Support heredocs (#45)

This adds support for heredocs in Dockerfiles. This required adding an external scanner to store the required state.

Co-authored-by: Camden Cheek <camden@ccheek.com>

.clang-format

@@ -0,0 +1 @@
+IndentWidth: 4

.editorconfig

@@ -0,0 +1,38 @@
+root = true
+
+[*]
+charset = utf-8
+end_of_line = lf
+insert_final_newline = true
+
+[*.{json,toml,yml,gyp}]
+indent_style = space
+indent_size = 2
+
+[*.js]
+indent_style = space
+indent_size = 2
+
+[*.rs]
+indent_style = space
+indent_size = 4
+
+[*.{c,cc,h}]
+indent_style = space
+indent_size = 4
+
+[*.{py,pyi}]
+indent_style = space
+indent_size = 4
+
+[*.swift]
+indent_style = space
+indent_size = 4
+
+[*.go]
+indent_style = tab
+indent_size = 8
+
+[Makefile]
+indent_style = tab
+indent_size = 8

.gitattributes

@@ -0,0 +1,11 @@
+* text eol=lf
+
+src/*.json linguist-generated
+src/parser.c linguist-generated
+src/tree_sitter/* linguist-generated
+
+bindings/** linguist-generated
+binding.gyp linguist-generated
+setup.py linguist-generated
+Makefile linguist-generated
+Package.swift linguist-generated

Package.swift

@@ -28,6 +28,7 @@ let package = Package(
                 ],
                 sources: [
                     "src/parser.c",
+                    "src/scanner.c",
                 ],
                 resources: [
                     .copy("queries")

binding.gyp

@@ -2,18 +2,29 @@
   "targets": [
     {
       "target_name": "tree_sitter_dockerfile_binding",
+      "dependencies": [
+        "<!(node -p \"require('node-addon-api').targets\"):node_addon_api_except",
+      ],
       "include_dirs": [
-        "<!(node -e \"require('nan')\")",
+        "src",
-        "src"
       ],
       "sources": [
         "bindings/node/binding.cc",
         "src/parser.c",
-        # If your language uses an external scanner, add it here.
+        "src/scanner.c",
       ],
+      "conditions": [
+        ["OS!='win'", {
           "cflags_c": [
-        "-std=c99",
+            "-std=c11",
-      ]
+          ],
+        }, { # OS == "win"
+          "cflags_c": [
+            "/std:c11",
+            "/utf-8",
+          ],
+        }],
+      ],
     }
   ]
 }

bindings/c/tree-sitter-dockerfile.pc.in

@@ -0,0 +1,11 @@
+prefix=@PREFIX@
+libdir=@LIBDIR@
+includedir=@INCLUDEDIR@
+
+Name: tree-sitter-dockerfile
+Description: Dockerfile grammar for tree-sitter
+URL: @URL@
+Version: @VERSION@
+Requires: @REQUIRES@
+Libs: -L${libdir} @ADDITIONAL_LIBS@ -ltree-sitter-dockerfile
+Cflags: -I${includedir}

bindings/go/binding.go

@@ -0,0 +1,13 @@
+package tree_sitter_dockerfile
+
+// #cgo CFLAGS: -std=c11 -fPIC
+// #include "../../src/parser.c"
+// #include "../../src/scanner.c"
+import "C"
+
+import "unsafe"
+
+// Get the tree-sitter Language for this grammar.
+func Language() unsafe.Pointer {
+	return unsafe.Pointer(C.tree_sitter_dockerfile())
+}

bindings/go/binding_test.go

@@ -0,0 +1,15 @@
+package tree_sitter_dockerfile_test
+
+import (
+	"testing"
+
+	tree_sitter_dockerfile "github.com/camdencheek/tree-sitter-dockerfile"
+	tree_sitter "github.com/smacker/go-tree-sitter"
+)
+
+func TestCanLoadGrammar(t *testing.T) {
+	language := tree_sitter.NewLanguage(tree_sitter_dockerfile.Language())
+	if language == nil {
+		t.Errorf("Error loading Dockerfile grammar")
+	}
+}

bindings/go/go.mod

@@ -0,0 +1,5 @@
+module github.com/camdencheek/tree-sitter-dockerfile
+
+go 1.22
+
+require github.com/smacker/go-tree-sitter v0.0.0-20230720070738-0d0a9f78d8f8

bindings/node/binding.cc

@@ -1,28 +1,20 @@
-#include "tree_sitter/parser.h"
+#include <napi.h>
-#include <node.h>
-#include "nan.h"
 
-using namespace v8;
+typedef struct TSLanguage TSLanguage;
 
 extern "C" TSLanguage *tree_sitter_dockerfile();
 
-namespace {
+// "tree-sitter", "language" hashed with BLAKE2
+const napi_type_tag LANGUAGE_TYPE_TAG = {
+  0x8AF2E5212AD58ABF, 0xD5006CAD83ABBA16
+};
 
-NAN_METHOD(New) {}
+Napi::Object Init(Napi::Env env, Napi::Object exports) {
-
+    exports["name"] = Napi::String::New(env, "dockerfile");
-void Init(Local<Object> exports, Local<Object> module) {
+    auto language = Napi::External<TSLanguage>::New(env, tree_sitter_dockerfile());
-  Local<FunctionTemplate> tpl = Nan::New<FunctionTemplate>(New);
+    language.TypeTag(&LANGUAGE_TYPE_TAG);
-  tpl->SetClassName(Nan::New("Language").ToLocalChecked());
+    exports["language"] = language;
-  tpl->InstanceTemplate()->SetInternalFieldCount(1);
+    return exports;
-
-  Local<Function> constructor = Nan::GetFunction(tpl).ToLocalChecked();
-  Local<Object> instance = constructor->NewInstance(Nan::GetCurrentContext()).ToLocalChecked();
-  Nan::SetInternalFieldPointer(instance, 0, tree_sitter_dockerfile());
-
-  Nan::Set(instance, Nan::New("name").ToLocalChecked(), Nan::New("dockerfile").ToLocalChecked());
-  Nan::Set(module, Nan::New("exports").ToLocalChecked(), instance);
 }
 
-NODE_MODULE(tree_sitter_dockerfile_binding, Init)
+NODE_API_MODULE(tree_sitter_dockerfile_binding, Init)
-
-}  // namespace

bindings/node/index.d.ts

@@ -0,0 +1,28 @@
+type BaseNode = {
+  type: string;
+  named: boolean;
+};
+
+type ChildNode = {
+  multiple: boolean;
+  required: boolean;
+  types: BaseNode[];
+};
+
+type NodeInfo =
+  | (BaseNode & {
+      subtypes: BaseNode[];
+    })
+  | (BaseNode & {
+      fields: { [name: string]: ChildNode };
+      children: ChildNode[];
+    });
+
+type Language = {
+  name: string;
+  language: unknown;
+  nodeTypeInfo: NodeInfo[];
+};
+
+declare const language: Language;
+export = language;

bindings/node/index.js

@@ -1,18 +1,6 @@
-try {
+const root = require("path").join(__dirname, "..", "..");
-  module.exports = require("../../build/Release/tree_sitter_dockerfile_binding");
+
-} catch (error1) {
+module.exports = require("node-gyp-build")(root);
-  if (error1.code !== 'MODULE_NOT_FOUND') {
-    throw error1;
-  }
-  try {
-    module.exports = require("../../build/Debug/tree_sitter_dockerfile_binding");
-  } catch (error2) {
-    if (error2.code !== 'MODULE_NOT_FOUND') {
-      throw error2;
-    }
-    throw error1
-  }
-}
 
 try {
   module.exports.nodeTypeInfo = require("../../src/node-types.json");

bindings/python/tree_sitter_dockerfile/__init__.py

@@ -0,0 +1,5 @@
+"Dockerfile grammar for tree-sitter"
+
+from ._binding import language
+
+__all__ = ["language"]

bindings/python/tree_sitter_dockerfile/__init__.pyi

@@ -0,0 +1 @@
+def language() -> int: ...

bindings/python/tree_sitter_dockerfile/binding.c

@@ -0,0 +1,27 @@
+#include <Python.h>
+
+typedef struct TSLanguage TSLanguage;
+
+TSLanguage *tree_sitter_dockerfile(void);
+
+static PyObject* _binding_language(PyObject *self, PyObject *args) {
+    return PyLong_FromVoidPtr(tree_sitter_dockerfile());
+}
+
+static PyMethodDef methods[] = {
+    {"language", _binding_language, METH_NOARGS,
+     "Get the tree-sitter language for this grammar."},
+    {NULL, NULL, 0, NULL}
+};
+
+static struct PyModuleDef module = {
+    .m_base = PyModuleDef_HEAD_INIT,
+    .m_name = "_binding",
+    .m_doc = NULL,
+    .m_size = -1,
+    .m_methods = methods
+};
+
+PyMODINIT_FUNC PyInit__binding(void) {
+    return PyModule_Create(&module);
+}

bindings/rust/build.rs

@@ -7,17 +7,18 @@ fn main() {
         .flag_if_supported("-Wno-unused-parameter")
         .flag_if_supported("-Wno-unused-but-set-variable")
         .flag_if_supported("-Wno-trigraphs");
+    #[cfg(target_env = "msvc")]
+    c_config.flag("-utf-8");
+
     let parser_path = src_dir.join("parser.c");
     c_config.file(&parser_path);
 
     // If your language uses an external scanner written in C,
     // then include this block of code:
 
-    /*
     let scanner_path = src_dir.join("scanner.c");
     c_config.file(&scanner_path);
     println!("cargo:rerun-if-changed={}", scanner_path.to_str().unwrap());
-    */
 
     c_config.compile("parser");
     println!("cargo:rerun-if-changed={}", parser_path.to_str().unwrap());

grammar.js

@@ -2,6 +2,13 @@ module.exports = grammar({
   name: "dockerfile",
 
   extras: ($) => [/\s+/, $.line_continuation],
+  externals: ($) => [
+    $.heredoc_marker,
+    $.heredoc_line,
+    $.heredoc_end,
+    $.heredoc_nl,
+    $.error_sentinel,
+  ],
 
   rules: {
     source_file: ($) => repeat(seq(choice($._instruction, $.comment), "\n")),
@@ -26,7 +33,7 @@ module.exports = grammar({
         $.healthcheck_instruction,
         $.shell_instruction,
         $.maintainer_instruction,
-        $.cross_build_instruction
+        $.cross_build_instruction,
       ),
 
     from_instruction: ($) =>
@@ -46,7 +53,8 @@ module.exports = grammar({
             $.mount_param
           )
         ),
-        choice($.json_string_array, $.shell_command)
+        choice($.json_string_array, $.shell_command),
+        repeat($.heredoc_block)
       ),
 
     cmd_instruction: ($) =>
@@ -75,9 +83,10 @@ module.exports = grammar({
         alias(/[aA][dD][dD]/, "ADD"),
         repeat($.param),
         repeat1(
-          seq($.path, $._non_newline_whitespace)
+          seq(alias($.path_with_heredoc, $.path), $._non_newline_whitespace)
         ),
-        $.path
+        alias($.path_with_heredoc, $.path),
+        repeat($.heredoc_block)
       ),
 
     copy_instruction: ($) =>
@@ -85,9 +94,10 @@ module.exports = grammar({
         alias(/[cC][oO][pP][yY]/, "COPY"),
         repeat($.param),
         repeat1(
-          seq($.path, $._non_newline_whitespace)
+          seq(alias($.path_with_heredoc, $.path), $._non_newline_whitespace)
         ),
-        $.path
+        alias($.path_with_heredoc, $.path),
+        repeat($.heredoc_block)
       ),
 
     entrypoint_instruction: ($) =>
@@ -193,15 +203,41 @@ module.exports = grammar({
         /.*/
       ),
 
+    heredoc_block: ($) =>
+      seq(
+        // A heredoc block starts with a line break after the instruction it
+        // belongs to. The herdoc_nl token is a special token that only matches
+        // \n if there's at least one open heredoc to avoid conflicts.
+        // We also alias this token to hide it from the output like all other
+        // whitespace.
+        alias($.heredoc_nl, "_heredoc_nl"),
+        repeat(seq($.heredoc_line, "\n")),
+        $.heredoc_end
+      ),
+
     path: ($) =>
       seq(
         choice(
-          /[^-\s\$]/, // cannot start with a '-' to avoid conflicts with params
+          /[^-\s\$<]/, // cannot start with a '-' to avoid conflicts with params
+          /<[^<]/, // cannot start with a '<<' to avoid conflicts with heredocs (a single < is fine, though)
           $.expansion
         ),
         repeat(choice(token.immediate(/[^\s\$]+/), $._immediate_expansion))
       ),
 
+    path_with_heredoc: ($) =>
+      choice(
+        $.heredoc_marker,
+        seq(
+          choice(
+            /[^-\s\$<]/, // cannot start with a '-' to avoid conflicts with params
+            /<[^-\s\$<]/,
+            $.expansion
+          ),
+          repeat(choice(token.immediate(/[^\s\$]+/), $._immediate_expansion))
+        )
+      ),
+
     expansion: $ =>
       seq("$", $._expansion_body),
 
@@ -361,9 +397,11 @@ module.exports = grammar({
         //       |--------param-------|
         //                              |--shell_command--|
         //
+        seq($.heredoc_marker, /[ \t]*/),
         /[,=-]/,
-        /[^\\\[\n#\s,=-][^\\\n]*/,
+        /[^\\\[\n#\s,=-][^\\\n<]*/,
-        /\\[^\n,=-]/
+        /\\[^\n,=-]/,
+        /<[^<]/,
       )
     ),
 
@@ -452,7 +490,7 @@ module.exports = grammar({
       )
     ),
 
-    _non_newline_whitespace: ($) => /[\t ]+/,
+    _non_newline_whitespace: ($) => token.immediate(/[\t ]+/),
 
     comment: ($) => /#.*/,
   },

package.json

@@ -3,16 +3,29 @@
   "version": "0.1.0",
   "description": "A tree-sitter module for the Dockerfile grammar",
   "main": "bindings/node",
+  "types": "bindings/node",
   "scripts": {
-    "test": "echo \"Error: no test specified\" && exit 1"
+    "test": "echo \"Error: no test specified\" && exit 1",
+    "install": "node-gyp-build",
+    "prebuildify": "prebuildify --napi --strip"
   },
   "author": "Camden Cheek <camden@ccheek.com>",
   "license": "ISC",
   "dependencies": {
-    "nan": "^2.14.2"
+    "node-addon-api": "^7.1.0",
+    "node-gyp-build": "^4.8.0"
+  },
+  "peerDependencies": {
+    "tree-sitter": "^0.21.0"
+  },
+  "peerDependenciesMeta": {
+    "tree_sitter": {
+      "optional": true
+    }
   },
   "devDependencies": {
-    "tree-sitter-cli": "^0.20.8"
+    "tree-sitter-cli": "^0.20.8",
+    "prebuildify": "^6.0.0"
   },
   "tree-sitter": [
     {
@@ -27,5 +40,13 @@
         "queries/highlights.scm"
       ]
     }
+  ],
+  "files": [
+    "grammar.js",
+    "binding.gyp",
+    "prebuilds/**",
+    "bindings/node/*",
+    "queries/*",
+    "src/**"
   ]
 }

pnpm-lock.yaml

@@ -0,0 +1,27 @@
+lockfileVersion: '6.0'
+
+settings:
+  autoInstallPeers: true
+  excludeLinksFromLockfile: false
+
+dependencies:
+  nan:
+    specifier: ^2.14.2
+    version: 2.18.0
+
+devDependencies:
+  tree-sitter-cli:
+    specifier: ^0.20.1
+    version: 0.20.8
+
+packages:
+
+  /nan@2.18.0:
+    resolution: {integrity: sha512-W7tfG7vMOGtD30sHoZSSc/JVYiyDPEyQVso/Zz+/uQd0B0L46gtC+pHha5FFMRpil6fm/AoEcRWyOVi4+E/f8w==}
+    dev: false
+
+  /tree-sitter-cli@0.20.8:
+    resolution: {integrity: sha512-XjTcS3wdTy/2cc/ptMLc/WRyOLECRYcMTrSWyhZnj1oGSOWbHLTklgsgRICU3cPfb0vy+oZCC33M43u6R1HSCA==}
+    hasBin: true
+    requiresBuild: true
+    dev: true

pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["setuptools>=42", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "tree-sitter-dockerfile"
+description = "Dockerfile grammar for tree-sitter"
+version = "0.1.0"
+keywords = ["incremental", "parsing", "tree-sitter", "dockerfile"]
+classifiers = [
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: MIT License",
+  "Topic :: Software Development :: Compilers",
+  "Topic :: Text Processing :: Linguistic",
+  "Typing :: Typed"
+]
+requires-python = ">=3.8"
+license.text = "MIT"
+readme = "README.md"
+
+[project.urls]
+Homepage = "https://github.com/camdencheek/tree-sitter-dockerfile"
+
+[project.optional-dependencies]
+core = ["tree-sitter~=0.21"]
+
+[tool.cibuildwheel]
+build = "cp38-*"
+build-frontend = "build"

queries/highlights.scm

@@ -19,6 +19,8 @@
 	"SHELL"
 	"MAINTAINER"
 	"CROSS_BUILD"
+	(heredoc_marker)
+	(heredoc_end)
 ] @keyword
 
 [
@@ -39,6 +41,7 @@
 	(double_quoted_string)
 	(single_quoted_string)
 	(json_string)
+	(heredoc_line)
 ] @string
 
 (expansion

setup.py

@@ -0,0 +1,60 @@
+from os.path import isdir, join
+from platform import system
+
+from setuptools import Extension, find_packages, setup
+from setuptools.command.build import build
+from wheel.bdist_wheel import bdist_wheel
+
+
+class Build(build):
+    def run(self):
+        if isdir("queries"):
+            dest = join(self.build_lib, "tree_sitter_dockerfile", "queries")
+            self.copy_tree("queries", dest)
+        super().run()
+
+
+class BdistWheel(bdist_wheel):
+    def get_tag(self):
+        python, abi, platform = super().get_tag()
+        if python.startswith("cp"):
+            python, abi = "cp38", "abi3"
+        return python, abi, platform
+
+
+setup(
+    packages=find_packages("bindings/python"),
+    package_dir={"": "bindings/python"},
+    package_data={
+        "tree_sitter_dockerfile": ["*.pyi", "py.typed"],
+        "tree_sitter_dockerfile.queries": ["*.scm"],
+    },
+    ext_package="tree_sitter_dockerfile",
+    ext_modules=[
+        Extension(
+            name="_binding",
+            sources=[
+                "bindings/python/tree_sitter_dockerfile/binding.c",
+                "src/parser.c",
+                "src/scanner.c",
+            ],
+            extra_compile_args=[
+                "-std=c11",
+            ] if system() != "Windows" else [
+                "/std:c11",
+                "/utf-8",
+            ],
+            define_macros=[
+                ("Py_LIMITED_API", "0x03080000"),
+                ("PY_SSIZE_T_CLEAN", None)
+            ],
+            include_dirs=["src"],
+            py_limited_api=True,
+        )
+    ],
+    cmdclass={
+        "build": Build,
+        "bdist_wheel": BdistWheel
+    },
+    zip_safe=False
+)

src/grammar.json

@@ -207,6 +207,13 @@
               "name": "shell_command"
             }
           ]
+        },
+        {
+          "type": "REPEAT",
+          "content": {
+            "type": "SYMBOL",
+            "name": "heredoc_block"
+          }
         }
       ]
     },
@@ -348,8 +355,13 @@
             "type": "SEQ",
             "members": [
               {
+                "type": "ALIAS",
+                "content": {
                   "type": "SYMBOL",
-                "name": "path"
+                  "name": "path_with_heredoc"
+                },
+                "named": true,
+                "value": "path"
               },
               {
                 "type": "SYMBOL",
@@ -359,8 +371,20 @@
           }
         },
         {
+          "type": "ALIAS",
+          "content": {
             "type": "SYMBOL",
-          "name": "path"
+            "name": "path_with_heredoc"
+          },
+          "named": true,
+          "value": "path"
+        },
+        {
+          "type": "REPEAT",
+          "content": {
+            "type": "SYMBOL",
+            "name": "heredoc_block"
+          }
         }
       ]
     },
@@ -389,8 +413,13 @@
             "type": "SEQ",
             "members": [
               {
+                "type": "ALIAS",
+                "content": {
                   "type": "SYMBOL",
-                "name": "path"
+                  "name": "path_with_heredoc"
+                },
+                "named": true,
+                "value": "path"
               },
               {
                 "type": "SYMBOL",
@@ -400,8 +429,20 @@
           }
         },
         {
+          "type": "ALIAS",
+          "content": {
             "type": "SYMBOL",
-          "name": "path"
+            "name": "path_with_heredoc"
+          },
+          "named": true,
+          "value": "path"
+        },
+        {
+          "type": "REPEAT",
+          "content": {
+            "type": "SYMBOL",
+            "name": "heredoc_block"
+          }
         }
       ]
     },
@@ -840,6 +881,40 @@
         }
       ]
     },
+    "heredoc_block": {
+      "type": "SEQ",
+      "members": [
+        {
+          "type": "ALIAS",
+          "content": {
+            "type": "SYMBOL",
+            "name": "heredoc_nl"
+          },
+          "named": false,
+          "value": "_heredoc_nl"
+        },
+        {
+          "type": "REPEAT",
+          "content": {
+            "type": "SEQ",
+            "members": [
+              {
+                "type": "SYMBOL",
+                "name": "heredoc_line"
+              },
+              {
+                "type": "STRING",
+                "value": "\n"
+              }
+            ]
+          }
+        },
+        {
+          "type": "SYMBOL",
+          "name": "heredoc_end"
+        }
+      ]
+    },
     "path": {
       "type": "SEQ",
       "members": [
@@ -848,7 +923,11 @@
           "members": [
             {
               "type": "PATTERN",
-              "value": "[^-\\s\\$]"
+              "value": "[^-\\s\\$<]"
+            },
+            {
+              "type": "PATTERN",
+              "value": "<[^<]"
             },
             {
               "type": "SYMBOL",
@@ -877,6 +956,56 @@
         }
       ]
     },
+    "path_with_heredoc": {
+      "type": "CHOICE",
+      "members": [
+        {
+          "type": "SYMBOL",
+          "name": "heredoc_marker"
+        },
+        {
+          "type": "SEQ",
+          "members": [
+            {
+              "type": "CHOICE",
+              "members": [
+                {
+                  "type": "PATTERN",
+                  "value": "[^-\\s\\$<]"
+                },
+                {
+                  "type": "PATTERN",
+                  "value": "<[^-\\s\\$<]"
+                },
+                {
+                  "type": "SYMBOL",
+                  "name": "expansion"
+                }
+              ]
+            },
+            {
+              "type": "REPEAT",
+              "content": {
+                "type": "CHOICE",
+                "members": [
+                  {
+                    "type": "IMMEDIATE_TOKEN",
+                    "content": {
+                      "type": "PATTERN",
+                      "value": "[^\\s\\$]+"
+                    }
+                  },
+                  {
+                    "type": "SYMBOL",
+                    "name": "_immediate_expansion"
+                  }
+                ]
+              }
+            }
+          ]
+        }
+      ]
+    },
     "expansion": {
       "type": "SEQ",
       "members": [
@@ -1508,17 +1637,34 @@
       "content": {
         "type": "CHOICE",
         "members": [
+          {
+            "type": "SEQ",
+            "members": [
+              {
+                "type": "SYMBOL",
+                "name": "heredoc_marker"
+              },
+              {
+                "type": "PATTERN",
+                "value": "[ \\t]*"
+              }
+            ]
+          },
           {
             "type": "PATTERN",
             "value": "[,=-]"
           },
           {
             "type": "PATTERN",
-            "value": "[^\\\\\\[\\n#\\s,=-][^\\\\\\n]*"
+            "value": "[^\\\\\\[\\n#\\s,=-][^\\\\\\n<]*"
           },
           {
             "type": "PATTERN",
             "value": "\\\\[^\\n,=-]"
+          },
+          {
+            "type": "PATTERN",
+            "value": "<[^<]"
           }
         ]
       }
@@ -1797,8 +1943,11 @@
       }
     },
     "_non_newline_whitespace": {
+      "type": "IMMEDIATE_TOKEN",
+      "content": {
         "type": "PATTERN",
         "value": "[\\t ]+"
+      }
     },
     "comment": {
       "type": "PATTERN",
@@ -1817,8 +1966,28 @@
   ],
   "conflicts": [],
   "precedences": [],
-  "externals": [],
+  "externals": [
+    {
+      "type": "SYMBOL",
+      "name": "heredoc_marker"
+    },
+    {
+      "type": "SYMBOL",
+      "name": "heredoc_line"
+    },
+    {
+      "type": "SYMBOL",
+      "name": "heredoc_end"
+    },
+    {
+      "type": "SYMBOL",
+      "name": "heredoc_nl"
+    },
+    {
+      "type": "SYMBOL",
+      "name": "error_sentinel"
+    }
+  ],
   "inline": [],
   "supertypes": []
 }
-

src/node-types.json

@@ -7,6 +7,10 @@
       "multiple": true,
       "required": true,
       "types": [
+        {
+          "type": "heredoc_block",
+          "named": true
+        },
         {
           "type": "param",
           "named": true
@@ -84,6 +88,10 @@
       "multiple": true,
       "required": true,
       "types": [
+        {
+          "type": "heredoc_block",
+          "named": true
+        },
         {
           "type": "param",
           "named": true
@@ -275,6 +283,25 @@
       ]
     }
   },
+  {
+    "type": "heredoc_block",
+    "named": true,
+    "fields": {},
+    "children": {
+      "multiple": true,
+      "required": true,
+      "types": [
+        {
+          "type": "heredoc_end",
+          "named": true
+        },
+        {
+          "type": "heredoc_line",
+          "named": true
+        }
+      ]
+    }
+  },
   {
     "type": "image_alias",
     "named": true,
@@ -606,6 +633,10 @@
         {
           "type": "expansion",
           "named": true
+        },
+        {
+          "type": "heredoc_marker",
+          "named": true
         }
       ]
     }
@@ -618,6 +649,10 @@
       "multiple": true,
       "required": true,
       "types": [
+        {
+          "type": "heredoc_block",
+          "named": true
+        },
         {
           "type": "json_string_array",
           "named": true
@@ -663,7 +698,17 @@
   {
     "type": "shell_fragment",
     "named": true,
-    "fields": {}
+    "fields": {},
+    "children": {
+      "multiple": true,
+      "required": false,
+      "types": [
+        {
+          "type": "heredoc_marker",
+          "named": true
+        }
+      ]
+    }
   },
   {
     "type": "shell_instruction",
@@ -1028,10 +1073,26 @@
     "type": "]",
     "named": false
   },
+  {
+    "type": "_heredoc_nl",
+    "named": false
+  },
   {
     "type": "escape_sequence",
     "named": true
   },
+  {
+    "type": "heredoc_end",
+    "named": true
+  },
+  {
+    "type": "heredoc_line",
+    "named": true
+  },
+  {
+    "type": "heredoc_marker",
+    "named": true
+  },
   {
     "type": "mount",
     "named": false

src/scanner.c

@@ -0,0 +1,318 @@
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <wctype.h>
+
+#include "tree_sitter/parser.h"
+
+#define MAX_HEREDOCS 10
+
+typedef struct {
+    bool in_heredoc;
+    bool stripping_heredoc;
+    unsigned heredoc_count;
+    char *heredocs[MAX_HEREDOCS];
+} scanner_state;
+
+enum TokenType {
+    HEREDOC_MARKER,
+    HEREDOC_LINE,
+    HEREDOC_END,
+    HEREDOC_NL,
+    ERROR_SENTINEL,
+};
+
+void *tree_sitter_dockerfile_external_scanner_create() {
+    scanner_state *state = malloc(sizeof(scanner_state));
+    memset(state, 0, sizeof(scanner_state));
+    return state;
+}
+
+void tree_sitter_dockerfile_external_scanner_destroy(void *payload) {
+    if (!payload)
+        return;
+
+    scanner_state *state = payload;
+    for (unsigned i = 0; i < MAX_HEREDOCS; i++) {
+        if (state->heredocs[i]) {
+            free(state->heredocs[i]);
+        }
+    }
+
+    free(state);
+}
+
+unsigned tree_sitter_dockerfile_external_scanner_serialize(void *payload,
+                                                           char *buffer) {
+    scanner_state *state = payload;
+
+    unsigned pos = 0;
+    buffer[pos++] = state->in_heredoc;
+    buffer[pos++] = state->stripping_heredoc;
+
+    for (unsigned i = 0; i < state->heredoc_count; i++) {
+        // Add the ending null byte to the length since we'll have to copy it as
+        // well.
+        unsigned len = strlen(state->heredocs[i]) + 1;
+
+        // If we run out of space, just drop the heredocs that don't fit.
+        // We need at least len + 1 bytes space since we'll copy len bytes below
+        // and later add a null byte at the end.
+        if (pos + len + 1 > TREE_SITTER_SERIALIZATION_BUFFER_SIZE) {
+            break;
+        }
+
+        memcpy(&buffer[pos], state->heredocs[i], len);
+        pos += len;
+    }
+
+    // Add a null byte at the end to make it easy to detect.
+    buffer[pos++] = 0;
+    return pos;
+}
+
+void tree_sitter_dockerfile_external_scanner_deserialize(void *payload,
+                                                         const char *buffer,
+                                                         unsigned length) {
+    scanner_state *state = payload;
+    // Free all current heredocs to avoid leaking memory when we overwrite the
+    // array later.
+    for (unsigned i = 0; i < state->heredoc_count; i++) {
+        free(state->heredocs[i]);
+        state->heredocs[i] = NULL;
+    }
+
+    if (length == 0) {
+        state->in_heredoc = false;
+        state->stripping_heredoc = false;
+        state->heredoc_count = 0;
+    } else {
+        unsigned pos = 0;
+        state->in_heredoc = buffer[pos++];
+        state->stripping_heredoc = buffer[pos++];
+
+        unsigned heredoc_count = 0;
+        for (unsigned i = 0; i < MAX_HEREDOCS; i++) {
+            unsigned len = strlen(&buffer[pos]);
+
+            // We found the ending null byte which means that we're done.
+            if (len == 0)
+                break;
+
+            // Account for the ending null byte in strings (again).
+            len++;
+            char *heredoc = malloc(len);
+            memcpy(heredoc, &buffer[pos], len);
+            state->heredocs[i] = heredoc;
+            heredoc_count++;
+
+            pos += len;
+        }
+
+        state->heredoc_count = heredoc_count;
+    }
+}
+
+static void skip_whitespace(TSLexer *lexer) {
+    while (lexer->lookahead != '\0' && lexer->lookahead != '\n' &&
+           iswspace(lexer->lookahead))
+        lexer->advance(lexer, true);
+}
+
+static bool scan_marker(scanner_state *state, TSLexer *lexer) {
+    skip_whitespace(lexer);
+
+    if (lexer->lookahead != '<')
+        return false;
+    lexer->advance(lexer, false);
+
+    if (lexer->lookahead != '<')
+        return false;
+    lexer->advance(lexer, false);
+
+    bool stripping = false;
+    if (lexer->lookahead == '-') {
+        stripping = true;
+        lexer->advance(lexer, false);
+    }
+
+    int32_t quote = 0;
+    if (lexer->lookahead == '"' || lexer->lookahead == '\'') {
+        quote = lexer->lookahead;
+        lexer->advance(lexer, false);
+    }
+
+    // Reserve a reasonable amount of space for the heredoc delimiter string.
+    // Most heredocs (like EOF, EOT, EOS, FILE, etc.) are pretty short so we'll
+    // usually only need a few bytes. We're also limited to less than 1024 bytes
+    // by tree-sitter since our state has to fit in
+    // TREE_SITTER_SERIALIZATION_BUFFER_SIZE.
+    const unsigned int del_space = 512;
+    char delimiter[del_space];
+
+    // We start recording the actual string at position 1 since we store whether
+    // it's a stripping heredoc in the first position (with either a dash or a
+    // space).
+    unsigned del_idx = 1;
+
+    while (lexer->lookahead != '\0' &&
+           (quote ? lexer->lookahead != quote : !iswspace(lexer->lookahead))) {
+        if (lexer->lookahead == '\\') {
+            lexer->advance(lexer, false);
+
+            if (lexer->lookahead == '\0') {
+                return false;
+            }
+        }
+
+        if (del_idx > 0) {
+            delimiter[del_idx++] = lexer->lookahead;
+        }
+        lexer->advance(lexer, false);
+
+        // If we run out of space, stop recording the delimiter but keep
+        // advancing the lexer to ensure that we at least parse the marker
+        // correctly. Reserve two bytes: one for the strip indicator and
+        // one for the terminating null byte.
+        if (del_idx >= del_space - 2) {
+            del_idx = 0;
+        }
+    }
+
+    if (quote) {
+        if (lexer->lookahead != quote) {
+            return false;
+        }
+        lexer->advance(lexer, false);
+    }
+
+    if (del_idx == 0) {
+        lexer->result_symbol = HEREDOC_MARKER;
+        return true;
+    }
+
+    delimiter[0] = stripping ? '-' : ' ';
+    delimiter[del_idx] = '\0';
+
+    // We copy the delimiter string to the heap here since we can't store our
+    // stack-allocated string in our state (which is stored on the heap).
+    char *del_copy = malloc(del_idx + 1);
+    memcpy(del_copy, delimiter, del_idx + 1);
+
+    if (state->heredoc_count == 0) {
+        state->heredoc_count = 1;
+        state->heredocs[0] = del_copy;
+        state->stripping_heredoc = stripping;
+    } else if (state->heredoc_count >= MAX_HEREDOCS) {
+        free(del_copy);
+    } else {
+        state->heredocs[state->heredoc_count++] = del_copy;
+    }
+
+    lexer->result_symbol = HEREDOC_MARKER;
+    return true;
+}
+
+static bool scan_content(scanner_state *state, TSLexer *lexer,
+                         const bool *valid_symbols) {
+    if (state->heredoc_count == 0) {
+        state->in_heredoc = false;
+        return false;
+    }
+
+    state->in_heredoc = true;
+
+    if (state->stripping_heredoc) {
+        skip_whitespace(lexer);
+    }
+
+    if (valid_symbols[HEREDOC_END]) {
+        unsigned delim_idx = 1;
+        // Look for the current heredoc delimiter.
+        while (state->heredocs[0][delim_idx] != '\0' &&
+               lexer->lookahead != '\0' &&
+               lexer->lookahead == state->heredocs[0][delim_idx]) {
+            lexer->advance(lexer, false);
+            delim_idx++;
+        }
+
+        // Check if the entire string matched.
+        if (state->heredocs[0][delim_idx] == '\0') {
+            lexer->result_symbol = HEREDOC_END;
+
+            // Shift the first heredoc off the list.
+            free(state->heredocs[0]);
+
+            for (unsigned i = 1; i < state->heredoc_count; i++) {
+                state->heredocs[i - 1] = state->heredocs[i];
+            }
+            state->heredocs[state->heredoc_count - 1] = NULL;
+            state->heredoc_count--;
+
+            if (state->heredoc_count > 0) {
+                state->stripping_heredoc = state->heredocs[0][0] == '-';
+            } else {
+                state->in_heredoc = false;
+            }
+
+            return true;
+        }
+    }
+
+    if (!valid_symbols[HEREDOC_LINE])
+        return false;
+
+    lexer->result_symbol = HEREDOC_LINE;
+
+    for (;;) {
+        switch (lexer->lookahead) {
+        case '\0':
+            if (lexer->eof(lexer)) {
+                state->in_heredoc = false;
+                return true;
+            }
+            lexer->advance(lexer, false);
+            break;
+
+        case '\n':
+            return true;
+
+        default:
+            lexer->advance(lexer, false);
+        }
+    }
+}
+
+bool tree_sitter_dockerfile_external_scanner_scan(void *payload, TSLexer *lexer,
+                                                  const bool *valid_symbols) {
+    scanner_state *state = payload;
+
+    if (valid_symbols[ERROR_SENTINEL]) {
+        if (state->in_heredoc) {
+            return scan_content(state, lexer, valid_symbols);
+        } else {
+            return scan_marker(state, lexer);
+        }
+    }
+
+    // HEREDOC_NL only matches a linebreak if there are open heredocs. This is
+    // necessary to avoid a conflict in the grammar since a normal line break
+    // could either be the start of a heredoc or the end of an instruction.
+    if (valid_symbols[HEREDOC_NL]) {
+        if (state->heredoc_count > 0 && lexer->lookahead == '\n') {
+            lexer->result_symbol = HEREDOC_NL;
+            lexer->advance(lexer, false);
+            return true;
+        }
+    }
+
+    if (valid_symbols[HEREDOC_MARKER]) {
+        return scan_marker(state, lexer);
+    }
+
+    if (valid_symbols[HEREDOC_LINE] || valid_symbols[HEREDOC_END]) {
+        return scan_content(state, lexer, valid_symbols);
+    }
+
+    return false;
+}

src/tree_sitter/alloc.h

@@ -0,0 +1,54 @@
+#ifndef TREE_SITTER_ALLOC_H_
+#define TREE_SITTER_ALLOC_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+// Allow clients to override allocation functions
+#ifdef TREE_SITTER_REUSE_ALLOCATOR
+
+extern void *(*ts_current_malloc)(size_t);
+extern void *(*ts_current_calloc)(size_t, size_t);
+extern void *(*ts_current_realloc)(void *, size_t);
+extern void (*ts_current_free)(void *);
+
+#ifndef ts_malloc
+#define ts_malloc  ts_current_malloc
+#endif
+#ifndef ts_calloc
+#define ts_calloc  ts_current_calloc
+#endif
+#ifndef ts_realloc
+#define ts_realloc ts_current_realloc
+#endif
+#ifndef ts_free
+#define ts_free    ts_current_free
+#endif
+
+#else
+
+#ifndef ts_malloc
+#define ts_malloc  malloc
+#endif
+#ifndef ts_calloc
+#define ts_calloc  calloc
+#endif
+#ifndef ts_realloc
+#define ts_realloc realloc
+#endif
+#ifndef ts_free
+#define ts_free    free
+#endif
+
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif // TREE_SITTER_ALLOC_H_

src/tree_sitter/array.h

@@ -0,0 +1,290 @@
+#ifndef TREE_SITTER_ARRAY_H_
+#define TREE_SITTER_ARRAY_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "./alloc.h"
+
+#include <assert.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+
+#ifdef _MSC_VER
+#pragma warning(disable : 4101)
+#elif defined(__GNUC__) || defined(__clang__)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wunused-variable"
+#endif
+
+#define Array(T)       \
+  struct {             \
+    T *contents;       \
+    uint32_t size;     \
+    uint32_t capacity; \
+  }
+
+/// Initialize an array.
+#define array_init(self) \
+  ((self)->size = 0, (self)->capacity = 0, (self)->contents = NULL)
+
+/// Create an empty array.
+#define array_new() \
+  { NULL, 0, 0 }
+
+/// Get a pointer to the element at a given `index` in the array.
+#define array_get(self, _index) \
+  (assert((uint32_t)(_index) < (self)->size), &(self)->contents[_index])
+
+/// Get a pointer to the first element in the array.
+#define array_front(self) array_get(self, 0)
+
+/// Get a pointer to the last element in the array.
+#define array_back(self) array_get(self, (self)->size - 1)
+
+/// Clear the array, setting its size to zero. Note that this does not free any
+/// memory allocated for the array's contents.
+#define array_clear(self) ((self)->size = 0)
+
+/// Reserve `new_capacity` elements of space in the array. If `new_capacity` is
+/// less than the array's current capacity, this function has no effect.
+#define array_reserve(self, new_capacity) \
+  _array__reserve((Array *)(self), array_elem_size(self), new_capacity)
+
+/// Free any memory allocated for this array. Note that this does not free any
+/// memory allocated for the array's contents.
+#define array_delete(self) _array__delete((Array *)(self))
+
+/// Push a new `element` onto the end of the array.
+#define array_push(self, element)                            \
+  (_array__grow((Array *)(self), 1, array_elem_size(self)), \
+   (self)->contents[(self)->size++] = (element))
+
+/// Increase the array's size by `count` elements.
+/// New elements are zero-initialized.
+#define array_grow_by(self, count) \
+  do { \
+    if ((count) == 0) break; \
+    _array__grow((Array *)(self), count, array_elem_size(self)); \
+    memset((self)->contents + (self)->size, 0, (count) * array_elem_size(self)); \
+    (self)->size += (count); \
+  } while (0)
+
+/// Append all elements from one array to the end of another.
+#define array_push_all(self, other)                                       \
+  array_extend((self), (other)->size, (other)->contents)
+
+/// Append `count` elements to the end of the array, reading their values from the
+/// `contents` pointer.
+#define array_extend(self, count, contents)                    \
+  _array__splice(                                               \
+    (Array *)(self), array_elem_size(self), (self)->size, \
+    0, count,  contents                                        \
+  )
+
+/// Remove `old_count` elements from the array starting at the given `index`. At
+/// the same index, insert `new_count` new elements, reading their values from the
+/// `new_contents` pointer.
+#define array_splice(self, _index, old_count, new_count, new_contents)  \
+  _array__splice(                                                       \
+    (Array *)(self), array_elem_size(self), _index,                \
+    old_count, new_count, new_contents                                 \
+  )
+
+/// Insert one `element` into the array at the given `index`.
+#define array_insert(self, _index, element) \
+  _array__splice((Array *)(self), array_elem_size(self), _index, 0, 1, &(element))
+
+/// Remove one element from the array at the given `index`.
+#define array_erase(self, _index) \
+  _array__erase((Array *)(self), array_elem_size(self), _index)
+
+/// Pop the last element off the array, returning the element by value.
+#define array_pop(self) ((self)->contents[--(self)->size])
+
+/// Assign the contents of one array to another, reallocating if necessary.
+#define array_assign(self, other) \
+  _array__assign((Array *)(self), (const Array *)(other), array_elem_size(self))
+
+/// Swap one array with another
+#define array_swap(self, other) \
+  _array__swap((Array *)(self), (Array *)(other))
+
+/// Get the size of the array contents
+#define array_elem_size(self) (sizeof *(self)->contents)
+
+/// Search a sorted array for a given `needle` value, using the given `compare`
+/// callback to determine the order.
+///
+/// If an existing element is found to be equal to `needle`, then the `index`
+/// out-parameter is set to the existing value's index, and the `exists`
+/// out-parameter is set to true. Otherwise, `index` is set to an index where
+/// `needle` should be inserted in order to preserve the sorting, and `exists`
+/// is set to false.
+#define array_search_sorted_with(self, compare, needle, _index, _exists) \
+  _array__search_sorted(self, 0, compare, , needle, _index, _exists)
+
+/// Search a sorted array for a given `needle` value, using integer comparisons
+/// of a given struct field (specified with a leading dot) to determine the order.
+///
+/// See also `array_search_sorted_with`.
+#define array_search_sorted_by(self, field, needle, _index, _exists) \
+  _array__search_sorted(self, 0, _compare_int, field, needle, _index, _exists)
+
+/// Insert a given `value` into a sorted array, using the given `compare`
+/// callback to determine the order.
+#define array_insert_sorted_with(self, compare, value) \
+  do { \
+    unsigned _index, _exists; \
+    array_search_sorted_with(self, compare, &(value), &_index, &_exists); \
+    if (!_exists) array_insert(self, _index, value); \
+  } while (0)
+
+/// Insert a given `value` into a sorted array, using integer comparisons of
+/// a given struct field (specified with a leading dot) to determine the order.
+///
+/// See also `array_search_sorted_by`.
+#define array_insert_sorted_by(self, field, value) \
+  do { \
+    unsigned _index, _exists; \
+    array_search_sorted_by(self, field, (value) field, &_index, &_exists); \
+    if (!_exists) array_insert(self, _index, value); \
+  } while (0)
+
+// Private
+
+typedef Array(void) Array;
+
+/// This is not what you're looking for, see `array_delete`.
+static inline void _array__delete(Array *self) {
+  if (self->contents) {
+    ts_free(self->contents);
+    self->contents = NULL;
+    self->size = 0;
+    self->capacity = 0;
+  }
+}
+
+/// This is not what you're looking for, see `array_erase`.
+static inline void _array__erase(Array *self, size_t element_size,
+                                uint32_t index) {
+  assert(index < self->size);
+  char *contents = (char *)self->contents;
+  memmove(contents + index * element_size, contents + (index + 1) * element_size,
+          (self->size - index - 1) * element_size);
+  self->size--;
+}
+
+/// This is not what you're looking for, see `array_reserve`.
+static inline void _array__reserve(Array *self, size_t element_size, uint32_t new_capacity) {
+  if (new_capacity > self->capacity) {
+    if (self->contents) {
+      self->contents = ts_realloc(self->contents, new_capacity * element_size);
+    } else {
+      self->contents = ts_malloc(new_capacity * element_size);
+    }
+    self->capacity = new_capacity;
+  }
+}
+
+/// This is not what you're looking for, see `array_assign`.
+static inline void _array__assign(Array *self, const Array *other, size_t element_size) {
+  _array__reserve(self, element_size, other->size);
+  self->size = other->size;
+  memcpy(self->contents, other->contents, self->size * element_size);
+}
+
+/// This is not what you're looking for, see `array_swap`.
+static inline void _array__swap(Array *self, Array *other) {
+  Array swap = *other;
+  *other = *self;
+  *self = swap;
+}
+
+/// This is not what you're looking for, see `array_push` or `array_grow_by`.
+static inline void _array__grow(Array *self, uint32_t count, size_t element_size) {
+  uint32_t new_size = self->size + count;
+  if (new_size > self->capacity) {
+    uint32_t new_capacity = self->capacity * 2;
+    if (new_capacity < 8) new_capacity = 8;
+    if (new_capacity < new_size) new_capacity = new_size;
+    _array__reserve(self, element_size, new_capacity);
+  }
+}
+
+/// This is not what you're looking for, see `array_splice`.
+static inline void _array__splice(Array *self, size_t element_size,
+                                 uint32_t index, uint32_t old_count,
+                                 uint32_t new_count, const void *elements) {
+  uint32_t new_size = self->size + new_count - old_count;
+  uint32_t old_end = index + old_count;
+  uint32_t new_end = index + new_count;
+  assert(old_end <= self->size);
+
+  _array__reserve(self, element_size, new_size);
+
+  char *contents = (char *)self->contents;
+  if (self->size > old_end) {
+    memmove(
+      contents + new_end * element_size,
+      contents + old_end * element_size,
+      (self->size - old_end) * element_size
+    );
+  }
+  if (new_count > 0) {
+    if (elements) {
+      memcpy(
+        (contents + index * element_size),
+        elements,
+        new_count * element_size
+      );
+    } else {
+      memset(
+        (contents + index * element_size),
+        0,
+        new_count * element_size
+      );
+    }
+  }
+  self->size += new_count - old_count;
+}
+
+/// A binary search routine, based on Rust's `std::slice::binary_search_by`.
+/// This is not what you're looking for, see `array_search_sorted_with` or `array_search_sorted_by`.
+#define _array__search_sorted(self, start, compare, suffix, needle, _index, _exists) \
+  do { \
+    *(_index) = start; \
+    *(_exists) = false; \
+    uint32_t size = (self)->size - *(_index); \
+    if (size == 0) break; \
+    int comparison; \
+    while (size > 1) { \
+      uint32_t half_size = size / 2; \
+      uint32_t mid_index = *(_index) + half_size; \
+      comparison = compare(&((self)->contents[mid_index] suffix), (needle)); \
+      if (comparison <= 0) *(_index) = mid_index; \
+      size -= half_size; \
+    } \
+    comparison = compare(&((self)->contents[*(_index)] suffix), (needle)); \
+    if (comparison == 0) *(_exists) = true; \
+    else if (comparison < 0) *(_index) += 1; \
+  } while (0)
+
+/// Helper macro for the `_sorted_by` routines below. This takes the left (existing)
+/// parameter by reference in order to work with the generic sorting function above.
+#define _compare_int(a, b) ((int)*(a) - (int)(b))
+
+#ifdef _MSC_VER
+#pragma warning(default : 4101)
+#elif defined(__GNUC__) || defined(__clang__)
+#pragma GCC diagnostic pop
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif  // TREE_SITTER_ARRAY_H_

src/tree_sitter/parser.h

@@ -13,9 +13,8 @@ extern "C" {
 #define ts_builtin_sym_end 0
 #define TREE_SITTER_SERIALIZATION_BUFFER_SIZE 1024
 
-typedef uint16_t TSStateId;
-
 #ifndef TREE_SITTER_API_H_
+typedef uint16_t TSStateId;
 typedef uint16_t TSSymbol;
 typedef uint16_t TSFieldId;
 typedef struct TSLanguage TSLanguage;
@@ -87,6 +86,11 @@ typedef union {
   } entry;
 } TSParseActionEntry;
 
+typedef struct {
+  int32_t start;
+  int32_t end;
+} TSCharacterRange;
+
 struct TSLanguage {
   uint32_t version;
   uint32_t symbol_count;
@@ -126,13 +130,38 @@ struct TSLanguage {
   const TSStateId *primary_state_ids;
 };
 
+static inline bool set_contains(TSCharacterRange *ranges, uint32_t len, int32_t lookahead) {
+  uint32_t index = 0;
+  uint32_t size = len - index;
+  while (size > 1) {
+    uint32_t half_size = size / 2;
+    uint32_t mid_index = index + half_size;
+    TSCharacterRange *range = &ranges[mid_index];
+    if (lookahead >= range->start && lookahead <= range->end) {
+      return true;
+    } else if (lookahead > range->end) {
+      index = mid_index;
+    }
+    size -= half_size;
+  }
+  TSCharacterRange *range = &ranges[index];
+  return (lookahead >= range->start && lookahead <= range->end);
+}
+
 /*
  *  Lexer Macros
  */
 
+#ifdef _MSC_VER
+#define UNUSED __pragma(warning(suppress : 4101))
+#else
+#define UNUSED __attribute__((unused))
+#endif
+
 #define START_LEXER()           \
   bool result = false;          \
   bool skip = false;            \
+  UNUSED                        \
   bool eof = false;             \
   int32_t lookahead;            \
   goto start;                   \
@@ -148,6 +177,17 @@ struct TSLanguage {
     goto next_state;         \
   }
 
+#define ADVANCE_MAP(...)                                              \
+  {                                                                   \
+    static const uint16_t map[] = { __VA_ARGS__ };                    \
+    for (uint32_t i = 0; i < sizeof(map) / sizeof(map[0]); i += 2) {  \
+      if (map[i] == lookahead) {                                      \
+        state = map[i + 1];                                           \
+        goto next_state;                                              \
+      }                                                               \
+    }                                                                 \
+  }
+
 #define SKIP(state_value) \
   {                       \
     skip = true;          \
@@ -166,7 +206,7 @@ struct TSLanguage {
  *  Parse Table Macros
  */
 
-#define SMALL_STATE(id) id - LARGE_STATE_COUNT
+#define SMALL_STATE(id) ((id) - LARGE_STATE_COUNT)
 
 #define STATE(id) id
 
@@ -176,7 +216,7 @@ struct TSLanguage {
   {{                                  \
     .shift = {                        \
       .type = TSParseActionTypeShift, \
-      .state = state_value            \
+      .state = (state_value)          \
     }                                 \
   }}
 
@@ -184,7 +224,7 @@ struct TSLanguage {
   {{                                  \
     .shift = {                        \
       .type = TSParseActionTypeShift, \
-      .state = state_value,           \
+      .state = (state_value),         \
       .repetition = true              \
     }                                 \
   }}
@@ -197,13 +237,14 @@ struct TSLanguage {
     }                                 \
   }}
 
-#define REDUCE(symbol_val, child_count_val, ...) \
+#define REDUCE(symbol_name, children, precedence, prod_id) \
   {{                                                       \
     .reduce = {                                            \
       .type = TSParseActionTypeReduce,                     \
-      .symbol = symbol_val,                      \
+      .symbol = symbol_name,                               \
-      .child_count = child_count_val,            \
+      .child_count = children,                             \
-      __VA_ARGS__                                \
+      .dynamic_precedence = precedence,                    \
+      .production_id = prod_id                             \
     },                                                     \
   }}
 

test/corpus/heredoc.txt

@@ -0,0 +1,435 @@
+==================
+Basic heredoc
+==================
+
+FROM busybox AS build
+
+RUN <<EOF
+echo "i am" >> /dest
+whoami >> /dest
+EOF
+
+FROM scratch
+COPY --from=build /dest /dest
+
+---
+
+(source_file
+  (from_instruction
+    (image_spec
+      (image_name))
+    (image_alias))
+  (run_instruction
+    (shell_command
+      (shell_fragment
+        (heredoc_marker)))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_end)))
+  (from_instruction
+    (image_spec
+      (image_name)))
+  (copy_instruction
+    (param)
+    (path)
+    (path)))
+
+==================
+Basic heredoc with space after marker
+==================
+
+FROM busybox AS build
+
+RUN <<EOF 
+echo "i am" >> /dest
+whoami >> /dest
+EOF
+
+FROM scratch
+COPY --from=build /dest /dest
+
+---
+
+(source_file
+  (from_instruction
+    (image_spec
+      (image_name))
+    (image_alias))
+  (run_instruction
+    (shell_command
+      (shell_fragment
+        (heredoc_marker)))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_end)))
+  (from_instruction
+    (image_spec
+      (image_name)))
+  (copy_instruction
+    (param)
+    (path)
+    (path)))
+
+==================
+Run heredoc
+==================
+
+FROM busybox AS build
+
+SHELL ["/bin/awk"]
+RUN <<EOF
+BEGIN {
+	print "foo" > "/dest"
+}
+EOF
+
+FROM scratch
+COPY --from=build /dest /dest
+
+---
+
+(source_file
+  (from_instruction
+    (image_spec
+      (image_name))
+    (image_alias))
+  (shell_instruction
+    (json_string_array
+      (json_string)))
+  (run_instruction
+    (shell_command
+      (shell_fragment
+        (heredoc_marker)))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_end)))
+  (from_instruction
+    (image_spec
+      (image_name)))
+  (copy_instruction
+    (param)
+    (path)
+    (path)))
+
+==================
+Run heredoc with shebang
+==================
+
+FROM busybox AS build
+
+RUN <<EOF
+#!/bin/awk -f
+BEGIN {
+	print "hello" >> "/dest"
+	print "world" >> "/dest"
+}
+EOF
+
+FROM scratch
+COPY --from=build /dest /dest
+
+---
+
+(source_file
+  (from_instruction
+    (image_spec
+      (image_name))
+    (image_alias))
+  (run_instruction
+    (shell_command
+      (shell_fragment
+        (heredoc_marker)))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_end)))
+  (from_instruction
+    (image_spec
+      (image_name)))
+  (copy_instruction
+    (param)
+    (path)
+    (path)))
+
+==================
+Run complex heredoc
+==================
+
+FROM busybox AS build
+
+WORKDIR /dest
+
+RUN cat <<EOF1 | tr '[:upper:]' '[:lower:]' > ./out1; \
+	cat <<EOF2 | tr '[:lower:]' '[:upper:]' > ./out2
+hello WORLD
+EOF1
+HELLO world
+EOF2
+
+RUN <<EOF 3<<IN1 4<<IN2 awk -f -
+BEGIN {
+	while ((getline line < "/proc/self/fd/3") > 0)
+		print tolower(line) > "./fd3"
+	while ((getline line < "/proc/self/fd/4") > 0)
+		print toupper(line) > "./fd4"
+}
+EOF
+hello WORLD
+IN1
+HELLO world
+IN2
+
+FROM scratch
+COPY --from=build /dest /
+
+---
+
+(source_file
+  (from_instruction
+    (image_spec
+      (image_name))
+    (image_alias))
+  (workdir_instruction
+    (path))
+  (run_instruction
+    (shell_command
+      (shell_fragment
+        (heredoc_marker))
+      (line_continuation)
+      (shell_fragment
+        (heredoc_marker)))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (run_instruction
+    (shell_command
+      (shell_fragment
+        (heredoc_marker)
+        (heredoc_marker)
+        (heredoc_marker)))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_line)
+      (heredoc_end))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (from_instruction
+    (image_spec
+      (image_name)))
+  (copy_instruction
+    (param)
+    (path)
+    (path)))
+
+=================================
+Copy with heredoc
+=================================
+
+FROM busybox AS build
+
+RUN adduser -D user
+WORKDIR /dest
+
+COPY <<EOF single
+single file
+EOF
+
+COPY <<EOF <<EOF2 double/
+first file
+EOF
+second file
+EOF2
+
+RUN mkdir -p /permfiles
+COPY --chmod=777 <<EOF /permfiles/all
+dummy content
+EOF
+COPY --chmod=0644 <<EOF /permfiles/rw
+dummy content
+EOF
+COPY --chown=user:user <<EOF /permfiles/owned
+dummy content
+EOF
+RUN stat -c "%04a" /permfiles/all >> perms && \
+  stat -c "%04a" /permfiles/rw >> perms && \
+  stat -c "%U:%G" /permfiles/owned >> perms
+
+FROM scratch
+COPY --from=build /dest /
+
+---
+
+(source_file
+  (from_instruction
+    (image_spec
+      (image_name))
+    (image_alias))
+  (run_instruction
+    (shell_command
+      (shell_fragment)))
+  (workdir_instruction
+    (path))
+  (copy_instruction
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (copy_instruction
+    (path
+      (heredoc_marker))
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (run_instruction
+    (shell_command
+      (shell_fragment)))
+  (copy_instruction
+    (param)
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (copy_instruction
+    (param)
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (copy_instruction
+    (param)
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (run_instruction
+    (shell_command
+      (shell_fragment)
+      (line_continuation)
+      (shell_fragment)
+      (line_continuation)
+      (shell_fragment)))
+  (from_instruction
+    (image_spec
+      (image_name)))
+  (copy_instruction
+    (param)
+    (path)
+    (path)))
+
+==================
+Heredoc with special symbols
+==================
+
+FROM scratch
+
+COPY <<EOF quotefile
+"quotes in file"
+EOF
+
+COPY <<EOF slashfile1
+\
+EOF
+COPY <<EOF slashfile2
+\\
+EOF
+COPY <<EOF slashfile3
+\$
+EOF
+
+COPY <<"EOF" rawslashfile1
+\
+EOF
+COPY <<"EOF" rawslashfile2
+\\
+EOF
+COPY <<"EOF" rawslashfile3
+\$
+EOF
+
+---
+
+(source_file
+  (from_instruction
+    (image_spec
+      (image_name)))
+  (copy_instruction
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (copy_instruction
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (copy_instruction
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (copy_instruction
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (copy_instruction
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (copy_instruction
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end)))
+  (copy_instruction
+    (path
+      (heredoc_marker))
+    (path)
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end))))

test/corpus/run.txt

@@ -78,3 +78,22 @@ run --mount=type=secret,id=aws,target=/root/.aws/credentials \
     (line_continuation)
     (shell_command
       (shell_fragment))))
+
+==================
+Run with heredoc
+==================
+
+RUN cat <<EOF
+test
+EOF
+
+---
+
+(source_file
+  (run_instruction
+    (shell_command
+      (shell_fragment
+        (heredoc_marker)))
+    (heredoc_block
+      (heredoc_line)
+      (heredoc_end))))