dpearson2699/swift-ios-skills/skills-natural-language

import NaturalLanguage
import Translation

import NaturalLanguage

func tokenizeWords(in text: String) -> [String] {
    let tokenizer = NLTokenizer(unit: .word)
    tokenizer.string = text

    let range = text.startIndex..<text.endIndex
    return tokenizer.tokens(for: range).map { String(text[$0]) }
}

Unit	Description
`.word`	Individual words
`.sentence`	Sentences
`.paragraph`	Paragraphs
`.document`	Entire document

let tokenizer = NLTokenizer(unit: .word)
tokenizer.string = text

tokenizer.enumerateTokens(in: text.startIndex..<text.endIndex) { range, attributes in
    if attributes.contains(.numeric) {
        print("Number: \(text[range])")
    }
    return true // continue enumeration
}

func detectLanguage(for text: String) -> NLLanguage? {
    NLLanguageRecognizer.dominantLanguage(for: text)
}

// Multiple hypotheses with confidence scores
func languageHypotheses(for text: String, max: Int = 5) -> [NLLanguage: Double] {
    let recognizer = NLLanguageRecognizer()
    recognizer.processString(text)
    return recognizer.languageHypotheses(withMaximum: max)
}

let recognizer = NLLanguageRecognizer()
recognizer.languageConstraints = [.english, .french, .spanish]
recognizer.processString(text)
let detected = recognizer.dominantLanguage

func tagPartsOfSpeech(in text: String) -> [(String, NLTag)] {
    let tagger = NLTagger(tagSchemes: [.lexicalClass])
    tagger.string = text

    var results: [(String, NLTag)] = []
    let range = text.startIndex..<text.endIndex
    let options: NLTagger.Options = [.omitPunctuation, .omitWhitespace]

    tagger.enumerateTags(in: range, unit: .word, scheme: .lexicalClass, options: options) { tag, tokenRange in
        if let tag {
            results.append((String(text[tokenRange]), tag))
        }
        return true
    }
    return results
}

Scheme	Output
`.lexicalClass`	Part of speech (noun, verb, adjective)
`.nameType`	Named entity type (person, place, organization)
`.nameTypeOrLexicalClass`	Combined NER + POS
`.lemma`	Base form of a word
`.language`	Per-token language
`.sentimentScore`	Sentiment polarity score

func extractEntities(from text: String) -> [(String, NLTag)] {
    let tagger = NLTagger(tagSchemes: [.nameType])
    tagger.string = text

    var entities: [(String, NLTag)] = []
    let options: NLTagger.Options = [.omitPunctuation, .omitWhitespace, .joinNames]

    tagger.enumerateTags(
        in: text.startIndex..<text.endIndex,
        unit: .word,
        scheme: .nameType,
        options: options
    ) { tag, tokenRange in
        if let tag, tag != .other {
            entities.append((String(text[tokenRange]), tag))
        }
        return true
    }
    return entities
}
// NLTag values: .personalName, .placeName, .organizationName

func sentimentScore(for text: String) -> Double? {
    let tagger = NLTagger(tagSchemes: [.sentimentScore])
    tagger.string = text

    let (tag, _) = tagger.tag(
        at: text.startIndex,
        unit: .paragraph,
        scheme: .sentimentScore
    )
    return tag.flatMap { Double($0.rawValue) }
}

func wordSimilarity(_ word1: String, _ word2: String) -> Double? {
    guard let embedding = NLEmbedding.wordEmbedding(for: .english) else { return nil }
    return embedding.distance(between: word1, and: word2, distanceType: .cosine)
}

func findSimilarWords(to word: String, count: Int = 5) -> [(String, Double)] {
    guard let embedding = NLEmbedding.wordEmbedding(for: .english) else { return [] }
    return embedding.neighbors(for: word, maximumCount: count, distanceType: .cosine)
}

func sentenceSimilarity(_ s1: String, _ s2: String) -> Double? {
    guard let embedding = NLEmbedding.sentenceEmbedding(for: .english) else { return nil }
    return embedding.distance(between: s1, and: s2, distanceType: .cosine)
}

import SwiftUI
import Translation

struct TranslatableView: View {
    @State private var showTranslation = false
    let text = "Hello, how are you?"

    var body: some View {
        Button { showTranslation = true } label: {
            Text(text)
        }
        .buttonStyle(.plain)
        .translationPresentation(
            isPresented: $showTranslation,
            text: text
        )
    }
}

struct TranslatingView: View {
    @State private var translatedText = ""
    @State private var translationErrorMessage: String?
    @State private var configuration: TranslationSession.Configuration?

    var body: some View {
        VStack {
            Text(translatedText)
            Button("Translate") {
                configuration = .init(source: Locale.Language(identifier: "en"),
                                      target: Locale.Language(identifier: "es"))
            }
        }
        .translationTask(configuration) { session in
            do {
                let response = try await session.translate("Hello, world!")
                await MainActor.run {
                    translatedText = response.targetText
                    translationErrorMessage = nil
                }
            } catch {
                let message = error.localizedDescription
                await MainActor.run {
                    translationErrorMessage = message
                }
            }
        }
    }
}

.translationTask(configuration) { session in
    do {
        let requests = texts.enumerated().map { index, text in
            TranslationSession.Request(sourceText: text,
                                       clientIdentifier: "\(index)")
        }
        let responses = try await session.translations(from: requests)
        for response in responses {
            print("\(response.sourceText) -> \(response.targetText)")
        }
    } catch {
        // Handle cancellation, unsupported languages, or download refusal.
    }
}

let availability = LanguageAvailability()
let status = await availability.status(
    from: Locale.Language(identifier: "en"),
    to: Locale.Language(identifier: "ja")
)
switch status {
case .installed: break    // Ready to translate offline
case .supported: break    // Needs download
case .unsupported: break  // Language pair not available
}

// WRONG
let sharedTagger = NLTagger(tagSchemes: [.lexicalClass])
DispatchQueue.concurrentPerform(iterations: 10) { _ in
    sharedTagger.string = someText  // Data race
}

// CORRECT
await withTaskGroup(of: Void.self) { group in
    for _ in 0..<10 {
        group.addTask {
            let tagger = NLTagger(tagSchemes: [.lexicalClass])
            tagger.string = someText
            // process...
        }
    }
}

// WRONG: Trying to do NER with raw Core ML
let coreMLModel = try MLModel(contentsOf: modelURL)

// CORRECT: Use NLTagger for built-in NER
let tagger = NLTagger(tagSchemes: [.nameType])

// Or load a custom Core ML model via NLModel
let nlModel = try NLModel(mlModel: coreMLModel)
tagger.setModels([nlModel], forTagScheme: .nameType)

// WRONG: Force unwrap
let embedding = NLEmbedding.wordEmbedding(for: .japanese)!

// CORRECT: Handle nil
guard let embedding = NLEmbedding.wordEmbedding(for: .japanese) else {
    // Embedding not available for this language
    return
}

// WRONG: New tagger per word
for word in words {
    let tagger = NLTagger(tagSchemes: [.lexicalClass])
    tagger.string = word
}

// CORRECT: Set string once, enumerate
let tagger = NLTagger(tagSchemes: [.lexicalClass])
tagger.string = fullText
tagger.enumerateTags(in: fullText.startIndex..<fullText.endIndex,
                     unit: .word, scheme: .lexicalClass, options: []) { tag, range in
    return true
}

// WRONG: Detect language of a single word
let lang = NLLanguageRecognizer.dominantLanguage(for: "chat")  // French or English?

// CORRECT: Provide context
let recognizer = NLLanguageRecognizer()
recognizer.languageHints = [.english: 0.8, .french: 0.2]
recognizer.processString("chat")

natural-language

Summary

SKILL.md

NaturalLanguage + Translation

Contents

Setup

Tokenization

Token Units

Enumerating with Attributes

Language Identification

Part-of-Speech Tagging

Common Tag Schemes

Named Entity Recognition

Sentiment Analysis

Text Embeddings

Translation

System Translation Overlay

Programmatic Translation

Batch Translation

Checking Language Availability

Common Mistakes

DON'T: Share NLTagger/NLTokenizer across threads

DON'T: Confuse NaturalLanguage with Core ML

DON'T: Assume embeddings exist for all languages

DON'T: Create a new tagger per token

DON'T: Ignore language hints for short text

Review Checklist

References

Related skills