package org.succlz123.utils; import java.io.UnsupportedEncodingException; import java.util.ArrayList; import java.util.Iterator; import java.util.List; import java.util.Locale; /** * <p>Operations on {@link String} that are * {@code null} safe.</p> * * <ul> * <li><b>IsEmpty/IsBlank</b> * - checks if a String contains text</li> * <li><b>Trim/Strip</b> * - removes leading and trailing whitespace</li> * <li><b>Equals</b> * - compares two strings null-safe</li> * <li><b>startsWith</b> * - check if a String starts with a prefix null-safe</li> * <li><b>endsWith</b> * - check if a String ends with a suffix null-safe</li> * <li><b>IndexOf/LastIndexOf/Contains</b> * - null-safe index-of checks * <li><b>IndexOfAny/LastIndexOfAny/IndexOfAnyBut/LastIndexOfAnyBut</b> * - index-of any of a set of Strings</li> * <li><b>ContainsOnly/ContainsNone/ContainsAny</b> * - does String contains only/none/any of these characters</li> * <li><b>Substring/Left/Right/Mid</b> * - null-safe substring extractions</li> * <li><b>SubstringBefore/SubstringAfter/SubstringBetween</b> * - substring extraction relative to other strings</li> * <li><b>Split/Join</b> * - splits a String into an array of substrings and vice versa</li> * <li><b>Remove/Delete</b> * - removes part of a String</li> * <li><b>Replace</b> * - Searches a String and replaces one String with another</li> * <li><b>Chomp/Chop</b> * - removes the last part of a String</li> * <li><b>LeftPad/RightPad/Center/Repeat</b> * - pads a String</li> * <li><b>UpperCase/LowerCase/SwapCase/Capitalize/Uncapitalize</b> * - changes the case of a String</li> * <li><b>CountMatches</b> * - counts the number of occurrences of one String in another</li> * <li><b>IsAlpha/IsNumeric/IsWhitespace/IsAsciiPrintable</b> * - checks the characters in a String</li> * <li><b>DefaultString</b> * - protects against a null input String</li> * <li><b>Reverse/ReverseDelimited</b> * - reverses a String</li> * <li><b>Abbreviate</b> * - abbreviates a string using ellipsis</li> * <li><b>Difference</b> * - compares Strings and reports on their differences</li> * <li><b>LevenshteinDistance</b> * - the number of changes needed to change one String into another</li> * </ul> * * <p>The {@code StringUtils} class defines certain words related to * String handling.</p> * * <ul> * <li>null - {@code null}</li> * <li>empty - a zero-length string ({@code ""})</li> * <li>space - the space character ({@code ' '}, char 32)</li> * <li>whitespace - the characters defined by {@link Character#isWhitespace(char)}</li> * <li>trim - the characters <= 32 as in {@link String#trim()}</li> * </ul> * * <p>{@code StringUtils} handles {@code null} input Strings quietly. * That is to say that a {@code null} input will return {@code null}. * Where a {@code boolean} or {@code int} is being returned * details vary by method.</p> * * <p>A side effect of the {@code null} handling is that a * {@code NullPointerException} should be considered a bug in * {@code StringUtils}.</p> * * <p>Methods in this class give sample code to explain their operation. * The symbol {@code *} is used to indicate any input including {@code null}.</p> * * <p>#ThreadSafe#</p> * @see String * @since 1.0 * @version $Id: StringUtils.java 1199894 2011-11-09 17:53:59Z ggregory $ */ public class StringUtils { /** * The empty String {@code ""}. */ public static final String EMPTY = ""; /** * Represents a failed index search. */ 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; /** * <p>{@code StringUtils} instances should NOT be constructed in * standard programming. Instead, the class should be used as * {@code StringUtils.trim(" foo ");}.</p> * * <p>This constructor is public to permit tools that require a JavaBean * instance to operate.</p> */ public StringUtils() { super(); } // Empty checks //----------------------------------------------------------------------- /** * <p>Checks if a CharSequence is empty ("") or null.</p> * * <pre> * StringUtils.isEmpty(null) = true * StringUtils.isEmpty("") = true * StringUtils.isEmpty(" ") = false * StringUtils.isEmpty("bob") = false * StringUtils.isEmpty(" bob ") = false * </pre> * * <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 */ public static boolean isEmpty(CharSequence cs) { return cs == null || cs.length() == 0; } /** * <p>Checks if a CharSequence is whitespace, empty ("") or null.</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 */ 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)) == false) { return false; } } return true; } // Trim //----------------------------------------------------------------------- /** * <p>Removes control characters (char <= 32) from both * ends of this String, handling {@code null} by returning * {@code null}.</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>To trim your choice of characters, use the * {@link #strip(String, String)} methods.</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>The String is trimmed using {@link String#trim()}. * Trim removes start and end characters <= 32. * To strip whitespace use {@link #stripToNull(String)}.</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 */ 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>The String is trimmed using {@link String#trim()}. * Trim removes start and end characters <= 32. * To strip whitespace use {@link #stripToEmpty(String)}.</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 */ public static String trimToEmpty(String str) { return str == null ? EMPTY : str.trim(); } // Stripping //----------------------------------------------------------------------- /** * <p>Strips whitespace from the start and end of a String.</p> * * <p>This is similar to {@link #trim(String)} but removes whitespace. * Whitespace is defined by {@link Character#isWhitespace(char)}.</p> * * <p>A {@code null} input String returns {@code null}.</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>This is similar to {@link #trimToNull(String)} but removes whitespace. * Whitespace is defined by {@link Character#isWhitespace(char)}.</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 */ public static String stripToNull(String str) { if (str == null) { return null; } str = strip(str, null); return str.length() == 0 ? null : str; } /** * <p>Strips whitespace from the start and end of a String returning * an empty String if {@code null} input.</p> * * <p>This is similar to {@link #trimToEmpty(String)} but removes whitespace. * Whitespace is defined by {@link Character#isWhitespace(char)}.</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 */ 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>A {@code null} input String returns {@code null}. * An empty string ("") input returns the empty string.</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> * * <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; } str = stripStart(str, stripChars); return stripEnd(str, stripChars); } /** * <p>Strips any of a set of characters from the start of a String.</p> * * <p>A {@code null} input String returns {@code null}. * An empty string ("") input returns the empty string.</p> * * <p>If the stripChars String is {@code null}, whitespace is * stripped as defined by {@link Character#isWhitespace(char)}.</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>A {@code null} input String returns {@code null}. * An empty string ("") input returns the empty string.</p> * * <p>If the stripChars String is {@code null}, whitespace is * stripped as defined by {@link Character#isWhitespace(char)}.</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); } // StripAll //----------------------------------------------------------------------- /** * <p>Strips whitespace from the start and end of every String in an array. * Whitespace is defined by {@link Character#isWhitespace(char)}.</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> * * <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>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> * * <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; } // Equals //----------------------------------------------------------------------- /** * <p>Compares two CharSequences, returning {@code true} if they are equal.</p> * * <p>{@code null}s are handled without exceptions. Two {@code null} * references are considered to be equal. The comparison is case sensitive.</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> * * @see String#equals(Object) * @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} */ 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>{@code null}s are handled without exceptions. Two {@code null} * references are considered equal. Comparison is case insensitive.</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} */ public static boolean equalsIgnoreCase(CharSequence str1, CharSequence str2) { if (str1 == null || str2 == null) { return str1 == str2; } else if (str1.length() != str2.length()) { return false; } return CharSequenceUtils.regionMatches(str1, true, 0, str2, 0, Math.max(str1.length(), str2.length())); } // IndexOf //----------------------------------------------------------------------- /** * <p>Finds the first index within a CharSequence, handling {@code null}. * This method uses {@link String#indexOf(int, int)} if possible.</p> * * <p>A {@code null} or empty ("") CharSequence will return {@code INDEX_NOT_FOUND (-1)}.</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 */ 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>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> * * <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 */ 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>A {@code null} CharSequence will return {@code -1}.</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 */ 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>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> * * <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 */ 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>Case in-sensitive find of the first index within a CharSequence.</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> * * <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 */ 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>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> * * <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 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 */ public static int indexOfIgnoreCase(CharSequence str, CharSequence searchStr, int startPos) { if (str == null || searchStr == null) { return INDEX_NOT_FOUND; } 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; } // LastIndexOf //----------------------------------------------------------------------- /** * <p>Finds the last index within a CharSequence, handling {@code null}. * This method uses {@link String#lastIndexOf(int)} if possible.</p> * * <p>A {@code null} or empty ("") CharSequence will return {@code -1}.</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 */ 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>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> * * <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 */ 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>A {@code null} CharSequence will return {@code -1}.</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 */ 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 first index within a CharSequence, handling {@code null}. * This method uses {@link String#lastIndexOf(String, int)} if possible.</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> * * <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 */ 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>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> * * <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 */ 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>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> * * <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 startPos the start position * @return the first index of the search CharSequence, * -1 if no match or {@code null} input */ public static int lastIndexOfIgnoreCase(CharSequence str, CharSequence searchStr, int startPos) { if (str == null || searchStr == null) { return INDEX_NOT_FOUND; } 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; } // Contains //----------------------------------------------------------------------- /** * <p>Checks if CharSequence contains a search character, handling {@code null}. * This method uses {@link String#indexOf(int)} if possible.</p> * * <p>A {@code null} or empty ("") CharSequence will return {@code false}.</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 */ 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>A {@code null} CharSequence will return {@code false}.</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 */ 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>A {@code null} CharSequence will return {@code false}.</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 */ 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; } // Substring //----------------------------------------------------------------------- /** * <p>Gets a substring from the specified String avoiding exceptions.</p> * * <p>A negative start position can be used to start {@code n} * characters from the end of the String.</p> * * <p>A {@code null} String will return {@code null}. * An empty ("") String will return "".</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 start 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 start) { if (str == null) { return null; } // handle negatives, which means last n characters if (start < 0) { start = str.length() + start; // remember start is negative } 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>A negative start position can be used to start/end {@code n} * characters from the end of the String.</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>If {@code start} is not strictly to the left of {@code end}, "" * is returned.</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 start the position to start from, negative means * count back from the end of the String by this many characters * @param end 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 start, int end) { if (str == null) { return null; } // handle negatives if (end < 0) { end = str.length() + end; // remember end is negative } if (start < 0) { start = str.length() + start; // remember start is negative } // 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); } // Left/Right/Mid //----------------------------------------------------------------------- /** * <p>Gets the leftmost {@code len} characters of a String.</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> * * <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>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> * * <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>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> * * <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 pos 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 pos, int len) { if (str == null) { return null; } 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); } // SubStringAfter/SubStringBefore //----------------------------------------------------------------------- /** * <p>Gets the substring before the first occurrence of a separator. * The separator is not returned.</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>If nothing is found, the string input is returned.</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 */ 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>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>If nothing is found, the empty string is returned.</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 */ 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>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>If nothing is found, the string input is returned.</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 */ 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>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>If nothing is found, the empty string is returned.</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 */ 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()); } // Substring between //----------------------------------------------------------------------- /** * <p>Gets the String that is nested in between two instances of the * same String.</p> * * <p>A {@code null} input String returns {@code null}. * A {@code null} tag returns {@code null}.</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 */ 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>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> * * <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 */ 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>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> * * <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 */ public static String[] substringsBetween(String str, String open, String close) { if (str == null || isEmpty(open) || isEmpty(close)) { return null; } int strLen = str.length(); if (strLen == 0) { return ArrayUtils.EMPTY_STRING_ARRAY; } int closeLen = close.length(); int openLen = open.length(); List<String> list = new ArrayList<String>(); 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 null; } return list.toArray(new String [list.size()]); } // Nested extraction //----------------------------------------------------------------------- // Splitting //----------------------------------------------------------------------- /** * <p>Splits the provided text into an array, using whitespace as the * separator. * Whitespace is defined by {@link Character#isWhitespace(char)}.</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>A {@code null} input String returns {@code null}.</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>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>A {@code null} input String returns {@code null}.</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"] * 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 */ 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>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>A {@code null} input String returns {@code null}. * A {@code null} separatorChars splits on whitespace.</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>The separator is not included in the returned String array. * Adjacent separators are treated as one separator.</p> * * <p>A {@code null} input String returns {@code null}. * A {@code null} separatorChars splits on whitespace.</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> * * <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>The separator(s) will not be included in the returned String array. * Adjacent separators are treated as one separator.</p> * * <p>A {@code null} input String returns {@code null}. * A {@code null} separator splits on whitespace.</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>The separator(s) will not be included in the returned String array. * Adjacent separators are treated as one separator.</p> * * <p>A {@code null} input String returns {@code null}. * A {@code null} separator splits on whitespace.</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>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>A {@code null} input String returns {@code null}. * A {@code null} separator splits on whitespace.</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 */ 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>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>A {@code null} input String returns {@code null}. * A {@code null} separator splits on whitespace.</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 */ 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 */ private static String[] splitByWholeSeparatorWorker( String str, String separator, int max, boolean preserveAllTokens) { if (str == null) { return null; } int len = str.length(); if (len == 0) { return ArrayUtils.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>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>A {@code null} input String returns {@code null}.</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 */ 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>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>A {@code null} input String returns {@code null}.</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 */ 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 null; } int len = str.length(); if (len == 0) { return ArrayUtils.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>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>A {@code null} input String returns {@code null}. * A {@code null} separatorChars splits on whitespace.</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 */ 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>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>A {@code null} input String returns {@code null}. * A {@code null} separatorChars splits on whitespace.</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> * * <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 */ 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 null; } int len = str.length(); if (len == 0) { return ArrayUtils.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. * <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 */ 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. * <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 */ 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 */ private static String[] splitByCharacterType(String str, boolean camelCase) { if (str == null) { return null; } if (str.length() == 0) { return ArrayUtils.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()]); } // Joining //----------------------------------------------------------------------- /** * <p>Joins the elements of the provided array into a single String * containing the provided list of elements.</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> * * <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 */ 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>No delimiter is added before or after the list. * Null objects or empty strings within the array are represented by * empty strings.</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 */ 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 * 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>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> * * <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>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> * * <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 "" * @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 separator, int startIndex, int endIndex) { if (array == null) { return null; } 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 * 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>No delimiter is added before or after the list. Null objects or empty * strings within the iteration are represented by empty strings.</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 */ 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 ObjectUtils.toString(first); } // two or more elements StringBuilder buf = new StringBuilder(64); // Java default is 16, 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>No delimiter is added before or after the list. * A {@code null} separator is the same as an empty String ("").</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 ObjectUtils.toString(first); } // two or more elements StringBuilder buf = new StringBuilder(64); // Java default is 16, 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>No delimiter is added before or after the list. Null objects or empty * strings within the iteration are represented by empty strings.</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 */ 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>No delimiter is added before or after the list. * A {@code null} separator is the same as an empty String ("").</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 */ public static String join(Iterable<?> iterable, String separator) { if (iterable == null) { return null; } return join(iterable.iterator(), separator); } // Delete //----------------------------------------------------------------------- /** * <p>Deletes all whitespaces from a String as defined by * {@link Character#isWhitespace(char)}.</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); } // Remove //----------------------------------------------------------------------- /** * <p>Removes all occurrences of a substring from within the source string.</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> * * <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 */ 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>A {@code null} source string will return {@code null}. * An empty ("") source string will return the empty string.</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 */ 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); } // Replacing //----------------------------------------------------------------------- /** * <p>Replaces a String with another String inside a larger String, once.</p> * * <p>A {@code null} reference passed to this method is a no-op.</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> * * @see #replace(String text, String searchString, String replacement, int max) * @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 */ 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>A {@code null} reference passed to this method is a no-op.</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> * * @see #replace(String text, String searchString, String replacement, int max) * @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 */ 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>A {@code null} reference passed to this method is a no-op.</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 max 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 max) { 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 ? 16 : max > 64 ? 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(); } // Replace, character based //----------------------------------------------------------------------- /** * <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>A {@code null} string input returns {@code null}. * An empty ("") string input returns an empty string.</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 */ 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>For example:<br /> * <code>replaceChars("hello", "ho", "jy") = jelly</code>.</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>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> * * <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 replaceChars a set of characters to replace, may be null * @return modified String, {@code null} if null string input */ public static String replaceChars(String str, String searchChars, String replaceChars) { if (isEmpty(str) || isEmpty(searchChars)) { return str; } 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; } // Chomping //----------------------------------------------------------------------- /** * <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>NOTE: This method changed in 2.0. * It now more closely matches Perl chomp.</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); } // Chopping //----------------------------------------------------------------------- /** * <p>Remove the last character from a String.</p> * * <p>If the String ends in {@code \r\n}, then remove both * of them.</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 < 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; } // Padding //----------------------------------------------------------------------- /** * <p>Repeat a String {@code repeat} times to form a * new String.</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 2 : char ch0 = str.charAt(0); char ch1 = str.charAt(1); char[] output2 = new char[outputLength]; for (int i = repeat * 2 - 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>Returns padding using the specified delimiter repeated * to a given length.</p> * * <pre> * StringUtils.repeat(0, 'e') = "" * StringUtils.repeat(3, 'e') = "eee" * StringUtils.repeat(-2, 'e') = "" * </pre> * * <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>The String is padded to the size of {@code size}.</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>The String is padded to the size of {@code size}.</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 */ 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; // returns original String when possible } 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>The String is padded to the size of {@code size}.</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 padStr 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 padStr) { if (str == null) { return null; } if (isEmpty(padStr)) { padStr = " "; } int padLen = padStr.length(); int strLen = str.length(); int pads = size - strLen; if (pads <= 0) { return str; // returns original String when possible } 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>The String is padded to the size of {@code size}.</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>Pad to a size of {@code size}.</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 */ 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; // returns original String when possible } 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>Pad to a size of {@code size}.</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 padStr 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 padStr) { if (str == null) { return null; } if (isEmpty(padStr)) { padStr = " "; } int padLen = padStr.length(); int strLen = str.length(); int pads = size - strLen; if (pads <= 0) { return str; // returns original String when possible } 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}. */ public static int length(CharSequence cs) { return cs == null ? 0 : cs.length(); } // Case conversion //----------------------------------------------------------------------- /** * <p>Converts a String to upper case as per {@link String#toUpperCase()}.</p> * * <p>A {@code null} input String returns {@code null}.</p> * * <pre> * StringUtils.upperCase(null) = null * StringUtils.upperCase("") = "" * StringUtils.upperCase("aBc") = "ABC" * </pre> * * <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>A {@code null} input String returns {@code null}.</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 */ 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>A {@code null} input String returns {@code null}.</p> * * <pre> * StringUtils.lowerCase(null) = null * StringUtils.lowerCase("") = "" * StringUtils.lowerCase("aBc") = "abc" * </pre> * * <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>A {@code null} input String returns {@code null}.</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 */ 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> * * <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 #uncapitalize(String) */ public static String capitalize(String str) { if (str == null || str.length() == 0) { return str; } if (Character.isLowerCase(str.charAt(0))) { char[] buffer = str.toCharArray(); buffer[0] = Character.toUpperCase(buffer[0]); return new String(buffer); } return str; } /** * <p>Uncapitalizes a String changing the first letter to title case as * per {@link Character#toLowerCase(char)}. No other letters are changed.</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 #capitalize(String) */ public static String uncapitalize(String str) { if (str == null || str.length() == 0) { return str; } if (Character.isUpperCase(str.charAt(0))) { char[] buffer = str.toCharArray(); buffer[0] = Character.toLowerCase(buffer[0]); return new String(buffer); } return str; } /** * <p>Swaps the case of a String changing upper and title case to * lower case, and lower case to upper case.</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> * * * <pre> * StringUtils.swapCase(null) = null * StringUtils.swapCase("") = "" * StringUtils.swapCase("The dog has a BONE") = "tHE DOG HAS A bone" * </pre> * * <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 (isEmpty(str)) { return str; } char[] buffer = str.toCharArray(); for (int i = 0; i < buffer.length; i++) { char ch = buffer[i]; if (Character.isUpperCase(ch) || Character.isTitleCase(ch)) { buffer[i] = Character.toLowerCase(ch); } else if (Character.isLowerCase(ch)) { buffer[i] = Character.toUpperCase(ch); } } return new String(buffer); } // Count matches //----------------------------------------------------------------------- /** * <p>Counts how many times the substring appears in the larger string.</p> * * <p>A {@code null} or empty ("") String input returns {@code 0}.</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} */ 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; } // Character Tests //----------------------------------------------------------------------- /** * <p>Checks if the CharSequence contains only Unicode letters.</p> * * <p>{@code null} will return {@code false}. * An empty CharSequence (length()=0) will return {@code false}.</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 */ 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)) == false) { return false; } } return true; } /** * <p>Checks if the CharSequence contains only Unicode letters and * space (' ').</p> * * <p>{@code null} will return {@code false} * An empty CharSequence (length()=0) will return {@code true}.</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 */ 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)) == false && cs.charAt(i) != ' ') { return false; } } return true; } /** * <p>Checks if the CharSequence contains only Unicode letters or digits.</p> * * <p>{@code null} will return {@code false}. * An empty CharSequence (length()=0) will return {@code false}.</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 */ 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)) == false) { return false; } } return true; } /** * <p>Checks if the CharSequence contains only Unicode letters, digits * or space ({@code ' '}).</p> * * <p>{@code null} will return {@code false}. * An empty CharSequence (length()=0) will return {@code true}.</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 */ 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)) == false && cs.charAt(i) != ' ') { return false; } } return true; } /** * <p>Checks if the CharSequence contains only ASCII printable characters.</p> * * <p>{@code null} will return {@code false}. * An empty CharSequence (length()=0) will return {@code true}.</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 */ 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)) == false) { 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>{@code null} will return {@code false}. * An empty CharSequence (length()=0) will return {@code false}.</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 */ 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)) == false) { 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>{@code null} will return {@code false}. * An empty CharSequence (length()=0) will return {@code true}.</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 */ 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)) == false && cs.charAt(i) != ' ') { return false; } } return true; } /** * <p>Checks if the CharSequence contains only whitespace.</p> * * <p>{@code null} will return {@code false}. * An empty CharSequence (length()=0) will return {@code true}.</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 */ 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)) == false) { return false; } } return true; } /** * <p>Checks if the CharSequence contains only lowercase characters.</p> * * <p>{@code null} will return {@code false}. * An empty CharSequence (length()=0) will return {@code false}.</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 */ 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)) == false) { return false; } } return true; } /** * <p>Checks if the CharSequence contains only uppercase characters.</p> * * <p>{@code null} will return {@code false}. * An empty String (length()=0) will return {@code false}.</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 */ 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)) == false) { return false; } } return true; } // Defaults //----------------------------------------------------------------------- /** * <p>Returns either the passed in String, * or if the String is {@code null}, an empty String ("").</p> * * <pre> * StringUtils.defaultString(null) = "" * StringUtils.defaultString("") = "" * StringUtils.defaultString("bat") = "bat" * </pre> * * @see ObjectUtils#toString(Object) * @see String#valueOf(Object) * @param str the String to check, may be null * @return the passed in String, or the empty String if it * was {@code null} */ 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> * * <pre> * StringUtils.defaultString(null, "NULL") = "NULL" * StringUtils.defaultString("", "NULL") = "" * StringUtils.defaultString("bat", "NULL") = "bat" * </pre> * * @see ObjectUtils#toString(Object,String) * @see String#valueOf(Object) * @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} */ 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 * empty or {@code null}, the value of {@code defaultStr}.</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 */ public static <T extends CharSequence> T defaultIfEmpty(T str, T defaultStr) { return isEmpty(str) ? defaultStr : str; } // Reversing //----------------------------------------------------------------------- /** * <p>Reverses a String as per {@link StringBuilder#reverse()}.</p> * * <p>A {@code null} String returns {@code null}.</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(); } // Abbreviating //----------------------------------------------------------------------- /** * <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>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> * * <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 */ 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>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>In no case will it return a String of length greater than * {@code maxWidth}.</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 offset 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 */ public static String abbreviate(String str, int offset, int maxWidth) { if (str == null) { return null; } if (maxWidth < 4) { throw new IllegalArgumentException("Minimum abbreviation width is 4"); } if (str.length() <= maxWidth) { return str; } if (offset > str.length()) { offset = str.length(); } if (str.length() - offset < maxWidth - 3) { offset = str.length() - (maxWidth - 3); } final String abrevMarker = "..."; if (offset <= 4) { return str.substring(0, maxWidth - 3) + abrevMarker; } if (maxWidth < 7) { throw new IllegalArgumentException("Minimum abbreviation width with offset is 7"); } if (offset + maxWidth - 3 < str.length()) { return abrevMarker + abbreviate(str.substring(offset), maxWidth - 3); } return abrevMarker + str.substring(str.length() - (maxWidth - 3)); } /** * <p>Abbreviates a String to the length passed, replacing the middle characters with the supplied * replacement String.</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> * * <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. */ public static String abbreviateMiddle(String str, String middle, int length) { if (isEmpty(str) || isEmpty(middle)) { return str; } if (length >= str.length() || length < middle.length()+2) { return str; } int targetSting = length-middle.length(); int startOffset = targetSting/2+targetSting%2; int endOffset = str.length()-targetSting/2; StringBuilder builder = new StringBuilder(length); builder.append(str.substring(0,startOffset)); builder.append(middle); builder.append(str.substring(endOffset)); return builder.toString(); } // startsWith //----------------------------------------------------------------------- /** * <p>Check if a CharSequence starts with a specified prefix.</p> * * <p>{@code null}s are handled without exceptions. Two {@code null} * references are considered to be equal. The comparison is case sensitive.</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> * * @see String#startsWith(String) * @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} */ 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>{@code null}s are handled without exceptions. Two {@code null} * references are considered to be equal. The comparison is case insensitive.</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> * * @see String#startsWith(String) * @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} */ 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> * * @see String#startsWith(String) * @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} */ 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> * * <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} */ public static boolean startsWithAny(CharSequence string, CharSequence... searchStrings) { if (isEmpty(string) || ArrayUtils.isEmpty(searchStrings)) { return false; } for (CharSequence searchString : searchStrings) { if (StringUtils.startsWith(string, searchString)) { return true; } } return false; } // endsWith //----------------------------------------------------------------------- /** * <p>Check if a CharSequence ends with a specified suffix.</p> * * <p>{@code null}s are handled without exceptions. Two {@code null} * references are considered to be equal. The comparison is case sensitive.</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> * * @see String#endsWith(String) * @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} */ 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>{@code null}s are handled without exceptions. Two {@code null} * references are considered to be equal. The comparison is case insensitive.</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> * * @see String#endsWith(String) * @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} */ 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> * * @see String#endsWith(String) * @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} */ 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>Check if a CharSequence ends with any of an array of specified strings.</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} */ public static boolean endsWithAny(CharSequence string, CharSequence... searchStrings) { if (isEmpty(string) || ArrayUtils.isEmpty(searchStrings)) { 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 */ public static String toString(byte[] bytes, String charsetName) throws UnsupportedEncodingException { return charsetName == null ? new String(bytes) : new String(bytes, charsetName); } }