mirror of
https://github.com/zulip/zulip.git
synced 2025-10-30 11:33:51 +00:00
df50280c54
Under the unicodedata distributed with Python 3.6, some Emoji are classified as `Cn`, and not `So`: ``` $ unicode 1f929 --long U+1F929 GRINNING FACE WITH STAR EYES UTF-8: f0 9f a4 a9 UTF-16BE: d83edd29 Decimal: 🤩 Octal: \0374451 🤩 Category: So (Symbol, Other); East Asian width: W (wide) Unicode block: 1F900..1F9FF; Supplemental Symbols and Pictographs Bidi: ON (Other Neutrals) $ python3.6 -c 'import unicodedata; print(unicodedata.category("\U0001f929"))' Cn $ python3.7 -c 'import unicodedata; print(unicodedata.category("\U0001f929"))' So ``` Drop `Cn` from the list of excluded Unicode character classes, and replace it with an explicit list of the 66 non-characters, which are invariant. Co-authored-by: Shlok Patel <shlokcpatel2001@gmail.com>
53 lines
1.8 KiB
Python
53 lines
1.8 KiB
Python
import unicodedata
|
|
from typing import Optional
|
|
|
|
from django.utils.translation import gettext as _
|
|
|
|
from zerver.lib.exceptions import JsonableError
|
|
from zerver.models import Stream
|
|
|
|
# There are 66 Unicode non-characters; see
|
|
# https://www.unicode.org/faq/private_use.html#nonchar4
|
|
unicode_non_chars = [
|
|
chr(x)
|
|
for x in list(range(0xFDD0, 0xFDF0)) # FDD0 through FDEF, inclusive
|
|
+ list(range(0xFFFE, 0x110000, 0x10000)) # 0xFFFE, 0x1FFFE, ... 0x10FFFE inclusive
|
|
+ list(range(0xFFFF, 0x110000, 0x10000)) # 0xFFFF, 0x1FFFF, ... 0x10FFFF inclusive
|
|
]
|
|
|
|
|
|
def check_string_is_printable(var: str) -> Optional[int]:
|
|
# Return position (1-indexed!) of the character which is not
|
|
# printable, None if no such character is present.
|
|
for i in range(len(var)):
|
|
unicode_character = unicodedata.category(var[i])
|
|
if (unicode_character in ["Cc", "Cs"]) or var[i] in unicode_non_chars:
|
|
return i + 1
|
|
return None
|
|
|
|
|
|
def check_stream_name(stream_name: str) -> None:
|
|
if stream_name.strip() == "":
|
|
raise JsonableError(_("Stream name can't be empty!"))
|
|
|
|
if len(stream_name) > Stream.MAX_NAME_LENGTH:
|
|
raise JsonableError(
|
|
_("Stream name too long (limit: {} characters).").format(Stream.MAX_NAME_LENGTH)
|
|
)
|
|
for i in stream_name:
|
|
if ord(i) == 0:
|
|
raise JsonableError(
|
|
_("Stream name '{}' contains NULL (0x00) characters.").format(stream_name)
|
|
)
|
|
|
|
|
|
def check_stream_topic(topic: str) -> None:
|
|
if topic.strip() == "":
|
|
raise JsonableError(_("Topic can't be empty!"))
|
|
|
|
invalid_character_pos = check_string_is_printable(topic)
|
|
if invalid_character_pos is not None:
|
|
raise JsonableError(
|
|
_("Invalid character in topic, at position {}!").format(invalid_character_pos)
|
|
)
|