Bring parser up to date with language changes in Zeek

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @bbannier

.github/dependabot.yml

@@ -0,0 +1,14 @@
+version: 2
+updates:
+  - package-ecosystem: "cargo" # See documentation for possible values
+    directory: "/"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "npm" # See documentation for possible values
+    directory: "/vscode"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "github-actions" # See documentation for possible values
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/workflows/test.yaml

@@ -1,59 +1,26 @@
-name: Build and tests
+name: Check
 
 on:
   pull_request:
   push:
     branches: [main]
-    tags:
-  schedule:
-    - cron: '0 0 * * *'
 
 jobs:
-  tests:
-    name: "Build and run parser tests"
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest, macos-latest]
-      fail-fast: false
+  test:
+    runs-on: ubuntu-latest
     steps:
-      - name: Checkout parser sources
-        uses: actions/checkout@v2
-
-      - name: Checkout Zeek sources
-        uses: actions/checkout@v2
-        with:
-          repository: zeek/zeek
-          path: test/zeek-src
-
-      - uses: actions/setup-node@v2
-        with:
-          node-version: '14'
-
-      - run: npm install
-
-      - name: Add Node.js to PATH
-        run: echo "$PWD/node_modules/.bin" >> $GITHUB_PATH
-
-      - name: Setup tree-sitter
-        # "tree-sitter init-config" adds $HOME/github as a default
-        # directory to look for languages in, so we create a symlink
-        # that directs it to our local clone.
-        run: |
-          ln -s $(cd .. && pwd) $HOME/github
-          tree-sitter init-config
-
-      - name: Generate parser
-        run: tree-sitter generate
-
-      - name: Test Zeek grammar
-        run: cd test && ./parse-zeek-tree.sh ./zeek-src/scripts
-
-      - name: Upload test artifacts
-        uses: actions/upload-artifact@v2
-        if: failure()
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
         with:
-          name: parser-errors
-          path: |
-            *.zeek
-            *.err
+          node-version: latest
+      - run: |
+          npm ci
+      - run: |
+          npm test
+
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+      - uses: pre-commit/[email protected]

.gitignore

@@ -1,4 +1 @@
 Cargo.toml
-binding.gyp
-bindings
-src

.gitmodules

@@ -1,3 +0,0 @@
-[submodule "src"]
-	path = src
-	url = https://github.com/ckreibich/tree-sitter-zeek-src

.pre-commit-config.yaml

@@ -0,0 +1,16 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v4.0.0-alpha.8
+    hooks:
+      - id: prettier
+
+exclude: ^(src|bindings)

README.md

@@ -0,0 +1,41 @@
+# tree-sitter-zeek
+
+[![Tests](https://github.com/zeek/tree-sitter-zeek/actions/workflows/test.yaml/badge.svg)](https://github.com/zeek/tree-sitter-zeek/actions/workflows/test.yaml)
+
+A [Zeek](https://zeek.org) grammar for [tree-sitter](https://github.com/tree-sitter/tree-sitter).
+
+## Background
+
+This grammar parses scripts written in the [Zeek scripting
+language](https://docs.zeek.org/en/master/script-reference/index.html).
+
+The goal of this grammar is to facilitate tooling around Zeek
+scripts. For that reason, its structure resembles Zeek's grammar but differs in
+a number of ways. For example, it tracks newlines explicitly and relies more
+strongly on precedence and associativity to resolve ambiguities. Like Zeek's
+parser, this one currently doesn't name symbols deeply: for example, the grammar
+features an `expr` rule that covers any kind of expression, but the choices
+aren't currently broken down into, say, `addition_expr`, `or_expr`, and
+similars.
+
+## Usage
+
+To use the generated parser directly (e.g. via any of tree-sitter's
+[language bindings](https://tree-sitter.github.io/tree-sitter/#language-bindings)),
+clone this repository recursively. We maintain a separate
+[git repository](https://github.com/zeek/tree-sitter-zeek-src)
+to track generated sources. You do not need the tree-sitter CLI
+to use those sources in your tooling, but you'll likely want it
+anyway to explore the parser. For example, `tree-sitter parse <script>`
+produces the script's syntax tree, and `tree-sitter highlight <script>`
+shows syntax-highlighted sources.
+
+## Building the parser
+
+- Install [tree-sitter](https://tree-sitter.github.io/tree-sitter/creating-parsers#installation) on your machine.
+- Generate the parser: run `tree-sitter generate`.
+
+## Testing
+
+There's currently no `tree-sitter test` testsuite. Instead, a test driver
+clones the Zeek repository and runs on every Zeek script in the distribution.

binding.gyp

@@ -0,0 +1,19 @@
+{
+  "targets": [
+    {
+      "target_name": "tree_sitter_zeek_binding",
+      "include_dirs": [
+        "<!(node -e \"require('nan')\")",
+        "src"
+      ],
+      "sources": [
+        "bindings/node/binding.cc",
+        "src/parser.c",
+        # If your language uses an external scanner, add it here.
+      ],
+      "cflags_c": [
+        "-std=c99",
+      ]
+    }
+  ]
+}

bindings/node/binding.cc

@@ -0,0 +1,28 @@
+#include "tree_sitter/parser.h"
+#include <node.h>
+#include "nan.h"
+
+using namespace v8;
+
+extern "C" TSLanguage * tree_sitter_zeek();
+
+namespace {
+
+NAN_METHOD(New) {}
+
+void Init(Local<Object> exports, Local<Object> module) {
+  Local<FunctionTemplate> tpl = Nan::New<FunctionTemplate>(New);
+  tpl->SetClassName(Nan::New("Language").ToLocalChecked());
+  tpl->InstanceTemplate()->SetInternalFieldCount(1);
+
+  Local<Function> constructor = Nan::GetFunction(tpl).ToLocalChecked();
+  Local<Object> instance = constructor->NewInstance(Nan::GetCurrentContext()).ToLocalChecked();
+  Nan::SetInternalFieldPointer(instance, 0, tree_sitter_zeek());
+
+  Nan::Set(instance, Nan::New("name").ToLocalChecked(), Nan::New("zeek").ToLocalChecked());
+  Nan::Set(module, Nan::New("exports").ToLocalChecked(), instance);
+}
+
+NODE_MODULE(tree_sitter_zeek_binding, Init)
+
+}  // namespace

bindings/node/index.js

@@ -0,0 +1,19 @@
+try {
+  module.exports = require("../../build/Release/tree_sitter_zeek_binding");
+} catch (error1) {
+  if (error1.code !== 'MODULE_NOT_FOUND') {
+    throw error1;
+  }
+  try {
+    module.exports = require("../../build/Debug/tree_sitter_zeek_binding");
+  } catch (error2) {
+    if (error2.code !== 'MODULE_NOT_FOUND') {
+      throw error2;
+    }
+    throw error1
+  }
+}
+
+try {
+  module.exports.nodeTypeInfo = require("../../src/node-types.json");
+} catch (_) {}