Skip to content

gh-97973: Return all necessary information from the tokenizer #97984

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Oct 6, 2022
Merged

gh-97973: Return all necessary information from the tokenizer #97984

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
0a7d0f6
gh-97973: Return all necessary information from the tokenizer
lysnikolaou Oct 6, 2022
c2320ba
Pass pointers so that struct does not get copied
lysnikolaou Oct 6, 2022
dee3359
Merge branch 'main' into tokenizer-return-token-2
lysnikolaou Oct 6, 2022
b28afed
Remove news blurb for now
lysnikolaou Oct 6, 2022
1e52242
📜🤖 Added by blurb_it.
blurb-it[bot] Oct 6, 2022
0aea48d
Merge branch 'main' into tokenizer-return-token-2
lysnikolaou Oct 6, 2022
689c670
Add assertion
lysnikolaou Oct 6, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Pass pointers so that struct does not get copied
  • Loading branch information
@lysnikolaou
lysnikolaou committed Oct 6, 2022
commit c2320ba5672eaaad1463c8138ed94a07380a7aec
26 changes: 13 additions & 13 deletions Parser/pegen.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,9 +123,9 @@ growable_comment_array_deallocate(growable_comment_array *arr) {
}

static int
_get_keyword_or_name_type(Parser *p, struct token new_token)
_get_keyword_or_name_type(Parser *p, struct token *new_token)
{
int name_len = new_token.end_col_offset - new_token.col_offset;
int name_len = new_token->end_col_offset - new_token->col_offset;
assert(name_len > 0);

if (name_len >= p->n_keyword_lists ||
Expand All @@ -134,19 +134,19 @@ _get_keyword_or_name_type(Parser *p, struct token new_token)
return NAME;
}
for (KeywordToken *k = p->keywords[name_len]; k != NULL && k->type != -1; k++) {
if (strncmp(k->str, new_token.start, name_len) == 0) {
if (strncmp(k->str, new_token->start, name_len) == 0) {
return k->type;
}
}
return NAME;
}

static int
initialize_token(Parser *p, Token *parser_token, struct token new_token, int token_type) {
initialize_token(Parser *p, Token *parser_token, struct token *new_token, int token_type) {
assert(parser_token != NULL);

parser_token->type = (token_type == NAME) ? _get_keyword_or_name_type(p, new_token) : token_type;
parser_token->bytes = PyBytes_FromStringAndSize(new_token.start, new_token.end - new_token.start);
parser_token->bytes = PyBytes_FromStringAndSize(new_token->start, new_token->end - new_token->start);
if (parser_token->bytes == NULL) {
return -1;
}
Expand All @@ -155,13 +155,13 @@ initialize_token(Parser *p, Token *parser_token, struct token new_token, int tok
return -1;
}

parser_token->level = new_token.level;
parser_token->lineno = new_token.lineno;
parser_token->col_offset = p->tok->lineno == p->starting_lineno ? p->starting_col_offset + new_token.col_offset
: new_token.col_offset;
parser_token->end_lineno = new_token.end_lineno;
parser_token->end_col_offset = p->tok->lineno == p->starting_lineno ? p->starting_col_offset + new_token.end_col_offset
: new_token.end_col_offset;
parser_token->level = new_token->level;
parser_token->lineno = new_token->lineno;
parser_token->col_offset = p->tok->lineno == p->starting_lineno ? p->starting_col_offset + new_token->col_offset
: new_token->col_offset;
parser_token->end_lineno = new_token->end_lineno;
parser_token->end_col_offset = p->tok->lineno == p->starting_lineno ? p->starting_col_offset + new_token->end_col_offset
: new_token->end_col_offset;

p->fill += 1;

Expand Down Expand Up @@ -238,7 +238,7 @@ _PyPegen_fill_token(Parser *p)
}

Token *t = p->tokens[p->fill];
return initialize_token(p, t, new_token, type);
return initialize_token(p, t, &new_token, type);
}

#if defined(Py_DEBUG)
Expand Down