commonmarker 0.10.0 → 0.11.0

data/ext/commonmarker/cmark/src/scanners.h

@@ -1,3 +1,6 @@
+#ifndef CMARK_SCANNERS_H
+#define CMARK_SCANNERS_H
+
 #include "cmark.h"
 #include "chunk.h"
 
@@ -55,3 +58,5 @@ bufsize_t _scan_dangerous_url(const unsigned char *p);
 #ifdef __cplusplus
 }
 #endif
+
+#endif

data/ext/commonmarker/cmark/src/scanners.re

@@ -37,7 +37,7 @@ bufsize_t _scan_at(bufsize_t (*scanner)(const unsigned char *), cmark_chunk *c,
 
   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'|'header'|'hr'|'html'|'iframe'|'legend'|'li'|'link'|'main'|'menu'|'menuitem'|'meta'|'nav'|'noframes'|'ol'|'optgroup'|'option'|'p'|'param'|'section'|'source'|'title'|'summary'|'table'|'tbody'|'td'|'tfoot'|'th'|'thead'|'title'|'tr'|'track'|'ul';
+  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'|'meta'|'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:._-]*;
 
@@ -71,7 +71,7 @@ bufsize_t _scan_at(bufsize_t (*scanner)(const unsigned char *), cmark_chunk *c,
   in_single_quotes = ['] (escaped_char|[^'\x00])* ['];
   in_parens        = [(] (escaped_char|[^)\x00])* [)];
 
-  scheme           = [A-Za-z ][A-Za-z.+-]{1,31};
+  scheme           = [A-Za-z][A-Za-z0-9.+-]{1,31};
 */
 
 // Try to match a scheme including colon.

data/ext/commonmarker/cmark/src/syntax_extension.c

@@ -0,0 +1,110 @@
+#include <stdlib.h>
+
+#include "cmark.h"
+#include "syntax_extension.h"
+#include "buffer.h"
+
+void cmark_syntax_extension_free(cmark_syntax_extension *extension) {
+  if (extension->free_function && extension->priv) {
+    extension->free_function(extension->priv);
+  }
+
+  cmark_llist_free(extension->special_inline_chars);
+  free(extension->name);
+  free(extension);
+}
+
+cmark_syntax_extension *cmark_syntax_extension_new(const char *name) {
+  cmark_syntax_extension *res = (cmark_syntax_extension *) calloc(1, sizeof(cmark_syntax_extension));
+  res->name = (char *) malloc(sizeof(char) * (strlen(name)) + 1);
+  strcpy(res->name, name);
+  return res;
+}
+
+cmark_node_type cmark_syntax_extension_add_node(int is_inline) {
+  cmark_node_type *ref = !is_inline ? &CMARK_NODE_LAST_BLOCK : &CMARK_NODE_LAST_INLINE;
+
+  if ((*ref & CMARK_NODE_VALUE_MASK) == CMARK_NODE_VALUE_MASK) {
+    assert(false);
+    return (cmark_node_type) 0;
+  }
+
+  return *ref = (cmark_node_type) ((int) *ref + 1);
+}
+
+void cmark_syntax_extension_set_open_block_func(cmark_syntax_extension *extension,
+                                                cmark_open_block_func func) {
+  extension->try_opening_block = func;
+}
+
+void cmark_syntax_extension_set_match_block_func(cmark_syntax_extension *extension,
+                                                 cmark_match_block_func func) {
+  extension->last_block_matches = func;
+}
+
+void cmark_syntax_extension_set_match_inline_func(cmark_syntax_extension *extension,
+                                                  cmark_match_inline_func func) {
+  extension->match_inline = func;
+}
+
+void cmark_syntax_extension_set_inline_from_delim_func(cmark_syntax_extension *extension,
+                                                       cmark_inline_from_delim_func func) {
+  extension->insert_inline_from_delim = func;
+}
+
+void cmark_syntax_extension_set_special_inline_chars(cmark_syntax_extension *extension,
+                                                     cmark_llist *special_chars) {
+  extension->special_inline_chars = special_chars;
+}
+
+void cmark_syntax_extension_set_get_type_string_func(cmark_syntax_extension *extension,
+                                                     cmark_get_type_string_func func) {
+  extension->get_type_string_func = func;
+}
+
+void cmark_syntax_extension_set_can_contain_func(cmark_syntax_extension *extension,
+                                                 cmark_can_contain_func func) {
+  extension->can_contain_func = func;
+}
+
+void cmark_syntax_extension_set_contains_inlines_func(cmark_syntax_extension *extension,
+                                                      cmark_contains_inlines_func func) {
+  extension->contains_inlines_func = func;
+}
+
+void cmark_syntax_extension_set_commonmark_render_func(cmark_syntax_extension *extension,
+                                                       cmark_common_render_func func) {
+  extension->commonmark_render_func = func;
+}
+
+void cmark_syntax_extension_set_latex_render_func(cmark_syntax_extension *extension,
+                                                  cmark_common_render_func func) {
+  extension->latex_render_func = func;
+}
+
+void cmark_syntax_extension_set_man_render_func(cmark_syntax_extension *extension,
+                                                cmark_common_render_func func) {
+  extension->man_render_func = func;
+}
+
+void cmark_syntax_extension_set_html_render_func(cmark_syntax_extension *extension,
+                                                 cmark_html_render_func func) {
+  extension->html_render_func = func;
+}
+
+void cmark_syntax_extension_set_html_filter_func(cmark_syntax_extension *extension,
+                                                 cmark_html_filter_func func) {
+  extension->html_filter_func = func;
+}
+
+void cmark_syntax_extension_set_postprocess_func(cmark_syntax_extension *extension,
+                                                 cmark_postprocess_func func) {
+  extension->postprocess_func = func;
+}
+
+void cmark_syntax_extension_set_private(cmark_syntax_extension *extension,
+                                        void *priv,
+                                        cmark_free_func free_func) {
+  extension->priv = priv;
+  extension->free_function = free_func;
+}

data/ext/commonmarker/cmark/src/syntax_extension.h

@@ -0,0 +1,27 @@
+#ifndef CMARK_SYNTAX_EXTENSION_H
+#define CMARK_SYNTAX_EXTENSION_H
+
+#include "cmark.h"
+#include "cmark_extension_api.h"
+
+struct cmark_syntax_extension {
+  cmark_match_block_func          last_block_matches;
+  cmark_open_block_func           try_opening_block;
+  cmark_match_inline_func         match_inline;
+  cmark_inline_from_delim_func    insert_inline_from_delim;
+  cmark_llist                   * special_inline_chars;
+  char                          * name;
+  void                          * priv;
+  cmark_free_func                 free_function;
+  cmark_get_type_string_func      get_type_string_func;
+  cmark_can_contain_func          can_contain_func;
+  cmark_contains_inlines_func     contains_inlines_func;
+  cmark_common_render_func        commonmark_render_func;
+  cmark_common_render_func        latex_render_func;
+  cmark_common_render_func        man_render_func;
+  cmark_html_render_func          html_render_func;
+  cmark_html_filter_func          html_filter_func;
+  cmark_postprocess_func          postprocess_func;
+};
+
+#endif

data/ext/commonmarker/cmark/suppressions

@@ -0,0 +1,28 @@
+{
+   .
+   Memcheck:Leak
+   match-leak-kinds: possible
+   fun:malloc_zone_malloc
+   fun:_objc_copyClassNamesForImage
+   fun:_ZL9protocolsv
+   fun:_Z9readClassP10objc_classbb
+   fun:gc_init
+   fun:_ZL33objc_initializeClassPair_internalP10objc_classPKcS0_S0_
+   fun:layout_string_create
+   fun:_ZL12realizeClassP10objc_class
+   fun:_ZL22copySwiftV1MangledNamePKcb
+   fun:_ZL22copySwiftV1MangledNamePKcb
+   fun:_ZL22copySwiftV1MangledNamePKcb
+   fun:_ZL22copySwiftV1MangledNamePKcb
+}
+{
+   .
+   Memcheck:Leak
+   match-leak-kinds: reachable
+   fun:malloc
+   fun:__smakebuf
+   fun:__srefill0
+   fun:__fread
+   fun:fread
+   fun:main
+}

data/ext/commonmarker/cmark/test/CMakeLists.txt

@@ -46,13 +46,24 @@ IF (PYTHONINTERP_FOUND)
     ${PYTHON_EXECUTABLE} "${CMAKE_CURRENT_SOURCE_DIR}/spec_tests.py" "--no-normalize" "--spec" "${CMAKE_CURRENT_SOURCE_DIR}/smart_punct.txt" "--program" "${CMAKE_CURRENT_BINARY_DIR}/../src/cmark --smart"
     )
 
-  add_test(roundtriptest_executable
+  add_test(extensions_executable
+    ${PYTHON_EXECUTABLE} "${CMAKE_CURRENT_SOURCE_DIR}/spec_tests.py" "--no-normalize" "--spec" "${CMAKE_CURRENT_SOURCE_DIR}/extensions.txt" "--program" "${CMAKE_CURRENT_BINARY_DIR}/../src/cmark -e table -e strikethrough -e whitelist -e autolink"
+    )
+
+  add_test(roundtriptest_library
     ${PYTHON_EXECUTABLE}
     "${CMAKE_CURRENT_SOURCE_DIR}/roundtrip_tests.py"
     "--spec" "${CMAKE_CURRENT_SOURCE_DIR}/spec.txt"
     "--library-dir" "${CMAKE_CURRENT_BINARY_DIR}/../src"
     )
 
+  add_test(roundtrip_extensions_executable
+    ${PYTHON_EXECUTABLE}
+    "${CMAKE_CURRENT_SOURCE_DIR}/roundtrip_tests.py"
+    "--spec" "${CMAKE_CURRENT_SOURCE_DIR}/extensions.txt"
+    "--program" "${CMAKE_CURRENT_BINARY_DIR}/../src/cmark -e table -e strikethrough -e whitelist -e autolink"
+    )
+
   add_test(regressiontest_executable
     ${PYTHON_EXECUTABLE}
     "${CMAKE_CURRENT_SOURCE_DIR}/spec_tests.py" "--no-normalize" "--spec"

data/ext/commonmarker/cmark/test/extensions.txt

@@ -0,0 +1,173 @@
+---
+title: Extensions test
+author: Yuki Izumi
+version: 0.1
+date: '2016-08-31'
+license: '[CC-BY-SA 4.0](http://creativecommons.org/licenses/by-sa/4.0/)'
+...
+
+## Tables
+
+Here's a well-formed table, doing everything it should.
+
+```````````````````````````````` example
+| abc | def |
+| --- | --- |
+| ghi | jkl |
+| mno | pqr |
+.
+<table>
+<thead>
+<tr>
+<th> abc</th>
+<th> def</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> ghi</td>
+<td> jkl</td>
+</tr>
+<tr>
+<td> mno</td>
+<td> pqr</td>
+</tr></tbody></table>
+````````````````````````````````
+
+We're going to mix up the table now; we'll demonstrate that inline formatting
+works fine, but block elements don't.  You can also have empty cells, and the
+textual alignment of the columns is shown to be irrelevant.
+
+```````````````````````````````` example
+Hello!
+
+| _abc_ | セン |
+| ----- | ---- |
+| 1. Block elements inside cells don't work. | |
+| But **_inline elements do_**. | x |
+
+Hi!
+.
+<p>Hello!</p>
+<table>
+<thead>
+<tr>
+<th> <em>abc</em></th>
+<th> セン</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> 1. Block elements inside cells don't work.</td>
+<td></td>
+</tr>
+<tr>
+<td> But <strong><em>inline elements do</em></strong>.</td>
+<td> x</td>
+</tr></tbody></table>
+<p>Hi!</p>
+````````````````````````````````
+
+Here we demonstrate some edge cases about what is and isn't a table.
+
+```````````````````````````````` example
+| Not enough table | to be considered table |
+
+| Not enough table | to be considered table |
+| Not enough table | to be considered table |
+
+| Just enough table | to be considered table |
+| ----------------- | ---------------------- |
+
+| ---- | --- |
+
+| x |
+| - |
+.
+<p>| Not enough table | to be considered table |</p>
+<p>| Not enough table | to be considered table |
+| Not enough table | to be considered table |</p>
+<table>
+<thead>
+<tr>
+<th> Just enough table</th>
+<th> to be considered table</th>
+</tr>
+</thead>
+<tbody></tbody></table>
+<p>| ---- | --- |</p>
+<table>
+<thead>
+<tr>
+<th> x</th>
+</tr>
+</thead>
+<tbody></tbody></table>
+````````````````````````````````
+
+
+## Strikethroughs
+
+A well-formed strikethrough.
+
+```````````````````````````````` example
+A proper ~strikethrough~.
+.
+<p>A proper <del>strikethrough</del>.</p>
+````````````````````````````````
+
+Some strikethrough edge cases.
+
+```````````````````````````````` example
+These are ~not strikethroughs.
+
+No, they are not~
+
+This ~is ~ legit~ isn't ~ legit.
+
+This is just ~~~~~one~~~~~ huge strikethrough.
+.
+<p>These are ~not strikethroughs.</p>
+<p>No, they are not~</p>
+<p>This <del>is ~ legit</del> isn't ~ legit.</p>
+<p>This is just <del>one</del> huge strikethrough.</p>
+````````````````````````````````
+
+
+## HTML whitelist
+
+
+```````````````````````````````` example
+This is <xmp> not okay, but **this** <strong>is</strong>.
+
+<p>This is <xmp> not okay, but **this** <strong>is</strong>.</p>
+
+Nope, I won't have <textarea>.
+
+<p>No <textarea> here either.</p>
+.
+<p>This is &lt;xmp> not okay, but <strong>this</strong> <strong>is</strong>.</p>
+<p>This is &lt;xmp> not okay, but **this** <strong>is</strong>.</p>
+<p>Nope, I won't have &lt;textarea>.</p>
+<p>No &lt;textarea> here either.</p>
+````````````````````````````````
+
+
+
+## Autolinks
+
+```````````````````````````````` example
+: http://google.com https://google.com
+
+<http://google.com/å> http://google.com/å
+
+scyther@pokemon.com
+
+www.github.com www.github.com/á
+
+.
+<p>: <a href="http://google.com">http://google.com</a> <a href="https://google.com">https://google.com</a></p>
+<p><a href="http://google.com/%C3%A5">http://google.com/å</a> <a href="http://google.com/%C3%A5">http://google.com/å</a></p>
+<p><a href="mailto:scyther@pokemon.com">scyther@pokemon.com</a></p>
+<p><a href="http://www.github.com">www.github.com</a> <a href="http://www.github.com/%C3%A1">www.github.com/á</a></p>
+````````````````````````````````

data/ext/commonmarker/cmark/test/regression.txt

@@ -32,3 +32,27 @@ Repeatedly solving
 <li>how techniques</li>
 </ul>
 ````````````````````````````````
+
+Issue jgm/CommonMark#430:  h2..h6 not recognized as block tags.
+
+```````````````````````````````` example
+<h1>lorem</h1>
+
+<h2>lorem</h2>
+
+<h3>lorem</h3>
+
+<h4>lorem</h4>
+
+<h5>lorem</h5>
+
+<h6>lorem</h6>
+.
+<h1>lorem</h1>
+<h2>lorem</h2>
+<h3>lorem</h3>
+<h4>lorem</h4>
+<h5>lorem</h5>
+<h6>lorem</h6>
+````````````````````````````````
+

data/ext/commonmarker/cmark/test/spec.txt

@@ -1985,7 +1985,7 @@ by their start and end conditions.  The block begins with a line that
 meets a [start condition](@) (after up to three spaces
 optional indentation).  It ends with the first subsequent line that
 meets a matching [end condition](@), or the last line of
-the document or other [container block](@), if no line is encountered that meets the
+the document or other [container block]), if no line is encountered that meets the
 [end condition].  If the first line meets both the [start condition]
 and the [end condition], the block will contain just that line.
 
@@ -2015,7 +2015,8 @@ followed by one of the strings (case-insensitive) `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`, `header`, `hr`,
+`footer`, `form`, `frame`, `frameset`,
+`h1`, `h2`, `h3`, `h4`, `h5`, `h6`, `head`, `header`, `hr`,
 `html`, `iframe`, `legend`, `li`, `link`, `main`, `menu`, `menuitem`,
 `meta`, `nav`, `noframes`, `ol`, `optgroup`, `option`, `p`, `param`,
 `section`, `source`, `summary`, `table`, `tbody`, `td`,
@@ -4730,8 +4731,7 @@ takes four spaces (a common case), but diverge in other cases.
 
 A [list](@) is a sequence of one or more
 list items [of the same type].  The list items
-may be separated by single [blank lines], but two
-blank lines end all containing lists.
+may be separated by any number of blank lines.
 
 Two list items are [of the same type](@)
 if they begin with a [list marker] of the same type.
@@ -4809,10 +4809,11 @@ Foo
 `Markdown.pl` does not allow this, through fear of triggering a list
 via a numeral in a hard-wrapped line:
 
-```````````````````````````````` markdown
+``` markdown
 The number of windows in my house is
 14.  The number of doors is 6.
-````````````````````````````````
+```
+
 Oddly, though, `Markdown.pl` *does* allow a blockquote to
 interrupt a paragraph, even though the same considerations might
 apply.
@@ -4821,10 +4822,12 @@ In CommonMark, we do allow lists to interrupt paragraphs, for
 two reasons.  First, it is natural and not uncommon for people
 to start lists without blank lines:
 
-    I need to buy
-    - new shoes
-    - a coat
-    - a plane ticket
+``` markdown
+I need to buy
+- new shoes
+- a coat
+- a plane ticket
+```
 
 Second, we are attracted to a
 
@@ -4836,20 +4839,24 @@ Second, we are attracted to a
 (Indeed, the spec for [list items] and [block quotes] presupposes
 this principle.) This principle implies that if
 
-      * I need to buy
-        - new shoes
-        - a coat
-        - a plane ticket
+``` markdown
+  * I need to buy
+    - new shoes
+    - a coat
+    - a plane ticket
+```
 
 is a list item containing a paragraph followed by a nested sublist,
 as all Markdown implementations agree it is (though the paragraph
 may be rendered without `<p>` tags, since the list is "tight"),
 then
 
-    I need to buy
-    - new shoes
-    - a coat
-    - a plane ticket
+``` markdown
+I need to buy
+- new shoes
+- a coat
+- a plane ticket
+```
 
 by itself should be a paragraph followed by a nested sublist.
 
@@ -6558,7 +6565,7 @@ Note that in the preceding case, the interpretation
 
 
 is precluded by the condition that a delimiter that
-can both open and close (like the `*` after `foo`
+can both open and close (like the `*` after `foo`)
 cannot form emphasis if the sum of the lengths of
 the delimiter runs containing the opening and
 closing delimiters is a multiple of 3.
@@ -6590,12 +6597,6 @@ omitted:
 ````````````````````````````````
 
 
-```````````````````````````````` example
-*foo**bar***
-.
-<p><em>foo<strong>bar</strong></em></p>
-````````````````````````````````
-
 Indefinite levels of nesting are possible:
 
 ```````````````````````````````` example
@@ -9045,7 +9046,7 @@ blocks.  But we cannot close unmatched blocks yet, because we may have a
 [lazy continuation line].
 
 2.  Next, after consuming the continuation markers for existing
-blocks, we look for new block starts (e.g. `>` for a block quote.
+blocks, we look for new block starts (e.g. `>` for a block quote).
 If we encounter a new block start, we close any blocks unmatched
 in step 1 before creating the new block as a child of the last
 matched block.