Lua highlighting

content/programming/projects/muscript.tree

@@ -261,7 +261,7 @@
                     - I don't know if I'll ever optimize this to be even more efficient than it
                     already is, but source ranges are mostly irrelevant to the high level task of
                     matching tokens, so maybe arranging the storage like
-                    ```rs
+                    ```rust
                     struct Tokens {
                         kinds: Vec<TokenKind>,
                         source_ranges: Vec<Range<usize>>,

content/treehouse/dev/syntax-highlighting.tree

@@ -132,3 +132,64 @@
         }
     }
     ```
+
+- `lua`
+
+    - patterns
+    ```lua
+    -- single-line comment
+    --[[
+        multi-line comment
+        NOTE: comments with [==[ ]==] are not supported due to a lack of backreference support
+              in Rust regex
+    ]]
+
+    'string' "string" [[multiline
+    string]]
+    0xABCD 0xA.B 0xAp+3 0xCE.DE5p-2
+    123 1.0 1.41e-3 1.42E+4 1.43e1
+    <bye_egg>
+    ...
+    + - * / % ^ == ~= <= >= #
+    funciton() ident
+    ```
+
+    - keywords
+    ```lua
+    if then else elseif end do function repeat until while for break return local in not and or goto
+    self
+    true false nil
+    <close> <const>
+    ```
+
+    - sample
+    ```lua
+    -- Ticks the scheduler: executes every active fiber, removes inactive fibers,
+    -- and ignores sleeping fibers.
+    --
+    -- Extra arguments passed to this function are passed to all running fibers.
+    function Scheduler:tick(...)
+        local time = timer.getTime()
+        local i = 1
+        while i <= #self.fibers do
+            local fiber = self.fibers[i]
+            local coro = fiber.coro
+            if time >= fiber.wakeAt then
+                local ok, result = coroutine.resume(coro, ...)
+                if not ok then
+                    error("scheduler for '"..self.name.."': "..
+                        "ticking '"..fiber.name.."' failed with an error\n"..result)
+                else
+                    if coroutine.status(coro) == "dead" then
+                        self.fibers[i] = self.fibers[#self.fibers]
+                        self.fibers[#self.fibers] = nil
+                        i = i - 1
+                    elseif result ~= nil and result > 0 then
+                        fiber.wakeAt = time + result
+                    end
+                end
+            end
+            i = i + 1
+        end
+    end
+    ```

crates/treehouse/src/html/highlight/tokenize.rs

@@ -51,6 +51,11 @@ impl CompiledSyntax {
                                 );
                                 last_match_end = capture.range().end;
                             }
+                            push_token(
+                                &mut tokens,
+                                types.default,
+                                i + last_match_end..i + whole_match.range().end,
+                            );
                             i += whole_match.range().end;
                             had_match = true;
                             break;

static/syntax/lua.json

@@ -0,0 +1,74 @@
+{
+    "patterns": [
+        {
+            "regex": "--\\[\\[.*?\\]\\]",
+            "flags": ["dotMatchesNewline"],
+            "is": "comment"
+        },
+        { "regex": "--.*", "is": "comment" },
+        { "regex": "'(\\\\'|[^'])*'", "is": "string" },
+        { "regex": "\"(\\\\\"|[^\"])*\"", "is": "string" },
+        {
+            "regex": "\\[\\[.+?\\]\\]",
+            "flags": ["dotMatchesNewline"],
+            "is": "string"
+        },
+        {
+            "regex": "0[xX][0-9a-fA-F]+(\\.[0-9a-fA-F]*)?([pP][-+]?[0-9]+)?",
+            "is": "literal"
+        },
+        { "regex": "0[xX]\\.[0-9a-fA-F]+([pP][-+]?[0-9]+)?", "is": "literal" },
+        { "regex": "[0-9_]+(\\.[0-9_]*([eE][-+]?[0-9_]+)?)?", "is": "literal" },
+        {
+            "regex": "<([a-zA-Z_][a-zA-Z0-9_]*)>",
+            "is": {
+                "default": "punct",
+                "captures": ["error error-attribute"]
+            }
+        },
+        { "regex": "\\.\\.\\.", "is": "punct" },
+        { "regex": "[+=/*^%#<>~.-]+", "is": "operator" },
+        {
+            "regex": "([a-zA-Z_][a-zA-Z0-9_]*)\\(",
+            "is": {
+                "default": "default",
+                "captures": ["function"]
+            }
+        },
+        { "regex": "[a-zA-Z_][a-zA-Z0-9_]*", "is": "identifier" }
+    ],
+    "keywords": {
+        "if": { "into": "keyword1" },
+        "then": { "into": "keyword1" },
+        "else": { "into": "keyword1" },
+        "elseif": { "into": "keyword1" },
+        "end": { "into": "keyword1" },
+        "do": { "into": "keyword1" },
+        "function": { "into": "keyword1" },
+        "repeat": { "into": "keyword1" },
+        "until": { "into": "keyword1" },
+        "while": { "into": "keyword1" },
+        "for": { "into": "keyword1" },
+        "break": { "into": "keyword1" },
+        "return": { "into": "keyword1" },
+        "local": { "into": "keyword1" },
+        "in": { "into": "keyword1" },
+        "not": { "into": "keyword1" },
+        "and": { "into": "keyword1" },
+        "or": { "into": "keyword1" },
+        "goto": { "into": "keyword1" },
+        "self": { "into": "keyword2" },
+        "true": { "into": "literal" },
+        "false": { "into": "literal" },
+        "nil": { "into": "literal" },
+
+        "close": {
+            "into": "keyword1",
+            "onlyReplaces": "error error-attribute"
+        },
+        "const": {
+            "into": "keyword1",
+            "onlyReplaces": "error error-attribute"
+        }
+    }
+}