Example usage for org.apache.commons.lang StringUtils normalizeSpace

Introduction

In this page you can find the example usage for org.apache.commons.lang StringUtils normalizeSpace.

Prototype

public static String normalizeSpace(String str) 

Source Link

Document

<p> Similar to <a href="http://www.w3.org/TR/xpath/#function-normalize-space"> http://www.w3.org/TR/xpath/#function-normalize -space</a> </p> <p> The function returns the argument string with whitespace normalized by using <code> #trim(String) </code> to remove leading and trailing whitespace and then replacing sequences of whitespace characters by a single space.

Usage

From source file:de.tudarmstadt.ukp.csniper.resbuild.stuff.CasFlusher.java

@Override
public void process(CAS aCas) throws AnalysisEngineProcessException {
    try {/*w  w  w .ja va  2  s .  co m*/
        int aBegin = 112715;//98877;
        int aEnd = 112734;//98993;
        OutputStream aOutputStream = System.out;

        Collection<? extends Annotation> annos;
        annos = JCasUtil.select(aCas.getJCas(), Sentence.class);
        Annotation a = new ArrayList<Annotation>(annos).get(92);
        aBegin = a.getBegin();
        aEnd = a.getEnd();
        if (aBegin > -1 && aEnd > -1) {
            annos = JCasUtil.selectCovered(aCas.getJCas(), Annotation.class, aBegin, aEnd);
        } else {
            annos = JCasUtil.select(aCas.getJCas(), Annotation.class);
        }
        for (Annotation anno : annos) {
            StringBuilder sb = new StringBuilder();
            sb.append("[" + anno.getClass().getSimpleName() + "] ");
            sb.append("(" + anno.getBegin() + "," + anno.getEnd() + ") ");
            sb.append(anno.getCoveredText() + "\n");
            try {
                IOUtils.write(sb, aOutputStream, "UTF-8");
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        for (PennTree pt : JCasUtil.selectCovered(aCas.getJCas(), PennTree.class, aBegin, aEnd)) {
            IOUtils.write(StringUtils.normalizeSpace(pt.getPennTree()), aOutputStream, "UTF-8");
        }
    } catch (CASException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

---

From source file:com.bahmanm.karun.PackageCollection.java

/**
 * Reads package information from a package directory.
 * //from w w w. j a  v a 2s .co  m
 * @param pkgDir Package directory
 * @return Package
 */
private Package readPackage(File pkgDir) throws FileNotFoundException, IOException {
    File f = new File(pkgDir.getAbsolutePath() + "/desc");
    FileInputStream fis = new FileInputStream(f);
    DataInputStream dis = new DataInputStream(fis);
    BufferedReader br = new BufferedReader(new InputStreamReader(dis));
    String line = null;
    Package pkg = new Package();
    try {
        boolean name = false;
        boolean desc = false;
        boolean version = false;
        while ((line = br.readLine()) != null) {
            line = StringUtils.normalizeSpace(line);
            if (line.equals("%NAME%")) {
                name = name ? false : true;
            } else if (line.equals("%VERSION%")) {
                version = version ? false : true;
            } else if (line.equals("%DESC%")) {
                desc = desc ? false : true;
            } else if (name) {
                pkg.setName(line);
                name = false;
            } else if (version) {
                pkg.setRepoVersion(line);
                version = false;
            } else if (desc) {
                pkg.setDescription(line);
                desc = false;
            }
        }
    } catch (IOException ex) {
        Logger.getLogger(PackageCollection.class.getName()).log(Level.SEVERE, null, ex);
    } finally {
        try {
            br.close();
            dis.close();
            fis.close();
        } catch (IOException ioex) {
            throw new IOException("Error closing stream or reader: " + ioex.getMessage());
        }
    }
    return pkg;
}

---

From source file:de.tudarmstadt.ukp.csniper.webapp.evaluation.MlPipeline.java

public void classify(File aModelDir, List<EvaluationResult> aToPredictList) throws IOException, UIMAException {
    TKSVMlightSequenceClassifierBuilder builder = new TKSVMlightSequenceClassifierBuilder();
    TKSVMlightSequenceClassifier classifier = builder.loadClassifierFromTrainingDirectory(aModelDir);
    File cFile = File.createTempFile("tkclassify", ".txt");

    BufferedWriter bw = null;/*from   ww w  .  j  a  va2  s.c o m*/
    try {
        bw = new BufferedWriter(new FileWriter(cFile));

        // predict unclassified
        CAS cas = CasCreationUtils.createCas(createTypeSystemDescription(), null, null);
        ProgressMeter progress = new ProgressMeter(aToPredictList.size());
        for (EvaluationResult result : aToPredictList) {
            cas.setDocumentText(result.getItem().getCoveredText());
            cas.setDocumentLanguage(language);

            // dummy sentence split
            sent.process(cas);

            // tokenize
            tok.process(cas);

            // get parse from db, or parse now
            String pennTree = parse(result, cas);

            // write tree to file
            Feature tree = new Feature("TK_tree", StringUtils.normalizeSpace(pennTree));
            TreeFeatureVector tfv = classifier.getFeaturesEncoder().encodeAll(Arrays.asList(tree));
            try {
                bw.write("0");
                bw.write(TKSVMlightDataWriter.createString(tfv));
                bw.write(SystemUtils.LINE_SEPARATOR);
            } catch (IOException e) {
                throw new AnalysisEngineProcessException(e);
            }
            cas.reset();
            progress.next();
            LOG.info(progress);
            if (task != null) {
                task.increment();
                task.checkCanceled();
            }
        }
    } finally {
        IOUtils.closeQuietly(bw);
    }

    // classify all
    List<Double> predictions = classifier.tkSvmLightPredict2(cFile);

    if (predictions.size() != aToPredictList.size()) {
        // TODO throw different exception instead
        throw new IOException("there are [" + predictions.size() + "] predictions, but ["
                + aToPredictList.size() + "] were expected.");
    }

    for (int i = 0; i < aToPredictList.size(); i++) {
        Mark m = (predictions.get(i) > THRESHOLD) ? Mark.PRED_CORRECT : Mark.PRED_WRONG;
        aToPredictList.get(i).setResult(m.getTitle());
    }
}

---

From source file:com.haulmont.cuba.web.gui.WebWindow.java

@Override
public String getStyleName() {
    return StringUtils.normalizeSpace(component.getStyleName().replace(C_WINDOW_LAYOUT, ""));
}

---

From source file:com.haulmont.cuba.web.gui.components.WebGroupBox.java

@Override
public String getStyleName() {
    return StringUtils.normalizeSpace(super.getStyleName().replace(GROUPBOX_PANEL_STYLENAME, ""));
}

---

From source file:de.tudarmstadt.ukp.csniper.webapp.evaluation.MlPipeline.java

public static File train(List<EvaluationResult> aTrainingList, EvaluationRepository aRepository)
        throws IOException, CleartkProcessingException {
    File modelDir = Files.createTempDir();
    DefaultTKSVMlightDataWriterFactory dataWriterFactory = new DefaultTKSVMlightDataWriterFactory();
    dataWriterFactory.setOutputDirectory(modelDir);
    DataWriter<Boolean> dataWriter = dataWriterFactory.createDataWriter();

    for (EvaluationResult result : aTrainingList) {
        CachedParse cp = aRepository.getCachedParse(result.getItem());
        if (cp == null || cp.getPennTree().isEmpty() || "ERROR".equals(cp.getPennTree())) {
            System.out.println("Unable to parse: [" + result.getItem().getCoveredText() + "] (cached)");
            continue;
        }/*from   w ww.j  a v a  2  s .  c  om*/

        Instance<Boolean> instance = new Instance<Boolean>();
        instance.add(new Feature("TK_tree", StringUtils.normalizeSpace(cp.getPennTree())));
        instance.setOutcome(Mark.fromString(result.getResult()) == Mark.CORRECT);
        dataWriter.write(instance);
    }

    dataWriter.finish();

    // train model
    try {
        Train.main(modelDir.getPath(), "-t", "5", "-c", "1.0", "-C", "+");
    } catch (Exception e) {
        throw new CleartkProcessingException(e);
    }

    return modelDir;
}

---

From source file:de.fhg.iais.cortex.services.ingest.worker.IndexerWorker.java

private void addPreviewToIndexAndStore(IIngestContext context, IIndexerDocument document) throws JAXBException {
    if (context.getAipObject().isNewFormat()) {
        Preview preview = context.getAipObject()
                .getObjectForPathOrNull(NewSchemaPaths.PATH_CORTEX_ITEM_PREVIEW.path(), Preview.class);

        String subtitle = preview.getSubtitle();
        if (!Strings.isNullOrEmpty(subtitle)) {
            document.addPreview(subtitle);
        }//from   w  ww .j av  a  2 s .c  o  m

        String title = preview.getTitle();
        document.storePreview(XmlProcessor.marshallToString(this.OBJECT_FACTORY.createPreview(preview)), title);
    } else {

        CortexItemPreview preview = context.getAipObject().getObjectForPathOrNull(
                OldSchemaPaths.PATH_CORTEX_ITEM_PREVIEW.path(), CortexItemPreview.class);

        String title = "";
        for (PreviewDiv.Div div : preview.getDiv().getDiv()) {
            if (div.getClazz().equals("subtitle")) {
                for (Serializable content : div.getContent()) {
                    if (content instanceof String) {
                        document.addPreview(StringUtils.normalizeSpace((String) content));
                    }
                }
            } else if (div.getClazz().equals("title")) {
                for (Serializable content : div.getContent()) {
                    if (content instanceof String) {
                        title += ((String) content).trim();
                    }
                }
            }
        }
        document.storePreview(
                XmlProcessor.marshallToString(this.OBJECT_FACTORY.createCortexItemPreview(preview)), title);
    }
}

---

From source file:de.fhg.iais.cortex.services.ingest.worker.IndexerWorker.java

private void addViewToIndex(IIngestContext context, IIndexerDocument document) throws JAXBException {

    AipObject aipObject = context.getAipObject();
    if (aipObject.isNewFormat()) {
        String institutionName = aipObject.getObjectForPathOrNull(
                NewSchemaPaths.PATH_CORTEX_ITEM_VIEW_ITEM_INSTITUTION_NAME.path(), String.class);
        if (!Strings.isNullOrEmpty(institutionName)) {
            document.addInstitutionName(institutionName);
        }/*from www.ja v a  2s.  com*/

        String rights = aipObject
                .getObjectForPathOrNull(NewSchemaPaths.PATH_CORTEX_ITEM_VIEW_ITEM_RIGHTS.path(), String.class);
        if (!Strings.isNullOrEmpty(rights)) {
            document.addView(StringUtils.normalizeSpace(rights));
        }

        Iterator<NewItemPropertyField> displayFields = aipObject.getIteratorForPath(
                NewSchemaPaths.PATH_CORTEX_ITEM_VIEW_ITEM_FIELDS_DISPLAY.path(), NewItemPropertyField.class);

        addFieldsFromView(document, displayFields);

        Iterator<NewItemPropertyField> extendedFields = aipObject.getIteratorForPath(
                NewSchemaPaths.PATH_CORTEX_ITEM_VIEW_ITEM_FIELDS_EXTENDED_DISPLAY.path(),
                NewItemPropertyField.class);
        addFieldsFromView(document, extendedFields);

        Cortex aip = aipObject.getAip();
        if (aip != null) {
            View view = aip.getView();
            if (view != null) {
                ViewInstitution institution = view.getCortexInstitution();
                if (institution != null) {
                    ViewInstitution.Locations locations = institution.getLocations();
                    if (locations != null) {
                        for (ViewInstitution.Locations.Location location : locations.getLocation()) {
                            Address institutionAddress = location.getAddress();
                            if (institutionAddress != null) {
                                document.addView(institutionAddress.getStreet());
                                document.addView(institutionAddress.getHouseIdentifier());
                                document.addView(institutionAddress.getAddressSupplement());
                                document.addView(institutionAddress.getPostalCode());
                                document.addView(institutionAddress.getCity());
                                document.addView(institutionAddress.getCountry());
                            }
                            String locationDisplayName = location.getLocationDisplayName();
                            if (!Strings.isNullOrEmpty(locationDisplayName)) {
                                document.addLocationDisplayName(locationDisplayName);
                            }
                        }
                    }
                }
            }
        }
    } else {
        String institutionName = aipObject.getObjectForPathOrNull(
                OldSchemaPaths.PATH_CORTEX_ITEM_VIEW_ITEM_INSTITUTION_NAME.path(), String.class);
        if (!Strings.isNullOrEmpty(institutionName)) {
            document.addInstitutionName(institutionName);
        }

        HtmlSnippet rights = aipObject.getObjectForPathOrNull(
                OldSchemaPaths.PATH_CORTEX_ITEM_VIEW_ITEM_RIGHTS.path(), HtmlSnippet.class);
        if (rights != null) {
            for (Serializable content : rights.getContent()) {
                if (content instanceof String) {
                    document.addView(StringUtils.normalizeSpace((String) content));
                }
            }
        }

        Iterator<ItemPropertyField> fields = aipObject.getIteratorForPath(
                OldSchemaPaths.PATH_CORTEX_ITEM_VIEW_ITEM_FIELDS.path(), ItemPropertyField.class);

        while (fields.hasNext()) {
            ItemPropertyField field = fields.next();
            for (Serializable content : field.getValue().getContent()) {
                if (content instanceof JAXBElement) {
                    JAXBElement<?> element = (JAXBElement<?>) content;
                    if (element.getValue() instanceof ItemPropertyField.Value.A) {
                        String normalizedLink = normalizeLink((A) element.getValue());
                        if (!Strings.isNullOrEmpty(normalizedLink)) {
                            document.addView(normalizedLink);
                        }
                    }
                } else if (content instanceof String) {
                    String contentAsString = StringUtils.normalizeSpace((String) content);
                    if (!Strings.isNullOrEmpty(contentAsString)) {
                        document.addView(contentAsString);
                    }
                }
            }
        }

        Address institutionAddress = aipObject.getObjectForPathOrNull(
                OldSchemaPaths.PATH_CORTEX_ITEM_VIEW_INSTITUTION_ADDRESS.path(), Address.class);

        if (institutionAddress != null) {
            document.addView(institutionAddress.getStreet());
            document.addView(institutionAddress.getHouseIdentifier());
            document.addView(institutionAddress.getAddressSupplement());
            document.addView(institutionAddress.getPostalCode());
            document.addView(institutionAddress.getCity());
            document.addView(institutionAddress.getCountry());
        }

    }
}

---

From source file:de.tudarmstadt.ukp.csniper.webapp.evaluation.MlPipeline.java

/**
 * Mind this method may return less results than parses were passed to it, e.g. because a 
 * cached parse may be empty or "ERROR" in which case no result for it is generated!
 *//*  www.  ja  v a  2  s. c o  m*/
public static List<EvaluationResult> classifyPreParsed(File aModelDir, List<CachedParse> aParses, String aType,
        String aUser) throws IOException, UIMAException {
    TKSVMlightSequenceClassifierBuilder builder = new TKSVMlightSequenceClassifierBuilder();
    TKSVMlightSequenceClassifier classifier = builder.loadClassifierFromTrainingDirectory(aModelDir);
    File cFile = File.createTempFile("tkclassify", ".txt");

    List<EvaluationItem> items = new ArrayList<EvaluationItem>();
    BufferedWriter bw = null;
    try {
        bw = new BufferedWriter(new FileWriter(cFile));

        for (CachedParse parse : aParses) {
            if (parse.getPennTree().isEmpty() || "ERROR".equals(parse.getPennTree())) {
                continue;
            }

            String coveredText;
            try {
                coveredText = PennTreeUtils.toText(parse.getPennTree());
            } catch (EmptyStackException e) {
                LOG.error("Invalid Penn Tree: [" + parse.getPennTree() + "]", e);
                continue;
            }

            // Prepare evaluation item to return
            EvaluationItem item = new EvaluationItem();
            item.setType(aType);
            item.setBeginOffset(parse.getBeginOffset());
            item.setEndOffset(parse.getEndOffset());
            item.setDocumentId(parse.getDocumentId());
            item.setCollectionId(parse.getCollectionId());
            item.setCoveredText(coveredText);
            items.add(item);

            // write tree to file
            Feature tree = new Feature("TK_tree", StringUtils.normalizeSpace(parse.getPennTree()));
            TreeFeatureVector tfv = classifier.getFeaturesEncoder().encodeAll(Arrays.asList(tree));

            bw.write("0");
            bw.write(TKSVMlightDataWriter.createString(tfv));
            bw.write(SystemUtils.LINE_SEPARATOR);
        }
    } catch (IOException e) {
        throw new AnalysisEngineProcessException(e);
    } finally {
        IOUtils.closeQuietly(bw);
    }

    // classify all
    List<Double> predictions = classifier.tkSvmLightPredict2(cFile);

    if (predictions.size() != items.size()) {
        // TODO throw different exception instead
        throw new IOException("there are [" + predictions.size() + "] predictions, but [" + items.size()
                + "] were expected.");
    }

    List<EvaluationResult> results = new ArrayList<EvaluationResult>();
    for (EvaluationItem item : items) {
        results.add(new EvaluationResult(item, aUser, ""));
    }

    for (int i = 0; i < results.size(); i++) {
        Mark m = (predictions.get(i) > THRESHOLD) ? Mark.PRED_CORRECT : Mark.PRED_WRONG;
        results.get(i).setResult(m.getTitle());
    }

    return results;
}

---

From source file:de.fhg.iais.cortex.services.ingest.worker.IndexerWorker.java

private String normalizeLink(A link) {
    String linkAsString = link.getValue();

    if (!Strings.isNullOrEmpty(link.getHref())) {
        linkAsString = link.getHref();/*from   www.  j av  a2  s  .c om*/
    }

    if (link.getHref().matches("http://.*")) {
        linkAsString = "";
    }

    return StringUtils.normalizeSpace(linkAsString);
}

---

• «
• 1
• 2
• 3
• 4
• 5
• »