Alpha conversion added

Model/LanguagesConverter.swift

@@ -0,0 +1,25 @@
+//
+//  Languages.swift
+//  Kiwix
+
+import Foundation
+
+enum LanguagesConverter {
+    static func convert(codes: Set<String>, validCodes: Set<String>) -> Set<String> {
+        let invalidCodes = codes.subtracting(validCodes)
+        let validatedCodes = codes.intersection(validCodes)
+        // try to convert from iso-2 to iso-3 format:
+        let converted = invalidCodes.compactMap(Self.convertToAlpha3(from:))
+        let convertedValidatedCodes = Set<String>(converted).intersection(validCodes)
+        return validatedCodes.union(convertedValidatedCodes)
+    }
+
+    static func convertToAlpha3(from alpha2: String) -> String? {
+        if #available(iOS 16, macOS 13, *) {
+            return Locale.LanguageCode(alpha2).identifier(.alpha3)
+        } else {
+            // Fallback on earlier versions
+            return AlphaCodesLookUpTable.alpha2ToAlpha3[alpha2]
+        }
+    }
+}

Model/Utilities/AlphaCodesLookUpTable.swift

@@ -0,0 +1,181 @@
+//
+//  AlphaCodesLookUpTable.swift
+//  Kiwix
+
+import Foundation
+
+// it's only needed for iOS 15 and macOS 12
+// should be removed once the min target gets to iOS 16 & macOS 13
+enum AlphaCodesLookUpTable {
+    static let alpha2ToAlpha3: [String: String] = [
+        "ab": "abk",
+        "af": "afr",
+        "am": "amh",
+        "an": "arg",
+        "ar": "ara",
+        "as": "asm",
+        "av": "ava",
+        "ay": "aym",
+        "az": "aze",
+        "ba": "bak",
+        "be": "bel",
+        "bg": "bul",
+        "bi": "bis",
+        "bm": "bam",
+        "bn": "ben",
+        "bo": "bod",
+        "br": "bre",
+        "bs": "bos",
+        "ca": "cat",
+        "ce": "che",
+        "ch": "cha",
+        "co": "cos",
+        "cr": "cre",
+        "cs": "ces",
+        "cu": "chu",
+        "cv": "chv",
+        "cy": "cym",
+        "da": "dan",
+        "de": "deu",
+        "dv": "div",
+        "dz": "dzo",
+        "ee": "ewe",
+        "el": "ell",
+        "en": "eng",
+        "eo": "epo",
+        "es": "spa",
+        "et": "est",
+        "eu": "eus",
+        "fa": "fas",
+        "ff": "ful",
+        "fi": "fin",
+        "fj": "fij",
+        "fo": "fao",
+        "fr": "fra",
+        "fy": "fry",
+        "ga": "gle",
+        "gd": "gla",
+        "gl": "glg",
+        "gn": "grn",
+        "gu": "guj",
+        "gv": "glv",
+        "ha": "hau",
+        "he": "heb",
+        "hi": "hin",
+        "hr": "hrv",
+        "ht": "hat",
+        "hu": "hun",
+        "hy": "hye",
+        "ia": "ina",
+        "id": "ind",
+        "ie": "ile",
+        "ig": "ibo",
+        "ik": "ipk",
+        "io": "ido",
+        "is": "isl",
+        "it": "ita",
+        "iu": "iku",
+        "ja": "jpn",
+        "jv": "jav",
+        "ka": "kat",
+        "kg": "kon",
+        "ki": "kik",
+        "kk": "kaz",
+        "kl": "kal",
+        "km": "khm",
+        "kn": "kan",
+        "ko": "kor",
+        "ks": "kas",
+        "ku": "kur",
+        "kv": "kom",
+        "kw": "cor",
+        "ky": "kir",
+        "la": "lat",
+        "lb": "ltz",
+        "lg": "lug",
+        "li": "lim",
+        "ln": "lin",
+        "lo": "lao",
+        "lt": "lit",
+        "lv": "lav",
+        "mg": "mlg",
+        "mi": "mri",
+        "mk": "mkd",
+        "ml": "mal",
+        "mn": "mon",
+        "mr": "mar",
+        "ms": "msa",
+        "mt": "mlt",
+        "my": "mya",
+        "na": "nau",
+        "nb": "nob",
+        "ne": "nep",
+        "nl": "nld",
+        "nn": "nno",
+        "no": "nor",
+        "nv": "nav",
+        "ny": "nya",
+        "oc": "oci",
+        "oj": "oji",
+        "om": "orm",
+        "or": "ori",
+        "os": "oss",
+        "pa": "pan",
+        "pi": "pli",
+        "pl": "pol",
+        "ps": "pus",
+        "pt": "por",
+        "qu": "que",
+        "rm": "roh",
+        "rn": "run",
+        "ro": "ron",
+        "ru": "rus",
+        "rw": "kin",
+        "sa": "san",
+        "sc": "srd",
+        "sd": "snd",
+        "se": "sme",
+        "sg": "sag",
+        "si": "sin",
+        "sk": "slk",
+        "sl": "slv",
+        "sm": "smo",
+        "sn": "sna",
+        "so": "som",
+        "sq": "sqi",
+        "sr": "srp",
+        "ss": "ssw",
+        "st": "sot",
+        "su": "sun",
+        "sv": "swe",
+        "sw": "swa",
+        "ta": "tam",
+        "te": "tel",
+        "tg": "tgk",
+        "th": "tha",
+        "ti": "tir",
+        "tk": "tuk",
+        "tn": "tsn",
+        "to": "ton",
+        "tr": "tur",
+        "ts": "tso",
+        "tt": "tat",
+        "tw": "twi",
+        "ty": "tah",
+        "ug": "uig",
+        "uk": "ukr",
+        "ur": "urd",
+        "uz": "uzb",
+        "ve": "ven",
+        "vi": "vie",
+        "vo": "vol",
+        "wa": "wln",
+        "wo": "wol",
+        "xh": "xho",
+        "yi": "yid",
+        "yo": "yor",
+        "za": "zha",
+        "zh": "zho",
+        "zu": "zul",
+    ]
+}

Tests/LanguagesConverterTests.swift

@@ -0,0 +1,67 @@
+//
+//  LanguagesConverterTests.swift
+//  UnitTests
+
+import XCTest
+@testable import Kiwix
+
+final class LanguagesConverterTests: XCTestCase {
+    func testShouldHaveEmptyResult() {
+        let empty: Set<String> = .init()
+        XCTAssertEqual(LanguagesConverter.convert(
+            codes: empty,
+            validCodes: empty
+        ), empty)
+        XCTAssertEqual(LanguagesConverter.convert(
+            codes: empty,
+            validCodes: .init(["eng", "fra"])
+        ), empty)
+    }
+
+    func testShouldFilterOutInvalidOnes() {
+        let empty: Set<String> = .init()
+        XCTAssertEqual(LanguagesConverter.convert(
+            codes: .init(["invalid 1", "invalid 2"]),
+            validCodes: .init(["eng", "fra"])
+        ),
+        empty)
+
+        XCTAssertEqual(LanguagesConverter.convert(
+            codes: .init(["invalid 1", "eng", "invalid 2"]),
+            validCodes: .init(["eng", "fra"])
+        ),
+        .init(["eng"]))
+    }
+
+    func testConversion() {
+        XCTAssertEqual(LanguagesConverter.convertToAlpha3(from: "ab"), "abk")
+        XCTAssertEqual(LanguagesConverter.convertToAlpha3(from: "ha"), "hau")
+        XCTAssertEqual(LanguagesConverter.convertToAlpha3(from: "en"), "eng")
+        XCTAssertEqual(LanguagesConverter.convertToAlpha3(from: "zh"), "zho")
+        XCTAssertEqual(LanguagesConverter.convertToAlpha3(from: "zu"), "zul")
+    }
+
+    func testShouldConvertValidOnes() {
+        XCTAssertEqual(LanguagesConverter.convert(
+            codes: .init(["en"]),
+            validCodes: .init(["fra", "ita", "eng"])
+        ),
+        .init(["eng"]))
+    }
+
+    func testShouldLeaveInAlpha3Ones() {
+        XCTAssertEqual(LanguagesConverter.convert(
+            codes: .init(["fr", "eng", "invalid"]),
+            validCodes: .init(["fra", "ita", "eng"])
+        ),
+        .init(["eng", "fra"]))
+    }
+
+    func testShouldIntersectToOnlyValidCodes() {
+        XCTAssertEqual(LanguagesConverter.convert(
+            codes: .init(["fr", "eng", "it"]),
+            validCodes: .init(["spa", "fin", "ita"])
+        ),
+        .init(["ita"]))
+    }
+}

Tests/OPDSParserTests.swift

@@ -7,7 +7,7 @@
 //
 
 import XCTest
-import Kiwix
+@testable import Kiwix
 
 final class OPDSParserTests: XCTestCase {    
     /// Test OPDSParser.parse throws error when OPDS data is invalid.