}
}
-
class IcuCollation extends Collation {
+ const FIRST_LETTER_VERSION = 1;
+
var $primaryCollator, $mainCollator, $locale;
var $firstLetterData;
);
/**
- * Additional characters (or character groups) to be considered first-letters
+ * Additional characters (or character groups) to be considered separate
+ * letters for given languages, or to be removed from the list of such
+ * letters (denoted by keys starting with '-').
+ *
+ * These are additions to (or subtractions from) the data stored in the
+ * first-letters-root.ser file (which among others includes full basic latin,
+ * cyrillic and greek alphabets).
*
- * Generated based on the primary level of Unicode collation tailorings
- * available at http://developer.mimer.com/charts/tailorings.htm .
+ * "Separate letter" is a letter that would have a separate heading/section
+ * for it in a dictionary or a phone book in this language. This data isn't
+ * used for sorting (the ICU library handles that), only for deciding which
+ * characters (or character groups) to use as headings.
+ *
+ * Initially generated based on the primary level of Unicode collation
+ * tailorings available at http://developer.mimer.com/charts/tailorings.htm ,
+ * later modified.
*
* 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.
*/
static $tailoringFirstLetters = array(
// Verified by native speakers
- 'pl' => array( "Ą", "Ć", "Ę", "Ł", "Ń", "Ó", "Ś", "Ź", "Ż" ),
+ 'be' => array( "Ё" ),
+ 'be-tarask' => array( "Ё" ),
+ 'en' => array(),
'fi' => array( "Å", "Ä", "Ö" ),
+ '-fi' => array( "Ǥ", "Ŋ", "Ŧ", "Ʒ" ), // sorted like G, N, T, Z - bug 46330
+ 'hu' => array( "Cs", "Dz", "Dzs", "Gy", "Ly", "Ny", "Ö", "Sz", "Ty", "Ü", "Zs" ),
+ 'it' => array(),
+ 'pl' => array( "Ą", "Ć", "Ę", "Ł", "Ń", "Ó", "Ś", "Ź", "Ż" ),
+ 'pt' => array(),
+ 'ru' => array(),
+ 'sv' => array( "Å", "Ä", "Ö" ),
+ '-sv' => array( "Þ" ), // sorted as "th" in Swedish, causing unexpected output - bug 45446
+ 'uk' => array( "Ґ", "Ь" ),
+ 'vi' => array( "Ă", "Â", "Đ", "Ê", "Ô", "Ơ", "Ư" ),
// Not verified, but likely correct
'af' => array(),
- 'ast' => array( "CH", "LL", "Ñ" ),
+ 'ast' => array( "Ch", "Ll", "Ñ" ),
'az' => array( "Ç", "Ə", "Ğ", "İ", "Ö", "Ş", "Ü" ),
- 'be' => array( "Ё" ),
'bg' => array(),
- 'br' => array( "CH", "C'H" ),
- 'bs' => array( "Ä\8c", "Ä\86", "DŽ", "Ä\90", "LJ", "NJ", "Š", "Ž" ),
+ 'br' => array( "Ch", "C'h" ),
+ 'bs' => array( "Ä\8c", "Ä\86", "Dž", "Ä\90", "Lj", "Nj", "Š", "Ž" ),
'ca' => array(),
'co' => array(),
- 'cs' => array( "Č", "CH", "Ř", "Š", "Ž" ),
- 'cy' => array( "CH", "DD", "FF", "NG", "LL", "PH", "RH", "TH" ),
+ 'cs' => array( "Č", "Ch", "Ř", "Š", "Ž" ),
+ 'cy' => array( "Ch", "Dd", "Ff", "Ng", "Ll", "Ph", "Rh", "Th" ),
'da' => array( "Æ", "Ø", "Å" ),
'de' => array(),
- 'dsb' => array( "Ä\8c", "Ä\86", "DŹ", "Ä\9a", "CH", "Ł", "Ń", "Ŕ", "Š", "Ś", "Ž", "Ź" ),
+ 'dsb' => array( "Ä\8c", "Ä\86", "Dź", "Ä\9a", "Ch", "Ł", "Ń", "Ŕ", "Š", "Ś", "Ž", "Ź" ),
'el' => array(),
- 'en' => array(),
'eo' => array( "Ĉ", "Ĝ", "Ĥ", "Ĵ", "Ŝ", "Ŭ" ),
'es' => array( "Ñ" ),
'et' => array( "Š", "Ž", "Õ", "Ä", "Ö", "Ü" ),
'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" ),
- 'hu' => array( "CS", "DZ", "DZS", "GY", "LY", "NY", "Ö", "SZ", "TY", "Ü", "ZS" ),
+ '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" ),
'is' => array( "Á", "Ð", "É", "Í", "Ó", "Ú", "Ý", "Þ", "Æ", "Ö", "Å" ),
- 'it' => array(),
'kk' => array( "Ү", "І" ),
'kl' => array( "Æ", "Ø", "Å" ),
'ku' => array( "Ç", "Ê", "Î", "Ş", "Û" ),
'lv' => array( "Č", "Ģ", "Ķ", "Ļ", "Ņ", "Š", "Ž" ),
'mk' => array(),
'mo' => array( "Ă", "Â", "Î", "Ş", "Ţ" ),
- 'mt' => array( "Ä\8a", "Ä ", "GĦ", "Ħ", "Ż" ),
+ 'mt' => array( "Ä\8a", "Ä ", "Għ", "Ħ", "Ż" ),
'nl' => array(),
'no' => array( "Æ", "Ø", "Å" ),
'oc' => array(),
- 'pt' => array(),
'rm' => array(),
'ro' => array( "Ă", "Â", "Î", "Ş", "Ţ" ),
- 'ru' => array(),
'rup' => array( "Ă", "Â", "Î", "Ľ", "Ń", "Ş", "Ţ" ),
'sco' => array(),
- 'sk' => array( "Ä", "Č", "CH", "Ô", "Š", "Ž" ),
+ '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" ),
+ 'sq' => array( "Ç", "Dh", "Ë", "Gj", "Ll", "Nj", "Rr", "Sh", "Th", "Xh", "Zh" ),
'sr' => array(),
- 'sv' => array( "Å", "Ä", "Ö" ),
'tk' => array( "Ç", "Ä", "Ž", "Ň", "Ö", "Ş", "Ü", "Ý" ),
- 'tl' => array( "Ñ", "NG" ), /* 'fil' in the data source */
+ 'tl' => array( "Ñ", "Ng" ),
'tr' => array( "Ç", "Ğ", "İ", "Ö", "Ş", "Ü" ),
'tt' => array( "Ә", "Ө", "Ү", "Җ", "Ң", "Һ" ),
- 'uk' => array( "Ґ", "Ь" ),
- 'uz' => array( "CH", "G'", "NG", "O'", "SH" ),
- 'vi' => array( "Ă", "Â", "Đ", "Ê", "Ô", "Ơ", "Ư" ),
+ 'uz' => array( "Ch", "G'", "Ng", "O'", "Sh" ),
);
const RECORD_LENGTH = 14;
$cacheKey = wfMemcKey( 'first-letters', $this->locale );
$cacheEntry = $cache->get( $cacheKey );
- if ( $cacheEntry ) {
+ if ( $cacheEntry && isset( $cacheEntry['version'] )
+ && $cacheEntry['version'] == self::FIRST_LETTER_VERSION )
+ {
$this->firstLetterData = $cacheEntry;
return $this->firstLetterData;
}
if ( isset ( self::$tailoringFirstLetters[$this->locale] ) ) {
$letters = wfGetPrecompiledData( "first-letters-root.ser" );
+ // Append additional characters
$letters = array_merge( $letters, self::$tailoringFirstLetters[$this->locale] );
+ // Remove unnecessary ones, if any
+ if ( isset( self::$tailoringFirstLetters[ '-' . $this->locale ] ) ) {
+ $letters = array_diff( $letters, self::$tailoringFirstLetters[ '-' . $this->locale ] );
+ }
} else {
$letters = wfGetPrecompiledData( "first-letters-{$this->locale}.ser" );
if ( $letters === false ) {
ksort( $letterMap, SORT_STRING );
$data = array(
'chars' => array_values( $letterMap ),
- 'keys' => array_keys( $letterMap )
+ 'keys' => array_keys( $letterMap ),
+ 'version' => self::FIRST_LETTER_VERSION,
);
// Reduce memory usage before caching
* Do a binary search, and return the index of the largest item that sorts
* less than or equal to the target value.
*
- * @param $valueCallback array A function to call to get the value with
+ * @param array $valueCallback A function to call to get the value with
* a given array index.
- * @param $valueCount int The number of items accessible via $valueCallback,
+ * @param int $valueCount The number of items accessible via $valueCallback,
* indexed from 0 to $valueCount - 1
- * @param $comparisonCallback array A callback to compare two values, returning
+ * @param array $comparisonCallback A callback to compare two values, returning
* -1, 0 or 1 in the style of strcmp().
- * @param $target string The target value to find.
+ * @param string $target The target value to find.
*
* @return int|bool The item index of the lower bound, or false if the target value
* sorts before all items.
dépôts / lhc / web / wiklou.git / blobdiff