feat(kernel): R7b Kotlin walker — kotlin module, vendored-grammar-C build, kotlin default-routed (#1382)
Sixth R7b port — the T1½ batch finale. Checklist-first recipe
(docs/design/kotlin-kernel-port-checklist.md, 1,121 lines, dist-extractor
ground truth); parity passed FIRST RUN on all three repos.
THE NOVEL MECHANISM — vendored-grammar-C (the §4 tracker's prescription,
first use): the crates.io tree-sitter-kotlin 0.3.8 pins `tree-sitter >= 0.21,
< 0.23` (the kernel links 0.25) and tree-sitter-kotlin-ng is a DIFFERENT
grammar (8 fields vs 0, renamed kinds — extractor-breaking), so no crate dep
is possible. The fwcd 0.3.8 tag's sha-matched parser.c + scanner.c are
vendored into codegraph-kernel/grammars/kotlin and compiled by build.rs (cc),
exposed via tree-sitter-language::LanguageFn. The wasm re-vendor is
behavior-NEUTRAL (0 CST/error disagreements across 1,984 gate-repo files;
old-vs-new full-init dumps byte-identical ×3) — a reproducibility re-vendor,
ABI stays 14.
Walker firsts: extension-function receivers (getReceiverType →
`WidgetK::extend` QN OVERRIDE with no package prefix, the qualified-receiver
`com::qext` first-segment bug, and the owner-contains fallback that excludes
`interface` kinds and is source-order dependent) and extractModifiers
(expect/actual platform modifiers → the node DECORATORS wire field on every
created node — the KMP synthesizer's feed, incl. `actual typealias`).
Preserved bug-for-bug: the FIELD_COUNT-0 dead cluster (no signatures, ZERO
type-annotation refs), hook-consumed property initializers emitting nothing
(incl. `by lazy {}`), the bodiless-vs-bodied class header asymmetry, enum-
entry bodies being invisible, KDoc never a docstring AND chain-breaking,
comment-gluing into import/package extents, `@Anno(args)` emitting nothing
while `@Marker` decorates, zero instantiates refs, the paren-then-lambda
`trailing()` garbage callee, text-includes visibility/suspend false
positives, and the packaged-file value-ref target drop. The fun-interface
misparse-recovery hook is DEFER-SHIELDED (every such file has_error) and
deliberately not ported. The swift-sweep lesson pre-applied: the shared
`assignment` shadow-prune case is implemented alongside the
property_declaration case.
Gates: sweeps 0-diff okio 299/322, okhttp 531/580, kotlinx.coroutines
1031/1082 (deferrals exactly the predicted 23/49/51 — both-arm grammar
reality incl. PHANTOM hasError files with complete CSTs; the kernel trusts
the flag); full-init dumps byte-identical ×3 (46.5k/108.9k/92.3k lines); KMP
expect/actual synthesis IDENTICAL across arms (412 edges on
kotlinx.coroutines — the tracker's KMP validation); kernel-kotlin-parity
suite (torture reflowed off the phantom shapes + .kts script + CRLF variants
+ fun-interface and phantom defer pins) + kotlin grammar-parity row (the
C-build ↔ wasm table identity proof); full suite 2,633 green ×2 under
CODEGRAPH_KERNEL_EXPECT=1. DEFAULT_ROUTED += kotlin (15 langs).
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Colby Mchenry
co-authored by
Claude Fable 5
Claude Fable 5
parent
09e301bbfa
commit
45a53eb5b5
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,530 @@
|
||||
#include "tree_sitter/array.h"
|
||||
#include "tree_sitter/parser.h"
|
||||
|
||||
#include <string.h>
|
||||
#include <wctype.h>
|
||||
|
||||
// Mostly a copy paste of tree-sitter-javascript/src/scanner.c
|
||||
|
||||
enum TokenType {
|
||||
AUTOMATIC_SEMICOLON,
|
||||
IMPORT_LIST_DELIMITER,
|
||||
SAFE_NAV,
|
||||
MULTILINE_COMMENT,
|
||||
STRING_START,
|
||||
STRING_END,
|
||||
STRING_CONTENT,
|
||||
};
|
||||
|
||||
/* Pretty much all of this code is taken from the Julia tree-sitter
|
||||
parser.
|
||||
|
||||
Julia has similar problems with multiline comments that can be nested,
|
||||
line comments, as well as line and multiline strings.
|
||||
|
||||
The most heavily edited section is `scan_string_content`,
|
||||
particularly with respect to interpolation.
|
||||
*/
|
||||
|
||||
// Block comments are easy to parse, but strings require extra-attention.
|
||||
|
||||
// The main problems that arise when parsing strings are:
|
||||
// 1. Triple quoted strings allow single quotes inside. e.g. """ "foo" """.
|
||||
// 2. Non-standard string literals don't allow interpolations or escape
|
||||
// sequences, but you can always write \" and \`.
|
||||
|
||||
// To efficiently store a delimiter, we take advantage of the fact that:
|
||||
// (int)'"' == 34 && (34 & 1) == 0
|
||||
// i.e. " has an even numeric representation, so we can store a triple
|
||||
// quoted delimiter as (delimiter + 1).
|
||||
|
||||
#define DELIMITER_LENGTH 3
|
||||
|
||||
typedef char Delimiter;
|
||||
|
||||
// We use a stack to keep track of the string delimiters.
|
||||
typedef Array(Delimiter) Stack;
|
||||
|
||||
static inline void stack_push(Stack *stack, char chr, bool triple) {
|
||||
if (stack->size >= TREE_SITTER_SERIALIZATION_BUFFER_SIZE) abort();
|
||||
array_push(stack, (Delimiter)(triple ? (chr + 1) : chr));
|
||||
}
|
||||
|
||||
static inline Delimiter stack_pop(Stack *stack) {
|
||||
if (stack->size == 0) abort();
|
||||
return array_pop(stack);
|
||||
}
|
||||
|
||||
static inline void skip(TSLexer *lexer) { lexer->advance(lexer, true); }
|
||||
|
||||
static inline void advance(TSLexer *lexer) { lexer->advance(lexer, false); }
|
||||
|
||||
// Scanner functions
|
||||
|
||||
static bool scan_string_start(TSLexer *lexer, Stack *stack) {
|
||||
if (lexer->lookahead != '"') return false;
|
||||
advance(lexer);
|
||||
lexer->mark_end(lexer);
|
||||
for (unsigned count = 1; count < DELIMITER_LENGTH; ++count) {
|
||||
if (lexer->lookahead != '"') {
|
||||
// It's not a triple quoted delimiter.
|
||||
stack_push(stack, '"', false);
|
||||
return true;
|
||||
}
|
||||
advance(lexer);
|
||||
}
|
||||
lexer->mark_end(lexer);
|
||||
stack_push(stack, '"', true);
|
||||
return true;
|
||||
}
|
||||
|
||||
static bool scan_string_content(TSLexer *lexer, Stack *stack) {
|
||||
if (stack->size == 0) return false; // Stack is empty. We're not in a string.
|
||||
Delimiter end_char = stack->contents[stack->size - 1]; // peek
|
||||
bool is_triple = false;
|
||||
bool has_content = false;
|
||||
if (end_char & 1) {
|
||||
is_triple = true;
|
||||
end_char -= 1;
|
||||
}
|
||||
while (lexer->lookahead) {
|
||||
if (lexer->lookahead == '$') {
|
||||
// if we did not just start reading stuff, then we should stop
|
||||
// lexing right here, so we can offer the opportunity to lex a
|
||||
// interpolated identifier
|
||||
if (has_content) {
|
||||
lexer->result_symbol = STRING_CONTENT;
|
||||
return has_content;
|
||||
}
|
||||
// otherwise, if this is the start, determine if it is an
|
||||
// interpolated identifier.
|
||||
// otherwise, it's just string content, so continue
|
||||
advance(lexer);
|
||||
if (iswalpha(lexer->lookahead) || lexer->lookahead == '{') {
|
||||
// this must be a string interpolation, let's
|
||||
// fail so we parse it as such
|
||||
return false;
|
||||
}
|
||||
lexer->result_symbol = STRING_CONTENT;
|
||||
lexer->mark_end(lexer);
|
||||
return true;
|
||||
}
|
||||
if (lexer->lookahead == '\\') {
|
||||
// if we see a \, then this might possibly escape a dollar sign
|
||||
// in which case, we should not defer to the interpolation
|
||||
advance(lexer);
|
||||
// this dollar sign is escaped, so it must be content.
|
||||
// we consume it here so we don't enter the dollar sign case above,
|
||||
// which leaves the possibility that it is an interpolation
|
||||
if (lexer->lookahead == '$') {
|
||||
advance(lexer);
|
||||
// however this leaves an edgecase where an escaped dollar sign could
|
||||
// appear at the end of a string (e.g "aa\$") which isn't handled
|
||||
// correctly; if we were at the end of the string, terminate properly
|
||||
if (lexer->lookahead == end_char) {
|
||||
stack_pop(stack);
|
||||
advance(lexer);
|
||||
lexer->mark_end(lexer);
|
||||
lexer->result_symbol = STRING_END;
|
||||
return true;
|
||||
}
|
||||
}
|
||||
} else if (lexer->lookahead == end_char) {
|
||||
if (is_triple) {
|
||||
lexer->mark_end(lexer);
|
||||
for (unsigned count = 1; count < DELIMITER_LENGTH; ++count) {
|
||||
advance(lexer);
|
||||
if (lexer->lookahead != end_char) {
|
||||
lexer->mark_end(lexer);
|
||||
lexer->result_symbol = STRING_CONTENT;
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
/* This is so if we lex something like
|
||||
"""foo"""
|
||||
^
|
||||
where we are at the `f`, we should quit after
|
||||
reading `foo`, and ascribe it to STRING_CONTENT.
|
||||
|
||||
Then, we restart and try to read the end.
|
||||
This is to prevent `foo` from being absorbed into
|
||||
the STRING_END token.
|
||||
*/
|
||||
if (has_content && lexer->lookahead == end_char) {
|
||||
lexer->result_symbol = STRING_CONTENT;
|
||||
return true;
|
||||
}
|
||||
|
||||
/* Since the string internals are all hidden in the syntax
|
||||
tree anyways, there's no point in going to the effort of
|
||||
specifically separating the string end from string contents.
|
||||
If we see a bunch of quotes in a row, then we just go until
|
||||
they stop appearing, then stop lexing and call it the
|
||||
string's end.
|
||||
*/
|
||||
lexer->result_symbol = STRING_END;
|
||||
lexer->mark_end(lexer);
|
||||
while (lexer->lookahead == end_char) {
|
||||
advance(lexer);
|
||||
lexer->mark_end(lexer);
|
||||
}
|
||||
stack_pop(stack);
|
||||
return true;
|
||||
}
|
||||
if (has_content) {
|
||||
lexer->mark_end(lexer);
|
||||
lexer->result_symbol = STRING_CONTENT;
|
||||
return true;
|
||||
}
|
||||
stack_pop(stack);
|
||||
advance(lexer);
|
||||
lexer->mark_end(lexer);
|
||||
lexer->result_symbol = STRING_END;
|
||||
return true;
|
||||
}
|
||||
advance(lexer);
|
||||
has_content = true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
static bool scan_multiline_comment(TSLexer *lexer) {
|
||||
if (lexer->lookahead != '/') return false;
|
||||
advance(lexer);
|
||||
if (lexer->lookahead != '*') return false;
|
||||
advance(lexer);
|
||||
|
||||
bool after_star = false;
|
||||
unsigned nesting_depth = 1;
|
||||
for (;;) {
|
||||
switch (lexer->lookahead) {
|
||||
case '*':
|
||||
advance(lexer);
|
||||
after_star = true;
|
||||
break;
|
||||
case '/':
|
||||
advance(lexer);
|
||||
if (after_star) {
|
||||
after_star = false;
|
||||
nesting_depth -= 1;
|
||||
if (nesting_depth == 0) {
|
||||
lexer->result_symbol = MULTILINE_COMMENT;
|
||||
lexer->mark_end(lexer);
|
||||
return true;
|
||||
}
|
||||
} else {
|
||||
after_star = false;
|
||||
if (lexer->lookahead == '*') {
|
||||
nesting_depth += 1;
|
||||
advance(lexer);
|
||||
}
|
||||
}
|
||||
break;
|
||||
case '\0':
|
||||
return false;
|
||||
default:
|
||||
advance(lexer);
|
||||
after_star = false;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static bool scan_whitespace_and_comments(TSLexer *lexer) {
|
||||
while (iswspace(lexer->lookahead)) skip(lexer);
|
||||
return lexer->lookahead != '/';
|
||||
}
|
||||
|
||||
static bool scan_for_word(TSLexer *lexer, const char* word, unsigned len) {
|
||||
skip(lexer);
|
||||
for (unsigned i = 0; i < len; ++i) {
|
||||
if (lexer->lookahead != word[i]) return false;
|
||||
skip(lexer);
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
static bool scan_automatic_semicolon(TSLexer *lexer) {
|
||||
lexer->result_symbol = AUTOMATIC_SEMICOLON;
|
||||
lexer->mark_end(lexer);
|
||||
|
||||
bool sameline = true;
|
||||
for (;;) {
|
||||
if (lexer->eof(lexer)) return true;
|
||||
|
||||
if (lexer->lookahead == ';') {
|
||||
advance(lexer);
|
||||
lexer->mark_end(lexer);
|
||||
return true;
|
||||
}
|
||||
|
||||
if (!iswspace(lexer->lookahead)) break;
|
||||
|
||||
if (lexer->lookahead == '\n') {
|
||||
skip(lexer);
|
||||
sameline = false;
|
||||
break;
|
||||
}
|
||||
|
||||
if (lexer->lookahead == '\r') {
|
||||
skip(lexer);
|
||||
|
||||
if (lexer->lookahead == '\n') skip(lexer);
|
||||
|
||||
sameline = false;
|
||||
break;
|
||||
}
|
||||
|
||||
skip(lexer);
|
||||
}
|
||||
|
||||
// Skip whitespace and comments
|
||||
if (!scan_whitespace_and_comments(lexer))
|
||||
return false;
|
||||
|
||||
if (sameline) {
|
||||
switch (lexer->lookahead) {
|
||||
// Don't insert a semicolon before an else
|
||||
case 'e':
|
||||
return !scan_for_word(lexer, "lse", 3);
|
||||
|
||||
case 'i':
|
||||
return scan_for_word(lexer, "mport", 5);
|
||||
|
||||
case ';':
|
||||
advance(lexer);
|
||||
lexer->mark_end(lexer);
|
||||
return true;
|
||||
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
switch (lexer->lookahead) {
|
||||
case ',':
|
||||
case '.':
|
||||
case ':':
|
||||
case '*':
|
||||
case '%':
|
||||
case '>':
|
||||
case '<':
|
||||
case '=':
|
||||
case '{':
|
||||
case '[':
|
||||
case '(':
|
||||
case '?':
|
||||
case '|':
|
||||
case '&':
|
||||
case '/':
|
||||
return false;
|
||||
|
||||
// Insert a semicolon before `--` and `++`, but not before binary `+` or `-`.
|
||||
// Insert before +/-Float
|
||||
case '+':
|
||||
skip(lexer);
|
||||
if (lexer->lookahead == '+') return true;
|
||||
return iswdigit(lexer->lookahead);
|
||||
|
||||
case '-':
|
||||
skip(lexer);
|
||||
if (lexer->lookahead == '-') return true;
|
||||
return iswdigit(lexer->lookahead);
|
||||
|
||||
// Don't insert a semicolon before `!=`, but do insert one before a unary `!`.
|
||||
case '!':
|
||||
skip(lexer);
|
||||
return lexer->lookahead != '=';
|
||||
|
||||
// Don't insert a semicolon before an else
|
||||
case 'e':
|
||||
return !scan_for_word(lexer, "lse", 3);
|
||||
|
||||
// Don't insert a semicolon before `in` or `instanceof`, but do insert one
|
||||
// before an identifier or an import.
|
||||
case 'i':
|
||||
skip(lexer);
|
||||
if (lexer->lookahead != 'n') return true;
|
||||
skip(lexer);
|
||||
if (!iswalpha(lexer->lookahead)) return false;
|
||||
return !scan_for_word(lexer, "stanceof", 8);
|
||||
|
||||
case ';':
|
||||
advance(lexer);
|
||||
lexer->mark_end(lexer);
|
||||
return true;
|
||||
|
||||
default:
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
static bool scan_safe_nav(TSLexer *lexer) {
|
||||
lexer->result_symbol = SAFE_NAV;
|
||||
lexer->mark_end(lexer);
|
||||
|
||||
// skip white space
|
||||
if (!scan_whitespace_and_comments(lexer))
|
||||
return false;
|
||||
|
||||
if (lexer->lookahead != '?')
|
||||
return false;
|
||||
|
||||
advance(lexer);
|
||||
|
||||
if (!scan_whitespace_and_comments(lexer))
|
||||
return false;
|
||||
|
||||
if (lexer->lookahead != '.')
|
||||
return false;
|
||||
|
||||
advance(lexer);
|
||||
lexer->mark_end(lexer);
|
||||
return true;
|
||||
}
|
||||
|
||||
static bool scan_line_sep(TSLexer *lexer) {
|
||||
// Line Seps: [ CR, LF, CRLF ]
|
||||
int state = 0;
|
||||
while (true) {
|
||||
switch(lexer->lookahead) {
|
||||
case ' ':
|
||||
case '\t':
|
||||
case '\v':
|
||||
// Skip whitespace
|
||||
advance(lexer);
|
||||
break;
|
||||
|
||||
case '\n':
|
||||
advance(lexer);
|
||||
return true;
|
||||
|
||||
case '\r':
|
||||
if (state == 1)
|
||||
return true;
|
||||
|
||||
state = 1;
|
||||
advance(lexer);
|
||||
break;
|
||||
|
||||
default:
|
||||
// We read a CR
|
||||
if (state == 1)
|
||||
return true;
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static bool scan_import_list_delimiter(TSLexer *lexer) {
|
||||
// Import lists are terminated either by an empty line or a non import statement
|
||||
lexer->result_symbol = IMPORT_LIST_DELIMITER;
|
||||
lexer->mark_end(lexer);
|
||||
|
||||
// if eof; return true
|
||||
if (lexer->eof(lexer))
|
||||
return true;
|
||||
|
||||
// Scan for the first line seperator
|
||||
if (!scan_line_sep(lexer))
|
||||
return false;
|
||||
|
||||
// if line.sep line.sep; return true
|
||||
if (scan_line_sep(lexer)) {
|
||||
lexer->mark_end(lexer);
|
||||
return true;
|
||||
}
|
||||
|
||||
// if line.sep [^import]; return true
|
||||
while (true) {
|
||||
switch (lexer->lookahead) {
|
||||
case ' ':
|
||||
case '\t':
|
||||
case '\v':
|
||||
// Skip whitespace
|
||||
advance(lexer);
|
||||
break;
|
||||
|
||||
case 'i':
|
||||
return !scan_for_word(lexer, "mport", 5);
|
||||
|
||||
default:
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
bool tree_sitter_kotlin_external_scanner_scan(void *payload, TSLexer *lexer, const bool *valid_symbols) {
|
||||
if (valid_symbols[AUTOMATIC_SEMICOLON]) {
|
||||
bool ret = scan_automatic_semicolon(lexer);
|
||||
if (!ret && valid_symbols[SAFE_NAV] && lexer->lookahead == '?') {
|
||||
return scan_safe_nav(lexer);
|
||||
}
|
||||
|
||||
// if we fail to find an automatic semicolon, it's still possible that we may
|
||||
// want to lex a string or comment later
|
||||
if (ret) return ret;
|
||||
}
|
||||
|
||||
if (valid_symbols[IMPORT_LIST_DELIMITER]) {
|
||||
return scan_import_list_delimiter(lexer);
|
||||
}
|
||||
|
||||
// content or end
|
||||
if (valid_symbols[STRING_CONTENT] && scan_string_content(lexer, payload)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
// a string might follow after some whitespace, so we can't lookahead
|
||||
// until we get rid of it
|
||||
while (iswspace(lexer->lookahead)) skip(lexer);
|
||||
|
||||
if (valid_symbols[STRING_START] && scan_string_start(lexer, payload)) {
|
||||
lexer->result_symbol = STRING_START;
|
||||
return true;
|
||||
}
|
||||
|
||||
if (valid_symbols[MULTILINE_COMMENT] && scan_multiline_comment(lexer)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (valid_symbols[SAFE_NAV]) {
|
||||
return scan_safe_nav(lexer);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
void *tree_sitter_kotlin_external_scanner_create() {
|
||||
Stack *stack = ts_calloc(1, sizeof(Stack));
|
||||
if (stack == NULL) abort();
|
||||
array_init(stack);
|
||||
return stack;
|
||||
}
|
||||
|
||||
void tree_sitter_kotlin_external_scanner_destroy(void *payload) {
|
||||
Stack *stack = (Stack *)payload;
|
||||
array_delete(stack);
|
||||
ts_free(stack);
|
||||
}
|
||||
|
||||
unsigned tree_sitter_kotlin_external_scanner_serialize(void *payload, char *buffer) {
|
||||
Stack *stack = (Stack *)payload;
|
||||
memcpy(buffer, stack->contents, stack->size);
|
||||
return stack->size;
|
||||
}
|
||||
|
||||
void tree_sitter_kotlin_external_scanner_deserialize(void *payload, const char *buffer, unsigned length) {
|
||||
Stack *stack = (Stack *)payload;
|
||||
if (length > 0) {
|
||||
array_reserve(stack, length);
|
||||
memcpy(stack->contents, buffer, length);
|
||||
stack->size = length;
|
||||
} else {
|
||||
array_clear(stack);
|
||||
}
|
||||
}
|
||||
@@ -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);
|
||||
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_
|
||||
@@ -0,0 +1,290 @@
|
||||
#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(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_
|
||||
@@ -0,0 +1,265 @@
|
||||
#ifndef TREE_SITTER_PARSER_H_
|
||||
#define TREE_SITTER_PARSER_H_
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#include <stdbool.h>
|
||||
#include <stdint.h>
|
||||
#include <stdlib.h>
|
||||
|
||||
#define ts_builtin_sym_error ((TSSymbol)-1)
|
||||
#define ts_builtin_sym_end 0
|
||||
#define TREE_SITTER_SERIALIZATION_BUFFER_SIZE 1024
|
||||
|
||||
#ifndef TREE_SITTER_API_H_
|
||||
typedef uint16_t TSStateId;
|
||||
typedef uint16_t TSSymbol;
|
||||
typedef uint16_t TSFieldId;
|
||||
typedef struct TSLanguage TSLanguage;
|
||||
#endif
|
||||
|
||||
typedef struct {
|
||||
TSFieldId field_id;
|
||||
uint8_t child_index;
|
||||
bool inherited;
|
||||
} TSFieldMapEntry;
|
||||
|
||||
typedef struct {
|
||||
uint16_t index;
|
||||
uint16_t length;
|
||||
} TSFieldMapSlice;
|
||||
|
||||
typedef struct {
|
||||
bool visible;
|
||||
bool named;
|
||||
bool supertype;
|
||||
} TSSymbolMetadata;
|
||||
|
||||
typedef struct TSLexer TSLexer;
|
||||
|
||||
struct TSLexer {
|
||||
int32_t lookahead;
|
||||
TSSymbol result_symbol;
|
||||
void (*advance)(TSLexer *, bool);
|
||||
void (*mark_end)(TSLexer *);
|
||||
uint32_t (*get_column)(TSLexer *);
|
||||
bool (*is_at_included_range_start)(const TSLexer *);
|
||||
bool (*eof)(const TSLexer *);
|
||||
};
|
||||
|
||||
typedef enum {
|
||||
TSParseActionTypeShift,
|
||||
TSParseActionTypeReduce,
|
||||
TSParseActionTypeAccept,
|
||||
TSParseActionTypeRecover,
|
||||
} TSParseActionType;
|
||||
|
||||
typedef union {
|
||||
struct {
|
||||
uint8_t type;
|
||||
TSStateId state;
|
||||
bool extra;
|
||||
bool repetition;
|
||||
} shift;
|
||||
struct {
|
||||
uint8_t type;
|
||||
uint8_t child_count;
|
||||
TSSymbol symbol;
|
||||
int16_t dynamic_precedence;
|
||||
uint16_t production_id;
|
||||
} reduce;
|
||||
uint8_t type;
|
||||
} TSParseAction;
|
||||
|
||||
typedef struct {
|
||||
uint16_t lex_state;
|
||||
uint16_t external_lex_state;
|
||||
} TSLexMode;
|
||||
|
||||
typedef union {
|
||||
TSParseAction action;
|
||||
struct {
|
||||
uint8_t count;
|
||||
bool reusable;
|
||||
} entry;
|
||||
} TSParseActionEntry;
|
||||
|
||||
typedef struct {
|
||||
int32_t start;
|
||||
int32_t end;
|
||||
} TSCharacterRange;
|
||||
|
||||
struct TSLanguage {
|
||||
uint32_t version;
|
||||
uint32_t symbol_count;
|
||||
uint32_t alias_count;
|
||||
uint32_t token_count;
|
||||
uint32_t external_token_count;
|
||||
uint32_t state_count;
|
||||
uint32_t large_state_count;
|
||||
uint32_t production_id_count;
|
||||
uint32_t field_count;
|
||||
uint16_t max_alias_sequence_length;
|
||||
const uint16_t *parse_table;
|
||||
const uint16_t *small_parse_table;
|
||||
const uint32_t *small_parse_table_map;
|
||||
const TSParseActionEntry *parse_actions;
|
||||
const char * const *symbol_names;
|
||||
const char * const *field_names;
|
||||
const TSFieldMapSlice *field_map_slices;
|
||||
const TSFieldMapEntry *field_map_entries;
|
||||
const TSSymbolMetadata *symbol_metadata;
|
||||
const TSSymbol *public_symbol_map;
|
||||
const uint16_t *alias_map;
|
||||
const TSSymbol *alias_sequences;
|
||||
const TSLexMode *lex_modes;
|
||||
bool (*lex_fn)(TSLexer *, TSStateId);
|
||||
bool (*keyword_lex_fn)(TSLexer *, TSStateId);
|
||||
TSSymbol keyword_capture_token;
|
||||
struct {
|
||||
const bool *states;
|
||||
const TSSymbol *symbol_map;
|
||||
void *(*create)(void);
|
||||
void (*destroy)(void *);
|
||||
bool (*scan)(void *, TSLexer *, const bool *symbol_whitelist);
|
||||
unsigned (*serialize)(void *, char *);
|
||||
void (*deserialize)(void *, const char *, unsigned);
|
||||
} external_scanner;
|
||||
const TSStateId *primary_state_ids;
|
||||
};
|
||||
|
||||
static inline bool set_contains(TSCharacterRange *ranges, uint32_t len, int32_t lookahead) {
|
||||
uint32_t index = 0;
|
||||
uint32_t size = len - index;
|
||||
while (size > 1) {
|
||||
uint32_t half_size = size / 2;
|
||||
uint32_t mid_index = index + half_size;
|
||||
TSCharacterRange *range = &ranges[mid_index];
|
||||
if (lookahead >= range->start && lookahead <= range->end) {
|
||||
return true;
|
||||
} else if (lookahead > range->end) {
|
||||
index = mid_index;
|
||||
}
|
||||
size -= half_size;
|
||||
}
|
||||
TSCharacterRange *range = &ranges[index];
|
||||
return (lookahead >= range->start && lookahead <= range->end);
|
||||
}
|
||||
|
||||
/*
|
||||
* Lexer Macros
|
||||
*/
|
||||
|
||||
#ifdef _MSC_VER
|
||||
#define UNUSED __pragma(warning(suppress : 4101))
|
||||
#else
|
||||
#define UNUSED __attribute__((unused))
|
||||
#endif
|
||||
|
||||
#define START_LEXER() \
|
||||
bool result = false; \
|
||||
bool skip = false; \
|
||||
UNUSED \
|
||||
bool eof = false; \
|
||||
int32_t lookahead; \
|
||||
goto start; \
|
||||
next_state: \
|
||||
lexer->advance(lexer, skip); \
|
||||
start: \
|
||||
skip = false; \
|
||||
lookahead = lexer->lookahead;
|
||||
|
||||
#define ADVANCE(state_value) \
|
||||
{ \
|
||||
state = state_value; \
|
||||
goto next_state; \
|
||||
}
|
||||
|
||||
#define ADVANCE_MAP(...) \
|
||||
{ \
|
||||
static const uint16_t map[] = { __VA_ARGS__ }; \
|
||||
for (uint32_t i = 0; i < sizeof(map) / sizeof(map[0]); i += 2) { \
|
||||
if (map[i] == lookahead) { \
|
||||
state = map[i + 1]; \
|
||||
goto next_state; \
|
||||
} \
|
||||
} \
|
||||
}
|
||||
|
||||
#define SKIP(state_value) \
|
||||
{ \
|
||||
skip = true; \
|
||||
state = state_value; \
|
||||
goto next_state; \
|
||||
}
|
||||
|
||||
#define ACCEPT_TOKEN(symbol_value) \
|
||||
result = true; \
|
||||
lexer->result_symbol = symbol_value; \
|
||||
lexer->mark_end(lexer);
|
||||
|
||||
#define END_STATE() return result;
|
||||
|
||||
/*
|
||||
* Parse Table Macros
|
||||
*/
|
||||
|
||||
#define SMALL_STATE(id) ((id) - LARGE_STATE_COUNT)
|
||||
|
||||
#define STATE(id) id
|
||||
|
||||
#define ACTIONS(id) id
|
||||
|
||||
#define SHIFT(state_value) \
|
||||
{{ \
|
||||
.shift = { \
|
||||
.type = TSParseActionTypeShift, \
|
||||
.state = (state_value) \
|
||||
} \
|
||||
}}
|
||||
|
||||
#define SHIFT_REPEAT(state_value) \
|
||||
{{ \
|
||||
.shift = { \
|
||||
.type = TSParseActionTypeShift, \
|
||||
.state = (state_value), \
|
||||
.repetition = true \
|
||||
} \
|
||||
}}
|
||||
|
||||
#define SHIFT_EXTRA() \
|
||||
{{ \
|
||||
.shift = { \
|
||||
.type = TSParseActionTypeShift, \
|
||||
.extra = true \
|
||||
} \
|
||||
}}
|
||||
|
||||
#define REDUCE(symbol_name, children, precedence, prod_id) \
|
||||
{{ \
|
||||
.reduce = { \
|
||||
.type = TSParseActionTypeReduce, \
|
||||
.symbol = symbol_name, \
|
||||
.child_count = children, \
|
||||
.dynamic_precedence = precedence, \
|
||||
.production_id = prod_id \
|
||||
}, \
|
||||
}}
|
||||
|
||||
#define RECOVER() \
|
||||
{{ \
|
||||
.type = TSParseActionTypeRecover \
|
||||
}}
|
||||
|
||||
#define ACCEPT_INPUT() \
|
||||
{{ \
|
||||
.type = TSParseActionTypeAccept \
|
||||
}}
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif // TREE_SITTER_PARSER_H_
|
||||
Reference in New Issue
Block a user