Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
3670305f0f | ||
|
|
ef9f91a6b7 |
@@ -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>0.6.3</string>
|
||||||
<key>CFBundleVersion</key>
|
<key>CFBundleVersion</key>
|
||||||
<string>10</string>
|
<string>11</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 +51,12 @@ 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?
|
||||||
|
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 +77,33 @@ 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) }
|
||||||
|
|
||||||
@@ -164,6 +194,7 @@ 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
|
||||||
@@ -218,6 +249,11 @@ public final class CompositionEngine {
|
|||||||
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 {
|
||||||
@@ -326,6 +362,7 @@ public final class CompositionEngine {
|
|||||||
|
|
||||||
public func reset() {
|
public func reset() {
|
||||||
keys = []
|
keys = []
|
||||||
|
held = nil
|
||||||
cursor = nil
|
cursor = nil
|
||||||
forcedMode = nil
|
forcedMode = nil
|
||||||
fixed = [:]
|
fixed = [:]
|
||||||
|
|||||||
@@ -428,6 +428,40 @@ 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 StartupTimingTests: XCTestCase {
|
final class StartupTimingTests: XCTestCase {
|
||||||
func testStartupTiming() throws {
|
func testStartupTiming() throws {
|
||||||
var t = Date()
|
var t = Date()
|
||||||
|
|||||||
@@ -20,6 +20,10 @@ 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
|
||||||
|
|
||||||
PASS = (False, None)
|
PASS = (False, None)
|
||||||
CONSUMED = (True, None)
|
CONSUMED = (True, None)
|
||||||
|
|
||||||
@@ -43,6 +47,8 @@ class CompositionEngine:
|
|||||||
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 +66,35 @@ 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)
|
||||||
@@ -178,6 +207,8 @@ class CompositionEngine:
|
|||||||
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
|
||||||
@@ -235,6 +266,11 @@ class CompositionEngine:
|
|||||||
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 +355,7 @@ class CompositionEngine:
|
|||||||
|
|
||||||
def reset(self):
|
def reset(self):
|
||||||
self.keys = []
|
self.keys = []
|
||||||
|
self.held = None
|
||||||
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": "0.6.3",
|
||||||
"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",
|
||||||
|
|||||||
@@ -279,5 +279,21 @@ 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 ")
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
unittest.main()
|
unittest.main()
|
||||||
|
|||||||
Reference in New Issue
Block a user