Pattern helper : Pattern « Regular Expressions « Java
Pattern helper
/*
* Static String formatting and query routines.
* Copyright (C) 2001-2005 Stephen Ostermiller
* http://ostermiller.org/contact.pl?regarding=Java+Utilities
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* See COPYING.TXT for details.
*/
import java.util.HashMap;
import java.util.regex.Pattern;
/**
* Utilities for String formatting, manipulation, and queries.
* More information about this class is available from <a target="_top" href=
* "http://ostermiller.org/utils/StringHelper.html">ostermiller.org</a>.
*
* @author Stephen Ostermiller http://ostermiller.org/contact.pl?regarding=Java+Utilities
* @since ostermillerutils 1.00.00
*/
public class StringHelper {
/**
* Build a regular expression that is each of the terms or'd together.
*
* @param terms a list of search terms.
* @param sb place to build the regular expression.
* @throws IllegalArgumentException if the length of terms is zero.
*
* @since ostermillerutils 1.02.25
*/
private static void buildFindAnyPattern(String[] terms, StringBuffer sb){
if (terms.length == 0) throw new IllegalArgumentException("There must be at least one term to find.");
sb.append("(?:");
for (int i=0; i<terms.length; i++){
if (i>0) sb.append("|");
sb.append("(?:");
sb.append(escapeRegularExpressionLiteral(terms[i]));
sb.append(")");
}
sb.append(")");
}
/**
* Compile a pattern that can will match a string if the string
* contains any of the given terms.
* <p>
* Usage:<br>
* <code>boolean b = getContainsAnyPattern(terms).matcher(s).matches();</code>
* <p>
* If multiple strings are matched against the same set of terms,
* it is more efficient to reuse the pattern returned by this function.
*
* @param terms Array of search strings.
* @return Compiled pattern that can be used to match a string to see if it contains any of the terms.
*
* @since ostermillerutils 1.02.25
*/
public static Pattern getContainsAnyPattern(String[] terms){
StringBuffer sb = new StringBuffer();
sb.append("(?s).*");
buildFindAnyPattern(terms, sb);
sb.append(".*");
return Pattern.compile(sb.toString());
}
/**
* Compile a pattern that can will match a string if the string
* equals any of the given terms.
* <p>
* Usage:<br>
* <code>boolean b = getEqualsAnyPattern(terms).matcher(s).matches();</code>
* <p>
* If multiple strings are matched against the same set of terms,
* it is more efficient to reuse the pattern returned by this function.
*
* @param terms Array of search strings.
* @return Compiled pattern that can be used to match a string to see if it equals any of the terms.
*
* @since ostermillerutils 1.02.25
*/
public static Pattern getEqualsAnyPattern(String[] terms){
StringBuffer sb = new StringBuffer();
sb.append("(?s)\\A");
buildFindAnyPattern(terms, sb);
sb.append("\\z");
return Pattern.compile(sb.toString());
}
/**
* Compile a pattern that can will match a string if the string
* starts with any of the given terms.
* <p>
* Usage:<br>
* <code>boolean b = getStartsWithAnyPattern(terms).matcher(s).matches();</code>
* <p>
* If multiple strings are matched against the same set of terms,
* it is more efficient to reuse the pattern returned by this function.
*
* @param terms Array of search strings.
* @return Compiled pattern that can be used to match a string to see if it starts with any of the terms.
*
* @since ostermillerutils 1.02.25
*/
public static Pattern getStartsWithAnyPattern(String[] terms){
StringBuffer sb = new StringBuffer();
sb.append("(?s)\\A");
buildFindAnyPattern(terms, sb);
sb.append(".*");
return Pattern.compile(sb.toString());
}
/**
* Compile a pattern that can will match a string if the string
* ends with any of the given terms.
* <p>
* Usage:<br>
* <code>boolean b = getEndsWithAnyPattern(terms).matcher(s).matches();</code>
* <p>
* If multiple strings are matched against the same set of terms,
* it is more efficient to reuse the pattern returned by this function.
*
* @param terms Array of search strings.
* @return Compiled pattern that can be used to match a string to see if it ends with any of the terms.
*
* @since ostermillerutils 1.02.25
*/
public static Pattern getEndsWithAnyPattern(String[] terms){
StringBuffer sb = new StringBuffer();
sb.append("(?s).*");
buildFindAnyPattern(terms, sb);
sb.append("\\z");
return Pattern.compile(sb.toString());
}
/**
* Compile a pattern that can will match a string if the string
* contains any of the given terms.
* <p>
* Case is ignored when matching using Unicode case rules.
* <p>
* Usage:<br>
* <code>boolean b = getContainsAnyPattern(terms).matcher(s).matches();</code>
* <p>
* If multiple strings are matched against the same set of terms,
* it is more efficient to reuse the pattern returned by this function.
*
* @param terms Array of search strings.
* @return Compiled pattern that can be used to match a string to see if it contains any of the terms.
*
* @since ostermillerutils 1.02.25
*/
public static Pattern getContainsAnyIgnoreCasePattern(String[] terms){
StringBuffer sb = new StringBuffer();
sb.append("(?i)(?u)(?s).*");
buildFindAnyPattern(terms, sb);
sb.append(".*");
return Pattern.compile(sb.toString());
}
/**
* Compile a pattern that can will match a string if the string
* equals any of the given terms.
* <p>
* Case is ignored when matching using Unicode case rules.
* <p>
* Usage:<br>
* <code>boolean b = getEqualsAnyPattern(terms).matcher(s).matches();</code>
* <p>
* If multiple strings are matched against the same set of terms,
* it is more efficient to reuse the pattern returned by this function.
*
* @param terms Array of search strings.
* @return Compiled pattern that can be used to match a string to see if it equals any of the terms.
*
* @since ostermillerutils 1.02.25
*/
public static Pattern getEqualsAnyIgnoreCasePattern(String[] terms){
StringBuffer sb = new StringBuffer();
sb.append("(?i)(?u)(?s)\\A");
buildFindAnyPattern(terms, sb);
sb.append("\\z");
return Pattern.compile(sb.toString());
}
/**
* Compile a pattern that can will match a string if the string
* starts with any of the given terms.
* <p>
* Case is ignored when matching using Unicode case rules.
* <p>
* Usage:<br>
* <code>boolean b = getStartsWithAnyPattern(terms).matcher(s).matches();</code>
* <p>
* If multiple strings are matched against the same set of terms,
* it is more efficient to reuse the pattern returned by this function.
*
* @param terms Array of search strings.
* @return Compiled pattern that can be used to match a string to see if it starts with any of the terms.
*
* @since ostermillerutils 1.02.25
*/
public static Pattern getStartsWithAnyIgnoreCasePattern(String[] terms){
StringBuffer sb = new StringBuffer();
sb.append("(?i)(?u)(?s)\\A");
buildFindAnyPattern(terms, sb);
sb.append(".*");
return Pattern.compile(sb.toString());
}
/**
* Compile a pattern that can will match a string if the string
* ends with any of the given terms.
* <p>
* Case is ignored when matching using Unicode case rules.
* <p>
* Usage:<br>
* <code>boolean b = getEndsWithAnyPattern(terms).matcher(s).matches();</code>
* <p>
* If multiple strings are matched against the same set of terms,
* it is more efficient to reuse the pattern returned by this function.
*
* @param terms Array of search strings.
* @return Compiled pattern that can be used to match a string to see if it ends with any of the terms.
*
* @since ostermillerutils 1.02.25
*/
public static Pattern getEndsWithAnyIgnoreCasePattern(String[] terms){
StringBuffer sb = new StringBuffer();
sb.append("(?i)(?u)(?s).*");
buildFindAnyPattern(terms, sb);
sb.append("\\z");
return Pattern.compile(sb.toString());
}
/**
* Tests to see if the given string contains any of the given terms.
* <p>
* This implementation is more efficient than the brute force approach
* of testing the string against each of the terms. It instead compiles
* a single regular expression that can test all the terms at once, and
* uses that expression against the string.
* <p>
* This is a convenience method. If multiple strings are tested against
* the same set of terms, it is more efficient not to compile the regular
* expression multiple times.
* @see #getContainsAnyPattern(String[])
*
* @param s String that may contain any of the given terms.
* @param terms list of substrings that may be contained in the given string.
* @return true iff one of the terms is a substring of the given string.
*
* @since ostermillerutils 1.02.25
*/
public static boolean containsAny(String s, String[] terms){
return getContainsAnyPattern(terms).matcher(s).matches();
}
/**
* Tests to see if the given string equals any of the given terms.
* <p>
* This implementation is more efficient than the brute force approach
* of testing the string against each of the terms. It instead compiles
* a single regular expression that can test all the terms at once, and
* uses that expression against the string.
* <p>
* This is a convenience method. If multiple strings are tested against
* the same set of terms, it is more efficient not to compile the regular
* expression multiple times.
* @see #getEqualsAnyPattern(String[])
*
* @param s String that may equal any of the given terms.
* @param terms list of strings that may equal the given string.
* @return true iff one of the terms is equal to the given string.
*
* @since ostermillerutils 1.02.25
*/
public static boolean equalsAny(String s, String[] terms){
return getEqualsAnyPattern(terms).matcher(s).matches();
}
/**
* Tests to see if the given string starts with any of the given terms.
* <p>
* This implementation is more efficient than the brute force approach
* of testing the string against each of the terms. It instead compiles
* a single regular expression that can test all the terms at once, and
* uses that expression against the string.
* <p>
* This is a convenience method. If multiple strings are tested against
* the same set of terms, it is more efficient not to compile the regular
* expression multiple times.
* @see #getStartsWithAnyPattern(String[])
*
* @param s String that may start with any of the given terms.
* @param terms list of strings that may start with the given string.
* @return true iff the given string starts with one of the given terms.
*
* @since ostermillerutils 1.02.25
*/
public static boolean startsWithAny(String s, String[] terms){
return getStartsWithAnyPattern(terms).matcher(s).matches();
}
/**
* Tests to see if the given string ends with any of the given terms.
* <p>
* This implementation is more efficient than the brute force approach
* of testing the string against each of the terms. It instead compiles
* a single regular expression that can test all the terms at once, and
* uses that expression against the string.
* <p>
* This is a convenience method. If multiple strings are tested against
* the same set of terms, it is more efficient not to compile the regular
* expression multiple times.
* @see #getEndsWithAnyPattern(String[])
*
* @param s String that may end with any of the given terms.
* @param terms list of strings that may end with the given string.
* @return true iff the given string ends with one of the given terms.
*
* @since ostermillerutils 1.02.25
*/
public static boolean endsWithAny(String s, String[] terms){
return getEndsWithAnyPattern(terms).matcher(s).matches();
}
/**
* Tests to see if the given string contains any of the given terms.
* <p>
* Case is ignored when matching using Unicode case rules.
* <p>
* This implementation is more efficient than the brute force approach
* of testing the string against each of the terms. It instead compiles
* a single regular expression that can test all the terms at once, and
* uses that expression against the string.
* <p>
* This is a convenience method. If multiple strings are tested against
* the same set of terms, it is more efficient not to compile the regular
* expression multiple times.
* @see #getContainsAnyIgnoreCasePattern(String[])
*
* @param s String that may contain any of the given terms.
* @param terms list of substrings that may be contained in the given string.
* @return true iff one of the terms is a substring of the given string.
*
* @since ostermillerutils 1.02.25
*/
public static boolean containsAnyIgnoreCase(String s, String[] terms){
return getContainsAnyIgnoreCasePattern(terms).matcher(s).matches();
}
/**
* Tests to see if the given string equals any of the given terms.
* <p>
* Case is ignored when matching using Unicode case rules.
* <p>
* This implementation is more efficient than the brute force approach
* of testing the string against each of the terms. It instead compiles
* a single regular expression that can test all the terms at once, and
* uses that expression against the string.
* <p>
* This is a convenience method. If multiple strings are tested against
* the same set of terms, it is more efficient not to compile the regular
* expression multiple times.
* @see #getEqualsAnyIgnoreCasePattern(String[])
*
* @param s String that may equal any of the given terms.
* @param terms list of strings that may equal the given string.
* @return true iff one of the terms is equal to the given string.
*
* @since ostermillerutils 1.02.25
*/
public static boolean equalsAnyIgnoreCase(String s, String[] terms){
return getEqualsAnyIgnoreCasePattern(terms).matcher(s).matches();
}
/**
* Tests to see if the given string starts with any of the given terms.
* <p>
* Case is ignored when matching using Unicode case rules.
* <p>
* This implementation is more efficient than the brute force approach
* of testing the string against each of the terms. It instead compiles
* a single regular expression that can test all the terms at once, and
* uses that expression against the string.
* <p>
* This is a convenience method. If multiple strings are tested against
* the same set of terms, it is more efficient not to compile the regular
* expression multiple times.
* @see #getStartsWithAnyIgnoreCasePattern(String[])
*
* @param s String that may start with any of the given terms.
* @param terms list of strings that may start with the given string.
* @return true iff the given string starts with one of the given terms.
*
* @since ostermillerutils 1.02.25
*/
public static boolean startsWithAnyIgnoreCase(String s, String[] terms){
return getStartsWithAnyIgnoreCasePattern(terms).matcher(s).matches();
}
/**
* Tests to see if the given string ends with any of the given terms.
* <p>
* Case is ignored when matching using Unicode case rules.
* <p>
* This implementation is more efficient than the brute force approach
* of testing the string against each of the terms. It instead compiles
* a single regular expression that can test all the terms at once, and
* uses that expression against the string.
* <p>
* This is a convenience method. If multiple strings are tested against
* the same set of terms, it is more efficient not to compile the regular
* expression multiple times.
* @see #getEndsWithAnyIgnoreCasePattern(String[])
*
* @param s String that may end with any of the given terms.
* @param terms list of strings that may end with the given string.
* @return true iff the given string ends with one of the given terms.
*
* @since ostermillerutils 1.02.25
*/
public static boolean endsWithAnyIgnoreCase(String s, String[] terms){
return getEndsWithAnyIgnoreCasePattern(terms).matcher(s).matches();
}
/**
* Escapes characters that have special meaning to
* regular expressions
*
* @param s String to be escaped
* @return escaped String
* @throws NullPointerException if s is null.
*
* @since ostermillerutils 1.02.25
*/
public static String escapeRegularExpressionLiteral(String s){
// According to the documentation in the Pattern class:
//
// The backslash character ('\') serves to introduce escaped constructs,
// as defined in the table above, as well as to quote characters that
// otherwise would be interpreted as unescaped constructs. Thus the
// expression \\ matches a single backslash and \{ matches a left brace.
//
// It is an error to use a backslash prior to any alphabetic character
// that does not denote an escaped construct; these are reserved for future
// extensions to the regular-expression language. A backslash may be used
// prior to a non-alphabetic character regardless of whether that character
// is part of an unescaped construct.
//
// As a result, escape everything except [0-9a-zA-Z]
int length = s.length();
int newLength = length;
// first check for characters that might
// be dangerous and calculate a length
// of the string that has escapes.
for (int i=0; i<length; i++){
char c = s.charAt(i);
if (!((c>='0' && c<='9') || (c>='A' && c<='Z') || (c>='a' && c<='z'))){
newLength += 1;
}
}
if (length == newLength){
// nothing to escape in the string
return s;
}
StringBuffer sb = new StringBuffer(newLength);
for (int i=0; i<length; i++){
char c = s.charAt(i);
if (!((c>='0' && c<='9') || (c>='A' && c<='Z') || (c>='a' && c<='z'))){
sb.append('\\');
}
sb.append(c);
}
return sb.toString();
}
}
