/// <summary>
/// Parses a tsurgeon script text input and compiles a tregex pattern and a list
/// of tsurgeon operations into a pair.
/// </summary>
/// <param name="reader">Reader to read patterns from</param>
/// <returns>
/// A pair of a tregex and tsurgeon pattern read from a file, or
/// <see langword="null"/>
/// when the operations present in the Reader have been exhausted
/// </returns>
/// <exception cref="System.IO.IOException">If any IO problem</exception>
public static Pair <TregexPattern, TsurgeonPattern> GetOperationFromReader(BufferedReader reader, TregexPatternCompiler compiler)
{
string patternString = GetTregexPatternFromReader(reader);
// log.info("Read tregex pattern: " + patternString);
if (patternString.IsEmpty())
{
return(null);
}
TregexPattern matchPattern = compiler.Compile(patternString);
TsurgeonPattern collectedPattern = GetTsurgeonOperationsFromReader(reader);
return(new Pair <TregexPattern, TsurgeonPattern>(matchPattern, collectedPattern));
}
/// <summary>
/// Compile the
/// <see cref="annotations"/>
/// collection given a
/// particular head finder. Subclasses should call this method at
/// least once before the class is used, and whenever the head finder
/// is changed.
/// </summary>
protected internal virtual void CompileAnnotations(IHeadFinder hf)
{
TregexPatternCompiler compiler = new TregexPatternCompiler(hf);
annotationPatterns.Clear();
foreach (KeyValuePair <string, Pair <string, Func <TregexMatcher, string> > > annotation in annotations)
{
TregexPattern compiled;
try
{
compiled = compiler.Compile(annotation.Value.First());
}
catch (TregexParseException e)
{
int nth = annotationPatterns.Count + 1;
log.Info("Parse exception on annotation pattern #" + nth + " initialization: " + e);
continue;
}
Pair <TregexPattern, Func <TregexMatcher, string> > behavior = new Pair <TregexPattern, Func <TregexMatcher, string> >(compiled, annotation.Value.Second());
annotationPatterns[annotation.Key] = behavior;
}
}
// to hold the specific prep or conjunction associated with the grammatical relation
// TODO document constructor
// TODO change to put specificString after longName, and then use string... for targetPatterns
private GrammaticalRelation(Language language,
string shortName,
string longName,
GrammaticalRelation parent,
string sourcePattern,
TregexPatternCompiler tregexCompiler,
string[] targetPatterns,
string specificString)
{
this.language = language;
this.shortName = shortName;
this.longName = longName;
this.parent = parent;
this.specific = specificString; // this can be null!
if (parent != null)
{
parent.AddChild(this);
}
if (sourcePattern != null)
{
/*try {*/
this.sourcePattern = new Regex("^(" + sourcePattern + ")$", RegexOptions.Compiled);
/*} catch (java.util.regex.PatternSyntaxException e) {
* throw new RuntimeException("Bad pattern: " + sourcePattern);
* }*/
}
else
{
this.sourcePattern = null;
}
foreach (string pattern in targetPatterns)
{
try
{
TregexPattern p = tregexCompiler.Compile(pattern);
this.targetPatterns.Add(p);
}
catch (TregexParseException pe)
{
throw new SystemException("Bad pattern: " + pattern, pe);
}
}
Dictionary <string, GrammaticalRelation> sToR;
StringsToRelations.TryGetValue(language, out sToR);
if (sToR == null)
{
sToR = new Dictionary <string, GrammaticalRelation>();
StringsToRelations.Add(language, sToR);
}
if (sToR.ContainsKey(ToString()))
{
var previous = sToR[ToString()];
if (!previous.IsFromString() && !IsFromString())
{
throw new ArgumentException("There is already a relation named " + ToString() + '!');
}
else
{
/* We get here if we previously just built a fake relation from a string
* we previously read in from a file.
*/
// TODO is it worth copying all of the information from this real
// relation into the old fake one?
}
sToR[ToString()] = this;
}
else
{
sToR.Add(ToString(), this);
}
/*GrammaticalRelation previous = sToR.put(ToString(), this);
* if (previous != null) {
* if (!previous.isFromString() && !isFromString()) {
* throw new ArgumentException("There is already a relation named " + ToString() + '!');
* } else {
* /* We get here if we previously just built a fake relation from a string
* we previously read in from a file.
#1#
* // TODO is it worth copying all of the information from this real
* // relation into the old fake one?
* }
* }*/
}
private GrammaticalRelation(Language language, string shortName, string longName, Edu.Stanford.Nlp.Trees.GrammaticalRelation parent, string sourcePattern, TregexPatternCompiler tregexCompiler, string[] targetPatterns, string specificString)
{
/* Non-static stuff */
// a regexp for node values at which this relation can hold
// to hold the specific prep or conjunction associated with the grammatical relation
// TODO document constructor
// TODO change to put specificString after longName, and then use String... for targetPatterns
this.language = language;
this.shortName = shortName;
this.longName = longName;
this.parent = parent;
this.specific = specificString;
// this can be null!
if (parent != null)
{
parent.AddChild(this);
}
if (sourcePattern != null)
{
try
{
this.sourcePattern = Pattern.Compile(sourcePattern);
}
catch (PatternSyntaxException)
{
throw new Exception("Bad pattern: " + sourcePattern);
}
}
else
{
this.sourcePattern = null;
}
foreach (string pattern in targetPatterns)
{
try
{
TregexPattern p = tregexCompiler.Compile(pattern);
this.targetPatterns.Add(p);
}
catch (TregexParseException pe)
{
throw new Exception("Bad pattern: " + pattern, pe);
}
}
Edu.Stanford.Nlp.Trees.GrammaticalRelation previous;
lock (stringsToRelations)
{
IDictionary <string, Edu.Stanford.Nlp.Trees.GrammaticalRelation> sToR = stringsToRelations[language];
if (sToR == null)
{
sToR = Generics.NewHashMap();
stringsToRelations[language] = sToR;
}
previous = sToR[ToString()] = this;
}
if (previous != null)
{
if (!previous.IsFromString() && !IsFromString())
{
throw new ArgumentException("There is already a relation named " + ToString() + '!');
}
}
}
