kistaro
39d77a8cae
Reorganize into grammars/<name>/ subdirs ( Zed's [grammars.*] supports a `path` field, so both grammars ship from this repo without a sibling- repo split ). Vendor tree-sitter-lua as the fork base for tree-sitter- pico8-lua; upstream MIT license preserved at grammars/pico-8-lua/ UPSTREAM-LICENSE.md. Dialect features added: != as ~= alias, \ integer divide, ^^ binary xor, >>> / <<> / >>< shifts and rotates, compound-assignment statements, memory peek prefixes @ % $ (% coexists with binary modulo), single-line `if (cond) stmt [else stmt]` and `while (cond) stmt`, statement-level print shorthand ?, and `#include path` directives. Identifier rule no longer accepts ! ? @ $ ( upstream did ). Pico-8 Lua language ( languages/pico-8-lua/, suffix .p8lua ) ships highlights with the full ~110 PICO-8 builtins as @function.builtin. The cart injection now hands __lua__ bodies to pico-8-lua, so .p8 carts and bare .p8lua files share the dialect-aware grammar. Examples updated to exercise the dialect end-to-end. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
75 lines
2.7 KiB
JavaScript
75 lines
2.7 KiB
JavaScript
/**
|
|
* tree-sitter grammar for the PICO-8 .p8 cartridge text format.
|
|
*
|
|
* The .p8 format is a flat text container divided into named sections
|
|
* delimited by lines of the form `__name__`. The first section is
|
|
* always `__lua__` and contains the cart's Lua source; the remaining
|
|
* sections (`__gfx__`, `__gff__`, `__label__`, `__map__`, `__sfx__`,
|
|
* `__music__`) hold hex-encoded asset data. The file begins with a
|
|
* fixed magic header line and a `version N` line.
|
|
*
|
|
* This grammar is intentionally minimal: it parses the section
|
|
* structure and exposes each section's body as a single named node
|
|
* so that injection queries (see languages/pico8-cart/injections.scm)
|
|
* can hand the contents off to other languages — most importantly
|
|
* Lua for the `__lua__` section.
|
|
*/
|
|
|
|
module.exports = grammar({
|
|
name: 'p8_cart',
|
|
|
|
// Whitespace is significant inside hex sections, so we don't skip it.
|
|
extras: $ => [],
|
|
|
|
rules: {
|
|
cartridge: $ => seq(
|
|
optional($.header),
|
|
optional($.version),
|
|
repeat($.section),
|
|
),
|
|
|
|
header: $ => /pico-8 cartridge \/\/[^\n]*\n/,
|
|
version: $ => /version[ \t]+\d+\n/,
|
|
|
|
section: $ => choice(
|
|
$.lua_section,
|
|
$.gfx_section,
|
|
$.gff_section,
|
|
$.label_section,
|
|
$.map_section,
|
|
$.sfx_section,
|
|
$.music_section,
|
|
$.unknown_section,
|
|
),
|
|
|
|
lua_section: $ => seq($.lua_marker, optional($.lua_content)),
|
|
gfx_section: $ => seq($.gfx_marker, optional($.body)),
|
|
gff_section: $ => seq($.gff_marker, optional($.body)),
|
|
label_section: $ => seq($.label_marker, optional($.body)),
|
|
map_section: $ => seq($.map_marker, optional($.body)),
|
|
sfx_section: $ => seq($.sfx_marker, optional($.body)),
|
|
music_section: $ => seq($.music_marker, optional($.body)),
|
|
unknown_section: $ => seq($.section_marker, optional($.body)),
|
|
|
|
lua_marker: $ => token(prec(2, '__lua__\n')),
|
|
gfx_marker: $ => token(prec(2, '__gfx__\n')),
|
|
gff_marker: $ => token(prec(2, '__gff__\n')),
|
|
label_marker: $ => token(prec(2, '__label__\n')),
|
|
map_marker: $ => token(prec(2, '__map__\n')),
|
|
sfx_marker: $ => token(prec(2, '__sfx__\n')),
|
|
music_marker: $ => token(prec(2, '__music__\n')),
|
|
section_marker: $ => token(prec(1, /__[a-z][a-z0-9_]*__\n/)),
|
|
|
|
lua_content: $ => repeat1($.line),
|
|
body: $ => repeat1($.line),
|
|
|
|
// A single physical line. The lexer prefers section markers over
|
|
// generic lines via the precedence above, so a line that happens
|
|
// to be exactly `__name__\n` will tokenize as a marker, not a line.
|
|
line: $ => choice(
|
|
token(prec(0, /[^\n]*\n/)),
|
|
token(prec(0, /[^\n]+/)), // final line with no trailing newline
|
|
),
|
|
},
|
|
});
|