view release on metacpan or  search on metacpan

modules/CommonMark/src/scanners.re  view on Meta::CPAN

#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;
	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'|'head'|'head...

  attributename = [a-zA-Z_:][a-zA-Z0-9:._-]*;

  unquotedvalue = [^\"'=<>`\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 = 'coap'|'doi'|'javascript'|'aaa'|'aaas'|'about'|'acap'|'cap'|'cid'|'crid'|'data'|'dav'|'dict'|'dns'|'file'|'ftp'|'geo'|'go'|'gopher'|'h323'|'http'|'https'|'iax'|'icap'|'im'|'imap'|'info'|'ipp'|'iris'|'iris.beep'|'iris.xpc'|'iris.xpcs'|'iris...
*/

// 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 match an HTML block tag start line, returning
// an integer code for the type of block (1-6, matching the spec).