Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
6b4ec39dc1 | ||
|
|
955b0ca5c3 | ||
|
|
251a16fa08 | ||
|
|
7cb1f62dfa | ||
|
|
3670305f0f | ||
|
|
ef9f91a6b7 |
@@ -16,7 +16,7 @@
|
|||||||
- **注音順序打錯也能修正**:`ㄧㄒㄠˇ`、`ㄒㄠㄧˇ` 都會變成 `ㄒㄧㄠˇ`(小)
|
- **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」
|
- **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
|
- **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
|
||||||
- **全形標點**:中文語境下 `?` `!` `<` 自動變成 `?` `!` `,`
|
- **全形標點**:中文語境下 `?` `!` `<` 自動變成 `?` `!` `,`;任何時候按 `` ` `` 再按標點鍵,一定得到全形標點(例如 `` `< `` = `,`)
|
||||||
- **完整詞庫**:約 17 萬筆,來自小麥注音 McBopomofo(MIT 授權)
|
- **完整詞庫**:約 17 萬筆,來自小麥注音 McBopomofo(MIT 授權)
|
||||||
|
|
||||||
## 下載與安裝
|
## 下載與安裝
|
||||||
@@ -58,6 +58,7 @@ SmartScreen 出現警告時,按「其他資訊 → 仍要執行」。解除安
|
|||||||
| Shift + 字母 | 打大寫字母(也會強制英文) |
|
| 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 `,。?!:()「」` |
|
| `< > ? ! : ( ) [ ]` | 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) |
|
| `, . / ; -` | 英文單字後是標點;在注音中是 ㄝ ㄡ ㄥ ㄤ ㄦ(例如 `2;3` = 檔) |
|
||||||
|
| `` ` `` + 標點鍵 | **強制全形標點**,不管前後是中文還是英文:`` `, `` `` `< `` = `,`、`` `. `` `` `> `` = `。`、`` `/ `` = `?`、`` `; `` = `;`、`` `: `` = `:`、`` `' `` `` `\ `` = `、`、`` `[ `` `` `] `` = `「」`、`` `{ `` `` `} `` = `『』`、`` `( `` `` `) `` = `()`、`` `! `` = `!`、`` `~ `` = `~`、`` `- `` = `——`、`` `= `` = `=`。`` ` `` 後面接其他鍵就是普通的反引號(` ``` ` 照常可用) |
|
||||||
|
|
||||||
## 運作方式
|
## 運作方式
|
||||||
|
|
||||||
@@ -211,13 +212,14 @@ windows/
|
|||||||
tests/ Python 測試
|
tests/ Python 測試
|
||||||
tools/ 產生資料檔、圖示
|
tools/ 產生資料檔、圖示
|
||||||
training/ 合成資料、訓練權重、Swift/Python 一致性測試資料
|
training/ 合成資料、訓練權重、Swift/Python 一致性測試資料
|
||||||
|
THIRD_PARTY_LICENSES.txt 第三方授權聲明(會打包進兩個安裝檔)
|
||||||
```
|
```
|
||||||
|
|
||||||
## 已知限制
|
## 已知限制
|
||||||
|
|
||||||
- Windows 版還沒在實機上測試過。
|
- Windows 版還沒在實機上測試過。
|
||||||
- 聲調鍵打在注音符號中間(例如 `uv3l`)無法自動修正。
|
- 聲調鍵打在注音符號中間(例如 `uv3l`)無法自動修正。
|
||||||
- 很短的字串(如 `up` 是英文還是 ㄧㄣ)本質上就有歧義,可能需要按 Tab 修正;修正後會記住。
|
- 很短的字串本質上就有歧義。像 `up`(也是 ㄧㄣ 因)這種常用的,按空白後會先保留,看下一個詞再決定(`up jo4` = 因為、`up the` = up the);其他判斷錯的可以按 Tab 修正,修正後會記住。
|
||||||
- 安裝檔沒有簽章(macOS 沒有 Developer ID,Windows 沒有程式碼簽章憑證)。
|
- 安裝檔沒有簽章(macOS 沒有 Developer ID,Windows 沒有程式碼簽章憑證)。
|
||||||
|
|
||||||
## 下一步(Roadmap)
|
## 下一步(Roadmap)
|
||||||
@@ -237,3 +239,5 @@ training/ 合成資料、訓練權重、Swift/Python 一致
|
|||||||
- 詞庫資料:[小麥注音 McBopomofo](https://github.com/openvanilla/McBopomofo)(MIT License)
|
- 詞庫資料:[小麥注音 McBopomofo](https://github.com/openvanilla/McBopomofo)(MIT License)
|
||||||
- Windows 輸入法框架:[PIME](https://github.com/EasyIME/PIME)(LGPL 2.1,使用者自行安裝,本專案不包含其程式碼)
|
- Windows 輸入法框架:[PIME](https://github.com/EasyIME/PIME)(LGPL 2.1,使用者自行安裝,本專案不包含其程式碼)
|
||||||
- 英文字典:Webster's Second International Dictionary(公有領域,macOS 的 `/usr/share/dict/words`)
|
- 英文字典:Webster's Second International Dictionary(公有領域,macOS 的 `/usr/share/dict/words`)
|
||||||
|
|
||||||
|
完整的第三方授權聲明(含小麥注音 MIT 授權全文)見 [THIRD_PARTY_LICENSES.txt](THIRD_PARTY_LICENSES.txt),Mac 版放在 `AutoZhuyin.app/Contents/Resources/`,Windows 版放在 zip 根目錄和安裝後的 `autozhuyin` 資料夾。
|
||||||
|
|||||||
@@ -15,9 +15,9 @@
|
|||||||
<key>CFBundlePackageType</key>
|
<key>CFBundlePackageType</key>
|
||||||
<string>APPL</string>
|
<string>APPL</string>
|
||||||
<key>CFBundleShortVersionString</key>
|
<key>CFBundleShortVersionString</key>
|
||||||
<string>0.6.2</string>
|
<string>0.7.1</string>
|
||||||
<key>CFBundleVersion</key>
|
<key>CFBundleVersion</key>
|
||||||
<string>10</string>
|
<string>13</string>
|
||||||
<key>InputMethodConnectionName</key>
|
<key>InputMethodConnectionName</key>
|
||||||
<string>com.autozhuyin.inputmethod.AutoZhuyin_Connection</string>
|
<string>com.autozhuyin.inputmethod.AutoZhuyin_Connection</string>
|
||||||
<key>InputMethodServerControllerClass</key>
|
<key>InputMethodServerControllerClass</key>
|
||||||
|
|||||||
@@ -51,6 +51,15 @@ public final class CompositionEngine {
|
|||||||
public var candidateIndex = 0
|
public var candidateIndex = 0
|
||||||
public var isShowingCandidates: Bool { !candidates.isEmpty }
|
public var isShowingCandidates: Bool { !candidates.isEmpty }
|
||||||
|
|
||||||
|
/// Index of a held space: an English word that is also a common one-syllable Chinese
|
||||||
|
/// reading ("up " = ㄧㄣ 因) is not committed on space; the next word decides
|
||||||
|
/// ("up jo4" = 因為, "up the" = up the).
|
||||||
|
private var held: Int?
|
||||||
|
/// "`" was typed: if the next key is in `symbols` it gives that full-width symbol
|
||||||
|
/// whatever the context; anything else makes it a plain backtick (so ``` still works).
|
||||||
|
public private(set) var pendingBacktick = false
|
||||||
|
static let holdMinScore = -3.5
|
||||||
|
|
||||||
private var previousMode: InputMode?
|
private var previousMode: InputMode?
|
||||||
private var previousCommitTime = Date.distantPast
|
private var previousCommitTime = Date.distantPast
|
||||||
/// How long the previous segment's mode keeps influencing the next one.
|
/// How long the previous segment's mode keeps influencing the next one.
|
||||||
@@ -71,9 +80,33 @@ public final class CompositionEngine {
|
|||||||
private func segments(of keys: [Character], finishing: Bool = false) -> [Segment] {
|
private func segments(of keys: [Character], finishing: Bool = false) -> [Segment] {
|
||||||
guard !keys.isEmpty else { return [] }
|
guard !keys.isEmpty else { return [] }
|
||||||
if let forced = forcedMode { return [Segment(range: 0..<keys.count, mode: forced)] }
|
if let forced = forcedMode { return [Segment(range: 0..<keys.count, mode: forced)] }
|
||||||
|
if let h = held, h < keys.count, keys[h] == " " {
|
||||||
|
return heldSegments(keys, held: h, finishing: finishing)
|
||||||
|
}
|
||||||
return classifier.segment(keys, finishing: finishing, previous: context)
|
return classifier.segment(keys, finishing: finishing, previous: context)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/// The held word is Chinese if the words typed after it start with Chinese.
|
||||||
|
private func heldSegments(_ keys: [Character], held h: Int, finishing: Bool) -> [Segment] {
|
||||||
|
let base = h + 1
|
||||||
|
let rest = classifier.segment(Array(keys[base...]), finishing: finishing, previous: nil).map {
|
||||||
|
Segment(range: ($0.range.lowerBound + base)..<($0.range.upperBound + base), mode: $0.mode)
|
||||||
|
}
|
||||||
|
if let first = rest.first, first.mode == .zhuyin {
|
||||||
|
return [Segment(range: 0..<first.range.upperBound, mode: .zhuyin)] + rest.dropFirst()
|
||||||
|
}
|
||||||
|
return [Segment(range: 0..<base, mode: .literal)] + rest
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Whether keys + space also read as a common Chinese syllable (see `held`).
|
||||||
|
private func isAmbiguousWord(_ keys: [Character]) -> Bool {
|
||||||
|
guard keys.allSatisfy({ $0.isASCII && $0.isLetter }) else { return false }
|
||||||
|
let p = ZhuyinParser.parse(keys + [" "])
|
||||||
|
guard p.pending == nil, p.syllables.count == 1 else { return false }
|
||||||
|
guard let best = classifier.lexicon.entries(for: p.syllables.map(\.syllable)).first else { return false }
|
||||||
|
return best.score >= CompositionEngine.holdMinScore
|
||||||
|
}
|
||||||
|
|
||||||
/// Current split of the buffer into Zhuyin / literal runs.
|
/// Current split of the buffer into Zhuyin / literal runs.
|
||||||
public var segments: [Segment] { segments(of: keys) }
|
public var segments: [Segment] { segments(of: keys) }
|
||||||
|
|
||||||
@@ -85,9 +118,11 @@ public final class CompositionEngine {
|
|||||||
|
|
||||||
public var markedPieces: [MarkedPiece] {
|
public var markedPieces: [MarkedPiece] {
|
||||||
let segs = segments
|
let segs = segments
|
||||||
return segs.enumerated().map { i, seg in
|
var pieces = segs.enumerated().map { i, seg in
|
||||||
MarkedPiece(text: render(seg, final: i < segs.count - 1), mode: seg.mode)
|
MarkedPiece(text: render(seg, final: i < segs.count - 1), mode: seg.mode)
|
||||||
}
|
}
|
||||||
|
if pendingBacktick { pieces.append(MarkedPiece(text: "`", mode: .literal)) }
|
||||||
|
return pieces
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Text for one segment. A non-final Zhuyin segment shows its unfinished syllable as Bopomofo.
|
/// Text for one segment. A non-final Zhuyin segment shows its unfinished syllable as Bopomofo.
|
||||||
@@ -156,6 +191,7 @@ public final class CompositionEngine {
|
|||||||
|
|
||||||
public func handle(_ key: KeyInput) -> KeyResult {
|
public func handle(_ key: KeyInput) -> KeyResult {
|
||||||
if isShowingCandidates { return handleCandidateKey(key) }
|
if isShowingCandidates { return handleCandidateKey(key) }
|
||||||
|
if pendingBacktick { return afterBacktick(key) }
|
||||||
|
|
||||||
switch key {
|
switch key {
|
||||||
case .character(let c):
|
case .character(let c):
|
||||||
@@ -164,6 +200,7 @@ public final class CompositionEngine {
|
|||||||
guard !keys.isEmpty else { return .passThrough }
|
guard !keys.isEmpty else { return .passThrough }
|
||||||
cursor = nil
|
cursor = nil
|
||||||
keys.removeLast()
|
keys.removeLast()
|
||||||
|
if let h = held, keys.count <= h { held = nil }
|
||||||
fixed = fixed.filter { $0.key < keys.count }
|
fixed = fixed.filter { $0.key < keys.count }
|
||||||
if keys.isEmpty { forcedMode = nil; fixed = [:] }
|
if keys.isEmpty { forcedMode = nil; fixed = [:] }
|
||||||
return .consumed
|
return .consumed
|
||||||
@@ -214,10 +251,19 @@ public final class CompositionEngine {
|
|||||||
cursor = nil // typing always continues at the end
|
cursor = nil // typing always continues at the end
|
||||||
// English mode: every key goes to the app as typed.
|
// English mode: every key goes to the app as typed.
|
||||||
if isEnglishMode && keys.isEmpty { return .passThrough }
|
if isEnglishMode && keys.isEmpty { return .passThrough }
|
||||||
|
if c == "`" {
|
||||||
|
pendingBacktick = true
|
||||||
|
return .consumed
|
||||||
|
}
|
||||||
if c == " " {
|
if c == " " {
|
||||||
guard !keys.isEmpty else { return .passThrough }
|
guard !keys.isEmpty else { return .passThrough }
|
||||||
let segs = segments(of: keys, finishing: true)
|
let segs = segments(of: keys, finishing: true)
|
||||||
if segs.last?.mode == .literal {
|
if segs.last?.mode == .literal {
|
||||||
|
if held == nil, segs.count == 1, forcedMode == nil, isAmbiguousWord(keys) {
|
||||||
|
held = keys.count
|
||||||
|
keys.append(" ")
|
||||||
|
return .consumed
|
||||||
|
}
|
||||||
return KeyResult(handled: true, commit: commitCurrent(segs) + " ")
|
return KeyResult(handled: true, commit: commitCurrent(segs) + " ")
|
||||||
}
|
}
|
||||||
if parse(ofLast: segs)?.pending != nil {
|
if parse(ofLast: segs)?.pending != nil {
|
||||||
@@ -254,6 +300,26 @@ public final class CompositionEngine {
|
|||||||
return ZhuyinParser.parse(Array(keys[last.range]))
|
return ZhuyinParser.parse(Array(keys[last.range]))
|
||||||
}
|
}
|
||||||
|
|
||||||
|
private func afterBacktick(_ key: KeyInput) -> KeyResult {
|
||||||
|
pendingBacktick = false
|
||||||
|
if key == .escape || key == .backspace { return .consumed }
|
||||||
|
let committed = keys.isEmpty ? "" : commitCurrent()
|
||||||
|
if case .character(let c) = key, let symbol = CompositionEngine.symbols[c] {
|
||||||
|
return KeyResult(handled: true, commit: committed + symbol)
|
||||||
|
}
|
||||||
|
// Not a symbol: the backtick was meant literally; then handle the key as usual.
|
||||||
|
var r = handle(key)
|
||||||
|
if !r.handled, case .character(let c) = key { r = KeyResult(handled: true, commit: String(c)) }
|
||||||
|
return KeyResult(handled: r.handled, commit: committed + "`" + (r.commit ?? ""))
|
||||||
|
}
|
||||||
|
|
||||||
|
/// "`" + key → full-width symbol.
|
||||||
|
static let symbols: [Character: String] = [
|
||||||
|
",": ",", "<": ",", ".": "。", ">": "。", "/": "?", "?": "?", ";": ";", ":": ":",
|
||||||
|
"'": "、", "\\": "、", "\"": "「", "[": "「", "]": "」", "{": "『", "}": "』",
|
||||||
|
"(": "(", ")": ")", "!": "!", "~": "~", "-": "——", "_": "——", "=": "=",
|
||||||
|
]
|
||||||
|
|
||||||
static let fullwidth: [Character: String] = [
|
static let fullwidth: [Character: String] = [
|
||||||
"<": ",", ">": "。", "?": "?", "!": "!", ":": ":", "\"": "「", "(": "(", ")": ")",
|
"<": ",", ">": "。", "?": "?", "!": "!", ":": ":", "\"": "「", "(": "(", ")": ")",
|
||||||
"{": "『", "}": "』", "[": "「", "]": "」", "~": "~", "_": "——",
|
"{": "『", "}": "』", "[": "「", "]": "」", "~": "~", "_": "——",
|
||||||
@@ -326,6 +392,8 @@ public final class CompositionEngine {
|
|||||||
|
|
||||||
public func reset() {
|
public func reset() {
|
||||||
keys = []
|
keys = []
|
||||||
|
held = nil
|
||||||
|
pendingBacktick = false
|
||||||
cursor = nil
|
cursor = nil
|
||||||
forcedMode = nil
|
forcedMode = nil
|
||||||
fixed = [:]
|
fixed = [:]
|
||||||
|
|||||||
@@ -0,0 +1,50 @@
|
|||||||
|
自動注音 AutoZhuyin — 第三方授權聲明 / Third-party notices
|
||||||
|
==========================================================
|
||||||
|
|
||||||
|
本軟體包含或使用下列第三方資料。
|
||||||
|
This software includes or uses the following third-party material.
|
||||||
|
|
||||||
|
|
||||||
|
1. 小麥注音 McBopomofo — 詞庫資料 (lexicon data)
|
||||||
|
------------------------------------------------
|
||||||
|
https://github.com/openvanilla/McBopomofo
|
||||||
|
|
||||||
|
lexicon.txt is converted from McBopomofo's data files (BPMFBase.txt,
|
||||||
|
BPMFMappings.txt, phrase.occ) by scripts/convert-mcbopomofo.py. No McBopomofo
|
||||||
|
program code is included.
|
||||||
|
|
||||||
|
MIT License
|
||||||
|
|
||||||
|
Copyright (c) 2011-2026 Mengjuei Hsieh et al.
|
||||||
|
|
||||||
|
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||||
|
of this software and associated documentation files (the "Software"), to deal
|
||||||
|
in the Software without restriction, including without limitation the rights
|
||||||
|
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||||
|
copies of the Software, and to permit persons to whom the Software is
|
||||||
|
furnished to do so, subject to the following conditions:
|
||||||
|
|
||||||
|
The above copyright notice and this permission notice shall be included in all
|
||||||
|
copies or substantial portions of the Software.
|
||||||
|
|
||||||
|
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||||
|
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||||
|
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||||
|
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||||
|
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||||
|
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||||
|
SOFTWARE.
|
||||||
|
|
||||||
|
|
||||||
|
2. Webster's Second International Dictionary — 英文字典 (English word list)
|
||||||
|
--------------------------------------------------------------------------
|
||||||
|
english-dict.txt is filtered from /usr/share/dict/words (Webster's Second
|
||||||
|
International Dictionary, 1934), which is in the public domain.
|
||||||
|
|
||||||
|
|
||||||
|
3. PIME — Windows 輸入法框架 (input method framework)
|
||||||
|
----------------------------------------------------
|
||||||
|
https://github.com/EasyIME/PIME — GNU LGPL 2.1
|
||||||
|
|
||||||
|
The Windows version runs as a module inside PIME, which users install
|
||||||
|
separately. No PIME code is included in this software.
|
||||||
@@ -428,6 +428,78 @@ final class FirstToneAfterEnglishTests: XCTestCase {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
final class HeldWordTests: XCTestCase {
|
||||||
|
func makeEngine() -> CompositionEngine {
|
||||||
|
CompositionEngine(classifier: Classifier(lexicon: sharedLexicon, english: sharedEnglish, weights: sharedWeights))
|
||||||
|
}
|
||||||
|
|
||||||
|
func type(_ s: String, into e: CompositionEngine) -> String {
|
||||||
|
var out = ""
|
||||||
|
for c in s {
|
||||||
|
let key: KeyInput = c == "\n" ? .enter : .character(c)
|
||||||
|
let r = e.handle(key)
|
||||||
|
if let t = r.commit { out += t } else if !r.handled { out.append(c) }
|
||||||
|
}
|
||||||
|
return out
|
||||||
|
}
|
||||||
|
|
||||||
|
/// "up " is also ㄧㄣ (因): the next word decides.
|
||||||
|
func testNextWordDecides() {
|
||||||
|
let cases = ["up jo4 ": "因為", "up the ": "up the ", "pick up the ": "pick up the ",
|
||||||
|
"up\n": "up", "i love ": "i love "]
|
||||||
|
for (keys, want) in cases {
|
||||||
|
XCTAssertEqual(type(keys, into: makeEngine()), want, keys)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func testHeldWordStaysComposing() {
|
||||||
|
let e = makeEngine()
|
||||||
|
XCTAssertEqual(type("up ", into: e), "")
|
||||||
|
XCTAssertEqual(e.markedText, "up ")
|
||||||
|
_ = e.handle(.backspace)
|
||||||
|
XCTAssertEqual(e.markedText, "up")
|
||||||
|
XCTAssertEqual(type(" the ", into: e), "up the ")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
final class BacktickSymbolTests: XCTestCase {
|
||||||
|
func makeEngine() -> CompositionEngine {
|
||||||
|
CompositionEngine(classifier: Classifier(lexicon: sharedLexicon, english: sharedEnglish, weights: sharedWeights))
|
||||||
|
}
|
||||||
|
|
||||||
|
func type(_ s: String, into e: CompositionEngine) -> String {
|
||||||
|
var out = ""
|
||||||
|
for c in s {
|
||||||
|
let key: KeyInput = c == "\n" ? .enter : .character(c)
|
||||||
|
let r = e.handle(key)
|
||||||
|
if let t = r.commit { out += t } else if !r.handled { out.append(c) }
|
||||||
|
}
|
||||||
|
return out
|
||||||
|
}
|
||||||
|
|
||||||
|
func testForcedSymbols() {
|
||||||
|
let cases = ["`<": ",", "`.": "。", "`?": "?", "`;": ";", "`[": "「",
|
||||||
|
"hello`,": "hello,", "su3cl3`.": "你好。", "```\n": "```"]
|
||||||
|
for (keys, want) in cases {
|
||||||
|
XCTAssertEqual(type(keys, into: makeEngine()), want, keys)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func testPlainBacktick() {
|
||||||
|
let e = makeEngine()
|
||||||
|
XCTAssertEqual(type("`", into: e), "")
|
||||||
|
XCTAssertEqual(e.markedText, "`")
|
||||||
|
XCTAssertEqual(type("ls` ", into: e), "`ls` ")
|
||||||
|
}
|
||||||
|
|
||||||
|
func testBackspaceCancels() {
|
||||||
|
let e = makeEngine()
|
||||||
|
_ = type("su3`", into: e)
|
||||||
|
_ = e.handle(.backspace)
|
||||||
|
XCTAssertEqual(e.markedText, "你")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
final class StartupTimingTests: XCTestCase {
|
final class StartupTimingTests: XCTestCase {
|
||||||
func testStartupTiming() throws {
|
func testStartupTiming() throws {
|
||||||
var t = Date()
|
var t = Date()
|
||||||
|
|||||||
@@ -19,6 +19,7 @@ mkdir -p "$APP/Contents/MacOS" "$APP/Contents/Resources"
|
|||||||
cp "$BIN" "$APP/Contents/MacOS/AutoZhuyin"
|
cp "$BIN" "$APP/Contents/MacOS/AutoZhuyin"
|
||||||
cp Resources/Info.plist "$APP/Contents/Info.plist"
|
cp Resources/Info.plist "$APP/Contents/Info.plist"
|
||||||
cp Resources/lexicon.txt Resources/english-common.txt Resources/classifier-weights.json "$APP/Contents/Resources/"
|
cp Resources/lexicon.txt Resources/english-common.txt Resources/classifier-weights.json "$APP/Contents/Resources/"
|
||||||
|
cp THIRD_PARTY_LICENSES.txt "$APP/Contents/Resources/"
|
||||||
# Precomputed English dictionary and bigram table (shared with the Windows build).
|
# Precomputed English dictionary and bigram table (shared with the Windows build).
|
||||||
python3 -I windows/tools/build_data.py >/dev/null
|
python3 -I windows/tools/build_data.py >/dev/null
|
||||||
cp windows/autozhuyin/data/english-dict.txt windows/autozhuyin/data/english-bigram.json "$APP/Contents/Resources/"
|
cp windows/autozhuyin/data/english-dict.txt windows/autozhuyin/data/english-bigram.json "$APP/Contents/Resources/"
|
||||||
|
|||||||
@@ -26,6 +26,9 @@ rsync -a --exclude __pycache__ --exclude '*.pyc' windows/autozhuyin "$OUT/"
|
|||||||
for f in install.bat uninstall.bat README.txt; do
|
for f in install.bat uninstall.bat README.txt; do
|
||||||
sed 's/$/\r/' "windows/installer/$f" > "$OUT/$f"
|
sed 's/$/\r/' "windows/installer/$f" > "$OUT/$f"
|
||||||
done
|
done
|
||||||
|
# Third-party notices: next to the installer and inside the installed folder.
|
||||||
|
sed 's/$/\r/' THIRD_PARTY_LICENSES.txt > "$OUT/THIRD_PARTY_LICENSES.txt"
|
||||||
|
cp "$OUT/THIRD_PARTY_LICENSES.txt" "$OUT/autozhuyin/"
|
||||||
|
|
||||||
(cd build && zip -qr -X "$NAME.zip" "$NAME")
|
(cd build && zip -qr -X "$NAME.zip" "$NAME")
|
||||||
echo "Built build/$NAME.zip"
|
echo "Built build/$NAME.zip"
|
||||||
|
|||||||
@@ -20,6 +20,19 @@ FULLWIDTH = {
|
|||||||
"{": "『", "}": "』", "[": "「", "]": "」", "~": "~", "_": "——",
|
"{": "『", "}": "』", "[": "「", "]": "」", "~": "~", "_": "——",
|
||||||
}
|
}
|
||||||
|
|
||||||
|
# An English word that is also a common one-syllable Chinese reading ("up " = ㄧㄣ 因)
|
||||||
|
# is not committed on space; the next word decides ("up jo4" = 因為, "up the" = up the).
|
||||||
|
HOLD_MIN_SCORE = -3.5
|
||||||
|
|
||||||
|
# "`" then one of these keys always gives the full-width symbol, whatever the context.
|
||||||
|
# "`" followed by anything else is just a backtick (so ``` still works).
|
||||||
|
BACKTICK = "`"
|
||||||
|
SYMBOLS = {
|
||||||
|
",": ",", "<": ",", ".": "。", ">": "。", "/": "?", "?": "?", ";": ";", ":": ":",
|
||||||
|
"'": "、", "\\": "、", '"': "「", "[": "「", "]": "」", "{": "『", "}": "』",
|
||||||
|
"(": "(", ")": ")", "!": "!", "~": "~", "-": "——", "_": "——", "=": "=",
|
||||||
|
}
|
||||||
|
|
||||||
PASS = (False, None)
|
PASS = (False, None)
|
||||||
CONSUMED = (True, None)
|
CONSUMED = (True, None)
|
||||||
|
|
||||||
@@ -37,12 +50,15 @@ class CompositionEngine:
|
|||||||
# English mode, toggled by a Shift tap when nothing is being typed: keys go straight
|
# 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.
|
# to the app (no composition, no underline) until Shift is tapped again.
|
||||||
self.english_mode = False
|
self.english_mode = False
|
||||||
|
self.backtick = False # "`" typed; the next key may be a forced symbol
|
||||||
self.fixed = {} # zhuyin segment start -> {(syl_start, syl_end): text}
|
self.fixed = {} # zhuyin segment start -> {(syl_start, syl_end): text}
|
||||||
self.candidates = []
|
self.candidates = []
|
||||||
self.candidate_index = 0
|
self.candidate_index = 0
|
||||||
self._candidate_segment_start = 0
|
self._candidate_segment_start = 0
|
||||||
# Composition cursor for choosing candidates: index into _cursor_stops(), None = end.
|
# Composition cursor for choosing candidates: index into _cursor_stops(), None = end.
|
||||||
self.cursor = None
|
self.cursor = None
|
||||||
|
# Index of a held space (see HOLD_MIN_SCORE), or None.
|
||||||
|
self.held = None
|
||||||
self._previous_mode = None
|
self._previous_mode = None
|
||||||
self._previous_time = float("-inf")
|
self._previous_time = float("-inf")
|
||||||
self._cache_key = None
|
self._cache_key = None
|
||||||
@@ -60,12 +76,35 @@ class CompositionEngine:
|
|||||||
if self.forced_mode:
|
if self.forced_mode:
|
||||||
return [(0, len(keys), self.forced_mode)]
|
return [(0, len(keys), self.forced_mode)]
|
||||||
ctx = self.context
|
ctx = self.context
|
||||||
cache_key = (tuple(keys), finishing, ctx)
|
held = self.held if self.held is not None and self.held < len(keys) and keys[self.held] == " " else None
|
||||||
|
cache_key = (tuple(keys), finishing, ctx, held)
|
||||||
if cache_key != self._cache_key:
|
if cache_key != self._cache_key:
|
||||||
self._cache_key = cache_key
|
self._cache_key = cache_key
|
||||||
|
if held is None:
|
||||||
self._cache_value = self.classifier.segment(keys, finishing, ctx)
|
self._cache_value = self.classifier.segment(keys, finishing, ctx)
|
||||||
|
else:
|
||||||
|
self._cache_value = self._held_segments(keys, held, finishing)
|
||||||
return self._cache_value
|
return self._cache_value
|
||||||
|
|
||||||
|
def _held_segments(self, keys, held, finishing):
|
||||||
|
"""The held word is Chinese if the words typed after it start with Chinese."""
|
||||||
|
rest = keys[held + 1:]
|
||||||
|
base = held + 1
|
||||||
|
rest_segs = [(a + base, b + base, m) for a, b, m in self.classifier.segment(rest, finishing, None)]
|
||||||
|
if rest_segs and rest_segs[0][2] == ZHUYIN:
|
||||||
|
return [(0, rest_segs[0][1], ZHUYIN)] + rest_segs[1:]
|
||||||
|
return [(0, base, LITERAL)] + rest_segs
|
||||||
|
|
||||||
|
def _is_ambiguous_word(self, keys):
|
||||||
|
"""Whether keys + space also read as a common Chinese syllable (see HOLD_MIN_SCORE)."""
|
||||||
|
if not all(k.isascii() and k.isalpha() for k in keys):
|
||||||
|
return False
|
||||||
|
p = bopomofo.parse(list(keys) + [" "])
|
||||||
|
if p.pending is not None or len(p.syllables) != 1:
|
||||||
|
return False
|
||||||
|
entries = self.classifier.lexicon.entries([s.syllable for s in p.syllables])
|
||||||
|
return bool(entries) and entries[0][1] >= HOLD_MIN_SCORE
|
||||||
|
|
||||||
@property
|
@property
|
||||||
def segments(self):
|
def segments(self):
|
||||||
return self._segments(self.keys)
|
return self._segments(self.keys)
|
||||||
@@ -142,7 +181,10 @@ class CompositionEngine:
|
|||||||
@property
|
@property
|
||||||
def marked_pieces(self):
|
def marked_pieces(self):
|
||||||
segs = self.segments
|
segs = self.segments
|
||||||
return [(self._render(s, i < len(segs) - 1), s[2]) for i, s in enumerate(segs)]
|
pieces = [(self._render(s, i < len(segs) - 1), s[2]) for i, s in enumerate(segs)]
|
||||||
|
if self.backtick:
|
||||||
|
pieces.append((BACKTICK, LITERAL))
|
||||||
|
return pieces
|
||||||
|
|
||||||
@property
|
@property
|
||||||
def marked_text(self):
|
def marked_text(self):
|
||||||
@@ -156,7 +198,7 @@ class CompositionEngine:
|
|||||||
|
|
||||||
def wants(self, key):
|
def wants(self, key):
|
||||||
"""Whether handle(key) would consume the key, without changing state."""
|
"""Whether handle(key) would consume the key, without changing state."""
|
||||||
if self.candidates or key == SHIFT_TAP:
|
if self.candidates or key == SHIFT_TAP or self.backtick:
|
||||||
return True
|
return True
|
||||||
if self.english_mode and not self.keys:
|
if self.english_mode and not self.keys:
|
||||||
return False # English mode: everything goes to the app as typed
|
return False # English mode: everything goes to the app as typed
|
||||||
@@ -173,11 +215,15 @@ class CompositionEngine:
|
|||||||
def handle(self, key):
|
def handle(self, key):
|
||||||
if self.candidates:
|
if self.candidates:
|
||||||
return self._handle_candidate_key(key)
|
return self._handle_candidate_key(key)
|
||||||
|
if self.backtick:
|
||||||
|
return self._after_backtick(key)
|
||||||
if key == BACKSPACE:
|
if key == BACKSPACE:
|
||||||
if not self.keys:
|
if not self.keys:
|
||||||
return PASS
|
return PASS
|
||||||
self.cursor = None
|
self.cursor = None
|
||||||
self.keys.pop()
|
self.keys.pop()
|
||||||
|
if self.held is not None and len(self.keys) <= self.held:
|
||||||
|
self.held = None
|
||||||
self.fixed = {k: v for k, v in self.fixed.items() if k < len(self.keys)}
|
self.fixed = {k: v for k, v in self.fixed.items() if k < len(self.keys)}
|
||||||
if not self.keys:
|
if not self.keys:
|
||||||
self.forced_mode = None
|
self.forced_mode = None
|
||||||
@@ -220,6 +266,19 @@ class CompositionEngine:
|
|||||||
return CONSUMED if self.keys else PASS
|
return CONSUMED if self.keys else PASS
|
||||||
return self._handle_character(key)
|
return self._handle_character(key)
|
||||||
|
|
||||||
|
def _after_backtick(self, key):
|
||||||
|
self.backtick = False
|
||||||
|
if key in (ESCAPE, BACKSPACE):
|
||||||
|
return CONSUMED
|
||||||
|
committed = self._commit() if self.keys else ""
|
||||||
|
if key in SYMBOLS:
|
||||||
|
return True, committed + SYMBOLS[key]
|
||||||
|
# Not a symbol: the backtick was meant literally; then handle the key as usual.
|
||||||
|
handled, more = self.handle(key)
|
||||||
|
if not handled and len(key) == 1:
|
||||||
|
handled, more = True, key
|
||||||
|
return handled, committed + BACKTICK + (more or "")
|
||||||
|
|
||||||
def _last_parse(self, segs):
|
def _last_parse(self, segs):
|
||||||
if not segs or segs[-1][2] != ZHUYIN:
|
if not segs or segs[-1][2] != ZHUYIN:
|
||||||
return None
|
return None
|
||||||
@@ -230,11 +289,19 @@ class CompositionEngine:
|
|||||||
self.cursor = None # typing always continues at the end
|
self.cursor = None # typing always continues at the end
|
||||||
if self.english_mode and not self.keys:
|
if self.english_mode and not self.keys:
|
||||||
return PASS # English mode: every key goes to the app as typed
|
return PASS # English mode: every key goes to the app as typed
|
||||||
|
if c == BACKTICK:
|
||||||
|
self.backtick = True
|
||||||
|
return CONSUMED
|
||||||
if c == " ":
|
if c == " ":
|
||||||
if not self.keys:
|
if not self.keys:
|
||||||
return PASS
|
return PASS
|
||||||
segs = self._segments(self.keys, finishing=True)
|
segs = self._segments(self.keys, finishing=True)
|
||||||
if segs[-1][2] == LITERAL:
|
if segs[-1][2] == LITERAL:
|
||||||
|
if (self.held is None and len(segs) == 1 and not self.forced_mode
|
||||||
|
and self._is_ambiguous_word(self.keys)):
|
||||||
|
self.held = len(self.keys)
|
||||||
|
self.keys.append(" ")
|
||||||
|
return CONSUMED
|
||||||
return True, self._commit(segs) + " "
|
return True, self._commit(segs) + " "
|
||||||
p = self._last_parse(segs)
|
p = self._last_parse(segs)
|
||||||
if p is not None and p.pending is not None:
|
if p is not None and p.pending is not None:
|
||||||
@@ -319,6 +386,8 @@ class CompositionEngine:
|
|||||||
|
|
||||||
def reset(self):
|
def reset(self):
|
||||||
self.keys = []
|
self.keys = []
|
||||||
|
self.held = None
|
||||||
|
self.backtick = False
|
||||||
self.cursor = None
|
self.cursor = None
|
||||||
self.forced_mode = None
|
self.forced_mode = None
|
||||||
self.fixed = {}
|
self.fixed = {}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"name": "自動注音 AutoZhuyin",
|
"name": "自動注音 AutoZhuyin",
|
||||||
"version": "0.6.2",
|
"version": "0.7.1",
|
||||||
"guid": "{3895C6E3-6D40-4B4B-B4EA-CEEC75382D23}",
|
"guid": "{3895C6E3-6D40-4B4B-B4EA-CEEC75382D23}",
|
||||||
"locale": "zh-Hant-TW",
|
"locale": "zh-Hant-TW",
|
||||||
"fallbackLocale": "zh-TW",
|
"fallbackLocale": "zh-TW",
|
||||||
|
|||||||
@@ -34,6 +34,9 @@
|
|||||||
打到一半時按,同 Tab 整段翻轉
|
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)
|
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 ,。?!:
|
< > ? ! : 中文語境下自動變成全形 ,。?!:
|
||||||
|
` + 標點 強制全形標點,例如 `< 或 `, = , `. = 。 `/ = ? `; = ;
|
||||||
|
`' = 、 `[ `] = 「」 `( `) = () `! = !
|
||||||
|
` 後面接其他鍵就是普通的反引號
|
||||||
|
|
||||||
注音符號的順序打錯也沒關係,例如 ㄧㄒㄠˇ 會自動變成 ㄒㄧㄠˇ(小)。
|
注音符號的順序打錯也沒關係,例如 ㄧㄒㄠˇ 會自動變成 ㄒㄧㄠˇ(小)。
|
||||||
|
|
||||||
|
|||||||
@@ -279,5 +279,41 @@ class FirstToneAfterEnglishTests(unittest.TestCase):
|
|||||||
self.assertEqual(len(e.marked_text), 1, keys)
|
self.assertEqual(len(e.marked_text), 1, keys)
|
||||||
|
|
||||||
|
|
||||||
|
class HeldWordTests(unittest.TestCase):
|
||||||
|
def test_next_word_decides(self):
|
||||||
|
cases = {"up jo4 ": "因為", "up the ": "up the ", "pick up the ": "pick up the ",
|
||||||
|
"up\n": "up", "i love ": "i love "}
|
||||||
|
for keys, want in cases.items():
|
||||||
|
self.assertEqual(type_keys(keys, make_engine()), want, keys)
|
||||||
|
|
||||||
|
def test_held_word_stays_composing(self):
|
||||||
|
e = make_engine()
|
||||||
|
self.assertEqual(type_keys("up ", e), "")
|
||||||
|
self.assertEqual(e.marked_text, "up ")
|
||||||
|
e.handle(BACKSPACE)
|
||||||
|
self.assertEqual(e.marked_text, "up")
|
||||||
|
self.assertEqual(type_keys(" the ", e), "up the ")
|
||||||
|
|
||||||
|
|
||||||
|
class BacktickSymbolTests(unittest.TestCase):
|
||||||
|
def test_forced_symbols(self):
|
||||||
|
cases = {"`<": ",", "`.": "。", "`?": "?", "`;": ";", "`[": "「",
|
||||||
|
"hello`,": "hello,", "su3cl3`.": "你好。", "```\n": "```"}
|
||||||
|
for keys, want in cases.items():
|
||||||
|
self.assertEqual(type_keys(keys, make_engine()), want, keys)
|
||||||
|
|
||||||
|
def test_plain_backtick(self):
|
||||||
|
e = make_engine()
|
||||||
|
self.assertEqual(type_keys("`", e), "")
|
||||||
|
self.assertEqual(e.marked_text, "`")
|
||||||
|
self.assertEqual(type_keys("ls` ", e), "`ls` ")
|
||||||
|
|
||||||
|
def test_escape_cancels(self):
|
||||||
|
e = make_engine()
|
||||||
|
type_keys("su3`", e)
|
||||||
|
e.handle(BACKSPACE)
|
||||||
|
self.assertEqual(e.marked_text, "你")
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
unittest.main()
|
unittest.main()
|
||||||
|
|||||||
Reference in New Issue
Block a user