♻️ 重构tree-sitter-tsf
This commit is contained in:
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,437 @@
|
||||
#include <wctype.h>
|
||||
#include <string.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include "tree_sitter/parser.h"
|
||||
|
||||
/* #define DEBUG 1 */
|
||||
#if DEBUG
|
||||
#define LOG(...) fprintf(stderr, "[SCANNER] " __VA_ARGS__)
|
||||
#else
|
||||
#define LOG(...)
|
||||
#endif
|
||||
|
||||
enum TokenType
|
||||
{
|
||||
TSLX_CONTENT,
|
||||
TSL_STATEMENT_START_TAG,
|
||||
TSL_STATEMENT_END_TAG,
|
||||
TSL_EXPRESSION_START_TAG,
|
||||
TSL_EXPRESSION_END_TAG,
|
||||
TSLX_END_TAG
|
||||
};
|
||||
|
||||
enum State
|
||||
{
|
||||
STATE_ROOT,
|
||||
STATE_TSLX,
|
||||
STATE_TSL_STATEMENT,
|
||||
STATE_TSL_EXPRESSION
|
||||
};
|
||||
|
||||
typedef struct
|
||||
{
|
||||
enum State* states;
|
||||
size_t capacity;
|
||||
size_t size;
|
||||
} StateStack;
|
||||
|
||||
static void stack_init(StateStack* stack)
|
||||
{
|
||||
stack->capacity = 8;
|
||||
stack->size = 0;
|
||||
stack->states = malloc(stack->capacity * sizeof(enum State));
|
||||
if (stack->states)
|
||||
{
|
||||
stack->states[0] = STATE_ROOT;
|
||||
stack->size = 1;
|
||||
}
|
||||
}
|
||||
|
||||
static void stack_free(StateStack* stack)
|
||||
{
|
||||
if (stack->states)
|
||||
{
|
||||
free(stack->states);
|
||||
stack->states = NULL;
|
||||
}
|
||||
stack->size = 0;
|
||||
stack->capacity = 0;
|
||||
}
|
||||
|
||||
static void stack_push(StateStack* stack, enum State state)
|
||||
{
|
||||
if (stack->size >= stack->capacity)
|
||||
{
|
||||
stack->capacity *= 2;
|
||||
stack->states = realloc(stack->states, stack->capacity * sizeof(enum State));
|
||||
}
|
||||
if (stack->states)
|
||||
{
|
||||
stack->states[stack->size++] = state;
|
||||
}
|
||||
}
|
||||
|
||||
static enum State stack_pop(StateStack* stack)
|
||||
{
|
||||
if (stack->size > 1)
|
||||
{
|
||||
return stack->states[--stack->size];
|
||||
}
|
||||
return STATE_ROOT;
|
||||
}
|
||||
|
||||
static enum State stack_top(const StateStack* stack)
|
||||
{
|
||||
return stack->size > 0 ? stack->states[stack->size - 1] : STATE_ROOT;
|
||||
}
|
||||
|
||||
void* tree_sitter_tsf_external_scanner_create()
|
||||
{
|
||||
StateStack* stack = malloc(sizeof(StateStack));
|
||||
if (stack)
|
||||
{
|
||||
stack_init(stack);
|
||||
}
|
||||
LOG("Scanner created\n");
|
||||
return stack;
|
||||
}
|
||||
|
||||
void tree_sitter_tsf_external_scanner_destroy(void* payload)
|
||||
{
|
||||
StateStack* stack = (StateStack*)payload;
|
||||
if (stack)
|
||||
{
|
||||
stack_free(stack);
|
||||
free(stack);
|
||||
}
|
||||
LOG("Scanner destroyed\n");
|
||||
}
|
||||
|
||||
unsigned tree_sitter_tsf_external_scanner_serialize(void* payload, char* buffer)
|
||||
{
|
||||
StateStack* stack = (StateStack*)payload;
|
||||
if (!stack || stack->size == 0)
|
||||
return 0;
|
||||
|
||||
size_t bytes_to_copy = stack->size * sizeof(enum State);
|
||||
if (bytes_to_copy > TREE_SITTER_SERIALIZATION_BUFFER_SIZE)
|
||||
{
|
||||
bytes_to_copy = TREE_SITTER_SERIALIZATION_BUFFER_SIZE;
|
||||
}
|
||||
|
||||
memcpy(buffer, stack->states, bytes_to_copy);
|
||||
return bytes_to_copy;
|
||||
}
|
||||
|
||||
void tree_sitter_tsf_external_scanner_deserialize(void* payload, const char* buffer, unsigned length)
|
||||
{
|
||||
StateStack* stack = (StateStack*)payload;
|
||||
if (!stack)
|
||||
return;
|
||||
|
||||
stack_free(stack);
|
||||
stack_init(stack);
|
||||
|
||||
if (length > 0)
|
||||
{
|
||||
size_t count = length / sizeof(enum State);
|
||||
for (size_t i = 0; i < count && i < stack->capacity; i++)
|
||||
{
|
||||
enum State state;
|
||||
memcpy(&state, buffer + i * sizeof(enum State), sizeof(enum State));
|
||||
if (i == 0)
|
||||
{
|
||||
stack->states[0] = state;
|
||||
}
|
||||
else
|
||||
{
|
||||
stack_push(stack, state);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static void skip_whitespace(TSLexer* lexer)
|
||||
{
|
||||
while (iswspace(lexer->lookahead))
|
||||
{
|
||||
lexer->advance(lexer, true);
|
||||
}
|
||||
}
|
||||
|
||||
static bool lookahead_for_close_tag(TSLexer* lexer)
|
||||
{
|
||||
LOG(" [lookahead_for_close_tag] Starting lookahead\n");
|
||||
|
||||
while (lexer->lookahead != '\0')
|
||||
{
|
||||
if (lexer->lookahead == '?')
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
if (lexer->lookahead == '>')
|
||||
{
|
||||
LOG(" [lookahead_for_close_tag] Found ?>, returning true\n");
|
||||
return true;
|
||||
}
|
||||
}
|
||||
else if (lexer->lookahead == '<')
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
if (lexer->lookahead == '?')
|
||||
{
|
||||
LOG(" [lookahead_for_close_tag] Found next <?, returning false\n");
|
||||
return false;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
}
|
||||
}
|
||||
|
||||
LOG(" [lookahead_for_close_tag] Reached EOF, returning false\n");
|
||||
return false;
|
||||
}
|
||||
|
||||
static int peek_special_tag(TSLexer* lexer)
|
||||
{
|
||||
if (lexer->lookahead != '<')
|
||||
return 0;
|
||||
|
||||
lexer->advance(lexer, false);
|
||||
if (lexer->lookahead != '?')
|
||||
return 0;
|
||||
|
||||
lexer->advance(lexer, false);
|
||||
|
||||
if (lexer->lookahead == '=')
|
||||
{
|
||||
LOG(" [peek_special_tag] Found <?=\n");
|
||||
return 1;
|
||||
}
|
||||
|
||||
if (towlower(lexer->lookahead) == 't')
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
if (towlower(lexer->lookahead) == 's')
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
if (towlower(lexer->lookahead) == 'l')
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
if (!iswalnum(lexer->lookahead) && lexer->lookahead != '_')
|
||||
{
|
||||
LOG(" [peek_special_tag] Found <?tsl\n");
|
||||
return 2;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static bool scan_tslx_content(TSLexer* lexer)
|
||||
{
|
||||
bool has_content = false;
|
||||
LOG(" [scan_tslx_content] Starting scan\n");
|
||||
|
||||
while (lexer->lookahead != '\0')
|
||||
{
|
||||
if (lexer->lookahead == '<')
|
||||
{
|
||||
lexer->mark_end(lexer);
|
||||
|
||||
int tag_type = peek_special_tag(lexer);
|
||||
|
||||
if (tag_type > 0)
|
||||
{
|
||||
LOG(" [scan_tslx_content] Found special tag, stopping. has_content=%d\n", has_content);
|
||||
return has_content;
|
||||
}
|
||||
|
||||
has_content = true;
|
||||
}
|
||||
else
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
has_content = true;
|
||||
}
|
||||
}
|
||||
|
||||
LOG(" [scan_tslx_content] Reached EOF, has_content=%d\n", has_content);
|
||||
return has_content;
|
||||
}
|
||||
|
||||
bool tree_sitter_tsf_external_scanner_scan(void* payload, TSLexer* lexer, const bool* valid_symbols)
|
||||
{
|
||||
StateStack* stack = (StateStack*)payload;
|
||||
if (!stack)
|
||||
{
|
||||
LOG("ERROR: stack is NULL\n");
|
||||
return false;
|
||||
}
|
||||
|
||||
enum State current_state = stack_top(stack);
|
||||
|
||||
LOG("\n=== SCAN START ===\n");
|
||||
LOG("Current state: %d (0=ROOT, 1=TSLX, 2=TSL_STATEMENT, 3=TSL_EXPRESSION)\n", current_state);
|
||||
LOG("Current char: '%c' (0x%02x)\n", lexer->lookahead, lexer->lookahead);
|
||||
LOG("Valid symbols: CONTENT=%d, TSL_START=%d, TSL_END=%d, EXPR_START=%d, EXPR_END=%d, TSLX_END=%d\n",
|
||||
valid_symbols[TSLX_CONTENT],
|
||||
valid_symbols[TSL_STATEMENT_START_TAG],
|
||||
valid_symbols[TSL_STATEMENT_END_TAG],
|
||||
valid_symbols[TSL_EXPRESSION_START_TAG],
|
||||
valid_symbols[TSL_EXPRESSION_END_TAG],
|
||||
valid_symbols[TSLX_END_TAG]);
|
||||
|
||||
// ⚠️ 关键修复：通过 valid_symbols 推断状态切换
|
||||
// 如果当前在 ROOT 状态，但 parser 期望 TSLX 内部的 token，说明刚匹配完 <?tslx>
|
||||
if (current_state == STATE_ROOT &&
|
||||
(valid_symbols[TSLX_CONTENT] ||
|
||||
valid_symbols[TSL_STATEMENT_START_TAG] ||
|
||||
valid_symbols[TSL_EXPRESSION_START_TAG] ||
|
||||
valid_symbols[TSLX_END_TAG]))
|
||||
{
|
||||
LOG("State transition: ROOT -> TSLX (inferred from valid_symbols)\n");
|
||||
stack_push(stack, STATE_TSLX);
|
||||
current_state = STATE_TSLX;
|
||||
}
|
||||
|
||||
if (current_state == STATE_TSL_STATEMENT || current_state == STATE_TSL_EXPRESSION)
|
||||
{
|
||||
skip_whitespace(lexer);
|
||||
LOG("After skip whitespace: '%c' (0x%02x)\n", lexer->lookahead, lexer->lookahead);
|
||||
}
|
||||
|
||||
if (current_state == STATE_TSLX)
|
||||
{
|
||||
LOG("In STATE_TSLX\n");
|
||||
|
||||
if (lexer->lookahead == '\0' && valid_symbols[TSLX_END_TAG])
|
||||
{
|
||||
LOG("Found EOF, returning TSLX_END_TAG\n");
|
||||
lexer->mark_end(lexer);
|
||||
lexer->result_symbol = TSLX_END_TAG;
|
||||
stack_pop(stack);
|
||||
return true;
|
||||
}
|
||||
|
||||
if (lexer->lookahead == '<')
|
||||
{
|
||||
LOG("Found '<', checking for tag\n");
|
||||
lexer->advance(lexer, false);
|
||||
|
||||
if (lexer->lookahead == '?')
|
||||
{
|
||||
LOG("Found '<?', checking tag type\n");
|
||||
lexer->advance(lexer, false);
|
||||
|
||||
if (lexer->lookahead == '=' && valid_symbols[TSL_EXPRESSION_START_TAG])
|
||||
{
|
||||
LOG("Found '<?=', returning TSL_EXPRESSION_START_TAG\n");
|
||||
lexer->advance(lexer, false);
|
||||
lexer->mark_end(lexer);
|
||||
lexer->result_symbol = TSL_EXPRESSION_START_TAG;
|
||||
stack_push(stack, STATE_TSL_EXPRESSION);
|
||||
return true;
|
||||
}
|
||||
|
||||
if (towlower(lexer->lookahead) == 't')
|
||||
{
|
||||
LOG("Found 't', checking for 'tsl'\n");
|
||||
lexer->advance(lexer, false);
|
||||
|
||||
if (towlower(lexer->lookahead) == 's')
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
|
||||
if (towlower(lexer->lookahead) == 'l')
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
|
||||
LOG("Found 'tsl', next char: '%c' (0x%02x)\n", lexer->lookahead, lexer->lookahead);
|
||||
|
||||
if (!iswalnum(lexer->lookahead) && lexer->lookahead != '_')
|
||||
{
|
||||
LOG("Valid <?tsl delimiter, performing lookahead\n");
|
||||
|
||||
lexer->mark_end(lexer);
|
||||
|
||||
bool has_close_tag = lookahead_for_close_tag(lexer);
|
||||
LOG("Lookahead result: has_close_tag = %d\n", has_close_tag);
|
||||
|
||||
if (has_close_tag && valid_symbols[TSL_STATEMENT_START_TAG])
|
||||
{
|
||||
LOG("Returning TSL_STATEMENT_START_TAG\n");
|
||||
lexer->result_symbol = TSL_STATEMENT_START_TAG;
|
||||
stack_push(stack, STATE_TSL_STATEMENT);
|
||||
return true;
|
||||
}
|
||||
else if (!has_close_tag && valid_symbols[TSLX_END_TAG])
|
||||
{
|
||||
LOG("Returning TSLX_END_TAG (<?tsl without ?>)\n");
|
||||
lexer->result_symbol = TSLX_END_TAG;
|
||||
stack_pop(stack);
|
||||
return true;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (valid_symbols[TSLX_CONTENT])
|
||||
{
|
||||
LOG("Trying to scan TSLX_CONTENT\n");
|
||||
if (scan_tslx_content(lexer))
|
||||
{
|
||||
LOG("Successfully scanned TSLX_CONTENT\n");
|
||||
lexer->result_symbol = TSLX_CONTENT;
|
||||
return true;
|
||||
}
|
||||
LOG("Failed to scan TSLX_CONTENT\n");
|
||||
}
|
||||
}
|
||||
|
||||
if (current_state == STATE_TSL_STATEMENT)
|
||||
{
|
||||
LOG("In STATE_TSL_STATEMENT\n");
|
||||
if (lexer->lookahead == '?' && valid_symbols[TSL_STATEMENT_END_TAG])
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
if (lexer->lookahead == '>')
|
||||
{
|
||||
LOG("Found '?>', returning TSL_STATEMENT_END_TAG\n");
|
||||
lexer->advance(lexer, false);
|
||||
lexer->mark_end(lexer);
|
||||
lexer->result_symbol = TSL_STATEMENT_END_TAG;
|
||||
stack_pop(stack);
|
||||
return true;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (current_state == STATE_TSL_EXPRESSION)
|
||||
{
|
||||
LOG("In STATE_TSL_EXPRESSION\n");
|
||||
if (lexer->lookahead == '?' && valid_symbols[TSL_EXPRESSION_END_TAG])
|
||||
{
|
||||
lexer->advance(lexer, false);
|
||||
if (lexer->lookahead == '>')
|
||||
{
|
||||
LOG("Found '?>', returning TSL_EXPRESSION_END_TAG\n");
|
||||
lexer->advance(lexer, false);
|
||||
lexer->mark_end(lexer);
|
||||
lexer->result_symbol = TSL_EXPRESSION_END_TAG;
|
||||
stack_pop(stack);
|
||||
return true;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
LOG("Returning false (no match)\n");
|
||||
return false;
|
||||
}
|
||||
@@ -0,0 +1,54 @@
|
||||
#ifndef TREE_SITTER_ALLOC_H_
|
||||
#define TREE_SITTER_ALLOC_H_
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#include <stdbool.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
|
||||
// Allow clients to override allocation functions
|
||||
#ifdef TREE_SITTER_REUSE_ALLOCATOR
|
||||
|
||||
extern void *(*ts_current_malloc)(size_t 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_
|
||||
@@ -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_
|
||||
@@ -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_
|
||||
Reference in New Issue
Block a user