   escapes["awk", "\"", ++escapes["awk", "\""], "s"]="\n";
 532   escapes["awk", "\"",   escapes["awk", "\""], "r"]="\\n";
 533   modes["awk", "'", "submodes" ]="\\\\";
 534   modes["awk", "'", "terminators"]="'";
 535   escapes["awk", "'", ++escapes["awk", "'"], "s"]="\\";
 536   escapes["awk", "'",   escapes["awk", "'"], "r"]="\\\\";
 537   escapes["awk", "'", ++escapes["awk", "'"], "s"]="'";
 538   escapes["awk", "'",   escapes["awk", "'"], "r"]="\\" "'";
 539   escapes["awk", "'", ++escapes["awk", "'"], "s"]="\n";
 540   escapes["awk", "'",   escapes["awk", "'"], "r"]="\\n";
 541   modes["awk", "{",  "submodes" ]="\\\\|\"|{|\\(|\\[|'|/\\*";
 542   modes["awk", "{",  "delimiters"]=" *, *";
 543   modes["awk", "{",  "terminators"]="}";
 544   modes["awk", "[",  "submodes" ]="\\\\|\"|{|\\(|\\[|'|/\\*";
 545   modes["awk", "[",  "delimiters"]=" *, *";
 546   modes["awk", "[",  "terminators"]="\\]";
 547   modes["awk", "(",  "submodes" ]="\\\\|\"|{|\\(|\\[|'|/\\*";
 548   modes["awk", "(",  "delimiters"]=" *, *";
 549   modes["awk", "(",  "terminators"]="\\)";
 550   modes["awk", "", "submodes"] = modes["awk", "", "submodes"] "|" "#";
 551   modes["awk", "#", "terminators"]="\n";
 552   escapes["awk", "#", ++escapes["awk", "#"], "s"]="\n";
 553   escapes["awk", "#",   escapes["awk", "#"], "r"]="\n#";
 554   debug=0;
 555   linenos=0;
 556   notangle_mode=0;
 557   root="*";
 558   tabs = "";
 559
 560   Optind = 1    # skip ARGV[0]
 561   while(getopt(ARGC, ARGV, "R:LdT:hr")!=-1) {
 562     if (Optopt == "R") root = Optarg;
 563     else if (Optopt == "r") root="";
 564     else if (Optopt == "L") linenos = 1;
 565     else if (Optopt == "d") debug = 1;
 566     else if (Optopt == "T") tabs = indent_string(Optarg+0);
 567     else if (Optopt == "h") help();
 568     else if (Optopt == "?") help();
 569   }
 570   for (i=1; i<Optind; i++) { ARGV[i]=""; }
 571 }
 572 /^\\Chunk{/ {
 573   if (match($0, "^\\\\Chunk{ *([^ ,}]*),?(.*)}", line)) {
 574     next_chunk_name = line[1];
 575     get_chunk_args(line[2], next_chunk_args);
 576   }
 577   next;
 578 }
 579 /^\\begin{lstlisting}|^\\begin{Chunk}/ {
 580   if (match($0, "}.*[[,] *name= *{? *([^], }]*)", line)) {
 581     new_chunk(line[1]);
 582   } else {
 583     new_chunk(next_chunk_name, next_chunk_args);
 584   }
 585   chunking=1;
 586   next;
 587 }
 588 /^[<]<.*[>]>=/ {
 589   if (match($0, "^[<]<(.*)[>]>= *$", line)) {
 590     chunking=1;
 591     notangle_mode=1;
 592     new_chunk(line[1]);
 593     next;
 594   }
 595 }
 596 /^\\[e]nd{lstlisting}|^\\[e]nd{Chunk}/ {
 597   chunking=0;
 598   active_chunk="";
 599   next;
 600 }
 601 /^@ *$/ {
 602   chunking=0;
 603   active_chunk="";
 604 }
 605 ! chunking { next; }
 606 length(active_chunk) {
 607   if (length(tabs)) {
 608     gsub("\t", tabs);
 609   }
 610   chunk = $0;
 611   indent = 0;
 612   while(match(chunk,
 613               "([=]<\\\\chunkref{([^}>]*)}(\\(.*\\)|)>|<<([a-zA-Z_][-a-zA-Z0-9_]*)>>)",
 614               line)\
 615   ) {
 616     chunklet = substr(chunk, 1, RSTART - 1);
 617     indent += length(chunklet);
 618     chunk_line(active_chunk, chunklet);
 619     chunk = substr(chunk, RSTART + RLENGTH);
 620     if (substr(line[1], 1, 1) == "=") {
 621       # chunk name up to }
 622         # FILTHY HACK
 623    gsub("\\\\#", "#", line[3]);
 624    gsub("\\\\textbackslash{}", "\\", line[3]);
 625       chunk_include(active_chunk, line[2] line[3], indent);
 626     } else if (substr(line[1], 1, 1) == "<") {
 627       chunk_include(active_chunk, line[4], indent);
 628     } else {
 629       error("Unknown chunk fragment: " line[1]);
 630     }
 631   }
 632   chunk_line(active_chunk, chunk);
 633   chunk_line(active_chunk, "\n");
 634 }
 635 END {
 636   if (debug) {
 637     print "------ chunk names "
 638     output_chunk_names();
 639     print "====== chunks"
 640     output_chunks();
 641     print "++++++ debug"
 642     for (a in chunks) {
 643       print a "=" chunks[a];
 644     }
 645   }
 646   ORS="";
 647   if (length(root)) output_chunk(root);
 648   else output_chunk_names();
 649 }
 650 function get_chunk_args(text, values,
 651   # optional parameters
 652   path, # hierarchical precursors
 653   # local vars
 654   a, name)
 655 {
 656   split("", next_chunk_args);
 657   while(length(text)) {
 658     if (match(text, "^ *}(.*)", a)) {
 659       return a[1];
 660     }
 661     if (! match(text, " *([^,=]*[^,= ]) *(([,=]) *(([^,}]*) *,* *(.*))|)$", a)) {
 662       return text;
 663     }
 664     name=a[1];
 665     if (a[3] == "=") {
 666       if (substr(a[4],1,1) == "{") {
 667         text = get_chunk_args(substr(a[4],2), values, path name SUBSEP);
 668       } else {
 669         values[path name]=a[5];
 670         text = a[6];
 671       }
 672     } else {
 673       values[path name]="";
 674       text = a[2];
 675     }
 676   }
 677   return text;
 678 }