Compare commits
6
Commits
v0.5.0
..
bb9cb0c4e0
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
bb9cb0c4e0 | ||
|
|
2c5c70c066 | ||
|
|
17f7d6f50d | ||
|
|
7e173a1da8 | ||
|
|
fa0b78e5a4 | ||
|
|
e928d08fdc |
@@ -12,7 +12,7 @@
|
||||
- **中英自動判斷**:每按一個鍵就重新判斷,組字區即時顯示結果(Mac 版英文以藍字顯示)
|
||||
- **中英混打不用空白**:`ji3hello` → 我hello、`hellosu3cl3` → hello你好,同一段內會自動切分
|
||||
- **判斷錯了按 Tab**:在中/英之間翻轉,輸入法會記住這組按鍵,下次自動判斷對
|
||||
- **單按 Shift 強制英文**:要打英文時先單按一下 Shift,接下來這個字照打、保持小寫
|
||||
- **單按 Shift 切換英文模式**:英文模式下按鍵直接送出、保持小寫、不顯示底線,再單按一次 Shift 回到中英自動判斷
|
||||
- **注音順序打錯也能修正**:`ㄧㄒㄠˇ`、`ㄒㄠㄧˇ` 都會變成 `ㄒㄧㄠˇ`(小)
|
||||
- **可省略聲調**:`jiap7`(ㄨㄛ ㄇㄣ˙)一樣能打出「我們」
|
||||
- **候選字**:用 ← → 把游標移到要改的字後面,按 ↓ 選字;選過的會固定下來
|
||||
@@ -54,7 +54,7 @@ SmartScreen 出現警告時,按「其他資訊 → 仍要執行」。解除安
|
||||
| ← → | 在組字區移動游標,選要改哪個字 |
|
||||
| ↓ | 開啟游標前那個字或詞的候選字(游標預設在最後),數字鍵 1–9 選字,Esc 關閉 |
|
||||
| Esc | 取消組字 |
|
||||
| **單按 Shift** | 沒在打字時:下一個字強制英文(保持小寫),送出後恢復自動判斷,再按一次取消。打到一半時:同 Tab,整段翻轉 |
|
||||
| **單按 Shift** | 沒在打字時:切換**英文模式**,按鍵直接送出、保持小寫、沒有底線,一直維持到再單按一次 Shift 才回到中英自動判斷。打到一半時:同 Tab,整段翻轉 |
|
||||
| Shift + 字母 | 打大寫字母(也會強制英文) |
|
||||
| `< > ? ! : ( ) [ ]` | 中文語境下自動轉成全形 `,。?!:()「」` |
|
||||
| `, . / ; -` | 英文單字後是標點;在注音中是 ㄝ ㄡ ㄥ ㄤ ㄦ(例如 `2;3` = 檔) |
|
||||
@@ -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>0.5.0</string>
|
||||
<string>0.6.1</string>
|
||||
<key>CFBundleVersion</key>
|
||||
<string>6</string>
|
||||
<string>9</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
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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 }
|
||||
|
||||
@@ -35,12 +35,12 @@ public final class CompositionEngine {
|
||||
public let converter: Converter
|
||||
|
||||
public private(set) var keys: [Character] = []
|
||||
/// Set by Tab / Shift tap: overrides the classifier for the whole buffer.
|
||||
/// Set by Tab / a Shift tap while typing: overrides the classifier for the whole
|
||||
/// buffer. It is a correction, learned on commit.
|
||||
public private(set) var forcedMode: InputMode?
|
||||
/// True when forcedMode corrects the classifier (learned on commit); false when the
|
||||
/// user forced English before typing (Shift tap on an empty buffer), which is not a
|
||||
/// correction and is not learned.
|
||||
private var forcedIsCorrection = false
|
||||
/// English mode, toggled by a Shift tap when nothing is being typed. Keys go straight
|
||||
/// to the app (no composition, no underline) until Shift is tapped again.
|
||||
public private(set) var isEnglishMode = false
|
||||
/// User-picked phrases: Zhuyin segment start (key index) → syllable range → text.
|
||||
private var fixed: [Int: [Range<Int>: String]] = [:]
|
||||
public private(set) var candidates: [Candidate] = []
|
||||
@@ -165,11 +165,7 @@ public final class CompositionEngine {
|
||||
cursor = nil
|
||||
keys.removeLast()
|
||||
fixed = fixed.filter { $0.key < keys.count }
|
||||
if keys.isEmpty {
|
||||
// A Shift-tap "next word is English" stays armed; a correction is dropped.
|
||||
if forcedIsCorrection { forcedMode = nil; forcedIsCorrection = false }
|
||||
fixed = [:]
|
||||
}
|
||||
if keys.isEmpty { forcedMode = nil; fixed = [:] }
|
||||
return .consumed
|
||||
case .enter:
|
||||
guard !keys.isEmpty else { return .passThrough }
|
||||
@@ -184,9 +180,10 @@ public final class CompositionEngine {
|
||||
return .consumed
|
||||
case .shiftTap:
|
||||
if keys.isEmpty {
|
||||
// Next word is English, typed as-is (lowercase stays lowercase). Tap again to cancel.
|
||||
forcedMode = forcedMode == .literal ? nil : .literal
|
||||
forcedIsCorrection = false
|
||||
// Toggle English mode; it stays on until the next Shift tap.
|
||||
isEnglishMode.toggle()
|
||||
previousMode = isEnglishMode ? .literal : nil
|
||||
previousCommitTime = now()
|
||||
} else {
|
||||
flip()
|
||||
}
|
||||
@@ -211,14 +208,12 @@ public final class CompositionEngine {
|
||||
/// Forces the whole buffer into the other mode (a correction that is learned).
|
||||
private func flip() {
|
||||
forcedMode = (mode == .zhuyin) ? .literal : .zhuyin
|
||||
forcedIsCorrection = true
|
||||
}
|
||||
|
||||
/// True while the user has forced English before typing anything (Shift tap).
|
||||
public var isEnglishArmed: Bool { keys.isEmpty && forcedMode == .literal }
|
||||
|
||||
private func handleCharacter(_ c: Character) -> KeyResult {
|
||||
cursor = nil // typing always continues at the end
|
||||
// English mode: every key goes to the app as typed.
|
||||
if isEnglishMode && keys.isEmpty { return .passThrough }
|
||||
if c == " " {
|
||||
guard !keys.isEmpty else { return .passThrough }
|
||||
let segs = segments(of: keys, finishing: true)
|
||||
@@ -315,7 +310,7 @@ public final class CompositionEngine {
|
||||
private func commitCurrent(_ given: [Segment]? = nil) -> String {
|
||||
let segs = given ?? segments
|
||||
let text = segs.map { render($0, final: true) }.joined()
|
||||
if let forced = forcedMode, forcedIsCorrection {
|
||||
if let forced = forcedMode {
|
||||
classifier.learned.record(String(keys), as: forced)
|
||||
}
|
||||
previousMode = segs.last?.mode
|
||||
@@ -333,7 +328,6 @@ public final class CompositionEngine {
|
||||
keys = []
|
||||
cursor = nil
|
||||
forcedMode = nil
|
||||
forcedIsCorrection = false
|
||||
fixed = [:]
|
||||
candidates = []
|
||||
}
|
||||
|
||||
@@ -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 })
|
||||
|
||||
@@ -265,10 +265,13 @@ 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"))
|
||||
@@ -297,13 +300,16 @@ final class ShiftTapTests: XCTestCase {
|
||||
return out
|
||||
}
|
||||
|
||||
func testShiftTapForcesNextWordEnglishLowercase() {
|
||||
func testShiftTapTogglesEnglishMode() {
|
||||
let e = engine()
|
||||
// "ru" alone would be ㄐㄧ (機); after a Shift tap it stays English, lowercase.
|
||||
XCTAssertEqual(type("⇧ru ", into: e), "ru ")
|
||||
// Automatic detection resumes after the word.
|
||||
XCTAssertFalse(e.isEnglishArmed)
|
||||
XCTAssertEqual(type("su3cl3\n", into: e), "你好")
|
||||
// "ru" alone would be ㄐㄧ (機); in English mode keys pass straight through, lowercase.
|
||||
XCTAssertEqual(type("⇧ru su ", into: e), "ru su ")
|
||||
XCTAssertTrue(e.isEnglishMode) // still English after spaces
|
||||
XCTAssertEqual(e.markedText, "") // never composed: no underline
|
||||
XCTAssertEqual(type("\n", into: e), "\n") // Enter goes to the app, mode stays
|
||||
XCTAssertTrue(e.isEnglishMode)
|
||||
XCTAssertEqual(type("⇧su3cl3\n", into: e), "你好") // tap again: automatic again
|
||||
XCTAssertFalse(e.isEnglishMode)
|
||||
}
|
||||
|
||||
func testShiftTapTwiceCancels() {
|
||||
@@ -316,22 +322,22 @@ final class ShiftTapTests: XCTestCase {
|
||||
XCTAssertEqual(e.mode, .literal)
|
||||
_ = e.handle(.shiftTap)
|
||||
XCTAssertEqual(e.mode, .zhuyin)
|
||||
XCTAssertFalse(e.isEnglishMode) // a flip, not English mode
|
||||
_ = type("\n", into: e)
|
||||
XCTAssertEqual(e.classifier.learned.weights["so"], 1) // a correction is learned
|
||||
}
|
||||
|
||||
func testForcingBeforeTypingIsNotLearned() {
|
||||
func testEnglishModeIsNotLearned() {
|
||||
let e = engine()
|
||||
_ = type("⇧hello ", into: e)
|
||||
XCTAssertNil(e.classifier.learned.weights["hello"])
|
||||
XCTAssertTrue(e.classifier.learned.weights.isEmpty)
|
||||
}
|
||||
|
||||
func testArmingSurvivesBackspace() {
|
||||
func testBackspaceInEnglishModeGoesToApp() {
|
||||
let e = engine()
|
||||
_ = type("⇧r", into: e)
|
||||
_ = e.handle(.backspace)
|
||||
XCTAssertTrue(e.isEnglishArmed)
|
||||
XCTAssertEqual(type("ru ", into: e), "ru ")
|
||||
_ = type("⇧", into: e)
|
||||
XCTAssertFalse(e.handle(.backspace).handled)
|
||||
XCTAssertTrue(e.isEnglishMode)
|
||||
}
|
||||
|
||||
func testDetector() {
|
||||
@@ -405,3 +411,16 @@ 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
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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)
|
||||
|
||||
@@ -142,8 +142,8 @@ class AutoZhuyinTextService(TextService):
|
||||
return False
|
||||
self.engine.handle(SHIFT_TAP)
|
||||
self._update(None)
|
||||
if self.engine.english_armed:
|
||||
self.showMessage("英文", 1)
|
||||
if not self.engine.keys:
|
||||
self.showMessage("英文" if self.engine.english_mode else "中英自動", 1)
|
||||
return True
|
||||
|
||||
# --- replies ---
|
||||
|
||||
@@ -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:
|
||||
|
||||
@@ -34,9 +34,9 @@ class CompositionEngine:
|
||||
self.now = now
|
||||
self.keys = []
|
||||
self.forced_mode = None
|
||||
# True when forced_mode corrects the classifier (learned on commit); False when the
|
||||
# user forced English before typing (Shift tap on an empty buffer).
|
||||
self._forced_is_correction = False
|
||||
# English mode, toggled by a Shift tap when nothing is being typed: keys go straight
|
||||
# to the app (no composition, no underline) until Shift is tapped again.
|
||||
self.english_mode = False
|
||||
self.fixed = {} # zhuyin segment start -> {(syl_start, syl_end): text}
|
||||
self.candidates = []
|
||||
self.candidate_index = 0
|
||||
@@ -150,19 +150,16 @@ class CompositionEngine:
|
||||
|
||||
# --- key handling ---
|
||||
|
||||
@property
|
||||
def english_armed(self):
|
||||
"""True while the user has forced English before typing anything (Shift tap)."""
|
||||
return not self.keys and self.forced_mode == LITERAL
|
||||
|
||||
def _flip(self):
|
||||
"""Forces the whole buffer into the other mode (a correction that is learned)."""
|
||||
self.forced_mode = LITERAL if self.mode == ZHUYIN else ZHUYIN
|
||||
self._forced_is_correction = True
|
||||
|
||||
def wants(self, key):
|
||||
"""Whether handle(key) would consume the key, without changing state."""
|
||||
if self.candidates or key == SHIFT_TAP:
|
||||
return True
|
||||
if self.english_mode and not self.keys:
|
||||
return False # English mode: everything goes to the app as typed
|
||||
if key in SPECIAL_KEYS:
|
||||
return bool(self.keys)
|
||||
if self.keys:
|
||||
@@ -183,14 +180,13 @@ class CompositionEngine:
|
||||
self.keys.pop()
|
||||
self.fixed = {k: v for k, v in self.fixed.items() if k < len(self.keys)}
|
||||
if not self.keys:
|
||||
# A Shift-tap "next word is English" stays armed; a correction is dropped.
|
||||
if self._forced_is_correction:
|
||||
self.forced_mode = None
|
||||
self._forced_is_correction = False
|
||||
self.forced_mode = None
|
||||
self.fixed = {}
|
||||
return CONSUMED
|
||||
if key == ENTER:
|
||||
return (True, self._commit()) if self.keys else PASS
|
||||
if not self.keys:
|
||||
return PASS
|
||||
return True, self._commit()
|
||||
if key == ESCAPE:
|
||||
if not self.keys:
|
||||
return PASS
|
||||
@@ -203,9 +199,10 @@ class CompositionEngine:
|
||||
return CONSUMED
|
||||
if key == SHIFT_TAP:
|
||||
if not self.keys:
|
||||
# Next word is English, typed as-is. Tap again to cancel.
|
||||
self.forced_mode = None if self.forced_mode == LITERAL else LITERAL
|
||||
self._forced_is_correction = False
|
||||
# Toggle English mode; it stays on until the next Shift tap.
|
||||
self.english_mode = not self.english_mode
|
||||
self._previous_mode = LITERAL if self.english_mode else None
|
||||
self._previous_time = self.now()
|
||||
else:
|
||||
self._flip()
|
||||
return CONSUMED
|
||||
@@ -231,6 +228,8 @@ class CompositionEngine:
|
||||
|
||||
def _handle_character(self, c):
|
||||
self.cursor = None # typing always continues at the end
|
||||
if self.english_mode and not self.keys:
|
||||
return PASS # English mode: every key goes to the app as typed
|
||||
if c == " ":
|
||||
if not self.keys:
|
||||
return PASS
|
||||
@@ -308,7 +307,7 @@ class CompositionEngine:
|
||||
def _commit(self, segs=None):
|
||||
segs = segs if segs is not None else self.segments
|
||||
text = "".join(self._render(s, True) for s in segs)
|
||||
if self.forced_mode and self._forced_is_correction:
|
||||
if self.forced_mode:
|
||||
self.classifier.learned.record("".join(self.keys), self.forced_mode)
|
||||
self._previous_mode = segs[-1][2] if segs else None
|
||||
self._previous_time = self.now()
|
||||
@@ -322,6 +321,5 @@ class CompositionEngine:
|
||||
self.keys = []
|
||||
self.cursor = None
|
||||
self.forced_mode = None
|
||||
self._forced_is_correction = False
|
||||
self.fixed = {}
|
||||
self.candidates = []
|
||||
|
||||
@@ -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())
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "自動注音 AutoZhuyin",
|
||||
"version": "0.5.0",
|
||||
"version": "0.6.1",
|
||||
"guid": "{3895C6E3-6D40-4B4B-B4EA-CEEC75382D23}",
|
||||
"locale": "zh-Hant-TW",
|
||||
"fallbackLocale": "zh-TW",
|
||||
|
||||
@@ -29,8 +29,9 @@
|
||||
← → 在組字區移動游標,選要改哪個字
|
||||
↓ 開啟游標前那個字或詞的候選字,按數字鍵 1–9 選字
|
||||
Esc 取消組字
|
||||
單按 Shift 下一個字強制英文(保持小寫),送出後恢復自動判斷;
|
||||
打到一半時按,同 Tab 整段翻轉。會出現「英文」小提示
|
||||
單按 Shift 切換英文模式(按鍵直接送出、保持小寫、沒有底線),
|
||||
再單按一次回到中英自動判斷,會出現「英文」/「中英自動」小提示;
|
||||
打到一半時按,同 Tab 整段翻轉
|
||||
Shift+字母 打大寫字母(也會強制英文)
|
||||
< > ? ! : 中文語境下自動變成全形 ,。?!:
|
||||
|
||||
|
||||
+23
-11
@@ -194,11 +194,15 @@ class MixedSegmentTests(unittest.TestCase):
|
||||
|
||||
|
||||
class ShiftTapTests(unittest.TestCase):
|
||||
def test_forces_next_word_english_lowercase(self):
|
||||
def test_toggles_english_mode(self):
|
||||
e = make_engine()
|
||||
self.assertEqual(type_keys("⇧ru ", e), "ru ")
|
||||
self.assertFalse(e.english_armed)
|
||||
self.assertEqual(type_keys("su3cl3\n", e), "你好")
|
||||
self.assertEqual(type_keys("⇧ru su ", e), "ru su ")
|
||||
self.assertTrue(e.english_mode)
|
||||
self.assertEqual(e.marked_text, "")
|
||||
self.assertEqual(e.handle(ENTER), (False, None))
|
||||
self.assertTrue(e.english_mode)
|
||||
self.assertEqual(type_keys("⇧su3cl3\n", e), "你好")
|
||||
self.assertFalse(e.english_mode)
|
||||
|
||||
def test_tap_twice_cancels(self):
|
||||
self.assertEqual(type_keys("⇧⇧su3cl3\n", make_engine()), "你好")
|
||||
@@ -208,20 +212,20 @@ class ShiftTapTests(unittest.TestCase):
|
||||
type_keys("so", e)
|
||||
e.handle(SHIFT_TAP)
|
||||
self.assertEqual(e.mode, ZHUYIN)
|
||||
self.assertFalse(e.english_mode)
|
||||
type_keys("\n", e)
|
||||
self.assertEqual(e.classifier.learned.weights["so"], 1)
|
||||
|
||||
def test_forcing_before_typing_not_learned(self):
|
||||
def test_english_mode_not_learned(self):
|
||||
e = make_engine()
|
||||
type_keys("⇧hello ", e)
|
||||
self.assertNotIn("hello", e.classifier.learned.weights)
|
||||
self.assertEqual(e.classifier.learned.weights, {})
|
||||
|
||||
def test_arming_survives_backspace(self):
|
||||
def test_backspace_goes_to_app(self):
|
||||
e = make_engine()
|
||||
type_keys("⇧r", e)
|
||||
e.handle(BACKSPACE)
|
||||
self.assertTrue(e.english_armed)
|
||||
self.assertEqual(type_keys("ru ", e), "ru ")
|
||||
e.handle(SHIFT_TAP)
|
||||
self.assertEqual(e.handle(BACKSPACE), (False, None))
|
||||
self.assertTrue(e.english_mode)
|
||||
|
||||
def test_detector(self):
|
||||
d = ShiftTapDetector()
|
||||
@@ -267,5 +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()
|
||||
|
||||
@@ -144,14 +144,15 @@ class ShiftTapWrapperTests(unittest.TestCase):
|
||||
def test_tap_forces_english_lowercase(self):
|
||||
reply = tap_shift(self.svc)
|
||||
self.assertEqual(reply.get("showMessage"), "英文")
|
||||
self.assertEqual(type_text(self.svc, "ru "), "ru ")
|
||||
self.assertEqual(type_text(self.svc, "ru su "), "ru su ")
|
||||
self.assertEqual(tap_shift(self.svc).get("showMessage"), "中英自動")
|
||||
|
||||
def test_shift_with_letter_is_not_a_tap(self):
|
||||
self.svc.filterKeyDown(FakeKeyEvent("⇧", shift=True))
|
||||
press(self.svc, "H", shift=True)
|
||||
up = FakeKeyEvent("⇧")
|
||||
self.assertFalse(self.svc.filterKeyUp(up))
|
||||
self.assertFalse(self.svc.engine.english_armed)
|
||||
self.assertFalse(self.svc.engine.english_mode)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user