markly 0.1.0

data/ext/markly/scanners.h

@@ -0,0 +1,62 @@
+#ifndef CMARK_SCANNERS_H
+#define CMARK_SCANNERS_H
+
+#include "cmark-gfm.h"
+#include "chunk.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+bufsize_t _scan_at(bufsize_t (*scanner)(const unsigned char *), cmark_chunk *c,
+                   bufsize_t offset);
+bufsize_t _scan_scheme(const unsigned char *p);
+bufsize_t _scan_autolink_uri(const unsigned char *p);
+bufsize_t _scan_autolink_email(const unsigned char *p);
+bufsize_t _scan_html_tag(const unsigned char *p);
+bufsize_t _scan_liberal_html_tag(const unsigned char *p);
+bufsize_t _scan_html_block_start(const unsigned char *p);
+bufsize_t _scan_html_block_start_7(const unsigned char *p);
+bufsize_t _scan_html_block_end_1(const unsigned char *p);
+bufsize_t _scan_html_block_end_2(const unsigned char *p);
+bufsize_t _scan_html_block_end_3(const unsigned char *p);
+bufsize_t _scan_html_block_end_4(const unsigned char *p);
+bufsize_t _scan_html_block_end_5(const unsigned char *p);
+bufsize_t _scan_link_title(const unsigned char *p);
+bufsize_t _scan_spacechars(const unsigned char *p);
+bufsize_t _scan_atx_heading_start(const unsigned char *p);
+bufsize_t _scan_setext_heading_line(const unsigned char *p);
+bufsize_t _scan_open_code_fence(const unsigned char *p);
+bufsize_t _scan_close_code_fence(const unsigned char *p);
+bufsize_t _scan_entity(const unsigned char *p);
+bufsize_t _scan_dangerous_url(const unsigned char *p);
+bufsize_t _scan_footnote_definition(const unsigned char *p);
+
+#define scan_scheme(c, n) _scan_at(&_scan_scheme, c, n)
+#define scan_autolink_uri(c, n) _scan_at(&_scan_autolink_uri, c, n)
+#define scan_autolink_email(c, n) _scan_at(&_scan_autolink_email, c, n)
+#define scan_html_tag(c, n) _scan_at(&_scan_html_tag, c, n)
+#define scan_liberal_html_tag(c, n) _scan_at(&_scan_liberal_html_tag, c, n)
+#define scan_html_block_start(c, n) _scan_at(&_scan_html_block_start, c, n)
+#define scan_html_block_start_7(c, n) _scan_at(&_scan_html_block_start_7, c, n)
+#define scan_html_block_end_1(c, n) _scan_at(&_scan_html_block_end_1, c, n)
+#define scan_html_block_end_2(c, n) _scan_at(&_scan_html_block_end_2, c, n)
+#define scan_html_block_end_3(c, n) _scan_at(&_scan_html_block_end_3, c, n)
+#define scan_html_block_end_4(c, n) _scan_at(&_scan_html_block_end_4, c, n)
+#define scan_html_block_end_5(c, n) _scan_at(&_scan_html_block_end_5, c, n)
+#define scan_link_title(c, n) _scan_at(&_scan_link_title, c, n)
+#define scan_spacechars(c, n) _scan_at(&_scan_spacechars, c, n)
+#define scan_atx_heading_start(c, n) _scan_at(&_scan_atx_heading_start, c, n)
+#define scan_setext_heading_line(c, n)                                         \
+  _scan_at(&_scan_setext_heading_line, c, n)
+#define scan_open_code_fence(c, n) _scan_at(&_scan_open_code_fence, c, n)
+#define scan_close_code_fence(c, n) _scan_at(&_scan_close_code_fence, c, n)
+#define scan_entity(c, n) _scan_at(&_scan_entity, c, n)
+#define scan_dangerous_url(c, n) _scan_at(&_scan_dangerous_url, c, n)
+#define scan_footnote_definition(c, n) _scan_at(&_scan_footnote_definition, c, n)
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

data/ext/markly/scanners.re

@@ -0,0 +1,326 @@
+#include <stdlib.h>
+#include "chunk.h"
+#include "scanners.h"
+
+bufsize_t _scan_at(bufsize_t (*scanner)(const unsigned char *), cmark_chunk *c, bufsize_t offset)
+{
+	bufsize_t res;
+	unsigned char *ptr = (unsigned char *)c->data;
+
+        if (ptr == NULL || offset > c->len) {
+          return 0;
+        } else {
+	  unsigned char lim = ptr[c->len];
+
+	  ptr[c->len] = '\0';
+	  res = scanner(ptr + offset);
+	  ptr[c->len] = lim;
+        }
+
+	return res;
+}
+
+/*!re2c
+  re2c:define:YYCTYPE  = "unsigned char";
+  re2c:define:YYCURSOR = p;
+  re2c:define:YYMARKER = marker;
+  re2c:define:YYCTXMARKER = marker;
+  re2c:yyfill:enable = 0;
+
+  wordchar = [^\x00-\x20];
+
+  spacechar = [ \t\v\f\r\n];
+
+  reg_char     = [^\\()\x00-\x20];
+
+  escaped_char = [\\][!"#$%&'()*+,./:;<=>?@[\\\]^_`{|}~-];
+
+  tagname = [A-Za-z][A-Za-z0-9-:]*;
+
+  blocktagname = 'address'|'article'|'aside'|'base'|'basefont'|'blockquote'|'body'|'caption'|'center'|'col'|'colgroup'|'dd'|'details'|'dialog'|'dir'|'div'|'dl'|'dt'|'fieldset'|'figcaption'|'figure'|'footer'|'form'|'frame'|'frameset'|'h1'|'h2'|'h3'|'h4'|'h5'|'h6'|'head'|'header'|'hr'|'html'|'iframe'|'legend'|'li'|'link'|'main'|'menu'|'menuitem'|'nav'|'noframes'|'ol'|'optgroup'|'option'|'p'|'param'|'section'|'source'|'title'|'summary'|'table'|'tbody'|'td'|'tfoot'|'th'|'thead'|'title'|'tr'|'track'|'ul';
+
+  attributename = [a-zA-Z_:][a-zA-Z0-9:._-]*;
+
+  unquotedvalue = [^ \t\r\n\v\f"'=<>`\x00]+;
+  singlequotedvalue = ['][^'\x00]*['];
+  doublequotedvalue = ["][^"\x00]*["];
+
+  attributevalue = unquotedvalue | singlequotedvalue | doublequotedvalue;
+
+  attributevaluespec = spacechar* [=] spacechar* attributevalue;
+
+  attribute = spacechar+ attributename attributevaluespec?;
+
+  opentag = tagname attribute* spacechar* [/]? [>];
+  closetag = [/] tagname spacechar* [>];
+
+  htmlcomment = "!---->" | ("!--" ([-]? [^\x00>-]) ([-]? [^\x00-])* "-->");
+
+  processinginstruction = "?" ([^?>\x00]+ | [?][^>\x00] | [>])* "?>";
+
+  declaration = "!" [A-Z]+ spacechar+ [^>\x00]* ">";
+
+  cdata = "![CDATA[" ([^\]\x00]+ | "]" [^\]\x00] | "]]" [^>\x00])* "]]>";
+
+  htmltag = opentag | closetag | htmlcomment | processinginstruction |
+            declaration | cdata;
+
+  in_parens_nosp   = [(] (reg_char|escaped_char|[\\])* [)];
+
+  in_double_quotes = ["] (escaped_char|[^"\x00])* ["];
+  in_single_quotes = ['] (escaped_char|[^'\x00])* ['];
+  in_parens        = [(] (escaped_char|[^)\x00])* [)];
+
+  scheme           = [A-Za-z][A-Za-z0-9.+-]{1,31};
+*/
+
+// Try to match a scheme including colon.
+bufsize_t _scan_scheme(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  scheme [:] { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Try to match URI autolink after first <, returning number of chars matched.
+bufsize_t _scan_autolink_uri(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  scheme [:][^\x00-\x20<>]*[>]  { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Try to match email autolink after first <, returning num of chars matched.
+bufsize_t _scan_autolink_email(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]+
+    [@]
+    [a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?
+    ([.][a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*
+    [>] { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Try to match an HTML tag after first <, returning num of chars matched.
+bufsize_t _scan_html_tag(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  htmltag { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Try to (liberally) match an HTML tag after first <, returning num of chars matched.
+bufsize_t _scan_liberal_html_tag(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [^\n\x00]+ [>] { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Try to match an HTML block tag start line, returning
+// an integer code for the type of block (1-6, matching the spec).
+// #7 is handled by a separate function, below.
+bufsize_t _scan_html_block_start(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+/*!re2c
+  [<] ('script'|'pre'|'style') (spacechar | [>]) { return 1; }
+  '<!--' { return 2; }
+  '<?' { return 3; }
+  '<!' [A-Z] { return 4; }
+  '<![CDATA[' { return 5; }
+  [<] [/]? blocktagname (spacechar | [/]? [>])  { return 6; }
+  * { return 0; }
+*/
+}
+
+// Try to match an HTML block tag start line of type 7, returning
+// 7 if successful, 0 if not.
+bufsize_t _scan_html_block_start_7(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+/*!re2c
+  [<] (opentag | closetag) [\t\n\f ]* [\r\n] { return 7; }
+  * { return 0; }
+*/
+}
+
+// Try to match an HTML block end line of type 1
+bufsize_t _scan_html_block_end_1(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [^\n\x00]* [<] [/] ('script'|'pre'|'style') [>] { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Try to match an HTML block end line of type 2
+bufsize_t _scan_html_block_end_2(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [^\n\x00]* '-->' { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Try to match an HTML block end line of type 3
+bufsize_t _scan_html_block_end_3(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [^\n\x00]* '?>' { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Try to match an HTML block end line of type 4
+bufsize_t _scan_html_block_end_4(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [^\n\x00]* '>' { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Try to match an HTML block end line of type 5
+bufsize_t _scan_html_block_end_5(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [^\n\x00]* ']]>' { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Try to match a link title (in single quotes, in double quotes, or
+// in parentheses), returning number of chars matched.  Allow one
+// level of internal nesting (quotes within quotes).
+bufsize_t _scan_link_title(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  ["] (escaped_char|[^"\x00])* ["]   { return (bufsize_t)(p - start); }
+  ['] (escaped_char|[^'\x00])* ['] { return (bufsize_t)(p - start); }
+  [(] (escaped_char|[^()\x00])* [)]  { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Match space characters, including newlines.
+bufsize_t _scan_spacechars(const unsigned char *p)
+{
+  const unsigned char *start = p; \
+/*!re2c
+  [ \t\v\f\r\n]+ { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Match ATX heading start.
+bufsize_t _scan_atx_heading_start(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [#]{1,6} ([ \t]+|[\r\n])  { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Match setext heading line.  Return 1 for level-1 heading,
+// 2 for level-2, 0 for no match.
+bufsize_t _scan_setext_heading_line(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+/*!re2c
+  [=]+ [ \t]* [\r\n] { return 1; }
+  [-]+ [ \t]* [\r\n] { return 2; }
+  * { return 0; }
+*/
+}
+
+// Scan an opening code fence.
+bufsize_t _scan_open_code_fence(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [`]{3,} / [^`\r\n\x00]*[\r\n] { return (bufsize_t)(p - start); }
+  [~]{3,} / [^\r\n\x00]*[\r\n] { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Scan a closing code fence with length at least len.
+bufsize_t _scan_close_code_fence(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [`]{3,} / [ \t]*[\r\n] { return (bufsize_t)(p - start); }
+  [~]{3,} / [ \t]*[\r\n] { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Scans an entity.
+// Returns number of chars matched.
+bufsize_t _scan_entity(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  [&] ([#] ([Xx][A-Fa-f0-9]{1,6}|[0-9]{1,7}) |[A-Za-z][A-Za-z0-9]{1,31} ) [;]
+     { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Returns positive value if a URL begins in a way that is potentially
+// dangerous, with javascript:, vbscript:, file:, or data:, otherwise 0.
+bufsize_t _scan_dangerous_url(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  'data:image/' ('png'|'gif'|'jpeg'|'webp') { return 0; }
+  'javascript:' | 'vbscript:' | 'file:' | 'data:' { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}
+
+// Scans a footnote definition opening.
+bufsize_t _scan_footnote_definition(const unsigned char *p)
+{
+  const unsigned char *marker = NULL;
+  const unsigned char *start = p;
+/*!re2c
+  '[^' ([^\] \r\n\x00\t]+) ']:' [ \t]* { return (bufsize_t)(p - start); }
+  * { return 0; }
+*/
+}

data/ext/markly/strikethrough.c

@@ -0,0 +1,167 @@
+#include "strikethrough.h"
+#include <parser.h>
+#include <render.h>
+
+cmark_node_type CMARK_NODE_STRIKETHROUGH;
+
+static cmark_node *match(cmark_syntax_extension *self, cmark_parser *parser,
+                         cmark_node *parent, unsigned char character,
+                         cmark_inline_parser *inline_parser) {
+  cmark_node *res = NULL;
+  int left_flanking, right_flanking, punct_before, punct_after, delims;
+  char buffer[101];
+
+  if (character != '~')
+    return NULL;
+
+  delims = cmark_inline_parser_scan_delimiters(
+      inline_parser, sizeof(buffer) - 1, '~',
+      &left_flanking,
+      &right_flanking, &punct_before, &punct_after);
+
+  memset(buffer, '~', delims);
+  buffer[delims] = 0;
+
+  res = cmark_node_new_with_mem(CMARK_NODE_TEXT, parser->mem);
+  cmark_node_set_literal(res, buffer);
+  res->start_line = res->end_line = cmark_inline_parser_get_line(inline_parser);
+  res->start_column = cmark_inline_parser_get_column(inline_parser) - delims;
+
+  if ((left_flanking || right_flanking) &&
+      (delims == 2 || (!(parser->options & CMARK_OPT_STRIKETHROUGH_DOUBLE_TILDE) && delims == 1))) {
+    cmark_inline_parser_push_delimiter(inline_parser, character, left_flanking,
+                                       right_flanking, res);
+  }
+
+  return res;
+}
+
+static delimiter *insert(cmark_syntax_extension *self, cmark_parser *parser,
+                         cmark_inline_parser *inline_parser, delimiter *opener,
+                         delimiter *closer) {
+  cmark_node *strikethrough;
+  cmark_node *tmp, *next;
+  delimiter *delim, *tmp_delim;
+  delimiter *res = closer->next;
+
+  strikethrough = opener->inl_text;
+
+  if (opener->inl_text->as.literal.len != closer->inl_text->as.literal.len)
+    goto done;
+
+  if (!cmark_node_set_type(strikethrough, CMARK_NODE_STRIKETHROUGH))
+    goto done;
+
+  cmark_node_set_syntax_extension(strikethrough, self);
+
+  tmp = cmark_node_next(opener->inl_text);
+
+  while (tmp) {
+    if (tmp == closer->inl_text)
+      break;
+    next = cmark_node_next(tmp);
+    cmark_node_append_child(strikethrough, tmp);
+    tmp = next;
+  }
+
+  strikethrough->end_column = closer->inl_text->start_column + closer->inl_text->as.literal.len - 1;
+  cmark_node_free(closer->inl_text);
+
+  delim = closer;
+  while (delim != NULL && delim != opener) {
+    tmp_delim = delim->previous;
+    cmark_inline_parser_remove_delimiter(inline_parser, delim);
+    delim = tmp_delim;
+  }
+
+  cmark_inline_parser_remove_delimiter(inline_parser, opener);
+
+done:
+  return res;
+}
+
+static const char *get_type_string(cmark_syntax_extension *extension,
+                                   cmark_node *node) {
+  return node->type == CMARK_NODE_STRIKETHROUGH ? "strikethrough" : "<unknown>";
+}
+
+static int can_contain(cmark_syntax_extension *extension, cmark_node *node,
+                       cmark_node_type child_type) {
+  if (node->type != CMARK_NODE_STRIKETHROUGH)
+    return false;
+
+  return CMARK_NODE_TYPE_INLINE_P(child_type);
+}
+
+static void commonmark_render(cmark_syntax_extension *extension,
+                              cmark_renderer *renderer, cmark_node *node,
+                              cmark_event_type ev_type, int options) {
+  renderer->out(renderer, node, "~~", false, LITERAL);
+}
+
+static void latex_render(cmark_syntax_extension *extension,
+                         cmark_renderer *renderer, cmark_node *node,
+                         cmark_event_type ev_type, int options) {
+  // requires \usepackage{ulem}
+  bool entering = (ev_type == CMARK_EVENT_ENTER);
+  if (entering) {
+    renderer->out(renderer, node, "\\sout{", false, LITERAL);
+  } else {
+    renderer->out(renderer, node, "}", false, LITERAL);
+  }
+}
+
+static void man_render(cmark_syntax_extension *extension,
+                       cmark_renderer *renderer, cmark_node *node,
+                       cmark_event_type ev_type, int options) {
+  bool entering = (ev_type == CMARK_EVENT_ENTER);
+  if (entering) {
+    renderer->cr(renderer);
+    renderer->out(renderer, node, ".ST \"", false, LITERAL);
+  } else {
+    renderer->out(renderer, node, "\"", false, LITERAL);
+    renderer->cr(renderer);
+  }
+}
+
+static void html_render(cmark_syntax_extension *extension,
+                        cmark_html_renderer *renderer, cmark_node *node,
+                        cmark_event_type ev_type, int options) {
+  bool entering = (ev_type == CMARK_EVENT_ENTER);
+  if (entering) {
+    cmark_strbuf_puts(renderer->html, "<del>");
+  } else {
+    cmark_strbuf_puts(renderer->html, "</del>");
+  }
+}
+
+static void plaintext_render(cmark_syntax_extension *extension,
+                             cmark_renderer *renderer, cmark_node *node,
+                             cmark_event_type ev_type, int options) {
+  renderer->out(renderer, node, "~", false, LITERAL);
+}
+
+cmark_syntax_extension *create_strikethrough_extension(void) {
+  cmark_syntax_extension *ext = cmark_syntax_extension_new("strikethrough");
+  cmark_llist *special_chars = NULL;
+
+  cmark_syntax_extension_set_get_type_string_func(ext, get_type_string);
+  cmark_syntax_extension_set_can_contain_func(ext, can_contain);
+  cmark_syntax_extension_set_commonmark_render_func(ext, commonmark_render);
+  cmark_syntax_extension_set_latex_render_func(ext, latex_render);
+  cmark_syntax_extension_set_man_render_func(ext, man_render);
+  cmark_syntax_extension_set_html_render_func(ext, html_render);
+  cmark_syntax_extension_set_plaintext_render_func(ext, plaintext_render);
+  CMARK_NODE_STRIKETHROUGH = cmark_syntax_extension_add_node(1);
+
+  cmark_syntax_extension_set_match_inline_func(ext, match);
+  cmark_syntax_extension_set_inline_from_delim_func(ext, insert);
+
+  cmark_mem *mem = cmark_get_default_mem_allocator();
+  special_chars = cmark_llist_append(mem, special_chars, (void *)'~');
+  cmark_syntax_extension_set_special_inline_chars(ext, special_chars);
+
+  cmark_syntax_extension_set_emphasis(ext, 1);
+
+  return ext;
+}