Files
AutoZhuyin/Sources/AutoZhuyinCore/EnglishModel.swift
T
2026-11-10 10:50:04 +08:00

94 lines
4.2 KiB
Swift

import Foundation
/// Scores how much a typed string looks like English.
///
/// Three sources of evidence:
/// - a list of common words (strong evidence, includes modern words like "ok", "email"),
/// - a large dictionary (e.g. /usr/share/dict/words, weaker evidence),
/// - a letter-bigram model trained on those words, for words not in either list.
public final class EnglishModel {
private var common = Set<String>()
private var dictionary = Set<String>()
private var sortedWords: [String] = []
private var sortedCommon: [String] = []
private var bigram: [String: Double] = [:] // "ab" -> log2 P(b|a); "^a", "a$" for boundaries
private var unseenBigram = -12.0
public init(commonWords: [String], dictionaryWords: [String] = []) {
common = Set(commonWords.map { $0.lowercased() }.filter { !$0.isEmpty })
dictionary = Set(dictionaryWords.map { $0.lowercased() }.filter { $0.count > 2 })
sortedCommon = common.sorted()
sortedWords = common.union(dictionary).sorted()
trainBigram()
}
/// Loads common words from a bundle resource file and the system dictionary if present.
public convenience init(commonWordsURL: URL?, systemDictionary: URL? = URL(fileURLWithPath: "/usr/share/dict/words")) {
func lines(_ url: URL?) -> [String] {
guard let url, let text = try? String(contentsOf: url, encoding: .utf8) else { return [] }
return text.split(whereSeparator: \.isNewline)
.map { $0.trimmingCharacters(in: .whitespaces) }
.filter { !$0.hasPrefix("#") }
}
self.init(commonWords: lines(commonWordsURL), dictionaryWords: lines(systemDictionary))
}
public func isCommon(_ w: String) -> Bool { common.contains(w.lowercased()) }
public func isWord(_ w: String) -> Bool { let l = w.lowercased(); return common.contains(l) || dictionary.contains(l) }
/// - Parameter complete: true when the user ended the word (space / punctuation),
/// false while still typing (prefixes of words get partial credit).
public func score(_ word: String, complete: Bool) -> Double {
let w = word.lowercased()
let n = Double(w.count)
guard !w.isEmpty else { return 0 }
if common.contains(w) { return 3 + n }
if dictionary.contains(w) { return 1 + 0.6 * n }
if !complete {
if hasPrefix(w, in: sortedCommon) { return 0.4 * n }
if hasPrefix(w, in: sortedWords) { return 0.2 * n }
}
// Unknown word: judge by how English-like its letter sequence is.
let plaus = plausibility(w)
return min(0.5 * n, max(-2 * n, n * (plaus + 4.2)))
}
/// Mean log2 probability per letter transition (≈ -3.5 for English, lower for gibberish).
public func plausibility(_ w: String) -> Double {
let chars = ["^"] + w.map(String.init) + ["$"]
var total = 0.0
for i in 1..<chars.count { total += bigram[chars[i - 1] + chars[i]] ?? unseenBigram }
return total / Double(chars.count - 1)
}
private func hasPrefix(_ p: String, in words: [String]) -> Bool {
var lo = 0, hi = words.count
while lo < hi {
let mid = (lo + hi) / 2
if words[mid] < p { lo = mid + 1 } else { hi = mid }
}
// words[lo] is the first word >= p; skip an exact match, then test the next one.
if lo < words.count && words[lo] == p { lo += 1 }
return lo < words.count && words[lo].hasPrefix(p)
}
private func trainBigram() {
var pair: [String: Double] = [:]
var first: [String: Double] = [:]
for w in sortedWords where w.allSatisfy({ $0.isLetter && $0.isASCII }) {
let weight = common.contains(w) ? 5.0 : 1.0
let chars = ["^"] + w.map(String.init) + ["$"]
for i in 1..<chars.count {
pair[chars[i - 1] + chars[i], default: 0] += weight
first[chars[i - 1], default: 0] += weight
}
}
// Add-one smoothing over 27 possible successors.
for (k, c) in pair {
let a = String(k.prefix(1))
bigram[k] = log2((c + 1) / ((first[a] ?? 0) + 27))
}
unseenBigram = log2(1.0 / ((first.values.max() ?? 1000) + 27))
}
}