/**
* Create a searcher manually, suppling a dependency tree, an optional classifier for when to
* split clauses, and a featurizer for that classifier. You almost certainly want to use {@link
* ClauseSplitter#load(String)} instead of this constructor.
*
* @param tree The dependency tree to search over.
* @param assumedTruth The assumed truth of the tree (relevant for natural logic inference). If in
* doubt, pass in true.
* @param isClauseClassifier The classifier for whether a given dependency arc should be a new
* clause. If this is not given, all arcs are treated as clause separators.
* @param featurizer The featurizer for the classifier. If no featurizer is given, one should be
* given in {@link ClauseSplitterSearchProblem#search(java.util.function.Predicate,
* Classifier, Map, java.util.function.Function, int)}, or else the classifier will be
* useless.
* @see ClauseSplitter#load(String)
*/
protected ClauseSplitterSearchProblem(
SemanticGraph tree,
boolean assumedTruth,
Optional<Classifier<ClauseSplitter.ClauseClassifierLabel, String>> isClauseClassifier,
Optional<
Function<
Triple<
ClauseSplitterSearchProblem.State,
ClauseSplitterSearchProblem.Action,
ClauseSplitterSearchProblem.State>,
Counter<String>>>
featurizer) {
this.tree = new SemanticGraph(tree);
this.assumedTruth = assumedTruth;
this.isClauseClassifier = isClauseClassifier;
this.featurizer = featurizer;
// Index edges
this.tree.edgeIterable().forEach(edgeToIndex::addToIndex);
// Get length
List<IndexedWord> sortedVertices = tree.vertexListSorted();
sentenceLength = sortedVertices.get(sortedVertices.size() - 1).index();
// Register extra edges
for (IndexedWord vertex : sortedVertices) {
extraEdgesByGovernor.put(vertex, new ArrayList<>());
extraEdgesByDependent.put(vertex, new ArrayList<>());
}
List<SemanticGraphEdge> extraEdges = Util.cleanTree(this.tree);
assert Util.isTree(this.tree);
for (SemanticGraphEdge edge : extraEdges) {
extraEdgesByGovernor.get(edge.getGovernor()).add(edge);
extraEdgesByDependent.get(edge.getDependent()).add(edge);
}
}
/**
* Prints out all matches of a semgrex pattern on a file of dependencies. <br>
* Usage:<br>
* java edu.stanford.nlp.semgraph.semgrex.SemgrexPattern [args] <br>
* See the help() function for a list of possible arguments to provide.
*/
public static void main(String[] args) throws IOException {
Map<String, Integer> flagMap = Generics.newHashMap();
flagMap.put(PATTERN, 1);
flagMap.put(TREE_FILE, 1);
flagMap.put(MODE, 1);
flagMap.put(EXTRAS, 1);
flagMap.put(CONLLU_FILE, 1);
flagMap.put(OUTPUT_FORMAT_OPTION, 1);
Map<String, String[]> argsMap = StringUtils.argsToMap(args, flagMap);
args = argsMap.get(null);
// TODO: allow patterns to be extracted from a file
if (!(argsMap.containsKey(PATTERN)) || argsMap.get(PATTERN).length == 0) {
help();
System.exit(2);
}
SemgrexPattern semgrex = SemgrexPattern.compile(argsMap.get(PATTERN)[0]);
String modeString = DEFAULT_MODE;
if (argsMap.containsKey(MODE) && argsMap.get(MODE).length > 0) {
modeString = argsMap.get(MODE)[0].toUpperCase();
}
SemanticGraphFactory.Mode mode = SemanticGraphFactory.Mode.valueOf(modeString);
String outputFormatString = DEFAULT_OUTPUT_FORMAT;
if (argsMap.containsKey(OUTPUT_FORMAT_OPTION) && argsMap.get(OUTPUT_FORMAT_OPTION).length > 0) {
outputFormatString = argsMap.get(OUTPUT_FORMAT_OPTION)[0].toUpperCase();
}
OutputFormat outputFormat = OutputFormat.valueOf(outputFormatString);
boolean useExtras = true;
if (argsMap.containsKey(EXTRAS) && argsMap.get(EXTRAS).length > 0) {
useExtras = Boolean.valueOf(argsMap.get(EXTRAS)[0]);
}
List<SemanticGraph> graphs = Generics.newArrayList();
// TODO: allow other sources of graphs, such as dependency files
if (argsMap.containsKey(TREE_FILE) && argsMap.get(TREE_FILE).length > 0) {
for (String treeFile : argsMap.get(TREE_FILE)) {
System.err.println("Loading file " + treeFile);
MemoryTreebank treebank = new MemoryTreebank(new TreeNormalizer());
treebank.loadPath(treeFile);
for (Tree tree : treebank) {
// TODO: allow other languages... this defaults to English
SemanticGraph graph =
SemanticGraphFactory.makeFromTree(
tree,
mode,
useExtras
? GrammaticalStructure.Extras.MAXIMAL
: GrammaticalStructure.Extras.NONE,
true);
graphs.add(graph);
}
}
}
if (argsMap.containsKey(CONLLU_FILE) && argsMap.get(CONLLU_FILE).length > 0) {
CoNLLUDocumentReader reader = new CoNLLUDocumentReader();
for (String conlluFile : argsMap.get(CONLLU_FILE)) {
System.err.println("Loading file " + conlluFile);
Iterator<SemanticGraph> it = reader.getIterator(IOUtils.readerFromString(conlluFile));
while (it.hasNext()) {
SemanticGraph graph = it.next();
graphs.add(graph);
}
}
}
for (SemanticGraph graph : graphs) {
SemgrexMatcher matcher = semgrex.matcher(graph);
if (!(matcher.find())) {
continue;
}
if (outputFormat == OutputFormat.LIST) {
System.err.println("Matched graph:");
System.err.println(graph.toString(SemanticGraph.OutputFormat.LIST));
boolean found = true;
while (found) {
System.err.println(
"Matches at: " + matcher.getMatch().value() + "-" + matcher.getMatch().index());
List<String> nodeNames = Generics.newArrayList();
nodeNames.addAll(matcher.getNodeNames());
Collections.sort(nodeNames);
for (String name : nodeNames) {
System.err.println(
" "
+ name
+ ": "
+ matcher.getNode(name).value()
+ "-"
+ matcher.getNode(name).index());
}
System.err.println();
found = matcher.find();
}
} else if (outputFormat == OutputFormat.OFFSET) {
if (graph.vertexListSorted().isEmpty()) {
continue;
}
System.out.printf(
"+%d %s%n",
graph.vertexListSorted().get(0).get(CoreAnnotations.LineNumberAnnotation.class),
argsMap.get(CONLLU_FILE)[0]);
}
}
}