private bool NotInBaseWords(string word) { List <string> suffixWords = new List <string>(); suffixWords.Add(word); foreach (AffixRule rule in SuffixRules.Values) { foreach (AffixEntry entry in rule.AffixEntries) { string tempWord = AffixUtility.RemoveSuffix(word, entry); if (tempWord != word) { if (_baseWords.ContainsKey(tempWord)) { if (this.VerifyAffixKey(tempWord, rule.Name[0])) { return(true); } } if (rule.AllowCombine) { suffixWords.Add(tempWord); } else { _possibleBaseWords.Add(tempWord); } } } } _possibleBaseWords.AddRange(suffixWords); foreach (AffixRule rule in PrefixRules.Values) { foreach (AffixEntry entry in rule.AffixEntries) { foreach (string suffixWord in suffixWords) { string tempWord = AffixUtility.RemovePrefix(suffixWord, entry); if (tempWord != suffixWord) { if (_baseWords.ContainsKey(tempWord)) { if (this.VerifyAffixKey(tempWord, rule.Name[0])) { return(true); } } _possibleBaseWords.Add(tempWord); } } } } return(false); }
public List <string> ExpandWord(Word word) { List <string> suffixWords = new List <string>(); List <string> words = new List <string>(); suffixWords.Add(word.Text); string prefixKeys = ""; foreach (char key in word.AffixKeys) { if (_suffixRules.ContainsKey(key.ToString())) { AffixRule rule = _suffixRules[key.ToString()]; string tempWord = AffixUtility.AddSuffix(word.Text, rule); if (tempWord != word.Text) { if (rule.AllowCombine) { suffixWords.Add(tempWord); } else { words.Add(tempWord); } } } else if (_prefixRules.ContainsKey(key.ToString())) { prefixKeys += key.ToString(); } } foreach (char key in prefixKeys) { AffixRule rule = _prefixRules[key.ToString()]; foreach (string suffixWord in suffixWords) { string tempWord = AffixUtility.AddPrefix(suffixWord, rule); if (tempWord != suffixWord) { words.Add(tempWord); } } } words.AddRange(suffixWords); return(words); }
public void Load(Stream dictionary) { StreamReader sr = new StreamReader(dictionary); string tempLine; Regex _spaceRegx = new Regex(@"[^\s]+", RegexOptions.None); MatchCollection partMatches; string currentSection = ""; AffixRule currentRule = null; while (sr.Peek() >= 0) { tempLine = sr.ReadLine().Trim(); if (tempLine.Length > 0) { switch (tempLine) { case "[Copyright]": case "[Try]": case "[Replace]": case "[Prefix]": case "[Suffix]": case "[Phonetic]": case "[Words]": currentSection = tempLine; break; default: switch (currentSection) { case "[Copyright]": break; case "[Try]": this.TryCharacters += tempLine; break; case "[Replace]": this.ReplaceCharacters.Add(tempLine); break; case "[Prefix]": case "[Suffix]": partMatches = _spaceRegx.Matches(tempLine); if (partMatches.Count == 3) { currentRule = new AffixRule(); currentRule.Name = partMatches[0].Value; if (partMatches[1].Value == "Y") { currentRule.AllowCombine = true; } if (currentSection == "[Prefix]") { this.PrefixRules.Add(currentRule.Name, currentRule); } else { this.SuffixRules.Add(currentRule.Name, currentRule); } } else if (partMatches.Count == 4) { if (currentRule.Name == partMatches[0].Value) { AffixEntry entry = new AffixEntry(); if (partMatches[1].Value != "0") { entry.StripCharacters = partMatches[1].Value; } entry.AddCharacters = partMatches[2].Value; AffixUtility.EncodeConditions(partMatches[3].Value, entry); currentRule.AffixEntries.Add(entry); } } break; case "[Phonetic]": partMatches = _spaceRegx.Matches(tempLine); if (partMatches.Count >= 2) { PhoneticRule rule = new PhoneticRule(); PhoneticUtility.EncodeRule(partMatches[0].Value, rule); rule.ReplaceString = partMatches[1].Value; _phoneticRules.Add(rule); } break; case "[Words]": string[] parts = tempLine.Split('/'); Word tempWord = new Word(); tempWord.Text = parts[0]; if (parts.Length >= 2) { tempWord.AffixKeys = parts[1]; } if (parts.Length >= 3) { tempWord.PhoneticCode = parts[2]; } this.BaseWords.Add(tempWord.Text, tempWord); break; } break; } } } sr.Close(); }