Skip to content

Fix lookahead of soft keywords in the PEG parser #20436

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 1 commit into from
May 26, 2020
Merged

Fix lookahead of soft keywords in the PEG parser #20436

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
12 changes: 12 additions & 0 deletions Lib/test/test_peg_generator/test_c_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -432,3 +432,15 @@ def test_soft_keywords_parse(self) -> None:
self.check_input_strings_for_grammar(valid_cases, invalid_cases)
"""
self.run_test(grammar_source, test_source)

def test_soft_keywords_lookahead(self) -> None:
grammar_source = """
start: &"if" "if" expr '+' expr NEWLINE
expr: NAME
"""
test_source = """
valid_cases = ["if if + if"]
invalid_cases = ["if if"]
self.check_input_strings_for_grammar(valid_cases, invalid_cases)
"""
self.run_test(grammar_source, test_source)
9 changes: 9 additions & 0 deletions Parser/pegen/pegen.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -718,6 +718,15 @@ _PyPegen_lookahead_with_name(int positive, expr_ty (func)(Parser *), Parser *p)
return (res != NULL) == positive;
}

int
_PyPegen_lookahead_with_string(int positive, expr_ty (func)(Parser *, const char*), Parser *p, const char* arg)
{
int mark = p->mark;
void *res = func(p, arg);
p->mark = mark;
return (res != NULL) == positive;
}

int
_PyPegen_lookahead_with_int(int positive, Token *(func)(Parser *, int), Parser *p, int arg)
{
Expand Down
1 change: 1 addition & 0 deletions Parser/pegen/pegen.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,6 +119,7 @@ int _PyPegen_is_memoized(Parser *p, int type, void *pres);

int _PyPegen_lookahead_with_name(int, expr_ty (func)(Parser *), Parser *);
int _PyPegen_lookahead_with_int(int, Token *(func)(Parser *, int), Parser *, int);
int _PyPegen_lookahead_with_string(int , expr_ty (func)(Parser *, const char*), Parser *, const char*);
int _PyPegen_lookahead(int, void *(func)(Parser *), Parser *);

Token *_PyPegen_expect_token(Parser *p, int type);
Expand Down
11 changes: 9 additions & 2 deletions Tools/peg_generator/pegen/c_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,8 @@ class NodeTypes(Enum):
STRING_TOKEN = 2
GENERIC_TOKEN = 3
KEYWORD = 4
CUT_OPERATOR = 5
SOFT_KEYWORD = 5
CUT_OPERATOR = 6


BASE_NODETYPES = {
Expand Down Expand Up @@ -123,7 +124,7 @@ def soft_keyword_helper(self, value: str) -> FunctionCall:
function="_PyPegen_expect_soft_keyword",
arguments=["p", value],
return_type="expr_ty",
nodetype=NodeTypes.NAME_TOKEN,
nodetype=NodeTypes.SOFT_KEYWORD,
comment=f"soft_keyword='{value}'",
)

Expand Down Expand Up @@ -217,6 +218,12 @@ def lookahead_call_helper(self, node: Lookahead, positive: int) -> FunctionCall:
arguments=[positive, call.function, *call.arguments],
return_type="int",
)
elif call.nodetype == NodeTypes.SOFT_KEYWORD:
return FunctionCall(
function=f"_PyPegen_lookahead_with_string",
arguments=[positive, call.function, *call.arguments],
return_type="int",
)
elif call.nodetype in {NodeTypes.GENERIC_TOKEN, NodeTypes.KEYWORD}:
return FunctionCall(
function=f"_PyPegen_lookahead_with_int",
Expand Down