/// <summary>
/// Returns a new CoreLabel instance based on the contents of the given
/// CoreMap. It copies the contents of the other CoreMap.
/// </summary>
/// <param name="label">The CoreMap to copy</param>
public CoreLabel(ICoreMap label) : base(label.Size())
{
foreach (var key in label.KeySet())
{
Set(key, label.Get(key));
}
}
/// <summary>
/// Returns a new CoreLabel instance based on the contents of the given
/// label.
/// </summary>
/// <remarks>
/// Returns a new CoreLabel instance based on the contents of the given
/// label. Warning: The behavior of this method is a bit disjunctive!
/// If label is a CoreMap (including CoreLabel), then its entire
/// contents is copied into this label.
/// If label is an IndexedWord, then the backing label is copied over
/// entirely.
/// But, otherwise, just the
/// value() and word iff it implements
/// <see cref="IHasWord"/>
/// is copied.
/// </remarks>
/// <param name="label">Basis for this label</param>
public CoreLabel(ILabel label)
: base(0)
{
if (label is ICoreMap)
{
ICoreMap cl = (ICoreMap)label;
SetCapacity(cl.Size());
foreach (Type key in cl.KeySet())
{
Set(key, cl.Get(key));
}
}
else
{
if (label is IndexedWord)
{
ICoreMap cl = ((IndexedWord)label).BackingLabel();
SetCapacity(cl.Size());
foreach (Type key in cl.KeySet())
{
Set(key, cl.Get(key));
}
}
else
{
if (label is IHasWord)
{
SetWord(((IHasWord)label).Word());
}
SetValue(label.Value());
}
}
}
public static void DumpCoreMapToStringBuilder(ICoreMap cm, StringBuilder sb)
{
foreach (Type rawKey in cm.KeySet())
{
Type key = (Type)rawKey;
string className = key.GetSimpleName();
object value = cm.Get(key);
sb.Append(className).Append(": ").Append(value).Append("\n");
}
}
/// <summary>Two CoreMaps are equal iff all keys and values are .equal.</summary>
public override bool Equals(object obj)
{
if (!(obj is ICoreMap))
{
return(false);
}
if (obj is HashableCoreMap)
{
// overridden behavior for HashableCoreMap
return(obj.Equals(this));
}
if (obj is Edu.Stanford.Nlp.Util.ArrayCoreMap)
{
// specialized equals for ArrayCoreMap
return(Equals((Edu.Stanford.Nlp.Util.ArrayCoreMap)obj));
}
// TODO: make the general equality work in the situation of loops in the object graph
// general equality
ICoreMap other = (ICoreMap)obj;
if (!this.KeySet().Equals(other.KeySet()))
{
return(false);
}
foreach (Type key in this.KeySet())
{
if (!other.ContainsKey(key))
{
return(false);
}
object thisV = this.Get(key);
object otherV = other.Get(key);
if (thisV == otherV)
{
continue;
}
// the two values must be unequal, so if either is null, the other isn't
if (thisV == null || otherV == null)
{
return(false);
}
if (!thisV.Equals(otherV))
{
return(false);
}
}
return(true);
}
/// <summary>Copy constructor.</summary>
/// <param name="other">The ArrayCoreMap to copy. It may not be null.</param>
public ArrayCoreMap(ICoreMap other)
{
ICollection <Type> otherKeys = other.KeySet();
size = otherKeys.Count;
keys = new Type[size];
values = new object[size];
int i = 0;
foreach (Type key in otherKeys)
{
this.keys[i] = key;
this.values[i] = other.Get(key);
i++;
}
}
/// <summary>
/// Copy constructor.
/// </summary>
/// <param name="other">The ArrayCoreMap to copy. It may not be null.</param>
public ArrayCoreMap(ICoreMap other)
{
/*Set<Class<?>>*/
var otherKeys = other.KeySet();
psize = otherKeys.Count;
keys = new Type[psize];
values = new Object[psize];
int i = 0;
foreach (var key in otherKeys)
{
this.keys[i] = key;
this.values[i] = other.Get(key);
i++;
}
}
// static stuff
/// <summary>
/// Merge one CoreMap into another -- that is, overwrite and add any keys in
/// the base CoreMap with those in the one to be merged.
/// </summary>
/// <remarks>
/// Merge one CoreMap into another -- that is, overwrite and add any keys in
/// the base CoreMap with those in the one to be merged.
/// This method is functional -- neither of the argument CoreMaps are changed.
/// </remarks>
/// <param name="base">The CoreMap to serve as the base (keys in this are lower priority)</param>
/// <param name="toBeMerged">The CoreMap to merge in (keys in this are higher priority)</param>
/// <returns>A new CoreMap representing the merge of the two inputs</returns>
public static ICoreMap Merge(ICoreMap @base, ICoreMap toBeMerged)
{
//(variables)
ICoreMap rtn = new ArrayCoreMap(@base.Size());
//(copy base)
foreach (Type key in @base.KeySet())
{
rtn.Set(key, @base.Get(key));
}
//(merge)
foreach (Type key_1 in toBeMerged.KeySet())
{
rtn.Set(key_1, toBeMerged.Get(key_1));
}
//(return)
return(rtn);
}
/// <summary>
/// Returns a new CoreLabel instance based on the contents of the given
/// CoreMap.
/// </summary>
/// <remarks>
/// Returns a new CoreLabel instance based on the contents of the given
/// CoreMap. It copies the contents of the other CoreMap.
/// </remarks>
/// <param name="label">The CoreMap to copy</param>
public CoreLabel(ICoreMap label)
: base(label.Size())
{
/* , HasContext */
// /**
// * Should warnings be printed when converting from MapLabel family.
// */
// private static final boolean VERBOSE = false;
IConsumer <Type> savedListener = ArrayCoreMap.listener;
// don't listen to the clone operation
ArrayCoreMap.listener = null;
foreach (Type key in label.KeySet())
{
Set(key, label.Get(key));
}
ArrayCoreMap.listener = savedListener;
}
private void CleanupTags(ICoreMap cm, IDictionary <object, bool> cleaned)
{
cm.Remove(typeof(Tags.TagsAnnotation));
foreach (Type key in cm.KeySet())
{
object obj = cm.Get(key);
if (!cleaned.Contains(obj))
{
cleaned[obj] = false;
if (obj is ICoreMap)
{
CleanupTags((ICoreMap)obj, cleaned);
}
else
{
if (obj is ICollection)
{
CleanupTags((ICollection)obj, cleaned);
}
}
cleaned[obj] = true;
}
}
}
/// <summary>
/// Copy constructor.
/// </summary>
/// <param name="other">The ArrayCoreMap to copy. It may not be null.</param>
public ArrayCoreMap(ICoreMap other)
{
/*Set<Class<?>>*/
var otherKeys = other.KeySet();
psize = otherKeys.Count;
keys = new Type[psize];
values = new Object[psize];
int i = 0;
foreach (var key in otherKeys)
{
this.keys[i] = key;
this.values[i] = other.Get(key);
i++;
}
}
/// <summary>Usage: java -cp "*" StanfordCoreNlpDemo [inputFile [outputTextFile [outputXmlFile]]]</summary>
/// <exception cref="System.IO.IOException"/>
public static void Main(string[] args)
{
// set up optional output files
PrintWriter @out;
if (args.Length > 1)
{
@out = new PrintWriter(args[1]);
}
else
{
@out = new PrintWriter(System.Console.Out);
}
PrintWriter xmlOut = null;
if (args.Length > 2)
{
xmlOut = new PrintWriter(args[2]);
}
// Create a CoreNLP pipeline. To build the default pipeline, you can just use:
// StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
// Here's a more complex setup example:
// Properties props = new Properties();
// props.put("annotators", "tokenize, ssplit, pos, lemma, ner, depparse");
// props.put("ner.model", "edu/stanford/nlp/models/ner/english.all.3class.distsim.crf.ser.gz");
// props.put("ner.applyNumericClassifiers", "false");
// StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
// Add in sentiment
Properties props = new Properties();
props.SetProperty("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref, sentiment");
StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
// Initialize an Annotation with some text to be annotated. The text is the argument to the constructor.
Annotation annotation;
if (args.Length > 0)
{
annotation = new Annotation(IOUtils.SlurpFileNoExceptions(args[0]));
}
else
{
annotation = new Annotation("Kosgi Santosh sent an email to Stanford University. He didn't get a reply.");
}
// run all the selected Annotators on this text
pipeline.Annotate(annotation);
// this prints out the results of sentence analysis to file(s) in good formats
pipeline.PrettyPrint(annotation, @out);
if (xmlOut != null)
{
pipeline.XmlPrint(annotation, xmlOut);
}
// Access the Annotation in code
// The toString() method on an Annotation just prints the text of the Annotation
// But you can see what is in it with other methods like toShorterString()
@out.Println();
@out.Println("The top level annotation");
@out.Println(annotation.ToShorterString());
@out.Println();
// An Annotation is a Map with Class keys for the linguistic analysis types.
// You can get and use the various analyses individually.
// For instance, this gets the parse tree of the first sentence in the text.
IList <ICoreMap> sentences = annotation.Get(typeof(CoreAnnotations.SentencesAnnotation));
if (sentences != null && !sentences.IsEmpty())
{
ICoreMap sentence = sentences[0];
@out.Println("The keys of the first sentence's CoreMap are:");
@out.Println(sentence.KeySet());
@out.Println();
@out.Println("The first sentence is:");
@out.Println(sentence.ToShorterString());
@out.Println();
@out.Println("The first sentence tokens are:");
foreach (ICoreMap token in sentence.Get(typeof(CoreAnnotations.TokensAnnotation)))
{
@out.Println(token.ToShorterString());
}
Tree tree = sentence.Get(typeof(TreeCoreAnnotations.TreeAnnotation));
@out.Println();
@out.Println("The first sentence parse tree is:");
tree.PennPrint(@out);
@out.Println();
@out.Println("The first sentence basic dependencies are:");
@out.Println(sentence.Get(typeof(SemanticGraphCoreAnnotations.BasicDependenciesAnnotation)).ToString(SemanticGraph.OutputFormat.List));
@out.Println("The first sentence collapsed, CC-processed dependencies are:");
SemanticGraph graph = sentence.Get(typeof(SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation));
@out.Println(graph.ToString(SemanticGraph.OutputFormat.List));
// Access coreference. In the coreference link graph,
// each chain stores a set of mentions that co-refer with each other,
// along with a method for getting the most representative mention.
// Both sentence and token offsets start at 1!
@out.Println("Coreference information");
IDictionary <int, CorefChain> corefChains = annotation.Get(typeof(CorefCoreAnnotations.CorefChainAnnotation));
if (corefChains == null)
{
return;
}
foreach (KeyValuePair <int, CorefChain> entry in corefChains)
{
@out.Println("Chain " + entry.Key);
foreach (CorefChain.CorefMention m in entry.Value.GetMentionsInTextualOrder())
{
// We need to subtract one since the indices count from 1 but the Lists start from 0
IList <CoreLabel> tokens = sentences[m.sentNum - 1].Get(typeof(CoreAnnotations.TokensAnnotation));
// We subtract two for end: one for 0-based indexing, and one because we want last token of mention not one following.
@out.Println(" " + m + ", i.e., 0-based character offsets [" + tokens[m.startIndex - 1].BeginPosition() + ", " + tokens[m.endIndex - 2].EndPosition() + ")");
}
}
@out.Println();
@out.Println("The first sentence overall sentiment rating is " + sentence.Get(typeof(SentimentCoreAnnotations.SentimentClass)));
}
IOUtils.CloseIgnoringExceptions(@out);
IOUtils.CloseIgnoringExceptions(xmlOut);
}
