public boolean addSortedExclusive(Annotation annot) {
Annotation currAnot = null;
// overlapping check
for (int i = 0; i < size(); ++i) {
currAnot = (Annotation) get(i);
if (annot.overlaps(currAnot)) {
return false;
} // if
} // for
long annotStart = annot.getStartNode().getOffset().longValue();
long currStart;
// insert
for (int i = 0; i < size(); ++i) {
currAnot = (Annotation) get(i);
currStart = currAnot.getStartNode().getOffset().longValue();
if (annotStart < currStart) {
insertElementAt(annot, i);
/*
Out.prln("Insert start: "+annotStart+" at position: "+i+" size="+size());
Out.prln("Current start: "+currStart);
*/
return true;
} // if
} // for
int size = size();
insertElementAt(annot, size);
// Out.prln("Insert start: "+annotStart+" at size position: "+size);
return true;
} // addSorted
public SeminarDatabase(String filename) throws FileNotFoundException, IOException {
this.filename = filename;
seminars = new HashMap();
BufferedReader reader = new BufferedReader(new FileReader(filename));
String line = reader.readLine();
while (line != null) {
String[] parts = line.split("\t");
String id = parts[0];
int count = (new Integer(parts[1])).intValue();
Vector annotationVector = new Vector();
for (int i = 0; i < count; i++) {
String line2 = reader.readLine();
String[] parts2 = line2.split("\t");
String type = parts2[0];
int offset = (new Integer(parts2[1])).intValue();
int length = (new Integer(parts2[2])).intValue();
Annotation annotation = new Annotation(type, offset, length);
annotation.text = parts2[3];
annotationVector.add(annotation);
}
Annotation[] annotations = (Annotation[]) annotationVector.toArray(new Annotation[0]);
Seminar seminar = new Seminar(annotations);
if (seminars.get(id) == null) {
seminars.put(id, new Vector());
}
((Vector) seminars.get(id)).add(seminar);
line = reader.readLine();
}
}
/** splits document 'doc' into sentences, adding 'sentence' annotations */
static void addSentences(Document doc) {
SpecialZoner.findSpecialZones(doc);
Vector<Annotation> textSegments = doc.annotationsOfType("TEXT");
if (textSegments == null) {
System.out.println("No <TEXT> in document");
return;
}
for (Annotation ann : textSegments) {
Span textSpan = ann.span();
// check document case
Ace.monocase = Ace.allLowerCase(doc);
// split into sentences
SentenceSplitter.split(doc, textSpan);
}
Vector<Annotation> sentences = doc.annotationsOfType("sentence");
if (sentences != null) {
int sentNo = 0;
for (Annotation sentence : sentences) {
sentNo++;
sentence.put("ID", "SENT-" + sentNo);
}
}
doc.removeAnnotationsOfType("dateline");
doc.removeAnnotationsOfType("textBreak");
doc.shrink("sentence");
}
private boolean hasParamAnnotation(Method method) {
Annotation[][] paramAnnotationArrays = method.getParameterAnnotations();
for (Annotation[] paramAnnotations : paramAnnotationArrays)
for (Annotation paramAnnotation : paramAnnotations)
if (paramAnnotation.annotationType().isAssignableFrom(Param.class)) return true;
return false;
}
public static boolean hasAnnotation(Annotation[] anns, Class<? extends Annotation> clazz) {
for (Annotation ann : anns) {
if (clazz == ann.annotationType()) {
return true;
}
}
return false;
}
/**
* train the tagger using the DocumentCollection in file 'trainingCollection'.
* 'trainingCollection' should consist of documents which have been explicitly tagged with
* part-of-speech information.
*/
void train(String trainingCollection) {
for (int i = 0; i < posTable.length; i++)
tagTable[i] = new String[] {"constit", "cat", posTable[i], posTable[i]};
// build ergodic HMM with one state for each POS (plus start and end states)
HMMstate startState = new HMMstate("start", "", WordFeatureHMMemitter.class);
posh.addState(startState);
for (int j = 0; j < posTable.length; j++) startState.addArc(new HMMarc(posTable[j], 0));
HMMstate endState = new HMMstate("end", "", WordFeatureHMMemitter.class);
posh.addState(endState);
for (int i = 0; i < posTable.length; i++) {
String pos = posTable[i];
HMMstate state = new HMMstate(pos, pos, WordFeatureHMMemitter.class);
posh.addState(state);
for (int j = 0; j < posTable.length; j++) state.addArc(new HMMarc(posTable[j], 0));
state.addArc(new HMMarc("end", 0));
}
posh.resolveNames();
posh.resetForTraining();
annotator = new HMMannotator(posh);
annotator.setTagTable(tagTable);
annotator.setBItag(false);
DocumentCollection col = new DocumentCollection(trainingCollection);
col.open();
for (int i = 0; i < col.size(); i++) {
ExternalDocument doc = col.get(i);
doc.open();
System.out.println("Training from " + doc.fileName());
// divide at endmarks (constit cat="."), adding "S" marks
int posn = 0;
int start = posn;
Vector anns;
while ((anns = doc.annotationsAt(posn, "constit")) != null) {
Annotation ann = (Annotation) anns.get(0);
posn = ann.span().end();
String pos = (String) ann.get("cat");
if (pos.equals(".")) {
doc.annotate("S", new Span(start, posn), new FeatureSet());
start = posn;
}
}
annotator.train(doc);
// free up space taken by annotations on document
doc.clearAnnotations();
}
posh.computeProbabilities();
}
/**
* hides (adds the 'hidden' feature) to all annotations of type <I>type</I> beginning at the
* starting position of span <I>span</I>.
*/
public static void hideAnnotations(Document doc, String type, Span span) {
for (int posn = span.start(); posn < span.end(); posn++) {
Vector annotations = doc.annotationsAt(posn, type);
if (annotations != null) {
for (int i = 0; i < annotations.size(); i++) {
Annotation ann = (Annotation) annotations.elementAt(i);
ann.put("hidden", "true");
// Console.println ("Hiding " + ann);
}
}
}
}
static void writeDoc1(Document doc, PrintStream out) throws IOException {
Vector<Annotation> entities = doc.annotationsOfType("entity");
if (entities == null) {
System.err.println("No Entity: " + doc);
return;
}
Iterator<Annotation> entityIt = entities.iterator();
int i = 0;
while (entityIt.hasNext()) {
Annotation entity = entityIt.next();
Vector mentions = (Vector) entity.get("mentions");
Iterator mentionIt = mentions.iterator();
String nameType = (String) entity.get("nameType");
while (mentionIt.hasNext()) {
Annotation mention1 = (Annotation) mentionIt.next();
Annotation mention2 = new Annotation("refobj", mention1.span(), new FeatureSet());
mention2.put("objid", Integer.toString(i));
if (nameType != null) {
mention2.put("netype", nameType);
}
doc.addAnnotation(mention2);
}
i++;
}
// remove other annotations.
String[] annotypes = doc.getAnnotationTypes();
for (i = 0; i < annotypes.length; i++) {
String t = annotypes[i];
if (!(t.equals("tagger") || t.equals("refobj") || t.equals("ENAMEX"))) {
doc.removeAnnotationsOfType(t);
}
}
writeDocRaw(doc, out);
return;
}
private static Vector<Annotation> parseAnnotations(Node parent) throws XmlParserException {
Vector<Annotation> annotations = new Vector<Annotation>();
NodeList nodes = parent.getChildNodes();
for (int nodeid = 0; nodeid < nodes.getLength(); ++nodeid) {
Node node = nodes.item(nodeid);
if (node.getNodeType() != Node.ELEMENT_NODE) continue;
Element element = (Element) node;
if (element.getTagName().equals("annotation")) {
String label = null, value = null, valuetype = null, unit = null;
NodeList annotation_nodes = element.getChildNodes();
for (int annotationid = 0; annotationid < annotation_nodes.getLength(); ++annotationid) {
Node annotation_node = annotation_nodes.item(annotationid);
if (annotation_node.getNodeType() != Node.ELEMENT_NODE) continue;
Element annotation_element = (Element) annotation_node;
if (annotation_element.getTagName().equals("label"))
label = annotation_element.getTextContent();
else if (annotation_element.getTagName().equals("value"))
value = annotation_element.getTextContent();
else if (annotation_element.getTagName().equals("valuetype"))
valuetype = annotation_element.getTextContent();
}
if (label == null || value == null || valuetype == null)
throw new XmlParserException("Annotation is missing either: label, value or valuetype");
Annotation annotation =
new Annotation(label, value, Annotation.ValueType.valueOf(valuetype));
annotation.setUnit(unit);
if (annotation.getValueType() == Annotation.ValueType.ONTOLOGY)
annotation.setOntologyRef(element.getAttribute("ontologyref"));
if (element.getAttribute("unit") != null) annotation.setUnit(element.getAttribute("unit"));
annotations.add(annotation);
}
}
return annotations;
}
protected Annotation parseAnnotation(Reader input, String fileName) throws IOException {
BufferedReader in = new BufferedReader(input);
Annotation ret = new Annotation(fileName);
String line = "";
int lineno = 0;
Matcher matcher = BLAME_PATTERN.matcher(line);
while ((line = in.readLine()) != null) {
++lineno;
matcher.reset(line);
if (matcher.find()) {
String rev = matcher.group(1);
String author = matcher.group(2).trim();
ret.addLine(rev, author, true);
} else {
OpenGrokLogger.getLogger()
.log(
Level.SEVERE,
"Error: did not find annotation in line {0}: [{1}]",
new Object[] {String.valueOf(lineno), line});
}
}
return ret;
}
private void runTest(Annotation annotation) throws IOException {
ByteArrayOutputStream out = new ByteArrayOutputStream();
serializer.write(annotation, out);
byte[] serialized = out.toByteArray();
ByteArrayInputStream in = new ByteArrayInputStream(serialized);
Annotation deserialized = serializer.read(in).first();
assertEquals(
annotation.get(CoreAnnotations.SentencesAnnotation.class).size(),
deserialized.get(CoreAnnotations.SentencesAnnotation.class).size());
for (int i = 0; i < annotation.get(CoreAnnotations.SentencesAnnotation.class).size(); ++i) {
verifySentence(
annotation.get(CoreAnnotations.SentencesAnnotation.class).get(i),
deserialized.get(CoreAnnotations.SentencesAnnotation.class).get(i));
}
}
@Override
public void handle(HttpExchange httpExchange) throws IOException {
// Set common response headers
httpExchange.getResponseHeaders().add("Access-Control-Allow-Origin", "*");
Future<String> json =
corenlpExecutor.submit(
() -> {
try {
// Get the document
Properties props =
new Properties() {
{
setProperty("annotators", "tokenize,ssplit,pos,lemma,ner,depparse");
}
};
Annotation doc = getDocument(props, httpExchange);
if (!doc.containsKey(CoreAnnotations.SentencesAnnotation.class)) {
StanfordCoreNLP pipeline = mkStanfordCoreNLP(props);
pipeline.annotate(doc);
}
// Construct the matcher
Map<String, String> params = getURLParams(httpExchange.getRequestURI());
// (get the pattern)
if (!params.containsKey("pattern")) {
respondError("Missing required parameter 'pattern'", httpExchange);
return "";
}
String pattern = params.get("pattern");
// (get whether to filter / find)
String filterStr = params.getOrDefault("filter", "false");
final boolean filter =
filterStr.trim().isEmpty()
|| "true".equalsIgnoreCase(filterStr.toLowerCase());
// (create the matcher)
final SemgrexPattern regex = SemgrexPattern.compile(pattern);
// Run TokensRegex
return JSONOutputter.JSONWriter.objectToJSON(
(docWriter) -> {
if (filter) {
// Case: just filter sentences
docWriter.set(
"sentences",
doc.get(CoreAnnotations.SentencesAnnotation.class)
.stream()
.map(
sentence ->
regex
.matcher(
sentence.get(
SemanticGraphCoreAnnotations
.CollapsedCCProcessedDependenciesAnnotation
.class))
.matches())
.collect(Collectors.toList()));
} else {
// Case: find matches
docWriter.set(
"sentences",
doc.get(CoreAnnotations.SentencesAnnotation.class)
.stream()
.map(
sentence ->
(Consumer<JSONOutputter.Writer>)
(JSONOutputter.Writer sentWriter) -> {
SemgrexMatcher matcher =
regex.matcher(
sentence.get(
SemanticGraphCoreAnnotations
.CollapsedCCProcessedDependenciesAnnotation
.class));
int i = 0;
while (matcher.find()) {
sentWriter.set(
Integer.toString(i),
(Consumer<JSONOutputter.Writer>)
(JSONOutputter.Writer matchWriter) -> {
IndexedWord match = matcher.getMatch();
matchWriter.set("text", match.word());
matchWriter.set(
"begin", match.index() - 1);
matchWriter.set("end", match.index());
for (String capture :
matcher.getNodeNames()) {
matchWriter.set(
"$" + capture,
(Consumer<JSONOutputter.Writer>)
groupWriter -> {
IndexedWord node =
matcher.getNode(
capture);
groupWriter.set(
"text", node.word());
groupWriter.set(
"begin",
node.index() - 1);
groupWriter.set(
"end", node.index());
});
}
});
i += 1;
}
sentWriter.set("length", i);
}));
}
});
} catch (Exception e) {
e.printStackTrace();
try {
respondError(e.getClass().getName() + ": " + e.getMessage(), httpExchange);
} catch (IOException ignored) {
}
}
return "";
});
// Send response
byte[] response = new byte[0];
try {
response = json.get(5, TimeUnit.SECONDS).getBytes();
} catch (InterruptedException | ExecutionException | TimeoutException e) {
respondError("Timeout when executing Semgrex query", httpExchange);
}
if (response.length > 0) {
httpExchange.getResponseHeaders().add("Content-Type", "text/json");
httpExchange.getResponseHeaders().add("Content-Length", Integer.toString(response.length));
httpExchange.sendResponseHeaders(HTTP_OK, response.length);
httpExchange.getResponseBody().write(response);
httpExchange.close();
}
}
@Override
public void handle(HttpExchange httpExchange) throws IOException {
// Set common response headers
httpExchange.getResponseHeaders().add("Access-Control-Allow-Origin", "*");
// Get sentence.
Properties props;
Annotation ann;
StanfordCoreNLP.OutputFormat of;
log("[" + httpExchange.getRemoteAddress() + "] Received message");
try {
props = getProperties(httpExchange);
ann = getDocument(props, httpExchange);
of =
StanfordCoreNLP.OutputFormat.valueOf(
props.getProperty("outputFormat", "json").toUpperCase());
// Handle direct browser connections (i.e., not a POST request).
if (ann.get(CoreAnnotations.TextAnnotation.class).length() == 0) {
log("[" + httpExchange.getRemoteAddress() + "] Interactive connection");
staticPageHandle.handle(httpExchange);
return;
}
log("[" + httpExchange.getRemoteAddress() + "] API call");
} catch (Exception e) {
// Return error message.
e.printStackTrace();
String response = e.getMessage();
httpExchange.getResponseHeaders().add("Content-Type", "text/plain");
httpExchange.sendResponseHeaders(HTTP_BAD_INPUT, response.length());
httpExchange.getResponseBody().write(response.getBytes());
httpExchange.close();
return;
}
try {
// Annotate
StanfordCoreNLP pipeline = mkStanfordCoreNLP(props);
Future<Annotation> completedAnnotationFuture =
corenlpExecutor.submit(
() -> {
pipeline.annotate(ann);
return ann;
});
Annotation completedAnnotation = completedAnnotationFuture.get(5, TimeUnit.SECONDS);
// Get output
ByteArrayOutputStream os = new ByteArrayOutputStream();
StanfordCoreNLP.createOutputter(props, AnnotationOutputter.getOptions(pipeline))
.accept(completedAnnotation, os);
os.close();
byte[] response = os.toByteArray();
httpExchange.getResponseHeaders().add("Content-Type", getContentType(props, of));
httpExchange.getResponseHeaders().add("Content-Length", Integer.toString(response.length));
httpExchange.sendResponseHeaders(HTTP_OK, response.length);
httpExchange.getResponseBody().write(response);
httpExchange.close();
} catch (TimeoutException e) {
respondError("CoreNLP request timed out", httpExchange);
} catch (Exception e) {
// Return error message.
respondError(e.getClass().getName() + ": " + e.getMessage(), httpExchange);
}
}
public static void main(String[] args) {
if (args.length != 2) {
System.out.println(
"This program expects two parameters: \n"
+ "1. Input predicted genes XML filename \n"
+ "2. Output GFF filename\n");
} else {
String inFileString = args[0];
String outFileString = args[1];
File inFile = new File(inFileString);
File outFile = new File(outFileString);
try {
BufferedWriter outBuff = new BufferedWriter(new FileWriter(outFile));
// writing header first
outBuff.write(GFF_HEADER + "\n");
Date currentDate = new Date();
outBuff.write(DATE_HEADER + currentDate.toString() + "\n");
outBuff.write(TYPE_HEADER + "\n");
BufferedReader reader = new BufferedReader(new FileReader(inFile));
String tempSt;
StringBuilder stBuilder = new StringBuilder();
while ((tempSt = reader.readLine()) != null) {
stBuilder.append(tempSt);
}
// closing input file reader
reader.close();
Annotation annotation = new Annotation(stBuilder.toString());
HashMap<String, TreeSet<GffLine>> linesPerContig = new HashMap<String, TreeSet<GffLine>>();
// -----------POTATIZING GENES----------------
List<Element> contigsGenes =
annotation
.asJDomElement()
.getChild(PredictedGenes.TAG_NAME)
.getChildren(ContigXML.TAG_NAME);
for (Element element : contigsGenes) {
ContigXML contig = new ContigXML(element);
TreeSet<GffLine> lines = new TreeSet<GffLine>();
linesPerContig.put(contig.getId(), lines);
List<XMLElement> genes = contig.getChildrenWith(PredictedGene.TAG_NAME);
for (XMLElement xMLElement : genes) {
PredictedGene gene = new PredictedGene(xMLElement.asJDomElement());
String geneLine =
contig.getId() + SEPARATOR + CHORIZO_GEN + SEPARATOR + GENE + SEPARATOR;
int beginPos = gene.getStartPosition();
int endPos = gene.getEndPosition();
int initPos = beginPos;
if (beginPos < endPos) {
geneLine += beginPos + SEPARATOR + endPos + SEPARATOR;
} else {
geneLine += endPos + SEPARATOR + beginPos + SEPARATOR;
initPos = endPos;
}
geneLine +=
gene.getEvalue()
+ SEPARATOR
+ gene.getStrand()
+ SEPARATOR
+ "."
+ SEPARATOR
+ LOCUS_TAG
+ gene.getId()
+ ";\n";
lines.add(new GffLine(initPos, geneLine));
// outBuff.write(geneLine);
String cdsLine = contig.getId() + SEPARATOR + CHORIZO_GEN + SEPARATOR + CDS + SEPARATOR;
if (gene.getStrand().equals(PredictedGene.POSITIVE_STRAND)) {
cdsLine +=
gene.getStartPosition() + SEPARATOR + (gene.getEndPosition() - 3) + SEPARATOR;
} else {
cdsLine +=
(gene.getEndPosition() - 3) + SEPARATOR + gene.getStartPosition() + SEPARATOR;
}
cdsLine +=
gene.getEvalue() + SEPARATOR + gene.getStrand() + SEPARATOR + "0" + SEPARATOR;
cdsLine +=
LOCUS_TAG
+ gene.getId()
+ ";"
+ PRODUCT
+ gene.getProteinNames()
+ ";"
+ CHORIZO_INFERENCE
+ gene.getAccession()
+ "\n";
// outBuff.write(cdsLine);
lines.add(new GffLine(initPos, cdsLine));
String startCodonLine =
contig.getId() + SEPARATOR + CHORIZO_GEN + SEPARATOR + START_CODON + SEPARATOR;
if (gene.getStrand().equals(PredictedGene.POSITIVE_STRAND)) {
startCodonLine +=
gene.getStartPosition() + SEPARATOR + (gene.getStartPosition() + 2) + SEPARATOR;
} else {
startCodonLine +=
(gene.getStartPosition() - 2) + SEPARATOR + gene.getStartPosition() + SEPARATOR;
}
startCodonLine +=
gene.getEvalue()
+ SEPARATOR
+ gene.getStrand()
+ SEPARATOR
+ "0"
+ SEPARATOR
+ LOCUS_TAG
+ gene.getId()
+ ";";
startCodonLine +=
PRODUCT
+ gene.getProteinNames()
+ ";"
+ CHORIZO_INFERENCE
+ gene.getAccession()
+ "\n";
// outBuff.write(startCodonLine);
lines.add(new GffLine(initPos, startCodonLine));
String stopCodonLine =
contig.getId() + SEPARATOR + CHORIZO_GEN + SEPARATOR + STOP_CODON + SEPARATOR;
if (gene.getStrand().equals(PredictedGene.POSITIVE_STRAND)) {
stopCodonLine +=
(gene.getEndPosition() + 1) + SEPARATOR + (gene.getEndPosition() + 3) + SEPARATOR;
} else {
stopCodonLine +=
(gene.getEndPosition() - 3) + SEPARATOR + (gene.getEndPosition() - 1) + SEPARATOR;
}
stopCodonLine +=
gene.getEvalue()
+ SEPARATOR
+ gene.getStrand()
+ SEPARATOR
+ "0"
+ SEPARATOR
+ LOCUS_TAG
+ gene.getId()
+ ";";
stopCodonLine +=
PRODUCT
+ gene.getProteinNames()
+ ";"
+ CHORIZO_INFERENCE
+ gene.getAccession()
+ "\n";
// outBuff.write(stopCodonLine);
lines.add(new GffLine(initPos, stopCodonLine));
}
}
// -----------POTATIZING RNAS-----------------
List<Element> contigsRnas =
annotation
.asJDomElement()
.getChild(PredictedRnas.TAG_NAME)
.getChildren(ContigXML.TAG_NAME);
for (Element element : contigsRnas) {
ContigXML contig = new ContigXML(element);
List<XMLElement> rnas = contig.getChildrenWith(PredictedRna.TAG_NAME);
TreeSet<GffLine> lines = linesPerContig.get(contig.getId());
if (lines == null) {
lines = new TreeSet<GffLine>();
linesPerContig.put(contig.getId(), lines);
}
for (XMLElement xMLElement : rnas) {
PredictedRna rna = new PredictedRna(xMLElement.asJDomElement());
String rnaLine = contig.getId() + SEPARATOR + CHORIZO_RNA + SEPARATOR + RNA + SEPARATOR;
int beginPos = rna.getStartPosition();
int endPos = rna.getEndPosition();
int initPos = beginPos;
if (beginPos < endPos) {
rnaLine += beginPos + SEPARATOR + endPos + SEPARATOR;
} else {
rnaLine += endPos + SEPARATOR + beginPos + SEPARATOR;
initPos = endPos;
}
rnaLine +=
rna.getEvalue()
+ SEPARATOR
+ rna.getStrand()
+ SEPARATOR
+ "."
+ SEPARATOR
+ LOCUS_TAG
+ rna.getId()
+ ";";
String columns[] = rna.getAnnotationUniprotId().split("\\|");
String rnaProduct = columns[3];
String refSeqId = columns[1];
String positions = columns[2].substring(1);
// ref|NC_007413|:3894075-3895562|16S ribosomal RNA| [locus_tag=Ava_R0035]
rnaLine +=
PRODUCT + rnaProduct + "," + "rna:RefSeq:" + refSeqId + " " + positions + "\n";
// outBuff.write(rnaLine);
lines.add(new GffLine(initPos, rnaLine));
}
}
Set<String> keys = linesPerContig.keySet();
for (String key : keys) {
TreeSet<GffLine> lines = linesPerContig.get(key);
GffLine line = lines.pollFirst();
while (line != null) {
outBuff.write(line.getLine());
line = lines.pollFirst();
}
}
outBuff.close();
System.out.println("Done!!! :D");
} catch (Exception e) {
e.printStackTrace();
}
}
}
/**
* Run from the command-line, with a list of URLs as argument.
*
* <p><B>NOTE:</B><br>
* This code will run with all the documents in memory - if you want to unload each from memory
* after use, add code to store the corpus in a DataStore.
*/
public static void main(String args[]) throws GateException, IOException {
// initialise the GATE library
Out.prln("Initialising GATE...");
Gate.init();
Out.prln("...GATE initialised");
// initialise ANNIE (this may take several minutes)
StandAloneAnnie annie = new StandAloneAnnie();
annie.initAnnie();
// create a GATE corpus and add a document for each command-line
// argument
Corpus corpus = Factory.newCorpus("StandAloneAnnie corpus");
for (int i = 0; i < args.length; i++) {
URL u = new URL(args[i]);
FeatureMap params = Factory.newFeatureMap();
params.put("sourceUrl", u);
params.put("preserveOriginalContent", new Boolean(true));
params.put("collectRepositioningInfo", new Boolean(true));
Out.prln("Creating doc for " + u);
Document doc = (Document) Factory.createResource("gate.corpora.DocumentImpl", params);
corpus.add(doc);
} // for each of args
// tell the pipeline about the corpus and run it
annie.setCorpus(corpus);
annie.execute();
// for each document, get an XML document with the
// person and location names added
Iterator iter = corpus.iterator();
int count = 0;
String startTagPart_1 = "<span GateID=\"";
String startTagPart_2 = "\" title=\"";
String startTagPart_3 = "\" style=\"background:Red;\">";
String endTag = "</span>";
while (iter.hasNext()) {
Document doc = (Document) iter.next();
AnnotationSet defaultAnnotSet = doc.getAnnotations();
Set annotTypesRequired = new HashSet();
annotTypesRequired.add("Person");
annotTypesRequired.add("Location");
Set<Annotation> peopleAndPlaces =
new HashSet<Annotation>(defaultAnnotSet.get(annotTypesRequired));
FeatureMap features = doc.getFeatures();
String originalContent =
(String) features.get(GateConstants.ORIGINAL_DOCUMENT_CONTENT_FEATURE_NAME);
RepositioningInfo info =
(RepositioningInfo) features.get(GateConstants.DOCUMENT_REPOSITIONING_INFO_FEATURE_NAME);
++count;
File file = new File("StANNIE_" + count + ".HTML");
Out.prln("File name: '" + file.getAbsolutePath() + "'");
if (originalContent != null && info != null) {
Out.prln("OrigContent and reposInfo existing. Generate file...");
Iterator it = peopleAndPlaces.iterator();
Annotation currAnnot;
SortedAnnotationList sortedAnnotations = new SortedAnnotationList();
while (it.hasNext()) {
currAnnot = (Annotation) it.next();
sortedAnnotations.addSortedExclusive(currAnnot);
} // while
StringBuffer editableContent = new StringBuffer(originalContent);
long insertPositionEnd;
long insertPositionStart;
// insert anotation tags backward
Out.prln("Unsorted annotations count: " + peopleAndPlaces.size());
Out.prln("Sorted annotations count: " + sortedAnnotations.size());
for (int i = sortedAnnotations.size() - 1; i >= 0; --i) {
currAnnot = (Annotation) sortedAnnotations.get(i);
insertPositionStart = currAnnot.getStartNode().getOffset().longValue();
insertPositionStart = info.getOriginalPos(insertPositionStart);
insertPositionEnd = currAnnot.getEndNode().getOffset().longValue();
insertPositionEnd = info.getOriginalPos(insertPositionEnd, true);
if (insertPositionEnd != -1 && insertPositionStart != -1) {
editableContent.insert((int) insertPositionEnd, endTag);
editableContent.insert((int) insertPositionStart, startTagPart_3);
editableContent.insert((int) insertPositionStart, currAnnot.getType());
editableContent.insert((int) insertPositionStart, startTagPart_2);
editableContent.insert((int) insertPositionStart, currAnnot.getId().toString());
editableContent.insert((int) insertPositionStart, startTagPart_1);
} // if
} // for
FileWriter writer = new FileWriter(file);
writer.write(editableContent.toString());
writer.close();
} // if - should generate
else if (originalContent != null) {
Out.prln("OrigContent existing. Generate file...");
Iterator it = peopleAndPlaces.iterator();
Annotation currAnnot;
SortedAnnotationList sortedAnnotations = new SortedAnnotationList();
while (it.hasNext()) {
currAnnot = (Annotation) it.next();
sortedAnnotations.addSortedExclusive(currAnnot);
} // while
StringBuffer editableContent = new StringBuffer(originalContent);
long insertPositionEnd;
long insertPositionStart;
// insert anotation tags backward
Out.prln("Unsorted annotations count: " + peopleAndPlaces.size());
Out.prln("Sorted annotations count: " + sortedAnnotations.size());
for (int i = sortedAnnotations.size() - 1; i >= 0; --i) {
currAnnot = (Annotation) sortedAnnotations.get(i);
insertPositionStart = currAnnot.getStartNode().getOffset().longValue();
insertPositionEnd = currAnnot.getEndNode().getOffset().longValue();
if (insertPositionEnd != -1 && insertPositionStart != -1) {
editableContent.insert((int) insertPositionEnd, endTag);
editableContent.insert((int) insertPositionStart, startTagPart_3);
editableContent.insert((int) insertPositionStart, currAnnot.getType());
editableContent.insert((int) insertPositionStart, startTagPart_2);
editableContent.insert((int) insertPositionStart, currAnnot.getId().toString());
editableContent.insert((int) insertPositionStart, startTagPart_1);
} // if
} // for
FileWriter writer = new FileWriter(file);
writer.write(editableContent.toString());
writer.close();
} else {
Out.prln("Content : " + originalContent);
Out.prln("Repositioning: " + info);
}
String xmlDocument = doc.toXml(peopleAndPlaces, false);
String fileName = new String("StANNIE_toXML_" + count + ".HTML");
FileWriter writer = new FileWriter(fileName);
writer.write(xmlDocument);
writer.close();
} // for each doc
} // main