case 'xx-uca-et':
return new CollationEt;
default:
- $match = array();
+ $match = [];
if ( preg_match( '/^uca-([a-z@=-]+)$/', $collationName, $match ) ) {
return new IcuCollation( $match[1] );
}
# Provide a mechanism for extensions to hook in.
$collationObject = null;
- Hooks::run( 'Collation::factory', array( $collationName, &$collationObject ) );
+ Hooks::run( 'Collation::factory', [ $collationName, &$collationObject ] );
if ( $collationObject instanceof Collation ) {
return $collationObject;
* is pretty useless for sorting Chinese text anyway. Japanese and Korean
* blocks are not included here, because they are smaller and more useful.
*/
- private static $cjkBlocks = array(
- array( 0x2E80, 0x2EFF ), // CJK Radicals Supplement
- array( 0x2F00, 0x2FDF ), // Kangxi Radicals
- array( 0x2FF0, 0x2FFF ), // Ideographic Description Characters
- array( 0x3000, 0x303F ), // CJK Symbols and Punctuation
- array( 0x31C0, 0x31EF ), // CJK Strokes
- array( 0x3200, 0x32FF ), // Enclosed CJK Letters and Months
- array( 0x3300, 0x33FF ), // CJK Compatibility
- array( 0x3400, 0x4DBF ), // CJK Unified Ideographs Extension A
- array( 0x4E00, 0x9FFF ), // CJK Unified Ideographs
- array( 0xF900, 0xFAFF ), // CJK Compatibility Ideographs
- array( 0xFE30, 0xFE4F ), // CJK Compatibility Forms
- array( 0x20000, 0x2A6DF ), // CJK Unified Ideographs Extension B
- array( 0x2A700, 0x2B73F ), // CJK Unified Ideographs Extension C
- array( 0x2B740, 0x2B81F ), // CJK Unified Ideographs Extension D
- array( 0x2F800, 0x2FA1F ), // CJK Compatibility Ideographs Supplement
- );
+ private static $cjkBlocks = [
+ [ 0x2E80, 0x2EFF ], // CJK Radicals Supplement
+ [ 0x2F00, 0x2FDF ], // Kangxi Radicals
+ [ 0x2FF0, 0x2FFF ], // Ideographic Description Characters
+ [ 0x3000, 0x303F ], // CJK Symbols and Punctuation
+ [ 0x31C0, 0x31EF ], // CJK Strokes
+ [ 0x3200, 0x32FF ], // Enclosed CJK Letters and Months
+ [ 0x3300, 0x33FF ], // CJK Compatibility
+ [ 0x3400, 0x4DBF ], // CJK Unified Ideographs Extension A
+ [ 0x4E00, 0x9FFF ], // CJK Unified Ideographs
+ [ 0xF900, 0xFAFF ], // CJK Compatibility Ideographs
+ [ 0xFE30, 0xFE4F ], // CJK Compatibility Forms
+ [ 0x20000, 0x2A6DF ], // CJK Unified Ideographs Extension B
+ [ 0x2A700, 0x2B73F ], // CJK Unified Ideographs Extension C
+ [ 0x2B740, 0x2B81F ], // CJK Unified Ideographs Extension D
+ [ 0x2F800, 0x2FA1F ], // CJK Compatibility Ideographs Supplement
+ ];
/**
* Additional characters (or character groups) to be considered separate
* Empty arrays are intended; this signifies that the data for the language is
* available and that there are, in fact, no additional letters to consider.
*/
- private static $tailoringFirstLetters = array(
+ private static $tailoringFirstLetters = [
// Verified by native speakers
- 'be' => array( "Ё" ),
- 'be-tarask' => array( "Ё" ),
- 'cy' => array( "Ch", "Dd", "Ff", "Ng", "Ll", "Ph", "Rh", "Th" ),
- 'en' => array(),
- 'fa' => array( "آ", "ء", "ه" ),
- 'fi' => array( "Å", "Ä", "Ö" ),
- 'fr' => array(),
- 'hu' => array( "Cs", "Dz", "Dzs", "Gy", "Ly", "Ny", "Ö", "Sz", "Ty", "Ü", "Zs" ),
- 'is' => array( "Á", "Ð", "É", "Í", "Ó", "Ú", "Ý", "Þ", "Æ", "Ö", "Å" ),
- 'it' => array(),
- 'lv' => array( "Č", "Ģ", "Ķ", "Ļ", "Ņ", "Š", "Ž" ),
- 'pl' => array( "Ą", "Ć", "Ę", "Ł", "Ń", "Ó", "Ś", "Ź", "Ż" ),
- 'pt' => array(),
- 'ru' => array(),
- 'sv' => array( "Å", "Ä", "Ö" ),
- 'sv@collation=standard' => array( "Å", "Ä", "Ö" ),
- 'uk' => array( "Ґ", "Ь" ),
- 'vi' => array( "Ă", "Â", "Đ", "Ê", "Ô", "Ơ", "Ư" ),
+ 'be' => [ "Ё" ],
+ 'be-tarask' => [ "Ё" ],
+ 'cy' => [ "Ch", "Dd", "Ff", "Ng", "Ll", "Ph", "Rh", "Th" ],
+ 'en' => [],
+ 'fa' => [ "آ", "ء", "ه" ],
+ 'fi' => [ "Å", "Ä", "Ö" ],
+ 'fr' => [],
+ 'hu' => [ "Cs", "Dz", "Dzs", "Gy", "Ly", "Ny", "Ö", "Sz", "Ty", "Ü", "Zs" ],
+ 'is' => [ "Á", "Ð", "É", "Í", "Ó", "Ú", "Ý", "Þ", "Æ", "Ö", "Å" ],
+ 'it' => [],
+ 'lv' => [ "Č", "Ģ", "Ķ", "Ļ", "Ņ", "Š", "Ž" ],
+ 'pl' => [ "Ą", "Ć", "Ę", "Ł", "Ń", "Ó", "Ś", "Ź", "Ż" ],
+ 'pt' => [],
+ 'ru' => [],
+ 'sv' => [ "Å", "Ä", "Ö" ],
+ 'sv@collation=standard' => [ "Å", "Ä", "Ö" ],
+ 'uk' => [ "Ґ", "Ь" ],
+ 'vi' => [ "Ă", "Â", "Đ", "Ê", "Ô", "Ơ", "Ư" ],
// Not verified, but likely correct
- 'af' => array(),
- 'ast' => array( "Ch", "Ll", "Ñ" ),
- 'az' => array( "Ç", "Ə", "Ğ", "İ", "Ö", "Ş", "Ü" ),
- 'bg' => array(),
- 'br' => array( "Ch", "C'h" ),
- 'bs' => array( "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ),
- 'ca' => array(),
- 'co' => array(),
- 'cs' => array( "Č", "Ch", "Ř", "Š", "Ž" ),
- 'da' => array( "Æ", "Ø", "Å" ),
- 'de' => array(),
- 'dsb' => array( "Č", "Ć", "Dź", "Ě", "Ch", "Ł", "Ń", "Ŕ", "Š", "Ś", "Ž", "Ź" ),
- 'el' => array(),
- 'eo' => array( "Ĉ", "Ĝ", "Ĥ", "Ĵ", "Ŝ", "Ŭ" ),
- 'es' => array( "Ñ" ),
- 'et' => array( "Š", "Ž", "Õ", "Ä", "Ö", "Ü", "W" ), // added W for CollationEt (xx-uca-et)
- 'eu' => array( "Ñ" ),
- 'fo' => array( "Á", "Ð", "Í", "Ó", "Ú", "Ý", "Æ", "Ø", "Å" ),
- 'fur' => array( "À", "Á", "Â", "È", "Ì", "Ò", "Ù" ),
- 'fy' => array(),
- 'ga' => array(),
- 'gd' => array(),
- 'gl' => array( "Ch", "Ll", "Ñ" ),
- 'hr' => array( "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ),
- 'hsb' => array( "Č", "Dź", "Ě", "Ch", "Ł", "Ń", "Ř", "Š", "Ć", "Ž" ),
- 'kk' => array( "Ү", "І" ),
- 'kl' => array( "Æ", "Ø", "Å" ),
- 'ku' => array( "Ç", "Ê", "Î", "Ş", "Û" ),
- 'ky' => array( "Ё" ),
- 'la' => array(),
- 'lb' => array(),
- 'lt' => array( "Č", "Š", "Ž" ),
- 'mk' => array(),
- 'mo' => array( "Ă", "Â", "Î", "Ş", "Ţ" ),
- 'mt' => array( "Ċ", "Ġ", "Għ", "Ħ", "Ż" ),
- 'nl' => array(),
- 'no' => array( "Æ", "Ø", "Å" ),
- 'oc' => array(),
- 'rm' => array(),
- 'ro' => array( "Ă", "Â", "Î", "Ş", "Ţ" ),
- 'rup' => array( "Ă", "Â", "Î", "Ľ", "Ń", "Ş", "Ţ" ),
- 'sco' => array(),
- 'sk' => array( "Ä", "Č", "Ch", "Ô", "Š", "Ž" ),
- 'sl' => array( "Č", "Š", "Ž" ),
- 'smn' => array( "Á", "Č", "Đ", "Ŋ", "Š", "Ŧ", "Ž", "Æ", "Ø", "Å", "Ä", "Ö" ),
- 'sq' => array( "Ç", "Dh", "Ë", "Gj", "Ll", "Nj", "Rr", "Sh", "Th", "Xh", "Zh" ),
- 'sr' => array(),
- 'tk' => array( "Ç", "Ä", "Ž", "Ň", "Ö", "Ş", "Ü", "Ý" ),
- 'tl' => array( "Ñ", "Ng" ),
- 'tr' => array( "Ç", "Ğ", "İ", "Ö", "Ş", "Ü" ),
- 'tt' => array( "Ә", "Ө", "Ү", "Җ", "Ң", "Һ" ),
- 'uz' => array( "Ch", "G'", "Ng", "O'", "Sh" ),
- );
+ 'af' => [],
+ 'ast' => [ "Ch", "Ll", "Ñ" ],
+ 'az' => [ "Ç", "Ə", "Ğ", "İ", "Ö", "Ş", "Ü" ],
+ 'bg' => [],
+ 'br' => [ "Ch", "C'h" ],
+ 'bs' => [ "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ],
+ 'ca' => [],
+ 'co' => [],
+ 'cs' => [ "Č", "Ch", "Ř", "Š", "Ž" ],
+ 'da' => [ "Æ", "Ø", "Å" ],
+ 'de' => [],
+ 'dsb' => [ "Č", "Ć", "Dź", "Ě", "Ch", "Ł", "Ń", "Ŕ", "Š", "Ś", "Ž", "Ź" ],
+ 'el' => [],
+ 'eo' => [ "Ĉ", "Ĝ", "Ĥ", "Ĵ", "Ŝ", "Ŭ" ],
+ 'es' => [ "Ñ" ],
+ 'et' => [ "Š", "Ž", "Õ", "Ä", "Ö", "Ü", "W" ], // added W for CollationEt (xx-uca-et)
+ 'eu' => [ "Ñ" ],
+ 'fo' => [ "Á", "Ð", "Í", "Ó", "Ú", "Ý", "Æ", "Ø", "Å" ],
+ 'fur' => [ "À", "Á", "Â", "È", "Ì", "Ò", "Ù" ],
+ 'fy' => [],
+ 'ga' => [],
+ 'gd' => [],
+ 'gl' => [ "Ch", "Ll", "Ñ" ],
+ 'hr' => [ "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ],
+ 'hsb' => [ "Č", "Dź", "Ě", "Ch", "Ł", "Ń", "Ř", "Š", "Ć", "Ž" ],
+ 'kk' => [ "Ү", "І" ],
+ 'kl' => [ "Æ", "Ø", "Å" ],
+ 'ku' => [ "Ç", "Ê", "Î", "Ş", "Û" ],
+ 'ky' => [ "Ё" ],
+ 'la' => [],
+ 'lb' => [],
+ 'lt' => [ "Č", "Š", "Ž" ],
+ 'mk' => [],
+ 'mo' => [ "Ă", "Â", "Î", "Ş", "Ţ" ],
+ 'mt' => [ "Ċ", "Ġ", "Għ", "Ħ", "Ż" ],
+ 'nl' => [],
+ 'no' => [ "Æ", "Ø", "Å" ],
+ 'oc' => [],
+ 'rm' => [],
+ 'ro' => [ "Ă", "Â", "Î", "Ş", "Ţ" ],
+ 'rup' => [ "Ă", "Â", "Î", "Ľ", "Ń", "Ş", "Ţ" ],
+ 'sco' => [],
+ 'sk' => [ "Ä", "Č", "Ch", "Ô", "Š", "Ž" ],
+ 'sl' => [ "Č", "Š", "Ž" ],
+ 'smn' => [ "Á", "Č", "Đ", "Ŋ", "Š", "Ŧ", "Ž", "Æ", "Ø", "Å", "Ä", "Ö" ],
+ 'sq' => [ "Ç", "Dh", "Ë", "Gj", "Ll", "Nj", "Rr", "Sh", "Th", "Xh", "Zh" ],
+ 'sr' => [],
+ 'tk' => [ "Ç", "Ä", "Ž", "Ň", "Ö", "Ş", "Ü", "Ý" ],
+ 'tl' => [ "Ñ", "Ng" ],
+ 'tr' => [ "Ç", "Ğ", "İ", "Ö", "Ş", "Ü" ],
+ 'tt' => [ "Ә", "Ө", "Ү", "Җ", "Ң", "Һ" ],
+ 'uz' => [ "Ch", "G'", "Ng", "O'", "Sh" ],
+ ];
const RECORD_LENGTH = 14;
// Do a binary search to find the correct letter to sort under
$min = ArrayUtils::findLowerBound(
- array( $this, 'getSortKeyByLetterIndex' ),
+ [ $this, 'getSortKeyByLetterIndex' ],
$this->getFirstLetterCount(),
'strcmp',
$sortKey );
$letters = array_diff( $letters, self::$tailoringFirstLetters['-' . $this->locale] );
}
// Apply digit transforms
- $digits = array( '0', '1', '2', '3', '4', '5', '6', '7', '8', '9' );
+ $digits = [ '0', '1', '2', '3', '4', '5', '6', '7', '8', '9' ];
$letters = array_diff( $letters, $digits );
foreach ( $digits as $digit ) {
$letters[] = $this->digitTransformLanguage->formatNum( $digit, true );
}
}
- // Sort the letters.
- //
- // It's impossible to have the precompiled data file properly sorted,
- // because the sort order changes depending on ICU version. If the
- // array is not properly sorted, the binary search will return random
- // results.
- //
- // We also take this opportunity to remove primary collisions.
- $letterMap = array();
+ /* Sort the letters.
+ *
+ * It's impossible to have the precompiled data file properly sorted,
+ * because the sort order changes depending on ICU version. If the
+ * array is not properly sorted, the binary search will return random
+ * results.
+ *
+ * We also take this opportunity to remove primary collisions.
+ */
+ $letterMap = [];
foreach ( $letters as $letter ) {
$key = $this->getPrimarySortKey( $letter );
if ( isset( $letterMap[$key] ) ) {
}
}
ksort( $letterMap, SORT_STRING );
- // Remove duplicate prefixes. Basically if something has a sortkey
- // which is a prefix of some other sortkey, then it is an
- // expansion and probably should not be considered a section
- // header.
- //
- // For example 'þ' is sometimes sorted as if it is the letters
- // 'th'. Other times it is its own primary element. Another
- // example is '₨'. Sometimes its a currency symbol. Sometimes it
- // is an 'R' followed by an 's'.
- //
- // Additionally an expanded element should always sort directly
- // after its first element due to they way sortkeys work.
- //
- // UCA sortkey elements are of variable length but no collation
- // element should be a prefix of some other element, so I think
- // this is safe. See:
- // * https://ssl.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm
- // * http://site.icu-project.org/design/collation/uca-weight-allocation
- //
- // Additionally, there is something called primary compression to
- // worry about. Basically, if you have two primary elements that
- // are more than one byte and both start with the same byte then
- // the first byte is dropped on the second primary. Additionally
- // either \x03 or \xFF may be added to mean that the next primary
- // does not start with the first byte of the first primary.
- //
- // This shouldn't matter much, as the first primary is not
- // changed, and that is what we are comparing against.
- //
- // tl;dr: This makes some assumptions about how icu implements
- // collations. It seems incredibly unlikely these assumptions
- // will change, but nonetheless they are assumptions.
+
+ /* Remove duplicate prefixes. Basically if something has a sortkey
+ * which is a prefix of some other sortkey, then it is an
+ * expansion and probably should not be considered a section
+ * header.
+ *
+ * For example 'þ' is sometimes sorted as if it is the letters
+ * 'th'. Other times it is its own primary element. Another
+ * example is '₨'. Sometimes its a currency symbol. Sometimes it
+ * is an 'R' followed by an 's'.
+ *
+ * Additionally an expanded element should always sort directly
+ * after its first element due to they way sortkeys work.
+ *
+ * UCA sortkey elements are of variable length but no collation
+ * element should be a prefix of some other element, so I think
+ * this is safe. See:
+ * - https://ssl.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm
+ * - http://site.icu-project.org/design/collation/uca-weight-allocation
+ *
+ * Additionally, there is something called primary compression to
+ * worry about. Basically, if you have two primary elements that
+ * are more than one byte and both start with the same byte then
+ * the first byte is dropped on the second primary. Additionally
+ * either \x03 or \xFF may be added to mean that the next primary
+ * does not start with the first byte of the first primary.
+ *
+ * This shouldn't matter much, as the first primary is not
+ * changed, and that is what we are comparing against.
+ *
+ * tl;dr: This makes some assumptions about how icu implements
+ * collations. It seems incredibly unlikely these assumptions
+ * will change, but nonetheless they are assumptions.
+ */
$prev = false;
- $duplicatePrefixes = array();
+ $duplicatePrefixes = [];
foreach ( $letterMap as $key => $value ) {
// Remove terminator byte. Otherwise the prefix
// comparison will get hung up on that.
unset( $letterMap[$badKey] );
// This code assumes that unsetting does not change sort order.
}
- $data = array(
+ $data = [
'chars' => array_values( $letterMap ),
'keys' => array_keys( $letterMap ),
'version' => self::FIRST_LETTER_VERSION,
- );
+ ];
// Reduce memory usage before caching
unset( $letterMap );
// Save to cache
$this->firstLetterData = $data;
- $cache->set( $cacheKey, $data, 86400 * 7 /* 1 week */ );
+ $cache->set( $cacheKey, $data, $cache::TTL_WEEK );
return $data;
}
$versionPrefix = substr( $icuVersion, 0, 3 );
// Source: http://site.icu-project.org/download
- $map = array(
+ $map = [
'50.' => '6.2',
'49.' => '6.1',
'4.8' => '6.0',
'3.8' => '5.0',
'3.6' => '5.0',
'3.4' => '4.1',
- );
+ ];
if ( isset( $map[$versionPrefix] ) ) {
return $map[$versionPrefix];
private static function mangle( $string ) {
return str_replace(
- array( 'w', 'W' ),
+ [ 'w', 'W' ],
'ᴡ', // U+1D21 'LATIN LETTER SMALL CAPITAL W'
$string
);