/**
* XMLを標準出力する。
*
* @param my_doc XMLの Document Node 。
* @param sortflag ソートするか否か。
*/
public static void output(Document my_doc, boolean sortflag, UDF_Env env) {
try {
if (sortflag) com.udfv.util.UDF_XML.sortDocumentbyEnv(my_doc, env);
OutputFormat format = new OutputFormat(my_doc, "UTF-8", true);
format.setLineWidth(0);
OutputStreamWriter osw = new OutputStreamWriter(System.out, "UTF-8");
XMLSerializer serial = new XMLSerializer(osw, format);
serial.serialize(my_doc.getDocumentElement());
} catch (Exception ex) {
ex.printStackTrace();
}
}
/**
* XMLをファイルに出力する。
*
* @param my_doc XMLの Document Node 。
* @param os 出力先のストリーム。
* @param sortflag ソートするか否か。
*/
public static void output(Document my_doc, OutputStream os, boolean sortflag, UDF_Env env) {
if (sortflag) {
try {
com.udfv.util.UDF_XML.sortDocumentbyEnv(my_doc, env);
} catch (Exception e1) {
e1.printStackTrace();
}
}
try {
OutputFormat format = new OutputFormat(my_doc, "UTF-8", true);
format.setLineWidth(0);
// Writer out = new OutputStreamWriter(new FileOutputStream(file), "UTF-8");
Writer out = new OutputStreamWriter(os, "UTF-8");
XMLSerializer serial = new XMLSerializer(out, format);
serial.serialize(my_doc.getDocumentElement());
out.close();
} catch (Exception e2) {
e2.printStackTrace();
}
}
/**
* エラーリストを XMLとして出力する。
*
* @param el エラーリスト
*/
public static void outputError(UDF_ErrorList el) {
Document doc = UDF_Util.genDocument();
Element root = doc.createElement("udf-error");
for (int i = 0; i < el.getSize(); i++) {
el.getError(i).toXML(doc, root);
}
doc.appendChild(root);
try {
OutputFormat format = new OutputFormat(doc, "UTF-8", true);
format.setLineWidth(0);
OutputStreamWriter osw = new OutputStreamWriter(System.out, "UTF-8");
XMLSerializer serial = new XMLSerializer(osw, format);
serial.serialize(doc.getDocumentElement());
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 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]);
}
}
}