1cmark(3) Library Functions Manual cmark(3)
2
6 cmark - CommonMark parsing, manipulating, and rendering
7
10 Simple Interface
11 char * cmark_markdown_to_html(const char *text, size_t len, int
12 options)
13 Convert text (assumed to be a UTF-8 encoded string with length len)
16 from CommonMark Markdown to HTML, returning a null-terminated,
17 UTF-8-encoded string. It is the caller's responsibility to free the
18 returned buffer.
19 Node Structure
22 typedef enum {
23 /* Error status */
24 CMARK_NODE_NONE,
25 /* Block */
27 CMARK_NODE_DOCUMENT,
28 CMARK_NODE_BLOCK_QUOTE,
29 CMARK_NODE_LIST,
30 CMARK_NODE_ITEM,
31 CMARK_NODE_CODE_BLOCK,
32 CMARK_NODE_HTML_BLOCK,
33 CMARK_NODE_CUSTOM_BLOCK,
34 CMARK_NODE_PARAGRAPH,
35 CMARK_NODE_HEADING,
36 CMARK_NODE_THEMATIC_BREAK,
37 CMARK_NODE_FIRST_BLOCK = CMARK_NODE_DOCUMENT,
39 CMARK_NODE_LAST_BLOCK = CMARK_NODE_THEMATIC_BREAK,
40 /* Inline */
42 CMARK_NODE_TEXT,
43 CMARK_NODE_SOFTBREAK,
44 CMARK_NODE_LINEBREAK,
45 CMARK_NODE_CODE,
46 CMARK_NODE_HTML_INLINE,
47 CMARK_NODE_CUSTOM_INLINE,
48 CMARK_NODE_EMPH,
49 CMARK_NODE_STRONG,
50 CMARK_NODE_LINK,
51 CMARK_NODE_IMAGE,
52 CMARK_NODE_FIRST_INLINE = CMARK_NODE_TEXT,
54 CMARK_NODE_LAST_INLINE = CMARK_NODE_IMAGE,
55 } cmark_node_type;
56 typedef enum {
61 CMARK_NO_LIST,
62 CMARK_BULLET_LIST,
63 CMARK_ORDERED_LIST
64 } cmark_list_type;
65 typedef enum {
70 CMARK_NO_DELIM,
71 CMARK_PERIOD_DELIM,
72 CMARK_PAREN_DELIM
73 } cmark_delim_type;
74 Custom memory allocator support
79 typedef struct cmark_mem {
80 void *(*calloc)(size_t, size_t);
81 void *(*realloc)(void *, size_t);
82 void (*free)(void *);
83 } cmark_mem;
84 Defines the memory allocation functions to be used by CMark when pars‐
87 ing and allocating a document tree
88 Creating and Destroying Nodes
91 cmark_node * cmark_node_new(cmark_node_type type)
92 Creates a new node of type type. Note that the node may have other
95 required properties, which it is the caller's responsibility to assign.
96 cmark_node * cmark_node_new_with_mem(cmark_node_type type, cmark_mem
99 *mem)
100 Same as cmark_node_new, but explicitly listing the memory allocator
103 used to allocate the node. Note: be sure to use the same allocator for
104 every node in a tree, or bad things can happen.
105 void cmark_node_free(cmark_node *node)
108 Frees the memory allocated for a node and any children.
111 Tree Traversal
114 cmark_node * cmark_node_next(cmark_node *node)
115 Returns the next node in the sequence after node, or NULL if there is
118 none.
119 cmark_node * cmark_node_previous(cmark_node *node)
122 Returns the previous node in the sequence after node, or NULL if there
125 is none.
126 cmark_node * cmark_node_parent(cmark_node *node)
129 Returns the parent of node, or NULL if there is none.
132 cmark_node * cmark_node_first_child(cmark_node *node)
135 Returns the first child of node, or NULL if node has no children.
138 cmark_node * cmark_node_last_child(cmark_node *node)
141 Returns the last child of node, or NULL if node has no children.
144 Iterator
147 An iterator will walk through a tree of nodes, starting from a root
148 node, returning one node at a time, together with information about
149 whether the node is being entered or exited. The iterator will first
150 descend to a child node, if there is one. When there is no child, the
151 iterator will go to the next sibling. When there is no next sibling,
152 the iterator will return to the parent (but with a cmark_event_type of
153 CMARK_EVENT_EXIT). The iterator will return CMARK_EVENT_DONE when it
154 reaches the root node again. One natural application is an HTML ren‐
155 derer, where an ENTER event outputs an open tag and an EXIT event out‐
156 puts a close tag. An iterator might also be used to transform an AST in
157 some systematic way, for example, turning all level-3 headings into
158 regular paragraphs.
159 void
161 usage_example(cmark_node *root) {
162 cmark_event_type ev_type;
163 cmark_iter *iter = cmark_iter_new(root);
164 while ((ev_type = cmark_iter_next(iter)) != CMARK_EVENT_DONE) {
166 cmark_node *cur = cmark_iter_get_node(iter);
167 // Do something with `cur` and `ev_type`
168 }
169 cmark_iter_free(iter);
171 }
172 Iterators will never return EXIT events for leaf nodes, which are nodes
174 of type:
175 · CMARK_NODE_HTML_BLOCK
177 · CMARK_NODE_THEMATIC_BREAK
179 · CMARK_NODE_CODE_BLOCK
181 · CMARK_NODE_TEXT
183 · CMARK_NODE_SOFTBREAK
185 · CMARK_NODE_LINEBREAK
187 · CMARK_NODE_CODE
189 · CMARK_NODE_HTML_INLINE
191 Nodes must only be modified after an EXIT event, or an ENTER event for
193 leaf nodes.
194 typedef enum {
197 CMARK_EVENT_NONE,
198 CMARK_EVENT_DONE,
199 CMARK_EVENT_ENTER,
200 CMARK_EVENT_EXIT
201 } cmark_event_type;
202 cmark_iter * cmark_iter_new(cmark_node *root)
207 Creates a new iterator starting at root. The current node and event
210 type are undefined until cmark_iter_next is called for the first time.
211 The memory allocated for the iterator should be released using
212 cmark_iter_free when it is no longer needed.
213 void cmark_iter_free(cmark_iter *iter)
216 Frees the memory allocated for an iterator.
219 cmark_event_type cmark_iter_next(cmark_iter *iter)
222 Advances to the next node and returns the event type
225 (CMARK_EVENT_ENTER, CMARK_EVENT_EXIT or CMARK_EVENT_DONE).
226 cmark_node * cmark_iter_get_node(cmark_iter *iter)
229 Returns the current node.
232 cmark_event_type cmark_iter_get_event_type(cmark_iter *iter)
235 Returns the current event type.
238 cmark_node * cmark_iter_get_root(cmark_iter *iter)
241 Returns the root node.
244 void cmark_iter_reset(cmark_iter *iter, cmark_node *current,
247 cmark_event_type event_type)
248 Resets the iterator so that the current node is current and the event
251 type is event_type. The new current node must be a descendant of the
252 root node or the root node itself.
253 Accessors
256 void * cmark_node_get_user_data(cmark_node *node)
257 Returns the user data of node.
260 int cmark_node_set_user_data(cmark_node *node, void *user_data)
263 Sets arbitrary user data for node. Returns 1 on success, 0 on failure.
266 cmark_node_type cmark_node_get_type(cmark_node *node)
269 Returns the type of node, or CMARK_NODE_NONE on error.
272 const char * cmark_node_get_type_string(cmark_node *node)
275 Like cmark_node_get_type, but returns a string representation of the
278 type, or "<unknown>".
279 const char * cmark_node_get_literal(cmark_node *node)
282 Returns the string contents of node, or an empty string if none is set.
285 Returns NULL if called on a node that does not have string content.
286 int cmark_node_set_literal(cmark_node *node, const char *content)
289 Sets the string contents of node. Returns 1 on success, 0 on failure.
292 int cmark_node_get_heading_level(cmark_node *node)
295 Returns the heading level of node, or 0 if node is not a heading.
298 int cmark_node_set_heading_level(cmark_node *node, int level)
301 Sets the heading level of node, returning 1 on success and 0 on error.
304 cmark_list_type cmark_node_get_list_type(cmark_node *node)
307 Returns the list type of node, or CMARK_NO_LIST if node is not a list.
310 int cmark_node_set_list_type(cmark_node *node, cmark_list_type type)
313 Sets the list type of node, returning 1 on success and 0 on error.
316 cmark_delim_type cmark_node_get_list_delim(cmark_node *node)
319 Returns the list delimiter type of node, or CMARK_NO_DELIM if node is
322 not a list.
323 int cmark_node_set_list_delim(cmark_node *node, cmark_delim_type delim)
326 Sets the list delimiter type of node, returning 1 on success and 0 on
329 error.
330 int cmark_node_get_list_start(cmark_node *node)
333 Returns starting number of node, if it is an ordered list, otherwise 0.
336 int cmark_node_set_list_start(cmark_node *node, int start)
339 Sets starting number of node, if it is an ordered list. Returns 1 on
342 success, 0 on failure.
343 int cmark_node_get_list_tight(cmark_node *node)
346 Returns 1 if node is a tight list, 0 otherwise.
349 int cmark_node_set_list_tight(cmark_node *node, int tight)
352 Sets the "tightness" of a list. Returns 1 on success, 0 on failure.
355 const char * cmark_node_get_fence_info(cmark_node *node)
358 Returns the info string from a fenced code block.
361 int cmark_node_set_fence_info(cmark_node *node, const char *info)
364 Sets the info string in a fenced code block, returning 1 on success and
367 0 on failure.
368 const char * cmark_node_get_url(cmark_node *node)
371 Returns the URL of a link or image node, or an empty string if no URL
374 is set. Returns NULL if called on a node that is not a link or image.
375 int cmark_node_set_url(cmark_node *node, const char *url)
378 Sets the URL of a link or image node. Returns 1 on success, 0 on fail‐
381 ure.
382 const char * cmark_node_get_title(cmark_node *node)
385 Returns the title of a link or image node, or an empty string if no
388 title is set. Returns NULL if called on a node that is not a link or
389 image.
390 int cmark_node_set_title(cmark_node *node, const char *title)
393 Sets the title of a link or image node. Returns 1 on success, 0 on
396 failure.
397 const char * cmark_node_get_on_enter(cmark_node *node)
400 Returns the literal "on enter" text for a custom node, or an empty
403 string if no on_enter is set. Returns NULL if called on a non-custom
404 node.
405 int cmark_node_set_on_enter(cmark_node *node, const char *on_enter)
408 Sets the literal text to render "on enter" for a custom node. Any
411 children of the node will be rendered after this text. Returns 1 on
412 success 0 on failure.
413 const char * cmark_node_get_on_exit(cmark_node *node)
416 Returns the literal "on exit" text for a custom node, or an empty
419 string if no on_exit is set. Returns NULL if called on a non-custom
420 node.
421 int cmark_node_set_on_exit(cmark_node *node, const char *on_exit)
424 Sets the literal text to render "on exit" for a custom node. Any chil‐
427 dren of the node will be rendered before this text. Returns 1 on suc‐
428 cess 0 on failure.
429 int cmark_node_get_start_line(cmark_node *node)
432 Returns the line on which node begins.
435 int cmark_node_get_start_column(cmark_node *node)
438 Returns the column at which node begins.
441 int cmark_node_get_end_line(cmark_node *node)
444 Returns the line on which node ends.
447 int cmark_node_get_end_column(cmark_node *node)
450 Returns the column at which node ends.
453 Tree Manipulation
456 void cmark_node_unlink(cmark_node *node)
457 Unlinks a node, removing it from the tree, but not freeing its memory.
460 (Use cmark_node_free for that.)
461 int cmark_node_insert_before(cmark_node *node, cmark_node *sibling)
464 Inserts sibling before node. Returns 1 on success, 0 on failure.
467 int cmark_node_insert_after(cmark_node *node, cmark_node *sibling)
470 Inserts sibling after node. Returns 1 on success, 0 on failure.
473 int cmark_node_replace(cmark_node *oldnode, cmark_node *newnode)
476 Replaces oldnode with newnode and unlinks oldnode (but does not free
479 its memory). Returns 1 on success, 0 on failure.
480 int cmark_node_prepend_child(cmark_node *node, cmark_node *child)
483 Adds child to the beginning of the children of node. Returns 1 on suc‐
486 cess, 0 on failure.
487 int cmark_node_append_child(cmark_node *node, cmark_node *child)
490 Adds child to the end of the children of node. Returns 1 on success, 0
493 on failure.
494 void cmark_consolidate_text_nodes(cmark_node *root)
497 Consolidates adjacent text nodes.
500 Parsing
503 Simple interface:
504 cmark_node *document = cmark_parse_document("Hello *world*", 13,
506 CMARK_OPT_DEFAULT);
507 Streaming interface:
509 cmark_parser *parser = cmark_parser_new(CMARK_OPT_DEFAULT);
511 FILE *fp = fopen("myfile.md", "rb");
512 while ((bytes = fread(buffer, 1, sizeof(buffer), fp)) > 0) {
513 cmark_parser_feed(parser, buffer, bytes);
514 if (bytes < sizeof(buffer)) {
515 break;
516 }
517 }
518 document = cmark_parser_finish(parser);
519 cmark_parser_free(parser);
520 cmark_parser * cmark_parser_new(int options)
523 Creates a new parser object.
526 cmark_parser * cmark_parser_new_with_mem(int options, cmark_mem *mem)
529 Creates a new parser object with the given memory allocator
532 void cmark_parser_free(cmark_parser *parser)
535 Frees memory allocated for a parser object.
538 void cmark_parser_feed(cmark_parser *parser, const char *buffer, size_t
541 len)
542 Feeds a string of length len to parser.
545 cmark_node * cmark_parser_finish(cmark_parser *parser)
548 Finish parsing and return a pointer to a tree of nodes.
551 cmark_node * cmark_parse_document(const char *buffer, size_t len, int
554 options)
555 Parse a CommonMark document in buffer of length len. Returns a pointer
558 to a tree of nodes. The memory allocated for the node tree should be
559 released using cmark_node_free when it is no longer needed.
560 cmark_node * cmark_parse_file(FILE *f, int options)
563 Parse a CommonMark document in file f, returning a pointer to a tree of
566 nodes. The memory allocated for the node tree should be released using
567 cmark_node_free when it is no longer needed.
568 Rendering
571 char * cmark_render_xml(cmark_node *root, int options)
572 Render a node tree as XML. It is the caller's responsibility to free
575 the returned buffer.
576 char * cmark_render_html(cmark_node *root, int options)
579 Render a node tree as an HTML fragment. It is up to the user to add an
582 appropriate header and footer. It is the caller's responsibility to
583 free the returned buffer.
584 char * cmark_render_man(cmark_node *root, int options, int width)
587 Render a node tree as a groff man page, without the header. It is the
590 caller's responsibility to free the returned buffer.
591 char * cmark_render_commonmark(cmark_node *root, int options, int
594 width)
595 Render a node tree as a commonmark document. It is the caller's respon‐
598 sibility to free the returned buffer.
599 char * cmark_render_latex(cmark_node *root, int options, int width)
602 Render a node tree as a LaTeX document. It is the caller's responsibil‐
605 ity to free the returned buffer.
606 Options
609 #define CMARK_OPT_DEFAULT 0
610 Default options.
613 Options affecting rendering
616 #define CMARK_OPT_SOURCEPOS (1 << 1)
617 Include a data-sourcepos attribute on all block elements.
620 #define CMARK_OPT_HARDBREAKS (1 << 2)
623 Render softbreak elements as hard line breaks.
626 #define CMARK_OPT_SAFE (1 << 3)
629 Suppress raw HTML and unsafe links (javascript:, vbscript:, file:, and
632 data:, except for image/png, image/gif, image/jpeg, or image/webp mime
633 types). Raw HTML is replaced by a placeholder HTML comment. Unsafe
634 links are replaced by empty strings.
635 #define CMARK_OPT_NOBREAKS (1 << 4)
638 Render softbreak elements as spaces.
641 Options affecting parsing
644 #define CMARK_OPT_NORMALIZE (1 << 8)
645 Legacy option (no effect).
648 #define CMARK_OPT_VALIDATE_UTF8 (1 << 9)
651 Validate UTF-8 in the input before parsing, replacing illegal sequences
654 with the replacement character U+FFFD.
655 #define CMARK_OPT_SMART (1 << 10)
658 Convert straight quotes to curly, --- to em dashes, -- to en dashes.
661 Version information
664 int cmark_version(void)
665 The library version as integer for runtime checks. Also available as
668 macro CMARK_VERSION for compile time checks.
669 · Bits 16-23 contain the major version.
671 · Bits 8-15 contain the minor version.
673 · Bits 0-7 contain the patchlevel.
675 In hexadecimal format, the number 0x010203 represents version 1.2.3.
677 const char * cmark_version_string(void)
680 The library version string for runtime checks. Also available as macro
683 CMARK_VERSION_STRING for compile time checks.
684
687 John MacFarlane, Vicent Marti, Kārlis Gaņģis, Nick Wellnhofer.
688LOCAL June 02, 2017 cmark(3)