commonmarker 0.6.0 → 0.7.0

data/ext/commonmarker/cmark/build/src/cmark_version.h

@@ -1,7 +1,7 @@
 #ifndef CMARK_VERSION_H
 #define CMARK_VERSION_H
 
-#define CMARK_VERSION ((0 << 16) | (23 << 8)  | 0)
-#define CMARK_VERSION_STRING "0.23.0"
+#define CMARK_VERSION ((0 << 16) | (24 << 8)  | 1)
+#define CMARK_VERSION_STRING "0.24.1"
 
 #endif

data/ext/commonmarker/cmark/build/src/config.h

@@ -1,3 +1,10 @@
+#ifndef CMARK_CONFIG_H
+#define CMARK_CONFIG_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 #define HAVE_STDBOOL_H
 
 #ifdef HAVE_STDBOOL_H
@@ -23,3 +30,47 @@
     #define CMARK_INLINE inline
   #endif
 #endif
+
+/* snprintf and vsnprintf fallbacks for MSVC before 2015,
+   due to Valentin Milea http://stackoverflow.com/questions/2915672/
+*/
+
+#if defined(_MSC_VER) && _MSC_VER < 1900
+
+#include <stdio.h>
+#include <stdarg.h>
+
+#define snprintf c99_snprintf
+#define vsnprintf c99_vsnprintf
+
+CMARK_INLINE int c99_vsnprintf(char *outBuf, size_t size, const char *format, va_list ap)
+{
+    int count = -1;
+
+    if (size != 0)
+        count = _vsnprintf_s(outBuf, size, _TRUNCATE, format, ap);
+    if (count == -1)
+        count = _vscprintf(format, ap);
+
+    return count;
+}
+
+CMARK_INLINE int c99_snprintf(char *outBuf, size_t size, const char *format, ...)
+{
+    int count;
+    va_list ap;
+
+    va_start(ap, format);
+    count = c99_vsnprintf(outBuf, size, format, ap);
+    va_end(ap);
+
+    return count;
+}
+
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

data/ext/commonmarker/cmark/build/src/libcmark.pc

@@ -5,6 +5,6 @@ includedir=/usr/local/include
 
 Name: libcmark
 Description: CommonMark parsing, rendering, and manipulation
-Version: 0.23.0
+Version: 0.24.1
 Libs: -L${libdir} -lcmark
 Cflags: -I${includedir}

data/ext/commonmarker/cmark/build/testdir/Makefile

@@ -81,7 +81,7 @@ install/local/fast: install/local
 # Special rule for the target edit_cache
 edit_cache:
 	@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --cyan "Running CMake cache editor..."
-	/usr/local/Cellar/cmake/2.8.10.1-boxen1/bin/ccmake -H$(CMAKE_SOURCE_DIR) -B$(CMAKE_BINARY_DIR)
+	/usr/local/Cellar/cmake/3.3.2/bin/ccmake -H$(CMAKE_SOURCE_DIR) -B$(CMAKE_BINARY_DIR)
 .PHONY : edit_cache
 
 # Special rule for the target edit_cache

data/ext/commonmarker/cmark/changelog.txt

@@ -1,3 +1,57 @@
+[0.24.1]
+
+  * Commonmark renderer:
+    + Use HTML comment, not two blank lines, to separate a list
+      item from a following code block or list.  This makes the
+      output more portable, since the "two blank lines" rule is
+      unique to CommonMark.  Also, it allows us to break out of
+      a sublist without breaking out of all levels of nesting.
+    + `is_autolink` - handle case where link has no children,
+      which previously caused a segfault.
+    + Use 4-space indent for bullet lists, for increased portability.
+    + Use 2-space + newline for line break for increased portability (#90).
+    + Improved punctuation escaping.  Previously all `)` and
+      `.` characters after digits were escaped; now they are
+      only escaped if they are genuinely in a position where
+      they'd cause a list item.  This is achieved by changes in
+      `render.c`: (a) `renderer->begin_content` is only set to
+      false after a string of digits at the beginning of the
+      line, and (b) we never break a line before a digit.
+      Also, `begin_content` is properly initialized to true.
+  * Handle NULL root in `consolidate_text_nodes`.
+
+[0.24.0]
+
+  * [API change] Added `cmark_node_replace(oldnode, newnode)`.
+  * Updated spec.txt to 0.24.
+  * Fixed edge case with escaped parens in link destination (#97).
+    This was also checked against the #82 case with asan.
+  * Removed unnecessary check for `fenced` in `cmark_render_html`.
+    It's sufficient to check that the info string is empty.
+    Indeed, those who use the API may well create a code block
+    with an info string without explicitly setting `fenced`.
+  * Updated format of `test/smart_punct.txt`.
+  * Updated `test/spec.txt`, `test/smart_punct.txt`, and
+    `spec_tests.py` to new format.
+  * Fixed `get_containing_block` logic in `src/commonmark.c`.
+    This did not allow for the possibility that a node might have no
+    containing block, causing the commonmark renderer to segfault if
+    passed an inline node with no block parent.
+  * Fixed string representations of `CUSTOM_BLOCK`,
+    `CUSTOM_INLINE`.  The old versions `raw_inline` and
+    `raw_block` were being used, and this led to incorrect xml output.
+  * Use default opts in python sample wrapper.
+  * Allow multiline setext header content, as per spec.
+  * Don't allow spaces in link destinations, even with pointy brackets.
+    Conforms to latest change in spec.
+  * Updated `scheme` scanner according to spec change.  We no longer use
+    a whitelist of valid schemes.
+  * Allow any kind of nodes as children of `CUSTOM_BLOCK` (#96).
+  * `cmark.h`: moved typedefs for iterator into iterator section.
+    This just moves some code around so it makes more sense
+    to read, and in the man page.
+  * Fixed `make_man_page.py` so it includes typedefs again.
+
 [0.23.0]
 
   * [API change] Added `CUSTOM_BLOCK` and `CUSTOM_INLINE` node types.

data/ext/commonmarker/cmark/man/make_man_page.py

@@ -83,9 +83,11 @@ with open(sourcefile, 'r') as cmarkh:
             state = 'default'
         elif typedef and typedef_end_re.match(line):
             typedef = False
+        elif typedef_start_re.match(line):
+            typedef = True
+            state = 'signature'
         elif state == 'man':
             state = 'signature'
-            typedef = typedef_start_re.match(line)
 
         # handle line
         if state == 'man':

data/ext/commonmarker/cmark/man/man3/cmark.3

@@ -1,4 +1,4 @@
-.TH cmark 3 "December 28, 2015" "LOCAL" "Library Functions Manual"
+.TH cmark 3 "January 11, 2016" "LOCAL" "Library Functions Manual"
 .SH
 NAME
 .PP
@@ -20,6 +20,80 @@ null\-terminated, UTF\-8\-encoded string.
 .SS
 Node Structure
 
+.PP
+.nf
+\fC
+.RS 0n
+typedef enum {
+  /* Error status */
+  CMARK_NODE_NONE,
+
+  /* Block */
+  CMARK_NODE_DOCUMENT,
+  CMARK_NODE_BLOCK_QUOTE,
+  CMARK_NODE_LIST,
+  CMARK_NODE_ITEM,
+  CMARK_NODE_CODE_BLOCK,
+  CMARK_NODE_HTML_BLOCK,
+  CMARK_NODE_CUSTOM_BLOCK,
+  CMARK_NODE_PARAGRAPH,
+  CMARK_NODE_HEADING,
+  CMARK_NODE_THEMATIC_BREAK,
+
+  CMARK_NODE_FIRST_BLOCK = CMARK_NODE_DOCUMENT,
+  CMARK_NODE_LAST_BLOCK = CMARK_NODE_THEMATIC_BREAK,
+
+  /* Inline */
+  CMARK_NODE_TEXT,
+  CMARK_NODE_SOFTBREAK,
+  CMARK_NODE_LINEBREAK,
+  CMARK_NODE_CODE,
+  CMARK_NODE_HTML_INLINE,
+  CMARK_NODE_CUSTOM_INLINE,
+  CMARK_NODE_EMPH,
+  CMARK_NODE_STRONG,
+  CMARK_NODE_LINK,
+  CMARK_NODE_IMAGE,
+
+  CMARK_NODE_FIRST_INLINE = CMARK_NODE_TEXT,
+  CMARK_NODE_LAST_INLINE = CMARK_NODE_IMAGE,
+} cmark_node_type;
+.RE
+\f[]
+.fi
+
+
+
+.PP
+.nf
+\fC
+.RS 0n
+typedef enum {
+  CMARK_NO_LIST,
+  CMARK_BULLET_LIST,
+  CMARK_ORDERED_LIST
+} cmark_list_type;
+.RE
+\f[]
+.fi
+
+
+
+.PP
+.nf
+\fC
+.RS 0n
+typedef enum {
+  CMARK_NO_DELIM,
+  CMARK_PERIOD_DELIM,
+  CMARK_PAREN_DELIM
+} cmark_delim_type;
+.RE
+\f[]
+.fi
+
+
+
 .SS
 Creating and Destroying Nodes
 
@@ -28,8 +102,8 @@ Creating and Destroying Nodes
 
 .PP
 Creates a new node of type \f[I]type\f[]. Note that the node may have
-other required properties, which it is the caller's responsibility to
-assign.
+other required properties, which it is the caller\[cq]s responsibility
+to assign.
 
 .PP
 \fIvoid\f[] \fBcmark_node_free\f[](\fIcmark_node *node\f[])
@@ -129,6 +203,22 @@ CMARK_NODE_HTML_INLINE
 Nodes must only be modified after an \f[C]EXIT\f[] event, or an
 \f[C]ENTER\f[] event for leaf nodes.
 
+.PP
+.nf
+\fC
+.RS 0n
+typedef enum {
+  CMARK_EVENT_NONE,
+  CMARK_EVENT_DONE,
+  CMARK_EVENT_ENTER,
+  CMARK_EVENT_EXIT
+} cmark_event_type;
+.RE
+\f[]
+.fi
+
+
+
 .PP
 \fIcmark_iter *\f[] \fBcmark_iter_new\f[](\fIcmark_node *root\f[])
 
@@ -286,7 +376,8 @@ Returns 1 if \f[I]node\f[] is a tight list, 0 otherwise.
 \fIint\f[] \fBcmark_node_set_list_tight\f[](\fIcmark_node *node\f[], \fIint tight\f[])
 
 .PP
-Sets the "tightness" of a list. Returns 1 on success, 0 on failure.
+Sets the \[lq]tightness\[rq] of a list. Returns 1 on success, 0 on
+failure.
 
 .PP
 \fIconst char *\f[] \fBcmark_node_get_fence_info\f[](\fIcmark_node *node\f[])
@@ -333,31 +424,31 @@ on failure.
 \fIconst char *\f[] \fBcmark_node_get_on_enter\f[](\fIcmark_node *node\f[])
 
 .PP
-Returns the literal "on enter" text for a custom \f[I]node\f[], or an
-empty string if no on_enter is set.
+Returns the literal \[lq]on enter\[rq] text for a custom \f[I]node\f[],
+or an empty string if no on_enter is set.
 
 .PP
 \fIint\f[] \fBcmark_node_set_on_enter\f[](\fIcmark_node *node\f[], \fIconst char *on_enter\f[])
 
 .PP
-Sets the literal text to render "on enter" for a custom \f[I]node\f[].
-Any children of the node will be rendered after this text. Returns 1 on
-success 0 on failure.
+Sets the literal text to render \[lq]on enter\[rq] for a custom
+\f[I]node\f[]. Any children of the node will be rendered after this
+text. Returns 1 on success 0 on failure.
 
 .PP
 \fIconst char *\f[] \fBcmark_node_get_on_exit\f[](\fIcmark_node *node\f[])
 
 .PP
-Returns the literal "on exit" text for a custom \f[I]node\f[], or an
-empty string if no on_exit is set.
+Returns the literal \[lq]on exit\[rq] text for a custom \f[I]node\f[],
+or an empty string if no on_exit is set.
 
 .PP
 \fIint\f[] \fBcmark_node_set_on_exit\f[](\fIcmark_node *node\f[], \fIconst char *on_exit\f[])
 
 .PP
-Sets the literal text to render "on exit" for a custom \f[I]node\f[].
-Any children of the node will be rendered before this text. Returns 1 on
-success 0 on failure.
+Sets the literal text to render \[lq]on exit\[rq] for a custom
+\f[I]node\f[]. Any children of the node will be rendered before this
+text. Returns 1 on success 0 on failure.
 
 .PP
 \fIint\f[] \fBcmark_node_get_start_line\f[](\fIcmark_node *node\f[])
@@ -407,6 +498,14 @@ on failure.
 Inserts \f[I]sibling\f[] after \f[I]node\f[]. Returns 1 on success, 0 on
 failure.
 
+.PP
+\fIint\f[] \fBcmark_node_replace\f[](\fIcmark_node *oldnode\f[], \fIcmark_node *newnode\f[])
+
+.PP
+Replaces \f[I]oldnode\f[] with \f[I]newnode\f[] and unlinks
+\f[I]oldnode\f[] (but does not free its memory). Returns 1 on success, 0
+on failure.
+
 .PP
 \fIint\f[] \fBcmark_node_prepend_child\f[](\fIcmark_node *node\f[], \fIcmark_node *child\f[])
 
@@ -624,7 +723,7 @@ with the replacement character U+FFFD.
 .fi
 
 .PP
-Convert straight quotes to curly, \-\-\- to em dashes, \-\- to en
+Convert straight quotes to curly, \[em] to em dashes, \[en] to en
 dashes.
 
 .SS

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

@@ -800,11 +800,7 @@ static void S_process_line(cmark_parser *parser, const unsigned char *buffer,
 
     } else if (!indented && container->type == CMARK_NODE_PARAGRAPH &&
                (lev =
-                    scan_setext_heading_line(&input, parser->first_nonspace)) &&
-               // check that there is only one line in the paragraph:
-               (cmark_strbuf_strrchr(
-                    &container->string_content, '\n',
-                    cmark_strbuf_len(&container->string_content) - 2) < 0)) {
+                    scan_setext_heading_line(&input, parser->first_nonspace))) {
 
       container->type = CMARK_NODE_HEADING;
       container->as.heading.level = lev;

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

@@ -48,8 +48,8 @@ static CMARK_INLINE void cmark_chunk_trim(cmark_chunk *c) {
   cmark_chunk_rtrim(c);
 }
 
-static CMARK_INLINE bufsize_t
-    cmark_chunk_strchr(cmark_chunk *ch, int c, bufsize_t offset) {
+static CMARK_INLINE bufsize_t cmark_chunk_strchr(cmark_chunk *ch, int c,
+                                                 bufsize_t offset) {
   const unsigned char *p =
       (unsigned char *)memchr(ch->data + offset, c, ch->len - offset);
   return p ? (bufsize_t)(p - ch->data) : ch->len;
@@ -96,8 +96,8 @@ static CMARK_INLINE cmark_chunk cmark_chunk_literal(const char *data) {
   return c;
 }
 
-static CMARK_INLINE cmark_chunk
-    cmark_chunk_dup(const cmark_chunk *ch, bufsize_t pos, bufsize_t len) {
+static CMARK_INLINE cmark_chunk cmark_chunk_dup(const cmark_chunk *ch,
+                                                bufsize_t pos, bufsize_t len) {
   cmark_chunk c = {ch->data + pos, len, 0};
   return c;
 }

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

@@ -86,13 +86,6 @@ typedef struct cmark_node cmark_node;
 typedef struct cmark_parser cmark_parser;
 typedef struct cmark_iter cmark_iter;
 
-typedef enum {
-  CMARK_EVENT_NONE,
-  CMARK_EVENT_DONE,
-  CMARK_EVENT_ENTER,
-  CMARK_EVENT_EXIT
-} cmark_event_type;
-
 /**
  * ## Creating and Destroying Nodes
  */
@@ -178,6 +171,13 @@ CMARK_EXPORT cmark_node *cmark_node_last_child(cmark_node *node);
  * leaf nodes.
  */
 
+typedef enum {
+  CMARK_EVENT_NONE,
+  CMARK_EVENT_DONE,
+  CMARK_EVENT_ENTER,
+  CMARK_EVENT_EXIT
+} cmark_event_type;
+
 /** Creates a new iterator starting at 'root'.  The current node and event
  * type are undefined until `cmark_iter_next` is called for the first time.
  */
@@ -387,6 +387,12 @@ CMARK_EXPORT int cmark_node_insert_before(cmark_node *node,
  */
 CMARK_EXPORT int cmark_node_insert_after(cmark_node *node, cmark_node *sibling);
 
+/** Replaces 'oldnode' with 'newnode' and unlinks 'oldnode' (but does
+ * not free its memory).
+ * Returns 1 on success, 0 on failure.
+ */
+CMARK_EXPORT int cmark_node_replace(cmark_node *oldnode, cmark_node *newnode);
+
 /** Adds 'child' to the beginning of the children of 'node'.
  * Returns 1 on success, 0 on failure.
  */

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

@@ -23,7 +23,11 @@
 static inline void outc(cmark_renderer *renderer, cmark_escaping escape,
                         int32_t c, unsigned char nextc) {
   bool needs_escaping = false;
-  char encoded[20];
+  bool follows_digit =
+      renderer->buffer->size > 0 &&
+      cmark_isdigit(renderer->buffer->ptr[renderer->buffer->size - 1]);
+  const size_t ENCODED_SIZE = 20;
+  char encoded[ENCODED_SIZE];
 
   needs_escaping =
       escape != LITERAL &&
@@ -31,9 +35,12 @@ static inline void outc(cmark_renderer *renderer, cmark_escaping escape,
         (c == '*' || c == '_' || c == '[' || c == ']' || c == '#' || c == '<' ||
          c == '>' || c == '\\' || c == '`' || c == '!' ||
          (c == '&' && isalpha(nextc)) || (c == '!' && nextc == '[') ||
-         (renderer->begin_content && (c == '-' || c == '+' || c == '=')) ||
-         ((c == '.' || c == ')') &&
-          isdigit(renderer->buffer->ptr[renderer->buffer->size - 1])))) ||
+         (renderer->begin_content && (c == '-' || c == '+' || c == '=') &&
+          // begin_content doesn't get set to false til we've passed digits
+          // at the beginning of line, so...
+          !follows_digit) ||
+         (renderer->begin_content && (c == '.' || c == ')') && follows_digit &&
+          (nextc == 0 || cmark_isspace(nextc))))) ||
        (escape == URL && (c == '`' || c == '<' || c == '>' || isspace(c) ||
                           c == '\\' || c == ')' || c == '(')) ||
        (escape == TITLE &&
@@ -42,7 +49,7 @@ static inline void outc(cmark_renderer *renderer, cmark_escaping escape,
   if (needs_escaping) {
     if (isspace(c)) {
       // use percent encoding for spaces
-      sprintf(encoded, "%%%2x", c);
+      snprintf(encoded, ENCODED_SIZE, "%%%2x", c);
       cmark_strbuf_puts(renderer->buffer, encoded);
       renderer->column += 3;
     } else {
@@ -121,6 +128,9 @@ static bool is_autolink(cmark_node *node) {
   }
 
   link_text = node->first_child;
+  if (link_text == NULL) {
+    return false;
+  }
   cmark_consolidate_text_nodes(link_text);
   realurl = (char *)url->data;
   realurllen = url->len;
@@ -135,12 +145,17 @@ static bool is_autolink(cmark_node *node) {
 
 // if node is a block node, returns node.
 // otherwise returns first block-level node that is an ancestor of node.
+// if there is no block-level ancestor, returns NULL.
 static cmark_node *get_containing_block(cmark_node *node) {
-  while (node && (node->type < CMARK_NODE_FIRST_BLOCK ||
-                  node->type > CMARK_NODE_LAST_BLOCK)) {
-    node = node->parent;
+  while (node) {
+    if (node->type >= CMARK_NODE_FIRST_BLOCK &&
+        node->type <= CMARK_NODE_LAST_BLOCK) {
+      return node;
+    } else {
+      node = node->parent;
+    }
   }
-  return node;
+  return NULL;
 }
 
 static int S_render_node(cmark_renderer *renderer, cmark_node *node,
@@ -153,7 +168,8 @@ static int S_render_node(cmark_renderer *renderer, cmark_node *node,
   bool entering = (ev_type == CMARK_EVENT_ENTER);
   const char *info, *code, *title;
   size_t info_len, code_len;
-  char listmarker[20];
+  const size_t LISTMARKER_SIZE = 20;
+  char listmarker[LISTMARKER_SIZE];
   char *emph_delim;
   bufsize_t marker_width;
 
@@ -163,10 +179,11 @@ static int S_render_node(cmark_renderer *renderer, cmark_node *node,
   if (!(node->type == CMARK_NODE_ITEM && node->prev == NULL && entering)) {
     tmp = get_containing_block(node);
     renderer->in_tight_list_item =
-        (tmp->type == CMARK_NODE_ITEM &&
-         cmark_node_get_list_tight(tmp->parent)) ||
-        (tmp && tmp->parent && tmp->parent->type == CMARK_NODE_ITEM &&
-         cmark_node_get_list_tight(tmp->parent->parent));
+        tmp && // tmp might be NULL if there is no containing block
+        ((tmp->type == CMARK_NODE_ITEM &&
+          cmark_node_get_list_tight(tmp->parent)) ||
+         (tmp && tmp->parent && tmp->parent->type == CMARK_NODE_ITEM &&
+          cmark_node_get_list_tight(tmp->parent->parent)));
   }
 
   switch (node->type) {
@@ -187,15 +204,17 @@ static int S_render_node(cmark_renderer *renderer, cmark_node *node,
   case CMARK_NODE_LIST:
     if (!entering && node->next && (node->next->type == CMARK_NODE_CODE_BLOCK ||
                                     node->next->type == CMARK_NODE_LIST)) {
-      // this ensures 2 blank lines after list,
-      // if before code block or list:
-      LIT("\n");
+      // this ensures that a following code block or list will be
+      // inteprereted correctly.
+      CR();
+      LIT("<!-- end list -->");
+      BLANKLINE();
     }
     break;
 
   case CMARK_NODE_ITEM:
     if (cmark_node_get_list_type(node->parent) == CMARK_BULLET_LIST) {
-      marker_width = 2;
+      marker_width = 4;
     } else {
       list_number = cmark_node_get_list_start(node->parent);
       list_delim = cmark_node_get_list_delim(node->parent);
@@ -207,22 +226,21 @@ static int S_render_node(cmark_renderer *renderer, cmark_node *node,
       // we ensure a width of at least 4 so
       // we get nice transition from single digits
       // to double
-      sprintf(listmarker, "%d%s%s", list_number,
-              list_delim == CMARK_PAREN_DELIM ? ")" : ".",
-              list_number < 10 ? "  " : " ");
+      snprintf(listmarker, LISTMARKER_SIZE, "%d%s%s", list_number,
+               list_delim == CMARK_PAREN_DELIM ? ")" : ".",
+               list_number < 10 ? "  " : " ");
       marker_width = safe_strlen(listmarker);
     }
     if (entering) {
       if (cmark_node_get_list_type(node->parent) == CMARK_BULLET_LIST) {
-        LIT("* ");
+        LIT("  - ");
         renderer->begin_content = true;
-        cmark_strbuf_puts(renderer->prefix, "  ");
       } else {
         LIT(listmarker);
         renderer->begin_content = true;
-        for (i = marker_width; i--;) {
-          cmark_strbuf_putc(renderer->prefix, ' ');
-        }
+      }
+      for (i = marker_width; i--;) {
+        cmark_strbuf_putc(renderer->prefix, ' ');
       }
     } else {
       cmark_strbuf_truncate(renderer->prefix,
@@ -314,7 +332,7 @@ static int S_render_node(cmark_renderer *renderer, cmark_node *node,
 
   case CMARK_NODE_LINEBREAK:
     if (!(CMARK_OPT_HARDBREAKS & options)) {
-      LIT("\\");
+      LIT("  ");
     }
     CR();
     break;