//[Test]
public void TestQuestions()
{
var sentences = new [] {
"How are you?",
"Do animals eat fruit ?",
"What do animals eat ?",
"Why do animals eat fruit ?",
"How much fruit do animals eat ?",
"Where do animals eat ?",
"When do animals eat ?"
};
// This test can't be done becouse a bug in the OpenNLP IKVM version
// https://issues.apache.org/jira/browse/OPENNLP-727
var jParser = CreateJavaParser(modelFile);
var sParser = CreateSharpParser(modelFile);
foreach (var sentence in sentences)
{
var jParses = opennlp.tools.cmdline.parser.ParserTool.parseLine(sentence, jParser, 1);
var sParses = ParserTool.ParseLine(sentence, sParser, 1);
CheckParseChild(jParses, sParses);
}
}
public void TestQuestionsManually()
{
var sentences = new[] {
"How are you?",
"Do animals eat fruit ?",
"What do animals eat ?",
"Why do animals eat fruit ?",
"How much fruit do animals eat ?",
"Where do animals eat ?",
"When do animals eat ?"
};
var results = new[] {
"(TOP (SBAR (WHADVP (WRB How)) (S (VP (VBP are))) (. you?)))",
"(TOP (SQ (VBP Do) (NP (NNS animals)) (VP (VB eat) (NP (NN fruit))) (. ?)))",
"(TOP (SBARQ (WHNP (WP What)) (SQ (VBP do) (NP (NNS animals)) (VP (VB eat))) (. ?)))",
"(TOP (SBARQ (WHADVP (WRB Why)) (SQ (VBP do) (NP (NNS animals)) (VP (VB eat) (NP (NN fruit)))) (. ?)))",
"(TOP (SBAR (WHADJP (WRB How)) (S (NP (JJ much) (NN fruit)) (VP (VBP do) (S (NP (NNS animals)) (VP (VB eat))))) (. ?)))",
"(TOP (SBARQ (WHADVP (WRB Where)) (SQ (VBP do) (NP (NNS animals)) (VP (VB eat))) (. ?)))",
"(TOP (SBARQ (WHADVP (WRB When)) (SQ (VBP do) (NP (NNS animals)) (VP (VB eat))) (. ?)))"
};
var sParser = CreateSharpParser(modelFile);
for (int i = 0; i < sentences.Length; i++)
{
var sParses = ParserTool.ParseLine(sentences[i], sParser, 1);
Assert.AreEqual(1, sParses.Length);
Assert.AreEqual(results[i], sParses[0].ToString());
}
}
public void TestParse()
{
var jParser = CreateJavaParser(modelFile);
var sParser = CreateSharpParser(modelFile);
var sentences = new[] {
"Let all your things have their places; let each part of your business have its time.",
"It has become appallingly obvious that our technology has exceeded our humanity.",
"The real problem is not whether machines think but whether men do.",
"The worst form of inequality is to try to make unequal things equal.",
"People won't have time for you if you are always angry or complaining.",
"To keep the body in good health is a duty... otherwise we shall not be able to keep our mind strong and clear.",
"You, yourself, as much as anybody in the entire universe, deserve your love and affection."
};
foreach (var sentence in sentences)
{
var jParses = opennlp.tools.cmdline.parser.ParserTool.parseLine(sentence, jParser, 1);
var sParses = ParserTool.ParseLine(sentence, sParser, 1);
var jsb = new java.lang.StringBuffer();
jParses[0].show(jsb);
Assert.That(sParses[0].ToString(), Is.EqualTo(jsb.ToString()));
}
}
//[Test]
public void TestParse()
{
// This test can't be done becouse a bug in the OpenNLP IKVM version
// https://issues.apache.org/jira/browse/OPENNLP-727
//const string sentence = "The quick brown fox jumps over the lazy dog .";
const string sentence = "How much fruit do animals eat ?";
var jParser = CreateJavaParser(modelFile);
var sParser = CreateSharpParser(modelFile);
var jParses = opennlp.tools.cmdline.parser.ParserTool.parseLine(sentence, jParser, 1);
var sParses = ParserTool.ParseLine(sentence, sParser, 1);
var jsb = new java.lang.StringBuffer();
jParses[0].show(jsb);
Assert.AreEqual("(TOP (SBAR (WHADJP (WRB How)) (S (NP (JJ much) (NN fruit)) (VP (VBP do) (S (NP (NNS animals)) (VP (VB eat))))) (. ?)))",
jsb.toString());
Assert.AreEqual("(TOP (SBAR (WHADJP (WRB How)) (S (NP (JJ much) (NN fruit)) (VP (VBP do) (S (NP (NNS animals)) (VP (VB eat))))) (. ?)))",
sParses[0].ToString());
Assert.NotNull(sParses);
//CheckParseChild(jParses, sParses);
}
/// <summary>
/// 使用openNLP做英文Parsing。model: en-parser-chunking.bin。
/// </summary>
/// <param name="sentence">英文句子。</param>
/// <returns>樹狀資料結構。</returns>
public Parse Parser(string sentence)
{
if (sentence.Length <= 0)
{
return(null);
}
LoadParser();
string result = String.Empty;
Parse[] topParses = ParserTool.parseLine(sentence, parser, 1);
return(topParses[0]);
}
public string[] getS(string sentence)
{
if (sentence.Length <= 0)
{
return(null);
}
temp = new List <string>();
Parse[] topParses = ParserTool.parseLine(sentence, parser, 1);
foreach (Parse p in topParses)
{
recursiveTraversalTree(p);
}
return(temp.ToArray());
}
public string Parser(string sentence)
{
if (sentence.Length <= 0)
{
return("");
}
string result = String.Empty;
Parse[] topParses = ParserTool.parseLine(sentence, parser, 1);
foreach (Parse p in topParses)
{
result += getPhrase(p);
}
return(result);
}
public ActionResult <int[, ]> GetMatrix([FromBody] string idOfMatrix)
{
var matrixProperties = ParserTool.ParseId(idOfMatrix);
if (matrixProperties == null)
{
return(BadRequest());
}
uint matrixIndex = MatrixTool.GetMatrixIndex(matrixProperties);
int [,] matrix = new int[matrixProperties.Rows, matrixProperties.Columns];
for (int i = 0; i < matrixProperties.Rows; i++)
{
for (int j = 0; j < matrixProperties.Columns; j++)
{
matrix[i, j] = (int)Math.Floor((Math.Cos(i / 15) + Math.Sin(j / matrixIndex)) * 10);
}
}
return(Ok(JsonConvert.SerializeObject(matrix)));
}
public void TestQuestions()
{
var sentences = new [] {
"How are you?",
"Do animals eat fruit ?",
"What do animals eat ?",
"Why do animals eat fruit ?",
"How much fruit do animals eat ?",
"Where do animals eat ?",
"When do animals eat ?"
};
var jParser = CreateJavaParser(modelFile);
var sParser = CreateSharpParser(modelFile);
foreach (var sentence in sentences)
{
var jParses = opennlp.tools.cmdline.parser.ParserTool.parseLine(sentence, jParser, 1);
var sParses = ParserTool.ParseLine(sentence, sParser, 1);
CheckParseChild(jParses, sParses);
}
}
public Dictionary <string, List <string> > Main(string line)
{
//debug sentence
// line = "Show me the sales of Kean Cola .25ltr Bottle in Nicosia from January 2017 to October 2017 as a line chart.";
matchedWords?.Clear();
nounPhrases?.Clear();
nouns?.Clear();
adjectivePhrases?.Clear();
verbPhrases?.Clear();
InputStream modelIn = new FileInputStream(HttpRuntime.AppDomainAppPath + "\\Models\\en-parser-chunking.bin");
InputStream modelIn1 = new FileInputStream(HttpRuntime.AppDomainAppPath + "\\Models\\en-ner-date.bin");
InputStream modelIn2 = new FileInputStream(HttpRuntime.AppDomainAppPath + "\\Models\\en-token.bin");
ParserModel model = new ParserModel(modelIn);
var myParser = ParserFactory.create(model);
var topParses = ParserTool.parseLine(line, myParser, 1);
foreach (var p in topParses)
{
GetSentenceParts(p);
}
try
{
TokenizerModel model1 = new TokenizerModel(modelIn2);
TokenNameFinderModel model2 = new TokenNameFinderModel(modelIn1);
Tokenizer tokenizer = new TokenizerME(model1);
var nameFinder = new NameFinderME(model2);
var tokens = tokenizer.tokenize(line);
var nameSpans = nameFinder.find(tokens);
var array = Span.spansToStrings(nameSpans, tokens);
//
// foreach (var v in array)
// {
// System.Diagnostics.Debug.WriteLine(v);
// }
dates = new HashSet <string>(array);
PrintSets();
// System.Diagnostics.Debug.WriteLine("\nProcessing Presentation type");
//
// if (nouns.Contains("table"))
// {
// matchedWords.Add(new Tuple<string, string>("PRESENTATION_TYPE", "table"));
// }
// if (nounPhrases.Contains("bar chart"))
// {
// matchedWords.Add(new Tuple<string, string>("PRESENTATION_TYPE", "bar chart"));
// }
// if (nounPhrases.Contains("line chart"))
// {
// matchedWords.Add(new Tuple<string, string>("PRESENTATION_TYPE", "line chart"));
// }
//TODO IF NO OPTION IS FOUND ASK THE USER TO GIVE YOU ONE. IMPLEMENT IT IN THE WEB VERSION SOON
System.Diagnostics.Debug.WriteLine("\nProcessing Dates");
if (dates.Count == 2)
{
if (dates.ElementAt(0).contains("from"))
{
var a = dates.ElementAt(0).replace("from", "");
List <string> newList = new List <string>();
newList.Add("START_PERIOD");
matchedWords.Add(a, newList);
newList = new List <string>();
newList.Add("END_PERIOD");
//todo fix when the date is the same here
matchedWords.Add(dates.ElementAt(1), newList);
}
else
{
List <string> newList = new List <string>();
newList.Add("START_PERIOD");
matchedWords.Add(dates.ElementAt(0), newList);
newList = new List <string>();
newList.Add("END_PERIOD");
//todo fix when the date is the same here
matchedWords.Add(dates.ElementAt(1), newList);
}
}
if (dates.Count == 1)
{
if (dates.ElementAt(0).contains("from"))
{
var a = dates.ElementAt(0).replace("from", "");
var dts = a.Split(new[] { " to " }, StringSplitOptions.None);
List <string> newList = new List <string>();
newList.Add("START_PERIOD");
matchedWords.Add(dts[0], newList);
newList = new List <string>();
newList.Add("END_PERIOD");
//todo fix when the date is the same here
matchedWords.Add(dts[1], newList);
}
else
{
List <string> newList = new List <string>();
newList.Add("START_PERIOD");
newList.Add("END_PERIOD");
//todo fix when the date is the same here
matchedWords.Add(dates.ElementAt(0), newList);
}
}
System.Diagnostics.Debug.WriteLine("\nProcessing noun phrases");
// var manager = new Manager();
// var serializer = new XmlSerializer(typeof(Manager.language));
// var loadStream = new FileStream("file2.xml", FileMode.Open, FileAccess.Read);
// var loadedObject = (Manager.language) serializer.Deserialize(loadStream);
var doc = new XmlDocument();
// System.Diagnostics.Debug.WriteLine(HttpRuntime.AppDomainAppPath);
// System.Diagnostics.Debug.WriteLine(HttpRuntime.AppDomainAppPath);
// System.Diagnostics.Debug.WriteLine(HttpRuntime.AppDomainAppPath);
// System.Diagnostics.Debug.WriteLine(HttpRuntime.AppDomainAppPath);
doc.Load(HttpRuntime.AppDomainAppPath + "\\file2.xml");
var root = doc.SelectSingleNode("*");
FindMatchingNodesFromXml(root, nounPhrases);
foreach (var item in nouns.ToList())
{
foreach (var VARIABLE in matchedWords)
{
if (VARIABLE.Key.Contains(item))
{
nouns.Remove(item); //Will work!
}
}
}
FindMatchingNodesFromXml(root, verbPhrases);
// FindMatchingNodesFromXml(root, nouns);
System.Diagnostics.Debug.WriteLine("\nProcessing verb phrases ");
System.Diagnostics.Debug.WriteLine("\nProcessing nouns ");
// construct the dictionary object and open it
var directory = Directory.GetCurrentDirectory() + "\\wordnet\\";
foreach (var variable in matchedWords)
{
System.Diagnostics.Debug.WriteLine(variable.Value + "\t\t" + variable.Key);
}
foreach (var variable in matchedWords)
{
string a = variable.Key;
if (line.Contains(a))
{
line = line.replace(a, "");
}
}
foreach (var variable in stopWordsofwordnet)
{
string a = " " + variable.toLowerCase() + " ";
if (line.Contains(a))
{
line = line.replace(a, " ");
}
}
if (line.contains("."))
{
line = line.replace(".", "");
}
if (line.contains("-"))
{
line = line.replace("-", " ");
}
System.Diagnostics.Debug.WriteLine("/////////////");
System.Diagnostics.Debug.WriteLine("SECOND PARSE STRING " + line);
System.Diagnostics.Debug.WriteLine("/////////////");
line = line.Trim();
topParses = ParserTool.parseLine(line, myParser, 1);
nounPhrases?.Clear();
dates?.Clear();
verbPhrases?.Clear();
nouns?.Clear();
foreach (var p in topParses)
{
//p.show();
GetSentenceParts(p);
}
FindMatchingNodesFromXml(root, nounPhrases);
foreach (var item in nouns.ToList())
{
foreach (var VARIABLE in matchedWords)
{
if (VARIABLE.Key.Contains(item))
{
nouns.Remove(item); //Will work!
}
}
}
FindMatchingNodesFromXml(root, verbPhrases);
FindMatchingNodesFromXml(root, nouns);
tokens = tokenizer.tokenize(line);
nameSpans = nameFinder.find(tokens);
array = Span.spansToStrings(nameSpans, tokens);
dates = new HashSet <string>(array);
PrintSets();
System.Diagnostics.Debug.WriteLine("\nProcessing Dates");
if (dates.Count == 2)
{
if (dates.ElementAt(0).contains("from"))
{
var a = dates.ElementAt(0).replace("from", "");
List <string> newList = new List <string>();
newList.Add("START_PERIOD");
matchedWords.Add(a, newList);
newList = new List <string>();
newList.Add("END_PERIOD");
//todo fix when the date is the same here
matchedWords.Add(dates.ElementAt(1), newList);
}
else
{
List <string> newList = new List <string>();
newList.Add("START_PERIOD");
matchedWords.Add(dates.ElementAt(0), newList);
newList = new List <string>();
newList.Add("END_PERIOD");
//todo fix when the date is the same here
matchedWords.Add(dates.ElementAt(1), newList);
}
}
if (dates.Count == 1)
{
if (dates.ElementAt(0).contains("from"))
{
var a = dates.ElementAt(0).replace("from", "");
var dts = a.Split(new[] { " to " }, StringSplitOptions.None);
List <string> newList = new List <string>();
newList.Add("START_PERIOD");
matchedWords.Add(dts[0], newList);
newList = new List <string>();
newList.Add("END_PERIOD");
//todo fix when the date is the same here
matchedWords.Add(dts[1], newList);
}
else
{
List <string> newList = new List <string>();
newList.Add("START_PERIOD");
newList.Add("END_PERIOD");
//todo fix when the date is the same here
matchedWords.Add(dates.ElementAt(0), newList);
}
}
System.Diagnostics.Debug.WriteLine("\nProcessing noun phrases");
// var manager = new Manager();
// var serializer = new XmlSerializer(typeof(Manager.language));
// var loadStream = new FileStream("file2.xml", FileMode.Open, FileAccess.Read);
// var loadedObject = (Manager.language) serializer.Deserialize(loadStream);
FindMatchingNodesFromXml(root, nounPhrases);
FindMatchingNodesFromXml(root, verbPhrases);
FindMatchingNodesFromXml(root, nouns);
foreach (var variable in matchedWords)
{
System.Diagnostics.Debug.WriteLine(variable.Value + "\t\t" + variable.Key);
}
doc = null;
GC.Collect();
GC.WaitForPendingFinalizers();
//MATCHING WITH WORD NET
System.Diagnostics.Debug.WriteLine(directory);
// var wordNet = new WordNetEngine();
//
// wordNet.AddDataSource(new StreamReader(Path.Combine(directory, "data.adj")), PartOfSpeech.Adjective);
// wordNet.AddDataSource(new StreamReader(Path.Combine(directory, "data.adv")), PartOfSpeech.Adverb);
// wordNet.AddDataSource(new StreamReader(Path.Combine(directory, "data.noun")), PartOfSpeech.Noun);
// wordNet.AddDataSource(new StreamReader(Path.Combine(directory, "data.verb")), PartOfSpeech.Verb);
//
// wordNet.AddIndexSource(new StreamReader(Path.Combine(directory, "index.adj")), PartOfSpeech.Adjective);
// wordNet.AddIndexSource(new StreamReader(Path.Combine(directory, "index.adv")), PartOfSpeech.Adverb);
// wordNet.AddIndexSource(new StreamReader(Path.Combine(directory, "index.noun")), PartOfSpeech.Noun);
// wordNet.AddIndexSource(new StreamReader(Path.Combine(directory, "index.verb")), PartOfSpeech.Verb);
//
// System.Diagnostics.Debug.WriteLine("Loading database...");
// wordNet.Load();
// System.Diagnostics.Debug.WriteLine("Load completed.");
// while (true)
// {
// System.Diagnostics.Debug.WriteLine("\nType first word");
//
// var word = System.Diagnostics.Debug.ReadLine();
// var synSetList = wordNet.GetSynSets(word);
//
// if (synSetList.Count == 0) System.Diagnostics.Debug.WriteLine($"No SynSet found for '{word}'");
//
// foreach (var synSet in synSetList)
// {
// var words = string.Join(", ", synSet.Words);
//
// System.Diagnostics.Debug.WriteLine($"\nWords: {words}");
// }
// }
}
catch (IOException e)
{
e.printStackTrace();
}
finally
{
if (modelIn1 != null)
{
try
{
modelIn1.close();
}
catch (IOException e)
{
}
}
if (modelIn2 != null)
{
try
{
modelIn2.close();
}
catch (IOException e)
{
}
}
// truncateLists(ref nounPhrases);
// truncateLists(ref nouns);
// truncateLists(ref dates);
// truncateLists(ref verbPhrases);
}
return(matchedWords);
}
