8000 Strings: throw exception on malformed UTF-8 in webalize() and toAscii() by VasekPurchart · Pull Request #205 · nette/utils · GitHub
[go: up one dir, main page]
Skip to content

Strings: throw exception on malformed UTF-8 in webalize() and toAscii() #205

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
dg merged 1 commit into from
Dec 3, 2019
Merged

Strings: throw exception on malformed UTF-8 in webalize() and toAscii() #205

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
2 changes: 1 addition & 1 deletion src/Utils/Strings.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,7 +142,7 @@ public static function toAscii(string $s): string
$transliterator = \Transliterator::create('Any-Latin; Latin-ASCII');
}

$s = preg_replace('#[^\x09\x0A\x0D\x20-\x7E\xA0-\x{2FF}\x{370}-\x{10FFFF}]#u', '', $s);
$s = self::pcre('preg_replace', ['#[^\x09\x0A\x0D\x20-\x7E\xA0-\x{2FF}\x{370}-\x{10FFFF}]#u', '', $s]);
$s = strtr($s, '`\'"^~?', "\x01\x02\x03\x04\x05\x06");
$s = str_replace(
["\u{201E}", "\u{201C}", "\u{201D}", "\u{201A}", "\u{2018}", "\u{2019}", "\u{B0}"],
Expand Down
3 changes: 3 additions & 0 deletions tests/Utils/Strings.toAscii().phpt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,9 @@ Assert::same('', Strings::toAscii("\u{10000}")); // U+10000
Assert::same('', Strings::toAscii("\u{A4}")); // non-ASCII char
Assert::same('a b', Strings::toAscii("a\u{A0}b")); // non-breaking space
Assert::same('Tarikh', Strings::toAscii("Ta\u{2BE}rikh")); // Taʾrikh
Assert::exception(function () {
Strings::toAscii("0123456789\xFF");
}, Nette\Utils\RegexpException::class, null, PREG_BAD_UTF8_ERROR);

if (class_exists('Transliterator') && \Transliterator::create('Any-Latin; Latin-ASCII')) {
Assert::same('Athena->Moskva', Strings::toAscii("\u{391}\u{3B8}\u{3AE}\u{3BD}\u{3B1}\u{2192}\u{41C}\u{43E}\u{441}\u{43A}\u{432}\u{430}")); // Αθήνα→Москва
Expand Down
3 changes: 3 additions & 0 deletions tests/Utils/Strings.webalize().phpt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,3 +17,6 @@ Assert::same('zlutoucky-kun-oooo', Strings::webalize("&\u{17D}LU\u{164}OU\u{10C}
Assert::same('ZLUTOUCKY-KUN-oooo', Strings::webalize("&\u{17D}LU\u{164}OU\u{10C}K\u{DD} K\u{16E}\u{147} \u{F6}\u{151}\u{F4}o!", null, false)); // &ŽLUŤOUČKÝ KŮŇ öőôo!
Assert::same('1-4-!', Strings::webalize("\u{BC} !", '!'));
Assert::same('a-b', Strings::webalize("a\u{A0}b")); // non-breaking space
Assert::exception(function () {
Strings::toAscii("0123456789\xFF");
}, Nette\Utils\RegexpException::class, null, PREG_BAD_UTF8_ERROR);
0