traxys/tree-sitter
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix parse error when reusing a node at the end of an included range

Browse source
This commit is contained in:
Max Brunsfeld 2022-11-11 16:34:57 -08:00
parent 618146260e
commit d07f864815
2 changed files with 46 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

47
lib/src/lexer.c
View file

@ -104,13 +104,16 @@ static void ts_lexer__get_lookahead(Lexer *self) {
static void ts_lexer_goto(Lexer *self, Length position) {
self->current_position = position;
bool found_included_range = false;
// Move to the first valid position at or after the given position.
bool found_included_range = false;
for (unsigned i = 0; i < self->included_range_count; i++) {
TSRange *included_range = &self->included_ranges[i];
if (included_range->end_byte > position.bytes) {
if (included_range->start_byte >= position.bytes) {
if (
included_range->end_byte > self->current_position.bytes &&
included_range->end_byte > included_range->start_byte
) {
if (included_range->start_byte >= self->current_position.bytes) {
self->current_position = (Length) {
.bytes = included_range->start_byte,
.extent = included_range->start_point,
@ -127,8 +130,8 @@ static void ts_lexer_goto(Lexer *self, Length position) {
// If the current position is outside of the current chunk of text,
// then clear out the current chunk of text.
if (self->chunk && (
position.bytes < self->chunk_start ||
position.bytes >= self->chunk_start + self->chunk_size
self->current_position.bytes < self->chunk_start ||
self->current_position.bytes >= self->chunk_start + self->chunk_size
)) {
ts_lexer__clear_chunk(self);
}
@ -164,27 +167,31 @@ static void ts_lexer__do_advance(Lexer *self, bool skip) {
}
}
const TSRange *current_range = NULL;
if (self->current_included_range_index < self->included_range_count) {
current_range = &self->included_ranges[self->current_included_range_index];
if (self->current_position.bytes == current_range->end_byte) {
self->current_included_range_index++;
if (self->current_included_range_index < self->included_range_count) {
current_range++;
self->current_position = (Length) {
current_range->start_byte,
current_range->start_point,
};
} else {
current_range = NULL;
}
const TSRange *current_range = &self->included_ranges[self->current_included_range_index];
while (
self->current_position.bytes >= current_range->end_byte ||
current_range->end_byte == current_range->start_byte
) {
self->current_included_range_index++;
if (self->current_included_range_index < self->included_range_count) {
current_range++;
self->current_position = (Length) {
current_range->start_byte,
current_range->start_point,
};
} else {
current_range = NULL;
break;
}
}
if (skip) self->token_start_position = self->current_position;
if (current_range) {
if (self->current_position.bytes >= self->chunk_start + self->chunk_size) {
if (
self->current_position.bytes < self->chunk_start ||
self->current_position.bytes >= self->chunk_start + self->chunk_size
) {
ts_lexer__get_chunk(self);
}
ts_lexer__get_lookahead(self);