From c00bd53c2a2bb7fc1bedb73eedf8ad0f225fdabd Mon Sep 17 00:00:00 2001
From: bgo-eiu <100172442+bgo-eiu@users.noreply.github.com>
Date: Sun, 28 Aug 2022 18:06:56 -0400
Subject: [PATCH] addressed overapplication of virama, normalized nukta
 characters

addresses https://phabricator.wikimedia.org/T91159
---
 rules/pa/pa-transliteration.js | 118 ++++++++++++++++++---------------
 1 file changed, 63 insertions(+), 55 deletions(-)

diff --git a/rules/pa/pa-transliteration.js b/rules/pa/pa-transliteration.js
index 33bbf4f13..8aaae73b7 100644
--- a/rules/pa/pa-transliteration.js
+++ b/rules/pa/pa-transliteration.js
@@ -5,11 +5,11 @@
 		id: 'pa-transliteration',
 		name: 'Punjabi Transliteration',
 		description: 'Punjabi transliteration',
-		date: '2012-10-16',
+		date: '2022-08-28',
 		URL: 'http://github.com/wikimedia/jquery.ime',
-		author: 'Amir E. Aharoni, inputs from Saurabh Choudhary and Surinder Wadhawan',
+		author: 'Amir E. Aharoni, inputs from Saurabh Choudhary, Surinder Wadhawan, bgo_eiu',
 		license: 'GPLv3',
-		version: '1.0',
+		version: '2.0',
 		contextLength: 2,
 		maxKeyLength: 4,
 		/* Semi-automatically created from the Hindi transliteration mapping using
@@ -17,23 +17,23 @@
 		 * s{(?<deva_letter>[ऀ-ॿ])}{chr(ord($+{deva_letter}) + 0x100)}xmsge;
 		 */
 		patterns: [
-			[ 'ਕ੍h', 'c', 'ਚ੍' ],
+			[ 'ਕh', 'c', 'ਚ' ],
 			[ '\\\\([A-Za-z\\>_~\\.0-9])', '\\\\', '$1' ],
 
 			// ਕ-ਹ is the main range of Indic letters.
-			// ੜ is an additional unique Gurmukhi letter.
-			[ '([ਕ-ਹੜ]਼?)੍a', '$1' ], // Short [a] after a consonant with virama removes the virama
-			[ '([ਕ-ਹੜ]਼?)੍A', '$1ਾ' ], // Long [a] after a consonant with virama removes the virama and adds long [a]
-			[ '([ਕ-ਹੜ]਼?)a', '$1ਾ' ], // 'aa' gives long [a] - short [a] after a consonant without virama adds long [a]
-			[ '([ਕ-ਹੜ]਼?)੍i', '$1ਿ' ],
-			[ '([ਕ-ਹੜ]਼?)(ਿi|੍I|ੇe)', '$1ੀ' ], // 'ii', 'I' and 'ee' give long [i].
-			[ '([ਕ-ਹੜ]਼?)੍u', '$1ੁ' ],
-			[ '([ਕ-ਹੜ]਼?)(ੁu|੍U|ੋo)', '$1ੂ' ], // 'uu', 'U' and 'oo' give long [u].
-			[ '([ਕ-ਹੜ]਼?)੍e', '$1ੇ' ],
-			[ '([ਕ-ਹੜ]਼?)(i|੍E)', '$1ੈ' ], // 'i' after a consonant without virama or 'E' after a consonant with Virama gives "ai"
-			[ '([ਕ-ਹੜ]਼?)੍[oO]', '$1ੋ' ],
-			[ '([ਕ-ਹੜ]਼?)u', '$1ੌ' ], // 'u' after a consonant without virama gives "au"
-			[ '([ਕ-ਹੜ])੍\\`', '$1਼੍' ], // '`' (backtick) after a consonant with virama adds a nukta before the virama
+			// ਖ਼, ਗ਼, ਜ਼, ੜ, ਫ਼ is are additional Gurmukhi letters.
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼]਼?)', '$1' ],
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼]਼?)a', '$1ਾ' ], // 'a' after a consonant adds long [a]
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼]਼?)i', '$1ਿ' ],
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼]਼?)(ਿi|I|ੇe)', '$1ੀ' ], // 'ii', 'I' and 'ee' give long [i].
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼]਼?)u', '$1ੁ' ],
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼]਼?)(ੁu|U|ੋo)', '$1ੂ' ], // 'uu', 'U' and 'oo' give long [u].
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼]਼?)e', '$1ੇ' ],
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼]਼?)E', '$1ੈ' ], // 'E' after a consonant gives "ai"
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼]਼?)o', '$1ੋ' ],
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼]਼?)O', '$1ੌ' ], // 'u' after a consonant gives "au"
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼])~', '$1ੑ' ], // '~' after a consonant adds virama
+			[ '([ਕ-ਹਖ਼ਗ਼ਜ਼ੜਫ਼])੍\\`', '$1਼੍' ], // '`' (backtick) after a consonant with virama adds a nukta before the virama
 
 			[ 'ਅa', 'ਆ' ], // aa
 			[ '(ਓo|ਉu)', 'ਊ' ], // oo, uu
@@ -43,61 +43,68 @@
 			[ '(ਏe|ਇi)', 'ਈ' ], // ee, ii
 			[ 'ਅu', 'ਔ' ], // au
 			[ 'ਂ[Mm^]', 'ਁ' ], // bindi + 'm', 'M', or '^' -> Adak bindi
-			[ 'ਣ੍N', 'ੰ' ], // Tippi - nasalization
+			[ 'ਣN', 'ੰ' ], // Tippi - nasalization
 
-			[ 'ਕ੍h', 'ਖ੍' ], // kh
-			[ 'ਗ੍h', 'ਘ੍' ], // gh
-			[ 'ਨ੍g', 'ਙ੍' ], // ng
-			[ 'ਚ੍h', 'ਛ੍' ], // ch
-			[ 'ਜ੍h', 'ਝ੍' ], // jh
-			[ 'ਨ੍j', 'ਞ੍' ], // nj
-			[ 'ਟ੍h', 'ਠ੍' ], // Th
-			[ 'ਡ੍h', 'ਢ੍' ], // Dh
-			[ 'ਤ੍h', 'ਥ੍' ], // th
-			[ 'ਦ੍h', 'ਧ੍' ], // dh
-			[ 'ਪ੍h', 'ਫ੍' ], // ph
-			[ 'ਬ੍h', 'ਭ੍' ], // bh
+			[ 'ਕh', 'ਖ' ], // kh
+			[ 'ਗh', 'ਘ' ], // gh
+			[ 'ਨg', 'ਙ' ], // ng
+			[ 'ਚh', 'ਛ' ], // ch
+			[ 'ਜh', 'ਝ' ], // jh
+			[ 'ਨj', 'ਞ' ], // nj
+			[ 'ਟh', 'ਠ' ], // Th
+			[ 'ਡh', 'ਢ' ], // Dh
+			[ 'ਤh', 'ਥ' ], // th
+			[ 'ਦh', 'ਧ' ], // dh
+			[ 'ਪh', 'ਫ' ], // ph
+			[ 'ਬh', 'ਭ' ], // bh
 
-			[ 'ਸ੍h', 'ਸ਼੍' ], // sh
-			[ 'ਕ਼੍h', 'ਖ਼੍' ], // k + nukta + h
+			[ 'ਸh', 'ਸ਼' ], // sh
+			[ 'ਕ਼h', 'ਖ਼' ], // k + nukta + h
 
 			[ 'a', 'ਅ' ],
-			[ 'b', 'ਬ੍' ],
-			[ 'c', 'ਚ੍' ],
-			[ 'd', 'ਦ੍' ],
+			[ 'b', 'ਬ' ],
+			[ 'c', 'ਚ' ],
+			[ 'd', 'ਦ' ],
 			[ 'e', 'ਏ' ],
-			[ 'f', 'ਫ੍' ],
-			[ 'F', 'ਫ਼੍' ], // With nukta
-			[ 'g', 'ਗ੍' ],
-			[ 'h', 'ਹ੍' ],
+			[ 'f', 'ਫ' ],
+			[ 'F', 'ਫ਼' ],
+			[ 'g', 'ਗ' ],
+			[ 'h', 'ਹ' ],
 			[ 'i', 'ਇ' ],
-			[ 'j', 'ਜ੍' ],
-			[ 'k', 'ਕ੍' ],
-			[ 'l', 'ਲ੍' ],
-			[ 'm', 'ਮ੍' ],
-			[ 'n', 'ਨ੍' ],
+			[ 'j', 'ਜ' ],
+			[ 'k', 'ਕ' ],
+			[ 'l', 'ਲ' ],
+			[ 'm', 'ਮ' ],
+			[ 'n', 'ਨ' ],
 			[ 'o', 'ਓ' ],
-			[ 'p', 'ਪ੍' ],
-			[ 'q', 'ੑ' ], // Udaat
-			[ 'r', 'ਰ੍' ],
-			[ 's', 'ਸ੍' ],
-			[ 't', 'ਤ੍' ],
+			[ 'p', 'ਪ' ],
+			[ 'q', 'ਕ਼' ],
+			[ 'r', 'ਰ' ],
+			[ 's', 'ਸ' ],
+			[ 't', 'ਤ' ],
 			[ 'u', 'ਉ' ],
 			[ '(v|w)', 'ਵ੍' ],
 			[ 'y', 'ਯ੍' ],
 			[ 'z', 'ੱ' ], // Addak - gemination
 			[ 'A', 'ਆ' ],
-			[ 'D', 'ਡ੍' ],
+			[ 'D', 'ਡ' ],
+			[ 'F', 'ਫ਼' ],
+			[ 'G', 'ਗ਼' ],
 			[ 'H', 'ਃ' ], // Visarga
 			[ 'I', 'ਈ' ],
+			[ 'J', 'ਜ਼' ],
+			[ 'K', 'ਖ਼' ],
+			[ 'L', 'ਲ਼'],
 			[ 'M', 'ਂ' ], // Bindi
-			[ 'N', 'ਣ੍' ],
-			[ 'R', 'ੜ੍' ], // Rra
-			[ 'S', 'ਸ਼੍' ],
-			[ 'T', 'ਟ੍' ],
+			[ 'N', 'ਣ' ],
+			[ 'Q', 'ੑ'], // Udaat
+			[ 'R', 'ੜ' ], // Rra
+			[ 'S', 'ਸ਼' ],
+			[ 'T', 'ਟ' ],
 			[ 'U', 'ਊ' ],
 			[ 'X', 'ੴ' ], // Ek onkar
 			[ 'Y', 'ੵ' ], // Yakash
+			[ 'Z', '.' ],
 			[ '0', '੦' ],
 			[ '1', '੧' ],
 			[ '2', '੨' ],
@@ -112,7 +119,8 @@
 			[ '\\`', '਼' ], // Nukta
 
 			[ '।\\.', '॥' ], // Double danda, must be before single danda
-			[ '\\.', '।' ] ] // Danda
+			[ '\\.', '।' ] // Danda
+		]
 	};
 
 	$.ime.register( paTransliteration );