public static void EncodeRule(string ruleText, PhoneticRule rule)
{
for (int i = 0; i < rule.Condition.Length; i++)
{
rule.Condition[i] = 0;
}
bool group = false;
bool end = false;
char[] memberChars = new char[200];
int numMember = 0;
foreach (char cond in ruleText)
{
switch (cond)
{
case '(':
group = true;
break;
case ')':
end = true;
break;
case '^':
rule.BeginningOnly = true;
break;
case '$':
rule.EndOnly = true;
break;
case '-':
rule.ConsumeCount++;
break;
case '<':
rule.ReplaceMode = true;
break;
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
rule.Priority = int.Parse(cond.ToString());
break;
default:
if (group)
{
memberChars[numMember] = cond;
numMember++;
}
else
{
end = true;
}
break;
}
if (end)
{
if (group)
{
for (int j = 0; j < numMember; j++)
{
int charCode = (int)memberChars[j];
rule.Condition[charCode] = rule.Condition[charCode] | (1 << rule.ConditionCount);
}
group = false;
numMember = 0;
}
else
{
int charCode = (int)cond;
rule.Condition[charCode] = rule.Condition[charCode] | (1 << rule.ConditionCount);
}
end = false;
rule.ConditionCount++;
}
}
}
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();
}