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
669
670
671
672
673
674
675
|
/*
* Functions necessary to parse a file and transform its content into
* a deck of slides containing lines. All based on markdown formating
* rules.
* Copyright (C) 2015 Michael Goehler
*
* This file is part of mdp.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*
*/
#include <ctype.h>
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <wchar.h>
#include <wctype.h>
#include <string.h>
#include "parser.h"
deck_t *markdown_load(FILE *input) {
wchar_t c = L'\0'; // char
int i = 0; // increment
int hc = 0; // header count
int lc = 0; // line count
int sc = 1; // slide count
int bits = 0; // markdown bits
int prev = 0; // markdown bits of previous line
deck_t *deck = new_deck();
slide_t *slide = deck->slide;
line_t *line = NULL;
line_t *tmp = NULL;
cstring_t *text = cstring_init();
// initialize bits as empty line
SET_BIT(bits, IS_EMPTY);
while ((c = fgetwc(input)) != WEOF) {
if (ferror(input)) {
fprintf(stderr, "markdown_load() failed to read input: %s\n", strerror(errno));
exit(EXIT_FAILURE);
}
if(c == L'\n') {
// markdown analyse
prev = bits;
bits = markdown_analyse(text, prev);
// if first line in file is markdown hr
if(!line && CHECK_BIT(bits, IS_HR)) {
// clear text
(text->reset)(text);
} else if(line && CHECK_BIT(bits, IS_STOP)) {
// set stop bit on last line
SET_BIT(line->bits, IS_STOP);
// clear text
(text->reset)(text);
// if text is markdown hr
} else if(CHECK_BIT(bits, IS_HR) &&
CHECK_BIT(line->bits, IS_EMPTY)) {
slide->lines = lc;
// clear text
(text->reset)(text);
// create next slide
slide = next_slide(slide);
sc++;
} else if(CHECK_BIT(bits, IS_TILDE_CODE) && CHECK_BIT(bits, IS_EMPTY)) {
// remove tilde code markers
(text->reset)(text);
} else {
// if slide ! has line
if(!slide->line || !line) {
// create new line
line = new_line();
slide->line = line;
lc = 1;
} else {
// create next line
line = next_line(line);
lc++;
}
// add text to line
line->text = text;
// add bits to line
line->bits = bits;
// calc offset
line->offset = next_nonblank(text, 0);
// adjust line length dynamicaly - excluding markup
if(line->text->value)
adjust_line_length(line);
// new text
text = cstring_init();
}
} else if(c == L'\t') {
// expand tab to spaces
for (i = 0; i < EXPAND_TABS; i++) {
(text->expand)(text, L' ');
}
} else if(c == L'\\') {
// add char to line
(text->expand)(text, c);
// if !IS_CODE add next char to line
// and do not increase line count
if(next_nonblank(text, 0) < CODE_INDENT) {
c = fgetwc(input);
(text->expand)(text, c);
}
} else if(iswprint(c) || iswspace(c)) {
// add char to line
(text->expand)(text, c);
}
}
(text->delete)(text);
slide->lines = lc;
deck->slides = sc;
// detect header
line = deck->slide->line;
if(line && line->text->size > 0 && line->text->value[0] == L'%') {
// assign header to deck
deck->header = line;
// find first non-header line
while(line && line->text->size > 0 && line->text->value[0] == L'%') {
hc++;
line = line->next;
}
// only split header if any non-header line is found
if(line) {
// split linked list
line->prev->next = NULL;
line->prev = NULL;
// remove header lines from slide
deck->slide->line = line;
// adjust counts
deck->headers += hc;
deck->slide->lines -= hc;
} else {
// remove header from deck
deck->header = NULL;
}
}
slide = deck->slide;
while(slide) {
line = slide->line;
// ignore mdpress format attributes
if(line &&
slide->lines > 1 &&
!CHECK_BIT(line->bits, IS_EMPTY) &&
line->text->value[line->offset] == L'=' &&
line->text->value[line->offset + 1] == L' ') {
// remove line from linked list
slide->line = line->next;
line->next->prev = NULL;
// maintain loop condition
tmp = line;
line = line->next;
// adjust line count
slide->lines -= 1;
// delete line
(tmp->text->delete)(tmp->text);
free(tmp);
}
while(line) {
// combine underlined H1/H2 in single line
if((CHECK_BIT(line->bits, IS_H1) ||
CHECK_BIT(line->bits, IS_H2)) &&
CHECK_BIT(line->bits, IS_EMPTY) &&
line->prev &&
!CHECK_BIT(line->prev->bits, IS_EMPTY)) {
// remove line from linked list
line->prev->next = line->next;
if(line->next)
line->next->prev = line->prev;
// set bits on previous line
if(CHECK_BIT(line->bits, IS_H1)) {
SET_BIT(line->prev->bits, IS_H1);
} else {
SET_BIT(line->prev->bits, IS_H2);
}
// adjust line count
slide->lines -= 1;
// maintain loop condition
tmp = line;
line = line->prev;
// delete line
(tmp->text->delete)(tmp->text);
free(tmp);
// pass enclosing flag IS_UNORDERED_LIST_3
// to nested levels for unordered lists
} else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_3)) {
tmp = line->next;
line_t *list_last_level_3 = line;
while(tmp &&
CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3)) {
if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3)) {
list_last_level_3 = tmp;
}
tmp = tmp->next;
}
for(tmp = line; tmp != list_last_level_3; tmp = tmp->next) {
SET_BIT(tmp->bits, IS_UNORDERED_LIST_3);
}
// pass enclosing flag IS_UNORDERED_LIST_2
// to nested levels for unordered lists
} else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_2)) {
tmp = line->next;
line_t *list_last_level_2 = line;
while(tmp &&
(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2) ||
CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3))) {
if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2)) {
list_last_level_2 = tmp;
}
tmp = tmp->next;
}
for(tmp = line; tmp != list_last_level_2; tmp = tmp->next) {
SET_BIT(tmp->bits, IS_UNORDERED_LIST_2);
}
// pass enclosing flag IS_UNORDERED_LIST_1
// to nested levels for unordered lists
} else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_1)) {
tmp = line->next;
line_t *list_last_level_1 = line;
while(tmp &&
(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_1) ||
CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2) ||
CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3))) {
if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_1)) {
list_last_level_1 = tmp;
}
tmp = tmp->next;
}
for(tmp = line; tmp != list_last_level_1; tmp = tmp->next) {
SET_BIT(tmp->bits, IS_UNORDERED_LIST_1);
}
}
line = line->next;
}
slide = slide->next;
}
return deck;
}
int markdown_analyse(cstring_t *text, int prev) {
// static variables can not be redeclaired, but changed outside of a declaration
// the program remembers their value on every function calls
static int unordered_list_level = 0;
static int unordered_list_level_offset[] = {-1, -1, -1, -1};
static int num_tilde_characters = 0;
int i = 0; // increment
int bits = 0; // markdown bits
int offset = 0; // text offset
int eol = 0; // end of line
int equals = 0, hashes = 0,
stars = 0, minus = 0,
spaces = 0, other = 0; // special character counts
const int unordered_list_offset = unordered_list_level_offset[unordered_list_level];
// return IS_EMPTY on null pointers
if(!text || !text->value) {
SET_BIT(bits, IS_EMPTY);
return bits;
}
// count leading spaces
offset = next_nonblank(text, 0);
// IS_TILDE_CODE
if (wcsncmp(text->value, L"~~~", 3) == 0) {
int tildes_in_line = next_nontilde(text, 0);
if (tildes_in_line >= num_tilde_characters) {
if (num_tilde_characters > 0) {
num_tilde_characters = 0;
} else {
num_tilde_characters = tildes_in_line;
}
SET_BIT(bits, IS_EMPTY);
SET_BIT(bits, IS_TILDE_CODE);
return bits;
}
}
if (num_tilde_characters > 0) {
SET_BIT(bits, IS_CODE);
SET_BIT(bits, IS_TILDE_CODE);
return bits;
}
// IS_STOP
if((offset < CODE_INDENT || !CHECK_BIT(prev, IS_CODE)) &&
(!wcsncmp(&text->value[offset], L"<br>", 4) ||
!wcsncmp(&text->value[offset], L"<BR>", 4) ||
!wcsncmp(&text->value[offset], L"^", 1))) {
SET_BIT(bits, IS_STOP);
return bits;
}
// strip trailing spaces
for(eol = text->size; eol > offset && iswspace(text->value[eol - 1]); eol--);
// IS_UNORDERED_LIST_#
if(text->size >= offset + 2 &&
(text->value[offset] == L'*' || text->value[offset] == L'-') &&
iswspace(text->value[offset + 1])) {
// if different from last lines offset
if(offset != unordered_list_offset) {
// test if offset matches a lower indent level
for(i = unordered_list_level; i >= 0; i--) {
if(unordered_list_level_offset[i] == offset) {
unordered_list_level = i;
break;
}
}
// if offset doesn't match any previously stored indent level
if(i != unordered_list_level) {
unordered_list_level = MIN(unordered_list_level + 1, UNORDERED_LIST_MAX_LEVEL);
// memorize the offset as next bigger indent level
unordered_list_level_offset[unordered_list_level] = offset;
}
}
// if no previous indent level matches, this must be the first line of the list
if(unordered_list_level == 0) {
unordered_list_level = 1;
unordered_list_level_offset[1] = offset;
}
switch(unordered_list_level) {
case 1: SET_BIT(bits, IS_UNORDERED_LIST_1); break;
case 2: SET_BIT(bits, IS_UNORDERED_LIST_2); break;
case 3: SET_BIT(bits, IS_UNORDERED_LIST_3); break;
default: break;
}
}
if(!CHECK_BIT(bits, IS_UNORDERED_LIST_1) &&
!CHECK_BIT(bits, IS_UNORDERED_LIST_2) &&
!CHECK_BIT(bits, IS_UNORDERED_LIST_3)) {
// continue list if indent level is still the same as in previous line
if ((CHECK_BIT(prev, IS_UNORDERED_LIST_1) ||
CHECK_BIT(prev, IS_UNORDERED_LIST_2) ||
CHECK_BIT(prev, IS_UNORDERED_LIST_3)) &&
offset >= unordered_list_offset) {
switch(unordered_list_level) {
case 1: SET_BIT(bits, IS_UNORDERED_LIST_1); break;
case 2: SET_BIT(bits, IS_UNORDERED_LIST_2); break;
case 3: SET_BIT(bits, IS_UNORDERED_LIST_3); break;
default: break;
}
// this line extends the previous list item
SET_BIT(bits, IS_UNORDERED_LIST_EXT);
// or reset indent level
} else {
unordered_list_level = 0;
}
}
if(!CHECK_BIT(bits, IS_UNORDERED_LIST_1) &&
!CHECK_BIT(bits, IS_UNORDERED_LIST_2) &&
!CHECK_BIT(bits, IS_UNORDERED_LIST_3)) {
// IS_CODE
if(offset >= CODE_INDENT &&
(CHECK_BIT(prev, IS_EMPTY) ||
CHECK_BIT(prev, IS_CODE) ||
CHECK_BIT(prev, IS_STOP))) {
SET_BIT(bits, IS_CODE);
} else {
// IS_QUOTE
if(text->value[offset] == L'>') {
SET_BIT(bits, IS_QUOTE);
}
// IS_CENTER
if(text->size >= offset + 3 &&
text->value[offset] == L'-' &&
text->value[offset + 1] == L'>' &&
iswspace(text->value[offset + 2])) {
SET_BIT(bits, IS_CENTER);
// remove start tag
(text->strip)(text, offset, 3);
eol -= 3;
if(text->size >= offset + 3 &&
text->value[eol - 1] == L'-' &&
text->value[eol - 2] == L'<' &&
iswspace(text->value[eol - 3])) {
// remove end tags
(text->strip)(text, eol - 3, 3);
// adjust end of line
for(eol = text->size; eol > offset && iswspace(text->value[eol - 1]); eol--);
}
}
for(i = offset; i < eol; i++) {
if(iswspace(text->value[i])) {
spaces++;
} else {
switch(text->value[i]) {
case L'=': equals++; break;
case L'#': hashes++; break;
case L'*': stars++; break;
case L'-': minus++; break;
case L'\\': other++; i++; break;
default: other++; break;
}
}
}
// IS_H1
if(equals > 0 &&
hashes + stars + minus + spaces + other == 0) {
SET_BIT(bits, IS_H1);
}
if(text->value[offset] == L'#' &&
iswspace(text->value[offset+1])) {
SET_BIT(bits, IS_H1);
SET_BIT(bits, IS_H1_ATX);
}
// IS_H2
if(minus > 0 &&
equals + hashes + stars + spaces + other == 0) {
SET_BIT(bits, IS_H2);
}
if(text->value[offset] == L'#' &&
text->value[offset+1] == L'#' &&
iswspace(text->value[offset+2])) {
SET_BIT(bits, IS_H2);
SET_BIT(bits, IS_H2_ATX);
}
// IS_HR
if((minus >= 3 && equals + hashes + stars + other == 0) ||
(stars >= 3 && equals + hashes + minus + other == 0)) {
SET_BIT(bits, IS_HR);
}
// IS_EMPTY
if(other == 0) {
SET_BIT(bits, IS_EMPTY);
}
}
}
return bits;
}
void markdown_debug(deck_t *deck, int debug) {
int sc = 0; // slide count
int lc = 0; // line count
int offset;
line_t *header;
if(debug == 1) {
fwprintf(stderr, L"headers: %i\nslides: %i\n", deck->headers, deck->slides);
} else if(debug > 1) {
// print header to STDERR
if(deck->header) {
header = deck->header;
while(header &&
header->length > 0 &&
header->text->value[0] == L'%') {
// skip descriptor word (e.g. %title:)
offset = next_blank(header->text, 0) + 1;
fwprintf(stderr, L"header: %S\n", &header->text->value[offset]);
header = header->next;
}
}
}
slide_t *slide = deck->slide;
line_t *line;
// print slide/line count to STDERR
while(slide) {
sc++;
if(debug == 1) {
fwprintf(stderr, L" slide %i: %i lines\n", sc, slide->lines);
} else if(debug > 1) {
// also print bits and line length
fwprintf(stderr, L" slide %i:\n", sc);
line = slide->line;
lc = 0;
while(line) {
lc++;
fwprintf(stderr, L" line %i: bits = %i, length = %i\n", lc, line->bits, line->length);
line = line->next;
}
}
slide = slide->next;
}
}
void adjust_line_length(line_t *line) {
int l = 0;
const static wchar_t *special = L"\\*_`"; // list of interpreted chars
const wchar_t *c = &line->text->value[line->offset];
cstack_t *stack = cstack_init();
// for each char in line
for(; *c; c++) {
// if char is in special char list
if(wcschr(special, *c)) {
// closing special char (or second backslash)
if((stack->top)(stack, *c)) {
if(*c == L'\\') l++;
(stack->pop)(stack);
// treat special as regular char
} else if((stack->top)(stack, L'\\')) {
l++;
(stack->pop)(stack);
// opening special char
} else {
(stack->push)(stack, *c);
}
} else {
// remove backslash from stack
if((stack->top)(stack, L'\\'))
(stack->pop)(stack);
l++;
}
}
if(CHECK_BIT(line->bits, IS_H1_ATX))
l -= 2;
if(CHECK_BIT(line->bits, IS_H2_ATX))
l -= 3;
line->length = l;
(stack->delete)(stack);
}
int next_nonblank(cstring_t *text, int i) {
while ((i < text->size) && iswspace((text->value)[i]))
i++;
return i;
}
int prev_blank(cstring_t *text, int i) {
while ((i > 0) && !iswspace((text->value)[i]))
i--;
return i;
}
int next_blank(cstring_t *text, int i) {
while ((i < text->size) && !iswspace((text->value)[i]))
i++;
return i;
}
int next_word(cstring_t *text, int i) {
return next_nonblank(text, next_blank(text, i));
}
int next_nontilde(cstring_t *text, int i) {
while ((i < text->size) && text->value[i] == L'~')
i++;
return i;
}
|