From: Santhosh Thottingal <santhosh.thottingal@gmail.com>
Date: Mon, 4 Jun 2012 09:19:35 +0000 (+0530)
Subject: Custom  grammar rules in javascript for some languages
X-Git-Tag: 1.31.0-rc.0~23345^2
X-Git-Url: https://git.heureux-cyclage.org/?p=lhc%2Fweb%2Fwiklou.git;a=commitdiff_plain;h=7c680ba0dca6867dc5d972f953ab8060f0c47eb5

Custom  grammar rules in javascript for some languages

Splitted from https://gerrit.wikimedia.org/r/4554
Grammar rules ported to js based on the php code.
Depends on the javascript Grammar parsing support by jqueryMsg

Change-Id: I701954a623467bf6c9abd3160e239c59cab567e9
---

diff --git a/resources/Resources.php b/resources/Resources.php
index 34b9be6732..1f2dcd09d1 100644
--- a/resources/Resources.php
+++ b/resources/Resources.php
@@ -687,6 +687,7 @@ return array(
 			'cu' => 'resources/mediawiki.language/languages/cu.js',
 			'cy' => 'resources/mediawiki.language/languages/cy.js',
 			'dsb' => 'resources/mediawiki.language/languages/dsb.js',
+			'fi' => 'resources/mediawiki.language/languages/fi.js',
 			'fr' => 'resources/mediawiki.language/languages/fr.js',
 			'ga' => 'resources/mediawiki.language/languages/ga.js',
 			'gd' => 'resources/mediawiki.language/languages/gd.js',
@@ -695,8 +696,10 @@ return array(
 			'hi' => 'resources/mediawiki.language/languages/hi.js',
 			'hr' => 'resources/mediawiki.language/languages/hr.js',
 			'hsb' => 'resources/mediawiki.language/languages/hsb.js',
+			'hu' => 'resources/mediawiki.language/languages/hu.js',
 			'hy' => 'resources/mediawiki.language/languages/hy.js',
 			'ksh' => 'resources/mediawiki.language/languages/ksh.js',
+			'la' => 'resources/mediawiki.language/languages/la.js',
 			'ln' => 'resources/mediawiki.language/languages/ln.js',
 			'lt' => 'resources/mediawiki.language/languages/lt.js',
 			'lv' => 'resources/mediawiki.language/languages/lv.js',
@@ -706,6 +709,7 @@ return array(
 			'mt' => 'resources/mediawiki.language/languages/mt.js',
 			'nl' => 'resources/mediawiki.language/languages/nl.js',
 			'nso' => 'resources/mediawiki.language/languages/nso.js',
+			'os' => 'resources/mediawiki.language/languages/os.js',
 			'pl' => 'resources/mediawiki.language/languages/pl.js',
 			'pt' => 'resources/mediawiki.language/languages/pt.js',
 			'pt-br' => 'resources/mediawiki.language/languages/pt-br.js',
diff --git a/resources/mediawiki.language/languages/bs.js b/resources/mediawiki.language/languages/bs.js
index 9f22426ae4..9affcf0c4d 100644
--- a/resources/mediawiki.language/languages/bs.js
+++ b/resources/mediawiki.language/languages/bs.js
@@ -18,3 +18,19 @@ mediaWiki.language.convertPlural = function( count, forms ) {
 			return forms[2];
 	}
 };
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'bs', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	switch ( form ) {
+		case 'instrumental': // instrumental
+			word = 's ' + word;
+			break;
+		case 'lokativ': // locative
+			word = 'o ' + word;
+			break;
+	}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/dsb.js b/resources/mediawiki.language/languages/dsb.js
index c3eaa1fceb..e3c5808741 100644
--- a/resources/mediawiki.language/languages/dsb.js
+++ b/resources/mediawiki.language/languages/dsb.js
@@ -16,3 +16,19 @@ mediaWiki.language.convertPlural = function( count, forms ) {
 			return forms[3];
 	}
 };
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'dsb', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	switch ( form ) {
+		case 'instrumental': // instrumental
+			word = 'z ' + word;
+			break;
+		case 'lokatiw': // lokatiw
+			word = 'wo ' + word;
+			break;
+	}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/fi.js b/resources/mediawiki.language/languages/fi.js
new file mode 100644
index 0000000000..374698dc79
--- /dev/null
+++ b/resources/mediawiki.language/languages/fi.js
@@ -0,0 +1,44 @@
+/**
+ *  Finnish (Suomi) language functions
+ *  @author Santhosh Thottingal
+ */
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'fi', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+
+	// vowel harmony flag
+	var aou = word.match( /[aou][^äöy]*$/i );
+	var origWord = word;
+	if ( word.match( /wiki$/i ) ) {
+		aou = false;
+	}
+	//append i after final consonant
+	if ( word.match( /[bcdfghjklmnpqrstvwxz]$/i ) )
+		word += 'i';
+
+	switch ( form ) {
+		case 'genitive':
+			word += 'n';
+			break;
+		case 'elative':
+			word += ( aou ? 'sta' : 'stä' );
+			break;
+		case 'partitive':
+			word += ( aou ? 'a' : 'ä' );
+			break;
+		case 'illative':
+			// Double the last letter and add 'n'
+			word += word.substr(  word.length-1 ) + 'n';
+			break;
+		case 'inessive':
+			word += ( aou ? 'ssa' : 'ssä' );
+			break;
+		default:
+			word = origWord;
+			break;
+	}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/ga.js b/resources/mediawiki.language/languages/ga.js
index 392801381e..51fce35b6d 100644
--- a/resources/mediawiki.language/languages/ga.js
+++ b/resources/mediawiki.language/languages/ga.js
@@ -12,3 +12,38 @@ mediaWiki.language.convertPlural = function( count, forms ) {
 	}
 	return forms[2];
 };
+
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'ga', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	switch ( form ) {
+		case 'ainmlae':
+			switch ( word ) {
+				case 'an Domhnach':
+					word = 'Dé Domhnaigh';
+					break;
+				case 'an Luan':
+					word = 'Dé Luain';
+					break;
+				case 'an Mháirt':
+					word = 'Dé Mháirt';
+					break;
+				case 'an Chéadaoin':
+					word = 'Dé Chéadaoin';
+					break;
+				case 'an Déardaoin':
+					word = 'Déardaoin';
+					break;
+				case 'an Aoine':
+					word = 'Dé hAoine';
+					break;
+				case 'an Satharn':
+					word = 'Dé Sathairn';
+					break;
+			}
+	}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/he.js b/resources/mediawiki.language/languages/he.js
index b74440e473..e737a7c0f2 100644
--- a/resources/mediawiki.language/languages/he.js
+++ b/resources/mediawiki.language/languages/he.js
@@ -12,3 +12,29 @@ mediaWiki.language.convertPlural = function( count, forms ) {
 	}
 	return forms[1];
 };
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'he', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	switch ( form ) {
+		case 'prefixed':
+		case 'תחילית': // the same word in Hebrew
+			// Duplicate prefixed "Waw", but only if it's not already double
+			if ( word.substr( 0, 1 ) === "ו" && word.substr( 0, 2 ) !== "וו" ) {
+				word = "ו" + word;
+			}
+
+			// Remove the "He" if prefixed
+			if ( word.substr( 0, 1 ) === "ה" ) {
+				word = word.substr( 1, word.length );
+			}
+
+			// Add a hyphen (maqaf) before numbers and non-Hebrew letters
+			if (  word.substr( 0, 1 ) < "א" ||  word.substr( 0, 1 ) > "ת" ) {
+				word = "Ö¾" + word;
+			}
+	}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/hsb.js b/resources/mediawiki.language/languages/hsb.js
index 8651fe41d8..6aa993c832 100644
--- a/resources/mediawiki.language/languages/hsb.js
+++ b/resources/mediawiki.language/languages/hsb.js
@@ -16,3 +16,20 @@ mediaWiki.language.convertPlural = function( count, forms ) {
 			return forms[3];
 	}
 };
+
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms =mw.language.getData( 'hsb', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	switch ( form ) {
+		case 'instrumental': // instrumental
+			word = 'z ' + word;
+			break;
+		case 'lokatiw': // lokatiw
+			word = 'wo ' + word;
+			break;
+		}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/hu.js b/resources/mediawiki.language/languages/hu.js
new file mode 100644
index 0000000000..eb3f1f3a49
--- /dev/null
+++ b/resources/mediawiki.language/languages/hu.js
@@ -0,0 +1,23 @@
+/**
+ *  Hungarian language functions
+ *  @author Santhosh Thottingal
+ */
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'hu', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	switch ( form ) {
+		case 'rol':
+			word += 'ról';
+			break;
+		case 'ba':
+			word += 'ba';
+			break;
+		case 'k':
+			word += 'k';
+			break;
+	}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/hy.js b/resources/mediawiki.language/languages/hy.js
index 734c26df54..b51b2b676f 100644
--- a/resources/mediawiki.language/languages/hy.js
+++ b/resources/mediawiki.language/languages/hy.js
@@ -6,3 +6,27 @@ mediaWiki.language.convertPlural = function( count, forms ) {
 	forms = mediaWiki.language.preConvertPlural( forms, 2 );
 	return ( Math.abs( count ) <= 1 ) ? forms[0] : forms[1];
 };
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'hy', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+
+	// These rules are not perfect, but they are currently only used for site names so it doesn't
+	// matter if they are wrong sometimes. Just add a special case for your site name if necessary.
+
+	switch ( form ) {
+		case 'genitive': // Õ½Õ¥Õ¼Õ¡Õ¯Õ¡Õ¶ Õ°Õ¸Õ¬Õ¸Õ¾
+			if ( word.substr( -1 ) === 'Õ¡' )
+				word = word.substr( 0, word.length -1 )  + 'Õ¡ÕµÕ«';
+			else if ( word.substr( -1 ) === 'Õ¸' )
+				word = word.substr( 0, word.length - 1 ) + 'Õ¸ÕµÕ«';
+			else if ( word.substr( -4 ) === 'գիրք' )
+				word = word.substr( 0, word.length - 4 ) + 'գրքի';
+			else
+				word = word + 'Õ«';
+			break;
+		}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/la.js b/resources/mediawiki.language/languages/la.js
new file mode 100644
index 0000000000..313bb1c202
--- /dev/null
+++ b/resources/mediawiki.language/languages/la.js
@@ -0,0 +1,50 @@
+/**
+ * Latin (lingua Latina) language functions
+ * @author Santhosh Thottingal
+ */
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'la', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	switch ( form ) {
+		case 'genitive':
+			// only a few declensions, and even for those mostly the singular only
+			word = word.replace( /u[ms]$/i, 'i' ); // 2nd declension singular
+			word = word.replace( /ommunia$/i, 'ommunium' ); // 3rd declension neuter plural (partly)
+			word = word.replace( /a$/i, 'ae' ); // 1st declension singular
+			word = word.replace( /libri$/i,'librorum' ); // 2nd declension plural (partly)
+			word = word.replace( /nuntii$/i, 'nuntiorum' ); // 2nd declension plural (partly)
+			word = word.replace( /tio$/i,'tionis' ); // 3rd declension singular (partly)
+			word = word.replace( /ns$/i, 'ntis' );
+			word = word.replace( /as$/i, 'atis' );
+			word = word.replace( /es$/i ,'ei' ); // 5th declension singular
+			break;
+		case 'accusative':
+			// only a few declensions, and even for those mostly the singular only
+			word = word.replace( /u[ms]$/i, 'um' ); // 2nd declension singular
+			word = word.replace( /ommunia$/i, 'am' ); // 3rd declension neuter plural (partly)
+			word = word.replace( /a$/i, 'ommunia' ); // 1st declension singular
+			word = word.replace( /libri$/i,'libros' ); // 2nd declension plural (partly)
+			word = word.replace( /nuntii$/i, 'nuntios' );// 2nd declension plural (partly)
+			word = word.replace( /tio$/i,'tionem' ); // 3rd declension singular (partly)
+			word = word.replace( /ns$/i, 'ntem' );
+			word = word.replace( /as$/i, 'atem');
+			word = word.replace( /es$/i ,'em' ); // 5th declension singular
+			break;
+		case 'ablative':
+			// only a few declensions, and even for those mostly the singular only
+			word = word.replace( /u[ms]$/i, 'o' ); // 2nd declension singular
+			word = word.replace( /ommunia$/i, 'ommunibus' ); // 3rd declension neuter plural (partly)
+			word = word.replace( /a$/i, 'a' ); // 1st declension singular
+			word = word.replace( /libri$/i,'libris' ); // 2nd declension plural (partly)
+			word = word.replace( /nuntii$/i, 'nuntiis' ); // 2nd declension plural (partly)
+			word = word.replace( /tio$/i,'tione' ); // 3rd declension singular (partly)
+			word = word.replace( /ns$/i, 'nte' );
+			word = word.replace( /as$/i, 'ate');
+			word = word.replace( /es$/i ,'e' ); // 5th declension singular
+			break;
+	}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/os.js b/resources/mediawiki.language/languages/os.js
new file mode 100644
index 0000000000..431e38c808
--- /dev/null
+++ b/resources/mediawiki.language/languages/os.js
@@ -0,0 +1,69 @@
+/**
+ * Ossetian (Ирон) language functions
+ * @author Santhosh Thottingal
+ */
+
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'os', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	// Ending for allative case
+	var end_allative = 'мæ';
+	// Variable for 'j' beetwen vowels
+	var jot = '';
+	// Variable for "-" for not Ossetic words
+	var hyphen = '';
+	// Variable for ending
+	var ending = '';
+	// Checking if the $word is in plural form
+	if ( word.match( /тæ$/i ) ) {
+		word = word.substring( 0, word.length - 1 );
+		end_allative = 'æм';
+	}
+	// Works if word is in singular form.
+	// Checking if word ends on one of the vowels: е, ё, и, о, ы, э, ю, я.
+	else if ( word.match( /[аæеёиоыэюя]$/i ) ) {
+		jot = 'й';
+	}
+	// Checking if word ends on 'у'. 'У' can be either consonant 'W' or vowel 'U' in cyrillic Ossetic.
+	// Examples: {{grammar:genitive|аунеу}} = аунеуы, {{grammar:genitive|лæппу}} = лæппуйы.
+	else if ( word.match( /у$/i ) ) {
+		if ( ! word.substring( word.length-2, word.length-1 ).match( /[аæеёиоыэюя]$/i ) ) {
+			jot = 'й';
+		}
+	} else if ( !word.match( /[бвгджзйклмнопрстфхцчшщьъ]$/i ) ) {
+		hyphen = '-';
+	}
+
+	switch ( form ) {
+		case 'genitive':
+			ending = hyphen + jot + 'ы';
+			break;
+		case 'dative':
+			ending = hyphen + jot + 'æн';
+			break;
+		case 'allative':
+			ending = hyphen + end_allative;
+			break;
+		case 'ablative':
+			if ( jot == 'й' ) {
+				ending = hyphen + jot + 'æ';
+			}
+			else {
+				ending = hyphen + jot + 'æй';
+			}
+			break;
+		case 'superessive':
+			ending = hyphen + jot + 'ыл';
+			break;
+		case 'equative':
+			ending = hyphen + jot + 'ау';
+			break;
+		case 'comitative':
+			ending = hyphen + 'имæ';
+			break;
+	}
+	return word + ending;
+};
diff --git a/resources/mediawiki.language/languages/ru.js b/resources/mediawiki.language/languages/ru.js
index 17c9293165..42be4f9d75 100644
--- a/resources/mediawiki.language/languages/ru.js
+++ b/resources/mediawiki.language/languages/ru.js
@@ -21,3 +21,29 @@ mediaWiki.language.convertPlural = function( count, forms ) {
 			return forms[2];
 	}
 };
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'ru', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	switch ( form ) {
+		case 'genitive': // родительный падеж
+			if ( (  word.substr( word.length - 4 )  == 'вики' ) || (  word.substr( word.length - 4 ) == 'Вики' ) ) {
+			}
+			else if ( word.substr( word.length - 1 ) == 'ь' )
+				word = word.substr(0, word.length - 1 ) + 'я';
+			else if ( word.substr( word.length - 2 ) == 'ия' )
+				word = word.substr(0, word.length - 2 ) + 'ии';
+			else if ( word.substr( word.length - 2 ) == 'ка' )
+				word = word.substr(0, word.length - 2 ) + 'ки';
+			else if ( word.substr( word.length - 2 )  == 'ти' )
+				word = word.substr(0, word.length - 2 ) + 'тей';
+			else if ( word.substr( word.length - 2 ) == 'ды' )
+				word = word.substr(0, word.length - 2 ) + 'дов';
+			else if ( word.substr( word.length - 3 ) == 'ник' )
+				word = word.substr(0, word.length - 3 ) + 'ника';
+			break;
+	}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/sl.js b/resources/mediawiki.language/languages/sl.js
index a887e0e082..cfb578126b 100644
--- a/resources/mediawiki.language/languages/sl.js
+++ b/resources/mediawiki.language/languages/sl.js
@@ -18,3 +18,19 @@ mediaWiki.language.convertPlural = function( count, forms ) {
 	}
 	return forms[4];
 };
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'sl', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	switch ( form ) {
+		case 'mestnik': // locative
+			word = 'o ' + word;
+			break;
+		case 'orodnik': // instrumental
+			word = 'z ' + word;
+			break;
+	}
+	return word;
+};
diff --git a/resources/mediawiki.language/languages/uk.js b/resources/mediawiki.language/languages/uk.js
index 5c1294e75d..372d441905 100644
--- a/resources/mediawiki.language/languages/uk.js
+++ b/resources/mediawiki.language/languages/uk.js
@@ -21,3 +21,35 @@ mediaWiki.language.convertPlural = function( count, forms ) {
 			return forms[2];
 	}
 };
+
+mediaWiki.language.convertGrammar = function( word, form ) {
+	var grammarForms = mw.language.getData( 'uk', 'grammarForms' );
+	if ( grammarForms && grammarForms[form] ) {
+		return grammarForms[form][word] ;
+	}
+	switch ( form ) {
+		case 'genitive': // родовий відмінок
+			if ( (  word.substr( word.length - 4 ) == 'вікі' ) || (  word.substr( word.length - 4 ) == 'Вікі' ) ) {
+			}
+			else if ( word.substr( word.length - 1 ) == 'ь' )
+				word = word.substr(0, word.length - 1 ) + 'я';
+			else if ( word.substr( word.length - 2 ) == 'ія' )
+				word = word.substr(0, word.length - 2 ) + 'ії';
+			else if ( word.substr( word.length - 2 ) == 'ка' )
+				word = word.substr(0, word.length - 2 ) + 'ки';
+			else if ( word.substr( word.length - 2 )  == 'ти' )
+				word = word.substr(0, word.length - 2 ) + 'тей';
+			else if ( word.substr( word.length - 2 ) == 'ды' )
+				word = word.substr(0, word.length - 2 ) + 'дов';
+			else if ( word.substr( word.length - 3 ) == 'ник' )
+				word = word.substr(0, word.length - 3 ) + 'ника';
+			break;
+		case 'accusative': // знахідний відмінок
+			if ( (  word.substr( word.length - 4 ) == 'вікі' ) || (  word.substr( word.length - 4 ) == 'Вікі' ) ) {
+			}
+			else if ( word.substr( word.length - 2 ) == 'ія' )
+				word = word.substr(0, word.length - 2 ) + 'ію';
+			break;
+	}
+	return word;
+};