Reorganize repo, add rust CLI and binding code,

This commit is contained in:
Max Brunsfeld 2019-01-04 17:31:49 -08:00
commit 47607cecf4
221 changed files with 11359 additions and 18038 deletions

View file

@ -0,0 +1,38 @@
#ifndef TREE_SITTER_COMPILER_H_
#define TREE_SITTER_COMPILER_H_
#ifdef __cplusplus
extern "C" {
#endif
#include <stdio.h>
typedef enum {
TSCompileErrorTypeNone,
TSCompileErrorTypeInvalidGrammar,
TSCompileErrorTypeInvalidRegex,
TSCompileErrorTypeUndefinedSymbol,
TSCompileErrorTypeInvalidExtraToken,
TSCompileErrorTypeInvalidExternalToken,
TSCompileErrorTypeLexConflict,
TSCompileErrorTypeParseConflict,
TSCompileErrorTypeEpsilonRule,
TSCompileErrorTypeInvalidTokenContents,
TSCompileErrorTypeInvalidRuleName,
TSCompileErrorTypeInvalidWordRule,
} TSCompileErrorType;
typedef struct {
char *code;
char *error_message;
TSCompileErrorType error_type;
} TSCompileResult;
TSCompileResult ts_compile_grammar(const char *input, FILE *log_file);
TSCompileResult ts_compile_property_sheet(const char *input, FILE *log_file);
#ifdef __cplusplus
}
#endif
#endif // TREE_SITTER_COMPILER_H_

View file

@ -0,0 +1,195 @@
#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_RUNTIME_H_
typedef uint16_t TSSymbol;
typedef struct TSLanguage TSLanguage;
#endif
typedef uint16_t TSStateId;
typedef struct {
bool visible : 1;
bool named : 1;
} 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)(TSLexer *);
};
typedef enum {
TSParseActionTypeShift,
TSParseActionTypeReduce,
TSParseActionTypeAccept,
TSParseActionTypeRecover,
} TSParseActionType;
typedef struct {
union {
struct {
TSStateId state;
bool extra : 1;
bool repetition : 1;
};
struct {
TSSymbol symbol;
int16_t dynamic_precedence;
uint8_t child_count;
uint8_t alias_sequence_id;
};
} params;
TSParseActionType type : 4;
} TSParseAction;
typedef struct {
uint16_t lex_state;
uint16_t external_lex_state;
} TSLexMode;
typedef union {
TSParseAction action;
struct {
uint8_t count;
bool reusable : 1;
};
} TSParseActionEntry;
struct TSLanguage {
uint32_t version;
uint32_t symbol_count;
uint32_t alias_count;
uint32_t token_count;
uint32_t external_token_count;
const char **symbol_names;
const TSSymbolMetadata *symbol_metadata;
const uint16_t *parse_table;
const TSParseActionEntry *parse_actions;
const TSLexMode *lex_modes;
const TSSymbol *alias_sequences;
uint16_t max_alias_sequence_length;
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 (*destroy)(void *);
bool (*scan)(void *, TSLexer *, const bool *symbol_whitelist);
unsigned (*serialize)(void *, char *);
void (*deserialize)(void *, const char *, unsigned);
} external_scanner;
};
/*
* Lexer Macros
*/
#define START_LEXER() \
bool result = false; \
int32_t lookahead; \
next_state: \
lookahead = lexer->lookahead;
#define ADVANCE(state_value) \
{ \
lexer->advance(lexer, false); \
state = state_value; \
goto next_state; \
}
#define SKIP(state_value) \
{ \
lexer->advance(lexer, 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 STATE(id) id
#define ACTIONS(id) id
#define SHIFT(state_value) \
{ \
{ \
.type = TSParseActionTypeShift, \
.params = {.state = state_value}, \
} \
}
#define SHIFT_REPEAT(state_value) \
{ \
{ \
.type = TSParseActionTypeShift, \
.params = { \
.state = state_value, \
.repetition = true \
}, \
} \
}
#define RECOVER() \
{ \
{ .type = TSParseActionTypeRecover } \
}
#define SHIFT_EXTRA() \
{ \
{ \
.type = TSParseActionTypeShift, \
.params = {.extra = true} \
} \
}
#define REDUCE(symbol_val, child_count_val, ...) \
{ \
{ \
.type = TSParseActionTypeReduce, \
.params = { \
.symbol = symbol_val, \
.child_count = child_count_val, \
__VA_ARGS__ \
} \
} \
}
#define ACCEPT_INPUT() \
{ \
{ .type = TSParseActionTypeAccept } \
}
#ifdef __cplusplus
}
#endif
#endif // TREE_SITTER_PARSER_H_

View file

@ -0,0 +1,156 @@
#ifndef TREE_SITTER_RUNTIME_H_
#define TREE_SITTER_RUNTIME_H_
#ifdef __cplusplus
extern "C" {
#endif
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <stdbool.h>
#define TREE_SITTER_LANGUAGE_VERSION 9
typedef uint16_t TSSymbol;
typedef struct TSLanguage TSLanguage;
typedef struct TSParser TSParser;
typedef struct TSTree TSTree;
typedef enum {
TSInputEncodingUTF8,
TSInputEncodingUTF16,
} TSInputEncoding;
typedef enum {
TSSymbolTypeRegular,
TSSymbolTypeAnonymous,
TSSymbolTypeAuxiliary,
} TSSymbolType;
typedef struct {
uint32_t row;
uint32_t column;
} TSPoint;
typedef struct {
TSPoint start_point;
TSPoint end_point;
uint32_t start_byte;
uint32_t end_byte;
} TSRange;
typedef struct {
void *payload;
const char *(*read)(void *payload, uint32_t byte_index, TSPoint position, uint32_t *bytes_read);
TSInputEncoding encoding;
} TSInput;
typedef enum {
TSLogTypeParse,
TSLogTypeLex,
} TSLogType;
typedef struct {
void *payload;
void (*log)(void *payload, TSLogType, const char *);
} TSLogger;
typedef struct {
uint32_t start_byte;
uint32_t old_end_byte;
uint32_t new_end_byte;
TSPoint start_point;
TSPoint old_end_point;
TSPoint new_end_point;
} TSInputEdit;
typedef struct {
uint32_t context[4];
const void *id;
const TSTree *tree;
} TSNode;
typedef struct {
const void *tree;
const void *id;
uint32_t context[2];
} TSTreeCursor;
TSParser *ts_parser_new();
void ts_parser_delete(TSParser *);
const TSLanguage *ts_parser_language(const TSParser *);
bool ts_parser_set_language(TSParser *, const TSLanguage *);
TSLogger ts_parser_logger(const TSParser *);
void ts_parser_set_logger(TSParser *, TSLogger);
void ts_parser_print_dot_graphs(TSParser *, FILE *);
void ts_parser_halt_on_error(TSParser *, bool);
TSTree *ts_parser_parse(TSParser *, const TSTree *, TSInput);
TSTree *ts_parser_parse_string(TSParser *, const TSTree *, const char *, uint32_t);
TSTree *ts_parser_parse_string_encoding(TSParser *, const TSTree *, const char *, uint32_t, TSInputEncoding);
bool ts_parser_enabled(const TSParser *);
void ts_parser_set_enabled(TSParser *, bool);
size_t ts_parser_operation_limit(const TSParser *);
void ts_parser_set_operation_limit(TSParser *, size_t);
void ts_parser_reset(TSParser *);
void ts_parser_set_included_ranges(TSParser *, const TSRange *, uint32_t);
const TSRange *ts_parser_included_ranges(const TSParser *, uint32_t *);
TSTree *ts_tree_copy(const TSTree *);
void ts_tree_delete(TSTree *);
TSNode ts_tree_root_node(const TSTree *);
void ts_tree_edit(TSTree *, const TSInputEdit *);
TSRange *ts_tree_get_changed_ranges(const TSTree *, const TSTree *, uint32_t *);
void ts_tree_print_dot_graph(const TSTree *, FILE *);
const TSLanguage *ts_tree_language(const TSTree *);
uint32_t ts_node_start_byte(TSNode);
TSPoint ts_node_start_point(TSNode);
uint32_t ts_node_end_byte(TSNode);
TSPoint ts_node_end_point(TSNode);
TSSymbol ts_node_symbol(TSNode);
const char *ts_node_type(TSNode);
char *ts_node_string(TSNode);
bool ts_node_eq(TSNode, TSNode);
bool ts_node_is_null(TSNode);
bool ts_node_is_named(TSNode);
bool ts_node_is_missing(TSNode);
bool ts_node_has_changes(TSNode);
bool ts_node_has_error(TSNode);
TSNode ts_node_parent(TSNode);
TSNode ts_node_child(TSNode, uint32_t);
TSNode ts_node_named_child(TSNode, uint32_t);
uint32_t ts_node_child_count(TSNode);
uint32_t ts_node_named_child_count(TSNode);
TSNode ts_node_next_sibling(TSNode);
TSNode ts_node_next_named_sibling(TSNode);
TSNode ts_node_prev_sibling(TSNode);
TSNode ts_node_prev_named_sibling(TSNode);
TSNode ts_node_first_child_for_byte(TSNode, uint32_t);
TSNode ts_node_first_named_child_for_byte(TSNode, uint32_t);
TSNode ts_node_descendant_for_byte_range(TSNode, uint32_t, uint32_t);
TSNode ts_node_named_descendant_for_byte_range(TSNode, uint32_t, uint32_t);
TSNode ts_node_descendant_for_point_range(TSNode, TSPoint, TSPoint);
TSNode ts_node_named_descendant_for_point_range(TSNode, TSPoint, TSPoint);
void ts_node_edit(TSNode *, const TSInputEdit *);
TSTreeCursor ts_tree_cursor_new(TSNode);
void ts_tree_cursor_delete(TSTreeCursor *);
void ts_tree_cursor_reset(TSTreeCursor *, TSNode);
TSNode ts_tree_cursor_current_node(const TSTreeCursor *);
bool ts_tree_cursor_goto_parent(TSTreeCursor *);
bool ts_tree_cursor_goto_next_sibling(TSTreeCursor *);
bool ts_tree_cursor_goto_first_child(TSTreeCursor *);
int64_t ts_tree_cursor_goto_first_child_for_byte(TSTreeCursor *, uint32_t);
uint32_t ts_language_symbol_count(const TSLanguage *);
const char *ts_language_symbol_name(const TSLanguage *, TSSymbol);
TSSymbol ts_language_symbol_for_name(const TSLanguage *, const char *);
TSSymbolType ts_language_symbol_type(const TSLanguage *, TSSymbol);
uint32_t ts_language_version(const TSLanguage *);
#ifdef __cplusplus
}
#endif
#endif // TREE_SITTER_RUNTIME_H_