Make grammar data loadable as an RL module and usable in JS

[lhc/web/wiklou.git] / languages / Language.php

diff --git a/languages/Language.php b/languages/Language.php
index 3e28759..4628812 100644 (file)
--- a/languages/Language.php
+++ b/languages/Language.php
@@ -137,6 +137,12 @@ class Language {
         */
        static private $fallbackLanguageCache = [];
 
+       /**
+        * Cache for grammar rules data
+        * @var MapCacheLRU|null
+        */
+       static private $grammarTransformations;
+
        /**
         * Cache for language names
         * @var HashBagOStuff|null
@@ -291,7 +297,7 @@ class Language {
                # Since these are limited, this is safe even later changes to the registry --
                # the only oddity is that it might change the type of the tag, and thus
                # the results from the capturing groups.
-               # http://www.iana.org/assignments/language-subtag-registry
+               # https://www.iana.org/assignments/language-subtag-registry
 
                $grandfathered = "en{$s}GB{$s}oed"
                        . "|i{$s}(?:ami|bnn|default|enochian|hak|klingon|lux|mingo|navajo|pwn|tao|tay|tsu)"
@@ -1623,7 +1629,7 @@ class Language {
         *
         * Based on a PHP-Nuke block by Sharjeel which is released under GNU/GPL license
         *
-        * @see http://phpnuke.org/modules.php?name=News&file=article&sid=8234&mode=thread&order=0&thold=0
+        * @see https://phpnuke.org/modules.php?name=News&file=article&sid=8234&mode=thread&order=0&thold=0
         *
         * @param string $ts
         *
@@ -1852,9 +1858,9 @@ class Language {
         * Algorithm to convert Gregorian dates to Thai solar dates,
         * Minguo dates or Minguo dates.
         *
-        * Link: http://en.wikipedia.org/wiki/Thai_solar_calendar
-        *       http://en.wikipedia.org/wiki/Minguo_calendar
-        *       http://en.wikipedia.org/wiki/Japanese_era_name
+        * Link: https://en.wikipedia.org/wiki/Thai_solar_calendar
+        *       https://en.wikipedia.org/wiki/Minguo_calendar
+        *       https://en.wikipedia.org/wiki/Japanese_era_name
         *
         * @param string $ts 14-character timestamp
         * @param string $cName Calender name
@@ -2593,7 +2599,7 @@ class Language {
        public function iconv( $in, $out, $string ) {
                # Even with //IGNORE iconv can whine about illegal characters in
                # *input* string. We just ignore those too.
-               # REF: http://bugs.php.net/bug.php?id=37166
+               # REF: https://bugs.php.net/bug.php?id=37166
                # REF: https://phabricator.wikimedia.org/T18885
                MediaWiki\suppressWarnings();
                $text = iconv( $in, $out . '//IGNORE', $string );
@@ -3730,6 +3736,7 @@ class Language {
 
                return $word;
        }
+
        /**
         * Get the grammar forms for the content language
         * @return array Array of grammar forms
@@ -3745,6 +3752,45 @@ class Language {
 
                return [];
        }
+
+       /**
+        * Get the grammar transformations data for the language.
+        * Used like grammar forms, with {{GRAMMAR}} and cases,
+        * but uses pairs of regexes and replacements instead of code.
+        *
+        * @return array[] Array of grammar transformations.
+        * @since 1.28
+        */
+       public function getGrammarTransformations() {
+               $languageCode = $this->getCode();
+
+               if ( self::$grammarTransformations === null ) {
+                       self::$grammarTransformations = new MapCacheLRU( 10 );
+               }
+
+               if ( self::$grammarTransformations->has( $languageCode ) ) {
+                       return self::$grammarTransformations->get( $languageCode );
+               }
+
+               $data = [];
+
+               $grammarDataFile = __DIR__ . "/data/grammarTransformations/$languageCode.json";
+               if ( is_readable( $grammarDataFile ) ) {
+                       $data = FormatJson::decode(
+                               file_get_contents( $grammarDataFile ),
+                               true
+                       );
+                       if ( $data === null ) {
+                               throw new MWException( "Invalid grammar data for \"$languageCode\"." );
+                               $data = [];
+                       }
+
+                       self::$grammarTransformations->set( $languageCode, $data );
+               }
+
+               return $data;
+       }
+
        /**
         * Provides an alternative text depending on specified gender.
         * Usage {{gender:username|masculine|feminine|unknown}}.
@@ -4461,14 +4507,15 @@ class Language {
        }
 
        /**
-        * @todo Document
+        * Formats a time given in seconds into a string representation of that time.
+        *
         * @param int|float $seconds
-        * @param array $format Optional
-        *   If $format['avoid'] === 'avoidseconds': don't mention seconds if $seconds >= 1 hour.
-        *   If $format['avoid'] === 'avoidminutes': don't mention seconds/minutes if $seconds > 48 hours.
+        * @param array $format An optional argument that formats the returned string in different ways:
+        *   If $format['avoid'] === 'avoidseconds': don't show seconds if $seconds >= 1 hour,
+        *   If $format['avoid'] === 'avoidminutes': don't show seconds/minutes if $seconds > 48 hours,
         *   If $format['noabbrevs'] is true: use 'seconds' and friends instead of 'seconds-abbrev'
         *     and friends.
-        *   For backwards compatibility, $format may also be one of the strings 'avoidseconds'
+        * @note For backwards compatibility, $format may also be one of the strings 'avoidseconds'
         *     or 'avoidminutes'.
         * @return string
         */