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(String name) 

Source Link

Document

Returns the offset after the last character of the subsequence captured by the given named-capturing group during the previous match operation.

Usage

From source file:com.nextep.designer.sqlgen.oracle.parser.OraclePackageParser.java

private String renameSqlEnd(String sql, String newName) {
    // Matching the END tag
    final Pattern pattern = Pattern.compile("end\\s+((\\w)+)(;|/|\\s)*$"); //$NON-NLS-1$
    final Matcher m = pattern.matcher(sql.toLowerCase());
    String newSql = sql;//w  w  w  . j  a  v a 2  s.c  om
    if (m.find()) {
        newSql = sql.substring(0, m.start(1)) + newName + sql.substring(m.end(1));
    }
    return newSql;
}

---

From source file:net.healeys.lexic.online.OnlineGame.java

public boolean submitWords(WebView display) {
    Pattern contentPat = Pattern.compile("([^;]+); charset=(.+)");
    for (int attempt = 0; attempt < MAX_ATTEMPTS; attempt++) {
        String url = BASE_URL + urls.get("words");

        Iterator<String> li = uniqueListIterator();
        StringBuffer sb = new StringBuffer(4096);
        while (li.hasNext()) {
            sb.append(li.next());//from   w  w w. j  a v  a2s  .  c o  m
            if (li.hasNext())
                sb.append(',');
        }
        String data = URLEncoder.encode(sb.toString());

        try {

            HttpClient httpClient = new DefaultHttpClient();
            HttpPost post = new HttpPost(url);
            addHeaders(post);

            post.setEntity(new StringEntity("words=" + data));

            HttpResponse resp = httpClient.execute(post);
            BufferedReader br = new BufferedReader(new InputStreamReader(resp.getEntity().getContent()));

            sb = new StringBuffer(4096);
            String line;
            while ((line = br.readLine()) != null) {
                sb.append(line);
                sb.append('\n');
            }

            String contentHeader = resp.getFirstHeader("Content-type").getValue();
            String contentType;
            String contentEncoding;
            Matcher mat = contentPat.matcher(contentHeader);
            if (mat.find()) {
                contentType = contentHeader.substring(mat.start(1), mat.end(1));
                contentEncoding = contentHeader.substring(mat.start(2), mat.end(2));
            } else {
                contentType = contentHeader;
                contentEncoding = "utf-8";
            }

            // Log.d(TAG,"url:"+url);
            // Log.d(TAG,"data:"+sb.toString());
            // Log.d(TAG,"contentType:"+contentType);
            // Log.d(TAG,"contentEncoding:"+contentEncoding);

            display.loadDataWithBaseURL(url, sb.toString(), "text/html", "utf-8", null);
            return true;
        } catch (Exception e) {
            // Log.d(TAG,"error submitting words",e);
        }
    }
    return false;
}

---

From source file:dk.netarkivet.harvester.harvesting.extractor.IcelandicExtractorJS.java

public long considerStrings(Extractor ext, CrawlURI curi, CharSequence cs, boolean handlingJSFile) {
    long foundLinks = 0;
    Matcher strings = TextUtils.getMatcher(JAVASCRIPT_STRING_EXTRACTOR, cs);
    int startIndex = 0;
    while (strings.find(startIndex)) {
        CharSequence subsequence = cs.subSequence(strings.start(2), strings.end(2));
        Matcher uri = TextUtils.getMatcher(STRING_URI_DETECTOR, subsequence);
        if (uri.matches()) {
            String string = uri.group();
            boolean falsePositive = false;
            try {
                string = StringEscapeUtils.unescapeJavaScript(string);
            } catch (NestableRuntimeException e) {
                LOGGER.log(Level.WARNING, "problem unescaping some javascript", e);
            }//  w  w  w. j  a  v  a 2 s.co  m
            string = UriUtils.speculativeFixup(string, curi.getUURI());

            // Filter out some bad false positives (should really fix regexp for URI detection) 
            if (string.contains("/.") || string.contains("@") || string.length() > 150) {
                // While legal in URIs, these are rare and usually an indication of a false positive
                // in the speculative extraction.
                falsePositive = true;
            }

            if (!falsePositive) {
                falsePositive = shouldIgnorePossibleRelativeLink(string);
            }

            if (falsePositive) {
                foundFalsePositives++;
            } else {
                foundLinks++;
                try {
                    int max = ext.getExtractorParameters().getMaxOutlinks();
                    if (handlingJSFile) {
                        addRelativeToVia(curi, max, string, JS_MISC, SPECULATIVE);
                    } else {
                        addRelativeToBase(curi, max, string, JS_MISC, SPECULATIVE);
                    }
                } catch (URIException e) {
                    ext.logUriError(e, curi.getUURI(), string);
                }
            }
        } else {
            foundLinks += considerStrings(ext, curi, subsequence, handlingJSFile);
        }

        // reconsider the last closing quote as possible opening quote
        startIndex = strings.end(2);
    }
    TextUtils.recycleMatcher(strings);
    return foundLinks;
}

---

From source file:com.github.rwitzel.streamflyer.xml.XmlVersionModifier.java

/**
 * @see com.github.rwitzel.streamflyer.core.Modifier#modify(java.lang.StringBuilder, int, boolean)
 *///from   w w w  . j  av  a 2 s  .c  o  m
@Override
public AfterModification modify(StringBuilder characterBuffer, int firstModifiableCharacterInBuffer,
        boolean endOfStreamHit) {

    switch (state) {

    case NO_LONGER_MODIFYING:

        return factory.skipEntireBuffer(characterBuffer, firstModifiableCharacterInBuffer, endOfStreamHit);

    case INITIAL:

        state = XmlVersionModifierState.PROLOG_REQUEST;

        // you never know how many whitespace characters are in the prolog
        return factory.modifyAgainImmediately(INITIAL_NUMBER_OF_CHARACTERS, firstModifiableCharacterInBuffer);

    case PROLOG_REQUEST:

        // (Should we do aware of BOMs here? No. I consider it the
        // responsibility of the caller to provide characters without BOM.)

        Matcher matcher = Pattern.compile("<\\?xml[^>]*version\\s*=\\s*['\"]((1.0)|(1.1))['\"].*")
                .matcher(characterBuffer);
        if (matcher.matches()) {

            // replace version in prolog
            characterBuffer.replace(matcher.start(1), matcher.end(1), xmlVersion);
        } else {
            // is there a prolog that is too long?
            Matcher matcher2 = Pattern.compile("<\\?xml.*").matcher(characterBuffer);
            if (matcher2.matches()) {
                // this is not normal at all -> throw exception
                throw new XmlPrologRidiculouslyLongException(characterBuffer.toString());
            }

            // insert prolog
            characterBuffer.insert(0, "<?xml version='" + xmlVersion + "'>");
        }

        state = XmlVersionModifierState.NO_LONGER_MODIFYING;

        return factory.skipEntireBuffer(characterBuffer, firstModifiableCharacterInBuffer, endOfStreamHit);

    default:
        throw new IllegalStateException("state " + state + " not supported");

    }

}

---

From source file:com.nextep.designer.sqlgen.oracle.parser.OraclePackageParser.java

@Override
public String parseName(String sql) {
    String tag = null;//from   w w  w .j  av  a  2  s.com
    if (isBody(sql)) {
        tag = "body"; //$NON-NLS-1$
    } else {
        tag = "package"; //$NON-NLS-1$
    }
    // Extracting procedure or function name from the SQL source
    Pattern pattern = Pattern.compile("\\s*(" + tag + ")\\s+((\\w)+)"); //$NON-NLS-1$ //$NON-NLS-2$ 
    Matcher m = pattern.matcher(sql.toLowerCase());
    // Looking for first occurrence
    String parsedName = null;
    if (m.find()) {
        parsedName = sql.substring(m.start(2), m.end(2));
    }
    return parsedName;
}

---

From source file:de.tudarmstadt.ukp.dkpro.core.textnormalizer.transformation.HyphenationRemover.java

@Override
public void process(JCas aInput, JCas aOutput) throws AnalysisEngineProcessException {
    StringBuilder c_new = new StringBuilder();
    final Matcher m = HYPHEN_PATTERN.matcher(aInput.getDocumentText());
    while (m.find()) {
        // The capturing groups count should be exactly 2.
        assert m.groupCount() == 2 : "Expected 2 groups but got " + m.groupCount();

        c_new.setLength(0);
        c_new.append(m.group(1));
        c_new.append(m.group(2));

        if (dict.contains(c_new.toString())) {
            replace(m.start(1), m.end(2), c_new.toString());
            //                getLogger().info(
            //                        "Conflated: [" + aInput.getDocumentText().substring(m.start(1), m.end(2))
            //                                + "] to [" + c_new + "]");
        }/*from  w  w w  .ja  v  a2 s .  c  om*/
    }
}

---

From source file:net.healeys.lexic.online.OnlineGame.java

public Iterator<Score> getScores() {
    Pattern startPat = Pattern.compile("^!START:([^,]+),(\\d+),(-?\\d+)$");
    Pattern endPat = Pattern.compile("^!END$");

    for (int attempt = 0; attempt < MAX_ATTEMPTS; attempt++) {
        try {//from w ww .j  a va  2  s  . co  m
            LinkedList<Score> scores = new LinkedList<Score>();

            HttpClient httpClient = new DefaultHttpClient();
            HttpGet get = new HttpGet(BASE_URL + urls.get("score"));
            addHeaders(get);

            HttpResponse resp = httpClient.execute(get);

            BufferedReader br = new BufferedReader(new InputStreamReader(resp.getEntity().getContent()));

            String username = "";
            int points = 0;
            int score = 0;
            String line;
            StringBuffer sb = new StringBuffer(0);
            while ((line = br.readLine()) != null) {
                // Log.d(TAG,"line:"+line);
                Matcher mat;
                if ((mat = startPat.matcher(line)).find()) {
                    // Log.d(TAG,"startPat matched"+line);
                    username = line.substring(mat.start(1), mat.end(1));
                    points = Integer.parseInt(line.substring(mat.start(2), mat.end(2)));
                    score = Integer.parseInt(line.substring(mat.start(3), mat.end(3)));
                    sb = new StringBuffer(2048);
                } else if ((mat = endPat.matcher(line)).find()) {
                    // Log.d(TAG,"endPat matched"+line);
                    scores.add(new Score(username, score, points, sb.toString()));
                } else if (sb != null && line.length() > 1) {
                    sb.append(line);
                    sb.append('\n');
                }
            }

            return scores.iterator();
        } catch (Exception e) {
            // Log.e(TAG,"getScores error",e);
        }
    }

    return null;
}

---

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

@Override
public void replaceEntityName(String newName) {
    Matcher entityMatcher = FROM_ENTITY_PATTERN.matcher(buffer);
    if (entityMatcher.find()) {
        buffer.replace(entityMatcher.start(FEP_ENTITY), entityMatcher.end(FEP_ENTITY), newName);
        return;//  w ww. j a  v a  2s.c  o  m
    }
    error("Unable to find entity name");
}

---

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

@Override
public void handleCaseInsensitiveParam(String paramName) {
    Pattern pattern = Pattern.compile(COND_PATTERN_REGEX + ":" + paramName, Pattern.CASE_INSENSITIVE);
    Matcher matcher = pattern.matcher(buffer);
    if (matcher.find()) {
        String field = matcher.group(1);
        buffer.replace(matcher.start(1), matcher.end(1), "lower(" + field + ")");
    }// www .ja  va  2  s .c  o m
}

---

From source file:edu.uab.ccts.nlp.uima.annotator.SegmentRegexAnnotator.java

/**
 * Add Segment annotations to the cas. First create a list of segments. Then
 * sort the list according to segment start. For each segment that has no
 * end, set the end to the [beginning of next segment - 1], or the eof.
 *///  w w  w  .ja  v a2s  .  c o m
@Override
public void process(JCas aJCas) throws AnalysisEngineProcessException {
    log.info("Starting SegmentRegexAnnotator with " + regexMap.size() + " segements.");
    String strDocText = aJCas.getDocumentText();
    if (strDocText == null)
        return;
    List<Segment> segmentsAdded = new ArrayList<Segment>();
    // find all the segments, set begin and id, add to list
    for (Map.Entry<SegmentRegex, Pattern> entry : regexMap.entrySet()) {
        if (log.isDebugEnabled()) {
            log.debug("applying regex:" + entry.getKey().getRegex());
        }
        Matcher matcher = entry.getValue().matcher(strDocText);
        while (matcher.find()) {
            Segment seg = new Segment(aJCas);
            if (entry.getKey().isLimitToRegex() && matcher.groupCount() == 1) {
                seg.setBegin(matcher.start(1));
                seg.setEnd(matcher.end(1));
            } else {
                seg.setBegin(matcher.start());
                if (entry.getKey().isLimitToRegex()) {
                    seg.setEnd(matcher.end());
                }
            }
            seg.setId(entry.getKey().getSegmentID());
            //if (log.isDebugEnabled()) {
            log.debug("found match: id=" + seg.getId() + ", begin=" + seg.getBegin() + " end=" + seg.getEnd());
            //}
            segmentsAdded.add(seg);
        }
    }
    if (log.isDebugEnabled()) {
        log.debug("segmentsAdded: " + segmentsAdded.size());
    }
    if (segmentsAdded.size() > 0) {
        // sort the segments by begin
        Collections.sort(segmentsAdded, new Comparator<Segment>() {

            // @Override
            public int compare(Segment o1, Segment o2) {
                return o1.getBegin() < o2.getBegin() ? -1 : o1.getBegin() > o2.getBegin() ? 1 : 0;
            }

        });
        // set the end for each segment
        for (int i = 0; i < segmentsAdded.size(); i++) {
            Segment seg = segmentsAdded.get(i);
            Segment segNext = (i + 1) < segmentsAdded.size() ? segmentsAdded.get(i + 1) : null;
            if (seg.getEnd() <= 0) {
                if (segNext != null) {
                    // set end to beginning of next segment
                    seg.setEnd(segNext.getBegin() - 1);
                } else {
                    // set end to doc end
                    seg.setEnd(strDocText.length());
                }
            } else {
                // segments shouldn't overlap
                if (segNext != null && segNext.getBegin() < seg.getEnd()) {
                    seg.setEnd(segNext.getBegin() - 1);
                }
            }
            //if (log.isDebugEnabled()) {
            log.debug("Adding Segment: segment id=" + seg.getId() + ", begin=" + seg.getBegin() + ", end="
                    + seg.getEnd());
            //}
            seg.addToIndexes();
        }
    }
    // ctakes 1.3.2 - anything not in a segment will not be annotated - add
    // text outside segments to the 'default' segment
    int end = 0;
    for (Segment seg : segmentsAdded) {
        if ((seg.getBegin() - 1) > end) {
            addGapSegment(aJCas, end, seg.getBegin() - 1);
        }
        end = seg.getEnd();
    }
    if (end < strDocText.length()) {
        addGapSegment(aJCas, end, strDocText.length());
    }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• »