All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.apache.commons.lang3.text.WordUtils Maven / Gradle / Ivy

The newest version!
/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 * 
 *      http://www.apache.org/licenses/LICENSE-2.0
 * 
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.commons.lang3.text;

import org.apache.commons.lang3.StringUtils;
import org.apache.commons.lang3.SystemUtils;

/**
 * 

Operations on Strings that contain words.

* *

This class tries to handle null input gracefully. * An exception will not be thrown for a null input. * Each method documents its behaviour in more detail.

* * @since 2.0 * @version $Id: WordUtils.java 1436770 2013-01-22 07:09:45Z ggregory $ */ public class WordUtils { /** *

WordUtils instances should NOT be constructed in * standard programming. Instead, the class should be used as * WordUtils.wrap("foo bar", 20);.

* *

This constructor is public to permit tools that require a JavaBean * instance to operate.

*/ public WordUtils() { super(); } // Wrapping //-------------------------------------------------------------------------- /** *

Wraps a single line of text, identifying words by ' '.

* *

New lines will be separated by the system property line separator. * Very long words, such as URLs will not be wrapped.

* *

Leading spaces on a new line are stripped. * Trailing spaces are not stripped.

* *
     * WordUtils.wrap(null, *) = null
     * WordUtils.wrap("", *) = ""
     * 
* * @param str the String to be word wrapped, may be null * @param wrapLength the column to wrap the words at, less than 1 is treated as 1 * @return a line with newlines inserted, null if null input */ public static String wrap(final String str, final int wrapLength) { return wrap(str, wrapLength, null, false); } /** *

Wraps a single line of text, identifying words by ' '.

* *

Leading spaces on a new line are stripped. * Trailing spaces are not stripped.

* *
     * WordUtils.wrap(null, *, *, *) = null
     * WordUtils.wrap("", *, *, *) = ""
     * 
* * @param str the String to be word wrapped, may be null * @param wrapLength the column to wrap the words at, less than 1 is treated as 1 * @param newLineStr the string to insert for a new line, * null uses the system property line separator * @param wrapLongWords true if long words (such as URLs) should be wrapped * @return a line with newlines inserted, null if null input */ public static String wrap(final String str, int wrapLength, String newLineStr, final boolean wrapLongWords) { if (str == null) { return null; } if (newLineStr == null) { newLineStr = SystemUtils.LINE_SEPARATOR; } if (wrapLength < 1) { wrapLength = 1; } final int inputLineLength = str.length(); int offset = 0; final StringBuilder wrappedLine = new StringBuilder(inputLineLength + 32); while (inputLineLength - offset > wrapLength) { if (str.charAt(offset) == ' ') { offset++; continue; } int spaceToWrapAt = str.lastIndexOf(' ', wrapLength + offset); if (spaceToWrapAt >= offset) { // normal case wrappedLine.append(str.substring(offset, spaceToWrapAt)); wrappedLine.append(newLineStr); offset = spaceToWrapAt + 1; } else { // really long word or URL if (wrapLongWords) { // wrap really long word one line at a time wrappedLine.append(str.substring(offset, wrapLength + offset)); wrappedLine.append(newLineStr); offset += wrapLength; } else { // do not wrap really long word, just extend beyond limit spaceToWrapAt = str.indexOf(' ', wrapLength + offset); if (spaceToWrapAt >= 0) { wrappedLine.append(str.substring(offset, spaceToWrapAt)); wrappedLine.append(newLineStr); offset = spaceToWrapAt + 1; } else { wrappedLine.append(str.substring(offset)); offset = inputLineLength; } } } } // Whatever is left in line is short enough to just pass through wrappedLine.append(str.substring(offset)); return wrappedLine.toString(); } // Capitalizing //----------------------------------------------------------------------- /** *

Capitalizes all the whitespace separated words in a String. * Only the first letter of each word is changed. To convert the * rest of each word to lowercase at the same time, * use {@link #capitalizeFully(String)}.

* *

Whitespace is defined by {@link Character#isWhitespace(char)}. * A null input String returns null. * Capitalization uses the Unicode title case, normally equivalent to * upper case.

* *
     * WordUtils.capitalize(null)        = null
     * WordUtils.capitalize("")          = ""
     * WordUtils.capitalize("i am FINE") = "I Am FINE"
     * 
* * @param str the String to capitalize, may be null * @return capitalized String, null if null String input * @see #uncapitalize(String) * @see #capitalizeFully(String) */ public static String capitalize(final String str) { return capitalize(str, null); } /** *

Capitalizes all the delimiter separated words in a String. * Only the first letter of each word is changed. To convert the * rest of each word to lowercase at the same time, * use {@link #capitalizeFully(String, char[])}.

* *

The delimiters represent a set of characters understood to separate words. * The first string character and the first non-delimiter character after a * delimiter will be capitalized.

* *

A null input String returns null. * Capitalization uses the Unicode title case, normally equivalent to * upper case.

* *
     * WordUtils.capitalize(null, *)            = null
     * WordUtils.capitalize("", *)              = ""
     * WordUtils.capitalize(*, new char[0])     = *
     * WordUtils.capitalize("i am fine", null)  = "I Am Fine"
     * WordUtils.capitalize("i aM.fine", {'.'}) = "I aM.Fine"
     * 
* * @param str the String to capitalize, may be null * @param delimiters set of characters to determine capitalization, null means whitespace * @return capitalized String, null if null String input * @see #uncapitalize(String) * @see #capitalizeFully(String) * @since 2.1 */ public static String capitalize(final String str, final char... delimiters) { final int delimLen = delimiters == null ? -1 : delimiters.length; if (StringUtils.isEmpty(str) || delimLen == 0) { return str; } final char[] buffer = str.toCharArray(); boolean capitalizeNext = true; for (int i = 0; i < buffer.length; i++) { final char ch = buffer[i]; if (isDelimiter(ch, delimiters)) { capitalizeNext = true; } else if (capitalizeNext) { buffer[i] = Character.toTitleCase(ch); capitalizeNext = false; } } return new String(buffer); } //----------------------------------------------------------------------- /** *

Converts all the whitespace separated words in a String into capitalized words, * that is each word is made up of a titlecase character and then a series of * lowercase characters.

* *

Whitespace is defined by {@link Character#isWhitespace(char)}. * A null input String returns null. * Capitalization uses the Unicode title case, normally equivalent to * upper case.

* *
     * WordUtils.capitalizeFully(null)        = null
     * WordUtils.capitalizeFully("")          = ""
     * WordUtils.capitalizeFully("i am FINE") = "I Am Fine"
     * 
* * @param str the String to capitalize, may be null * @return capitalized String, null if null String input */ public static String capitalizeFully(final String str) { return capitalizeFully(str, null); } /** *

Converts all the delimiter separated words in a String into capitalized words, * that is each word is made up of a titlecase character and then a series of * lowercase characters.

* *

The delimiters represent a set of characters understood to separate words. * The first string character and the first non-delimiter character after a * delimiter will be capitalized.

* *

A null input String returns null. * Capitalization uses the Unicode title case, normally equivalent to * upper case.

* *
     * WordUtils.capitalizeFully(null, *)            = null
     * WordUtils.capitalizeFully("", *)              = ""
     * WordUtils.capitalizeFully(*, null)            = *
     * WordUtils.capitalizeFully(*, new char[0])     = *
     * WordUtils.capitalizeFully("i aM.fine", {'.'}) = "I am.Fine"
     * 
* * @param str the String to capitalize, may be null * @param delimiters set of characters to determine capitalization, null means whitespace * @return capitalized String, null if null String input * @since 2.1 */ public static String capitalizeFully(String str, final char... delimiters) { final int delimLen = delimiters == null ? -1 : delimiters.length; if (StringUtils.isEmpty(str) || delimLen == 0) { return str; } str = str.toLowerCase(); return capitalize(str, delimiters); } //----------------------------------------------------------------------- /** *

Uncapitalizes all the whitespace separated words in a String. * Only the first letter of each word is changed.

* *

Whitespace is defined by {@link Character#isWhitespace(char)}. * A null input String returns null.

* *
     * WordUtils.uncapitalize(null)        = null
     * WordUtils.uncapitalize("")          = ""
     * WordUtils.uncapitalize("I Am FINE") = "i am fINE"
     * 
* * @param str the String to uncapitalize, may be null * @return uncapitalized String, null if null String input * @see #capitalize(String) */ public static String uncapitalize(final String str) { return uncapitalize(str, null); } /** *

Uncapitalizes all the whitespace separated words in a String. * Only the first letter of each word is changed.

* *

The delimiters represent a set of characters understood to separate words. * The first string character and the first non-delimiter character after a * delimiter will be uncapitalized.

* *

Whitespace is defined by {@link Character#isWhitespace(char)}. * A null input String returns null.

* *
     * WordUtils.uncapitalize(null, *)            = null
     * WordUtils.uncapitalize("", *)              = ""
     * WordUtils.uncapitalize(*, null)            = *
     * WordUtils.uncapitalize(*, new char[0])     = *
     * WordUtils.uncapitalize("I AM.FINE", {'.'}) = "i AM.fINE"
     * 
* * @param str the String to uncapitalize, may be null * @param delimiters set of characters to determine uncapitalization, null means whitespace * @return uncapitalized String, null if null String input * @see #capitalize(String) * @since 2.1 */ public static String uncapitalize(final String str, final char... delimiters) { final int delimLen = delimiters == null ? -1 : delimiters.length; if (StringUtils.isEmpty(str) || delimLen == 0) { return str; } final char[] buffer = str.toCharArray(); boolean uncapitalizeNext = true; for (int i = 0; i < buffer.length; i++) { final char ch = buffer[i]; if (isDelimiter(ch, delimiters)) { uncapitalizeNext = true; } else if (uncapitalizeNext) { buffer[i] = Character.toLowerCase(ch); uncapitalizeNext = false; } } return new String(buffer); } //----------------------------------------------------------------------- /** *

Swaps the case of a String using a word based algorithm.

* *
    *
  • Upper case character converts to Lower case
  • *
  • Title case character converts to Lower case
  • *
  • Lower case character after Whitespace or at start converts to Title case
  • *
  • Other Lower case character converts to Upper case
  • *
* *

Whitespace is defined by {@link Character#isWhitespace(char)}. * A null input String returns null.

* *
     * StringUtils.swapCase(null)                 = null
     * StringUtils.swapCase("")                   = ""
     * StringUtils.swapCase("The dog has a BONE") = "tHE DOG HAS A bone"
     * 
* * @param str the String to swap case, may be null * @return the changed String, null if null String input */ public static String swapCase(final String str) { if (StringUtils.isEmpty(str)) { return str; } final char[] buffer = str.toCharArray(); boolean whitespace = true; for (int i = 0; i < buffer.length; i++) { final char ch = buffer[i]; if (Character.isUpperCase(ch)) { buffer[i] = Character.toLowerCase(ch); whitespace = false; } else if (Character.isTitleCase(ch)) { buffer[i] = Character.toLowerCase(ch); whitespace = false; } else if (Character.isLowerCase(ch)) { if (whitespace) { buffer[i] = Character.toTitleCase(ch); whitespace = false; } else { buffer[i] = Character.toUpperCase(ch); } } else { whitespace = Character.isWhitespace(ch); } } return new String(buffer); } //----------------------------------------------------------------------- /** *

Extracts the initial letters from each word in the String.

* *

The first letter of the string and all first letters after * whitespace are returned as a new string. * Their case is not changed.

* *

Whitespace is defined by {@link Character#isWhitespace(char)}. * A null input String returns null.

* *
     * WordUtils.initials(null)             = null
     * WordUtils.initials("")               = ""
     * WordUtils.initials("Ben John Lee")   = "BJL"
     * WordUtils.initials("Ben J.Lee")      = "BJ"
     * 
* * @param str the String to get initials from, may be null * @return String of initial letters, null if null String input * @see #initials(String,char[]) * @since 2.2 */ public static String initials(final String str) { return initials(str, null); } /** *

Extracts the initial letters from each word in the String.

* *

The first letter of the string and all first letters after the * defined delimiters are returned as a new string. * Their case is not changed.

* *

If the delimiters array is null, then Whitespace is used. * Whitespace is defined by {@link Character#isWhitespace(char)}. * A null input String returns null. * An empty delimiter array returns an empty String.

* *
     * WordUtils.initials(null, *)                = null
     * WordUtils.initials("", *)                  = ""
     * WordUtils.initials("Ben John Lee", null)   = "BJL"
     * WordUtils.initials("Ben J.Lee", null)      = "BJ"
     * WordUtils.initials("Ben J.Lee", [' ','.']) = "BJL"
     * WordUtils.initials(*, new char[0])         = ""
     * 
* * @param str the String to get initials from, may be null * @param delimiters set of characters to determine words, null means whitespace * @return String of initial letters, null if null String input * @see #initials(String) * @since 2.2 */ public static String initials(final String str, final char... delimiters) { if (StringUtils.isEmpty(str)) { return str; } if (delimiters != null && delimiters.length == 0) { return ""; } final int strLen = str.length(); final char[] buf = new char[strLen / 2 + 1]; int count = 0; boolean lastWasGap = true; for (int i = 0; i < strLen; i++) { final char ch = str.charAt(i); if (isDelimiter(ch, delimiters)) { lastWasGap = true; } else if (lastWasGap) { buf[count++] = ch; lastWasGap = false; } else { continue; // ignore ch } } return new String(buf, 0, count); } //----------------------------------------------------------------------- /** * Is the character a delimiter. * * @param ch the character to check * @param delimiters the delimiters * @return true if it is a delimiter */ private static boolean isDelimiter(final char ch, final char[] delimiters) { if (delimiters == null) { return Character.isWhitespace(ch); } for (final char delimiter : delimiters) { if (ch == delimiter) { return true; } } return false; } }




© 2015 - 2024 Weber Informatics LLC | Privacy Policy