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

List of usage examples for org.apache.commons.lang StringUtils countMatches

  1. HOME
  2. Java
  3. org.apache.commons
  4. org.apache.commons.lang.*
  5. StringUtils
  6. countMatches

Introduction

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

Prototype

public static int countMatches(String str, String sub)

Source Link

Document

Counts how many times the substring appears in the larger String.

Usage

From source file:no.imr.stox.functions.utils.CovariateUtils.java

public static String getFullPeriod(String period, Integer year) {
    Integer n = StringUtils.countMatches(period, "/");
    switch (n) {//from   w  w w.j ava  2 s.  c  om
    case 1:
        if (!(year % 400 == 0 || year % 4 == 0 && year % 100 != 0)) {
            // Reduce february max from 29 to 28 on max date
            Integer ns = period.indexOf("/");
            Integer day = Conversion.safeSubstringToIntegerNULL(period, 0, ns);
            Integer month = Conversion.safeSubstringToIntegerNULL(period, ns + 1, period.length());
            if (month == 2 && day == 29) {
                return IMRdate.encodeDateStr(day, month - 1, year);
            }
        }
        return period + "/" + year;
    case 2:
        return period;
    }
    return null;
}

From source file:nz.ac.waikato.its.irr.scripts.FixSquishedMetadata.java

private static boolean process(Item item, String schema, String element, String qualifier, String delimiter,
        int minMatches, boolean dryRun) throws SQLException, AuthorizeException {
    boolean changes = false;
    List<Metadatum> newMetadata = new ArrayList<>();

    Metadatum[] allMd = item.getMetadata(schema, element, qualifier, Item.ANY);
    for (Metadatum md : allMd) {
        if (StringUtils.isNotBlank(md.value) && StringUtils.countMatches(md.value, delimiter) >= minMatches) {
            String[] individualValues = StringUtils.splitByWholeSeparator(md.value, delimiter);
            for (int i = 0; i < individualValues.length; i++) {
                individualValues[i] = individualValues[i].replaceAll("(\\r|\\n|\\t)", " ").replaceAll("  ", " ")
                        .trim();//from  w w  w.  ja v a  2 s.c  o  m
            }
            System.out.println("item id=" + item.getID() + ": split |" + md.value + "| into |"
                    + StringUtils.join(individualValues, '|') + "|");
            if (!dryRun) {
                for (String individualValue : individualValues) {
                    if (StringUtils.isNotBlank(individualValue)) {
                        Metadatum newMd = new Metadatum();
                        newMd.language = md.language;
                        newMd.value = individualValue;
                        newMetadata.add(newMd);
                    }
                }
                changes = true;
            }
        } else {
            newMetadata.add(md);
        }
    }
    if (!dryRun && changes) {
        item.clearMetadata(schema, element, qualifier, Item.ANY);
        for (Metadatum newMd : newMetadata) {
            item.addMetadata(schema, element, qualifier, newMd.language, newMd.value, newMd.authority,
                    newMd.confidence);
        }
        item.updateMetadata();
    }
    return changes;
}

From source file:opennlp.tools.chatbot.SnippetToParagraphAndSectionHeaderContent.java

public HitBase formTextFromOriginalPageGivenSnippet(HitBase item) {

    Pair<String[], Map<String, String>> sentsMap = extractSentencesAndSectionMapFromPage(item.getUrl());
    if (sentsMap == null)
        return item;

    String[] sents = sentsMap.getFirst();
    item.setSectionHeaderContent(sentsMap.getSecond());

    // String title = item.getTitle().replace("<b>", " ").replace("</b>", "
    // ")//w  w  w  . j ava 2  s.c o  m
    // .replace(" ", " ").replace(" ", " ");
    // generation results for this sentence
    List<String> result = new ArrayList<String>();
    // form plain text from snippet
    String snapshot = item.getAbstractText().replace("<b>", " ").replace("</b>", " ").replace("  ", " ")
            .replace("  ", " ").replace("\"", "");

    String snapshotMarked = snapshot.replace(" ...", ".");
    List<String> fragments = TextProcessor.splitToSentences(snapshotMarked);
    if (fragments.size() < 3 && StringUtils.countMatches(snapshotMarked, ".") > 1) {
        snapshotMarked = snapshotMarked.replace("..", "&").replace(".", "&");
        String[] fragmSents = snapshotMarked.split("&");
        fragments = Arrays.asList(fragmSents);
    }

    for (String f : fragments) {
        String followSent = null;
        if (f.length() < 50)
            continue;
        String pageSentence = "";
        // try to find original sentence from webpage

        try {
            String[] mainAndFollowSent = getFullOriginalSentenceFromWebpageBySnippetFragment(f, sents);
            pageSentence = mainAndFollowSent[0];
            followSent = mainAndFollowSent[1];
            if (pageSentence != null && followSent != null)
                result.add(pageSentence + "\n" + followSent);
            else if (pageSentence != null) {
                result.add(pageSentence);
            } else {
                result.add(f);
                LOG.info("Could not find the original sentence \n" + f + "\n in the page ");
            }

        } catch (Exception e) {

            e.printStackTrace();
        }
    }
    item.setOriginalSentences(result);
    return item;
}

From source file:opennlp.tools.parse_thicket.apps.SnippetToParagraph.java

public HitBase formTextFromOriginalPageGivenSnippet(HitBase item) {

    String[] sents = extractSentencesFromPage(item.getUrl());

    String title = item.getTitle().replace("<b>", " ").replace("</b>", " ").replace("  ", " ").replace("  ",
            " ");
    // generation results for this sentence
    List<String> result = new ArrayList<String>();
    // form plain text from snippet
    String snapshot = item.getAbstractText().replace("<b>", " ").replace("</b>", " ").replace("  ", " ")
            .replace("  ", " ").replace("\"", "");

    String snapshotMarked = snapshot.replace(" ...", ".");
    List<String> fragments = TextProcessor.splitToSentences(snapshotMarked);
    if (fragments.size() < 3 && StringUtils.countMatches(snapshotMarked, ".") > 1) {
        snapshotMarked = snapshotMarked.replace("..", "&").replace(".", "&");
        String[] fragmSents = snapshotMarked.split("&");
        fragments = Arrays.asList(fragmSents);
    }//from  w  w w .j a v a2  s  .c  o  m

    for (String f : fragments) {
        String followSent = null;
        if (f.length() < 50)
            continue;
        String pageSentence = "";
        // try to find original sentence from webpage

        try {
            String[] mainAndFollowSent = getFullOriginalSentenceFromWebpageBySnippetFragment(f, sents);
            pageSentence = mainAndFollowSent[0];
            followSent = mainAndFollowSent[1];
            if (pageSentence != null)
                result.add(pageSentence);
            else {
                result.add(f);
                LOG.info("Could not find the original sentence \n" + f + "\n in the page ");
            }
            //if (followSent !=null)
            //   result.add(followSent);
        } catch (Exception e) {

            e.printStackTrace();
        }
    }
    item.setOriginalSentences(result);
    return item;
}

From source file:opennlp.tools.parse_thicket.kernel_interface.SnippetToParagraphFull.java

public HitBase formTextFromOriginalPageGivenSnippet(HitBase item) {

    String[] sents = extractSentencesFromPage(item.getUrl());

    // String title = item.getTitle().replace("<b>", " ").replace("</b>", "
    // ")/*from  w  w  w.  j  a v  a2 s  .  c  om*/
    // .replace(" ", " ").replace(" ", " ");
    // generation results for this sentence
    List<String> result = new ArrayList<String>();
    // form plain text from snippet
    String snapshot = item.getAbstractText().replace("<b>", " ").replace("</b>", " ").replace("  ", " ")
            .replace("  ", " ").replace("\"", "");

    String snapshotMarked = snapshot.replace(" ...", ".");
    List<String> fragments = TextProcessor.splitToSentences(snapshotMarked);
    if (fragments.size() < 3 && StringUtils.countMatches(snapshotMarked, ".") > 1) {
        snapshotMarked = snapshotMarked.replace("..", "&").replace(".", "&");
        String[] fragmSents = snapshotMarked.split("&");
        fragments = Arrays.asList(fragmSents);
    }

    for (String f : fragments) {
        String followSent = null;
        if (f.length() < 50)
            continue;
        String pageSentence = "";
        // try to find original sentence from webpage

        try {
            String[] mainAndFollowSent = getFullOriginalSentenceFromWebpageBySnippetFragment(f, sents);
            pageSentence = mainAndFollowSent[0];
            followSent = mainAndFollowSent[1];
            if (pageSentence != null && followSent != null)
                result.add(pageSentence + "\n" + followSent);
            else if (pageSentence != null) {
                result.add(pageSentence);
            } else {
                result.add(f);
                LOG.info("Could not find the original sentence \n" + f + "\n in the page ");
            }

        } catch (Exception e) {

            e.printStackTrace();
        }
    }
    item.setOriginalSentences(result);
    return item;
}

From source file:opennlp.tools.textsimilarity.TextProcessor.java

private static HashSet<String> extractCommonSegments(Pair<List<String>, Map<String, HashSet<Integer>>> objA,
        Pair<List<String>, Map<String, HashSet<Integer>>> objB, Integer segSize) {

    HashSet<String> commonSegments = new HashSet<String>();

    List<String> tokensA = objA.getFirst();

    Map<String, HashSet<Integer>> tokenPosB = objB.getSecond();

    HashSet<Integer> lastPositions = null;
    int segLength = 1;
    StringBuffer segmentStr = new StringBuffer();

    for (int i = 0; i < tokensA.size(); i++) {
        String token = tokensA.get(i);
        HashSet<Integer> positions = null;
        // if ((positions = tokenPosB.get(token)) != null &&
        // !token.equals("<punc>") &&
        // !StopList.getInstance().isStopWord(token) && token.length()>1) {
        if ((positions = tokenPosB.get(token)) != null) {
            // we have a list of positions
            if (lastPositions != null) {
                // see if there is overlap in positions
                if (hasNextPosition(lastPositions, positions)) {
                    segLength++;//from   ww  w.ja va  2  s  .  c om

                    commonSegments.remove(segmentStr.toString().trim());
                    segmentStr.append(" ");
                    segmentStr.append(token);
                    if (StringUtils.countMatches(segmentStr.toString(), " ") >= segSize) {
                        commonSegments.add(segmentStr.toString().trim());
                    }
                    lastPositions = positions;

                } else {
                    // did not find segment, reset
                    segLength = 1;
                    segmentStr.setLength(0);
                    lastPositions = null;
                }
            } else {
                lastPositions = positions;
                segmentStr.append(" ");
                segmentStr.append(token);
            }
        } else {
            // did not find segment, reset
            segLength = 1;
            segmentStr.setLength(0);
            lastPositions = null;
        }
    }

    return commonSegments;
}

From source file:org.alfresco.module.vti.handler.alfresco.AlfrescoMeetingServiceHandler.java

/**
 * @see org.alfresco.module.vti.handler.MeetingServiceHandler#createWorkspace(String, String, int, TimeZoneInformation, SessionUser)
 *///w  w  w  .  ja v a 2s.  c o  m
public String createWorkspace(String title, String templateName, int lcid,
        TimeZoneInformation timeZoneInformation, SessionUser user) throws Exception {
    // Build the site name from the title
    String siteName = removeIllegalCharacters(title);

    // A list of underscores is not a valid name.
    int matches = StringUtils.countMatches(siteName, "_");
    if (matches > 0 && siteName.length() == matches) {
        siteName = DEFAULT_SITE_NAME;
    }

    // Build a unique name up
    SiteInfo siteInfo = null;
    String newSiteName = null;
    int i = 0;
    do {
        newSiteName = truncateSiteName(siteName, i == 0 ? "" : "_" + i);
        siteInfo = siteService.getSite(newSiteName);
        i++;
    } while (siteInfo != null);

    // Have it created
    shareUtils.createSite(user, MEETING_WORKSPACE_NAME, newSiteName, title, "", true);
    return newSiteName;
}

From source file:org.apache.activemq.web.AjaxTest.java

public void assertResponseCount(int expected, String actual) {
    int occurrences = StringUtils.countMatches(actual, "<response");
    assertEquals("Expected number of <response> elements is not correct.", expected, occurrences);
}

From source file:org.apache.ambari.server.serveraction.upgrades.OozieConfigCalculationTest.java

/**
 * Checks that -Dhdp.version is added to $HADOOP_OPTS variable at oozie-env
 * content./*from   ww  w.  ja  v a  2  s  .c o m*/
 * Also checks that it is not added multiple times during upgrades
 * @throws Exception
 */
@Test
public void testOozieEnvWithMissingParam() throws Exception {
    // Test case when old content does not contain $HADOOP_OPTS variable at all
    String oldContent = "#!/bin/bash\n" + "\n" + "if [ -d \"/usr/lib/bigtop-tomcat\" ]; then\n"
            + "  export OOZIE_CONFIG=${OOZIE_CONFIG:-/etc/oozie/conf}\n"
            + "  export CATALINA_BASE=${CATALINA_BASE:-{{oozie_server_dir}}}\n"
            + "  export CATALINA_TMPDIR=${CATALINA_TMPDIR:-/var/tmp/oozie}\n"
            + "  export OOZIE_CATALINA_HOME=/usr/lib/bigtop-tomcat\n" + "fi\n" + "\n"
            + "# export OOZIE_BASE_URL=\"http://${OOZIE_HTTP_HOSTNAME}:${OOZIE_HTTP_PORT}/oozie\"\n"
            + "export JAVA_LIBRARY_PATH={{hadoop_lib_home}}/native/Linux-amd64-64";
    String newContent = OozieConfigCalculation.processPropertyValue(oldContent);
    assertTrue(newContent.endsWith("export HADOOP_OPTS=\"-Dhdp.version=$HDP_VERSION $HADOOP_OPTS\" "));
    // Test case when old content contains proper $HADOOP_OPTS variable
    oldContent = newContent;
    newContent = OozieConfigCalculation.processPropertyValue(oldContent);
    assertEquals(newContent, oldContent);
    assertEquals(1, StringUtils.countMatches(newContent, "-Dhdp.version"));
    // Test case when old content contains $HADOOP_OPTS variable with some value
    oldContent = "#!/bin/bash\n" + "\n" + "if [ -d \"/usr/lib/bigtop-tomcat\" ]; then\n"
            + "  export OOZIE_CONFIG=${OOZIE_CONFIG:-/etc/oozie/conf}\n"
            + "  export CATALINA_BASE=${CATALINA_BASE:-{{oozie_server_dir}}}\n"
            + "  export CATALINA_TMPDIR=${CATALINA_TMPDIR:-/var/tmp/oozie}\n"
            + "  export OOZIE_CATALINA_HOME=/usr/lib/bigtop-tomcat\n"
            + "  export HADOOP_OPTS=-Dsome.option1 -Dsome.option1 $HADOOP_OPTS\n" + "fi\n" + "\n"
            + "# export OOZIE_BASE_URL=\"http://${OOZIE_HTTP_HOSTNAME}:${OOZIE_HTTP_PORT}/oozie\"\n"
            + "export JAVA_LIBRARY_PATH={{hadoop_lib_home}}/native/Linux-amd64-64";
    newContent = OozieConfigCalculation.processPropertyValue(oldContent);
    assertEquals("#!/bin/bash\n" + "\n" + "if [ -d \"/usr/lib/bigtop-tomcat\" ]; then\n"
            + "  export OOZIE_CONFIG=${OOZIE_CONFIG:-/etc/oozie/conf}\n"
            + "  export CATALINA_BASE=${CATALINA_BASE:-{{oozie_server_dir}}}\n"
            + "  export CATALINA_TMPDIR=${CATALINA_TMPDIR:-/var/tmp/oozie}\n"
            + "  export OOZIE_CATALINA_HOME=/usr/lib/bigtop-tomcat\n"
            + "  export HADOOP_OPTS=-Dsome.option1 -Dsome.option1 $HADOOP_OPTS\n" + "fi\n" + "\n"
            + "# export OOZIE_BASE_URL=\"http://${OOZIE_HTTP_HOSTNAME}:${OOZIE_HTTP_PORT}/oozie\"\n"
            + "export JAVA_LIBRARY_PATH={{hadoop_lib_home}}/native/Linux-amd64-64\n"
            + "export HADOOP_OPTS=\"-Dhdp.version=$HDP_VERSION $HADOOP_OPTS\" ", newContent);
}

From source file:org.apache.archiva.rest.services.DefaultBrowseService.java

protected List<ArtifactContentEntry> readFileEntries(File file, String filterPath, String repoId)
        throws IOException {
    Map<String, ArtifactContentEntry> artifactContentEntryMap = new HashMap<>();
    int filterDepth = StringUtils.countMatches(filterPath, "/");
    /*if ( filterDepth == 0 )
    {/*from   w  ww .j  av  a2  s  . com*/
    filterDepth = 1;
    }*/
    JarFile jarFile = new JarFile(file);
    try {
        Enumeration<JarEntry> jarEntryEnumeration = jarFile.entries();
        while (jarEntryEnumeration.hasMoreElements()) {
            JarEntry currentEntry = jarEntryEnumeration.nextElement();
            String cleanedEntryName = StringUtils.endsWith(currentEntry.getName(), "/") ? //
                    StringUtils.substringBeforeLast(currentEntry.getName(), "/") : currentEntry.getName();
            String entryRootPath = getRootPath(cleanedEntryName);
            int depth = StringUtils.countMatches(cleanedEntryName, "/");
            if (StringUtils.isEmpty(filterPath) //
                    && !artifactContentEntryMap.containsKey(entryRootPath) //
                    && depth == filterDepth) {

                artifactContentEntryMap.put(entryRootPath,
                        new ArtifactContentEntry(entryRootPath, !currentEntry.isDirectory(), depth, repoId));
            } else {
                if (StringUtils.startsWith(cleanedEntryName, filterPath) //
                        && (depth == filterDepth || (!currentEntry.isDirectory() && depth == filterDepth))) {
                    artifactContentEntryMap.put(cleanedEntryName, new ArtifactContentEntry(cleanedEntryName,
                            !currentEntry.isDirectory(), depth, repoId));
                }
            }
        }

        if (StringUtils.isNotEmpty(filterPath)) {
            Map<String, ArtifactContentEntry> filteredArtifactContentEntryMap = new HashMap<>();

            for (Map.Entry<String, ArtifactContentEntry> entry : artifactContentEntryMap.entrySet()) {
                filteredArtifactContentEntryMap.put(entry.getKey(), entry.getValue());
            }

            List<ArtifactContentEntry> sorted = getSmallerDepthEntries(filteredArtifactContentEntryMap);
            if (sorted == null) {
                return Collections.emptyList();
            }
            Collections.sort(sorted, ArtifactContentEntryComparator.INSTANCE);
            return sorted;
        }
    } finally {
        if (jarFile != null) {
            jarFile.close();
        }
    }
    List<ArtifactContentEntry> sorted = new ArrayList<>(artifactContentEntryMap.values());
    Collections.sort(sorted, ArtifactContentEntryComparator.INSTANCE);
    return sorted;
}