public DictionaryMetaObject(string DictName, string DictDescript, string DictPrefix, string DictContents)
{
DictionaryName = DictName;
DictionaryDescription = DictDescript;
DictionaryRawText = DictContents;
DictionaryCategoryPrefix = DictPrefix;
UseDictionary = true;
DictData = new DictionaryData();
}
public DictionaryData ParseDict(DictionaryMetaObject DictionaryToParse)
{
DictionaryData DictData = DictionaryToParse.DictData;
// ____ _ _ ____ _ _ ____ _ ___ _ _ _
// | _ \ ___ _ __ _ _| | __ _| |_ ___ | _ \(_) ___| |_| _ \ __ _| |_ __ _ / _ \| |__ (_) ___ ___| |_
// | |_) / _ \| '_ \| | | | |/ _` | __/ _ \ | | | | |/ __| __| | | |/ _` | __/ _` | | | | | '_ \| |/ _ \/ __| __|
// | __/ (_) | |_) | |_| | | (_| | || __/ | |_| | | (__| |_| |_| | (_| | || (_| | | |_| | |_) | | __/ (__| |_
// |_| \___/| .__/ \__,_|_|\__,_|\__\___| |____/|_|\___|\__|____/ \__,_|\__\__,_| \___/|_.__// |\___|\___|\__|
// |_| |__/
//parse out the the dictionary file
DictData.MaxWords = 0;
//yeah, there's levels to this thing
DictData.FullDictionary = new Dictionary <string, Dictionary <int, Dictionary <string, string[]> > >();
DictData.FullDictionary.Add("Wildcards", new Dictionary <int, Dictionary <string, string[]> >());
DictData.FullDictionary.Add("Standards", new Dictionary <int, Dictionary <string, string[]> >());
DictData.WildCardArrays = new Dictionary <int, string[]>();
DictData.PrecompiledWildcards = new Dictionary <string, Regex>();
List <string> AllEntriesInFile = new List <string>();
Dictionary <int, List <string> > WildCardLists = new Dictionary <int, List <string> >();
string[] DicSplit = DictionaryToParse.DictionaryRawText.Split(new char[] { '%' }, 3, StringSplitOptions.None);
string[] HeaderLines = DicSplit[1].Split(new[] { "\r\n", "\r", "\n" }, StringSplitOptions.RemoveEmptyEntries);
string[] EntryLines = DicSplit[2].Split(new[] { "\r\n", "\r", "\n" }, StringSplitOptions.RemoveEmptyEntries);
DictData.NumCats = HeaderLines.Length;
//now that we know the number of categories, we can fill out the arrays
DictData.CatNames = new string[DictData.NumCats];
DictData.CatValues = new string[DictData.NumCats];
//Map Out the Categories
for (int i = 0; i < DictData.NumCats; i++)
{
string[] HeaderRow = HeaderLines[i].Trim().Split(new char[] { '\t' }, 2);
DictData.CatValues[i] = HeaderRow[0];
DictData.CatNames[i] = HeaderRow[1];
}
//Map out the dictionary entries
for (int i = 0; i < EntryLines.Length; i++)
{
string EntryLine = EntryLines[i].Trim();
while (EntryLine.Contains(" "))
{
EntryLine.Replace(" ", " ");
}
string[] EntryRow = EntryLine.Trim().Split(new char[] { '\t' }, StringSplitOptions.RemoveEmptyEntries);
if (EntryRow.Length > 1 && !String.IsNullOrWhiteSpace(EntryRow[0]))
{
int Words_In_Entry = EntryRow[0].Split(' ').Length;
if (Words_In_Entry > DictData.MaxWords)
{
DictData.MaxWords = Words_In_Entry;
}
//this is something special added to this version of the "parse dictionary" method
//allows us to keep track of each entry within the dictionary file
AllEntriesInFile.Add(EntryRow[0].ToLower());
if (EntryRow[0].Contains("*"))
{
if (DictData.FullDictionary["Wildcards"].ContainsKey(Words_In_Entry))
{
if (!DictData.FullDictionary["Wildcards"][Words_In_Entry].ContainsKey(EntryRow[0].ToLower()))
{
DictData.FullDictionary["Wildcards"][Words_In_Entry].Add(EntryRow[0].ToLower(), EntryRow.Skip(1).ToArray());
WildCardLists[Words_In_Entry].Add(EntryRow[0].ToLower());
DictData.PrecompiledWildcards.Add(EntryRow[0].ToLower(), new Regex("^" + Regex.Escape(EntryRow[0].ToLower()).Replace("\\*", ".*"), RegexOptions.Compiled));
}
}
else
{
DictData.FullDictionary["Wildcards"].Add(Words_In_Entry, new Dictionary <string, string[]> {
{ EntryRow[0].ToLower(), EntryRow.Skip(1).ToArray() }
});
WildCardLists.Add(Words_In_Entry, new List <string>(new string[] { EntryRow[0].ToLower() }));
DictData.PrecompiledWildcards.Add(EntryRow[0].ToLower(), new Regex("^" + Regex.Escape(EntryRow[0].ToLower()).Replace("\\*", ".*"), RegexOptions.Compiled));
}
}
else
{
if (DictData.FullDictionary["Standards"].ContainsKey(Words_In_Entry))
{
if (!DictData.FullDictionary["Standards"][Words_In_Entry].ContainsKey(EntryRow[0].ToLower()))
{
DictData.FullDictionary["Standards"][Words_In_Entry].Add(EntryRow[0].ToLower(), EntryRow.Skip(1).ToArray());
}
}
else
{
DictData.FullDictionary["Standards"].Add(Words_In_Entry, new Dictionary <string, string[]> {
{ EntryRow[0].ToLower(), EntryRow.Skip(1).ToArray() }
});
}
}
}
}
for (int i = DictData.MaxWords; i > 0; i--)
{
if (WildCardLists.ContainsKey(i))
{
DictData.WildCardArrays.Add(i, WildCardLists[i].ToArray());
}
}
WildCardLists.Clear();
DictData.DictionaryLoaded = true;
DictData.AllEntries = AllEntriesInFile;
DictData.AllEntriesArray = AllEntriesInFile.ToArray();
//MessageBox.Show("Your dictionary has been successfully loaded.", "Success", MessageBoxButtons.OK, MessageBoxIcon.Information);
return(DictData);
}
private Dictionary <string, ulong[]> AnalyzeText(DictionaryData DictData, string[] Words)
{
//this matches the EntryFreqTracker dictionary from the main part of the plugin
//we'll build this up here, then aggregate it back into the main version once we return
//the results from this method
Dictionary <string, ulong[]> WordsCaptured_Raw = new Dictionary <string, ulong[]>();
int TotalStringLength = Words.Length;
Dictionary <string, int> DictionaryResults = new Dictionary <string, int>();
for (int i = 0; i < DictData.NumCats; i++)
{
DictionaryResults.Add(DictData.CatValues[i], 0);
}
for (int i = 0; i < TotalStringLength; i++)
{
//iterate over n-grams, starting with the largest possible n-gram (derived from the user's dictionary file)
for (int NumberOfWords = DictData.MaxWords; NumberOfWords > 0; NumberOfWords--)
{
//make sure that we don't overextend past the array
if (i + NumberOfWords - 1 >= TotalStringLength)
{
continue;
}
//make the target string
string TargetString;
if (NumberOfWords > 1)
{
TargetString = String.Join(" ", Words.Skip(i).Take(NumberOfWords).ToArray());
}
else
{
TargetString = Words[i];
}
//look for an exact match
if (DictData.FullDictionary["Standards"].ContainsKey(NumberOfWords))
{
//this is what we do when a word is captured
if (DictData.FullDictionary["Standards"][NumberOfWords].ContainsKey(TargetString))
{
//make sure that the word is contained in our tracking dictionary
if (!WordsCaptured_Raw.ContainsKey(TargetString))
{
WordsCaptured_Raw.Add(TargetString, new ulong[UserLoadedDictionary.DictData.NumCats]);
}
//we iterate over each category that the word belongs to, and we increment it accordingly
for (int j = 0; j < DictData.FullDictionary["Standards"][NumberOfWords][TargetString].Length; j++)
{
int CategoryOutputPosition = OutputDataMap[DictData.FullDictionary["Standards"][NumberOfWords][TargetString][j]];
//right now I'm just adding 1, but later
//i might revisit and add "NumberOfWords" instead
//there's no objectively right answer
WordsCaptured_Raw[TargetString][CategoryOutputPosition] += 1;
}
//manually increment the for loop so that we're not testing on words that have already been picked up
i += NumberOfWords - 1;
//break out of the lower level for loop back to moving on to new words altogether
break;
}
}
//if there isn't an exact match, we have to go through the wildcards
if (DictData.WildCardArrays.ContainsKey(NumberOfWords))
{
for (int j = 0; j < DictData.WildCardArrays[NumberOfWords].Length; j++)
{
if (DictData.PrecompiledWildcards[DictData.WildCardArrays[NumberOfWords][j]].Matches(TargetString).Count > 0)
{
//make sure that the word is contained in our tracking dictionary
if (!WordsCaptured_Raw.ContainsKey(DictData.WildCardArrays[NumberOfWords][j]))
{
WordsCaptured_Raw.Add(DictData.WildCardArrays[NumberOfWords][j], new ulong[UserLoadedDictionary.DictData.NumCats]);
}
for (int k = 0; k < DictData.FullDictionary["Wildcards"][NumberOfWords][DictData.WildCardArrays[NumberOfWords][j]].Length; k++)
{
//if (DictionaryResults.ContainsKey(DictData.FullDictionary["Wildcards"][NumberOfWords][DictData.WildCardArrays[NumberOfWords][j]][k])) DictionaryResults[DictData.FullDictionary["Wildcards"][NumberOfWords][DictData.WildCardArrays[NumberOfWords][j]][k]] += NumberOfWords;
//we iterate over each category that the word belongs to, and we increment it accordingly
int CategoryOutputPosition = OutputDataMap[DictData.FullDictionary["Wildcards"][NumberOfWords][DictData.WildCardArrays[NumberOfWords][j]][k]];
//right now I'm just adding 1, but later
//i might revisit and add "NumberOfWords" instead
//there's no objectively right answer
WordsCaptured_Raw[DictData.WildCardArrays[NumberOfWords][j]][CategoryOutputPosition] += 1;
}
//manually increment the for loop so that we're not testing on words that have already been picked up
i += NumberOfWords - 1;
//break out of the lower level for loop back to moving on to new words altogether
break;
}
}
}
}
}
return(WordsCaptured_Raw);
}
