Update to CommonMark v0.31.2

Author: lexi-lambda

commonmark-doc/scribblings/commonmark.scrbl

@@ -43,7 +43,7 @@
                                  values))
    (apply hyperlink
           #:style style
-          (~a "https://spec.commonmark.org/0.30/#"
+          (~a "https://spec.commonmark.org/0.31.2/#"
               (~> (string-foldcase tag)
                   maybe-singularize
                   (string-replace #px"[^a-z]+" "-")))
@@ -70,7 +70,7 @@
 
 @defmodule[commonmark]{
 
-The @racketmodname[commonmark] library implements a @|CommonMark|-compliant Markdown parser. Currently, it passes all test cases in @hyperlink["https://spec.commonmark.org/0.30/"]{v0.30 of the specification}. By default, only the Markdown features specified by @CommonMark are supported, but non-standard support for @tech{footnotes} can be optionally enabled; see the @secref{extensions} section of this manual for more details.
+The @racketmodname[commonmark] library implements a @|CommonMark|-compliant Markdown parser. Currently, it passes all test cases in @hyperlink["https://spec.commonmark.org/0.31.2/"]{v0.31.2 of the specification}. By default, only the Markdown features specified by @CommonMark are supported, but non-standard support for @tech{footnotes} can be optionally enabled; see the @secref{extensions} section of this manual for more details.
 
 The @racketmodname[commonmark] module reprovides all of the bindings provided by @racketmodname[commonmark/parse] and @racketmodname[commonmark/render/html] (but @emph{not} the bindings provided by @racketmodname[commonmark/struct]).}
 

commonmark-lib/commonmark/private/parse/block.rkt

@@ -26,7 +26,7 @@
                                        (:* "\\1[ \t]*" #:min 2)
                                        :eol))
 
-;; <https://spec.commonmark.org/0.30/#list-marker>
+;; <https://spec.commonmark.org/0.31.2/#list-marker>
 (define-for-syntax (:list-marker #:interrupt? interrupt?)
   ; If the list is ordered, it can only interrupt a paragraph if the
   ; start number is 1.
@@ -330,7 +330,7 @@
           (set! partially-consumed-tab? #f)
           (list* full-match indent group-matches)]))))
 
-  ;; <https://spec.commonmark.org/0.30/#block-quote-marker>
+  ;; <https://spec.commonmark.org/0.31.2/#block-quote-marker>
   (define (try-read-blockquote-marker)
     (try-with-optional-indent
      (λ (pos indent)
@@ -355,7 +355,7 @@
           #t]
          [_ #f]))))
 
-  ;; <https://spec.commonmark.org/0.30/#list-marker>
+  ;; <https://spec.commonmark.org/0.31.2/#list-marker>
   (define (try-read-list-marker #:interrupt? interrupt?)
     (try-with-optional-indent
      (λ (pos indent)
@@ -545,7 +545,7 @@
                                          "h3" "h4" "h5" "h6" "head" "header" "hr" "html"
                                          "iframe" "legend" "li" "link" "main" "menu"
                                          "menuitem" "nav" "noframes" "ol" "optgroup"
-                                         "option" "p" "param" "section" "source"
+                                         "option" "p" "param" "search" "section"
                                          "summary" "table" "tbody" "td" "tfoot" "th"
                                          "thead" "title" "tr" "track" "ul"))
                           (:or "[ \t>]" :eol "/>"))))))
@@ -998,7 +998,7 @@ of the list item. |#
 ;; Link reference definitions
 
 ;; § 4.7 Link reference definitions
-;; <https://spec.commonmark.org/0.30/#link-reference-definition>
+;; <https://spec.commonmark.org/0.31.2/#link-reference-definition>
 (define (try-read-link-reference-definition in)
   (define (try-peek-eol start-pos)
     (match (regexp-match-peek-positions (px "^" "[ \t\r\n]*" :eol) in start-pos)

commonmark-lib/commonmark/private/parse/common.rkt

@@ -33,11 +33,11 @@
 ;; § 2.1 Characters and lines
 
 (begin-for-syntax
-  ; <https://spec.commonmark.org/0.30/#line-ending>
+  ; <https://spec.commonmark.org/0.31.2/#line-ending>
   (define :newline (:: "\n|\r\n?"))
-  ; <https://spec.commonmark.org/0.30/#ascii-punctuation-character>
+  ; <https://spec.commonmark.org/0.31.2/#ascii-punctuation-character>
   (define :ascii-punctuation "[!-/:-@[-`{-~]")
-  ; <https://spec.commonmark.org/0.30/#ascii-control-character>
+  ; <https://spec.commonmark.org/0.31.2/#ascii-control-character>
   (define :ascii-control: "\0-\x1F\x7F")
 
   ; Often referred to in the spec using the phrase “spaces, tabs, and up to one
@@ -47,12 +47,12 @@
   (define :space* (:* "[" :space: "]"))
   (define :space+ (:+ "[" :space: "]"))
 
-  ; <https://spec.commonmark.org/0.30/#link-destination>
+  ; <https://spec.commonmark.org/0.31.2/#link-destination>
   (define :link-destination
     (:or "<([^\r\n]*?)(?<!\\\\)>"
          (:group "[^< " :ascii-control: "]")))
 
-  ;; § 6.5 Raw HTML <https://spec.commonmark.org/0.30/#raw-html>
+  ;; § 6.5 Raw HTML <https://spec.commonmark.org/0.31.2/#raw-html>
   (define (:html-open-close #:allow-newlines? allow-newlines?)
     (define-values [:sp: :sp* :sp+ :nl:]
       (if allow-newlines?
@@ -86,8 +86,8 @@
       (char<=? #\{ c #\~)))
 
 (define (unicode-punctuation? c)
-  (or (ascii-punctuation? c)
-      (memq (char-general-category c) '(pc pd pe pf pi po ps))))
+  (or (char-punctuation? c)
+      (char-symbolic? c)))
 
 ;; -----------------------------------------------------------------------------
 
@@ -106,21 +106,21 @@
                                 "\\]")
                             in start-pos)
     [(list peeked-bytes (app bytes->string/utf-8 label-str))
-     ; From <https://spec.commonmark.org/0.30/#link-label>:
+     ; From <https://spec.commonmark.org/0.31.2/#link-label>:
      ;   “Between these brackets there must be at least one character that is
      ;    not a space, tab, or line ending.”
      #:when (regexp-match? (px "[^" :space: "]") label-str)
      (list (+ start-pos (bytes-length peeked-bytes))
            (normalize-link-label label-str))]
     [_ #f]))
 
-;; <https://spec.commonmark.org/0.30/#matches>
+;; <https://spec.commonmark.org/0.31.2/#matches>
 (define (normalize-link-label str)
   (~> (string-foldcase str)
       (string-trim (px :space+))
       (string-replace (px :space+) " ")))
 
-;; <https://spec.commonmark.org/0.30/#link-destination>
+;; <https://spec.commonmark.org/0.31.2/#link-destination>
 (define (try-peek-link-destination in [start-pos 0])
   (match (regexp-match-peek #px"^<([^\r\n]*?)(?<!\\\\)>" in start-pos)
     ; First, the simple case: a destination enclosed in <angle brackets>.

commonmark-lib/commonmark/private/parse/inline.rkt

@@ -29,10 +29,10 @@
   ;; § 6.5 Raw HTML
   (define :html-tag
     (let ()
-      (define :comment (:: "<!--" "(?!>|->)" (:* (:or "[^-]" "-[^-]")) "-->"))
-      (define :instruction (:: "<\\?" (:* (:or "[^?]" "\\?[^>]")) "\\?>"))
+      (define :comment (:: "<!--" (:or ">" "->" (:: (:*? ".") "-->"))))
+      (define :instruction (:: "<\\?" (:*? ".") "\\?>"))
       (define :declaration (:: "<!" "[a-zA-Z]" "[^>]*" ">"))
-      (define :cdata-section (:: "<!\\[CDATA\\[" (:* (:or "[^]]" "\\][^]]" "\\]\\][^>]")) "\\]\\]>"))
+      (define :cdata-section (:: "<!\\[CDATA\\[" (:*? ".") "\\]\\]>"))
 
       (:or (:html-open-close #:allow-newlines? #t) :comment :instruction :declaration :cdata-section))))
 
@@ -312,15 +312,15 @@ positions in characters rather than bytes, which explains why we need to call
 
   (define (try-read-link-target content-label-str)
     (or
-     ;; Full reference links <https://spec.commonmark.org/0.30/#reference-link>
+     ;; Full reference links <https://spec.commonmark.org/0.31.2/#reference-link>
      (match-and*
       [(try-peek-link-label in) => (list label-pos label-str)]
       [(hash-ref link-reference-defns label-str #f)
        => link-ref
        (read-bytes label-pos in)
        link-ref])
 
-     ;; Inline links <https://spec.commonmark.org/0.30/#inline-link>
+     ;; Inline links <https://spec.commonmark.org/0.31.2/#inline-link>
      (let ()
        (define (try-peek-end start-pos)
          (match-and*
@@ -370,8 +370,8 @@ positions in characters rather than bytes, which explains why we need to call
      (let ()
        (define normalized-label (normalize-link-label content-label-str))
        (or
-        ;; Collapsed reference links <https://spec.commonmark.org/0.30/#collapsed-reference-link>,
-        ;;   and shortcut reference links <https://spec.commonmark.org/0.30/#shortcut-reference-link>
+        ;; Collapsed reference links <https://spec.commonmark.org/0.31.2/#collapsed-reference-link>,
+        ;;   and shortcut reference links <https://spec.commonmark.org/0.31.2/#shortcut-reference-link>
         (match-and*
          [(hash-ref link-reference-defns normalized-label #f) => link-ref]
          [(or (regexp-try-match #px"^\\[\\]" in)