add test cases and adjust (reduce) the transliteration (#37)

* update tests * revisit transliteration * add more test cases and adjust the transliteration * bump version
alpancs · Mar 20, 2024 · c75f530 · c75f530
1 parent 7f4143b
commit c75f530
Show file tree

Hide file tree

Showing 3 changed files with 19 additions and 14 deletions.
diff --git a/Cargo.toml b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "quranize"
-version = "0.11.1"
+version = "0.11.2"
 authors = ["Alfan Nur Fauzan <[email protected]>"]
 edition = "2021"
 description = "Encoding transliterations into Quran forms."

diff --git a/src/quranize.rs b/src/quranize.rs
@@ -207,7 +207,7 @@ mod tests {
 
     #[test]
     fn test_quranize_default() {
-        let q = Quranize::new(70);
+        let q = Quranize::default();
         assert_eq!(q.e("allah"), vec!["اللَّهَ", "اللَّهُ", "ءاللَّهُ", "اللَّهِ"]);
         assert_eq!(q.e("illa billah"), vec!["إِلّا بِاللَّهِ"]);
         assert_eq!(q.e("alquran"), vec!["القُرءانَ", "القُرءانُ", "القُرءانِ"]);
@@ -225,6 +225,7 @@ mod tests {
         assert_eq!(q.e("qulhuwallahuahad"), vec!["قُل هُوَ اللَّهُ أَحَدٌ"]);
         assert_eq!(q.e("alla tahzani"), vec!["أَلّا تَحزَنى"]);
         assert_eq!(q.e("innasya niaka"), vec!["إِنَّ شانِئَكَ"]);
+        assert_eq!(q.e("innasya ni'aka"), vec!["إِنَّ شانِئَكَ"]);
         assert_eq!(q.e("wasalamun alaihi"), vec!["وَسَلٰمٌ عَلَيهِ"]);
         assert_eq!(q.e("ulaika hum"), vec!["أُولٰئِكَ هُم", "أُولٰئِكَ هُمُ"]);
         assert_eq!(q.e("waladdoollin"), vec!["وَلَا الضّالّينَ"]);
@@ -235,11 +236,14 @@ mod tests {
         assert_eq!(q.e("robbil alamin"), vec!["رَبِّ العٰلَمينَ"]);
         assert_eq!(q.e("husnul maab"), vec!["حُسنُ المَـٔابِ"]);
         assert_eq!(q.e("kufuwan"), vec!["كُفُوًا"]);
+        assert_eq!(q.e("yukhodiun"), vec!["يُخٰدِعونَ"]);
+        assert_eq!(q.e("indallah"), vec!["عِندَ اللَّهِ", "عِندِ اللَّهِ"]);
+        assert_eq!(q.e("alimul ghoibi"), vec!["عٰلِمُ الغَيبِ"]);
     }
 
     #[test]
     fn test_first_aya() {
-        let q = Quranize::new(70);
+        let q = Quranize::new(25);
         assert_eq!(q.e("alif lam mim"), vec!["الم"]);
         assert_eq!(q.e("alif laaam miiim"), vec!["الم"]);
         assert_eq!(q.e("nuun"), vec!["ن"]);
@@ -249,7 +253,7 @@ mod tests {
 
     #[test]
     fn test_alfatihah() {
-        let q = Quranize::default();
+        let q = Quranize::new(100);
         assert_eq!(
             q.e("bismillahirrohmanirrohiim"),
             vec!["بِسمِ اللَّهِ الرَّحمٰنِ الرَّحيمِ"]
@@ -273,7 +277,7 @@ mod tests {
 
     #[test]
     fn test_al_ikhlas() {
-        let q = Quranize::new(70);
+        let q = Quranize::new(50);
         assert_eq!(q.e("qulhuwallahuahad"), vec!["قُل هُوَ اللَّهُ أَحَدٌ"]);
         assert_eq!(q.e("allahussomad"), vec!["اللَّهُ الصَّمَدُ"]);
         assert_eq!(q.e("lam yalid walam yulad"), vec!["لَم يَلِد وَلَم يولَد"]);

diff --git a/src/quranize/transliterations.rs b/src/quranize/transliterations.rs
@@ -8,13 +8,13 @@ pub(super) fn map(c: char) -> &'static [&'static str] {
     match c {
         SPACE => &[""],
 
-        LETTER_HAMZA => &["'", "k", "a", "i", "u"],
-        LETTER_ALEF_WITH_MADDA_ABOVE => &["a", "'a", "aa"],
-        LETTER_ALEF_WITH_HAMZA_ABOVE => &["'", "k", "a", "u"],
-        LETTER_WAW_WITH_HAMZA_ABOVE => &["'", "k", "u"],
+        LETTER_HAMZA => &["'", "a"],
+        LETTER_ALEF_WITH_MADDA_ABOVE => &["a", "aa"],
+        LETTER_ALEF_WITH_HAMZA_ABOVE => &["a", "u"],
+        LETTER_WAW_WITH_HAMZA_ABOVE => &["u"],
         LETTER_ALEF_WITH_HAMZA_BELOW => &["i"],
-        LETTER_YEH_WITH_HAMZA_ABOVE => &["'", "k", "a", "i"],
-        LETTER_ALEF => &["a", "o", "aa", "oo"],
+        LETTER_YEH_WITH_HAMZA_ABOVE => &["'", "a", "i"],
+        LETTER_ALEF => &["a", "aa", "o", "oo"],
         LETTER_BEH => &["b"],
         LETTER_TEH_MARBUTA => &["h", "t"],
         LETTER_TEH => &["t"],
@@ -32,7 +32,7 @@ pub(super) fn map(c: char) -> &'static [&'static str] {
         LETTER_DAD => &["d", "dh", "dz"],
         LETTER_TAH => &["t", "th"],
         LETTER_ZAH => &["d", "dh", "dz"],
-        LETTER_AIN => &["'", "'a", "'i", "'u", "k", "a", "i", "u"],
+        LETTER_AIN => &["'", "a", "u", "i", "k"],
         LETTER_GHAIN => &["g", "gh"],
 
         TATWEEL => &["a", "o"],
@@ -44,9 +44,9 @@ pub(super) fn map(c: char) -> &'static [&'static str] {
         LETTER_MEEM => &["m"],
         LETTER_NOON => &["n"],
         LETTER_HEH => &["h"],
-        LETTER_WAW => &["w", "u"],
+        LETTER_WAW => &["w", "u", "uu"],
         LETTER_ALEF_MAKSURA => &["a", "o", "i"],
-        LETTER_YEH => &["y", "i", "ii", "iya", "iyi", "iyu"],
+        LETTER_YEH => &["y", "i", "ii"],
 
         FATHATAN => &["an", "on", ""],
         DAMMATAN => &["un", ""],
@@ -67,6 +67,7 @@ pub(super) fn contextual_map(c0: char, c1: char) -> &'static [&'static str] {
         (SPACE, LETTER_ALEF)
         | (LETTER_HAMZA, LETTER_ALEF)
         | (LETTER_ALEF, LETTER_LAM)
+        | (LETTER_AIN, LETTER_WAW)
         | (LETTER_AIN, LETTER_SUPERSCRIPT_ALEF)
         | (LETTER_WAW, LETTER_ALEF)
         | (FATHATAN, LETTER_ALEF)