Jai syntax highlighting
This commit is contained in:
parent
79695eca2c
commit
086ac34c4d
|
|
@ -1,3 +1,4 @@
|
|||
.DS_Store
|
||||
build/
|
||||
build_new/temp
|
||||
current_dist*/
|
||||
|
|
|
|||
|
|
@ -44,9 +44,10 @@ build_tree_sitter() {
|
|||
clang $CLANG_OPTS "${INCLUDES[@]}" "${CUSTOM_ROOT}/lang/cpp/scanner.cc" -o $TEMP_OUT_DIR/cpp_scanner.o
|
||||
print_success "Complete"
|
||||
|
||||
# Lang: C
|
||||
print_step "Building tree-sitter C Language Lib"
|
||||
clang $CLANG_OPTS "${INCLUDES[@]}" "${CUSTOM_ROOT}/lang/c/parser.c" -o $TEMP_OUT_DIR/c_parser.o
|
||||
# Lang: Jai
|
||||
print_step "Building tree-sitter Jai Language Lib"
|
||||
clang $CLANG_OPTS "${INCLUDES[@]}" "${CUSTOM_ROOT}/lang/jai/parser.c" -o $TEMP_OUT_DIR/jai_parser.o
|
||||
clang $CLANG_OPTS "${INCLUDES[@]}" "${CUSTOM_ROOT}/lang/jai/scanner.cc" -o $TEMP_OUT_DIR/jai_scanner.o
|
||||
print_success "Complete"
|
||||
|
||||
# Link tree-sitter lib and parser obj files into a static library to link into main custom dll
|
||||
|
|
|
|||
|
|
@ -3,35 +3,350 @@
|
|||
// TEMP until I implement more generic language stuff
|
||||
/////////////////////////////////////////////
|
||||
|
||||
/////////////////////////////////////////////
|
||||
// C
|
||||
|
||||
/////////////////////////////////////////////
|
||||
// C++
|
||||
|
||||
TSQuery* tree_sitter_cpp_index_query;
|
||||
String_Const_u8 TS_CPP_INDEX_QUERY = string_u8_litexpr("(_ \"{\" @Start \"}\" @End ) @ScopeNest\n");
|
||||
|
||||
String_Const_u8 TS_CPP_HIGHLIGHT_QUERY = string_u8_litexpr("(call_expression function: ["
|
||||
" (identifier) @defcolor_function"
|
||||
" (field_expression field: (field_identifier) @defcolor_function)])"
|
||||
"(function_declarator"
|
||||
" declarator: [(identifier) (field_identifier)] @defcolor_function)"
|
||||
String_Const_u8 TS_CPP_HIGHLIGHT_QUERY = string_u8_litexpr(R"DONE(
|
||||
(call_expression function: [
|
||||
(identifier) @defcolor_function
|
||||
(field_expression field: (field_identifier) @defcolor_function)])
|
||||
|
||||
"(preproc_def"
|
||||
" name: (identifier) @defcolor_macro)"
|
||||
"(preproc_function_def"
|
||||
" name: (identifier) @defcolor_macro)"
|
||||
(function_declarator
|
||||
declarator: [(identifier) (field_identifier)] @defcolor_function)
|
||||
|
||||
"(type_identifier) @defcolor_type"
|
||||
"(call_expression"
|
||||
" function: (parenthesized_expression"
|
||||
" (identifier) @defcolor_type))"
|
||||
(preproc_def
|
||||
name: (identifier) @defcolor_macro)
|
||||
|
||||
"[(primitive_type) (type_qualifier) (storage_class_specifier)"
|
||||
" (break_statement) (continue_statement) \"union\" \"return\" \"do\""
|
||||
" \"while\" \"for\" \"if\" \"class\" \"struct\" \"enum\" \"sizeof\""
|
||||
" \"else\" \"switch\" \"case\"] @defcolor_keyword"
|
||||
(preproc_function_def
|
||||
name: (identifier) @defcolor_macro)
|
||||
|
||||
"[(number_literal) (string_literal)] @defcolor_str_constant"
|
||||
"[(preproc_directive) \"#define\" \"#if\" \"#elif\" \"#else\" \"#endif\""
|
||||
" \"#include\"] @defcolor_preproc"
|
||||
"[\"{\" \"}\" \";\" \":\" \",\"] @defcolor_text_default"
|
||||
"(comment) @defcolor_comment");
|
||||
(type_identifier) @defcolor_type
|
||||
|
||||
(call_expression
|
||||
function: (parenthesized_expression
|
||||
(identifier) @defcolor_type))
|
||||
|
||||
[(primitive_type) (type_qualifier) (storage_class_specifier)
|
||||
(break_statement) (continue_statement) "union" "return" "do"
|
||||
"while" "for" "if" "class" "struct" "enum" "sizeof"
|
||||
"else" "switch" "case"] @defcolor_keyword
|
||||
|
||||
[(number_literal) (string_literal) (raw_string_literal)] @defcolor_str_constant
|
||||
|
||||
[(preproc_directive) "#define" "#if" "#elif" "#else" "#endif"
|
||||
"#include"] @defcolor_preproc
|
||||
|
||||
["{" "}" ";" ":" ","] @defcolor_text_default
|
||||
|
||||
(comment) @defcolor_comment
|
||||
)DONE");
|
||||
|
||||
/////////////////////////////////////////////
|
||||
// Jai
|
||||
|
||||
String_Const_u8 TS_JAI_HIGHLIGHT_QUERY = string_u8_litexpr(R"DONE(
|
||||
|
||||
; keywords
|
||||
[
|
||||
"if"
|
||||
"else"
|
||||
"break"
|
||||
"continue"
|
||||
"return"
|
||||
"struct"
|
||||
"enum"
|
||||
"for"
|
||||
"defer"
|
||||
"cast"
|
||||
"xx"
|
||||
"ifx"
|
||||
"null"
|
||||
] @defcolor_keyword
|
||||
|
||||
; # preceeded
|
||||
[
|
||||
(compiler_directive)
|
||||
(import)
|
||||
(char_string)
|
||||
] @defcolor_macro
|
||||
|
||||
(import (identifier) @defcolor_type)
|
||||
|
||||
; Identifiers
|
||||
(struct_declaration
|
||||
name: (identifier) @defcolor_type
|
||||
)
|
||||
|
||||
(struct_literal
|
||||
type: (identifier) @defcolor_type
|
||||
)
|
||||
|
||||
(enum_declaration
|
||||
name: (identifier) @defcolor_type
|
||||
)
|
||||
|
||||
(enum_declaration "{" (identifier) @defcolor_type)
|
||||
|
||||
(variable_declaration
|
||||
type: (types) @defcolor_type
|
||||
)
|
||||
|
||||
(procedure_declaration
|
||||
name: (identifier) @defcolor_function
|
||||
)
|
||||
|
||||
(call_expression
|
||||
function: (identifier) @defcolor_function
|
||||
)
|
||||
|
||||
(procedure
|
||||
result: (procedure_returns) @defcolor_type
|
||||
)
|
||||
|
||||
; Constants & Literals
|
||||
[
|
||||
(string)
|
||||
(string_directive)
|
||||
] @defcolor_str_constant
|
||||
(escape_sequence) @defcolor_special_character
|
||||
(integer) @defcolor_int_constant
|
||||
(float) @defcolor_float_constant
|
||||
(boolean) @defcolor_bool_constant
|
||||
|
||||
(array_literal
|
||||
type: (identifier) @defcolor_type
|
||||
)
|
||||
|
||||
; Comments
|
||||
(note) @defcolor_comment
|
||||
(block_comment) @defcolor_comment
|
||||
(block_comment_text) @defcolor_comment
|
||||
|
||||
)DONE");
|
||||
|
||||
// NOTE(PS): source: https://github.com/St0wy/tree-sitter-jai/blob/main/queries/highlights.scm
|
||||
String_Const_u8 TS_JAI_HIGHLIGHT_QUERY_ = string_u8_litexpr(R"DONE(
|
||||
|
||||
[
|
||||
(compiler_directive)
|
||||
(import)
|
||||
] @defcolor_macro
|
||||
|
||||
; Keywords
|
||||
; TODO : complete this list
|
||||
[
|
||||
"struct"
|
||||
"enum"
|
||||
"defer"
|
||||
"cast"
|
||||
"xx"
|
||||
"return"
|
||||
] @defcolor_keyword
|
||||
|
||||
; Conditionals
|
||||
[
|
||||
"if"
|
||||
"else"
|
||||
"case"
|
||||
"break"
|
||||
] @defcolor_keyword
|
||||
|
||||
((if_expression
|
||||
[
|
||||
"then"
|
||||
"ifx"
|
||||
"else"
|
||||
] @defcolor_keyword)
|
||||
(#set! "priority" 105))
|
||||
|
||||
; Repeats
|
||||
|
||||
[
|
||||
"for"
|
||||
"while"
|
||||
"continue"
|
||||
] @defcolor_keyword
|
||||
|
||||
; Variables
|
||||
|
||||
(identifier) @defcolor_text_default
|
||||
|
||||
; Namespaces
|
||||
|
||||
(import (identifier) @defcolor_text_default)
|
||||
|
||||
; Parameters
|
||||
|
||||
(parameter (identifier) @defcolor_text_default ":" "="? (identifier)? @defcolor_str_constant)
|
||||
|
||||
(default_parameter (identifier) @defcolor_text_default ":=")
|
||||
|
||||
(call_expression argument: (identifier) @defcolor_text_default "=")
|
||||
|
||||
; Functions
|
||||
|
||||
(procedure_declaration (identifier) @defcolor_function)
|
||||
|
||||
(procedure_declaration (identifier) @defcolor_function (procedure (block)))
|
||||
|
||||
(call_expression function: (identifier) @defcolor_function)
|
||||
|
||||
; Types
|
||||
|
||||
(type (identifier) @defcolor_type)
|
||||
|
||||
((type (identifier) @defcolor_type)
|
||||
(#any-of? @type.builtin
|
||||
"bool"
|
||||
"int" "s8" "s16" "s32" "s64"
|
||||
"u8" "u16" "u32" "u64"
|
||||
"string"))
|
||||
|
||||
|
||||
(struct_declaration (identifier) @defcolor_type "::")
|
||||
|
||||
(enum_declaration (identifier) @defcolor_type "::")
|
||||
|
||||
;(union_declaration (identifier) @defcolor_type "::")
|
||||
|
||||
(const_declaration (identifier) @defcolor_type "::" [(array_type) (pointer_type)])
|
||||
|
||||
(struct . (identifier) @defcolor_type)
|
||||
|
||||
;(field_type . (identifier) @namespace "." (identifier) @defcolor_type)
|
||||
|
||||
;(bit_set_type (identifier) @defcolor_type ";")
|
||||
|
||||
;(procedure_type (parameters (parameter (identifier) @defcolor_type)))
|
||||
|
||||
;(polymorphic_parameters (identifier) @defcolor_type)
|
||||
|
||||
((identifier) @defcolor_type
|
||||
(#lua-match? @defcolor_type "^[A-Z][a-zA-Z0-9]*$")
|
||||
(#not-has-parent? @defcolor_type parameter procedure_declaration call_expression))
|
||||
|
||||
; Fields
|
||||
|
||||
(member_expression "." (identifier) @defcolor_text_default)
|
||||
|
||||
;(struct_type "{" (identifier) @defcolor_text_default)
|
||||
|
||||
(struct_field (identifier) @defcolor_text_default "="?)
|
||||
|
||||
(field (identifier) @defcolor_text_default)
|
||||
|
||||
; Constants
|
||||
|
||||
((identifier) @defcolor_text_default
|
||||
(#lua-match? @defcolor_str_constnat "^_*[A-Z][A-Z0-9_]*$")
|
||||
(#not-has-parent? @text_default type parameter))
|
||||
|
||||
(member_expression . "." (identifier) @defcolor_text_default)
|
||||
|
||||
(enum_declaration "{" (identifier) @defcolor_text_default)
|
||||
|
||||
; Literals
|
||||
|
||||
(number) @defcolor_int_constant
|
||||
|
||||
(float) @defcolor_float_constant
|
||||
|
||||
(string) @defcolor_str_constnat
|
||||
|
||||
;(character) @defcolor_str_constnat
|
||||
|
||||
(escape_sequence) @defcolor_str_constant
|
||||
|
||||
(boolean) @defcolor_bool_constant
|
||||
|
||||
[
|
||||
(uninitialized)
|
||||
(null)
|
||||
] @defcolor_text_default
|
||||
|
||||
((identifier) @defcolor_text_default
|
||||
(#any-of? @defcolor_text_default "context"))
|
||||
|
||||
; Operators
|
||||
|
||||
[
|
||||
":="
|
||||
"="
|
||||
"+"
|
||||
"-"
|
||||
"*"
|
||||
"/"
|
||||
"%"
|
||||
"%%"
|
||||
">"
|
||||
">="
|
||||
"<"
|
||||
"<="
|
||||
"=="
|
||||
"!="
|
||||
"~="
|
||||
"|"
|
||||
"~"
|
||||
"&"
|
||||
"&~"
|
||||
"<<"
|
||||
">>"
|
||||
"||"
|
||||
"&&"
|
||||
"!"
|
||||
".."
|
||||
"+="
|
||||
"-="
|
||||
"*="
|
||||
"/="
|
||||
"%="
|
||||
"&="
|
||||
"|="
|
||||
"^="
|
||||
"<<="
|
||||
">>="
|
||||
"||="
|
||||
"&&="
|
||||
"&~="
|
||||
;"..="
|
||||
;"..<"
|
||||
;"?"
|
||||
] @defcolor_operator
|
||||
|
||||
; Punctuation
|
||||
|
||||
[ "{" "}" ] @defcolor_text_default
|
||||
|
||||
[ "(" ")" ] @defcolor_text_default
|
||||
|
||||
[ "[" "]" ] @defcolor_text_default
|
||||
|
||||
[
|
||||
"::"
|
||||
"->"
|
||||
"."
|
||||
","
|
||||
":"
|
||||
";"
|
||||
] @defcolor_text_default
|
||||
|
||||
; Comments
|
||||
|
||||
[
|
||||
(comment)
|
||||
(block_comment)
|
||||
] @defcolor_comment
|
||||
|
||||
; Errors
|
||||
|
||||
(ERROR) @defcolor_comment_pop
|
||||
)DONE");
|
||||
|
||||
////////////////////////////////////////////////////////////////////
|
||||
// Language Management
|
||||
|
|
@ -123,15 +438,36 @@ tree_sitter_init(Application_Links* app)
|
|||
String_Const_u8 highlight_query_str = TS_CPP_HIGHLIGHT_QUERY;
|
||||
TSQuery* highlight_query = ts_query_new(
|
||||
language,
|
||||
(const char *)TS_CPP_HIGHLIGHT_QUERY.str,
|
||||
(u32)TS_CPP_HIGHLIGHT_QUERY.size,
|
||||
(const char *)highlight_query_str.str,
|
||||
(u32)highlight_query_str.size,
|
||||
&error_offset, &query_error
|
||||
);
|
||||
tree_sitter_register_language(SCu8("c"), language, highlight_query);
|
||||
tree_sitter_register_language(SCu8("cpp"), language, highlight_query);
|
||||
tree_sitter_register_language(SCu8("h"), language, highlight_query);
|
||||
tree_sitter_register_language(SCu8("hpp"), language, highlight_query);
|
||||
tree_sitter_register_language(SCu8("cc"), language, highlight_query);
|
||||
}
|
||||
|
||||
{ // Register Jai
|
||||
TSLanguage* language = tree_sitter_jai();
|
||||
String_Const_u8 highlight_query_str = TS_JAI_HIGHLIGHT_QUERY;
|
||||
TSQuery* highlight_query = ts_query_new(
|
||||
language,
|
||||
(const char *)highlight_query_str.str,
|
||||
(u32)highlight_query_str.size,
|
||||
&error_offset, &query_error
|
||||
);
|
||||
if (!highlight_query)
|
||||
{
|
||||
print_message(app, SCu8("Error creating jai highlight query\n"));
|
||||
printf("%.*s\n", (int)Min(highlight_query_str.size-error_offset, 100), highlight_query_str.str + error_offset);
|
||||
}
|
||||
else
|
||||
{
|
||||
tree_sitter_register_language(SCu8("jai"), language, highlight_query);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
function void
|
||||
|
|
@ -146,15 +482,15 @@ function void
|
|||
tree_sitter_end_buffer(Application_Links* app, Buffer_ID buffer_id)
|
||||
{
|
||||
Managed_Scope buffer_scope = buffer_get_managed_scope(app, buffer_id);
|
||||
Buffer_Tree_Sitter_Data* tree_data = scope_attachment(app, buffer_scope, buffer_tree_sitter_data_id, Buffer_Tree_Sitter_Data);
|
||||
if (!tree_data) return;
|
||||
|
||||
Async_Task *tree_sitter_parse_task = scope_attachment(app, buffer_scope, buffer_tree_sitter_parse_task_id, Async_Task);
|
||||
if (async_task_is_running_or_pending(&global_async_system, *tree_sitter_parse_task))
|
||||
if (tree_sitter_parse_task && async_task_is_running_or_pending(&global_async_system, *tree_sitter_parse_task))
|
||||
{
|
||||
async_task_cancel(app, &global_async_system, *tree_sitter_parse_task);
|
||||
}
|
||||
|
||||
Buffer_Tree_Sitter_Data* tree_data = scope_attachment(app, buffer_scope, buffer_tree_sitter_data_id, Buffer_Tree_Sitter_Data);
|
||||
if (!tree_data || !tree_data->tree) return;
|
||||
system_mutex_acquire(tree_data->tree_mutex);
|
||||
ts_tree_delete(tree_data->tree);
|
||||
system_mutex_release(tree_data->tree_mutex);
|
||||
|
|
|
|||
|
|
@ -26,7 +26,7 @@ global Tree_Sitter_Languages tree_sitter_languages;
|
|||
|
||||
extern "C" {
|
||||
TSLanguage *tree_sitter_cpp();
|
||||
TSLanguage *tree_sitter_c();
|
||||
TSLanguage *tree_sitter_jai();
|
||||
}
|
||||
|
||||
CUSTOM_ID(attachment, buffer_tree_sitter_data_id);
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -1,119 +1,152 @@
|
|||
#include <tree_sitter/parser.h>
|
||||
#include <string>
|
||||
#include <cwctype>
|
||||
#include "tree_sitter/alloc.h"
|
||||
#include "tree_sitter/parser.h"
|
||||
|
||||
namespace {
|
||||
#include <assert.h>
|
||||
#include <string.h>
|
||||
#include <wctype.h>
|
||||
|
||||
using std::wstring;
|
||||
using std::iswspace;
|
||||
enum TokenType { RAW_STRING_DELIMITER, RAW_STRING_CONTENT };
|
||||
|
||||
enum TokenType {
|
||||
RAW_STRING_LITERAL,
|
||||
};
|
||||
/// The spec limits delimiters to 16 chars
|
||||
#define MAX_DELIMITER_LENGTH 16
|
||||
|
||||
struct Scanner {
|
||||
bool scan(TSLexer *lexer, const bool *valid_symbols) {
|
||||
while (iswspace(lexer->lookahead)) {
|
||||
lexer->advance(lexer, true);
|
||||
}
|
||||
typedef struct {
|
||||
uint8_t delimiter_length;
|
||||
wchar_t delimiter[MAX_DELIMITER_LENGTH];
|
||||
} Scanner;
|
||||
|
||||
lexer->result_symbol = RAW_STRING_LITERAL;
|
||||
static inline void advance(TSLexer *lexer) { lexer->advance(lexer, false); }
|
||||
|
||||
// Raw string literals can start with: R, LR, uR, UR, u8R
|
||||
// Consume 'R'
|
||||
if (lexer->lookahead == 'L' || lexer->lookahead == 'U') {
|
||||
lexer->advance(lexer, false);
|
||||
if (lexer->lookahead != 'R') {
|
||||
return false;
|
||||
}
|
||||
} else if (lexer->lookahead == 'u') {
|
||||
lexer->advance(lexer, false);
|
||||
if (lexer->lookahead == '8') {
|
||||
lexer->advance(lexer, false);
|
||||
if (lexer->lookahead != 'R') {
|
||||
return false;
|
||||
static inline void reset(Scanner *scanner) {
|
||||
scanner->delimiter_length = 0;
|
||||
memset(scanner->delimiter, 0, sizeof scanner->delimiter);
|
||||
}
|
||||
|
||||
/// Scan the raw string delimiter in R"delimiter(content)delimiter"
|
||||
static bool scan_raw_string_delimiter(Scanner *scanner, TSLexer *lexer) {
|
||||
if (scanner->delimiter_length > 0) {
|
||||
// Closing delimiter: must exactly match the opening delimiter.
|
||||
// We already checked this when scanning content, but this is how we
|
||||
// know when to stop. We can't stop at ", because R"""hello""" is valid.
|
||||
for (int i = 0; i < scanner->delimiter_length; ++i) {
|
||||
if (lexer->lookahead != scanner->delimiter[i]) {
|
||||
return false;
|
||||
}
|
||||
advance(lexer);
|
||||
}
|
||||
} else if (lexer->lookahead != 'R') {
|
||||
return false;
|
||||
}
|
||||
} else if (lexer->lookahead != 'R') {
|
||||
return false;
|
||||
}
|
||||
lexer->advance(lexer, false);
|
||||
|
||||
// Consume '"'
|
||||
if (lexer->lookahead != '"') return false;
|
||||
lexer->advance(lexer, false);
|
||||
|
||||
// Consume '(', delimiter
|
||||
wstring delimiter;
|
||||
for (;;) {
|
||||
if (lexer->lookahead == 0 || lexer->lookahead == '\\' || iswspace(lexer->lookahead)) {
|
||||
return false;
|
||||
}
|
||||
if (lexer->lookahead == '(') {
|
||||
lexer->advance(lexer, false);
|
||||
break;
|
||||
}
|
||||
delimiter += lexer->lookahead;
|
||||
lexer->advance(lexer, false);
|
||||
reset(scanner);
|
||||
return true;
|
||||
}
|
||||
|
||||
// Consume content, delimiter, ')', '"'
|
||||
int delimiter_index = -1;
|
||||
// Opening delimiter: record the d-char-sequence up to (.
|
||||
// d-char is any basic character except parens, backslashes, and spaces.
|
||||
for (;;) {
|
||||
if (lexer->lookahead == 0) return false;
|
||||
if (scanner->delimiter_length >= MAX_DELIMITER_LENGTH || lexer->eof(lexer) || lexer->lookahead == '\\' ||
|
||||
iswspace(lexer->lookahead)) {
|
||||
return false;
|
||||
}
|
||||
if (lexer->lookahead == '(') {
|
||||
// Rather than create a token for an empty delimiter, we fail and
|
||||
// let the grammar fall back to a delimiter-less rule.
|
||||
return scanner->delimiter_length > 0;
|
||||
}
|
||||
scanner->delimiter[scanner->delimiter_length++] = lexer->lookahead;
|
||||
advance(lexer);
|
||||
}
|
||||
}
|
||||
|
||||
if (delimiter_index >= 0) {
|
||||
if (static_cast<unsigned>(delimiter_index) == delimiter.size()) {
|
||||
if (lexer->lookahead == '"') {
|
||||
lexer->advance(lexer, false);
|
||||
/// Scan the raw string content in R"delimiter(content)delimiter"
|
||||
static bool scan_raw_string_content(Scanner *scanner, TSLexer *lexer) {
|
||||
// The progress made through the delimiter since the last ')'.
|
||||
// The delimiter may not contain ')' so a single counter suffices.
|
||||
for (int delimiter_index = -1;;) {
|
||||
// If we hit EOF, consider the content to terminate there.
|
||||
// This forms an incomplete raw_string_literal, and models the code
|
||||
// well.
|
||||
if (lexer->eof(lexer)) {
|
||||
lexer->mark_end(lexer);
|
||||
return true;
|
||||
} else {
|
||||
delimiter_index = -1;
|
||||
}
|
||||
} else {
|
||||
if (lexer->lookahead == delimiter[delimiter_index]) {
|
||||
delimiter_index++;
|
||||
} else {
|
||||
delimiter_index = -1;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (delimiter_index == -1 && lexer->lookahead == ')') {
|
||||
delimiter_index = 0;
|
||||
}
|
||||
if (delimiter_index >= 0) {
|
||||
if (delimiter_index == scanner->delimiter_length) {
|
||||
if (lexer->lookahead == '"') {
|
||||
return true;
|
||||
}
|
||||
delimiter_index = -1;
|
||||
} else {
|
||||
if (lexer->lookahead == scanner->delimiter[delimiter_index]) {
|
||||
delimiter_index += 1;
|
||||
} else {
|
||||
delimiter_index = -1;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
lexer->advance(lexer, false);
|
||||
if (delimiter_index == -1 && lexer->lookahead == ')') {
|
||||
// The content doesn't include the )delimiter" part.
|
||||
// We must still scan through it, but exclude it from the token.
|
||||
lexer->mark_end(lexer);
|
||||
delimiter_index = 0;
|
||||
}
|
||||
|
||||
advance(lexer);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
}
|
||||
|
||||
extern "C" {
|
||||
|
||||
void *tree_sitter_cpp_external_scanner_create() {
|
||||
return new Scanner();
|
||||
Scanner *scanner = (Scanner *)ts_calloc(1, sizeof(Scanner));
|
||||
memset(scanner, 0, sizeof(Scanner));
|
||||
return scanner;
|
||||
}
|
||||
|
||||
bool tree_sitter_cpp_external_scanner_scan(void *payload, TSLexer *lexer,
|
||||
const bool *valid_symbols) {
|
||||
Scanner *scanner = static_cast<Scanner *>(payload);
|
||||
return scanner->scan(lexer, valid_symbols);
|
||||
bool tree_sitter_cpp_external_scanner_scan(void *payload, TSLexer *lexer, const bool *valid_symbols) {
|
||||
Scanner *scanner = (Scanner *)payload;
|
||||
|
||||
if (valid_symbols[RAW_STRING_DELIMITER] && valid_symbols[RAW_STRING_CONTENT]) {
|
||||
// we're in error recovery
|
||||
return false;
|
||||
}
|
||||
|
||||
// No skipping leading whitespace: raw-string grammar is space-sensitive.
|
||||
if (valid_symbols[RAW_STRING_DELIMITER]) {
|
||||
lexer->result_symbol = RAW_STRING_DELIMITER;
|
||||
return scan_raw_string_delimiter(scanner, lexer);
|
||||
}
|
||||
|
||||
if (valid_symbols[RAW_STRING_CONTENT]) {
|
||||
lexer->result_symbol = RAW_STRING_CONTENT;
|
||||
return scan_raw_string_content(scanner, lexer);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
unsigned tree_sitter_cpp_external_scanner_serialize(void *payload, char *buffer) {
|
||||
return 0;
|
||||
static_assert(MAX_DELIMITER_LENGTH * sizeof(wchar_t) < TREE_SITTER_SERIALIZATION_BUFFER_SIZE,
|
||||
"Serialized delimiter is too long!");
|
||||
|
||||
Scanner *scanner = (Scanner *)payload;
|
||||
size_t size = scanner->delimiter_length * sizeof(wchar_t);
|
||||
memcpy(buffer, scanner->delimiter, size);
|
||||
return (unsigned)size;
|
||||
}
|
||||
|
||||
void tree_sitter_cpp_external_scanner_deserialize(void *payload, const char *buffer, unsigned length) {
|
||||
assert(length % sizeof(wchar_t) == 0 && "Can't decode serialized delimiter!");
|
||||
|
||||
Scanner *scanner = (Scanner *)payload;
|
||||
scanner->delimiter_length = length / sizeof(wchar_t);
|
||||
if (length > 0) {
|
||||
memcpy(&scanner->delimiter[0], buffer, length);
|
||||
}
|
||||
}
|
||||
|
||||
void tree_sitter_cpp_external_scanner_destroy(void *payload) {
|
||||
Scanner *scanner = static_cast<Scanner *>(payload);
|
||||
delete scanner;
|
||||
Scanner *scanner = (Scanner *)payload;
|
||||
ts_free(scanner);
|
||||
}
|
||||
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,283 @@
|
|||
#include <tree_sitter/alloc.h>
|
||||
#include <tree_sitter/array.h>
|
||||
#include <tree_sitter/parser.h>
|
||||
|
||||
#include <string.h>
|
||||
#include <wchar.h>
|
||||
#include <wctype.h>
|
||||
|
||||
typedef enum {
|
||||
// IDENTIFIER,
|
||||
HEREDOC_START,
|
||||
HEREDOC_END,
|
||||
ERROR_SENTINEL,
|
||||
} TokenType;
|
||||
|
||||
// typedef Array(char) String;
|
||||
typedef Array(int32_t) String32;
|
||||
|
||||
static inline bool string_eq(String32 *self, String32 *other) {
|
||||
if (self->size != other->size)
|
||||
return false;
|
||||
if (self->size == 0)
|
||||
return self->size == other->size;
|
||||
return memcmp(self->contents, other->contents, self->size * sizeof(self->contents[0])) == 0;
|
||||
}
|
||||
|
||||
typedef struct {
|
||||
Array(String32) heredocs;
|
||||
} Scanner;
|
||||
|
||||
typedef enum { ERROR, END } ScanContentResult;
|
||||
|
||||
static inline void reset_heredoc(String32 *heredoc) {
|
||||
array_delete(heredoc);
|
||||
}
|
||||
|
||||
static inline void advance(TSLexer *lexer) { if (!lexer->eof(lexer)) lexer->advance(lexer, false); }
|
||||
static inline void skip(TSLexer *lexer) { if (!lexer->eof(lexer)) lexer->advance(lexer, true); }
|
||||
|
||||
static inline bool starts_identifier(int32_t c) { return iswalpha(c) || c == '_' || c >= 0x80; }
|
||||
static inline bool continues_identifier(int32_t c) { return iswalnum(c) || c == '_' || c >= 0x80; }
|
||||
|
||||
static String32 scan_heredoc_word(TSLexer *lexer) {
|
||||
String32 result = (String32)array_new();
|
||||
|
||||
while (continues_identifier(lexer->lookahead)) {
|
||||
array_push(&result, lexer->lookahead);
|
||||
advance(lexer);
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
/*
|
||||
static int check_for_keyword(String ident) {
|
||||
switch (ident.size) {
|
||||
case 2:
|
||||
if (strncmp(ident.contents, "if", 2) == 0) return 1;
|
||||
if (strncmp(ident.contents, "xx", 2) == 0) return 1;
|
||||
return 0;
|
||||
case 3:
|
||||
if (strncmp(ident.contents, "ifx", 3) == 0) return 1;
|
||||
if (strncmp(ident.contents, "for", 3) == 0) return 1;
|
||||
return 0;
|
||||
case 4:
|
||||
if (strncmp(ident.contents, "then", 4) == 0) return 1;
|
||||
if (strncmp(ident.contents, "else", 4) == 0) return 1;
|
||||
if (strncmp(ident.contents, "null", 4) == 0) return 1;
|
||||
if (strncmp(ident.contents, "case", 4) == 0) return 1;
|
||||
if (strncmp(ident.contents, "enum", 4) == 0) return 1;
|
||||
if (strncmp(ident.contents, "true", 4) == 0) return 1;
|
||||
if (strncmp(ident.contents, "cast", 4) == 0) return 1;
|
||||
return 0;
|
||||
case 5:
|
||||
if (strncmp(ident.contents, "while", 5) == 0) return 1;
|
||||
if (strncmp(ident.contents, "break", 5) == 0) return 1;
|
||||
if (strncmp(ident.contents, "using", 5) == 0) return 1;
|
||||
if (strncmp(ident.contents, "defer", 5) == 0) return 1;
|
||||
if (strncmp(ident.contents, "false", 5) == 0) return 1;
|
||||
if (strncmp(ident.contents, "union", 5) == 0) return 1;
|
||||
return 0;
|
||||
case 6:
|
||||
if (strncmp(ident.contents, "return", 6) == 0) return 1;
|
||||
if (strncmp(ident.contents, "struct", 6) == 0) return 1;
|
||||
if (strncmp(ident.contents, "remove", 6) == 0) return 1;
|
||||
if (strncmp(ident.contents, "inline", 6) == 0) return 1;
|
||||
return 0;
|
||||
case 7:
|
||||
if (strncmp(ident.contents, "size_of", 7) == 0) return 1;
|
||||
if (strncmp(ident.contents, "type_of", 7) == 0) return 1;
|
||||
if (strncmp(ident.contents, "code_of", 7) == 0) return 1;
|
||||
if (strncmp(ident.contents, "context", 7) == 0) return 1;
|
||||
return 0;
|
||||
case 8:
|
||||
if (strncmp(ident.contents, "continue", 8) == 0) return 1;
|
||||
if (strncmp(ident.contents, "operator", 8) == 0) return 1;
|
||||
return 0;
|
||||
case 9:
|
||||
if (strncmp(ident.contents, "type_info", 9) == 0) return 1;
|
||||
if (strncmp(ident.contents, "no_inline", 9) == 0) return 1;
|
||||
if (strncmp(ident.contents, "interface", 9) == 0) return 1;
|
||||
return 0;
|
||||
case 10:
|
||||
if (strncmp(ident.contents, "enum_flags", 10) == 0) return 1;
|
||||
return 0;
|
||||
case 11:
|
||||
if (strncmp(ident.contents, "is_constant", 11) == 0) return 1;
|
||||
return 0;
|
||||
case 12:
|
||||
if (strncmp(ident.contents, "push_context", 12) == 0) return 1;
|
||||
return 0;
|
||||
case 14:
|
||||
if (strncmp(ident.contents, "initializer_of", 14) == 0) return 1;
|
||||
return 0;
|
||||
default:
|
||||
return 0;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
*/
|
||||
|
||||
extern "C" {
|
||||
|
||||
bool tree_sitter_jai_external_scanner_scan(void *payload, TSLexer *lexer, const bool *valid_symbols) {
|
||||
const bool is_error_recovery = valid_symbols[ERROR_SENTINEL];
|
||||
if (is_error_recovery)
|
||||
return false;
|
||||
|
||||
lexer->mark_end(lexer);
|
||||
/*
|
||||
if (valid_symbols[IDENTIFIER]) {
|
||||
|
||||
lexer->result_symbol = IDENTIFIER;
|
||||
while (iswspace(lexer->lookahead))
|
||||
skip(lexer);
|
||||
|
||||
if (starts_identifier(lexer->lookahead)) {
|
||||
String ident = (String)array_new();
|
||||
array_push(&ident, lexer->lookahead);
|
||||
|
||||
advance(lexer);
|
||||
while (1) {
|
||||
if (continues_identifier(lexer->lookahead)) {
|
||||
array_push(&ident, lexer->lookahead);
|
||||
advance(lexer);
|
||||
continue;
|
||||
} else if (lexer->lookahead == '\\') {
|
||||
advance(lexer);
|
||||
while (iswspace(lexer->lookahead)) {
|
||||
advance(lexer);
|
||||
}
|
||||
continue;
|
||||
}
|
||||
break;
|
||||
}
|
||||
bool keyword = check_for_keyword(ident);
|
||||
array_delete(&ident);
|
||||
|
||||
lexer->mark_end(lexer);
|
||||
return !keyword;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
*/
|
||||
|
||||
Scanner *scanner = (Scanner *)payload;
|
||||
|
||||
if (valid_symbols[HEREDOC_END]) {
|
||||
lexer->result_symbol = HEREDOC_END;
|
||||
if (scanner->heredocs.size == 0)
|
||||
return false;
|
||||
|
||||
String32 heredoc = *array_back(&scanner->heredocs);
|
||||
while (iswspace(lexer->lookahead))
|
||||
skip(lexer);
|
||||
|
||||
String32 word = scan_heredoc_word(lexer);
|
||||
if (!string_eq(&word, &heredoc)) {
|
||||
array_delete(&word);
|
||||
return false;
|
||||
}
|
||||
array_delete(&word);
|
||||
|
||||
lexer->mark_end(lexer);
|
||||
array_delete(&array_pop(&scanner->heredocs));
|
||||
return true;
|
||||
}
|
||||
|
||||
if (valid_symbols[HEREDOC_START]) {
|
||||
lexer->result_symbol = HEREDOC_START;
|
||||
String32 heredoc = array_new();
|
||||
|
||||
while (iswspace(lexer->lookahead))
|
||||
skip(lexer);
|
||||
|
||||
heredoc = scan_heredoc_word(lexer);
|
||||
if (heredoc.size == 0) {
|
||||
array_delete(&heredoc);
|
||||
return false;
|
||||
}
|
||||
lexer->mark_end(lexer);
|
||||
|
||||
array_push(&scanner->heredocs, heredoc);
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
void *tree_sitter_jai_external_scanner_create() {
|
||||
Scanner *scanner = (Scanner*)ts_calloc(1, sizeof(Scanner));
|
||||
array_init(&scanner->heredocs);
|
||||
return scanner;
|
||||
}
|
||||
|
||||
unsigned tree_sitter_jai_external_scanner_serialize(void *payload, char *buffer) {
|
||||
Scanner *scanner = (Scanner *)payload;
|
||||
unsigned size = 0;
|
||||
|
||||
buffer[size++] = (char)scanner->heredocs.size;
|
||||
for (unsigned j = 0; j < scanner->heredocs.size; j++) {
|
||||
String32 *heredoc = &scanner->heredocs.contents[j];
|
||||
unsigned word_size = heredoc->size * sizeof(heredoc->contents[0]);
|
||||
|
||||
if (size + 5 + word_size >= TREE_SITTER_SERIALIZATION_BUFFER_SIZE)
|
||||
return 0;
|
||||
|
||||
memcpy(&buffer[size], &heredoc->size, sizeof(int32_t));
|
||||
size += sizeof(int32_t);
|
||||
if (heredoc->size > 0) {
|
||||
memcpy(&buffer[size], heredoc->contents, word_size);
|
||||
size += word_size;
|
||||
}
|
||||
}
|
||||
|
||||
return size;
|
||||
}
|
||||
|
||||
|
||||
void tree_sitter_jai_external_scanner_deserialize(void *payload, const char *buffer, unsigned length) {
|
||||
Scanner *scanner = (Scanner *)payload;
|
||||
unsigned size = 0;
|
||||
for (uint32_t i = 0; i < scanner->heredocs.size; i++)
|
||||
reset_heredoc(array_get(&scanner->heredocs, i));
|
||||
|
||||
if (length == 0)
|
||||
return;
|
||||
|
||||
uint8_t open_heredoc_count = buffer[size++];
|
||||
for (unsigned i = 0; i < open_heredoc_count; i++) {
|
||||
String32 *heredoc = NULL;
|
||||
if (i < scanner->heredocs.size) {
|
||||
heredoc = array_get(&scanner->heredocs, i);
|
||||
} else {
|
||||
String32 new_heredoc = array_new();
|
||||
array_push(&scanner->heredocs, new_heredoc);
|
||||
heredoc = array_back(&scanner->heredocs);
|
||||
}
|
||||
|
||||
memcpy(&heredoc->size, &buffer[size], sizeof(int32_t));
|
||||
size += sizeof(int32_t);
|
||||
unsigned word_size = heredoc->size * sizeof(heredoc->contents[0]);
|
||||
if (word_size > 0) {
|
||||
array_reserve(heredoc, heredoc->size);
|
||||
memcpy(heredoc->contents, &buffer[size], word_size);
|
||||
size += word_size;
|
||||
}
|
||||
}
|
||||
|
||||
assert(size == length);
|
||||
}
|
||||
|
||||
void tree_sitter_jai_external_scanner_destroy(void *payload) {
|
||||
Scanner *scanner = (Scanner *)payload;
|
||||
for (size_t i = 0; i < scanner->heredocs.size; i++) {
|
||||
array_delete(&scanner->heredocs.contents[i]);
|
||||
}
|
||||
array_delete(&scanner->heredocs);
|
||||
ts_free(scanner);
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,41 @@
|
|||
#ifndef TREE_SITTER_ALLOC_H_
|
||||
#define TREE_SITTER_ALLOC_H_
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#include <stdbool.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
|
||||
#if defined(TREE_SITTER_HIDDEN_SYMBOLS) || defined(_WIN32)
|
||||
#define TS_PUBLIC
|
||||
#else
|
||||
#define TS_PUBLIC __attribute__((visibility("default")))
|
||||
#endif
|
||||
|
||||
TS_PUBLIC extern void *(*ts_current_malloc)(size_t size);
|
||||
TS_PUBLIC extern void *(*ts_current_calloc)(size_t count, size_t size);
|
||||
TS_PUBLIC extern void *(*ts_current_realloc)(void *ptr, size_t size);
|
||||
TS_PUBLIC extern void (*ts_current_free)(void *ptr);
|
||||
|
||||
// Allow clients to override allocation functions
|
||||
#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
|
||||
|
||||
#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 "./ts_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) \
|
||||
(ts_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) {
|
||||
ts_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;
|
||||
ts_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_
|
||||
|
|
@ -13,12 +13,16 @@ extern "C" {
|
|||
#define ts_builtin_sym_end 0
|
||||
#define TREE_SITTER_SERIALIZATION_BUFFER_SIZE 1024
|
||||
|
||||
typedef uint16_t TSStateId;
|
||||
|
||||
#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 {
|
||||
|
|
@ -27,10 +31,11 @@ typedef struct {
|
|||
bool inherited;
|
||||
} TSFieldMapEntry;
|
||||
|
||||
// Used to index the field and supertype maps.
|
||||
typedef struct {
|
||||
uint16_t index;
|
||||
uint16_t length;
|
||||
} TSFieldMapSlice;
|
||||
} TSMapSlice;
|
||||
|
||||
typedef struct {
|
||||
bool visible;
|
||||
|
|
@ -48,6 +53,7 @@ struct 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 {
|
||||
|
|
@ -79,6 +85,12 @@ typedef struct {
|
|||
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 {
|
||||
|
|
@ -87,8 +99,13 @@ typedef union {
|
|||
} entry;
|
||||
} TSParseActionEntry;
|
||||
|
||||
typedef struct {
|
||||
int32_t start;
|
||||
int32_t end;
|
||||
} TSCharacterRange;
|
||||
|
||||
struct TSLanguage {
|
||||
uint32_t version;
|
||||
uint32_t abi_version;
|
||||
uint32_t symbol_count;
|
||||
uint32_t alias_count;
|
||||
uint32_t token_count;
|
||||
|
|
@ -104,13 +121,13 @@ struct TSLanguage {
|
|||
const TSParseActionEntry *parse_actions;
|
||||
const char * const *symbol_names;
|
||||
const char * const *field_names;
|
||||
const TSFieldMapSlice *field_map_slices;
|
||||
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 TSLexMode *lex_modes;
|
||||
const TSLexerMode *lex_modes;
|
||||
bool (*lex_fn)(TSLexer *, TSStateId);
|
||||
bool (*keyword_lex_fn)(TSLexer *, TSStateId);
|
||||
TSSymbol keyword_capture_token;
|
||||
|
|
@ -124,15 +141,48 @@ struct TSLanguage {
|
|||
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; \
|
||||
|
|
@ -148,6 +198,17 @@ struct TSLanguage {
|
|||
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; \
|
||||
|
|
@ -166,7 +227,7 @@ struct TSLanguage {
|
|||
* Parse Table Macros
|
||||
*/
|
||||
|
||||
#define SMALL_STATE(id) id - LARGE_STATE_COUNT
|
||||
#define SMALL_STATE(id) ((id) - LARGE_STATE_COUNT)
|
||||
|
||||
#define STATE(id) id
|
||||
|
||||
|
|
@ -176,7 +237,7 @@ struct TSLanguage {
|
|||
{{ \
|
||||
.shift = { \
|
||||
.type = TSParseActionTypeShift, \
|
||||
.state = state_value \
|
||||
.state = (state_value) \
|
||||
} \
|
||||
}}
|
||||
|
||||
|
|
@ -184,7 +245,7 @@ struct TSLanguage {
|
|||
{{ \
|
||||
.shift = { \
|
||||
.type = TSParseActionTypeShift, \
|
||||
.state = state_value, \
|
||||
.state = (state_value), \
|
||||
.repetition = true \
|
||||
} \
|
||||
}}
|
||||
|
|
@ -197,14 +258,15 @@ struct TSLanguage {
|
|||
} \
|
||||
}}
|
||||
|
||||
#define REDUCE(symbol_val, child_count_val, ...) \
|
||||
{{ \
|
||||
.reduce = { \
|
||||
.type = TSParseActionTypeReduce, \
|
||||
.symbol = symbol_val, \
|
||||
.child_count = child_count_val, \
|
||||
__VA_ARGS__ \
|
||||
}, \
|
||||
#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() \
|
||||
|
|
@ -221,4 +283,4 @@ struct TSLanguage {
|
|||
}
|
||||
#endif
|
||||
|
||||
#endif // TREE_SITTER_PARSER_H_
|
||||
#endif // TREE_SITTER_PARSER_H_
|
||||
|
|
|
|||
|
|
@ -0,0 +1,49 @@
|
|||
#import "Basic";
|
||||
Basic :: #import "Basic";
|
||||
|
||||
Options :: struct
|
||||
{
|
||||
foo: int;
|
||||
}
|
||||
|
||||
Enum :: enum
|
||||
{
|
||||
Test;
|
||||
Inavlid;
|
||||
}
|
||||
|
||||
main :: () -> void
|
||||
{
|
||||
options1: Options;
|
||||
options2 := Options.{
|
||||
foo = bar
|
||||
};
|
||||
|
||||
array_lit1: [..]string;
|
||||
array_lit2 := string.["hello", "there\n"];
|
||||
|
||||
lit_str := "string";
|
||||
lit_int := 5555;
|
||||
lit_float := 6.28;
|
||||
lit_bool := float;
|
||||
lit_char := #char "c";
|
||||
|
||||
if cnd {
|
||||
|
||||
}
|
||||
|
||||
if cnd2 == {
|
||||
case 5;
|
||||
case .Bar;
|
||||
case;
|
||||
}
|
||||
|
||||
for i: 0..5 { continue; break; }
|
||||
for arr {}
|
||||
|
||||
proc_call();
|
||||
Basic.print();
|
||||
|
||||
|
||||
return;
|
||||
}
|
||||
Loading…
Reference in New Issue