/* * tries to match the unique child of the NodePattern node to a node. * Returns "true" if succeeds. */ private boolean matchChild() { // entering here (given that it's called only once in matches()) // we know finished is false, and either nextChild == null // (meaning goToNextChild has not been called) or nextChild exists // and has a label or backreference that matches if (nextMatch == null) { // I haven't been initialized yet, so my child // certainly can't be matched yet. return false; } if (childMatcher == null) { if (!matchedOnce) { matchedOnce = true; return true; } return false; } // childMatcher.namesToNodes.putAll(this.namesToNodes); // childMatcher.namesToRelations.putAll(this.namesToRelations); boolean match = childMatcher.matches(); if (match) { // namesToNodes.putAll(childMatcher.namesToNodes); // namesToRelations.putAll(childMatcher.namesToRelations); // System.out.println(node.word() + " " + // namesToNodes.get("partnerTwo")); } else { if (nextMatch != null) { decommitVariableGroups(); decommitNamedNodes(); decommitNamedRelations(); } } return match; }
private void resetChild() { if (childMatcher == null) { if (myNode.child == null) { matchedOnce = false; } else { childMatcher = myNode.child.matcher( sg, alignment, sg_aligned, (myNode.reln instanceof GraphRelation.ALIGNMENT) ? !hyp : hyp, nextMatch, namesToNodes, namesToRelations, variableStrings, ignoreCase); } } else { childMatcher.resetChildIter(nextMatch); } }
/** * 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]); } } }