Example usage for java.util.regex Matcher end

Introduction

In this page you can find the example usage for java.util.regex Matcher end.

Prototype

public int end() 

Source Link

Document

Returns the offset after the last character matched.

Usage

From source file:com.thoughtworks.go.domain.materials.Modification.java

public Set<String> getCardNumbersFromComment() {
    Set<String> cardNumbers = new TreeSet<>();
    Pattern pattern = Pattern.compile("#(\\d+)");
    String comment = this.comment == null ? "" : this.comment;
    Matcher matcher = pattern.matcher(comment);

    while (hasMatch(matcher)) {
        cardNumbers.add(id(matcher));/*from   w  w  w .  jav  a 2s  .co  m*/
        matcher.end();
    }

    return cardNumbers;
}

---

From source file:babel.content.pages.PageVersion.java

/**
 * Used to construct a page version from a set of nutch page related objects.
 * Should only be used by NutchPageExtractor.
 *///from w w  w  .j  av a 2s  . c o m
public PageVersion(String segmentId, List<NutchChunk> chunks, Page page) {
    this();

    Writable curVal;
    CrawlDatum curCD;
    Content curCT;
    ParseData curPD;
    ParseText curPT;

    // Store Segment ID
    m_verProps.set(PROP_SEGMENT_ID, segmentId);

    // Unwrap all of the page related information
    for (NutchChunk chunk : chunks) {
        curVal = chunk.get();

        if (curVal instanceof CrawlDatum) {
            // Get fetch information
            curCD = (CrawlDatum) curVal;

            if (curCD.getStatus() == CrawlDatum.STATUS_FETCH_SUCCESS) {
                m_verProps.set(PROP_FETCH_TIME, Long.toString(curCD.getFetchTime()));
                m_verProps.set(PROP_MODIFIED_TIME, Long.toString(curCD.getModifiedTime()));
            }
        } else if (curVal instanceof Content) {
            // Get the original unparsed content
            curCT = (Content) curVal;

            try {
                String str = new String(curCT.getContent(), DEFAULT_CHARSET);
                Matcher m = Pattern.compile("<html[^>]*>", Pattern.CASE_INSENSITIVE).matcher(str);

                if (m.find()) {
                    str = str.substring(m.start(), m.end());
                    m = Pattern.compile("\\slang\\s*=\\s*\"*([^\\s=\"]+)\"*", Pattern.CASE_INSENSITIVE)
                            .matcher(str);

                    if (m.find()) {
                        str = str.substring(m.start(1), m.end(1)).trim().toLowerCase();
                        if (str.length() > 0) {
                            page.setLanguage(Language.fromString(str));
                        }
                    }
                }
            } catch (Exception e) {
            }
        } else if (curVal instanceof ParseData) {
            // Get data extracted from page content
            curPD = (ParseData) curVal;
            if (curPD.getStatus().isSuccess()) {
                m_verProps.set(PROP_TITLE, curPD.getTitle());
                m_parseMeta.setAll(curPD.getParseMeta());
                m_contentMeta.setAll(curPD.getContentMeta());
                m_outLinks = curPD.getOutlinks();
            }
        } else if (curVal instanceof ParseText) {
            // Get parsed content
            curPT = (ParseText) curVal;
            m_content = setStr(curPT.getText());
        } else if (LOG.isWarnEnabled()) {
            LOG.warn("Unrecognized type: " + curVal.getClass());
        }
    }
}

---

From source file:com.spend.spendService.DomainLearning.java

private void GetNewQuery() {
    try {/*www  .ja v a 2 s . c o m*/
        TimerTask timertask = new TimerTask() {
            public void run() {
                try {
                    domainList = new ArrayList<String>();
                    String[] seList = getSearchEngineNamesArray();
                    /* get urls from seedurlraw table */
                    PreparedStatement psmt = con.prepareStatement("SELECT url FROM seedurlraw");
                    ResultSet rs = psmt.executeQuery();
                    String regex = "[/]";
                    String regex2 = "[.]";
                    String PLDomain;
                    while (rs.next()) {
                        PLDomain = rs.getString("url");
                        PLDomain = PLDomain.replaceAll("http://|https://", "");
                        Pattern p = Pattern.compile(regex);
                        Matcher m = p.matcher(PLDomain);
                        if (m.find()) {
                            PLDomain = PLDomain.substring(0, m.start());
                        }
                        Pattern p2 = Pattern.compile(regex2);
                        Matcher m2 = p2.matcher(PLDomain);
                        int count = 0;
                        while (m2.find()) {
                            count++;
                        }
                        m2 = p2.matcher(PLDomain);
                        if (count > 1 && m2.find()) {
                            PLDomain = PLDomain.substring(m2.end());
                        }

                        //System.out.println(PLDomain);                        

                        if (!domainList.contains(PLDomain)) {
                            domainList.add(PLDomain);
                            newQuery = "sparql endpoint site:" + PLDomain;
                            for (Object se : seList) {
                                PreparedStatement psmt1 = con.prepareStatement(
                                        "INSERT INTO searchqueue(searchText,disabled,searchEngineName) VALUES(?,0,?);");
                                psmt1.setString(1, newQuery);
                                psmt1.setString(2, se.toString());
                                psmt1.executeUpdate();
                                psmt1.close();
                            }
                        }
                    }
                } catch (Exception ex) {
                    System.out
                            .println("DomainLearning.java timertask run function SQL ERROR " + ex.getMessage());
                }
            }
        };
        Timer timer = new Timer();
        DateFormat dateformat = new SimpleDateFormat("dd-MM-yyyy HH:mm:ss");
        Date date = dateformat.parse("20-07-2017 00:00:00"); // set date and time
        timer.schedule(timertask, date, 1000 * 60 * 60 * 24 * 7); // for a week 1000*60*60*24*7
    } catch (Exception ex) {
        System.out.println("DomainLearning.java GetNewQuery function ERROR " + ex.getMessage());
    }
}

---

From source file:com.haulmont.cuba.core.global.QueryTransformerRegex.java

@Override
public boolean removeDistinct() {
    Matcher matcher = SELECT_DISTINCT_PATTERN.matcher(buffer);
    if (matcher.find()) {
        buffer.replace(matcher.start(), matcher.end(), "select");
        return true;
    }/*from w ww  .j  a v a 2s .  c  o m*/
    return false;
}

---

From source file:com.epam.reportportal.extension.bugtracking.jira.JiraStrategy.java

/**
 * Parse ticket description and find binary data
 *
 * @param issueInput/*from  w ww .j  a v  a2  s .  c om*/
 * @return
 */
private Map<String, String> findBinaryData(IssueInput issueInput) {
    Map<String, String> binary = new HashMap<>();
    String description = issueInput.getField(IssueFieldId.DESCRIPTION_FIELD.id).getValue().toString();
    if (null != description) {
        // !54086a2c3c0c7d4446beb3e6.jpg| or [^54086a2c3c0c7d4446beb3e6.xml]
        String regex = "(!|\\[\\^).{24}.{0,5}(\\||\\])";
        Matcher matcher = Pattern.compile(regex).matcher(description);
        while (matcher.find()) {
            String rawValue = description.subSequence(matcher.start(), matcher.end()).toString();
            String binaryDataName = rawValue.replace("!", "").replace("[", "").replace("]", "").replace("^", "")
                    .replace("|", "");
            String binaryDataId = binaryDataName.split("\\.")[0];
            binary.put(binaryDataId, binaryDataName);
        }
    }
    return binary;
}

---

From source file:com.kenshoo.freemarker.util.DataModelParser.java

public static Map<String, Object> parse(String src, TimeZone timeZone) throws DataModelParsingException {
    if (!StringUtils.hasText(src)) {
        return Collections.emptyMap();
    }/*from  w w  w  . j ava 2s  .  co m*/

    Map<String, Object> dataModel = new LinkedHashMap<>();

    String lastName = null;
    int lastAssignmentStartEnd = 0;
    final Matcher assignmentStart = ASSIGNMENT_START.matcher(src);
    findAssignments: while (true) {
        boolean hasNextAssignment = assignmentStart.find(lastAssignmentStartEnd);

        if (lastName != null) {
            String value = src.substring(lastAssignmentStartEnd,
                    hasNextAssignment ? assignmentStart.start() : src.length()).trim();
            final Object parsedValue;
            try {
                parsedValue = parseValue(value, timeZone);
            } catch (DataModelParsingException e) {
                throw new DataModelParsingException(
                        "Failed to parse the value of \"" + lastName + "\":\n" + e.getMessage(), e.getCause());
            }
            dataModel.put(lastName, parsedValue);
        }

        if (lastName == null && (!hasNextAssignment || assignmentStart.start() != 0)) {
            throw new DataModelParsingException(
                    "The data model specification must start with an assignment (name=value).");
        }

        if (!hasNextAssignment) {
            break findAssignments;
        }

        lastName = assignmentStart.group(1).trim();
        lastAssignmentStartEnd = assignmentStart.end();
    }

    return dataModel;
}

---

From source file:com.hp.alm.ali.idea.entity.tree.EntityNode.java

public String toString() {
    String name = entity.getPropertyValue("name");
    if (loading) {
        name += "..."; // TODO: show as icon
    }//  www .jav a2  s . c  o  m
    String filter = model.getFilter();
    if (!filter.isEmpty()) {
        Matcher matcher = Pattern.compile(wildcardToRegex(filter), Pattern.CASE_INSENSITIVE).matcher(name);
        List<Pair<Integer, Integer>> list = new LinkedList<Pair<Integer, Integer>>();
        while (matcher.find()) {
            list.add(new Pair<Integer, Integer>(matcher.start(), matcher.end()));
        }
        if (!list.isEmpty()) {
            Collections.reverse(list);
            for (Pair<Integer, Integer> match : list) {
                name = name.substring(0, match.first) + "<b>" + name.substring(match.first, match.second)
                        + "</b>" + name.substring(match.second);
            }
            return "<html>" + name + "</html>";
        }
    }
    return name;
}

---

From source file:org.ala.harvester.WaissHarvester.java

/**
 * @see org.ala.harvester.Harvester#start()
 *//* ww  w.j a v a 2s. c om*/
@SuppressWarnings("unchecked")
@Override
public void start(int infosourceId) throws Exception {

    // TODO Auto-generated method stub
    Thread.sleep(timeGap);

    // Obtains the image listing on the page number specified.
    // Instance variable `currentResDom` will have new
    // DOM representation of the result.
    String indexStr = getIndexPageStr();
    //        String xpathToImageUrls = "//div[@align='center']/a[@target='_blank']/@href";
    //        
    //        Document document = getDocument(indexStr.getBytes());
    //        XPathFactory factory = XPathFactory.newInstance();
    //        XPath xpath = factory.newXPath();
    //        
    //        NodeList nodes = (NodeList) xpath.evaluate(xpathToImageUrls, document, XPathConstants.NODESET);
    //        
    //        for (int i = 0; i < nodes.getLength(); i++) {
    //            String imageUrl = (nodes.item(i)).getNodeValue();
    //            imageUrl = StringUtils.trimToNull(imageUrl);
    //            
    //            if (imageUrl != null && !"".equals(imageUrl)) {
    //                imageUrl = "http://www.museum.wa.gov.au/waiss/pages/" + imageUrl;
    //                System.out.println(imageUrl);
    //            }
    //        }

    Pattern speciesPattern = Pattern.compile("(?:<a href=\")" + "(images/[a-zA-Z0-9\\.]*)"
            + "(?:\" target=\"_blank\"><img src=\")" + "(?:\\.\\./a_data/[a-zA-Z0-9_]{1,}\\.jpg)"
            + "(?:\" width=\"[0-9]{1,}\" height=\"[0-9]{1,}\" border=\"[0-9]{1,}\"></a></div></td>[\\s]{0,}<td[ width=\"422]*>[\\s]*[<div align=\"center\">]*<span class=\"style4\"><strong>)"
            + "([a-zA-Z \\-']*)" + "(?:</strong>[ ]*\\([ ]*<em>)" + "([a-zA-Z ]*)");

    Pattern creatorPattern = Pattern.compile("(?:Photo: )" + "([a-zA-Z ]{1,})");

    Matcher m = speciesPattern.matcher(indexStr);

    String[] creatorArray = new String[9];

    Matcher m2 = creatorPattern.matcher(indexStr);

    int searchIdx2 = 0;
    int creatorCounter = 0;

    while (m2.find(searchIdx2)) {
        int endIdx2 = m2.end();

        String creator = m2.group(1);

        if (creator != null && !"".equals(creator)) {
            creatorArray[creatorCounter] = creator;
            creatorCounter++;
        }

        searchIdx2 = endIdx2;
    }

    int speciesCounter = 0;
    int searchIdx = 0;
    // get all the family links
    while (m.find(searchIdx)) {
        int endIdx = m.end();
        //          String found = content.substring(startIdx, endIdx);
        String url = "http://www.museum.wa.gov.au/waiss/pages/" + m.group(1);
        String commonName = m.group(2);
        String sciName = m.group(3);
        //            String generatedUrl = this.endpoint + url;
        //
        System.out.println("URL:" + url);
        System.out.println("Common Name: " + commonName);
        System.out.println("Sci Name:" + sciName);
        //            
        processSingleImage(url.trim(), commonName.trim(), sciName.trim(), infosourceId,
                creatorArray[speciesCounter]);
        speciesCounter++;
        //
        //            identifiers.add(generatedUrl);

        searchIdx = endIdx;
    }

    System.out.println(speciesCounter);

}

---

From source file:org.ala.harvester.BlueTierHarvester.java

private Map<String, String> matchStr(Pattern p, String str, int imageUrlPosition, int sciNamePosition) {
    Matcher m = p.matcher(str);
    Map<String, String> urlNameMap = new HashMap<String, String>();

    int searchIdx = 0;

    while (m.find(searchIdx)) {
        int endIdx = m.end();
        //          String found = content.substring(startIdx, endIdx);
        String imageUrl = m.group(imageUrlPosition);
        String sciName = m.group(sciNamePosition);

        imageUrl = imageUrl.replaceFirst("\\.\\./", "");

        String generatedUrl = baseUrl + imageUrl;

        //            System.out.println("URL:" + generatedUrl);
        //            System.out.println("Name:" + sciName);

        //            storeImageDoc(generatedUrl, sciName);

        urlNameMap.put(generatedUrl, sciName);

        searchIdx = endIdx;/*from   www . jav a2s. c o m*/
    }

    return urlNameMap;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• »