Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
1dacb8f164 | ||
|
|
bfeed22916 | ||
|
|
bb9cb0c4e0 | ||
|
|
2c5c70c066 |
@@ -144,12 +144,12 @@ python3 training/make_parity.py # 權重或特徵改了之後都要重
|
||||
|
||||
目前的結果(10,000 筆測試資料):
|
||||
|
||||
| | 送出時整段判斷正確 | 打字過程中顯示正確 |
|
||||
|---|---|---|
|
||||
| 手調權重 | 97.58% | 86.15% |
|
||||
| 訓練後 | **99.62%** | 87.81% |
|
||||
| | 送出時整段判斷正確 | 打字過程中顯示正確 | 跟前一個字語言不同時 |
|
||||
|---|---|---|---|
|
||||
| 手調權重 | 97.84% | 88.19% | 96.2% |
|
||||
| 訓練後 | **99.52%** | **91.49%** | **99.3%** |
|
||||
|
||||
送出時的錯誤率從 2.4% 降到 0.4%。「打字過程中」本來就有歧義(例如 `ji3h` 的 `h` 可能是英文的開頭,也可能是注音 ㄘ),所以準確率比較低,但最後送出的結果才是重點。
|
||||
訓練資料也模擬了「前一個字是中文或英文」和「按下空白(一聲)的那一刻」,所以「前一個字」的影響(`ctx.zh` / `ctx.lit`)也是訓練出來的,不是手調的。「打字過程中」本來就有歧義(例如 `ji3h` 的 `h` 可能是英文的開頭,也可能是注音 ㄘ),所以準確率比較低,但最後送出的結果才是重點。
|
||||
|
||||
新增特徵時,Swift 和 Python 兩邊都要加,預設權重設成 0,然後重新訓練。
|
||||
|
||||
|
||||
@@ -15,9 +15,9 @@
|
||||
<key>CFBundlePackageType</key>
|
||||
<string>APPL</string>
|
||||
<key>CFBundleShortVersionString</key>
|
||||
<string>0.6.0</string>
|
||||
<string>0.6.2</string>
|
||||
<key>CFBundleVersion</key>
|
||||
<string>8</string>
|
||||
<string>10</string>
|
||||
<key>InputMethodConnectionName</key>
|
||||
<string>com.autozhuyin.inputmethod.AutoZhuyin_Connection</string>
|
||||
<key>InputMethodServerControllerClass</key>
|
||||
|
||||
@@ -1,39 +1,41 @@
|
||||
{
|
||||
"about": "AutoZhuyin classifier weights, learned by training/train.py",
|
||||
"trained": "2026-11-11",
|
||||
"examples": 40001,
|
||||
"examples": 40000,
|
||||
"test_accuracy": {
|
||||
"commit": 0.9962,
|
||||
"typing": 0.8781
|
||||
"commit": 0.9952,
|
||||
"typing": 0.9149
|
||||
},
|
||||
"weights": {
|
||||
"lit.bias": 0.4276,
|
||||
"lit.common": -0.3465,
|
||||
"lit.common_len": 0.81,
|
||||
"lit.dict": -1.7902,
|
||||
"lit.dict_len": 0.6765,
|
||||
"lit.digits": -2.7403,
|
||||
"lit.num_digits": -0.0751,
|
||||
"lit.num_others": -0.7433,
|
||||
"lit.others": -1.5685,
|
||||
"lit.prefix_common_len": 0.2082,
|
||||
"lit.prefix_dict_len": 0.0003,
|
||||
"lit.short": -0.2397,
|
||||
"lit.unknown_score": 0.213,
|
||||
"ctx.lit": 0.0916,
|
||||
"ctx.zh": 0.1349,
|
||||
"lit.bias": 0.3982,
|
||||
"lit.common": -0.2906,
|
||||
"lit.common_len": 0.8046,
|
||||
"lit.dict": -1.6662,
|
||||
"lit.dict_len": 0.6441,
|
||||
"lit.digits": -2.9689,
|
||||
"lit.num_digits": -0.018,
|
||||
"lit.num_others": -0.5554,
|
||||
"lit.others": -2.0002,
|
||||
"lit.prefix_common_len": 0.2831,
|
||||
"lit.prefix_dict_len": 0.0299,
|
||||
"lit.short": -0.2482,
|
||||
"lit.unknown_score": 0.2479,
|
||||
"lit.upper": 20.0,
|
||||
"seg.switch": -1.7203,
|
||||
"zh.bias": 1.3522,
|
||||
"zh.lexscore": 0.26,
|
||||
"seg.switch": -1.7596,
|
||||
"zh.bias": 1.3423,
|
||||
"zh.lexscore": 0.2917,
|
||||
"zh.pending_invalid": -5.0,
|
||||
"zh.pending_prefix": -0.9295,
|
||||
"zh.phrase": 0.4595,
|
||||
"zh.reordered": -1.4348,
|
||||
"zh.pending_prefix": -0.9162,
|
||||
"zh.phrase": 0.4499,
|
||||
"zh.reordered": -1.3079,
|
||||
"zh.stray": -5.0,
|
||||
"zh.toned_invalid": -5.0,
|
||||
"zh.toned_valid_lex": -0.9823,
|
||||
"zh.toned_valid_nolex": -1.8742,
|
||||
"zh.unconfirmed": -0.7891,
|
||||
"zh.toned_valid_lex": -0.9018,
|
||||
"zh.toned_valid_nolex": -1.6341,
|
||||
"zh.unconfirmed": -0.7952,
|
||||
"zh.untoned_mid_invalid": -5.0,
|
||||
"zh.untoned_mid_valid": -2.8009
|
||||
"zh.untoned_mid_valid": -2.7479
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,22 +11,28 @@ enum Shared {
|
||||
|
||||
static let classifier: Classifier = {
|
||||
let bundle = Bundle.main
|
||||
let start = Date()
|
||||
let lexicon = Lexicon()
|
||||
if let url = bundle.url(forResource: "lexicon", withExtension: "txt"),
|
||||
let text = try? String(contentsOf: url, encoding: .utf8) {
|
||||
lexicon.load(text)
|
||||
let data = try? Data(contentsOf: url) {
|
||||
lexicon.load(data: data)
|
||||
}
|
||||
// Optional user phrases: ~/Library/Application Support/AutoZhuyin/user-phrases.txt
|
||||
if let support = FileManager.default.urls(for: .applicationSupportDirectory, in: .userDomainMask).first {
|
||||
let userFile = support.appendingPathComponent("AutoZhuyin/user-phrases.txt")
|
||||
if let text = try? String(contentsOf: userFile, encoding: .utf8) { lexicon.load(text) }
|
||||
}
|
||||
let english = EnglishModel(commonWordsURL: bundle.url(forResource: "english-common", withExtension: "txt"))
|
||||
let english = EnglishModel(commonWordsURL: bundle.url(forResource: "english-common", withExtension: "txt"),
|
||||
dictionaryURL: bundle.url(forResource: "english-dict", withExtension: "txt"),
|
||||
bigramURL: bundle.url(forResource: "english-bigram", withExtension: "json"))
|
||||
let saved = UserDefaults.standard.dictionary(forKey: learnedKey) as? [String: Int] ?? [:]
|
||||
let learned = LearnedPreferences(weights: saved) { weights in
|
||||
UserDefaults.standard.set(weights, forKey: learnedKey)
|
||||
}
|
||||
let trained = Features.loadWeights(from: bundle.url(forResource: "classifier-weights", withExtension: "json"))
|
||||
NSLog("AutoZhuyin: data loaded in %.0f ms", Date().timeIntervalSince(start) * 1000)
|
||||
// Only needed for untoned syllables; build it off the startup path.
|
||||
DispatchQueue.global(qos: .utility).async { lexicon.prepareTonelessIndex() }
|
||||
return Classifier(lexicon: lexicon, english: english, learned: learned, weights: trained)
|
||||
}()
|
||||
}
|
||||
|
||||
@@ -58,9 +58,6 @@ public final class Classifier {
|
||||
/// Feature weights: the hand-tuned defaults overlaid with trained ones.
|
||||
public private(set) var weights: FeatureVector
|
||||
|
||||
/// How much the previous segment's mode pulls the current one.
|
||||
public var contextWeight = 1.5
|
||||
|
||||
public init(lexicon: Lexicon, english: EnglishModel, learned: LearnedPreferences = LearnedPreferences(),
|
||||
weights: FeatureVector = [:]) {
|
||||
self.lexicon = lexicon
|
||||
@@ -69,23 +66,22 @@ public final class Classifier {
|
||||
self.weights = Features.defaultWeights.merging(weights) { _, new in new }
|
||||
}
|
||||
|
||||
/// (Zhuyin features or nil, literal features or nil) for one segment.
|
||||
public func segmentFeatures(_ seg: [Character], isLast: Bool, afterOther: Bool,
|
||||
finishing: Bool) -> (FeatureVector?, FeatureVector?) {
|
||||
(Features.zhuyin(seg, lexicon: lexicon, isLast: isLast, afterOther: afterOther, finishing: finishing),
|
||||
Features.literal(seg, english: english, isLast: isLast, afterOther: afterOther, finishing: finishing))
|
||||
/// (Zhuyin features or nil, literal features or nil) for one segment. `previous` (mode of
|
||||
/// the text committed just before) only affects the first segment.
|
||||
public func segmentFeatures(_ seg: [Character], isLast: Bool, afterOther: Bool, finishing: Bool,
|
||||
previous: InputMode? = nil) -> (FeatureVector?, FeatureVector?) {
|
||||
(Features.zhuyin(seg, lexicon: lexicon, isLast: isLast, afterOther: afterOther,
|
||||
finishing: finishing, previous: previous),
|
||||
Features.literal(seg, english: english, isLast: isLast, afterOther: afterOther,
|
||||
finishing: finishing, previous: previous))
|
||||
}
|
||||
|
||||
private func scores(_ seg: [Character], isLast: Bool, afterOther: Bool, finishing: Bool,
|
||||
previous: InputMode?, whole: Bool) -> [Double] {
|
||||
let (fz, fl) = segmentFeatures(seg, isLast: isLast, afterOther: afterOther, finishing: finishing)
|
||||
let (fz, fl) = segmentFeatures(seg, isLast: isLast, afterOther: afterOther,
|
||||
finishing: finishing, previous: previous)
|
||||
var zh = fz.map { Features.dot(weights, $0) } ?? -.infinity
|
||||
var lit = fl.map { Features.dot(weights, $0) } ?? -.infinity
|
||||
switch previous {
|
||||
case .zhuyin?: zh += contextWeight
|
||||
case .literal?: lit += contextWeight
|
||||
case nil: break
|
||||
}
|
||||
if whole {
|
||||
let b = learned.bias(for: String(seg))
|
||||
if b > 0 { zh += b } else { lit -= b }
|
||||
|
||||
@@ -8,33 +8,63 @@ import Foundation
|
||||
/// - a letter-bigram model trained on those words, for words not in either list.
|
||||
public final class EnglishModel {
|
||||
private var common = Set<String>()
|
||||
private var dictionary = Set<String>()
|
||||
private var sortedWords: [String] = []
|
||||
private var sortedCommon: [String] = []
|
||||
/// Dictionary words (lowercase, > 2 letters), sorted: membership and prefix checks are
|
||||
/// binary searches, so no 230k-entry Set has to be built at startup.
|
||||
private var sortedDict: [String] = []
|
||||
private var bigram: [String: Double] = [:] // "ab" -> log2 P(b|a); "^a", "a$" for boundaries
|
||||
private var unseenBigram = -12.0
|
||||
|
||||
public init(commonWords: [String], dictionaryWords: [String] = []) {
|
||||
/// - Parameter bigram: precomputed table (english-bigram.json); trained from the words if nil.
|
||||
public init(commonWords: [String], dictionaryWords: [String] = [],
|
||||
bigram: (table: [String: Double], unseen: Double)? = nil) {
|
||||
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()
|
||||
var dict = dictionaryWords.map { $0.lowercased() }.filter { $0.count > 2 }
|
||||
if !zip(dict, dict.dropFirst()).allSatisfy({ $0 < $1 }) {
|
||||
dict = Array(Set(dict)).sorted()
|
||||
}
|
||||
sortedDict = dict
|
||||
if let bigram {
|
||||
self.bigram = bigram.table
|
||||
unseenBigram = bigram.unseen
|
||||
} else {
|
||||
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")) {
|
||||
/// Loads the bundled data files. Falls back to the system word list and to training
|
||||
/// the bigram table when the precomputed files are missing.
|
||||
public convenience init(commonWordsURL: URL?, dictionaryURL: URL? = nil, bigramURL: URL? = nil) {
|
||||
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("#") }
|
||||
.filter { !$0.isEmpty && !$0.hasPrefix("#") }
|
||||
}
|
||||
self.init(commonWords: lines(commonWordsURL), dictionaryWords: lines(systemDictionary))
|
||||
var bigram: (table: [String: Double], unseen: Double)?
|
||||
if let url = bigramURL, let data = try? Data(contentsOf: url),
|
||||
let obj = try? JSONSerialization.jsonObject(with: data) as? [String: Any],
|
||||
let table = obj["table"] as? [String: Double], let unseen = obj["unseen"] as? Double {
|
||||
bigram = (table, unseen)
|
||||
}
|
||||
let dictURL = dictionaryURL.flatMap { FileManager.default.fileExists(atPath: $0.path) ? $0 : nil }
|
||||
?? URL(fileURLWithPath: "/usr/share/dict/words")
|
||||
self.init(commonWords: lines(commonWordsURL), dictionaryWords: lines(dictURL), bigram: bigram)
|
||||
}
|
||||
|
||||
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) }
|
||||
public func isWord(_ w: String) -> Bool { let l = w.lowercased(); return common.contains(l) || inDictionary(l) }
|
||||
|
||||
private func inDictionary(_ w: String) -> Bool {
|
||||
let i = lowerBound(w, in: sortedDict)
|
||||
return i < sortedDict.count && sortedDict[i] == w
|
||||
}
|
||||
|
||||
/// Some word strictly longer than `p` starts with it (common words or dictionary).
|
||||
private func isPrefixOfWord(_ p: String) -> Bool {
|
||||
hasPrefix(p, in: sortedCommon) || hasPrefix(p, in: sortedDict)
|
||||
}
|
||||
|
||||
/// - Parameter complete: true when the user ended the word (space / punctuation),
|
||||
/// false while still typing (prefixes of words get partial credit).
|
||||
@@ -43,10 +73,10 @@ public final class EnglishModel {
|
||||
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 inDictionary(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 }
|
||||
if isPrefixOfWord(w) { return 0.2 * n }
|
||||
}
|
||||
// Unknown word: judge by how English-like its letter sequence is.
|
||||
let plaus = plausibility(w)
|
||||
@@ -63,12 +93,12 @@ public final class EnglishModel {
|
||||
if common.contains(w) {
|
||||
f["lit.common"] = 1
|
||||
f["lit.common_len"] = n
|
||||
} else if dictionary.contains(w) {
|
||||
} else if inDictionary(w) {
|
||||
f["lit.dict"] = 1
|
||||
f["lit.dict_len"] = n
|
||||
} else if !complete && hasPrefix(w, in: sortedCommon) {
|
||||
f["lit.prefix_common_len"] = n
|
||||
} else if !complete && hasPrefix(w, in: sortedWords) {
|
||||
} else if !complete && isPrefixOfWord(w) {
|
||||
f["lit.prefix_dict_len"] = n
|
||||
} else {
|
||||
let plaus = plausibility(w)
|
||||
@@ -85,12 +115,17 @@ public final class EnglishModel {
|
||||
return total / Double(chars.count - 1)
|
||||
}
|
||||
|
||||
private func hasPrefix(_ p: String, in words: [String]) -> Bool {
|
||||
private func lowerBound(_ p: String, in words: [String]) -> Int {
|
||||
var lo = 0, hi = words.count
|
||||
while lo < hi {
|
||||
let mid = (lo + hi) / 2
|
||||
if words[mid] < p { lo = mid + 1 } else { hi = mid }
|
||||
}
|
||||
return lo
|
||||
}
|
||||
|
||||
private func hasPrefix(_ p: String, in words: [String]) -> Bool {
|
||||
var lo = lowerBound(p, in: words)
|
||||
// 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)
|
||||
@@ -99,7 +134,7 @@ public final class EnglishModel {
|
||||
private func trainBigram() {
|
||||
var pair: [String: Double] = [:]
|
||||
var first: [String: Double] = [:]
|
||||
for w in sortedWords where w.allSatisfy({ $0.isLetter && $0.isASCII }) {
|
||||
for w in Set(sortedCommon + sortedDict).sorted() 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 {
|
||||
|
||||
@@ -42,6 +42,9 @@ public enum Features {
|
||||
"lit.others": -1.5,
|
||||
// Segmentation
|
||||
"seg.switch": -3.0,
|
||||
// Context: the first segment has the same mode as the previously committed text
|
||||
"ctx.zh": 1.5,
|
||||
"ctx.lit": 1.5,
|
||||
]
|
||||
|
||||
/// Reads {"weights": {...}} from a JSON file; empty if missing or invalid.
|
||||
@@ -58,7 +61,8 @@ public enum Features {
|
||||
|
||||
/// Features of `keys` read as Zhuyin, or nil if impossible.
|
||||
public static func zhuyin(_ keys: [Character], lexicon: Lexicon, isLast: Bool = true,
|
||||
afterOther: Bool = false, finishing: Bool = false) -> FeatureVector? {
|
||||
afterOther: Bool = false, finishing: Bool = false,
|
||||
previous: InputMode? = nil) -> FeatureVector? {
|
||||
let parse = ZhuyinParser.parse(keys)
|
||||
// A Zhuyin segment followed by another must end with a tone.
|
||||
if !isLast && parse.pending != nil { return nil }
|
||||
@@ -107,18 +111,27 @@ public enum Features {
|
||||
if isLast && afterOther && !finishing && !parse.syllables.contains(where: \.toned) {
|
||||
add("zh.unconfirmed")
|
||||
}
|
||||
if afterOther { add("seg.switch") }
|
||||
if afterOther {
|
||||
add("seg.switch")
|
||||
} else if previous == .zhuyin {
|
||||
add("ctx.zh")
|
||||
}
|
||||
return f
|
||||
}
|
||||
|
||||
/// Features of `keys` output as typed, or nil if impossible.
|
||||
public static func literal(_ keys: [Character], english: EnglishModel, isLast: Bool = true,
|
||||
afterOther: Bool = false, finishing: Bool = false) -> FeatureVector? {
|
||||
afterOther: Bool = false, finishing: Bool = false,
|
||||
previous: InputMode? = nil) -> FeatureVector? {
|
||||
if keys.isEmpty || keys.contains(" ") { return nil }
|
||||
let complete = !isLast || finishing
|
||||
var f: FeatureVector = ["lit.bias": 1]
|
||||
func add(_ k: String, _ v: Double = 1) { f[k, default: 0] += v }
|
||||
if afterOther { add("seg.switch") }
|
||||
if afterOther {
|
||||
add("seg.switch")
|
||||
} else if previous == .literal {
|
||||
add("ctx.lit")
|
||||
}
|
||||
if keys.contains(where: { $0.isUppercase }) { add("lit.upper") }
|
||||
|
||||
let letters = String(keys.filter { $0.isLetter })
|
||||
|
||||
@@ -11,58 +11,159 @@ public struct LexiconEntry: Equatable {
|
||||
/// File format, one entry per line (`#` starts a comment):
|
||||
/// ㄋㄧˇ-ㄏㄠˇ 你好 -4.2
|
||||
/// The phrase/reading columns may be in either order; the score is optional.
|
||||
///
|
||||
/// Loading is on the input method's startup path, so the file is parsed as raw bytes,
|
||||
/// and the tone-ignoring index (only needed for untoned syllables) is built lazily —
|
||||
/// call `prepareTonelessIndex()` from a background queue to have it ready.
|
||||
public final class Lexicon {
|
||||
private var exact: [String: [LexiconEntry]] = [:]
|
||||
private var toneless: [String: [LexiconEntry]] = [:]
|
||||
private var tonelessIndex: [String: [LexiconEntry]]?
|
||||
private let lock = NSLock()
|
||||
public private(set) var maxPhraseLength = 1
|
||||
|
||||
public init() {}
|
||||
|
||||
public convenience init(contentsOf url: URL) throws {
|
||||
self.init()
|
||||
load(try String(contentsOf: url, encoding: .utf8))
|
||||
load(data: try Data(contentsOf: url))
|
||||
}
|
||||
|
||||
public func load(_ text: String) {
|
||||
for line in text.split(whereSeparator: \.isNewline) {
|
||||
let trimmed = line.trimmingCharacters(in: .whitespaces)
|
||||
if trimmed.isEmpty || trimmed.hasPrefix("#") { continue }
|
||||
let cols = trimmed.split(whereSeparator: { $0 == " " || $0 == "\t" }).map(String.init)
|
||||
guard cols.count >= 2 else { continue }
|
||||
let (reading, phrase) = Lexicon.isBopomofo(cols[0]) ? (cols[0], cols[1]) : (cols[1], cols[0])
|
||||
guard Lexicon.isBopomofo(reading) else { continue }
|
||||
let score = cols.count >= 3 ? Double(cols[2]) ?? -6 : -6
|
||||
add(reading: reading, phrase: phrase, score: score)
|
||||
}
|
||||
for key in exact.keys { exact[key]?.sort { $0.score > $1.score } }
|
||||
for key in toneless.keys { toneless[key]?.sort { $0.score > $1.score } }
|
||||
load(data: Data(text.utf8))
|
||||
}
|
||||
|
||||
public func add(reading rawReading: String, phrase: String, score: Double) {
|
||||
let entry = LexiconEntry(phrase: phrase, score: score)
|
||||
public func load(data: Data) {
|
||||
lock.lock()
|
||||
defer { lock.unlock() }
|
||||
exact.reserveCapacity(exact.count + data.count / 30)
|
||||
data.withUnsafeBytes { (raw: UnsafeRawBufferPointer) in
|
||||
let bytes = raw.bindMemory(to: UInt8.self)
|
||||
let n = bytes.count
|
||||
var i = 0
|
||||
while i < n {
|
||||
var end = i
|
||||
while end < n && bytes[end] != 0x0A { end += 1 }
|
||||
parseLine(bytes, i, end)
|
||||
i = end + 1
|
||||
}
|
||||
}
|
||||
for (key, entries) in exact where entries.count > 1 {
|
||||
exact[key] = entries.sorted { $0.score > $1.score }
|
||||
}
|
||||
tonelessIndex = nil // rebuilt on demand
|
||||
}
|
||||
|
||||
/// Splits one line into up to three space/tab separated fields.
|
||||
private func parseLine(_ b: UnsafeBufferPointer<UInt8>, _ start: Int, _ end: Int) {
|
||||
var fields: [Range<Int>] = []
|
||||
var i = start
|
||||
while i < end && fields.count < 3 {
|
||||
while i < end && (b[i] == 0x20 || b[i] == 0x09 || b[i] == 0x0D) { i += 1 }
|
||||
if i >= end { break }
|
||||
if fields.isEmpty && b[i] == 0x23 { return } // "#" comment
|
||||
let s = i
|
||||
while i < end && b[i] != 0x20 && b[i] != 0x09 && b[i] != 0x0D { i += 1 }
|
||||
fields.append(s..<i)
|
||||
}
|
||||
guard fields.count >= 2 else { return }
|
||||
func str(_ r: Range<Int>) -> String { String(decoding: UnsafeBufferPointer(rebasing: b[r]), as: UTF8.self) }
|
||||
let (r, p) = Lexicon.isBopomofo(b, fields[0]) ? (fields[0], fields[1]) : (fields[1], fields[0])
|
||||
guard Lexicon.isBopomofo(b, r) else { return }
|
||||
let score = fields.count >= 3 ? Lexicon.parseDouble(b, fields[2]) ?? -6 : -6
|
||||
// Neutral tone written as a prefix ("˙ㄉㄜ") needs normalising; detect it on bytes.
|
||||
var prefixNeutral = b[r.lowerBound] == 0xCB
|
||||
var k = r.lowerBound
|
||||
while !prefixNeutral && k + 2 < r.upperBound {
|
||||
if b[k] == 0x2D && b[k + 1] == 0xCB && b[k + 2] == 0x99 { prefixNeutral = true }
|
||||
k += 1
|
||||
}
|
||||
addEntry(reading: str(r), phrase: str(p), score: score, normalise: prefixNeutral)
|
||||
}
|
||||
|
||||
/// Parses "-3.9151"-style decimals without creating a String.
|
||||
private static func parseDouble(_ b: UnsafeBufferPointer<UInt8>, _ r: Range<Int>) -> Double? {
|
||||
var i = r.lowerBound
|
||||
var sign = 1.0
|
||||
if i < r.upperBound && (b[i] == 0x2D || b[i] == 0x2B) { sign = b[i] == 0x2D ? -1 : 1; i += 1 }
|
||||
var value = 0.0, scale = 1.0, digits = 0, fraction = false
|
||||
while i < r.upperBound {
|
||||
let c = b[i]
|
||||
if c >= 0x30 && c <= 0x39 {
|
||||
if fraction { scale /= 10; value += Double(c - 0x30) * scale } else { value = value * 10 + Double(c - 0x30) }
|
||||
digits += 1
|
||||
} else if c == 0x2E && !fraction {
|
||||
fraction = true
|
||||
} else {
|
||||
return Double(String(decoding: UnsafeBufferPointer(rebasing: b[r]), as: UTF8.self))
|
||||
}
|
||||
i += 1
|
||||
}
|
||||
return digits > 0 ? sign * value : nil
|
||||
}
|
||||
|
||||
/// Adds one entry (call `load` for bulk data; this does not re-sort).
|
||||
public func add(reading: String, phrase: String, score: Double) {
|
||||
lock.lock()
|
||||
defer { lock.unlock() }
|
||||
let key = addEntry(reading: reading, phrase: phrase, score: score, normalise: reading.contains("˙"))
|
||||
exact[key]?.sort { $0.score > $1.score }
|
||||
tonelessIndex = nil
|
||||
}
|
||||
|
||||
@discardableResult
|
||||
private func addEntry(reading rawReading: String, phrase: String, score: Double, normalise: Bool) -> String {
|
||||
var reading = rawReading
|
||||
// Some data sets write the neutral tone as a prefix ("˙ㄉㄜ"); we use a suffix.
|
||||
let syllables = rawReading.split(separator: "-").map { s -> String in
|
||||
s.hasPrefix("˙") ? String(s.dropFirst()) + "˙" : String(s)
|
||||
if normalise {
|
||||
reading = reading.split(separator: "-").map { s -> String in
|
||||
s.hasPrefix("˙") ? String(s.dropFirst()) + "˙" : String(s)
|
||||
}.joined(separator: "-")
|
||||
}
|
||||
let reading = syllables.joined(separator: "-")
|
||||
maxPhraseLength = max(maxPhraseLength, syllables.count)
|
||||
if !(exact[reading]?.contains { $0.phrase == phrase } ?? false) {
|
||||
exact[reading, default: []].append(entry)
|
||||
maxPhraseLength = max(maxPhraseLength, reading.utf8.reduce(1) { $0 + ($1 == 0x2D ? 1 : 0) })
|
||||
if exact[reading] == nil {
|
||||
exact[reading] = [LexiconEntry(phrase: phrase, score: score)]
|
||||
} else if !exact[reading]!.contains(where: { $0.phrase == phrase }) {
|
||||
exact[reading]!.append(LexiconEntry(phrase: phrase, score: score))
|
||||
}
|
||||
let key = Lexicon.stripTones(reading)
|
||||
if let i = toneless[key]?.firstIndex(where: { $0.phrase == phrase }) {
|
||||
toneless[key]![i].score = max(toneless[key]![i].score, score)
|
||||
} else {
|
||||
toneless[key, default: []].append(entry)
|
||||
return reading
|
||||
}
|
||||
|
||||
/// Builds the index that ignores tones (for untoned syllables). Safe to call from a
|
||||
/// background queue; lookups build it themselves if it is not ready yet.
|
||||
public func prepareTonelessIndex() {
|
||||
lock.lock()
|
||||
defer { lock.unlock() }
|
||||
_ = buildTonelessIfNeeded()
|
||||
}
|
||||
|
||||
private func buildTonelessIfNeeded() -> [String: [LexiconEntry]] {
|
||||
if let index = tonelessIndex { return index }
|
||||
var best: [String: [String: Double]] = [:]
|
||||
for (reading, entries) in exact {
|
||||
let key = Lexicon.stripTones(reading)
|
||||
for e in entries {
|
||||
if let s = best[key]?[e.phrase], s >= e.score { continue }
|
||||
best[key, default: [:]][e.phrase] = e.score
|
||||
}
|
||||
}
|
||||
var index: [String: [LexiconEntry]] = [:]
|
||||
index.reserveCapacity(best.count)
|
||||
for (key, phrases) in best {
|
||||
index[key] = phrases.map { LexiconEntry(phrase: $0.key, score: $0.value) }
|
||||
.sorted { $0.score != $1.score ? $0.score > $1.score : $0.phrase < $1.phrase }
|
||||
}
|
||||
tonelessIndex = index
|
||||
return index
|
||||
}
|
||||
|
||||
/// Entries for a sequence of readings. Untoned syllables match any tone.
|
||||
public func entries(for syllables: [Syllable]) -> [LexiconEntry] {
|
||||
lock.lock()
|
||||
defer { lock.unlock() }
|
||||
if syllables.allSatisfy({ $0.tone != nil }) {
|
||||
return exact[syllables.map(\.reading).joined(separator: "-")] ?? []
|
||||
}
|
||||
return toneless[syllables.map(\.toneless).joined(separator: "-")] ?? []
|
||||
return buildTonelessIfNeeded()[syllables.map(\.toneless).joined(separator: "-")] ?? []
|
||||
}
|
||||
|
||||
public func bestScore(for syllable: Syllable) -> Double? {
|
||||
@@ -81,4 +182,13 @@ public final class Lexicon {
|
||||
guard let first = s.unicodeScalars.first else { return false }
|
||||
return (0x3105...0x312F).contains(first.value) || first == "˙"
|
||||
}
|
||||
|
||||
/// Same test on raw UTF-8: Bopomofo U+3105–U+312F is E3 84 85…E3 84 AF; "˙" is CB 99.
|
||||
private static func isBopomofo(_ b: UnsafeBufferPointer<UInt8>, _ r: Range<Int>) -> Bool {
|
||||
guard r.count >= 2 else { return false }
|
||||
if b[r.lowerBound] == 0xCB && b[r.lowerBound + 1] == 0x99 { return true }
|
||||
guard r.count >= 3, b[r.lowerBound] == 0xE3, b[r.lowerBound + 1] == 0x84 else { return false }
|
||||
let c = b[r.lowerBound + 2]
|
||||
return c >= 0x85 && c <= 0xAF
|
||||
}
|
||||
}
|
||||
|
||||
@@ -6,7 +6,10 @@ private let resources = URL(fileURLWithPath: #filePath)
|
||||
.appendingPathComponent("Resources")
|
||||
|
||||
private let sharedLexicon = try! Lexicon(contentsOf: resources.appendingPathComponent("lexicon.txt"))
|
||||
private let sharedEnglish = EnglishModel(commonWordsURL: resources.appendingPathComponent("english-common.txt"))
|
||||
private let windowsData = resources.deletingLastPathComponent().appendingPathComponent("windows/autozhuyin/data")
|
||||
private let sharedEnglish = EnglishModel(commonWordsURL: resources.appendingPathComponent("english-common.txt"),
|
||||
dictionaryURL: windowsData.appendingPathComponent("english-dict.txt"),
|
||||
bigramURL: windowsData.appendingPathComponent("english-bigram.json"))
|
||||
private let sharedWeights = Features.loadWeights(from: resources.appendingPathComponent("classifier-weights.json"))
|
||||
|
||||
final class ParserTests: XCTestCase {
|
||||
@@ -265,10 +268,13 @@ final class ParityTests: XCTestCase {
|
||||
for fx in fixtures {
|
||||
let keys = Array(fx["keys"] as! String)
|
||||
let expected = (fx["segments"] as! [[Any]]).map { "\($0[0])-\($0[1]):\($0[2])" }
|
||||
let got = c.segment(keys, finishing: fx["finishing"] as! Bool).map {
|
||||
let previous = (fx["previous"] as? String).flatMap(InputMode.init(rawValue:))
|
||||
let got = c.segment(keys, finishing: fx["finishing"] as! Bool, previous: previous).map {
|
||||
"\($0.range.lowerBound)-\($0.range.upperBound):\($0.mode.rawValue)"
|
||||
}
|
||||
if got != expected { mismatches.append("\(String(keys)) finishing=\(fx["finishing"]!): \(got) vs \(expected)") }
|
||||
if got != expected {
|
||||
mismatches.append("\(String(keys)) finishing=\(fx["finishing"]!) previous=\(String(describing: previous)): \(got) vs \(expected)")
|
||||
}
|
||||
}
|
||||
XCTAssertGreaterThan(fixtures.count, 300)
|
||||
XCTAssertTrue(mismatches.isEmpty, "\(mismatches.count) mismatches:\n" + mismatches.prefix(10).joined(separator: "\n"))
|
||||
@@ -408,3 +414,28 @@ final class CursorTests: XCTestCase {
|
||||
XCTAssertTrue(e.isShowingCandidates)
|
||||
}
|
||||
}
|
||||
|
||||
final class FirstToneAfterEnglishTests: XCTestCase {
|
||||
/// After an English word, a first-tone syllable + space must stay Chinese (機, 吃, 書…).
|
||||
func testFirstToneAfterEnglish() {
|
||||
for keys in ["ru", "t", "gj", "vup", "tj", "el"] {
|
||||
let e = CompositionEngine(classifier: Classifier(lexicon: sharedLexicon, english: sharedEnglish, weights: sharedWeights))
|
||||
var out = ""
|
||||
for c in "hello " + keys + " " { if let t = e.handle(.character(c)).commit { out += t } }
|
||||
XCTAssertEqual(out, "hello ", keys)
|
||||
XCTAssertEqual(e.markedText.count, 1, keys) // still composing one Chinese character
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
final class StartupTimingTests: XCTestCase {
|
||||
func testStartupTiming() throws {
|
||||
var t = Date()
|
||||
func lap(_ name: String) { print(String(format: "STARTUP %@: %.3fs", name, Date().timeIntervalSince(t))); t = Date() }
|
||||
_ = try Lexicon(contentsOf: resources.appendingPathComponent("lexicon.txt")); lap("lexicon")
|
||||
_ = EnglishModel(commonWordsURL: resources.appendingPathComponent("english-common.txt"),
|
||||
dictionaryURL: windowsData.appendingPathComponent("english-dict.txt"),
|
||||
bigramURL: windowsData.appendingPathComponent("english-bigram.json")); lap("english")
|
||||
_ = Features.loadWeights(from: resources.appendingPathComponent("classifier-weights.json")); lap("weights")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -19,6 +19,9 @@ mkdir -p "$APP/Contents/MacOS" "$APP/Contents/Resources"
|
||||
cp "$BIN" "$APP/Contents/MacOS/AutoZhuyin"
|
||||
cp Resources/Info.plist "$APP/Contents/Info.plist"
|
||||
cp Resources/lexicon.txt Resources/english-common.txt Resources/classifier-weights.json "$APP/Contents/Resources/"
|
||||
# Precomputed English dictionary and bigram table (shared with the Windows build).
|
||||
python3 -I windows/tools/build_data.py >/dev/null
|
||||
cp windows/autozhuyin/data/english-dict.txt windows/autozhuyin/data/english-bigram.json "$APP/Contents/Resources/"
|
||||
|
||||
if [ ! -f build/icon.tiff ]; then
|
||||
xcrun swift scripts/make-icon.swift build/icon.tiff
|
||||
|
||||
@@ -23,14 +23,14 @@ def main():
|
||||
clf = core.Classifier(lexicon, english, weights=core.Classifier.load_weights(WEIGHTS_PATH))
|
||||
gen = Generator(os.path.join(DATA, "lexicon.txt"), os.path.join(DATA, "english-common.txt"),
|
||||
os.path.join(DATA, "english-dict.txt"), seed=7)
|
||||
cases = [(k, f) for k in HAND_PICKED for f in (False, True)]
|
||||
while len(cases) < 400:
|
||||
cases = [(k, f, p) for k in HAND_PICKED for f in (False, True) for p in (None, "literal")]
|
||||
while len(cases) < 500:
|
||||
ex = gen.example()
|
||||
if len(ex["keys"]) <= 28:
|
||||
cases.append((ex["keys"], ex["finishing"]))
|
||||
cases.append((gen.prefix_of(ex)["keys"], False))
|
||||
fixtures = [{"keys": k, "finishing": f,
|
||||
"segments": [[s, e, m] for s, e, m in clf.segment(list(k), f)]} for k, f in cases]
|
||||
cases.append((ex["keys"], ex["finishing"], ex["previous"]))
|
||||
cases.append((gen.prefix_of(ex)["keys"], False, ex["previous"]))
|
||||
fixtures = [{"keys": k, "finishing": f, "previous": p,
|
||||
"segments": [[s, e, m] for s, e, m in clf.segment(list(k), f, p)]} for k, f, p in cases]
|
||||
with open(OUT, "w", encoding="utf-8") as fh:
|
||||
json.dump(fixtures, fh, ensure_ascii=False, indent=0)
|
||||
print("wrote %d fixtures to %s" % (len(fixtures), OUT))
|
||||
|
||||
+5114
-3374
File diff suppressed because it is too large
Load Diff
+17
-2
@@ -102,16 +102,31 @@ class Generator:
|
||||
labels = "".join(m * len(p) for m, p in parts)
|
||||
if parts[-1][0] == "l":
|
||||
finishing = True # English / numbers end with a space
|
||||
elif keys[-1] == " " and self.rng.random() < 0.6:
|
||||
# The moment the space (first tone) is pressed: the buffer has no space yet and
|
||||
# the input method decides "first tone" vs "English word + space".
|
||||
keys, labels, finishing = keys[:-1], labels[:-1], True
|
||||
kind += "/tone1"
|
||||
else:
|
||||
# Chinese ends with Enter, or space after a finished (toned) syllable.
|
||||
finishing = keys[-1] != " " and self.rng.random() < 0.5
|
||||
return {"keys": keys, "labels": labels, "finishing": finishing, "kind": kind}
|
||||
return {"keys": keys, "labels": labels, "finishing": finishing, "kind": kind,
|
||||
"previous": self.previous_mode(labels[0])}
|
||||
|
||||
def previous_mode(self, first_label):
|
||||
"""Mode of the text committed just before: none, mostly the same, sometimes the other."""
|
||||
r = self.rng.random()
|
||||
if r < 0.35:
|
||||
return None
|
||||
same = core.ZHUYIN if first_label == "z" else core.LITERAL
|
||||
other = core.LITERAL if first_label == "z" else core.ZHUYIN
|
||||
return same if r < 0.80 else other
|
||||
|
||||
def prefix_of(self, ex):
|
||||
"""The buffer while still typing: a random cut, not finishing."""
|
||||
cut = self.rng.randint(1, len(ex["keys"]) - 1) if len(ex["keys"]) > 1 else 1
|
||||
return {"keys": ex["keys"][:cut], "labels": ex["labels"][:cut], "finishing": False,
|
||||
"kind": ex["kind"] + "/prefix"}
|
||||
"kind": ex["kind"] + "/prefix", "previous": ex["previous"]}
|
||||
|
||||
|
||||
def _cumulative(ws):
|
||||
|
||||
+19
-10
@@ -45,12 +45,12 @@ def labels_of(segs, n):
|
||||
return "".join(lab)
|
||||
|
||||
|
||||
def seg_features(clf, keys, segs, finishing):
|
||||
def seg_features(clf, keys, segs, finishing, previous):
|
||||
"""Summed features of a segmentation, or None if any segment is impossible."""
|
||||
total = defaultdict(float)
|
||||
n = len(keys)
|
||||
for idx, (s, e, m) in enumerate(segs):
|
||||
fz, fl = clf.segment_features(keys[s:e], e == n, idx > 0, finishing)
|
||||
fz, fl = clf.segment_features(keys[s:e], e == n, idx > 0, finishing, previous if idx == 0 else None)
|
||||
f = fz if m == core.ZHUYIN else fl
|
||||
if f is None:
|
||||
return None
|
||||
@@ -62,12 +62,13 @@ def seg_features(clf, keys, segs, finishing):
|
||||
def evaluate(clf, weights, data):
|
||||
by_kind = defaultdict(lambda: [0, 0])
|
||||
for ex in data:
|
||||
segs = clf.segment(list(ex["keys"]), ex["finishing"], None, weights)
|
||||
segs = clf.segment(list(ex["keys"]), ex["finishing"], ex["previous"], weights)
|
||||
ok = labels_of(segs, len(ex["keys"])) == ex["labels"]
|
||||
bucket = by_kind["prefix" if ex["kind"].endswith("/prefix") else ex["kind"]]
|
||||
bucket[0] += ok
|
||||
bucket[1] += 1
|
||||
commit = [v for k, v in by_kind.items() if k != "prefix"]
|
||||
kind = "prefix" if ex["kind"].endswith("/prefix") else ex["kind"]
|
||||
for k in (kind, "after-other") if _after_other(ex) else (kind,):
|
||||
by_kind[k][0] += ok
|
||||
by_kind[k][1] += 1
|
||||
commit = [v for k, v in by_kind.items() if k not in ("prefix", "after-other")]
|
||||
summary = {
|
||||
"commit": sum(c for c, _ in commit) / max(1, sum(t for _, t in commit)),
|
||||
"prefix": by_kind["prefix"][0] / max(1, by_kind["prefix"][1]),
|
||||
@@ -76,6 +77,14 @@ def evaluate(clf, weights, data):
|
||||
return summary
|
||||
|
||||
|
||||
def _after_other(ex):
|
||||
"""Committed buffer whose first segment differs from the text typed just before."""
|
||||
if ex["kind"].endswith("/prefix") or ex["previous"] is None:
|
||||
return False
|
||||
first = core.ZHUYIN if ex["labels"][0] == "z" else core.LITERAL
|
||||
return ex["previous"] != first
|
||||
|
||||
|
||||
def show(name, s):
|
||||
kinds = " ".join("%s %.1f%%" % (k, 100 * v) for k, v in s["by_kind"].items())
|
||||
print("%-9s commit %.2f%% typing %.2f%% [%s]" % (name, 100 * s["commit"], 100 * s["prefix"], kinds))
|
||||
@@ -92,11 +101,11 @@ def train(clf, data, epochs, lr, seed):
|
||||
t0 = time.time()
|
||||
for ex in data:
|
||||
keys = list(ex["keys"])
|
||||
pred = clf.segment(keys, ex["finishing"], None, w)
|
||||
pred = clf.segment(keys, ex["finishing"], ex["previous"], w)
|
||||
if labels_of(pred, len(keys)) != ex["labels"]:
|
||||
gold = gold_segments(ex["labels"])
|
||||
fg = seg_features(clf, keys, gold, ex["finishing"])
|
||||
fp = seg_features(clf, keys, pred, ex["finishing"])
|
||||
fg = seg_features(clf, keys, gold, ex["finishing"], ex["previous"])
|
||||
fp = seg_features(clf, keys, pred, ex["finishing"], ex["previous"])
|
||||
if fg is not None and fp is not None:
|
||||
mistakes += 1
|
||||
scale = lr * (0.5 if ex["kind"].endswith("/prefix") else 1.0)
|
||||
|
||||
@@ -30,7 +30,6 @@ class LearnedPreferences:
|
||||
|
||||
|
||||
class Classifier:
|
||||
context_weight = 1.5
|
||||
|
||||
def __init__(self, lexicon, english, learned=None, weights=None):
|
||||
self.lexicon = lexicon
|
||||
@@ -49,20 +48,17 @@ class Classifier:
|
||||
except (OSError, ValueError):
|
||||
return {}
|
||||
|
||||
def segment_features(self, seg, is_last, after_other, finishing):
|
||||
"""(zhuyin features or None, literal features or None) for one segment."""
|
||||
def segment_features(self, seg, is_last, after_other, finishing, previous=None):
|
||||
"""(zhuyin features or None, literal features or None) for one segment.
|
||||
`previous` (mode of the text committed just before) only affects the first segment."""
|
||||
seg = list(seg)
|
||||
return (zhuyin_features(seg, self.lexicon, is_last, after_other, finishing),
|
||||
literal_features(seg, self.english, is_last, after_other, finishing))
|
||||
return (zhuyin_features(seg, self.lexicon, is_last, after_other, finishing, previous),
|
||||
literal_features(seg, self.english, is_last, after_other, finishing, previous))
|
||||
|
||||
def _scores(self, seg, is_last, after_other, finishing, previous, whole, weights):
|
||||
fz, fl = self.segment_features(seg, is_last, after_other, finishing)
|
||||
fz, fl = self.segment_features(seg, is_last, after_other, finishing, previous)
|
||||
zh = dot(weights, fz) if fz is not None else NEG_INF
|
||||
lit = dot(weights, fl) if fl is not None else NEG_INF
|
||||
if previous == ZHUYIN:
|
||||
zh += self.context_weight
|
||||
elif previous == LITERAL:
|
||||
lit += self.context_weight
|
||||
if whole:
|
||||
b = self.learned.bias("".join(seg))
|
||||
if b > 0:
|
||||
|
||||
@@ -41,6 +41,9 @@ DEFAULT_WEIGHTS = {
|
||||
"lit.others": -1.5,
|
||||
# Segmentation
|
||||
"seg.switch": -3.0,
|
||||
# Context: the first segment has the same mode as the previously committed text
|
||||
"ctx.zh": 1.5,
|
||||
"ctx.lit": 1.5,
|
||||
}
|
||||
|
||||
|
||||
@@ -52,7 +55,7 @@ def _add(f, k, v=1.0):
|
||||
f[k] = f.get(k, 0.0) + v
|
||||
|
||||
|
||||
def zhuyin_features(keys, lexicon, is_last=True, after_other=False, finishing=False):
|
||||
def zhuyin_features(keys, lexicon, is_last=True, after_other=False, finishing=False, previous=None):
|
||||
"""Features of `keys` read as Zhuyin, or None if impossible."""
|
||||
parse = bopomofo.parse(keys)
|
||||
if not is_last and parse.pending is not None:
|
||||
@@ -99,10 +102,12 @@ def zhuyin_features(keys, lexicon, is_last=True, after_other=False, finishing=Fa
|
||||
_add(f, "zh.unconfirmed")
|
||||
if after_other:
|
||||
_add(f, "seg.switch")
|
||||
elif previous == "zhuyin":
|
||||
_add(f, "ctx.zh")
|
||||
return f
|
||||
|
||||
|
||||
def literal_features(keys, english, is_last=True, after_other=False, finishing=False):
|
||||
def literal_features(keys, english, is_last=True, after_other=False, finishing=False, previous=None):
|
||||
"""Features of `keys` output as typed, or None if impossible."""
|
||||
if not keys or " " in keys:
|
||||
return None
|
||||
@@ -110,6 +115,8 @@ def literal_features(keys, english, is_last=True, after_other=False, finishing=F
|
||||
f = {"lit.bias": 1.0}
|
||||
if after_other:
|
||||
_add(f, "seg.switch")
|
||||
elif previous == "literal":
|
||||
_add(f, "ctx.lit")
|
||||
if any(c.isupper() for c in keys):
|
||||
_add(f, "lit.upper")
|
||||
letters = "".join(c for c in keys if c.isalpha())
|
||||
|
||||
@@ -16,7 +16,7 @@ class Lexicon:
|
||||
|
||||
def __init__(self):
|
||||
self.exact = {}
|
||||
self.toneless = {}
|
||||
self._toneless = None # built on first use (only untoned syllables need it)
|
||||
self.max_phrase_length = 1
|
||||
|
||||
@classmethod
|
||||
@@ -42,9 +42,10 @@ class Lexicon:
|
||||
except ValueError:
|
||||
score = -6.0
|
||||
self.add(reading, phrase, score)
|
||||
for table in (self.exact, self.toneless):
|
||||
for v in table.values():
|
||||
for v in self.exact.values():
|
||||
if len(v) > 1:
|
||||
v.sort(key=lambda e: -e[1])
|
||||
self._toneless = None
|
||||
|
||||
def add(self, reading, phrase, score):
|
||||
syllables = [s[1:] + "˙" if s.startswith("˙") else s for s in reading.split("-")]
|
||||
@@ -53,15 +54,20 @@ class Lexicon:
|
||||
entries = self.exact.setdefault(reading, [])
|
||||
if not any(p == phrase for p, _ in entries):
|
||||
entries.append((phrase, score))
|
||||
key = _strip_tones(reading)
|
||||
tl = self.toneless.setdefault(key, [])
|
||||
for i, (p, s) in enumerate(tl):
|
||||
if p == phrase:
|
||||
if score > s:
|
||||
tl[i] = (p, score)
|
||||
break
|
||||
else:
|
||||
tl.append((phrase, score))
|
||||
self._toneless = None
|
||||
|
||||
@property
|
||||
def toneless(self):
|
||||
"""Index ignoring tones: toneless reading -> [(phrase, best score)], best first."""
|
||||
if self._toneless is None:
|
||||
best = {}
|
||||
for reading, entries in self.exact.items():
|
||||
bucket = best.setdefault(_strip_tones(reading), {})
|
||||
for phrase, score in entries:
|
||||
if score > bucket.get(phrase, float("-inf")):
|
||||
bucket[phrase] = score
|
||||
self._toneless = {k: sorted(v.items(), key=lambda e: -e[1]) for k, v in best.items()}
|
||||
return self._toneless
|
||||
|
||||
def entries(self, syllables):
|
||||
if all(s.tone is not None for s in syllables):
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "自動注音 AutoZhuyin",
|
||||
"version": "0.6.0",
|
||||
"version": "0.6.2",
|
||||
"guid": "{3895C6E3-6D40-4B4B-B4EA-CEEC75382D23}",
|
||||
"locale": "zh-Hant-TW",
|
||||
"fallbackLocale": "zh-TW",
|
||||
|
||||
@@ -271,5 +271,13 @@ class CursorTests(unittest.TestCase):
|
||||
self.assertTrue(e.showing_candidates)
|
||||
|
||||
|
||||
class FirstToneAfterEnglishTests(unittest.TestCase):
|
||||
def test_first_tone_after_english(self):
|
||||
for keys in ["ru", "t", "gj", "vup", "tj", "el"]:
|
||||
e = make_engine()
|
||||
self.assertEqual(type_keys("hello " + keys + " ", e), "hello ", keys)
|
||||
self.assertEqual(len(e.marked_text), 1, keys)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
Reference in New Issue
Block a user