Skip to content
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.

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

Add a 'not in line' symbol to search #587

Merged
merged 1 commit into from
Feb 2, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
19 changes: 15 additions & 4 deletions hed/models/expression_parser.py
Original file line number Diff line number Diff line change
Expand Up @@ -7,9 +7,6 @@ def __init__(self, group, tag):
self.group = group
# todo: rename tag: children
if not isinstance(tag, list):
from hed import HedString
if isinstance(tag, HedString):
breakHere = 3
new_tags = [tag]
else:
new_tags = tag.copy()
Expand Down Expand Up @@ -68,6 +65,7 @@ class Token:
Wildcard = 10
ExactMatch = 11
ExactMatchEnd = 12
NotInLine = 13 # Not currently a token. In development and may become one.

def __init__(self, text):
tokens = {
Expand All @@ -86,6 +84,7 @@ def __init__(self, text):
"???": Token.Wildcard, # Any Group
"{": Token.ExactMatch, # Nothing else
"}": Token.ExactMatchEnd, # Nothing else
"@": Token.NotInLine
}
self.kind = tokens.get(text, Token.Tag)
self.text = text
Expand All @@ -105,6 +104,10 @@ def __init__(self, token, left=None, right=None):
self.right = right
self.token = token
self._match_mode = "/" in token.text
self._must_not_be_in_line = False
if token.text.startswith("@"):
self._must_not_be_in_line = True
token.text = token.text[1:]
if token.text.startswith('"') and token.text.endswith('"') and len(token.text) > 2:
self._match_mode = 1
token.text = token.text[1:-1]
Expand All @@ -129,6 +132,13 @@ def handle_expr(self, hed_group, exact=False):
else:
groups_found = hed_group.find_tags_with_term(self.token.text, recursive=True, include_groups=2)

if self._must_not_be_in_line:
# If we found this, and it cannot be in the line.
if groups_found:
groups_found = []
else:
groups_found = [(None, group) for group in hed_group.get_all_groups()]

# If we're checking for all groups, also need to add parents.
if exact:
all_found_groups = [search_result(group, tag) for tag, group in groups_found]
Expand Down Expand Up @@ -172,6 +182,7 @@ def handle_expr(self, hed_group, exact=False):
# finally simplify the list and remove duplicates.

return return_list

def __str__(self):
output_str = "("
if self.left:
Expand Down Expand Up @@ -398,7 +409,7 @@ def _parse(self, expression_string):
def _tokenize(self, expression_string):
grouping_re = r"\[\[|\[|\]\]|\]|}|{"
paren_re = r"\)|\(|~"
word_re = r"\?+|@|\band\b|\bor\b|,|[\"_\-a-zA-Z0-9/.^#\*]+"
word_re = r"\?+|\band\b|\bor\b|,|[\"_\-a-zA-Z0-9/.^#\*@]+"
re_string = fr"({grouping_re}|{paren_re}|{word_re})"
token_re = re.compile(re_string)

Expand Down
49 changes: 42 additions & 7 deletions tests/models/test_expression_parser.py
Original file line number Diff line number Diff line change
Expand Up @@ -651,18 +651,53 @@ def test_logical_negation(self):
hed_string = HedString("A, C")
self.assertEqual(bool(expression.search_hed_string(hed_string)), False)

def test_kay(self):
def test_not_in_line(self):
test_strings = {
"Event, (Event, Sensory-event)": True,
"A": True,
"B": False,
"C": True,
"A, B": False,
"A, C": True,
"B, C": False,
"A, B, C": False,
"D, A, B": False,
"A, B, (C)": False,
"(A, B, (C))": False,
"(A, B, (C)), D": False,
"(A, B, (C)), (D), E": False,
}
self.base_test("Event", test_strings)
self.base_test("@B", test_strings)

def test_not_in_line2(self):
test_strings = {
"Event, (Event, Sensory-event), Event": True,
"A": False,
"B": False,
"C": True,
"A, B": False,
"A, C": True,
"B, C": False,
"A, B, C": False,
"D, A, B": False,
"A, B, (C)": False,
"(A, B, (C))": False,
"(A, B, (C)), D": False,
"(A, B, (C)), (D), E": False,
}
self.base_test("Event and Sensory-event", test_strings)
self.base_test("@B and C", test_strings)

def test_not_in_line3(self):
test_strings = {
"Sensory-event, (Event, Sensory-event), Event": True,
"A": True,
"B": True,
"C": False,
"A, B": True,
"A, C": False,
"B, C": True,
"A, B, C": True,
"D, A, B": True,
"A, B, (C)": True,
"(A, B, (C))": True,
"(A, B, (C)), D": True,
"(A, B, (C)), (D), E": True,
}
self.base_test("[Sensory-event]", test_strings)
self.base_test("@C or B", test_strings)