Merge #162 feat: numbered listitems

Author: justinmk

README.md

@@ -14,24 +14,27 @@ Overview
 
 - `block` is the main top-level node, delimited by blank line(s) or any line
   starting with `<` (codeblock terminator).
-  - contains `line` and `line_li` nodes.
+  - Contains `line` and `line_li` nodes.
 - `line`:
-  - contains atoms (words, tags, taglinks, …)
-  - contains headings (`h1`, `h2`, `h3`, `column_heading`) because `codeblock`
+  - Contains atoms (words, tags, taglinks, …)
+  - Contains headings (`h1`, `h2`, `h3`, `column_heading`) because `codeblock`
     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.
-  - consumes lines until blank line, codeblock, or next listitem.
-  - nesting is ignored: indented listitems are parsed as siblings.
+  - 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.
 - `codeblock`:
-  - contained by `line` or `line_li`, because ">" can start a codeblock at the
+  - Contained by `line` or `line_li`, because ">" can start a codeblock at the
     end of any line.
-  - contains `line` nodes without `word` nodes: it's just the full raw text
+  - Contains `line` nodes without `word` nodes: it's just the full raw text
     line including whitespace. This is somewhat dictated by its "preformatted"
     nature; parsing the contents would require loading a "child" language
     (injection). See [#2](https://github.com/neovim/tree-sitter-vimdoc/issues/2).
-  - the terminating `<` (and any following whitespace) is discarded (anonymous).
+  - The terminating `<` (and any following whitespace) is discarded (anonymous).
 - `url` intentionally does not capture `.,)` at the end of the URL. See also [Known issues](#known-issues).
 - `h1` = "Heading 1": `======` followed by text and optional `*tags*`.
 - `h2` = "Heading 2": `------` followed by text and optional `*tags*`.
@@ -43,6 +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

@@ -13,7 +13,8 @@
 // @ts-check
 
 const _uppercase_word = /[A-Z0-9.()][-A-Z0-9.()_]+/;
-const _li_token = /[-•][ ]+/;
+// Listitem (incl. numbered items).
+const _li_token = /([-•]|([0-9]{1,3}\.))[ ]+/;
 
 module.exports = grammar({
   name: 'vimdoc',
@@ -49,9 +50,10 @@ module.exports = grammar({
       alias($.word_noli, $.word),
       $._atom_common,
     ),
+    // Word NOT matching (numbered) listitem.
     word_noli: ($) => choice(
-      // Lines contained by line_li must not start with a listitem symbol.
-      token(prec(-1, /[^-•\n\t ][^(\[\n\t ]*/)),
+      // Lines contained by line_li must not start with (numbered) listitem symbol.
+      token(prec(-1, /(([^-•\n\t ])|([^0-9\n\t ][^.\n\t ]))[^.(\[\n\t ]*/)),
       token(prec(-1, /[-•][^\n\t ]+/)),
       $._word_common,
     ),
@@ -164,7 +166,7 @@ module.exports = grammar({
     // Listitem: consumes prefixed line and all adjacent non-prefixed lines.
     line_li: ($) => prec.right(1, seq(
       optional(token.immediate('<')),  // Treat codeblock-terminating "<" as whitespace.
-      _li_token,
+      alias(_li_token, $.prefix),
       choice(
         alias(seq(repeat1($._atom), /\n/), $.line),
         seq(alias(repeat1($._atom), $.line), $.codeblock),