Skip to content

Strings::toAscii() fixed to correctly convert german umlauts (BC break) #240

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, 2020
Merged

Strings::toAscii() fixed to correctly convert german umlauts (BC break) #240

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 @@ -158,7 +158,7 @@ public static function toAscii(string $s): string
$s = self::pcre('preg_replace', ['#[^\x09\x0A\x0D\x20-\x7E\xA0-\x{2FF}\x{370}-\x{10FFFF}]#u', '', $s]);

// transliteration (by Transliterator and iconv) is not optimal, replace some characters directly
$s = strtr($s, ["\u{201E}" => '"', "\u{201C}" => '"', "\u{201D}" => '"', "\u{201A}" => "'", "\u{2018}" => "'", "\u{2019}" => "'", "\u{B0}" => '^', "\u{42F}" => 'Ya', "\u{44F}" => 'ya', "\u{42E}" => 'Yu', "\u{44E}" => 'yu']); // „ “ ” ‚ ‘ ’ ° Я я Ю ю
$s = strtr($s, ["\u{201E}" => '"', "\u{201C}" => '"', "\u{201D}" => '"', "\u{201A}" => "'", "\u{2018}" => "'", "\u{2019}" => "'", "\u{B0}" => '^', "\u{42F}" => 'Ya', "\u{44F}" => 'ya', "\u{42E}" => 'Yu', "\u{44E}" => 'yu', "\u{c4}" => 'Ae', "\u{d6}" => 'Oe', "\u{dc}" => 'Ue', "\u{1e9e}" => 'Ss', "\u{e4}" => 'ae', "\u{f6}" => 'oe', "\u{fc}" => 'ue', "\u{df}" => 'ss']); // „ “ ” ‚ ‘ ’ ° Я я Ю ю Ä Ö Ü ẞ ä ö ü ß
if ($iconv !== 'libiconv') {
$s = strtr($s, ["\u{AE}" => '(R)', "\u{A9}" => '(c)', "\u{2026}" => '...', "\u{AB}" => '<<', "\u{BB}" => '>>', "\u{A3}" => 'lb', "\u{A5}" => 'yen', "\u{B2}" => '^2', "\u{B3}" => '^3', "\u{B5}" => 'u', "\u{B9}" => '^1', "\u{BA}" => 'o', "\u{BF}" => '?', "\u{2CA}" => "'", "\u{2CD}" => '_', "\u{2DD}" => '"', "\u{1FEF}" => '', "\u{20AC}" => 'EUR', "\u{2122}" => 'TM', "\u{212E}" => 'e', "\u{2190}" => '<-', "\u{2191}" => '^', "\u{2192}" => '->', "\u{2193}" => 'V', "\u{2194}" => '<->']); // ® © … « » £ ¥ ² ³ µ ¹ º ¿ ˊ ˍ ˝ ` € ™ ℮ ← ↑ → ↓ ↔
}
Expand Down
3 changes: 2 additions & 1 deletion tests/Utils/Strings.toAscii().phpt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ use Tester\Assert;
require __DIR__ . '/../bootstrap.php';


Assert::same('ZLUTOUCKY KUN oooo--', Strings::toAscii("\u{17D}LU\u{164}OU\u{10C}K\u{DD} K\u{16E}\u{147} \u{F6}\u{151}\u{F4}o\x2d\u{2013}")); // ŽLUŤOUČKÝ KŮŇ öőôo
Assert::same('ZLUTOUCKY KUN oeooo--', Strings::toAscii("\u{17D}LU\u{164}OU\u{10C}K\u{DD} K\u{16E}\u{147} \u{F6}\u{151}\u{F4}o\x2d\u{2013}")); // ŽLUŤOUČKÝ KŮŇ öőôo
Assert::same('Zlutoucky kun', Strings::toAscii("Z\u{30C}lut\u{30C}ouc\u{30C}ky\u{301} ku\u{30A}n\u{30C}")); // Žluťoučký kůň with combining characters
Assert::same('Z `\'"^~?', Strings::toAscii("\u{17D} `'\"^~?"));
Assert::same('"""\'\'\'>><<^', Strings::toAscii("\u{201E}\u{201C}\u{201D}\u{201A}\u{2018}\u{2019}\u{BB}\u{AB}\u{B0}")); // „“”‚‘’»«°
Expand All @@ -31,3 +31,4 @@ if (class_exists('Transliterator') && \Transliterator::create('Any-Latin; Latin-


Assert::same('Ya ya Yu yu', Strings::toAscii("\u{42F} \u{44F} \u{42E} \u{44E}")); // Я я Ю ю
Assert::same('Ae Oe Ue Ss ae oe ue ss', Strings::toAscii("\u{c4} \u{d6} \u{dc} \u{1e9e} \u{e4} \u{f6} \u{fc} \u{df}")); // Ä Ö Ü ẞ ä ö ü ß
4 changes: 2 additions & 2 deletions tests/Utils/Strings.webalize().phpt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,8 @@ use Tester\Assert;
require __DIR__ . '/../bootstrap.php';


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!")); // &ŽLUŤOUČKÝ KŮŇ öőôo!
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('zlutoucky-kun-oeooo', 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!")); // &ŽLUŤOUČKÝ KŮŇ öőôo!
Assert::same('ZLUTOUCKY-KUN-oeooo', 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!
if (class_exists('Transliterator') && \Transliterator::create('Any-Latin; Latin-ASCII')) {
Assert::same('1-4-!', Strings::webalize("\u{BC} !", '!'));
}
Expand Down