From c6156c4b06260a809d1e0d68c76e468199659780 Mon Sep 17 00:00:00 2001
From: robin <robinp.1273@gmail.com>
Date: Sun, 15 Jul 2012 15:47:21 -0400
Subject: [PATCH] Add language converter for Uzbek.

Also add tests per Hashar, based on the Serbian file but less since
Uzbek does not have "variant guessing" or custom plural rules.

Change-Id: I27da994b88fbe13cfb7df12851e704d881397666
---
 RELEASE-NOTES-1.20                         |   1 +
 languages/classes/LanguageUz.php           | 136 +++++++++++++++++++++
 tests/phpunit/languages/LanguageUzTest.php | 120 ++++++++++++++++++
 3 files changed, 257 insertions(+)
 create mode 100644 languages/classes/LanguageUz.php
 create mode 100644 tests/phpunit/languages/LanguageUzTest.php

diff --git a/RELEASE-NOTES-1.20 b/RELEASE-NOTES-1.20
index 8473a275ec..29341a6bd6 100644
--- a/RELEASE-NOTES-1.20
+++ b/RELEASE-NOTES-1.20
@@ -218,6 +218,7 @@ changes to languages because of Bugzilla reports.
 * (bug 36012) Space in $separatorTransformTable should be non-breaking in
   Portuguese, Esperanto and Udmurt.
 * Turoyo (tru) added.
+* Cyrillic-Latin language converter added for Uzbek (uz).
 
 === Other changes in 1.20 ===
 * The user_token field is now left empty until a user attempts to login and
diff --git a/languages/classes/LanguageUz.php b/languages/classes/LanguageUz.php
new file mode 100644
index 0000000000..6c0f1f62be
--- /dev/null
+++ b/languages/classes/LanguageUz.php
@@ -0,0 +1,136 @@
+<?php
+/**
+ * Uzbek specific code.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ * http://www.gnu.org/copyleft/gpl.html
+ *
+ * @file
+ * @ingroup Language
+ */
+
+require_once( dirname( __FILE__ ) . '/../LanguageConverter.php' );
+
+/**
+ * @ingroup Language
+ */
+class UzConverter extends LanguageConverter {
+	var $toLatin = array(
+		'а' => 'a', 'А' => 'A',
+		'б' => 'b', 'Б' => 'B',
+		'д' => 'd', 'Д' => 'D',
+		'е' => 'e', 'Е' => 'E',
+		'э' => 'e', 'Э' => 'E',
+		'в' => 'v', 'В' => 'V',
+		'х' => 'x', 'Х' => 'X',
+		'ғ' => 'gʻ', 'Ғ' => 'Gʻ',
+		'г' => 'g', 'Г' => 'G',
+		'Ò³' => 'h', 'Ò²' => 'H',
+		'ж' => 'j', 'Ж' => 'J',
+		'з' => 'z', 'З' => 'Z',
+		'и' => 'i', 'И' => 'I',
+		'к' => 'k', 'К' => 'K',
+		'л' => 'l', 'Л' => 'L',
+		'м' => 'm', 'М' => 'M',
+		'н' => 'n', 'Н' => 'N',
+		'о' => 'o', 'О' => 'O',
+		'п' => 'p', 'П' => 'P',
+		'р' => 'r', 'Р' => 'R',
+		'с' => 's', 'С' => 'S',
+		'т' => 't', 'Т' => 'T',
+		'у' => 'u', 'У' => 'U',
+		'ф' => 'f', 'Ф' => 'F',
+		'ц' => 'c', 'Ц' => 'C',
+		'ў' => 'oʻ', 'Ў' => 'Oʻ',
+		'ц' => 'ts', 'Ц' => 'Ts', // note: at the beginning of a word and right after a consonant, only "s" is used
+		'қ' => 'q', 'Қ' => 'Q',
+		'ё' => 'yo', 'Ё' => 'Yo',
+		'ю' => 'yu', 'Ю' => 'Yu',
+		'ч' => 'ch', 'Ч' => 'Ch',
+		'ш' => 'sh', 'Ш' => 'Sh',
+		'й' => 'y', 'Й' => 'Y',
+		'я' => 'ya', 'Я' => 'Ya',
+		'ъ' => 'ʼ',
+	);
+
+	var $toCyrillic = array(
+		'a' => 'а', 'A' => 'А',
+		'b' => 'б', 'B' => 'Б',
+		'd' => 'д', 'D' => 'Д',
+		'e' => 'е', 'E' => 'Е',
+		' e' => ' э', ' E' => ' Э', // "э" is used at the beginning of a word instead of "e"
+		'ye' => 'е', 'Ye' => 'Е',
+		'f' => 'ф', 'F' => 'Ф',
+		'g' => 'г', 'G' => 'Г',
+		'g‘' => 'ғ', 'G‘' => 'Ғ', 'gʻ' => 'ғ', 'Gʻ' => 'Ғ',
+		'h'  => 'Ò³', 'H' => 'Ò²',
+		'i' => 'и', 'I' => 'И',
+		'k'  => 'к', 'K' => 'К',
+		'l' => 'л', 'L' => 'Л',
+		'm' => 'м', 'M' => 'М',
+		'n' => 'н', 'N' => 'Н',
+		'o' => 'о', 'O' => 'О',
+		'p' => 'п', 'P' => 'П',
+		'r' => 'р', 'R' => 'Р',
+		's' => 'с', 'S' => 'С',
+		't' => 'т', 'T' => 'Т',
+		'u' => 'у', 'U' => 'У',
+		'v' => 'в', 'V' => 'В',
+		'x' => 'х', 'X' => 'Х',
+		'z' => 'з', 'Z' => 'З',
+		'j' => 'ж', 'J' => 'Ж',
+		'o‘' => 'ў', 'O‘' => 'Ў', 'oʻ' => 'ў', 'Oʻ' => 'Ў',
+		'ts' => 'ц', 'Ts' => 'Ц',
+		'q' => 'қ', 'Q' => 'Қ',
+		'yo' => 'ё', 'Yo' => 'Ё',
+		'yu' => 'ю', 'Yu' => 'Ю',
+		'ch' => 'ч', 'Ch' => 'Ч',
+		'sh' => 'ш', 'Sh' => 'Ш',
+		'y' => 'й', 'Y' => 'Й',
+		'ya' => 'я', 'Ya' => 'Я',
+		'ʼ' => 'ъ',
+	);
+
+	function loadDefaultTables() {
+		$this->mTables = array(
+			'uz-cyrl' => new ReplacementArray( $this->toCyrillic ),
+			'uz-latn' => new ReplacementArray( $this->toLatin ),
+			'uz'      => new ReplacementArray()
+		);
+	}
+
+}
+
+/**
+ * Uzbek
+ *
+ * @ingroup Language
+ */
+class LanguageUz extends Language {
+	function __construct() {
+		global $wgHooks;
+		parent::__construct();
+
+		$variants = array( 'uz', 'uz-latn', 'uz-cyrl' );
+		$variantfallbacks = array(
+			'uz'    => 'uz-latn',
+			'uz-cyrl' => 'uz',
+			'uz-latn' => 'uz',
+		);
+
+		$this->mConverter = new UzConverter( $this, 'uz', $variants, $variantfallbacks );
+		$wgHooks['ArticleSaveComplete'][] = $this->mConverter;
+	}
+}
diff --git a/tests/phpunit/languages/LanguageUzTest.php b/tests/phpunit/languages/LanguageUzTest.php
new file mode 100644
index 0000000000..86f483d0fc
--- /dev/null
+++ b/tests/phpunit/languages/LanguageUzTest.php
@@ -0,0 +1,120 @@
+<?php
+/**
+ * PHPUnit tests for the Uzbek language.
+ * The language can be represented using two scripts:
+ *  - Latin (uz-latn)
+ *  - Cyrillic (uz-cyrl)
+ *
+ * @author Robin Pepermans
+ * @author Antoine Musso <hashar at free dot fr>
+ * @copyright Copyright © 2012, Robin Pepermans
+ * @copyright Copyright © 2011, Antoine Musso <hashar at free dot fr>
+ * @file
+ */
+
+require_once dirname( dirname( __FILE__ ) ) . '/bootstrap.php';
+
+/** Tests for MediaWiki languages/LanguageUz.php */
+class LanguageUzTest extends MediaWikiTestCase {
+	/* Language object. Initialized before each test */
+	private $lang;
+
+	function setUp() {
+		$this->lang = Language::factory( 'uz' );
+	}
+	function tearDown() {
+		unset( $this->lang );
+	}
+
+	/**
+	 * @author Nikola Smolenski
+	 */
+	function testConversionToCyrillic() {
+		// A convertion of Latin to Cyrillic
+		$this->assertEquals( 'абвгғ',
+			$this->convertToCyrillic( 'abvggÊ»' )
+		);
+		// Same as above, but assert that -{}-s must be removed and not converted
+		$this->assertEquals( 'ljабnjвгўоdb',
+			$this->convertToCyrillic( '-{lj}-ab-{nj}-vgoʻo-{db}-' )
+		);
+		// A simple convertion of Cyrillic to Cyrillic
+		$this->assertEquals( 'абвг',
+			$this->convertToCyrillic( 'абвг' )
+		);
+		// Same as above, but assert that -{}-s must be removed and not converted
+		$this->assertEquals( 'ljабnjвгdaž',
+			$this->convertToCyrillic( '-{lj}-аб-{nj}-вг-{da}-ž' )
+		);
+	}
+
+	function testConversionToLatin() {
+		// A simple convertion of Latin to Latin
+		$this->assertEquals( 'abdef',
+			$this->convertToLatin( 'abdef' )
+		);
+		// A convertion of Cyrillic to Latin
+		$this->assertEquals( 'gʻabtsdOʻQyo',
+			$this->convertToLatin( 'ғабцдЎҚё' )
+		);
+	}
+
+	##### HELPERS #####################################################
+	/**
+	 * Wrapper to verify text stay the same after applying conversion
+	 * @param $text string Text to convert
+	 * @param $variant string Language variant 'uz-cyrl' or 'uz-latn'
+	 * @param $msg string Optional message
+	 */
+	function assertUnConverted( $text, $variant, $msg = '' ) {
+		$this->assertEquals(
+			$text,
+			$this->convertTo( $text, $variant ),
+			$msg
+		);
+	}
+	/**
+	 * Wrapper to verify a text is different once converted to a variant.
+	 * @param $text string Text to convert
+	 * @param $variant string Language variant 'uz-cyrl' or 'uz-latn'
+	 * @param $msg string Optional message
+	 */
+	function assertConverted( $text, $variant, $msg = '' ) {
+		$this->assertNotEquals(
+			$text,
+			$this->convertTo( $text, $variant ),
+			$msg
+		);
+	}
+
+	/**
+	 * Verifiy the given Cyrillic text is not converted when using
+	 * using the cyrillic variant and converted to Latin when using
+	 * the Latin variant.
+	 */
+	function assertCyrillic( $text, $msg = '' ) {
+		$this->assertUnConverted( $text, 'uz-cyrl', $msg );
+		$this->assertConverted( $text, 'uz-latn', $msg );
+	}
+	/**
+	 * Verifiy the given Latin text is not converted when using
+	 * using the Latin variant and converted to Cyrillic when using
+	 * the Cyrillic variant.
+	 */
+	function assertLatin( $text, $msg = '' ) {
+		$this->assertUnConverted( $text, 'uz-latn', $msg );
+		$this->assertConverted( $text, 'uz-cyrl', $msg );
+	}
+
+
+	/** Wrapper for converter::convertTo() method*/
+	function convertTo( $text, $variant ) {
+		return $this->lang->mConverter->convertTo( $text, $variant );
+	}
+	function convertToCyrillic( $text ) {
+		return $this->convertTo( $text, 'uz-cyrl' );
+	}
+	function convertToLatin( $text ) {
+		return $this->convertTo( $text, 'uz-latn' );
+	}
+}
-- 
2.20.1