From 4e516a7cd5f9a58edd19b587967d9a0522556ad3 Mon Sep 17 00:00:00 2001 From: ObserverOfTime Date: Sun, 31 Mar 2024 22:09:29 +0300 Subject: [PATCH] feat(schema): add json schema --- .gitattributes | 4 +- README.md | 2 +- package.json | 4 +- schema/core/grammar.js | 4 +- schema/core/package.json | 3 +- schema/json/grammar.js | 21 ++ schema/json/package.json | 7 + schema/json/src/grammar.json | 69 +++++ schema/json/src/node-types.json | 45 ++++ schema/json/src/parser.c | 262 +++++++++++++++++++ schema/json/src/tree_sitter/alloc.h | 54 ++++ schema/json/src/tree_sitter/array.h | 290 ++++++++++++++++++++++ schema/json/src/tree_sitter/parser.h | 230 +++++++++++++++++ schema/update-schema.js | 6 +- src/scanner.c | 9 +- src/{schema.generated.c => schema.core.c} | 2 +- src/schema.json.c | 102 ++++++++ 17 files changed, 1101 insertions(+), 13 deletions(-) create mode 100644 schema/json/grammar.js create mode 100644 schema/json/package.json create mode 100644 schema/json/src/grammar.json create mode 100644 schema/json/src/node-types.json create mode 100644 schema/json/src/parser.c create mode 100644 schema/json/src/tree_sitter/alloc.h create mode 100644 schema/json/src/tree_sitter/array.h create mode 100644 schema/json/src/tree_sitter/parser.h rename src/{schema.generated.c => schema.core.c} (99%) create mode 100644 src/schema.json.c diff --git a/.gitattributes b/.gitattributes index 78fcbf8..b1d00c1 100644 --- a/.gitattributes +++ b/.gitattributes @@ -4,8 +4,8 @@ src/*.json linguist-generated src/parser.c linguist-generated src/tree_sitter/* linguist-generated -src/schema.generated.c linguist-generated -schema/src/** linguist-generated +src/schema.*.c linguist-generated +schema/*/src/** linguist-generated bindings/** linguist-generated binding.gyp linguist-generated diff --git a/README.md b/README.md index 3c5a6d9..89365a8 100644 --- a/README.md +++ b/README.md @@ -11,7 +11,7 @@ A tree-sitter parser for YAML files. ## References -- [YAML version 1.2](https://yaml.org/spec/1.2/spec.html) +- [YAML version 1.2](https://yaml.org/spec/1.2.2/) [ci]: https://img.shields.io/github/actions/workflow/status/tree-sitter-grammars/tree-sitter-yaml/ci.yml?logo=github&label=CI [discord]: https://img.shields.io/discord/1063097320771698699?logo=discord&label=discord diff --git a/package.json b/package.json index 1010b01..1a61e84 100644 --- a/package.json +++ b/package.json @@ -50,7 +50,7 @@ }, "scripts": { "build": "tree-sitter generate --no-bindings", - "postbuild": "node schema/update-schema.js", + "postbuild": "npm run --prefix schema/core build", "test": "tree-sitter test", "install": "node-gyp-build", "prebuildify": "prebuildify --napi --strip" @@ -68,7 +68,7 @@ "injection-regex": "^ya?ml$", "highlights": "queries/highlights.scm", "external-files": [ - "src/schema.generated.c" + "src/schema.core.c" ] } ] diff --git a/schema/core/grammar.js b/schema/core/grammar.js index f4bbede..2ae7356 100644 --- a/schema/core/grammar.js +++ b/schema/core/grammar.js @@ -1,6 +1,4 @@ -/** - * @see {@link Core Schema|https://yaml.org/spec/1.2/spec.html#schema/core} - */ +/** @see {@link Core Schema|https://yaml.org/spec/1.2.2/#103-core-schema} */ /// diff --git a/schema/core/package.json b/schema/core/package.json index 90ca874..f24b8bc 100644 --- a/schema/core/package.json +++ b/schema/core/package.json @@ -1,6 +1,7 @@ { "private": true, "scripts": { - "build": "tree-sitter generate --no-bindings" + "build": "tree-sitter generate --no-bindings", + "postbuild": "node ../update-schema.js core" } } diff --git a/schema/json/grammar.js b/schema/json/grammar.js new file mode 100644 index 0000000..24bdba6 --- /dev/null +++ b/schema/json/grammar.js @@ -0,0 +1,21 @@ +/** @see {@link JSON Schema|https://yaml.org/spec/1.2.2/#102-json-schema} */ + +/// + +module.exports = grammar({ + name: "json_schema", + + extras: _ => [], + + rules: { + scalar: $ => choice($.null, $.bool, $.int, $.float), + + null: _ => token("null"), + + bool: _ => token(choice("true", "false")), + + int: _ => token(/-?(0|[1-9][0-9]*)/), + + float: _ => token(/-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][-+]?[0-9]+)?/), + }, +}); diff --git a/schema/json/package.json b/schema/json/package.json new file mode 100644 index 0000000..76a1a1d --- /dev/null +++ b/schema/json/package.json @@ -0,0 +1,7 @@ +{ + "private": true, + "scripts": { + "build": "tree-sitter generate --no-bindings", + "postbuild": "node ../update-schema.js json" + } +} diff --git a/schema/json/src/grammar.json b/schema/json/src/grammar.json new file mode 100644 index 0000000..e2f0e70 --- /dev/null +++ b/schema/json/src/grammar.json @@ -0,0 +1,69 @@ +{ + "name": "json_schema", + "rules": { + "scalar": { + "type": "CHOICE", + "members": [ + { + "type": "SYMBOL", + "name": "null" + }, + { + "type": "SYMBOL", + "name": "bool" + }, + { + "type": "SYMBOL", + "name": "int" + }, + { + "type": "SYMBOL", + "name": "float" + } + ] + }, + "null": { + "type": "TOKEN", + "content": { + "type": "STRING", + "value": "null" + } + }, + "bool": { + "type": "TOKEN", + "content": { + "type": "CHOICE", + "members": [ + { + "type": "STRING", + "value": "true" + }, + { + "type": "STRING", + "value": "false" + } + ] + } + }, + "int": { + "type": "TOKEN", + "content": { + "type": "PATTERN", + "value": "-?(0|[1-9][0-9]*)" + } + }, + "float": { + "type": "TOKEN", + "content": { + "type": "PATTERN", + "value": "-?(0|[1-9][0-9]*)(\\.[0-9]*)?([eE][-+]?[0-9]+)?" + } + } + }, + "extras": [], + "conflicts": [], + "precedences": [], + "externals": [], + "inline": [], + "supertypes": [] +} diff --git a/schema/json/src/node-types.json b/schema/json/src/node-types.json new file mode 100644 index 0000000..29cca72 --- /dev/null +++ b/schema/json/src/node-types.json @@ -0,0 +1,45 @@ +[ + { + "type": "scalar", + "named": true, + "fields": {}, + "children": { + "multiple": false, + "required": true, + "types": [ + { + "type": "bool", + "named": true + }, + { + "type": "float", + "named": true + }, + { + "type": "int", + "named": true + }, + { + "type": "null", + "named": true + } + ] + } + }, + { + "type": "bool", + "named": true + }, + { + "type": "float", + "named": true + }, + { + "type": "int", + "named": true + }, + { + "type": "null", + "named": true + } +] \ No newline at end of file diff --git a/schema/json/src/parser.c b/schema/json/src/parser.c new file mode 100644 index 0000000..30e364f --- /dev/null +++ b/schema/json/src/parser.c @@ -0,0 +1,262 @@ +#include "tree_sitter/parser.h" + +#if defined(__GNUC__) || defined(__clang__) +#pragma GCC diagnostic ignored "-Wmissing-field-initializers" +#endif + +#define LANGUAGE_VERSION 14 +#define STATE_COUNT 4 +#define LARGE_STATE_COUNT 2 +#define SYMBOL_COUNT 6 +#define ALIAS_COUNT 0 +#define TOKEN_COUNT 5 +#define EXTERNAL_TOKEN_COUNT 0 +#define FIELD_COUNT 0 +#define MAX_ALIAS_SEQUENCE_LENGTH 1 +#define PRODUCTION_ID_COUNT 1 + +enum ts_symbol_identifiers { + sym_null = 1, + sym_bool = 2, + sym_int = 3, + sym_float = 4, + sym_scalar = 5, +}; + +static const char * const ts_symbol_names[] = { + [ts_builtin_sym_end] = "end", + [sym_null] = "null", + [sym_bool] = "bool", + [sym_int] = "int", + [sym_float] = "float", + [sym_scalar] = "scalar", +}; + +static const TSSymbol ts_symbol_map[] = { + [ts_builtin_sym_end] = ts_builtin_sym_end, + [sym_null] = sym_null, + [sym_bool] = sym_bool, + [sym_int] = sym_int, + [sym_float] = sym_float, + [sym_scalar] = sym_scalar, +}; + +static const TSSymbolMetadata ts_symbol_metadata[] = { + [ts_builtin_sym_end] = { + .visible = false, + .named = true, + }, + [sym_null] = { + .visible = true, + .named = true, + }, + [sym_bool] = { + .visible = true, + .named = true, + }, + [sym_int] = { + .visible = true, + .named = true, + }, + [sym_float] = { + .visible = true, + .named = true, + }, + [sym_scalar] = { + .visible = true, + .named = true, + }, +}; + +static const TSSymbol ts_alias_sequences[PRODUCTION_ID_COUNT][MAX_ALIAS_SEQUENCE_LENGTH] = { + [0] = {0}, +}; + +static const uint16_t ts_non_terminal_alias_map[] = { + 0, +}; + +static const TSStateId ts_primary_state_ids[STATE_COUNT] = { + [0] = 0, + [1] = 1, + [2] = 2, + [3] = 3, +}; + +static bool ts_lex(TSLexer *lexer, TSStateId state) { + START_LEXER(); + eof = lexer->eof(lexer); + switch (state) { + case 0: + if (eof) ADVANCE(13); + if (lookahead == '-') ADVANCE(1); + if (lookahead == '0') ADVANCE(16); + if (lookahead == 'f') ADVANCE(2); + if (lookahead == 'n') ADVANCE(10); + if (lookahead == 't') ADVANCE(7); + if (('1' <= lookahead && lookahead <= '9')) ADVANCE(17); + END_STATE(); + case 1: + if (lookahead == '0') ADVANCE(16); + if (('1' <= lookahead && lookahead <= '9')) ADVANCE(17); + END_STATE(); + case 2: + if (lookahead == 'a') ADVANCE(4); + END_STATE(); + case 3: + if (lookahead == 'e') ADVANCE(15); + END_STATE(); + case 4: + if (lookahead == 'l') ADVANCE(8); + END_STATE(); + case 5: + if (lookahead == 'l') ADVANCE(14); + END_STATE(); + case 6: + if (lookahead == 'l') ADVANCE(5); + END_STATE(); + case 7: + if (lookahead == 'r') ADVANCE(9); + END_STATE(); + case 8: + if (lookahead == 's') ADVANCE(3); + END_STATE(); + case 9: + if (lookahead == 'u') ADVANCE(3); + END_STATE(); + case 10: + if (lookahead == 'u') ADVANCE(6); + END_STATE(); + case 11: + if (lookahead == '+' || + lookahead == '-') ADVANCE(12); + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(19); + END_STATE(); + case 12: + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(19); + END_STATE(); + case 13: + ACCEPT_TOKEN(ts_builtin_sym_end); + END_STATE(); + case 14: + ACCEPT_TOKEN(sym_null); + END_STATE(); + case 15: + ACCEPT_TOKEN(sym_bool); + END_STATE(); + case 16: + ACCEPT_TOKEN(sym_int); + if (lookahead == '.') ADVANCE(18); + if (lookahead == 'E' || + lookahead == 'e') ADVANCE(11); + END_STATE(); + case 17: + ACCEPT_TOKEN(sym_int); + if (lookahead == '.') ADVANCE(18); + if (lookahead == 'E' || + lookahead == 'e') ADVANCE(11); + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(17); + END_STATE(); + case 18: + ACCEPT_TOKEN(sym_float); + if (lookahead == 'E' || + lookahead == 'e') ADVANCE(11); + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(18); + END_STATE(); + case 19: + ACCEPT_TOKEN(sym_float); + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(19); + END_STATE(); + default: + return false; + } +} + +static const TSLexMode ts_lex_modes[STATE_COUNT] = { + [0] = {.lex_state = 0}, + [1] = {.lex_state = 0}, + [2] = {.lex_state = 0}, + [3] = {.lex_state = 0}, +}; + +static const uint16_t ts_parse_table[LARGE_STATE_COUNT][SYMBOL_COUNT] = { + [0] = { + [ts_builtin_sym_end] = ACTIONS(1), + [sym_null] = ACTIONS(1), + [sym_bool] = ACTIONS(1), + [sym_int] = ACTIONS(1), + [sym_float] = ACTIONS(1), + }, + [1] = { + [sym_scalar] = STATE(3), + [sym_null] = ACTIONS(3), + [sym_bool] = ACTIONS(3), + [sym_int] = ACTIONS(5), + [sym_float] = ACTIONS(5), + }, +}; + +static const uint16_t ts_small_parse_table[] = { + [0] = 1, + ACTIONS(7), 1, + ts_builtin_sym_end, + [4] = 1, + ACTIONS(9), 1, + ts_builtin_sym_end, +}; + +static const uint32_t ts_small_parse_table_map[] = { + [SMALL_STATE(2)] = 0, + [SMALL_STATE(3)] = 4, +}; + +static const TSParseActionEntry ts_parse_actions[] = { + [0] = {.entry = {.count = 0, .reusable = false}}, + [1] = {.entry = {.count = 1, .reusable = false}}, RECOVER(), + [3] = {.entry = {.count = 1, .reusable = true}}, SHIFT(2), + [5] = {.entry = {.count = 1, .reusable = false}}, SHIFT(2), + [7] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_scalar, 1), + [9] = {.entry = {.count = 1, .reusable = true}}, ACCEPT_INPUT(), +}; + +#ifdef __cplusplus +extern "C" { +#endif +#ifdef TREE_SITTER_HIDE_SYMBOLS +#define TS_PUBLIC +#elif defined(_WIN32) +#define TS_PUBLIC __declspec(dllexport) +#else +#define TS_PUBLIC __attribute__((visibility("default"))) +#endif + +TS_PUBLIC const TSLanguage *tree_sitter_json_schema() { + static const TSLanguage language = { + .version = LANGUAGE_VERSION, + .symbol_count = SYMBOL_COUNT, + .alias_count = ALIAS_COUNT, + .token_count = TOKEN_COUNT, + .external_token_count = EXTERNAL_TOKEN_COUNT, + .state_count = STATE_COUNT, + .large_state_count = LARGE_STATE_COUNT, + .production_id_count = PRODUCTION_ID_COUNT, + .field_count = FIELD_COUNT, + .max_alias_sequence_length = MAX_ALIAS_SEQUENCE_LENGTH, + .parse_table = &ts_parse_table[0][0], + .small_parse_table = ts_small_parse_table, + .small_parse_table_map = ts_small_parse_table_map, + .parse_actions = ts_parse_actions, + .symbol_names = ts_symbol_names, + .symbol_metadata = ts_symbol_metadata, + .public_symbol_map = ts_symbol_map, + .alias_map = ts_non_terminal_alias_map, + .alias_sequences = &ts_alias_sequences[0][0], + .lex_modes = ts_lex_modes, + .lex_fn = ts_lex, + .primary_state_ids = ts_primary_state_ids, + }; + return &language; +} +#ifdef __cplusplus +} +#endif diff --git a/schema/json/src/tree_sitter/alloc.h b/schema/json/src/tree_sitter/alloc.h new file mode 100644 index 0000000..1f4466d --- /dev/null +++ b/schema/json/src/tree_sitter/alloc.h @@ -0,0 +1,54 @@ +#ifndef TREE_SITTER_ALLOC_H_ +#define TREE_SITTER_ALLOC_H_ + +#ifdef __cplusplus +extern "C" { +#endif + +#include +#include +#include + +// 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_ diff --git a/schema/json/src/tree_sitter/array.h b/schema/json/src/tree_sitter/array.h new file mode 100644 index 0000000..15a3b23 --- /dev/null +++ b/schema/json/src/tree_sitter/array.h @@ -0,0 +1,290 @@ +#ifndef TREE_SITTER_ARRAY_H_ +#define TREE_SITTER_ARRAY_H_ + +#ifdef __cplusplus +extern "C" { +#endif + +#include "./alloc.h" + +#include +#include +#include +#include +#include + +#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_ diff --git a/schema/json/src/tree_sitter/parser.h b/schema/json/src/tree_sitter/parser.h new file mode 100644 index 0000000..17b4fde --- /dev/null +++ b/schema/json/src/tree_sitter/parser.h @@ -0,0 +1,230 @@ +#ifndef TREE_SITTER_PARSER_H_ +#define TREE_SITTER_PARSER_H_ + +#ifdef __cplusplus +extern "C" { +#endif + +#include +#include +#include + +#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; + +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; +}; + +/* + * 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 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_val, child_count_val, ...) \ + {{ \ + .reduce = { \ + .type = TSParseActionTypeReduce, \ + .symbol = symbol_val, \ + .child_count = child_count_val, \ + __VA_ARGS__ \ + }, \ + }} + +#define RECOVER() \ + {{ \ + .type = TSParseActionTypeRecover \ + }} + +#define ACCEPT_INPUT() \ + {{ \ + .type = TSParseActionTypeAccept \ + }} + +#ifdef __cplusplus +} +#endif + +#endif // TREE_SITTER_PARSER_H_ diff --git a/schema/update-schema.js b/schema/update-schema.js index 22fa805..8c8cf27 100755 --- a/schema/update-schema.js +++ b/schema/update-schema.js @@ -6,7 +6,9 @@ const { writeFileSync } = require("fs"); const { readFile } = require("fs/promises"); const { join } = require("path"); -readFile(join(__dirname, process.argv[2] ?? "core", "src", "parser.c"), "utf8").then(input => { +const schema = process.argv[2] ?? "core"; + +readFile(join(__dirname, schema, "src", "parser.c"), "utf8").then(input => { const cases = extractCases(input); const enums = ["RS_STR"]; const content = "switch (sch_stt) " + block([ @@ -37,7 +39,7 @@ readFile(join(__dirname, process.argv[2] ?? "core", "src", "parser.c"), "utf8"). .replace(/lookahead/g, "cur_chr"), ]); writeFileSync( - join(__dirname, "..", "src", "schema.generated.c"), + join(__dirname, "..", "src", `schema.${schema}.c`), [ "#include ", "#define SCH_STT_FRZ -1", diff --git a/src/scanner.c b/src/scanner.c index b7d41f2..bea022e 100644 --- a/src/scanner.c +++ b/src/scanner.c @@ -1,7 +1,14 @@ #include "tree_sitter/array.h" #include "tree_sitter/parser.h" -#include "./schema.generated.c" +#define _str(x) #x +#define _file(x) _str(./schema.x.c) + +#ifndef YAML_SCHEMA +#define YAML_SCHEMA core +#endif + +#include _file(YAML_SCHEMA) // clang-format off diff --git a/src/schema.generated.c b/src/schema.core.c similarity index 99% rename from src/schema.generated.c rename to src/schema.core.c index 1e7e318..cb53d7d 100644 --- a/src/schema.generated.c +++ b/src/schema.core.c @@ -195,6 +195,6 @@ static int8_t adv_sch_stt(int8_t sch_stt, int32_t cur_chr, ResultSchema *rlt_sch *rlt_sch = RS_STR; return SCH_STT_FRZ; } - if (cur_chr != '\r' && cur_chr != '\n' && cur_chr != ' ' && cur_chr != 0) *rlt_sch = RS_STR; + if (cur_chr != '\r' && cur_chr != '\n' && cur_chr != ' ' && cur_chr != 0) {*rlt_sch = RS_STR;} return SCH_STT_FRZ; } diff --git a/src/schema.json.c b/src/schema.json.c new file mode 100644 index 0000000..ba879cb --- /dev/null +++ b/src/schema.json.c @@ -0,0 +1,102 @@ +#include + +#define SCH_STT_FRZ -1 + +typedef enum { + RS_STR, + RS_INT, + RS_BOOL, + RS_NULL, + RS_FLOAT, +} ResultSchema; + +static int8_t adv_sch_stt(int8_t sch_stt, int32_t cur_chr, ResultSchema *rlt_sch) { + switch (sch_stt) { + case SCH_STT_FRZ: + break; + case 0: + if (cur_chr == '-') {*rlt_sch = RS_STR; return 1;} + if (cur_chr == '0') {*rlt_sch = RS_INT; return 16;} + if (cur_chr == 'f') {*rlt_sch = RS_STR; return 2;} + if (cur_chr == 'n') {*rlt_sch = RS_STR; return 10;} + if (cur_chr == 't') {*rlt_sch = RS_STR; return 7;} + if (('1' <= cur_chr && cur_chr <= '9')) {*rlt_sch = RS_INT; return 17;} + break; + case 1: + if (cur_chr == '0') {*rlt_sch = RS_INT; return 16;} + if (('1' <= cur_chr && cur_chr <= '9')) {*rlt_sch = RS_INT; return 17;} + break; + case 2: + if (cur_chr == 'a') {*rlt_sch = RS_STR; return 4;} + break; + case 3: + if (cur_chr == 'e') {*rlt_sch = RS_BOOL; return 15;} + break; + case 4: + if (cur_chr == 'l') {*rlt_sch = RS_STR; return 8;} + break; + case 5: + if (cur_chr == 'l') {*rlt_sch = RS_NULL; return 14;} + break; + case 6: + if (cur_chr == 'l') {*rlt_sch = RS_STR; return 5;} + break; + case 7: + if (cur_chr == 'r') {*rlt_sch = RS_STR; return 9;} + break; + case 8: + if (cur_chr == 's') {*rlt_sch = RS_STR; return 3;} + break; + case 9: + if (cur_chr == 'u') {*rlt_sch = RS_STR; return 3;} + break; + case 10: + if (cur_chr == 'u') {*rlt_sch = RS_STR; return 6;} + break; + case 11: + if (cur_chr == '+' || + cur_chr == '-') {*rlt_sch = RS_STR; return 12;} + if (('0' <= cur_chr && cur_chr <= '9')) {*rlt_sch = RS_FLOAT; return 19;} + break; + case 12: + if (('0' <= cur_chr && cur_chr <= '9')) {*rlt_sch = RS_FLOAT; return 19;} + break; + case 13: + abort(); + break; + case 14: + *rlt_sch = RS_NULL; + break; + case 15: + *rlt_sch = RS_BOOL; + break; + case 16: + *rlt_sch = RS_INT; + if (cur_chr == '.') {*rlt_sch = RS_FLOAT; return 18;} + if (cur_chr == 'E' || + cur_chr == 'e') {*rlt_sch = RS_STR; return 11;} + break; + case 17: + *rlt_sch = RS_INT; + if (cur_chr == '.') {*rlt_sch = RS_FLOAT; return 18;} + if (cur_chr == 'E' || + cur_chr == 'e') {*rlt_sch = RS_STR; return 11;} + if (('0' <= cur_chr && cur_chr <= '9')) {*rlt_sch = RS_INT; return 17;} + break; + case 18: + *rlt_sch = RS_FLOAT; + if (cur_chr == 'E' || + cur_chr == 'e') {*rlt_sch = RS_STR; return 11;} + if (('0' <= cur_chr && cur_chr <= '9')) {*rlt_sch = RS_FLOAT; return 18;} + break; + case 19: + *rlt_sch = RS_FLOAT; + if (('0' <= cur_chr && cur_chr <= '9')) {*rlt_sch = RS_FLOAT; return 19;} + break; + default: + *rlt_sch = RS_STR; + return SCH_STT_FRZ; + } + if (cur_chr != '\r' && cur_chr != '\n' && cur_chr != ' ' && cur_chr != 0) {*rlt_sch = RS_STR;} + return SCH_STT_FRZ; +}