Implement unordered lists.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
diff --git a/README.md b/README.md
index 01b4f3c..16b98d4 100644
--- a/README.md
+++ b/README.md
@@ -78,7 +78,7 @@ more or less forms our to do list.
- **Blocks and Inlines:**
- [x] 3.1 Precedence
- - [ ] 3.2 Container blocks and leaf blocks
+ - [x] 3.2 Container blocks and leaf blocks
- **Leaf Blocks:**
- [x] 4.1 Thematic breaks
diff --git a/md2html/md2html.c b/md2html/md2html.c
index f4142c7..355a6f0 100644
--- a/md2html/md2html.c
+++ b/md2html/md2html.c
@@ -338,6 +338,8 @@ enter_block_callback(MD_BLOCKTYPE type, void* detail, void* userdata)
switch(type) {
case MD_BLOCK_DOC: /* noop */ break;
case MD_BLOCK_QUOTE: MEMBUF_APPEND_LITERAL(out, "<blockquote>\n"); break;
+ case MD_BLOCK_UL: MEMBUF_APPEND_LITERAL(out, "<ul>\n"); break;
+ case MD_BLOCK_LI: MEMBUF_APPEND_LITERAL(out, "<li>"); break;
case MD_BLOCK_HR: MEMBUF_APPEND_LITERAL(out, "<hr>\n"); break;
case MD_BLOCK_H: MEMBUF_APPEND_LITERAL(out, head[((MD_BLOCK_H_DETAIL*)detail)->level - 1]); break;
case MD_BLOCK_CODE: open_code_block(out, (const MD_BLOCK_CODE_DETAIL*) detail); break;
@@ -363,6 +365,8 @@ leave_block_callback(MD_BLOCKTYPE type, void* detail, void* userdata)
switch(type) {
case MD_BLOCK_DOC: /*noop*/ break;
case MD_BLOCK_QUOTE: MEMBUF_APPEND_LITERAL(out, "</blockquote>\n"); break;
+ case MD_BLOCK_UL: MEMBUF_APPEND_LITERAL(out, "</ul>\n"); break;
+ case MD_BLOCK_LI: MEMBUF_APPEND_LITERAL(out, "</li>\n"); break;
case MD_BLOCK_HR: /*noop*/ break;
case MD_BLOCK_H: MEMBUF_APPEND_LITERAL(out, head[((MD_BLOCK_H_DETAIL*)detail)->level - 1]); break;
case MD_BLOCK_CODE: MEMBUF_APPEND_LITERAL(out, "</code></pre>\n"); break;
diff --git a/md4c/md4c.c b/md4c/md4c.c
index 7505b64..5be5103 100644
--- a/md4c/md4c.c
+++ b/md4c/md4c.c
@@ -74,6 +74,7 @@
typedef struct MD_MARK_tag MD_MARK;
typedef struct MD_BLOCK_tag MD_BLOCK;
+typedef struct MD_CONTAINER_tag MD_CONTAINER;
typedef struct MD_LINK_REF_DEF_tag MD_LINK_REF_DEF;
@@ -138,6 +139,13 @@ struct MD_CTX_tag {
unsigned n_block_bytes;
unsigned alloc_block_bytes;
+ /* For container block analysis. */
+ MD_CONTAINER* containers;
+ unsigned n_containers;
+ unsigned alloc_containers;
+
+ int last_line_is_blank;
+
/* Minimal indentation to call the block "indented code block". */
unsigned code_indent_offset;
@@ -1924,8 +1932,6 @@ struct MD_MARK_tag {
static MD_MARK*
md_push_mark(MD_CTX* ctx)
{
- MD_MARK* mark;
-
if(ctx->n_marks >= ctx->alloc_marks) {
MD_MARK* new_marks;
@@ -1939,9 +1945,7 @@ md_push_mark(MD_CTX* ctx)
ctx->marks = new_marks;
}
- mark = &ctx->marks[ctx->n_marks];
- ctx->n_marks++;
- return mark;
+ return &ctx->marks[ctx->n_marks++];
}
#define PUSH_MARK_() \
@@ -3555,22 +3559,37 @@ abort:
}
-/*******************************
- *** Processing Leaf Block ***
- *******************************/
+/**************************
+ *** Processing Block ***
+ **************************/
+
+#define MD_BLOCK_CONTAINER_OPENER 0x01
+#define MD_BLOCK_CONTAINER_CLOSER 0x02
+#define MD_BLOCK_CONTAINER (MD_BLOCK_CONTAINER_OPENER | MD_BLOCK_CONTAINER_CLOSER)
+#define MD_BLOCK_LOOSE_LIST 0x04
struct MD_BLOCK_tag {
- MD_BLOCKTYPE type : 16;
+ MD_BLOCKTYPE type : 8;
+ unsigned flags : 8;
/* MD_BLOCK_H: Header level (1 - 6)
* MD_BLOCK_CODE: Non-zero if fenced, zero if indented.
* MD_BLOCK_TABLE: Column count (as determined by the table underline)
*/
- unsigned data : 16;
+ unsigned data : 16;
unsigned n_lines;
};
+struct MD_CONTAINER_tag {
+ CHAR ch;
+ int is_loose;
+ unsigned mark_indent;
+ unsigned contents_indent;
+ OFF block_byte_off;
+};
+
+
static int
md_process_normal_block_contents(MD_CTX* ctx, const MD_LINE* lines, int n_lines)
{
@@ -3599,6 +3618,8 @@ md_process_verbatim_block_contents(MD_CTX* ctx, MD_TEXTTYPE text_type, const MD_
const MD_VERBATIMLINE* line = &lines[i];
int indent = line->indent;
+ MD_ASSERT(indent >= 0);
+
/* Output code indentation. */
while(indent > SIZEOF_ARRAY(indent_str)) {
MD_TEXT(text_type, indent_str, SIZEOF_ARRAY(indent_str));
@@ -3673,16 +3694,22 @@ md_setup_fenced_code_detail(MD_CTX* ctx, const MD_BLOCK* block, MD_BLOCK_CODE_DE
}
static int
-md_process_block(MD_CTX* ctx, const MD_BLOCK* block)
+md_process_leaf_block(MD_CTX* ctx, const MD_BLOCK* block)
{
union {
MD_BLOCK_H_DETAIL header;
MD_BLOCK_CODE_DETAIL code;
} det;
int ret = 0;
+ int is_in_tight_list;
memset(&det, 0, sizeof(det));
+ if(ctx->n_containers == 0)
+ is_in_tight_list = FALSE;
+ else
+ is_in_tight_list = !ctx->containers[ctx->n_containers-1].is_loose;
+
switch(block->type) {
case MD_BLOCK_H:
det.header.level = block->data;
@@ -3699,7 +3726,8 @@ md_process_block(MD_CTX* ctx, const MD_BLOCK* block)
break;
}
- MD_ENTER_BLOCK(block->type, (void*) &det);
+ if(!is_in_tight_list || block->type != MD_BLOCK_P)
+ MD_ENTER_BLOCK(block->type, (void*) &det);
/* Process the block contents accordingly to is type. */
switch(block->type) {
@@ -3730,7 +3758,8 @@ md_process_block(MD_CTX* ctx, const MD_BLOCK* block)
if(ret != 0)
goto abort;
- MD_LEAVE_BLOCK(block->type, (void*) &det);
+ if(!is_in_tight_list || block->type != MD_BLOCK_P)
+ MD_LEAVE_BLOCK(block->type, (void*) &det);
abort:
return ret;
@@ -3742,15 +3771,41 @@ md_process_all_blocks(MD_CTX* ctx)
unsigned byte_off = 0;
int ret = 0;
+ /* ctx->containers now is not needed for detection of lists and list items
+ * so we reuse it for tracking what lists are loose or tight. We rely
+ * on the fact the vector is large enough to hold the deepest nesting
+ * level of lists. */
+ ctx->n_containers = 0;
+
while(byte_off < ctx->n_block_bytes) {
MD_BLOCK* block = (MD_BLOCK*)((char*)ctx->block_bytes + byte_off);
- MD_CHECK(md_process_block(ctx, block));
+
+ if(block->flags & MD_BLOCK_CONTAINER) {
+ if(block->flags & MD_BLOCK_CONTAINER_CLOSER) {
+ MD_LEAVE_BLOCK(block->type, NULL);
+
+ if(block->type == MD_BLOCK_UL)
+ ctx->n_containers--;
+ }
+
+ if(block->flags & MD_BLOCK_CONTAINER_OPENER) {
+ MD_ENTER_BLOCK(block->type, NULL);
+
+ if(block->type == MD_BLOCK_UL) {
+ ctx->containers[ctx->n_containers].is_loose = (block->flags & MD_BLOCK_LOOSE_LIST);
+ ctx->n_containers++;
+ }
+ }
+ } else {
+ MD_CHECK(md_process_leaf_block(ctx, block));
+
+ if(block->type == MD_BLOCK_CODE || block->type == MD_BLOCK_HTML)
+ byte_off += block->n_lines * sizeof(MD_VERBATIMLINE);
+ else
+ byte_off += block->n_lines * sizeof(MD_LINE);
+ }
byte_off += sizeof(MD_BLOCK);
- if(block->type == MD_BLOCK_CODE || block->type == MD_BLOCK_HTML)
- byte_off += block->n_lines * sizeof(MD_VERBATIMLINE);
- else
- byte_off += block->n_lines * sizeof(MD_LINE);
}
ctx->n_block_bytes = 0;
@@ -3835,6 +3890,7 @@ md_start_new_block(MD_CTX* ctx, const MD_LINE_ANALYSIS* line)
break;
}
+ block->flags = 0;
block->data = line->data;
block->n_lines = 0;
@@ -3912,11 +3968,6 @@ md_end_current_block(MD_CTX* ctx)
/* Mark we are not building any block anymore. */
ctx->current_block = NULL;
- /* Consider flush of all complete blocks */
- // TODO: we cannot do this if we look ahead for link ref. def. or if we
- // are inside a list which can yet turn from tight to loose.
- //MD_CHECK(md_process_all_blocks(ctx));
-
abort:
return ret;
}
@@ -3951,6 +4002,28 @@ md_add_line_into_current_block(MD_CTX* ctx, const MD_LINE_ANALYSIS* analysis)
return 0;
}
+static int
+md_push_container_bytes(MD_CTX* ctx, MD_BLOCKTYPE type, unsigned flags)
+{
+ MD_BLOCK* block;
+ int ret = 0;
+
+ MD_CHECK(md_end_current_block(ctx));
+
+ block = (MD_BLOCK*) md_push_block_bytes(ctx, sizeof(MD_BLOCK));
+ if(block == NULL)
+ return -1;
+
+ block->type = type;
+ block->flags = flags;
+ block->data = 0;
+ block->n_lines = 0;
+
+abort:
+ return ret;
+}
+
+
/***********************
*** Line Analysis ***
@@ -4365,30 +4438,162 @@ md_line_contains_char(MD_CTX* ctx, OFF beg, CHAR ch, OFF* p_pos)
return FALSE;
}
-/* Analyze type of the line and find some its properties. This serves as a
- * main input for determining type and boundaries of a block. */
-static void
-md_analyze_line(MD_CTX* ctx, OFF beg, OFF* p_end,
- const MD_LINE_ANALYSIS* pivot_line, MD_LINE_ANALYSIS* line)
+
+static int
+md_is_container_compatible(const MD_CONTAINER* pivot, const MD_CONTAINER* container)
+{
+ if(container->ch != pivot->ch)
+ return FALSE;
+ if(container->mark_indent > pivot->contents_indent)
+ return FALSE;
+
+ return TRUE;
+}
+
+static int
+md_push_container(MD_CTX* ctx, const MD_CONTAINER* container)
+{
+ if(ctx->n_containers >= ctx->alloc_containers) {
+ MD_CONTAINER* new_containers;
+
+ ctx->alloc_containers = (ctx->alloc_containers > 0 ? ctx->alloc_containers * 2 : 16);
+ new_containers = realloc(ctx->containers, ctx->alloc_containers * sizeof(MD_CONTAINER));
+ if(new_containers == NULL) {
+ MD_LOG("realloc() failed.");
+ return -1;
+ }
+
+ ctx->containers = new_containers;
+ }
+
+ memcpy(&ctx->containers[ctx->n_containers++], container, sizeof(MD_CONTAINER));
+ return 0;
+}
+
+static int
+md_enter_child_containers(MD_CTX* ctx, int n_children)
+{
+ int i;
+ int ret = 0;
+
+ for(i = ctx->n_containers - n_children; i < ctx->n_containers; i++) {
+ MD_CONTAINER* c = &ctx->containers[i];
+
+ switch(c->ch) {
+ case _T('-'):
+ case _T('+'):
+ case _T('*'):
+ /* Remember offset in ctx->block_bytes so we can revisit the
+ * block if we detect it is a loose list. */
+ c->block_byte_off = ctx->n_block_bytes;
+ MD_CHECK(md_push_container_bytes(ctx, MD_BLOCK_UL, MD_BLOCK_CONTAINER_OPENER));
+ MD_CHECK(md_push_container_bytes(ctx, MD_BLOCK_LI, MD_BLOCK_CONTAINER_OPENER));
+ break;
+
+ default:
+ MD_UNREACHABLE();
+ break;
+ }
+ }
+
+abort:
+ return ret;
+}
+
+static int
+md_leave_child_containers(MD_CTX* ctx, int n_keep)
+{
+ int ret = 0;
+
+ while(ctx->n_containers > n_keep) {
+ switch(ctx->containers[ctx->n_containers-1].ch) {
+ case _T('-'):
+ case _T('+'):
+ case _T('*'):
+ MD_CHECK(md_push_container_bytes(ctx, MD_BLOCK_LI, MD_BLOCK_CONTAINER_CLOSER));
+ MD_CHECK(md_push_container_bytes(ctx, MD_BLOCK_UL, MD_BLOCK_CONTAINER_CLOSER));
+ break;
+
+ default:
+ MD_UNREACHABLE();
+ break;
+ }
+
+ ctx->n_containers--;
+ }
+
+abort:
+ return ret;
+}
+
+static int
+md_is_container_mark(MD_CTX* ctx, unsigned indent, OFF beg, OFF* p_end, MD_CONTAINER* p_container)
{
OFF off = beg;
- line->type = MD_LINE_BLANK;
- line->indent = 0;
+ if(off+1 < ctx->size && ISANYOF(off, _T("-+*")) && CH(off+1) == _T(' ')) {
+ p_container->ch = CH(off);
+ p_container->is_loose = FALSE;
+ p_container->mark_indent = indent;
+ p_container->contents_indent = indent + 2;
+ *p_end = off+2;
+ return TRUE;
+ }
+
+ return FALSE;
+}
+
+static unsigned
+md_line_indentation(MD_CTX* ctx, OFF beg, OFF* p_end)
+{
+ OFF off = beg;
+ unsigned indent = 0;
- /* Eat indentation. */
while(off < ctx->size && ISBLANK(off)) {
if(CH(off) == _T('\t'))
- line->indent = (line->indent + 4) & ~3;
+ indent = (indent + 4) & ~3;
else
- line->indent++;
+ indent++;
off++;
}
+ *p_end = off;
+ return indent;
+}
+
+static const MD_LINE_ANALYSIS md_dummy_blank_line = { MD_LINE_BLANK, 0 };
+
+/* Analyze type of the line and find some its properties. This serves as a
+ * main input for determining type and boundaries of a block. */
+static int
+md_analyze_line(MD_CTX* ctx, OFF beg, OFF* p_end,
+ const MD_LINE_ANALYSIS* pivot_line, MD_LINE_ANALYSIS* line)
+{
+ int n_parents = 0;
+ int n_brothers = 0;
+ int n_children = 0;
+ MD_CONTAINER container;
+ int prev_line_is_blank = ctx->last_line_is_blank;
+ OFF off = beg;
+ int ret = 0;
+
+ line->indent = md_line_indentation(ctx, off, &off);
line->beg = off;
+ /* Given the indentation, determine how many of the current containers
+ * are our parents. */
+ while(n_parents < ctx->n_containers &&
+ line->indent >= ctx->containers[n_parents].contents_indent)
+ {
+ line->indent -= ctx->containers[n_parents].contents_indent;
+ n_parents++;
+ }
+
+redo:
/* Check whether we are fenced code continuation. */
if(pivot_line->type == MD_LINE_FENCEDCODE) {
+ line->beg = off;
+
/* We are another MD_LINE_FENCEDCODE unless we are closing fence
* which we transform into MD_LINE_BLANK. */
if(line->indent < ctx->code_indent_offset) {
@@ -4399,24 +4604,15 @@ md_analyze_line(MD_CTX* ctx, OFF beg, OFF* p_end,
}
/* Change indentation accordingly to the initial code fence. */
- if(line->indent > pivot_line->indent)
- line->indent -= pivot_line->indent;
- else
- line->indent = 0;
-
- line->type = MD_LINE_FENCEDCODE;
- goto done;
- }
+ if(n_parents == ctx->n_containers) {
+ if(line->indent > pivot_line->indent)
+ line->indent -= pivot_line->indent;
+ else
+ line->indent = 0;
- /* Check whether we are indented code line.
- * Note indented code block cannot interrupt paragraph. */
- if((pivot_line->type == MD_LINE_BLANK || pivot_line->type == MD_LINE_INDENTEDCODE)
- && line->indent >= ctx->code_indent_offset)
- {
- line->type = MD_LINE_INDENTEDCODE;
- line->indent -= ctx->code_indent_offset;
- line->data = 0;
- goto done;
+ line->type = MD_LINE_FENCEDCODE;
+ goto done;
+ }
}
/* Check whether we are HTML block continuation. */
@@ -4442,36 +4638,38 @@ md_analyze_line(MD_CTX* ctx, OFF beg, OFF* p_end,
goto done;
}
- /* Check whether we are table continuation. */
- if(pivot_line->type == MD_LINE_TABLE) {
- if(md_line_contains_char(ctx, off, _T('|'), &off)) {
- line->type = MD_LINE_TABLE;
- goto done;
- }
- }
-
- /* Check whether we are blank line.
- * Note blank lines after indented code are treated as part of that block.
- * If they are at the end of the block, it is discarded by caller.
- */
+ /* Check for blank line. */
if(off >= ctx->size || ISNEWLINE(off)) {
- line->indent = 0;
- if(pivot_line->type == MD_LINE_INDENTEDCODE)
+ /* Blank line does not need any real indentation to be nested inside
+ * a list. */
+ n_parents = ctx->n_containers;
+
+ if(pivot_line->type == MD_LINE_INDENTEDCODE) {
line->type = MD_LINE_INDENTEDCODE;
- else
+ if(line->indent > ctx->code_indent_offset)
+ line->indent -= ctx->code_indent_offset;
+ else
+ line->indent = 0;
+ ctx->last_line_is_blank = FALSE;
+ } else {
line->type = MD_LINE_BLANK;
+ ctx->last_line_is_blank = TRUE;
+ }
goto done;
+ } else {
+ ctx->last_line_is_blank = FALSE;
}
- /* Check whether we are ATX header. */
- if(line->indent < ctx->code_indent_offset && CH(off) == _T('#')) {
- unsigned level;
-
- if(md_is_atxheader_line(ctx, off, &line->beg, &off, &level)) {
- line->type = MD_LINE_ATXHEADER;
- line->data = level;
- goto done;
- }
+ /* Check for indented code.
+ * Note indented code block cannot interrupt paragraph. */
+ if(line->indent >= ctx->code_indent_offset &&
+ (pivot_line->type == MD_LINE_BLANK || pivot_line->type == MD_LINE_INDENTEDCODE))
+ {
+ line->type = MD_LINE_INDENTEDCODE;
+ MD_ASSERT(line->indent >= ctx->code_indent_offset);
+ line->indent -= ctx->code_indent_offset;
+ line->data = 0;
+ goto done;
}
/* Check whether we are Setext underline. */
@@ -4487,9 +4685,7 @@ md_analyze_line(MD_CTX* ctx, OFF beg, OFF* p_end,
}
}
- /* Check whether we are thematic break line.
- * (We check the indentation to fix http://spec.commonmark.org/0.26/#example-19)
- * (Keep this after check for Setext underline as that one has higher priority). */
+ /* Check for thematic break line. */
if(line->indent < ctx->code_indent_offset && ISANYOF(off, _T("-_*"))) {
if(md_is_hr_line(ctx, off, &off)) {
line->type = MD_LINE_HR;
@@ -4497,6 +4693,47 @@ md_analyze_line(MD_CTX* ctx, OFF beg, OFF* p_end,
}
}
+ /* Check whether we are table continuation. */
+ if(pivot_line->type == MD_LINE_TABLE) {
+ if(md_line_contains_char(ctx, off, _T('|'), &off)) {
+ line->type = MD_LINE_TABLE;
+ goto done;
+ }
+ }
+
+ /* Check for start of a new container block. */
+ if(md_is_container_mark(ctx, line->indent, off, &off, &container)) {
+ line->beg = off;
+ line->indent = md_line_indentation(ctx, off, &off);
+
+ if(n_brothers + n_children == 0) {
+ pivot_line = &md_dummy_blank_line;
+
+ if(n_parents < ctx->n_containers && md_is_container_compatible(&ctx->containers[n_parents], &container)) {
+ n_brothers++;
+ goto redo;
+ }
+ }
+
+ if(n_children == 0)
+ MD_CHECK(md_leave_child_containers(ctx, n_parents + n_brothers));
+
+ n_children++;
+ MD_CHECK(md_push_container(ctx, &container));
+ goto redo;
+ }
+
+ /* Check for ATX header. */
+ if(line->indent < ctx->code_indent_offset && CH(off) == _T('#')) {
+ unsigned level;
+
+ if(md_is_atxheader_line(ctx, off, &line->beg, &off, &level)) {
+ line->type = MD_LINE_ATXHEADER;
+ line->data = level;
+ goto done;
+ }
+ }
+
/* Check whether we are starting code fence. */
if(CH(off) == _T('`') || CH(off) == _T('~')) {
if(md_is_opening_code_fence(ctx, off, &off)) {
@@ -4506,9 +4743,8 @@ md_analyze_line(MD_CTX* ctx, OFF beg, OFF* p_end,
}
}
- /* Check whether we are start of raw HTML block. */
- if(CH(off) == _T('<') && !(ctx->r.flags & MD_FLAG_NOHTMLBLOCKS)
- && line->indent < ctx->code_indent_offset)
+ /* Check for start of raw HTML block. */
+ if(CH(off) == _T('<') && !(ctx->r.flags & MD_FLAG_NOHTMLBLOCKS))
{
ctx->html_block_type = md_is_html_block_start_condition(ctx, off);
@@ -4528,7 +4764,7 @@ md_analyze_line(MD_CTX* ctx, OFF beg, OFF* p_end,
}
}
- /* Check whether we are table underline. */
+ /* Check for table underline. */
if((ctx->r.flags & MD_FLAG_TABLES) && pivot_line->type == MD_LINE_TEXT &&
(CH(off) == _T('|') || CH(off) == _T('-') || CH(off) == _T(':')))
{
@@ -4546,6 +4782,10 @@ md_analyze_line(MD_CTX* ctx, OFF beg, OFF* p_end,
/* By default, we are normal text line. */
line->type = MD_LINE_TEXT;
+ if(pivot_line->type == MD_LINE_TEXT && n_brothers + n_children == 0) {
+ /* Lazy continuation. */
+ n_parents = ctx->n_containers;
+ }
done:
/* Eat rest of the line contents */
@@ -4555,7 +4795,7 @@ done:
/* Set end of the line. */
line->end = off;
- /* But for ATX header, we should not include the optional tailing mark. */
+ /* But for ATX header, we should exclude the optional trailing mark. */
if(line->type == MD_LINE_ATXHEADER) {
OFF tmp = line->end;
while(tmp > line->beg && CH(tmp-1) == _T(' '))
@@ -4566,7 +4806,7 @@ done:
line->end = tmp;
}
- /* Trim tailing spaces. */
+ /* Trim trailing spaces. */
if(line->type != MD_LINE_INDENTEDCODE && line->type != MD_LINE_FENCEDCODE) {
while(line->end > line->beg && CH(line->end-1) == _T(' '))
line->end--;
@@ -4579,9 +4819,31 @@ done:
off++;
*p_end = off;
-}
-static const MD_LINE_ANALYSIS md_dummy_blank_line = { MD_LINE_BLANK, 0 };
+ /* If we belong to a list after seeing a blank line, the list is loose. */
+ if(prev_line_is_blank && line->type != MD_LINE_BLANK && n_parents + n_brothers > 0) {
+ MD_BLOCK* block = (MD_BLOCK*) (((char*)ctx->block_bytes) +
+ ctx->containers[n_parents + n_brothers - 1].block_byte_off);
+ block->flags |= MD_BLOCK_LOOSE_LIST;
+ }
+
+ /* Leave any containers we are not part of anymore. */
+ if(n_children == 0 && n_parents + n_brothers < ctx->n_containers)
+ MD_CHECK(md_leave_child_containers(ctx, n_parents + n_brothers));
+
+ /* Enter any container we found a mark for. */
+ if(n_brothers > 0) {
+ MD_ASSERT(n_brothers == 1);
+ MD_CHECK(md_push_container_bytes(ctx, MD_BLOCK_LI,
+ MD_BLOCK_CONTAINER_CLOSER | MD_BLOCK_CONTAINER_OPENER));
+ }
+
+ if(n_children > 0)
+ MD_CHECK(md_enter_child_containers(ctx, n_children));
+
+abort:
+ return ret;
+}
static int
md_process_line(MD_CTX* ctx, const MD_LINE_ANALYSIS** p_pivot_line, const MD_LINE_ANALYSIS* line)
@@ -4664,12 +4926,13 @@ md_process_doc(MD_CTX *ctx)
if(line == pivot_line)
line = (line == &line_buf[0] ? &line_buf[1] : &line_buf[0]);
- md_analyze_line(ctx, off, &off, pivot_line, line);
+ MD_CHECK(md_analyze_line(ctx, off, &off, pivot_line, line));
MD_CHECK(md_process_line(ctx, &pivot_line, line));
}
/* Process all blocks. */
md_end_current_block(ctx);
+ MD_CHECK(md_leave_child_containers(ctx, 0));
MD_CHECK(md_process_all_blocks(ctx));
MD_LEAVE_BLOCK(MD_BLOCK_DOC, NULL);
@@ -4684,6 +4947,10 @@ abort:
(unsigned)(ctx->alloc_block_bytes));
MD_LOG(buffer);
+ sprintf(buffer, "Alloced %u bytes for containers buffer.",
+ (unsigned)(ctx->alloc_containers * sizeof(MD_CONTAINER)));
+ MD_LOG(buffer);
+
sprintf(buffer, "Alloced %u bytes for marks buffer.",
(unsigned)(ctx->alloc_marks * sizeof(MD_MARK)));
MD_LOG(buffer);
@@ -4723,9 +4990,10 @@ md_parse(const MD_CHAR* text, MD_SIZE size, const MD_RENDERER* renderer, void* u
/* Clean-up. */
md_free_link_ref_defs(&ctx);
- free(ctx.block_bytes);
- free(ctx.marks);
free(ctx.buffer);
+ free(ctx.marks);
+ free(ctx.block_bytes);
+ free(ctx.containers);
return ret;
}
diff --git a/md4c/md4c.h b/md4c/md4c.h
index 4086935..eeba0bc 100644
--- a/md4c/md4c.h
+++ b/md4c/md4c.h
@@ -62,6 +62,12 @@ enum MD_BLOCKTYPE_tag {
/* <blockquote>...</blockquote> */
MD_BLOCK_QUOTE,
+ /* <ul>...</ul> */
+ MD_BLOCK_UL,
+
+ /* <li>...</li> */
+ MD_BLOCK_LI,
+
/* <hr> */
MD_BLOCK_HR,