aboutsummaryrefslogtreecommitdiffstats
path: root/includes/Collation.php
diff options
context:
space:
mode:
authorMatmaRex <matma.rex@gmail.com>2013-02-28 16:44:26 +0100
committerMatmaRex <matma.rex@gmail.com>2013-03-05 13:45:15 +0100
commitd01cbb41483ab4001b384ddfbc3275cc7e5093c6 (patch)
treeb1e93d97a485edcfa9440eff742b7733ca4b578f /includes/Collation.php
parentafec7906ad2a6c63dfee57c6e5a9fe043e8b5d6c (diff)
downloadmediawikicore-d01cbb41483ab4001b384ddfbc3275cc7e5093c6.tar.gz
mediawikicore-d01cbb41483ab4001b384ddfbc3275cc7e5093c6.zip
adjusted comments for IcuCollation::$tailoringFirstLetters
More information about what actually sits in that array. Summary of modifications to the Mimer data so far: * removed data for "traditional" variants of de (German) and es (Spanish) * used code 'tl' instead of 'fil' for Tagalog/Filipino * added be-tarask (Belarusian Taraškievica) Change-Id: I97273c52599a5eda3f63366d697b077d6b17ba81
Diffstat (limited to 'includes/Collation.php')
-rw-r--r--includes/Collation.php21
1 files changed, 15 insertions, 6 deletions
diff --git a/includes/Collation.php b/includes/Collation.php
index b0f770fb33d0..0ace6ba9e260 100644
--- a/includes/Collation.php
+++ b/includes/Collation.php
@@ -181,20 +181,29 @@ class IcuCollation extends Collation {
);
/**
- * Additional characters (or character groups) to be considered first-letters
+ * Additional characters (or character groups) to be considered separate
+ * letters for given languages, compared to 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" ),
- 'fi' => array( "Å", "Ä", "Ö" ),
'be' => array( "Ё" ),
'be-tarask' => array( "Ё" ),
+ 'fi' => array( "Å", "Ä", "Ö" ),
+ 'pl' => array( "Ą", "Ć", "Ę", "Ł", "Ń", "Ó", "Ś", "Ź", "Ż" ),
'ru' => array(),
// Not verified, but likely correct
'af' => array(),
@@ -254,7 +263,7 @@ class IcuCollation extends Collation {
'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" ),