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
41 deck_t *deck = new_deck();
42 slide_t *slide = deck->slide;
45 cstring_t *text = cstring_init();
47 while ((c = fgetc(input)) != EOF) {
49 fprintf(stderr, "markdown_load() failed to read input: %s\n", strerror(errno));
56 bits = markdown_analyse(text);
58 // if first line in file is markdown hr
59 if(!line && CHECK_BIT(bits, IS_HR)) {
64 // if text is markdown hr
65 } else if(CHECK_BIT(bits, IS_HR) &&
66 CHECK_BIT(line->bits, IS_EMPTY)) {
74 slide = next_slide(slide);
79 // if slide ! has line
90 line = next_line(line);
102 line->offset = next_nonblank(text, 0);
104 // adjust line length dynamicaly - excluding markup
106 adjust_line_length(line);
109 text = cstring_init();
112 } else if(c == '\t') {
114 // expand tab to spaces
115 for (i = 0; i < EXPAND_TABS; i++) {
116 (text->expand)(text, ' ');
119 } else if(c == '\\') {
122 (text->expand)(text, c);
124 // if !IS_CODE add next char to line
125 // and do not increase line count
126 if(next_nonblank(text, 0) < CODE_INDENT) {
129 (text->expand)(text, c);
133 // if utf-8 char > 1 byte add remaing to line
134 for(i = 0; i < length_utf8(c) - 1; i++) {
136 (text->expand)(text, c);
142 } else if(isprint(c) || isspace((unsigned char) c)) {
145 (text->expand)(text, c);
147 } else if(is_utf8(c)) {
150 (text->expand)(text, c);
152 // if utf-8 char > 1 byte add remaing to line
153 for(i = 0; i < length_utf8(c) - 1; i++) {
155 (text->expand)(text, c);
164 line = deck->slide->line;
165 if(line && line->text->size > 0 && line->text->text[0] == '%') {
167 // assign header to deck
170 // find first non-header line
171 while(line->text->size > 0 && line->text->text[0] == '%') {
177 line->prev->next = NULL;
180 // remove header lines from slide
181 deck->slide->line = line;
185 deck->slide->lines -= hc;
192 if((CHECK_BIT(line->bits, IS_H1) ||
193 CHECK_BIT(line->bits, IS_H2)) &&
194 CHECK_BIT(line->bits, IS_EMPTY) &&
196 !CHECK_BIT(line->prev->bits, IS_EMPTY)) {
197 // combine underlined H1/H2 in single line
199 // remove line from linked list
200 line->prev->next = line->next;
202 line->next->prev = line->prev;
204 // set bits on previous line
205 if(CHECK_BIT(line->bits, IS_H1)) {
206 SET_BIT(line->prev->bits, IS_H1);
208 SET_BIT(line->prev->bits, IS_H2);
214 // maintain loop condition
219 (tmp->text->delete)(tmp->text);
222 } else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_3)) {
224 line_t *list_last_level_3 = line;
227 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3)) {
228 if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3)) {
229 list_last_level_3 = tmp;
234 for(tmp = line; tmp != list_last_level_3; tmp = tmp->next) {
235 SET_BIT(tmp->bits, IS_UNORDERED_LIST_3);
238 } else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_2)) {
240 line_t *list_last_level_2 = line;
243 (CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2) ||
244 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3))) {
245 if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2)) {
246 list_last_level_2 = tmp;
251 for(tmp = line; tmp != list_last_level_2; tmp = tmp->next) {
252 SET_BIT(tmp->bits, IS_UNORDERED_LIST_2);
255 } else if(CHECK_BIT(line->bits, IS_UNORDERED_LIST_1)) {
257 line_t *list_last_level_1 = line;
260 (CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_1) ||
261 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_2) ||
262 CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_3))) {
263 if(CHECK_BIT(tmp->bits, IS_UNORDERED_LIST_1)) {
264 list_last_level_1 = tmp;
269 for(tmp = line; tmp != list_last_level_1; tmp = tmp->next) {
270 SET_BIT(tmp->bits, IS_UNORDERED_LIST_1);
282 int markdown_analyse(cstring_t *text) {
284 static int unordered_list_level = 0;
285 static int unordered_list_level_offset[] = {-1, -1, -1, -1};
287 int i = 0; // increment
288 int bits = 0; // markdown bits
289 int offset = 0; // text offset
290 int eol = 0; // end of line
292 int equals = 0, hashes = 0,
293 stars = 0, minus = 0,
294 spaces = 0, other = 0; // special character counts
296 const int unordered_list_offset = unordered_list_level_offset[unordered_list_level];
298 // return IS_EMPTY on null pointers
299 if(!text || !text->text) {
300 SET_BIT(bits, IS_EMPTY);
304 // count leading spaces
305 offset = next_nonblank(text, 0);
307 // strip trailing spaces
308 for(eol = text->size; eol > offset && isspace((unsigned char) text->text[eol - 1]); eol--);
310 // IS_UNORDERED_LIST_#
311 if(text->size >= offset + 2 &&
312 (text->text[offset] == '*' || text->text[offset] == '-') &&
313 text->text[offset + 1] == ' ') {
315 for(i = offset; i<eol; i++) {
316 if(text->text[i] != '*' &&
317 text->text[i] != '-' &&
318 text->text[i] != ' ') {
319 if(offset > unordered_list_offset + CODE_INDENT) {
320 SET_BIT(bits, IS_CODE);
321 } else if(offset != unordered_list_offset) {
322 for(i = unordered_list_level; i >= 0; i--) {
323 if(unordered_list_level_offset[i] == offset) {
324 unordered_list_level = i;
328 if(i != unordered_list_level) {
329 unordered_list_level = MIN(unordered_list_level + 1, UNORDERED_LIST_MAX_LEVEL);
330 unordered_list_level_offset[unordered_list_level] = offset;
334 if(unordered_list_level == 0) {
335 unordered_list_level = 1;
336 unordered_list_level_offset[1] = offset;
339 switch(unordered_list_level) {
340 case 1: SET_BIT(bits, IS_UNORDERED_LIST_1); break;
341 case 2: SET_BIT(bits, IS_UNORDERED_LIST_2); break;
342 case 3: SET_BIT(bits, IS_UNORDERED_LIST_3); break;
351 if(!CHECK_BIT(bits, IS_UNORDERED_LIST_1) &&
352 !CHECK_BIT(bits, IS_UNORDERED_LIST_2) &&
353 !CHECK_BIT(bits, IS_UNORDERED_LIST_3)) {
355 unordered_list_level = 0;
358 if(offset >= CODE_INDENT) {
359 SET_BIT(bits, IS_CODE);
364 if(text->text[offset] == '>') {
365 SET_BIT(bits, IS_QUOTE);
369 if(text->size >= offset + 3 &&
370 text->text[offset] == '-' &&
371 text->text[offset + 1] == '>' &&
372 text->text[offset + 2] == ' ') {
373 SET_BIT(bits, IS_CENTER);
376 (text->strip)(text, offset, 3);
379 if(text->size >= offset + 3 &&
380 text->text[eol - 1] == '-' &&
381 text->text[eol - 2] == '<' &&
382 text->text[eol - 3] == ' ') {
385 (text->strip)(text, eol - 3, 3);
387 // adjust end of line
388 for(eol = text->size; eol > offset && isspace((unsigned char) text->text[eol - 1]); eol--);
393 for(i = offset; i < eol; i++) {
395 if(text->text[i] == ' ') {
399 switch(text->text[i]) {
400 case '=': equals++; break;
401 case '#': hashes++; break;
402 case '*': stars++; break;
403 case '-': minus++; break;
404 case '\\': other++; i++; break;
405 default: other++; break;
412 hashes + stars + minus + spaces + other == 0) {
413 SET_BIT(bits, IS_H1);
415 if(text->text[offset] == '#' &&
416 text->text[offset+1] == ' ') {
417 SET_BIT(bits, IS_H1);
418 SET_BIT(bits, IS_H1_ATX);
423 equals + hashes + stars + spaces + other == 0) {
424 SET_BIT(bits, IS_H2);
426 if(text->text[offset] == '#' &&
427 text->text[offset+1] == '#' &&
428 text->text[offset+2] == ' ') {
429 SET_BIT(bits, IS_H2);
430 SET_BIT(bits, IS_H2_ATX);
434 if((minus >= 3 && equals + hashes + stars + other == 0) ||
435 (stars >= 3 && equals + hashes + minus + other == 0)) {
437 SET_BIT(bits, IS_HR);
442 SET_BIT(bits, IS_EMPTY);
450 void markdown_debug(deck_t *deck, int debug) {
452 int sc = 0; // slide count
453 int lc = 0; // line count
459 fprintf(stderr, "headers: %i\nslides: %i\n", deck->headers, deck->slides);
461 } else if(debug > 1) {
463 // print header to STDERR
465 header = deck->header;
467 header->length > 0 &&
468 header->text->text[0] == '%') {
470 // skip descriptor word (e.g. %title:)
471 offset = next_blank(header->text, 0) + 1;
473 fprintf(stderr, "header: %s\n", &header->text->text[offset]);
474 header = header->next;
479 slide_t *slide = deck->slide;
482 // print slide/line count to STDERR
487 fprintf(stderr, " slide %i: %i lines\n", sc, slide->lines);
489 } else if(debug > 1) {
491 // also print bits and line length
492 fprintf(stderr, " slide %i:\n", sc);
497 fprintf(stderr, " line %i: bits = %i, length = %i\n", lc, line->bits, line->length);
506 void adjust_line_length(line_t *line) {
508 const static char *special = "\\*_`"; // list of interpreted chars
509 const char *c = &line->text->text[line->offset];
510 cstack_t *stack = cstack_init();
512 // for each char in line
514 // if char is in special char list
515 if(strchr(special, *c)) {
517 // closing special char (or second backslash)
518 if((stack->top)(stack, *c)) {
522 // treat special as regular char
523 } else if((stack->top)(stack, '\\')) {
527 // opening special char
529 (stack->push)(stack, *c);
533 // remove backslash from stack
534 if((stack->top)(stack, '\\'))
540 if(CHECK_BIT(line->bits, IS_H1_ATX))
542 if(CHECK_BIT(line->bits, IS_H2_ATX))
547 (stack->delete)(stack);
550 bool is_utf8(char ch) {
551 return (ch & 0x80) != 0x00;
554 int length_utf8(char ch) {
556 int i = 0; // increment
566 int next_nonblank(cstring_t *text, int i) {
567 while ((i < text->size) && isspace((unsigned char) (text->text)[i]))
573 int prev_blank(cstring_t *text, int i) {
574 while ((i > 0) && !isspace((unsigned char) (text->text)[i]))
580 int next_blank(cstring_t *text, int i) {
581 while ((i < text->size) && !isspace((unsigned char) (text->text)[i]))
587 int next_word(cstring_t *text, int i) {
588 return next_nonblank(text, next_blank(text, i));