interscript-maps 2.0.5

data/maps/alalc-ell-Grek-Latn-2010.imp

@@ -0,0 +1,382 @@
+metadata {
+  authority_id: alalc
+  id: 2010
+  language: iso-639-2:ell
+  source_script: Grek
+  destination_script: Latn
+  name: Greek Romanization, 2010
+  url: http://catdir.loc.gov/catdir/cpso/romanization/greek.pdf
+  creation_date: 2010
+  description: |
+    ALA-LC Romanization table for Greek
+
+  notes:
+    - Applies to texts after 1453 (Modern Greek)
+    - This table presupposes monotonic accentuation; rough breathings are accordingly not addressed.
+    - Generalised gramma digraph rule to capitals
+}
+
+tests {
+  test "Ένα πράμα μόνον με παρακίνησε κι εμένα να γράψω ότι τούτην την πατρίδα την έχομεν όλοι μαζί, και σοφοί κι αμαθείς και πλούσιοι και φτωχοί και πολιτικοί και στρατιωτικοί και οι πλέον μικρότεροι άνθρωποι· όσοι αγωνιστήκαμεν, αναλόγως ο καθείς, έχομεν να ζήσομεν εδώ. Το λοιπόν δουλέψαμεν όλοι μαζί, να την φυλάμεν κι όλοι μαζί και να μην λέγει ούτε ο δυνατός «εγώ» ούτε ο αδύνατος. Ξέρετε πότε να λέγει ο καθείς «εγώ»; Όταν αγωνιστεί μόνος του και φκιάσει ή χαλάσει, να λέγει «εγώ»· όταν όμως αγωνίζονται πολλοί και φκιάνουν, τότε να λένε «εμείς». Είμαστε εις το «εμείς» κι όχι εις το «εγώ». Και εις το εξής να μάθομεν γνώση, αν θέλομεν να φκιάσομεν χωριόν, να ζήσομεν όλοι μαζί.\n\nΓιάννης Μακρυγιάννης.\n", "Ena prama monon me parakinēse ki emena na grapsō oti toutēn tēn patrida tēn echomen oloi mazi, kai sophoi ki amatheis kai plousioi kai phtōchoi kai politikoi kai stratiōtikoi kai oi pleon mikroteroi anthrōpoi; osoi agōnistēkamen, analogōs o katheis, echomen na zēsomen edō. To loipon doulepsamen oloi mazi, na tēn phylamen ki oloi mazi kai na mēn legei oute o dynatos «egō» oute o adynatos. Xerete pote na legei o katheis «egō»? Otan agōnistei monos tou kai phkiasei ē chalasei, na legei «egō»; otan omōs agōnizontai polloi kai phkianoun, tote na lene «emeis». Eimaste eis to «emeis» ki ochi eis to «egō». Kai eis to exēs na mathomen gnōsē, an thelomen na phkiasomen chōrion, na zēsomen oloi mazi.\n\nGiannēs Makrygiannēs.\n"
+  test "ΑΘΗΝΑ", "ATHĒNA"
+  test "μπαμπάκι", "bampaki"
+  test "νταντά", "ḏanta"
+  test "γκέγκε", "gkenke"
+  test "Γκαμπόν", "Gkampon"
+  test "Μάγχη", "Manchē"
+  test "κογξ", "konx"
+  test "υιός", "uios"
+  test "Υιός", "Uios"
+  test "νεράντζι", "nerantzi"
+  test "Γοίθιος", "Goithios"
+  test "μπέικον", "beikon"
+  test "μπέϊκον", "beikon"
+  test "βόλεϊ", "volei"
+  test "αθεΐα", "atheia"
+  test "Εϊγιαφιάτλαγιοκουτλ", "Eigiaphiatlagiokoutl"
+  test "Εΐτζι", "Eitzi"
+  test "Μυρτώο", "Myrtōo"
+  test "αέρας", "aeras"
+  test "γαυ γαυ", "gau gau"
+  test "Ταΰγετος", "Taygetos"
+  test "σπρέυ", "sprey"
+  test "Αθήνα", "Athēna"
+  test "Άγιον Όρος", "Agion Oros"
+  test "Άγραφα", "Agrapha"
+  test "Αγρίνιο", "Agrinio"
+  test "Αίγινα", "Aigina"
+  test "Αίγιο", "Aigio"
+  test "Αλεξανδρούπολη", "Alexandroupolē"
+  test "Αλεποχώρι", "Alepochōri"
+  test "Αμοργός", "Amorgos"
+  test "Άμφισσα", "Amphissa"
+  test "Αράχωβα", "Arachōva"
+  test "Άργος", "Argos"
+  test "Αρκαδία", "Arkadia"
+  test "Άρτα", "Arta"
+  test "Βελούχι", "Velouchi"
+  test "Βέροια", "Veroia"
+  test "Βοιωτία", "Voiōtia"
+  test "Βόλος", "Volos"
+  test "Βόνιτσα", "Vonitsa"
+  test "Γαλαξίδι", "Galaxidi"
+  test "Γαλάτσι", "Galatsi"
+  test "Γιαννιτσά", "Giannitsa"
+  test "Γλυφάδα", "Glyphada"
+  test "Γρανίτσα", "Granitsa"
+  test "Γρεβενά", "Grevena"
+  test "Γύθειο", "Gytheio"
+  test "Διόνυσος", "Dionysos"
+  test "Δίστομο", "Distomo"
+  test "Δολιανά", "Doliana"
+  test "Δράμα", "Drama"
+  test "Δωδεκάνησα", "Dōdekanēsa"
+  test "Έδεσσα", "Edessa"
+  test "Ελευσίνα", "Eleusina"
+  test "Επίδαυρος", "Epidauros"
+  test "Επτάνησα", "Eptanēsa"
+  test "Ερμούπολη", "Ermoupolē"
+  test "Εύβοια", "Euvoia"
+  test "Ζάκυνθος", "Zakynthos"
+  test "Ήπειρος", "Ēpeiros"
+  test "Ηράκλειο", "Ērakleio"
+  test "Θάσος", "Thasos"
+  test "Θεσσαλονίκη", "Thessalonikē"
+  test "Θεσσαλία", "Thessalia"
+  test "Θεσπρωτία", "Thesprōtia"
+  test "Θήβα", "Thēva"
+  test "Θράκη", "Thrakē"
+  test "Ιθάκη", "Ithakē"
+  test "Ίος", "Ios"
+  test "Ιωάννινα", "Iōannina"
+  test "Καβάλα", "Kavala"
+  test "Καλάβρυτα", "Kalavryta"
+  test "Καλαμάτα", "Kalamata"
+  test "Καλαμπάκα", "Kalampaka"
+  test "Καλύβια", "Kalyvia"
+  test "Κάλυμνος", "Kalymnos"
+  test "Καρδίτσα", "Karditsa"
+  test "Καρπενήσι", "Karpenēsi"
+  test "Κάρυστος", "Karystos"
+  test "Καστελλόριζο", "Kastellorizo"
+  test "Καστοριά", "Kastoria"
+  test "Κατερίνη", "Katerinē"
+  test "Κάτω Αχαΐα", "Katō Achaia"
+  test "Κερατέα", "Keratea"
+  test "Κέρκυρα", "Kerkyra"
+  test "Κεφαλλονιά", "Kephallonia"
+  test "Κηφισιά", "Kēphisia"
+  test "Κιλκίς", "Kilkis"
+  test "Κοζάνη", "Kozanē"
+  test "Κολωνός", "Kolōnos"
+  test "Κομοτηνή", "Komotēnē"
+  test "Κόρινθος", "Korinthos"
+  test "Κορώνη", "Korōnē"
+  test "Κρανίδι", "Kranidi"
+  test "Κρέστενα", "Krestena"
+  test "Κρήτη", "Krētē"
+  test "Κύθηρα", "Kythēra"
+  test "Κυκλάδες", "Kyklades"
+  test "Κύμη", "Kymē"
+  test "Κυψέλη", "Kypselē"
+  test "Κως", "Kōs"
+  test "Λαγκαδάς", "Lankadas"
+  test "Λαμία", "Lamia"
+  test "Λάρισα", "Larisa"
+  test "Λαύριο", "Laurio"
+  test "Λέρος", "Leros"
+  test "Λέσβος", "Lesvos"
+  test "Λευκάδα", "Leukada"
+  test "Λήμνος", "Lēmnos"
+  test "Λιβαδειά", "Livadeia"
+  test "Μακεδονία", "Makedonia"
+  test "Μάνη", "Manē"
+  test "Μαραθώνας", "Marathōnas"
+  test "Μαρκόπουλο", "Markopoulo"
+  test "Μαρούσι", "Marousi"
+  test "Μέγαρα", "Megara"
+  test "Μεσολόγγι", "Mesolongi"
+  test "Μεταξουργείο", "Metaxourgeio"
+  test "Μέτσοβο", "Metsovo"
+  test "Μήλος", "Mēlos"
+  test "Μύκονος", "Mykonos"
+  test "Μυστράς", "Mystras"
+  test "Μυτιλήνη", "Mytilēnē"
+  test "Νάξος", "Naxos"
+  test "Νάουσα", "Naousa"
+  test "Ναύπακτος", "Naupaktos"
+  test "Ναύπλιο", "Nauplio"
+  test "Νέα Σμύρνη", "Nea Smyrnē"
+  test "Νίσυρος", "Nisyros"
+  test "Ξάνθη", "Xanthē"
+  test "Όλυμπος", "Olympos"
+  test "Παγκράτι", "Pankrati"
+  test "Παπάγου", "Papagou"
+  test "Πάρος", "Paros"
+  test "Πασαλιμάνι", "Pasalimani"
+  test "Πατήσια", "Patēsia"
+  test "Πάτμος", "Patmos"
+  test "Πάτρα", "Patra"
+  test "Πειραιάς", "Peiraias"
+  test "Πελοπόννησος", "Peloponnēsos"
+  test "Περιστέρι", "Peristeri"
+  test "Πεύκη", "Peukē"
+  test "Πήλιο", "Pēlio"
+  test "Πολύγυρος", "Polygyros"
+  test "Πόρος", "Poros"
+  test "Πρέβεζα", "Preveza"
+  test "Πτολεμαΐδα", "Ptolemaida"
+  test "Πύλος", "Pylos"
+  test "Πύργος", "Pyrgos"
+  test "Ρέθυμνο", "Rethymno"
+  test "Ρόδος", "Rodos"
+  test "Ρούμελη", "Roumelē"
+  test "Σαλαμίνα", "Salamina"
+  test "Σαμοθράκη", "Samothrakē"
+  test "Σάμος", "Samos"
+  test "Σαντορίνη", "Santorinē"
+  test "Σέρρες", "Serres"
+  test "Σίκινος", "Sikinos"
+  test "Σίφνος", "Siphnos"
+  test "Σκιάθος", "Skiathos"
+  test "Σκόπελος", "Skopelos"
+  test "Σούλι", "Souli"
+  test "Σπάρτη", "Spartē"
+  test "Στερεά Ελλάδα", "Sterea Ellada"
+  test "Στύρα", "Styra"
+  test "Σύμη", "Symē"
+  test "Σύρος", "Syros"
+  test "Σφακιά", "Sphakia"
+  test "Τήλος", "Tēlos"
+  test "Τήνος", "Tēnos"
+  test "Τρίκαλα", "Trikala"
+  test "Τρίπολη", "Tripolē"
+  test "Τσακωνιά", "Tsakōnia"
+  test "Ύδρα", "Ydra"
+  test "Φάληρο", "Phalēro"
+  test "Φλώρινα", "Phlōrina"
+  test "Φολέγανδρος", "Pholegandros"
+  test "Χάλκη", "Chalkē"
+  test "Χαλκίδα", "Chalkida"
+  test "Χαλάνδρι", "Chalandri"
+  test "Χαλκιδική", "Chalkidikē"
+  test "Χανιά", "Chania"
+  test "Χίος", "Chios"
+  test "Ψαρά", "Psara"
+  test "Αβάνα", "Avana"
+  test "Αγγλία", "Anglia"
+  test "Αϊβαλί", "Aivali"
+  test "Αλεξάνδρεια", "Alexandreia"
+  test "Άμστερνταμ", "Amsterntam"
+  test "Βαυαρία", "Vauaria"
+  test "Βενετία", "Venetia"
+  test "Βερολίνο", "Verolino"
+  test "Βερόνα", "Verona"
+  test "Βιέννη", "Viennē"
+  test "Γένοβα", "Genova"
+  test "Δουβλίνο", "Douvlino"
+  test "Καλαβρία", "Kalavria"
+  test "Καλιφόρνια", "Kaliphornia"
+  test "Καύκασος", "Kaukasos"
+  test "Κονγκό", "Konnko"
+  test "Κορσική", "Korsikē"
+  test "Κουρδιστάν", "Kourdistan"
+  test "Κωνσταντινούπολη", "Kōnstantinoupolē"
+  test "Κατεχόμενη Κύπρος", "Katechomenē Kypros"
+  test "Λαπωνία", "Lapōnia"
+  test "Λευκωσία", "Leukōsia"
+  test "Λιβόρνο", "Livorno"
+  test "Λονδίνο", "Londino"
+  test "Λυών", "Lyōn"
+  test "Μάλαγα", "Malaga"
+  test "Μασσαλία", "Massalia"
+  test "Μικρονησία", "Mikronēsia"
+  test "Μιλάνο", "Milano"
+  test "Μόσχα", "Moscha"
+  test "Μπολόνια", "Bolonia"
+  test "Νάπολη", "Napolē"
+  test "Νταγκεστάν", "Ḏankestan"
+  test "Νέα Υόρκη", "Nea Yorkē"
+  test "Οξφόρδη", "Oxphordē"
+  test "Ουαλία", "Oualia"
+  test "Παρίσι", "Parisi"
+  test "Πάφος", "Paphos"
+  test "Πολυνησία", "Polynēsia"
+  test "Ρώμη", "Rōmē"
+  test "Σαμάρεια", "Samareia"
+  test "Σικελία", "Sikelia"
+  test "Σκανδιναβία", "Skandinavia"
+  test "Σκόπια", "Skopia"
+  test "Σκωτία", "Skōtia"
+  test "Σμύρνη", "Smyrnē"
+  test "Ταϊτή", "Taitē"
+  test "Ταταρστάν", "Tatarstan"
+  test "Τζαμάικα", "Tzamaika"
+  test "Τηλλυρία", "Tēllyria"
+  test "Τιρόλο", "Tirolo"
+  test "Τορίνο", "Torino"
+  test "Φανάρι", "Phanari"
+  test "Φλωρεντία", "Phlōrentia"
+  test "Χαβάη", "Chavaē"
+  test "Χονγκ Κονγκ", "Chongk Kongk"
+}
+
+dependency "unicode", import: true
+
+# https://en.wikipedia.org/wiki/Romanization_of_Greek
+stage {
+
+  # RULES
+  sub "\u03A5", "U", before: any("ΑαΕεΟοΗηΩω") # Υ (after Α, Ε, Ο, Η, Ω)
+  sub "\u03C5", "u", before: any("ΑαΕεΟοΗηΩω") # υ (after Α, Ε, Ο, Η, Ω)
+  sub "\u03CD", "u", before: any("ΑαΕεΟοΗηΩω") # ύ (after Α, Ε, Ο, Η, Ω)
+  sub "\u03A5", "U", after: any("Ιιί") # Υ (before Ι)
+  sub "\u03C5", "u", after: any("Ιιί") # Υ (before Ι)
+  sub "\u0393", "N", after: any("γΓξΞχΧ") # Γ (before Γ, Ξ, Χ)
+  sub "\u03b3", "n", after: any("γΓξΞχΧ") # γ (before Γ, Ξ, Χ)
+  sub "\u0393", "N", after: "Ν", before: "Κ"
+  sub "\u03b3", "n", after: "ν", before: "κ"
+  sub "\u0393", "N", before: any(greek), not_before: boundary, after: any("κΚ") + any(greek), not_after: any("κΚ") + boundary # Γ (before Κ medially)
+  sub "\u03b3", "n", before: any(greek), not_before: boundary, after: any("κΚ") + any(greek), not_after: any("κΚ") + boundary # Γ (before Κ medially)
+  sub "\u039D\u03A4", "Ḏ", before: boundary # ΝΤ
+  sub "\u039D\u03C4", "Ḏ", before: boundary # Ντ
+  sub "\u03BD\u03C4", "ḏ", before: boundary # ντ
+  sub "\u039C\u03A0", "B", before: boundary # ΜΠ
+  sub "\u039C\u03C0", "B", before: boundary # Μπ
+  sub "\u03BC\u03C0", "b", before: boundary # μπ
+  sub "\u037E", "?" # ;
+  sub "\u003B", "?" # ;
+
+
+  # CHARACTERS
+  parallel {
+    sub "'", ""
+    sub "Ά", "A" # Ά
+    sub "Α", "A" # Α
+    sub "Β", "V" # Β
+    sub "Γ", "G" # Γ
+    sub "Δ", "D" # Δ
+    sub "Ε", "E" # Ε
+    sub "Ζ", "Z" # Ζ
+    sub "Η", "Ē" # Η
+    sub "Θ", "Th" # Θ
+    sub "Θ", "TH", after: any("ΆΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΈΉΊΌΏΪΫ") # Θ
+    sub "Θ", "TH", before: any("ΆΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΈΉΊΌΏΪΫ") # Θ
+
+    sub "Ι", "I" # Ι
+    sub "Κ", "K" # Κ
+    sub "Λ", "L" # Λ
+    sub "Μ", "M" # Μ
+    sub "Ν", "N" # Ν
+    sub "Ξ", "X" # Ξ
+    sub "Ο", "O" # Ο
+    sub "Π", "P" # Π
+    sub "Ρ", "R" # Ρ
+    sub "Σ", "S" # Σ
+    sub "Τ", "T" # Τ
+    sub "Υ", "Y" # Υ
+    sub "Φ", "Ph" # Φ
+    sub "Φ", "PH", after: any("ΆΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΈΉΊΌΏΪΫ") # Φ
+    sub "Φ", "PH", before: any("ΆΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΈΉΊΌΏΪΫ") # Φ
+
+    sub "Χ", "Ch" # Χ
+    sub "Χ", "CH", after: any("ΆΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΈΉΊΌΏΪΫ") # Χ
+    sub "Χ", "CH", before: any("ΆΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΈΉΊΌΏΪΫ") # Χ
+
+    sub "Ψ", "Ps" # Ψ
+    sub "Ψ", "PS", after: any("ΆΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΈΉΊΌΏΪΫ") # Ψ
+    sub "Ψ", "PS", before: any("ΆΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΈΉΊΌΏΪΫ") # Ψ
+
+    sub "Ω", "Ō" # Ω
+    sub "Έ", "E" # Έ
+    sub "Ή", "Ē" # Ή
+    sub "Ί", "I" # Ί
+    sub "Ό", "O" # Ό
+    sub "Ύ", "Y" # Ύ
+    sub "Ώ", "Ō" # Ώ
+    sub "Ϊ", "I" # Ϊ
+    sub "Ϋ", "Y" # Ϋ
+
+    sub "ά", "a" # ά
+    sub "α", "a" # α
+    sub "β", "v" # β
+    sub "γ", "g" # γ
+    sub "δ", "d" # δ
+    sub "ε", "e" # ε
+    sub "ζ", "z" # ζ
+    sub "η", "ē" # η
+    sub "θ", "th" # θ
+    sub "ι", "i" # ι
+    sub "κ", "k" # κ
+    sub "λ", "l" # λ
+    sub "μ", "m" # μ
+    sub "ν", "n" # ν
+    sub "ξ", "x" # ξ
+    sub "ο", "o" # ο
+    sub "π", "p" # π
+    sub "ρ", "r" # ρ
+    sub "σ", "s" # σ
+    sub "ς", "s" # ς
+    sub "τ", "t" # τ
+    sub "υ", "y" # υ
+    sub "φ", "ph" # φ
+    sub "χ", "ch" # χ
+    sub "ψ", "ps" # ψ
+    sub "ω", "ō" # ω
+    sub "έ", "e" # έ
+    sub "ή", "ē" # ή
+    sub "ί", "i" # ί
+    sub "ό", "o" # ό
+    sub "ύ", "y" # ύ
+    sub "ώ", "ō" # ώ
+    sub "ϊ", "i" # ϊ
+    sub "ϋ", "y" # ϋ
+    sub "ΐ", "i" # ΐ
+    sub "ΰ", "y" # ΰ
+
+    sub "·", ";" # ·
+    sub "·", ";" # ·
+  }
+
+}
+

data/maps/alalc-guj-Gujr-Latn-1997.imp

@@ -0,0 +1,223 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:guj
+  source_script: Gujr
+  destination_script: Latn
+  name: Gujarati Romanization, 1997
+  url: http://catdir.loc.gov/catdir/cpso/romanization/gujarati.pdf
+  creation_date: 1997
+  description: |
+    ALA-LC Romanization table for Gujarati
+
+  notes:
+
+    - Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+      vowels following a consonant can be found in grammars; no distinction between the two is
+      made in transliteration.
+
+    - |
+      The vowel a is implicit after all consonants and consonant clusters and is supplied in
+      transliteration, with the following exceptions:
+      a) when another vowel is indicated by its appropriate sign and
+      b) when the absence of any vowel is indicated by the subscript symbol ( ્ ) called halanta or
+      virāma.
+
+    - |
+      Exception: Anusvāra is transliterated by:
+      a) ṅ before gutturals,
+      b) ñ before palatals,
+      c) ṇ before cerebrals,
+      d) n before dentals, and
+      e) m before labials.
+
+    - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+}
+
+tests {
+  test "અમિત શાહનો કોરોના રિપોર્ટ ૨ ઓગસ્ટે પોઝિટિવ આવ્યો હતો, ત્યારથી તેમનું સ્વાસ્થ્ય સારું નથી", "amita śāhanȏ kȏrȏnā ripȏrṭa 2 ȏgasṭȇ pȏjhiṭiva āvyȏ hatȏ, tyārathī tȇmanuṃ svāsthya sāruṃ nathī"
+  test "મેદાંતા હોસ્પિટલમાં તેમનો ઇલાજ ચાલી રહ્યો હતો", "mȇdāntā hȏspiṭalamāṃ tȇmanȏ ilāja cālī rahyȏ hatȏ"
+  test "ભારતના વિશ્વનાથન આનંદે શેનયાનમાં પહેલો ફિડે શતરંજ વિશ્વ કપ જીત્યો", "bhāratanā viśvanāthana ānandȇ śȇnayānamāṃ pahȇlȏ phiḍȇ śatarañja viśva kapa jītyȏ"
+  test "ભારતીય વડા પ્રધાન જવાહરલાલ નેહરુએ ૪૦ લાખ હિન્દુઓ અને મુસલમાનોના પારસ્પરિક સ્થાનાંતરણનું સૂચન આપ્યું", "bhāratīya vaḍā pradhāna javāharalāla nȇharuȇ 40 lākha hinduȏ anȇ musalamānȏnā pārasparika sthānāntaraṇanuṃ sūcana āpyuṃ"
+  test "લિબિયાના એલ અજિજિયામાં ધરતી પર સૌથી વધુ તાપમાન નોંધાયું. એ વખતે છાયામાં નોંધવામાં આવેલું તાપમાન ૫૮ ડિગ્રી સેલ્સિયસ હતું.", "libiyānā ȇla ajijiyāmāṃ dharatī para sauthī vadhu tāpamāna nȏndhāyuṃ. ȇ vakhatȇ chāyāmāṃ nȏndhavāmāṃ āvȇluṃ tāpamāna 58 ḍigrī sȇlsiyasa hatuṃ."
+  test "પ્રથમ વિશ્વયુદ્ધઃ જર્મની અને ફ્રાન્સ વચ્ચે એસ્નેની લડાઈ શરૂ થઈ હતી", "prathama viśvayuddhaḥ jarmanī anȇ phrānsa vaccȇ ȇsnȇnī laḍāī śarū thaī hatī"
+  test "એન્ગ્લો-મિસ્ત્ર યુદ્ધઃ તેલ અલ કેબિરનું યુદ્ધ લડવામાં આવ્યું હતું.", "ȇnglȏ-mistra yuddhaḥ tȇla ala kȇbiranuṃ yuddha laḍavāmāṃ āvyuṃ hatuṃ."
+  test "પુરાવા ન હતા, એ જ કારણે કેસ ચાલ્યો નહીં, પણ તેમને નજરકેદ રાખવામાં આવ્યા", "purāvā na hatā, ȇ ja kāraṇȇ kȇsa cālyȏ nahīṃ, paṇa tȇmanȇ najarakȇda rākhavāmāṃ āvyā"
+  test "સરદાર પટેલે નક્કી કર્યું હતું કે કાશ્મીર ભારતનો હિસ્સો બનશે; ૯૧ વર્ષ પહેલાં લાહોર જેલમાં ભૂખહડતાળ દરમિયાન શહીદ થયા હતા જતીન દાસ", "saradāra paṭȇlȇ nakkī karyuṃ hatuṃ kȇ kāśmīra bhāratanȏ hissȏ banaśȇ; 91 varsha pahȇlāṃ lāhȏra jȇlamāṃ bhūkhahaḍatāḷa daramiyāna śahīda thayā hatā jatīna dāsa"
+  test "કોરોના પ્રોટોકોલ વચ્ચે આજે મેડિકલ પ્રવેશ પરીક્ષા લેવાશેઃ એન્ટ્રી ટચ ફ્રી રહેશે, એડમિટ કાર્ડ બાર કોડથી ચેક થશે", "kȏrȏnā prȏṭȏkȏla vaccȇ ājȇ mȇḍikala pravȇśa parīkshā lȇvāśȇḥ ȇnṭrī ṭaca phrī rahȇśȇ, ȇḍamiṭa kārḍa bāra kȏḍathī cȇka thaśȇ"
+  test "અલ્ ક઼`ઇદ્ માં હવામાન", "al ka`id māṃ havāmāna"
+  test "મંત્રાલય તથા ખ઼.ય ના વિ૨ષ્ઠ અધિકા૨ીઓ ઉપસ્થિત ૨હ્યા હતા", "mantrālaya tathā kha.ya nā vi2shṭha adhikā2īȏ upasthita 2hyā hatā"
+}
+
+aliases {
+  def_alias characters_set1, any("\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd")
+}
+
+stage {
+
+  # RULES
+  # note 3
+    sub "\u0A82", "ṅ", after: any("કખગઘઙ")
+    sub "\u0A82", "ñ", after: any("ચછજઝઞ")
+    sub "\u0A82", "ṇ", after: any("ટઠડઢણ")
+    sub "\u0A82", "n", after: any("તથદધન")
+    sub "\u0A82", "m", after: any("પફબભમ")
+
+  # note[2(a,b)]
+    sub "ક", "k", after: characters_set1
+    sub "ખ", "kh", after: characters_set1
+    sub "ગ", "g", after: characters_set1
+    sub "ઘ", "gh", after: characters_set1
+    sub "ઙ", "ṅ", after: characters_set1
+    sub "ચ", "c", after: characters_set1
+    sub "છ", "ch", after: characters_set1
+    sub "જ", "j", after: characters_set1
+    sub "ઝ", "jh", after: characters_set1
+    sub "ઞ", "ñ", after: characters_set1
+    sub "ટ", "ṭ", after: characters_set1
+    sub "ઠ", "ṭh", after: characters_set1
+    sub "ડ", "ḍ", after: characters_set1
+    sub "ઢ", "ḍh", after: characters_set1
+    sub "ણ", "ṇ", after: characters_set1
+    sub "ત", "t", after: characters_set1
+    sub "થ", "th", after: characters_set1
+    sub "દ", "d", after: characters_set1
+    sub "ધ", "dh", after: characters_set1
+    sub "ન", "n", after: characters_set1
+    sub "પ", "p", after: characters_set1
+    sub "ફ", "ph", after: characters_set1
+    sub "બ", "b", after: characters_set1
+    sub "ભ", "bh", after: characters_set1
+    sub "મ", "m", after: characters_set1
+    sub "ય", "y", after: characters_set1
+    sub "ર", "r", after: characters_set1
+    sub "લ", "l", after: characters_set1
+    sub "ળ", "ḷ", after: characters_set1
+    sub "વ", "v", after: characters_set1
+    sub "શ", "ś", after: characters_set1
+    sub "ષ", "sh", after: characters_set1
+    sub "સ", "s", after: characters_set1
+    sub "હ", "h", after: characters_set1
+
+
+
+  # CHARACTERS
+  parallel {
+
+    sub "અ", "a"
+    sub "આ", "ā"
+    sub "ઇ", "i"
+    sub "ઈ", "ī"
+    sub "ઉ", "u"
+    sub "ઊ", "ū"
+    sub "ઋ", "ṛ"
+
+    sub "ઍ", "e"
+    sub "એ", "ȇ"
+    sub "ઐ", "ai"
+
+    sub "ઑ", "o"
+    sub "ઓ", "ȏ"
+    sub "ઔ", "au"
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "ક", "ka"
+    sub "ખ", "kha"
+    sub "ગ", "ga"
+    sub "ઘ", "gha"
+    sub "ઙ", "ṅa"
+
+    # Palatals
+    sub "ચ", "ca"
+    sub "છ", "cha"
+    sub "જ", "ja"
+    sub "ઝ", "jha"
+    sub "ઞ", "ña"
+
+    # Cerebrals
+    sub "ટ", "ṭa"
+    sub "ઠ", "ṭha"
+    sub "ડ", "ḍa"
+    sub "ઢ", "ḍha"
+    sub "ણ", "ṇa"
+
+    # Dentals
+    sub "ત", "ta"
+    sub "થ", "tha"
+    sub "દ", "da"
+    sub "ધ", "dha"
+    sub "ન", "na"
+
+    # Labials
+    sub "પ", "pa"
+    sub "ફ", "pha"
+    sub "બ", "ba"
+    sub "ભ", "bha"
+    sub "મ", "ma"
+
+    # Semivowels
+    sub "ય", "ya"
+    sub "ર", "ra"
+    sub "લ", "la"
+    sub "ળ", "ḷa"
+    sub "વ", "va"
+
+    # Sibilants
+    sub "શ", "śa"
+    sub "ષ", "sha"
+    sub "સ", "sa"
+
+
+    # Aspirate
+    sub "હ", "ha"
+
+    # Bisarga
+    sub "ઃ", "ḥ"
+
+    # Anusvāra
+    sub "ં", "ṃ"
+
+    # Abagraha  (see Note 4)
+    sub "ઽ", "’" # (apostrophe)
+
+    # Medials # Needed for connecting constants
+
+    sub "ા", "ā"
+    sub "િ", "i"
+    sub "ી", "ī"
+    sub "ુ", "u"
+    sub "ૂ", "ū"
+    sub "ૃ", "ṛ"
+    sub "ૅ", "e"
+    sub "ે", "ȇ"
+    sub "ૈ", "ai"
+    sub "ૉ", "o"
+    sub "ો", "ȏ"
+    sub "ૌ", "au"
+
+    # digits
+
+    sub "૦", "0"
+    sub "૧", "1"
+    sub "૨", "2"
+    sub "૩", "3"
+    sub "૪", "4"
+    sub "૫", "5"
+    sub "૬", "6"
+    sub "૭", "7"
+    sub "૮", "8"
+    sub "૯", "9"
+
+
+
+    sub "્", ""
+    sub "઼", ""
+    sub "।", "."
+    sub "\u09CD", "" # Used for joining
+    sub "‍", "" # Used for joining
+  }
+
+  compose
+}
+