/// <summary>
/// Copies the elements of an array at the end of this instance of 'AffixEntryCollection'.
/// </summary>
/// <param name='value'>
/// An array of 'AffixEntry' objects to add to the collection.
/// </param>
public void AddRange(AffixEntry[] value)
{
for (int Counter = 0; (Counter < value.Length); Counter = (Counter + 1))
{
this.Add(value[Counter]);
}
}
/// <summary>
/// Removes the affix suffix rule entry for the word if valid
/// </summary>
/// <param name="word" type="string">
/// <para>
/// The word to be modified
/// </para>
/// </param>
/// <param name="entry" type="NetSpell.SpellChecker.Dictionary.Affix.AffixEntry">
/// <para>
/// The affix rule entry to use
/// </para>
/// </param>
/// <returns>
/// The word after affix removed. Will be the same word if affix could not be removed.
/// </returns>
/// <remarks>
/// This method does not verify that the returned word is a valid word, only that the affix can be removed
/// </remarks>
public static string RemoveSuffix(string word, AffixEntry entry)
{
int tempLength = word.Length - entry.AddCharacters.Length;
if ((tempLength > 0) &&
(tempLength + entry.StripCharacters.Length >= entry.ConditionCount) &&
(word.EndsWith(entry.AddCharacters)))
{
// word with out affix
string tempWord = word.Substring(0, tempLength);
// add back strip chars
tempWord += entry.StripCharacters;
// check that this is valid
int passCount = 0;
for (int i = 0; i < entry.ConditionCount; i++)
{
int charCode = (int)tempWord[tempWord.Length - (entry.ConditionCount - i)];
if ((entry.Condition[charCode] & (1 << i)) == (1 << i))
{
passCount++;
}
}
if (passCount == entry.ConditionCount)
{
return(tempWord);
}
}
return(word);
}
/// <summary>
/// Generates the condition character array
/// </summary>
/// <param name="conditionText" type="string">
/// <para>
/// the text form of the conditions
/// </para>
/// </param>
/// <param name="entry" type="NetSpell.SpellChecker.Dictionary.Affix.AffixEntry">
/// <para>
/// The AffixEntry to add the condition array to
/// </para>
/// </param>
public static void EncodeConditions(string conditionText, AffixEntry entry)
{
// clear the conditions array
for (int i=0; i < entry.Condition.Length; i++)
{
entry.Condition[i] = 0;
}
// if no condition just return
if (conditionText == ".")
{
entry.ConditionCount = 0;
return;
}
bool neg = false; /* complement indicator */
bool group = false; /* group indicator */
bool end = false; /* end condition indicator */
int num = 0; /* number of conditions */
char [] memberChars = new char[200];
int numMember = 0; /* number of member in group */
foreach (char cond in conditionText)
{
// parse member group
if (cond == '[')
{
group = true; // start a group
}
else if (cond == '^' && group)
{
neg = true; // negative group
}
else if (cond == ']')
{
end = true; // end of a group
}
else if (group)
{
// add chars to group
memberChars[numMember] = cond;
numMember++;
}
else
{
end = true; // no group
}
// set condition
if (end)
{
if (group)
{
if (neg)
{
// turn all chars on
for (int j=0; j < entry.Condition.Length; j++)
{
entry.Condition[j] = entry.Condition[j] | (1 << num);
}
// turn off chars in member group
for (int j=0; j < numMember; j++)
{
int charCode = (int)memberChars[j];
entry.Condition[charCode] = entry.Condition[charCode] & ~(1 << num);
}
}
else
{
// turn on chars in member group
for (int j=0; j < numMember; j++)
{
int charCode = (int)memberChars[j];
entry.Condition[charCode] = entry.Condition[charCode] | (1 << num);
}
}
group = false;
neg = false;
numMember = 0;
} // if group
else
{
if (cond == '.')
{
// wild card character, turn all chars on
for (int j=0; j < entry.Condition.Length; j++)
{
entry.Condition[j] = entry.Condition[j] | (1 << num);
}
}
else
{
// turn on char
int charCode = (int)cond;
entry.Condition[charCode] = entry.Condition[charCode] | (1 << num);
}
} // not group
end = false;
num++;
} // if end
} // foreach char
entry.ConditionCount = num;
return;
}
/// <summary>
/// Adds a 'AffixEntry' item with the specified value to the 'AffixEntryCollection'
/// </summary>
/// <param name='value'>
/// The 'AffixEntry' to add.
/// </param>
/// <returns>
/// The index at which the new element was inserted.
/// </returns>
public int Add(AffixEntry value)
{
return List.Add(value);
}
/// <summary>
/// Initializes a new instance of 'AffixEntryCollection' with an array of 'AffixEntry' objects.
/// </summary>
/// <param name='value'>
/// An array of 'AffixEntry' objects with which to initialize the collection
/// </param>
public AffixEntryCollection(AffixEntry[] value)
{
this.AddRange(value);
}
/// <summary>
/// Removes a specific item from the 'AffixEntryCollection'.
/// </summary>
/// <param name='value'>
/// The item to remove from the 'AffixEntryCollection'.
/// </param>
public void Remove(AffixEntry value)
{
List.Remove(value);
}
/// <summary>
/// Inserts an existing 'AffixEntry' into the collection at the specified index.
/// </summary>
/// <param name='index'>
/// The zero-based index where the new item should be inserted.
/// </param>
/// <param name='value'>
/// The item to insert.
/// </param>
public void Insert(int index, AffixEntry value)
{
List.Insert(index, value);
}
/// <summary>
/// Returns the index of a 'AffixEntry' object in the collection.
/// </summary>
/// <param name='value'>
/// The 'AffixEntry' object whose index will be retrieved.
/// </param>
/// <returns>
/// If found, the index of the value; otherwise, -1.
/// </returns>
public int IndexOf(AffixEntry value)
{
return List.IndexOf(value);
}
/// <summary>
/// Returns the index of a 'AffixEntry' object in the collection.
/// </summary>
/// <param name='value'>
/// The 'AffixEntry' object whose index will be retrieved.
/// </param>
/// <returns>
/// If found, the index of the value; otherwise, -1.
/// </returns>
public int IndexOf(AffixEntry value)
{
return(List.IndexOf(value));
}
/// <summary>
/// Gets a value indicating whether the 'AffixEntryCollection' contains the specified value.
/// </summary>
/// <param name='value'>
/// The item to locate.
/// </param>
/// <returns>
/// True if the item exists in the collection; false otherwise.
/// </returns>
public bool Contains(AffixEntry value)
{
return List.Contains(value);
}
/// <summary>
/// Generates the condition character array
/// </summary>
/// <param name="conditionText" type="string">
/// <para>
/// the text form of the conditions
/// </para>
/// </param>
/// <param name="entry" type="NetSpell.SpellChecker.Dictionary.Affix.AffixEntry">
/// <para>
/// The AffixEntry to add the condition array to
/// </para>
/// </param>
public static void EncodeConditions(string conditionText, AffixEntry entry)
{
// clear the conditions array
for (int i = 0; i < entry.Condition.Length; i++)
{
entry.Condition[i] = 0;
}
// if no condition just return
if (conditionText == ".")
{
entry.ConditionCount = 0;
return;
}
bool neg = false; /* complement indicator */
bool group = false; /* group indicator */
bool end = false; /* end condition indicator */
int num = 0; /* number of conditions */
char [] memberChars = new char[200];
int numMember = 0; /* number of member in group */
foreach (char cond in conditionText)
{
// parse member group
if (cond == '[')
{
group = true; // start a group
}
else if (cond == '^' && group)
{
neg = true; // negative group
}
else if (cond == ']')
{
end = true; // end of a group
}
else if (group)
{
// add chars to group
memberChars[numMember] = cond;
numMember++;
}
else
{
end = true; // no group
}
// set condition
if (end)
{
if (group)
{
if (neg)
{
// turn all chars on
for (int j = 0; j < entry.Condition.Length; j++)
{
entry.Condition[j] = entry.Condition[j] | (1 << num);
}
// turn off chars in member group
for (int j = 0; j < numMember; j++)
{
int charCode = (int)memberChars[j];
entry.Condition[charCode] = entry.Condition[charCode] & ~(1 << num);
}
}
else
{
// turn on chars in member group
for (int j = 0; j < numMember; j++)
{
int charCode = (int)memberChars[j];
entry.Condition[charCode] = entry.Condition[charCode] | (1 << num);
}
}
group = false;
neg = false;
numMember = 0;
} // if group
else
{
if (cond == '.')
{
// wild card character, turn all chars on
for (int j = 0; j < entry.Condition.Length; j++)
{
entry.Condition[j] = entry.Condition[j] | (1 << num);
}
}
else
{
// turn on char
int charCode = (int)cond;
entry.Condition[charCode] = entry.Condition[charCode] | (1 << num);
}
} // not group
end = false;
num++;
} // if end
} // foreach char
entry.ConditionCount = num;
return;
}
/// <summary>
/// Adds a 'AffixEntry' item with the specified value to the 'AffixEntryCollection'
/// </summary>
/// <param name='value'>
/// The 'AffixEntry' to add.
/// </param>
/// <returns>
/// The index at which the new element was inserted.
/// </returns>
public int Add(AffixEntry value)
{
return(List.Add(value));
}
/// <summary>
/// Removes a specific item from the 'AffixEntryCollection'.
/// </summary>
/// <param name='value'>
/// The item to remove from the 'AffixEntryCollection'.
/// </param>
public void Remove(AffixEntry value)
{
List.Remove(value);
}
/// <summary>
/// Inserts an existing 'AffixEntry' into the collection at the specified index.
/// </summary>
/// <param name='index'>
/// The zero-based index where the new item should be inserted.
/// </param>
/// <param name='value'>
/// The item to insert.
/// </param>
public void Insert(int index, AffixEntry value)
{
List.Insert(index, value);
}
/// <summary>
/// Removes the affix suffix rule entry for the word if valid
/// </summary>
/// <param name="word" type="string">
/// <para>
/// The word to be modified
/// </para>
/// </param>
/// <param name="entry" type="NetSpell.SpellChecker.Dictionary.Affix.AffixEntry">
/// <para>
/// The affix rule entry to use
/// </para>
/// </param>
/// <returns>
/// The word after affix removed. Will be the same word if affix could not be removed.
/// </returns>
/// <remarks>
/// This method does not verify that the returned word is a valid word, only that the affix can be removed
/// </remarks>
public static string RemoveSuffix(string word, AffixEntry entry)
{
int tempLength = word.Length - entry.AddCharacters.Length;
if ((tempLength > 0)
&& (tempLength + entry.StripCharacters.Length >= entry.ConditionCount)
&& (word.EndsWith(entry.AddCharacters)))
{
// word with out affix
string tempWord = word.Substring(0, tempLength);
// add back strip chars
tempWord += entry.StripCharacters;
// check that this is valid
int passCount = 0;
for (int i = 0; i < entry.ConditionCount; i++)
{
int charCode = (int)tempWord[tempWord.Length - (entry.ConditionCount - i)];
if ((entry.Condition[charCode] & (1 << i)) == (1 << i))
{
passCount++;
}
}
if (passCount == entry.ConditionCount)
{
return tempWord;
}
}
return word;
}
/// <summary>
/// Copies the 'AffixEntryCollection' values to a one-dimensional System.Array
/// instance starting at the specified array index.
/// </summary>
/// <param name='array'>
/// The one-dimensional System.Array that represents the copy destination.
/// </param>
/// <param name='index'>
/// The index in the array where copying begins.
/// </param>
public void CopyTo(AffixEntry[] array, int index)
{
List.CopyTo(array, index);
}
/// <summary>
/// Initializes the dictionary by loading and parsing the
/// dictionary file and the user file.
/// </summary>
public void Initialize()
{
// clean up data first
_baseWords.Clear();
_replaceCharacters.Clear();
_prefixRules.Clear();
_suffixRules.Clear();
_phoneticRules.Clear();
_tryCharacters = "";
// the following is used to split a line by white space
Regex _spaceRegx = new Regex(@"[^\s]+", RegexOptions.Compiled);
MatchCollection partMatches;
string currentSection = "";
AffixRule currentRule = null;
string dictionaryPath = Path.Combine(_dictionaryFolder, _dictionaryFile);
TraceWriter.TraceInfo("Loading Dictionary:{0}", dictionaryPath);
// open dictionary file
FileStream fs = new FileStream(dictionaryPath, FileMode.Open, FileAccess.Read, FileShare.Read);
StreamReader sr = new StreamReader(fs, Encoding.UTF8);
// read line by line
while (sr.Peek() >= 0)
{
string tempLine = sr.ReadLine().Trim();
if (tempLine.Length > 0)
{
// check for section flag
switch (tempLine)
{
case "[Copyright]" :
case "[Try]" :
case "[Replace]" :
case "[Prefix]" :
case "[Suffix]" :
case "[Phonetic]" :
case "[Words]" :
// set current section that is being parsed
currentSection = tempLine;
break;
default :
// parse line and place in correct object
switch (currentSection)
{
case "[Copyright]" :
this.Copyright += tempLine + "\r\n";
break;
case "[Try]" : // ISpell try chars
this.TryCharacters += tempLine;
break;
case "[Replace]" : // ISpell replace chars
this.ReplaceCharacters.Add(tempLine);
break;
case "[Prefix]" : // MySpell prefix rules
case "[Suffix]" : // MySpell suffix rules
// split line by white space
partMatches = _spaceRegx.Matches(tempLine);
// if 3 parts, then new rule
if (partMatches.Count == 3)
{
currentRule = new AffixRule();
// part 1 = affix key
currentRule.Name = partMatches[0].Value;
// part 2 = combine flag
if (partMatches[1].Value == "Y") currentRule.AllowCombine = true;
// part 3 = entry count, not used
if (currentSection == "[Prefix]")
{
// add to prefix collection
this.PrefixRules.Add(currentRule.Name, currentRule);
}
else
{
// add to suffix collection
this.SuffixRules.Add(currentRule.Name, currentRule);
}
}
//if 4 parts, then entry for current rule
else if (partMatches.Count == 4)
{
// part 1 = affix key
if (currentRule.Name == partMatches[0].Value)
{
AffixEntry entry = new AffixEntry();
// part 2 = strip char
if (partMatches[1].Value != "0") entry.StripCharacters = partMatches[1].Value;
// part 3 = add chars
entry.AddCharacters = partMatches[2].Value;
// part 4 = conditions
AffixUtility.EncodeConditions(partMatches[3].Value, entry);
currentRule.AffixEntries.Add(entry);
}
}
break;
case "[Phonetic]" : // ASpell phonetic rules
// split line by white space
partMatches = _spaceRegx.Matches(tempLine);
if (partMatches.Count >= 2)
{
PhoneticRule rule = new PhoneticRule();
PhoneticUtility.EncodeRule(partMatches[0].Value, ref rule);
rule.ReplaceString = partMatches[1].Value;
_phoneticRules.Add(rule);
}
break;
case "[Words]" : // dictionary word list
// splits word into its parts
string[] parts = tempLine.Split('/');
Word tempWord = new Word();
// part 1 = base word
tempWord.Text = parts[0];
// part 2 = affix keys
if (parts.Length >= 2) tempWord.AffixKeys = parts[1];
// part 3 = phonetic code
if (parts.Length >= 3) tempWord.PhoneticCode = parts[2];
this.BaseWords.Add(tempWord.Text, tempWord);
break;
} // currentSection swith
break;
} //tempLine switch
} // if templine
} // read line
// close files
sr.Close();
fs.Close();
TraceWriter.TraceInfo("Dictionary Loaded BaseWords:{0}; PrefixRules:{1}; SuffixRules:{2}; PhoneticRules:{3}",
this.BaseWords.Count, this.PrefixRules.Count, this.SuffixRules.Count, this.PhoneticRules.Count);
this.LoadUserFile();
_initialized = true;
}
/// <summary>
/// Gets a value indicating whether the 'AffixEntryCollection' contains the specified value.
/// </summary>
/// <param name='value'>
/// The item to locate.
/// </param>
/// <returns>
/// True if the item exists in the collection; false otherwise.
/// </returns>
public bool Contains(AffixEntry value)
{
return(List.Contains(value));
}
