@acristoffers/tree-sitter-matlab 1.2.4 → 1.2.13

package/README.md

@@ -60,38 +60,40 @@ Given the existence of external method definition, maybe that is even the
 correct thing to do, since we don't know if the current file is inside a
 special class folder.
 
-# Known problems
-
-Newlines, just like whitespaces, are mostly ignored. In the case of spaces, it
-allows `abs( a )` and `abs(a)` to be described by the same, simple rule. In the
-case of newlines, it allows many multiline constructs (like, `if`, `while`,
-`function`) to be expressed the same way.
+# Installation
 
-This creates the undesired side-effect that some constructs, which are not
-accepted by MATLAB, are correctly parsed, like:
+This parser is available in the following editors:
 
-```matlab
-function (
-  a
-)
-end
-```
+| Editor | Plugin              | Highlights | Folds | Indents | Code Format | Injections  | Locals |
+| :---   | :---                | :---       | :---  | :---    | :---        | :---        | :---   |
+| Emacs  | [Emacs-MATLAB-Mode] | ✔          | ✘     | ✔       | ✔           | ✔           | ✘      |
+| Helix  | Builtin             | ✔          | ✘     | ✔       | ✘           | ✘           | ✘      |
+| NeoVim | [nvim-treesitter]   | ✔          | ✔     | ✔       | ✘           | ✔           | ✔      |
 
-This, however, is hard to fix. The assumption that newlines are ignored by
-default is all over the grammar and changing it requires making changes to too
-many rules, which also make them all more complex and fragile. Therefore, this
-change won't be made.
+The columns have the following meaning:
 
-# Installation
+- *Highlights*: supports syntax highlight
+- *Folds*: supports code folding
+- *Indents*: supports code indenting, which adjusts the leftmost whitespace on each line.
+- *Code Format*: indent includes code formatting that standardizes the spacing of language elements
+  within code lines, aligns matrix columns, adds missing commas within cells and matrices, etc.
+- *Injections*: supports embedding the language into another language (i.e.: MATLAB code blocks inside
+  Markdown or [org-mode](https://orgmode.org/))
+- *Locals*: supports identifying variables/functions/etc scope
 
-This parser is now the default for the following editors:
+# Known issues
 
-- Emacs: Through the `tree-sitter-langs` package.
-- Helix: Builtin, now in master and will be available in the next release (whatever comes after 23.05).
-- Neovim: Through the `nvim-treesitter` plugin.
+- There is a conflict between numbers and element-wise operators that will
+  cause a wrong parse if there is no space between the number and the operator.
+  For example, `1./a` will be interpreted as `1. / a` instead of the correct
+  `1 ./ a`. This problem does not happen if there is a space between the number
+  and the operator.
 
 # Screenshots
 
 ![First Screenshot](https://raw.githubusercontent.com/acristoffers/tree-sitter-matlab/screenshots/s1.png)
 ![Second Screenshot](https://raw.githubusercontent.com/acristoffers/tree-sitter-matlab/screenshots/s2.png)
 ![Third Screenshot](https://raw.githubusercontent.com/acristoffers/tree-sitter-matlab/screenshots/s3.png)
+
+[Emacs-MATLAB-Mode]: https://github.com/mathworks/Emacs-MATLAB-Mode
+[nvim-treesitter]: https://github.com/nvim-treesitter/nvim-treesitter

package/grammar.js

@@ -44,6 +44,8 @@ module.exports = grammar({
     [$._index_row, $.row],
     [$.function_call, $._function_call_with_keywords],
     [$.block, $._functionless_block],
+    [$.function_definition, $._function_definition_with_end],
+    [$._function_definition_with_end],
   ],
 
   externals: ($) => [
@@ -71,9 +73,12 @@ module.exports = grammar({
 
   rules: {
     source_file: ($) =>
-      choice(
-        optional(seq($._block, repeat($.function_definition))),
-        repeat1($.function_definition),
+      seq(
+        repeat($._end_of_line),
+        choice(
+          optional(seq($._block, repeat($.function_definition))),
+          repeat1($.function_definition),
+        ),
       ),
 
     _block: ($) =>
@@ -235,6 +240,7 @@ module.exports = grammar({
             $.postfix_operator,
             $.string,
             $.unary_operator,
+            $.not_operator,
           ),
           ')',
         ),
@@ -261,7 +267,22 @@ module.exports = grammar({
         ),
       ),
 
-    not_operator: ($) => prec(PREC.not, seq('~', $._expression)),
+    not_operator: ($) => prec(PREC.not, seq('~', choice(
+      $.cell,
+      $.function_call,
+      $.handle_operator,
+      $.identifier,
+      $.matrix,
+      $.metaclass_operator,
+      $.not_operator,
+      $.number,
+      $.parenthesis,
+      $.postfix_operator,
+      $.range,
+      $.string,
+      $.unary_operator,
+      $.field_expression,
+    ))),
 
     metaclass_operator: ($) => prec.left(seq('?', seq($.identifier, repeat(seq('.', $.identifier))))),
 
@@ -344,15 +365,15 @@ module.exports = grammar({
     matrix: ($) =>
       seq(
         '[',
-        repeat("\n"),
-        optional(seq($.row, repeat(seq(choice(';', /[\r\n]/), optional($.row))))),
+        repeat(choice(/[,]*;[ ,;]*/, /[\r\n]/)),
+        optional(seq($.row, repeat(seq(choice(/[,]*;[ ,;]*/, /[\r\n]/), optional($.row))))),
         ']',
       ),
     cell: ($) =>
       seq(
         '{',
-        repeat("\n"),
-        optional(seq($.row, repeat(seq(choice(';', /[\r\n]/), optional($.row))))),
+        repeat(choice(/[,]*;[ ,;]*/, /[\r\n]/)),
+        optional(seq($.row, repeat(seq(choice(/[,]*;[ ,;]*/, /[\r\n]/), optional($.row))))),
         '}',
       ),
 
@@ -461,7 +482,7 @@ module.exports = grammar({
               alias($._index_unary_operator, $.unary_operator),
             ),
           ),
-          choice(".'", "'"),
+          choice(alias($._transpose, "'"), alias($._ctranspose, ".'")),
         ),
       ),
     _index_row: ($) =>
@@ -506,14 +527,20 @@ module.exports = grammar({
         ),
       ),
     _index_parenthesis: ($) => seq('(', $._index_expression, ')'),
+    // _index_expression is intentionally a superset of _expression to avoid
+    // conflicts like obj([1;end]) where the parser would otherwise reduce to
+    // a non-index matrix/row too early.
     _index_expression: ($) =>
       choice(
         alias($._index_boolean_operator, $.boolean_operator),
         $.field_expression,
         $.function_call,
+        $.handle_operator,
         $.identifier,
         $.cell,
+        $.lambda,
         alias($._index_matrix, $.matrix),
+        $.metaclass_operator,
         alias($._index_not_operator, $.not_operator),
         $.number,
         alias($._index_comparison_operator, $.comparison_operator),
@@ -569,7 +596,7 @@ module.exports = grammar({
         ),
       );
     },
-    _index_argument: ($) => choice($.spread_operator, choice(prec.dynamic(1, $._index_expression), prec.dynamic(-1, $._expression))),
+    _index_argument: ($) => choice($.spread_operator, $._index_expression),
     _index_arguments: ($) => commaSep1(field('argument', $._index_argument)),
 
     arguments: ($) =>
@@ -705,7 +732,7 @@ module.exports = grammar({
       ),
 
     iterator: ($) => seq($.identifier, '=', $._expression),
-    parfor_options: ($) => choice($.number, $.identifier, $.function_call, $.string),
+    parfor_options: ($) => choice($.number, $.identifier, $.field_expression, $.function_call, $.string),
     for_statement: ($) =>
       choice(
         seq(
@@ -786,7 +813,7 @@ module.exports = grammar({
         'arguments',
         optional(alias($._argument_attributes, $.attributes)),
         repeat1($._end_of_line),
-        repeat(choice($.property, seq($.class_property, repeat1($._end_of_line)))),
+        repeat(seq(choice($.property, $.class_property), repeat1($._end_of_line))),
         'end',
         optional($._end_of_line),
       )),
@@ -796,36 +823,39 @@ module.exports = grammar({
     function_arguments: ($) =>
       seq('(', field('arguments', optional($._lambda_arguments)), ')'),
     function_definition: ($) =>
-      prec.right(seq(
+      prec.dynamic(0, seq(
         'function',
         optional($.function_output),
         optional(choice('get.', 'set.')),
         field('name', choice($.identifier, $.property_name, alias($.end_keyword, $.identifier))),
         optional($.function_arguments),
         $._end_of_line,
-        repeat($.arguments_statement),
-        repeat($.comment),
-        repeat($._end_of_line),
+        repeat(seq(repeat(choice($.comment, $._end_of_line)), $.arguments_statement)),
+        repeat(choice($.comment, $._end_of_line)),
         optional(alias($._functionless_block, $.block)),
         optional(seq(choice('end', 'endfunction'), optional(';'))),
       )),
     _function_definition_with_end: ($) =>
-      prec.right(seq(
+      prec.dynamic(1, seq(
         'function',
         optional($.function_output),
         optional(choice('get.', 'set.')),
         field('name', choice($.identifier, $.property_name, alias($.end_keyword, $.identifier))),
         optional($.function_arguments),
-        $._end_of_line,
-        repeat($.arguments_statement),
-        repeat($.comment),
-        repeat($._end_of_line),
-        optional($.block),
+        optional(
+          seq(
+            $._end_of_line,
+            repeat(seq(repeat(choice($.comment, $._end_of_line)), $.arguments_statement)),
+            repeat(choice($.comment, $._end_of_line)),
+            optional($.block),
+          )
+        ),
         choice('end', 'endfunction'),
         optional(';'),
       )),
 
-    attribute: ($) => seq($.identifier, optional(seq('=', $._expression))),
+    _negated_attribute: ($) => seq("~", $.identifier),
+    attribute: ($) => choice(alias($._negated_attribute, $.not_operator), seq($.identifier, optional(seq('=', $._expression)))),
     attributes: ($) =>
       seq('(', $.attribute, repeat(seq(',', $.attribute)), ')'),
     superclasses: ($) =>
@@ -837,46 +867,44 @@ module.exports = grammar({
     default_value: ($) => seq('=', $._expression),
     property_name: ($) =>
       prec.right(
-        prec.dynamic(
-          -1,
-          seq(
-            $.identifier,
-            repeat(seq('.', $.identifier)),
-            optional(seq('.', '*')),
-          ),
+        -1,
+        seq(
+          $.identifier,
+          repeat(seq('.', $.identifier)),
+          optional(seq('.', '*')),
         ),
       ),
     property: ($) =>
-      choice(
-        seq(
-          field(
-            'name',
-            choice($.identifier, $.property_name, $.ignored_argument),
+      prec.right(
+        choice(
+          seq(
+            field(
+              'name',
+              choice($.identifier, $.property_name, $.ignored_argument),
+            ),
+            optional($.dimensions),
+            optional(choice($.identifier, $.property_name)),
+            optional($.validation_functions),
+            optional($.default_value),
           ),
-          optional($.dimensions),
-          optional(choice($.identifier, $.property_name)),
-          optional($.validation_functions),
-          optional($.default_value),
-          repeat1($._end_of_line),
+          seq(
+            field(
+              'name',
+              choice($.identifier, $.property_name, $.ignored_argument),
+            ),
+            '@',
+            $.identifier,
+            alias(optional(choice('vector', 'matrix', 'scalar')), $.identifier),
+            optional($.default_value),
+          )
         ),
-        seq(
-          field(
-            'name',
-            choice($.identifier, $.property_name, $.ignored_argument),
-          ),
-          '@',
-          $.identifier,
-          alias(optional(choice('vector', 'matrix', 'scalar')), $.identifier),
-          optional($.default_value),
-          repeat1($._end_of_line),
-        )
       ),
     properties: ($) =>
       seq(
         'properties',
         optional($.attributes),
-        repeat1($._end_of_line),
-        repeat($.property),
+        $._end_of_line,
+        repeat(choice(seq($.property, $._end_of_line), $._end_of_line, $.comment)),
         'end',
       ),
     function_signature: ($) =>
@@ -890,10 +918,11 @@ module.exports = grammar({
       seq(
         'methods',
         optional($.attributes),
-        repeat1($._end_of_line),
+        repeat($._end_of_line),
         repeat(
           seq(
             choice(
+              $.comment,
               alias(seq($.function_output, field('name', alias('end', $.identifier)), $.function_arguments), $.function_signature),
               $.function_signature,
               alias($._function_definition_with_end, $.function_definition)),
@@ -906,7 +935,7 @@ module.exports = grammar({
         'events',
         optional($.attributes),
         $._end_of_line,
-        repeat(choice(seq($.identifier, $._end_of_line), $._end_of_line)),
+        repeat(choice(seq($.identifier, $._end_of_line), $._end_of_line, $.comment)),
         'end',
       ),
     enum: ($) =>
@@ -916,7 +945,7 @@ module.exports = grammar({
         'enumeration',
         optional($.attributes),
         $._end_of_line,
-        repeat(choice(seq($.enum, $._end_of_line), $._end_of_line)),
+        repeat(choice(seq($.enum, $._end_of_line), $._end_of_line, $.comment)),
         'end',
       ),
     class_definition: ($) =>
@@ -926,7 +955,7 @@ module.exports = grammar({
         field('name', $.identifier),
         optional($.superclasses),
         $._end_of_line,
-        repeat(choice($.properties, $.methods, $.events, $.enumeration, ';')),
+        repeat(choice($.properties, $.methods, $.events, $.enumeration, $._end_of_line, $.comment)),
         'end',
       ),
 
@@ -957,8 +986,8 @@ module.exports = grammar({
 
     number: ($) => choice(
       /(\d+|\d+\.\d*|\.\d+)([eEdD][+-]?\d+)?[ij]?/,
-      /0[xX][\dA-Fa-f]+([su](8|16|32|64))?/,
-      /0[bB][01]+([su](8|16|32|64))?/
+      /0[xX][\dA-Fa-f]+([suSU](8|16|32|64))?/,
+      /0[bB][01]+([suSU](8|16|32|64))?/
     ),
 
     end_keyword: ($) => 'end',

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@acristoffers/tree-sitter-matlab",
-  "version": "1.2.4",
+  "version": "1.2.13",
   "description": "MATLAB tree-sitter parser",
   "keywords": [
     "incremental",