} //ParagraphList()
/// <summary>
/// Paramaterized constructor
/// </summary>
/// <param name="t">Text object to pull Paragraphs from</param>
public ParagraphList(Text t)
{
List <string> tokens = new List <string>(t.GetTokens());
int lastToken, firstToken; //token the search starts from & last token in the paragraph
int result; //location of first \n or \r found
double total = 0; //for avg word count
//add first paragraph -- no need to worry about location
Paragraphs.Add(new Paragraph(t, 0));
NumParagraphs = 1;
firstToken = 0;
while (true)
{
//determine end of paragraph
while (true)
{
result = tokens.IndexOf("\n", firstToken);
if ((tokens.IndexOf("\r", firstToken) < result && tokens.IndexOf("\r", firstToken) != -1) || result == -1)
{
result = tokens.IndexOf("\r", firstToken);
}
if (result + 1 >= tokens.Count) //end of file
{
lastToken = tokens.Count - 1;
break;
}//if
else if (tokens[result].Equals(tokens[result + 1])) //two consecutive newlines or returns found
{
lastToken = result;
break;
}//else if
else
{
firstToken = result + 1;
}
}//while
if (lastToken != tokens.Count - 1)
{
Paragraphs.Add(new Paragraph(t, lastToken + 1)); //add the NEXT paragraph to the list
NumParagraphs++;
firstToken = lastToken + 1;
}//if
else //Paragraph found is last one -- already added on previous loop
{
break;
}
}//while
//determine avg word count
for (int i = 0; i < NumParagraphs; i++)
{
total += Paragraphs[i].NumWords;
} //for
AvgWordCount = total / NumParagraphs;
} //ParagraphList(Text)
}//Words()
/// <summary>
/// Paramaterized constructor
/// </summary>
/// <param name="t">Text file to be split into DistinctWords</param>
public Words(Text t)
{
words = new List <DistinctWord>();
List <String> tokens = new List <String>();
tokens = t.GetTokens();
foreach (string token in tokens)
{
words.Add(new DistinctWord(token));
}//foreach
Alphabetize();
}//Words(Text)
} //Sentence()
/// <summary>
/// Paramaterized constructor
/// </summary>
/// <param name="t">Text to pull sentence from</param>
/// <param name="location">token index where sentence begins</param>
#region SentCon
public Sentence(Text t, int location)
{
Regex r = new Regex(@"(\W)");
//find end location
List <string> tokens = new List <string>(t.GetTokens());
int end = tokens.IndexOf(".", location); //assume the first . is the end of the sentence
if ((tokens.IndexOf("?", location) < end && tokens.IndexOf("?", location) != -1) || end == -1) //if there is a ? and it's before the first .
{
end = tokens.IndexOf("?", location); //first ? is the end of the sentence
}
if ((tokens.IndexOf("!", location) < end && tokens.IndexOf("!", location) != -1) || end == -1) //if there is a ! and it's before the first ./?
{
end = tokens.IndexOf("!", location); //first ! is the end of the sentence
}
FirstToken = location;
if (end != -1)
{
LastToken = end;
}
else //sentence ends without punctuation
{
LastToken = tokens.Count() - 1;
}
//generate sentence
FullSentence = Utility.FormatText(tokens, FirstToken, LastToken, 0, 0);
//find word count
WordCount = (LastToken - FirstToken);
for (int i = FirstToken; i < LastToken; i++)
{
if (r.IsMatch(tokens[i]))
{
WordCount--;
}
} //for
//find avg word length
double total = 0;
for (int i = FirstToken; i < LastToken; i++)
{
total += tokens[i].Length;
} //for
AvgWordLength = total / WordCount;
} //Sentence(Text, int)
} //SentenceList()
/// <summary>
/// Paramaterized constructor
/// </summary>
/// <param name="t">Text to be split into sentences</param>
public SentenceList(Text t)
{
int location; //stores location of punctuation mark
List <string> tokens = t.GetTokens(); //tokens
Sentences = new List <Sentence>(); //initialize sentence list
int nextSent = 0; //location of start of next sentence
double total = 0; //combined amount of words in list, used for avg
//add first sentence - no need to worry about start location, it's always 0
Sentences.Add(new Sentence(t, 0));
NumSentences = 1;
while (true)
{
//locate nearest punctuation mark
location = tokens.IndexOf(".", nextSent);
if ((location > tokens.IndexOf("?", nextSent) && tokens.IndexOf("?", nextSent) != -1) || location == -1)
{
location = tokens.IndexOf("?", nextSent);
}
if ((location > tokens.IndexOf("!", nextSent) && tokens.IndexOf("!", nextSent) != -1) || location == -1)
{
location = tokens.IndexOf("!", nextSent);
}
nextSent = location + 1;
if (location != -1 &&
nextSent < tokens.Count())
{
Sentences.Add(new Sentence(t, (location + 1)));
NumSentences++;
}//if
else
{
break;
}
}//while
//find avg word count
foreach (Sentence s in Sentences)
{
total += s.WordCount;
} //foreach
AvgWordCount = total / NumSentences;
} //SentenceList(Text)
} //Paragraph()
/// <summary>
/// Paramterized constructor
/// </summary>
/// <param name="t">Text to pull paragraph from</param>
/// <param name="location">Location to begin extracting paragraph</param>
public Paragraph(Text t, int location)
{
int result; //location of \n or \r found
double total = 0; //used for average calculation
List <string> tokens = new List <String>(t.GetTokens()); //token list
FirstToken = location;
//determine end of paragraph
while (true)
{
result = tokens.IndexOf("\n", location);
if ((tokens.IndexOf("\r", location) < result && tokens.IndexOf("\r", location) != -1) || result == -1)
{
result = tokens.IndexOf("\r", location);
}
if (result + 1 >= tokens.Count) //end of file
{
LastToken = tokens.Count - 1;
break;
}//if
else if (tokens[result].Equals(tokens[result + 1])) //two consecutive newlines or returns found
{
LastToken = result;
break;
}//else if
else
{
location = result + 1;
}
}//while
NumWords = LastToken - FirstToken;
//find sentence locations
List <Sentence> sentList = new List <Sentence>();
int nextSent = 0;
//add first sentence - no need to worry about start location, it's always 0
sentList.Add(new Sentence(t, FirstToken));
NumSentences = 1;
while (true)
{
//locate nearest punctuation mark
location = tokens.IndexOf(".", nextSent);
if ((location > tokens.IndexOf("?", nextSent) && tokens.IndexOf("?", nextSent) != -1) || location == -1)
{
location = tokens.IndexOf("?", nextSent);
}
if ((location > tokens.IndexOf("!", nextSent) && tokens.IndexOf("!", nextSent) != -1) || location == -1)
{
location = tokens.IndexOf("!", nextSent);
}
nextSent = location + 1;
if (location != -1 && nextSent < LastToken)
{
sentList.Add(new Sentence(t, location + 1));
NumSentences++;
}//if
else
{
break;
}
}//while
foreach (Sentence s in sentList)
{
total += s.WordCount;
}//foreach
AvgSentenceWordCount = total / NumSentences;
//generate text paragraph
OriginalParagraph = Utility.FormatText(tokens, FirstToken, LastToken, 0, 0);
}//Paragraph(Text)