Add new grammars and improve demo

- Add PHP, XML, AWK, Batch, JQ, VB.NET, and F# grammars
- Restructure PHP and XML from monorepo to flat structure
- Fix AWK scanner (remove debug printf incompatible with wasm-sysroot)
- Fix F# scanner (inline common/scanner.h)
- Improve demo: merge source/output panels, add gzip compression
- Switch from zopfli to flate2 for faster gzip compression
- Run xtask in release mode

Author: fasterthanlime

.cargo/config.toml

@@ -1,2 +1,2 @@
 [alias]
-xtask = "run --package xtask --"
+xtask = "run --release --package xtask --"

.gitignore

@@ -32,3 +32,7 @@ node_modules/
 /tree-sitter-zig/
 /tree-sitter/
 /wasm-sysroot/
+
+# Pre-compressed demo files
+demo/*.br
+demo/*.gz

Cargo.lock

@@ -5,7 +5,9 @@ members = [
     "crates/arborium-ada",
     "crates/arborium-agda",
     "crates/arborium-asm",
+    "crates/arborium-awk",
     "crates/arborium-bash",
+    "crates/arborium-batch",
     "crates/arborium-c",
     "crates/arborium-c-sharp",
     "crates/arborium-caddy",
@@ -26,6 +28,7 @@ members = [
     "crates/arborium-elm",
     "crates/arborium-erlang",
     "crates/arborium-fish",
+    "crates/arborium-fsharp",
     "crates/arborium-gleam",
     "crates/arborium-glsl",
     "crates/arborium-go",
@@ -40,6 +43,7 @@ members = [
     "crates/arborium-java",
     "crates/arborium-javascript",
     "crates/arborium-jinja2",
+    "crates/arborium-jq",
     "crates/arborium-json",
     "crates/arborium-julia",
     "crates/arborium-kdl",
@@ -52,6 +56,7 @@ members = [
     "crates/arborium-nix",
     "crates/arborium-objc",
     "crates/arborium-perl",
+    "crates/arborium-php",
     "crates/arborium-python",
     "crates/arborium-query",
     "crates/arborium-r",
@@ -70,10 +75,12 @@ members = [
     "crates/arborium-toml",
     "crates/arborium-typst",
     "crates/arborium-uiua",
+    "crates/arborium-vb",
     "crates/arborium-verilog",
     "crates/arborium-vim",
     "crates/arborium-vue",
     "crates/arborium-x86asm",
+    "crates/arborium-xml",
     "crates/arborium-yaml",
     "crates/arborium-zig",
     "crates/arborium-zsh",
@@ -89,3 +96,11 @@ version = "0.1.0"
 edition = "2024"
 license = "MIT OR Apache-2.0"
 repository = "https://github.com/bearcove/arborium"
+
+# Optimize for size in release builds (especially important for WASM)
+[profile.release]
+opt-level = "z"
+lto = true
+codegen-units = 1
+panic = "abort"
+strip = true

Cargo.toml

@@ -64,6 +64,12 @@ repo = "https://github.com/elm-tooling/tree-sitter-elm"
 commit = "d0bec479c0422ed5eb01467790bd3912142fe987"
 license = "MIT"
 
+[fsharp]
+repo = "https://github.com/ionide/tree-sitter-fsharp"
+commit = "5141851c278a99958469eb1736c7afc4ec738e47"
+license = "MIT"
+# Note: This grammar has a subdirectory structure - using fsharp subdirectory
+
 [gleam]
 repo = "https://github.com/gleam-lang/tree-sitter-gleam"
 commit = "f4d55f3c5b690d4afe8853da892bc290d96deb34"
@@ -286,3 +292,33 @@ license = "MIT"
 repo = "https://github.com/tree-sitter-grammars/tree-sitter-capnp"
 commit = "7b0883c03e5edd34ef7bcf703194204299d7099f"
 license = "MIT"
+
+[php]
+repo = "https://github.com/tree-sitter/tree-sitter-php"
+commit = "7d07b41ce2d442ca9a90ed85d0075eccc17ae315"
+license = "MIT"
+
+[xml]
+repo = "https://github.com/tree-sitter-grammars/tree-sitter-xml"
+commit = "863dbc381f44f6c136a399e684383b977bb2beaa"
+license = "MIT"
+
+[awk]
+repo = "https://github.com/Beaglefoot/tree-sitter-awk"
+commit = "34bbdc7cce8e803096f47b625979e34c1be38127"
+license = "MIT"
+
+[batch]
+repo = "https://github.com/davidevofficial/tree-sitter-batch"
+commit = "737a031b42240bf61bf7ea5e4356d4e0580dd6d9"
+license = "MIT"
+
+[jq]
+repo = "https://github.com/flurie/tree-sitter-jq"
+commit = "c204e36d2c3c6fce1f57950b12cabcc24e5cc4d9"
+license = "MIT"
+
+[vb]
+repo = "https://github.com/CodeAnt-AI/tree-sitter-vb-dotnet"
+commit = "cfca210ce8fdcb5245bd9cd5c47ce0a21a8488d5"
+license = "MIT"

GRAMMARS.toml

@@ -0,0 +1,19 @@
+[package]
+name = "arborium-awk"
+version = "0.1.0"
+edition = "2024"
+description = "awk grammar for arborium (tree-sitter bindings)"
+license = "MIT"
+repository = "https://github.com/bearcove/arborium"
+keywords = ["tree-sitter", "awk", "syntax-highlighting"]
+categories = ["parsing", "text-processing"]
+
+[lib]
+path = "src/lib.rs"
+
+[dependencies]
+tree-sitter-patched-arborium = { version = "0.25.10", path = "../../tree-sitter" }
+arborium = { version = "0.1.0", path = "../arborium" }
+
+[build-dependencies]
+cc = { version = "1", features = ["parallel"] }

crates/arborium-awk/Cargo.toml

@@ -0,0 +1,26 @@
+fn main() {
+    let src_dir = "../../tree-sitter-awk/src";
+
+    println!("cargo:rerun-if-changed={}/parser.c", src_dir);
+    println!("cargo:rerun-if-changed={}/scanner.c", src_dir);
+
+    let mut build = cc::Build::new();
+
+    build
+        .include(src_dir)
+        .include(format!("{}/tree_sitter", src_dir))
+        .warnings(false)
+        .flag_if_supported("-Wno-unused-parameter")
+        .flag_if_supported("-Wno-unused-but-set-variable")
+        .flag_if_supported("-Wno-trigraphs");
+
+    // For WASM builds, use our custom sysroot (provided by arborium crate via links = "arborium")
+    if let Ok(sysroot) = std::env::var("DEP_ARBORIUM_WASM_SYSROOT") {
+        build.include(&sysroot);
+    }
+
+    build.file(format!("{}/parser.c", src_dir));
+    build.file(format!("{}/scanner.c", src_dir));
+
+    build.compile("tree_sitter_awk");
+}