public void AppliesTo_TermDoesNotOccurInRange_ReturnsFalse()
{
IKeyTerm term = KeyTermMatchBuilderTests.AddMockedKeyTerm("tom", 002003001, 002003003);
KeyTermMatch match = new KeyTermMatch(new List <Word>(new Word[] { "tom" }), term, true);
Assert.IsFalse(match.AppliesTo(002003002, 002003002));
}
public void AppliesTo_TermAllowedToMatchAnywhere_ReturnsTrue()
{
IKeyTerm term = KeyTermMatchBuilderTests.AddMockedKeyTerm("tom");
KeyTermMatch match = new KeyTermMatch(new List <Word>(new Word[] { "tom" }), term, false);
Assert.IsTrue(match.AppliesTo(-1, -1));
}
/// ------------------------------------------------------------------------------------
/// <summary>
/// Copy constructor (only valid for an object having a single term).
/// </summary>
/// <param name="matchBase">The base match from which this match will be created.</param>
/// ------------------------------------------------------------------------------------
internal KeyTermMatch(KeyTermMatch matchBase) :
this(matchBase.m_words, matchBase.m_terms[0], matchBase.MatchForRefOnly)
{
if (matchBase.m_terms.Count != 1)
{
throw new ArgumentException("KeyTermMatch copy constructor only valid for making" +
" copies of a new in-progress match with a single underlying key term.");
}
}
/// ------------------------------------------------------------------------------------
/// <summary>
/// Determines whether the part of the phrase we're considering matches the key term so
/// far.
/// </summary>
/// ------------------------------------------------------------------------------------
private bool PhraseEqualsKeyTermSoFar(KeyTermMatch term, int cMatchingWordsInTermSoFar)
{
int cCompare = Math.Min(term.WordCount, cMatchingWordsInTermSoFar);
for (int iWord = m_iStartMatch; iWord < cCompare + m_iStartMatch; iWord++)
{
if (!term[iWord - m_iStartMatch].IsEquivalent(m_words[iWord]))
{
return(false);
}
}
return(true);
}
public void RuleToLimitMatchToTermRefs()
{
Dictionary <string, KeyTermRule> rules = new Dictionary <string, KeyTermRule>();
KeyTermRule rule = new KeyTermRule();
rule.id = "ask";
rule.Rule = KeyTermRule.RuleType.MatchForRefOnly;
rules[rule.id] = rule;
KeyTermMatchBuilder bldr = new KeyTermMatchBuilder(AddMockedKeyTerm(rule.id, 34),
new ReadonlyDictionary <string, KeyTermRule>(rules), null);
Assert.AreEqual(1, bldr.Matches.Count());
KeyTermMatch ktm = VerifyKeyTermMatch(bldr, 0, false, "ask");
Assert.IsFalse(ktm.AppliesTo(30, 33));
Assert.IsTrue(ktm.AppliesTo(34, 34));
Assert.IsFalse(ktm.AppliesTo(35, 39));
}
/// ------------------------------------------------------------------------------------
/// <summary>
/// Verifies the key term match.
/// </summary>
/// ------------------------------------------------------------------------------------
private static KeyTermMatch VerifyKeyTermMatch(KeyTermMatchBuilder bldr, int iMatch,
bool matchAnywhere, params string[] words)
{
KeyTermMatch ktm = bldr.Matches.ElementAt(iMatch);
Assert.AreEqual(words.Length, ktm.WordCount);
for (int i = 0; i < words.Length; i++)
{
Assert.AreEqual(words[i], ktm[i].Text);
}
Assert.IsTrue(ktm.MatchForRefOnly != matchAnywhere);
// The following is really a test of the KeyTermMatch.AppliesTo method:
if (matchAnywhere)
{
Random r = new Random(DateTime.Now.Millisecond);
Assert.IsTrue(ktm.AppliesTo(r.Next(), r.Next()));
}
return(ktm);
}
/// ------------------------------------------------------------------------------------
/// <summary>
/// Populates the key terms table.
/// </summary>
/// ------------------------------------------------------------------------------------
private void PopulateKeyTermsTable(IEnumerable <IKeyTerm> keyTerms, KeyTermRules rules)
{
KeyTermMatchBuilder matchBuilder;
foreach (IKeyTerm keyTerm in keyTerms)
{
matchBuilder = new KeyTermMatchBuilder(keyTerm,
rules == null ? null : rules.RulesDictionary, rules == null ? null : rules.RegexRules);
foreach (KeyTermMatch matcher in matchBuilder.Matches.Where(matcher => matcher.WordCount != 0))
{
List <KeyTermMatch> foundMatchers;
Word firstWord = matcher[0];
if (!m_keyTermsTable.TryGetValue(firstWord, out foundMatchers))
{
m_keyTermsTable[firstWord] = foundMatchers = new List <KeyTermMatch>();
}
KeyTermMatch existingMatcher = foundMatchers.FirstOrDefault(m => m.Equals(matcher));
if (existingMatcher == null)
{
foundMatchers.Add(matcher);
}
else
{
existingMatcher.AddTerm(keyTerm);
}
}
}
#if DEBUG
if (rules != null)
{
string unUsedRules = rules.RulesDictionary.Values.Where(r => !r.Used).ToString(Environment.NewLine);
if (unUsedRules.Length > 0)
{
MessageBox.Show("Unused KeyTerm Rules: \n" + unUsedRules, "Transcelerator");
}
}
#endif
}
/// ------------------------------------------------------------------------------------
/// <summary>
/// Finds the best key term in the list of words starting at m_iStartMatch and including
/// up to m_iNextWord. As new words are considered, the list of possible matches
/// (m_matches) is reduced by any that no longer match until there is exactly one match
/// that exactly equals the words in the key term or the list is empty.
/// </summary>
/// ------------------------------------------------------------------------------------
private KeyTermMatch FindBestKeyTerm()
{
if (m_keyTermsTable == null)
{
return(null);
}
Word nextWord = m_words[m_iNextWord];
if (m_iStartMatch == m_iNextWord)
{
List <KeyTermMatch> matches;
m_matches = null;
if (m_keyTermsTable.TryGetValue(nextWord, out matches))
{
m_matches = new List <KeyTermMatch>(matches.Where(m => m.AppliesTo(m_phrase.StartRef, m_phrase.EndRef)));
}
if (m_matches == null || m_matches.All(m => m.WordCount > 1))
{
var baseWord = nextWord.Text;
Word stem = s_stemmer.stemTerm(baseWord);
while (stem.Text != baseWord)
{
if (m_keyTermsTable.TryGetValue(stem, out matches))
{
stem.AddAlternateForm(nextWord);
matches = new List <KeyTermMatch>(matches.Where(m => m.AppliesTo(m_phrase.StartRef, m_phrase.EndRef)));
if (m_matches == null)
{
m_matches = matches;
}
else
{
m_matches.AddRange(matches);
}
}
baseWord = stem.Text;
stem = s_stemmer.stemTerm(baseWord);
}
if (m_matches == null || m_matches.Count == 0)
{
m_iStartMatch++;
return(null);
}
}
// If we found a one-word exact match and there are no other key terms that start
// with that word, then we return it. The code below would handle this, but it's such
// a common case, we want it to be fast. If there are one or more multi-word key
// terms that start with this word, we need to keep looking.
if (m_matches.Count == 1 && m_matches[0].WordCount == 1)
{
return(m_matches[0]);
}
}
int cMatchingWordsInTermSoFar = m_iNextWord - m_iStartMatch + 1;
int lengthOfBestMatch = 0;
KeyTermMatch longestMatch = null;
// Remove from the possible matches any that don't match so far
for (int iTerm = 0; iTerm < m_matches.Count; iTerm++)
{
KeyTermMatch term = m_matches[iTerm];
if (!PhraseEqualsKeyTermSoFar(term, cMatchingWordsInTermSoFar) ||
(AtEndOfPhrase && term.WordCount > cMatchingWordsInTermSoFar))
{
m_matches.RemoveAt(iTerm--);
}
else if (term.WordCount > lengthOfBestMatch)
{
lengthOfBestMatch = term.WordCount;
longestMatch = term;
}
}
if (m_matches.Count == 0)
{
// The only matches we had were multi-word matches, and the addition of the current
// word made it so that none of them matched. Therefore, we don't have a key term
// starting at iStartMatch.
m_iNextWord = m_iStartMatch; // The for loop in Parse will increment this.
m_iStartMatch++;
return(null);
}
if ((m_matches.Count == 1 && lengthOfBestMatch < cMatchingWordsInTermSoFar) || (lengthOfBestMatch == cMatchingWordsInTermSoFar))
{
return(longestMatch);
}
return(null);
}
/// ------------------------------------------------------------------------------------
/// <summary>
/// Cleans up the given source-language phrase (makes it all lowercase and removes
/// punctuation and extraneous whitespace) and returns a collection of phrase parts,
/// broken up by key terms.
/// </summary>
/// <returns>Collection of phrase parts</returns>
/// ------------------------------------------------------------------------------------
internal IEnumerable <ParsedPart> Parse()
{
KeyTermMatch bestKeyTerm = null;
int minUnhandled = m_iStartMatch = m_iNextWord = 0;
if (m_questionWords != null)
{
foreach (int count in m_questionWords.Keys.OrderByDescending(k => k))
{
foreach (List <Word> questionPhrase in m_questionWords[count])
{
bool match = true;
int i;
for (i = 0; i < count; i++)
{
if (m_iNextWord + i >= m_words.Count || questionPhrase[i] != m_words[m_iNextWord + i])
{
match = false;
break;
}
}
if (match)
{
yield return(YieldTranslatablePart(m_words.Take(count), m_phrase));
m_iStartMatch = m_iNextWord = minUnhandled = count;
break;
}
}
}
}
for (; m_iNextWord < m_words.Count;)
{
bestKeyTerm = FindBestKeyTerm();
if (bestKeyTerm == null)
{
if (m_words[m_iNextWord].IsNumber)
{
if (m_iNextWord > minUnhandled)
{
yield return(YieldTranslatablePart(m_words.Skip(minUnhandled).Take(m_iNextWord - minUnhandled), m_phrase));
}
yield return(new ParsedPart(Int32.Parse(m_words[m_iNextWord].Text)));
m_iStartMatch = minUnhandled = ++m_iNextWord;
}
else
{
m_iNextWord++;
}
}
else
{
// We've found the best key term we're going to find.
int keyTermWordCount = bestKeyTerm.WordCount;
if (m_iStartMatch > minUnhandled)
{
yield return(YieldTranslatablePart(m_words.Skip(minUnhandled).Take(m_iStartMatch - minUnhandled), m_phrase));
}
m_keyTermsUsedForPhrase.Add(bestKeyTerm);
bestKeyTerm.InUse = true;
yield return(new ParsedPart(bestKeyTerm));
m_iStartMatch = m_iNextWord = minUnhandled = m_iStartMatch + keyTermWordCount;
}
}
if (minUnhandled < m_words.Count)
{
yield return(YieldTranslatablePart(m_words.Skip(minUnhandled), m_phrase));
}
}
