Add support for more locales

Author: kean

Modules/Package.swift

@@ -20,6 +20,7 @@ let package = Package(
         .library(name: "WordPressFlux", targets: ["WordPressFlux"]),
         .library(name: "WordPressShared", targets: ["WordPressShared"]),
         .library(name: "WordPressUI", targets: ["WordPressUI"]),
+        .library(name: "WordPressIntelligence", targets: ["WordPressIntelligence"]),
         .library(name: "WordPressReader", targets: ["WordPressReader"]),
         .library(name: "WordPressCore", targets: ["WordPressCore"]),
         .library(name: "WordPressCoreProtocols", targets: ["WordPressCoreProtocols"]),
@@ -163,6 +164,10 @@ let package = Package(
             // This package should never have dependencies – it exists to expose protocols implemented in WordPressCore
             // to UI code, because `wordpress-rs` doesn't work nicely with previews.
         ]),
+        .target(name: "WordPressIntelligence", dependencies: [
+            "WordPressShared",
+            .product(name: "SwiftSoup", package: "SwiftSoup"),
+        ]),
         .target(name: "WordPressLegacy", dependencies: ["DesignSystem", "WordPressShared"]),
         .target(name: "WordPressSharedObjC", resources: [.process("Resources")], swiftSettings: [.swiftLanguageMode(.v5)]),
         .target(
@@ -251,6 +256,7 @@ let package = Package(
         .testTarget(name: "WordPressSharedObjCTests", dependencies: [.target(name: "WordPressShared"), .target(name: "WordPressTesting")], swiftSettings: [.swiftLanguageMode(.v5)]),
         .testTarget(name: "WordPressUIUnitTests", dependencies: [.target(name: "WordPressUI")], swiftSettings: [.swiftLanguageMode(.v5)]),
         .testTarget(name: "WordPressCoreTests", dependencies: [.target(name: "WordPressCore")]),
+        .testTarget(name: "WordPressIntelligenceTests", dependencies: [.target(name: "WordPressIntelligence")])
     ]
 )
 
@@ -348,6 +354,7 @@ enum XcodeSupport {
             "ShareExtensionCore",
             "Support",
             "WordPressFlux",
+            "WordPressIntelligence",
             "WordPressShared",
             "WordPressLegacy",
             "WordPressReader",

Modules/Sources/WordPressIntelligence/IntelligenceService.swift

@@ -0,0 +1,65 @@
+import Foundation
+import FoundationModels
+import NaturalLanguage
+
+public enum IntelligenceService {
+    /// Maximum context size for language model sessions (in tokens).
+    ///
+    /// A single token corresponds to three or four characters in languages like
+    /// English, Spanish, or German, and one token per character in languages like
+    /// Japanese, Chinese, or Korean. In a single session, the sum of all tokens
+    /// in the instructions, all prompts, and all outputs count toward the context window size.
+    ///
+    /// https://developer.apple.com/documentation/foundationmodels/generating-content-and-performing-tasks-with-foundation-models#Consider-context-size-limits-per-session
+    public static let contextSizeLimit = 4096
+
+    /// Checks if intelligence features are supported on the current device.
+    public nonisolated static var isSupported: Bool {
+        guard #available(iOS 26, *) else {
+            return false
+        }
+        switch SystemLanguageModel.default.availability {
+        case .available:
+            return true
+        case .unavailable(let reason):
+            switch reason {
+            case .appleIntelligenceNotEnabled, .modelNotReady:
+                return true
+            case .deviceNotEligible:
+                return false
+            @unknown default:
+                return false
+            }
+        }
+    }
+
+    /// Extracts relevant text from post content, removing HTML and limiting size.
+    public static func extractRelevantText(from post: String, ratio: CGFloat = 0.6) -> String {
+        let extract = try? ContentExtractor.extractRelevantText(from: post)
+        let postSizeLimit = Double(IntelligenceService.contextSizeLimit) * ratio
+        return String((extract ?? post).prefix(Int(postSizeLimit)))
+    }
+
+    /// - note: As documented in https://developer.apple.com/documentation/foundationmodels/supporting-languages-and-locales-with-foundation-models?changes=_10_5#Use-Instructions-to-set-the-locale-and-language
+    static func makeLocaleInstructions(for locale: Locale = Locale.current) -> String {
+        if Locale.Language(identifier: "en_US").isEquivalent(to: locale.language) {
+            return "" // Skip the locale phrase for U.S. English.
+        }
+        return "The person's locale is \(locale.identifier)."
+    }
+
+    /// Detects the dominant language of the given text.
+    ///
+    /// - Parameter text: The text to analyze
+    /// - Returns: The detected language code (e.g., "en", "es", "fr", "ja"), or nil if detection fails
+    public static func detectLanguage(from text: String) -> String? {
+        let recognizer = NLLanguageRecognizer()
+        recognizer.processString(text)
+
+        guard let languageCode = recognizer.dominantLanguage else {
+            return nil
+        }
+
+        return languageCode.rawValue
+    }
+}

Modules/Sources/WordPressIntelligence/Parameters/ContentLength.swift

@@ -0,0 +1,58 @@
+import Foundation
+import WordPressShared
+
+/// Target length for generated text.
+///
+/// Ranges are calibrated for English and account for cross-language variance.
+/// Sentences are the primary indicator; word counts accommodate language differences.
+///
+/// - **Short**: 1-2 sentences (15-35 words) - Social media, search snippets
+/// - **Medium**: 2-4 sentences (30-90 words) - RSS feeds, blog listings
+/// - **Long**: 5-7 sentences (90-130 words) - Detailed previews, newsletters
+///
+/// Word ranges are intentionally wide (2-2.3x) to handle differences in language
+/// structure (German compounds, Romance wordiness, CJK tokenization).
+public enum ContentLength: Int, CaseIterable, Sendable {
+    case short
+    case medium
+    case long
+
+    public var displayName: String {
+        switch self {
+        case .short:
+            AppLocalizedString("generation.length.short", value: "Short", comment: "Generated content length (needs to be short)")
+        case .medium:
+            AppLocalizedString("generation.length.medium", value: "Medium", comment: "Generated content length (needs to be short)")
+        case .long:
+            AppLocalizedString("generation.length.long", value: "Long", comment: "Generated content length (needs to be short)")
+        }
+    }
+
+    public var trackingName: String {
+        switch self {
+        case .short: "short"
+        case .medium: "medium"
+        case .long: "long"
+        }
+    }
+
+    public var promptModifier: String {
+        "\(sentenceRange.lowerBound)-\(sentenceRange.upperBound) sentences (\(wordRange.lowerBound)-\(wordRange.upperBound) words)"
+    }
+
+    public var sentenceRange: ClosedRange<Int> {
+        switch self {
+        case .short: 1...2
+        case .medium: 2...4
+        case .long: 5...7
+        }
+    }
+
+    public var wordRange: ClosedRange<Int> {
+        switch self {
+        case .short: 15...35
+        case .medium: 40...80
+        case .long: 90...130
+        }
+    }
+}

Modules/Sources/WordPressIntelligence/Parameters/WritingStyle.swift

@@ -0,0 +1,40 @@
+import Foundation
+import WordPressShared
+
+/// Writing style for generated text.
+public enum WritingStyle: String, CaseIterable, Sendable {
+    case engaging
+    case conversational
+    case witty
+    case formal
+    case professional
+
+    public var displayName: String {
+        switch self {
+        case .engaging:
+            AppLocalizedString("generation.style.engaging", value: "Engaging", comment: "AI generation style")
+        case .conversational:
+            AppLocalizedString("generation.style.conversational", value: "Conversational", comment: "AI generation style")
+        case .witty:
+            AppLocalizedString("generation.style.witty", value: "Witty", comment: "AI generation style")
+        case .formal:
+            AppLocalizedString("generation.style.formal", value: "Formal", comment: "AI generation style")
+        case .professional:
+            AppLocalizedString("generation.style.professional", value: "Professional", comment: "AI generation style")
+        }
+    }
+
+    var promptModifier: String {
+        "\(rawValue) (\(promptModifierDetails))"
+    }
+
+    var promptModifierDetails: String {
+        switch self {
+        case .engaging: "engaging and compelling tone"
+        case .witty: "witty, creative, entertaining"
+        case .conversational: "friendly and conversational tone"
+        case .formal: "formal and academic tone"
+        case .professional: "professional and polished tone"
+        }
+    }
+}

Modules/Sources/WordPressIntelligence/UseCases/PostExcerptGenerator.swift

@@ -0,0 +1,109 @@
+import Foundation
+import FoundationModels
+
+/// Excerpt generation for WordPress posts.
+///
+/// Generates multiple excerpt variations for blog posts with customizable
+/// length and writing style. Supports session-based usage (for UI with continuity)
+/// and one-shot generation (for tests and background tasks).
+@available(iOS 26, *)
+public struct PostExcerptGenerator {
+    public var length: ContentLength
+    public var style: WritingStyle
+    public var options: GenerationOptions
+
+    public init(
+        length: ContentLength,
+        style: WritingStyle,
+        options: GenerationOptions = GenerationOptions(temperature: 0.7)
+    ) {
+        self.length = length
+        self.style = style
+        self.options = options
+    }
+
+    /// Generates excerpts with this configuration.
+    public func generate(for content: String) async throws -> [String] {
+        let prompt = await makePrompt(content: content)
+        let response = try await makeSession().respond(
+            to: prompt,
+            generating: Result.self,
+            options: options
+        )
+        return response.content.excerpts
+    }
+
+    /// Creates a language model session configured for excerpt generation.
+    public func makeSession() -> LanguageModelSession {
+        LanguageModelSession(
+            model: .init(guardrails: .permissiveContentTransformations),
+            instructions: Self.instructions
+        )
+    }
+
+    /// Instructions for the language model session.
+    public static var instructions: String {
+        """
+        You are helping a WordPress user generate an excerpt for their post or page.
+
+        **Parameters**
+        - POST_CONTENT: post contents (HTML or plain text)
+        - TARGET_LANGUAGE: detected language code (e.g., "en", "es", "fr", "ja")
+        - TARGET_LENGTH: sentence count (primary) and word range (secondary)
+        - GENERATION_STYLE: writing style to apply
+
+        \(IntelligenceService.makeLocaleInstructions())
+
+        **Requirements**
+        1. ⚠️ LANGUAGE: Match TARGET_LANGUAGE code if provided, otherwise match POST_CONTENT language. Never translate or default to English.
+
+        2. ⚠️ LENGTH: Match TARGET_LENGTH sentence count, stay within word range. Write complete sentences only.
+
+        3. ⚠️ STYLE: Follow GENERATION_STYLE exactly.
+
+        **Best Practices**
+        - Capture the post's main value proposition
+        - Use active voice and strategic keywords naturally
+        - Don't duplicate the opening paragraph
+        - Work as standalone copy for search results, social media, and email
+        """
+    }
+
+    /// Creates a prompt for this excerpt configuration.
+    ///
+    /// This method handles content extraction (removing HTML, limiting size) and language detection
+    /// automatically before creating the prompt.
+    ///
+    /// - Parameter content: The raw post content (may include HTML)
+    /// - Returns: The formatted prompt ready for the language model
+    public func makePrompt(content: String) async -> String {
+        let extractedContent = IntelligenceService.extractRelevantText(from: content)
+        let language = IntelligenceService.detectLanguage(from: extractedContent)
+        let languageInstruction = language.map { "TARGET_LANGUAGE: \($0)\n" } ?? ""
+
+        return """
+        Generate EXACTLY 3 different excerpts for the given post.
+
+        \(languageInstruction)TARGET_LENGTH: \(length.promptModifier)
+        CRITICAL: Write \(length.sentenceRange.lowerBound)-\(length.sentenceRange.upperBound) complete sentences. Stay within \(length.wordRange.lowerBound)-\(length.wordRange.upperBound) words.
+
+        GENERATION_STYLE: \(style.promptModifier)
+
+        POST_CONTENT:
+        \(extractedContent)
+        """
+    }
+
+    /// Prompt for generating additional excerpt options.
+    public static var loadMorePrompt: String {
+        "Generate 3 additional excerpts following the same TARGET_LENGTH and GENERATION_STYLE requirements"
+    }
+
+    // MARK: - Result Type
+
+    @Generable
+    public struct Result {
+        @Guide(description: "Suggested post excerpts", .count(3))
+        public var excerpts: [String]
+    }
+}