static void Main()
{
var jarRoot = @"C:\Users\Burds\Downloads\Stanford.NLP.NET-master (1)\Stanford.NLP.NET-master\samples\Stanford.NLP.POSTagger.CSharp\bin\Debug\stanford-postagger-2018-02-27";
var modelsDirectory = jarRoot + @"\models";
// Loading POS Tagger
var tagger = new MaxentTagger(modelsDirectory + @"\english-left3words-distsim.tagger");
// Text for tagging
var text = "This is a test sentence.";
string[] arr = new string[10];
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
string[] getType = new string[10];
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
Console.WriteLine(SentenceUtils.listToString(taggedSentence, false));
var data = new List <DataClass>();
for (int i = 0; i < taggedSentence.size() - 1; i++)
{
string myString = taggedSentence.get(i).ToString();
data.Add(new DataClass
{
SWord = sentence.get(i).ToString(),
WType = myString.Substring(myString.IndexOf("/") + 1)
});
//getType[i] = myString.Substring(myString.IndexOf("/") + 1);
}
}
}
static void Main(string[] args)
{
// Loading POS Tagger
var tagger = new MaxentTagger(@"Resources/english-bidirectional-distsim.tagger");
// Text for tagging
//var text = @"یک روز آمدم ";
var text = "hello how are you?";
IList <Tuple <string, string> > tagged = new List <Tuple <string, string> >();
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
System.Console.WriteLine(SentenceUtils.listToString(taggedSentence, false));
for (int i = 0; i < taggedSentence.size(); i++)
{
var t = taggedSentence.toArray()[i].ToString().Split('/');
tagged.Add(Tuple.Create(t[0], t[1]));
}
}
}
private void TagReader(Reader reader)
{
var sentences = MaxentTagger.tokenizeText(reader).toArray();
Assert.NotNull(sentences);
foreach (ArrayList sentence in sentences)
{
var tSentence = _tagger.tagSentence(sentence);
TestContext.Out.WriteLine(SentenceUtils.listToString(tSentence, false));
}
}
public string send(string text)
{
string[] exampleWords = text.Split(
new char[] { ' ', ',', '.', ')', '(' }, StringSplitOptions.RemoveEmptyEntries);
ILemmatizer lmtz = new LemmatizerPrebuiltCompact(LemmaSharp.LanguagePrebuilt.English);
StringBuilder sb = new StringBuilder();
foreach (string word in exampleWords)
{
sb.Append(LemmatizeOne(lmtz, word) + " ");
}
string finalstring = sb.ToString();
var jarRoot = @"E:\stanford-postagger-full-2015-12-09\stanford-postagger-full-2015-12-09";
var modelsDirectory = jarRoot + @"\models";
// Loading POS Tagger
var tagger = new MaxentTagger(modelsDirectory + @"\wsj-0-18-bidirectional-nodistsim.tagger");
// Text for tagging
StringBuilder str = new StringBuilder();
var sentences = MaxentTagger.tokenizeText(new java.io.StringReader(finalstring)).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
string sent = SentenceUtils.listToString(taggedSentence, false);
String[] tokens = sent.Split(' ');
for (int i = 0; i < tokens.Length; i++)
{
if (tokens[i].Contains("/VB"))
{
str.Append(tokens[i] + " ");
}
}
}
return(str.ToString());
}
static void Main()
{
var jarRoot = @"..\..\..\..\data\paket-files\nlp.stanford.edu\stanford-postagger-full-2018-10-16";
var modelsDirectory = jarRoot + @"\models";
// Loading POS Tagger
var tagger = new MaxentTagger(modelsDirectory + @"\wsj-0-18-bidirectional-nodistsim.tagger");
// Text for tagging
var text = "A Part-Of-Speech Tagger (POS Tagger) is a piece of software that reads text in some language "
+ "and assigns parts of speech to each word (and other token), such as noun, verb, adjective, etc., although "
+ "generally computational applications use more fine-grained POS tags like 'noun-plural'.";
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
Console.WriteLine(SentenceUtils.listToString(taggedSentence, false));
}
}
public List <TargetCandidate> GetAllNounPhrases(string[] sentence, string[] target)
{
var tree = lexParser.apply(SentenceUtils.toCoreLabelList(sentence));
var dependencies = grammaticalStructureFactory.newGrammaticalStructure(tree).typedDependenciesCCprocessed();
List <TargetCandidate> nounPhrases = new List <TargetCandidate>();
var subTrees = tree.subTreeList();
for (int i = 0; i < subTrees.size(); i++)
{
Tree subTree = (Tree)subTrees.get(i);
if (subTree.label().value() == "NP")
{
NounPhrase phrase = NounPhrase.SetSentence(sentence, tree, dependencies, target);
phrase.SetPhrase(SentenceUtils.listToString(subTree.yield()));
nounPhrases.Add(new TargetCandidate(phrase, caching));
}
}
return(nounPhrases);
}
void Start()
{
singleton = this;
if (!System.IO.File.Exists(model))
{
throw new Exception($"Check path to the model file '{model}'");
}
// Load our custom directional classifier
spatialClassifier = CRFClassifier.getClassifier(customModelDirectory + @"/spatialDirectionModel.gaz.ser.gz");
// Loading POS Tagger
MaxentTagger tagger = new MaxentTagger(model);
var sentences = MaxentTagger.tokenizeText(new java.io.StringReader(input)).toArray();
foreach (java.util.ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
Debug.Log(SentenceUtils.listToString(taggedSentence, false));
debugDisplay.text = (SentenceUtils.listToString(taggedSentence, false));
String previousNoun = null;
String connectingPhrase = "";
foreach (var x in taggedSentence.toArray())
{
String taggedWord = x.ToString();
String word = taggedWord.Split('/').FirstOrDefault();
if (taggedWord.Contains("/NN") &&
false == (spatialClassifier as CRFClassifier).classifyToString($"{connectingPhrase} {word}")
?.Split(' ').Where(s => !s.Contains("/0")).Where(s2 => s2.Split('/').First() == word).Any())
{
nounStack += ((nounStack.ToArray().Any()) ? " " : "") + word;
lastIsPlural |= taggedWord.Contains("/NNS");
}
else
{
if (nounStack != "")
{
var id = getModelId(nounStack);
Debug.Log($"Found id for {nounStack}");
debugDisplay.text = $"Found id for {nounStack}";
if (id != null)
{
sceneObjects.Add(new sceneObject(nounStack, id, lastIsPlural, (previousNoun == null), !sceneObjects.Where(s => s.name == nounStack).Any(), parseDirection(previousNoun, connectingPhrase)));
}
connectingPhrase = "";
previousNoun = word;
nounStack = "";
}
connectingPhrase += ((!connectingPhrase.ToCharArray().Any()) ? "" : " ") + word;
}
}
if (nounStack != "")
{
var id = getModelId(nounStack);
Debug.Log($"Found id for {nounStack}");
debugDisplay.text = $"Found id for {nounStack}";
if (id != null)
{
sceneObjects.Add(new sceneObject(nounStack, id, lastIsPlural, (previousNoun == null), !sceneObjects.Where(s => s.name == nounStack).Any(), parseDirection(previousNoun, connectingPhrase)));
}
}
}
// Once we have all our ids start downloading the models
// download = https://archive3d.net/?a=download&do=get&id={modelId}
// Set up dictonary of locations
var uniqueOnes = sceneObjects.Where(u => u.unique);
foreach (var sceneObj in uniqueOnes)
{
sceneObject.namedModels.Add(sceneObj.name, null);
}
DownloadFiles();
beginCheck = true;
}
public String getParse(String ask)
{
String directories;
directories = System.IO.Directory.GetCurrentDirectory();
List <object> NP = new List <object>();
var jarRoot = directories + @"\stanford-postagger-2018-02-27";
var modelsDirectory = jarRoot + @"\models";
List <DataClass> newdata = new List <DataClass>();
// Loading POS Tagger
var tagger = new MaxentTagger(modelsDirectory + @"\english-left3words-distsim.tagger");
var data = new List <DataClass>();
// Text for tagging
var text = ask;
string[] arr = new string[10];
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
string[] getType = new string[10];
String tagString = "";
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
Console.WriteLine(SentenceUtils.listToString(taggedSentence, false));
tagString = string.Join(" ", taggedSentence);
for (int i = 0; i <= taggedSentence.size() - 1; i++)
{
String myString = taggedSentence.get(i).ToString();
data.Add(new DataClass
{
SWord = sentence.get(i).ToString(),
WType = myString.Substring(myString.IndexOf("/") + 1)
});
//getType[i] = myString.Substring(myString.IndexOf("/") + 1);
}
}
//int k = 0;
String outStr = "";
String[] locations = { "Pasig", "Manila", "Laguna de Bay", "Philippines", "Marikina" };
for (int k = 0; k <= data.Count - 1; k++)
{
if (locations.Contains(data[k].SWord) && data[k + 1].WType != "NNP")
{
data[k].WType = "LC";
}
outStr = outStr + data[k].SWord + "/" + data[k].WType;
// k++;
}
//String[] locations = { "Pasig", "Manila", "Laguna de Bay", "Philippines", "Marikina" };
String outPut = "[" + outStr + "]";
// return s;
return(tagString);
}
private void button2_Click(object sender, EventArgs e)
{
//-----------------RSQ-------Requirement Sentence Quality----------------------------------------
string location = "C:/Users/PRATHYUSH/Desktop/text.txt";
System.IO.StreamWriter file = new System.IO.StreamWriter(location);
file.WriteLine("------------------Requirement Sentence Quality---------------------");
var jarRoot = @"C:\Users\PRATHYUSH\Desktop\project files\stanford-postagger-full-2018-10-16";
var modelsDirectory = jarRoot + @"\models";
// Loading POS Tagger
var tagger = new MaxentTagger(modelsDirectory + @"\wsj-0-18-bidirectional-nodistsim.tagger");
//----------------------------------------------------------------------------------------------------
string FilePath = path;
string FileText = new System.IO.StreamReader(FilePath).ReadToEnd();
string[] SentenceArray = FileText.Split('.', '!', '?');
//string arrays containing the necessary words
string[] ImplicitWords = { "this", "This", "these", "These", "that", "those", "it", "they", "they", "above", "below", "previous", "next", "following", "last", "and first" };
string[] OptionalWords = { "can", "eventually", "if appropriate", "if needed", "may", "optionally", "possibly" };
string[] VagueWords = { "adequate", "back", "bad", "clear", "close", "easy", "efficient", "far", "fast", "future", "good", "in front", "low", "near", "new", "old", "past", "recent", "significant", "slow", "strong", "today’s", "useful", "weak", "and well" };
string[] WeakWords = { "as a minimum", "as applicable", "as appropriate", "be able to", "be capable", "not limited to", "the capability of", "the capability to", "easy", "effective", "if practical", "normal", "provide for", "to be determined", "and timely" };
string[] DirectiveWords = { "figures", "for example", "table", "note", "i.e.", "e.g." };
string[] Continuances = { "below", "as follows", "following", "listed", "in particular", "support", "and" };
string[] imperatives = { "Shall", "shall", "Must", "must", "is required to", "Are Applicable", "Are to", "are to", "Responsible for", "will", "should" };
for (int i = 0; i < SentenceArray.Length; i++)
{
file.WriteLine(" ");
file.WriteLine("Sentence {0}", i + 1);
file.WriteLine(SentenceArray[i]);
file.WriteLine("------ Multiple Sentence ------ ");
object[] sentences = MaxentTagger.tokenizeText(new StringReader(SentenceArray[i])).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
file.WriteLine(SentenceUtils.listToString(taggedSentence, false));
var myRegX = new Regex("/V");
MatchCollection m = myRegX.Matches(SentenceUtils.listToString(taggedSentence, false));
if (m.Count > 0)
{
file.WriteLine("Verb Count - " + m.Count);
}
}
file.WriteLine("------ Implicit Words ------ ");
for (int j = 0; j < ImplicitWords.Length; j++)
{
var myRegEx = new Regex("\\b" + ImplicitWords[j] + "\\b");
MatchCollection matches = myRegEx.Matches(SentenceArray[i]);
int impword = matches.Count;
imp = impword + imp;
if (matches.Count > 0)
{
file.WriteLine(ImplicitWords[j] + " - " + matches.Count + " times");
}
}
file.WriteLine("------ Optional Words ------ ");
for (int j = 0; j < OptionalWords.Length; j++)
{
var myRegEx = new Regex("\\b" + OptionalWords[j] + "\\b");
MatchCollection matches = myRegEx.Matches(SentenceArray[i]);
int optword = matches.Count;
opt = optword + opt;
if (matches.Count > 0)
{
file.WriteLine(OptionalWords[j] + " - " + matches.Count + " times");
}
}
file.WriteLine("------ Vague Words ------ ");
for (int j = 0; j < VagueWords.Length; j++)
{
var myRegEx = new Regex("\\b" + VagueWords[j] + "\\b");
MatchCollection matches = myRegEx.Matches(SentenceArray[i]);
int vagword = matches.Count;
vague = vagword + vague;
if (matches.Count > 0)
{
file.WriteLine(VagueWords[j] + " - " + matches.Count + " times");
}
}
file.WriteLine("------ Weak Words ------ ");
for (int j = 0; j < WeakWords.Length; j++)
{
var myRegEx = new Regex("\\b" + WeakWords[j] + "\\b");
MatchCollection matches = myRegEx.Matches(SentenceArray[i]);
int Weword = matches.Count;
weak = Weword + weak;
if (matches.Count > 0)
{
file.WriteLine(WeakWords[j] + " - " + matches.Count + " times");
}
}
file.WriteLine("------ Directive Words ------ ");
for (int j = 0; j < DirectiveWords.Length; j++)
{
var myRegEx = new Regex("\\b" + DirectiveWords[j] + "\\b");
MatchCollection matches = myRegEx.Matches(SentenceArray[i]);
int diwords = matches.Count;
direct = diwords + direct;
if (matches.Count > 0)
{
file.WriteLine(DirectiveWords[j] + " - " + matches.Count + " times");
}
}
file.WriteLine("------ Continuance Words ------ ");
for (int j = 0; j < Continuances.Length; j++)
{
var myRegEx = new Regex("\\b" + Continuances[j] + "\\b");
MatchCollection matches = myRegEx.Matches(SentenceArray[i]);
int contwords = matches.Count;
cont = contwords + cont;
if (matches.Count > 0)
{
file.WriteLine(Continuances[j] + " - " + matches.Count + " times");
}
}
file.WriteLine("------ imperatives ------ ");
for (int j = 0; j < imperatives.Length; j++)
{
var myRegEx = new Regex("\\b" + imperatives[j] + "\\b");
MatchCollection matches = myRegEx.Matches(SentenceArray[i]);
int imptawords = matches.Count;
impta = imptawords + impta;
if (matches.Count > 0)
{
file.WriteLine(imperatives[j] + " - " + matches.Count + " times");
}
}
}
file.WriteLine("------------ ");
file.WriteLine("------ Total tally ------ ");
file.WriteLine("DirectiveWords" + " - " + direct + " times");
file.WriteLine("weak words" + " - " + weak + " times");
file.WriteLine("vague words" + " - " + vague + " times");
file.WriteLine("optional words" + " - " + opt + " times");
file.WriteLine("implicit words" + " - " + imp + " times");
file.WriteLine("continuance words" + " - " + cont + " times");
file.WriteLine("imperative words" + " - " + impta + " times");
//-------------------------RDQ------Requirement Document Quality-----------------------------------------
file.WriteLine("\r\n\r\n------------Requirement Document Quality-------------\r\n \r\n");
double LinesCount;
int CharCount;
double WordsCount;
string Path = path;
string Text = new System.IO.StreamReader(Path).ReadToEnd();
CharCount = Text.Trim().Length; //total char
LinesCount = Text.Split('.', '!', '?').Length; //total lines
WordsCount = Text.Split(' ').Length; // total Words
file.WriteLine("Character count is {0} \r\n", CharCount);
file.WriteLine("Word count is {0} \r\n", WordsCount);
file.WriteLine("Line count is {0} \r\n", LinesCount);
//finding the number of syllables
string contents = System.IO.File.ReadAllText(path);
int SCount = SyllableCount(contents);
file.WriteLine("Syllable count is {0} \r\n", SCount);
//finding the Flesch index
file.WriteLine("finding the Flesch index: \r\n");
double ASL = WordsCount / LinesCount;
file.WriteLine("Average Sentence Length");
file.WriteLine("{0}\r\n", ASL);
double ASW = SCount / WordsCount;
file.WriteLine("Average number of syllables per word");
file.WriteLine("{0}\r\n", ASW);
double FRI = 206.835 - (1.015 * ASL) - (84.6 * ASW);
file.WriteLine("The Flesch index is");
file.WriteLine("{0}\r\n", FRI);
//printinh the ranges for flesch index value
file.WriteLine("Flesch index ranges:\r\n \r\n100 - 90 \t very easy to read (5th grade) \r\n90 – 80 \t easy to read (6th grade) \r\n80 – 70 \t fairly easy to read (7th grade) \r\n70 – 60 \t plain english (8th & 9th grade) \r\n60 – 50 \t fairly difficult to read (10th - 12th grade) \r\n50 – 30 \t difficult to read (College) \r\n30 – 0 \t very difficult to read (College graduate) \r\n\r\n");
//finding the Automatic Readabilty index
file.WriteLine("finding the Automatic readabilty index:\r\n");
double AVL = CharCount / WordsCount;
file.WriteLine("the average number of letters per word");
file.WriteLine("{0}\r\n", AVL);
double AVW = WordsCount / LinesCount;
file.WriteLine("the average number of words in sentences");
file.WriteLine("{0}\r\n", AVW);
double ARI = (AVL * 4.71) + (AVW * 0.5) - 21.43;
file.WriteLine("The Automatic readability index is");
file.WriteLine("{0}\r\n", ARI);
file.WriteLine("Automatic redability index ranges:\r\n \r\n10 - 11 \tFifth Grade. \r\n11 - 12 \tSixth Grade. \r\n12 - 13 \tSeventh Grade. \r\n13 - 14 \tEighth Grade. \r\n14 - 15 \tNinth Grade. \r\n15 - 16 \tTenth Grade. \r\n16 - 17 \tEleventh grade. \r\n17 - 20 \tTwelfth grade. \r\n20 - 24 \tCollege. \r\n24 - 27 \tCollege graduate.");
file.Flush();
file.Close();
System.Console.WriteLine("The output is stored in the file {0}", location);
}