feat(group): add tree-sitter-proto for .proto file parsing

Addresses @magyargergo's suggestion on #796 to replace the manual
string-sanitizing .proto parser with a tree-sitter grammar.

- **Vendored `tree-sitter-proto`** in `vendor/tree-sitter-proto/`.
  Grammar source from [coder3101/tree-sitter-proto](https://github.com/coder3101/tree-sitter-proto)
  (latest `grammar.js`), parser.c regenerated with `tree-sitter-cli
  0.24` to produce ABI version 14 — compatible with the project's
  `tree-sitter 0.25` runtime (which supports ABI ≤ 14). Added as
  `optionalDependency` with `file:./vendor/tree-sitter-proto`.

- **New `grpc-patterns/proto.ts` plugin** — uses the same
  `compilePatterns` + `runCompiledPatterns` infrastructure as every
  other plugin. Two queries:
  - `(package (full_ident) @pkg)` — package declaration
  - `(service (service_name) @service_name (rpc (rpc_name) @rpc_name))`
    — one match per (service, rpc) pair

- **Graceful fallback** — `tree-sitter-proto` is an optional
  dependency. If it fails to install (platform incompatibility) or
  fails the runtime smoke-test (`setLanguage` + `parse` on a trivial
  proto), `PROTO_GRPC_PLUGIN` stays `null` and the orchestrator
  uses the existing manual parser. The smoke-test catches the
  `SyntaxNode` TDZ error that occurs in vitest's fork-based test
  runner.

- **Orchestrator updated** — when `hasProtoPlugin` is true, `.proto`
  files are handled by the plugin loop (they're included in
  `GRPC_SCAN_GLOB`), and the manual `parseProtoFile` loop is
  skipped. `buildProtoContext` still runs to build the proto map
  for cross-referencing source-file detections.

1. **No manual comment/string stripping.** The old parser needed
   `stripProtoCommentsAndStrings` (110 lines) to avoid counting
   braces inside comments and string literals. tree-sitter handles
   this natively.
2. **No brace-depth tracking.** `extractServiceBlocks` used a manual
   depth counter to find service boundaries. tree-sitter's AST gives
   us `service` → `service_name` + `rpc` → `rpc_name` directly.
3. **Performance.** tree-sitter's C-based parser is faster than
   character-by-character JS scanning + regex on large proto files.

- `grpc-extractor.test.ts` — **43/43 pass** (unchanged)
- All other extractor tests — 99/99 pass
- `npx tsc -p tsconfig.json --noEmit` clean

Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
ivkond 2026-04-12 12:39:50 +00:00 committed by Claude
parent 2d9a830aa0
commit 62d2dc1c75
No known key found for this signature in database
15 changed files with 12232 additions and 28 deletions

View file

@ -65,6 +65,7 @@
"optionalDependencies": {
"tree-sitter-dart": "github:UserNobody14/tree-sitter-dart#80e23c07b64494f7e21090bb3450223ef0b192f4",
"tree-sitter-kotlin": "^0.3.8",
"tree-sitter-proto": "file:./vendor/tree-sitter-proto",
"tree-sitter-swift": "^0.6.0"
}
},
@ -5296,6 +5297,10 @@
"node": "^18 || ^20 || >= 21"
}
},
"node_modules/tree-sitter-proto": {
"resolved": "vendor/tree-sitter-proto",
"link": true
},
"node_modules/tree-sitter-python": {
"version": "0.23.4",
"resolved": "https://registry.npmjs.org/tree-sitter-python/-/tree-sitter-python-0.23.4.tgz",
@ -5877,6 +5882,29 @@
"peerDependencies": {
"zod": "^3.25.28 || ^4"
}
},
"vendor/tree-sitter-proto": {
"version": "0.4.1",
"hasInstallScript": true,
"license": "MIT",
"optional": true,
"dependencies": {
"node-addon-api": "^8.0.0",
"node-gyp-build": "^4.8.0"
},
"peerDependencies": {
"tree-sitter": ">=0.21.0"
}
},
"vendor/tree-sitter-proto/node_modules/node-addon-api": {
"version": "8.7.0",
"resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-8.7.0.tgz",
"integrity": "sha512-9MdFxmkKaOYVTV+XVRG8ArDwwQ77XIgIPyKASB1k3JPq3M8fGQQQE3YpMOrKm6g//Ktx8ivZr8xo1Qmtqub+GA==",
"license": "MIT",
"optional": true,
"engines": {
"node": "^18 || ^20 || >= 21"
}
}
}
}

View file

@ -87,6 +87,7 @@
"optionalDependencies": {
"tree-sitter-dart": "github:UserNobody14/tree-sitter-dart#80e23c07b64494f7e21090bb3450223ef0b192f4",
"tree-sitter-kotlin": "^0.3.8",
"tree-sitter-proto": "file:./vendor/tree-sitter-proto",
"tree-sitter-swift": "^0.6.0"
},
"devDependencies": {

View file

@ -4,7 +4,12 @@ import { glob } from 'glob';
import Parser from 'tree-sitter';
import type { ContractExtractor, CypherExecutor } from '../contract-extractor.js';
import type { ExtractedContract, RepoHandle } from '../types.js';
import { GRPC_SCAN_GLOB, getPluginForFile, type GrpcDetection } from './grpc-patterns/index.js';
import {
GRPC_SCAN_GLOB,
getPluginForFile,
hasProtoPlugin,
type GrpcDetection,
} from './grpc-patterns/index.js';
/**
* Language-agnostic orchestrator for gRPC (provider + consumer) contract
@ -362,28 +367,33 @@ export class GrpcExtractor implements ContractExtractor {
): Promise<ExtractedContract[]> {
const out: ExtractedContract[] = [];
const protoContext = await buildProtoContext(repoPath);
// ─── Proto files — definitive provider source ─────────────────
const protoFiles = await glob('**/*.proto', {
cwd: repoPath,
ignore: ['**/node_modules/**', '**/.git/**', '**/vendor/**'],
nodir: true,
});
for (const rel of protoFiles) {
const content = readSafe(repoPath, rel);
if (content) {
out.push(
...this.parseProtoFile(
content,
rel,
protoContext.packagesByProto.get(normalizeProtoPath(rel)) ?? '',
),
);
}
}
const protoMap = protoContext.servicesByName;
// ─── Source files — delegate to per-language plugins ──────────
// ─── Proto files — definitive provider source ─────────────────
// When tree-sitter-proto is available, .proto files are handled by
// the plugin loop below (they're in GRPC_SCAN_GLOB). Otherwise
// fall back to the manual string-sanitizing parser.
if (!hasProtoPlugin) {
const protoFiles = await glob('**/*.proto', {
cwd: repoPath,
ignore: ['**/node_modules/**', '**/.git/**', '**/vendor/**'],
nodir: true,
});
for (const rel of protoFiles) {
const content = readSafe(repoPath, rel);
if (content) {
out.push(
...this.parseProtoFile(
content,
rel,
protoContext.packagesByProto.get(normalizeProtoPath(rel)) ?? '',
),
);
}
}
}
// ─── Source files (+ .proto when plugin available) ────────────
const sourceFiles = await glob(GRPC_SCAN_GLOB, {
cwd: repoPath,
ignore: ['**/node_modules/**', '**/.git/**', '**/vendor/**', '**/dist/**', '**/build/**'],

View file

@ -4,16 +4,18 @@ import { GO_GRPC_PLUGIN } from './go.js';
import { JAVA_GRPC_PLUGIN } from './java.js';
import { PYTHON_GRPC_PLUGIN } from './python.js';
import { JAVASCRIPT_GRPC_PLUGIN, TYPESCRIPT_GRPC_PLUGIN, TSX_GRPC_PLUGIN } from './node.js';
import { PROTO_GRPC_PLUGIN } from './proto.js';
export type { GrpcDetection, GrpcLanguagePlugin, GrpcRole } from './types.js';
export { PROTO_GRPC_PLUGIN, extractPackageFromTree } from './proto.js';
/**
* File-extension gRPC language plugin registry. Mirrors the shape
* of `http-patterns/index.ts` and `topic-patterns/index.ts`.
*
* To add a new language drop a `grpc-patterns/<lang>.ts` exporting a
* `GrpcLanguagePlugin`, import + register it here, and widen
* `GRPC_SCAN_GLOB` if needed. No edits to `grpc-extractor.ts` required.
* `.proto` files are registered only when `tree-sitter-proto` is
* available (it's an optionalDependency). When absent, the orchestrator
* falls back to the built-in manual proto parser.
*/
const REGISTRY: Record<string, GrpcLanguagePlugin> = {
'.go': GO_GRPC_PLUGIN,
@ -23,15 +25,23 @@ const REGISTRY: Record<string, GrpcLanguagePlugin> = {
'.jsx': JAVASCRIPT_GRPC_PLUGIN,
'.ts': TYPESCRIPT_GRPC_PLUGIN,
'.tsx': TSX_GRPC_PLUGIN,
...(PROTO_GRPC_PLUGIN ? { '.proto': PROTO_GRPC_PLUGIN } : {}),
};
/**
* Glob for source files worth scanning for gRPC server/client patterns.
* `.proto` files are handled directly by the orchestrator's in-tree
* string-sanitizing parser (no `tree-sitter-proto` grammar is
* installed).
* Includes `.proto` when the grammar is available.
*/
export const GRPC_SCAN_GLOB = '**/*.{go,java,py,ts,tsx,js,jsx}';
export const GRPC_SCAN_GLOB = PROTO_GRPC_PLUGIN
? '**/*.{go,java,py,ts,tsx,js,jsx,proto}'
: '**/*.{go,java,py,ts,tsx,js,jsx}';
/**
* Whether the tree-sitter proto plugin is available. The orchestrator
* uses this to decide between the tree-sitter path and the fallback
* manual parser for `.proto` files.
*/
export const hasProtoPlugin = PROTO_GRPC_PLUGIN !== null;
/**
* Return the gRPC plugin registered for the given file's extension,

View file

@ -0,0 +1,147 @@
import { createRequire } from 'node:module';
import {
compilePatterns,
runCompiledPatterns,
type CompiledPatterns,
type LanguagePatterns,
} from '../tree-sitter-scanner.js';
import type { GrpcDetection, GrpcLanguagePlugin } from './types.js';
/**
* Protobuf (.proto) tree-sitter plugin for gRPC contract extraction.
*
* Uses `tree-sitter-proto` (coder3101/tree-sitter-proto) as an
* optionalDependency if the grammar is not installed (e.g. native
* compilation failed on an unusual platform), the plugin exports
* `null` and the orchestrator falls back to the existing manual
* string-sanitizing parser.
*
* The grammar is vendored in `vendor/tree-sitter-proto/` with
* parser.c regenerated against tree-sitter-cli 0.24 (ABI version 14)
* so it is compatible with the project's tree-sitter 0.25 runtime.
*/
const _require = createRequire(import.meta.url);
let ProtoGrammar: unknown = null;
try {
ProtoGrammar = _require('tree-sitter-proto');
} catch {
// Grammar not installed — PROTO_GRPC_PLUGIN will be null.
}
let PACKAGE_PATTERNS: CompiledPatterns<Record<string, never>> | null = null;
let SERVICE_PATTERNS: CompiledPatterns<Record<string, never>> | null = null;
if (ProtoGrammar) {
try {
// Validate that the grammar actually loads end-to-end: compile queries
// AND parse + walk a trivial proto file. tree-sitter's internal
// `initializeLanguageNodeClasses` can fail with a TDZ error in some
// test runners (vitest forks) when SyntaxNode isn't fully initialized
// yet. Catching that here ensures `PROTO_GRPC_PLUGIN` stays null and
// the orchestrator falls back to the manual parser.
// eslint-disable-next-line @typescript-eslint/no-explicit-any
const _Parser = _require('tree-sitter') as any;
// Smoke-test: parse + setLanguage to verify the grammar is
// end-to-end compatible with this tree-sitter runtime.
const _testParser = new _Parser();
_testParser.setLanguage(ProtoGrammar);
_testParser.parse('service X { rpc Y (R) returns (R); }');
PACKAGE_PATTERNS = compilePatterns({
name: 'proto-package',
language: ProtoGrammar,
patterns: [
{
meta: {},
query: `(package (full_ident) @pkg)`,
},
],
} satisfies LanguagePatterns<Record<string, never>>);
SERVICE_PATTERNS = compilePatterns({
name: 'proto-service',
language: ProtoGrammar,
patterns: [
{
meta: {},
query: `
(service
(service_name) @service_name
(rpc
(rpc_name) @rpc_name))
`,
},
],
} satisfies LanguagePatterns<Record<string, never>>);
} catch {
// Compilation failed (grammar ABI mismatch?) — fall back to null.
PACKAGE_PATTERNS = null;
SERVICE_PATTERNS = null;
ProtoGrammar = null;
}
}
function buildPlugin(): GrpcLanguagePlugin | null {
if (!ProtoGrammar || !PACKAGE_PATTERNS || !SERVICE_PATTERNS) return null;
const pkgPatterns = PACKAGE_PATTERNS;
const svcPatterns = SERVICE_PATTERNS;
return {
name: 'proto-grpc',
language: ProtoGrammar,
scan(tree) {
const out: GrpcDetection[] = [];
// Extract `package` declaration (first match wins).
let pkg = '';
for (const match of runCompiledPatterns(pkgPatterns, tree)) {
const pkgNode = match.captures.pkg;
if (pkgNode) {
pkg = pkgNode.text;
break;
}
}
// Extract `service → rpc` pairs. The query returns one match per
// (service, rpc) combination thanks to the nested structure.
for (const match of runCompiledPatterns(svcPatterns, tree)) {
const serviceNode = match.captures.service_name;
const rpcNode = match.captures.rpc_name;
if (!serviceNode || !rpcNode) continue;
const serviceName = serviceNode.text;
const methodName = rpcNode.text;
out.push({
role: 'provider',
serviceName,
symbolName: `${serviceName}.${methodName}`,
source: 'proto',
methodName,
// Proto definitions are the canonical source of truth — always
// high confidence regardless of cross-referencing.
confidenceWithProto: 0.85,
confidenceWithoutProto: 0.85,
});
}
return out;
},
};
}
/**
* The proto plugin, or `null` if tree-sitter-proto is not available.
* The orchestrator checks this at import time and decides whether to
* use the tree-sitter path or the fallback manual parser.
*/
export const PROTO_GRPC_PLUGIN: GrpcLanguagePlugin | null = buildPlugin();
/** The package declaration text from a proto file's tree. */
export function extractPackageFromTree(tree: import('tree-sitter').Tree): string {
if (!PACKAGE_PATTERNS) return '';
for (const match of runCompiledPatterns(PACKAGE_PATTERNS, tree)) {
const pkgNode = match.captures.pkg;
if (pkgNode) return pkgNode.text;
}
return '';
}

View file

@ -0,0 +1,30 @@
{
"targets": [
{
"target_name": "tree_sitter_proto_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.
],
"conditions": [
["OS!='win'", {
"cflags_c": [
"-std=c11",
],
}, { # OS == "win"
"cflags_c": [
"/std:c11",
"/utf-8",
],
}],
],
}
]
}

View file

@ -0,0 +1,20 @@
#include <napi.h>
typedef struct TSLanguage TSLanguage;
extern "C" TSLanguage *tree_sitter_proto();
// "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, "proto");
auto language = Napi::External<TSLanguage>::New(env, tree_sitter_proto());
language.TypeTag(&LANGUAGE_TYPE_TAG);
exports["language"] = language;
return exports;
}
NODE_API_MODULE(tree_sitter_proto_binding, Init)

View file

@ -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;

View file

@ -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 (_) {}

View file

@ -0,0 +1,18 @@
{
"name": "tree-sitter-proto",
"version": "0.4.1",
"description": "tree-sitter grammar for protobuf — ABI 14 build from coder3101/tree-sitter-proto latest grammar.js, compatible with tree-sitter 0.25",
"repository": "https://github.com/coder3101/tree-sitter-proto",
"license": "MIT",
"main": "bindings/node",
"scripts": {
"install": "node-gyp-build"
},
"peerDependencies": {
"tree-sitter": ">=0.21.0"
},
"dependencies": {
"node-addon-api": "^8.0.0",
"node-gyp-build": "^4.8.0"
}
}

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

View file

@ -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 size);
extern void *(*ts_current_calloc)(size_t count, size_t size);
extern void *(*ts_current_realloc)(void *ptr, size_t size);
extern void (*ts_current_free)(void *ptr);
#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_

View file

@ -0,0 +1,291 @@
#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(push)
#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(pop)
#elif defined(__GNUC__) || defined(__clang__)
#pragma GCC diagnostic pop
#endif
#ifdef __cplusplus
}
#endif
#endif // TREE_SITTER_ARRAY_H_

View file

@ -0,0 +1,266 @@
#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 *);
void (*log)(const TSLexer *, const char *, ...);
};
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_