diff options
Diffstat (limited to 'vendor/voku')
| -rw-r--r-- | vendor/voku/portable-ascii/.whitesource | 12 | ||||
| -rw-r--r-- | vendor/voku/portable-ascii/CHANGELOG.md | 14 | ||||
| -rw-r--r-- | vendor/voku/portable-ascii/README.md | 16 | ||||
| -rw-r--r-- | vendor/voku/portable-ascii/build/docs/base.md | 4 | ||||
| -rw-r--r-- | vendor/voku/portable-ascii/src/voku/helper/ASCII.php | 92 |
5 files changed, 112 insertions, 26 deletions
diff --git a/vendor/voku/portable-ascii/.whitesource b/vendor/voku/portable-ascii/.whitesource new file mode 100644 index 000000000..55b922e8c --- /dev/null +++ b/vendor/voku/portable-ascii/.whitesource @@ -0,0 +1,12 @@ +{ + "scanSettings": { + "baseBranches": [] + }, + "checkRunSettings": { + "vulnerableCheckRunConclusionLevel": "failure", + "displayMode": "diff" + }, + "issueSettings": { + "minSeverityLevel": "LOW" + } +}
\ No newline at end of file diff --git a/vendor/voku/portable-ascii/CHANGELOG.md b/vendor/voku/portable-ascii/CHANGELOG.md index 6e5357d08..04b64acdd 100644 --- a/vendor/voku/portable-ascii/CHANGELOG.md +++ b/vendor/voku/portable-ascii/CHANGELOG.md @@ -1,5 +1,19 @@ # Changelog +### 1.6.1 (2021-01-24) + +- revert: prefer "Russian - Passport (2013), ICAO" instead of "Russian - GOST 7.79-2000(B)" +- revert: fix "Ukrainian" char-mapping (thanks to @Andr1yk0) +- revert: fix "Persian" char-mapping (thanks to @frost-cyber) + +### 1.6.0 (2021-01-24) + +- prefer "Russian - Passport (2013), ICAO" instead of "Russian - GOST 7.79-2000(B)" +- fix "Ukrainian" char-mapping (thanks to @Andr1yk0) +- fix "Persian" char-mapping (thanks to @frost-cyber) +- fix "ASCII::normalize_whitespace()" -> "CARRIAGE RETURN" is more like "<br>" and no "\n" +- add "ASCII::to_ascii_remap()" -> this method will return broken characters and is only for special cases + ### 1.5.6 (2020-11-12) - "ASCII::normalize_whitespace()" -> can now also remove "control characters" if needed v2 diff --git a/vendor/voku/portable-ascii/README.md b/vendor/voku/portable-ascii/README.md index 9dd7cecef..929c21e29 100644 --- a/vendor/voku/portable-ascii/README.md +++ b/vendor/voku/portable-ascii/README.md @@ -1,7 +1,7 @@ [//]: # (AUTO-GENERATED BY "PHP README Helper": base file -> docs/base.md) -[](https://travis-ci.com/voku/portable-ascii) +[](https://github.com/voku/portable-ascii/actions) [](https://ci.appveyor.com/project/voku/portable-ascii/branch/master) -[](https://coveralls.io/github/voku/portable-ascii?branch=master) +[](https://codecov.io/github/voku/portable-ascii?branch=master) [](https://www.codacy.com/app/voku/portable-ascii) [](https://packagist.org/packages/voku/portable-ascii) [](https://packagist.org/packages/voku/portable-ascii) @@ -96,8 +96,8 @@ The API from the "ASCII"-Class is written as small static methods. </td><td><a href="#getalllanguages-string">getAllLanguages</a> </td><td><a href="#is_asciistring-str-bool">is_ascii</a> </td><td><a href="#normalize_mswordstring-str-string">normalize_msword</a> -</td></tr><tr><td><a href="#normalize_whitespacestring-str-bool-keepnonbreakingspace-bool-keepbidiunicodecontrols-bool-replaceseparatorswithnewline-string">normalize_whitespace</a> -</td><td><a href="#remove_invisible_charactersstring-str-bool-url_encoded-string-replacement-bool-keep_control_characters-string">remove_invisible_characters</a> +</td></tr><tr><td><a href="#normalize_whitespacestring-str-bool-keepnonbreakingspace-bool-keepbidiunicodecontrols-bool-normalize_control_characters-string">normalize_whitespace</a> +</td><td><a href="#remove_invisible_charactersstring-str-bool-url_encoded-string-replacement-bool-keep_basic_control_characters-string">remove_invisible_characters</a> </td><td><a href="#to_asciistring-str-string-language-bool-remove_unsupported_chars-bool-replace_extra_symbols-bool-use_transliterate-boolnull-replace_single_chars_only-string">to_ascii</a> </td><td><a href="#to_filenamestring-str-bool-use_transliterate-string-fallback_char-string">to_filename</a> </td></tr><tr><td><a href="#to_slugifystring-str-string-separator-string-language-string-replacements-bool-replace_extra_symbols-bool-use_str_to_lower-bool-use_transliterate-string">to_slugify</a> @@ -254,7 +254,7 @@ ASCII::normalize_msword('„Abcdef…”'); // '"Abcdef..."' -------- -#### normalize_whitespace(string $str, bool $keepNonBreakingSpace, bool $keepBidiUnicodeControls, bool $replaceSeparatorsWithNewline): string +#### normalize_whitespace(string $str, bool $keepNonBreakingSpace, bool $keepBidiUnicodeControls, bool $normalize_control_characters): string <a href="#voku-php-readme-class-methods">↑</a> Normalize the whitespace. @@ -267,14 +267,14 @@ ASCII::normalize_whitespace("abc-\xc2\xa0-öäü-\xe2\x80\xaf-\xE2\x80\xAC", tru - `bool $keepNonBreakingSpace [optional] <p>Set to true, to keep non-breaking-spaces.</p>` - `bool $keepBidiUnicodeControls [optional] <p>Set to true, to keep non-printable (for the web) bidirectional text chars.</p>` -- `bool $replaceSeparatorsWithNewline [optional] <p>Set to true, to convert LINE and PARAGRAPH SEPARATOR with "\n".</p>` +- `bool $normalize_control_characters [optional] <p>Set to true, to convert e.g. LINE-, PARAGRAPH-SEPARATOR with "\n" and LINE TABULATION with "\t".</p>` **Return:** - `string <p>A string with normalized whitespace.</p>` -------- -#### remove_invisible_characters(string $str, bool $url_encoded, string $replacement, bool $keep_control_characters): string +#### remove_invisible_characters(string $str, bool $url_encoded, string $replacement, bool $keep_basic_control_characters): string <a href="#voku-php-readme-class-methods">↑</a> Remove invisible characters from a string. @@ -286,7 +286,7 @@ copy&past from https://github.com/bcit-ci/CodeIgniter/blob/develop/system/core/C - `string $str` - `bool $url_encoded` - `string $replacement` -- `bool $keep_control_characters` +- `bool $keep_basic_control_characters` **Return:** - `string` diff --git a/vendor/voku/portable-ascii/build/docs/base.md b/vendor/voku/portable-ascii/build/docs/base.md index e21e73137..ca949d8b6 100644 --- a/vendor/voku/portable-ascii/build/docs/base.md +++ b/vendor/voku/portable-ascii/build/docs/base.md @@ -1,6 +1,6 @@ -[](https://travis-ci.com/voku/portable-ascii) +[](https://github.com/voku/portable-ascii/actions) [](https://ci.appveyor.com/project/voku/portable-ascii/branch/master) -[](https://coveralls.io/github/voku/portable-ascii?branch=master) +[](https://codecov.io/github/voku/portable-ascii?branch=master) [](https://www.codacy.com/app/voku/portable-ascii) [](https://packagist.org/packages/voku/portable-ascii) [](https://packagist.org/packages/voku/portable-ascii) diff --git a/vendor/voku/portable-ascii/src/voku/helper/ASCII.php b/vendor/voku/portable-ascii/src/voku/helper/ASCII.php index d4ec32ab1..aa676abda 100644 --- a/vendor/voku/portable-ascii/src/voku/helper/ASCII.php +++ b/vendor/voku/portable-ascii/src/voku/helper/ASCII.php @@ -200,7 +200,7 @@ final class ASCII * * @return string[] * - * @psalm-return array<string, string> + * @phpstan-return array<string, string> */ public static function getAllLanguages(): array { @@ -238,7 +238,7 @@ final class ASCII * * @return array * - * @psalm-return array<string, array<string , string>> + * @phpstan-return array<string, array<string , string>> */ public static function charsArray(bool $replace_extra_symbols = false): array { @@ -268,7 +268,7 @@ final class ASCII * @return array * <p>An array of replacements.</p> * - * @psalm-return array<string, array<int, string>> + * @phpstan-return array<string, array<int, string>> */ public static function charsArrayWithMultiLanguageValues(bool $replace_extra_symbols = false): array { @@ -300,10 +300,7 @@ final class ASCII $CHARS_ARRAY[$cacheKey] = $return; - /** @noinspection PhpSillyAssignmentInspection - hack for phpstan */ - /** @var array<string, array<int, string>> $return */ - $return = $return; - + /** @var array<string, array<int, string>> $return - hack for phpstan */ return $return; } @@ -332,7 +329,7 @@ final class ASCII * @return array * <p>An array of replacements.</p> * - * @psalm-return array{orig: string[], replace: string[]}|array<string, string> + * @phpstan-return array{orig: string[], replace: string[]}|array<string, string> */ public static function charsArrayWithOneLanguage( string $language = self::ENGLISH_LANGUAGE_CODE, @@ -428,7 +425,7 @@ final class ASCII * @return array * <p>An array of replacements.</p> * - * @psalm-return array{orig: string[], replace: string[]}|array<string, string> + * @phpstan-return array{orig: string[], replace: string[]}|array<string, string> */ public static function charsArrayWithSingleLanguageValues( bool $replace_extra_symbols = false, @@ -616,7 +613,7 @@ final class ASCII * @param bool $keepNonBreakingSpace [optional] <p>Set to true, to keep non-breaking-spaces.</p> * @param bool $keepBidiUnicodeControls [optional] <p>Set to true, to keep non-printable (for the web) * bidirectional text chars.</p> - * @param bool $normalize_control_characters [optional] <p>Set to true, to convert LINE-, PARAGRAPH-SEPARATOR with "\n" and LINE TABULATION with "\t".</p> + * @param bool $normalize_control_characters [optional] <p>Set to true, to convert e.g. LINE-, PARAGRAPH-SEPARATOR with "\n" and LINE TABULATION with "\t".</p> * * @psalm-pure * @@ -645,16 +642,14 @@ final class ASCII "\x0d\x0c", // 'END OF LINE' "\xe2\x80\xa8", // 'LINE SEPARATOR' "\xe2\x80\xa9", // 'PARAGRAPH SEPARATOR' - "\x0c", // 'FORM FEED' - "\x0d", // 'CARRIAGE RETURN' - "\x0b", // 'VERTICAL TAB' + "\x0c", // 'FORM FEED' // "\f" + "\x0b", // 'VERTICAL TAB' // "\v" ], [ "\n", "\n", "\n", "\n", - "\n", "\t", ], $str @@ -738,6 +733,71 @@ final class ASCII } /** + * WARNING: This method will return broken characters and is only for special cases. + * + * Convert two UTF-8 encoded string to a single-byte strings suitable for + * functions that need the same string length after the conversion. + * + * The function simply uses (and updates) a tailored dynamic encoding + * (in/out map parameter) where non-ascii characters are remapped to + * the range [128-255] in order of appearance. + * + * @param string $str1 + * @param string $str2 + * + * @return string[] + * + * @phpstan-return array{0: string, 1: string} + */ + public static function to_ascii_remap(string $str1, string $str2): array + { + $charMap = []; + $str1 = self::to_ascii_remap_intern($str1, $charMap); + $str2 = self::to_ascii_remap_intern($str2, $charMap); + + return [$str1, $str2]; + } + + /** + * WARNING: This method will return broken characters and is only for special cases. + * + * Convert a UTF-8 encoded string to a single-byte string suitable for + * functions that need the same string length after the conversion. + * + * The function simply uses (and updates) a tailored dynamic encoding + * (in/out map parameter) where non-ascii characters are remapped to + * the range [128-255] in order of appearance. + * + * Thus, it supports up to 128 different multibyte code points max over + * the whole set of strings sharing this encoding. + * + * Source: https://github.com/KEINOS/mb_levenshtein + * + * @param string $str UTF-8 string to be converted to extended ASCII. + * @return string Mapped borken string. + */ + private static function to_ascii_remap_intern(string $str, array &$map): string + { + // find all utf-8 characters + $matches = []; + if (!\preg_match_all('/[\xC0-\xF7][\x80-\xBF]+/', $str, $matches)) { + return $str; // plain ascii string + } + + // update the encoding map with the characters not already met + $mapCount = \count($map); + foreach ($matches[0] as $mbc) { + if (!isset($map[$mbc])) { + $map[$mbc] = \chr(128 + $mapCount); + $mapCount++; + } + } + + // finally remap non-ascii characters + return \strtr($str, $map); + } + + /** * Returns an ASCII version of the string. A set of non-ASCII characters are * replaced with their closest ASCII counterparts, and the rest are removed * by default. The language or locale of the source string can be supplied @@ -807,7 +867,7 @@ final class ASCII $EXTRA_SYMBOLS_CACHE === null ) { $EXTRA_SYMBOLS_CACHE = []; - foreach (self::$ASCII_EXTRAS ?? [] as $extrasLanguageTmp => $extrasDataTmp) { + foreach (self::$ASCII_EXTRAS ?? [] as $extrasDataTmp) { foreach ($extrasDataTmp as $extrasDataKeyTmp => $extrasDataValueTmp) { $EXTRA_SYMBOLS_CACHE[$extrasDataKeyTmp] = $extrasDataKeyTmp; } @@ -933,7 +993,7 @@ final class ASCII } } - foreach ($matches[0] as $keyTmp => $char) { + foreach ($matches[0] as $char) { if ( !isset($charDone[$char]) && |