Java tutorial
package com.sjdf.platform.xss; import com.sjdf.platform.CommonPlatformConstant; import java.io.UnsupportedEncodingException; import java.lang.reflect.InvocationTargetException; import java.lang.reflect.Method; import java.util.*; import java.util.regex.Pattern; /** * Create at 20131111 ?6:04:27 * * @category author KETQI */ public abstract class StringUtils { public static final String[] EMPTY_STRING_ARRAY = new String[0]; /** * The empty String {@code ""}. * * @since 2.0 */ public static final String EMPTY = ""; /** * Represents a failed index search. * * @since 2.1 */ public static final int INDEX_NOT_FOUND = -1; /** * <p> * The maximum size to which the padding constant(s) can expand. * </p> */ private static final int PAD_LIMIT = 8192; /** * A regex pattern for recognizing blocks of whitespace characters. */ private static final Pattern WHITESPACE_BLOCK = Pattern.compile("\\s+"); /** * <p> * {@code StringUtils} instances should NOT be constructed in standard * programming. Instead, the class should be used as * {@code StringUtils.trim(" foo ");}. * </p> * <p/> * <p> * This constructor is public to permit tools that require a JavaBean * instance to operate. * </p> */ public StringUtils() { super(); } /** * <p> * Checks if a CharSequence is empty ("") or null. * </p> * <p/> * <pre> * StringUtils.isEmpty(null) = true * StringUtils.isEmpty("") = true * StringUtils.isEmpty(" ") = false * StringUtils.isEmpty("bob") = false * StringUtils.isEmpty(" bob ") = false * </pre> * <p/> * <p> * NOTE: This method changed in Lang version 2.0. It no longer trims the * CharSequence. That functionality is available in isBlank(). * </p> * * @param cs the CharSequence to check, may be null * @return {@code true} if the CharSequence is empty or null * @since 3.0 Changed signature from isEmpty(String) to * isEmpty(CharSequence) */ public static boolean isEmpty(CharSequence cs) { return cs == null || cs.length() == 0; } /** * <p> * Checks if a CharSequence is not empty ("") and not null. * </p> * <p/> * <pre> * StringUtils.isNotEmpty(null) = false * StringUtils.isNotEmpty("") = false * StringUtils.isNotEmpty(" ") = true * StringUtils.isNotEmpty("bob") = true * StringUtils.isNotEmpty(" bob ") = true * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if the CharSequence is not empty and not null * @since 3.0 Changed signature from isNotEmpty(String) to * isNotEmpty(CharSequence) */ public static boolean isNotEmpty(CharSequence cs) { return !StringUtils.isEmpty(cs); } /** * <p> * Checks if a CharSequence is whitespace, empty ("") or null. * </p> * <p/> * <pre> * StringUtils.isBlank(null) = true * StringUtils.isBlank("") = true * StringUtils.isBlank(" ") = true * StringUtils.isBlank("bob") = false * StringUtils.isBlank(" bob ") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if the CharSequence is null, empty or whitespace * @since 3.0 Changed signature from isBlank(String) to * isBlank(CharSequence) */ public static boolean isBlank(CharSequence cs) { int strLen; if (cs == null || (strLen = cs.length()) == 0) { return true; } for (int i = 0; i < strLen; i++) { if (!Character.isWhitespace(cs.charAt(i))) { return false; } } return true; } /** * <p> * Checks if a CharSequence is not empty (""), not null and not whitespace * only. * </p> * <p/> * <pre> * StringUtils.isNotBlank(null) = false * StringUtils.isNotBlank("") = false * StringUtils.isNotBlank(" ") = false * StringUtils.isNotBlank("bob") = true * StringUtils.isNotBlank(" bob ") = true * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if the CharSequence is not empty and not null and * not whitespace * @since 3.0 Changed signature from isNotBlank(String) to * isNotBlank(CharSequence) */ public static boolean isNotBlank(CharSequence cs) { return !StringUtils.isBlank(cs); } /** * <p> * Removes control characters (char <= 32) from both ends of this String, * handling {@code null} by returning {@code null}. * </p> * <p/> * <p> * The String is trimmed using {@link String#trim()}. Trim removes start and * end characters <= 32. To strip whitespace use {@link #strip(String)}. * </p> * <p/> * <p> * To trim your choice of characters, use the {@link #strip(String, String)} * methods. * </p> * <p/> * <pre> * StringUtils.trim(null) = null * StringUtils.trim("") = "" * StringUtils.trim(" ") = "" * StringUtils.trim("abc") = "abc" * StringUtils.trim(" abc ") = "abc" * </pre> * * @param str the String to be trimmed, may be null * @return the trimmed string, {@code null} if null String input */ public static String trim(String str) { return str == null ? null : str.trim(); } /** * <p> * Removes control characters (char <= 32) from both ends of this String * returning {@code null} if the String is empty ("") after the trim or if * it is {@code null}. * <p/> * <p> * The String is trimmed using {@link String#trim()}. Trim removes start and * end characters <= 32. To strip whitespace use * {@link #stripToNull(String)}. * </p> * <p/> * <pre> * StringUtils.trimToNull(null) = null * StringUtils.trimToNull("") = null * StringUtils.trimToNull(" ") = null * StringUtils.trimToNull("abc") = "abc" * StringUtils.trimToNull(" abc ") = "abc" * </pre> * * @param str the String to be trimmed, may be null * @return the trimmed String, {@code null} if only chars <= 32, empty or * null String input * @since 2.0 */ public static String trimToNull(String str) { String ts = trim(str); return isEmpty(ts) ? null : ts; } /** * <p> * Removes control characters (char <= 32) from both ends of this String * returning an empty String ("") if the String is empty ("") after the trim * or if it is {@code null}. * <p/> * <p> * The String is trimmed using {@link String#trim()}. Trim removes start and * end characters <= 32. To strip whitespace use * {@link #stripToEmpty(String)}. * </p> * <p/> * <pre> * StringUtils.trimToEmpty(null) = "" * StringUtils.trimToEmpty("") = "" * StringUtils.trimToEmpty(" ") = "" * StringUtils.trimToEmpty("abc") = "abc" * StringUtils.trimToEmpty(" abc ") = "abc" * </pre> * * @param str the String to be trimmed, may be null * @return the trimmed String, or an empty String if {@code null} input * @since 2.0 */ public static String trimToEmpty(String str) { return str == null ? EMPTY : str.trim(); } /** * <p> * Strips whitespace from the start and end of a String. * </p> * <p/> * <p> * This is similar to {@link #trim(String)} but removes whitespace. * Whitespace is defined by {@link Character#isWhitespace(char)}. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.strip(null) = null * StringUtils.strip("") = "" * StringUtils.strip(" ") = "" * StringUtils.strip("abc") = "abc" * StringUtils.strip(" abc") = "abc" * StringUtils.strip("abc ") = "abc" * StringUtils.strip(" abc ") = "abc" * StringUtils.strip(" ab c ") = "ab c" * </pre> * * @param str the String to remove whitespace from, may be null * @return the stripped String, {@code null} if null String input */ public static String strip(String str) { return strip(str, null); } /** * <p> * Strips whitespace from the start and end of a String returning * {@code null} if the String is empty ("") after the strip. * </p> * <p/> * <p> * This is similar to {@link #trimToNull(String)} but removes whitespace. * Whitespace is defined by {@link Character#isWhitespace(char)}. * </p> * <p/> * <pre> * StringUtils.stripToNull(null) = null * StringUtils.stripToNull("") = null * StringUtils.stripToNull(" ") = null * StringUtils.stripToNull("abc") = "abc" * StringUtils.stripToNull(" abc") = "abc" * StringUtils.stripToNull("abc ") = "abc" * StringUtils.stripToNull(" abc ") = "abc" * StringUtils.stripToNull(" ab c ") = "ab c" * </pre> * * @param str the String to be stripped, may be null * @return the stripped String, {@code null} if whitespace, empty or null * String input * @since 2.0 */ public static String stripToNull(String str) { if (str == null) { return null; } String string = strip(str, null); return string.length() == 0 ? null : string; } /** * <p> * Strips whitespace from the start and end of a String returning an empty * String if {@code null} input. * </p> * <p/> * <p> * This is similar to {@link #trimToEmpty(String)} but removes whitespace. * Whitespace is defined by {@link Character#isWhitespace(char)}. * </p> * <p/> * <pre> * StringUtils.stripToEmpty(null) = "" * StringUtils.stripToEmpty("") = "" * StringUtils.stripToEmpty(" ") = "" * StringUtils.stripToEmpty("abc") = "abc" * StringUtils.stripToEmpty(" abc") = "abc" * StringUtils.stripToEmpty("abc ") = "abc" * StringUtils.stripToEmpty(" abc ") = "abc" * StringUtils.stripToEmpty(" ab c ") = "ab c" * </pre> * * @param str the String to be stripped, may be null * @return the trimmed String, or an empty String if {@code null} input * @since 2.0 */ public static String stripToEmpty(String str) { return str == null ? EMPTY : strip(str, null); } /** * <p> * Strips any of a set of characters from the start and end of a String. * This is similar to {@link String#trim()} but allows the characters to be * stripped to be controlled. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. An empty string ("") * input returns the empty string. * </p> * <p/> * <p> * If the stripChars String is {@code null}, whitespace is stripped as * defined by {@link Character#isWhitespace(char)}. Alternatively use * {@link #strip(String)}. * </p> * <p/> * <pre> * StringUtils.strip(null, *) = null * StringUtils.strip("", *) = "" * StringUtils.strip("abc", null) = "abc" * StringUtils.strip(" abc", null) = "abc" * StringUtils.strip("abc ", null) = "abc" * StringUtils.strip(" abc ", null) = "abc" * StringUtils.strip(" abcyx", "xyz") = " abc" * </pre> * * @param str the String to remove characters from, may be null * @param stripChars the characters to remove, null treated as whitespace * @return the stripped String, {@code null} if null String input */ public static String strip(String str, String stripChars) { if (isEmpty(str)) { return str; } String string = stripStart(str, stripChars); return stripEnd(string, stripChars); } /** * <p> * Strips any of a set of characters from the start of a String. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. An empty string ("") * input returns the empty string. * </p> * <p/> * <p> * If the stripChars String is {@code null}, whitespace is stripped as * defined by {@link Character#isWhitespace(char)}. * </p> * <p/> * <pre> * StringUtils.stripStart(null, *) = null * StringUtils.stripStart("", *) = "" * StringUtils.stripStart("abc", "") = "abc" * StringUtils.stripStart("abc", null) = "abc" * StringUtils.stripStart(" abc", null) = "abc" * StringUtils.stripStart("abc ", null) = "abc " * StringUtils.stripStart(" abc ", null) = "abc " * StringUtils.stripStart("yxabc ", "xyz") = "abc " * </pre> * * @param str the String to remove characters from, may be null * @param stripChars the characters to remove, null treated as whitespace * @return the stripped String, {@code null} if null String input */ public static String stripStart(String str, String stripChars) { int strLen; if (str == null || (strLen = str.length()) == 0) { return str; } int start = 0; if (stripChars == null) { while (start != strLen && Character.isWhitespace(str.charAt(start))) { start++; } } else if (stripChars.length() == 0) { return str; } else { while (start != strLen && stripChars.indexOf(str.charAt(start)) != INDEX_NOT_FOUND) { start++; } } return str.substring(start); } /** * <p> * Strips any of a set of characters from the end of a String. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. An empty string ("") * input returns the empty string. * </p> * <p/> * <p> * If the stripChars String is {@code null}, whitespace is stripped as * defined by {@link Character#isWhitespace(char)}. * </p> * <p/> * <pre> * StringUtils.stripEnd(null, *) = null * StringUtils.stripEnd("", *) = "" * StringUtils.stripEnd("abc", "") = "abc" * StringUtils.stripEnd("abc", null) = "abc" * StringUtils.stripEnd(" abc", null) = " abc" * StringUtils.stripEnd("abc ", null) = "abc" * StringUtils.stripEnd(" abc ", null) = " abc" * StringUtils.stripEnd(" abcyx", "xyz") = " abc" * StringUtils.stripEnd("120.00", ".0") = "12" * </pre> * * @param str the String to remove characters from, may be null * @param stripChars the set of characters to remove, null treated as whitespace * @return the stripped String, {@code null} if null String input */ public static String stripEnd(String str, String stripChars) { int end; if (str == null || (end = str.length()) == 0) { return str; } if (stripChars == null) { while (end != 0 && Character.isWhitespace(str.charAt(end - 1))) { end--; } } else if (stripChars.length() == 0) { return str; } else { while (end != 0 && stripChars.indexOf(str.charAt(end - 1)) != INDEX_NOT_FOUND) { end--; } } return str.substring(0, end); } /** * <p> * Strips whitespace from the start and end of every String in an array. * Whitespace is defined by {@link Character#isWhitespace(char)}. * </p> * <p/> * <p> * A new array is returned each time, except for length zero. A {@code null} * array will return {@code null}. An empty array will return itself. A * {@code null} array entry will be ignored. * </p> * <p/> * <pre> * StringUtils.stripAll(null) = null * StringUtils.stripAll([]) = [] * StringUtils.stripAll(["abc", " abc"]) = ["abc", "abc"] * StringUtils.stripAll(["abc ", null]) = ["abc", null] * </pre> * * @param strs the array to remove whitespace from, may be null * @return the stripped Strings, {@code null} if null array input */ public static String[] stripAll(String... strs) { return stripAll(strs, null); } /** * <p> * Strips any of a set of characters from the start and end of every String * in an array. * </p> * Whitespace is defined by {@link Character#isWhitespace(char)}.</p> * <p/> * <p> * A new array is returned each time, except for length zero. A {@code null} * array will return {@code null}. An empty array will return itself. A * {@code null} array entry will be ignored. A {@code null} stripChars will * strip whitespace as defined by {@link Character#isWhitespace(char)}. * </p> * <p/> * <pre> * StringUtils.stripAll(null, *) = null * StringUtils.stripAll([], *) = [] * StringUtils.stripAll(["abc", " abc"], null) = ["abc", "abc"] * StringUtils.stripAll(["abc ", null], null) = ["abc", null] * StringUtils.stripAll(["abc ", null], "yz") = ["abc ", null] * StringUtils.stripAll(["yabcz", null], "yz") = ["abc", null] * </pre> * * @param strs the array to remove characters from, may be null * @param stripChars the characters to remove, null treated as whitespace * @return the stripped Strings, {@code null} if null array input */ public static String[] stripAll(String[] strs, String stripChars) { int strsLen; if (strs == null || (strsLen = strs.length) == 0) { return strs; } String[] newArr = new String[strsLen]; for (int i = 0; i < strsLen; i++) { newArr[i] = strip(strs[i], stripChars); } return newArr; } /** * <p> * Removes diacritics (~= accents) from a string. The case will not be * altered. * </p> * <p> * For instance, 'à' will be replaced by 'a'. * </p> * <p> * Note that ligatures will be left as is. * </p> * <p/> * <p> * This method will use the first available implementation of: Java 6's * {@link java.text.Normalizer}, Java 1.3–1.5's * {@code sun.text.Normalizer} * </p> * <p/> * <pre> * StringUtils.stripAccents(null) = null * StringUtils.stripAccents("") = "" * StringUtils.stripAccents("control") = "control" * StringUtils.stripAccents("éclair") = "eclair" * </pre> * * @param input String to be stripped * @return input text with diacritics removed * @since 3.0 */ // See also Lucene's ASCIIFoldingFilter (Lucene 2.9) that replaces accented // characters by their unaccented equivalent (and uncommitted bug fix: // https://issues.apache.org/jira/browse/LUCENE-1343?focusedCommentId=12858907&page=com.atlassian.jira.plugin.system.issuetabpanels%3Acomment-tabpanel#action_12858907). public static String stripAccents(String input) { if (input == null) { return null; } try { String result; if (InitStripAccents.JAVA6NORMALIZE_METHOD != null) { result = removeAccentsJava6(input); } else if (InitStripAccents.SUN_DECOMPOSE_METHOD != null) { result = removeAccentsSUN(input); } else { throw new UnsupportedOperationException("The stripAccents(CharSequence) method requires at least" + " Java6, but got: " + InitStripAccents.JAVA6EXCEPTION + "; or a Sun JVM: " + InitStripAccents.SUN_EXCEPTION); } // Note that none of the above methods correctly remove ligatures... return result; } catch (IllegalArgumentException iae) { throw new RuntimeException("IllegalArgumentException occurred", iae); } catch (IllegalAccessException iae) { throw new RuntimeException("IllegalAccessException occurred", iae); } catch (InvocationTargetException ite) { throw new RuntimeException("InvocationTargetException occurred", ite); } catch (SecurityException se) { throw new RuntimeException("SecurityException occurred", se); } } /** * Use {@code java.text.Normalizer#normalize(CharSequence, Normalizer.Form)} * (but be careful, this class exists in Java 1.3, with an entirely * different meaning!) * * @param text the text to be processed * @return the processed string * @throws IllegalAccessException may be thrown by a reflection call * @throws InvocationTargetException if a reflection call throws an exception * @throws IllegalStateException if the {@code Normalizer} class is not available */ private static String removeAccentsJava6(CharSequence text) throws IllegalAccessException, InvocationTargetException { if (InitStripAccents.JAVA6NORMALIZE_METHOD == null || InitStripAccents.JAVA6NORMALIZER_FORM_NFD == null) { throw new IllegalStateException("java.text.Normalizer is not available", InitStripAccents.JAVA6EXCEPTION); } String result; result = (String) InitStripAccents.JAVA6NORMALIZE_METHOD.invoke(null, new Object[] { text, InitStripAccents.JAVA6NORMALIZER_FORM_NFD }); result = InitStripAccents.JAVA6PATTERN.matcher(result).replaceAll("");//$NON-NLS-1$ return result; } /** * Use {@code sun.text.Normalizer#decompose(String, boolean, int)} * * @param text the text to be processed * @return the processed string * @throws IllegalAccessException may be thrown by a reflection call * @throws InvocationTargetException if a reflection call throws an exception * @throws IllegalStateException if the {@code Normalizer} class is not available */ private static String removeAccentsSUN(CharSequence text) throws IllegalAccessException, InvocationTargetException { if (InitStripAccents.SUN_DECOMPOSE_METHOD == null) { throw new IllegalStateException("sun.text.Normalizer is not available", InitStripAccents.SUN_EXCEPTION); } String result; result = (String) InitStripAccents.SUN_DECOMPOSE_METHOD.invoke(null, new Object[] { text, Boolean.FALSE, Integer.valueOf(0) }); result = InitStripAccents.SUN_PATTERN.matcher(result).replaceAll("");//$NON-NLS-1$ return result; } /** * IOD container for stripAccent() initialisation Create at 20131126 * ?3:03:47 * * @author KETQI */ private static class InitStripAccents { // SUN internal, Java 1.3 -> Java 5 private static final Throwable SUN_EXCEPTION; private static final Method SUN_DECOMPOSE_METHOD; private static final Pattern SUN_PATTERN = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");//$NON-NLS-1$ // Java 6+ private static final Throwable JAVA6EXCEPTION; private static final Method JAVA6NORMALIZE_METHOD; private static final Object JAVA6NORMALIZER_FORM_NFD; private static final Pattern JAVA6PATTERN = SUN_PATTERN; static { // Set up defaults for final static fields Object java6NormalizerFormNFD = null; Method java6NormalizeMethod = null; Method sunDecomposeMethod = null; Throwable java6Exception = null; Throwable sunException = null; try { Class<?> normalizerFormClass = Thread.currentThread().getContextClassLoader() .loadClass("java.text.Normalizer$Form");//$NON-NLS-1$ java6NormalizerFormNFD = normalizerFormClass.getField("NFD").get(null);//$NON-NLS-1$ Class<?> normalizerClass = Thread.currentThread().getContextClassLoader() .loadClass("java.text.Normalizer");//$NON-NLS-1$ java6NormalizeMethod = normalizerClass.getMethod("normalize", //$NON-NLS-1$ new Class[] { CharSequence.class, normalizerFormClass });//$NON-NLS-1$ } catch (Exception e1) { // Only check for Sun method if Java 6 method is not available java6Exception = e1; try { Class<?> normalizerClass = Thread.currentThread().getContextClassLoader() .loadClass("sun.text.Normalizer");//$NON-NLS-1$ sunDecomposeMethod = normalizerClass.getMethod("decompose", //$NON-NLS-1$ new Class[] { String.class, Boolean.TYPE, Integer.TYPE });//$NON-NLS-1$ } catch (Exception e2) { sunException = e2; } } // Set up final static fields JAVA6EXCEPTION = java6Exception; JAVA6NORMALIZER_FORM_NFD = java6NormalizerFormNFD; JAVA6NORMALIZE_METHOD = java6NormalizeMethod; SUN_EXCEPTION = sunException; SUN_DECOMPOSE_METHOD = sunDecomposeMethod; } } /** * <p> * Compares two CharSequences, returning {@code true} if they are equal. * </p> * <p/> * <p> * {@code null}s are handled without exceptions. Two {@code null} references * are considered to be equal. The comparison is case sensitive. * </p> * <p/> * <pre> * StringUtils.equals(null, null) = true * StringUtils.equals(null, "abc") = false * StringUtils.equals("abc", null) = false * StringUtils.equals("abc", "abc") = true * StringUtils.equals("abc", "ABC") = false * </pre> * * @param cs1 the first CharSequence, may be null * @param cs2 the second CharSequence, may be null * @return {@code true} if the CharSequences are equal, case sensitive, or * both {@code null} * @see java.lang.String#equals(Object) * @since 3.0 Changed signature from equals(String, String) to * equals(CharSequence, CharSequence) */ public static boolean equals(CharSequence cs1, CharSequence cs2) { return cs1 == null ? cs2 == null : cs1.equals(cs2); } /** * <p> * Compares two CharSequences, returning {@code true} if they are equal * ignoring the case. * </p> * <p/> * <p> * {@code null}s are handled without exceptions. Two {@code null} references * are considered equal. Comparison is case insensitive. * </p> * <p/> * <pre> * StringUtils.equalsIgnoreCase(null, null) = true * StringUtils.equalsIgnoreCase(null, "abc") = false * StringUtils.equalsIgnoreCase("abc", null) = false * StringUtils.equalsIgnoreCase("abc", "abc") = true * StringUtils.equalsIgnoreCase("abc", "ABC") = true * </pre> * * @param str1 the first CharSequence, may be null * @param str2 the second CharSequence, may be null * @return {@code true} if the CharSequence are equal, case insensitive, or * both {@code null} * @since 3.0 Changed signature from equalsIgnoreCase(String, String) to * equalsIgnoreCase(CharSequence, CharSequence) */ public static boolean equalsIgnoreCase(CharSequence str1, CharSequence str2) { if (str1 == null || str2 == null) { return str1 == str2; } else { return CharSequenceUtils.regionMatches(str1, true, 0, str2, 0, Math.max(str1.length(), str2.length())); } } /** * <p> * Finds the first index within a CharSequence, handling {@code null}. This * method uses {@link String#indexOf(int, int)} if possible. * </p> * <p/> * <p> * A {@code null} or empty ("") CharSequence will return * {@code INDEX_NOT_FOUND (-1)}. * </p> * <p/> * <pre> * StringUtils.indexOf(null, *) = -1 * StringUtils.indexOf("", *) = -1 * StringUtils.indexOf("aabaabaa", 'a') = 0 * StringUtils.indexOf("aabaabaa", 'b') = 2 * </pre> * * @param seq the CharSequence to check, may be null * @param searchChar the character to find * @return the first index of the search character, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from indexOf(String, int) to * indexOf(CharSequence, int) */ public static int indexOf(CharSequence seq, int searchChar) { if (isEmpty(seq)) { return INDEX_NOT_FOUND; } return CharSequenceUtils.indexOf(seq, searchChar, 0); } /** * <p> * Finds the first index within a CharSequence from a start position, * handling {@code null}. This method uses {@link String#indexOf(int, int)} * if possible. * </p> * <p/> * <p> * A {@code null} or empty ("") CharSequence will return * {@code (INDEX_NOT_FOUND) -1}. A negative start position is treated as * zero. A start position greater than the string length returns {@code -1}. * </p> * <p/> * <pre> * StringUtils.indexOf(null, *, *) = -1 * StringUtils.indexOf("", *, *) = -1 * StringUtils.indexOf("aabaabaa", 'b', 0) = 2 * StringUtils.indexOf("aabaabaa", 'b', 3) = 5 * StringUtils.indexOf("aabaabaa", 'b', 9) = -1 * StringUtils.indexOf("aabaabaa", 'b', -1) = 2 * </pre> * * @param seq the CharSequence to check, may be null * @param searchChar the character to find * @param startPos the start position, negative treated as zero * @return the first index of the search character, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from indexOf(String, int, int) to * indexOf(CharSequence, int, int) */ public static int indexOf(CharSequence seq, int searchChar, int startPos) { if (isEmpty(seq)) { return INDEX_NOT_FOUND; } return CharSequenceUtils.indexOf(seq, searchChar, startPos); } /** * <p> * Finds the first index within a CharSequence, handling {@code null}. This * method uses {@link String#indexOf(String, int)} if possible. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. * </p> * <p/> * <pre> * StringUtils.indexOf(null, *) = -1 * StringUtils.indexOf(*, null) = -1 * StringUtils.indexOf("", "") = 0 * StringUtils.indexOf("", *) = -1 (except when * = "") * StringUtils.indexOf("aabaabaa", "a") = 0 * StringUtils.indexOf("aabaabaa", "b") = 2 * StringUtils.indexOf("aabaabaa", "ab") = 1 * StringUtils.indexOf("aabaabaa", "") = 0 * </pre> * * @param seq the CharSequence to check, may be null * @param searchSeq the CharSequence to find, may be null * @return the first index of the search CharSequence, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from indexOf(String, String) to * indexOf(CharSequence, CharSequence) */ public static int indexOf(CharSequence seq, CharSequence searchSeq) { if (seq == null || searchSeq == null) { return INDEX_NOT_FOUND; } return CharSequenceUtils.indexOf(seq, searchSeq, 0); } /** * <p> * Finds the first index within a CharSequence, handling {@code null}. This * method uses {@link String#indexOf(String, int)} if possible. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. A negative start * position is treated as zero. An empty ("") search CharSequence always * matches. A start position greater than the string length only matches an * empty search CharSequence. * </p> * <p/> * <pre> * StringUtils.indexOf(null, *, *) = -1 * StringUtils.indexOf(*, null, *) = -1 * StringUtils.indexOf("", "", 0) = 0 * StringUtils.indexOf("", *, 0) = -1 (except when * = "") * StringUtils.indexOf("aabaabaa", "a", 0) = 0 * StringUtils.indexOf("aabaabaa", "b", 0) = 2 * StringUtils.indexOf("aabaabaa", "ab", 0) = 1 * StringUtils.indexOf("aabaabaa", "b", 3) = 5 * StringUtils.indexOf("aabaabaa", "b", 9) = -1 * StringUtils.indexOf("aabaabaa", "b", -1) = 2 * StringUtils.indexOf("aabaabaa", "", 2) = 2 * StringUtils.indexOf("abc", "", 9) = 3 * </pre> * * @param seq the CharSequence to check, may be null * @param searchSeq the CharSequence to find, may be null * @param startPos the start position, negative treated as zero * @return the first index of the search CharSequence, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from indexOf(String, String, int) to * indexOf(CharSequence, CharSequence, int) */ public static int indexOf(CharSequence seq, CharSequence searchSeq, int startPos) { if (seq == null || searchSeq == null) { return INDEX_NOT_FOUND; } return CharSequenceUtils.indexOf(seq, searchSeq, startPos); } /** * <p> * Finds the n-th index within a CharSequence, handling {@code null}. This * method uses {@link String#indexOf(String)} if possible. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. * </p> * <p/> * <pre> * StringUtils.ordinalIndexOf(null, *, *) = -1 * StringUtils.ordinalIndexOf(*, null, *) = -1 * StringUtils.ordinalIndexOf("", "", *) = 0 * StringUtils.ordinalIndexOf("aabaabaa", "a", 1) = 0 * StringUtils.ordinalIndexOf("aabaabaa", "a", 2) = 1 * StringUtils.ordinalIndexOf("aabaabaa", "b", 1) = 2 * StringUtils.ordinalIndexOf("aabaabaa", "b", 2) = 5 * StringUtils.ordinalIndexOf("aabaabaa", "ab", 1) = 1 * StringUtils.ordinalIndexOf("aabaabaa", "ab", 2) = 4 * StringUtils.ordinalIndexOf("aabaabaa", "", 1) = 0 * StringUtils.ordinalIndexOf("aabaabaa", "", 2) = 0 * </pre> * <p/> * <p> * Note that 'head(CharSequence str, int n)' may be implemented as: * </p> * <p/> * <pre> * str.substring(0, lastOrdinalIndexOf(str, "\n", n)) * </pre> * * @param str the CharSequence to check, may be null * @param searchStr the CharSequence to find, may be null * @param ordinal the n-th {@code searchStr} to find * @return the n-th index of the search CharSequence, {@code -1} ( * {@code INDEX_NOT_FOUND}) if no match or {@code null} string input * @since 3.0 Changed signature from ordinalIndexOf(String, String, int) to * ordinalIndexOf(CharSequence, CharSequence, int) */ public static int ordinalIndexOf(CharSequence str, CharSequence searchStr, int ordinal) { return ordinalIndexOf(str, searchStr, ordinal, false); } /** * <p> * Finds the n-th index within a String, handling {@code null}. This method * uses {@link String#indexOf(String)} if possible. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. * </p> * * @param str the CharSequence to check, may be null * @param searchStr the CharSequence to find, may be null * @param ordinal the n-th {@code searchStr} to find * @param lastIndex true if lastOrdinalIndexOf() otherwise false if * ordinalIndexOf() * @return the n-th index of the search CharSequence, {@code -1} ( * {@code INDEX_NOT_FOUND}) if no match or {@code null} string input */ // Shared code between ordinalIndexOf(String,String,int) and // lastOrdinalIndexOf(String,String,int) private static int ordinalIndexOf(CharSequence str, CharSequence searchStr, int ordinal, boolean lastIndex) { if (str == null || searchStr == null || ordinal <= 0) { return INDEX_NOT_FOUND; } if (searchStr.length() == 0) { return lastIndex ? str.length() : 0; } int found = 0; int index = lastIndex ? str.length() : INDEX_NOT_FOUND; do { if (lastIndex) { index = CharSequenceUtils.lastIndexOf(str, searchStr, index - 1); } else { index = CharSequenceUtils.indexOf(str, searchStr, index + 1); } if (index < 0) { return index; } found++; } while (found < ordinal); return index; } /** * <p> * Case in-sensitive find of the first index within a CharSequence. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. A negative start * position is treated as zero. An empty ("") search CharSequence always * matches. A start position greater than the string length only matches an * empty search CharSequence. * </p> * <p/> * <pre> * StringUtils.indexOfIgnoreCase(null, *) = -1 * StringUtils.indexOfIgnoreCase(*, null) = -1 * StringUtils.indexOfIgnoreCase("", "") = 0 * StringUtils.indexOfIgnoreCase("aabaabaa", "a") = 0 * StringUtils.indexOfIgnoreCase("aabaabaa", "b") = 2 * StringUtils.indexOfIgnoreCase("aabaabaa", "ab") = 1 * </pre> * * @param str the CharSequence to check, may be null * @param searchStr the CharSequence to find, may be null * @return the first index of the search CharSequence, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from indexOfIgnoreCase(String, String) to * indexOfIgnoreCase(CharSequence, CharSequence) */ public static int indexOfIgnoreCase(CharSequence str, CharSequence searchStr) { return indexOfIgnoreCase(str, searchStr, 0); } /** * <p> * Case in-sensitive find of the first index within a CharSequence from the * specified position. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. A negative start * position is treated as zero. An empty ("") search CharSequence always * matches. A start position greater than the string length only matches an * empty search CharSequence. * </p> * <p/> * <pre> * StringUtils.indexOfIgnoreCase(null, *, *) = -1 * StringUtils.indexOfIgnoreCase(*, null, *) = -1 * StringUtils.indexOfIgnoreCase("", "", 0) = 0 * StringUtils.indexOfIgnoreCase("aabaabaa", "A", 0) = 0 * StringUtils.indexOfIgnoreCase("aabaabaa", "B", 0) = 2 * StringUtils.indexOfIgnoreCase("aabaabaa", "AB", 0) = 1 * StringUtils.indexOfIgnoreCase("aabaabaa", "B", 3) = 5 * StringUtils.indexOfIgnoreCase("aabaabaa", "B", 9) = -1 * StringUtils.indexOfIgnoreCase("aabaabaa", "B", -1) = 2 * StringUtils.indexOfIgnoreCase("aabaabaa", "", 2) = 2 * StringUtils.indexOfIgnoreCase("abc", "", 9) = 3 * </pre> * * @param str the CharSequence to check, may be null * @param searchStr the CharSequence to find, may be null * @param start the start position, negative treated as zero * @return the first index of the search CharSequence, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from indexOfIgnoreCase(String, String, int) * to indexOfIgnoreCase(CharSequence, CharSequence, int) */ public static int indexOfIgnoreCase(CharSequence str, CharSequence searchStr, int start) { if (str == null || searchStr == null) { return INDEX_NOT_FOUND; } int startPos = start; if (startPos < 0) { startPos = 0; } int endLimit = str.length() - searchStr.length() + 1; if (startPos > endLimit) { return INDEX_NOT_FOUND; } if (searchStr.length() == 0) { return startPos; } for (int i = startPos; i < endLimit; i++) { if (CharSequenceUtils.regionMatches(str, true, i, searchStr, 0, searchStr.length())) { return i; } } return INDEX_NOT_FOUND; } /** * <p> * Finds the last index within a CharSequence, handling {@code null}. This * method uses {@link String#lastIndexOf(int)} if possible. * </p> * <p/> * <p> * A {@code null} or empty ("") CharSequence will return {@code -1}. * </p> * <p/> * <pre> * StringUtils.lastIndexOf(null, *) = -1 * StringUtils.lastIndexOf("", *) = -1 * StringUtils.lastIndexOf("aabaabaa", 'a') = 7 * StringUtils.lastIndexOf("aabaabaa", 'b') = 5 * </pre> * * @param seq the CharSequence to check, may be null * @param searchChar the character to find * @return the last index of the search character, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from lastIndexOf(String, int) to * lastIndexOf(CharSequence, int) */ public static int lastIndexOf(CharSequence seq, int searchChar) { if (isEmpty(seq)) { return INDEX_NOT_FOUND; } return CharSequenceUtils.lastIndexOf(seq, searchChar, seq.length()); } /** * <p> * Finds the last index within a CharSequence from a start position, * handling {@code null}. This method uses * {@link String#lastIndexOf(int, int)} if possible. * </p> * <p/> * <p> * A {@code null} or empty ("") CharSequence will return {@code -1}. A * negative start position returns {@code -1}. A start position greater than * the string length searches the whole string. * </p> * <p/> * <pre> * StringUtils.lastIndexOf(null, *, *) = -1 * StringUtils.lastIndexOf("", *, *) = -1 * StringUtils.lastIndexOf("aabaabaa", 'b', 8) = 5 * StringUtils.lastIndexOf("aabaabaa", 'b', 4) = 2 * StringUtils.lastIndexOf("aabaabaa", 'b', 0) = -1 * StringUtils.lastIndexOf("aabaabaa", 'b', 9) = 5 * StringUtils.lastIndexOf("aabaabaa", 'b', -1) = -1 * StringUtils.lastIndexOf("aabaabaa", 'a', 0) = 0 * </pre> * * @param seq the CharSequence to check, may be null * @param searchChar the character to find * @param startPos the start position * @return the last index of the search character, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from lastIndexOf(String, int, int) to * lastIndexOf(CharSequence, int, int) */ public static int lastIndexOf(CharSequence seq, int searchChar, int startPos) { if (isEmpty(seq)) { return INDEX_NOT_FOUND; } return CharSequenceUtils.lastIndexOf(seq, searchChar, startPos); } /** * <p> * Finds the last index within a CharSequence, handling {@code null}. This * method uses {@link String#lastIndexOf(String)} if possible. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. * </p> * <p/> * <pre> * StringUtils.lastIndexOf(null, *) = -1 * StringUtils.lastIndexOf(*, null) = -1 * StringUtils.lastIndexOf("", "") = 0 * StringUtils.lastIndexOf("aabaabaa", "a") = 7 * StringUtils.lastIndexOf("aabaabaa", "b") = 5 * StringUtils.lastIndexOf("aabaabaa", "ab") = 4 * StringUtils.lastIndexOf("aabaabaa", "") = 8 * </pre> * * @param seq the CharSequence to check, may be null * @param searchSeq the CharSequence to find, may be null * @return the last index of the search String, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from lastIndexOf(String, String) to * lastIndexOf(CharSequence, CharSequence) */ public static int lastIndexOf(CharSequence seq, CharSequence searchSeq) { if (seq == null || searchSeq == null) { return INDEX_NOT_FOUND; } return CharSequenceUtils.lastIndexOf(seq, searchSeq, seq.length()); } /** * <p> * Finds the n-th last index within a String, handling {@code null}. This * method uses {@link String#lastIndexOf(String)}. * </p> * <p/> * <p> * A {@code null} String will return {@code -1}. * </p> * <p/> * <pre> * StringUtils.lastOrdinalIndexOf(null, *, *) = -1 * StringUtils.lastOrdinalIndexOf(*, null, *) = -1 * StringUtils.lastOrdinalIndexOf("", "", *) = 0 * StringUtils.lastOrdinalIndexOf("aabaabaa", "a", 1) = 7 * StringUtils.lastOrdinalIndexOf("aabaabaa", "a", 2) = 6 * StringUtils.lastOrdinalIndexOf("aabaabaa", "b", 1) = 5 * StringUtils.lastOrdinalIndexOf("aabaabaa", "b", 2) = 2 * StringUtils.lastOrdinalIndexOf("aabaabaa", "ab", 1) = 4 * StringUtils.lastOrdinalIndexOf("aabaabaa", "ab", 2) = 1 * StringUtils.lastOrdinalIndexOf("aabaabaa", "", 1) = 8 * StringUtils.lastOrdinalIndexOf("aabaabaa", "", 2) = 8 * </pre> * <p/> * <p> * Note that 'tail(CharSequence str, int n)' may be implemented as: * </p> * <p/> * <pre> * str.substring(lastOrdinalIndexOf(str, "\n", n) + 1) * </pre> * * @param str the CharSequence to check, may be null * @param searchStr the CharSequence to find, may be null * @param ordinal the n-th last {@code searchStr} to find * @return the n-th last index of the search CharSequence, {@code -1} ( * {@code INDEX_NOT_FOUND}) if no match or {@code null} string input * @since 3.0 Changed signature from lastOrdinalIndexOf(String, String, int) * to lastOrdinalIndexOf(CharSequence, CharSequence, int) */ public static int lastOrdinalIndexOf(CharSequence str, CharSequence searchStr, int ordinal) { return ordinalIndexOf(str, searchStr, ordinal, true); } /** * <p> * Finds the first index within a CharSequence, handling {@code null}. This * method uses {@link String#lastIndexOf(String, int)} if possible. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. A negative start * position returns {@code -1}. An empty ("") search CharSequence always * matches unless the start position is negative. A start position greater * than the string length searches the whole string. * </p> * <p/> * <pre> * StringUtils.lastIndexOf(null, *, *) = -1 * StringUtils.lastIndexOf(*, null, *) = -1 * StringUtils.lastIndexOf("aabaabaa", "a", 8) = 7 * StringUtils.lastIndexOf("aabaabaa", "b", 8) = 5 * StringUtils.lastIndexOf("aabaabaa", "ab", 8) = 4 * StringUtils.lastIndexOf("aabaabaa", "b", 9) = 5 * StringUtils.lastIndexOf("aabaabaa", "b", -1) = -1 * StringUtils.lastIndexOf("aabaabaa", "a", 0) = 0 * StringUtils.lastIndexOf("aabaabaa", "b", 0) = -1 * </pre> * * @param seq the CharSequence to check, may be null * @param searchSeq the CharSequence to find, may be null * @param startPos the start position, negative treated as zero * @return the first index of the search CharSequence, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from lastIndexOf(String, String, int) to * lastIndexOf(CharSequence, CharSequence, int) */ public static int lastIndexOf(CharSequence seq, CharSequence searchSeq, int startPos) { if (seq == null || searchSeq == null) { return INDEX_NOT_FOUND; } return CharSequenceUtils.lastIndexOf(seq, searchSeq, startPos); } /** * <p> * Case in-sensitive find of the last index within a CharSequence. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. A negative start * position returns {@code -1}. An empty ("") search CharSequence always * matches unless the start position is negative. A start position greater * than the string length searches the whole string. * </p> * <p/> * <pre> * StringUtils.lastIndexOfIgnoreCase(null, *) = -1 * StringUtils.lastIndexOfIgnoreCase(*, null) = -1 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "A") = 7 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B") = 5 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "AB") = 4 * </pre> * * @param str the CharSequence to check, may be null * @param searchStr the CharSequence to find, may be null * @return the first index of the search CharSequence, -1 if no match or * {@code null} string input * @since 3.0 Changed signature from lastIndexOfIgnoreCase(String, String) * to lastIndexOfIgnoreCase(CharSequence, CharSequence) */ public static int lastIndexOfIgnoreCase(CharSequence str, CharSequence searchStr) { if (str == null || searchStr == null) { return INDEX_NOT_FOUND; } return lastIndexOfIgnoreCase(str, searchStr, str.length()); } /** * <p> * Case in-sensitive find of the last index within a CharSequence from the * specified position. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. A negative start * position returns {@code -1}. An empty ("") search CharSequence always * matches unless the start position is negative. A start position greater * than the string length searches the whole string. * </p> * <p/> * <pre> * StringUtils.lastIndexOfIgnoreCase(null, *, *) = -1 * StringUtils.lastIndexOfIgnoreCase(*, null, *) = -1 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "A", 8) = 7 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", 8) = 5 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "AB", 8) = 4 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", 9) = 5 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", -1) = -1 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "A", 0) = 0 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", 0) = -1 * </pre> * * @param str the CharSequence to check, may be null * @param searchStr the CharSequence to find, may be null * @param start the start position * @return the first index of the search CharSequence, -1 if no match or * {@code null} input * @since 3.0 Changed signature from lastIndexOfIgnoreCase(String, String, * int) to lastIndexOfIgnoreCase(CharSequence, CharSequence, int) */ public static int lastIndexOfIgnoreCase(CharSequence str, CharSequence searchStr, int start) { if (str == null || searchStr == null) { return INDEX_NOT_FOUND; } int startPos = start; if (startPos > str.length() - searchStr.length()) { startPos = str.length() - searchStr.length(); } if (startPos < 0) { return INDEX_NOT_FOUND; } if (searchStr.length() == 0) { return startPos; } for (int i = startPos; i >= 0; i--) { if (CharSequenceUtils.regionMatches(str, true, i, searchStr, 0, searchStr.length())) { return i; } } return INDEX_NOT_FOUND; } /** * <p> * Checks if CharSequence contains a search character, handling {@code null} * . This method uses {@link String#indexOf(int)} if possible. * </p> * <p/> * <p> * A {@code null} or empty ("") CharSequence will return {@code false}. * </p> * <p/> * <pre> * StringUtils.contains(null, *) = false * StringUtils.contains("", *) = false * StringUtils.contains("abc", 'a') = true * StringUtils.contains("abc", 'z') = false * </pre> * * @param seq the CharSequence to check, may be null * @param searchChar the character to find * @return true if the CharSequence contains the search character, false if * not or {@code null} string input * @since 3.0 Changed signature from contains(String, int) to * contains(CharSequence, int) */ public static boolean contains(CharSequence seq, int searchChar) { if (isEmpty(seq)) { return false; } return CharSequenceUtils.indexOf(seq, searchChar, 0) >= 0; } /** * <p> * Checks if CharSequence contains a search CharSequence, handling * {@code null}. This method uses {@link String#indexOf(String)} if * possible. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code false}. * </p> * <p/> * <pre> * StringUtils.contains(null, *) = false * StringUtils.contains(*, null) = false * StringUtils.contains("", "") = true * StringUtils.contains("abc", "") = true * StringUtils.contains("abc", "a") = true * StringUtils.contains("abc", "z") = false * </pre> * * @param seq the CharSequence to check, may be null * @param searchSeq the CharSequence to find, may be null * @return true if the CharSequence contains the search CharSequence, false * if not or {@code null} string input * @since 3.0 Changed signature from contains(String, String) to * contains(CharSequence, CharSequence) */ public static boolean contains(CharSequence seq, CharSequence searchSeq) { if (seq == null || searchSeq == null) { return false; } return CharSequenceUtils.indexOf(seq, searchSeq, 0) >= 0; } /** * <p> * Checks if CharSequence contains a search CharSequence irrespective of * case, handling {@code null}. Case-insensitivity is defined as by * {@link String#equalsIgnoreCase(String)}. * <p/> * <p> * A {@code null} CharSequence will return {@code false}. * </p> * <p/> * <pre> * StringUtils.contains(null, *) = false * StringUtils.contains(*, null) = false * StringUtils.contains("", "") = true * StringUtils.contains("abc", "") = true * StringUtils.contains("abc", "a") = true * StringUtils.contains("abc", "z") = false * StringUtils.contains("abc", "A") = true * StringUtils.contains("abc", "Z") = false * </pre> * * @param str the CharSequence to check, may be null * @param searchStr the CharSequence to find, may be null * @return true if the CharSequence contains the search CharSequence * irrespective of case or false if not or {@code null} string input * @since 3.0 Changed signature from containsIgnoreCase(String, String) to * containsIgnoreCase(CharSequence, CharSequence) */ public static boolean containsIgnoreCase(CharSequence str, CharSequence searchStr) { if (str == null || searchStr == null) { return false; } int len = searchStr.length(); int max = str.length() - len; for (int i = 0; i <= max; i++) { if (CharSequenceUtils.regionMatches(str, true, i, searchStr, 0, len)) { return true; } } return false; } /** * Check whether the given CharSequence contains any whitespace characters. * * @param seq the CharSequence to check (may be {@code null}) * @return {@code true} if the CharSequence is not empty and contains at * least 1 whitespace character * @see java.lang.Character#isWhitespace * @since 3.0 */ // From org.springframework.util.StringUtils, under Apache License 2.0 public static boolean containsWhitespace(CharSequence seq) { if (isEmpty(seq)) { return false; } int strLen = seq.length(); for (int i = 0; i < strLen; i++) { if (Character.isWhitespace(seq.charAt(i))) { return true; } } return false; } /** * <p> * Search a CharSequence to find the first index of any character in the * given set of characters. * </p> * <p/> * <p> * A {@code null} String will return {@code -1}. A {@code null} or zero * length search array will return {@code -1}. * </p> * <p/> * <pre> * StringUtils.indexOfAny(null, *) = -1 * StringUtils.indexOfAny("", *) = -1 * StringUtils.indexOfAny(*, null) = -1 * StringUtils.indexOfAny(*, []) = -1 * StringUtils.indexOfAny("zzabyycdxx",['z','a']) = 0 * StringUtils.indexOfAny("zzabyycdxx",['b','y']) = 3 * StringUtils.indexOfAny("aba", ['z']) = -1 * </pre> * * @param cs the CharSequence to check, may be null * @param searchChars the chars to search for, may be null * @return the index of any of the chars, -1 if no match or null input * @since 3.0 Changed signature from indexOfAny(String, char[]) to * indexOfAny(CharSequence, char...) */ public static int indexOfAny(CharSequence cs, char... searchChars) { if (isEmpty(cs) || searchChars == null) { return INDEX_NOT_FOUND; } int csLen = cs.length(); int csLast = csLen - 1; int searchLen = searchChars.length; int searchLast = searchLen - 1; for (int i = 0; i < csLen; i++) { char ch = cs.charAt(i); for (int j = 0; j < searchLen; j++) { if (searchChars[j] == ch) { if (i < csLast && j < searchLast && Character.isHighSurrogate(ch)) { // ch is a supplementary character if (searchChars[j + 1] == cs.charAt(i + 1)) { return i; } } else { return i; } } } } return INDEX_NOT_FOUND; } /** * <p> * Search a CharSequence to find the first index of any character in the * given set of characters. * </p> * <p/> * <p> * A {@code null} String will return {@code -1}. A {@code null} search * string will return {@code -1}. * </p> * <p/> * <pre> * StringUtils.indexOfAny(null, *) = -1 * StringUtils.indexOfAny("", *) = -1 * StringUtils.indexOfAny(*, null) = -1 * StringUtils.indexOfAny(*, "") = -1 * StringUtils.indexOfAny("zzabyycdxx", "za") = 0 * StringUtils.indexOfAny("zzabyycdxx", "by") = 3 * StringUtils.indexOfAny("aba","z") = -1 * </pre> * * @param cs the CharSequence to check, may be null * @param searchChars the chars to search for, may be null * @return the index of any of the chars, -1 if no match or null input * @since 3.0 Changed signature from indexOfAny(String, String) to * indexOfAny(CharSequence, String) */ public static int indexOfAny(CharSequence cs, String searchChars) { if (isEmpty(cs) || isEmpty(searchChars)) { return INDEX_NOT_FOUND; } return indexOfAny(cs, searchChars.toCharArray()); } /** * <p> * Checks if the CharSequence contains any character in the given set of * characters. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code false}. A {@code null} or * zero length search array will return {@code false}. * </p> * <p/> * <pre> * StringUtils.containsAny(null, *) = false * StringUtils.containsAny("", *) = false * StringUtils.containsAny(*, null) = false * StringUtils.containsAny(*, []) = false * StringUtils.containsAny("zzabyycdxx",['z','a']) = true * StringUtils.containsAny("zzabyycdxx",['b','y']) = true * StringUtils.containsAny("aba", ['z']) = false * </pre> * * @param cs the CharSequence to check, may be null * @param searchChars the chars to search for, may be null * @return the {@code true} if any of the chars are found, {@code false} if * no match or null input * @since 3.0 Changed signature from containsAny(String, char[]) to * containsAny(CharSequence, char...) */ public static boolean containsAny(CharSequence cs, char... searchChars) { if (isEmpty(cs) || searchChars == null) { return false; } int csLength = cs.length(); int searchLength = searchChars.length; int csLast = csLength - 1; int searchLast = searchLength - 1; for (int i = 0; i < csLength; i++) { char ch = cs.charAt(i); for (int j = 0; j < searchLength; j++) { if (searchChars[j] == ch) { if (Character.isHighSurrogate(ch)) { if (j == searchLast) { // missing low surrogate, fine, like // String.indexOf(String) return true; } if (i < csLast && searchChars[j + 1] == cs.charAt(i + 1)) { return true; } } else { // ch is in the Basic Multilingual Plane return true; } } } } return false; } /** * <p> * Checks if the CharSequence contains any character in the given set of * characters. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code false}. A {@code null} * search CharSequence will return {@code false}. * </p> * <p/> * <pre> * StringUtils.containsAny(null, *) = false * StringUtils.containsAny("", *) = false * StringUtils.containsAny(*, null) = false * StringUtils.containsAny(*, "") = false * StringUtils.containsAny("zzabyycdxx", "za") = true * StringUtils.containsAny("zzabyycdxx", "by") = true * StringUtils.containsAny("aba","z") = false * </pre> * * @param cs the CharSequence to check, may be null * @param searchChars the chars to search for, may be null * @return the {@code true} if any of the chars are found, {@code false} if * no match or null input * @since 3.0 Changed signature from containsAny(String, String) to * containsAny(CharSequence, CharSequence) */ public static boolean containsAny(CharSequence cs, CharSequence searchChars) { if (searchChars == null) { return false; } return containsAny(cs, CharSequenceUtils.toCharArray(searchChars)); } /** * <p> * Searches a CharSequence to find the first index of any character not in * the given set of characters. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. A {@code null} or * zero length search array will return {@code -1}. * </p> * <p/> * <pre> * StringUtils.indexOfAnyBut(null, *) = -1 * StringUtils.indexOfAnyBut("", *) = -1 * StringUtils.indexOfAnyBut(*, null) = -1 * StringUtils.indexOfAnyBut(*, []) = -1 * StringUtils.indexOfAnyBut("zzabyycdxx", new char[] {'z', 'a'} ) = 3 * StringUtils.indexOfAnyBut("aba", new char[] {'z'} ) = 0 * StringUtils.indexOfAnyBut("aba", new char[] {'a', 'b'} ) = -1 * * </pre> * * @param cs the CharSequence to check, may be null * @param searchChars the chars to search for, may be null * @return the index of any of the chars, -1 if no match or null input * @since 3.0 Changed signature from indexOfAnyBut(String, char[]) to * indexOfAnyBut(CharSequence, char...) */ public static int indexOfAnyBut(CharSequence cs, char... searchChars) { if (isEmpty(cs) || searchChars == null) { return INDEX_NOT_FOUND; } int csLen = cs.length(); int csLast = csLen - 1; int searchLen = searchChars.length; int searchLast = searchLen - 1; outer: for (int i = 0; i < csLen; i++) { char ch = cs.charAt(i); for (int j = 0; j < searchLen; j++) { if (searchChars[j] == ch) { if (i < csLast && j < searchLast && Character.isHighSurrogate(ch)) { if (searchChars[j + 1] == cs.charAt(i + 1)) { continue outer; } } else { continue outer; } } } return i; } return INDEX_NOT_FOUND; } /** * <p> * Search a CharSequence to find the first index of any character not in the * given set of characters. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. A {@code null} or * empty search string will return {@code -1}. * </p> * <p/> * <pre> * StringUtils.indexOfAnyBut(null, *) = -1 * StringUtils.indexOfAnyBut("", *) = -1 * StringUtils.indexOfAnyBut(*, null) = -1 * StringUtils.indexOfAnyBut(*, "") = -1 * StringUtils.indexOfAnyBut("zzabyycdxx", "za") = 3 * StringUtils.indexOfAnyBut("zzabyycdxx", "") = -1 * StringUtils.indexOfAnyBut("aba","ab") = -1 * </pre> * * @param seq the CharSequence to check, may be null * @param searchChars the chars to search for, may be null * @return the index of any of the chars, -1 if no match or null input * @since 3.0 Changed signature from indexOfAnyBut(String, String) to * indexOfAnyBut(CharSequence, CharSequence) */ public static int indexOfAnyBut(CharSequence seq, CharSequence searchChars) { if (isEmpty(seq) || isEmpty(searchChars)) { return INDEX_NOT_FOUND; } int strLen = seq.length(); for (int i = 0; i < strLen; i++) { char ch = seq.charAt(i); boolean chFound = CharSequenceUtils.indexOf(searchChars, ch, 0) >= 0; if (i + 1 < strLen && Character.isHighSurrogate(ch)) { char ch2 = seq.charAt(i + 1); if (chFound && CharSequenceUtils.indexOf(searchChars, ch2, 0) < 0) { return i; } } else { if (!chFound) { return i; } } } return INDEX_NOT_FOUND; } /** * <p> * Checks if the CharSequence contains only certain characters. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code false}. A {@code null} * valid character array will return {@code false}. An empty CharSequence * (length()=0) always returns {@code true}. * </p> * <p/> * <pre> * StringUtils.containsOnly(null, *) = false * StringUtils.containsOnly(*, null) = false * StringUtils.containsOnly("", *) = true * StringUtils.containsOnly("ab", '') = false * StringUtils.containsOnly("abab", 'abc') = true * StringUtils.containsOnly("ab1", 'abc') = false * StringUtils.containsOnly("abz", 'abc') = false * </pre> * * @param cs the String to check, may be null * @param valid an array of valid chars, may be null * @return true if it only contains valid chars and is non-null * @since 3.0 Changed signature from containsOnly(String, char[]) to * containsOnly(CharSequence, char...) */ public static boolean containsOnly(CharSequence cs, char... valid) { // All these pre-checks are to maintain API with an older version if (valid == null || cs == null) { return false; } if (cs.length() == 0) { return true; } if (valid.length == 0) { return false; } return indexOfAnyBut(cs, valid) == INDEX_NOT_FOUND; } /** * <p> * Checks if the CharSequence contains only certain characters. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code false}. A {@code null} * valid character String will return {@code false}. An empty String * (length()=0) always returns {@code true}. * </p> * <p/> * <pre> * StringUtils.containsOnly(null, *) = false * StringUtils.containsOnly(*, null) = false * StringUtils.containsOnly("", *) = true * StringUtils.containsOnly("ab", "") = false * StringUtils.containsOnly("abab", "abc") = true * StringUtils.containsOnly("ab1", "abc") = false * StringUtils.containsOnly("abz", "abc") = false * </pre> * * @param cs the CharSequence to check, may be null * @param validChars a String of valid chars, may be null * @return true if it only contains valid chars and is non-null * @since 3.0 Changed signature from containsOnly(String, String) to * containsOnly(CharSequence, String) */ public static boolean containsOnly(CharSequence cs, String validChars) { if (cs == null || validChars == null) { return false; } return containsOnly(cs, validChars.toCharArray()); } /** * <p> * Checks that the CharSequence does not contain certain characters. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code true}. A {@code null} * invalid character array will return {@code true}. An empty CharSequence * (length()=0) always returns true. * </p> * <p/> * <pre> * StringUtils.containsNone(null, *) = true * StringUtils.containsNone(*, null) = true * StringUtils.containsNone("", *) = true * StringUtils.containsNone("ab", '') = true * StringUtils.containsNone("abab", 'xyz') = true * StringUtils.containsNone("ab1", 'xyz') = true * StringUtils.containsNone("abz", 'xyz') = false * </pre> * * @param cs the CharSequence to check, may be null * @param searchChars an array of invalid chars, may be null * @return true if it contains none of the invalid chars, or is null * @since 3.0 Changed signature from containsNone(String, char[]) to * containsNone(CharSequence, char...) */ public static boolean containsNone(CharSequence cs, char... searchChars) { if (cs == null || searchChars == null) { return true; } int csLen = cs.length(); int csLast = csLen - 1; int searchLen = searchChars.length; int searchLast = searchLen - 1; for (int i = 0; i < csLen; i++) { char ch = cs.charAt(i); for (int j = 0; j < searchLen; j++) { if (searchChars[j] == ch) { if (Character.isHighSurrogate(ch)) { if (j == searchLast) { // missing low surrogate, fine, like // String.indexOf(String) return false; } if (i < csLast && searchChars[j + 1] == cs.charAt(i + 1)) { return false; } } else { // ch is in the Basic Multilingual Plane return false; } } } } return true; } /** * <p> * Checks that the CharSequence does not contain certain characters. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code true}. A {@code null} * invalid character array will return {@code true}. An empty String ("") * always returns true. * </p> * <p/> * <pre> * StringUtils.containsNone(null, *) = true * StringUtils.containsNone(*, null) = true * StringUtils.containsNone("", *) = true * StringUtils.containsNone("ab", "") = true * StringUtils.containsNone("abab", "xyz") = true * StringUtils.containsNone("ab1", "xyz") = true * StringUtils.containsNone("abz", "xyz") = false * </pre> * * @param cs the CharSequence to check, may be null * @param invalidChars a String of invalid chars, may be null * @return true if it contains none of the invalid chars, or is null * @since 3.0 Changed signature from containsNone(String, String) to * containsNone(CharSequence, String) */ public static boolean containsNone(CharSequence cs, String invalidChars) { if (cs == null || invalidChars == null) { return true; } return containsNone(cs, invalidChars.toCharArray()); } /** * <p> * Find the first index of any of a set of potential substrings. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. A {@code null} or * zero length search array will return {@code -1}. A {@code null} search * array entry will be ignored, but a search array containing "" will return * {@code 0} if {@code str} is not null. This method uses * {@link String#indexOf(String)} if possible. * </p> * <p/> * <pre> * StringUtils.indexOfAny(null, *) = -1 * StringUtils.indexOfAny(*, null) = -1 * StringUtils.indexOfAny(*, []) = -1 * StringUtils.indexOfAny("zzabyycdxx", ["ab","cd"]) = 2 * StringUtils.indexOfAny("zzabyycdxx", ["cd","ab"]) = 2 * StringUtils.indexOfAny("zzabyycdxx", ["mn","op"]) = -1 * StringUtils.indexOfAny("zzabyycdxx", ["zab","aby"]) = 1 * StringUtils.indexOfAny("zzabyycdxx", [""]) = 0 * StringUtils.indexOfAny("", [""]) = 0 * StringUtils.indexOfAny("", ["a"]) = -1 * </pre> * * @param str the CharSequence to check, may be null * @param searchStrs the CharSequences to search for, may be null * @return the first index of any of the searchStrs in str, -1 if no match * @since 3.0 Changed signature from indexOfAny(String, String[]) to * indexOfAny(CharSequence, CharSequence...) */ public static int indexOfAny(CharSequence str, CharSequence... searchStrs) { if (str == null || searchStrs == null) { return INDEX_NOT_FOUND; } int sz = searchStrs.length; // String's can't have a MAX_VALUEth index. int ret = Integer.MAX_VALUE; int tmp = 0; for (int i = 0; i < sz; i++) { CharSequence search = searchStrs[i]; if (search == null) { continue; } tmp = CharSequenceUtils.indexOf(str, search, 0); if (tmp == INDEX_NOT_FOUND) { continue; } if (tmp < ret) { ret = tmp; } } return ret == Integer.MAX_VALUE ? INDEX_NOT_FOUND : ret; } /** * <p> * Find the latest index of any of a set of potential substrings. * </p> * <p/> * <p> * A {@code null} CharSequence will return {@code -1}. A {@code null} search * array will return {@code -1}. A {@code null} or zero length search array * entry will be ignored, but a search array containing "" will return the * length of {@code str} if {@code str} is not null. This method uses * {@link String#indexOf(String)} if possible * </p> * <p/> * <pre> * StringUtils.lastIndexOfAny(null, *) = -1 * StringUtils.lastIndexOfAny(*, null) = -1 * StringUtils.lastIndexOfAny(*, []) = -1 * StringUtils.lastIndexOfAny(*, [null]) = -1 * StringUtils.lastIndexOfAny("zzabyycdxx", ["ab","cd"]) = 6 * StringUtils.lastIndexOfAny("zzabyycdxx", ["cd","ab"]) = 6 * StringUtils.lastIndexOfAny("zzabyycdxx", ["mn","op"]) = -1 * StringUtils.lastIndexOfAny("zzabyycdxx", ["mn","op"]) = -1 * StringUtils.lastIndexOfAny("zzabyycdxx", ["mn",""]) = 10 * </pre> * * @param str the CharSequence to check, may be null * @param searchStrs the CharSequences to search for, may be null * @return the last index of any of the CharSequences, -1 if no match * @since 3.0 Changed signature from lastIndexOfAny(String, String[]) to * lastIndexOfAny(CharSequence, CharSequence) */ public static int lastIndexOfAny(CharSequence str, CharSequence... searchStrs) { if (str == null || searchStrs == null) { return INDEX_NOT_FOUND; } int sz = searchStrs.length; int ret = INDEX_NOT_FOUND; int tmp = 0; for (int i = 0; i < sz; i++) { CharSequence search = searchStrs[i]; if (search == null) { continue; } tmp = CharSequenceUtils.lastIndexOf(str, search, str.length()); if (tmp > ret) { ret = tmp; } } return ret; } /** * <p> * Gets a substring from the specified String avoiding exceptions. * </p> * <p/> * <p> * A negative start position can be used to start {@code n} characters from * the end of the String. * </p> * <p/> * <p> * A {@code null} String will return {@code null}. An empty ("") String will * return "". * </p> * <p/> * <pre> * StringUtils.substring(null, *) = null * StringUtils.substring("", *) = "" * StringUtils.substring("abc", 0) = "abc" * StringUtils.substring("abc", 2) = "c" * StringUtils.substring("abc", 4) = "" * StringUtils.substring("abc", -2) = "bc" * StringUtils.substring("abc", -4) = "abc" * </pre> * * @param str the String to get the substring from, may be null * @param startPos the position to start from, negative means count back from the * end of the String by this many characters * @return substring from start position, {@code null} if null String input */ public static String substring(String str, int startPos) { if (str == null) { return null; } int start = startPos; // handle negatives, which means last n characters if (start < 0) { start = str.length() + start; } if (start < 0) { start = 0; } if (start > str.length()) { return EMPTY; } return str.substring(start); } /** * <p> * Gets a substring from the specified String avoiding exceptions. * </p> * <p/> * <p> * A negative start position can be used to start/end {@code n} characters * from the end of the String. * </p> * <p/> * <p> * The returned substring starts with the character in the {@code start} * position and ends before the {@code end} position. All position counting * is zero-based -- i.e., to start at the beginning of the string use * {@code start = 0}. Negative start and end positions can be used to * specify offsets relative to the end of the String. * </p> * <p/> * <p> * If {@code start} is not strictly to the left of {@code end}, "" is * returned. * </p> * <p/> * <pre> * StringUtils.substring(null, *, *) = null * StringUtils.substring("", * , *) = ""; * StringUtils.substring("abc", 0, 2) = "ab" * StringUtils.substring("abc", 2, 0) = "" * StringUtils.substring("abc", 2, 4) = "c" * StringUtils.substring("abc", 4, 6) = "" * StringUtils.substring("abc", 2, 2) = "" * StringUtils.substring("abc", -2, -1) = "b" * StringUtils.substring("abc", -4, 2) = "ab" * </pre> * * @param str the String to get the substring from, may be null * @param startPos the position to start from, negative means count back from the * end of the String by this many characters * @param endPos the position to end at (exclusive), negative means count back * from the end of the String by this many characters * @return substring from start position to end position, {@code null} if * null String input */ public static String substring(String str, int startPos, int endPos) { if (str == null) { return null; } int start = startPos, end = endPos; // handle negatives if (end < 0) { end = str.length() + end; } if (start < 0) { start = str.length() + start; } // check length next if (end > str.length()) { end = str.length(); } // if start is greater than end, return "" if (start > end) { return EMPTY; } if (start < 0) { start = 0; } if (end < 0) { end = 0; } return str.substring(start, end); } /** * <p> * Gets the leftmost {@code len} characters of a String. * </p> * <p/> * <p> * If {@code len} characters are not available, or the String is * {@code null}, the String will be returned without an exception. An empty * String is returned if len is negative. * </p> * <p/> * <pre> * StringUtils.left(null, *) = null * StringUtils.left(*, -ve) = "" * StringUtils.left("", *) = "" * StringUtils.left("abc", 0) = "" * StringUtils.left("abc", 2) = "ab" * StringUtils.left("abc", 4) = "abc" * </pre> * * @param str the String to get the leftmost characters from, may be null * @param len the length of the required String * @return the leftmost characters, {@code null} if null String input */ public static String left(String str, int len) { if (str == null) { return null; } if (len < 0) { return EMPTY; } if (str.length() <= len) { return str; } return str.substring(0, len); } /** * <p> * Gets the rightmost {@code len} characters of a String. * </p> * <p/> * <p> * If {@code len} characters are not available, or the String is * {@code null}, the String will be returned without an an exception. An * empty String is returned if len is negative. * </p> * <p/> * <pre> * StringUtils.right(null, *) = null * StringUtils.right(*, -ve) = "" * StringUtils.right("", *) = "" * StringUtils.right("abc", 0) = "" * StringUtils.right("abc", 2) = "bc" * StringUtils.right("abc", 4) = "abc" * </pre> * * @param str the String to get the rightmost characters from, may be null * @param len the length of the required String * @return the rightmost characters, {@code null} if null String input */ public static String right(String str, int len) { if (str == null) { return null; } if (len < 0) { return EMPTY; } if (str.length() <= len) { return str; } return str.substring(str.length() - len); } /** * <p> * Gets {@code len} characters from the middle of a String. * </p> * <p/> * <p> * If {@code len} characters are not available, the remainder of the String * will be returned without an exception. If the String is {@code null}, * {@code null} will be returned. An empty String is returned if len is * negative or exceeds the length of {@code str}. * </p> * <p/> * <pre> * StringUtils.mid(null, *, *) = null * StringUtils.mid(*, *, -ve) = "" * StringUtils.mid("", 0, *) = "" * StringUtils.mid("abc", 0, 2) = "ab" * StringUtils.mid("abc", 0, 4) = "abc" * StringUtils.mid("abc", 2, 4) = "c" * StringUtils.mid("abc", 4, 2) = "" * StringUtils.mid("abc", -2, 2) = "ab" * </pre> * * @param str the String to get the characters from, may be null * @param startPos the position to start from, negative treated as zero * @param len the length of the required String * @return the middle characters, {@code null} if null String input */ public static String mid(String str, int startPos, int len) { if (str == null) { return null; } int pos = startPos; if (len < 0 || pos > str.length()) { return EMPTY; } if (pos < 0) { pos = 0; } if (str.length() <= pos + len) { return str.substring(pos); } return str.substring(pos, pos + len); } /** * <p> * Gets the substring before the first occurrence of a separator. The * separator is not returned. * </p> * <p/> * <p> * A {@code null} string input will return {@code null}. An empty ("") * string input will return the empty string. A {@code null} separator will * return the input string. * </p> * <p/> * <p> * If nothing is found, the string input is returned. * </p> * <p/> * <pre> * StringUtils.substringBefore(null, *) = null * StringUtils.substringBefore("", *) = "" * StringUtils.substringBefore("abc", "a") = "" * StringUtils.substringBefore("abcba", "b") = "a" * StringUtils.substringBefore("abc", "c") = "ab" * StringUtils.substringBefore("abc", "d") = "abc" * StringUtils.substringBefore("abc", "") = "" * StringUtils.substringBefore("abc", null) = "abc" * </pre> * * @param str the String to get a substring from, may be null * @param separator the String to search for, may be null * @return the substring before the first occurrence of the separator, * {@code null} if null String input * @since 2.0 */ public static String substringBefore(String str, String separator) { if (isEmpty(str) || separator == null) { return str; } if (separator.length() == 0) { return EMPTY; } int pos = str.indexOf(separator); if (pos == INDEX_NOT_FOUND) { return str; } return str.substring(0, pos); } /** * <p> * Gets the substring after the first occurrence of a separator. The * separator is not returned. * </p> * <p/> * <p> * A {@code null} string input will return {@code null}. An empty ("") * string input will return the empty string. A {@code null} separator will * return the empty string if the input string is not {@code null}. * </p> * <p/> * <p> * If nothing is found, the empty string is returned. * </p> * <p/> * <pre> * StringUtils.substringAfter(null, *) = null * StringUtils.substringAfter("", *) = "" * StringUtils.substringAfter(*, null) = "" * StringUtils.substringAfter("abc", "a") = "bc" * StringUtils.substringAfter("abcba", "b") = "cba" * StringUtils.substringAfter("abc", "c") = "" * StringUtils.substringAfter("abc", "d") = "" * StringUtils.substringAfter("abc", "") = "abc" * </pre> * * @param str the String to get a substring from, may be null * @param separator the String to search for, may be null * @return the substring after the first occurrence of the separator, * {@code null} if null String input * @since 2.0 */ public static String substringAfter(String str, String separator) { if (isEmpty(str)) { return str; } if (separator == null) { return EMPTY; } int pos = str.indexOf(separator); if (pos == INDEX_NOT_FOUND) { return EMPTY; } return str.substring(pos + separator.length()); } /** * <p> * Gets the substring before the last occurrence of a separator. The * separator is not returned. * </p> * <p/> * <p> * A {@code null} string input will return {@code null}. An empty ("") * string input will return the empty string. An empty or {@code null} * separator will return the input string. * </p> * <p/> * <p> * If nothing is found, the string input is returned. * </p> * <p/> * <pre> * StringUtils.substringBeforeLast(null, *) = null * StringUtils.substringBeforeLast("", *) = "" * StringUtils.substringBeforeLast("abcba", "b") = "abc" * StringUtils.substringBeforeLast("abc", "c") = "ab" * StringUtils.substringBeforeLast("a", "a") = "" * StringUtils.substringBeforeLast("a", "z") = "a" * StringUtils.substringBeforeLast("a", null) = "a" * StringUtils.substringBeforeLast("a", "") = "a" * </pre> * * @param str the String to get a substring from, may be null * @param separator the String to search for, may be null * @return the substring before the last occurrence of the separator, * {@code null} if null String input * @since 2.0 */ public static String substringBeforeLast(String str, String separator) { if (isEmpty(str) || isEmpty(separator)) { return str; } int pos = str.lastIndexOf(separator); if (pos == INDEX_NOT_FOUND) { return str; } return str.substring(0, pos); } /** * <p> * Gets the substring after the last occurrence of a separator. The * separator is not returned. * </p> * <p/> * <p> * A {@code null} string input will return {@code null}. An empty ("") * string input will return the empty string. An empty or {@code null} * separator will return the empty string if the input string is not * {@code null}. * </p> * <p/> * <p> * If nothing is found, the empty string is returned. * </p> * <p/> * <pre> * StringUtils.substringAfterLast(null, *) = null * StringUtils.substringAfterLast("", *) = "" * StringUtils.substringAfterLast(*, "") = "" * StringUtils.substringAfterLast(*, null) = "" * StringUtils.substringAfterLast("abc", "a") = "bc" * StringUtils.substringAfterLast("abcba", "b") = "a" * StringUtils.substringAfterLast("abc", "c") = "" * StringUtils.substringAfterLast("a", "a") = "" * StringUtils.substringAfterLast("a", "z") = "" * </pre> * * @param str the String to get a substring from, may be null * @param separator the String to search for, may be null * @return the substring after the last occurrence of the separator, * {@code null} if null String input * @since 2.0 */ public static String substringAfterLast(String str, String separator) { if (isEmpty(str)) { return str; } if (isEmpty(separator)) { return EMPTY; } int pos = str.lastIndexOf(separator); if (pos == INDEX_NOT_FOUND || pos == str.length() - separator.length()) { return EMPTY; } return str.substring(pos + separator.length()); } /** * <p> * Gets the String that is nested in between two instances of the same * String. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} tag * returns {@code null}. * </p> * <p/> * <pre> * StringUtils.substringBetween(null, *) = null * StringUtils.substringBetween("", "") = "" * StringUtils.substringBetween("", "tag") = null * StringUtils.substringBetween("tagabctag", null) = null * StringUtils.substringBetween("tagabctag", "") = "" * StringUtils.substringBetween("tagabctag", "tag") = "abc" * </pre> * * @param str the String containing the substring, may be null * @param tag the String before and after the substring, may be null * @return the substring, {@code null} if no match * @since 2.0 */ public static String substringBetween(String str, String tag) { return substringBetween(str, tag, tag); } /** * <p> * Gets the String that is nested in between two Strings. Only the first * match is returned. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} * open/close returns {@code null} (no match). An empty ("") open and close * returns an empty string. * </p> * <p/> * <pre> * StringUtils.substringBetween("wx[b]yz", "[", "]") = "b" * StringUtils.substringBetween(null, *, *) = null * StringUtils.substringBetween(*, null, *) = null * StringUtils.substringBetween(*, *, null) = null * StringUtils.substringBetween("", "", "") = "" * StringUtils.substringBetween("", "", "]") = null * StringUtils.substringBetween("", "[", "]") = null * StringUtils.substringBetween("yabcz", "", "") = "" * StringUtils.substringBetween("yabcz", "y", "z") = "abc" * StringUtils.substringBetween("yabczyabcz", "y", "z") = "abc" * </pre> * * @param str the String containing the substring, may be null * @param open the String before the substring, may be null * @param close the String after the substring, may be null * @return the substring, {@code null} if no match * @since 2.0 */ public static String substringBetween(String str, String open, String close) { if (str == null || open == null || close == null) { return null; } int start = str.indexOf(open); if (start != INDEX_NOT_FOUND) { int end = str.indexOf(close, start + open.length()); if (end != INDEX_NOT_FOUND) { return str.substring(start + open.length(), end); } } return null; } /** * <p> * Searches a String for substrings delimited by a start and end tag, * returning all matching substrings in an array. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} * open/close returns {@code null} (no match). An empty ("") open/close * returns {@code null} (no match). * </p> * <p/> * <pre> * StringUtils.substringsBetween("[a][b][c]", "[", "]") = ["a","b","c"] * StringUtils.substringsBetween(null, *, *) = null * StringUtils.substringsBetween(*, null, *) = null * StringUtils.substringsBetween(*, *, null) = null * StringUtils.substringsBetween("", "[", "]") = [] * </pre> * * @param str the String containing the substrings, null returns null, empty * returns empty * @param open the String identifying the start of the substring, empty * returns null * @param close the String identifying the end of the substring, empty returns * null * @return a String Array of substrings, or {@code null} if no match * @since 2.3 */ public static String[] substringsBetween(String str, String open, String close) { if (str == null || isEmpty(open) || isEmpty(close)) { return new String[0]; } int strLen = str.length(); if (strLen == 0) { return new String[0]; } int closeLen = close.length(); int openLen = open.length(); List<String> list = new ArrayList<>(); int pos = 0; while (pos < strLen - closeLen) { int start = str.indexOf(open, pos); if (start < 0) { break; } start += openLen; int end = str.indexOf(close, start); if (end < 0) { break; } list.add(str.substring(start, end)); pos = end + closeLen; } if (list.isEmpty()) { return new String[0]; } return list.toArray(new String[list.size()]); } /** * <p> * Splits the provided text into an array, using whitespace as the * separator. Whitespace is defined by {@link Character#isWhitespace(char)}. * </p> * <p/> * <p> * The separator is not included in the returned String array. Adjacent * separators are treated as one separator. For more control over the split * use the StrTokenizer class. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.split(null) = null * StringUtils.split("") = [] * StringUtils.split("abc def") = ["abc", "def"] * StringUtils.split("abc def") = ["abc", "def"] * StringUtils.split(" abc ") = ["abc"] * </pre> * * @param str the String to parse, may be null * @return an array of parsed Strings, {@code null} if null String input */ public static String[] split(String str) { return split(str, null, -1); } /** * <p> * Splits the provided text into an array, separator specified. This is an * alternative to using StringTokenizer. * </p> * <p/> * <p> * The separator is not included in the returned String array. Adjacent * separators are treated as one separator. For more control over the split * use the StrTokenizer class. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.split(null, *) = null * StringUtils.split("", *) = [] * StringUtils.split("a.b.c", '.') = ["a", "b", "c"] * StringUtils.split("a..b.c", '.') = ["a", "b", "c"] * StringUtils.split("a:b:c", '.') = ["a:b:c"] * StringUtils.split("a b c", ' ') = ["a", "b", "c"] * </pre> * * @param str the String to parse, may be null * @param separatorChar the character used as the delimiter * @return an array of parsed Strings, {@code null} if null String input * @since 2.0 */ public static String[] split(String str, char separatorChar) { return splitWorker(str, separatorChar, false); } /** * <p> * Splits the provided text into an array, separators specified. This is an * alternative to using StringTokenizer. * </p> * <p/> * <p> * The separator is not included in the returned String array. Adjacent * separators are treated as one separator. For more control over the split * use the StrTokenizer class. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} * separatorChars splits on whitespace. * </p> * <p/> * <pre> * StringUtils.split(null, *) = null * StringUtils.split("", *) = [] * StringUtils.split("abc def", null) = ["abc", "def"] * StringUtils.split("abc def", " ") = ["abc", "def"] * StringUtils.split("abc def", " ") = ["abc", "def"] * StringUtils.split("ab:cd:ef", ":") = ["ab", "cd", "ef"] * </pre> * * @param str the String to parse, may be null * @param separatorChars the characters used as the delimiters, {@code null} splits on * whitespace * @return an array of parsed Strings, {@code null} if null String input */ public static String[] split(String str, String separatorChars) { return splitWorker(str, separatorChars, -1, false); } /** * <p> * Splits the provided text into an array with a maximum length, separators * specified. * </p> * <p/> * <p> * The separator is not included in the returned String array. Adjacent * separators are treated as one separator. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} * separatorChars splits on whitespace. * </p> * <p/> * <p> * If more than {@code max} delimited substrings are found, the last * returned string includes all characters after the first {@code max - 1} * returned strings (including separator characters). * </p> * <p/> * <pre> * StringUtils.split(null, *, *) = null * StringUtils.split("", *, *) = [] * StringUtils.split("ab de fg", null, 0) = ["ab", "cd", "ef"] * StringUtils.split("ab de fg", null, 0) = ["ab", "cd", "ef"] * StringUtils.split("ab:cd:ef", ":", 0) = ["ab", "cd", "ef"] * StringUtils.split("ab:cd:ef", ":", 2) = ["ab", "cd:ef"] * </pre> * * @param str the String to parse, may be null * @param separatorChars the characters used as the delimiters, {@code null} splits on * whitespace * @param max the maximum number of elements to include in the array. A zero * or negative value implies no limit * @return an array of parsed Strings, {@code null} if null String input */ public static String[] split(String str, String separatorChars, int max) { return splitWorker(str, separatorChars, max, false); } /** * <p> * Splits the provided text into an array, separator string specified. * </p> * <p/> * <p> * The separator(s) will not be included in the returned String array. * Adjacent separators are treated as one separator. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} * separator splits on whitespace. * </p> * <p/> * <pre> * StringUtils.splitByWholeSeparator(null, *) = null * StringUtils.splitByWholeSeparator("", *) = [] * StringUtils.splitByWholeSeparator("ab de fg", null) = ["ab", "de", "fg"] * StringUtils.splitByWholeSeparator("ab de fg", null) = ["ab", "de", "fg"] * StringUtils.splitByWholeSeparator("ab:cd:ef", ":") = ["ab", "cd", "ef"] * StringUtils.splitByWholeSeparator("ab-!-cd-!-ef", "-!-") = ["ab", "cd", "ef"] * </pre> * * @param str the String to parse, may be null * @param separator String containing the String to be used as a delimiter, * {@code null} splits on whitespace * @return an array of parsed Strings, {@code null} if null String was input */ public static String[] splitByWholeSeparator(String str, String separator) { return splitByWholeSeparatorWorker(str, separator, -1, false); } /** * <p> * Splits the provided text into an array, separator string specified. * Returns a maximum of {@code max} substrings. * </p> * <p/> * <p> * The separator(s) will not be included in the returned String array. * Adjacent separators are treated as one separator. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} * separator splits on whitespace. * </p> * <p/> * <pre> * StringUtils.splitByWholeSeparator(null, *, *) = null * StringUtils.splitByWholeSeparator("", *, *) = [] * StringUtils.splitByWholeSeparator("ab de fg", null, 0) = ["ab", "de", "fg"] * StringUtils.splitByWholeSeparator("ab de fg", null, 0) = ["ab", "de", "fg"] * StringUtils.splitByWholeSeparator("ab:cd:ef", ":", 2) = ["ab", "cd:ef"] * StringUtils.splitByWholeSeparator("ab-!-cd-!-ef", "-!-", 5) = ["ab", "cd", "ef"] * StringUtils.splitByWholeSeparator("ab-!-cd-!-ef", "-!-", 2) = ["ab", "cd-!-ef"] * </pre> * * @param str the String to parse, may be null * @param separator String containing the String to be used as a delimiter, * {@code null} splits on whitespace * @param max the maximum number of elements to include in the returned * array. A zero or negative value implies no limit. * @return an array of parsed Strings, {@code null} if null String was input */ public static String[] splitByWholeSeparator(String str, String separator, int max) { return splitByWholeSeparatorWorker(str, separator, max, false); } /** * <p> * Splits the provided text into an array, separator string specified. * </p> * <p/> * <p> * The separator is not included in the returned String array. Adjacent * separators are treated as separators for empty tokens. For more control * over the split use the StrTokenizer class. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} * separator splits on whitespace. * </p> * <p/> * <pre> * StringUtils.splitByWholeSeparatorPreserveAllTokens(null, *) = null * StringUtils.splitByWholeSeparatorPreserveAllTokens("", *) = [] * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab de fg", null) = ["ab", "de", "fg"] * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab de fg", null) = ["ab", "", "", "de", "fg"] * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab:cd:ef", ":") = ["ab", "cd", "ef"] * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab-!-cd-!-ef", "-!-") = ["ab", "cd", "ef"] * </pre> * * @param str the String to parse, may be null * @param separator String containing the String to be used as a delimiter, * {@code null} splits on whitespace * @return an array of parsed Strings, {@code null} if null String was input * @since 2.4 */ public static String[] splitByWholeSeparatorPreserveAllTokens(String str, String separator) { return splitByWholeSeparatorWorker(str, separator, -1, true); } /** * <p> * Splits the provided text into an array, separator string specified. * Returns a maximum of {@code max} substrings. * </p> * <p/> * <p> * The separator is not included in the returned String array. Adjacent * separators are treated as separators for empty tokens. For more control * over the split use the StrTokenizer class. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} * separator splits on whitespace. * </p> * <p/> * <pre> * StringUtils.splitByWholeSeparatorPreserveAllTokens(null, *, *) = null * StringUtils.splitByWholeSeparatorPreserveAllTokens("", *, *) = [] * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab de fg", null, 0) = ["ab", "de", "fg"] * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab de fg", null, 0) = ["ab", "", "", "de", "fg"] * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab:cd:ef", ":", 2) = ["ab", "cd:ef"] * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab-!-cd-!-ef", "-!-", 5) = ["ab", "cd", "ef"] * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab-!-cd-!-ef", "-!-", 2) = ["ab", "cd-!-ef"] * </pre> * * @param str the String to parse, may be null * @param separator String containing the String to be used as a delimiter, * {@code null} splits on whitespace * @param max the maximum number of elements to include in the returned * array. A zero or negative value implies no limit. * @return an array of parsed Strings, {@code null} if null String was input * @since 2.4 */ public static String[] splitByWholeSeparatorPreserveAllTokens(String str, String separator, int max) { return splitByWholeSeparatorWorker(str, separator, max, true); } /** * Performs the logic for the {@code splitByWholeSeparatorPreserveAllTokens} * methods. * * @param str the String to parse, may be {@code null} * @param separator String containing the String to be used as a delimiter, * {@code null} splits on whitespace * @param max the maximum number of elements to include in the returned * array. A zero or negative value implies no limit. * @param preserveAllTokens if {@code true}, adjacent separators are treated as empty * token separators; if {@code false}, adjacent separators are * treated as one separator. * @return an array of parsed Strings, {@code null} if null String input * @since 2.4 */ private static String[] splitByWholeSeparatorWorker(String str, String separator, int max, boolean preserveAllTokens) { if (str == null) { return new String[0]; } int len = str.length(); if (len == 0) { return EMPTY_STRING_ARRAY; } if (separator == null || EMPTY.equals(separator)) { // Split on whitespace. return splitWorker(str, null, max, preserveAllTokens); } int separatorLength = separator.length(); ArrayList<String> substrings = new ArrayList<String>(); int numberOfSubstrings = 0; int beg = 0; int end = 0; while (end < len) { end = str.indexOf(separator, beg); if (end > -1) { if (end > beg) { numberOfSubstrings += 1; if (numberOfSubstrings == max) { end = len; substrings.add(str.substring(beg)); } else { // The following is OK, because String.substring( beg, // end ) excludes // the character at the position 'end'. substrings.add(str.substring(beg, end)); // Set the starting point for the next search. // The following is equivalent to beg = end + // (separatorLength - 1) + 1, // which is the right calculation: beg = end + separatorLength; } } else { // We found a consecutive occurrence of the separator, so // skip it. if (preserveAllTokens) { numberOfSubstrings += 1; if (numberOfSubstrings == max) { end = len; substrings.add(str.substring(beg)); } else { substrings.add(EMPTY); } } beg = end + separatorLength; } } else { // String.substring( beg ) goes from 'beg' to the end of the // String. substrings.add(str.substring(beg)); end = len; } } return substrings.toArray(new String[substrings.size()]); } /** * <p> * Splits the provided text into an array, using whitespace as the * separator, preserving all tokens, including empty tokens created by * adjacent separators. This is an alternative to using StringTokenizer. * Whitespace is defined by {@link Character#isWhitespace(char)}. * </p> * <p/> * <p> * The separator is not included in the returned String array. Adjacent * separators are treated as separators for empty tokens. For more control * over the split use the StrTokenizer class. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.splitPreserveAllTokens(null) = null * StringUtils.splitPreserveAllTokens("") = [] * StringUtils.splitPreserveAllTokens("abc def") = ["abc", "def"] * StringUtils.splitPreserveAllTokens("abc def") = ["abc", "", "def"] * StringUtils.splitPreserveAllTokens(" abc ") = ["", "abc", ""] * </pre> * * @param str the String to parse, may be {@code null} * @return an array of parsed Strings, {@code null} if null String input * @since 2.1 */ public static String[] splitPreserveAllTokens(String str) { return splitWorker(str, null, -1, true); } /** * <p> * Splits the provided text into an array, separator specified, preserving * all tokens, including empty tokens created by adjacent separators. This * is an alternative to using StringTokenizer. * </p> * <p/> * <p> * The separator is not included in the returned String array. Adjacent * separators are treated as separators for empty tokens. For more control * over the split use the StrTokenizer class. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.splitPreserveAllTokens(null, *) = null * StringUtils.splitPreserveAllTokens("", *) = [] * StringUtils.splitPreserveAllTokens("a.b.c", '.') = ["a", "b", "c"] * StringUtils.splitPreserveAllTokens("a..b.c", '.') = ["a", "", "b", "c"] * StringUtils.splitPreserveAllTokens("a:b:c", '.') = ["a:b:c"] * StringUtils.splitPreserveAllTokens("a\tb\nc", null) = ["a", "b", "c"] * StringUtils.splitPreserveAllTokens("a b c", ' ') = ["a", "b", "c"] * StringUtils.splitPreserveAllTokens("a b c ", ' ') = ["a", "b", "c", ""] * StringUtils.splitPreserveAllTokens("a b c ", ' ') = ["a", "b", "c", "", ""] * StringUtils.splitPreserveAllTokens(" a b c", ' ') = ["", a", "b", "c"] * StringUtils.splitPreserveAllTokens(" a b c", ' ') = ["", "", a", "b", "c"] * StringUtils.splitPreserveAllTokens(" a b c ", ' ') = ["", a", "b", "c", ""] * </pre> * * @param str the String to parse, may be {@code null} * @param separatorChar the character used as the delimiter, {@code null} splits on * whitespace * @return an array of parsed Strings, {@code null} if null String input * @since 2.1 */ public static String[] splitPreserveAllTokens(String str, char separatorChar) { return splitWorker(str, separatorChar, true); } /** * Performs the logic for the {@code split} and * {@code splitPreserveAllTokens} methods that do not return a maximum array * length. * * @param str the String to parse, may be {@code null} * @param separatorChar the separate character * @param preserveAllTokens if {@code true}, adjacent separators are treated as empty * token separators; if {@code false}, adjacent separators are * treated as one separator. * @return an array of parsed Strings, {@code null} if null String input */ private static String[] splitWorker(String str, char separatorChar, boolean preserveAllTokens) { // Performance tuned for 2.0 (JDK1.4) if (str == null) { return new String[0]; } int len = str.length(); if (len == 0) { return EMPTY_STRING_ARRAY; } List<String> list = new ArrayList<String>(); int i = 0, start = 0; boolean match = false; boolean lastMatch = false; while (i < len) { if (str.charAt(i) == separatorChar) { if (match || preserveAllTokens) { list.add(str.substring(start, i)); match = false; lastMatch = true; } start = ++i; continue; } lastMatch = false; match = true; i++; } if (match || preserveAllTokens && lastMatch) { list.add(str.substring(start, i)); } return list.toArray(new String[list.size()]); } /** * <p> * Splits the provided text into an array, separators specified, preserving * all tokens, including empty tokens created by adjacent separators. This * is an alternative to using StringTokenizer. * </p> * <p/> * <p> * The separator is not included in the returned String array. Adjacent * separators are treated as separators for empty tokens. For more control * over the split use the StrTokenizer class. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} * separatorChars splits on whitespace. * </p> * <p/> * <pre> * StringUtils.splitPreserveAllTokens(null, *) = null * StringUtils.splitPreserveAllTokens("", *) = [] * StringUtils.splitPreserveAllTokens("abc def", null) = ["abc", "def"] * StringUtils.splitPreserveAllTokens("abc def", " ") = ["abc", "def"] * StringUtils.splitPreserveAllTokens("abc def", " ") = ["abc", "", def"] * StringUtils.splitPreserveAllTokens("ab:cd:ef", ":") = ["ab", "cd", "ef"] * StringUtils.splitPreserveAllTokens("ab:cd:ef:", ":") = ["ab", "cd", "ef", ""] * StringUtils.splitPreserveAllTokens("ab:cd:ef::", ":") = ["ab", "cd", "ef", "", ""] * StringUtils.splitPreserveAllTokens("ab::cd:ef", ":") = ["ab", "", cd", "ef"] * StringUtils.splitPreserveAllTokens(":cd:ef", ":") = ["", cd", "ef"] * StringUtils.splitPreserveAllTokens("::cd:ef", ":") = ["", "", cd", "ef"] * StringUtils.splitPreserveAllTokens(":cd:ef:", ":") = ["", cd", "ef", ""] * </pre> * * @param str the String to parse, may be {@code null} * @param separatorChars the characters used as the delimiters, {@code null} splits on * whitespace * @return an array of parsed Strings, {@code null} if null String input * @since 2.1 */ public static String[] splitPreserveAllTokens(String str, String separatorChars) { return splitWorker(str, separatorChars, -1, true); } /** * <p> * Splits the provided text into an array with a maximum length, separators * specified, preserving all tokens, including empty tokens created by * adjacent separators. * </p> * <p/> * <p> * The separator is not included in the returned String array. Adjacent * separators are treated as separators for empty tokens. Adjacent * separators are treated as one separator. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. A {@code null} * separatorChars splits on whitespace. * </p> * <p/> * <p> * If more than {@code max} delimited substrings are found, the last * returned string includes all characters after the first {@code max - 1} * returned strings (including separator characters). * </p> * <p/> * <pre> * StringUtils.splitPreserveAllTokens(null, *, *) = null * StringUtils.splitPreserveAllTokens("", *, *) = [] * StringUtils.splitPreserveAllTokens("ab de fg", null, 0) = ["ab", "cd", "ef"] * StringUtils.splitPreserveAllTokens("ab de fg", null, 0) = ["ab", "cd", "ef"] * StringUtils.splitPreserveAllTokens("ab:cd:ef", ":", 0) = ["ab", "cd", "ef"] * StringUtils.splitPreserveAllTokens("ab:cd:ef", ":", 2) = ["ab", "cd:ef"] * StringUtils.splitPreserveAllTokens("ab de fg", null, 2) = ["ab", " de fg"] * StringUtils.splitPreserveAllTokens("ab de fg", null, 3) = ["ab", "", " de fg"] * StringUtils.splitPreserveAllTokens("ab de fg", null, 4) = ["ab", "", "", "de fg"] * </pre> * * @param str the String to parse, may be {@code null} * @param separatorChars the characters used as the delimiters, {@code null} splits on * whitespace * @param max the maximum number of elements to include in the array. A zero * or negative value implies no limit * @return an array of parsed Strings, {@code null} if null String input * @since 2.1 */ public static String[] splitPreserveAllTokens(String str, String separatorChars, int max) { return splitWorker(str, separatorChars, max, true); } /** * Performs the logic for the {@code split} and * {@code splitPreserveAllTokens} methods that return a maximum array * length. * * @param str the String to parse, may be {@code null} * @param separatorChars the separate character * @param max the maximum number of elements to include in the array. A zero * or negative value implies no limit. * @param preserveAllTokens if {@code true}, adjacent separators are treated as empty * token separators; if {@code false}, adjacent separators are * treated as one separator. * @return an array of parsed Strings, {@code null} if null String input */ private static String[] splitWorker(String str, String separatorChars, int max, boolean preserveAllTokens) { // Performance tuned for 2.0 (JDK1.4) // Direct code is quicker than StringTokenizer. // Also, StringTokenizer uses isSpace() not isWhitespace() if (str == null) { return new String[0]; } int len = str.length(); if (len == 0) { return EMPTY_STRING_ARRAY; } List<String> list = new ArrayList<String>(); int sizePlus1 = 1; int i = 0, start = 0; boolean match = false; boolean lastMatch = false; if (separatorChars == null) { // Null separator means use whitespace while (i < len) { if (Character.isWhitespace(str.charAt(i))) { if (match || preserveAllTokens) { lastMatch = true; if (sizePlus1++ == max) { i = len; lastMatch = false; } list.add(str.substring(start, i)); match = false; } start = ++i; continue; } lastMatch = false; match = true; i++; } } else if (separatorChars.length() == 1) { // Optimise 1 character case char sep = separatorChars.charAt(0); while (i < len) { if (str.charAt(i) == sep) { if (match || preserveAllTokens) { lastMatch = true; if (sizePlus1++ == max) { i = len; lastMatch = false; } list.add(str.substring(start, i)); match = false; } start = ++i; continue; } lastMatch = false; match = true; i++; } } else { // standard case while (i < len) { if (separatorChars.indexOf(str.charAt(i)) >= 0) { if (match || preserveAllTokens) { lastMatch = true; if (sizePlus1++ == max) { i = len; lastMatch = false; } list.add(str.substring(start, i)); match = false; } start = ++i; continue; } lastMatch = false; match = true; i++; } } if (match || preserveAllTokens && lastMatch) { list.add(str.substring(start, i)); } return list.toArray(new String[list.size()]); } /** * <p/> * Splits a String by Character type as returned by * {@code java.lang.Character.getType(char)}. Groups of contiguous * characters of the same type are returned as complete tokens. * <p/> * <pre> * StringUtils.splitByCharacterType(null) = null * StringUtils.splitByCharacterType("") = [] * StringUtils.splitByCharacterType("ab de fg") = ["ab", " ", "de", " ", "fg"] * StringUtils.splitByCharacterType("ab de fg") = ["ab", " ", "de", " ", "fg"] * StringUtils.splitByCharacterType("ab:cd:ef") = ["ab", ":", "cd", ":", "ef"] * StringUtils.splitByCharacterType("number5") = ["number", "5"] * StringUtils.splitByCharacterType("fooBar") = ["foo", "B", "ar"] * StringUtils.splitByCharacterType("foo200Bar") = ["foo", "200", "B", "ar"] * StringUtils.splitByCharacterType("ASFRules") = ["ASFR", "ules"] * </pre> * * @param str the String to split, may be {@code null} * @return an array of parsed Strings, {@code null} if null String input * @since 2.4 */ public static String[] splitByCharacterType(String str) { return splitByCharacterType(str, false); } /** * <p/> * Splits a String by Character type as returned by * {@code java.lang.Character.getType(char)}. Groups of contiguous * characters of the same type are returned as complete tokens, with the * following exception: the character of type * {@code Character.UPPERCASE_LETTER}, if any, immediately preceding a token * of type {@code Character.LOWERCASE_LETTER} will belong to the following * token rather than to the preceding, if any, * {@code Character.UPPERCASE_LETTER} token. * <p/> * <pre> * StringUtils.splitByCharacterTypeCamelCase(null) = null * StringUtils.splitByCharacterTypeCamelCase("") = [] * StringUtils.splitByCharacterTypeCamelCase("ab de fg") = ["ab", " ", "de", " ", "fg"] * StringUtils.splitByCharacterTypeCamelCase("ab de fg") = ["ab", " ", "de", " ", "fg"] * StringUtils.splitByCharacterTypeCamelCase("ab:cd:ef") = ["ab", ":", "cd", ":", "ef"] * StringUtils.splitByCharacterTypeCamelCase("number5") = ["number", "5"] * StringUtils.splitByCharacterTypeCamelCase("fooBar") = ["foo", "Bar"] * StringUtils.splitByCharacterTypeCamelCase("foo200Bar") = ["foo", "200", "Bar"] * StringUtils.splitByCharacterTypeCamelCase("ASFRules") = ["ASF", "Rules"] * </pre> * * @param str the String to split, may be {@code null} * @return an array of parsed Strings, {@code null} if null String input * @since 2.4 */ public static String[] splitByCharacterTypeCamelCase(String str) { return splitByCharacterType(str, true); } /** * <p/> * Splits a String by Character type as returned by * {@code java.lang.Character.getType(char)}. Groups of contiguous * characters of the same type are returned as complete tokens, with the * following exception: if {@code camelCase} is {@code true}, the character * of type {@code Character.UPPERCASE_LETTER}, if any, immediately preceding * a token of type {@code Character.LOWERCASE_LETTER} will belong to the * following token rather than to the preceding, if any, * {@code Character.UPPERCASE_LETTER} token. * * @param str the String to split, may be {@code null} * @param camelCase whether to use so-called "camel-case" for letter types * @return an array of parsed Strings, {@code null} if null String input * @since 2.4 */ private static String[] splitByCharacterType(String str, boolean camelCase) { if (str == null) { return new String[0]; } if (str.length() == 0) { return EMPTY_STRING_ARRAY; } char[] c = str.toCharArray(); List<String> list = new ArrayList<String>(); int tokenStart = 0; int currentType = Character.getType(c[tokenStart]); for (int pos = tokenStart + 1; pos < c.length; pos++) { int type = Character.getType(c[pos]); if (type == currentType) { continue; } if (camelCase && type == Character.LOWERCASE_LETTER && currentType == Character.UPPERCASE_LETTER) { int newTokenStart = pos - 1; if (newTokenStart != tokenStart) { list.add(new String(c, tokenStart, newTokenStart - tokenStart)); tokenStart = newTokenStart; } } else { list.add(new String(c, tokenStart, pos - tokenStart)); tokenStart = pos; } currentType = type; } list.add(new String(c, tokenStart, c.length - tokenStart)); return list.toArray(new String[list.size()]); } /** * <p> * Joins the elements of the provided array into a single String containing * the provided list of elements. * </p> * <p/> * <p> * No separator is added to the joined String. Null objects or empty strings * within the array are represented by empty strings. * </p> * <p/> * <pre> * StringUtils.join(null) = null * StringUtils.join([]) = "" * StringUtils.join([null]) = "" * StringUtils.join(["a", "b", "c"]) = "abc" * StringUtils.join([null, "", "a"]) = "a" * </pre> * * @param <T> the specific type of values to join together * @param elements the values to join together, may be null * @return the joined String, {@code null} if null array input * @since 3.0 Changed signature to use varargs */ @SuppressWarnings("unchecked") public static <T> String join(T... elements) { return join(elements, null); } /** * <p> * Joins the elements of the provided array into a single String containing * the provided list of elements. * </p> * <p/> * <p> * No delimiter is added before or after the list. Null objects or empty * strings within the array are represented by empty strings. * </p> * <p/> * <pre> * StringUtils.join(null, *) = null * StringUtils.join([], *) = "" * StringUtils.join([null], *) = "" * StringUtils.join(["a", "b", "c"], ';') = "a;b;c" * StringUtils.join(["a", "b", "c"], null) = "abc" * StringUtils.join([null, "", "a"], ';') = ";;a" * </pre> * * @param array the array of values to join together, may be null * @param separator the separator character to use * @return the joined String, {@code null} if null array input * @since 2.0 */ public static String join(Object[] array, char separator) { if (array == null) { return null; } return join(array, separator, 0, array.length); } /** * <p> * Joins the elements of the provided array into a single String containing * the provided list of elements. * </p> * <p/> * <p> * No delimiter is added before or after the list. Null objects or empty * strings within the array are represented by empty strings. * </p> * <p/> * <pre> * StringUtils.join(null, *) = null * StringUtils.join([], *) = "" * StringUtils.join([null], *) = "" * StringUtils.join(["a", "b", "c"], ';') = "a;b;c" * StringUtils.join(["a", "b", "c"], null) = "abc" * StringUtils.join([null, "", "a"], ';') = ";;a" * </pre> * * @param array the array of values to join together, may be null * @param separator the separator character to use * @param startIndex the first index to start joining from. It is an error to pass * in an end index past the end of the array * @param endIndex the index to stop joining from (exclusive). It is an error to * pass in an end index past the end of the array * @return the joined String, {@code null} if null array input * @since 2.0 */ public static String join(Object[] array, char separator, int startIndex, int endIndex) { if (array == null) { return null; } int noOfItems = endIndex - startIndex; if (noOfItems <= 0) { return EMPTY; } StringBuilder buf = new StringBuilder(noOfItems * CommonPlatformConstant.LENGTH_16); for (int i = startIndex; i < endIndex; i++) { if (i > startIndex) { buf.append(separator); } if (array[i] != null) { buf.append(array[i]); } } return buf.toString(); } /** * <p> * Joins the elements of the provided array into a single String containing * the provided list of elements. * </p> * <p/> * <p> * No delimiter is added before or after the list. A {@code null} separator * is the same as an empty String (""). Null objects or empty strings within * the array are represented by empty strings. * </p> * <p/> * <pre> * StringUtils.join(null, *) = null * StringUtils.join([], *) = "" * StringUtils.join([null], *) = "" * StringUtils.join(["a", "b", "c"], "--") = "a--b--c" * StringUtils.join(["a", "b", "c"], null) = "abc" * StringUtils.join(["a", "b", "c"], "") = "abc" * StringUtils.join([null, "", "a"], ',') = ",,a" * </pre> * * @param array the array of values to join together, may be null * @param separator the separator character to use, null treated as "" * @return the joined String, {@code null} if null array input */ public static String join(Object[] array, String separator) { if (array == null) { return null; } return join(array, separator, 0, array.length); } /** * <p> * Joins the elements of the provided array into a single String containing * the provided list of elements. * </p> * <p/> * <p> * No delimiter is added before or after the list. A {@code null} separator * is the same as an empty String (""). Null objects or empty strings within * the array are represented by empty strings. * </p> * <p/> * <pre> * StringUtils.join(null, *) = null * StringUtils.join([], *) = "" * StringUtils.join([null], *) = "" * StringUtils.join(["a", "b", "c"], "--") = "a--b--c" * StringUtils.join(["a", "b", "c"], null) = "abc" * StringUtils.join(["a", "b", "c"], "") = "abc" * StringUtils.join([null, "", "a"], ',') = ",,a" * </pre> * * @param array the array of values to join together, may be null * @param separat the separator character to use, null treated as "" * @param startIndex the first index to start joining from. It is an error to pass * in an end index past the end of the array * @param endIndex the index to stop joining from (exclusive). It is an error to * pass in an end index past the end of the array * @return the joined String, {@code null} if null array input */ public static String join(Object[] array, String separat, int startIndex, int endIndex) { if (array == null) { return null; } String separator = separat; if (separator == null) { separator = EMPTY; } // endIndex - startIndex > 0: Len = NofStrings *(len(firstString) + // len(separator)) // (Assuming that all Strings are roughly equally long) int noOfItems = endIndex - startIndex; if (noOfItems <= 0) { return EMPTY; } StringBuilder buf = new StringBuilder(noOfItems * CommonPlatformConstant.LENGTH_16); for (int i = startIndex; i < endIndex; i++) { if (i > startIndex) { buf.append(separator); } if (array[i] != null) { buf.append(array[i]); } } return buf.toString(); } /** * <p> * Joins the elements of the provided {@code Iterator} into a single String * containing the provided elements. * </p> * <p/> * <p> * No delimiter is added before or after the list. Null objects or empty * strings within the iteration are represented by empty strings. * </p> * <p/> * <p> * See the examples here: {@link #join(Object[], char)}. * </p> * * @param iterator the {@code Iterator} of values to join together, may be null * @param separator the separator character to use * @return the joined String, {@code null} if null iterator input * @since 2.0 */ public static String join(Iterator<?> iterator, char separator) { // handle null, zero and one elements before building a buffer if (iterator == null) { return null; } if (!iterator.hasNext()) { return EMPTY; } Object first = iterator.next(); if (!iterator.hasNext()) { return first == null ? "" : first.toString(); } // two or more elements StringBuilder buf = new StringBuilder(CommonPlatformConstant.LENGTH_256); // probably too small if (first != null) { buf.append(first); } while (iterator.hasNext()) { buf.append(separator); Object obj = iterator.next(); if (obj != null) { buf.append(obj); } } return buf.toString(); } /** * <p> * Joins the elements of the provided {@code Iterator} into a single String * containing the provided elements. * </p> * <p/> * <p> * No delimiter is added before or after the list. A {@code null} separator * is the same as an empty String (""). * </p> * <p/> * <p> * See the examples here: {@link #join(Object[], String)}. * </p> * * @param iterator the {@code Iterator} of values to join together, may be null * @param separator the separator character to use, null treated as "" * @return the joined String, {@code null} if null iterator input */ public static String join(Iterator<?> iterator, String separator) { // handle null, zero and one elements before building a buffer if (iterator == null) { return null; } if (!iterator.hasNext()) { return EMPTY; } Object first = iterator.next(); if (!iterator.hasNext()) { return first == null ? "" : first.toString(); } // two or more elements StringBuilder buf = new StringBuilder(CommonPlatformConstant.LENGTH_256); // probably too small if (first != null) { buf.append(first); } while (iterator.hasNext()) { if (separator != null) { buf.append(separator); } Object obj = iterator.next(); if (obj != null) { buf.append(obj); } } return buf.toString(); } /** * <p> * Joins the elements of the provided {@code Iterable} into a single String * containing the provided elements. * </p> * <p/> * <p> * No delimiter is added before or after the list. Null objects or empty * strings within the iteration are represented by empty strings. * </p> * <p/> * <p> * See the examples here: {@link #join(Object[], char)}. * </p> * * @param iterable the {@code Iterable} providing the values to join together, * may be null * @param separator the separator character to use * @return the joined String, {@code null} if null iterator input * @since 2.3 */ public static String join(Iterable<?> iterable, char separator) { if (iterable == null) { return null; } return join(iterable.iterator(), separator); } /** * <p> * Joins the elements of the provided {@code Iterable} into a single String * containing the provided elements. * </p> * <p/> * <p> * No delimiter is added before or after the list. A {@code null} separator * is the same as an empty String (""). * </p> * <p/> * <p> * See the examples here: {@link #join(Object[], String)}. * </p> * * @param iterable the {@code Iterable} providing the values to join together, * may be null * @param separator the separator character to use, null treated as "" * @return the joined String, {@code null} if null iterator input * @since 2.3 */ public static String join(Iterable<?> iterable, String separator) { if (iterable == null) { return null; } return join(iterable.iterator(), separator); } /** * <p> * Deletes all whitespaces from a String as defined by * {@link Character#isWhitespace(char)}. * </p> * <p/> * <pre> * StringUtils.deleteWhitespace(null) = null * StringUtils.deleteWhitespace("") = "" * StringUtils.deleteWhitespace("abc") = "abc" * StringUtils.deleteWhitespace(" ab c ") = "abc" * </pre> * * @param str the String to delete whitespace from, may be null * @return the String without whitespaces, {@code null} if null String input */ public static String deleteWhitespace(String str) { if (isEmpty(str)) { return str; } int sz = str.length(); char[] chs = new char[sz]; int count = 0; for (int i = 0; i < sz; i++) { if (!Character.isWhitespace(str.charAt(i))) { chs[count++] = str.charAt(i); } } if (count == sz) { return str; } return new String(chs, 0, count); } /** * <p> * Removes a substring only if it is at the beginning of a source string, * otherwise returns the source string. * </p> * <p/> * <p> * A {@code null} source string will return {@code null}. An empty ("") * source string will return the empty string. A {@code null} search string * will return the source string. * </p> * <p/> * <pre> * StringUtils.removeStart(null, *) = null * StringUtils.removeStart("", *) = "" * StringUtils.removeStart(*, null) = * * StringUtils.removeStart("www.domain.com", "www.") = "domain.com" * StringUtils.removeStart("domain.com", "www.") = "domain.com" * StringUtils.removeStart("www.domain.com", "domain") = "www.domain.com" * StringUtils.removeStart("abc", "") = "abc" * </pre> * * @param str the source String to search, may be null * @param remove the String to search for and remove, may be null * @return the substring with the string removed if found, {@code null} if * null String input * @since 2.1 */ public static String removeStart(String str, String remove) { if (isEmpty(str) || isEmpty(remove)) { return str; } if (str.startsWith(remove)) { return str.substring(remove.length()); } return str; } /** * <p> * Case insensitive removal of a substring if it is at the beginning of a * source string, otherwise returns the source string. * </p> * <p/> * <p> * A {@code null} source string will return {@code null}. An empty ("") * source string will return the empty string. A {@code null} search string * will return the source string. * </p> * <p/> * <pre> * StringUtils.removeStartIgnoreCase(null, *) = null * StringUtils.removeStartIgnoreCase("", *) = "" * StringUtils.removeStartIgnoreCase(*, null) = * * StringUtils.removeStartIgnoreCase("www.domain.com", "www.") = "domain.com" * StringUtils.removeStartIgnoreCase("www.domain.com", "WWW.") = "domain.com" * StringUtils.removeStartIgnoreCase("domain.com", "www.") = "domain.com" * StringUtils.removeStartIgnoreCase("www.domain.com", "domain") = "www.domain.com" * StringUtils.removeStartIgnoreCase("abc", "") = "abc" * </pre> * * @param str the source String to search, may be null * @param remove the String to search for (case insensitive) and remove, may be * null * @return the substring with the string removed if found, {@code null} if * null String input * @since 2.4 */ public static String removeStartIgnoreCase(String str, String remove) { if (isEmpty(str) || isEmpty(remove)) { return str; } if (startsWithIgnoreCase(str, remove)) { return str.substring(remove.length()); } return str; } /** * <p> * Removes a substring only if it is at the end of a source string, * otherwise returns the source string. * </p> * <p/> * <p> * A {@code null} source string will return {@code null}. An empty ("") * source string will return the empty string. A {@code null} search string * will return the source string. * </p> * <p/> * <pre> * StringUtils.removeEnd(null, *) = null * StringUtils.removeEnd("", *) = "" * StringUtils.removeEnd(*, null) = * * StringUtils.removeEnd("www.domain.com", ".com.") = "www.domain.com" * StringUtils.removeEnd("www.domain.com", ".com") = "www.domain" * StringUtils.removeEnd("www.domain.com", "domain") = "www.domain.com" * StringUtils.removeEnd("abc", "") = "abc" * </pre> * * @param str the source String to search, may be null * @param remove the String to search for and remove, may be null * @return the substring with the string removed if found, {@code null} if * null String input * @since 2.1 */ public static String removeEnd(String str, String remove) { if (isEmpty(str) || isEmpty(remove)) { return str; } if (str.endsWith(remove)) { return str.substring(0, str.length() - remove.length()); } return str; } /** * <p> * Case insensitive removal of a substring if it is at the end of a source * string, otherwise returns the source string. * </p> * <p/> * <p> * A {@code null} source string will return {@code null}. An empty ("") * source string will return the empty string. A {@code null} search string * will return the source string. * </p> * <p/> * <pre> * StringUtils.removeEndIgnoreCase(null, *) = null * StringUtils.removeEndIgnoreCase("", *) = "" * StringUtils.removeEndIgnoreCase(*, null) = * * StringUtils.removeEndIgnoreCase("www.domain.com", ".com.") = "www.domain.com" * StringUtils.removeEndIgnoreCase("www.domain.com", ".com") = "www.domain" * StringUtils.removeEndIgnoreCase("www.domain.com", "domain") = "www.domain.com" * StringUtils.removeEndIgnoreCase("abc", "") = "abc" * StringUtils.removeEndIgnoreCase("www.domain.com", ".COM") = "www.domain") * StringUtils.removeEndIgnoreCase("www.domain.COM", ".com") = "www.domain") * </pre> * * @param str the source String to search, may be null * @param remove the String to search for (case insensitive) and remove, may be * null * @return the substring with the string removed if found, {@code null} if * null String input * @since 2.4 */ public static String removeEndIgnoreCase(String str, String remove) { if (isEmpty(str) || isEmpty(remove)) { return str; } if (endsWithIgnoreCase(str, remove)) { return str.substring(0, str.length() - remove.length()); } return str; } /** * <p> * Removes all occurrences of a substring from within the source string. * </p> * <p/> * <p> * A {@code null} source string will return {@code null}. An empty ("") * source string will return the empty string. A {@code null} remove string * will return the source string. An empty ("") remove string will return * the source string. * </p> * <p/> * <pre> * StringUtils.remove(null, *) = null * StringUtils.remove("", *) = "" * StringUtils.remove(*, null) = * * StringUtils.remove(*, "") = * * StringUtils.remove("queued", "ue") = "qd" * StringUtils.remove("queued", "zz") = "queued" * </pre> * * @param str the source String to search, may be null * @param remove the String to search for and remove, may be null * @return the substring with the string removed if found, {@code null} if * null String input * @since 2.1 */ public static String remove(String str, String remove) { if (isEmpty(str) || isEmpty(remove)) { return str; } return replace(str, remove, EMPTY, -1); } /** * <p> * Removes all occurrences of a character from within the source string. * </p> * <p/> * <p> * A {@code null} source string will return {@code null}. An empty ("") * source string will return the empty string. * </p> * <p/> * <pre> * StringUtils.remove(null, *) = null * StringUtils.remove("", *) = "" * StringUtils.remove("queued", 'u') = "qeed" * StringUtils.remove("queued", 'z') = "queued" * </pre> * * @param str the source String to search, may be null * @param remove the char to search for and remove, may be null * @return the substring with the char removed if found, {@code null} if * null String input * @since 2.1 */ public static String remove(String str, char remove) { if (isEmpty(str) || str.indexOf(remove) == INDEX_NOT_FOUND) { return str; } char[] chars = str.toCharArray(); int pos = 0; for (int i = 0; i < chars.length; i++) { if (chars[i] != remove) { chars[pos++] = chars[i]; } } return new String(chars, 0, pos); } /** * <p> * Replaces a String with another String inside a larger String, once. * </p> * <p/> * <p> * A {@code null} reference passed to this method is a no-op. * </p> * <p/> * <pre> * StringUtils.replaceOnce(null, *, *) = null * StringUtils.replaceOnce("", *, *) = "" * StringUtils.replaceOnce("any", null, *) = "any" * StringUtils.replaceOnce("any", *, null) = "any" * StringUtils.replaceOnce("any", "", *) = "any" * StringUtils.replaceOnce("aba", "a", null) = "aba" * StringUtils.replaceOnce("aba", "a", "") = "ba" * StringUtils.replaceOnce("aba", "a", "z") = "zba" * </pre> * * @param text text to search and replace in, may be null * @param searchString the String to search for, may be null * @param replacement the String to replace with, may be null * @return the text with any replacements processed, {@code null} if null * String input * @see #replace(String text, String searchString, String replacement, int * max) */ public static String replaceOnce(String text, String searchString, String replacement) { return replace(text, searchString, replacement, 1); } /** * <p> * Replaces all occurrences of a String within another String. * </p> * <p/> * <p> * A {@code null} reference passed to this method is a no-op. * </p> * <p/> * <pre> * StringUtils.replace(null, *, *) = null * StringUtils.replace("", *, *) = "" * StringUtils.replace("any", null, *) = "any" * StringUtils.replace("any", *, null) = "any" * StringUtils.replace("any", "", *) = "any" * StringUtils.replace("aba", "a", null) = "aba" * StringUtils.replace("aba", "a", "") = "b" * StringUtils.replace("aba", "a", "z") = "zbz" * </pre> * * @param text text to search and replace in, may be null * @param searchString the String to search for, may be null * @param replacement the String to replace it with, may be null * @return the text with any replacements processed, {@code null} if null * String input * @see #replace(String text, String searchString, String replacement, int * max) */ public static String replace(String text, String searchString, String replacement) { return replace(text, searchString, replacement, -1); } /** * <p> * Replaces a String with another String inside a larger String, for the * first {@code max} values of the search String. * </p> * <p/> * <p> * A {@code null} reference passed to this method is a no-op. * </p> * <p/> * <pre> * StringUtils.replace(null, *, *, *) = null * StringUtils.replace("", *, *, *) = "" * StringUtils.replace("any", null, *, *) = "any" * StringUtils.replace("any", *, null, *) = "any" * StringUtils.replace("any", "", *, *) = "any" * StringUtils.replace("any", *, *, 0) = "any" * StringUtils.replace("abaa", "a", null, -1) = "abaa" * StringUtils.replace("abaa", "a", "", -1) = "b" * StringUtils.replace("abaa", "a", "z", 0) = "abaa" * StringUtils.replace("abaa", "a", "z", 1) = "zbaa" * StringUtils.replace("abaa", "a", "z", 2) = "zbza" * StringUtils.replace("abaa", "a", "z", -1) = "zbzz" * </pre> * * @param text text to search and replace in, may be null * @param searchString the String to search for, may be null * @param replacement the String to replace it with, may be null * @param maximum maximum number of values to replace, or {@code -1} if no * maximum * @return the text with any replacements processed, {@code null} if null * String input */ public static String replace(String text, String searchString, String replacement, int maximum) { int max = maximum; if (isEmpty(text) || isEmpty(searchString) || replacement == null || max == 0) { return text; } int start = 0; int end = text.indexOf(searchString, start); if (end == INDEX_NOT_FOUND) { return text; } int replLength = searchString.length(); int increase = replacement.length() - replLength; increase = increase < 0 ? 0 : increase; increase *= max < 0 ? CommonPlatformConstant.LENGTH_16 : max > CommonPlatformConstant.LENGTH_64 ? CommonPlatformConstant.LENGTH_64 : max; StringBuilder buf = new StringBuilder(text.length() + increase); while (end != INDEX_NOT_FOUND) { buf.append(text.substring(start, end)).append(replacement); start = end + replLength; if (--max == 0) { break; } end = text.indexOf(searchString, start); } buf.append(text.substring(start)); return buf.toString(); } /** * <p> * Replaces all occurrences of Strings within another String. * </p> * <p/> * <p> * A {@code null} reference passed to this method is a no-op, or if any * "search string" or "string to replace" is null, that replace will be * ignored. This will not repeat. For repeating replaces, call the * overloaded method. * </p> * <p/> * <pre> * StringUtils.replaceEach(null, *, *) = null * StringUtils.replaceEach("", *, *) = "" * StringUtils.replaceEach("aba", null, null) = "aba" * StringUtils.replaceEach("aba", new String[0], null) = "aba" * StringUtils.replaceEach("aba", null, new String[0]) = "aba" * StringUtils.replaceEach("aba", new String[]{"a"}, null) = "aba" * StringUtils.replaceEach("aba", new String[]{"a"}, new String[]{""}) = "b" * StringUtils.replaceEach("aba", new String[]{null}, new String[]{"a"}) = "aba" * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"w", "t"}) = "wcte" * (example of how it does not repeat) * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}) = "dcte" * </pre> * * @param text text to search and replace in, no-op if null * @param searchList the Strings to search for, no-op if null * @param replacementList the Strings to replace them with, no-op if null * @return the text with any replacements processed, {@code null} if null * String input * @throws IllegalArgumentException if the lengths of the arrays are not the same (null is ok, * and/or size 0) * @since 2.4 */ public static String replaceEach(String text, String[] searchList, String[] replacementList) { return replaceEach(text, searchList, replacementList, false, 0); } /** * <p> * Replaces all occurrences of Strings within another String. * </p> * <p/> * <p> * A {@code null} reference passed to this method is a no-op, or if any * "search string" or "string to replace" is null, that replace will be * ignored. * </p> * <p/> * <pre> * StringUtils.replaceEach(null, *, *, *) = null * StringUtils.replaceEach("", *, *, *) = "" * StringUtils.replaceEach("aba", null, null, *) = "aba" * StringUtils.replaceEach("aba", new String[0], null, *) = "aba" * StringUtils.replaceEach("aba", null, new String[0], *) = "aba" * StringUtils.replaceEach("aba", new String[]{"a"}, null, *) = "aba" * StringUtils.replaceEach("aba", new String[]{"a"}, new String[]{""}, *) = "b" * StringUtils.replaceEach("aba", new String[]{null}, new String[]{"a"}, *) = "aba" * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"w", "t"}, *) = "wcte" * (example of how it repeats) * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}, false) = "dcte" * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}, true) = "tcte" * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "ab"}, true) = IllegalStateException * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "ab"}, false) = "dcabe" * </pre> * * @param text text to search and replace in, no-op if null * @param searchList the Strings to search for, no-op if null * @param replacementList the Strings to replace them with, no-op if null * @return the text with any replacements processed, {@code null} if null * String input * @throws IllegalStateException if the search is repeating and there is an endless loop due * to outputs of one being inputs to another * @throws IllegalArgumentException if the lengths of the arrays are not the same (null is ok, * and/or size 0) * @since 2.4 */ public static String replaceEachRepeatedly(String text, String[] searchList, String[] replacementList) { // timeToLive should be 0 if not used or nothing to replace, else it's // the length of the replace array int timeToLive = searchList == null ? 0 : searchList.length; return replaceEach(text, searchList, replacementList, true, timeToLive); } /** * <p> * Replaces all occurrences of Strings within another String. * </p> * <p/> * <p> * A {@code null} reference passed to this method is a no-op, or if any * "search string" or "string to replace" is null, that replace will be * ignored. * </p> * <p/> * <pre> * StringUtils.replaceEach(null, *, *, *) = null * StringUtils.replaceEach("", *, *, *) = "" * StringUtils.replaceEach("aba", null, null, *) = "aba" * StringUtils.replaceEach("aba", new String[0], null, *) = "aba" * StringUtils.replaceEach("aba", null, new String[0], *) = "aba" * StringUtils.replaceEach("aba", new String[]{"a"}, null, *) = "aba" * StringUtils.replaceEach("aba", new String[]{"a"}, new String[]{""}, *) = "b" * StringUtils.replaceEach("aba", new String[]{null}, new String[]{"a"}, *) = "aba" * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"w", "t"}, *) = "wcte" * (example of how it repeats) * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}, false) = "dcte" * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}, true) = "tcte" * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "ab"}, *) = IllegalStateException * </pre> * * @param text text to search and replace in, no-op if null * @param searchList the Strings to search for, no-op if null * @param replacementList the Strings to replace them with, no-op if null * @param repeat if true, then replace repeatedly until there are no more * possible replacements or timeToLive < 0 * @param timeToLive if less than 0 then there is a circular reference and endless * loop * @return the text with any replacements processed, {@code null} if null * String input * @throws IllegalStateException if the search is repeating and there is an endless loop due * to outputs of one being inputs to another * @throws IllegalArgumentException if the lengths of the arrays are not the same (null is ok, * and/or size 0) * @since 2.4 */ private static String replaceEach(String text, String[] searchList, String[] replacementList, boolean repeat, int timeToLive) { // mchyzer Performance note: This creates very few new objects (one // major goal) // let me know if there are performance requests, we can create a // harness to measure if (text == null || text.length() == 0 || searchList == null || searchList.length == 0 || replacementList == null || replacementList.length == 0) { return text; } // if recursing, this shouldn't be less than 0 if (timeToLive < 0) { throw new IllegalStateException("Aborting to protect against StackOverflowError - " + "output of one loop is the input of another"); } int searchLength = searchList.length; int replacementLength = replacementList.length; // make sure lengths are ok, these need to be equal if (searchLength != replacementLength) { throw new IllegalArgumentException( "Search and Replace array lengths don't match: " + searchLength + " vs " + replacementLength); } // keep track of which still have matches boolean[] noMoreMatchesForReplIndex = new boolean[searchLength]; // index on index that the match was found int textIndex = -1; int replaceIndex = -1; int tempIndex = -1; // index of replace array that will replace the search string found // NOTE: logic duplicated below START for (int i = 0; i < searchLength; i++) { if (noMoreMatchesForReplIndex[i] || searchList[i] == null || searchList[i].length() == 0 || replacementList[i] == null) { continue; } tempIndex = text.indexOf(searchList[i]); // see if we need to keep searching for this if (tempIndex == -1) { noMoreMatchesForReplIndex[i] = true; } else { if (textIndex == -1 || tempIndex < textIndex) { textIndex = tempIndex; replaceIndex = i; } } } // NOTE: logic mostly below END // no search strings found, we are done if (textIndex == -1) { return text; } int start = 0; // get a good guess on the size of the result buffer so it doesn't have // to double if it goes over a bit int increase = 0; // count the replacement text elements that are larger than their // corresponding text being replaced for (int i = 0; i < searchList.length; i++) { if (searchList[i] == null || replacementList[i] == null) { continue; } int greater = replacementList[i].length() - searchList[i].length(); if (greater > 0) { increase += CommonPlatformConstant.LENGTH_3 * greater; } } // have upper-bound at 20% increase, then let Java take over increase = Math.min(increase, text.length() / CommonPlatformConstant.LENGTH_5); StringBuilder buf = new StringBuilder(text.length() + increase); while (textIndex != -1) { for (int i = start; i < textIndex; i++) { buf.append(text.charAt(i)); } buf.append(replacementList[replaceIndex]); start = textIndex + searchList[replaceIndex].length(); textIndex = -1; replaceIndex = -1; tempIndex = -1; // find the next earliest match // NOTE: logic mostly duplicated above START for (int i = 0; i < searchLength; i++) { if (noMoreMatchesForReplIndex[i] || searchList[i] == null || searchList[i].length() == 0 || replacementList[i] == null) { continue; } tempIndex = text.indexOf(searchList[i], start); // see if we need to keep searching for this if (tempIndex == -1) { noMoreMatchesForReplIndex[i] = true; } else { if (textIndex == -1 || tempIndex < textIndex) { textIndex = tempIndex; replaceIndex = i; } } } // NOTE: logic duplicated above END } int textLength = text.length(); for (int i = start; i < textLength; i++) { buf.append(text.charAt(i)); } String result = buf.toString(); if (!repeat) { return result; } return replaceEach(result, searchList, replacementList, repeat, timeToLive - 1); } /** * <p> * Replaces all occurrences of a character in a String with another. This is * a null-safe version of {@link String#replace(char, char)}. * </p> * <p/> * <p> * A {@code null} string input returns {@code null}. An empty ("") string * input returns an empty string. * </p> * <p/> * <pre> * StringUtils.replaceChars(null, *, *) = null * StringUtils.replaceChars("", *, *) = "" * StringUtils.replaceChars("abcba", 'b', 'y') = "aycya" * StringUtils.replaceChars("abcba", 'z', 'y') = "abcba" * </pre> * * @param str String to replace characters in, may be null * @param searchChar the character to search for, may be null * @param replaceChar the character to replace, may be null * @return modified String, {@code null} if null string input * @since 2.0 */ public static String replaceChars(String str, char searchChar, char replaceChar) { if (str == null) { return null; } return str.replace(searchChar, replaceChar); } /** * <p> * Replaces multiple characters in a String in one go. This method can also * be used to delete characters. * </p> * <p/> * <p> * For example:<br /> * <code>replaceChars("hello", "ho", "jy") = jelly</code> * . * </p> * <p/> * <p> * A {@code null} string input returns {@code null}. An empty ("") string * input returns an empty string. A null or empty set of search characters * returns the input string. * </p> * <p/> * <p> * The length of the search characters should normally equal the length of * the replace characters. If the search characters is longer, then the * extra search characters are deleted. If the search characters is shorter, * then the extra replace characters are ignored. * </p> * <p/> * <pre> * StringUtils.replaceChars(null, *, *) = null * StringUtils.replaceChars("", *, *) = "" * StringUtils.replaceChars("abc", null, *) = "abc" * StringUtils.replaceChars("abc", "", *) = "abc" * StringUtils.replaceChars("abc", "b", null) = "ac" * StringUtils.replaceChars("abc", "b", "") = "ac" * StringUtils.replaceChars("abcba", "bc", "yz") = "ayzya" * StringUtils.replaceChars("abcba", "bc", "y") = "ayya" * StringUtils.replaceChars("abcba", "bc", "yzx") = "ayzya" * </pre> * * @param str String to replace characters in, may be null * @param searchChars a set of characters to search for, may be null * @param replace a set of characters to replace, may be null * @return modified String, {@code null} if null string input * @since 2.0 */ public static String replaceChars(String str, String searchChars, String replace) { if (isEmpty(str) || isEmpty(searchChars)) { return str; } String replaceChars = replace; if (replaceChars == null) { replaceChars = EMPTY; } boolean modified = false; int replaceCharsLength = replaceChars.length(); int strLength = str.length(); StringBuilder buf = new StringBuilder(strLength); for (int i = 0; i < strLength; i++) { char ch = str.charAt(i); int index = searchChars.indexOf(ch); if (index >= 0) { modified = true; if (index < replaceCharsLength) { buf.append(replaceChars.charAt(index)); } } else { buf.append(ch); } } if (modified) { return buf.toString(); } return str; } // Overlay // ----------------------------------------------------------------------- /** * <p> * Overlays part of a String with another String. * </p> * <p/> * <p> * A {@code null} string input returns {@code null}. A negative index is * treated as zero. An index greater than the string length is treated as * the string length. The start index is always the smaller of the two * indices. * </p> * <p/> * <pre> * StringUtils.overlay(null, *, *, *) = null * StringUtils.overlay("", "abc", 0, 0) = "abc" * StringUtils.overlay("abcdef", null, 2, 4) = "abef" * StringUtils.overlay("abcdef", "", 2, 4) = "abef" * StringUtils.overlay("abcdef", "", 4, 2) = "abef" * StringUtils.overlay("abcdef", "zzzz", 2, 4) = "abzzzzef" * StringUtils.overlay("abcdef", "zzzz", 4, 2) = "abzzzzef" * StringUtils.overlay("abcdef", "zzzz", -1, 4) = "zzzzef" * StringUtils.overlay("abcdef", "zzzz", 2, 8) = "abzzzz" * StringUtils.overlay("abcdef", "zzzz", -2, -3) = "zzzzabcdef" * StringUtils.overlay("abcdef", "zzzz", 8, 10) = "abcdefzzzz" * </pre> * * @param str the String to do overlaying in, may be null * @param over the String to overlay, may be null * @param startPos the position to start overlaying at * @param endPos the position to stop overlaying before * @return overlayed String, {@code null} if null String input * @since 2.0 */ public static String overlay(String str, String over, int startPos, int endPos) { if (str == null) { return null; } String overlay = over; int start = startPos, end = endPos; if (overlay == null) { overlay = EMPTY; } int len = str.length(); if (start < 0) { start = 0; } if (start > len) { start = len; } if (end < 0) { end = 0; } if (end > len) { end = len; } if (start > end) { int temp = start; start = end; end = temp; } return new StringBuilder(len + start - end + overlay.length() + 1).append(str.substring(0, start)) .append(overlay).append(str.substring(end)).toString(); } /** * <p> * Removes one newline from end of a String if it's there, otherwise leave * it alone. A newline is "{@code \n}", "{@code \r}", or * "{@code \r\n}". * </p> * <p/> * <p> * NOTE: This method changed in 2.0. It now more closely matches Perl chomp. * </p> * <p/> * <pre> * StringUtils.chomp(null) = null * StringUtils.chomp("") = "" * StringUtils.chomp("abc \r") = "abc " * StringUtils.chomp("abc\n") = "abc" * StringUtils.chomp("abc\r\n") = "abc" * StringUtils.chomp("abc\r\n\r\n") = "abc\r\n" * StringUtils.chomp("abc\n\r") = "abc\n" * StringUtils.chomp("abc\n\rabc") = "abc\n\rabc" * StringUtils.chomp("\r") = "" * StringUtils.chomp("\n") = "" * StringUtils.chomp("\r\n") = "" * </pre> * * @param str the String to chomp a newline from, may be null * @return String without newline, {@code null} if null String input */ public static String chomp(String str) { if (isEmpty(str)) { return str; } if (str.length() == 1) { char ch = str.charAt(0); if (ch == CharUtils.CR || ch == CharUtils.LF) { return EMPTY; } return str; } int lastIdx = str.length() - 1; char last = str.charAt(lastIdx); if (last == CharUtils.LF) { if (str.charAt(lastIdx - 1) == CharUtils.CR) { lastIdx--; } } else if (last != CharUtils.CR) { lastIdx++; } return str.substring(0, lastIdx); } /** * <p> * Removes {@code separator} from the end of {@code str} if it's there, * otherwise leave it alone. * </p> * <p/> * <p> * NOTE: This method changed in version 2.0. It now more closely matches * Perl chomp. For the previous behavior, use * {@link #substringBeforeLast(String, String)}. This method uses * {@link String#endsWith(String)}. * </p> * <p/> * <pre> * StringUtils.chomp(null, *) = null * StringUtils.chomp("", *) = "" * StringUtils.chomp("foobar", "bar") = "foo" * StringUtils.chomp("foobar", "baz") = "foobar" * StringUtils.chomp("foo", "foo") = "" * StringUtils.chomp("foo ", "foo") = "foo " * StringUtils.chomp(" foo", "foo") = " " * StringUtils.chomp("foo", "foooo") = "foo" * StringUtils.chomp("foo", "") = "foo" * StringUtils.chomp("foo", null) = "foo" * </pre> * * @param str the String to chomp from, may be null * @param separator separator String, may be null * @return String without trailing separator, {@code null} if null String * input * {@link StringUtils#removeEnd(String, String)} instead */ public static String chomp(String str, String separator) { return removeEnd(str, separator); } /** * <p> * Remove the last character from a String. * </p> * <p/> * <p> * If the String ends in {@code \r\n}, then remove both of them. * </p> * <p/> * <pre> * StringUtils.chop(null) = null * StringUtils.chop("") = "" * StringUtils.chop("abc \r") = "abc " * StringUtils.chop("abc\n") = "abc" * StringUtils.chop("abc\r\n") = "abc" * StringUtils.chop("abc") = "ab" * StringUtils.chop("abc\nabc") = "abc\nab" * StringUtils.chop("a") = "" * StringUtils.chop("\r") = "" * StringUtils.chop("\n") = "" * StringUtils.chop("\r\n") = "" * </pre> * * @param str the String to chop last character from, may be null * @return String without last character, {@code null} if null String input */ public static String chop(String str) { if (str == null) { return null; } int strLen = str.length(); if (strLen < CommonPlatformConstant.LENGTH_2) { return EMPTY; } int lastIdx = strLen - 1; String ret = str.substring(0, lastIdx); char last = str.charAt(lastIdx); if (last == CharUtils.LF && ret.charAt(lastIdx - 1) == CharUtils.CR) { return ret.substring(0, lastIdx - 1); } return ret; } /** * <p> * Repeat a String {@code repeat} times to form a new String. * </p> * <p/> * <pre> * StringUtils.repeat(null, 2) = null * StringUtils.repeat("", 0) = "" * StringUtils.repeat("", 2) = "" * StringUtils.repeat("a", 3) = "aaa" * StringUtils.repeat("ab", 2) = "abab" * StringUtils.repeat("a", -2) = "" * </pre> * * @param str the String to repeat, may be null * @param repeat number of times to repeat str, negative treated as zero * @return a new String consisting of the original String repeated, * {@code null} if null String input */ public static String repeat(String str, int repeat) { // Performance tuned for 2.0 (JDK1.4) if (str == null) { return null; } if (repeat <= 0) { return EMPTY; } int inputLength = str.length(); if (repeat == 1 || inputLength == 0) { return str; } if (inputLength == 1 && repeat <= PAD_LIMIT) { return repeat(str.charAt(0), repeat); } int outputLength = inputLength * repeat; switch (inputLength) { case 1: return repeat(str.charAt(0), repeat); case CommonPlatformConstant.LENGTH_2: char ch0 = str.charAt(0); char ch1 = str.charAt(1); char[] output2 = new char[outputLength]; for (int i = repeat * CommonPlatformConstant.LENGTH_2 - CommonPlatformConstant.LENGTH_2; i >= 0; i--, i--) { output2[i] = ch0; output2[i + 1] = ch1; } return new String(output2); default: StringBuilder buf = new StringBuilder(outputLength); for (int i = 0; i < repeat; i++) { buf.append(str); } return buf.toString(); } } /** * <p> * Repeat a String {@code repeat} times to form a new String, with a String * separator injected each time. * </p> * <p/> * <pre> * StringUtils.repeat(null, null, 2) = null * StringUtils.repeat(null, "x", 2) = null * StringUtils.repeat("", null, 0) = "" * StringUtils.repeat("", "", 2) = "" * StringUtils.repeat("", "x", 3) = "xxx" * StringUtils.repeat("?", ", ", 3) = "?, ?, ?" * </pre> * * @param str the String to repeat, may be null * @param separator the String to inject, may be null * @param repeat number of times to repeat str, negative treated as zero * @return a new String consisting of the original String repeated, * {@code null} if null String input * @since 2.5 */ public static String repeat(String str, String separator, int repeat) { if (str == null || separator == null) { return repeat(str, repeat); } else { // given that repeat(String, int) is quite optimized, better to rely // on it than try and splice this into it String result = repeat(str + separator, repeat); return removeEnd(result, separator); } } /** * <p> * Returns padding using the specified delimiter repeated to a given length. * </p> * <p/> * <pre> * StringUtils.repeat(0, 'e') = "" * StringUtils.repeat(3, 'e') = "eee" * StringUtils.repeat(-2, 'e') = "" * </pre> * <p/> * <p> * Note: this method doesn't not support padding with <a * href="http://www.unicode.org/glossary/#supplementary_character">Unicode * Supplementary Characters</a> as they require a pair of {@code char}s to * be represented. If you are needing to support full I18N of your * applications consider using {@link #repeat(String, int)} instead. * </p> * * @param ch character to repeat * @param repeat number of times to repeat char, negative treated as zero * @return String with repeated character * @see #repeat(String, int) */ public static String repeat(char ch, int repeat) { char[] buf = new char[repeat]; for (int i = repeat - 1; i >= 0; i--) { buf[i] = ch; } return new String(buf); } /** * <p> * Right pad a String with spaces (' '). * </p> * <p/> * <p> * The String is padded to the size of {@code size}. * </p> * <p/> * <pre> * StringUtils.rightPad(null, *) = null * StringUtils.rightPad("", 3) = " " * StringUtils.rightPad("bat", 3) = "bat" * StringUtils.rightPad("bat", 5) = "bat " * StringUtils.rightPad("bat", 1) = "bat" * StringUtils.rightPad("bat", -1) = "bat" * </pre> * * @param str the String to pad out, may be null * @param size the size to pad to * @return right padded String or original String if no padding is * necessary, {@code null} if null String input */ public static String rightPad(String str, int size) { return rightPad(str, size, ' '); } /** * <p> * Right pad a String with a specified character. * </p> * <p/> * <p> * The String is padded to the size of {@code size}. * </p> * <p/> * <pre> * StringUtils.rightPad(null, *, *) = null * StringUtils.rightPad("", 3, 'z') = "zzz" * StringUtils.rightPad("bat", 3, 'z') = "bat" * StringUtils.rightPad("bat", 5, 'z') = "batzz" * StringUtils.rightPad("bat", 1, 'z') = "bat" * StringUtils.rightPad("bat", -1, 'z') = "bat" * </pre> * * @param str the String to pad out, may be null * @param size the size to pad to * @param padChar the character to pad with * @return right padded String or original String if no padding is * necessary, {@code null} if null String input * @since 2.0 */ public static String rightPad(String str, int size, char padChar) { if (str == null) { return null; } int pads = size - str.length(); if (pads <= 0) { return str; } if (pads > PAD_LIMIT) { return rightPad(str, size, String.valueOf(padChar)); } return str.concat(repeat(padChar, pads)); } /** * <p> * Right pad a String with a specified String. * </p> * <p/> * <p> * The String is padded to the size of {@code size}. * </p> * <p/> * <pre> * StringUtils.rightPad(null, *, *) = null * StringUtils.rightPad("", 3, "z") = "zzz" * StringUtils.rightPad("bat", 3, "yz") = "bat" * StringUtils.rightPad("bat", 5, "yz") = "batyz" * StringUtils.rightPad("bat", 8, "yz") = "batyzyzy" * StringUtils.rightPad("bat", 1, "yz") = "bat" * StringUtils.rightPad("bat", -1, "yz") = "bat" * StringUtils.rightPad("bat", 5, null) = "bat " * StringUtils.rightPad("bat", 5, "") = "bat " * </pre> * * @param str the String to pad out, may be null * @param size the size to pad to * @param pad the String to pad with, null or empty treated as single space * @return right padded String or original String if no padding is * necessary, {@code null} if null String input */ public static String rightPad(String str, int size, String pad) { if (str == null) { return null; } String padStr = pad; if (isEmpty(padStr)) { padStr = " "; } int padLen = padStr.length(); int strLen = str.length(); int pads = size - strLen; if (pads <= 0) { return str; } if (padLen == 1 && pads <= PAD_LIMIT) { return rightPad(str, size, padStr.charAt(0)); } if (pads == padLen) { return str.concat(padStr); } else if (pads < padLen) { return str.concat(padStr.substring(0, pads)); } else { char[] padding = new char[pads]; char[] padChars = padStr.toCharArray(); for (int i = 0; i < pads; i++) { padding[i] = padChars[i % padLen]; } return str.concat(new String(padding)); } } /** * <p> * Left pad a String with spaces (' '). * </p> * <p/> * <p> * The String is padded to the size of {@code size}. * </p> * <p/> * <pre> * StringUtils.leftPad(null, *) = null * StringUtils.leftPad("", 3) = " " * StringUtils.leftPad("bat", 3) = "bat" * StringUtils.leftPad("bat", 5) = " bat" * StringUtils.leftPad("bat", 1) = "bat" * StringUtils.leftPad("bat", -1) = "bat" * </pre> * * @param str the String to pad out, may be null * @param size the size to pad to * @return left padded String or original String if no padding is necessary, * {@code null} if null String input */ public static String leftPad(String str, int size) { return leftPad(str, size, ' '); } /** * <p> * Left pad a String with a specified character. * </p> * <p/> * <p> * Pad to a size of {@code size}. * </p> * <p/> * <pre> * StringUtils.leftPad(null, *, *) = null * StringUtils.leftPad("", 3, 'z') = "zzz" * StringUtils.leftPad("bat", 3, 'z') = "bat" * StringUtils.leftPad("bat", 5, 'z') = "zzbat" * StringUtils.leftPad("bat", 1, 'z') = "bat" * StringUtils.leftPad("bat", -1, 'z') = "bat" * </pre> * * @param str the String to pad out, may be null * @param size the size to pad to * @param padChar the character to pad with * @return left padded String or original String if no padding is necessary, * {@code null} if null String input * @since 2.0 */ public static String leftPad(String str, int size, char padChar) { if (str == null) { return null; } int pads = size - str.length(); if (pads <= 0) { return str; } if (pads > PAD_LIMIT) { return leftPad(str, size, String.valueOf(padChar)); } return repeat(padChar, pads).concat(str); } /** * <p> * Left pad a String with a specified String. * </p> * <p/> * <p> * Pad to a size of {@code size}. * </p> * <p/> * <pre> * StringUtils.leftPad(null, *, *) = null * StringUtils.leftPad("", 3, "z") = "zzz" * StringUtils.leftPad("bat", 3, "yz") = "bat" * StringUtils.leftPad("bat", 5, "yz") = "yzbat" * StringUtils.leftPad("bat", 8, "yz") = "yzyzybat" * StringUtils.leftPad("bat", 1, "yz") = "bat" * StringUtils.leftPad("bat", -1, "yz") = "bat" * StringUtils.leftPad("bat", 5, null) = " bat" * StringUtils.leftPad("bat", 5, "") = " bat" * </pre> * * @param str the String to pad out, may be null * @param size the size to pad to * @param pad the String to pad with, null or empty treated as single space * @return left padded String or original String if no padding is necessary, * {@code null} if null String input */ public static String leftPad(String str, int size, String pad) { if (str == null) { return null; } String padStr = pad; if (isEmpty(padStr)) { padStr = " "; } int padLen = padStr.length(); int strLen = str.length(); int pads = size - strLen; if (pads <= 0) { return str; } if (padLen == 1 && pads <= PAD_LIMIT) { return leftPad(str, size, padStr.charAt(0)); } if (pads == padLen) { return padStr.concat(str); } else if (pads < padLen) { return padStr.substring(0, pads).concat(str); } else { char[] padding = new char[pads]; char[] padChars = padStr.toCharArray(); for (int i = 0; i < pads; i++) { padding[i] = padChars[i % padLen]; } return new String(padding).concat(str); } } /** * Gets a CharSequence length or {@code 0} if the CharSequence is * {@code null}. * * @param cs a CharSequence or {@code null} * @return CharSequence length or {@code 0} if the CharSequence is * {@code null}. * @since 3.0 Changed signature from length(String) to length(CharSequence) */ public static int length(CharSequence cs) { return cs == null ? 0 : cs.length(); } /** * <p> * Centers a String in a larger String of size {@code size} using the space * character (' '). * <p> * <p/> * <p> * If the size is less than the String length, the String is returned. A * {@code null} String returns {@code null}. A negative size is treated as * zero. * </p> * <p/> * <p> * Equivalent to {@code center(str, size, " ")}. * </p> * <p/> * <pre> * StringUtils.center(null, *) = null * StringUtils.center("", 4) = " " * StringUtils.center("ab", -1) = "ab" * StringUtils.center("ab", 4) = " ab " * StringUtils.center("abcd", 2) = "abcd" * StringUtils.center("a", 4) = " a " * </pre> * * @param str the String to center, may be null * @param size the int size of new String, negative treated as zero * @return centered String, {@code null} if null String input */ public static String center(String str, int size) { return center(str, size, ' '); } /** * <p> * Centers a String in a larger String of size {@code size}. Uses a supplied * character as the value to pad the String with. * </p> * <p/> * <p> * If the size is less than the String length, the String is returned. A * {@code null} String returns {@code null}. A negative size is treated as * zero. * </p> * <p/> * <pre> * StringUtils.center(null, *, *) = null * StringUtils.center("", 4, ' ') = " " * StringUtils.center("ab", -1, ' ') = "ab" * StringUtils.center("ab", 4, ' ') = " ab" * StringUtils.center("abcd", 2, ' ') = "abcd" * StringUtils.center("a", 4, ' ') = " a " * StringUtils.center("a", 4, 'y') = "yayy" * </pre> * * @param string the String to center, may be null * @param size the int size of new String, negative treated as zero * @param padChar the character to pad the new String with * @return centered String, {@code null} if null String input * @since 2.0 */ public static String center(String string, int size, char padChar) { String str = string; if (str == null || size <= 0) { return str; } int strLen = str.length(); int pads = size - strLen; if (pads <= 0) { return str; } str = leftPad(str, strLen + pads / CommonPlatformConstant.LENGTH_2, padChar); str = rightPad(str, size, padChar); return str; } /** * <p> * Centers a String in a larger String of size {@code size}. Uses a supplied * String as the value to pad the String with. * </p> * <p/> * <p> * If the size is less than the String length, the String is returned. A * {@code null} String returns {@code null}. A negative size is treated as * zero. * </p> * <p/> * <pre> * StringUtils.center(null, *, *) = null * StringUtils.center("", 4, " ") = " " * StringUtils.center("ab", -1, " ") = "ab" * StringUtils.center("ab", 4, " ") = " ab" * StringUtils.center("abcd", 2, " ") = "abcd" * StringUtils.center("a", 4, " ") = " a " * StringUtils.center("a", 4, "yz") = "yayz" * StringUtils.center("abc", 7, null) = " abc " * StringUtils.center("abc", 7, "") = " abc " * </pre> * * @param string the String to center, may be null * @param size the int size of new String, negative treated as zero * @param pad the String to pad the new String with, must not be null or * empty * @return centered String, {@code null} if null String input * @throws IllegalArgumentException if padStr is {@code null} or empty */ public static String center(String string, int size, String pad) { String str = string; if (str == null || size <= 0) { return str; } String padStr = pad; if (isEmpty(padStr)) { padStr = " "; } int strLen = str.length(); int pads = size - strLen; if (pads <= 0) { return str; } str = leftPad(str, strLen + pads / CommonPlatformConstant.LENGTH_2, padStr); str = rightPad(str, size, padStr); return str; } /** * <p> * Converts a String to upper case as per {@link String#toUpperCase()}. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.upperCase(null) = null * StringUtils.upperCase("") = "" * StringUtils.upperCase("aBc") = "ABC" * </pre> * <p/> * <p> * <strong>Note:</strong> As described in the documentation for * {@link String#toUpperCase()}, the result of this method is affected by * the current locale. For platform-independent case transformations, the * method {@link #lowerCase(String, Locale)} should be used with a specific * locale (e.g. {@link Locale#ENGLISH}). * </p> * * @param str the String to upper case, may be null * @return the upper cased String, {@code null} if null String input */ public static String upperCase(String str) { if (str == null) { return null; } return str.toUpperCase(); } /** * <p> * Converts a String to upper case as per {@link String#toUpperCase(Locale)} * . * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.upperCase(null, Locale.ENGLISH) = null * StringUtils.upperCase("", Locale.ENGLISH) = "" * StringUtils.upperCase("aBc", Locale.ENGLISH) = "ABC" * </pre> * * @param str the String to upper case, may be null * @param locale the locale that defines the case transformation rules, must * not be null * @return the upper cased String, {@code null} if null String input * @since 2.5 */ public static String upperCase(String str, Locale locale) { if (str == null) { return null; } return str.toUpperCase(locale); } /** * <p> * Converts a String to lower case as per {@link String#toLowerCase()}. * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.lowerCase(null) = null * StringUtils.lowerCase("") = "" * StringUtils.lowerCase("aBc") = "abc" * </pre> * <p/> * <p> * <strong>Note:</strong> As described in the documentation for * {@link String#toLowerCase()}, the result of this method is affected by * the current locale. For platform-independent case transformations, the * method {@link #lowerCase(String, Locale)} should be used with a specific * locale (e.g. {@link Locale#ENGLISH}). * </p> * * @param str the String to lower case, may be null * @return the lower cased String, {@code null} if null String input */ public static String lowerCase(String str) { if (str == null) { return null; } return str.toLowerCase(); } /** * <p> * Converts a String to lower case as per {@link String#toLowerCase(Locale)} * . * </p> * <p/> * <p> * A {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.lowerCase(null, Locale.ENGLISH) = null * StringUtils.lowerCase("", Locale.ENGLISH) = "" * StringUtils.lowerCase("aBc", Locale.ENGLISH) = "abc" * </pre> * * @param str the String to lower case, may be null * @param locale the locale that defines the case transformation rules, must * not be null * @return the lower cased String, {@code null} if null String input * @since 2.5 */ public static String lowerCase(String str, Locale locale) { if (str == null) { return null; } return str.toLowerCase(locale); } /** * <p> * Capitalizes a String changing the first letter to title case as per * {@link Character#toTitleCase(char)}. No other letters are changed. * </p> * <p/> * <p> * For a word based algorithm, see * {@link org.apache.commons.lang3.text.WordUtils#capitalize(String)}. A * {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.capitalize(null) = null * StringUtils.capitalize("") = "" * StringUtils.capitalize("cat") = "Cat" * StringUtils.capitalize("cAt") = "CAt" * </pre> * * @param str the String to capitalize, may be null * @return the capitalized String, {@code null} if null String input * @see org.apache.commons.lang3.text.WordUtils#capitalize(String) * @see #uncapitalize(String) * @since 2.0 */ public static String capitalize(String str) { int strLen; if (str == null || (strLen = str.length()) == 0) { return str; } return new StringBuilder(strLen).append(Character.toTitleCase(str.charAt(0))).append(str.substring(1)) .toString(); } /** * <p> * Uncapitalizes a String changing the first letter to title case as per * {@link Character#toLowerCase(char)}. No other letters are changed. * </p> * <p/> * <p> * For a word based algorithm, see * {@link org.apache.commons.lang3.text.WordUtils#uncapitalize(String)}. A * {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.uncapitalize(null) = null * StringUtils.uncapitalize("") = "" * StringUtils.uncapitalize("Cat") = "cat" * StringUtils.uncapitalize("CAT") = "cAT" * </pre> * * @param str the String to uncapitalize, may be null * @return the uncapitalized String, {@code null} if null String input * @see org.apache.commons.lang3.text.WordUtils#uncapitalize(String) * @see #capitalize(String) * @since 2.0 */ public static String uncapitalize(String str) { int strLen; if (str == null || (strLen = str.length()) == 0) { return str; } return new StringBuilder(strLen).append(Character.toLowerCase(str.charAt(0))).append(str.substring(1)) .toString(); } /** * <p> * Swaps the case of a String changing upper and title case to lower case, * and lower case to upper case. * </p> * <p/> * <ul> * <li>Upper case character converts to Lower case</li> * <li>Title case character converts to Lower case</li> * <li>Lower case character converts to Upper case</li> * </ul> * <p/> * <p> * For a word based algorithm, see * {@link org.apache.commons.lang3.text.WordUtils#swapCase(String)}. A * {@code null} input String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.swapCase(null) = null * StringUtils.swapCase("") = "" * StringUtils.swapCase("The dog has a BONE") = "tHE DOG HAS A bone" * </pre> * <p/> * <p> * NOTE: This method changed in Lang version 2.0. It no longer performs a * word based algorithm. If you only use ASCII, you will notice no change. * That functionality is available in * org.apache.commons.lang3.text.WordUtils. * </p> * * @param str the String to swap case, may be null * @return the changed String, {@code null} if null String input */ public static String swapCase(String str) { if (StringUtils.isEmpty(str)) { return str; } char[] buffer = str.toCharArray(); for (int i = 0; i < buffer.length; i++) { char ch = buffer[i]; if (Character.isUpperCase(ch)) { buffer[i] = Character.toLowerCase(ch); } else if (Character.isTitleCase(ch)) { buffer[i] = Character.toLowerCase(ch); } else if (Character.isLowerCase(ch)) { buffer[i] = Character.toUpperCase(ch); } } return new String(buffer); } /** * <p> * Counts how many times the substring appears in the larger string. * </p> * <p/> * <p> * A {@code null} or empty ("") String input returns {@code 0}. * </p> * <p/> * <pre> * StringUtils.countMatches(null, *) = 0 * StringUtils.countMatches("", *) = 0 * StringUtils.countMatches("abba", null) = 0 * StringUtils.countMatches("abba", "") = 0 * StringUtils.countMatches("abba", "a") = 2 * StringUtils.countMatches("abba", "ab") = 1 * StringUtils.countMatches("abba", "xxx") = 0 * </pre> * * @param str the CharSequence to check, may be null * @param sub the substring to count, may be null * @return the number of occurrences, 0 if either CharSequence is * {@code null} * @since 3.0 Changed signature from countMatches(String, String) to * countMatches(CharSequence, CharSequence) */ public static int countMatches(CharSequence str, CharSequence sub) { if (isEmpty(str) || isEmpty(sub)) { return 0; } int count = 0; int idx = 0; while ((idx = CharSequenceUtils.indexOf(str, sub, idx)) != INDEX_NOT_FOUND) { count++; idx += sub.length(); } return count; } /** * <p> * Checks if the CharSequence contains only Unicode letters. * </p> * <p/> * <p> * {@code null} will return {@code false}. An empty CharSequence * (length()=0) will return {@code false}. * </p> * <p/> * <pre> * StringUtils.isAlpha(null) = false * StringUtils.isAlpha("") = false * StringUtils.isAlpha(" ") = false * StringUtils.isAlpha("abc") = true * StringUtils.isAlpha("ab2c") = false * StringUtils.isAlpha("ab-c") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if only contains letters, and is non-null * @since 3.0 Changed "" to return false and not true */ public static boolean isAlpha(CharSequence cs) { if (cs == null || cs.length() == 0) { return false; } int sz = cs.length(); for (int i = 0; i < sz; i++) { if (!Character.isLetter(cs.charAt(i))) { return false; } } return true; } /** * <p> * Checks if the CharSequence contains only Unicode letters and space (' '). * </p> * <p/> * <p> * {@code null} will return {@code false} An empty CharSequence (length()=0) * will return {@code true}. * </p> * <p/> * <pre> * StringUtils.isAlphaSpace(null) = false * StringUtils.isAlphaSpace("") = true * StringUtils.isAlphaSpace(" ") = true * StringUtils.isAlphaSpace("abc") = true * StringUtils.isAlphaSpace("ab c") = true * StringUtils.isAlphaSpace("ab2c") = false * StringUtils.isAlphaSpace("ab-c") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if only contains letters and space, and is non-null * @since 3.0 Changed signature from isAlphaSpace(String) to * isAlphaSpace(CharSequence) */ public static boolean isAlphaSpace(CharSequence cs) { if (cs == null) { return false; } int sz = cs.length(); for (int i = 0; i < sz; i++) { if (!Character.isLetter(cs.charAt(i)) && cs.charAt(i) != ' ') { return false; } } return true; } /** * <p> * Checks if the CharSequence contains only Unicode letters or digits. * </p> * <p/> * <p> * {@code null} will return {@code false}. An empty CharSequence * (length()=0) will return {@code false}. * </p> * <p/> * <pre> * StringUtils.isAlphanumeric(null) = false * StringUtils.isAlphanumeric("") = false * StringUtils.isAlphanumeric(" ") = false * StringUtils.isAlphanumeric("abc") = true * StringUtils.isAlphanumeric("ab c") = false * StringUtils.isAlphanumeric("ab2c") = true * StringUtils.isAlphanumeric("ab-c") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if only contains letters or digits, and is non-null * @since 3.0 Changed "" to return false and not true */ public static boolean isAlphanumeric(CharSequence cs) { if (cs == null || cs.length() == 0) { return false; } int sz = cs.length(); for (int i = 0; i < sz; i++) { if (!Character.isLetterOrDigit(cs.charAt(i))) { return false; } } return true; } /** * <p> * Checks if the CharSequence contains only Unicode letters, digits or space * ({@code ' '}). * </p> * <p/> * <p> * {@code null} will return {@code false}. An empty CharSequence * (length()=0) will return {@code true}. * </p> * <p/> * <pre> * StringUtils.isAlphanumericSpace(null) = false * StringUtils.isAlphanumericSpace("") = true * StringUtils.isAlphanumericSpace(" ") = true * StringUtils.isAlphanumericSpace("abc") = true * StringUtils.isAlphanumericSpace("ab c") = true * StringUtils.isAlphanumericSpace("ab2c") = true * StringUtils.isAlphanumericSpace("ab-c") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if only contains letters, digits or space, and is * non-null * @since 3.0 Changed signature from isAlphanumericSpace(String) to * isAlphanumericSpace(CharSequence) */ public static boolean isAlphanumericSpace(CharSequence cs) { if (cs == null) { return false; } int sz = cs.length(); for (int i = 0; i < sz; i++) { if (!Character.isLetterOrDigit(cs.charAt(i)) && cs.charAt(i) != ' ') { return false; } } return true; } /** * <p> * Checks if the CharSequence contains only ASCII printable characters. * </p> * <p/> * <p> * {@code null} will return {@code false}. An empty CharSequence * (length()=0) will return {@code true}. * </p> * <p/> * <pre> * StringUtils.isAsciiPrintable(null) = false * StringUtils.isAsciiPrintable("") = true * StringUtils.isAsciiPrintable(" ") = true * StringUtils.isAsciiPrintable("Ceki") = true * StringUtils.isAsciiPrintable("ab2c") = true * StringUtils.isAsciiPrintable("!ab-c~") = true * StringUtils.isAsciiPrintable("\u0020") = true * StringUtils.isAsciiPrintable("\u0021") = true * StringUtils.isAsciiPrintable("\u007e") = true * StringUtils.isAsciiPrintable("\u007f") = false * StringUtils.isAsciiPrintable("Ceki G\u00fclc\u00fc") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if every character is in the range 32 thru 126 * @since 3.0 Changed signature from isAsciiPrintable(String) to * isAsciiPrintable(CharSequence) */ public static boolean isAsciiPrintable(CharSequence cs) { if (cs == null) { return false; } int sz = cs.length(); for (int i = 0; i < sz; i++) { if (!CharUtils.isAsciiPrintable(cs.charAt(i))) { return false; } } return true; } /** * <p> * Checks if the CharSequence contains only Unicode digits. A decimal point * is not a Unicode digit and returns false. * </p> * <p/> * <p> * {@code null} will return {@code false}. An empty CharSequence * (length()=0) will return {@code false}. * </p> * <p/> * <pre> * StringUtils.isNumeric(null) = false * StringUtils.isNumeric("") = false * StringUtils.isNumeric(" ") = false * StringUtils.isNumeric("123") = true * StringUtils.isNumeric("12 3") = false * StringUtils.isNumeric("ab2c") = false * StringUtils.isNumeric("12-3") = false * StringUtils.isNumeric("12.3") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if only contains digits, and is non-null * @since 3.0 Changed "" to return false and not true */ public static boolean isNumeric(CharSequence cs) { if (cs == null || cs.length() == 0) { return false; } int sz = cs.length(); for (int i = 0; i < sz; i++) { if (!Character.isDigit(cs.charAt(i))) { return false; } } return true; } /** * <p> * Checks if the CharSequence contains only Unicode digits or space ( * {@code ' '}). A decimal point is not a Unicode digit and returns false. * </p> * <p/> * <p> * {@code null} will return {@code false}. An empty CharSequence * (length()=0) will return {@code true}. * </p> * <p/> * <pre> * StringUtils.isNumericSpace(null) = false * StringUtils.isNumericSpace("") = true * StringUtils.isNumericSpace(" ") = true * StringUtils.isNumericSpace("123") = true * StringUtils.isNumericSpace("12 3") = true * StringUtils.isNumericSpace("ab2c") = false * StringUtils.isNumericSpace("12-3") = false * StringUtils.isNumericSpace("12.3") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if only contains digits or space, and is non-null * @since 3.0 Changed signature from isNumericSpace(String) to * isNumericSpace(CharSequence) */ public static boolean isNumericSpace(CharSequence cs) { if (cs == null) { return false; } int sz = cs.length(); for (int i = 0; i < sz; i++) { if (!Character.isDigit(cs.charAt(i)) && cs.charAt(i) != ' ') { return false; } } return true; } /** * <p> * Checks if the CharSequence contains only whitespace. * </p> * <p/> * <p> * {@code null} will return {@code false}. An empty CharSequence * (length()=0) will return {@code true}. * </p> * <p/> * <pre> * StringUtils.isWhitespace(null) = false * StringUtils.isWhitespace("") = true * StringUtils.isWhitespace(" ") = true * StringUtils.isWhitespace("abc") = false * StringUtils.isWhitespace("ab2c") = false * StringUtils.isWhitespace("ab-c") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if only contains whitespace, and is non-null * @since 3.0 Changed signature from isWhitespace(String) to * isWhitespace(CharSequence) */ public static boolean isWhitespace(CharSequence cs) { if (cs == null) { return false; } int sz = cs.length(); for (int i = 0; i < sz; i++) { if (!Character.isWhitespace(cs.charAt(i))) { return false; } } return true; } /** * <p> * Checks if the CharSequence contains only lowercase characters. * </p> * <p/> * <p> * {@code null} will return {@code false}. An empty CharSequence * (length()=0) will return {@code false}. * </p> * <p/> * <pre> * StringUtils.isAllLowerCase(null) = false * StringUtils.isAllLowerCase("") = false * StringUtils.isAllLowerCase(" ") = false * StringUtils.isAllLowerCase("abc") = true * StringUtils.isAllLowerCase("abC") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if only contains lowercase characters, and is * non-null * @since 3.0 Changed signature from isAllLowerCase(String) to * isAllLowerCase(CharSequence) */ public static boolean isAllLowerCase(CharSequence cs) { if (cs == null || isEmpty(cs)) { return false; } int sz = cs.length(); for (int i = 0; i < sz; i++) { if (!Character.isLowerCase(cs.charAt(i))) { return false; } } return true; } /** * <p> * Checks if the CharSequence contains only uppercase characters. * </p> * <p/> * <p> * {@code null} will return {@code false}. An empty String (length()=0) will * return {@code false}. * </p> * <p/> * <pre> * StringUtils.isAllUpperCase(null) = false * StringUtils.isAllUpperCase("") = false * StringUtils.isAllUpperCase(" ") = false * StringUtils.isAllUpperCase("ABC") = true * StringUtils.isAllUpperCase("aBC") = false * </pre> * * @param cs the CharSequence to check, may be null * @return {@code true} if only contains uppercase characters, and is * non-null * @since 3.0 Changed signature from isAllUpperCase(String) to * isAllUpperCase(CharSequence) */ public static boolean isAllUpperCase(CharSequence cs) { if (cs == null || isEmpty(cs)) { return false; } int sz = cs.length(); for (int i = 0; i < sz; i++) { if (!Character.isUpperCase(cs.charAt(i))) { return false; } } return true; } /** * <p> * Returns either the passed in String, or if the String is {@code null}, an * empty String (""). * </p> * <p/> * <pre> * StringUtils.defaultString(null) = "" * StringUtils.defaultString("") = "" * StringUtils.defaultString("bat") = "bat" * </pre> * * @param str the String to check, may be null * @return the passed in String, or the empty String if it was {@code null} * @see String#valueOf(Object) */ public static String defaultString(String str) { return str == null ? EMPTY : str; } /** * <p> * Returns either the passed in String, or if the String is {@code null}, * the value of {@code defaultStr}. * </p> * <p/> * <pre> * StringUtils.defaultString(null, "NULL") = "NULL" * StringUtils.defaultString("", "NULL") = "" * StringUtils.defaultString("bat", "NULL") = "bat" * </pre> * * @param str the String to check, may be null * @param defaultStr the default String to return if the input is {@code null}, may * be null * @return the passed in String, or the default if it was {@code null} * @see String#valueOf(Object) */ public static String defaultString(String str, String defaultStr) { return str == null ? defaultStr : str; } /** * <p> * Returns either the passed in CharSequence, or if the CharSequence is * whitespace, empty ("") or {@code null}, the value of {@code defaultStr}. * </p> * <p/> * <pre> * StringUtils.defaultIfBlank(null, "NULL") = "NULL" * StringUtils.defaultIfBlank("", "NULL") = "NULL" * StringUtils.defaultIfBlank(" ", "NULL") = "NULL" * StringUtils.defaultIfBlank("bat", "NULL") = "bat" * StringUtils.defaultIfBlank("", null) = null * </pre> * * @param <T> the specific kind of CharSequence * @param str the CharSequence to check, may be null * @param defaultStr the default CharSequence to return if the input is whitespace, * empty ("") or {@code null}, may be null * @return the passed in CharSequence, or the default * @see StringUtils#defaultString(String, String) */ public static <T extends CharSequence> T defaultIfBlank(T str, T defaultStr) { return StringUtils.isBlank(str) ? defaultStr : str; } /** * <p> * Returns either the passed in CharSequence, or if the CharSequence is * empty or {@code null}, the value of {@code defaultStr}. * </p> * <p/> * <pre> * StringUtils.defaultIfEmpty(null, "NULL") = "NULL" * StringUtils.defaultIfEmpty("", "NULL") = "NULL" * StringUtils.defaultIfEmpty(" ", "NULL") = " " * StringUtils.defaultIfEmpty("bat", "NULL") = "bat" * StringUtils.defaultIfEmpty("", null) = null * </pre> * * @param <T> the specific kind of CharSequence * @param str the CharSequence to check, may be null * @param defaultStr the default CharSequence to return if the input is empty ("") * or {@code null}, may be null * @return the passed in CharSequence, or the default * @see StringUtils#defaultString(String, String) */ public static <T extends CharSequence> T defaultIfEmpty(T str, T defaultStr) { return StringUtils.isEmpty(str) ? defaultStr : str; } /** * <p> * Reverses a String as per {@link StringBuilder#reverse()}. * </p> * <p/> * <p> * A {@code null} String returns {@code null}. * </p> * <p/> * <pre> * StringUtils.reverse(null) = null * StringUtils.reverse("") = "" * StringUtils.reverse("bat") = "tab" * </pre> * * @param str the String to reverse, may be null * @return the reversed String, {@code null} if null String input */ public static String reverse(String str) { if (str == null) { return null; } return new StringBuilder(str).reverse().toString(); } /** * <p> * Reverses a String that is delimited by a specific character. * </p> * <p/> * <p> * The Strings between the delimiters are not reversed. Thus * java.lang.String becomes String.lang.java (if the delimiter is * {@code '.'}). * </p> * <p/> * <pre> * StringUtils.reverseDelimited(null, *) = null * StringUtils.reverseDelimited("", *) = "" * StringUtils.reverseDelimited("a.b.c", 'x') = "a.b.c" * StringUtils.reverseDelimited("a.b.c", ".") = "c.b.a" * </pre> * * @param str the String to reverse, may be null * @param separatorChar the separator character to use * @return the reversed String, {@code null} if null String input * @since 2.0 */ public static String reverseDelimited(String str, char separatorChar) { if (str == null) { return null; } // could implement manually, but simple way is to reuse other, // probably slower, methods. String[] strs = split(str, separatorChar); int i = 0; int j = strs.length - 1; String tmp; while (j > i) { tmp = strs[j]; strs[j] = strs[i]; strs[i] = tmp; j--; i++; } return join(strs, separatorChar); } /** * <p> * Abbreviates a String using ellipses. This will turn * "Now is the time for all good men" into "Now is the time for..." * </p> * <p/> * <p> * Specifically: * <ul> * <li>If {@code str} is less than {@code maxWidth} characters long, return * it.</li> * <li>Else abbreviate it to {@code (substring(str, 0, max-3) + "...")}.</li> * <li>If {@code maxWidth} is less than {@code 4}, throw an * {@code IllegalArgumentException}.</li> * <li>In no case will it return a String of length greater than * {@code maxWidth}.</li> * </ul> * </p> * <p/> * <pre> * StringUtils.abbreviate(null, *) = null * StringUtils.abbreviate("", 4) = "" * StringUtils.abbreviate("abcdefg", 6) = "abc..." * StringUtils.abbreviate("abcdefg", 7) = "abcdefg" * StringUtils.abbreviate("abcdefg", 8) = "abcdefg" * StringUtils.abbreviate("abcdefg", 4) = "a..." * StringUtils.abbreviate("abcdefg", 3) = IllegalArgumentException * </pre> * * @param str the String to check, may be null * @param maxWidth maximum length of result String, must be at least 4 * @return abbreviated String, {@code null} if null String input * @throws IllegalArgumentException if the width is too small * @since 2.0 */ public static String abbreviate(String str, int maxWidth) { return abbreviate(str, 0, maxWidth); } /** * <p> * Abbreviates a String using ellipses. This will turn * "Now is the time for all good men" into "...is the time for..." * </p> * <p/> * <p> * Works like {@code abbreviate(String, int)}, but allows you to specify a * "left edge" offset. Note that this left edge is not necessarily going to * be the leftmost character in the result, or the first character following * the ellipses, but it will appear somewhere in the result. * <p/> * <p> * In no case will it return a String of length greater than * {@code maxWidth}. * </p> * <p/> * <pre> * StringUtils.abbreviate(null, *, *) = null * StringUtils.abbreviate("", 0, 4) = "" * StringUtils.abbreviate("abcdefghijklmno", -1, 10) = "abcdefg..." * StringUtils.abbreviate("abcdefghijklmno", 0, 10) = "abcdefg..." * StringUtils.abbreviate("abcdefghijklmno", 1, 10) = "abcdefg..." * StringUtils.abbreviate("abcdefghijklmno", 4, 10) = "abcdefg..." * StringUtils.abbreviate("abcdefghijklmno", 5, 10) = "...fghi..." * StringUtils.abbreviate("abcdefghijklmno", 6, 10) = "...ghij..." * StringUtils.abbreviate("abcdefghijklmno", 8, 10) = "...ijklmno" * StringUtils.abbreviate("abcdefghijklmno", 10, 10) = "...ijklmno" * StringUtils.abbreviate("abcdefghijklmno", 12, 10) = "...ijklmno" * StringUtils.abbreviate("abcdefghij", 0, 3) = IllegalArgumentException * StringUtils.abbreviate("abcdefghij", 5, 6) = IllegalArgumentException * </pre> * * @param str the String to check, may be null * @param start left edge of source String * @param maxWidth maximum length of result String, must be at least 4 * @return abbreviated String, {@code null} if null String input * @throws IllegalArgumentException if the width is too small * @since 2.0 */ public static String abbreviate(String str, int start, int maxWidth) { if (str == null) { return null; } if (maxWidth < CommonPlatformConstant.LENGTH_4) { throw new IllegalArgumentException("Minimum abbreviation width is 4"); } if (str.length() <= maxWidth) { return str; } int offset = start; if (offset > str.length()) { offset = str.length(); } if (str.length() - offset < maxWidth - CommonPlatformConstant.LENGTH_3) { offset = str.length() - (maxWidth - CommonPlatformConstant.LENGTH_3); } final String abrevMarker = "..."; if (offset <= CommonPlatformConstant.LENGTH_4) { return str.substring(0, maxWidth - CommonPlatformConstant.LENGTH_3) + abrevMarker; } if (maxWidth < CommonPlatformConstant.LENGTH_7) { throw new IllegalArgumentException("Minimum abbreviation width with offset is 7"); } if (offset + maxWidth - CommonPlatformConstant.LENGTH_3 < str.length()) { return abrevMarker + abbreviate(str.substring(offset), maxWidth - CommonPlatformConstant.LENGTH_3); } return abrevMarker + str.substring(str.length() - (maxWidth - CommonPlatformConstant.LENGTH_3)); } /** * <p> * Abbreviates a String to the length passed, replacing the middle * characters with the supplied replacement String. * </p> * <p/> * <p> * This abbreviation only occurs if the following criteria is met: * <ul> * <li>Neither the String for abbreviation nor the replacement String are * null or empty</li> * <li>The length to truncate to is less than the length of the supplied * String</li> * <li>The length to truncate to is greater than 0</li> * <li>The abbreviated String will have enough room for the length supplied * replacement String and the first and last characters of the supplied * String for abbreviation</li> * </ul> * Otherwise, the returned String will be the same as the supplied String * for abbreviation. * </p> * <p/> * <pre> * StringUtils.abbreviateMiddle(null, null, 0) = null * StringUtils.abbreviateMiddle("abc", null, 0) = "abc" * StringUtils.abbreviateMiddle("abc", ".", 0) = "abc" * StringUtils.abbreviateMiddle("abc", ".", 3) = "abc" * StringUtils.abbreviateMiddle("abcdef", ".", 4) = "ab.f" * </pre> * * @param str the String to abbreviate, may be null * @param middle the String to replace the middle characters with, may be null * @param length the length to abbreviate {@code str} to. * @return the abbreviated String if the above criteria is met, or the * original String supplied for abbreviation. * @since 2.5 */ public static String abbreviateMiddle(String str, String middle, int length) { if (isEmpty(str) || isEmpty(middle)) { return str; } if (length >= str.length() || length < middle.length() + CommonPlatformConstant.LENGTH_2) { return str; } int targetSting = length - middle.length(); int startOffset = targetSting / CommonPlatformConstant.LENGTH_2 + targetSting % CommonPlatformConstant.LENGTH_2; int endOffset = str.length() - targetSting / CommonPlatformConstant.LENGTH_2; StringBuilder builder = new StringBuilder(length); builder.append(str.substring(0, startOffset)); builder.append(middle); builder.append(str.substring(endOffset)); return builder.toString(); } /** * <p> * Compares two Strings, and returns the portion where they differ. (More * precisely, return the remainder of the second String, starting from where * it's different from the first.) * </p> * <p/> * <p> * For example, * {@code difference("i am a machine", "i am a robot") -> "robot"}. * </p> * <p/> * <pre> * StringUtils.difference(null, null) = null * StringUtils.difference("", "") = "" * StringUtils.difference("", "abc") = "abc" * StringUtils.difference("abc", "") = "" * StringUtils.difference("abc", "abc") = "" * StringUtils.difference("ab", "abxyz") = "xyz" * StringUtils.difference("abcde", "abxyz") = "xyz" * StringUtils.difference("abcde", "xyz") = "xyz" * </pre> * * @param str1 the first String, may be null * @param str2 the second String, may be null * @return the portion of str2 where it differs from str1; returns the empty * String if they are equal * @since 2.0 */ public static String difference(String str1, String str2) { if (str1 == null) { return str2; } if (str2 == null) { return str1; } int at = indexOfDifference(str1, str2); if (at == INDEX_NOT_FOUND) { return EMPTY; } return str2.substring(at); } /** * <p> * Compares two CharSequences, and returns the index at which the * CharSequences begin to differ. * </p> * <p/> * <p> * For example, * {@code indexOfDifference("i am a machine", "i am a robot") -> 7} * </p> * <p/> * <pre> * StringUtils.indexOfDifference(null, null) = -1 * StringUtils.indexOfDifference("", "") = -1 * StringUtils.indexOfDifference("", "abc") = 0 * StringUtils.indexOfDifference("abc", "") = 0 * StringUtils.indexOfDifference("abc", "abc") = -1 * StringUtils.indexOfDifference("ab", "abxyz") = 2 * StringUtils.indexOfDifference("abcde", "abxyz") = 2 * StringUtils.indexOfDifference("abcde", "xyz") = 0 * </pre> * * @param cs1 the first CharSequence, may be null * @param cs2 the second CharSequence, may be null * @return the index where cs1 and cs2 begin to differ; -1 if they are equal * @since 3.0 Changed signature from indexOfDifference(String, String) to * indexOfDifference(CharSequence, CharSequence) */ public static int indexOfDifference(CharSequence cs1, CharSequence cs2) { if (cs1 == cs2) { return INDEX_NOT_FOUND; } if (cs1 == null || cs2 == null) { return 0; } int i; for (i = 0; i < cs1.length() && i < cs2.length(); ++i) { if (cs1.charAt(i) != cs2.charAt(i)) { break; } } if (i < cs2.length() || i < cs1.length()) { return i; } return INDEX_NOT_FOUND; } /** * <p> * Compares all CharSequences in an array and returns the index at which the * CharSequences begin to differ. * </p> * <p/> * <p> * For example, * <code>indexOfDifference(new String[] {"i am a machine", "i am a robot"}) -> 7</code> * </p> * <p/> * <pre> * StringUtils.indexOfDifference(null) = -1 * StringUtils.indexOfDifference(new String[] {}) = -1 * StringUtils.indexOfDifference(new String[] {"abc"}) = -1 * StringUtils.indexOfDifference(new String[] {null, null}) = -1 * StringUtils.indexOfDifference(new String[] {"", ""}) = -1 * StringUtils.indexOfDifference(new String[] {"", null}) = 0 * StringUtils.indexOfDifference(new String[] {"abc", null, null}) = 0 * StringUtils.indexOfDifference(new String[] {null, null, "abc"}) = 0 * StringUtils.indexOfDifference(new String[] {"", "abc"}) = 0 * StringUtils.indexOfDifference(new String[] {"abc", ""}) = 0 * StringUtils.indexOfDifference(new String[] {"abc", "abc"}) = -1 * StringUtils.indexOfDifference(new String[] {"abc", "a"}) = 1 * StringUtils.indexOfDifference(new String[] {"ab", "abxyz"}) = 2 * StringUtils.indexOfDifference(new String[] {"abcde", "abxyz"}) = 2 * StringUtils.indexOfDifference(new String[] {"abcde", "xyz"}) = 0 * StringUtils.indexOfDifference(new String[] {"xyz", "abcde"}) = 0 * StringUtils.indexOfDifference(new String[] {"i am a machine", "i am a robot"}) = 7 * </pre> * * @param css array of CharSequences, entries may be null * @return the index where the strings begin to differ; -1 if they are all * equal * @since 3.0 Changed signature from indexOfDifference(String...) to * indexOfDifference(CharSequence...) */ public static int indexOfDifference(CharSequence... css) { if (css == null || css.length <= 1) { return INDEX_NOT_FOUND; } boolean anyStringNull = false; boolean allStringsNull = true; int arrayLen = css.length; int shortestStrLen = Integer.MAX_VALUE; int longestStrLen = 0; // find the min and max string lengths; this avoids checking to make // sure we are not exceeding the length of the string each time through // the bottom loop. for (int i = 0; i < arrayLen; i++) { if (css[i] == null) { anyStringNull = true; shortestStrLen = 0; } else { allStringsNull = false; shortestStrLen = Math.min(css[i].length(), shortestStrLen); longestStrLen = Math.max(css[i].length(), longestStrLen); } } // handle lists containing all nulls or all empty strings if (allStringsNull || longestStrLen == 0 && !anyStringNull) { return INDEX_NOT_FOUND; } // handle lists containing some nulls or some empty strings if (shortestStrLen == 0) { return 0; } // find the position with the first difference across all strings int firstDiff = -1; for (int stringPos = 0; stringPos < shortestStrLen; stringPos++) { char comparisonChar = css[0].charAt(stringPos); for (int arrayPos = 1; arrayPos < arrayLen; arrayPos++) { if (css[arrayPos].charAt(stringPos) != comparisonChar) { firstDiff = stringPos; break; } } if (firstDiff != -1) { break; } } if (firstDiff == -1 && shortestStrLen != longestStrLen) { // we compared all of the characters up to the length of the // shortest string and didn't find a match, but the string lengths // vary, so return the length of the shortest string. return shortestStrLen; } return firstDiff; } /** * <p> * Compares all Strings in an array and returns the initial sequence of * characters that is common to all of them. * </p> * <p/> * <p> * For example, * <code>getCommonPrefix(new String[] {"i am a machine", "i am a robot"}) -> "i am a "</code> * </p> * <p/> * <pre> * StringUtils.getCommonPrefix(null) = "" * StringUtils.getCommonPrefix(new String[] {}) = "" * StringUtils.getCommonPrefix(new String[] {"abc"}) = "abc" * StringUtils.getCommonPrefix(new String[] {null, null}) = "" * StringUtils.getCommonPrefix(new String[] {"", ""}) = "" * StringUtils.getCommonPrefix(new String[] {"", null}) = "" * StringUtils.getCommonPrefix(new String[] {"abc", null, null}) = "" * StringUtils.getCommonPrefix(new String[] {null, null, "abc"}) = "" * StringUtils.getCommonPrefix(new String[] {"", "abc"}) = "" * StringUtils.getCommonPrefix(new String[] {"abc", ""}) = "" * StringUtils.getCommonPrefix(new String[] {"abc", "abc"}) = "abc" * StringUtils.getCommonPrefix(new String[] {"abc", "a"}) = "a" * StringUtils.getCommonPrefix(new String[] {"ab", "abxyz"}) = "ab" * StringUtils.getCommonPrefix(new String[] {"abcde", "abxyz"}) = "ab" * StringUtils.getCommonPrefix(new String[] {"abcde", "xyz"}) = "" * StringUtils.getCommonPrefix(new String[] {"xyz", "abcde"}) = "" * StringUtils.getCommonPrefix(new String[] {"i am a machine", "i am a robot"}) = "i am a " * </pre> * * @param strs array of String objects, entries may be null * @return the initial sequence of characters that are common to all Strings * in the array; empty String if the array is null, the elements are * all null or if there is no common prefix. * @since 2.4 */ public static String getCommonPrefix(String... strs) { if (strs == null || strs.length == 0) { return EMPTY; } int smallestIndexOfDiff = indexOfDifference(strs); if (smallestIndexOfDiff == INDEX_NOT_FOUND) { // all strings were identical if (strs[0] == null) { return EMPTY; } return strs[0]; } else if (smallestIndexOfDiff == 0) { // there were no common initial characters return EMPTY; } else { // we found a common initial character sequence return strs[0].substring(0, smallestIndexOfDiff); } } /** * <p> * Find the Levenshtein distance between two Strings. * </p> * <p/> * <p> * This is the number of changes needed to change one String into another, * where each change is a single character modification (deletion, insertion * or substitution). * </p> * <p/> * <p> * The previous implementation of the Levenshtein distance algorithm was * from <a * href="http://www.merriampark.com/ld.htm">http://www.merriampark.com * /ld.htm</a> * </p> * <p/> * <p> * Chas Emerick has written an implementation in Java, which avoids an * OutOfMemoryError which can occur when my Java implementation is used with * very large strings.<br> * This implementation of the Levenshtein distance algorithm is from <a * href="http://www.merriampark.com/ldjava.htm">http://www.merriampark.com/ * ldjava.htm</a> * </p> * <p/> * <pre> * StringUtils.getLevenshteinDistance(null, *) = IllegalArgumentException * StringUtils.getLevenshteinDistance(*, null) = IllegalArgumentException * StringUtils.getLevenshteinDistance("","") = 0 * StringUtils.getLevenshteinDistance("","a") = 1 * StringUtils.getLevenshteinDistance("aaapppp", "") = 7 * StringUtils.getLevenshteinDistance("frog", "fog") = 1 * StringUtils.getLevenshteinDistance("fly", "ant") = 3 * StringUtils.getLevenshteinDistance("elephant", "hippo") = 7 * StringUtils.getLevenshteinDistance("hippo", "elephant") = 7 * StringUtils.getLevenshteinDistance("hippo", "zzzzzzzz") = 8 * StringUtils.getLevenshteinDistance("hello", "hallo") = 1 * </pre> * * @param ss the first String, must not be null * @param tt the second String, must not be null * @return result distance * @throws IllegalArgumentException if either String input {@code null} * @since 3.0 Changed signature from getLevenshteinDistance(String, String) * to getLevenshteinDistance(CharSequence, CharSequence) */ public static int getLevenshteinDistance(CharSequence ss, CharSequence tt) { CharSequence s = ss, t = tt; if (s == null || t == null) { throw new IllegalArgumentException("Strings must not be null"); } /** * The difference between this impl. and the previous is that, rather * than creating and retaining a matrix of size s.length() + 1 by * t.length() + 1, we maintain two single-dimensional arrays of length * s.length() + 1. The first, d, is the 'current working' distance array * that maintains the newest distance cost counts as we iterate through * the characters of String s. Each time we increment the index of * String t we are comparing, d is copied to p, the second int[]. Doing * so allows us to retain the previous cost counts as required by the * algorithm (taking the minimum of the cost count to the left, up one, * and diagonally up and to the left of the current cost count being * calculated). (Note that the arrays aren't really copied anymore, just * switched...this is clearly much better than cloning an array or doing * a System.arraycopy() each time through the outer loop.) * * Effectively, the difference between the two implementations is this * one does not cause an out of memory condition when calculating the LD * over two very large strings. */ int n = s.length(); int m = t.length(); if (n == 0) { return m; } else if (m == 0) { return n; } if (n > m) { // swap the input strings to consume less memory CharSequence tmp = s; s = t; t = tmp; n = m; m = t.length(); } int[] p = new int[n + 1]; int[] d = new int[n + 1]; int[] pd; // indexes into strings s and t int i; int j; char tj; int cost; for (i = 0; i <= n; i++) { p[i] = i; } for (j = 1; j <= m; j++) { tj = t.charAt(j - 1); d[0] = j; for (i = 1; i <= n; i++) { cost = s.charAt(i - 1) == tj ? 0 : 1; // minimum of cell to the left+1, to the top+1, diagonally left // and up +cost d[i] = Math.min(Math.min(d[i - 1] + 1, p[i] + 1), p[i - 1] + cost); } // copy current distance counts to 'previous row' distance counts pd = p; p = d; d = pd; } // our last action in the above loop was to switch d and p, so p now // actually has the most recent cost counts return p[n]; } /** * <p> * Find the Levenshtein distance between two Strings if it's less than or * equal to a given threshold. * </p> * <p/> * <p> * This is the number of changes needed to change one String into another, * where each change is a single character modification (deletion, insertion * or substitution). * </p> * <p/> * <p> * This implementation follows from Algorithms on Strings, Trees and * Sequences by Dan Gusfield and Chas Emerick's implementation of the * Levenshtein distance algorithm from <a * href="http://www.merriampark.com/ld.htm" * >http://www.merriampark.com/ld.htm</a> * </p> * <p/> * <pre> * StringUtils.getLevenshteinDistance(null, *, *) = IllegalArgumentException * StringUtils.getLevenshteinDistance(*, null, *) = IllegalArgumentException * StringUtils.getLevenshteinDistance(*, *, -1) = IllegalArgumentException * StringUtils.getLevenshteinDistance("","", 0) = 0 * StringUtils.getLevenshteinDistance("aaapppp", "", 8) = 7 * StringUtils.getLevenshteinDistance("aaapppp", "", 7) = 7 * StringUtils.getLevenshteinDistance("aaapppp", "", 6)) = -1 * StringUtils.getLevenshteinDistance("elephant", "hippo", 7) = 7 * StringUtils.getLevenshteinDistance("elephant", "hippo", 6) = -1 * StringUtils.getLevenshteinDistance("hippo", "elephant", 7) = 7 * StringUtils.getLevenshteinDistance("hippo", "elephant", 6) = -1 * </pre> * * @param ss the first String, must not be null * @param tt the second String, must not be null * @param threshold the target threshold, must not be negative * @return result distance, or {@code -1} if the distance would be greater * than the threshold * @throws IllegalArgumentException if either String input {@code null} or negative threshold */ public static int getLevenshteinDistance(CharSequence ss, CharSequence tt, int threshold) { CharSequence s = ss, t = tt; if (s == null || t == null) { throw new IllegalArgumentException("Strings must not be null"); } if (threshold < 0) { throw new IllegalArgumentException("Threshold must not be negative"); } /** * This implementation only computes the distance if it's less than or * equal to the threshold value, returning -1 if it's greater. The * advantage is performance: unbounded distance is O(nm), but a bound of * k allows us to reduce it to O(km) time by only computing a diagonal * stripe of width 2k + 1 of the cost table. It is also possible to use * this to compute the unbounded Levenshtein distance by starting the * threshold at 1 and doubling each time until the distance is found; * this is O(dm), where d is the distance. * * One subtlety comes from needing to ignore entries on the border of * our stripe eg. p[] = |#|#|#|* d[] = *|#|#|#| We must ignore the entry * to the left of the leftmost member We must ignore the entry above the * rightmost member * * Another subtlety comes from our stripe running off the matrix if the * strings aren't of the same size. Since string s is always swapped to * be the shorter of the two, the stripe will always run off to the * upper right instead of the lower left of the matrix. * * As a concrete example, suppose s is of length 5, t is of length 7, * and our threshold is 1. In this case we're going to walk a stripe of * length 3. The matrix would look like so: * * 1 2 3 4 5 1 |#|#| | | | 2 |#|#|#| | | 3 | |#|#|#| | 4 | | |#|#|#| 5 | * | | |#|#| 6 | | | | |#| 7 | | | | | | * * Note how the stripe leads off the table as there is no possible way * to turn a string of length 5 into one of length 7 in edit distance of * 1. * * Additionally, this implementation decreases memory usage by using two * single-dimensional arrays and swapping them back and forth instead of * allocating an entire n by m matrix. This requires a few minor * changes, such as immediately returning when it's detected that the * stripe has run off the matrix and initially filling the arrays with * large values so that entries we don't compute are ignored. * * See Algorithms on Strings, Trees and Sequences by Dan Gusfield for * some discussion. */ int n = s.length(); int m = t.length(); // if one string is empty, the edit distance is necessarily the length // of the other if (n == 0) { return m <= threshold ? m : -1; } else if (m == 0) { return n <= threshold ? n : -1; } if (n > m) { // swap the two strings to consume less memory CharSequence tmp = s; s = t; t = tmp; n = m; m = t.length(); } int[] p = new int[n + 1]; int[] d = new int[n + 1]; int[] pd; // fill in starting table values int boundary = Math.min(n, threshold) + 1; for (int i = 0; i < boundary; i++) { p[i] = i; } // these fills ensure that the value above the rightmost entry of our // stripe will be ignored in following loop iterations Arrays.fill(p, boundary, p.length, Integer.MAX_VALUE); Arrays.fill(d, Integer.MAX_VALUE); // iterates through t for (int j = 1; j <= m; j++) { char tj = t.charAt(j - 1); d[0] = j; // compute stripe indices, constrain to array size int min = Math.max(1, j - threshold); int max = Math.min(n, j + threshold); // the stripe may lead off of the table if s and t are of different // sizes if (min > max) { return -1; } // ignore entry left of leftmost if (min > 1) { d[min - 1] = Integer.MAX_VALUE; } // iterates through [min, max] in s for (int i = min; i <= max; i++) { if (s.charAt(i - 1) == tj) { // diagonally left and up d[i] = p[i - 1]; } else { // 1 + minimum of cell to the left, to the top, diagonally // left and up d[i] = 1 + Math.min(Math.min(d[i - 1], p[i]), p[i - 1]); } } // copy current distance counts to 'previous row' distance counts pd = p; p = d; d = pd; } // if p[n] is greater than the threshold, there's no guarantee on it // being the correct // distance if (p[n] <= threshold) { return p[n]; } else { return -1; } } /** * <p> * Check if a CharSequence starts with a specified prefix. * </p> * <p/> * <p> * {@code null}s are handled without exceptions. Two {@code null} references * are considered to be equal. The comparison is case sensitive. * </p> * <p/> * <pre> * StringUtils.startsWith(null, null) = true * StringUtils.startsWith(null, "abc") = false * StringUtils.startsWith("abcdef", null) = false * StringUtils.startsWith("abcdef", "abc") = true * StringUtils.startsWith("ABCDEF", "abc") = false * </pre> * * @param str the CharSequence to check, may be null * @param prefix the prefix to find, may be null * @return {@code true} if the CharSequence starts with the prefix, case * sensitive, or both {@code null} * @see java.lang.String#startsWith(String) * @since 3.0 Changed signature from startsWith(String, String) to * startsWith(CharSequence, CharSequence) */ public static boolean startsWith(CharSequence str, CharSequence prefix) { return startsWith(str, prefix, false); } /** * <p> * Case insensitive check if a CharSequence starts with a specified prefix. * </p> * <p/> * <p> * {@code null}s are handled without exceptions. Two {@code null} references * are considered to be equal. The comparison is case insensitive. * </p> * <p/> * <pre> * StringUtils.startsWithIgnoreCase(null, null) = true * StringUtils.startsWithIgnoreCase(null, "abc") = false * StringUtils.startsWithIgnoreCase("abcdef", null) = false * StringUtils.startsWithIgnoreCase("abcdef", "abc") = true * StringUtils.startsWithIgnoreCase("ABCDEF", "abc") = true * </pre> * * @param str the CharSequence to check, may be null * @param prefix the prefix to find, may be null * @return {@code true} if the CharSequence starts with the prefix, case * insensitive, or both {@code null} * @see java.lang.String#startsWith(String) * @since 3.0 Changed signature from startsWithIgnoreCase(String, String) to * startsWithIgnoreCase(CharSequence, CharSequence) */ public static boolean startsWithIgnoreCase(CharSequence str, CharSequence prefix) { return startsWith(str, prefix, true); } /** * <p> * Check if a CharSequence starts with a specified prefix (optionally case * insensitive). * </p> * * @param str the CharSequence to check, may be null * @param prefix the prefix to find, may be null * @param ignoreCase indicates whether the compare should ignore case (case * insensitive) or not. * @return {@code true} if the CharSequence starts with the prefix or both * {@code null} * @see java.lang.String#startsWith(String) */ private static boolean startsWith(CharSequence str, CharSequence prefix, boolean ignoreCase) { if (str == null || prefix == null) { return str == null && prefix == null; } if (prefix.length() > str.length()) { return false; } return CharSequenceUtils.regionMatches(str, ignoreCase, 0, prefix, 0, prefix.length()); } /** * <p> * Check if a CharSequence starts with any of an array of specified strings. * </p> * <p/> * <pre> * StringUtils.startsWithAny(null, null) = false * StringUtils.startsWithAny(null, new String[] {"abc"}) = false * StringUtils.startsWithAny("abcxyz", null) = false * StringUtils.startsWithAny("abcxyz", new String[] {""}) = false * StringUtils.startsWithAny("abcxyz", new String[] {"abc"}) = true * StringUtils.startsWithAny("abcxyz", new String[] {null, "xyz", "abc"}) = true * </pre> * * @param string the CharSequence to check, may be null * @param searchStrings the CharSequences to find, may be null or empty * @return {@code true} if the CharSequence starts with any of the the * prefixes, case insensitive, or both {@code null} * @since 3.0 Changed signature from startsWithAny(String, String[]) to * startsWithAny(CharSequence, CharSequence...) */ public static boolean startsWithAny(CharSequence string, CharSequence... searchStrings) { if (isEmpty(string) || searchStrings == null) { return false; } for (CharSequence searchString : searchStrings) { if (StringUtils.startsWith(string, searchString)) { return true; } } return false; } /** * <p> * Check if a CharSequence ends with a specified suffix. * </p> * <p/> * <p> * {@code null}s are handled without exceptions. Two {@code null} references * are considered to be equal. The comparison is case sensitive. * </p> * <p/> * <pre> * StringUtils.endsWith(null, null) = true * StringUtils.endsWith(null, "def") = false * StringUtils.endsWith("abcdef", null) = false * StringUtils.endsWith("abcdef", "def") = true * StringUtils.endsWith("ABCDEF", "def") = false * StringUtils.endsWith("ABCDEF", "cde") = false * </pre> * * @param str the CharSequence to check, may be null * @param suffix the suffix to find, may be null * @return {@code true} if the CharSequence ends with the suffix, case * sensitive, or both {@code null} * @see java.lang.String#endsWith(String) * @since 3.0 Changed signature from endsWith(String, String) to * endsWith(CharSequence, CharSequence) */ public static boolean endsWith(CharSequence str, CharSequence suffix) { return endsWith(str, suffix, false); } /** * <p> * Case insensitive check if a CharSequence ends with a specified suffix. * </p> * <p/> * <p> * {@code null}s are handled without exceptions. Two {@code null} references * are considered to be equal. The comparison is case insensitive. * </p> * <p/> * <pre> * StringUtils.endsWithIgnoreCase(null, null) = true * StringUtils.endsWithIgnoreCase(null, "def") = false * StringUtils.endsWithIgnoreCase("abcdef", null) = false * StringUtils.endsWithIgnoreCase("abcdef", "def") = true * StringUtils.endsWithIgnoreCase("ABCDEF", "def") = true * StringUtils.endsWithIgnoreCase("ABCDEF", "cde") = false * </pre> * * @param str the CharSequence to check, may be null * @param suffix the suffix to find, may be null * @return {@code true} if the CharSequence ends with the suffix, case * insensitive, or both {@code null} * @see java.lang.String#endsWith(String) * @since 3.0 Changed signature from endsWithIgnoreCase(String, String) to * endsWithIgnoreCase(CharSequence, CharSequence) */ public static boolean endsWithIgnoreCase(CharSequence str, CharSequence suffix) { return endsWith(str, suffix, true); } /** * <p> * Check if a CharSequence ends with a specified suffix (optionally case * insensitive). * </p> * * @param str the CharSequence to check, may be null * @param suffix the suffix to find, may be null * @param ignoreCase indicates whether the compare should ignore case (case * insensitive) or not. * @return {@code true} if the CharSequence starts with the prefix or both * {@code null} * @see java.lang.String#endsWith(String) */ private static boolean endsWith(CharSequence str, CharSequence suffix, boolean ignoreCase) { if (str == null || suffix == null) { return str == null && suffix == null; } if (suffix.length() > str.length()) { return false; } int strOffset = str.length() - suffix.length(); return CharSequenceUtils.regionMatches(str, ignoreCase, strOffset, suffix, 0, suffix.length()); } /** * <p> * Similar to <a * href="http://www.w3.org/TR/xpath/#function-normalize-space"> * http://www.w3.org/TR/xpath/#function-normalize -space</a> * </p> * <p> * The function returns the argument string with whitespace normalized by * using <code>{@link #trim(String)}</code> to remove leading and trailing * whitespace and then replacing sequences of whitespace characters by a * single space. * </p> * In XML Whitespace characters are the same as those allowed by the <a * href="http://www.w3.org/TR/REC-xml/#NT-S">S</a> production, which is S * ::= (#x20 | #x9 | #xD | #xA)+ * <p> * Java's regexp pattern \s defines whitespace as [ \t\n\x0B\f\r] * <p> * For reference: * <ul> * <li>\x0B = vertical tab</li> * <li>\f = #xC = form feed</li> * <li>#x20 = space</li> * <li>#x9 = \t</li> * <li>#xA = \n</li> * <li>#xD = \r</li> * </ul> * </p> * <p> * The difference is that Java's whitespace includes vertical tab and form * feed, which this functional will also normalize. Additionally * <code>{@link #trim(String)}</code> removes control characters (char <= * 32) from both ends of this String. * </p> * * @param str the source String to normalize whitespaces from, may be null * @return the modified string with whitespace normalized, {@code null} if * null String input * @see Pattern * @see #trim(String) * @see <a * href="http://www.w3.org/TR/xpath/#function-normalize-space">http://www.w3.org/TR/xpath/#function-normalize-space</a> * @since 3.0 */ public static String normalizeSpace(String str) { if (str == null) { return null; } return WHITESPACE_BLOCK.matcher(trim(str)).replaceAll(" "); } /** * <p> * Check if a CharSequence ends with any of an array of specified strings. * </p> * <p/> * <pre> * StringUtils.endsWithAny(null, null) = false * StringUtils.endsWithAny(null, new String[] {"abc"}) = false * StringUtils.endsWithAny("abcxyz", null) = false * StringUtils.endsWithAny("abcxyz", new String[] {""}) = true * StringUtils.endsWithAny("abcxyz", new String[] {"xyz"}) = true * StringUtils.endsWithAny("abcxyz", new String[] {null, "xyz", "abc"}) = true * </pre> * * @param string the CharSequence to check, may be null * @param searchStrings the CharSequences to find, may be null or empty * @return {@code true} if the CharSequence ends with any of the the * prefixes, case insensitive, or both {@code null} * @since 3.0 */ public static boolean endsWithAny(CharSequence string, CharSequence... searchStrings) { if (isEmpty(string) || searchStrings == null) { return false; } for (CharSequence searchString : searchStrings) { if (StringUtils.endsWith(string, searchString)) { return true; } } return false; } /** * Converts a <code>byte[]</code> to a String using the specified character * encoding. * * @param bytes the byte array to read from * @param charsetName the encoding to use, if null then use the platform default * @return a new String * @throws UnsupportedEncodingException If the named charset is not supported * @throws NullPointerException if the input is null * @since 3.1 */ public static String toString(byte[] bytes, String charsetName) throws UnsupportedEncodingException { return charsetName == null ? new String(bytes) : new String(bytes, charsetName); } }