Enable Beginning-of-Sentence prediction for contextual dict.
Bug: 14161647
Bug: 14119293
Change-Id: I0c00f13966db88e4de85e245e7bced43c9d474b2
diff --git a/java/src/com/android/inputmethod/latin/ExpandableBinaryDictionary.java b/java/src/com/android/inputmethod/latin/ExpandableBinaryDictionary.java
index 4dbfa0b..b1966bf 100644
--- a/java/src/com/android/inputmethod/latin/ExpandableBinaryDictionary.java
+++ b/java/src/com/android/inputmethod/latin/ExpandableBinaryDictionary.java
@@ -122,6 +122,12 @@
return mBinaryDictionary.isValidDictionary();
}
+ // TODO: Remove and always enable beginning of sentence prediction. Currently, this is enabled
+ // only for ContextualDictionary.
+ protected boolean enableBeginningOfSentencePrediction() {
+ return false;
+ }
+
/**
* Creates a new expandable binary dictionary.
*
@@ -398,6 +404,10 @@
if (mBinaryDictionary == null) {
return null;
}
+ if (composer.size() == 0 && prevWordsInfo.mIsBeginningOfSentence
+ && !enableBeginningOfSentencePrediction()) {
+ return null;
+ }
final ArrayList<SuggestedWordInfo> suggestions =
mBinaryDictionary.getSuggestions(composer, prevWordsInfo, proximityInfo,
blockOffensiveWords, additionalFeaturesOptions, sessionId,
diff --git a/java/src/com/android/inputmethod/latin/personalization/ContextualDictionary.java b/java/src/com/android/inputmethod/latin/personalization/ContextualDictionary.java
index 96755a9..81ac6cc 100644
--- a/java/src/com/android/inputmethod/latin/personalization/ContextualDictionary.java
+++ b/java/src/com/android/inputmethod/latin/personalization/ContextualDictionary.java
@@ -35,6 +35,7 @@
// Always reset the contents.
clear();
}
+
@UsedForTesting
public static ContextualDictionary getDictionary(final Context context, final Locale locale,
final File dictFile, final String dictNamePrefix) {
@@ -42,6 +43,11 @@
}
@Override
+ protected boolean enableBeginningOfSentencePrediction() {
+ return true;
+ }
+
+ @Override
public boolean isValidWord(final String word) {
// Strings out of this dictionary should not be considered existing words.
return false;
diff --git a/native/jni/com_android_inputmethod_latin_BinaryDictionary.cpp b/native/jni/com_android_inputmethod_latin_BinaryDictionary.cpp
index 476338e..f62b24c 100644
--- a/native/jni/com_android_inputmethod_latin_BinaryDictionary.cpp
+++ b/native/jni/com_android_inputmethod_latin_BinaryDictionary.cpp
@@ -249,7 +249,7 @@
env->GetFloatArrayRegion(inOutLanguageWeight, 0, 1 /* len */, &languageWeight);
SuggestionResults suggestionResults(MAX_RESULTS);
const PrevWordsInfo prevWordsInfo(prevWordCodePoints, prevWordCodePointsLength,
- false /* isStartOfSentence */);
+ isBeginningOfSentence);
if (givenSuggestOptions.isGesture() || inputSize > 0) {
// TODO: Use SuggestionResults to return suggestions.
dictionary->getSuggestions(pInfo, traverseSession, xCoordinates, yCoordinates,
diff --git a/native/jni/src/suggest/core/session/prev_words_info.h b/native/jni/src/suggest/core/session/prev_words_info.h
index 56c53c1..640f6a2 100644
--- a/native/jni/src/suggest/core/session/prev_words_info.h
+++ b/native/jni/src/suggest/core/session/prev_words_info.h
@@ -85,6 +85,14 @@
return mPrevWordCodePointCount[n - 1];
}
+ // n is 1-indexed.
+ bool isNthPrevWordBeginningOfSentence(const int n) const {
+ if (n <= 0 || n > MAX_PREV_WORD_COUNT_FOR_N_GRAM) {
+ return false;
+ }
+ return mIsBeginningOfSentence[n - 1];
+ }
+
private:
DISALLOW_COPY_AND_ASSIGN(PrevWordsInfo);
diff --git a/native/jni/src/suggest/policyimpl/dictionary/structure/v4/ver4_patricia_trie_policy.cpp b/native/jni/src/suggest/policyimpl/dictionary/structure/v4/ver4_patricia_trie_policy.cpp
index 09c7b7d..1e10f24 100644
--- a/native/jni/src/suggest/policyimpl/dictionary/structure/v4/ver4_patricia_trie_policy.cpp
+++ b/native/jni/src/suggest/policyimpl/dictionary/structure/v4/ver4_patricia_trie_policy.cpp
@@ -246,7 +246,24 @@
false /* tryLowerCaseSearch */);
// TODO: Support N-gram.
if (prevWordsPtNodePos[0] == NOT_A_DICT_POS) {
- return false;
+ if (prevWordsInfo->isNthPrevWordBeginningOfSentence(1 /* n */)) {
+ const std::vector<UnigramProperty::ShortcutProperty> shortcuts;
+ const UnigramProperty beginningOfSentenceUnigramProperty(
+ true /* representsBeginningOfSentence */, true /* isNotAWord */,
+ false /* isBlacklisted */, MAX_PROBABILITY /* probability */,
+ NOT_A_TIMESTAMP /* timestamp */, 0 /* level */, 0 /* count */, &shortcuts);
+ if (!addUnigramEntry(prevWordsInfo->getNthPrevWordCodePoints(1 /* n */),
+ prevWordsInfo->getNthPrevWordCodePointCount(1 /* n */),
+ &beginningOfSentenceUnigramProperty)) {
+ AKLOGE("Cannot add unigram entry for the beginning-of-sentence.");
+ return false;
+ }
+ // Refresh Terminal PtNode positions.
+ prevWordsInfo->getPrevWordsTerminalPtNodePos(this, prevWordsPtNodePos,
+ false /* tryLowerCaseSearch */);
+ } else {
+ return false;
+ }
}
const int word1Pos = getTerminalPtNodePositionOfWord(
bigramProperty->getTargetCodePoints()->data(),