OSGKeyboard/OSGKeyboardShared/Typing/RimePersonalDictionaryExporter.swift

// RimePersonalDictionaryExporter.swift
// OSGKeyboard · Shared
//
// Turns PersonalDictionary into an osg_personal Rime table that the
// main osg_pinyin dictionary imports. High weight keeps same-code
// personal hits above the baseline lexicon.

import CryptoKit
import Foundation

public enum RimePersonalDictionaryExporter {
    public static let dictionaryName = "osg_personal"
    /// Above any baseline `osg_pinyin` weight so same-code hits pin to top.
    public static let pinWeight = 50_000_000

    public struct Entry: Equatable, Sendable {
        public let text: String
        public let code: String
        public let weight: Int

        public init(text: String, code: String, weight: Int = RimePersonalDictionaryExporter.pinWeight) {
            self.text = text
            self.code = code
            self.weight = weight
        }
    }

    /// Builds Rime rows for Chinese (pinyin-coded), English (latin-coded),
    /// and Latin aliases that should surface the canonical term.
    public static func entries(
        from dictionary: PersonalDictionary,
        annotator: RimePinyinAnnotator
    ) -> [Entry] {
        var seen = Set<String>()
        var rows: [Entry] = []

        func append(text: String, code: String) {
            let key = "\(text)\t\(code)"
            guard seen.insert(key).inserted else { return }
            rows.append(Entry(text: text, code: code))
        }

        for entry in dictionary.effectiveEntries {
            let term = entry.term.trimmingCharacters(in: .whitespacesAndNewlines)
            guard !term.isEmpty else { continue }

            if let code = annotator.code(for: term) {
                append(text: term, code: code)
            }

            // Latin aliases → alternate codes for the canonical term
            // (e.g. brand English → 中文专名). Chinese ASR aliases stay out.
            for alias in entry.aliases {
                let trimmed = alias.trimmingCharacters(in: .whitespacesAndNewlines)
                guard !trimmed.isEmpty else { continue }
                guard !HanScript.containsIdeograph(in: trimmed) else { continue }
                let latin = RimePinyinAnnotator.latinSpellerCode(trimmed)
                guard !latin.isEmpty else { continue }
                append(text: term, code: latin)
            }
        }

        return rows.sorted {
            if $0.text != $1.text {
                return $0.text.localizedStandardCompare($1.text) == .orderedAscending
            }
            return $0.code < $1.code
        }
    }

    public static func yaml(
        from dictionary: PersonalDictionary,
        annotator: RimePinyinAnnotator
    ) -> String {
        yaml(entries: entries(from: dictionary, annotator: annotator))
    }

    public static func yaml(entries: [Entry]) -> String {
        var lines: [String] = [
            "# Generated by OSGKeyboard from PersonalDictionary. Do not edit.",
            "---",
            "name: \(dictionaryName)",
            "version: \"1.0\"",
            "sort: by_weight",
            "columns:",
            "  - text",
            "  - code",
            "  - weight",
            "..."
        ]
        for entry in entries {
            lines.append("\(entry.text)\t\(entry.code)\t\(entry.weight)")
        }
        lines.append("")
        return lines.joined(separator: "\n")
    }

    public static func fingerprint(of yaml: String) -> String {
        let digest = SHA256.hash(data: Data(yaml.utf8))
        return digest.map { String(format: "%02x", $0) }.joined()
    }

    /// Injects `import_tables: [osg_personal]` into a baseline dict header.
    public static func injectingImportTables(into baselineYAML: String) -> String {
        if baselineYAML.contains("import_tables:") {
            return baselineYAML
        }
        let needle = "use_preset_vocabulary: false\n"
        let injection = """
            use_preset_vocabulary: false
            import_tables:
              - \(dictionaryName)

            """
        if let range = baselineYAML.range(of: needle) {
            return baselineYAML.replacingCharacters(in: range, with: injection)
        }
        // Fallback: insert after the `---` document start block's name line.
        let nameNeedle = "name: osg_pinyin\n"
        if let range = baselineYAML.range(of: nameNeedle) {
            let injectionAfterName = """
                name: osg_pinyin
                import_tables:
                  - \(dictionaryName)

                """
            return baselineYAML.replacingCharacters(in: range, with: injectionAfterName)
        }
        return baselineYAML
    }
}