fix(install): vendor tree-sitter-dart source (#1125)

Avoid remote git/SSH downloads for the Dart grammar during Docker and npm installs by resolving tree-sitter-dart from vendored source and building it during postinstall.

Made-with: Cursor
This commit is contained in:
Gergő Magyar
2026-04-27 21:15:37 +01:00
committed by GitHub
parent 38ccf7ceb1
commit 780ee83d52
22 changed files with 227807 additions and 28 deletions
+16 -26
View File
@@ -65,7 +65,7 @@
"optionalDependencies": {
"node-addon-api": "^8.0.0",
"node-gyp-build": "^4.8.0",
"tree-sitter-dart": "git+https://github.com/UserNobody14/tree-sitter-dart.git#80e23c07b64494f7e21090bb3450223ef0b192f4",
"tree-sitter-dart": "file:./vendor/tree-sitter-dart",
"tree-sitter-kotlin": "^0.3.8",
"tree-sitter-proto": "file:./vendor/tree-sitter-proto",
"tree-sitter-swift": "^0.6.0"
@@ -5100,31 +5100,8 @@
}
},
"node_modules/tree-sitter-dart": {
"version": "1.0.0",
"resolved": "git+ssh://git@github.com/UserNobody14/tree-sitter-dart.git#80e23c07b64494f7e21090bb3450223ef0b192f4",
"integrity": "sha512-Bs/1wAOIJ2akPEXlE/XVpuES19Oo3NqoSJRJ/0N2r38qAd9nTXdqmaGHQ44/JXnA6QHcbgD2YzCCc4wUc98cyQ==",
"hasInstallScript": true,
"license": "ISC",
"optional": true,
"dependencies": {
"node-addon-api": "^7.1.0",
"node-gyp-build": "^4.8.0"
},
"peerDependencies": {
"tree-sitter": "^0.21.0"
},
"peerDependenciesMeta": {
"tree_sitter": {
"optional": true
}
}
},
"node_modules/tree-sitter-dart/node_modules/node-addon-api": {
"version": "7.1.1",
"resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-7.1.1.tgz",
"integrity": "sha512-5m3bsyrjFWE1xf7nz7YXdN4udnVtXK6/Yfgn5qnahL6bCkf2yKt4k3nuTKAtT4r3IG8JNR2ncsIMdZuAzJjHQQ==",
"license": "MIT",
"optional": true
"resolved": "vendor/tree-sitter-dart",
"link": true
},
"node_modules/tree-sitter-go": {
"version": "0.23.4",
@@ -5768,6 +5745,19 @@
"zod": "^3.25.28 || ^4"
}
},
"vendor/tree-sitter-dart": {
"version": "1.0.0",
"license": "ISC",
"optional": true,
"peerDependencies": {
"tree-sitter": "^0.21.0"
},
"peerDependenciesMeta": {
"tree_sitter": {
"optional": true
}
}
},
"vendor/tree-sitter-proto": {
"version": "0.4.1",
"license": "MIT",
+2 -2
View File
@@ -47,7 +47,7 @@
"test:integration": "vitest run test/integration",
"test:watch": "vitest",
"test:coverage": "vitest run --coverage",
"postinstall": "node scripts/patch-tree-sitter-swift.cjs && node scripts/build-tree-sitter-proto.cjs",
"postinstall": "node scripts/patch-tree-sitter-swift.cjs && node scripts/build-tree-sitter-dart.cjs && node scripts/build-tree-sitter-proto.cjs",
"prepare": "node scripts/build.js",
"prepack": "node scripts/build.js"
},
@@ -88,7 +88,7 @@
"optionalDependencies": {
"node-addon-api": "^8.0.0",
"node-gyp-build": "^4.8.0",
"tree-sitter-dart": "git+https://github.com/UserNobody14/tree-sitter-dart.git#80e23c07b64494f7e21090bb3450223ef0b192f4",
"tree-sitter-dart": "file:./vendor/tree-sitter-dart",
"tree-sitter-kotlin": "^0.3.8",
"tree-sitter-proto": "file:./vendor/tree-sitter-proto",
"tree-sitter-swift": "^0.6.0"
@@ -0,0 +1,42 @@
#!/usr/bin/env node
const fs = require('fs');
const path = require('path');
const { execSync } = require('child_process');
const dartDir = path.join(__dirname, '..', 'node_modules', 'tree-sitter-dart');
const bindingGyp = path.join(dartDir, 'binding.gyp');
const bindingNode = path.join(dartDir, 'build', 'Release', 'tree_sitter_dart_binding.node');
try {
if (!fs.existsSync(bindingGyp) || fs.existsSync(bindingNode)) {
process.exit(0);
}
try {
require.resolve('node-addon-api');
require.resolve('node-gyp-build');
} catch (resolveErr) {
console.warn(
'[tree-sitter-dart] Skipping build: hoisted build deps not resolvable (%s).',
resolveErr.message,
);
console.warn(
'[tree-sitter-dart] Dart parsing will be unavailable. Install without --no-optional and with scripts enabled to build.',
);
process.exit(0);
}
console.log('[tree-sitter-dart] Building native binding...');
execSync('npx node-gyp rebuild', {
cwd: dartDir,
stdio: 'pipe',
timeout: 180000,
});
console.log('[tree-sitter-dart] Native binding built successfully');
} catch (err) {
console.warn('[tree-sitter-dart] Could not build native binding:', err.message);
console.warn(
'[tree-sitter-dart] Dart parsing will be unavailable. Non-Dart functionality is unaffected.',
);
process.exit(0);
}
+9
View File
@@ -41,6 +41,15 @@ describe('CLI commands', () => {
});
});
describe('optional parser dependencies', () => {
it('uses vendored source for tree-sitter-dart instead of a remote dependency', async () => {
const pkg = await import('../../package.json', { with: { type: 'json' } });
expect(pkg.default.optionalDependencies['tree-sitter-dart']).toBe(
'file:./vendor/tree-sitter-dart',
);
});
});
describe('analyzeCommand', () => {
it('is a function', async () => {
const { analyzeCommand } = await import('../../src/cli/analyze.js');
@@ -0,0 +1,2 @@
build/
node_modules/
+18
View File
@@ -0,0 +1,18 @@
# tree-sitter-dart
This is a tree-sitter grammar written for the dart programming language. We attempt to adhere as closely as possible to the dart language spec. Initially it was started with a copy of the tree-sitter Java grammar which is why there may be a few relics included in here. For the sake of simplifying the syntax tree, many items were made inlined with tree-sitter's "underscore" method of writing rules.
# Getting Started
- Go to the project directory
- run `npm install` (first time)
- run `npm run build_init` (first time) `npm run build` (subsequent times)
- run `npm run test`
# To test a single highlight file
- run `tree-sitter highlight test/highlight/types.dart`
# To test a single test file
- run `tree-sitter test -f 'testcasefilter'`
- for example `tree-sitter test -f 'dart string literals'`
# To show the output of a parse for a sample file (for example while debugging highlight issues)
- run `tree-sitter parse path/to/file.dart`
+31
View File
@@ -0,0 +1,31 @@
{
"targets": [
{
"target_name": "tree_sitter_dart_binding",
"dependencies": [
"<!(node -p \"require('node-addon-api').targets\"):node_addon_api_except",
],
"include_dirs": [
"src",
],
"sources": [
"bindings/node/binding.cc",
"src/parser.c",
# NOTE: if your language has an external scanner, add it here.
"src/scanner.c",
],
"conditions": [
["OS!='win'", {
"cflags_c": [
"-std=c11",
],
}, { # OS == "win"
"cflags_c": [
"/std:c11",
"/utf-8",
],
}],
],
}
]
}
@@ -0,0 +1,20 @@
#include <napi.h>
typedef struct TSLanguage TSLanguage;
extern "C" TSLanguage *tree_sitter_dart();
// "tree-sitter", "language" hashed with BLAKE2
const napi_type_tag LANGUAGE_TYPE_TAG = {
0x8AF2E5212AD58ABF, 0xD5006CAD83ABBA16
};
Napi::Object Init(Napi::Env env, Napi::Object exports) {
exports["name"] = Napi::String::New(env, "dart");
auto language = Napi::External<TSLanguage>::New(env, tree_sitter_dart());
language.TypeTag(&LANGUAGE_TYPE_TAG);
exports["language"] = language;
return exports;
}
NODE_API_MODULE(tree_sitter_dart_binding, Init)
@@ -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;
@@ -0,0 +1,7 @@
const root = require("path").join(__dirname, "..", "..");
module.exports = require("node-gyp-build")(root);
try {
module.exports.nodeTypeInfo = require("../../src/node-types.json");
} catch (_) {}
File diff suppressed because it is too large Load Diff
+18
View File
@@ -0,0 +1,18 @@
{
"name": "tree-sitter-dart",
"version": "1.0.0",
"description": "Dart grammar attempt for tree-sitter",
"repository": "https://github.com/UserNobody14/tree-sitter-dart",
"license": "ISC",
"main": "bindings/node",
"types": "bindings/node",
"_vendoredBy": "gitnexus - pinned to UserNobody14/tree-sitter-dart commit 80e23c07b64494f7e21090bb3450223ef0b192f4. Build deps are hoisted into gitnexus/package.json optionalDependencies, and native compilation is performed by gitnexus/scripts/build-tree-sitter-dart.cjs at gitnexus postinstall.",
"peerDependencies": {
"tree-sitter": "^0.21.0"
},
"peerDependenciesMeta": {
"tree_sitter": {
"optional": true
}
}
}
+246
View File
@@ -0,0 +1,246 @@
; Variable
(identifier) @variable
; Keywords
; --------------------
[
(assert_builtin)
(break_builtin)
(const_builtin)
(part_of_builtin)
(rethrow_builtin)
(void_type)
"abstract"
"as"
"async"
"async*"
"await"
"base"
"case"
"catch"
"class"
"continue"
"covariant"
"default"
"deferred"
"do"
"dynamic"
"else"
"enum"
"export"
"extends"
"extension"
"external"
"factory"
"final"
"finally"
"for"
"Function"
"get"
"hide"
"if"
"implements"
"import"
"in"
"interface"
"is"
"late"
"library"
"mixin"
"new"
"on"
"operator"
"part"
"required"
"return"
"sealed"
"set"
"show"
"static"
"super"
"switch"
"sync*"
"throw"
"try"
"typedef"
"var"
"when"
"while"
"with"
"yield"
] @keyword
; Methods
; --------------------
; NOTE: This query is a bit of a work around for the fact that the dart grammar doesn't
; specifically identify a node as a function call
(((identifier) @function (#match? @function "^_?[a-z]"))
. (selector . (argument_part))) @function
; Annotations
; --------------------
(annotation
name: (identifier) @attribute)
; Operators and Tokens
; --------------------
(template_substitution
"$" @punctuation.special
"{" @punctuation.special
"}" @punctuation.special
) @none
(template_substitution
"$" @punctuation.special
(identifier_dollar_escaped) @variable
) @none
(escape_sequence) @string.escape
[
"@"
"=>"
".."
"??"
"=="
"?"
":"
"&&"
"%"
"<"
">"
"="
">="
"<="
"||"
"~/"
(increment_operator)
(is_operator)
(prefix_operator)
(equality_operator)
(additive_operator)
] @operator
(type_arguments
"<" @punctuation.bracket
">" @punctuation.bracket)
(type_parameters
"<" @punctuation.bracket
">" @punctuation.bracket)
[
"("
")"
"["
"]"
"{"
"}"
] @punctuation.bracket
; Delimiters
; --------------------
[
";"
"."
","
] @punctuation.delimiter
; Types
; --------------------
(type_identifier) @type
((type_identifier) @type.builtin
(#match? @type.builtin "^(int|double|String|bool|List|Set|Map|Runes|Symbol)$"))
(class_definition
name: (identifier) @type)
(constructor_signature
name: (identifier) @type)
(scoped_identifier
scope: (identifier) @type)
(function_signature
name: (identifier) @function)
(getter_signature
(identifier) @function)
(setter_signature
name: (identifier) @function)
((scoped_identifier
scope: (identifier) @type
name: (identifier) @type)
(#match? @type "^[a-zA-Z]"))
; Enums
; -------------------
(enum_declaration
name: (identifier) @type)
(enum_constant
name: (identifier) @identifier.constant)
; Variables
; --------------------
; var keyword
(inferred_type) @keyword
((identifier) @type
(#match? @type "^_?[A-Z].*[a-z]"))
("Function" @type)
(this) @variable.builtin
; properties
(unconditional_assignable_selector
(identifier) @property)
(conditional_assignable_selector
(identifier) @property)
(cascade_section
(cascade_selector
(identifier) @property))
((selector
(unconditional_assignable_selector (identifier) @function))
(selector (argument_part (arguments)))
)
(cascade_section
(cascade_selector (identifier) @function)
(argument_part (arguments))
)
; assignments
(assignment_expression
left: (assignable_expression) @variable)
(this) @variable.builtin
; Parameters
; --------------------
(formal_parameter
name: (identifier) @identifier.parameter)
(named_argument
(label (identifier) @identifier.parameter))
; Literals
; --------------------
[
(hex_integer_literal)
(decimal_integer_literal)
(decimal_floating_point_literal)
; TODO: inaccessbile nodes
; (octal_integer_literal)
; (hex_floating_point_literal)
] @number
(string_literal) @string
(symbol_literal (identifier) @constant) @constant
(true) @boolean
(false) @boolean
(null_literal) @constant.null
(documentation_comment) @comment
(comment) @comment
+92
View File
@@ -0,0 +1,92 @@
(class_definition
name: (identifier) @name) @definition.class
(method_signature
(function_signature)) @definition.method
(type_alias
(type_identifier) @name) @definition.type
(method_signature
(getter_signature
name: (identifier) @name)) @definition.method
(method_signature
(setter_signature
name: (identifier) @name)) @definition.method
(method_signature
(function_signature
name: (identifier) @name)) @definition.method
(method_signature
(factory_constructor_signature
(identifier) @name)) @definition.method
(method_signature
(constructor_signature
name: (identifier) @name)) @definition.method
(method_signature
(operator_signature)) @definition.method
(method_signature) @definition.method
(mixin_declaration
(mixin)
(identifier) @name) @definition.mixin
(extension_declaration
name: (identifier) @name) @definition.extension
(new_expression
(type_identifier) @name) @reference.class
(enum_declaration
name: (identifier) @name) @definition.enum
(function_signature
name: (identifier) @name) @definition.function
(initialized_variable_definition
name: (identifier)
value: (identifier) @name
value: (selector
"!"?
(argument_part
(arguments
(argument)*))?)?) @reference.class
(assignment_expression
left: (assignable_expression
(identifier)
(unconditional_assignable_selector
"."
(identifier) @name))) @reference.call
(assignment_expression
left: (assignable_expression
(identifier)
(conditional_assignable_selector
"?."
(identifier) @name))) @reference.call
((identifier) @name
(selector
"!"?
(conditional_assignable_selector
"?." (identifier) @name)?
(unconditional_assignable_selector
"."? (identifier) @name)?
(argument_part
(arguments
(argument)*))?)*
(cascade_section
(cascade_selector
(identifier)) @name
(argument_part
(arguments
(argument)*))?)?) @reference.call
+1
View File
@@ -0,0 +1 @@
(if_statement (block))
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+130
View File
@@ -0,0 +1,130 @@
#include "tree_sitter/parser.h"
#include <wctype.h>
enum TokenType {
TEMPLATE_CHARS_SINGLE,
TEMPLATE_CHARS_DOUBLE,
TEMPLATE_CHARS_SINGLE_SINGLE,
TEMPLATE_CHARS_DOUBLE_SINGLE,
TEMPLATE_CHARS_RAW_SLASH,
BLOCK_COMMENT,
DOCUMENTATION_BLOCK_COMMENT,
};
void *tree_sitter_dart_external_scanner_create() { return NULL; }
void tree_sitter_dart_external_scanner_destroy(void *p) {}
void tree_sitter_dart_external_scanner_reset(void *p) {}
unsigned tree_sitter_dart_external_scanner_serialize(void *p, char *buffer) { return 0; }
void tree_sitter_dart_external_scanner_deserialize(void *p, const char *b, unsigned n) {}
static void advance(TSLexer *lexer) { lexer->advance(lexer, false); }
static void skip(TSLexer *lexer) { lexer->advance(lexer, true); }
static bool scan_multiline_comments(TSLexer *lexer) {
bool documentation_comment = false;
advance(lexer);
if (lexer->lookahead != '*') return false;
advance(lexer);
if (lexer->lookahead == '*') documentation_comment = true;
bool after_star = false;
unsigned nesting_depth = 1;
for (;;) {
switch (lexer->lookahead) {
case '\0':
return false;
case '*':
advance(lexer);
after_star = true;
break;
case '/':
if (after_star) {
advance(lexer);
after_star = false;
nesting_depth--;
if (nesting_depth == 0) {
if (!documentation_comment) {
lexer->result_symbol = BLOCK_COMMENT;
} else {
lexer->result_symbol = DOCUMENTATION_BLOCK_COMMENT;
}
return true;
}
} else {
advance(lexer);
after_star = false;
if (lexer->lookahead == '*') {
nesting_depth++;
advance(lexer);
}
}
break;
default:
advance(lexer);
after_star = false;
break;
}
}
return false;
}
static bool scan_templates(TSLexer *lexer, const bool *valid_symbols) {
if(valid_symbols[TEMPLATE_CHARS_DOUBLE]) {
lexer->result_symbol = TEMPLATE_CHARS_DOUBLE;
} else if (valid_symbols[TEMPLATE_CHARS_SINGLE]) {
lexer->result_symbol = TEMPLATE_CHARS_SINGLE;
} else if (valid_symbols[TEMPLATE_CHARS_SINGLE_SINGLE]) {
lexer->result_symbol = TEMPLATE_CHARS_SINGLE_SINGLE;
} else {
lexer->result_symbol = TEMPLATE_CHARS_DOUBLE_SINGLE;
}
for (bool has_content = false;; has_content = true) {
lexer->mark_end(lexer);
switch (lexer->lookahead) {
case '\'':
case '"':
return has_content;
case '\n':
if (valid_symbols[TEMPLATE_CHARS_DOUBLE_SINGLE] || valid_symbols[TEMPLATE_CHARS_SINGLE_SINGLE]) return false;
advance(lexer);
break;
case '\0':
return false;
case '$':
return has_content;
case '\\':
if (valid_symbols[TEMPLATE_CHARS_RAW_SLASH]) {
lexer->result_symbol = TEMPLATE_CHARS_RAW_SLASH;
advance(lexer);
} else {
return has_content;
}
break;
default:
advance(lexer);
}
}
return true;
}
bool tree_sitter_dart_external_scanner_scan(void *payload, TSLexer *lexer,
const bool *valid_symbols) {
if (
valid_symbols[TEMPLATE_CHARS_DOUBLE] ||
valid_symbols[TEMPLATE_CHARS_SINGLE] ||
valid_symbols[TEMPLATE_CHARS_DOUBLE_SINGLE] ||
valid_symbols[TEMPLATE_CHARS_SINGLE_SINGLE]
) {
return scan_templates(lexer, valid_symbols);
}
while (iswspace(lexer->lookahead)) lexer->advance(lexer, true);
if (lexer->lookahead == '/') {
return scan_multiline_comments(lexer);
}
return false;
}
@@ -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_
+290
View File
@@ -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_
@@ -0,0 +1,265 @@
#ifndef TREE_SITTER_PARSER_H_
#define TREE_SITTER_PARSER_H_
#ifdef __cplusplus
extern "C" {
#endif
#include <stdbool.h>
#include <stdint.h>
#include <stdlib.h>
#define ts_builtin_sym_error ((TSSymbol)-1)
#define ts_builtin_sym_end 0
#define TREE_SITTER_SERIALIZATION_BUFFER_SIZE 1024
#ifndef TREE_SITTER_API_H_
typedef uint16_t TSStateId;
typedef uint16_t TSSymbol;
typedef uint16_t TSFieldId;
typedef struct TSLanguage TSLanguage;
#endif
typedef struct {
TSFieldId field_id;
uint8_t child_index;
bool inherited;
} TSFieldMapEntry;
typedef struct {
uint16_t index;
uint16_t length;
} TSFieldMapSlice;
typedef struct {
bool visible;
bool named;
bool supertype;
} TSSymbolMetadata;
typedef struct TSLexer TSLexer;
struct TSLexer {
int32_t lookahead;
TSSymbol result_symbol;
void (*advance)(TSLexer *, bool);
void (*mark_end)(TSLexer *);
uint32_t (*get_column)(TSLexer *);
bool (*is_at_included_range_start)(const TSLexer *);
bool (*eof)(const TSLexer *);
};
typedef enum {
TSParseActionTypeShift,
TSParseActionTypeReduce,
TSParseActionTypeAccept,
TSParseActionTypeRecover,
} TSParseActionType;
typedef union {
struct {
uint8_t type;
TSStateId state;
bool extra;
bool repetition;
} shift;
struct {
uint8_t type;
uint8_t child_count;
TSSymbol symbol;
int16_t dynamic_precedence;
uint16_t production_id;
} reduce;
uint8_t type;
} TSParseAction;
typedef struct {
uint16_t lex_state;
uint16_t external_lex_state;
} TSLexMode;
typedef union {
TSParseAction action;
struct {
uint8_t count;
bool reusable;
} entry;
} TSParseActionEntry;
typedef struct {
int32_t start;
int32_t end;
} TSCharacterRange;
struct TSLanguage {
uint32_t version;
uint32_t symbol_count;
uint32_t alias_count;
uint32_t token_count;
uint32_t external_token_count;
uint32_t state_count;
uint32_t large_state_count;
uint32_t production_id_count;
uint32_t field_count;
uint16_t max_alias_sequence_length;
const uint16_t *parse_table;
const uint16_t *small_parse_table;
const uint32_t *small_parse_table_map;
const TSParseActionEntry *parse_actions;
const char * const *symbol_names;
const char * const *field_names;
const TSFieldMapSlice *field_map_slices;
const TSFieldMapEntry *field_map_entries;
const TSSymbolMetadata *symbol_metadata;
const TSSymbol *public_symbol_map;
const uint16_t *alias_map;
const TSSymbol *alias_sequences;
const TSLexMode *lex_modes;
bool (*lex_fn)(TSLexer *, TSStateId);
bool (*keyword_lex_fn)(TSLexer *, TSStateId);
TSSymbol keyword_capture_token;
struct {
const bool *states;
const TSSymbol *symbol_map;
void *(*create)(void);
void (*destroy)(void *);
bool (*scan)(void *, TSLexer *, const bool *symbol_whitelist);
unsigned (*serialize)(void *, char *);
void (*deserialize)(void *, const char *, unsigned);
} external_scanner;
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; \
next_state: \
lexer->advance(lexer, skip); \
start: \
skip = false; \
lookahead = lexer->lookahead;
#define ADVANCE(state_value) \
{ \
state = state_value; \
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; \
state = state_value; \
goto next_state; \
}
#define ACCEPT_TOKEN(symbol_value) \
result = true; \
lexer->result_symbol = symbol_value; \
lexer->mark_end(lexer);
#define END_STATE() return result;
/*
* Parse Table Macros
*/
#define SMALL_STATE(id) ((id) - LARGE_STATE_COUNT)
#define STATE(id) id
#define ACTIONS(id) id
#define SHIFT(state_value) \
{{ \
.shift = { \
.type = TSParseActionTypeShift, \
.state = (state_value) \
} \
}}
#define SHIFT_REPEAT(state_value) \
{{ \
.shift = { \
.type = TSParseActionTypeShift, \
.state = (state_value), \
.repetition = true \
} \
}}
#define SHIFT_EXTRA() \
{{ \
.shift = { \
.type = TSParseActionTypeShift, \
.extra = true \
} \
}}
#define REDUCE(symbol_name, children, precedence, prod_id) \
{{ \
.reduce = { \
.type = TSParseActionTypeReduce, \
.symbol = symbol_name, \
.child_count = children, \
.dynamic_precedence = precedence, \
.production_id = prod_id \
}, \
}}
#define RECOVER() \
{{ \
.type = TSParseActionTypeRecover \
}}
#define ACCEPT_INPUT() \
{{ \
.type = TSParseActionTypeAccept \
}}
#ifdef __cplusplus
}
#endif
#endif // TREE_SITTER_PARSER_H_