ResearchLogger switch word segmentation

Previously, a logunit was considered a word only if it was all letters.  This is important for
tracking bigrams correctly.

Now, a logunit must have only at least one letter.  The dictionary check is still performed,
and punctuation, etc. still comes in as separate LogUnits.  But a word can contain a space,
which helps set up for logging words where spaces are inserted automatically, and other situations
in which text is committed with an additional space tacked onto the end.

Change-Id: Ia74094a99058890d20a9cdadf2d0989841a79a41
main
Kurt Partridge 2012-08-09 12:24:47 -07:00
parent 98967539fd
commit 6a0720478d
1 changed files with 5 additions and 5 deletions

View File

@ -731,20 +731,20 @@ public class ResearchLogger implements SharedPreferences.OnSharedPreferenceChang
researchLog.publish(closingLogUnit, true /* isIncludingPrivateData */);
}
private boolean hasOnlyLetters(final String word) {
private boolean hasLetters(final String word) {
final int length = word.length();
for (int i = 0; i < length; i = word.offsetByCodePoints(i, 1)) {
final int codePoint = word.codePointAt(i);
if (!Character.isLetter(codePoint)) {
return false;
}
}
if (Character.isLetter(codePoint)) {
return true;
}
}
return false;
}
private void onWordComplete(final String word) {
Log.d(TAG, "onWordComplete: " + word);
if (word != null && word.length() > 0 && hasOnlyLetters(word)) {
if (word != null && word.length() > 0 && hasLetters(word)) {
mCurrentLogUnit.setWord(word);
mStatistics.recordWordEntered();
}