feat: numbered listitems

- Capture numbered listiems in the existing `line_li` form.
- Introduce `prefix` capture so that consumers can check if a listitem
  is ordered (numbered) or unordered.

Author: justinmk

README.md

@@ -21,7 +21,9 @@ Overview
     terminated by "implicit stop" (no terminating `<`) consumes blank lines, so
     `block` has no way to end.
 - `line_li` ("listitem")
-  - Lines starting with `-`/`•` (_not_ `+`/`*`) are listitems.
+  - Lines starting with `-`/`•`/`[0-9].` (_not_ `+`/`*`) are listitems.
+  - Use the `prefix` node to detect if the listitem is ordered (numbered) or
+    unodered.
   - Consumes lines until blank line, codeblock, or next listitem.
   - Nesting is ignored: indented listitems are parsed as siblings. Consumers can
     check leading whitespace to decide nesting.
@@ -44,6 +46,12 @@ Known issues
 
 - Input must end with newline/EOL (`\n`). Grammar does not support files without EOL.
 - Input must end with a blank line. Though this doesn't seem to matter in practice.
+- Any line starting with `1.` (or other number) is treated as a listitem, even
+  if the first line of its `block` is not a listitem. Example:
+  ```
+  Foo was 0, not
+  1. Uh oh.
+  ```
 - Spec requires that `codeblock` delimiter ">" must be preceded by a space
   (" >"), not a tab. But currently the grammar doesn't enforce this. Example:
   `:help lcs-tab`.

grammar.js

@@ -13,10 +13,8 @@
 // @ts-check
 
 const _uppercase_word = /[A-Z0-9.()][-A-Z0-9.()_]+/;
-// List-item.
-const _li_token = /[-•][ ]+/;
-// Numbered list-item.
-const _num_li_token = /[0-9]{1,3}\.[ ]+/;
+// Listitem (incl. numbered items).
+const _li_token = /([-•]|([0-9]{1,3}\.))[ ]+/;
 
 module.exports = grammar({
   name: 'vimdoc',
@@ -136,8 +134,7 @@ module.exports = grammar({
       choice(
         repeat1($.line),
         repeat1($.line_li),
-        repeat1($.line_li_num),
-        seq(repeat1($.line), repeat1(choice($.line_li, $.line_li_num))),
+        seq(repeat1($.line), repeat1($.line_li)),
       ),
       choice(
         token.immediate('<'),  // Treat codeblock-terminating "<" as whitespace.
@@ -169,17 +166,7 @@ module.exports = grammar({
     // Listitem: consumes prefixed line and all adjacent non-prefixed lines.
     line_li: ($) => prec.right(1, seq(
       optional(token.immediate('<')),  // Treat codeblock-terminating "<" as whitespace.
-      _li_token,
-      choice(
-        alias(seq(repeat1($._atom), /\n/), $.line),
-        seq(alias(repeat1($._atom), $.line), $.codeblock),
-      ),
-      repeat(alias($._line_noli, $.line)),
-    )),
-    // Numbered listitem: consumes prefixed line and all adjacent non-prefixed lines.
-    line_li_num: ($) => prec.right(1, seq(
-      optional(token.immediate('<')),  // Treat codeblock-terminating "<" as whitespace.
-      _num_li_token,
+      alias(_li_token, $.prefix),
       choice(
         alias(seq(repeat1($._atom), /\n/), $.line),
         seq(alias(repeat1($._atom), $.line), $.codeblock),

test/corpus/heading3-column_heading.txt

@@ -224,34 +224,38 @@ ABC not-h3
       (word)
       (word)))
   (block
-    (line
-      (word)
-      (optionlink
-        (word))
-      (codespan
-        (word))
-      (word)
-      (word))
-    (line
-      (codespan
+    (line_li
+      (prefix)
+      (line
+        (optionlink
+          (word))
+        (codespan
+          (word))
+        (word)
         (word))
-      (word)
-      (word))
-    (line
-      (word)
-      (word)
-      (word)
-      (word)
-      (word))
-    (line
-      (word)
-      (word)
-      (word)
-      (codespan
+      (line)
+      (line
+        (codespan
+          (word))
+        (word)
+        (word)))
+    (line_li
+      (prefix)
+      (line
+        (word)
+        (word)
+        (word)
         (word))
-      (word)
-      (word)
-      (word))))
+      (line)
+      (line
+        (word)
+        (word)
+        (word)
+        (codespan
+          (word))
+        (word)
+        (word)
+        (word)))))
 
 ================================================================================
 NOT column_heading