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/>.
34 deck_t *markdown_load(FILE *input) {
36 wchar_t c = L'\0'; // char
37 int i = 0; // increment
38 int hc = 0; // header count
39 int lc = 0; // line count
40 int sc = 1; // slide count
41 int bits = 0; // markdown bits
42 int prev = 0; // markdown bits of previous line
44 deck_t *deck = new_deck();
45 slide_t *slide = deck->slide;
48 cstring_t *text = cstring_init();
50 // initialize bits as empty line
51 SET_BIT(bits, IS_EMPTY);
53 while ((c = fgetwc(input)) != WEOF) {
55 fprintf(stderr, "markdown_load() failed to read input: %s\n", strerror(errno));
63 bits = markdown_analyse(text, prev);
65 // if first line in file is markdown hr
66 if(!line && CHECK_BIT(bits, IS_HR)) {
71 } else if(line && CHECK_BIT(bits, IS_STOP)) {
73 // set stop bit on last line
74 SET_BIT(line->bits, IS_STOP);
79 // if text is markdown hr
80 } else if(CHECK_BIT(bits, IS_HR) &&
81 CHECK_BIT(line->bits, IS_EMPTY)) {
89 slide = next_slide(slide);
94 // if slide ! has line
95 if(!slide->line || !line) {
105 line = next_line(line);
117 line->offset = next_nonblank(text, 0);
119 // adjust line length dynamicaly - excluding markup
120 if(line->text->value)
121 adjust_line_length(line);
124 text = cstring_init();
127 } else if(c == L'\t') {
129 // expand tab to spaces
130 for (i = 0; i < EXPAND_TABS; i++) {
131 (text->expand)(text, L' ');
134 } else if(c == L'\\') {
137 (text->expand)(text, c);
139 // if !IS_CODE add next char to line
140 // and do not increase line count
141 if(next_nonblank(text, 0) < CODE_INDENT) {
144 (text->expand)(text, c);
147 } else if(iswprint(c) || iswspace(c)) {
150 (text->expand)(text, c);
153 (text->delete)(text);
159 line = deck->slide->line;
160 if(line && line->text->size > 0 && line->text->value[0] == L'%') {
162 // assign header to deck
165 // find first non-header line
166 while(line && line->text->size > 0 && line->text->value[0] == L'%') {
171 // only split header if any non-header line is found
175 line->prev->next = NULL;
178 // remove header lines from slide
179 deck->slide->line = line;
183 deck->slide->lines -= hc;
186 // remove header from deck
195 // combine underlined H1/H2 in single line
196 if((CHECK_BIT(line->bits, IS_H1) ||
197 CHECK_BIT(line->bits, IS_H2)) &&
198 CHECK_BIT(line->bits, IS_EMPTY) &&
200 !CHECK_BIT(line->prev->bits, IS_EMPTY)) {
203 // remove line from linked list
204 line->prev->next = line->next;
206 line->next->prev = line->prev;
208 // set bits on previous line
209 if(CHECK_BIT(line->bits, IS_H1)) {
210 SET_BIT(line->prev->bits, IS_H1);
212 SET_BIT(line->prev->bits, IS_H2);
218 // maintain loop condition
223 (tmp->text->delete)(tmp->text);
226 // pass enclosing flag IS_UNORDERED_LIST_3
227 // to nested levels for unordered lists
228 } else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_3)) {
230 line_t *list_last_level_3 = line;
233 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3)) {
234 if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3)) {
235 list_last_level_3 = tmp;
240 for(tmp = line; tmp != list_last_level_3; tmp = tmp->next) {
241 SET_BIT(tmp->bits, IS_UNORDERED_LIST_3);
244 // pass enclosing flag IS_UNORDERED_LIST_2
245 // to nested levels for unordered lists
246 } else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_2)) {
248 line_t *list_last_level_2 = line;
251 (CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2) ||
252 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3))) {
253 if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2)) {
254 list_last_level_2 = tmp;
259 for(tmp = line; tmp != list_last_level_2; tmp = tmp->next) {
260 SET_BIT(tmp->bits, IS_UNORDERED_LIST_2);
263 // pass enclosing flag IS_UNORDERED_LIST_1
264 // to nested levels for unordered lists
265 } else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_1)) {
267 line_t *list_last_level_1 = line;
270 (CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_1) ||
271 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2) ||
272 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3))) {
273 if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_1)) {
274 list_last_level_1 = tmp;
279 for(tmp = line; tmp != list_last_level_1; tmp = tmp->next) {
280 SET_BIT(tmp->bits, IS_UNORDERED_LIST_1);
292 int markdown_analyse(cstring_t *text, int prev) {
294 // static variables can not be redeclaired, but changed outside of a declaration
295 // the program remembers their value on every function calls
296 static int unordered_list_level = 0;
297 static int unordered_list_level_offset[] = {-1, -1, -1, -1};
299 int i = 0; // increment
300 int bits = 0; // markdown bits
301 int offset = 0; // text offset
302 int eol = 0; // end of line
304 int equals = 0, hashes = 0,
305 stars = 0, minus = 0,
306 spaces = 0, other = 0; // special character counts
308 const int unordered_list_offset = unordered_list_level_offset[unordered_list_level];
310 // return IS_EMPTY on null pointers
311 if(!text || !text->value) {
312 SET_BIT(bits, IS_EMPTY);
316 // count leading spaces
317 offset = next_nonblank(text, 0);
320 if((offset < CODE_INDENT || !CHECK_BIT(prev, IS_CODE)) &&
321 (!wcsncmp(&text->value[offset], L"<br>", 4) ||
322 !wcsncmp(&text->value[offset], L"<BR>", 4) ||
323 !wcsncmp(&text->value[offset], L"^", 1))) {
324 SET_BIT(bits, IS_STOP);
328 // strip trailing spaces
329 for(eol = text->size; eol > offset && iswspace(text->value[eol - 1]); eol--);
331 // IS_UNORDERED_LIST_#
332 if(text->size >= offset + 2 &&
333 (text->value[offset] == L'*' || text->value[offset] == L'-') &&
334 iswspace(text->value[offset + 1])) {
336 // if different from last lines offset
337 if(offset != unordered_list_offset) {
339 // test if offset matches a lower indent level
340 for(i = unordered_list_level; i >= 0; i--) {
341 if(unordered_list_level_offset[i] == offset) {
342 unordered_list_level = i;
346 // if offset doesn't match any previously stored indent level
347 if(i != unordered_list_level) {
348 unordered_list_level = MIN(unordered_list_level + 1, UNORDERED_LIST_MAX_LEVEL);
349 // memorize the offset as next bigger indent level
350 unordered_list_level_offset[unordered_list_level] = offset;
354 // if no previous indent level matches, this must be the first line of the list
355 if(unordered_list_level == 0) {
356 unordered_list_level = 1;
357 unordered_list_level_offset[1] = offset;
360 switch(unordered_list_level) {
361 case 1: SET_BIT(bits, IS_UNORDERED_LIST_1); break;
362 case 2: SET_BIT(bits, IS_UNORDERED_LIST_2); break;
363 case 3: SET_BIT(bits, IS_UNORDERED_LIST_3); break;
368 if(!CHECK_BIT(bits, IS_UNORDERED_LIST_1) &&
369 !CHECK_BIT(bits, IS_UNORDERED_LIST_2) &&
370 !CHECK_BIT(bits, IS_UNORDERED_LIST_3)) {
372 // continue list if indent level is still the same as in previous line
373 if ((CHECK_BIT(prev, IS_UNORDERED_LIST_1) ||
374 CHECK_BIT(prev, IS_UNORDERED_LIST_2) ||
375 CHECK_BIT(prev, IS_UNORDERED_LIST_3)) &&
376 offset >= unordered_list_offset) {
378 switch(unordered_list_level) {
379 case 1: SET_BIT(bits, IS_UNORDERED_LIST_1); break;
380 case 2: SET_BIT(bits, IS_UNORDERED_LIST_2); break;
381 case 3: SET_BIT(bits, IS_UNORDERED_LIST_3); break;
385 // this line extends the previous list item
386 SET_BIT(bits, IS_UNORDERED_LIST_EXT);
388 // or reset indent level
390 unordered_list_level = 0;
394 if(!CHECK_BIT(bits, IS_UNORDERED_LIST_1) &&
395 !CHECK_BIT(bits, IS_UNORDERED_LIST_2) &&
396 !CHECK_BIT(bits, IS_UNORDERED_LIST_3)) {
399 if(offset >= CODE_INDENT &&
400 (CHECK_BIT(prev, IS_EMPTY) ||
401 CHECK_BIT(prev, IS_CODE) ||
402 CHECK_BIT(prev, IS_STOP))) {
403 SET_BIT(bits, IS_CODE);
408 if(text->value[offset] == L'>') {
409 SET_BIT(bits, IS_QUOTE);
413 if(text->size >= offset + 3 &&
414 text->value[offset] == L'-' &&
415 text->value[offset + 1] == L'>' &&
416 iswspace(text->value[offset + 2])) {
417 SET_BIT(bits, IS_CENTER);
420 (text->strip)(text, offset, 3);
423 if(text->size >= offset + 3 &&
424 text->value[eol - 1] == L'-' &&
425 text->value[eol - 2] == L'<' &&
426 iswspace(text->value[eol - 3])) {
429 (text->strip)(text, eol - 3, 3);
431 // adjust end of line
432 for(eol = text->size; eol > offset && iswspace(text->value[eol - 1]); eol--);
437 for(i = offset; i < eol; i++) {
439 if(iswspace(text->value[i])) {
443 switch(text->value[i]) {
444 case L'=': equals++; break;
445 case L'#': hashes++; break;
446 case L'*': stars++; break;
447 case L'-': minus++; break;
448 case L'\\': other++; i++; break;
449 default: other++; break;
456 hashes + stars + minus + spaces + other == 0) {
457 SET_BIT(bits, IS_H1);
459 if(text->value[offset] == L'#' &&
460 iswspace(text->value[offset+1])) {
461 SET_BIT(bits, IS_H1);
462 SET_BIT(bits, IS_H1_ATX);
467 equals + hashes + stars + spaces + other == 0) {
468 SET_BIT(bits, IS_H2);
470 if(text->value[offset] == L'#' &&
471 text->value[offset+1] == L'#' &&
472 iswspace(text->value[offset+2])) {
473 SET_BIT(bits, IS_H2);
474 SET_BIT(bits, IS_H2_ATX);
478 if((minus >= 3 && equals + hashes + stars + other == 0) ||
479 (stars >= 3 && equals + hashes + minus + other == 0)) {
481 SET_BIT(bits, IS_HR);
486 SET_BIT(bits, IS_EMPTY);
494 void markdown_debug(deck_t *deck, int debug) {
496 int sc = 0; // slide count
497 int lc = 0; // line count
503 fwprintf(stderr, L"headers: %i\nslides: %i\n", deck->headers, deck->slides);
505 } else if(debug > 1) {
507 // print header to STDERR
509 header = deck->header;
511 header->length > 0 &&
512 header->text->value[0] == L'%') {
514 // skip descriptor word (e.g. %title:)
515 offset = next_blank(header->text, 0) + 1;
517 fwprintf(stderr, L"header: %S\n", &header->text->value[offset]);
518 header = header->next;
523 slide_t *slide = deck->slide;
526 // print slide/line count to STDERR
531 fwprintf(stderr, L" slide %i: %i lines\n", sc, slide->lines);
533 } else if(debug > 1) {
535 // also print bits and line length
536 fwprintf(stderr, L" slide %i:\n", sc);
541 fwprintf(stderr, L" line %i: bits = %i, length = %i\n", lc, line->bits, line->length);
550 void adjust_line_length(line_t *line) {
552 const static wchar_t *special = L"\\*_`"; // list of interpreted chars
553 const wchar_t *c = &line->text->value[line->offset];
554 cstack_t *stack = cstack_init();
556 // for each char in line
558 // if char is in special char list
559 if(wcschr(special, *c)) {
561 // closing special char (or second backslash)
562 if((stack->top)(stack, *c)) {
566 // treat special as regular char
567 } else if((stack->top)(stack, L'\\')) {
571 // opening special char
573 (stack->push)(stack, *c);
577 // remove backslash from stack
578 if((stack->top)(stack, L'\\'))
584 if(CHECK_BIT(line->bits, IS_H1_ATX))
586 if(CHECK_BIT(line->bits, IS_H2_ATX))
591 (stack->delete)(stack);
594 int next_nonblank(cstring_t *text, int i) {
595 while ((i < text->size) && iswspace((text->value)[i]))
601 int prev_blank(cstring_t *text, int i) {
602 while ((i > 0) && !iswspace((text->value)[i]))
608 int next_blank(cstring_t *text, int i) {
609 while ((i < text->size) && !iswspace((text->value)[i]))
615 int next_word(cstring_t *text, int i) {
616 return next_nonblank(text, next_blank(text, i));