lobo/srf-tree-sitter
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

initial commit - all ai generated

Browse source
This commit is contained in:
Emil Lerch 2026-04-10 15:01:25 -07:00
parent f7e08cf7b2
commit cb9234aeef
Signed by: lobo
GPG key ID: A7B62D657EF764F8
16 changed files with 3997 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
.gitignore vendored Normal file
View file

@ -0,0 +1,4 @@
node_modules/
build/
.build/
package-lock.json

4
.mise.toml Normal file
View file

@ -0,0 +1,4 @@
[tools]
node = "22.15.0"
prek = "0.3.1"
tree-sitter = "0.26.8"

26
.pre-commit-config.yaml Normal file
View file

@ -0,0 +1,26 @@
# See https://pre-commit.com for more information
# See https://pre-commit.com/hooks.html for more hooks
repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v6.0.0
hooks:
- id: trailing-whitespace
- id: end-of-file-fixer
- id: check-yaml
- id: check-added-large-files
- repo: local
hooks:
- id: tree-sitter-generate
name: Generate tree-sitter parser
entry: tree-sitter
args: ["generate"]
language: system
files: grammar\.js$
pass_filenames: false
- id: tree-sitter-test
name: Run tree-sitter tests
entry: tree-sitter
args: ["test"]
language: system
types: [file]
pass_filenames: false

21
LICENSE Normal file
View file

@ -0,0 +1,21 @@
MIT License
Copyright (c) 2026 Emil Lerch
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

52
README.md Normal file
View file

@ -0,0 +1,52 @@
# srf-tree-sitter
Tree-sitter grammar for [SRF (Simple Record Format)](https://git.lerch.org/lobo/srf).
## Setup
```sh
mise install
npm install
```
## Build & Test
```sh
mise exec -- tree-sitter generate
mise exec -- tree-sitter test
```
## Neovim Integration
Register the parser and configure highlighting in your Neovim config:
```lua
local parser_config = require("nvim-treesitter.parsers").get_parser_configs()
parser_config.srf = {
install_info = {
url = "https://git.lerch.org/lobo/srf-tree-sitter.git",
files = { "src/parser.c" },
branch = "main",
},
filetype = "srf",
}
vim.filetype.add({
extension = {
srf = "srf",
},
})
```
Then install the parser:
```vim
:TSInstall srf
```
Copy `queries/highlights.scm` to your Neovim runtime queries directory:
```sh
mkdir -p ~/.config/nvim/queries/srf
cp queries/highlights.scm ~/.config/nvim/queries/srf/highlights.scm
```

114
grammar.js Normal file
View file

@ -0,0 +1,114 @@
/**
* @file SRF (Simple Record Format) grammar for tree-sitter
* @author Emil Lerch
* @license MIT
*/
/// <reference types="tree-sitter-cli/dsl" />
// @ts-check
module.exports = grammar({
name: 'srf',
extras: _ => [],
rules: {
document: $ => repeat($._line),
_line: $ => choice(
$.magic,
$.directive,
$.comment,
$.field,
$.blank_line,
),
magic: $ => seq(
'#!srfv1',
optional($.inline_comment),
'\n',
),
inline_comment: _ => /[ \t]+#[^\n]*/,
directive: $ => choice(
$.directive_long,
$.directive_compact,
$.directive_requireeof,
$.directive_eof,
$.directive_expires,
$.directive_created,
$.directive_modified,
$.directive_unknown,
),
directive_long: $ => seq('#!long', optional($.inline_comment), '\n'),
directive_compact: $ => seq('#!compact', optional($.inline_comment), '\n'),
directive_requireeof: $ => seq('#!requireeof', optional($.inline_comment), '\n'),
directive_eof: $ => seq('#!eof', optional($.inline_comment), '\n'),
directive_expires: $ => seq(
'#!expires=',
field('value', $.timestamp),
optional($.inline_comment),
'\n',
),
directive_created: $ => seq(
'#!created=',
field('value', $.timestamp),
optional($.inline_comment),
'\n',
),
directive_modified: $ => seq(
'#!modified=',
field('value', $.timestamp),
optional($.inline_comment),
'\n',
),
directive_unknown: _ => seq(
/#!/,
/[a-zA-Z][a-zA-Z0-9_]*/,
optional(seq('=', /[^\n]*/)),
'\n',
),
timestamp: _ => /[0-9-]+/,
comment: _ => token(seq('#', optional(seq(/[^!\n]/, /[^\n]*/)), '\n')),
blank_line: _ => token(/[ \t]*\n/),
field: $ => choice(
$.typed_field,
$.untyped_field,
),
typed_field: $ => seq(
$.key,
':',
$.type_hint,
':',
optional($.value),
/[,\n]/,
),
untyped_field: $ => seq(
$.key,
'::',
optional($.value),
/[,\n]/,
),
key: _ => /[^#\n:, \t][^:,]*/,
type_hint: _ => choice(
'string',
'num',
'bool',
'null',
'binary',
/[0-9]+/,
),
value: _ => /[^\n,]+/,
},
});

16
package.json Normal file
View file

@ -0,0 +1,16 @@
{
"name": "tree-sitter-srf",
"version": "0.0.1",
"description": "SRF (Simple Record Format) grammar for tree-sitter",
"main": "index.js",
"author": "Emil Lerch",
"license": "MIT",
"devDependencies": {
"tree-sitter-cli": "^0.26.0"
},
"scripts": {
"generate": "tree-sitter generate",
"test": "tree-sitter test",
"build": "tree-sitter generate && tree-sitter test"
}
}

24
queries/highlights.scm Normal file
View file

@ -0,0 +1,24 @@
(magic) @keyword.directive
(directive_long) @keyword.directive
(directive_compact) @keyword.directive
(directive_requireeof) @keyword.directive
(directive_eof) @keyword.directive
(directive_expires) @keyword.directive
(directive_created) @keyword.directive
(directive_modified) @keyword.directive
(directive_unknown) @keyword.directive
(timestamp) @number
(comment) @comment
(inline_comment) @comment
(key) @property
(type_hint) @type
(value) @string
":" @punctuation.delimiter
"::" @punctuation.delimiter

512
src/grammar.json Normal file
View file

@ -0,0 +1,512 @@
{
"$schema": "https://tree-sitter.github.io/tree-sitter/assets/schemas/grammar.schema.json",
"name": "srf",
"rules": {
"document": {
"type": "REPEAT",
"content": {
"type": "SYMBOL",
"name": "_line"
}
},
"_line": {
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "magic"
},
{
"type": "SYMBOL",
"name": "directive"
},
{
"type": "SYMBOL",
"name": "comment"
},
{
"type": "SYMBOL",
"name": "field"
},
{
"type": "SYMBOL",
"name": "blank_line"
}
]
},
"magic": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "#!srfv1"
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "inline_comment"
},
{
"type": "BLANK"
}
]
},
{
"type": "STRING",
"value": "\n"
}
]
},
"inline_comment": {
"type": "PATTERN",
"value": "[ \\t]+#[^\\n]*"
},
"directive": {
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "directive_long"
},
{
"type": "SYMBOL",
"name": "directive_compact"
},
{
"type": "SYMBOL",
"name": "directive_requireeof"
},
{
"type": "SYMBOL",
"name": "directive_eof"
},
{
"type": "SYMBOL",
"name": "directive_expires"
},
{
"type": "SYMBOL",
"name": "directive_created"
},
{
"type": "SYMBOL",
"name": "directive_modified"
},
{
"type": "SYMBOL",
"name": "directive_unknown"
}
]
},
"directive_long": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "#!long"
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "inline_comment"
},
{
"type": "BLANK"
}
]
},
{
"type": "STRING",
"value": "\n"
}
]
},
"directive_compact": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "#!compact"
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "inline_comment"
},
{
"type": "BLANK"
}
]
},
{
"type": "STRING",
"value": "\n"
}
]
},
"directive_requireeof": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "#!requireeof"
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "inline_comment"
},
{
"type": "BLANK"
}
]
},
{
"type": "STRING",
"value": "\n"
}
]
},
"directive_eof": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "#!eof"
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "inline_comment"
},
{
"type": "BLANK"
}
]
},
{
"type": "STRING",
"value": "\n"
}
]
},
"directive_expires": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "#!expires="
},
{
"type": "FIELD",
"name": "value",
"content": {
"type": "SYMBOL",
"name": "timestamp"
}
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "inline_comment"
},
{
"type": "BLANK"
}
]
},
{
"type": "STRING",
"value": "\n"
}
]
},
"directive_created": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "#!created="
},
{
"type": "FIELD",
"name": "value",
"content": {
"type": "SYMBOL",
"name": "timestamp"
}
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "inline_comment"
},
{
"type": "BLANK"
}
]
},
{
"type": "STRING",
"value": "\n"
}
]
},
"directive_modified": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "#!modified="
},
{
"type": "FIELD",
"name": "value",
"content": {
"type": "SYMBOL",
"name": "timestamp"
}
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "inline_comment"
},
{
"type": "BLANK"
}
]
},
{
"type": "STRING",
"value": "\n"
}
]
},
"directive_unknown": {
"type": "SEQ",
"members": [
{
"type": "PATTERN",
"value": "#!"
},
{
"type": "PATTERN",
"value": "[a-zA-Z][a-zA-Z0-9_]*"
},
{
"type": "CHOICE",
"members": [
{
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "="
},
{
"type": "PATTERN",
"value": "[^\\n]*"
}
]
},
{
"type": "BLANK"
}
]
},
{
"type": "STRING",
"value": "\n"
}
]
},
"timestamp": {
"type": "PATTERN",
"value": "[0-9-]+"
},
"comment": {
"type": "TOKEN",
"content": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "#"
},
{
"type": "CHOICE",
"members": [
{
"type": "SEQ",
"members": [
{
"type": "PATTERN",
"value": "[^!\\n]"
},
{
"type": "PATTERN",
"value": "[^\\n]*"
}
]
},
{
"type": "BLANK"
}
]
},
{
"type": "STRING",
"value": "\n"
}
]
}
},
"blank_line": {
"type": "TOKEN",
"content": {
"type": "PATTERN",
"value": "[ \\t]*\\n"
}
},
"field": {
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "typed_field"
},
{
"type": "SYMBOL",
"name": "untyped_field"
}
]
},
"typed_field": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "key"
},
{
"type": "STRING",
"value": ":"
},
{
"type": "SYMBOL",
"name": "type_hint"
},
{
"type": "STRING",
"value": ":"
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "value"
},
{
"type": "BLANK"
}
]
},
{
"type": "PATTERN",
"value": "[,\\n]"
}
]
},
"untyped_field": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "key"
},
{
"type": "STRING",
"value": "::"
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "value"
},
{
"type": "BLANK"
}
]
},
{
"type": "PATTERN",
"value": "[,\\n]"
}
]
},
"key": {
"type": "PATTERN",
"value": "[^#\\n:, \\t][^:,]*"
},
"type_hint": {
"type": "CHOICE",
"members": [
{
"type": "STRING",
"value": "string"
},
{
"type": "STRING",
"value": "num"
},
{
"type": "STRING",
"value": "bool"
},
{
"type": "STRING",
"value": "null"
},
{
"type": "STRING",
"value": "binary"
},
{
"type": "PATTERN",
"value": "[0-9]+"
}
]
},
"value": {
"type": "PATTERN",
"value": "[^\\n,]+"
}
},
"extras": [],
"conflicts": [],
"precedences": [],
"externals": [],
"inline": [],
"supertypes": [],
"reserved": {}
}

393
src/node-types.json Normal file
View file

@ -0,0 +1,393 @@
[
{
"type": "directive",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": true,
"types": [
{
"type": "directive_compact",
"named": true
},
{
"type": "directive_created",
"named": true
},
{
"type": "directive_eof",
"named": true
},
{
"type": "directive_expires",
"named": true
},
{
"type": "directive_long",
"named": true
},
{
"type": "directive_modified",
"named": true
},
{
"type": "directive_requireeof",
"named": true
},
{
"type": "directive_unknown",
"named": true
}
]
}
},
{
"type": "directive_compact",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": false,
"types": [
{
"type": "inline_comment",
"named": true
}
]
}
},
{
"type": "directive_created",
"named": true,
"fields": {
"value": {
"multiple": false,
"required": true,
"types": [
{
"type": "timestamp",
"named": true
}
]
}
},
"children": {
"multiple": false,
"required": false,
"types": [
{
"type": "inline_comment",
"named": true
}
]
}
},
{
"type": "directive_eof",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": false,
"types": [
{
"type": "inline_comment",
"named": true
}
]
}
},
{
"type": "directive_expires",
"named": true,
"fields": {
"value": {
"multiple": false,
"required": true,
"types": [
{
"type": "timestamp",
"named": true
}
]
}
},
"children": {
"multiple": false,
"required": false,
"types": [
{
"type": "inline_comment",
"named": true
}
]
}
},
{
"type": "directive_long",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": false,
"types": [
{
"type": "inline_comment",
"named": true
}
]
}
},
{
"type": "directive_modified",
"named": true,
"fields": {
"value": {
"multiple": false,
"required": true,
"types": [
{
"type": "timestamp",
"named": true
}
]
}
},
"children": {
"multiple": false,
"required": false,
"types": [
{
"type": "inline_comment",
"named": true
}
]
}
},
{
"type": "directive_requireeof",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": false,
"types": [
{
"type": "inline_comment",
"named": true
}
]
}
},
{
"type": "directive_unknown",
"named": true,
"fields": {}
},
{
"type": "document",
"named": true,
"root": true,
"fields": {},
"children": {
"multiple": true,
"required": false,
"types": [
{
"type": "blank_line",
"named": true
},
{
"type": "comment",
"named": true
},
{
"type": "directive",
"named": true
},
{
"type": "field",
"named": true
},
{
"type": "magic",
"named": true
}
]
}
},
{
"type": "field",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": true,
"types": [
{
"type": "typed_field",
"named": true
},
{
"type": "untyped_field",
"named": true
}
]
}
},
{
"type": "magic",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": false,
"types": [
{
"type": "inline_comment",
"named": true
}
]
}
},
{
"type": "type_hint",
"named": true,
"fields": {}
},
{
"type": "typed_field",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "key",
"named": true
},
{
"type": "type_hint",
"named": true
},
{
"type": "value",
"named": true
}
]
}
},
{
"type": "untyped_field",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "key",
"named": true
},
{
"type": "value",
"named": true
}
]
}
},
{
"type": "\n",
"named": false
},
{
"type": "#!compact",
"named": false
},
{
"type": "#!created=",
"named": false
},
{
"type": "#!eof",
"named": false
},
{
"type": "#!expires=",
"named": false
},
{
"type": "#!long",
"named": false
},
{
"type": "#!modified=",
"named": false
},
{
"type": "#!requireeof",
"named": false
},
{
"type": "#!srfv1",
"named": false
},
{
"type": ":",
"named": false
},
{
"type": "::",
"named": false
},
{
"type": "=",
"named": false
},
{
"type": "binary",
"named": false
},
{
"type": "blank_line",
"named": true
},
{
"type": "bool",
"named": false
},
{
"type": "comment",
"named": true
},
{
"type": "inline_comment",
"named": true
},
{
"type": "key",
"named": true
},
{
"type": "null",
"named": false
},
{
"type": "num",
"named": false
},
{
"type": "string",
"named": false
},
{
"type": "timestamp",
"named": true
},
{
"type": "value",
"named": true
}
]

1917
src/parser.c Normal file
View file

File diff suppressed because it is too large Load diff

54
src/tree_sitter/alloc.h Normal file
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_

330
src/tree_sitter/array.h Normal file
View file

@ -0,0 +1,330 @@
#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) \
((self)->contents = _array__reserve( \
(void *)(self)->contents, &(self)->capacity, \
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) \
do { \
if ((self)->contents) ts_free((self)->contents); \
(self)->contents = NULL; \
(self)->size = 0; \
(self)->capacity = 0; \
} while (0)
/// Push a new `element` onto the end of the array.
#define array_push(self, element) \
do { \
(self)->contents = _array__grow( \
(void *)(self)->contents, (self)->size, &(self)->capacity, \
1, array_elem_size(self) \
); \
(self)->contents[(self)->size++] = (element); \
} while(0)
/// Increase the array's size by `count` elements.
/// New elements are zero-initialized.
#define array_grow_by(self, count) \
do { \
if ((count) == 0) break; \
(self)->contents = _array__grow( \
(self)->contents, (self)->size, &(self)->capacity, \
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, other_contents) \
(self)->contents = _array__splice( \
(void*)(self)->contents, &(self)->size, &(self)->capacity, \
array_elem_size(self), (self)->size, 0, count, other_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) \
(self)->contents = _array__splice( \
(void *)(self)->contents, &(self)->size, &(self)->capacity, \
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) \
(self)->contents = _array__splice( \
(void *)(self)->contents, &(self)->size, &(self)->capacity, \
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((void *)(self)->contents, &(self)->size, 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) \
(self)->contents = _array__assign( \
(void *)(self)->contents, &(self)->size, &(self)->capacity, \
(const void *)(other)->contents, (other)->size, array_elem_size(self) \
)
/// Swap one array with another
#define array_swap(self, other) \
do { \
void *_array_swap_tmp = (void *)(self)->contents; \
(self)->contents = (other)->contents; \
(other)->contents = _array_swap_tmp; \
_array__swap(&(self)->size, &(self)->capacity, \
&(other)->size, &(other)->capacity); \
} while (0)
/// 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
// Pointers to individual `Array` fields (rather than the entire `Array` itself)
// are passed to the various `_array__*` functions below to address strict aliasing
// violations that arises when the _entire_ `Array` struct is passed as `Array(void)*`.
//
// The `Array` type itself was not altered as a solution in order to avoid breakage
// with existing consumers (in particular, parsers with external scanners).
/// This is not what you're looking for, see `array_erase`.
static inline void _array__erase(void* self_contents, uint32_t *size,
size_t element_size, uint32_t index) {
assert(index < *size);
char *contents = (char *)self_contents;
memmove(contents + index * element_size, contents + (index + 1) * element_size,
(*size - index - 1) * element_size);
(*size)--;
}
/// This is not what you're looking for, see `array_reserve`.
static inline void *_array__reserve(void *contents, uint32_t *capacity,
size_t element_size, uint32_t new_capacity) {
void *new_contents = contents;
if (new_capacity > *capacity) {
if (contents) {
new_contents = ts_realloc(contents, new_capacity * element_size);
} else {
new_contents = ts_malloc(new_capacity * element_size);
}
*capacity = new_capacity;
}
return new_contents;
}
/// This is not what you're looking for, see `array_assign`.
static inline void *_array__assign(void* self_contents, uint32_t *self_size, uint32_t *self_capacity,
const void *other_contents, uint32_t other_size, size_t element_size) {
void *new_contents = _array__reserve(self_contents, self_capacity, element_size, other_size);
*self_size = other_size;
memcpy(new_contents, other_contents, *self_size * element_size);
return new_contents;
}
/// This is not what you're looking for, see `array_swap`.
static inline void _array__swap(uint32_t *self_size, uint32_t *self_capacity,
uint32_t *other_size, uint32_t *other_capacity) {
uint32_t tmp_size = *self_size;
uint32_t tmp_capacity = *self_capacity;
*self_size = *other_size;
*self_capacity = *other_capacity;
*other_size = tmp_size;
*other_capacity = tmp_capacity;
}
/// This is not what you're looking for, see `array_push` or `array_grow_by`.
static inline void *_array__grow(void *contents, uint32_t size, uint32_t *capacity,
uint32_t count, size_t element_size) {
void *new_contents = contents;
uint32_t new_size = size + count;
if (new_size > *capacity) {
uint32_t new_capacity = *capacity * 2;
if (new_capacity < 8) new_capacity = 8;
if (new_capacity < new_size) new_capacity = new_size;
new_contents = _array__reserve(contents, capacity, element_size, new_capacity);
}
return new_contents;
}
/// This is not what you're looking for, see `array_splice`.
static inline void *_array__splice(void *self_contents, uint32_t *size, uint32_t *capacity,
size_t element_size,
uint32_t index, uint32_t old_count,
uint32_t new_count, const void *elements) {
uint32_t new_size = *size + new_count - old_count;
uint32_t old_end = index + old_count;
uint32_t new_end = index + new_count;
assert(old_end <= *size);
void *new_contents = _array__reserve(self_contents, capacity, element_size, new_size);
char *contents = (char *)new_contents;
if (*size > old_end) {
memmove(
contents + new_end * element_size,
contents + old_end * element_size,
(*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
);
}
}
*size += new_count - old_count;
return new_contents;
}
/// 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_

286
src/tree_sitter/parser.h Normal file
View file

@ -0,0 +1,286 @@
#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;
typedef struct TSLanguageMetadata {
uint8_t major_version;
uint8_t minor_version;
uint8_t patch_version;
} TSLanguageMetadata;
#endif
typedef struct {
TSFieldId field_id;
uint8_t child_index;
bool inherited;
} TSFieldMapEntry;
// Used to index the field and supertype maps.
typedef struct {
uint16_t index;
uint16_t length;
} TSMapSlice;
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 struct {
uint16_t lex_state;
uint16_t external_lex_state;
uint16_t reserved_word_set_id;
} TSLexerMode;
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 abi_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 TSMapSlice *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 TSLexerMode *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;
const char *name;
const TSSymbol *reserved_words;
uint16_t max_reserved_word_set_size;
uint32_t supertype_count;
const TSSymbol *supertype_symbols;
const TSMapSlice *supertype_map_slices;
const TSSymbol *supertype_map_entries;
TSLanguageMetadata metadata;
};
static inline bool set_contains(const 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;
const 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;
}
const 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_

214
test/corpus/basics.txt Normal file
View file

@ -0,0 +1,214 @@
==================
Basic long format
==================
#!srfv1
#!long
name::alice
age:num:30
---
(document
(blank_line)
(magic)
(directive
(directive_long))
(field
(untyped_field
(key)
(value)))
(field
(typed_field
(key)
(type_hint)
(value))))
==================
Basic compact format
==================
#!srfv1
name::alice,age:num:30
---
(document
(blank_line)
(magic)
(field
(untyped_field
(key)
(value)))
(field
(typed_field
(key)
(type_hint)
(value))))
==================
Directives
==================
#!srfv1
#!requireeof
#!long
#!expires=1772589213
#!created=1772500000
#!modified=1772500001
name::alice
#!eof
---
(document
(blank_line)
(magic)
(directive
(directive_requireeof))
(directive
(directive_long))
(directive
(directive_expires
value: (timestamp)))
(directive
(directive_created
value: (timestamp)))
(directive
(directive_modified
value: (timestamp)))
(field
(untyped_field
(key)
(value)))
(blank_line)
(directive
(directive_eof)))
==================
Comments
==================
#!srfv1
# This is a comment
name::alice
---
(document
(blank_line)
(magic)
(comment)
(field
(untyped_field
(key)
(value))))
==================
All type hints
==================
#!srfv1
name:string:alice
age:num:30
active:bool:true
missing:null:
data:binary:aGVsbG8=
bio:12:hello world!
---
(document
(blank_line)
(magic)
(field
(typed_field
(key)
(type_hint)
(value)))
(field
(typed_field
(key)
(type_hint)
(value)))
(field
(typed_field
(key)
(type_hint)
(value)))
(field
(typed_field
(key)
(type_hint)))
(field
(typed_field
(key)
(type_hint)
(value)))
(field
(typed_field
(key)
(type_hint)
(value))))
==================
Inline comments on directives
==================
#!srfv1 # version header
#!long # use long format
name::alice
---
(document
(blank_line)
(magic
(inline_comment))
(directive
(directive_long
(inline_comment)))
(field
(untyped_field
(key)
(value))))
==================
Multiple records long format
==================
#!srfv1
#!long
name::alice
age:num:30
name::bob
age:num:25
---
(document
(blank_line)
(magic)
(directive
(directive_long))
(field
(untyped_field
(key)
(value)))
(field
(typed_field
(key)
(type_hint)
(value)))
(blank_line)
(field
(untyped_field
(key)
(value)))
(field
(typed_field
(key)
(type_hint)
(value))))

30
tree-sitter.json Normal file
View file

@ -0,0 +1,30 @@
{
"grammars": [
{
"name": "srf",
"camelcase": "SRF",
"scope": "source.srf",
"path": ".",
"file-types": [
"srf"
],
"highlights": "queries/highlights.scm"
}
],
"metadata": {
"version": "0.0.1",
"license": "MIT",
"description": "SRF (Simple Record Format) grammar for tree-sitter",
"authors": [
{
"name": "Emil Lerch"
}
],
"links": {
"repository": "https://git.lerch.org/lobo/srf-tree-sitter"
}
},
"bindings": {
"c": true
}
}