Java Code Examples for java.util.regex.Pattern#UNIX_LINES

The following examples show how to use java.util.regex.Pattern#UNIX_LINES . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: TRegex.java    From sql-layer with GNU Affero General Public License v3.0 6 votes vote down vote up
private static int parseOptionFlags(String opts) {
    int flags = 0;
    for(int i = 0; i < opts.length(); ++i) {
        switch(opts.charAt(i)) {
            // Standard 'special construct match flags'
            case 'i': flags |= Pattern.CASE_INSENSITIVE; break;
            case 'd': flags |= Pattern.UNIX_LINES; break;
            case 'm': flags |= Pattern.MULTILINE; break;
            case 's': flags |= Pattern.DOTALL; break;
            case 'u': flags |= Pattern.UNICODE_CASE; break;
            case 'x': flags |= Pattern.COMMENTS; break;
            // And pick a letters for remaining flags
            case 'l': flags |= Pattern.LITERAL; break;
            case 'c': flags |= Pattern.CANON_EQ; break;
            default:
                throw new InvalidParameterValueException("Invalid option: " + opts.charAt(i));
        }
    }
    return flags;
}
 
Example 2
Source File: PropertyPatternMessageColorizer.java    From otroslogviewer with Apache License 2.0 6 votes vote down vote up
public void init(InputStream in) throws ConfigurationException {
  propertiesConfiguration = new PropertiesConfiguration();
  propertiesConfiguration.setDelimiterParsingDisabled(true);
  propertiesConfiguration.load(in, "UTF-8");
  configuration = new DataConfiguration(propertiesConfiguration);
  configuration.setDelimiterParsingDisabled(true);
  String pa = configuration.getString(PROP_PATTERN);
  int flags = 0;
  flags = flags | (configuration.getBoolean(PROP_PATTERN_CANON_EQ, false) ? Pattern.CANON_EQ : 0);
  flags = flags | (configuration.getBoolean(PROP_PATTERN_CASE_INSENSITIVE, false) ? Pattern.CASE_INSENSITIVE : 0);
  flags = flags | (configuration.getBoolean(PROP_PATTERN_COMMENTS, false) ? Pattern.COMMENTS : 0);
  flags = flags | (configuration.getBoolean(PROP_PATTERN_DOTALL, false) ? Pattern.DOTALL : 0);
  flags = flags | (configuration.getBoolean(PROP_PATTERN_LITERAL, false) ? Pattern.LITERAL : 0);
  flags = flags | (configuration.getBoolean(PROP_PATTERN_MULTILINE, false) ? Pattern.MULTILINE : 0);
  flags = flags | (configuration.getBoolean(PROP_PATTERN_UNICODE_CASE, false) ? Pattern.UNICODE_CASE : 0);
  flags = flags | (configuration.getBoolean(PROP_PATTERN_UNIX_LINES, false) ? Pattern.UNIX_LINES : 0);

  pattern = Pattern.compile(pa, flags);
  groupCount = countGroups(pattern);
  name = configuration.getString(PROP_NAME, "NAME NOT SET!");
  description = configuration.getString(PROP_DESCRIPTION, "DESCRIPTION NOT SET!");
  testMessage = configuration.getString(PROP_TEST_MESSAGE, "");

}
 
Example 3
Source File: SearchPanel.java    From RegexReplacer with MIT License 6 votes vote down vote up
private int getRegexFlag() {
	int flag = 0;
	if (unixLinesCkb.isSelected())
		flag |= Pattern.UNIX_LINES;
	if (caseInsensitiveCkb.isSelected())
		flag |= Pattern.CASE_INSENSITIVE;
	if (commentsCkb.isSelected())
		flag |= Pattern.COMMENTS;
	if (multilineCkb.isSelected())
		flag |= Pattern.MULTILINE;
	if (literalCkb.isSelected())
		flag |= Pattern.LITERAL;
	if (dotallCkb.isSelected())
		flag |= Pattern.DOTALL;
	if (unicodeCaseCkb.isSelected())
		flag |= Pattern.UNICODE_CASE;
	if (canonEqCkb.isSelected())
		flag |= Pattern.CANON_EQ;
	return flag;
}
 
Example 4
Source File: ExtractText.java    From localization_nifi with Apache License 2.0 5 votes vote down vote up
int getCompileFlags(ProcessContext context) {
    int flags = (context.getProperty(UNIX_LINES).asBoolean() ? Pattern.UNIX_LINES : 0)
            | (context.getProperty(CASE_INSENSITIVE).asBoolean() ? Pattern.CASE_INSENSITIVE : 0)
            | (context.getProperty(COMMENTS).asBoolean() ? Pattern.COMMENTS : 0)
            | (context.getProperty(MULTILINE).asBoolean() ? Pattern.MULTILINE : 0)
            | (context.getProperty(LITERAL).asBoolean() ? Pattern.LITERAL : 0)
            | (context.getProperty(DOTALL).asBoolean() ? Pattern.DOTALL : 0)
            | (context.getProperty(UNICODE_CASE).asBoolean() ? Pattern.UNICODE_CASE : 0)
            | (context.getProperty(CANON_EQ).asBoolean() ? Pattern.CANON_EQ : 0)
            | (context.getProperty(UNICODE_CHARACTER_CLASS).asBoolean() ? Pattern.UNICODE_CHARACTER_CLASS : 0);
    return flags;
}
 
Example 5
Source File: RegexMatcher.java    From Elasticsearch with Apache License 2.0 5 votes vote down vote up
public static int parseFlags(@Nullable BytesRef flagsString) {
    int flags = 0;
    if (flagsString == null) {
        return flags;
    }
    for (char flag : flagsString.utf8ToString().toCharArray()) {
        switch (flag) {
            case 'i':
                flags = flags | Pattern.CASE_INSENSITIVE;
                break;
            case 'u':
                flags = flags | Pattern.UNICODE_CASE;
                break;
            case 'U':
                flags = flags | Pattern.UNICODE_CHARACTER_CLASS;
                break;
            case 's':
                flags = flags | Pattern.DOTALL;
                break;
            case 'm':
                flags = flags | Pattern.MULTILINE;
                break;
            case 'x':
                flags = flags | Pattern.COMMENTS;
                break;
            case 'd':
                flags = flags | Pattern.UNIX_LINES;
                break;
            default:
                break;
        }
    }

    return flags;
}
 
Example 6
Source File: Regex.java    From Elasticsearch with Apache License 2.0 5 votes vote down vote up
public static int flagsFromString(String flags) {
    int pFlags = 0;
    for (String s : Strings.delimitedListToStringArray(flags, "|")) {
        if (s.isEmpty()) {
            continue;
        }
        s = s.toUpperCase(Locale.ROOT);
        if ("CASE_INSENSITIVE".equals(s)) {
            pFlags |= Pattern.CASE_INSENSITIVE;
        } else if ("MULTILINE".equals(s)) {
            pFlags |= Pattern.MULTILINE;
        } else if ("DOTALL".equals(s)) {
            pFlags |= Pattern.DOTALL;
        } else if ("UNICODE_CASE".equals(s)) {
            pFlags |= Pattern.UNICODE_CASE;
        } else if ("CANON_EQ".equals(s)) {
            pFlags |= Pattern.CANON_EQ;
        } else if ("UNIX_LINES".equals(s)) {
            pFlags |= Pattern.UNIX_LINES;
        } else if ("LITERAL".equals(s)) {
            pFlags |= Pattern.LITERAL;
        } else if ("COMMENTS".equals(s)) {
            pFlags |= Pattern.COMMENTS;
        } else if ("UNICODE_CHAR_CLASS".equals(s)) {
            pFlags |= UNICODE_CHARACTER_CLASS;
        } else {
            throw new IllegalArgumentException("Unknown regex flag [" + s + "]");
        }
    }
    return pFlags;
}
 
Example 7
Source File: Regex.java    From Elasticsearch with Apache License 2.0 5 votes vote down vote up
public static String flagsToString(int flags) {
    StringBuilder sb = new StringBuilder();
    if ((flags & Pattern.CASE_INSENSITIVE) != 0) {
        sb.append("CASE_INSENSITIVE|");
    }
    if ((flags & Pattern.MULTILINE) != 0) {
        sb.append("MULTILINE|");
    }
    if ((flags & Pattern.DOTALL) != 0) {
        sb.append("DOTALL|");
    }
    if ((flags & Pattern.UNICODE_CASE) != 0) {
        sb.append("UNICODE_CASE|");
    }
    if ((flags & Pattern.CANON_EQ) != 0) {
        sb.append("CANON_EQ|");
    }
    if ((flags & Pattern.UNIX_LINES) != 0) {
        sb.append("UNIX_LINES|");
    }
    if ((flags & Pattern.LITERAL) != 0) {
        sb.append("LITERAL|");
    }
    if ((flags & Pattern.COMMENTS) != 0) {
        sb.append("COMMENTS|");
    }
    if ((flags & UNICODE_CHARACTER_CLASS) != 0) {
        sb.append("UNICODE_CHAR_CLASS|");
    }
    return sb.toString();
}
 
Example 8
Source File: TermsComponentTest.java    From lucene-solr with Apache License 2.0 5 votes vote down vote up
@Test
public void testRegexpFlagParsing() {
    ModifiableSolrParams params = new ModifiableSolrParams();
    params.add(TermsParams.TERMS_REGEXP_FLAG, "case_insensitive", "literal", "comments", "multiline", "unix_lines",
            "unicode_case", "dotall", "canon_eq");
    try (TermsComponent termsComponent = new TermsComponent()) {
      int flags = termsComponent.resolveRegexpFlags(params);
      int expected = Pattern.CASE_INSENSITIVE | Pattern.LITERAL | Pattern.COMMENTS | Pattern.MULTILINE | Pattern.UNIX_LINES
          | Pattern.UNICODE_CASE | Pattern.DOTALL | Pattern.CANON_EQ;
      assertEquals(expected, flags);
    } catch (IOException e) {
      fail("Error closing TermsComponent");
    }
}
 
Example 9
Source File: ShellCommands.java    From DotCi with MIT License 5 votes vote down vote up
public Pattern regexp(String re) {
    final int n = re.length() - 1;
    final int flags = Pattern.UNIX_LINES | Pattern.MULTILINE;
    if (re.charAt(0) != '^') {
        re = ".*" + re;
    }
    if (re.charAt(n) != '$') {
        re = re + ".*";
    }
    return Pattern.compile(re, flags);
}
 
Example 10
Source File: ExtractText.java    From nifi with Apache License 2.0 5 votes vote down vote up
int getCompileFlags(ProcessContext context) {
    int flags = (context.getProperty(UNIX_LINES).asBoolean() ? Pattern.UNIX_LINES : 0)
            | (context.getProperty(CASE_INSENSITIVE).asBoolean() ? Pattern.CASE_INSENSITIVE : 0)
            | (context.getProperty(COMMENTS).asBoolean() ? Pattern.COMMENTS : 0)
            | (context.getProperty(MULTILINE).asBoolean() ? Pattern.MULTILINE : 0)
            | (context.getProperty(LITERAL).asBoolean() ? Pattern.LITERAL : 0)
            | (context.getProperty(DOTALL).asBoolean() ? Pattern.DOTALL : 0)
            | (context.getProperty(UNICODE_CASE).asBoolean() ? Pattern.UNICODE_CASE : 0)
            | (context.getProperty(CANON_EQ).asBoolean() ? Pattern.CANON_EQ : 0)
            | (context.getProperty(UNICODE_CHARACTER_CLASS).asBoolean() ? Pattern.UNICODE_CHARACTER_CLASS : 0);
    return flags;
}
 
Example 11
Source File: Regex.java    From crate with Apache License 2.0 5 votes vote down vote up
public static int flagsFromString(String flags) {
    int pFlags = 0;
    for (String s : Strings.delimitedListToStringArray(flags, "|")) {
        if (s.isEmpty()) {
            continue;
        }
        s = s.toUpperCase(Locale.ROOT);
        if ("CASE_INSENSITIVE".equals(s)) {
            pFlags |= Pattern.CASE_INSENSITIVE;
        } else if ("MULTILINE".equals(s)) {
            pFlags |= Pattern.MULTILINE;
        } else if ("DOTALL".equals(s)) {
            pFlags |= Pattern.DOTALL;
        } else if ("UNICODE_CASE".equals(s)) {
            pFlags |= Pattern.UNICODE_CASE;
        } else if ("CANON_EQ".equals(s)) {
            pFlags |= Pattern.CANON_EQ;
        } else if ("UNIX_LINES".equals(s)) {
            pFlags |= Pattern.UNIX_LINES;
        } else if ("LITERAL".equals(s)) {
            pFlags |= Pattern.LITERAL;
        } else if ("COMMENTS".equals(s)) {
            pFlags |= Pattern.COMMENTS;
        } else if (("UNICODE_CHAR_CLASS".equals(s)) || ("UNICODE_CHARACTER_CLASS".equals(s))) {
            pFlags |= UNICODE_CHARACTER_CLASS;
        } else {
            throw new IllegalArgumentException("Unknown regex flag [" + s + "]");
        }
    }
    return pFlags;
}
 
Example 12
Source File: RegexMatcher.java    From crate with Apache License 2.0 5 votes vote down vote up
public static int parseFlags(@Nullable String flagsString) {
    int flags = 0;
    if (flagsString == null) {
        return flags;
    }
    for (char flag : flagsString.toCharArray()) {
        switch (flag) {
            case 'i':
                flags = flags | Pattern.CASE_INSENSITIVE;
                break;
            case 'u':
                flags = flags | Pattern.UNICODE_CASE;
                break;
            case 'U':
                flags = flags | Pattern.UNICODE_CHARACTER_CLASS;
                break;
            case 's':
                flags = flags | Pattern.DOTALL;
                break;
            case 'm':
                flags = flags | Pattern.MULTILINE;
                break;
            case 'x':
                flags = flags | Pattern.COMMENTS;
                break;
            case 'd':
                flags = flags | Pattern.UNIX_LINES;
                break;
            case ' ':
            case 'g':
                // handled in isGlobalFunction
                break;
            default:
                throw new IllegalArgumentException("The regular expression flag is unknown: " + flag);
        }
    }

    return flags;
}
 
Example 13
Source File: StrictEvaluationStrategy.java    From rdf4j with BSD 3-Clause "New" or "Revised" License 4 votes vote down vote up
/**
 * Determines whether the two operands match according to the <code>regex</code> operator.
 *
 * @return <tt>true</tt> if the operands match according to the <tt>regex</tt> operator, <tt>false</tt> otherwise.
 */
public Value evaluate(Regex node, BindingSet bindings)
		throws QueryEvaluationException {
	Value arg = evaluate(node.getArg(), bindings);
	Value parg = evaluate(node.getPatternArg(), bindings);
	Value farg = null;
	ValueExpr flagsArg = node.getFlagsArg();
	if (flagsArg != null) {
		farg = evaluate(flagsArg, bindings);
	}

	if (QueryEvaluationUtil.isStringLiteral(arg) && QueryEvaluationUtil.isSimpleLiteral(parg)
			&& (farg == null || QueryEvaluationUtil.isSimpleLiteral(farg))) {
		String text = ((Literal) arg).getLabel();
		String ptn = ((Literal) parg).getLabel();
		String flags = "";
		if (farg != null) {
			flags = ((Literal) farg).getLabel();
		}
		// TODO should this Pattern be cached?
		int f = 0;
		for (char c : flags.toCharArray()) {
			switch (c) {
			case 's':
				f |= Pattern.DOTALL;
				break;
			case 'm':
				f |= Pattern.MULTILINE;
				break;
			case 'i':
				f |= Pattern.CASE_INSENSITIVE;
				f |= Pattern.UNICODE_CASE;
				break;
			case 'x':
				f |= Pattern.COMMENTS;
				break;
			case 'd':
				f |= Pattern.UNIX_LINES;
				break;
			case 'u':
				f |= Pattern.UNICODE_CASE;
				break;
			case 'q':
				f |= Pattern.LITERAL;
				break;
			default:
				throw new ValueExprEvaluationException(flags);
			}
		}
		Pattern pattern = Pattern.compile(ptn, f);
		boolean result = pattern.matcher(text).find();
		return BooleanLiteral.valueOf(result);
	}

	throw new ValueExprEvaluationException();
}
 
Example 14
Source File: HalyardValueExprEvaluation.java    From Halyard with Apache License 2.0 4 votes vote down vote up
/**
 * Determines whether the two operands match according to the <code>regex</code> operator.
 *
 * @return <tt>true</tt> if the operands match according to the
 * <tt>regex</tt> operator, <tt>false</tt> otherwise.
 */
private Value evaluate(Regex node, BindingSet bindings) throws ValueExprEvaluationException, QueryEvaluationException {
    Value arg = evaluate(node.getArg(), bindings);
    Value parg = evaluate(node.getPatternArg(), bindings);
    Value farg = null;
    ValueExpr flagsArg = node.getFlagsArg();
    if (flagsArg != null) {
        farg = evaluate(flagsArg, bindings);
    }
    if (QueryEvaluationUtil.isStringLiteral(arg) && QueryEvaluationUtil.isSimpleLiteral(parg)
            && (farg == null || QueryEvaluationUtil.isSimpleLiteral(farg))) {
        String text = ((Literal) arg).getLabel();
        String ptn = ((Literal) parg).getLabel();
        String flags = "";
        if (farg != null) {
            flags = ((Literal) farg).getLabel();
        }
        // TODO should this Pattern be cached?
        int f = 0;
        for (char c : flags.toCharArray()) {
            switch (c) {
                case 's':
                    f |= Pattern.DOTALL;
                    break;
                case 'm':
                    f |= Pattern.MULTILINE;
                    break;
                case 'i':
                    f |= Pattern.CASE_INSENSITIVE;
                    f |= Pattern.UNICODE_CASE;
                    break;
                case 'x':
                    f |= Pattern.COMMENTS;
                    break;
                case 'd':
                    f |= Pattern.UNIX_LINES;
                    break;
                case 'u':
                    f |= Pattern.UNICODE_CASE;
                    break;
                default:
                    throw new ValueExprEvaluationException(flags);
            }
        }
        Pattern pattern = Pattern.compile(ptn, f);
        boolean result = pattern.matcher(text).find();
        return BooleanLiteral.valueOf(result);
    }
    throw new ValueExprEvaluationException();
}
 
Example 15
Source File: RegexBOp.java    From database with GNU General Public License v2.0 4 votes vote down vote up
private static Pattern getPattern(final Value parg, final Value farg)
            throws IllegalArgumentException {
        
        if (debug) {
            log.debug("regex pattern: " + parg);
            log.debug("regex flags: " + farg);
        }
        
        //BLZG-1200 Literals with language types are not included in REGEX
        if (QueryEvaluationUtil.isPlainLiteral(parg)
                && (farg == null || QueryEvaluationUtil.isPlainLiteral(farg))) {

            final String ptn = ((Literal) parg).getLabel();
            String flags = "";
            if (farg != null) {
                flags = ((Literal)farg).getLabel();
            }
            int f = 0;
            for (char c : flags.toCharArray()) {
                // See https://www.w3.org/TR/xpath-functions/#flags
                switch (c) {
                    case 's':
                        f |= Pattern.DOTALL;
                        break;
                    case 'm':
                        f |= Pattern.MULTILINE;
                        break;
                    case 'i': {
                    /*
                     * The SPARQL REGEX operator is based on the XQuery REGEX
                     * operator. That operator should be Unicode clean by
                     * default. Therefore, when case-folding is specified, we
                     * also need to include the UNICODE_CASE option.
                     * 
                     * @see <a
                     * href="https://sourceforge.net/apps/trac/bigdata/ticket/655"
                     * > SPARQL REGEX operator does not perform case-folding
                     * correctly for Unicode data </a>
                     */
                        f |= Pattern.CASE_INSENSITIVE;
                        f |= Pattern.UNICODE_CASE;
                        break;
                    }
                    case 'x':
                        f |= Pattern.COMMENTS;
                        break;
                    case 'd':
                        f |= Pattern.UNIX_LINES;
                        break;
                    case 'u': // Implicit with 'i' flag.
//                      f |= Pattern.UNICODE_CASE;
                        break;
                    case 'q':
                        f |= Pattern.LITERAL;
                        break;
                    default:
                        throw new IllegalArgumentException();
                }
            }
            final Pattern pattern = Pattern.compile(ptn, f);
            return pattern;
        }
        
        throw new IllegalArgumentException();
        
    }
 
Example 16
Source File: ReplaceBOp.java    From database with GNU General Public License v2.0 4 votes vote down vote up
private static Pattern getPattern(final Value pattern, final Value flags) 
		throws IllegalArgumentException {
	
	if (!QueryEvaluationUtil.isSimpleLiteral(pattern)) {
		throw new IllegalArgumentException(
				"incompatible operand for REPLACE: " + pattern);
	}

	String flagString = null;
	if (flags != null) {
		if (!QueryEvaluationUtil.isSimpleLiteral(flags)) {
			throw new IllegalArgumentException(
					"incompatible operand for REPLACE: " + flags);
		}
		flagString = ((Literal) flags).getLabel();
	}

	String patternString = ((Literal) pattern).getLabel();

	int f = 0;
	if (flagString != null) {
		for (char c : flagString.toCharArray()) {
               // See https://www.w3.org/TR/xpath-functions/#flags
			switch (c) {
			case 's':
				f |= Pattern.DOTALL;
				break;
			case 'm':
				f |= Pattern.MULTILINE;
				break;
			case 'i':
				f |= Pattern.CASE_INSENSITIVE;
				break;
			case 'x':
				f |= Pattern.COMMENTS;
				break;
			case 'd':
				f |= Pattern.UNIX_LINES;
				break;
			case 'u':
				f |= Pattern.UNICODE_CASE;
				break;
			case 'q':
				f |= Pattern.LITERAL;
				break;
			default:
				throw new IllegalArgumentException(flagString);
			}
		}
	}

	Pattern p = Pattern.compile(patternString, f);
	
	return p;
	
}