update: normed lots of stuff
This commit is contained in:
parent
978636b6ef
commit
50a2f3d4be
118 changed files with 1145 additions and 1330 deletions
|
|
@ -6,37 +6,37 @@
|
|||
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
|
||||
/* +#+#+#+#+#+ +#+ */
|
||||
/* Created: 2024/08/31 18:06:07 by maiboyer #+# #+# */
|
||||
/* Updated: 2024/08/31 18:23:07 by maiboyer ### ########.fr */
|
||||
/* Updated: 2024/09/19 16:58:25 by maiboyer ### ########.fr */
|
||||
/* */
|
||||
/* ************************************************************************** */
|
||||
|
||||
#include "me/types.h"
|
||||
#include "parser/lexer.h"
|
||||
|
||||
bool ts_lexer__eof(const TSLexer *_self);
|
||||
t_u32 ts_lexer__get_column(TSLexer *_self);
|
||||
void ts_lexer__advance(TSLexer *_self, bool skip);
|
||||
bool ts_lexer__eof(const t_lexer *_self);
|
||||
t_u32 ts_lexer__get_column(t_lexer *_self);
|
||||
void ts_lexer__advance(t_lexer *_self, bool skip);
|
||||
void ts_lexer__clear_chunk(t_lexer *self);
|
||||
void ts_lexer__get_chunk(t_lexer *self);
|
||||
void ts_lexer__get_lookahead(t_lexer *self);
|
||||
void ts_lexer__mark_end(TSLexer *_self);
|
||||
void ts_lexer__mark_end(t_lexer *_self);
|
||||
void ts_lexer_advance_to_end(t_lexer *self);
|
||||
void ts_lexer_goto(t_lexer *self, Length position);
|
||||
void ts_lexer_goto(t_lexer *self, t_length position);
|
||||
|
||||
bool ts_lexer__do_advance_loop(t_lexer *self, const TSRange **current_range);
|
||||
bool ts_lexer__do_advance_loop(t_lexer *self, const t_range **current_range);
|
||||
void ts_lexer__do_advance_after_loop(t_lexer *self, bool skip,
|
||||
const TSRange *cur);
|
||||
const t_range *cur);
|
||||
|
||||
// Intended to be called only from functions that control logging.
|
||||
void ts_lexer__do_advance(t_lexer *self, bool skip)
|
||||
{
|
||||
const TSRange *cur = \
|
||||
const t_range *cur = \
|
||||
&self->included_ranges[self->current_included_range_index];
|
||||
|
||||
if (self->lookahead_size)
|
||||
{
|
||||
self->current_position.bytes += self->lookahead_size;
|
||||
if (self->data.lookahead == '\n')
|
||||
if (self->funcs.lookahead == '\n')
|
||||
{
|
||||
self->current_position.extent.row++;
|
||||
self->current_position.extent.column = 0;
|
||||
|
|
@ -53,7 +53,7 @@ void ts_lexer__do_advance(t_lexer *self, bool skip)
|
|||
|
||||
// Advance to the next character in the source code, retrieving a new
|
||||
// chunk of source code if needed.
|
||||
void ts_lexer__advance(TSLexer *_self, bool skip)
|
||||
void ts_lexer__advance(t_lexer *_self, bool skip)
|
||||
{
|
||||
t_lexer *self;
|
||||
|
||||
|
|
@ -63,14 +63,14 @@ void ts_lexer__advance(TSLexer *_self, bool skip)
|
|||
ts_lexer__do_advance(self, skip);
|
||||
}
|
||||
|
||||
bool ts_lexer__do_advance_loop(t_lexer *self, const TSRange **current_range)
|
||||
bool ts_lexer__do_advance_loop(t_lexer *self, const t_range **current_range)
|
||||
{
|
||||
if (self->current_included_range_index < self->included_range_count)
|
||||
self->current_included_range_index++;
|
||||
if (self->current_included_range_index < self->included_range_count)
|
||||
{
|
||||
(*current_range)++;
|
||||
self->current_position = (Length){
|
||||
self->current_position = (t_length){
|
||||
(*current_range)->start_byte,
|
||||
(*current_range)->start_point,
|
||||
};
|
||||
|
|
@ -84,7 +84,7 @@ bool ts_lexer__do_advance_loop(t_lexer *self, const TSRange **current_range)
|
|||
}
|
||||
|
||||
void ts_lexer__do_advance_after_loop(t_lexer *self, bool skip,
|
||||
const TSRange *cur)
|
||||
const t_range *cur)
|
||||
{
|
||||
if (skip)
|
||||
self->token_start_position = self->current_position;
|
||||
|
|
@ -99,7 +99,7 @@ void ts_lexer__do_advance_after_loop(t_lexer *self, bool skip,
|
|||
else
|
||||
{
|
||||
ts_lexer__clear_chunk(self);
|
||||
self->data.lookahead = '\0';
|
||||
self->funcs.lookahead = '\0';
|
||||
self->lookahead_size = 1;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -13,16 +13,16 @@
|
|||
#include "me/types.h"
|
||||
#include "parser/lexer.h"
|
||||
|
||||
bool ts_lexer__eof(const TSLexer *_self);
|
||||
t_u32 ts_lexer__get_column(TSLexer *_self);
|
||||
void ts_lexer__advance(TSLexer *_self, bool skip);
|
||||
bool ts_lexer__eof(const t_lexer *_self);
|
||||
t_u32 ts_lexer__get_column(t_lexer *_self);
|
||||
void ts_lexer__advance(t_lexer *_self, bool skip);
|
||||
void ts_lexer__do_advance(t_lexer *self, bool skip);
|
||||
void ts_lexer__clear_chunk(t_lexer *self);
|
||||
void ts_lexer__get_chunk(t_lexer *self);
|
||||
void ts_lexer__get_lookahead(t_lexer *self);
|
||||
void ts_lexer__mark_end(TSLexer *_self);
|
||||
void ts_lexer__mark_end(t_lexer *_self);
|
||||
void ts_lexer_advance_to_end(t_lexer *self);
|
||||
void ts_lexer_goto(t_lexer *self, Length position);
|
||||
void ts_lexer_goto(t_lexer *self, t_length position);
|
||||
|
||||
// Clear the currently stored chunk of source code, because the lexer's
|
||||
// position has changed.
|
||||
|
|
|
|||
|
|
@ -6,28 +6,28 @@
|
|||
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
|
||||
/* +#+#+#+#+#+ +#+ */
|
||||
/* Created: 2024/08/31 18:07:07 by maiboyer #+# #+# */
|
||||
/* Updated: 2024/08/31 18:12:10 by maiboyer ### ########.fr */
|
||||
/* Updated: 2024/09/19 16:58:53 by maiboyer ### ########.fr */
|
||||
/* */
|
||||
/* ************************************************************************** */
|
||||
|
||||
#include "me/types.h"
|
||||
#include "parser/lexer.h"
|
||||
|
||||
bool ts_lexer__eof(const TSLexer *_self);
|
||||
t_u32 ts_lexer__get_column(TSLexer *_self);
|
||||
void ts_lexer__advance(TSLexer *_self, bool skip);
|
||||
bool ts_lexer__eof(const t_lexer *_self);
|
||||
t_u32 ts_lexer__get_column(t_lexer *_self);
|
||||
void ts_lexer__advance(t_lexer *_self, bool skip);
|
||||
void ts_lexer__do_advance(t_lexer *self, bool skip);
|
||||
void ts_lexer__clear_chunk(t_lexer *self);
|
||||
void ts_lexer__get_chunk(t_lexer *self);
|
||||
void ts_lexer__get_lookahead(t_lexer *self);
|
||||
void ts_lexer__mark_end(TSLexer *_self);
|
||||
void ts_lexer__mark_end(t_lexer *_self);
|
||||
void ts_lexer_advance_to_end(t_lexer *self);
|
||||
void ts_lexer_goto(t_lexer *self, Length position);
|
||||
void ts_lexer_goto(t_lexer *self, t_length position);
|
||||
|
||||
// Check if the lexer has reached EOF. This state is stored
|
||||
// by setting the lexer's `current_included_range_index` such that
|
||||
// it has consumed all of its available ranges.
|
||||
bool ts_lexer__eof(const TSLexer *_self)
|
||||
bool ts_lexer__eof(const t_lexer *_self)
|
||||
{
|
||||
t_lexer *self;
|
||||
|
||||
|
|
@ -37,14 +37,14 @@ bool ts_lexer__eof(const TSLexer *_self)
|
|||
|
||||
// Mark that a token match has completed. This can be called multiple
|
||||
// times if a longer match is found later.
|
||||
void ts_lexer__mark_end(TSLexer *_self)
|
||||
void ts_lexer__mark_end(t_lexer *_self)
|
||||
{
|
||||
t_lexer *self;
|
||||
TSRange *current_included_range;
|
||||
TSRange *previous_included_range;
|
||||
t_range *current_included_range;
|
||||
t_range *previous_included_range;
|
||||
|
||||
self = (t_lexer *)_self;
|
||||
if (!ts_lexer__eof(&self->data))
|
||||
if (!ts_lexer__eof(self))
|
||||
{
|
||||
current_included_range = \
|
||||
&self->included_ranges[self->current_included_range_index];
|
||||
|
|
@ -52,7 +52,7 @@ void ts_lexer__mark_end(TSLexer *_self)
|
|||
&& self->current_position.bytes == current_included_range->start_byte)
|
||||
{
|
||||
previous_included_range = current_included_range - 1;
|
||||
self->token_end_position = (Length){
|
||||
self->token_end_position = (t_length){
|
||||
previous_included_range->end_byte,
|
||||
previous_included_range->end_point,
|
||||
};
|
||||
|
|
@ -65,5 +65,5 @@ void ts_lexer__mark_end(TSLexer *_self)
|
|||
void ts_lexer_advance_to_end(t_lexer *self)
|
||||
{
|
||||
while (self->chunk)
|
||||
ts_lexer__advance(&self->data, false);
|
||||
ts_lexer__advance(self, false);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -13,18 +13,18 @@
|
|||
#include "me/types.h"
|
||||
#include "parser/lexer.h"
|
||||
|
||||
bool ts_lexer__eof(const TSLexer *_self);
|
||||
t_u32 ts_lexer__get_column(TSLexer *_self);
|
||||
void ts_lexer__advance(TSLexer *_self, bool skip);
|
||||
bool ts_lexer__eof(const t_lexer *_self);
|
||||
t_u32 ts_lexer__get_column(t_lexer *_self);
|
||||
void ts_lexer__advance(t_lexer *_self, bool skip);
|
||||
void ts_lexer__do_advance(t_lexer *self, bool skip);
|
||||
void ts_lexer__clear_chunk(t_lexer *self);
|
||||
void ts_lexer__get_chunk(t_lexer *self);
|
||||
void ts_lexer__get_lookahead(t_lexer *self);
|
||||
void ts_lexer__mark_end(TSLexer *_self);
|
||||
void ts_lexer__mark_end(t_lexer *_self);
|
||||
void ts_lexer_advance_to_end(t_lexer *self);
|
||||
void ts_lexer_goto(t_lexer *self, Length position);
|
||||
void ts_lexer_goto(t_lexer *self, t_length position);
|
||||
|
||||
t_u32 ts_lexer__get_column(TSLexer *_self)
|
||||
t_u32 ts_lexer__get_column(t_lexer *_self)
|
||||
{
|
||||
t_lexer *self;
|
||||
t_u32 goal_byte;
|
||||
|
|
|
|||
|
|
@ -6,32 +6,32 @@
|
|||
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
|
||||
/* +#+#+#+#+#+ +#+ */
|
||||
/* Created: 2024/08/31 18:08:11 by maiboyer #+# #+# */
|
||||
/* Updated: 2024/08/31 18:39:32 by maiboyer ### ########.fr */
|
||||
/* Updated: 2024/09/19 16:59:09 by maiboyer ### ########.fr */
|
||||
/* */
|
||||
/* ************************************************************************** */
|
||||
|
||||
#include "me/types.h"
|
||||
#include "parser/lexer.h"
|
||||
|
||||
bool ts_lexer__eof(const TSLexer *_self);
|
||||
t_u32 ts_lexer__get_column(TSLexer *_self);
|
||||
void ts_lexer__advance(TSLexer *_self, bool skip);
|
||||
bool ts_lexer__eof(const t_lexer *_self);
|
||||
t_u32 ts_lexer__get_column(t_lexer *_self);
|
||||
void ts_lexer__advance(t_lexer *_self, bool skip);
|
||||
void ts_lexer__do_advance(t_lexer *self, bool skip);
|
||||
void ts_lexer__clear_chunk(t_lexer *self);
|
||||
void ts_lexer__get_chunk(t_lexer *self);
|
||||
void ts_lexer__get_lookahead(t_lexer *self);
|
||||
void ts_lexer__mark_end(TSLexer *_self);
|
||||
void ts_lexer__mark_end(t_lexer *_self);
|
||||
void ts_lexer_advance_to_end(t_lexer *self);
|
||||
void ts_lexer_goto(t_lexer *self, Length position);
|
||||
void ts_lexer_goto(t_lexer *self, t_length position);
|
||||
|
||||
void ts_lexer_goto_inside_loop(t_lexer *self, bool *found_included_range,
|
||||
TSRange *included_range, t_usize i);
|
||||
t_range *included_range, t_usize i);
|
||||
void ts_lexer_goto_after_loop(t_lexer *self, bool found_included_range);
|
||||
|
||||
void ts_lexer_goto(t_lexer *self, Length position)
|
||||
void ts_lexer_goto(t_lexer *self, t_length position)
|
||||
{
|
||||
bool found_included_range;
|
||||
TSRange *included_range;
|
||||
t_range *included_range;
|
||||
t_u32 i;
|
||||
|
||||
included_range = NULL;
|
||||
|
|
@ -54,11 +54,11 @@ void ts_lexer_goto(t_lexer *self, Length position)
|
|||
}
|
||||
|
||||
void ts_lexer_goto_inside_loop(t_lexer *self, bool *found_included_range,
|
||||
TSRange *included_range, t_usize i)
|
||||
t_range *included_range, t_usize i)
|
||||
{
|
||||
if (included_range->start_byte >= self->current_position.bytes)
|
||||
{
|
||||
self->current_position = (Length){
|
||||
self->current_position = (t_length){
|
||||
.bytes = included_range->start_byte,
|
||||
.extent = included_range->start_point,
|
||||
};
|
||||
|
|
@ -69,7 +69,7 @@ void ts_lexer_goto_inside_loop(t_lexer *self, bool *found_included_range,
|
|||
|
||||
void ts_lexer_goto_after_loop(t_lexer *self, bool found_included_range)
|
||||
{
|
||||
TSRange *last_included_range;
|
||||
t_range *last_included_range;
|
||||
|
||||
if (found_included_range)
|
||||
{
|
||||
|
|
@ -78,19 +78,19 @@ void ts_lexer_goto_after_loop(t_lexer *self, bool found_included_range)
|
|||
+ self->chunk_size))
|
||||
ts_lexer__clear_chunk(self);
|
||||
self->lookahead_size = 0;
|
||||
self->data.lookahead = '\0';
|
||||
self->funcs.lookahead = '\0';
|
||||
}
|
||||
else
|
||||
{
|
||||
self->current_included_range_index = self->included_range_count;
|
||||
last_included_range = &self->included_ranges[self->included_range_count
|
||||
- 1];
|
||||
self->current_position = (Length){
|
||||
self->current_position = (t_length){
|
||||
.bytes = last_included_range->end_byte,
|
||||
.extent = last_included_range->end_point,
|
||||
};
|
||||
ts_lexer__clear_chunk(self);
|
||||
self->lookahead_size = 1;
|
||||
self->data.lookahead = '\0';
|
||||
self->funcs.lookahead = '\0';
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
|
||||
/* +#+#+#+#+#+ +#+ */
|
||||
/* Created: 2024/08/31 17:58:01 by maiboyer #+# #+# */
|
||||
/* Updated: 2024/08/31 18:25:16 by maiboyer ### ########.fr */
|
||||
/* Updated: 2024/09/19 16:59:58 by maiboyer ### ########.fr */
|
||||
/* */
|
||||
/* ************************************************************************** */
|
||||
|
||||
|
|
@ -15,27 +15,27 @@
|
|||
|
||||
#define BYTE_ORDER_MARK 0xFEFF
|
||||
|
||||
bool ts_lexer__eof(const TSLexer *_self);
|
||||
t_u32 ts_lexer__get_column(TSLexer *_self);
|
||||
void ts_lexer__advance(TSLexer *_self, bool skip);
|
||||
bool ts_lexer__eof(const t_lexer *_self);
|
||||
t_u32 ts_lexer__get_column(t_lexer *_self);
|
||||
void ts_lexer__advance(t_lexer *_self, bool skip);
|
||||
void ts_lexer__clear_chunk(t_lexer *self);
|
||||
void ts_lexer__get_chunk(t_lexer *self);
|
||||
void ts_lexer__get_lookahead(t_lexer *self);
|
||||
void ts_lexer__mark_end(TSLexer *_self);
|
||||
void ts_lexer__mark_end(t_lexer *_self);
|
||||
void ts_lexer_advance_to_end(t_lexer *self);
|
||||
void ts_lexer_goto(t_lexer *self, Length position);
|
||||
void ts_lexer_goto(t_lexer *self, t_length position);
|
||||
|
||||
void ts_lexer_init(t_lexer *self)
|
||||
{
|
||||
static TSRange default_range = {.start_point = {\
|
||||
static t_range default_range = {.start_point = {\
|
||||
.row = 0, .column = 0, }, .end_point = {.row = UINT32_MAX, \
|
||||
.column = UINT32_MAX, }, .start_byte = 0, .end_byte = UINT32_MAX};
|
||||
|
||||
*self = (t_lexer){
|
||||
.data = {
|
||||
.funcs = {
|
||||
.advance = ts_lexer__advance,
|
||||
.mark_end = ts_lexer__mark_end,
|
||||
.get_column = ts_lexer__get_column,
|
||||
.get_column = NULL, //ts_lexer__get_column,
|
||||
.eof = ts_lexer__eof,
|
||||
.lookahead = 0,
|
||||
.result_symbol = 0, },
|
||||
|
|
@ -49,14 +49,14 @@ void ts_lexer_init(t_lexer *self)
|
|||
};
|
||||
}
|
||||
|
||||
void ts_lexer_set_input(t_lexer *self, TSInput input)
|
||||
void ts_lexer_set_input(t_lexer *self, t_input input)
|
||||
{
|
||||
self->input = input;
|
||||
ts_lexer__clear_chunk(self);
|
||||
ts_lexer_goto(self, self->current_position);
|
||||
}
|
||||
|
||||
void ts_lexer_reset(t_lexer *self, Length position)
|
||||
void ts_lexer_reset(t_lexer *self, t_length position)
|
||||
{
|
||||
if (position.bytes != self->current_position.bytes)
|
||||
ts_lexer_goto(self, position);
|
||||
|
|
@ -66,24 +66,24 @@ void ts_lexer_start(t_lexer *self)
|
|||
{
|
||||
self->token_start_position = self->current_position;
|
||||
self->token_end_position = LENGTH_UNDEFINED;
|
||||
self->data.result_symbol = 0;
|
||||
self->funcs.result_symbol = 0;
|
||||
self->did_get_column = false;
|
||||
if (!ts_lexer__eof(&self->data))
|
||||
if (!ts_lexer__eof(self))
|
||||
{
|
||||
if (!self->chunk_size)
|
||||
ts_lexer__get_chunk(self);
|
||||
if (!self->lookahead_size)
|
||||
ts_lexer__get_lookahead(self);
|
||||
if (self->current_position.bytes == 0
|
||||
&& self->data.lookahead == BYTE_ORDER_MARK)
|
||||
ts_lexer__advance(&self->data, true);
|
||||
&& self->funcs.lookahead == BYTE_ORDER_MARK)
|
||||
ts_lexer__advance(self, true);
|
||||
}
|
||||
}
|
||||
|
||||
void ts_lexer_finish(t_lexer *self, t_u32 *lookahead_end_byte)
|
||||
{
|
||||
if (length_is_undefined(self->token_end_position))
|
||||
ts_lexer__mark_end(&self->data);
|
||||
ts_lexer__mark_end(self);
|
||||
(void)(lookahead_end_byte);
|
||||
if (self->token_end_position.bytes < self->token_start_position.bytes)
|
||||
self->token_start_position = self->token_end_position;
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
|
||||
/* +#+#+#+#+#+ +#+ */
|
||||
/* Created: 2024/08/31 18:09:03 by maiboyer #+# #+# */
|
||||
/* Updated: 2024/08/31 18:09:03 by maiboyer ### ########.fr */
|
||||
/* Updated: 2024/09/19 17:00:15 by maiboyer ### ########.fr */
|
||||
/* */
|
||||
/* ************************************************************************** */
|
||||
|
||||
|
|
@ -14,16 +14,16 @@
|
|||
#include "parser/input.h"
|
||||
#include "parser/lexer.h"
|
||||
|
||||
bool ts_lexer__eof(const TSLexer *_self);
|
||||
t_u32 ts_lexer__get_column(TSLexer *_self);
|
||||
void ts_lexer__advance(TSLexer *_self, bool skip);
|
||||
bool ts_lexer__eof(const t_lexer *_self);
|
||||
t_u32 ts_lexer__get_column(t_lexer *_self);
|
||||
void ts_lexer__advance(t_lexer *_self, bool skip);
|
||||
void ts_lexer__do_advance(t_lexer *self, bool skip);
|
||||
void ts_lexer__clear_chunk(t_lexer *self);
|
||||
void ts_lexer__get_chunk(t_lexer *self);
|
||||
void ts_lexer__get_lookahead(t_lexer *self);
|
||||
void ts_lexer__mark_end(TSLexer *_self);
|
||||
void ts_lexer__mark_end(t_lexer *_self);
|
||||
void ts_lexer_advance_to_end(t_lexer *self);
|
||||
void ts_lexer_goto(t_lexer *self, Length position);
|
||||
void ts_lexer_goto(t_lexer *self, t_length position);
|
||||
|
||||
void ts_lexer__get_lookahead(t_lexer *self)
|
||||
{
|
||||
|
|
@ -36,11 +36,11 @@ void ts_lexer__get_lookahead(t_lexer *self)
|
|||
if (size == 0)
|
||||
{
|
||||
self->lookahead_size = 1;
|
||||
self->data.lookahead = '\0';
|
||||
self->funcs.lookahead = '\0';
|
||||
return ;
|
||||
}
|
||||
chunk = (const t_u8 *)self->chunk + position_in_chunk;
|
||||
self->lookahead_size = ts_decode_ascii(chunk, size, &self->data.lookahead);
|
||||
if (self->data.lookahead == TS_DECODE_ERROR)
|
||||
self->lookahead_size = ts_decode_ascii(chunk, size, &self->funcs.lookahead);
|
||||
if (self->funcs.lookahead == TS_DECODE_ERROR)
|
||||
self->lookahead_size = 1;
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue