summaryrefslogtreecommitdiff
path: root/zwgc/lexer.c
blob: 16e04e61605215eefd9c76038d019e95b178728f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
/* This file is part of the Project Athena Zephyr Notification System.
 * It is one of the source files comprising zwgc, the Zephyr WindowGram
 * client.
 *
 *      Created by:     Marc Horowitz <marc@athena.mit.edu>
 *
 *      $Id$
 *
 *      Copyright (c) 1989 by the Massachusetts Institute of Technology.
 *      For copying and distribution information, see the file
 *      "mit-copyright.h".
 */

#include <sysdep.h>

#if (!defined(lint) && !defined(SABER))
static const char rcsid_lexer_c[] = "$Id$";
#endif

#include <zephyr/mit-copyright.h>

/****************************************************************************/
/*                                                                          */
/*               The lexer for the zwgc description language:               */
/*                                                                          */
/****************************************************************************/

#include "new_memory.h"
#include "new_string.h"
#include "int_dictionary.h"
#include "lexer.h"
#include "parser.h"
#include "y.tab.h"

/*
 * yylineno - this holds the current line # we are on.  Updated automatically
 *            by input() and unput().
 */

int yylineno;

/*
 * keyword_dict - this dictionary maps keyword names to their token numbers.
 */

static int_dictionary keyword_dict = NULL;

/****************************************************************************/
/*                                                                          */
/*                               I/O functions:                             */
/*                                                                          */
/****************************************************************************/

/*
 * input_file - this holds the FILE pointer to the file currently being lexed.
 */

static FILE *input_file;

/*
 * pushback - if not -1, holds a character that was pushed back by unput but
 *            not yet read by input.
 */

static int pushback = -1;

static char input()
{
    int c;

    if (pushback != -1) {
	c = pushback;
	pushback = -1;
	if (c=='\n')
	  yylineno++;
	return(c);
    }

    c = getc(input_file);
    if (c=='\n')
      yylineno++;
    if (c==EOF)
      c = 0;

    return(c);
}

static void unput(c)
     int c;
{
#ifdef DEBUG
    if (pushback != -1) {
	printf("Attempt to push back 2 characters at one time!\n");
	exit(1);
    }
#endif

    pushback = c;
    if (c == '\n')
      yylineno--;
}

/****************************************************************************/
/*                                                                          */
/*                           Initialization routines:                       */
/*                                                                          */
/****************************************************************************/

struct keyword_info {
    string keyword;
    int keyword_number;
};

/*
 * keywords - This table holds a copy of the mapping from keyword name to
 *            token number and is used to initialize keyword_dict:
 */

static struct keyword_info keywords[] =   {
                   { "and", '&' },
		   { "appendport", APPENDPORT },
		   { "buffer", BUFFER },
		   { "break", BREAK },
		   { "closeinput", CLOSEINPUT },
		   { "closeoutput", CLOSEOUTPUT },
		   { "closeport", CLOSEPORT },
		   { "case", CASE },
		   { "clearbuf", CLEARBUF },
		   { "default", DEFAULT },
		   { "do", DO },
		   { "downcase", DOWNCASE },
		   { "else", ELSE },
		   { "elseif", ELSEIF },
		   { "endcase", ENDCASE },
		   { "endif", ENDIF },
		   { "endwhile", ENDWHILE },
		   { "exec", EXEC },
		   { "execport", EXECPORT },
		   { "exit", EXIT },
		   { "fields", FIELDS },
		   { "get", GET },
		   { "getenv", GETENV },
		   { "if", IF },
		   { "inputport", INPUTPORT },
		   { "lany", LANY },
		   { "lbreak", LBREAK },
		   { "lspan", LSPAN },
		   { "match", MATCH },
		   { "noop", NOOP },
		   { "not", '!' },		
		   { "or", '|' },
		   { "outputport", OUTPUTPORT },
		   { "print", PRINT },
		   { "protect", PROTECT },
		   { "put", PUT },
		   { "rany", RANY },
		   { "rbreak", RBREAK },
		   { "rspan", RSPAN },
		   { "set", SET },
		   { "show", SHOW },
		   { "stylestrip", STYLESTRIP },
		   { "substitute", SUBSTITUTE },
		   { "then", THEN },
		   { "upcase", UPCASE },
		   { "while", WHILE },
		   { "verbatim", VERBATIM },
		   { "zvar", ZVAR } };

/*
 * lex_open - this routine [re]initializes the lexer & prepares it to lex
 *            a file.  Resets current line # to 1.
 */

void lex_open(file)
     FILE *file;
{
    /*
     * Initialize I/O:
     */
    input_file = file;
    yylineno = 1;
    pushback = -1;

    /*
     * Initialize keyword_dict from keywords if needed:
     */
    if (!keyword_dict) {
	int i;

	keyword_dict = int_dictionary_Create(101);

	for (i=0; i<sizeof(keywords)/sizeof(struct keyword_info); i++)
	  int_dictionary_Define(keyword_dict, keywords[i].keyword,
				0)->value = keywords[i].keyword_number;
    }
}

/****************************************************************************/
/*                                                                          */
/*                            lex subroutines:                              */
/*                                                                          */
/****************************************************************************/

/*
 * eat_escape_code - this rountine eats an escape code & returns the character
 *                   it codes for or 0 if it codes for "".
 *                   (an escape code is what follows a '\\' in a quoted
 *                   string)  Current escape codes are:
 *
 *                       "n"          == '\n'
 *                       "t"          == '\t'
 *                       "b"          == '\b'
 *                       "\n"         == "" (i.e., returns 0)
 *                       <EOF>        == ""
 *                       [0-7]{1,3}   == the character represented by the code
 *                                       interpreted as an octal number.
 *                       [^ntb0-7\n]  == the same character.  I.e., "*" == '*'
 */

#define  is_octal_digit(c)           (((c)>='0') && ((c)<='7'))

static char eat_escape_code()
{
    int c, coded_char;

    c = input();

    switch (c) {
      case 0:  /* i.e., EOF */
	unput(c);
	return(c);
      case '\n':
	return(0);
      case 'n':
	return('\n');
      case 't':
	return('\t');
      case 'b':
	return('\b');
      case '0':   case '1':   case '2':   case '3':
      case '4':   case '5':   case '6':   case '7':
	coded_char = c - '0';
	c = input();
	if (!is_octal_digit(c)) {
	    unput(c);
	    return(coded_char);
	}
	coded_char = coded_char*8 + c-'0';
	c = input();
	if (!is_octal_digit(c)) {
	    unput(c);
	    return(coded_char);
	}
	return(coded_char*8 + c-'0');
      default:
	return(c);
    }
}

/*
 * eat_string - this routine eats characters allowing escape codes via '\\'
 *              until a '"' is eaten.  If no '"' is seen before a '\n' or
 *              the <EOF>, a parse_error is set & 0 is returned.  Otherwise,
 *              the string represented by what has been eaten is returned.
 *              I.e., 'hello \n there"' would cause "hello \n there" to be
 *              returned.  (thats not a <cr> in the first case, a <cr> in the
 *              second)  The returned string is on the heap & must be freed
 *              eventually.  This routine should be passed the line # that the
 *              string we are eating started on.
 */

static char *eat_string(starting_line)
     int starting_line;
{
    int c;
    char buffer[500];
    char *ptr = buffer;

    for (;;) {
	/*
	 * Get the next input character, handling EOF:
	 */
	c = input();
	if (!c) {
	    unput(c);
	    report_parse_error("unterminated string found beginning",
			    starting_line);
	    return(0);
	}

	/*
	 * Deal with special characters ('\\', '"', and '\n'):
	 */
	if (c=='\\') {
	    c = eat_escape_code();
	    if (!c)
	      continue;
	} else if (c == '"') {
	    *ptr = 0;
	    return(string_Copy(buffer));
	} else if (c == '\n') {
	    unput(c);        /* fix line # reference to right line # */
	    report_parse_error("carriage return found in string", yylineno);
	    return(0);
	}

	/*
	 * Add the character c to the current string:
	 */
	*ptr = c;
	ptr++;

	/*
	 * If out of buffer space, do a recursive call then
	 * concatanate the result to the string read in so far to get the
	 * entire string and return that:
	 */
	if (ptr>buffer+sizeof(buffer)-20) {
	    string rest_of_string, result;

	    rest_of_string = eat_string(starting_line);
	    if (!rest_of_string)
	      return(0);
	    
	    *ptr = 0;
	    result = string_Concat(buffer, rest_of_string);
	    free(rest_of_string);
	    return(result);
	}
    }
}

/*
 * eat_show_line - internal routine for eat_show:
 *
 *        This routine reads in a physical line of text allowing escape
 *    codes via '\\'.  If the line ends with a newline, the newline is eaten.
 *    If the line ends with a EOF, the EOF is not eaten.  The string
 *    represented by what has been eaten is returned.  The returned string
 *    is on the heap & must be freed eventually.  If test_for_endshow is
 *    true and the line read in starts off with "endshow" exactly
 *    (i.e., no escape codes) followed by any non-identifier-char, then
 *    instead of doing the above, we just eat the "endshow" & return 0.
 */

static char *eat_show_line(test_for_endshow)
     int test_for_endshow;
{
    int c;
    int saw_escape_code = 0;
    int starting_line = yylineno;
    char buffer[200];      /* This must be large enough to hold "endshow" */
    char *ptr = buffer;

    while (yylineno == starting_line) {
	c = input();
	if (!c) {
	    unput(c);
	    *ptr = '\0';
	    return(string_Copy(buffer));
	} else if (c == '\\') {
	    saw_escape_code = 1;
	    c = eat_escape_code();
	    if (!c)
	      continue;
	}

	*ptr = c;
	ptr++;

	if ((ptr==buffer+strlen("endshow")) && test_for_endshow)
	  if (!strncmp(buffer, "endshow", strlen("endshow"))
	      && !saw_escape_code) {
	      c = input();
	      unput(c);
	      if (!is_identifier_char(c))
		return(0);
	  }

	if (ptr>buffer+sizeof(buffer)-2) {
	    string the_line;
	    string rest_of_line = eat_show_line(0);

	    *ptr = '\0';
	    the_line = string_Concat(buffer, rest_of_line);
	    free(rest_of_line);
	    return(the_line);
	}
    }

    *ptr = '\0';
    return(string_Copy(buffer));
}

/*
 * eat_til_endshow - this routine eats characters allowing escape codes via
 *                   '\\' up to a endshow\{nonalpha} found at the
 *                   start of a line not counting leading whitespace.
 *                   If <EOF> is seen before the terminator, a parse_error
 *                   is set & 0 returned.  Otherwise, the string represented
 *                   by what has been eaten (escape codes replaced by what
 *                   they stand for and leading spaces and tabs removed from
 *                   each physical line) is returned.  The returned string
 *                   is on the heap & must be freed eventually.  Note that
 *                   to embed endshow in a message, endsho\w can be used.
 *                   This routine should be passed the line # of the show
 *                   command it is being used to process for use in error
 *                   messages.
 */

static char *eat_til_endshow(start_line_no)
     int start_line_no;
{
    register int c;
    string text_so_far = string_Copy("");
    string next_line;

    for (;;) {
	/*
	 * Skip the spaces & tabs at the start of the current line:
	 */
	while ((c=input()), c==' ' || c=='\t') ;
	unput(c);

	/*
	 * Handle unterminated shows:
	 */
	if (!c) {
	    report_parse_error("unterminated show beginning", start_line_no);
	    free(text_so_far);
	    return(0);
	}

	/*
	 * Read in rest of the line (including the <cr> at end), allowing
	 * for escape codes and checking for "endshow{nonalpha}" at the
	 * start of the line.  (Note: \<newline> is considered the
	 * end of a line here!)
	 */
	next_line = eat_show_line(1);

	if (!next_line)  /* i.e., is this the endshow line? */
	  return(text_so_far);

	text_so_far = string_Concat2(text_so_far, next_line);
	free(next_line);
    }
}

/*
 * handle_show - this routine is called after "show"\{nonalpha} is
 *               found to handle up to the endshow.  The token # is
 *               returned.
 */

static int handle_show()
{
    int c;
    int start_line_no = yylineno;

    /*
     * Eat up ' ' and '\t's after show.  If the next character is a newline,
     * eat it.  This is so we don't get an extra newline when we call
     * eat_til_endshow:
     */
    while (c=input(), c==' ' || c=='\t') ;
    if (c!='\n')
      unput(c);

    if (yylval.text = eat_til_endshow(start_line_no))
      return(SHOW);
    else
      return(ERROR);
}

/****************************************************************************/
/*                                                                          */
/*                         The main lexer itself:                           */
/*                                                                          */
/****************************************************************************/

/*
 * yylex - performs as per. the yacc manual's requirements
 */

int yylex()
{
    register int c, last_char;
    register char *ptr;
    int start_line_no;
    int_dictionary_binding *binding;
    char varname[MAX_IDENTIFIER_LENGTH+1];

    for (;;) {
	switch (c = input()) {

	    /*
	     * Skip whitespace:
	     */
	  case ' ':   case '\t':   case '\n':
	    continue;

	    /*
	     * '#' comments out everything up to the and including
	     * the next <cr>:
	     */
	  case '#':
	    while ( (c=input()) && (c!='\n') ) ;
	    if (!c)
	      unput(c);
	    continue;

	    /*
	     * Handle c-style comments.  Note that "/[^*]" is not the start
	     * of any valid token.
	     */
	  case '/':
	    start_line_no = yylineno;

	    /* verify that next character is a '*': */
	    if ((c=input()) != '*')
	      return(ERROR);

	    /* Scan until "*\/" or <EOF>: */
	    for (last_char=0; ; last_char=c) {
		c = input();
		if (c == '/' && (last_char=='*'))
		  break;
		if (!c) {
		    unput(c);
		    report_parse_error("unterminated c style comment found beginning", start_line_no);
		    return(ERROR);
		}
	    }
	    continue;

	    /*
	     * The following characters lex as themselves:
	     *   '+', '|', '&', '(', ')', '.', ',' and <EOF>:
	     */
	  case   0:   case '+':   case '|':   case '&':   case '(':
	  case ')':   case '.':	  case ',':
	    return(c);

	    /*
	     * Handle "=[^~=]", "=~", and "==":
	     */
	  case '=':
	    switch (c = input()) {
	      case '~':
		return(REGEQ);
	      case '=':
		return(EQ);
	      default:
		unput(c);
		return('=');
	    }

	    /*
	     * Handle "![^~=]", "!~", and "!=":
	     */
	  case '!':
	    switch (c = input()) {
	      case '~':
		return(REGNEQ);
	      case '=':
		return(NEQ);
	      default:
		unput(c);
		return('!');
	    }

	    /*
	     * Handle identifiers and keywords:
	     *
	     * Note that the below set of characters is hard coded from
	     * is_identifier_char from parser.h.
	     */
	  case 'a':   case 'b':   case 'c':   case 'd':   case 'e':
	  case 'f':   case 'g':   case 'h':   case 'i':   case 'j':
	  case 'k':   case 'l':   case 'm':   case 'n':   case 'o':
	  case 'p':   case 'q':   case 'r':   case 's':   case 't':
	  case 'u':   case 'v':   case 'w':   case 'x':   case 'y':
	  case 'z':
	  case 'A':   case 'B':   case 'C':   case 'D':   case 'E':
	  case 'F':   case 'G':   case 'H':   case 'I':   case 'J':
	  case 'K':   case 'L':   case 'M':   case 'N':   case 'O':
	  case 'P':   case 'Q':   case 'R':   case 'S':   case 'T':
	  case 'U':   case 'V':   case 'W':   case 'X':   case 'Y':
	  case 'Z':
	  case '0':   case '1':   case '2':   case '3':   case '4':
	  case '5':   case '6':   case '7':   case '8':   case '9':
	  case '_':
	    /*
	     * Read in the first MAX_IDENTIFIER_LENGTH characters of the
	     * identifier into varname null terminated.  Eat
	     * the rest of the characters of the identifier:
	     */
	    for (ptr = varname;;) {
		if (ptr<varname+MAX_IDENTIFIER_LENGTH)
		  *(ptr++) = c;
		c = input();
		if (!is_identifier_char(c))
		  break;
	    }
	    unput(c);
	    *ptr = '\0';

	    /*
	     * Look up the identifier in the keyword dictionary.
	     * If its a match, return the keyword's #.  In the case
	     * of show, call handle_show to do more processing.
	     * If not a match, treat as a variable name.
	     */
	    binding = int_dictionary_Lookup(keyword_dict, varname);
	    if (!binding) {
		yylval.text = string_Copy(varname);
		return(VARNAME);
	    }
	    if (binding->value == SHOW)
	      return(handle_show());
	    else
	      return(binding->value);

	    /*
	     * Handle "${identifier}".  Note that $ followed by a
	     * non-identifier character is not the start of any valid token.
	     */
	  case '$':
	    c = input();
	    if (!is_identifier_char(c))
	      return(ERROR);
    
	    /*
	     * Read in the first MAX_IDENTIFIER_LENGTH characters of the
	     * identifier into varname null terminated.  Eat
	     * the rest of the characters of the identifier:
	     */
	    for (ptr = varname;;) {
		if (ptr<varname+MAX_IDENTIFIER_LENGTH)
		  *(ptr++) = c;
		c = input();
		if (!is_identifier_char(c))
		  break;
	    }
	    unput(c);
	    *ptr = '\0';

	    yylval.text = string_Copy(varname);
	    return(VARREF);

	    /*
	     * Handle constant strings:
	     */
	  case '"':
	    if (yylval.text = eat_string(yylineno))
	      return(STRING);
	    else
	      return(ERROR);

	    /*
	     * All other characters do not start valid tokens:
	     */
	  default:
	    return(ERROR);
	}
    }
}