Example usage for java.util.regex Pattern DOTALL

Introduction

In this page you can find the example usage for java.util.regex Pattern DOTALL.

Prototype

int DOTALL

To view the source code for java.util.regex Pattern DOTALL.

Click Source Link

Document

Enables dotall mode.

Usage

From source file:org.apache.hadoop.hive.serde2.RegexSerDe.java

@Override
public void initialize(Configuration conf, Properties tbl) throws SerDeException {

    // We can get the table definition from tbl.

    // Read the configuration parameters
    inputRegex = tbl.getProperty(INPUT_REGEX);
    String columnNameProperty = tbl.getProperty(serdeConstants.LIST_COLUMNS);
    String columnTypeProperty = tbl.getProperty(serdeConstants.LIST_COLUMN_TYPES);
    boolean inputRegexIgnoreCase = "true".equalsIgnoreCase(tbl.getProperty(INPUT_REGEX_CASE_SENSITIVE));

    // output format string is not supported anymore, warn user of deprecation
    if (null != tbl.getProperty("output.format.string")) {
        LOG.warn("output.format.string has been deprecated");
    }//from  www. ja va 2 s . c o m

    // Parse the configuration parameters
    if (inputRegex != null) {
        inputPattern = Pattern.compile(inputRegex,
                Pattern.DOTALL + (inputRegexIgnoreCase ? Pattern.CASE_INSENSITIVE : 0));
    } else {
        inputPattern = null;
        throw new SerDeException("This table does not have serde property \"input.regex\"!");
    }

    List<String> columnNames = Arrays.asList(columnNameProperty.split(","));
    columnTypes = TypeInfoUtils.getTypeInfosFromTypeString(columnTypeProperty);
    assert columnNames.size() == columnTypes.size();
    numColumns = columnNames.size();

    /* Constructing the row ObjectInspector:
     * The row consists of some set of primitive columns, each column will
     * be a java object of primitive type.
     */
    List<ObjectInspector> columnOIs = new ArrayList<ObjectInspector>(columnNames.size());
    for (int c = 0; c < numColumns; c++) {
        TypeInfo typeInfo = columnTypes.get(c);
        if (typeInfo instanceof PrimitiveTypeInfo) {
            PrimitiveTypeInfo pti = (PrimitiveTypeInfo) columnTypes.get(c);
            AbstractPrimitiveJavaObjectInspector oi = PrimitiveObjectInspectorFactory
                    .getPrimitiveJavaObjectInspector(pti);
            columnOIs.add(oi);
        } else {
            throw new SerDeException(getClass().getName() + " doesn't allow column [" + c + "] named "
                    + columnNames.get(c) + " with type " + columnTypes.get(c));
        }
    }

    // StandardStruct uses ArrayList to store the row.
    rowOI = ObjectInspectorFactory.getStandardStructObjectInspector(columnNames, columnOIs,
            Lists.newArrayList(Splitter.on('\0').split(tbl.getProperty("columns.comments"))));

    row = new ArrayList<Object>(numColumns);
    // Constructing the row object, etc, which will be reused for all rows.
    for (int c = 0; c < numColumns; c++) {
        row.add(null);
    }
    outputFields = new Object[numColumns];
    outputRowText = new Text();
}

---

From source file:de.ist.clonto.webwiki.InfoboxParser.java

private String replaceHTMLComments(String text) {
    text = Pattern.compile("<!--.*?-->", Pattern.MULTILINE | Pattern.DOTALL).matcher(text).replaceAll("");

    return text;// w w  w .j  a  v  a2s . com
}

---

From source file:org.opennms.web.rest.v1.AcknowledgmentRestServiceIT.java

@Test
@JUnitTemporaryDatabase/*from   ww w . j  a v a  2  s.  c o  m*/
public void testAcknowlegeNotification() throws Exception {
    final Pattern p = Pattern.compile("^.*<answeredBy>(.*?)</answeredBy>.*$",
            Pattern.DOTALL & Pattern.MULTILINE);
    sendData(POST, MediaType.APPLICATION_FORM_URLENCODED, "/acks", "notifId=1&action=ack", 200);
    String xml = sendRequest(GET, "/notifications/1", new HashMap<String, String>(), 200);
    Matcher m = p.matcher(xml);
    assertTrue(m.matches());
    assertTrue(m.group(1).equals("admin"));
    sendData(POST, MediaType.APPLICATION_FORM_URLENCODED, "/acks", "notifId=1&action=unack", 200);
    xml = sendRequest(GET, "/notifications/1", new HashMap<String, String>(), 200);
    m = p.matcher(xml);
    assertFalse(m.matches());
}

---

From source file:org.apache.hadoop.hive.contrib.serde2.RegexSerDe.java

@Override
public void initialize(Configuration conf, Properties tbl) throws SerDeException {

    // We can get the table definition from tbl.

    // Read the configuration parameters
    inputRegex = tbl.getProperty(INPUT_REGEX);
    outputFormatString = tbl.getProperty(OUTPUT_FORMAT_STRING);
    String columnNameProperty = tbl.getProperty(serdeConstants.LIST_COLUMNS);
    String columnTypeProperty = tbl.getProperty(serdeConstants.LIST_COLUMN_TYPES);
    boolean inputRegexIgnoreCase = "true".equalsIgnoreCase(tbl.getProperty(INPUT_REGEX_CASE_SENSITIVE));

    // Parse the configuration parameters
    if (inputRegex != null) {
        inputPattern = Pattern.compile(inputRegex,
                Pattern.DOTALL + (inputRegexIgnoreCase ? Pattern.CASE_INSENSITIVE : 0));
    } else {/*from  w w w  .j  ava2  s  .com*/
        inputPattern = null;
    }
    List<String> columnNames = Arrays.asList(columnNameProperty.split(","));
    List<TypeInfo> columnTypes = TypeInfoUtils.getTypeInfosFromTypeString(columnTypeProperty);
    assert columnNames.size() == columnTypes.size();
    numColumns = columnNames.size();

    // All columns have to be of type STRING.
    for (int c = 0; c < numColumns; c++) {
        if (!columnTypes.get(c).equals(TypeInfoFactory.stringTypeInfo)) {
            throw new SerDeException(getClass().getName() + " only accepts string columns, but column[" + c
                    + "] named " + columnNames.get(c) + " has type " + columnTypes.get(c));
        }
    }

    // Constructing the row ObjectInspector:
    // The row consists of some string columns, each column will be a java
    // String object.
    List<ObjectInspector> columnOIs = new ArrayList<ObjectInspector>(columnNames.size());
    for (int c = 0; c < numColumns; c++) {
        columnOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
    }
    // StandardStruct uses ArrayList to store the row.
    rowOI = ObjectInspectorFactory.getStandardStructObjectInspector(columnNames, columnOIs);

    // Constructing the row object, etc, which will be reused for all rows.
    row = new ArrayList<String>(numColumns);
    for (int c = 0; c < numColumns; c++) {
        row.add(null);
    }
    outputFields = new Object[numColumns];
    outputRowText = new Text();
}

---

From source file:org.openrdf.repository.sparql.query.SPARQLQuery.java

protected Set<String> getBindingNames() {
    if (bindings.size() == 0)
        return Collections.EMPTY_SET;
    Set<String> names = new HashSet<String>();
    String qry = query;//from  ww w .  j ava2  s.  c  o  m
    int b = qry.indexOf('{');
    String select = qry.substring(0, b);
    for (String name : bindings.getBindingNames()) {
        String replacement = getReplacement(bindings.getValue(name));
        if (replacement != null) {
            String pattern = ".*[\\?\\$]" + name + "\\W.*";
            if (Pattern.compile(pattern, Pattern.MULTILINE | Pattern.DOTALL).matcher(select).matches()) {
                names.add(name);
            }
        }
    }
    return names;
}

---

From source file:fr.dudie.acrachilisync.tools.upgrade.IssueDescriptionReaderV1.java

/**
 * Extracts the list of bug occurrences from the description.
 * //from  w  w  w . ja  va 2s . co  m
 * @param pDescription
 *            the issue description
 * @param pStacktraceMD5
 *            the stacktrace MD5 hash the issue is related to
 * @return the ACRA bug occurrences listed in the description
 * @throws IssueParseException
 *             malformed issue description
 */
private Map<String, Date> parseAcraOccurrencesTable(final String pDescription, final String pStacktraceMD5)
        throws IssueParseException {

    final Map<String, Date> occur = new HashMap<String, Date>();

    // escape braces { and } to use strings in regexp
    final String header = IssueDescriptionUtilsV1.getOccurrencesTableHeader();
    final String escHeader = Pattern.quote(header);

    // regexp to find occurrences tables
    final Pattern p = Pattern.compile(escHeader + IssueDescriptionUtilsV1.EOL + "(?:" + OCCURR_LINE_PATTERN
            + IssueDescriptionUtilsV1.EOL + "+)+", Pattern.DOTALL | Pattern.CASE_INSENSITIVE);
    final Matcher m = p.matcher(pDescription);

    if (m.find()) {
        // regexp to find occurrences lines
        final Pattern pLine = Pattern.compile(OCCURR_LINE_PATTERN);
        final Matcher mLine = pLine.matcher(m.group());
        while (mLine.find()) {
            final StringTokenizer line = new StringTokenizer(mLine.group(), "|");
            final String acraReportId = line.nextToken();
            final String acraUserCrashDate = line.nextToken();
            try {
                occur.put(acraReportId, IssueDescriptionUtilsV1.parseDate(acraUserCrashDate));
            } catch (final ParseException e) {
                throw new IssueParseException("Unable to parse user crash date of ACRA report " + acraReportId,
                        e);
            }
        }
    } else {
        throw new IssueParseException("No crash occurrence table found in the description");
    }

    if (m.find()) {
        throw new IssueParseException("More than 1 occurrence table found in the description");
    }

    if (MapUtils.isEmpty(occur)) {
        throw new IssueParseException("0 user crash occurrence found in the description");
    }

    return occur;
}

---

From source file:org.languagetool.tools.RuleAsXmlSerializerTest.java

@Test
public void testRuleMatchesToXML() throws IOException {
    final List<RuleMatch> matches = new ArrayList<>();
    final String text = "This is an test sentence. Here's another sentence with more text.";
    final FakeRule rule = new FakeRule();
    final RuleMatch match = new RuleMatch(rule, 8, 10, "myMessage");
    match.setColumn(99);/*w  ww. jav  a2 s  .c  om*/
    match.setEndColumn(100);
    match.setLine(44);
    match.setEndLine(45);
    matches.add(match);
    final String xml = SERIALIZER.ruleMatchesToXml(matches, text, 5, NORMAL_XML, LANG,
            Collections.<String>emptyList());
    assertTrue(xml.startsWith("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"));
    final Pattern matchesPattern = Pattern.compile(".*<matches software=\"LanguageTool\" version=\""
            + JLanguageTool.VERSION + "\" buildDate=\".*?\">.*", Pattern.DOTALL);
    final Matcher matcher = matchesPattern.matcher(xml);
    assertTrue("Did not find expected '<matches>' element, got: " + xml, matcher.matches());
    assertTrue(xml.contains(">\n"
            + "<error fromy=\"44\" fromx=\"98\" toy=\"45\" tox=\"99\" ruleId=\"FAKE_ID\" msg=\"myMessage\" "
            + "replacements=\"\" context=\"...s is an test...\" contextoffset=\"8\" offset=\"8\" errorlength=\"2\" "
            + "locqualityissuetype=\"misspelling\"/>\n" + "</matches>\n"));
}

---

From source file:stroom.xml.converter.ds3.ConfigFilter.java

@Override
public void startElement(String uri, String localName, String qName, Attributes atts) throws SAXException {
    if (localName.equals(XML_ELEMENT_DATA_SPLITTER)) {
        inRoot = true;/*  ww  w. j av a 2s .com*/
        if (parentDeque.peek().getNodeType() == NodeType.ROOT) {
            final RootFactory rootFactory = (RootFactory) parentDeque.peek();
            rootFactory.setBufferSize(getInt(atts, XML_ATTRIBUTE_BUFFER_SIZE, RootFactory.DEFAULT_BUFFER_SIZE));
            rootFactory.setIgnoreErrors(getIgnoreErorrs(atts));
        }

    } else if (!inRoot) {
        throw new SAXException("Unknown root element \"" + localName + "\"");

    } else if (localName.equals(XML_ELEMENT_SPLIT)) {
        final String id = atts.getValue(XML_ATTRIBUTE_ID);
        final String delimiter = unescape(atts.getValue(XML_ATTRIBUTE_DELIMITER));
        final String escape = atts.getValue(XML_ATTRIBUTE_ESCAPE);
        final String containerStart = atts.getValue(XML_ATTRIBUTE_CONTAINER_START);
        final String containerEnd = atts.getValue(XML_ATTRIBUTE_CONTAINER_END);

        final NodeFactory parent = parentDeque.peek();
        final NodeFactory node = new SplitFactory(parent, id, getMinMatch(atts), getMaxMatch(atts),
                getOnlyMatch(atts), delimiter, escape, containerStart, containerEnd);
        parentDeque.push(node);

    } else if (localName.equals(XML_ELEMENT_REGEX)) {
        final String id = atts.getValue(XML_ATTRIBUTE_ID);
        final String pattern = atts.getValue(XML_ATTRIBUTE_PATTERN);
        final boolean caseInsensitive = getBool(atts, XML_ATTRIBUTE_CASE_INSENSITIVE, false);
        final boolean dotAll = getBool(atts, XML_ATTRIBUTE_DOT_ALL, false);
        final int advance = getInt(atts, XML_ATTRIBUTE_ADVANCE, -1);

        int flags = 0;
        if (caseInsensitive) {
            flags += Pattern.CASE_INSENSITIVE;
        }
        if (dotAll) {
            flags += Pattern.DOTALL;
        }

        final NodeFactory parent = parentDeque.peek();
        final NodeFactory node = new RegexFactory(parent, id, getMinMatch(atts), getMaxMatch(atts),
                getOnlyMatch(atts), advance, pattern, flags);
        parentDeque.push(node);

    } else if (localName.equals(XML_ELEMENT_ALL)) {
        final String id = atts.getValue(XML_ATTRIBUTE_ID);

        final NodeFactory parent = parentDeque.peek();
        final NodeFactory node = new AllFactory(parent, id);
        parentDeque.push(node);

    } else if (localName.equals(XML_ELEMENT_GROUP)) {
        final String id = atts.getValue(XML_ATTRIBUTE_ID);
        final String value = atts.getValue(XML_ATTRIBUTE_VALUE);

        final NodeFactory parent = parentDeque.peek();
        final NodeFactory node = new GroupFactory(parent, id, value, getReverse(atts), getMatchOrder(atts),
                getIgnoreErorrs(atts));
        parentDeque.push(node);

    } else if (localName.equals(XML_ELEMENT_VAR)) {
        final String id = atts.getValue(XML_ATTRIBUTE_ID);

        final NodeFactory parent = parentDeque.peek();
        final NodeFactory node = new VarFactory(parent, id);
        parentDeque.push(node);

    } else if (localName.equals(XML_ELEMENT_DATA)) {
        final String id = atts.getValue(XML_ATTRIBUTE_ID);
        final String name = atts.getValue(XML_ATTRIBUTE_NAME);
        final String value = atts.getValue(XML_ATTRIBUTE_VALUE);

        final NodeFactory parent = parentDeque.peek();
        final NodeFactory node = new DataFactory(parent, id, name, value);
        parentDeque.push(node);
    }

    super.startElement(uri, localName, qName, atts);
}

---

From source file:org.geotools.data.couchdb.client.CouchDBUtils.java

public static String stripComments(String json) {
    Pattern pat = Pattern.compile("/\\*(?:.)*?\\*/", Pattern.MULTILINE | Pattern.DOTALL);
    return pat.matcher(json).replaceAll("");
}

---

From source file:net.riezebos.thoth.configuration.persistence.dbs.DDLExecuter.java

protected String applyDialect(String command) {
    String timestampRe = "\\{fn CURRENT_TIMESTAMP\\}";
    command = command.replaceAll(timestampRe, databaseIdiom.getCurrentTimeDDL());

    // Only translate create/alter statements
    boolean createOrAlter = command.toLowerCase().startsWith("create")
            || command.toLowerCase().startsWith("alter") || command.toLowerCase().startsWith("rename")
            || command.toLowerCase().startsWith("drop");
    if (!createOrAlter)
        return command;

    for (TranslationPair wa : translations) {
        if (!wa.exclude(command)) {
            command = ThothUtil.replaceWord(command + " ", wa.getFrom(), wa.getTo(), SEPARATORS).trim();
        }/*w w  w. java2s  .  c  o  m*/
    }

    for (TranslationPair wa : workarounds) {
        Pattern pattern = Pattern.compile(wa.getFrom(), Pattern.CASE_INSENSITIVE | Pattern.DOTALL);
        command = pattern.matcher(command).replaceAll(wa.getTo());
    }

    command = databaseIdiom.applyDialect(command);
    return command;
}

---

• «
• 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
• 40
• 41
• 42
• 43
• 44
• »