Merge "Update unit test for beginning-of-sentence."

This commit is contained in:
Keisuke Kuroyanagi 2014-06-12 07:37:29 +00:00 committed by Android (Google) Code Review
commit 89899e14df
2 changed files with 25 additions and 12 deletions

View file

@ -256,8 +256,25 @@ bool Ver4PatriciaTriePolicy::addNgramEntry(const PrevWordsInfo *const prevWordsI
false /* tryLowerCaseSearch */);
// TODO: Support N-gram.
if (prevWordsPtNodePos[0] == NOT_A_DICT_POS) {
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(),
bigramProperty->getTargetCodePoints()->size(), false /* forceLowerCaseSearch */);

View file

@ -1450,27 +1450,23 @@ public class BinaryDictionaryTests extends AndroidTestCase {
0 /* offset */, dictFile.length(), true /* useFullEditDistance */,
Locale.getDefault(), TEST_LOCALE, true /* isUpdatable */);
final int dummyProbability = 0;
binaryDictionary.addUnigramEntry("", dummyProbability, "" /* shortcutTarget */,
BinaryDictionary.NOT_A_PROBABILITY /* shortcutProbability */,
true /* isBeginningOfSentence */, true /* isNotAWord */, false /* isBlacklisted */,
BinaryDictionary.NOT_A_VALID_TIMESTAMP /* timestamp */);
final PrevWordsInfo prevWordsInfoStartOfSentence = PrevWordsInfo.BEGINNING_OF_SENTENCE;
final PrevWordsInfo prevWordsInfoBeginningOfSentence = PrevWordsInfo.BEGINNING_OF_SENTENCE;
final int bigramProbability = 200;
addUnigramWord(binaryDictionary, "aaa", dummyProbability);
binaryDictionary.addNgramEntry(prevWordsInfoStartOfSentence, "aaa", bigramProbability,
binaryDictionary.addNgramEntry(prevWordsInfoBeginningOfSentence, "aaa", bigramProbability,
BinaryDictionary.NOT_A_VALID_TIMESTAMP /* timestamp */);
assertEquals(bigramProbability,
binaryDictionary.getNgramProbability(prevWordsInfoStartOfSentence, "aaa"));
binaryDictionary.addNgramEntry(prevWordsInfoStartOfSentence, "aaa", bigramProbability,
binaryDictionary.getNgramProbability(prevWordsInfoBeginningOfSentence, "aaa"));
binaryDictionary.addNgramEntry(prevWordsInfoBeginningOfSentence, "aaa", bigramProbability,
BinaryDictionary.NOT_A_VALID_TIMESTAMP /* timestamp */);
addUnigramWord(binaryDictionary, "bbb", dummyProbability);
binaryDictionary.addNgramEntry(prevWordsInfoStartOfSentence, "bbb", bigramProbability,
binaryDictionary.addNgramEntry(prevWordsInfoBeginningOfSentence, "bbb", bigramProbability,
BinaryDictionary.NOT_A_VALID_TIMESTAMP /* timestamp */);
binaryDictionary.flushWithGC();
assertEquals(bigramProbability,
binaryDictionary.getNgramProbability(prevWordsInfoStartOfSentence, "aaa"));
binaryDictionary.getNgramProbability(prevWordsInfoBeginningOfSentence, "aaa"));
assertEquals(bigramProbability,
binaryDictionary.getNgramProbability(prevWordsInfoStartOfSentence, "bbb"));
binaryDictionary.getNgramProbability(prevWordsInfoBeginningOfSentence, "bbb"));
}
public void testGetMaxFrequencyOfExactMatches() {