raphael/minishell
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

splitted parser and grammar into two separate .a

Browse source
This commit is contained in:
Maix0 2024-05-30 19:57:33 +02:00
parent 84705f955e
commit 6cc16ff7ef
16 changed files with 6548 additions and 7381 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.clang-format
View file

@ -1,6 +1,6 @@
BasedOnStyle: Microsoft BasedOnStyle: Microsoft
IndentWidth: 4 IndentWidth: 4
ColumnLimit: 80 ColumnLimit: 1600
UseTab: Always UseTab: Always
SortIncludes: CaseInsensitive SortIncludes: CaseInsensitive
IndentPPDirectives: AfterHash IndentPPDirectives: AfterHash

1
.gitignore vendored
View file

@ -54,3 +54,4 @@ objects/
minishell minishell
.envrc .envrc
.idea .idea
parser/split_rust

16
Makefile
View file

@ -6,7 +6,7 @@
# By: rparodi <rparodi@student.42.fr> +#+ +:+ +#+ # # By: rparodi <rparodi@student.42.fr> +#+ +:+ +#+ #
# +#+#+#+#+#+ +#+ # # +#+#+#+#+#+ +#+ #
# Created: 2023/11/12 11:05:05 by rparodi #+# #+# # # Created: 2023/11/12 11:05:05 by rparodi #+# #+# #
# Updated: 2024/05/08 16:01:18 by maiboyer ### ########.fr # # Updated: 2024/05/30 18:03:52 by maiboyer ### ########.fr #
# # # #
# **************************************************************************** # # **************************************************************************** #
@ -25,15 +25,25 @@ SRC_DIR = ./sources
GEN_DIR = ./output GEN_DIR = ./output
NAME = minishell NAME = minishell
PMAKE =
ifndef PMAKE_DISABLE
ifeq ($(shell uname), Linux)
PMAKE = -j$(shell grep -c ^processor /proc/cpuinfo)
endif
ifeq ($(shell uname), Darwin)
PMAKE = -j$(shell sysctl -n hw.ncpu)
endif
endif
# All (make all) # All (make all)
all: all:
@$(MAKE) --no-print-directory header OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd) @$(MAKE) --no-print-directory header OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd)
@$(MAKE) --no-print-directory -f./Minishell.mk OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd) @$(MAKE) --no-print-directory -f./Minishell.mk OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd) $(PMAKE)
@$(MAKE) --no-print-directory footer OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd) @$(MAKE) --no-print-directory footer OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd)
bonus: bonus:
@$(MAKE) --no-print-directory header OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd) @$(MAKE) --no-print-directory header OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd)
@$(MAKE) --no-print-directory -f./Minishell.mk OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd) bonus @$(MAKE) --no-print-directory -f./Minishell.mk OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd) $(PMAKE) bonus
@$(MAKE) --no-print-directory footer OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd) @$(MAKE) --no-print-directory footer OBJDIRNAME=$(OBJDIRNAME) BASE_PATH=$(shell pwd)
# Header # Header

7
Minishell.mk
View file

@ -6,7 +6,7 @@
# By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ # # By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ #
# +#+#+#+#+#+ +#+ # # +#+#+#+#+#+ +#+ #
# Created: 2024/04/28 17:28:30 by maiboyer #+# #+# # # Created: 2024/04/28 17:28:30 by maiboyer #+# #+# #
# Updated: 2024/05/26 16:21:15 by maiboyer ### ########.fr # # Updated: 2024/05/30 19:52:58 by maiboyer ### ########.fr #
# # # #
# **************************************************************************** # # **************************************************************************** #
@ -55,7 +55,7 @@ END = \033[0m
.PHONY: all Bonus .PHONY: all Bonus
LIBS_NAMES = me gmr aq ast LIBS_NAMES = me gmr aq ast parser
LIBS_FILES = $(addprefix $(OBJDIRNAME)/, $(addsuffix .a, $(addprefix lib, $(LIBS_NAMES)))) LIBS_FILES = $(addprefix $(OBJDIRNAME)/, $(addsuffix .a, $(addprefix lib, $(LIBS_NAMES))))
LIBS_FLAGS = $(addprefix -l, $(LIBS_NAMES)) LIBS_FLAGS = $(addprefix -l, $(LIBS_NAMES))
@ -63,7 +63,8 @@ all:
@$(MAKE) -C ./stdme/ "LIB_NAME=$(shell realpath ./stdme)/" "BUILD_DIR=$(shell realpath ./$(OBJDIRNAME))" libme.a @$(MAKE) -C ./stdme/ "LIB_NAME=$(shell realpath ./stdme)/" "BUILD_DIR=$(shell realpath ./$(OBJDIRNAME))" libme.a
@$(MAKE) -C ./allocator/ "LIB_NAME=$(shell realpath ./allocator)/" "BUILD_DIR=$(shell realpath ./$(OBJDIRNAME))" libaq.a @$(MAKE) -C ./allocator/ "LIB_NAME=$(shell realpath ./allocator)/" "BUILD_DIR=$(shell realpath ./$(OBJDIRNAME))" libaq.a
@$(MAKE) -C ./ast/ "LIB_NAME=$(shell realpath ./ast)/" "BUILD_DIR=$(shell realpath ./$(OBJDIRNAME))" libast.a @$(MAKE) -C ./ast/ "LIB_NAME=$(shell realpath ./ast)/" "BUILD_DIR=$(shell realpath ./$(OBJDIRNAME))" libast.a
@$(MAKE) -C ./parser/ "LIB_NAME=$(shell realpath ./parser)/" "BUILD_DIR=$(shell realpath ./$(OBJDIRNAME))" libgmr.a @$(MAKE) -C ./parser/ -f./Grammar.mk "LIB_NAME=$(shell realpath ./parser)/" "BUILD_DIR=$(shell realpath ./$(OBJDIRNAME))" libgmr.a
@$(MAKE) -C ./parser/ -f./Parser.mk "LIB_NAME=$(shell realpath ./parser)/" "BUILD_DIR=$(shell realpath ./$(OBJDIRNAME))" libparser.a
@$(MAKE) -f./Minishell.mk $(NAME) @$(MAKE) -f./Minishell.mk $(NAME)

71
flake.lock generated
View file

@ -108,6 +108,24 @@
"type": "github" "type": "github"
} }
}, },
"flake-utils_5": {
"inputs": {
"systems": "systems_5"
},
"locked": {
"lastModified": 1705309234,
"narHash": "sha256-uNRRNRKmJyCRC/8y1RqBkqWBLM034y4qN7EprSdmgyA=",
"owner": "numtide",
"repo": "flake-utils",
"rev": "1ef2e671c3b0c19053962c07dbda38332dcebf26",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "flake-utils",
"type": "github"
}
},
"generic_c": { "generic_c": {
"inputs": { "inputs": {
"flake-utils": "flake-utils_3", "flake-utils": "flake-utils_3",
@ -219,12 +237,29 @@
"type": "indirect" "type": "indirect"
} }
}, },
"nixpkgs_6": {
"locked": {
"lastModified": 1706487304,
"narHash": "sha256-LE8lVX28MV2jWJsidW13D2qrHU/RUUONendL2Q/WlJg=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "90f456026d284c22b3e3497be980b2e47d0b28ac",
"type": "github"
},
"original": {
"owner": "NixOS",
"ref": "nixpkgs-unstable",
"repo": "nixpkgs",
"type": "github"
}
},
"root": { "root": {
"inputs": { "inputs": {
"c_formatter_42": "c_formatter_42", "c_formatter_42": "c_formatter_42",
"flake-utils": "flake-utils_2", "flake-utils": "flake-utils_2",
"generic_c": "generic_c", "generic_c": "generic_c",
"nixpkgs": "nixpkgs_5" "nixpkgs": "nixpkgs_5",
"rust-overlay": "rust-overlay_2"
} }
}, },
"rust-overlay": { "rust-overlay": {
@ -246,6 +281,25 @@
"type": "github" "type": "github"
} }
}, },
"rust-overlay_2": {
"inputs": {
"flake-utils": "flake-utils_5",
"nixpkgs": "nixpkgs_6"
},
"locked": {
"lastModified": 1717035469,
"narHash": "sha256-MzH+yjKULH3HCRj9QCTwBvqq4LZkR0ZqRE/QfGOGC2E=",
"owner": "oxalica",
"repo": "rust-overlay",
"rev": "095702e63a40e86f339d11864da9dc965b70a01e",
"type": "github"
},
"original": {
"owner": "oxalica",
"repo": "rust-overlay",
"type": "github"
}
},
"systems": { "systems": {
"locked": { "locked": {
"lastModified": 1681028828, "lastModified": 1681028828,
@ -305,6 +359,21 @@
"repo": "default", "repo": "default",
"type": "github" "type": "github"
} }
},
"systems_5": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
} }
}, },
"root": "root", "root": "root",

10
flake.nix
View file

@ -4,17 +4,22 @@
inputs.flake-utils.url = "github:numtide/flake-utils"; inputs.flake-utils.url = "github:numtide/flake-utils";
inputs.generic_c.url = "github:Maix0/generic_c"; inputs.generic_c.url = "github:Maix0/generic_c";
inputs.c_formatter_42.url = "github:Maix0/c_formatter_42-flake"; inputs.c_formatter_42.url = "github:Maix0/c_formatter_42-flake";
inputs.rust-overlay.url = "github:oxalica/rust-overlay";
outputs = { outputs = {
self, self,
nixpkgs, nixpkgs,
flake-utils, flake-utils,
generic_c, generic_c,
c_formatter_42 c_formatter_42,
rust-overlay,
}: }:
flake-utils.lib.eachDefaultSystem ( flake-utils.lib.eachDefaultSystem (
system: let system: let
pkgs = nixpkgs.legacyPackages.${system}; pkgs = import nixpkgs {
inherit system;
overlays = [(import rust-overlay)];
};
in { in {
devShell = pkgs.mkShell { devShell = pkgs.mkShell {
packages = with pkgs; [ packages = with pkgs; [
@ -28,6 +33,7 @@
c_formatter_42.packages.${system}.default c_formatter_42.packages.${system}.default
llvmPackages.bintools llvmPackages.bintools
norminette norminette
rust-bin.stable.latest.default
]; ];
VALGRIND_INC_OPT = "${pkgs.valgrind.dev}/include"; VALGRIND_INC_OPT = "${pkgs.valgrind.dev}/include";
ASAN_OPTIONS = "strict_string_checks=1:detect_stack_use_after_return=1:check_initialization_order=1:strict_init_order=1"; ASAN_OPTIONS = "strict_string_checks=1:detect_stack_use_after_return=1:check_initialization_order=1:strict_init_order=1";

8755
parser/Filelist.mk
View file

File diff suppressed because it is too large Load diff

73
parser/Grammar.mk Normal file
View file

@ -0,0 +1,73 @@
# **************************************************************************** #
# #
# ::: :::::::: #
# Grammar.mk :+: :+: :+: #
# +:+ +:+ +:+ #
# By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ #
# +#+#+#+#+#+ +#+ #
# Created: 2023/11/03 13:20:01 by maiboyer #+# #+# #
# Updated: 2024/05/30 19:51:10 by maiboyer ### ########.fr #
# #
# **************************************************************************** #
ANAME = gmr
BUILD_DIR = ../build
SRC_DIR = ./static
BONUS_FLAGS =
NAME = lib$(ANAME).a
LIB_NAME ?=
TARGET = $(BUILD_DIR)/$(NAME)
CC ?= cc
CFLAGS = -Wall -Wextra -Werror -MMD -I./includes -I../includes -I../output/include
#CFLAGS += -fsanitize=address -fno-omit-frame-pointer -fsanitize-address-use-after-return=runtime -fno-common -fsanitize-address-use-after-scope
include ./Filelist.mk
SRC = $(addsuffix .c,$(addprefix $(SRC_DIR)/,$(SRC_FILES)))
OBJ = $(addsuffix .o,$(addprefix $(BUILD_DIR)/$(ANAME)/,$(SRC_FILES)))
DEPS = $(addsuffix .d,$(addprefix $(BUILD_DIR)/$(ANAME)/,$(SRC_FILES)))
INCLUDES =
GREEN = \033[32m
GREY = \033[0;90m
RED = \033[0;31m
GOLD = \033[38;5;220m
END = \033[0m
.PHONY: all clean fclean re
all: $(NAME)
$(NAME): $(TARGET)
$(TARGET): $(OBJ)
@echo -e '$(GREY) Linking\t$(END)$(GREEN)$(NAME)$(END)'
@ar rcs $(BUILD_DIR)/$(NAME) $(OBJ)
$(BUILD_DIR)/$(ANAME)/%.o: $(SRC_DIR)/%.c
@mkdir -p $(dir $@)
@echo -e '$(GREY) Compiling\t$(END)$(GREEN)$<$(END)'
@$(CC) $(CFLAGS) $(INCLUDES) -c $< -o $@
clean:
@- $(foreach LIB,$(LIBS), \
make clean LIB_NAME=$(LIB)/ BUILD_DIR=$(realpath $(BUILD_DIR)) -C $(LIB) --no-print-directory || true;\
)
$(if $(LIB_NAME),,\
rm -rf $(BUILD_DIR) \
)
fclean: clean
@- $(foreach LIB,$(LIBS), \
make fclean LIB_NAME=$(LIB)/ BUILD_DIR=$(realpath $(BUILD_DIR)) -C $(LIB) --no-print-directory || true;\
)
rm -f $(BUILD_DIR)/$(NAME)
re:
@$(MAKE) --no-print-directory fclean
@$(MAKE) --no-print-directory all
-include $(DEPS)

82
parser/Makefile
View file

@ -3,81 +3,23 @@
# ::: :::::::: # # ::: :::::::: #
# Makefile :+: :+: :+: # # Makefile :+: :+: :+: #
# +:+ +:+ +:+ # # +:+ +:+ +:+ #
# By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ # # By: rparodi <rparodi@student.42.fr> +#+ +:+ +#+ #
# +#+#+#+#+#+ +#+ # # +#+#+#+#+#+ +#+ #
# Created: 2023/11/03 13:20:01 by maiboyer #+# #+# # # Created: 2023/11/12 11:05:05 by rparodi #+# #+# #
# Updated: 2024/05/25 16:29:29 by maiboyer ### ########.fr # # Updated: 2024/05/30 19:46:52 by maiboyer ### ########.fr #
# # # #
# **************************************************************************** # # **************************************************************************** #
BUILD_DIR = ../build BUILD_DIR ?= ../build/
SRC_DIR = ./
BONUS_FLAGS = all:
NAME = libgmr.a @$(MAKE) --no-print-directory -f Parser.mk "LIB_NAME=$(shell realpath .)/" "BUILD_DIR=$(shell realpath $(BUILD_DIR))" libparser.a
LIB_NAME ?= @$(MAKE) --no-print-directory -f Grammar.mk "LIB_NAME=$(shell realpath .)/" "BUILD_DIR=$(shell realpath $(BUILD_DIR))" libgmr.a
TARGET = $(BUILD_DIR)/$(NAME)
CC ?= cc
CFLAGS = -Wall -Wextra -Werror -MMD -I./includes -I../includes -I../output/include
#CFLAGS += -fsanitize=address -fno-omit-frame-pointer -fsanitize-address-use-after-return=runtime -fno-common -fsanitize-address-use-after-scope
include ./Filelist.mk
SRC_FILES += ./src/combined ./src/scanner libparser.a:
SRC = $(addsuffix .c,$(addprefix $(SRC_DIR)/,$(SRC_FILES))) @$(MAKE) --no-print-directory -f Parser.mk "LIB_NAME=$(shell realpath .)/" "BUILD_DIR=$(shell realpath $(BUILD_DIR))" libparser.a
OBJ = $(addsuffix .o,$(addprefix $(BUILD_DIR)/gmr/,$(SRC_FILES)))
DEPS = $(addsuffix .d,$(addprefix $(BUILD_DIR)/gmr/,$(SRC_FILES)))
INCLUDES = libgmr.a:
GREEN = \033[32m @$(MAKE) --no-print-directory -f Grammar.mk "LIB_NAME=$(shell realpath .)/" "BUILD_DIR=$(shell realpath $(BUILD_DIR))" libgmr.a
GREY = \033[0;90m
RED = \033[0;31m
GOLD = \033[38;5;220m
END = \033[0m
.PHONY: all .PHONY: all bonus clean fclean re libparser.a libgmr.a
.PHONY: libs_build
.PHONY: bonus
.PHONY: clean
.PHONY: fclean
.PHONY: re
.PHONY: format
.PHONY: subject
.PHONY: submit
.PHONY: so
all: $(NAME)
$(NAME): $(TARGET)
$(TARGET): $(OBJ)
@#echo "ar rcs $(BUILD_DIR)/$(NAME) <OBJS...>"
@echo -e '$(GREY) Linking\t$(END)$(GREEN)$(NAME)$(END)'
@ar rcs $(BUILD_DIR)/$(NAME) $(OBJ)
$(BUILD_DIR)/gmr/%.o: $(SRC_DIR)/%.c
@mkdir -p $(dir $@)
@echo -e '$(GREY) Compiling\t$(END)$(GREEN)$<$(END)'
@$(CC) $(CFLAGS) $(INCLUDES) -c $< -o $@
clean:
@- $(foreach LIB,$(LIBS), \
make clean LIB_NAME=$(LIB)/ BUILD_DIR=$(realpath $(BUILD_DIR)) -C $(LIB) --no-print-directory || true;\
)
$(if $(LIB_NAME),,\
rm -rf $(BUILD_DIR) \
)
fclean: clean
@- $(foreach LIB,$(LIBS), \
make fclean LIB_NAME=$(LIB)/ BUILD_DIR=$(realpath $(BUILD_DIR)) -C $(LIB) --no-print-directory || true;\
)
rm -f $(BUILD_DIR)/$(NAME)
re:
@$(MAKE) --no-print-directory fclean
@$(MAKE) --no-print-directory all
generate_filelist:
@/usr/bin/env zsh -c "tree -iFf --noreport $(SRC_DIR) | rg '^$(SRC_DIR)/(.*)\.c\$$' --replace '\$$1' | sort -u" > ./source_files.list
-include $(DEPS)

75
parser/Parser.mk Normal file
View file

@ -0,0 +1,75 @@
# **************************************************************************** #
# #
# ::: :::::::: #
# Parser.mk :+: :+: :+: #
# +:+ +:+ +:+ #
# By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ #
# +#+#+#+#+#+ +#+ #
# Created: 2023/11/03 13:20:01 by maiboyer #+# #+# #
# Updated: 2024/05/30 19:41:06 by maiboyer ### ########.fr #
# #
# **************************************************************************** #
ANAME = parser
BUILD_DIR = ../build
SRC_DIR = ./src
GEN_DIR = ./generic
BONUS_FLAGS =
NAME = lib$(ANAME).a
LIB_NAME ?=
TARGET = $(BUILD_DIR)/$(NAME)
CC ?= cc
CFLAGS = -Wall -Wextra -Werror -MMD -I./includes -I../includes -I../output/include
#CFLAGS += -fsanitize=address -fno-omit-frame-pointer -fsanitize-address-use-after-return=runtime -fno-common -fsanitize-address-use-after-scope
SRC_FILES = combined scanner funcs create_language
GEN_FILES =
SRC = $(addsuffix .c,$(addprefix $(SRC_DIR)/,$(SRC_FILES))) $(addsuffix .c,$(addprefix $(GEN_DIR)/,$(GEN_FILES)))
OBJ = $(addsuffix .o,$(addprefix $(BUILD_DIR)/$(ANAME)/,$(SRC_FILES))) $(addsuffix .o,$(addprefix $(BUILD_DIR)/$(ANAME)/,$(GEN_FILES)))
DEPS = $(addsuffix .d,$(addprefix $(BUILD_DIR)/$(ANAME)/,$(SRC_FILES))) $(addsuffix .d,$(addprefix $(BUILD_DIR)/$(ANAME)/,$(GEN_FILES)))
INCLUDES =
GREEN = \033[32m
GREY = \033[0;90m
RED = \033[0;31m
GOLD = \033[38;5;220m
END = \033[0m
.PHONY: all clean fclean re
all: $(NAME)
$(NAME): $(TARGET)
$(TARGET): $(OBJ)
@#echo "ar rcs $(BUILD_DIR)/$(NAME) <OBJS...>"
@echo -e '$(GREY) Linking\t$(END)$(GREEN)$(NAME)$(END)'
@ar rcs $(BUILD_DIR)/$(NAME) $(OBJ)
$(BUILD_DIR)/$(ANAME)/%.o: $(SRC_DIR)/%.c
@mkdir -p $(dir $@)
@echo -e '$(GREY) Compiling\t$(END)$(GREEN)$<$(END)'
@$(CC) $(CFLAGS) $(INCLUDES) -c $< -o $@
clean:
@- $(foreach LIB,$(LIBS), \
make clean LIB_NAME=$(LIB)/ BUILD_DIR=$(realpath $(BUILD_DIR)) -C $(LIB) --no-print-directory || true;\
)
$(if $(LIB_NAME),,\
rm -rf $(BUILD_DIR) \
)
fclean: clean
@- $(foreach LIB,$(LIBS), \
make fclean LIB_NAME=$(LIB)/ BUILD_DIR=$(realpath $(BUILD_DIR)) -C $(LIB) --no-print-directory || true;\
)
rm -f $(BUILD_DIR)/$(NAME)
re:
@$(MAKE) --no-print-directory fclean
@$(MAKE) --no-print-directory all
-include $(DEPS)

721
parser/src/api.h
View file

@ -59,728 +59,7 @@
// tree's own heap data. // tree's own heap data.
#define ts_subtree_children(self) ((self).data.is_inline ? NULL : (t_subtree *)((self).ptr) - (self).ptr->child_count) #define ts_subtree_children(self) ((self).data.is_inline ? NULL : (t_subtree *)((self).ptr) - (self).ptr->child_count)
/// 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))
static inline size_t atomic_load(const volatile size_t *p)
{
return (*p);
}
static inline uint32_t atomic_inc(volatile uint32_t *p)
{
return (++(*p));
}
static inline uint32_t atomic_dec(volatile uint32_t *p)
{
return (--(*p));
}
static inline bool ts_language_is_symbol_external(const t_language *self, t_symbol symbol)
{
return 0 < symbol && symbol < self->external_token_count + 1;
}
static inline const t_parse_action *ts_language_actions(const t_language *self, t_state_id state, t_symbol symbol, uint32_t *count)
{
t_table_entry entry;
ts_language_table_entry(self, state, symbol, &entry);
*count = entry.action_count;
return entry.actions;
}
static inline bool ts_language_has_reduce_action(const t_language *self, t_state_id state, t_symbol symbol)
{
t_table_entry entry;
ts_language_table_entry(self, state, symbol, &entry);
return entry.action_count > 0 && entry.actions[0].type == TSParseActionTypeReduce;
}
// Lookup the table value for a given symbol and state.
//
// For non-terminal symbols, the table value represents a successor state.
// For terminal symbols, it represents an index in the actions table.
// For 'large' parse states, this is a direct lookup. For 'small' parse
// states, this requires searching through the symbol groups to find
// the given symbol.
static inline uint16_t ts_language_lookup(const t_language *self, t_state_id state, t_symbol symbol)
{
if (state >= self->large_state_count)
{
uint32_t index = self->small_parse_table_map[state - self->large_state_count];
const uint16_t *data = &self->small_parse_table[index];
uint16_t group_count = *(data++);
for (unsigned i = 0; i < group_count; i++)
{
uint16_t section_value = *(data++);
uint16_t symbol_count = *(data++);
for (unsigned j = 0; j < symbol_count; j++)
{
if (*(data++) == symbol)
return section_value;
}
}
return 0;
}
else
{
return self->parse_table[state * self->symbol_count + symbol];
}
}
static inline bool ts_language_has_actions(const t_language *self, t_state_id state, t_symbol symbol)
{
return ts_language_lookup(self, state, symbol) != 0;
}
// Iterate over all of the symbols that are valid in the given state.
//
// For 'large' parse states, this just requires iterating through
// all possible symbols and checking the parse table for each one.
// For 'small' parse states, this exploits the structure of the
// table to only visit the valid symbols.
static inline t_lookahead_iterator ts_language_lookaheads(const t_language *self, t_state_id state)
{
bool is_small_state = state >= self->large_state_count;
const uint16_t *data;
const uint16_t *group_end = NULL;
uint16_t group_count = 0;
if (is_small_state)
{
uint32_t index = self->small_parse_table_map[state - self->large_state_count];
data = &self->small_parse_table[index];
group_end = data + 1;
group_count = *data;
}
else
{
data = &self->parse_table[state * self->symbol_count] - 1;
}
return (t_lookahead_iterator){
.language = self,
.data = data,
.group_end = group_end,
.group_count = group_count,
.is_small_state = is_small_state,
.symbol = UINT16_MAX,
.next_state = 0,
};
}
static inline bool ts_lookahead_iterator__next(t_lookahead_iterator *self)
{
// For small parse states, valid symbols are listed explicitly,
// grouped by their value. There's no need to look up the actions
// again until moving to the next group.
if (self->is_small_state)
{
self->data++;
if (self->data == self->group_end)
{
if (self->group_count == 0)
return false;
self->group_count--;
self->table_value = *(self->data++);
unsigned symbol_count = *(self->data++);
self->group_end = self->data + symbol_count;
self->symbol = *self->data;
}
else
{
self->symbol = *self->data;
return true;
}
}
// For large parse states, iterate through every symbol until one
// is found that has valid actions.
else
{
do
{
self->data++;
self->symbol++;
if (self->symbol >= self->language->symbol_count)
return false;
self->table_value = *self->data;
} while (!self->table_value);
}
// Depending on if the symbols is terminal or non-terminal, the table value
// either represents a list of actions or a successor state.
if (self->symbol < self->language->token_count)
{
const t_parse_action_entry *entry = &self->language->parse_actions[self->table_value];
self->action_count = entry->entry.count;
self->actions = (const t_parse_action *)(entry + 1);
self->next_state = 0;
}
else
{
self->action_count = 0;
self->next_state = self->table_value;
}
return true;
}
// Whether the state is a "primary state". If this returns false, it indicates
// that there exists another state that behaves identically to this one with
// respect to query analysis.
static inline bool ts_language_state_is_primary(const t_language *self, t_state_id state)
{
if (self->version >= LANGUAGE_VERSION_WITH_PRIMARY_STATES)
{
return state == self->primary_state_ids[state];
}
else
{
return true;
}
}
static inline const bool *ts_language_enabled_external_tokens(const t_language *self, unsigned external_scanner_state)
{
if (external_scanner_state == 0)
{
return NULL;
}
else
{
return self->external_scanner.states + self->external_token_count * external_scanner_state;
}
}
static inline const t_symbol *ts_language_alias_sequence(const t_language *self, uint32_t production_id)
{
return production_id ? &self->alias_sequences[production_id * self->max_alias_sequence_length] : NULL;
}
static inline t_symbol ts_language_alias_at(const t_language *self, uint32_t production_id, uint32_t child_index)
{
return production_id ? self->alias_sequences[production_id * self->max_alias_sequence_length + child_index] : 0;
}
static inline void ts_language_field_map(const t_language *self, uint32_t production_id, const t_field_map_entry **start, const t_field_map_entry **end)
{
if (self->field_count == 0)
{
*start = NULL;
*end = NULL;
return;
}
t_field_map_slice slice = self->field_map_slices[production_id];
*start = &self->field_map_entries[slice.index];
*end = &self->field_map_entries[slice.index] + slice.length;
}
static inline void ts_language_aliases_for_symbol(const t_language *self, t_symbol original_symbol, const t_symbol **start, const t_symbol **end)
{
*start = &self->public_symbol_map[original_symbol];
*end = *start + 1;
unsigned idx = 0;
for (;;)
{
t_symbol symbol = self->alias_map[idx++];
if (symbol == 0 || symbol > original_symbol)
break;
uint16_t count = self->alias_map[idx++];
if (symbol == original_symbol)
{
*start = &self->alias_map[idx];
*end = &self->alias_map[idx + count];
break;
}
idx += count;
}
}
static const t_length LENGTH_UNDEFINED = {0, {0, 1}}; static const t_length LENGTH_UNDEFINED = {0, {0, 1}};
static const t_length LENGTH_MAX = {UINT32_MAX, {UINT32_MAX, UINT32_MAX}}; static const t_length LENGTH_MAX = {UINT32_MAX, {UINT32_MAX, UINT32_MAX}};
static t_point point_add(t_point a, t_point b);
static t_point point_sub(t_point a, t_point b);
static inline bool length_is_undefined(t_length length)
{
return length.bytes == 0 && length.extent.column != 0;
}
static inline t_length length_min(t_length len1, t_length len2)
{
return (len1.bytes < len2.bytes) ? len1 : len2;
}
static inline t_length length_add(t_length len1, t_length len2)
{
t_length result;
result.bytes = len1.bytes + len2.bytes;
result.extent = point_add(len1.extent, len2.extent);
return result;
}
static inline t_length length_sub(t_length len1, t_length len2)
{
t_length result;
result.bytes = len1.bytes - len2.bytes;
result.extent = point_sub(len1.extent, len2.extent);
return result;
}
static inline t_length length_zero(void)
{
t_length result = {0, {0, 0}};
return result;
}
static inline t_length length_saturating_sub(t_length len1, t_length len2)
{
if (len1.bytes > len2.bytes)
{
return length_sub(len1, len2);
}
else
{
return length_zero();
}
}
static inline bool set_contains(t_char_range *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;
t_char_range *range = &ranges[mid_index];
if (lookahead >= range->start && lookahead <= range->end)
{
return true;
}
else if (lookahead > range->end)
{
index = mid_index;
}
size -= half_size;
}
t_char_range *range = &ranges[index];
return (lookahead >= range->start && lookahead <= range->end);
}
static inline t_point point__new(unsigned row, unsigned column)
{
t_point result = {row, column};
return result;
}
static inline t_point point_add(t_point a, t_point b)
{
if (b.row > 0)
return point__new(a.row + b.row, b.column);
else
return point__new(a.row, a.column + b.column);
}
static inline t_point point_sub(t_point a, t_point b)
{
if (a.row > b.row)
return point__new(a.row - b.row, a.column);
else
return point__new(0, a.column - b.column);
}
static inline bool point_lte(t_point a, t_point b)
{
return (a.row < b.row) || (a.row == b.row && a.column <= b.column);
}
static inline bool point_lt(t_point a, t_point b)
{
return (a.row < b.row) || (a.row == b.row && a.column < b.column);
}
static inline bool point_gt(t_point a, t_point b)
{
return (a.row > b.row) || (a.row == b.row && a.column > b.column);
}
static inline bool point_gte(t_point a, t_point b)
{
return (a.row > b.row) || (a.row == b.row && a.column >= b.column);
}
static inline bool point_eq(t_point a, t_point b)
{
return a.row == b.row && a.column == b.column;
}
static inline t_point point_min(t_point a, t_point b)
{
if (a.row < b.row || (a.row == b.row && a.column < b.column))
return a;
else
return b;
}
static inline t_point point_max(t_point a, t_point b)
{
if (a.row > b.row || (a.row == b.row && a.column > b.column))
return a;
else
return b;
}
static inline void ts_reduce_action_set_add(t_reduce_action_set *self, t_reduce_action new_action)
{
for (uint32_t i = 0; i < self->size; i++)
{
t_reduce_action action = self->contents[i];
if (action.symbol == new_action.symbol && action.count == new_action.count)
return;
}
array_push(self, new_action);
}
static inline t_reusable_node reusable_node_new(void)
{
return (t_reusable_node){array_new(), NULL_SUBTREE};
}
static inline void reusable_node_clear(t_reusable_node *self)
{
array_clear(&self->stack);
self->last_external_token = NULL_SUBTREE;
}
static inline t_subtree reusable_node_tree(t_reusable_node *self)
{
return self->stack.size > 0 ? self->stack.contents[self->stack.size - 1].tree : NULL_SUBTREE;
}
static inline uint32_t reusable_node_byte_offset(t_reusable_node *self)
{
return self->stack.size > 0 ? self->stack.contents[self->stack.size - 1].byte_offset : UINT32_MAX;
}
static inline void reusable_node_delete(t_reusable_node *self)
{
array_delete(&self->stack);
}
static inline uint32_t ts_subtree_total_bytes(t_subtree self);
static inline uint32_t ts_subtree_child_count(t_subtree self);
static inline bool ts_subtree_has_external_tokens(t_subtree self);
static inline void reusable_node_advance(t_reusable_node *self)
{
t_stack_entry last_entry = *array_back(&self->stack);
uint32_t byte_offset = last_entry.byte_offset + ts_subtree_total_bytes(last_entry.tree);
if (ts_subtree_has_external_tokens(last_entry.tree))
{
self->last_external_token = ts_subtree_last_external_token(last_entry.tree);
}
t_subtree tree;
uint32_t next_index;
do
{
t_stack_entry popped_entry = array_pop(&self->stack);
next_index = popped_entry.child_index + 1;
if (self->stack.size == 0)
return;
tree = array_back(&self->stack)->tree;
} while (ts_subtree_child_count(tree) <= next_index);
array_push(&self->stack, ((t_stack_entry){
.tree = ts_subtree_children(tree)[next_index],
.child_index = next_index,
.byte_offset = byte_offset,
}));
}
static inline bool reusable_node_descend(t_reusable_node *self)
{
t_stack_entry last_entry = *array_back(&self->stack);
if (ts_subtree_child_count(last_entry.tree) > 0)
{
array_push(&self->stack, ((t_stack_entry){
.tree = ts_subtree_children(last_entry.tree)[0],
.child_index = 0,
.byte_offset = last_entry.byte_offset,
}));
return true;
}
else
{
return false;
}
}
static inline void reusable_node_advance_past_leaf(t_reusable_node *self)
{
while (reusable_node_descend(self))
{
}
reusable_node_advance(self);
}
static inline void reusable_node_reset(t_reusable_node *self, t_subtree tree)
{
reusable_node_clear(self);
array_push(&self->stack, ((t_stack_entry){
.tree = tree,
.child_index = 0,
.byte_offset = 0,
}));
// Never reuse the root node, because it has a non-standard internal
// structure due to transformations that are applied when it is accepted:
// adding the EOF child and any extra children.
if (!reusable_node_descend(self))
{
reusable_node_clear(self);
}
}
#define SUBTREE_GET(self, name) ((self).data.is_inline ? (self).data.name : (self).ptr->name)
static inline t_symbol ts_subtree_symbol(t_subtree self)
{
return SUBTREE_GET(self, symbol);
}
static inline bool ts_subtree_visible(t_subtree self)
{
return SUBTREE_GET(self, visible);
}
static inline bool ts_subtree_named(t_subtree self)
{
return SUBTREE_GET(self, named);
}
static inline bool ts_subtree_extra(t_subtree self)
{
return SUBTREE_GET(self, extra);
}
static inline bool ts_subtree_has_changes(t_subtree self)
{
return SUBTREE_GET(self, has_changes);
}
static inline bool ts_subtree_missing(t_subtree self)
{
return SUBTREE_GET(self, is_missing);
}
static inline bool ts_subtree_is_keyword(t_subtree self)
{
return SUBTREE_GET(self, is_keyword);
}
static inline t_state_id ts_subtree_parse_state(t_subtree self)
{
return SUBTREE_GET(self, parse_state);
}
static inline uint32_t ts_subtree_lookahead_bytes(t_subtree self)
{
return SUBTREE_GET(self, lookahead_bytes);
}
#undef SUBTREE_GET
// Get the size needed to store a heap-allocated subtree with the given
// number of children.
static inline size_t ts_subtree_alloc_size(uint32_t child_count)
{
return child_count * sizeof(t_subtree) + sizeof(t_subtree_heap_data);
}
static inline void ts_subtree_set_extra(t_mutable_subtree *self, bool is_extra)
{
if (self->data.is_inline)
{
self->data.extra = is_extra;
}
else
{
self->ptr->extra = is_extra;
}
}
static inline t_symbol ts_subtree_leaf_symbol(t_subtree self)
{
if (self.data.is_inline)
return self.data.symbol;
if (self.ptr->child_count == 0)
return self.ptr->symbol;
return self.ptr->first_leaf.symbol;
}
static inline t_state_id ts_subtree_leaf_parse_state(t_subtree self)
{
if (self.data.is_inline)
return self.data.parse_state;
if (self.ptr->child_count == 0)
return self.ptr->parse_state;
return self.ptr->first_leaf.parse_state;
}
static inline t_length ts_subtree_padding(t_subtree self)
{
if (self.data.is_inline)
{
t_length result = {self.data.padding_bytes, {self.data.padding_rows, self.data.padding_columns}};
return result;
}
else
{
return self.ptr->padding;
}
}
static inline t_length ts_subtree_size(t_subtree self)
{
if (self.data.is_inline)
{
t_length result = {self.data.size_bytes, {0, self.data.size_bytes}};
return result;
}
else
{
return self.ptr->size;
}
}
static inline t_length ts_subtree_total_size(t_subtree self)
{
return length_add(ts_subtree_padding(self), ts_subtree_size(self));
}
static inline uint32_t ts_subtree_total_bytes(t_subtree self)
{
return ts_subtree_total_size(self).bytes;
}
static inline uint32_t ts_subtree_child_count(t_subtree self)
{
return self.data.is_inline ? 0 : self.ptr->child_count;
}
static inline uint32_t ts_subtree_repeat_depth(t_subtree self)
{
return self.data.is_inline ? 0 : self.ptr->repeat_depth;
}
static inline uint32_t ts_subtree_is_repetition(t_subtree self)
{
return self.data.is_inline ? 0 : !self.ptr->named && !self.ptr->visible && self.ptr->child_count != 0;
}
static inline uint32_t ts_subtree_visible_descendant_count(t_subtree self)
{
return (self.data.is_inline || self.ptr->child_count == 0) ? 0 : self.ptr->visible_descendant_count;
}
static inline uint32_t ts_subtree_visible_child_count(t_subtree self)
{
if (ts_subtree_child_count(self) > 0)
{
return self.ptr->visible_child_count;
}
else
{
return 0;
}
}
static inline uint32_t ts_subtree_error_cost(t_subtree self)
{
if (ts_subtree_missing(self))
{
return ERROR_COST_PER_MISSING_TREE + ERROR_COST_PER_RECOVERY;
}
else
{
return self.data.is_inline ? 0 : self.ptr->error_cost;
}
}
static inline int32_t ts_subtree_dynamic_precedence(t_subtree self)
{
return (self.data.is_inline || self.ptr->child_count == 0) ? 0 : self.ptr->dynamic_precedence;
}
static inline uint16_t ts_subtree_production_id(t_subtree self)
{
if (ts_subtree_child_count(self) > 0)
{
return self.ptr->production_id;
}
else
{
return 0;
}
}
static inline bool ts_subtree_fragile_left(t_subtree self)
{
return self.data.is_inline ? false : self.ptr->fragile_left;
}
static inline bool ts_subtree_fragile_right(t_subtree self)
{
return self.data.is_inline ? false : self.ptr->fragile_right;
}
static inline bool ts_subtree_has_external_tokens(t_subtree self)
{
return self.data.is_inline ? false : self.ptr->has_external_tokens;
}
static inline bool ts_subtree_has_external_scanner_state_change(t_subtree self)
{
return self.data.is_inline ? false : self.ptr->has_external_scanner_state_change;
}
static inline bool ts_subtree_depends_on_column(t_subtree self)
{
return self.data.is_inline ? false : self.ptr->depends_on_column;
}
static inline bool ts_subtree_is_fragile(t_subtree self)
{
return self.data.is_inline ? false : (self.ptr->fragile_left || self.ptr->fragile_right);
}
static inline bool ts_subtree_is_error(t_subtree self)
{
return ts_subtree_symbol(self) == ts_builtin_sym_error;
}
static inline bool ts_subtree_is_eof(t_subtree self)
{
return ts_subtree_symbol(self) == ts_builtin_sym_end;
}
static inline t_subtree ts_subtree_from_mut(t_mutable_subtree self)
{
t_subtree result;
result.data = self.data;
return result;
}
static inline t_mutable_subtree ts_subtree_to_mut_unsafe(t_subtree self)
{
t_mutable_subtree result;
result.data = self.data;
return result;
}
static inline t_subtree ts_tree_cursor_current_subtree(const t_tree_cursor *_self)
{
const t_tree_cursor *self = (const t_tree_cursor *)_self;
t_tree_cursor_entry *last_entry = array_back(&self->stack);
return *last_entry->subtree;
}
#endif // TREE_SITTER_TREE_H_ #endif // TREE_SITTER_TREE_H_

15
parser/src/api_structs.h
View file

@ -12,7 +12,7 @@ typedef uint16_t t_state_id;
typedef uint16_t t_symbol; typedef uint16_t t_symbol;
typedef uint64_t t_parser_clock; typedef uint64_t t_parser_clock;
typedef uint64_t t_parser_duration; typedef uint64_t t_parser_duration;
typedef unsigned t_stack_version; typedef uint32_t t_stack_version;
typedef union u_parse_action_entry t_parse_action_entry; typedef union u_parse_action_entry t_parse_action_entry;
typedef union u_subtree t_subtree; typedef union u_subtree t_subtree;
@ -126,8 +126,7 @@ struct s_parse_range
struct s_parse_input struct s_parse_input
{ {
void *payload; void *payload;
const char *(*read)(void *payload, uint32_t byte_index, t_point position, const char *(*read)(void *payload, uint32_t byte_index, t_point position, uint32_t *bytes_read);
uint32_t *bytes_read);
t_input_encoding encoding; t_input_encoding encoding;
}; };
@ -520,8 +519,8 @@ struct s_language
void *(*create)(void); void *(*create)(void);
void (*destroy)(void *); void (*destroy)(void *);
bool (*scan)(void *, t_lexer_data *, const bool *symbol_whitelist); bool (*scan)(void *, t_lexer_data *, const bool *symbol_whitelist);
unsigned (*serialize)(void *, char *); uint32_t (*serialize)(void *, char *);
void (*deserialize)(void *, const char *, unsigned); void (*deserialize)(void *, const char *, uint32_t);
} external_scanner; } external_scanner;
const t_state_id *primary_state_ids; const t_state_id *primary_state_ids;
}; };
@ -552,8 +551,8 @@ struct s_reduce_action
{ {
uint32_t count; uint32_t count;
t_symbol symbol; t_symbol symbol;
int dynamic_precedence; int32_t dynamic_precedence;
unsigned short production_id; uint16_t production_id;
}; };
struct s_stack_entry struct s_stack_entry
@ -574,7 +573,7 @@ struct s_first_tree
t_subtree root; t_subtree root;
const t_language *language; const t_language *language;
t_parse_range *included_ranges; t_parse_range *included_ranges;
unsigned included_range_count; uint32_t included_range_count;
}; };
#endif // API_STRUCTS_H #endif // API_STRUCTS_H

87
parser/src/array.h
View file

@ -31,8 +31,7 @@
#endif #endif
/// Initialize an array. /// Initialize an array.
#define array_init(self) \ #define array_init(self) ((self)->size = 0, (self)->capacity = 0, (self)->contents = NULL)
((self)->size = 0, (self)->capacity = 0, (self)->contents = NULL)
/// Create an empty array. /// Create an empty array.
#define array_new() \ #define array_new() \
@ -41,8 +40,7 @@
} }
/// Get a pointer to the element at a given `index` in the array. /// Get a pointer to the element at a given `index` in the array.
#define array_get(self, _index) \ #define array_get(self, _index) (assert((uint32_t)(_index) < (self)->size), &(self)->contents[_index])
(assert((uint32_t)(_index) < (self)->size), &(self)->contents[_index])
/// Get a pointer to the first element in the array. /// Get a pointer to the first element in the array.
#define array_front(self) array_get(self, 0) #define array_front(self) array_get(self, 0)
@ -56,17 +54,14 @@
/// Reserve `new_capacity` elements of space in the array. If `new_capacity` is /// 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. /// less than the array's current capacity, this function has no effect.
#define array_reserve(self, new_capacity) \ #define array_reserve(self, new_capacity) _array__reserve((Array *)(self), array_elem_size(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 /// Free any memory allocated for this array. Note that this does not free any
/// memory allocated for the array's contents. /// memory allocated for the array's contents.
#define array_delete(self) _array__delete((Array *)(self)) #define array_delete(self) _array__delete((Array *)(self))
/// Push a new `element` onto the end of the array. /// Push a new `element` onto the end of the array.
#define array_push(self, element) \ #define array_push(self, element) (_array__grow((Array *)(self), 1, array_elem_size(self)), (self)->contents[(self)->size++] = (element))
(_array__grow((Array *)(self), 1, array_elem_size(self)), \
(self)->contents[(self)->size++] = (element))
/// Increase the array's size by `count` elements. /// Increase the array's size by `count` elements.
/// New elements are zero-initialized. /// New elements are zero-initialized.
@ -76,44 +71,34 @@
if ((count) == 0) \ if ((count) == 0) \
break; \ break; \
_array__grow((Array *)(self), count, array_elem_size(self)); \ _array__grow((Array *)(self), count, array_elem_size(self)); \
memset((self)->contents + (self)->size, 0, \ memset((self)->contents + (self)->size, 0, (count) * array_elem_size(self)); \
(count) * array_elem_size(self)); \
(self)->size += (count); \ (self)->size += (count); \
} while (0) } while (0)
/// Append all elements from one array to the end of another. /// Append all elements from one array to the end of another.
#define array_push_all(self, other) \ #define array_push_all(self, other) array_extend((self), (other)->size, (other)->contents)
array_extend((self), (other)->size, (other)->contents)
/// Append `count` elements to the end of the array, reading their values from /// Append `count` elements to the end of the array, reading their values from
/// the `contents` pointer. /// the `contents` pointer.
#define array_extend(self, count, contents) \ #define array_extend(self, count, contents) _array__splice((Array *)(self), array_elem_size(self), (self)->size, 0, 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 /// 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 same index, insert `new_count` new elements, reading their values from
/// the `new_contents` pointer. /// the `new_contents` pointer.
#define array_splice(self, _index, old_count, new_count, new_contents) \ #define array_splice(self, _index, old_count, new_count, new_contents) \
_array__splice((Array *)(self), array_elem_size(self), _index, old_count, \ _array__splice((Array *)(self), array_elem_size(self), _index, old_count, new_count, new_contents)
new_count, new_contents)
/// Insert one `element` into the array at the given `index`. /// Insert one `element` into the array at the given `index`.
#define array_insert(self, _index, element) \ #define array_insert(self, _index, element) _array__splice((Array *)(self), array_elem_size(self), _index, 0, 1, &(element))
_array__splice((Array *)(self), array_elem_size(self), _index, 0, 1, \
&(element))
/// Remove one element from the array at the given `index`. /// Remove one element from the array at the given `index`.
#define array_erase(self, _index) \ #define array_erase(self, _index) _array__erase((Array *)(self), array_elem_size(self), _index)
_array__erase((Array *)(self), array_elem_size(self), _index)
/// Pop the last element off the array, returning the element by value. /// Pop the last element off the array, returning the element by value.
#define array_pop(self) ((self)->contents[--(self)->size]) #define array_pop(self) ((self)->contents[--(self)->size])
/// Assign the contents of one array to another, reallocating if necessary. /// Assign the contents of one array to another, reallocating if necessary.
#define array_assign(self, other) \ #define array_assign(self, other) _array__assign((Array *)(self), (const Array *)(other), array_elem_size(self))
_array__assign((Array *)(self), (const Array *)(other), \
array_elem_size(self))
/// Swap one array with another /// Swap one array with another
#define array_swap(self, other) _array__swap((Array *)(self), (Array *)(other)) #define array_swap(self, other) _array__swap((Array *)(self), (Array *)(other))
@ -129,16 +114,19 @@
/// out-parameter is set to true. Otherwise, `index` is set to an index where /// 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` /// `needle` should be inserted in order to preserve the sorting, and `exists`
/// is set to false. /// is set to false.
#define array_search_sorted_with(self, compare, needle, _index, _exists) \ #define array_search_sorted_with(self, compare, needle, _index, _exists) _array__search_sorted(self, 0, compare, , needle, _index, _exists)
_array__search_sorted(self, 0, compare, , needle, _index, _exists)
/// 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))
/// Search a sorted array for a given `needle` value, using integer comparisons /// 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 /// of a given struct field (specified with a leading dot) to determine the
/// order. /// order.
/// ///
/// See also `array_search_sorted_with`. /// See also `array_search_sorted_with`.
#define array_search_sorted_by(self, field, needle, _index, _exists) \ #define array_search_sorted_by(self, field, needle, _index, _exists) _array__search_sorted(self, 0, _compare_int, 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` /// Insert a given `value` into a sorted array, using the given `compare`
/// callback to determine the order. /// callback to determine the order.
@ -179,27 +167,22 @@ static inline void _array__delete(Array *self)
} }
/// This is not what you're looking for, see `array_erase`. /// This is not what you're looking for, see `array_erase`.
static inline void _array__erase(Array *self, size_t element_size, static inline void _array__erase(Array *self, size_t element_size, uint32_t index)
uint32_t index)
{ {
assert(index < self->size); assert(index < self->size);
char *contents = (char *)self->contents; char *contents = (char *)self->contents;
memmove(contents + index * element_size, memmove(contents + index * element_size, contents + (index + 1) * element_size, (self->size - index - 1) * element_size);
contents + (index + 1) * element_size,
(self->size - index - 1) * element_size);
self->size--; self->size--;
} }
/// This is not what you're looking for, see `array_reserve`. /// This is not what you're looking for, see `array_reserve`.
static inline void _array__reserve(Array *self, size_t element_size, static inline void _array__reserve(Array *self, size_t element_size, uint32_t new_capacity)
uint32_t new_capacity)
{ {
if (new_capacity > self->capacity) if (new_capacity > self->capacity)
{ {
if (self->contents) if (self->contents)
{ {
self->contents = self->contents = realloc(self->contents, new_capacity * element_size);
realloc(self->contents, new_capacity * element_size);
} }
else else
{ {
@ -210,8 +193,7 @@ static inline void _array__reserve(Array *self, size_t element_size,
} }
/// This is not what you're looking for, see `array_assign`. /// This is not what you're looking for, see `array_assign`.
static inline void _array__assign(Array *self, const Array *other, static inline void _array__assign(Array *self, const Array *other, size_t element_size)
size_t element_size)
{ {
_array__reserve(self, element_size, other->size); _array__reserve(self, element_size, other->size);
self->size = other->size; self->size = other->size;
@ -227,8 +209,7 @@ static inline void _array__swap(Array *self, Array *other)
} }
/// This is not what you're looking for, see `array_push` or `array_grow_by`. /// 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, static inline void _array__grow(Array *self, uint32_t count, size_t element_size)
size_t element_size)
{ {
uint32_t new_size = self->size + count; uint32_t new_size = self->size + count;
if (new_size > self->capacity) if (new_size > self->capacity)
@ -243,9 +224,7 @@ static inline void _array__grow(Array *self, uint32_t count,
} }
/// This is not what you're looking for, see `array_splice`. /// This is not what you're looking for, see `array_splice`.
static inline void _array__splice(Array *self, size_t element_size, 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 index, uint32_t old_count,
uint32_t new_count, const void *elements)
{ {
uint32_t new_size = self->size + new_count - old_count; uint32_t new_size = self->size + new_count - old_count;
uint32_t old_end = index + old_count; uint32_t old_end = index + old_count;
@ -257,21 +236,17 @@ static inline void _array__splice(Array *self, size_t element_size,
char *contents = (char *)self->contents; char *contents = (char *)self->contents;
if (self->size > old_end) if (self->size > old_end)
{ {
memmove(contents + new_end * element_size, memmove(contents + new_end * element_size, contents + old_end * element_size, (self->size - old_end) * element_size);
contents + old_end * element_size,
(self->size - old_end) * element_size);
} }
if (new_count > 0) if (new_count > 0)
{ {
if (elements) if (elements)
{ {
memcpy((contents + index * element_size), elements, memcpy((contents + index * element_size), elements, new_count * element_size);
new_count * element_size);
} }
else else
{ {
memset((contents + index * element_size), 0, memset((contents + index * element_size), 0, new_count * element_size);
new_count * element_size);
} }
} }
self->size += new_count - old_count; self->size += new_count - old_count;
@ -280,8 +255,7 @@ static inline void _array__splice(Array *self, size_t element_size,
/// A binary search routine, based on Rust's `std::slice::binary_search_by`. /// 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 /// This is not what you're looking for, see `array_search_sorted_with` or
/// `array_search_sorted_by`. /// `array_search_sorted_by`.
#define _array__search_sorted(self, start, compare, suffix, needle, _index, \ #define _array__search_sorted(self, start, compare, suffix, needle, _index, _exists) \
_exists) \
do \ do \
{ \ { \
*(_index) = start; \ *(_index) = start; \
@ -294,8 +268,7 @@ static inline void _array__splice(Array *self, size_t element_size,
{ \ { \
uint32_t half_size = size / 2; \ uint32_t half_size = size / 2; \
uint32_t mid_index = *(_index) + half_size; \ uint32_t mid_index = *(_index) + half_size; \
comparison = \ comparison = compare(&((self)->contents[mid_index] suffix), (needle)); \
compare(&((self)->contents[mid_index] suffix), (needle)); \
if (comparison <= 0) \ if (comparison <= 0) \
*(_index) = mid_index; \ *(_index) = mid_index; \
size -= half_size; \ size -= half_size; \

2747
parser/src/combined.c
View file

File diff suppressed because it is too large Load diff

711
parser/src/funcs.c Normal file
View file

@ -0,0 +1,711 @@
/* ************************************************************************** */
/* */
/* ::: :::::::: */
/* funcs.c :+: :+: :+: */
/* +:+ +:+ +:+ */
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/05/30 19:21:01 by maiboyer #+# #+# */
/* Updated: 2024/05/30 19:22:53 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
#include "./api.h"
size_t atomic_load(const volatile size_t *p)
{
return (*p);
}
uint32_t atomic_inc(volatile uint32_t *p)
{
return (++(*p));
}
uint32_t atomic_dec(volatile uint32_t *p)
{
return (--(*p));
}
bool ts_language_is_symbol_external(const t_language *self, t_symbol symbol)
{
return 0 < symbol && symbol < self->external_token_count + 1;
}
const t_parse_action *ts_language_actions(const t_language *self, t_state_id state, t_symbol symbol, uint32_t *count)
{
t_table_entry entry;
ts_language_table_entry(self, state, symbol, &entry);
*count = entry.action_count;
return entry.actions;
}
bool ts_language_has_reduce_action(const t_language *self, t_state_id state, t_symbol symbol)
{
t_table_entry entry;
ts_language_table_entry(self, state, symbol, &entry);
return entry.action_count > 0 && entry.actions[0].type == TSParseActionTypeReduce;
}
uint16_t ts_language_lookup(const t_language *self, t_state_id state, t_symbol symbol)
{
if (state >= self->large_state_count)
{
uint32_t index = self->small_parse_table_map[state - self->large_state_count];
const uint16_t *data = &self->small_parse_table[index];
uint16_t group_count = *(data++);
for (unsigned i = 0; i < group_count; i++)
{
uint16_t section_value = *(data++);
uint16_t symbol_count = *(data++);
for (unsigned j = 0; j < symbol_count; j++)
{
if (*(data++) == symbol)
return section_value;
}
}
return 0;
}
else
{
return self->parse_table[state * self->symbol_count + symbol];
}
}
bool ts_language_has_actions(const t_language *self, t_state_id state, t_symbol symbol)
{
return ts_language_lookup(self, state, symbol) != 0;
}
t_lookahead_iterator ts_language_lookaheads(const t_language *self, t_state_id state)
{
bool is_small_state = state >= self->large_state_count;
const uint16_t *data;
const uint16_t *group_end = NULL;
uint16_t group_count = 0;
if (is_small_state)
{
uint32_t index = self->small_parse_table_map[state - self->large_state_count];
data = &self->small_parse_table[index];
group_end = data + 1;
group_count = *data;
}
else
{
data = &self->parse_table[state * self->symbol_count] - 1;
}
return (t_lookahead_iterator){
.language = self,
.data = data,
.group_end = group_end,
.group_count = group_count,
.is_small_state = is_small_state,
.symbol = UINT16_MAX,
.next_state = 0,
};
}
bool ts_lookahead_iterator__next(t_lookahead_iterator *self)
{
// For small parse states, valid symbols are listed explicitly,
// grouped by their value. There's no need to look up the actions
// again until moving to the next group.
if (self->is_small_state)
{
self->data++;
if (self->data == self->group_end)
{
if (self->group_count == 0)
return false;
self->group_count--;
self->table_value = *(self->data++);
unsigned symbol_count = *(self->data++);
self->group_end = self->data + symbol_count;
self->symbol = *self->data;
}
else
{
self->symbol = *self->data;
return true;
}
}
// For large parse states, iterate through every symbol until one
// is found that has valid actions.
else
{
do
{
self->data++;
self->symbol++;
if (self->symbol >= self->language->symbol_count)
return false;
self->table_value = *self->data;
} while (!self->table_value);
}
// Depending on if the symbols is terminal or non-terminal, the table value
// either represents a list of actions or a successor state.
if (self->symbol < self->language->token_count)
{
const t_parse_action_entry *entry = &self->language->parse_actions[self->table_value];
self->action_count = entry->entry.count;
self->actions = (const t_parse_action *)(entry + 1);
self->next_state = 0;
}
else
{
self->action_count = 0;
self->next_state = self->table_value;
}
return true;
}
bool ts_language_state_is_primary(const t_language *self, t_state_id state)
{
if (self->version >= LANGUAGE_VERSION_WITH_PRIMARY_STATES)
{
return state == self->primary_state_ids[state];
}
else
{
return true;
}
}
const bool *ts_language_enabled_external_tokens(const t_language *self, unsigned external_scanner_state)
{
if (external_scanner_state == 0)
{
return NULL;
}
else
{
return self->external_scanner.states + self->external_token_count * external_scanner_state;
}
}
const t_symbol *ts_language_alias_sequence(const t_language *self, uint32_t production_id)
{
return production_id ? &self->alias_sequences[production_id * self->max_alias_sequence_length] : NULL;
}
t_symbol ts_language_alias_at(const t_language *self, uint32_t production_id, uint32_t child_index)
{
return production_id ? self->alias_sequences[production_id * self->max_alias_sequence_length + child_index] : 0;
}
void ts_language_field_map(const t_language *self, uint32_t production_id, const t_field_map_entry **start, const t_field_map_entry **end)
{
if (self->field_count == 0)
{
*start = NULL;
*end = NULL;
return;
}
t_field_map_slice slice = self->field_map_slices[production_id];
*start = &self->field_map_entries[slice.index];
*end = &self->field_map_entries[slice.index] + slice.length;
}
void ts_language_aliases_for_symbol(const t_language *self, t_symbol original_symbol, const t_symbol **start, const t_symbol **end)
{
*start = &self->public_symbol_map[original_symbol];
*end = *start + 1;
unsigned idx = 0;
for (;;)
{
t_symbol symbol = self->alias_map[idx++];
if (symbol == 0 || symbol > original_symbol)
break;
uint16_t count = self->alias_map[idx++];
if (symbol == original_symbol)
{
*start = &self->alias_map[idx];
*end = &self->alias_map[idx + count];
break;
}
idx += count;
}
}
bool length_is_undefined(t_length length)
{
return length.bytes == 0 && length.extent.column != 0;
}
t_length length_min(t_length len1, t_length len2)
{
return (len1.bytes < len2.bytes) ? len1 : len2;
}
t_length length_add(t_length len1, t_length len2)
{
t_length result;
result.bytes = len1.bytes + len2.bytes;
result.extent = point_add(len1.extent, len2.extent);
return result;
}
t_length length_sub(t_length len1, t_length len2)
{
t_length result;
result.bytes = len1.bytes - len2.bytes;
result.extent = point_sub(len1.extent, len2.extent);
return result;
}
t_length length_zero(void)
{
t_length result = {0, {0, 0}};
return result;
}
t_length length_saturating_sub(t_length len1, t_length len2)
{
if (len1.bytes > len2.bytes)
{
return length_sub(len1, len2);
}
else
{
return length_zero();
}
}
bool set_contains(t_char_range *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;
t_char_range *range = &ranges[mid_index];
if (lookahead >= range->start && lookahead <= range->end)
{
return true;
}
else if (lookahead > range->end)
{
index = mid_index;
}
size -= half_size;
}
t_char_range *range = &ranges[index];
return (lookahead >= range->start && lookahead <= range->end);
}
t_point point__new(unsigned row, unsigned column)
{
t_point result = {row, column};
return result;
}
t_point point_add(t_point a, t_point b)
{
if (b.row > 0)
return point__new(a.row + b.row, b.column);
else
return point__new(a.row, a.column + b.column);
}
t_point point_sub(t_point a, t_point b)
{
if (a.row > b.row)
return point__new(a.row - b.row, a.column);
else
return point__new(0, a.column - b.column);
}
bool point_lte(t_point a, t_point b)
{
return (a.row < b.row) || (a.row == b.row && a.column <= b.column);
}
bool point_lt(t_point a, t_point b)
{
return (a.row < b.row) || (a.row == b.row && a.column < b.column);
}
bool point_gt(t_point a, t_point b)
{
return (a.row > b.row) || (a.row == b.row && a.column > b.column);
}
bool point_gte(t_point a, t_point b)
{
return (a.row > b.row) || (a.row == b.row && a.column >= b.column);
}
bool point_eq(t_point a, t_point b)
{
return a.row == b.row && a.column == b.column;
}
t_point point_min(t_point a, t_point b)
{
if (a.row < b.row || (a.row == b.row && a.column < b.column))
return a;
else
return b;
}
t_point point_max(t_point a, t_point b)
{
if (a.row > b.row || (a.row == b.row && a.column > b.column))
return a;
else
return b;
}
void ts_reduce_action_set_add(t_reduce_action_set *self, t_reduce_action new_action)
{
for (uint32_t i = 0; i < self->size; i++)
{
t_reduce_action action = self->contents[i];
if (action.symbol == new_action.symbol && action.count == new_action.count)
return;
}
array_push(self, new_action);
}
t_reusable_node reusable_node_new(void)
{
return (t_reusable_node){array_new(), NULL_SUBTREE};
}
void reusable_node_clear(t_reusable_node *self)
{
array_clear(&self->stack);
self->last_external_token = NULL_SUBTREE;
}
t_subtree reusable_node_tree(t_reusable_node *self)
{
return self->stack.size > 0 ? self->stack.contents[self->stack.size - 1].tree : NULL_SUBTREE;
}
uint32_t reusable_node_byte_offset(t_reusable_node *self)
{
return self->stack.size > 0 ? self->stack.contents[self->stack.size - 1].byte_offset : UINT32_MAX;
}
void reusable_node_delete(t_reusable_node *self)
{
array_delete(&self->stack);
}
void reusable_node_advance(t_reusable_node *self)
{
t_stack_entry last_entry = *array_back(&self->stack);
uint32_t byte_offset = last_entry.byte_offset + ts_subtree_total_bytes(last_entry.tree);
if (ts_subtree_has_external_tokens(last_entry.tree))
{
self->last_external_token = ts_subtree_last_external_token(last_entry.tree);
}
t_subtree tree;
uint32_t next_index;
do
{
t_stack_entry popped_entry = array_pop(&self->stack);
next_index = popped_entry.child_index + 1;
if (self->stack.size == 0)
return;
tree = array_back(&self->stack)->tree;
} while (ts_subtree_child_count(tree) <= next_index);
array_push(&self->stack, ((t_stack_entry){
.tree = ts_subtree_children(tree)[next_index],
.child_index = next_index,
.byte_offset = byte_offset,
}));
}
bool reusable_node_descend(t_reusable_node *self)
{
t_stack_entry last_entry = *array_back(&self->stack);
if (ts_subtree_child_count(last_entry.tree) > 0)
{
array_push(&self->stack, ((t_stack_entry){
.tree = ts_subtree_children(last_entry.tree)[0],
.child_index = 0,
.byte_offset = last_entry.byte_offset,
}));
return true;
}
else
{
return false;
}
}
void reusable_node_advance_past_leaf(t_reusable_node *self)
{
while (reusable_node_descend(self))
{
}
reusable_node_advance(self);
}
void reusable_node_reset(t_reusable_node *self, t_subtree tree)
{
reusable_node_clear(self);
array_push(&self->stack, ((t_stack_entry){
.tree = tree,
.child_index = 0,
.byte_offset = 0,
}));
// Never reuse the root node, because it has a non-standard internal
// structure due to transformations that are applied when it is accepted:
// adding the EOF child and any extra children.
if (!reusable_node_descend(self))
{
reusable_node_clear(self);
}
}
#define SUBTREE_GET(self, name) ((self).data.is_inline ? (self).data.name : (self).ptr->name)
t_symbol ts_subtree_symbol(t_subtree self)
{
return SUBTREE_GET(self, symbol);
}
bool ts_subtree_visible(t_subtree self)
{
return SUBTREE_GET(self, visible);
}
bool ts_subtree_named(t_subtree self)
{
return SUBTREE_GET(self, named);
}
bool ts_subtree_extra(t_subtree self)
{
return SUBTREE_GET(self, extra);
}
bool ts_subtree_has_changes(t_subtree self)
{
return SUBTREE_GET(self, has_changes);
}
bool ts_subtree_missing(t_subtree self)
{
return SUBTREE_GET(self, is_missing);
}
bool ts_subtree_is_keyword(t_subtree self)
{
return SUBTREE_GET(self, is_keyword);
}
t_state_id ts_subtree_parse_state(t_subtree self)
{
return SUBTREE_GET(self, parse_state);
}
uint32_t ts_subtree_lookahead_bytes(t_subtree self)
{
return SUBTREE_GET(self, lookahead_bytes);
}
size_t ts_subtree_alloc_size(uint32_t child_count)
{
return child_count * sizeof(t_subtree) + sizeof(t_subtree_heap_data);
}
void ts_subtree_set_extra(t_mutable_subtree *self, bool is_extra)
{
if (self->data.is_inline)
{
self->data.extra = is_extra;
}
else
{
self->ptr->extra = is_extra;
}
}
t_symbol ts_subtree_leaf_symbol(t_subtree self)
{
if (self.data.is_inline)
return self.data.symbol;
if (self.ptr->child_count == 0)
return self.ptr->symbol;
return self.ptr->first_leaf.symbol;
}
t_state_id ts_subtree_leaf_parse_state(t_subtree self)
{
if (self.data.is_inline)
return self.data.parse_state;
if (self.ptr->child_count == 0)
return self.ptr->parse_state;
return self.ptr->first_leaf.parse_state;
}
t_length ts_subtree_padding(t_subtree self)
{
if (self.data.is_inline)
{
t_length result = {self.data.padding_bytes, {self.data.padding_rows, self.data.padding_columns}};
return result;
}
else
{
return self.ptr->padding;
}
}
t_length ts_subtree_size(t_subtree self)
{
if (self.data.is_inline)
{
t_length result = {self.data.size_bytes, {0, self.data.size_bytes}};
return result;
}
else
{
return self.ptr->size;
}
}
t_length ts_subtree_total_size(t_subtree self)
{
return length_add(ts_subtree_padding(self), ts_subtree_size(self));
}
uint32_t ts_subtree_total_bytes(t_subtree self)
{
return ts_subtree_total_size(self).bytes;
}
uint32_t ts_subtree_child_count(t_subtree self)
{
return self.data.is_inline ? 0 : self.ptr->child_count;
}
uint32_t ts_subtree_repeat_depth(t_subtree self)
{
return self.data.is_inline ? 0 : self.ptr->repeat_depth;
}
uint32_t ts_subtree_is_repetition(t_subtree self)
{
return self.data.is_inline ? 0 : !self.ptr->named && !self.ptr->visible && self.ptr->child_count != 0;
}
uint32_t ts_subtree_visible_descendant_count(t_subtree self)
{
return (self.data.is_inline || self.ptr->child_count == 0) ? 0 : self.ptr->visible_descendant_count;
}
uint32_t ts_subtree_visible_child_count(t_subtree self)
{
if (ts_subtree_child_count(self) > 0)
{
return self.ptr->visible_child_count;
}
else
{
return 0;
}
}
uint32_t ts_subtree_error_cost(t_subtree self)
{
if (ts_subtree_missing(self))
{
return ERROR_COST_PER_MISSING_TREE + ERROR_COST_PER_RECOVERY;
}
else
{
return self.data.is_inline ? 0 : self.ptr->error_cost;
}
}
int32_t ts_subtree_dynamic_precedence(t_subtree self)
{
return (self.data.is_inline || self.ptr->child_count == 0) ? 0 : self.ptr->dynamic_precedence;
}
uint16_t ts_subtree_production_id(t_subtree self)
{
if (ts_subtree_child_count(self) > 0)
{
return self.ptr->production_id;
}
else
{
return 0;
}
}
bool ts_subtree_fragile_left(t_subtree self)
{
return self.data.is_inline ? false : self.ptr->fragile_left;
}
bool ts_subtree_fragile_right(t_subtree self)
{
return self.data.is_inline ? false : self.ptr->fragile_right;
}
bool ts_subtree_has_external_tokens(t_subtree self)
{
return self.data.is_inline ? false : self.ptr->has_external_tokens;
}
bool ts_subtree_has_external_scanner_state_change(t_subtree self)
{
return self.data.is_inline ? false : self.ptr->has_external_scanner_state_change;
}
bool ts_subtree_depends_on_column(t_subtree self)
{
return self.data.is_inline ? false : self.ptr->depends_on_column;
}
bool ts_subtree_is_fragile(t_subtree self)
{
return self.data.is_inline ? false : (self.ptr->fragile_left || self.ptr->fragile_right);
}
bool ts_subtree_is_error(t_subtree self)
{
return ts_subtree_symbol(self) == ts_builtin_sym_error;
}
bool ts_subtree_is_eof(t_subtree self)
{
return ts_subtree_symbol(self) == ts_builtin_sym_end;
}
t_subtree ts_subtree_from_mut(t_mutable_subtree self)
{
t_subtree result;
result.data = self.data;
return result;
}
t_mutable_subtree ts_subtree_to_mut_unsafe(t_subtree self)
{
t_mutable_subtree result;
result.data = self.data;
return result;
}
t_subtree ts_tree_cursor_current_subtree(const t_tree_cursor *_self)
{
const t_tree_cursor *self = (const t_tree_cursor *)_self;
t_tree_cursor_entry *last_entry = array_back(&self->stack);
return *last_entry->subtree;
}

104
parser/src/funcs.h
View file

@ -3,28 +3,78 @@
#include "./api_structs.h" #include "./api_structs.h"
bool ts_external_scanner_state_eq(const t_external_scanner_state *self, const char *, unsigned); bool length_is_undefined(t_length length);
bool point_eq(t_point a, t_point b);
bool point_gt(t_point a, t_point b);
bool point_gte(t_point a, t_point b);
bool point_lt(t_point a, t_point b);
bool point_lte(t_point a, t_point b);
bool reusable_node_descend(t_reusable_node *self);
bool set_contains(t_char_range *ranges, uint32_t len, int32_t lookahead);
bool ts_external_scanner_state_eq(const t_external_scanner_state *self, const char *, uint32_t);
bool ts_language_has_actions(const t_language *self, t_state_id state, t_symbol symbol);
bool ts_language_has_reduce_action(const t_language *self, t_state_id state, t_symbol symbol);
bool ts_language_is_symbol_external(const t_language *self, t_symbol symbol);
bool ts_language_state_is_primary(const t_language *self, t_state_id state);
bool ts_lexer_set_included_ranges(t_lexer *self, const t_parse_range *ranges, uint32_t count); bool ts_lexer_set_included_ranges(t_lexer *self, const t_parse_range *ranges, uint32_t count);
bool ts_range_array_intersects(const t_range_array *self, unsigned start_index, uint32_t start_byte, uint32_t end_byte); bool ts_lookahead_iterator__next(t_lookahead_iterator *self);
bool ts_range_array_intersects(const t_range_array *self, uint32_t start_index, uint32_t start_byte, uint32_t end_byte);
bool ts_stack_can_merge(t_stack *, t_stack_version, t_stack_version); bool ts_stack_can_merge(t_stack *, t_stack_version, t_stack_version);
bool ts_stack_has_advanced_since_error(const t_stack *, t_stack_version); bool ts_stack_has_advanced_since_error(const t_stack *, t_stack_version);
bool ts_stack_is_active(const t_stack *, t_stack_version); bool ts_stack_is_active(const t_stack *, t_stack_version);
bool ts_stack_is_halted(const t_stack *, t_stack_version); bool ts_stack_is_halted(const t_stack *, t_stack_version);
bool ts_stack_is_paused(const t_stack *, t_stack_version); bool ts_stack_is_paused(const t_stack *, t_stack_version);
bool ts_stack_merge(t_stack *, t_stack_version, t_stack_version); bool ts_stack_merge(t_stack *, t_stack_version, t_stack_version);
bool ts_subtree_depends_on_column(t_subtree self);
bool ts_subtree_external_scanner_state_eq(t_subtree, t_subtree); bool ts_subtree_external_scanner_state_eq(t_subtree, t_subtree);
bool ts_subtree_extra(t_subtree self);
bool ts_subtree_fragile_left(t_subtree self);
bool ts_subtree_fragile_right(t_subtree self);
bool ts_subtree_has_changes(t_subtree self);
bool ts_subtree_has_external_scanner_state_change(t_subtree self);
bool ts_subtree_has_external_tokens(t_subtree self);
bool ts_subtree_has_external_tokens(t_subtree self);
bool ts_subtree_is_eof(t_subtree self);
bool ts_subtree_is_error(t_subtree self);
bool ts_subtree_is_fragile(t_subtree self);
bool ts_subtree_is_keyword(t_subtree self);
bool ts_subtree_missing(t_subtree self);
bool ts_subtree_named(t_subtree self);
bool ts_subtree_visible(t_subtree self);
char *ts_subtree_string(t_subtree, t_symbol, bool, const t_language *, bool include_all); char *ts_subtree_string(t_subtree, t_symbol, bool, const t_language *, bool include_all);
const bool *ts_language_enabled_external_tokens(const t_language *self, uint32_t external_scanner_state);
const char *ts_external_scanner_state_data(const t_external_scanner_state *); const char *ts_external_scanner_state_data(const t_external_scanner_state *);
const t_external_scanner_state *ts_subtree_external_scanner_state(t_subtree self); const t_external_scanner_state *ts_subtree_external_scanner_state(t_subtree self);
const t_parse_action *ts_language_actions(const t_language *self, t_state_id state, t_symbol symbol, uint32_t *count);
const t_symbol *ts_language_alias_sequence(const t_language *self, uint32_t production_id);
int ts_stack_dynamic_precedence(t_stack *, t_stack_version); int ts_stack_dynamic_precedence(t_stack *, t_stack_version);
int ts_subtree_compare(t_subtree, t_subtree, t_subtree_pool *); int ts_subtree_compare(t_subtree, t_subtree, t_subtree_pool *);
t_first_tree *ts_tree_new(t_subtree root, const t_language *language, const t_parse_range *, unsigned); int32_t ts_subtree_dynamic_precedence(t_subtree self);
size_t atomic_load(const volatile size_t *p);
size_t ts_subtree_alloc_size(uint32_t child_count);
t_first_tree *ts_tree_new(t_subtree root, const t_language *language, const t_parse_range *, uint32_t);
t_length length_add(t_length len1, t_length len2);
t_length length_min(t_length len1, t_length len2);
t_length length_saturating_sub(t_length len1, t_length len2);
t_length length_sub(t_length len1, t_length len2);
t_length length_zero(void);
t_length ts_stack_position(const t_stack *, t_stack_version); t_length ts_stack_position(const t_stack *, t_stack_version);
t_length ts_subtree_padding(t_subtree self);
t_length ts_subtree_size(t_subtree self);
t_length ts_subtree_total_size(t_subtree self);
t_lookahead_iterator ts_language_lookaheads(const t_language *self, t_state_id state);
t_mutable_subtree ts_subtree_make_mut(t_subtree_pool *, t_subtree); t_mutable_subtree ts_subtree_make_mut(t_subtree_pool *, t_subtree);
t_mutable_subtree ts_subtree_new_node(t_symbol, t_subtree_array *, unsigned, const t_language *); t_mutable_subtree ts_subtree_new_node(t_symbol, t_subtree_array *, uint32_t, const t_language *);
t_mutable_subtree ts_subtree_to_mut_unsafe(t_subtree self);
t_parse_node ts_node_new(const t_first_tree *, const t_subtree *, t_length, t_symbol); t_parse_node ts_node_new(const t_first_tree *, const t_subtree *, t_length, t_symbol);
t_parse_node ts_tree_cursor_parent_node(const t_tree_cursor *); t_parse_node ts_tree_cursor_parent_node(const t_tree_cursor *);
t_parse_range *ts_lexer_included_ranges(const t_lexer *self, uint32_t *count); t_parse_range *ts_lexer_included_ranges(const t_lexer *self, uint32_t *count);
t_point point__new(uint32_t row, uint32_t column);
t_point point_add(t_point a, t_point b);
t_point point_max(t_point a, t_point b);
t_point point_min(t_point a, t_point b);
t_point point_sub(t_point a, t_point b);
t_reusable_node reusable_node_new(void);
t_stack *ts_stack_new(t_subtree_pool *); t_stack *ts_stack_new(t_subtree_pool *);
t_stack_slice_array ts_stack_pop_all(t_stack *, t_stack_version); t_stack_slice_array ts_stack_pop_all(t_stack *, t_stack_version);
t_stack_slice_array ts_stack_pop_count(t_stack *, t_stack_version, uint32_t count); t_stack_slice_array ts_stack_pop_count(t_stack *, t_stack_version, uint32_t count);
@ -33,26 +83,56 @@ t_stack_summary *ts_stack_get_summary(t_stack *, t_stack_version);
t_stack_version ts_stack_copy_version(t_stack *, t_stack_version); t_stack_version ts_stack_copy_version(t_stack *, t_stack_version);
t_state_id ts_language_next_state(const t_language *self, t_state_id state, t_symbol symbol); t_state_id ts_language_next_state(const t_language *self, t_state_id state, t_symbol symbol);
t_state_id ts_stack_state(const t_stack *, t_stack_version); t_state_id ts_stack_state(const t_stack *, t_stack_version);
t_state_id ts_subtree_leaf_parse_state(t_subtree self);
t_state_id ts_subtree_parse_state(t_subtree self);
t_subtree reusable_node_tree(t_reusable_node *self);
t_subtree ts_stack_last_external_token(const t_stack *, t_stack_version); t_subtree ts_stack_last_external_token(const t_stack *, t_stack_version);
t_subtree ts_stack_resume(t_stack *, t_stack_version); t_subtree ts_stack_resume(t_stack *, t_stack_version);
t_subtree ts_subtree_edit(t_subtree, const t_input_edit *edit, t_subtree_pool *); t_subtree ts_subtree_edit(t_subtree, const t_input_edit *edit, t_subtree_pool *);
t_subtree ts_subtree_from_mut(t_mutable_subtree self);
t_subtree ts_subtree_last_external_token(t_subtree); t_subtree ts_subtree_last_external_token(t_subtree);
t_subtree ts_subtree_new_error(t_subtree_pool *, int32_t, t_length, t_length, uint32_t, t_state_id, const t_language *); t_subtree ts_subtree_new_error(t_subtree_pool *, int32_t, t_length, t_length, uint32_t, t_state_id, const t_language *);
t_subtree ts_subtree_new_error_node(t_subtree_array *, bool, const t_language *); t_subtree ts_subtree_new_error_node(t_subtree_array *, bool, const t_language *);
t_subtree ts_subtree_new_leaf(t_subtree_pool *, t_symbol, t_length, t_length, uint32_t, t_state_id, bool, bool, bool, const t_language *); t_subtree ts_subtree_new_leaf(t_subtree_pool *, t_symbol, t_length, t_length, uint32_t, t_state_id, bool, bool, bool, const t_language *);
t_subtree ts_subtree_new_missing_leaf(t_subtree_pool *, t_symbol, t_length, uint32_t, const t_language *); t_subtree ts_subtree_new_missing_leaf(t_subtree_pool *, t_symbol, t_length, uint32_t, const t_language *);
t_subtree ts_tree_cursor_current_subtree(const t_tree_cursor *_self);
t_subtree_array ts_stack_pop_error(t_stack *, t_stack_version); t_subtree_array ts_stack_pop_error(t_stack *, t_stack_version);
t_subtree_pool ts_subtree_pool_new(uint32_t capacity); t_subtree_pool ts_subtree_pool_new(uint32_t capacity);
t_symbol ts_language_alias_at(const t_language *self, uint32_t production_id, uint32_t child_index);
t_symbol ts_language_public_symbol(const t_language *, t_symbol); t_symbol ts_language_public_symbol(const t_language *, t_symbol);
t_symbol ts_subtree_leaf_symbol(t_subtree self);
t_symbol ts_subtree_symbol(t_subtree self);
t_symbol_metadata ts_language_symbol_metadata(const t_language *, t_symbol); t_symbol_metadata ts_language_symbol_metadata(const t_language *, t_symbol);
t_tree_cursor_step ts_tree_cursor_goto_first_child_internal(t_tree_cursor *); t_tree_cursor_step ts_tree_cursor_goto_first_child_internal(t_tree_cursor *);
t_tree_cursor_step ts_tree_cursor_goto_next_sibling_internal(t_tree_cursor *); t_tree_cursor_step ts_tree_cursor_goto_next_sibling_internal(t_tree_cursor *);
uint16_t ts_language_lookup(const t_language *self, t_state_id state, t_symbol symbol);
uint16_t ts_subtree_production_id(t_subtree self);
uint32_t atomic_dec(volatile uint32_t *p);
uint32_t atomic_inc(volatile uint32_t *p);
uint32_t reusable_node_byte_offset(t_reusable_node *self);
uint32_t ts_stack_version_count(const t_stack *); uint32_t ts_stack_version_count(const t_stack *);
unsigned ts_stack_error_cost(const t_stack *, t_stack_version version); uint32_t ts_subtree_child_count(t_subtree self);
unsigned ts_stack_node_count_since_error(const t_stack *, t_stack_version); uint32_t ts_subtree_child_count(t_subtree self);
unsigned ts_subtree_get_changed_ranges(const t_subtree *old_tree, const t_subtree *new_tree, t_tree_cursor *cursor1, t_tree_cursor *cursor2, const t_language *language, const t_range_array *included_range_differences, t_parse_range **ranges); uint32_t ts_subtree_error_cost(t_subtree self);
uint32_t ts_subtree_is_repetition(t_subtree self);
uint32_t ts_subtree_lookahead_bytes(t_subtree self);
uint32_t ts_subtree_repeat_depth(t_subtree self);
uint32_t ts_subtree_total_bytes(t_subtree self);
uint32_t ts_subtree_total_bytes(t_subtree self);
uint32_t ts_subtree_visible_child_count(t_subtree self);
uint32_t ts_subtree_visible_descendant_count(t_subtree self);
uint32_t ts_stack_error_cost(const t_stack *, t_stack_version version);
uint32_t ts_stack_node_count_since_error(const t_stack *, t_stack_version);
uint32_t ts_subtree_get_changed_ranges(const t_subtree *old_tree, const t_subtree *new_tree, t_tree_cursor *cursor1, t_tree_cursor *cursor2, const t_language *language, const t_range_array *included_range_differences, t_parse_range **ranges);
void reusable_node_advance(t_reusable_node *self);
void reusable_node_advance_past_leaf(t_reusable_node *self);
void reusable_node_clear(t_reusable_node *self);
void reusable_node_delete(t_reusable_node *self);
void reusable_node_reset(t_reusable_node *self, t_subtree tree);
void ts_external_scanner_state_delete(t_external_scanner_state *self); void ts_external_scanner_state_delete(t_external_scanner_state *self);
void ts_external_scanner_state_init(t_external_scanner_state *, const char *, unsigned); void ts_external_scanner_state_init(t_external_scanner_state *, const char *, uint32_t);
void ts_language_aliases_for_symbol(const t_language *self, t_symbol original_symbol, const t_symbol **start, const t_symbol **end);
void ts_language_field_map(const t_language *self, uint32_t production_id, const t_field_map_entry **start, const t_field_map_entry **end);
void ts_language_table_entry(const t_language *, t_state_id, t_symbol, t_table_entry *); void ts_language_table_entry(const t_language *, t_state_id, t_symbol, t_table_entry *);
void ts_lexer_advance_to_end(t_lexer *lexer); void ts_lexer_advance_to_end(t_lexer *lexer);
void ts_lexer_delete(t_lexer *lexer); void ts_lexer_delete(t_lexer *lexer);
@ -62,13 +142,14 @@ void ts_lexer_mark_end(t_lexer *lexer);
void ts_lexer_reset(t_lexer *lexer, t_length); void ts_lexer_reset(t_lexer *lexer, t_length);
void ts_lexer_set_input(t_lexer *lexer, t_parse_input); void ts_lexer_set_input(t_lexer *lexer, t_parse_input);
void ts_lexer_start(t_lexer *lexer); void ts_lexer_start(t_lexer *lexer);
void ts_range_array_get_changed_ranges(const t_parse_range *old_ranges, unsigned old_range_count, const t_parse_range *new_ranges, unsigned new_range_count, t_range_array *differences); void ts_range_array_get_changed_ranges(const t_parse_range *old_ranges, uint32_t old_range_count, const t_parse_range *new_ranges, uint32_t new_range_count, t_range_array *differences);
void ts_reduce_action_set_add(t_reduce_action_set *self, t_reduce_action new_action);
void ts_stack_clear(t_stack *); void ts_stack_clear(t_stack *);
void ts_stack_delete(t_stack *); void ts_stack_delete(t_stack *);
void ts_stack_halt(t_stack *, t_stack_version); void ts_stack_halt(t_stack *, t_stack_version);
void ts_stack_pause(t_stack *, t_stack_version, t_subtree); void ts_stack_pause(t_stack *, t_stack_version, t_subtree);
void ts_stack_push(t_stack *, t_stack_version, t_subtree, bool, t_state_id); void ts_stack_push(t_stack *, t_stack_version, t_subtree, bool, t_state_id);
void ts_stack_record_summary(t_stack *, t_stack_version, unsigned max_depth); void ts_stack_record_summary(t_stack *, t_stack_version, uint32_t max_depth);
void ts_stack_remove_version(t_stack *, t_stack_version); void ts_stack_remove_version(t_stack *, t_stack_version);
void ts_stack_renumber_version(t_stack *, t_stack_version, t_stack_version); void ts_stack_renumber_version(t_stack *, t_stack_version, t_stack_version);
void ts_stack_set_last_external_token(t_stack *, t_stack_version, t_subtree); void ts_stack_set_last_external_token(t_stack *, t_stack_version, t_subtree);
@ -82,10 +163,11 @@ void ts_subtree_balance(t_subtree, t_subtree_pool *, const t_language *);
void ts_subtree_pool_delete(t_subtree_pool *); void ts_subtree_pool_delete(t_subtree_pool *);
void ts_subtree_release(t_subtree_pool *, t_subtree); void ts_subtree_release(t_subtree_pool *, t_subtree);
void ts_subtree_retain(t_subtree); void ts_subtree_retain(t_subtree);
void ts_subtree_set_extra(t_mutable_subtree *self, bool is_extra);
void ts_subtree_set_symbol(t_mutable_subtree *, t_symbol, const t_language *); void ts_subtree_set_symbol(t_mutable_subtree *, t_symbol, const t_language *);
void ts_subtree_summarize(t_mutable_subtree, const t_subtree *, uint32_t, const t_language *); void ts_subtree_summarize(t_mutable_subtree, const t_subtree *, uint32_t, const t_language *);
void ts_subtree_summarize_children(t_mutable_subtree, const t_language *); void ts_subtree_summarize_children(t_mutable_subtree, const t_language *);
void ts_tree_cursor_current_status(const t_tree_cursor *, t_field_id *, bool *, bool *, bool *, t_symbol *, unsigned *); void ts_tree_cursor_current_status(const t_tree_cursor *, t_field_id *, bool *, bool *, bool *, t_symbol *, uint32_t *);
void ts_tree_cursor_init(t_tree_cursor *, t_parse_node); void ts_tree_cursor_init(t_tree_cursor *, t_parse_node);
#endif // FUNCS_H #endif // FUNCS_H