/**
* Initialise the ANNIE system. This creates a "corpus pipeline" application that can be used to
* run sets of documents through the extraction system.
*/
public void initAnnie() throws GateException, IOException {
Out.prln("Initialising ANNIE...");
// load the ANNIE application from the saved state in plugins/ANNIE
File pluginsHome = Gate.getPluginsHome();
File anniePlugin = new File(pluginsHome, "ANNIE");
File annieGapp = new File(anniePlugin, "ANNIE_with_defaults.gapp");
annieController = (CorpusController) PersistenceManager.loadObjectFromFile(annieGapp);
Out.prln("...ANNIE loaded");
} // initAnnie()
@Override
public Resource init() throws ResourceInstantiationException {
gracefulExit = false;
if (configFileURL == null) {
gracefulExit = true;
gate.util.Err.println("No configuration file provided!");
}
if (japeURL == null) {
gracefulExit = true;
gate.util.Err.println("No JAPE grammar file provided!");
}
// create the init params for the JAPE transducer
FeatureMap params = Factory.newFeatureMap();
params.put(Transducer.TRANSD_GRAMMAR_URL_PARAMETER_NAME, japeURL);
// Code borrowed from Mark Greenwood's Measurements PR
if (japeTransducer == null) {
// if this is the first time we are running init then actually create a
// new transducer as we don't already have one
FeatureMap hidden = Factory.newFeatureMap();
Gate.setHiddenAttribute(hidden, true);
japeTransducer =
(Transducer) Factory.createResource("gate.creole.Transducer", params, hidden);
} else {
// we are being run through a call to reInit so simply re-init the
// underlying JAPE transducer
japeTransducer.setParameterValues(params);
japeTransducer.reInit();
}
ConfigReader config = new ConfigReader(configFileURL);
gracefulExit = config.config();
try {
HashMap<String, String> options = config.getOptions();
patternMap = new HashMap<String, Pattern>();
addSuffixPattern("disease_suffix", options);
addWordPattern("disease_abbrevs", options);
addWordPattern("disease_sense", options);
addWordExtraPattern("disease_sense_context", options);
addPossessiveWordPattern("disease_named_syndrome", options);
addWordExtraPattern("disease_generic_context", options);
addWordExtraPattern("disease_anatomy_context", options);
addSuffixPluralPattern("procedure_suffix", options);
addWordPluralPattern("procedure_key", options);
addWordExtraPattern("procedure_anatomy_context", options);
addWordPluralPattern("symptom_key", options);
addWordPattern("test_key", options);
addSuffixPattern("anatomy_suffix_adjective", options);
addSuffixPattern("anatomy_suffix", options);
addPrefixPattern("anatomy_prefix", options);
addWordPattern("anatomy_position", options);
addWordPluralPattern("anatomy_space_region_junction", options);
addWordPattern("anatomy_part_adjective", options);
addWordPattern("anatomy_latin_noun", options);
addWordPattern("anatomy_muscle", options);
addWordPluralPattern("anatomy_part", options);
addWordPluralPattern("anatomy_fluid", options);
} catch (NullPointerException ne) {
gracefulExit = true;
gate.util.Err.println(
"Missing or unset configuration options. Please check configuration file.");
}
return this;
} // end init()
/**
* 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