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.

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

Fix issues with long strings #30

Open
wants to merge 6 commits into
base: master
Choose a base branch
from
Open

Fix issues with long strings #30

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d73fe9a
added ascii filter, minor code cleanup
Jul 1, 2021
07d999d
minor changes
Jul 1, 2021
f998905
simplified conditional
Jul 5, 2021
befb6cf
fix condition
Jul 5, 2021
c725872
fix condition
Jul 5, 2021
c1e4ea7
simplified expression
Jul 5, 2021
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
13 changes: 6 additions & 7 deletions confusables/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,11 @@
from itertools import product

from .config import CONFUSABLE_MAPPING_PATH, NON_NORMAL_ASCII_CHARS
from .utils import is_ascii


# read confusable mappings from file, build 2-way map of the pairs
with open(os.path.join(os.path.dirname(__file__), CONFUSABLE_MAPPING_PATH), "r") as mappings:
CONFUSABLE_MAP = json.loads(mappings.readline())
CONFUSABLE_MAP = json.load(mappings)


def is_confusable(str1, str2):
Expand Down Expand Up @@ -52,20 +51,20 @@ def confusable_regex(string, include_character_padding=False):
return regex

def normalize(string, prioritize_alpha=False):
normal_forms = set([""])
normal_forms = {""}
for char in string:
normalized_chars = []
confusable_chars = confusable_characters(char)
if not is_ascii(char) or not char.isalpha():
if not (char.isascii() and char.isalnum()):
for confusable in confusable_chars:
if prioritize_alpha:
if ((char.isalpha() and confusable.isalpha() and is_ascii(confusable)) or (not char.isalpha() and is_ascii(confusable))) and confusable not in NON_NORMAL_ASCII_CHARS:
if ((char.isalpha() and confusable.isalpha() and confusable.isascii()) or (not char.isalpha() and confusable.isascii())) and confusable not in NON_NORMAL_ASCII_CHARS:
normal = confusable
if len(confusable) > 1:
normal = normalize(confusable)[0]
normalized_chars.append(normal)
else:
if is_ascii(confusable) and confusable not in NON_NORMAL_ASCII_CHARS:
if confusable.isascii() and confusable not in NON_NORMAL_ASCII_CHARS:
normal = confusable
if len(confusable) > 1:
normal = normalize(confusable)[0]
Expand All @@ -75,5 +74,5 @@ def normalize(string, prioritize_alpha=False):

if len(normalized_chars) == 0:
normalized_chars = [char]
normal_forms = set([x[0]+x[1].lower() for x in list(product(normal_forms, normalized_chars))])
normal_forms = {x[0]+x[1].lower() for x in list(product(normal_forms, normalized_chars))}
return sorted(list(normal_forms))
43 changes: 20 additions & 23 deletions confusables/parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ def _get_accented_characters(char):
def _get_confusable_chars(character, unicode_confusable_map, depth):
mapped_chars = unicode_confusable_map[character]

group = set([character])
group = {character}
if depth <= MAX_SIMILARITY_DEPTH:
for mapped_char in mapped_chars:
group.update(_get_confusable_chars(mapped_char, unicode_confusable_map, depth + 1))
Expand All @@ -40,30 +40,28 @@ def parse_new_mapping_file():
if unicode_confusable_map.get(str1):
unicode_confusable_map[str1].add(str2)
else:
unicode_confusable_map[str1] = set([str2])
unicode_confusable_map[str1] = {str2}

if unicode_confusable_map.get(str2):
unicode_confusable_map[str2].add(str1)
else:
unicode_confusable_map[str2] = set([str1])
unicode_confusable_map[str2] = {str1}

if len(str1) == 1:
case_change = str1.lower() if str1.isupper() else str1.upper()
if case_change != str1:
unicode_confusable_map[str1].add(case_change)
if unicode_confusable_map.get(case_change) is not None:
unicode_confusable_map[case_change].add(str1)
else:
unicode_confusable_map[case_change] = set([str1])
case_change = str1.swapcase()
unicode_confusable_map[str1].add(case_change)
if unicode_confusable_map.get(case_change) is not None:
unicode_confusable_map[case_change].add(str1)
else:
unicode_confusable_map[case_change] = {str1}

if len(str2) == 1:
case_change = str2.lower() if str2.isupper() else str2.upper()
if case_change != str2:
unicode_confusable_map[str2].add(case_change)
if unicode_confusable_map.get(case_change) is not None:
unicode_confusable_map[case_change].add(str2)
else:
unicode_confusable_map[case_change] = set([str2])
case_change = str2.swapcase()
unicode_confusable_map[str2].add(case_change)
if unicode_confusable_map.get(case_change) is not None:
unicode_confusable_map[case_change].add(str2)
else:
unicode_confusable_map[case_change] = {str2}

for char in string.ascii_lowercase:
accented = _get_accented_characters(char)
Expand All @@ -72,7 +70,7 @@ def parse_new_mapping_file():
if unicode_confusable_map.get(accent):
unicode_confusable_map[accent].add(char)
else:
unicode_confusable_map[accent] = set([char])
unicode_confusable_map[accent] = {char}

for char in string.ascii_uppercase:
accented = _get_accented_characters(char)
Expand All @@ -81,17 +79,16 @@ def parse_new_mapping_file():
if unicode_confusable_map.get(accent):
unicode_confusable_map[accent].add(char)
else:
unicode_confusable_map[accent] = set([char])
unicode_confusable_map[accent] = {char}

CONFUSABLE_MAP = {}
characters_to_map = list(unicode_confusable_map.keys())
for character in list(unicode_confusable_map.keys()):
for character in unicode_confusable_map.keys():
char_group = _get_confusable_chars(character, unicode_confusable_map, 0)

CONFUSABLE_MAP[character] = list(char_group)

mapping_file = open(os.path.join(os.path.dirname(__file__), CONFUSABLE_MAPPING_PATH), "w")
mapping_file.write(json.dumps(CONFUSABLE_MAP))
json.dump(CONFUSABLE_MAP,mapping_file)
mapping_file.close()

parse_new_mapping_file()
parse_new_mapping_file()
5 changes: 0 additions & 5 deletions confusables/utils.py
View file
Open in desktop

This file was deleted.