2 * Functions necessary to parse a file and transform its content into
3 * a deck of slides containing lines. All based on markdown formating
5 * Copyright (C) 2014 Michael Goehler
7 * This file is part of mdp.
9 * This program is free software: you can redistribute it and/or modify
10 * it under the terms of the GNU General Public License as published by
11 * the Free Software Foundation, either version 3 of the License, or
12 * (at your option) any later version.
14 * This program is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17 * GNU General Public License for more details.
19 * You should have received a copy of the GNU General Public License
20 * along with this program. If not, see <http://www.gnu.org/licenses/>.
32 deck_t *markdown_load(FILE *input) {
35 int i = 0; // increment
36 int hc = 0; // header count
37 int lc = 0; // line count
38 int sc = 1; // slide count
39 int bits = 0; // markdown bits
40 int prev = 0; // markdown bits of previous line
42 deck_t *deck = new_deck();
43 slide_t *slide = deck->slide;
46 cstring_t *text = cstring_init();
48 // initialize bits as empty line
49 SET_BIT(bits, IS_EMPTY);
51 while ((c = fgetc(input)) != EOF) {
53 fprintf(stderr, "markdown_load() failed to read input: %s\n", strerror(errno));
61 bits = markdown_analyse(text, prev);
63 // if first line in file is markdown hr
64 if(!line && CHECK_BIT(bits, IS_HR)) {
69 // if text is markdown hr
70 } else if(CHECK_BIT(bits, IS_HR) &&
71 CHECK_BIT(line->bits, IS_EMPTY)) {
79 slide = next_slide(slide);
84 // if slide ! has line
95 line = next_line(line);
107 line->offset = next_nonblank(text, 0);
109 // adjust line length dynamicaly - excluding markup
111 adjust_line_length(line);
114 text = cstring_init();
117 } else if(c == '\t') {
119 // expand tab to spaces
120 for (i = 0; i < EXPAND_TABS; i++) {
121 (text->expand)(text, ' ');
124 } else if(c == '\\') {
127 (text->expand)(text, c);
129 // if !IS_CODE add next char to line
130 // and do not increase line count
131 if(next_nonblank(text, 0) < CODE_INDENT) {
134 (text->expand)(text, c);
138 // if utf-8 char > 1 byte add remaing to line
139 for(i = 0; i < length_utf8(c) - 1; i++) {
141 (text->expand)(text, c);
147 } else if(isprint(c) || isspace((unsigned char) c)) {
150 (text->expand)(text, c);
152 } else if(is_utf8(c)) {
155 (text->expand)(text, c);
157 // if utf-8 char > 1 byte add remaing to line
158 for(i = 0; i < length_utf8(c) - 1; i++) {
160 (text->expand)(text, c);
169 line = deck->slide->line;
170 if(line && line->text->size > 0 && line->text->text[0] == '%') {
172 // assign header to deck
175 // find first non-header line
176 while(line->text->size > 0 && line->text->text[0] == '%') {
182 line->prev->next = NULL;
185 // remove header lines from slide
186 deck->slide->line = line;
190 deck->slide->lines -= hc;
197 // combine underlined H1/H2 in single line
198 if((CHECK_BIT(line->bits, IS_H1) ||
199 CHECK_BIT(line->bits, IS_H2)) &&
200 CHECK_BIT(line->bits, IS_EMPTY) &&
202 !CHECK_BIT(line->prev->bits, IS_EMPTY)) {
205 // remove line from linked list
206 line->prev->next = line->next;
208 line->next->prev = line->prev;
210 // set bits on previous line
211 if(CHECK_BIT(line->bits, IS_H1)) {
212 SET_BIT(line->prev->bits, IS_H1);
214 SET_BIT(line->prev->bits, IS_H2);
220 // maintain loop condition
225 (tmp->text->delete)(tmp->text);
228 // pass enclosing flag IS_UNORDERED_LIST_3
229 // to nested levels for unordered lists
230 } else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_3)) {
232 line_t *list_last_level_3 = line;
235 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3)) {
236 if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3)) {
237 list_last_level_3 = tmp;
242 for(tmp = line; tmp != list_last_level_3; tmp = tmp->next) {
243 SET_BIT(tmp->bits, IS_UNORDERED_LIST_3);
246 // pass enclosing flag IS_UNORDERED_LIST_2
247 // to nested levels for unordered lists
248 } else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_2)) {
250 line_t *list_last_level_2 = line;
253 (CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2) ||
254 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3))) {
255 if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2)) {
256 list_last_level_2 = tmp;
261 for(tmp = line; tmp != list_last_level_2; tmp = tmp->next) {
262 SET_BIT(tmp->bits, IS_UNORDERED_LIST_2);
265 // pass enclosing flag IS_UNORDERED_LIST_1
266 // to nested levels for unordered lists
267 } else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_1)) {
269 line_t *list_last_level_1 = line;
272 (CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_1) ||
273 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2) ||
274 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3))) {
275 if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_1)) {
276 list_last_level_1 = tmp;
281 for(tmp = line; tmp != list_last_level_1; tmp = tmp->next) {
282 SET_BIT(tmp->bits, IS_UNORDERED_LIST_1);
294 int markdown_analyse(cstring_t *text, int prev) {
296 // static variables can not be redeclaired, but changed outside of a declaration
297 // the program remembers their value on every function calls
298 static int unordered_list_level = 0;
299 static int unordered_list_level_offset[] = {-1, -1, -1, -1};
301 int i = 0; // increment
302 int bits = 0; // markdown bits
303 int offset = 0; // text offset
304 int eol = 0; // end of line
306 int equals = 0, hashes = 0,
307 stars = 0, minus = 0,
308 spaces = 0, other = 0; // special character counts
310 const int unordered_list_offset = unordered_list_level_offset[unordered_list_level];
312 // return IS_EMPTY on null pointers
313 if(!text || !text->text) {
314 SET_BIT(bits, IS_EMPTY);
318 // count leading spaces
319 offset = next_nonblank(text, 0);
321 // strip trailing spaces
322 for(eol = text->size; eol > offset && isspace((unsigned char) text->text[eol - 1]); eol--);
324 // IS_UNORDERED_LIST_#
325 if(text->size >= offset + 2 &&
326 (text->text[offset] == '*' || text->text[offset] == '-') &&
327 text->text[offset + 1] == ' ') {
329 // if different from last lines offset
330 if(offset != unordered_list_offset) {
332 // test if offset matches a lower indent level
333 for(i = unordered_list_level; i >= 0; i--) {
334 if(unordered_list_level_offset[i] == offset) {
335 unordered_list_level = i;
339 // if offset doesn't match any previously stored indent level
340 if(i != unordered_list_level) {
341 unordered_list_level = MIN(unordered_list_level + 1, UNORDERED_LIST_MAX_LEVEL);
342 // memorize the offset as next bigger indent level
343 unordered_list_level_offset[unordered_list_level] = offset;
347 // if no previous indent level matches, this must be the first line of the list
348 if(unordered_list_level == 0) {
349 unordered_list_level = 1;
350 unordered_list_level_offset[1] = offset;
353 switch(unordered_list_level) {
354 case 1: SET_BIT(bits, IS_UNORDERED_LIST_1); break;
355 case 2: SET_BIT(bits, IS_UNORDERED_LIST_2); break;
356 case 3: SET_BIT(bits, IS_UNORDERED_LIST_3); break;
361 if(!CHECK_BIT(bits, IS_UNORDERED_LIST_1) &&
362 !CHECK_BIT(bits, IS_UNORDERED_LIST_2) &&
363 !CHECK_BIT(bits, IS_UNORDERED_LIST_3)) {
365 // continue list if indent level is still the same as in previous line
366 if ((CHECK_BIT(prev, IS_UNORDERED_LIST_1) ||
367 CHECK_BIT(prev, IS_UNORDERED_LIST_2) ||
368 CHECK_BIT(prev, IS_UNORDERED_LIST_3)) &&
369 offset >= unordered_list_offset) {
371 switch(unordered_list_level) {
372 case 1: SET_BIT(bits, IS_UNORDERED_LIST_1); break;
373 case 2: SET_BIT(bits, IS_UNORDERED_LIST_2); break;
374 case 3: SET_BIT(bits, IS_UNORDERED_LIST_3); break;
378 // this line extends the previous list item
379 SET_BIT(bits, IS_UNORDERED_LIST_EXT);
381 // or reset indent level
383 unordered_list_level = 0;
387 if(!CHECK_BIT(bits, IS_UNORDERED_LIST_1) &&
388 !CHECK_BIT(bits, IS_UNORDERED_LIST_2) &&
389 !CHECK_BIT(bits, IS_UNORDERED_LIST_3)) {
392 if(offset >= CODE_INDENT &&
393 (CHECK_BIT(prev, IS_EMPTY) ||
394 CHECK_BIT(prev, IS_CODE))) {
395 SET_BIT(bits, IS_CODE);
400 if(text->text[offset] == '>') {
401 SET_BIT(bits, IS_QUOTE);
405 if(text->size >= offset + 3 &&
406 text->text[offset] == '-' &&
407 text->text[offset + 1] == '>' &&
408 text->text[offset + 2] == ' ') {
409 SET_BIT(bits, IS_CENTER);
412 (text->strip)(text, offset, 3);
415 if(text->size >= offset + 3 &&
416 text->text[eol - 1] == '-' &&
417 text->text[eol - 2] == '<' &&
418 text->text[eol - 3] == ' ') {
421 (text->strip)(text, eol - 3, 3);
423 // adjust end of line
424 for(eol = text->size; eol > offset && isspace((unsigned char) text->text[eol - 1]); eol--);
429 for(i = offset; i < eol; i++) {
431 if(text->text[i] == ' ') {
435 switch(text->text[i]) {
436 case '=': equals++; break;
437 case '#': hashes++; break;
438 case '*': stars++; break;
439 case '-': minus++; break;
440 case '\\': other++; i++; break;
441 default: other++; break;
448 hashes + stars + minus + spaces + other == 0) {
449 SET_BIT(bits, IS_H1);
451 if(text->text[offset] == '#' &&
452 text->text[offset+1] == ' ') {
453 SET_BIT(bits, IS_H1);
454 SET_BIT(bits, IS_H1_ATX);
459 equals + hashes + stars + spaces + other == 0) {
460 SET_BIT(bits, IS_H2);
462 if(text->text[offset] == '#' &&
463 text->text[offset+1] == '#' &&
464 text->text[offset+2] == ' ') {
465 SET_BIT(bits, IS_H2);
466 SET_BIT(bits, IS_H2_ATX);
470 if((minus >= 3 && equals + hashes + stars + other == 0) ||
471 (stars >= 3 && equals + hashes + minus + other == 0)) {
473 SET_BIT(bits, IS_HR);
478 SET_BIT(bits, IS_EMPTY);
486 void markdown_debug(deck_t *deck, int debug) {
488 int sc = 0; // slide count
489 int lc = 0; // line count
495 fprintf(stderr, "headers: %i\nslides: %i\n", deck->headers, deck->slides);
497 } else if(debug > 1) {
499 // print header to STDERR
501 header = deck->header;
503 header->length > 0 &&
504 header->text->text[0] == '%') {
506 // skip descriptor word (e.g. %title:)
507 offset = next_blank(header->text, 0) + 1;
509 fprintf(stderr, "header: %s\n", &header->text->text[offset]);
510 header = header->next;
515 slide_t *slide = deck->slide;
518 // print slide/line count to STDERR
523 fprintf(stderr, " slide %i: %i lines\n", sc, slide->lines);
525 } else if(debug > 1) {
527 // also print bits and line length
528 fprintf(stderr, " slide %i:\n", sc);
533 fprintf(stderr, " line %i: bits = %i, length = %i\n", lc, line->bits, line->length);
542 void adjust_line_length(line_t *line) {
544 const static char *special = "\\*_`"; // list of interpreted chars
545 const char *c = &line->text->text[line->offset];
546 cstack_t *stack = cstack_init();
548 // for each char in line
550 // if char is in special char list
551 if(strchr(special, *c)) {
553 // closing special char (or second backslash)
554 if((stack->top)(stack, *c)) {
558 // treat special as regular char
559 } else if((stack->top)(stack, '\\')) {
563 // opening special char
565 (stack->push)(stack, *c);
569 // remove backslash from stack
570 if((stack->top)(stack, '\\'))
576 if(CHECK_BIT(line->bits, IS_H1_ATX))
578 if(CHECK_BIT(line->bits, IS_H2_ATX))
583 (stack->delete)(stack);
586 bool is_utf8(char ch) {
587 return (ch & 0x80) != 0x00;
590 int length_utf8(char ch) {
592 int i = 0; // increment
602 int next_nonblank(cstring_t *text, int i) {
603 while ((i < text->size) && isspace((unsigned char) (text->text)[i]))
609 int prev_blank(cstring_t *text, int i) {
610 while ((i > 0) && !isspace((unsigned char) (text->text)[i]))
616 int next_blank(cstring_t *text, int i) {
617 while ((i < text->size) && !isspace((unsigned char) (text->text)[i]))
623 int next_word(cstring_t *text, int i) {
624 return next_nonblank(text, next_blank(text, i));